From 6e0110c247c8794a16573d1e238f92489cc27c8a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 29 Apr 2021 13:40:11 -0400 Subject: mm/memcg: Remove 'page' parameter to mem_cgroup_charge_statistics() The last use of 'page' was removed by commit 468c398233da ("mm: memcontrol: switch to native NR_ANON_THPS counter"), so we can now remove the parameter from the function. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Michal Hocko Acked-by: Johannes Weiner Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6da5020a8656..7d560bbcac70 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -799,7 +799,6 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, - struct page *page, int nr_pages) { /* pagein of a big page is an event. So, ignore page size */ @@ -5669,9 +5668,9 @@ static int mem_cgroup_move_account(struct page *page, ret = 0; local_irq_disable(); - mem_cgroup_charge_statistics(to, page, nr_pages); + mem_cgroup_charge_statistics(to, nr_pages); memcg_check_events(to, page); - mem_cgroup_charge_statistics(from, page, -nr_pages); + mem_cgroup_charge_statistics(from, -nr_pages); memcg_check_events(from, page); local_irq_enable(); out_unlock: @@ -6693,7 +6692,7 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) commit_charge(page, memcg); local_irq_disable(); - mem_cgroup_charge_statistics(memcg, page, nr_pages); + mem_cgroup_charge_statistics(memcg, nr_pages); memcg_check_events(memcg, page); local_irq_enable(); out: @@ -6976,7 +6975,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) commit_charge(newpage, memcg); local_irq_save(flags); - mem_cgroup_charge_statistics(memcg, newpage, nr_pages); + mem_cgroup_charge_statistics(memcg, nr_pages); memcg_check_events(memcg, newpage); local_irq_restore(flags); } @@ -7204,7 +7203,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); - mem_cgroup_charge_statistics(memcg, page, -nr_entries); + mem_cgroup_charge_statistics(memcg, -nr_entries); memcg_check_events(memcg, page); css_put(&memcg->css); -- cgit v1.2.3 From 658b69c9d85211e2c56af4f73bbe55a4e0da04b2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 29 Apr 2021 14:51:26 -0400 Subject: mm/memcg: Use the node id in mem_cgroup_update_tree() By using the node id in mem_cgroup_update_tree(), we can delete soft_limit_tree_from_page() and mem_cgroup_page_nodeinfo(). Saves 42 bytes of kernel text on my config. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michal Hocko Acked-by: Johannes Weiner Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 24 ++++-------------------- 1 file changed, 4 insertions(+), 20 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 7d560bbcac70..ac6ed42ca141 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -456,28 +456,12 @@ ino_t page_cgroup_ino(struct page *page) return ino; } -static struct mem_cgroup_per_node * -mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page) -{ - int nid = page_to_nid(page); - - return memcg->nodeinfo[nid]; -} - static struct mem_cgroup_tree_per_node * soft_limit_tree_node(int nid) { return soft_limit_tree.rb_tree_per_node[nid]; } -static struct mem_cgroup_tree_per_node * -soft_limit_tree_from_page(struct page *page) -{ - int nid = page_to_nid(page); - - return soft_limit_tree.rb_tree_per_node[nid]; -} - static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, struct mem_cgroup_tree_per_node *mctz, unsigned long new_usage_in_excess) @@ -548,13 +532,13 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg) return excess; } -static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) +static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid) { unsigned long excess; struct mem_cgroup_per_node *mz; struct mem_cgroup_tree_per_node *mctz; - mctz = soft_limit_tree_from_page(page); + mctz = soft_limit_tree_node(nid); if (!mctz) return; /* @@ -562,7 +546,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) * because their event counter is not touched. */ for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_page_nodeinfo(memcg, page); + mz = memcg->nodeinfo[nid]; excess = soft_limit_excess(memcg); /* * We have to update the tree if mz is on RB-tree or @@ -852,7 +836,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) MEM_CGROUP_TARGET_SOFTLIMIT); mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page); + mem_cgroup_update_tree(memcg, page_to_nid(page)); } } -- cgit v1.2.3 From 2ab082ba76f99ba83a496e7bbe3082d6d5096d1e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 25 Jun 2021 08:57:02 -0400 Subject: mm/memcg: Remove soft_limit_tree_node() Opencode this one-line function in its three callers. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michal Hocko Acked-by: Johannes Weiner Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ac6ed42ca141..316d005566b8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -456,12 +456,6 @@ ino_t page_cgroup_ino(struct page *page) return ino; } -static struct mem_cgroup_tree_per_node * -soft_limit_tree_node(int nid) -{ - return soft_limit_tree.rb_tree_per_node[nid]; -} - static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz, struct mem_cgroup_tree_per_node *mctz, unsigned long new_usage_in_excess) @@ -538,7 +532,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid) struct mem_cgroup_per_node *mz; struct mem_cgroup_tree_per_node *mctz; - mctz = soft_limit_tree_node(nid); + mctz = soft_limit_tree.rb_tree_per_node[nid]; if (!mctz) return; /* @@ -577,7 +571,7 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) for_each_node(nid) { mz = memcg->nodeinfo[nid]; - mctz = soft_limit_tree_node(nid); + mctz = soft_limit_tree.rb_tree_per_node[nid]; if (mctz) mem_cgroup_remove_exceeded(mz, mctz); } @@ -3364,7 +3358,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, if (order > 0) return 0; - mctz = soft_limit_tree_node(pgdat->node_id); + mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id]; /* * Do not even bother to check the largest node if the root -- cgit v1.2.3 From 8e88bd2dfde222285a56a54b0400942b5b33da20 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 25 Jun 2021 09:05:47 -0400 Subject: mm/memcg: Convert memcg_check_events to take a node ID memcg_check_events only uses the page's nid, so call page_to_nid in the callers to make the interface easier to understand. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Michal Hocko Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 316d005566b8..a064a85d51da 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -819,7 +819,7 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg, * Check events in order. * */ -static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) +static void memcg_check_events(struct mem_cgroup *memcg, int nid) { /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, @@ -830,7 +830,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) MEM_CGROUP_TARGET_SOFTLIMIT); mem_cgroup_threshold(memcg); if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page_to_nid(page)); + mem_cgroup_update_tree(memcg, nid); } } @@ -5555,7 +5555,7 @@ static int mem_cgroup_move_account(struct page *page, struct lruvec *from_vec, *to_vec; struct pglist_data *pgdat; unsigned int nr_pages = compound ? thp_nr_pages(page) : 1; - int ret; + int nid, ret; VM_BUG_ON(from == to); VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5644,12 +5644,13 @@ static int mem_cgroup_move_account(struct page *page, __unlock_page_memcg(from); ret = 0; + nid = page_to_nid(page); local_irq_disable(); mem_cgroup_charge_statistics(to, nr_pages); - memcg_check_events(to, page); + memcg_check_events(to, nid); mem_cgroup_charge_statistics(from, -nr_pages); - memcg_check_events(from, page); + memcg_check_events(from, nid); local_irq_enable(); out_unlock: unlock_page(page); @@ -6671,7 +6672,7 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) local_irq_disable(); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, page); + memcg_check_events(memcg, page_to_nid(page)); local_irq_enable(); out: return ret; @@ -6777,7 +6778,7 @@ struct uncharge_gather { unsigned long nr_memory; unsigned long pgpgout; unsigned long nr_kmem; - struct page *dummy_page; + int nid; }; static inline void uncharge_gather_clear(struct uncharge_gather *ug) @@ -6801,7 +6802,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) local_irq_save(flags); __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); __this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory); - memcg_check_events(ug->memcg, ug->dummy_page); + memcg_check_events(ug->memcg, ug->nid); local_irq_restore(flags); /* drop reference from uncharge_page */ @@ -6842,7 +6843,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) uncharge_gather_clear(ug); } ug->memcg = memcg; - ug->dummy_page = page; + ug->nid = page_to_nid(page); /* pairs with css_put in uncharge_batch */ css_get(&memcg->css); @@ -6954,7 +6955,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) local_irq_save(flags); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, newpage); + memcg_check_events(memcg, page_to_nid(newpage)); local_irq_restore(flags); } @@ -7182,7 +7183,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) */ VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, -nr_entries); - memcg_check_events(memcg, page); + memcg_check_events(memcg, page_to_nid(page)); css_put(&memcg->css); } -- cgit v1.2.3 From 1b7e4464d43a488e383843bf96ec62d12393bff1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 14:59:26 -0400 Subject: mm/memcg: Add folio_memcg() and related functions memcg information is only stored in the head page, so the memcg subsystem needs to assure that all accesses are to the head page. The first step is converting page_memcg() to folio_memcg(). The callers of page_memcg() and PageMemcgKmem() are not yet ready to be converted to use folios, so retain them as wrappers around folio_memcg() and folio_memcg_kmem(). They will be converted in a later patch set. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 110 ++++++++++++++++++++++++++------------------- mm/memcontrol.c | 21 +++++---- 2 files changed, 77 insertions(+), 54 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..06659670db32 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -369,7 +369,7 @@ enum page_memcg_data_flags { #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) -static inline bool PageMemcgKmem(struct page *page); +static inline bool folio_memcg_kmem(struct folio *folio); /* * After the initialization objcg->memcg is always pointing at @@ -384,73 +384,77 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) } /* - * __page_memcg - get the memory cgroup associated with a non-kmem page - * @page: a pointer to the page struct + * __folio_memcg - Get the memory cgroup associated with a non-kmem folio + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * kmem pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * kmem folios. */ -static inline struct mem_cgroup *__page_memcg(struct page *page) +static inline struct mem_cgroup *__folio_memcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * __page_objcg - get the object cgroup associated with a kmem page - * @page: a pointer to the page struct + * __folio_objcg - get the object cgroup associated with a kmem folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the object cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the object cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * LRU pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * LRU folios. */ -static inline struct obj_cgroup *__page_objcg(struct page *page) +static inline struct obj_cgroup *__folio_objcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * page_memcg - get the memory cgroup associated with a page - * @page: a pointer to the page struct + * folio_memcg - Get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages. + * against some type of folios, e.g. slab folios or ex-slab folios. * - * For a non-kmem page any of the following ensures page and memcg binding + * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * - * - the page lock + * - the folio lock * - LRU isolation * - lock_page_memcg() * - exclusive reference * - * For a kmem page a caller should hold an rcu read lock to protect memcg - * associated with a kmem page from being released. + * For a kmem folio a caller should hold an rcu read lock to protect memcg + * associated with a kmem folio from being released. */ +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + if (folio_memcg_kmem(folio)) + return obj_cgroup_memcg(__folio_objcg(folio)); + return __folio_memcg(folio); +} + static inline struct mem_cgroup *page_memcg(struct page *page) { - if (PageMemcgKmem(page)) - return obj_cgroup_memcg(__page_objcg(page)); - else - return __page_memcg(page); + return folio_memcg(page_folio(page)); } /* @@ -523,17 +527,18 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) #ifdef CONFIG_MEMCG_KMEM /* - * PageMemcgKmem - check if the page has MemcgKmem flag set - * @page: a pointer to the page struct + * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. + * @folio: Pointer to the folio. * - * Checks if the page has MemcgKmem flag set. The caller must ensure that - * the page has an associated memory cgroup. It's not safe to call this function - * against some types of pages, e.g. slab pages. + * Checks if the folio has MemcgKmem flag set. The caller must ensure + * that the folio has an associated memory cgroup. It's not safe to call + * this function against some types of folios, e.g. slab folios. */ -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { - VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page); - return page->memcg_data & MEMCG_DATA_KMEM; + VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + return folio->memcg_data & MEMCG_DATA_KMEM; } /* @@ -577,7 +582,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #else -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { return false; } @@ -593,6 +598,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #endif +static inline bool PageMemcgKmem(struct page *page) +{ + return folio_memcg_kmem(page_folio(page)); +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -1115,6 +1125,11 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; @@ -1131,6 +1146,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; } +static inline bool folio_memcg_kmem(struct folio *folio) +{ + return false; +} + static inline bool PageMemcgKmem(struct page *page) { return false; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a064a85d51da..1385ac6f688e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2992,15 +2992,16 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) */ void __memcg_kmem_uncharge_page(struct page *page, int order) { + struct folio *folio = page_folio(page); struct obj_cgroup *objcg; unsigned int nr_pages = 1 << order; - if (!PageMemcgKmem(page)) + if (!folio_memcg_kmem(folio)) return; - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); obj_cgroup_uncharge_pages(objcg, nr_pages); - page->memcg_data = 0; + folio->memcg_data = 0; obj_cgroup_put(objcg); } @@ -3234,17 +3235,18 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) */ void split_page_memcg(struct page *head, unsigned int nr) { - struct mem_cgroup *memcg = page_memcg(head); + struct folio *folio = page_folio(head); + struct mem_cgroup *memcg = folio_memcg(folio); int i; if (mem_cgroup_disabled() || !memcg) return; for (i = 1; i < nr; i++) - head[i].memcg_data = head->memcg_data; + folio_page(folio, i)->memcg_data = folio->memcg_data; - if (PageMemcgKmem(head)) - obj_cgroup_get_many(__page_objcg(head), nr - 1); + if (folio_memcg_kmem(folio)) + obj_cgroup_get_many(__folio_objcg(folio), nr - 1); else css_get_many(&memcg->css, nr - 1); } @@ -6811,6 +6813,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { + struct folio *folio = page_folio(page); unsigned long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; @@ -6824,14 +6827,14 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) * exclusive access to the page. */ if (use_objcg) { - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); /* * This get matches the put at the end of the function and * kmem pages do not hold memcg references anymore. */ memcg = get_mem_cgroup_from_objcg(objcg); } else { - memcg = __page_memcg(page); + memcg = __folio_memcg(folio); } if (!memcg) -- cgit v1.2.3 From 118f2875490b027218594db9e2effb52cebc7693 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 29 Apr 2021 14:07:12 -0400 Subject: mm/memcg: Convert commit_charge() to take a folio The memcg_data is only set on the head page, so enforce that by typing it as a folio. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Michal Hocko Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1385ac6f688e..e352225970d2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2711,9 +2711,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) } #endif -static void commit_charge(struct page *page, struct mem_cgroup *memcg) +static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) { - VM_BUG_ON_PAGE(page_memcg(page), page); + VM_BUG_ON_FOLIO(folio_memcg(folio), folio); /* * Any of the following ensures page's memcg stability: * @@ -2722,7 +2722,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg) * - lock_page_memcg() * - exclusive reference */ - page->memcg_data = (unsigned long)memcg; + folio->memcg_data = (unsigned long)memcg; } static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) @@ -6662,7 +6662,8 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) { - unsigned int nr_pages = thp_nr_pages(page); + struct folio *folio = page_folio(page); + long nr_pages = folio_nr_pages(folio); int ret; ret = try_charge(memcg, gfp, nr_pages); @@ -6670,7 +6671,7 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) goto out; css_get(&memcg->css); - commit_charge(page, memcg); + commit_charge(folio, memcg); local_irq_disable(); mem_cgroup_charge_statistics(memcg, nr_pages); @@ -6922,21 +6923,21 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) */ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) { + struct folio *newfolio = page_folio(newpage); struct mem_cgroup *memcg; - unsigned int nr_pages; + long nr_pages = folio_nr_pages(newfolio); unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage); - VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage), - newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); + VM_BUG_ON_FOLIO(PageAnon(oldpage) != folio_test_anon(newfolio), newfolio); + VM_BUG_ON_FOLIO(compound_nr(oldpage) != nr_pages, newfolio); if (mem_cgroup_disabled()) return; /* Page cache replacement: new page already charged? */ - if (page_memcg(newpage)) + if (folio_memcg(newfolio)) return; memcg = page_memcg(oldpage); @@ -6945,8 +6946,6 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) return; /* Force-charge the new page. The old one will be freed soon */ - nr_pages = thp_nr_pages(newpage); - if (!mem_cgroup_is_root(memcg)) { page_counter_charge(&memcg->memory, nr_pages); if (do_memsw_account()) @@ -6954,7 +6953,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) } css_get(&memcg->css); - commit_charge(newpage, memcg); + commit_charge(newfolio, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, nr_pages); -- cgit v1.2.3 From 8f425e4ed0eb3ef0b2d85a9efccf947ca6aa9b1c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 25 Jun 2021 09:27:04 -0400 Subject: mm/memcg: Convert mem_cgroup_charge() to take a folio Convert all callers of mem_cgroup_charge() to call page_folio() on the page they're currently passing in. Many of them will be converted to use folios themselves soon. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 28 +++++++++++++++++++++------- kernel/events/uprobes.c | 3 ++- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 4 ++-- mm/ksm.c | 3 ++- mm/memcontrol.c | 28 +++++++--------------------- mm/memory.c | 9 +++++---- mm/migrate.c | 2 +- mm/shmem.c | 2 +- mm/userfaultfd.c | 2 +- 11 files changed, 44 insertions(+), 41 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 06659670db32..19a51729e00c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -694,14 +694,28 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) page_counter_read(&memcg->memory); } -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); + +/** + * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. + * @folio: Folio to charge. + * @mm: mm context of the allocating task. + * @gfp: Reclaim mode. + * + * Try to charge @folio to the memcg that @mm belongs to, reclaiming + * pages according to @gfp if necessary. If @mm is NULL, try to + * charge to the active memcg. + * + * Do not use this for folios allocated for swapin. + * + * Return: 0 on success. Otherwise, an error code is returned. + */ +static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, + gfp_t gfp) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_charge(page, mm, gfp_mask); + return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, @@ -1199,8 +1213,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) return false; } -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +static inline int mem_cgroup_charge(struct folio *folio, + struct mm_struct *mm, gfp_t gfp) { return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index af24dc3febbe..6357c3580d07 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,7 +167,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); + err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm, + GFP_KERNEL); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index d74be9fb3aa2..816af226f49d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -889,7 +889,7 @@ noinline int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, NULL, gfp); + error = mem_cgroup_charge(page_folio(page), NULL, gfp); if (error) goto error; charged = true; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5e9ef0fc261e..d49986a10d83 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -603,7 +603,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 045cc579f724..8480a3b05bcc 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1087,7 +1087,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1658,7 +1658,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/ksm.c b/mm/ksm.c index a5716fdec1aa..c246a0b0ac75 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2578,7 +2578,8 @@ struct page *ksm_might_need_to_copy(struct page *page, return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) { + if (new_page && + mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { put_page(new_page); new_page = NULL; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e352225970d2..dbca7bf92737 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6660,9 +6660,9 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_low_usage))); } -static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) +static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, + gfp_t gfp) { - struct folio *folio = page_folio(page); long nr_pages = folio_nr_pages(folio); int ret; @@ -6675,34 +6675,19 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) local_irq_disable(); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, page_to_nid(page)); + memcg_check_events(memcg, folio_nid(folio)); local_irq_enable(); out: return ret; } -/** - * __mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. if @mm is NULL, try to - * charge to the active memcg. - * - * Do not use this for pages allocated for swapin. - * - * Returns 0 on success. Otherwise, an error code is returned. - */ -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { struct mem_cgroup *memcg; int ret; memcg = get_mem_cgroup_from_mm(mm); - ret = charge_memcg(page, memcg, gfp_mask); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6723,6 +6708,7 @@ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { + struct folio *folio = page_folio(page); struct mem_cgroup *memcg; unsigned short id; int ret; @@ -6737,7 +6723,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); rcu_read_unlock(); - ret = charge_memcg(page, memcg, gfp); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; diff --git a/mm/memory.c b/mm/memory.c index 269992ba3fa3..b67d80526bee 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -990,7 +990,7 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, if (!new_page) return NULL; - if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } @@ -3019,7 +3019,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3769,7 +3769,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -4193,7 +4193,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm, + GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } diff --git a/mm/migrate.c b/mm/migrate.c index a6a7743ee98f..da55d2a8638d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2846,7 +2846,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/shmem.c b/mm/shmem.c index b5860f4a2738..a2e653aeb536 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -710,7 +710,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp); + error = mem_cgroup_charge(page_folio(page), charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 7a9008415534..36e5f6ab976f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -164,7 +164,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, -- cgit v1.2.3 From c4ed6ebfcb0929d204ab7548496c0d28bd408b36 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 29 Jun 2021 21:47:12 -0400 Subject: mm/memcg: Convert uncharge_page() to uncharge_folio() Use a folio rather than a page to ensure that we're only operating on base or head pages, and not tail pages. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index dbca7bf92737..64eac157db79 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6794,24 +6794,23 @@ static void uncharge_batch(const struct uncharge_gather *ug) memcg_check_events(ug->memcg, ug->nid); local_irq_restore(flags); - /* drop reference from uncharge_page */ + /* drop reference from uncharge_folio */ css_put(&ug->memcg->css); } -static void uncharge_page(struct page *page, struct uncharge_gather *ug) +static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) { - struct folio *folio = page_folio(page); - unsigned long nr_pages; + long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; - bool use_objcg = PageMemcgKmem(page); + bool use_objcg = folio_memcg_kmem(folio); - VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); /* * Nobody should be changing or seriously looking at - * page memcg or objcg at this point, we have fully - * exclusive access to the page. + * folio memcg or objcg at this point, we have fully + * exclusive access to the folio. */ if (use_objcg) { objcg = __folio_objcg(folio); @@ -6833,19 +6832,19 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) uncharge_gather_clear(ug); } ug->memcg = memcg; - ug->nid = page_to_nid(page); + ug->nid = folio_nid(folio); /* pairs with css_put in uncharge_batch */ css_get(&memcg->css); } - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); if (use_objcg) { ug->nr_memory += nr_pages; ug->nr_kmem += nr_pages; - page->memcg_data = 0; + folio->memcg_data = 0; obj_cgroup_put(objcg); } else { /* LRU pages aren't accounted at the root level */ @@ -6853,7 +6852,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) ug->nr_memory += nr_pages; ug->pgpgout++; - page->memcg_data = 0; + folio->memcg_data = 0; } css_put(&memcg->css); @@ -6874,7 +6873,7 @@ void __mem_cgroup_uncharge(struct page *page) return; uncharge_gather_clear(&ug); - uncharge_page(page, &ug); + uncharge_folio(page_folio(page), &ug); uncharge_batch(&ug); } @@ -6888,11 +6887,11 @@ void __mem_cgroup_uncharge(struct page *page) void __mem_cgroup_uncharge_list(struct list_head *page_list) { struct uncharge_gather ug; - struct page *page; + struct folio *folio; uncharge_gather_clear(&ug); - list_for_each_entry(page, page_list, lru) - uncharge_page(page, &ug); + list_for_each_entry(folio, page_list, lru) + uncharge_folio(folio, &ug); if (ug.memcg) uncharge_batch(&ug); } -- cgit v1.2.3 From bbc6b703b21963e909f633cf7718903ed5094319 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 1 May 2021 20:42:23 -0400 Subject: mm/memcg: Convert mem_cgroup_uncharge() to take a folio Convert all the callers to call page_folio(). Most of them were already using a head page, but a few of them I can't prove were, so this may actually fix a bug. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 15 +++++++++++---- mm/filemap.c | 2 +- mm/khugepaged.c | 4 ++-- mm/memcontrol.c | 14 ++++---------- mm/memory-failure.c | 2 +- mm/memremap.c | 2 +- mm/page_alloc.c | 2 +- mm/swap.c | 2 +- 8 files changed, 22 insertions(+), 21 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 19a51729e00c..b4bc052db32b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -722,12 +722,19 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); -void __mem_cgroup_uncharge(struct page *page); -static inline void mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio); + +/** + * mem_cgroup_uncharge - Uncharge a folio. + * @folio: Folio to uncharge. + * + * Uncharge a folio previously charged with mem_cgroup_charge(). + */ +static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; - __mem_cgroup_uncharge(page); + __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_list(struct list_head *page_list); @@ -1229,7 +1236,7 @@ static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) { } -static inline void mem_cgroup_uncharge(struct page *page) +static inline void mem_cgroup_uncharge(struct folio *folio) { } diff --git a/mm/filemap.c b/mm/filemap.c index 816af226f49d..44fcd9d1dd65 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -940,7 +940,7 @@ unlock: if (xas_error(&xas)) { error = xas_error(&xas); if (charged) - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); goto error; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 8480a3b05bcc..6d56e7abd2b8 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1211,7 +1211,7 @@ out_up_write: mmap_write_unlock(mm); out_nolock: if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); trace_mm_collapse_huge_page(mm, isolated, result); return; } @@ -1975,7 +1975,7 @@ xa_unlocked: out: VM_BUG_ON(!list_empty(&pagelist)); if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); /* TODO: tracepoints */ } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 64eac157db79..6321ed6d6e5a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6858,22 +6858,16 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) css_put(&memcg->css); } -/** - * __mem_cgroup_uncharge - uncharge a page - * @page: page to uncharge - * - * Uncharge a page previously charged with __mem_cgroup_charge(). - */ -void __mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio) { struct uncharge_gather ug; - /* Don't touch page->lru of any random page, pre-check: */ - if (!page_memcg(page)) + /* Don't touch folio->lru of any random page, pre-check: */ + if (!folio_memcg(folio)) return; uncharge_gather_clear(&ug); - uncharge_folio(page_folio(page), &ug); + uncharge_folio(folio, &ug); uncharge_batch(&ug); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3e6449f2102a..fffe4afaff43 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -762,7 +762,7 @@ static int delete_from_lru_cache(struct page *p) * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ - mem_cgroup_uncharge(p); + mem_cgroup_uncharge(page_folio(p)); /* * drop the page count elevated by isolate_lru_page() diff --git a/mm/memremap.c b/mm/memremap.c index ed593bf87109..5a66a71ab591 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -505,7 +505,7 @@ void free_devmap_managed_page(struct page *page) __ClearPageWaiters(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); /* * When a device_private page is freed, the page->mapping field diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b37435c274cf..869d0b06e1ef 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -724,7 +724,7 @@ static inline void free_the_page(struct page *page, unsigned int order) void free_compound_page(struct page *page) { - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_the_page(page, compound_order(page)); } diff --git a/mm/swap.c b/mm/swap.c index 0edbcb9c8876..5679ce5bc362 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -94,7 +94,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_unref_page(page, 0); } -- cgit v1.2.3 From d21bba2b7d0ae19dd1279e10aee61c37a17aba74 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 May 2021 18:14:59 -0400 Subject: mm/memcg: Convert mem_cgroup_migrate() to take folios Convert all callers of mem_cgroup_migrate() to call page_folio() first. They all look like they're using head pages already, but this proves it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 4 ++-- mm/filemap.c | 4 +++- mm/memcontrol.c | 35 +++++++++++++++++------------------ mm/migrate.c | 4 +++- mm/shmem.c | 5 ++++- 5 files changed, 29 insertions(+), 23 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b4bc052db32b..07eda24ec581 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -745,7 +745,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) __mem_cgroup_uncharge_list(page_list); } -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); +void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node @@ -1244,7 +1244,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_migrate(struct page *old, struct page *new) +static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } diff --git a/mm/filemap.c b/mm/filemap.c index 44fcd9d1dd65..5368a4dcc35e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -835,6 +835,8 @@ EXPORT_SYMBOL(file_write_and_wait_range); */ void replace_page_cache_page(struct page *old, struct page *new) { + struct folio *fold = page_folio(old); + struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; @@ -848,7 +850,7 @@ void replace_page_cache_page(struct page *old, struct page *new) new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(old, new); + mem_cgroup_migrate(fold, fnew); xas_lock_irq(&xas); xas_store(&xas, new); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6321ed6d6e5a..c83d2f862f8a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6891,36 +6891,35 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) } /** - * mem_cgroup_migrate - charge a page's replacement - * @oldpage: currently circulating page - * @newpage: replacement page + * mem_cgroup_migrate - Charge a folio's replacement. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Charge @newpage as a replacement page for @oldpage. @oldpage will + * Charge @new as a replacement folio for @old. @old will * be uncharged upon free. * - * Both pages must be locked, @newpage->mapping must be set up. + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +void mem_cgroup_migrate(struct folio *old, struct folio *new) { - struct folio *newfolio = page_folio(newpage); struct mem_cgroup *memcg; - long nr_pages = folio_nr_pages(newfolio); + long nr_pages = folio_nr_pages(new); unsigned long flags; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); - VM_BUG_ON_FOLIO(PageAnon(oldpage) != folio_test_anon(newfolio), newfolio); - VM_BUG_ON_FOLIO(compound_nr(oldpage) != nr_pages, newfolio); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new); if (mem_cgroup_disabled()) return; - /* Page cache replacement: new page already charged? */ - if (folio_memcg(newfolio)) + /* Page cache replacement: new folio already charged? */ + if (folio_memcg(new)) return; - memcg = page_memcg(oldpage); - VM_WARN_ON_ONCE_PAGE(!memcg, oldpage); + memcg = folio_memcg(old); + VM_WARN_ON_ONCE_FOLIO(!memcg, old); if (!memcg) return; @@ -6932,11 +6931,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) } css_get(&memcg->css); - commit_charge(newfolio, memcg); + commit_charge(new, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, page_to_nid(newpage)); + memcg_check_events(memcg, folio_nid(new)); local_irq_restore(flags); } diff --git a/mm/migrate.c b/mm/migrate.c index da55d2a8638d..bfb8ba490479 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -542,6 +542,8 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, */ void migrate_page_states(struct page *newpage, struct page *page) { + struct folio *folio = page_folio(page); + struct folio *newfolio = page_folio(newpage); int cpupid; if (PageError(page)) @@ -609,7 +611,7 @@ void migrate_page_states(struct page *newpage, struct page *page) copy_page_owner(page, newpage); if (!PageHuge(page)) - mem_cgroup_migrate(page, newpage); + mem_cgroup_migrate(folio, newfolio); } EXPORT_SYMBOL(migrate_page_states); diff --git a/mm/shmem.c b/mm/shmem.c index a2e653aeb536..1588f33d009a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1637,6 +1637,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; + struct folio *old, *new; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; @@ -1673,7 +1674,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { - mem_cgroup_migrate(oldpage, newpage); + old = page_folio(oldpage); + new = page_folio(newpage); + mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } -- cgit v1.2.3 From 9d8053fc7a21ee2b3a540165d09418955258d9e8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 4 May 2021 11:43:01 -0400 Subject: mm/memcg: Convert mem_cgroup_track_foreign_dirty_slowpath() to folio The page was only being used for the memcg and to gather trace information, so this is a simple conversion. The only caller of mem_cgroup_track_foreign_dirty() will be converted to folios in a later patch, so doing this now makes that patch simpler. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 7 ++++--- include/trace/events/writeback.h | 8 ++++---- mm/memcontrol.c | 6 +++--- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 07eda24ec581..1c2776c3a223 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1599,17 +1599,18 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { + struct folio *folio = page_folio(page); if (mem_cgroup_disabled()) return; - if (unlikely(&page_memcg(page)->css != wb->memcg_css)) - mem_cgroup_track_foreign_dirty_slowpath(page, wb); + if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5..297871ca0004 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -236,9 +236,9 @@ TRACE_EVENT(inode_switch_wbs, TRACE_EVENT(track_foreign_dirty, - TP_PROTO(struct page *page, struct bdi_writeback *wb), + TP_PROTO(struct folio *folio, struct bdi_writeback *wb), - TP_ARGS(page, wb), + TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) @@ -250,7 +250,7 @@ TRACE_EVENT(track_foreign_dirty, ), TP_fast_assign( - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); @@ -258,7 +258,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup); + __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c83d2f862f8a..4a04bddefdbc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4516,17 +4516,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, * As being wrong occasionally doesn't matter, updates and accesses to the * records are lockless and racy. */ -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb) { - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); struct memcg_cgwb_frn *frn; u64 now = get_jiffies_64(); u64 oldest_at = now; int oldest = -1; int i; - trace_track_foreign_dirty(page, wb); + trace_track_foreign_dirty(folio, wb); /* * Pick the slot to use. If there is already a slot for @wb, keep -- cgit v1.2.3 From f70ad448741580bf61cdfbeb02229c581409760a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 17:26:00 -0400 Subject: mm/memcg: Add folio_memcg_lock() and folio_memcg_unlock() These are the folio equivalents of lock_page_memcg() and unlock_page_memcg(). lock_page_memcg() and unlock_page_memcg() have too many callers to be easily replaced in a single patch, so reimplement them as wrappers for now to be cleaned up later when enough callers have been converted to use folios. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 10 ++++++++++ mm/memcontrol.c | 45 +++++++++++++++++++++++++++++---------------- 2 files changed, 39 insertions(+), 16 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1c2776c3a223..be85450f066f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -978,6 +978,8 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); extern bool cgroup_memory_noswap; #endif +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); @@ -1397,6 +1399,14 @@ static inline void unlock_page_memcg(struct page *page) { } +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + static inline void mem_cgroup_handle_over_high(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4a04bddefdbc..23fe124fe78d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1933,18 +1933,17 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } /** - * lock_page_memcg - lock a page and memcg binding - * @page: the page + * folio_memcg_lock - Bind a folio to its memcg. + * @folio: The folio. * - * This function protects unlocked LRU pages from being moved to + * This function prevents unlocked LRU folios from being moved to * another cgroup. * - * It ensures lifetime of the locked memcg. Caller is responsible - * for the lifetime of the page. + * It ensures lifetime of the bound memcg. The caller is responsible + * for the lifetime of the folio. */ -void lock_page_memcg(struct page *page) +void folio_memcg_lock(struct folio *folio) { - struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; unsigned long flags; @@ -1958,7 +1957,7 @@ void lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return; again: - memcg = page_memcg(head); + memcg = folio_memcg(folio); if (unlikely(!memcg)) return; @@ -1972,7 +1971,7 @@ again: return; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page_memcg(head)) { + if (memcg != folio_memcg(folio)) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -1986,9 +1985,15 @@ again: memcg->move_lock_task = current; memcg->move_lock_flags = flags; } +EXPORT_SYMBOL(folio_memcg_lock); + +void lock_page_memcg(struct page *page) +{ + folio_memcg_lock(page_folio(page)); +} EXPORT_SYMBOL(lock_page_memcg); -static void __unlock_page_memcg(struct mem_cgroup *memcg) +static void __folio_memcg_unlock(struct mem_cgroup *memcg) { if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; @@ -2003,14 +2008,22 @@ static void __unlock_page_memcg(struct mem_cgroup *memcg) } /** - * unlock_page_memcg - unlock a page and memcg binding - * @page: the page + * folio_memcg_unlock - Release the binding between a folio and its memcg. + * @folio: The folio. + * + * This releases the binding created by folio_memcg_lock(). This does + * not change the accounting of this folio to its memcg, but it does + * permit others to change it. */ -void unlock_page_memcg(struct page *page) +void folio_memcg_unlock(struct folio *folio) { - struct page *head = compound_head(page); + __folio_memcg_unlock(folio_memcg(folio)); +} +EXPORT_SYMBOL(folio_memcg_unlock); - __unlock_page_memcg(page_memcg(head)); +void unlock_page_memcg(struct page *page) +{ + folio_memcg_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page_memcg); @@ -5643,7 +5656,7 @@ static int mem_cgroup_move_account(struct page *page, page->memcg_data = (unsigned long)to; - __unlock_page_memcg(from); + __folio_memcg_unlock(from); ret = 0; nid = page_to_nid(page); -- cgit v1.2.3 From fcce4672c06ad5f6eb9497607ac942490b25d3af Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Mar 2021 16:34:06 -0500 Subject: mm/memcg: Convert mem_cgroup_move_account() to use a folio This saves dozens of bytes of text by eliminating a lot of calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- mm/memcontrol.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 23fe124fe78d..c17681defeec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5567,38 +5567,39 @@ static int mem_cgroup_move_account(struct page *page, struct mem_cgroup *from, struct mem_cgroup *to) { + struct folio *folio = page_folio(page); struct lruvec *from_vec, *to_vec; struct pglist_data *pgdat; - unsigned int nr_pages = compound ? thp_nr_pages(page) : 1; + unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1; int nid, ret; VM_BUG_ON(from == to); - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON(compound && !PageTransHuge(page)); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + VM_BUG_ON(compound && !folio_test_multi(folio)); /* * Prevent mem_cgroup_migrate() from looking at * page's memory cgroup of its source page while we change it. */ ret = -EBUSY; - if (!trylock_page(page)) + if (!folio_trylock(folio)) goto out; ret = -EINVAL; - if (page_memcg(page) != from) + if (folio_memcg(folio) != from) goto out_unlock; - pgdat = page_pgdat(page); + pgdat = folio_pgdat(folio); from_vec = mem_cgroup_lruvec(from, pgdat); to_vec = mem_cgroup_lruvec(to, pgdat); - lock_page_memcg(page); + folio_memcg_lock(folio); - if (PageAnon(page)) { - if (page_mapped(page)) { + if (folio_test_anon(folio)) { + if (folio_mapped(folio)) { __mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages); - if (PageTransHuge(page)) { + if (folio_test_transhuge(folio)) { __mod_lruvec_state(from_vec, NR_ANON_THPS, -nr_pages); __mod_lruvec_state(to_vec, NR_ANON_THPS, @@ -5609,18 +5610,18 @@ static int mem_cgroup_move_account(struct page *page, __mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages); - if (PageSwapBacked(page)) { + if (folio_test_swapbacked(folio)) { __mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages); __mod_lruvec_state(to_vec, NR_SHMEM, nr_pages); } - if (page_mapped(page)) { + if (folio_mapped(folio)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } - if (PageDirty(page)) { - struct address_space *mapping = page_mapping(page); + if (folio_test_dirty(folio)) { + struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { __mod_lruvec_state(from_vec, NR_FILE_DIRTY, @@ -5631,7 +5632,7 @@ static int mem_cgroup_move_account(struct page *page, } } - if (PageWriteback(page)) { + if (folio_test_writeback(folio)) { __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); } @@ -5654,12 +5655,12 @@ static int mem_cgroup_move_account(struct page *page, css_get(&to->css); css_put(&from->css); - page->memcg_data = (unsigned long)to; + folio->memcg_data = (unsigned long)to; __folio_memcg_unlock(from); ret = 0; - nid = page_to_nid(page); + nid = folio_nid(folio); local_irq_disable(); mem_cgroup_charge_statistics(to, nr_pages); @@ -5668,7 +5669,7 @@ static int mem_cgroup_move_account(struct page *page, memcg_check_events(from, nid); local_irq_enable(); out_unlock: - unlock_page(page); + folio_unlock(folio); out: return ret; } -- cgit v1.2.3 From b1baabd995ab8e830dbf647fe731b51e12b8cedd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 20:00:28 -0400 Subject: mm/memcg: Add folio_lruvec() This replaces mem_cgroup_page_lruvec(). All callers converted. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 20 +++++++++----------- mm/compaction.c | 2 +- mm/memcontrol.c | 9 ++++++--- mm/swap.c | 3 ++- mm/workingset.c | 3 ++- 5 files changed, 20 insertions(+), 17 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index be85450f066f..35577caf27d9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -784,18 +784,17 @@ out: } /** - * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page - * @page: the page + * folio_lruvec - return lruvec for isolating/putting an LRU folio + * @folio: Pointer to the folio. * - * This function relies on page->mem_cgroup being stable. + * This function relies on folio->mem_cgroup being stable. */ -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); - VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); - return mem_cgroup_lruvec(memcg, pgdat); + VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); + return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); @@ -1256,10 +1255,9 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - + struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } diff --git a/mm/compaction.c b/mm/compaction.c index bfc93da1c2c7..37dfdf2b2287 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1022,7 +1022,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!TestClearPageLRU(page)) goto isolate_fail_put; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(page_folio(page)); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c17681defeec..ea4f879d2771 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1154,9 +1154,10 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) */ struct lruvec *lock_page_lruvec(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1166,9 +1167,10 @@ struct lruvec *lock_page_lruvec(struct page *page) struct lruvec *lock_page_lruvec_irq(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock_irq(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1178,9 +1180,10 @@ struct lruvec *lock_page_lruvec_irq(struct page *page) struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock_irqsave(&lruvec->lru_lock, *flags); lruvec_memcg_debug(lruvec, page); diff --git a/mm/swap.c b/mm/swap.c index 5679ce5bc362..65a74c89e7cf 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -293,7 +293,8 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) void lru_note_cost_page(struct page *page) { - lru_note_cost(mem_cgroup_page_lruvec(page), + struct folio *folio = page_folio(page); + lru_note_cost(folio_lruvec(folio), page_is_file_lru(page), thp_nr_pages(page)); } diff --git a/mm/workingset.c b/mm/workingset.c index d5b81e4f4cbe..3deb408a240d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -397,6 +397,7 @@ out: */ void workingset_activation(struct page *page) { + struct folio *folio = page_folio(page); struct mem_cgroup *memcg; struct lruvec *lruvec; @@ -411,7 +412,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); -- cgit v1.2.3 From e809c3fedeeb806993349e7bf797b4c2b728be7d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 21:59:47 -0400 Subject: mm/memcg: Add folio_lruvec_lock() and similar functions These are the folio equivalents of lock_page_lruvec() and similar functions. Also convert lruvec_memcg_debug() to take a folio. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 32 ++++++++++--------- mm/compaction.c | 2 +- mm/huge_memory.c | 5 +-- mm/memcontrol.c | 77 +++++++++++++++++++++++++++++----------------- mm/rmap.c | 2 +- mm/swap.c | 8 +++-- mm/vmscan.c | 3 +- 7 files changed, 79 insertions(+), 50 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 35577caf27d9..30d2cd7b5c9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -801,15 +801,16 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct lruvec *lock_page_lruvec(struct page *page); -struct lruvec *lock_page_lruvec_irq(struct page *page); -struct lruvec *lock_page_lruvec_irqsave(struct page *page, +struct lruvec *folio_lruvec_lock(struct folio *folio); +struct lruvec *folio_lruvec_lock_irq(struct folio *folio); +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page); +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); #else -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } #endif @@ -1261,7 +1262,8 @@ static inline struct lruvec *folio_lruvec(struct folio *folio) return &pgdat->__lruvec; } -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } @@ -1291,26 +1293,26 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -static inline struct lruvec *lock_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irq(struct page *page) +static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page, +static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; @@ -1576,6 +1578,7 @@ static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) static inline struct lruvec *relock_page_lruvec_irq(struct page *page, struct lruvec *locked_lruvec) { + struct folio *folio = page_folio(page); if (locked_lruvec) { if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; @@ -1583,13 +1586,14 @@ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, unlock_page_lruvec_irq(locked_lruvec); } - return lock_page_lruvec_irq(page); + return folio_lruvec_lock_irq(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, struct lruvec *locked_lruvec, unsigned long *flags) { + struct folio *folio = page_folio(page); if (locked_lruvec) { if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; @@ -1597,7 +1601,7 @@ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, unlock_page_lruvec_irqrestore(locked_lruvec, *flags); } - return lock_page_lruvec_irqsave(page, flags); + return folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/mm/compaction.c b/mm/compaction.c index 37dfdf2b2287..fbc60f964c38 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1032,7 +1032,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); locked = lruvec; - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, page_folio(page)); /* Try get exclusive access under lock */ if (!skip_updated) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d49986a10d83..e5ea5f775d5c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2405,7 +2405,8 @@ static void __split_huge_page_tail(struct page *head, int tail, static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end) { - struct page *head = compound_head(page); + struct folio *folio = page_folio(page); + struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; unsigned long offset = 0; @@ -2424,7 +2425,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ - lruvec = lock_page_lruvec(head); + lruvec = folio_lruvec_lock(folio); for (i = nr - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ea4f879d2771..8dab23a71fc4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1126,67 +1126,88 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, } #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; - memcg = page_memcg(page); + memcg = folio_memcg(folio); if (!memcg) - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio); else - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio); } #endif /** - * lock_page_lruvec - lock and return lruvec for a given page. - * @page: the page + * folio_lruvec_lock - Lock the lruvec for a folio. + * @folio: Pointer to the folio. * * These functions are safe to use under any of the following conditions: - * - page locked - * - PageLRU cleared - * - lock_page_memcg() - * - page->_refcount is zero + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held. */ -struct lruvec *lock_page_lruvec(struct page *page) +struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irq(struct page *page) +/** + * folio_lruvec_lock_irq - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock_irq(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) +/** + * folio_lruvec_lock_irqsave - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * @flags: Pointer to irqsave flags. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, + unsigned long *flags) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock_irqsave(&lruvec->lru_lock, *flags); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } diff --git a/mm/rmap.c b/mm/rmap.c index 6aebd1747251..059556dbefec 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -34,7 +34,7 @@ * mapping->private_lock (in __set_page_dirty_buffers) * lock_page_memcg move_lock (in __set_page_dirty_buffers) * i_pages lock (widely used) - * lruvec->lru_lock (in lock_page_lruvec_irq) + * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) diff --git a/mm/swap.c b/mm/swap.c index 65a74c89e7cf..d1fc964def12 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -80,10 +80,11 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { static void __page_cache_release(struct page *page) { if (PageLRU(page)) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; unsigned long flags; - lruvec = lock_page_lruvec_irqsave(page, &flags); + lruvec = folio_lruvec_lock_irqsave(folio, &flags); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); @@ -350,11 +351,12 @@ static inline void activate_page_drain(int cpu) static void activate_page(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - page = compound_head(page); + page = &folio->page; if (TestClearPageLRU(page)) { - lruvec = lock_page_lruvec_irq(page); + lruvec = folio_lruvec_lock_irq(folio); __activate_page(page, lruvec); unlock_page_lruvec_irq(lruvec); SetPageLRU(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 74296c2d1fed..8694e1549bcd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2090,6 +2090,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, */ int isolate_lru_page(struct page *page) { + struct folio *folio = page_folio(page); int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); @@ -2099,7 +2100,7 @@ int isolate_lru_page(struct page *page) struct lruvec *lruvec; get_page(page); - lruvec = lock_page_lruvec_irq(page); + lruvec = folio_lruvec_lock_irq(folio); del_page_from_lru_list(page, lruvec); unlock_page_lruvec_irq(lruvec); ret = 0; -- cgit v1.2.3