From e4b294c2d8f73af4cd41ff30638ad0e4769dc56a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:24:46 -0800 Subject: mm: add fields for compound destructor and order into struct page Currently, we use lru.next/lru.prev plus cast to access or set destructor and order of compound page. Let's replace it with explicit fields in struct page. Signed-off-by: Kirill A. Shutemov Acked-by: Jerome Marchand Acked-by: Christoph Lameter Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 ++++----- include/linux/mm_types.h | 8 ++++++++ 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 65db4aee738a..8dd4fde9d2e5 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -627,29 +627,28 @@ int split_free_page(struct page *page); * prototype for that function and accessor functions. * These are _only_ valid on the head of a PG_compound page. */ -typedef void compound_page_dtor(struct page *); static inline void set_compound_page_dtor(struct page *page, compound_page_dtor *dtor) { - page[1].lru.next = (void *)dtor; + page[1].compound_dtor = dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { - return (compound_page_dtor *)page[1].lru.next; + return page[1].compound_dtor; } static inline int compound_order(struct page *page) { if (!PageHead(page)) return 0; - return (unsigned long)page[1].lru.prev; + return page[1].compound_order; } static inline void set_compound_order(struct page *page, unsigned long order) { - page[1].lru.prev = (void *)order; + page[1].compound_order = order; } #ifdef CONFIG_MMU diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 07c8bd3f7b48..20ff2105b564 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -28,6 +28,8 @@ struct mem_cgroup; IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) #define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) +typedef void compound_page_dtor(struct page *); + /* * Each physical page in the system has a struct page associated with * it to keep track of whatever it is we are using the page for at the @@ -142,6 +144,12 @@ struct page { struct rcu_head rcu_head; /* Used by SLAB * when destroying via RCU */ + /* First tail page of compound page */ + struct { + compound_page_dtor *compound_dtor; + unsigned long compound_order; + }; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS pgtable_t pmd_huge_pte; /* protected by page->ptl */ #endif -- cgit v1.2.3 From 1d148e218a0d0566b1c06f2f45f1436d53b049b2 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:48 -0800 Subject: mm: add VM_BUG_ON_PAGE() to page_mapcount() Add VM_BUG_ON_PAGE() for slab pages. _mapcount is an union with slab struct in struct page, so we must avoid accessing _mapcount if this page is a slab page. Also remove the unneeded bracket. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 8dd4fde9d2e5..c6bf813a6b3d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -484,7 +484,8 @@ static inline void page_mapcount_reset(struct page *page) static inline int page_mapcount(struct page *page) { - return atomic_read(&(page)->_mapcount) + 1; + VM_BUG_ON_PAGE(PageSlab(page), page); + return atomic_read(&page->_mapcount) + 1; } static inline int page_count(struct page *page) -- cgit v1.2.3 From 56873f43abdcd574b25105867a990f067747b2f4 Mon Sep 17 00:00:00 2001 From: "Wang, Yalin" Date: Wed, 11 Feb 2015 15:24:51 -0800 Subject: mm:add KPF_ZERO_PAGE flag for /proc/kpageflags Add KPF_ZERO_PAGE flag for zero_page, so that userspace processes can detect zero_page in /proc/kpageflags, and then do memory analysis more accurately. Signed-off-by: Yalin Wang Acked-by: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/pagemap.txt | 8 ++++++++ fs/proc/page.c | 16 +++++++++++++--- include/linux/huge_mm.h | 12 ++++++++++++ include/uapi/linux/kernel-page-flags.h | 1 + mm/huge_memory.c | 7 +------ tools/vm/page-types.c | 1 + 6 files changed, 36 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt index 5948e455c4d2..6fbd55ef6b45 100644 --- a/Documentation/vm/pagemap.txt +++ b/Documentation/vm/pagemap.txt @@ -62,6 +62,8 @@ There are three components to pagemap: 20. NOPAGE 21. KSM 22. THP + 23. BALLOON + 24. ZERO_PAGE Short descriptions to the page flags: @@ -102,6 +104,12 @@ Short descriptions to the page flags: 22. THP contiguous pages which construct transparent hugepages +23. BALLOON + balloon compaction page + +24. ZERO_PAGE + zero page for pfn_zero or huge_zero page + [IO related page flags] 1. ERROR IO error occurred 3. UPTODATE page has up-to-date data diff --git a/fs/proc/page.c b/fs/proc/page.c index 1e3187da1fed..7eee2d8b97d9 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -121,9 +122,18 @@ u64 stable_page_flags(struct page *page) * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon * to make sure a given page is a thp, not a non-huge compound page. */ - else if (PageTransCompound(page) && (PageLRU(compound_head(page)) || - PageAnon(compound_head(page)))) - u |= 1 << KPF_THP; + else if (PageTransCompound(page)) { + struct page *head = compound_head(page); + + if (PageLRU(head) || PageAnon(head)) + u |= 1 << KPF_THP; + else if (is_huge_zero_page(head)) { + u |= 1 << KPF_ZERO_PAGE; + u |= 1 << KPF_THP; + } + } else if (is_zero_pfn(page_to_pfn(page))) + u |= 1 << KPF_ZERO_PAGE; + /* * Caveats on high order pages: page->_count will only be set diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ad9051bab267..f10b20f05159 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -157,6 +157,13 @@ static inline int hpage_nr_pages(struct page *page) extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pmd_t pmd, pmd_t *pmdp); +extern struct page *huge_zero_page; + +static inline bool is_huge_zero_page(struct page *page) +{ + return ACCESS_ONCE(huge_zero_page) == page; +} + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) @@ -206,6 +213,11 @@ static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_str return 0; } +static inline bool is_huge_zero_page(struct page *page) +{ + return false; +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/uapi/linux/kernel-page-flags.h b/include/uapi/linux/kernel-page-flags.h index 2f96d233c980..a6c4962e5d46 100644 --- a/include/uapi/linux/kernel-page-flags.h +++ b/include/uapi/linux/kernel-page-flags.h @@ -32,6 +32,7 @@ #define KPF_KSM 21 #define KPF_THP 22 #define KPF_BALLOON 23 +#define KPF_ZERO_PAGE 24 #endif /* _UAPILINUX_KERNEL_PAGE_FLAGS_H */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 817a875f2b8c..889713180980 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -171,12 +171,7 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static struct page *huge_zero_page __read_mostly; - -static inline bool is_huge_zero_page(struct page *page) -{ - return ACCESS_ONCE(huge_zero_page) == page; -} +struct page *huge_zero_page __read_mostly; static inline bool is_huge_zero_pmd(pmd_t pmd) { diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 264fbc297e0b..8bdf16b8ba60 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -133,6 +133,7 @@ static const char * const page_flag_names[] = { [KPF_KSM] = "x:ksm", [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", + [KPF_ZERO_PAGE] = "z:zero_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", -- cgit v1.2.3 From 93aa7d95248d04b934eb8e89717c7b8d6400bf2b Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:24:59 -0800 Subject: swap: remove unused mem_cgroup_uncharge_swapcache declaration The body of this function was removed by commit 0a31bc97c80c ("mm: memcontrol: rewrite uncharge API"). Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 15 --------------- mm/shmem.c | 2 +- 2 files changed, 1 insertion(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/swap.h b/include/linux/swap.h index 34e8b60ab973..7067eca501e2 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -437,16 +437,6 @@ extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; -#ifdef CONFIG_MEMCG -extern void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout); -#else -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout) -{ -} -#endif - #else /* CONFIG_SWAP */ #define swap_address_space(entry) (NULL) @@ -547,11 +537,6 @@ static inline swp_entry_t get_swap_page(void) return entry; } -static inline void -mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) -{ -} - #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ diff --git a/mm/shmem.c b/mm/shmem.c index b3e403181981..864c878401e6 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1131,7 +1131,7 @@ repeat: * truncated or holepunched since swap was confirmed. * shmem_undo_range() will have done some of the * unaccounting, now delete_from_swap_cache() will do - * the rest (including mem_cgroup_uncharge_swapcache). + * the rest. * Reset swap.val? No, leave it so "failed" goes back to * "repeat": reading a hole and writing should succeed. */ -- cgit v1.2.3 From 6de226191d12fce30331ebf024ca3ed24834f0ee Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:25:01 -0800 Subject: mm: memcontrol: track move_lock state internally The complexity of memcg page stat synchronization is currently leaking into the callsites, forcing them to keep track of the move_lock state and the IRQ flags. Simplify the API by tracking it in the memcg. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Reviewed-by: Vladimir Davydov Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 12 +++----- mm/memcontrol.c | 68 ++++++++++++++++++++++++++-------------------- mm/page-writeback.c | 12 +++----- mm/rmap.c | 12 +++----- 4 files changed, 51 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fb212e1d700d..76b4084b8d08 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -138,12 +138,10 @@ static inline bool mem_cgroup_disabled(void) return false; } -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked, - unsigned long *flags); -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags); +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx, int val); +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) @@ -285,14 +283,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, unsigned long *flags) +static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { return NULL; } -static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, - bool *locked, unsigned long *flags) +static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f3f8a4f52a0c..028d07c79104 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -325,9 +325,11 @@ struct mem_cgroup { /* * set > 0 if pages under this cgroup are moving to other cgroup. */ - atomic_t moving_account; + atomic_t moving_account; /* taken only while moving_account > 0 */ - spinlock_t move_lock; + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; /* * percpu counter. */ @@ -1977,34 +1979,33 @@ cleanup: /** * mem_cgroup_begin_page_stat - begin a page state statistics transaction * @page: page that is going to change accounted state - * @locked: &memcg->move_lock slowpath was taken - * @flags: IRQ-state flags for &memcg->move_lock * * This function must mark the beginning of an accounted page state * change to prevent double accounting when the page is concurrently * being moved to another memcg: * - * memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + * memcg = mem_cgroup_begin_page_stat(page); * if (TestClearPageState(page)) * mem_cgroup_update_page_stat(memcg, state, -1); - * mem_cgroup_end_page_stat(memcg, locked, flags); - * - * The RCU lock is held throughout the transaction. The fast path can - * get away without acquiring the memcg->move_lock (@locked is false) - * because page moving starts with an RCU grace period. - * - * The RCU lock also protects the memcg from being freed when the page - * state that is going to change is the only thing preventing the page - * from being uncharged. E.g. end-writeback clearing PageWriteback(), - * which allows migration to go ahead and uncharge the page before the - * account transaction might be complete. + * mem_cgroup_end_page_stat(memcg); */ -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, - unsigned long *flags) +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { struct mem_cgroup *memcg; + unsigned long flags; + /* + * The RCU lock is held throughout the transaction. The fast + * path can get away without acquiring the memcg->move_lock + * because page moving starts with an RCU grace period. + * + * The RCU lock also protects the memcg from being freed when + * the page state that is going to change is the only thing + * preventing the page from being uncharged. + * E.g. end-writeback clearing PageWriteback(), which allows + * migration to go ahead and uncharge the page before the + * account transaction might be complete. + */ rcu_read_lock(); if (mem_cgroup_disabled()) @@ -2014,16 +2015,22 @@ again: if (unlikely(!memcg)) return NULL; - *locked = false; if (atomic_read(&memcg->moving_account) <= 0) return memcg; - spin_lock_irqsave(&memcg->move_lock, *flags); + spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page->mem_cgroup) { - spin_unlock_irqrestore(&memcg->move_lock, *flags); + spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } - *locked = true; + + /* + * When charge migration first begins, we can have locked and + * unlocked page stat updates happening concurrently. Track + * the task who has the lock for mem_cgroup_end_page_stat(). + */ + memcg->move_lock_task = current; + memcg->move_lock_flags = flags; return memcg; } @@ -2031,14 +2038,17 @@ again: /** * mem_cgroup_end_page_stat - finish a page state statistics transaction * @memcg: the memcg that was accounted against - * @locked: value received from mem_cgroup_begin_page_stat() - * @flags: value received from mem_cgroup_begin_page_stat() */ -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags) +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { - if (memcg && *locked) - spin_unlock_irqrestore(&memcg->move_lock, *flags); + if (memcg && memcg->move_lock_task == current) { + unsigned long flags = memcg->move_lock_flags; + + memcg->move_lock_task = NULL; + memcg->move_lock_flags = 0; + + spin_unlock_irqrestore(&memcg->move_lock, flags); + } rcu_read_unlock(); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6f4335238e33..fb71e9deca85 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2308,12 +2308,10 @@ EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2338,19 +2336,17 @@ int test_clear_page_writeback(struct page *page) dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2380,7 +2376,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } diff --git a/mm/rmap.c b/mm/rmap.c index 70b32498d4f2..5e3e09081164 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1085,24 +1085,20 @@ void page_add_new_anon_rmap(struct page *page, void page_add_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); } - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } static void page_remove_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) @@ -1123,7 +1119,7 @@ static void page_remove_file_rmap(struct page *page) if (unlikely(PageMlocked(page))) clear_page_mlock(page); out: - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } /** -- cgit v1.2.3 From 44628d9755e249aab9a6e1a17407d2f4278047ee Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Wed, 11 Feb 2015 15:25:10 -0800 Subject: mm: fix typo of MIGRATE_RESERVE in comment Found it when I want to jump to the definition of MIGRATE_RESERVE ctags. Signed-off-by: Baoquan He Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 2f0856d14b21..b41829701334 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -426,7 +426,7 @@ struct zone { const char *name; /* - * Number of MIGRATE_RESEVE page block. To maintain for just + * Number of MIGRATE_RESERVE page block. To maintain for just * optimization. Protected by zone->lock. */ int nr_migrate_reserve_block; -- cgit v1.2.3 From e66f17ff71772b209eed39de35aaa99ba819c93d Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:25:22 -0800 Subject: mm/hugetlb: take page table lock in follow_huge_pmd() We have a race condition between move_pages() and freeing hugepages, where move_pages() calls follow_page(FOLL_GET) for hugepages internally and tries to get its refcount without preventing concurrent freeing. This race crashes the kernel, so this patch fixes it by moving FOLL_GET code for hugepages into follow_huge_pmd() with taking the page table lock. This patch intentionally removes page==NULL check after pte_page. This is justified because pte_page() never returns NULL for any architectures or configurations. This patch changes the behavior of follow_huge_pmd() for tail pages and then tail pages can be pinned/returned. So the caller must be changed to properly handle the returned tail pages. We could have a choice to add the similar locking to follow_huge_(addr|pud) for consistency, but it's not necessary because currently these functions don't support FOLL_GET flag, so let's leave it for future development. Here is the reproducer: $ cat movepages.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 #define PS 0x1000 int main(int argc, char *argv[]) { int i; int nr_hp = strtol(argv[1], NULL, 0); int nr_p = nr_hp * HPS / PS; int ret; void **addrs; int *status; int *nodes; pid_t pid; pid = strtol(argv[2], NULL, 0); addrs = malloc(sizeof(char *) * nr_p + 1); status = malloc(sizeof(char *) * nr_p + 1); nodes = malloc(sizeof(char *) * nr_p + 1); while (1) { for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 1; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); for (i = 0; i < nr_p; i++) { addrs[i] = (void *)ADDR_INPUT + i * PS; nodes[i] = 0; status[i] = 0; } ret = numa_move_pages(pid, nr_p, addrs, nodes, status, MPOL_MF_MOVE_ALL); if (ret == -1) err("move_pages"); } return 0; } $ cat hugepage.c #include #include #include #define ADDR_INPUT 0x700000000000UL #define HPS 0x200000 int main(int argc, char *argv[]) { int nr_hp = strtol(argv[1], NULL, 0); char *p; while (1) { p = mmap((void *)ADDR_INPUT, nr_hp * HPS, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (p != (void *)ADDR_INPUT) { perror("mmap"); break; } memset(p, 0, nr_hp * HPS); munmap(p, nr_hp * HPS); } } $ sysctl vm.nr_hugepages=40 $ ./hugepage 10 & $ ./movepages 10 $(pgrep -f hugepage) Fixes: e632a938d914 ("mm: migrate: add hugepage migration code to move_pages()") Signed-off-by: Naoya Horiguchi Reported-by: Hugh Dickins Cc: James Hogan Cc: David Rientjes Cc: Mel Gorman Cc: Johannes Weiner Cc: Michal Hocko Cc: Rik van Riel Cc: Andrea Arcangeli Cc: Luiz Capitulino Cc: Nishanth Aravamudan Cc: Lee Schermerhorn Cc: Steve Capper Cc: [3.12+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 8 ++++---- include/linux/swapops.h | 4 ++++ mm/gup.c | 25 ++++++++----------------- mm/hugetlb.c | 48 ++++++++++++++++++++++++++++++++++-------------- mm/migrate.c | 5 +++-- 5 files changed, 53 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7d7856359920..7b5785032049 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -99,9 +99,9 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write); + pmd_t *pmd, int flags); struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write); + pud_t *pud, int flags); int pmd_huge(pmd_t pmd); int pud_huge(pud_t pmd); unsigned long hugetlb_change_protection(struct vm_area_struct *vma, @@ -133,8 +133,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m) static inline void hugetlb_show_meminfo(void) { } -#define follow_huge_pmd(mm, addr, pmd, write) NULL -#define follow_huge_pud(mm, addr, pud, write) NULL +#define follow_huge_pmd(mm, addr, pmd, flags) NULL +#define follow_huge_pud(mm, addr, pud, flags) NULL #define prepare_hugepage_range(file, addr, len) (-EINVAL) #define pmd_huge(x) 0 #define pud_huge(x) 0 diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 50cbc876be56..831a3168ab35 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -135,6 +135,8 @@ static inline void make_migration_entry_read(swp_entry_t *entry) *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); } +extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); extern void migration_entry_wait_huge(struct vm_area_struct *vma, @@ -148,6 +150,8 @@ static inline int is_migration_entry(swp_entry_t swp) } #define migration_entry_to_page(swp) NULL static inline void make_migration_entry_read(swp_entry_t *entryp) { } +static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, diff --git a/mm/gup.c b/mm/gup.c index 12bc2bc33da7..1a8ab05918e0 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - if (flags & FOLL_GET) - return NULL; - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - return page; + page = follow_huge_pud(mm, address, pud, flags); + if (page) + return page; + return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); @@ -179,19 +179,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - if (flags & FOLL_GET) { - /* - * Refcount on tail pages are not well-defined and - * shouldn't be taken. The caller should handle a NULL - * return when trying to follow tail pages. - */ - if (PageHead(page)) - get_page(page); - else - page = NULL; - } - return page; + page = follow_huge_pmd(mm, address, pmd, flags); + if (page) + return page; + return no_page_table(vma, flags); } if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) return no_page_table(vma, flags); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d96b8bfa748f..5aca3707450f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3675,28 +3675,48 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address, struct page * __weak follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) + pmd_t *pmd, int flags) { - struct page *page; - - if (!pmd_present(*pmd)) - return NULL; - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + struct page *page = NULL; + spinlock_t *ptl; +retry: + ptl = pmd_lockptr(mm, pmd); + spin_lock(ptl); + /* + * make sure that the address range covered by this pmd is not + * unmapped from other threads. + */ + if (!pmd_huge(*pmd)) + goto out; + if (pmd_present(*pmd)) { + page = pte_page(*(pte_t *)pmd) + + ((address & ~PMD_MASK) >> PAGE_SHIFT); + if (flags & FOLL_GET) + get_page(page); + } else { + if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pmd, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); return page; } struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) + pud_t *pud, int flags) { - struct page *page; + if (flags & FOLL_GET) + return NULL; - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); - return page; + return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); } #ifdef CONFIG_MEMORY_FAILURE diff --git a/mm/migrate.c b/mm/migrate.c index 6e284bcca8bb..f98067e5d353 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -197,7 +197,7 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, +void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { pte_t pte; @@ -1236,7 +1236,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm, goto put_and_set; if (PageHuge(page)) { - isolate_huge_page(page, &pagelist); + if (PageHead(page)) + isolate_huge_page(page, &pagelist); goto put_and_set; } -- cgit v1.2.3 From 1a6d53a105406d97396c87511afd6f09b4dc8ad2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:44 -0800 Subject: mm: reduce try_to_compact_pages parameters Expand the usage of the struct alloc_context introduced in the previous patch also for calling try_to_compact_pages(), to reduce the number of its parameters. Since the function is in different compilation unit, we need to move alloc_context definition in the shared mm/internal.h header. With this change we get simpler code and small savings of code size and stack usage: add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-27 (-27) function old new delta __alloc_pages_direct_compact 283 256 -27 add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-13 (-13) function old new delta try_to_compact_pages 582 569 -13 Stack usage of __alloc_pages_direct_compact goes from 24 to none (per scripts/checkstack.pl). Signed-off-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 17 +++++++++-------- mm/compaction.c | 23 +++++++++++------------ mm/internal.h | 22 ++++++++++++++++++++++ mm/page_alloc.c | 27 ++------------------------- 4 files changed, 44 insertions(+), 45 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3238ffa33f68..f2efda2e6ac6 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -21,6 +21,8 @@ /* Zone lock or lru_lock was contended in async compaction */ #define COMPACT_CONTENDED_LOCK 2 +struct alloc_context; /* in mm/internal.h */ + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -30,10 +32,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); extern int fragmentation_index(struct zone *zone, unsigned int order); -extern unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *mask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx); +extern unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended); extern void compact_pgdat(pg_data_t *pgdat, int order); extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, @@ -101,10 +102,10 @@ static inline bool compaction_restarting(struct zone *zone, int order) } #else -static inline unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, + unsigned int order, int alloc_flags, + const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { return COMPACT_CONTINUE; } diff --git a/mm/compaction.c b/mm/compaction.c index 546e571e9d60..9c7e6909dd29 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1335,22 +1335,20 @@ int sysctl_extfrag_threshold = 500; /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation - * @zonelist: The zonelist used for the current allocation - * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation - * @nodemask: The allowed nodes to allocate from + * @order: The order of the current allocation + * @alloc_flags: The allocation flags of the current allocation + * @ac: The context of current allocation * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that determines if compaction was aborted due to * need_resched() or lock contention * * This is the main entry point for direct page compaction. */ -unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { - enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; @@ -1365,8 +1363,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, return COMPACT_SKIPPED; /* Compact each zone in the list */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, - nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { int status; int zone_contended; @@ -1374,7 +1372,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, continue; status = compact_zone_order(zone, order, gfp_mask, mode, - &zone_contended, alloc_flags, classzone_idx); + &zone_contended, alloc_flags, + ac->classzone_idx); rc = max(status, rc); /* * It takes at least one zone that wasn't lock contended @@ -1384,7 +1383,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), - classzone_idx, alloc_flags)) { + ac->classzone_idx, alloc_flags)) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller diff --git a/mm/internal.h b/mm/internal.h index efad241f7014..c4d6c9b43491 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -109,6 +109,28 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); * in mm/page_alloc.c */ +/* + * Structure for holding the mostly immutable allocation parameters passed + * between functions involved in allocations, including the alloc_pages* + * family of functions. + * + * nodemask, migratetype and high_zoneidx are initialized only once in + * __alloc_pages_nodemask() and then never change. + * + * zonelist, preferred_zone and classzone_idx are set first in + * __alloc_pages_nodemask() for the fast path, and might be later changed + * in __alloc_pages_slowpath(). All other functions pass the whole strucure + * by a const pointer. + */ +struct alloc_context { + struct zonelist *zonelist; + nodemask_t *nodemask; + struct zone *preferred_zone; + int classzone_idx; + int migratetype; + enum zone_type high_zoneidx; +}; + /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 4aead0bd8d44..d664eb922a7d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -232,27 +232,6 @@ EXPORT_SYMBOL(nr_node_ids); EXPORT_SYMBOL(nr_online_nodes); #endif -/* - * Structure for holding the mostly immutable allocation parameters passed - * between alloc_pages* family of functions. - * - * nodemask, migratetype and high_zoneidx are initialized only once in - * __alloc_pages_nodemask() and then never change. - * - * zonelist, preferred_zone and classzone_idx are set first in - * __alloc_pages_nodemask() for the fast path, and might be later changed - * in __alloc_pages_slowpath(). All other functions pass the whole strucure - * by a const pointer. - */ -struct alloc_context { - struct zonelist *zonelist; - nodemask_t *nodemask; - struct zone *preferred_zone; - int classzone_idx; - int migratetype; - enum zone_type high_zoneidx; -}; - int page_group_by_mobility_disabled __read_mostly; void set_pageblock_migratetype(struct page *page, int migratetype) @@ -2429,10 +2408,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; current->flags |= PF_MEMALLOC; - compact_result = try_to_compact_pages(ac->zonelist, order, gfp_mask, - ac->nodemask, mode, - contended_compaction, - alloc_flags, ac->classzone_idx); + compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + mode, contended_compaction); current->flags &= ~PF_MEMALLOC; switch (compact_result) { -- cgit v1.2.3 From 05891fb06517d19ae5357c9dc44e96bbe0300a3c Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:25:47 -0800 Subject: mm: microoptimize zonelist operations next_zones_zonelist() returns a zoneref pointer, as well as a zone pointer via extra parameter. Since the latter can be trivially obtained by dereferencing the former, the overhead of the extra parameter is unjustified. This patch thus removes the zone parameter from next_zones_zonelist(). Both callers happen to be in the same header file, so it's simple to add the zoneref dereference inline. We save some bytes of code size. add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-105 (-105) function old new delta nr_free_zone_pages 129 115 -14 __alloc_pages_nodemask 2300 2285 -15 get_page_from_freelist 2652 2576 -76 add/remove: 0/0 grow/shrink: 1/0 up/down: 10/0 (10) function old new delta try_to_compact_pages 569 579 +10 Signed-off-by: Vlastimil Babka Cc: Mel Gorman Cc: Zhang Yanfei Cc: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 13 +++++++------ mm/mmzone.c | 4 +--- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b41829701334..f279d9c158cd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -970,7 +970,6 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) * @z - The cursor used as a starting point for the search * @highest_zoneidx - The zone index of the highest zone to return * @nodes - An optional nodemask to filter the zonelist with - * @zone - The first suitable zone found is returned via this parameter * * This function returns the next zone at or below a given zone index that is * within the allowed nodemask using a cursor as the starting point for the @@ -980,8 +979,7 @@ static inline int zonelist_node_idx(struct zoneref *zoneref) */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone); + nodemask_t *nodes); /** * first_zones_zonelist - Returns the first zone at or below highest_zoneidx within the allowed nodemask in a zonelist @@ -1000,8 +998,10 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, nodemask_t *nodes, struct zone **zone) { - return next_zones_zonelist(zonelist->_zonerefs, highest_zoneidx, nodes, - zone); + struct zoneref *z = next_zones_zonelist(zonelist->_zonerefs, + highest_zoneidx, nodes); + *zone = zonelist_zone(z); + return z; } /** @@ -1018,7 +1018,8 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, nodemask) \ for (z = first_zones_zonelist(zlist, highidx, nodemask, &zone); \ zone; \ - z = next_zones_zonelist(++z, highidx, nodemask, &zone)) \ + z = next_zones_zonelist(++z, highidx, nodemask), \ + zone = zonelist_zone(z)) \ /** * for_each_zone_zonelist - helper macro to iterate over valid zones in a zonelist at or below a given zone index diff --git a/mm/mmzone.c b/mm/mmzone.c index bf34fb8556db..7d87ebb0d632 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -54,8 +54,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) /* Returns the next zone at or below highest_zoneidx in a zonelist */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone) + nodemask_t *nodes) { /* * Find the next suitable zone to use for the allocation. @@ -69,7 +68,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, (z->zone && !zref_in_nodemask(z, nodes))) z++; - *zone = zonelist_zone(z); return z; } -- cgit v1.2.3 From 90cbc2508827e1e15dca23361c33cc26dd2b9e99 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 11 Feb 2015 15:25:55 -0800 Subject: vmscan: force scan offline memory cgroups Since commit b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined groups") pages charged to a memory cgroup are not reparented when the cgroup is removed. Instead, they are supposed to be reclaimed in a regular way, along with pages accounted to online memory cgroups. However, an lruvec of an offline memory cgroup will sooner or later get so small that it will be scanned only at low scan priorities (see get_scan_count()). Therefore, if there are enough reclaimable pages in big lruvecs, pages accounted to offline memory cgroups will never be scanned at all, wasting memory. Fix this by unconditionally forcing scanning dead lruvecs from kswapd. [akpm@linux-foundation.org: fix build] Signed-off-by: Vladimir Davydov Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 6 ++++++ mm/memcontrol.c | 14 ++++++++++++++ mm/vmscan.c | 8 ++++++-- 3 files changed, 26 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 76b4084b8d08..353537a5981a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -102,6 +102,7 @@ void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); * For memory reclaim. */ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); +bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); @@ -266,6 +267,11 @@ mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return 1; } +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + return true; +} + static inline unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 028d07c79104..6187ca4d5dc2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1367,6 +1367,20 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return inactive * inactive_ratio < active; } +bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) diff --git a/mm/vmscan.c b/mm/vmscan.c index f756a202d5d5..b6dfa0081a8e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1903,8 +1903,12 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && !zone_reclaimable(zone)) - force_scan = true; + if (current_is_kswapd()) { + if (!zone_reclaimable(zone)) + force_scan = true; + if (!mem_cgroup_lruvec_online(lruvec)) + force_scan = true; + } if (!global_reclaim(sc)) force_scan = true; -- cgit v1.2.3 From 650c5e565492f9092552bfe4d65935196c7d9567 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:03 -0800 Subject: mm: page_counter: pull "-1" handling out of page_counter_memparse() The unified hierarchy interface for memory cgroups will no longer use "-1" to mean maximum possible resource value. In preparation for this, make the string an argument and let the caller supply it. Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_counter.h | 3 ++- mm/hugetlb_cgroup.c | 2 +- mm/memcontrol.c | 4 ++-- mm/page_counter.c | 7 ++++--- net/ipv4/tcp_memcontrol.c | 2 +- 5 files changed, 10 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 955421575d16..17fa4f8de3a6 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -41,7 +41,8 @@ int page_counter_try_charge(struct page_counter *counter, struct page_counter **fail); void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages); int page_counter_limit(struct page_counter *counter, unsigned long limit); -int page_counter_memparse(const char *buf, unsigned long *nr_pages); +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages); static inline void page_counter_reset_watermark(struct page_counter *counter) { diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 037e1c00a5b7..6e0057439a46 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -279,7 +279,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, return -EINVAL; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index dc5c4cd0afdf..6453ea5a27aa 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3414,7 +3414,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, int ret; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; @@ -3786,7 +3786,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, unsigned long usage; int i, size, ret; - ret = page_counter_memparse(args, &threshold); + ret = page_counter_memparse(args, "-1", &threshold); if (ret) return ret; diff --git a/mm/page_counter.c b/mm/page_counter.c index a009574fbba9..11b4beda14ba 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -166,18 +166,19 @@ int page_counter_limit(struct page_counter *counter, unsigned long limit) /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse + * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ -int page_counter_memparse(const char *buf, unsigned long *nr_pages) +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages) { - char unlimited[] = "-1"; char *end; u64 bytes; - if (!strncmp(buf, unlimited, sizeof(unlimited))) { + if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 272327134a1b..c2a75c6957a1 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -120,7 +120,7 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, switch (of_cft(of)->private) { case RES_LIMIT: /* see memcontrol.c */ - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) break; mutex_lock(&tcp_limit_mutex); -- cgit v1.2.3 From 241994ed8649f7300667be8b13a9e04ae04e05a1 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 11 Feb 2015 15:26:06 -0800 Subject: mm: memcontrol: default hierarchy interface for memory Introduce the basic control files to account, partition, and limit memory using cgroups in default hierarchy mode. This interface versioning allows us to address fundamental design issues in the existing memory cgroup interface, further explained below. The old interface will be maintained indefinitely, but a clearer model and improved workload performance should encourage existing users to switch over to the new one eventually. The control files are thus: - memory.current shows the current consumption of the cgroup and its descendants, in bytes. - memory.low configures the lower end of the cgroup's expected memory consumption range. The kernel considers memory below that boundary to be a reserve - the minimum that the workload needs in order to make forward progress - and generally avoids reclaiming it, unless there is an imminent risk of entering an OOM situation. - memory.high configures the upper end of the cgroup's expected memory consumption range. A cgroup whose consumption grows beyond this threshold is forced into direct reclaim, to work off the excess and to throttle new allocations heavily, but is generally allowed to continue and the OOM killer is not invoked. - memory.max configures the hard maximum amount of memory that the cgroup is allowed to consume before the OOM killer is invoked. - memory.events shows event counters that indicate how often the cgroup was reclaimed while below memory.low, how often it was forced to reclaim excess beyond memory.high, how often it hit memory.max, and how often it entered OOM due to memory.max. This allows users to identify configuration problems when observing a degradation in workload performance. An overcommitted system will have an increased rate of low boundary breaches, whereas increased rates of high limit breaches, maximum hits, or even OOM situations will indicate internally overcommitted cgroups. For existing users of memory cgroups, the following deviations from the current interface are worth pointing out and explaining: - The original lower boundary, the soft limit, is defined as a limit that is per default unset. As a result, the set of cgroups that global reclaim prefers is opt-in, rather than opt-out. The costs for optimizing these mostly negative lookups are so high that the implementation, despite its enormous size, does not even provide the basic desirable behavior. First off, the soft limit has no hierarchical meaning. All configured groups are organized in a global rbtree and treated like equal peers, regardless where they are located in the hierarchy. This makes subtree delegation impossible. Second, the soft limit reclaim pass is so aggressive that it not just introduces high allocation latencies into the system, but also impacts system performance due to overreclaim, to the point where the feature becomes self-defeating. The memory.low boundary on the other hand is a top-down allocated reserve. A cgroup enjoys reclaim protection when it and all its ancestors are below their low boundaries, which makes delegation of subtrees possible. Secondly, new cgroups have no reserve per default and in the common case most cgroups are eligible for the preferred reclaim pass. This allows the new low boundary to be efficiently implemented with just a minor addition to the generic reclaim code, without the need for out-of-band data structures and reclaim passes. Because the generic reclaim code considers all cgroups except for the ones running low in the preferred first reclaim pass, overreclaim of individual groups is eliminated as well, resulting in much better overall workload performance. - The original high boundary, the hard limit, is defined as a strict limit that can not budge, even if the OOM killer has to be called. But this generally goes against the goal of making the most out of the available memory. The memory consumption of workloads varies during runtime, and that requires users to overcommit. But doing that with a strict upper limit requires either a fairly accurate prediction of the working set size or adding slack to the limit. Since working set size estimation is hard and error prone, and getting it wrong results in OOM kills, most users tend to err on the side of a looser limit and end up wasting precious resources. The memory.high boundary on the other hand can be set much more conservatively. When hit, it throttles allocations by forcing them into direct reclaim to work off the excess, but it never invokes the OOM killer. As a result, a high boundary that is chosen too aggressively will not terminate the processes, but instead it will lead to gradual performance degradation. The user can monitor this and make corrections until the minimal memory footprint that still gives acceptable performance is found. In extreme cases, with many concurrent allocations and a complete breakdown of reclaim progress within the group, the high boundary can be exceeded. But even then it's mostly better to satisfy the allocation from the slack available in other groups or the rest of the system than killing the group. Otherwise, memory.max is there to limit this type of spillover and ultimately contain buggy or even malicious applications. - The original control file names are unwieldy and inconsistent in many different ways. For example, the upper boundary hit count is exported in the memory.failcnt file, but an OOM event count has to be manually counted by listening to memory.oom_control events, and lower boundary / soft limit events have to be counted by first setting a threshold for that value and then counting those events. Also, usage and limit files encode their units in the filename. That makes the filenames very long, even though this is not information that a user needs to be reminded of every time they type out those names. To address these naming issues, as well as to signal clearly that the new interface carries a new configuration model, the naming conventions in it necessarily differ from the old interface. - The original limit files indicate the state of an unset limit with a very high number, and a configured limit can be unset by echoing -1 into those files. But that very high number is implementation and architecture dependent and not very descriptive. And while -1 can be understood as an underflow into the highest possible value, -2 or -10M etc. do not work, so it's not inconsistent. memory.low, memory.high, and memory.max will use the string "infinity" to indicate and set the highest possible value. [akpm@linux-foundation.org: use seq_puts() for basic strings] Signed-off-by: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/cgroups/unified-hierarchy.txt | 79 ++++++++++ include/linux/memcontrol.h | 32 ++++ mm/memcontrol.c | 229 ++++++++++++++++++++++++++-- mm/vmscan.c | 22 ++- 4 files changed, 348 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt index 4f4563277864..71daa35ec2d9 100644 --- a/Documentation/cgroups/unified-hierarchy.txt +++ b/Documentation/cgroups/unified-hierarchy.txt @@ -327,6 +327,85 @@ supported and the interface files "release_agent" and - use_hierarchy is on by default and the cgroup file for the flag is not created. +- The original lower boundary, the soft limit, is defined as a limit + that is per default unset. As a result, the set of cgroups that + global reclaim prefers is opt-in, rather than opt-out. The costs + for optimizing these mostly negative lookups are so high that the + implementation, despite its enormous size, does not even provide the + basic desirable behavior. First off, the soft limit has no + hierarchical meaning. All configured groups are organized in a + global rbtree and treated like equal peers, regardless where they + are located in the hierarchy. This makes subtree delegation + impossible. Second, the soft limit reclaim pass is so aggressive + that it not just introduces high allocation latencies into the + system, but also impacts system performance due to overreclaim, to + the point where the feature becomes self-defeating. + + The memory.low boundary on the other hand is a top-down allocated + reserve. A cgroup enjoys reclaim protection when it and all its + ancestors are below their low boundaries, which makes delegation of + subtrees possible. Secondly, new cgroups have no reserve per + default and in the common case most cgroups are eligible for the + preferred reclaim pass. This allows the new low boundary to be + efficiently implemented with just a minor addition to the generic + reclaim code, without the need for out-of-band data structures and + reclaim passes. Because the generic reclaim code considers all + cgroups except for the ones running low in the preferred first + reclaim pass, overreclaim of individual groups is eliminated as + well, resulting in much better overall workload performance. + +- The original high boundary, the hard limit, is defined as a strict + limit that can not budge, even if the OOM killer has to be called. + But this generally goes against the goal of making the most out of + the available memory. The memory consumption of workloads varies + during runtime, and that requires users to overcommit. But doing + that with a strict upper limit requires either a fairly accurate + prediction of the working set size or adding slack to the limit. + Since working set size estimation is hard and error prone, and + getting it wrong results in OOM kills, most users tend to err on the + side of a looser limit and end up wasting precious resources. + + The memory.high boundary on the other hand can be set much more + conservatively. When hit, it throttles allocations by forcing them + into direct reclaim to work off the excess, but it never invokes the + OOM killer. As a result, a high boundary that is chosen too + aggressively will not terminate the processes, but instead it will + lead to gradual performance degradation. The user can monitor this + and make corrections until the minimal memory footprint that still + gives acceptable performance is found. + + In extreme cases, with many concurrent allocations and a complete + breakdown of reclaim progress within the group, the high boundary + can be exceeded. But even then it's mostly better to satisfy the + allocation from the slack available in other groups or the rest of + the system than killing the group. Otherwise, memory.max is there + to limit this type of spillover and ultimately contain buggy or even + malicious applications. + +- The original control file names are unwieldy and inconsistent in + many different ways. For example, the upper boundary hit count is + exported in the memory.failcnt file, but an OOM event count has to + be manually counted by listening to memory.oom_control events, and + lower boundary / soft limit events have to be counted by first + setting a threshold for that value and then counting those events. + Also, usage and limit files encode their units in the filename. + That makes the filenames very long, even though this is not + information that a user needs to be reminded of every time they type + out those names. + + To address these naming issues, as well as to signal clearly that + the new interface carries a new configuration model, the naming + conventions in it necessarily differ from the old interface. + +- The original limit files indicate the state of an unset limit with a + Very High Number, and a configured limit can be unset by echoing -1 + into those files. But that very high number is implementation and + architecture dependent and not very descriptive. And while -1 can + be understood as an underflow into the highest possible value, -2 or + -10M etc. do not work, so it's not consistent. + + memory.low, memory.high, and memory.max will use the string + "infinity" to indicate and set the highest possible value. 5. Planned Changes diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 353537a5981a..6cfd934c7c9b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -52,7 +52,27 @@ struct mem_cgroup_reclaim_cookie { unsigned int generation; }; +enum mem_cgroup_events_index { + MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ + MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ + MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ + MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ + MEM_CGROUP_EVENTS_NSTATS, + /* default hierarchy events */ + MEMCG_LOW = MEM_CGROUP_EVENTS_NSTATS, + MEMCG_HIGH, + MEMCG_MAX, + MEMCG_OOM, + MEMCG_NR_EVENTS, +}; + #ifdef CONFIG_MEMCG +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr); + +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); + int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, @@ -175,6 +195,18 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; +static inline void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ +} + +static inline bool mem_cgroup_low(struct mem_cgroup *root, + struct mem_cgroup *memcg) +{ + return false; +} + static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6453ea5a27aa..ee97c9ac62c0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -97,14 +97,6 @@ static const char * const mem_cgroup_stat_names[] = { "swap", }; -enum mem_cgroup_events_index { - MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ - MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ - MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ - MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ - MEM_CGROUP_EVENTS_NSTATS, -}; - static const char * const mem_cgroup_events_names[] = { "pgpgin", "pgpgout", @@ -138,7 +130,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEM_CGROUP_STAT_NSTATS]; - unsigned long events[MEM_CGROUP_EVENTS_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -284,6 +276,10 @@ struct mem_cgroup { struct page_counter memsw; struct page_counter kmem; + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + unsigned long soft_limit; /* vmpressure notifications */ @@ -2315,6 +2311,8 @@ retry: if (!(gfp_mask & __GFP_WAIT)) goto nomem; + mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); + nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -2356,6 +2354,8 @@ retry: if (fatal_signal_pending(current)) goto bypass; + mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages)); nomem: if (!(gfp_mask & __GFP_NOFAIL)) @@ -2367,6 +2367,16 @@ done_restock: css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); + /* + * If the hierarchy is above the normal consumption range, + * make the charging task trim their excess contribution. + */ + do { + if (page_counter_read(&memcg->memory) <= memcg->high) + continue; + mem_cgroup_events(memcg, MEMCG_HIGH, 1); + try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + } while ((memcg = parent_mem_cgroup(memcg))); done: return ret; } @@ -4276,7 +4286,7 @@ out_kfree: return ret; } -static struct cftype mem_cgroup_files[] = { +static struct cftype mem_cgroup_legacy_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), @@ -4552,6 +4562,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent_css == NULL) { root_mem_cgroup = memcg; page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4597,6 +4608,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (parent->use_hierarchy) { page_counter_init(&memcg->memory, &parent->memory); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, &parent->memsw); page_counter_init(&memcg->kmem, &parent->kmem); @@ -4607,6 +4619,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) */ } else { page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4682,6 +4695,8 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX); mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX); memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX); + memcg->low = 0; + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; } @@ -5267,6 +5282,147 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) mem_cgroup_from_css(root_css)->use_hierarchy = true; } +static u64 memory_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_usage(mem_cgroup_from_css(css), false); +} + +static int memory_low_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long low = ACCESS_ONCE(memcg->low); + + if (low == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long low; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &low); + if (err) + return err; + + memcg->low = low; + + return nbytes; +} + +static int memory_high_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long high = ACCESS_ONCE(memcg->high); + + if (high == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &high); + if (err) + return err; + + memcg->high = high; + + return nbytes; +} + +static int memory_max_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long max = ACCESS_ONCE(memcg->memory.limit); + + if (max == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); + + return 0; +} + +static ssize_t memory_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &max); + if (err) + return err; + + err = mem_cgroup_resize_limit(memcg, max); + if (err) + return err; + + return nbytes; +} + +static int memory_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + + seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW)); + seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH)); + seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX)); + seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM)); + + return 0; +} + +static struct cftype memory_files[] = { + { + .name = "current", + .read_u64 = memory_current_read, + }, + { + .name = "low", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_low_show, + .write = memory_low_write, + }, + { + .name = "high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_high_show, + .write = memory_high_write, + }, + { + .name = "max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_max_show, + .write = memory_max_write, + }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_events_show, + }, + { } /* terminate */ +}; + struct cgroup_subsys memory_cgrp_subsys = { .css_alloc = mem_cgroup_css_alloc, .css_online = mem_cgroup_css_online, @@ -5277,7 +5433,8 @@ struct cgroup_subsys memory_cgrp_subsys = { .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, - .legacy_cftypes = mem_cgroup_files, + .dfl_cftypes = memory_files, + .legacy_cftypes = mem_cgroup_legacy_files, .early_init = 0, }; @@ -5312,6 +5469,56 @@ static void __init enable_swap_cgroup(void) } #endif +/** + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); +} + +/** + * mem_cgroup_low - check if memory consumption is below the normal range + * @root: the highest ancestor to consider + * @memcg: the memory cgroup to check + * + * Returns %true if memory consumption of @memcg, and that of all + * configurable ancestors up to @root, is below the normal range. + */ +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) +{ + if (mem_cgroup_disabled()) + return false; + + /* + * The toplevel group doesn't have a configurable range, so + * it's never low when looked at directly, and it is not + * considered an ancestor when assessing the hierarchy. + */ + + if (memcg == root_mem_cgroup) + return false; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; + + while (memcg != root) { + memcg = parent_mem_cgroup(memcg); + + if (memcg == root_mem_cgroup) + break; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; + } + return true; +} + #ifdef CONFIG_MEMCG_SWAP /** * mem_cgroup_swapout - transfer a memsw charge to swap diff --git a/mm/vmscan.c b/mm/vmscan.c index b6dfa0081a8e..8e645ee52045 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -91,6 +91,9 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; + /* Can cgroups be reclaimed below their normal consumption range? */ + unsigned int may_thrash:1; + unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ @@ -2294,6 +2297,12 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, struct lruvec *lruvec; int swappiness; + if (mem_cgroup_low(root, memcg)) { + if (!sc->may_thrash) + continue; + mem_cgroup_events(memcg, MEMCG_LOW, 1); + } + lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); @@ -2315,8 +2324,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, mem_cgroup_iter_break(root, memcg); break; } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } while ((memcg = mem_cgroup_iter(root, memcg, &reclaim))); /* * Shrink the slab caches in the same proportion that @@ -2519,10 +2527,11 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { + int initial_priority = sc->priority; unsigned long total_scanned = 0; unsigned long writeback_threshold; bool zones_reclaimable; - +retry: delayacct_freepages_start(); if (global_reclaim(sc)) @@ -2572,6 +2581,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (sc->compaction_ready) return 1; + /* Untapped cgroup reserves? Don't OOM, retry. */ + if (!sc->may_thrash) { + sc->priority = initial_priority; + sc->may_thrash = 1; + goto retry; + } + /* Any of the zones still reclaimable? Don't OOM. */ if (zones_reclaimable) return 1; -- cgit v1.2.3 From 49550b605587924b3336386caae53200c68969d3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:12 -0800 Subject: oom: add helpers for setting and clearing TIF_MEMDIE This patchset addresses a race which was described in the changelog for 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend"): : PM freezer relies on having all tasks frozen by the time devices are : getting frozen so that no task will touch them while they are getting : frozen. But OOM killer is allowed to kill an already frozen task in order : to handle OOM situtation. In order to protect from late wake ups OOM : killer is disabled after all tasks are frozen. This, however, still keeps : a window open when a killed task didn't manage to die by the time : freeze_processes finishes. The original patch hasn't closed the race window completely because that would require a more complex solution as it can be seen by this patchset. The primary motivation was to close the race condition between OOM killer and PM freezer _completely_. As Tejun pointed out, even though the race condition is unlikely the harder it would be to debug weird bugs deep in the PM freezer when the debugging options are reduced considerably. I can only speculate what might happen when a task is still runnable unexpectedly. On a plus side and as a side effect the oom enable/disable has a better (full barrier) semantic without polluting hot paths. I have tested the series in KVM with 100M RAM: - many small tasks (20M anon mmap) which are triggering OOM continually - s2ram which resumes automatically is triggered in a loop echo processors > /sys/power/pm_test while true do echo mem > /sys/power/state sleep 1s done - simple module which allocates and frees 20M in 8K chunks. If it sees freezing(current) then it tries another round of allocation before calling try_to_freeze - debugging messages of PM stages and OOM killer enable/disable/fail added and unmark_oom_victim is delayed by 1s after it clears TIF_MEMDIE and before it wakes up waiters. - rebased on top of the current mmotm which means some necessary updates in mm/oom_kill.c. mark_tsk_oom_victim is now called under task_lock but I think this should be OK because __thaw_task shouldn't interfere with any locking down wake_up_process. Oleg? As expected there are no OOM killed tasks after oom is disabled and allocations requested by the kernel thread are failing after all the tasks are frozen and OOM disabled. I wasn't able to catch a race where oom_killer_disable would really have to wait but I kinda expected the race is really unlikely. [ 242.609330] Killed process 2992 (mem_eater) total-vm:24412kB, anon-rss:2164kB, file-rss:4kB [ 243.628071] Unmarking 2992 OOM victim. oom_victims: 1 [ 243.636072] (elapsed 2.837 seconds) done. [ 243.641985] Trying to disable OOM killer [ 243.643032] Waiting for concurent OOM victims [ 243.644342] OOM killer disabled [ 243.645447] Freezing remaining freezable tasks ... (elapsed 0.005 seconds) done. [ 243.652983] Suspending console(s) (use no_console_suspend to debug) [ 243.903299] kmem_eater: page allocation failure: order:1, mode:0x204010 [...] [ 243.992600] PM: suspend of devices complete after 336.667 msecs [ 243.993264] PM: late suspend of devices complete after 0.660 msecs [ 243.994713] PM: noirq suspend of devices complete after 1.446 msecs [ 243.994717] ACPI: Preparing to enter system sleep state S3 [ 243.994795] PM: Saving platform NVS memory [ 243.994796] Disabling non-boot CPUs ... The first 2 patches are simple cleanups for OOM. They should go in regardless the rest IMO. Patches 3 and 4 are trivial printk -> pr_info conversion and they should go in ditto. The main patch is the last one and I would appreciate acks from Tejun and Rafael. I think the OOM part should be OK (except for __thaw_task vs. task_lock where a look from Oleg would appreciated) but I am not so sure I haven't screwed anything in the freezer code. I have found several surprises there. This patch (of 5): This patch is just a preparatory and it doesn't introduce any functional change. Note: I am utterly unhappy about lowmemory killer abusing TIF_MEMDIE just to wait for the oom victim and to prevent from new killing. This is just a side effect of the flag. The primary meaning is to give the oom victim access to the memory reserves and that shouldn't be necessary here. Signed-off-by: Michal Hocko Cc: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/lowmemorykiller.c | 7 ++++++- include/linux/oom.h | 4 ++++ kernel/exit.c | 2 +- mm/memcontrol.c | 2 +- mm/oom_kill.c | 23 ++++++++++++++++++++--- 5 files changed, 32 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c index b545d3d1da3e..feafa172b155 100644 --- a/drivers/staging/android/lowmemorykiller.c +++ b/drivers/staging/android/lowmemorykiller.c @@ -160,7 +160,12 @@ static unsigned long lowmem_scan(struct shrinker *s, struct shrink_control *sc) selected->pid, selected->comm, selected_oom_score_adj, selected_tasksize); lowmem_deathpending_timeout = jiffies + HZ; - set_tsk_thread_flag(selected, TIF_MEMDIE); + /* + * FIXME: lowmemorykiller shouldn't abuse global OOM killer + * infrastructure. There is no real reason why the selected + * task should have access to the memory reserves. + */ + mark_tsk_oom_victim(selected); send_sig(SIGKILL, selected, 0); rem += selected_tasksize; } diff --git a/include/linux/oom.h b/include/linux/oom.h index 76200984d1e2..b42b80f88c3a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -47,6 +47,10 @@ static inline bool oom_task_origin(const struct task_struct *p) return !!(p->signal->oom_flags & OOM_FLAG_ORIGIN); } +extern void mark_tsk_oom_victim(struct task_struct *tsk); + +extern void unmark_oom_victim(void); + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff --git a/kernel/exit.c b/kernel/exit.c index 6806c55475ee..02b3d1ab2ec0 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,7 @@ static void exit_mm(struct task_struct *tsk) task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); - clear_thread_flag(TIF_MEMDIE); + unmark_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 11c9e6a1dad5..fe4d258ef32b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1556,7 +1556,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * quickly exit and free its memory. */ if (fatal_signal_pending(current) || task_will_free_mem(current)) { - set_thread_flag(TIF_MEMDIE); + mark_tsk_oom_victim(current); return; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 294493a7ae4b..80b34e285f96 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -416,6 +416,23 @@ void note_oom_kill(void) atomic_inc(&oom_kills); } +/** + * mark_tsk_oom_victim - marks the given taks as OOM victim. + * @tsk: task to mark + */ +void mark_tsk_oom_victim(struct task_struct *tsk) +{ + set_tsk_thread_flag(tsk, TIF_MEMDIE); +} + +/** + * unmark_oom_victim - unmarks the current task as OOM victim. + */ +void unmark_oom_victim(void) +{ + clear_thread_flag(TIF_MEMDIE); +} + #define K(x) ((x) << (PAGE_SHIFT-10)) /* * Must be called while holding a reference to p, which will be released upon @@ -440,7 +457,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ task_lock(p); if (p->mm && task_will_free_mem(p)) { - set_tsk_thread_flag(p, TIF_MEMDIE); + mark_tsk_oom_victim(p); task_unlock(p); put_task_struct(p); return; @@ -495,7 +512,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; - set_tsk_thread_flag(victim, TIF_MEMDIE); + mark_tsk_oom_victim(victim); pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), @@ -652,7 +669,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ if (current->mm && (fatal_signal_pending(current) || task_will_free_mem(current))) { - set_thread_flag(TIF_MEMDIE); + mark_tsk_oom_victim(current); return; } -- cgit v1.2.3 From c32b3cbe0d067a9cfae85aa70ba1e97ceba0ced7 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 11 Feb 2015 15:26:24 -0800 Subject: oom, PM: make OOM detection in the freezer path raceless Commit 5695be142e20 ("OOM, PM: OOM killed task shouldn't escape PM suspend") has left a race window when OOM killer manages to note_oom_kill after freeze_processes checks the counter. The race window is quite small and really unlikely and partial solution deemed sufficient at the time of submission. Tejun wasn't happy about this partial solution though and insisted on a full solution. That requires the full OOM and freezer's task freezing exclusion, though. This is done by this patch which introduces oom_sem RW lock and turns oom_killer_disable() into a full OOM barrier. oom_killer_disabled check is moved from the allocation path to the OOM level and we take oom_sem for reading for both the check and the whole OOM invocation. oom_killer_disable() takes oom_sem for writing so it waits for all currently running OOM killer invocations. Then it disable all the further OOMs by setting oom_killer_disabled and checks for any oom victims. Victims are counted via mark_tsk_oom_victim resp. unmark_oom_victim. The last victim wakes up all waiters enqueued by oom_killer_disable(). Therefore this function acts as the full OOM barrier. The page fault path is covered now as well although it was assumed to be safe before. As per Tejun, "We used to have freezing points deep in file system code which may be reacheable from page fault." so it would be better and more robust to not rely on freezing points here. Same applies to the memcg OOM killer. out_of_memory tells the caller whether the OOM was allowed to trigger and the callers are supposed to handle the situation. The page allocation path simply fails the allocation same as before. The page fault path will retry the fault (more on that later) and Sysrq OOM trigger will simply complain to the log. Normally there wouldn't be any unfrozen user tasks after try_to_freeze_tasks so the function will not block. But if there was an OOM killer racing with try_to_freeze_tasks and the OOM victim didn't finish yet then we have to wait for it. This should complete in a finite time, though, because - the victim cannot loop in the page fault handler (it would die on the way out from the exception) - it cannot loop in the page allocator because all the further allocation would fail and __GFP_NOFAIL allocations are not acceptable at this stage - it shouldn't be blocked on any locks held by frozen tasks (try_to_freeze expects lockless context) and kernel threads and work queues are not frozen yet Signed-off-by: Michal Hocko Suggested-by: Tejun Heo Cc: David Rientjes Cc: Johannes Weiner Cc: Oleg Nesterov Cc: Cong Wang Cc: "Rafael J. Wysocki" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/tty/sysrq.c | 5 +- include/linux/oom.h | 14 ++---- kernel/exit.c | 3 +- kernel/power/process.c | 50 ++++--------------- mm/memcontrol.c | 2 +- mm/oom_kill.c | 132 +++++++++++++++++++++++++++++++++++++++++-------- mm/page_alloc.c | 17 +------ 7 files changed, 132 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index 0071469ecbf1..259a4d5a4e8f 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -355,8 +355,9 @@ static struct sysrq_key_op sysrq_term_op = { static void moom_callback(struct work_struct *ignored) { - out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL, - 0, NULL, true); + if (!out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), + GFP_KERNEL, 0, NULL, true)) + pr_info("OOM request ignored because killer is disabled\n"); } static DECLARE_WORK(moom_work, moom_callback); diff --git a/include/linux/oom.h b/include/linux/oom.h index b42b80f88c3a..d5771bed59c9 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -72,22 +72,14 @@ extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, unsigned long totalpages, const nodemask_t *nodemask, bool force_kill); -extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *mask, bool force_kill); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disabled; - -static inline void oom_killer_disable(void) -{ - oom_killer_disabled = true; -} - -static inline void oom_killer_enable(void) -{ - oom_killer_disabled = false; -} +extern bool oom_killer_disable(void); +extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); diff --git a/kernel/exit.c b/kernel/exit.c index 02b3d1ab2ec0..feff10bbb307 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -435,7 +435,8 @@ static void exit_mm(struct task_struct *tsk) task_unlock(tsk); mm_update_next_owner(mm); mmput(mm); - unmark_oom_victim(); + if (test_thread_flag(TIF_MEMDIE)) + unmark_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) diff --git a/kernel/power/process.c b/kernel/power/process.c index 3ac45f192e9f..564f786df470 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -108,30 +108,6 @@ static int try_to_freeze_tasks(bool user_only) return todo ? -EBUSY : 0; } -static bool __check_frozen_processes(void) -{ - struct task_struct *g, *p; - - for_each_process_thread(g, p) - if (p != current && !freezer_should_skip(p) && !frozen(p)) - return false; - - return true; -} - -/* - * Returns true if all freezable tasks (except for current) are frozen already - */ -static bool check_frozen_processes(void) -{ - bool ret; - - read_lock(&tasklist_lock); - ret = __check_frozen_processes(); - read_unlock(&tasklist_lock); - return ret; -} - /** * freeze_processes - Signal user space processes to enter the refrigerator. * The current thread will not be frozen. The same process that calls @@ -142,7 +118,6 @@ static bool check_frozen_processes(void) int freeze_processes(void) { int error; - int oom_kills_saved; error = __usermodehelper_disable(UMH_FREEZING); if (error) @@ -157,29 +132,22 @@ int freeze_processes(void) pm_wakeup_clear(); pr_info("Freezing user space processes ... "); pm_freezing = true; - oom_kills_saved = oom_kills_count(); error = try_to_freeze_tasks(true); if (!error) { __usermodehelper_set_disable_depth(UMH_DISABLED); - oom_killer_disable(); - - /* - * There might have been an OOM kill while we were - * freezing tasks and the killed task might be still - * on the way out so we have to double check for race. - */ - if (oom_kills_count() != oom_kills_saved && - !check_frozen_processes()) { - __usermodehelper_set_disable_depth(UMH_ENABLED); - pr_cont("OOM in progress."); - error = -EBUSY; - } else { - pr_cont("done."); - } + pr_cont("done."); } pr_cont("\n"); BUG_ON(in_atomic()); + /* + * Now that the whole userspace is frozen we need to disbale + * the OOM killer to disallow any further interference with + * killable tasks. + */ + if (!error && !oom_killer_disable()) + error = -EBUSY; + if (error) thaw_processes(); return error; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fe4d258ef32b..fbf64e6f64e4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1930,7 +1930,7 @@ bool mem_cgroup_oom_synchronize(bool handle) if (!memcg) return false; - if (!handle) + if (!handle || oom_killer_disabled) goto cleanup; owait.memcg = memcg; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 3cbd76b8c13b..b8df76ee2be3 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -398,30 +398,27 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } /* - * Number of OOM killer invocations (including memcg OOM killer). - * Primarily used by PM freezer to check for potential races with - * OOM killed frozen task. + * Number of OOM victims in flight */ -static atomic_t oom_kills = ATOMIC_INIT(0); +static atomic_t oom_victims = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); -int oom_kills_count(void) -{ - return atomic_read(&oom_kills); -} - -void note_oom_kill(void) -{ - atomic_inc(&oom_kills); -} +bool oom_killer_disabled __read_mostly; +static DECLARE_RWSEM(oom_sem); /** * mark_tsk_oom_victim - marks the given taks as OOM victim. * @tsk: task to mark + * + * Has to be called with oom_sem taken for read and never after + * oom has been disabled already. */ void mark_tsk_oom_victim(struct task_struct *tsk) { - set_tsk_thread_flag(tsk, TIF_MEMDIE); - + WARN_ON(oom_killer_disabled); + /* OOM killer might race with memcg OOM */ + if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; /* * Make sure that the task is woken up from uninterruptible sleep * if it is frozen because OOM killer wouldn't be able to free @@ -429,14 +426,70 @@ void mark_tsk_oom_victim(struct task_struct *tsk) * that TIF_MEMDIE tasks should be ignored. */ __thaw_task(tsk); + atomic_inc(&oom_victims); } /** * unmark_oom_victim - unmarks the current task as OOM victim. + * + * Wakes up all waiters in oom_killer_disable() */ void unmark_oom_victim(void) { - clear_thread_flag(TIF_MEMDIE); + if (!test_and_clear_thread_flag(TIF_MEMDIE)) + return; + + down_read(&oom_sem); + /* + * There is no need to signal the lasst oom_victim if there + * is nobody who cares. + */ + if (!atomic_dec_return(&oom_victims) && oom_killer_disabled) + wake_up_all(&oom_victims_wait); + up_read(&oom_sem); +} + +/** + * oom_killer_disable - disable OOM killer + * + * Forces all page allocations to fail rather than trigger OOM killer. + * Will block and wait until all OOM victims are killed. + * + * The function cannot be called when there are runnable user tasks because + * the userspace would see unexpected allocation failures as a result. Any + * new usage of this function should be consulted with MM people. + * + * Returns true if successful and false if the OOM killer cannot be + * disabled. + */ +bool oom_killer_disable(void) +{ + /* + * Make sure to not race with an ongoing OOM killer + * and that the current is not the victim. + */ + down_write(&oom_sem); + if (test_thread_flag(TIF_MEMDIE)) { + up_write(&oom_sem); + return false; + } + + oom_killer_disabled = true; + up_write(&oom_sem); + + wait_event(oom_victims_wait, !atomic_read(&oom_victims)); + + return true; +} + +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) +{ + down_write(&oom_sem); + oom_killer_disabled = false; + up_write(&oom_sem); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -637,7 +690,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) } /** - * out_of_memory - kill the "best" process when we run out of memory + * __out_of_memory - kill the "best" process when we run out of memory * @zonelist: zonelist pointer * @gfp_mask: memory allocation flags * @order: amount of memory being requested as a power of 2 @@ -649,7 +702,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *nodemask, bool force_kill) { const nodemask_t *mpol_mask; @@ -718,6 +771,32 @@ out: schedule_timeout_killable(1); } +/** + * out_of_memory - tries to invoke OOM killer. + * @zonelist: zonelist pointer + * @gfp_mask: memory allocation flags + * @order: amount of memory being requested as a power of 2 + * @nodemask: nodemask passed to page allocator + * @force_kill: true if a task must be killed, even if others are exiting + * + * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable() + * when it returns false. Otherwise returns true. + */ +bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, + int order, nodemask_t *nodemask, bool force_kill) +{ + bool ret = false; + + down_read(&oom_sem); + if (!oom_killer_disabled) { + __out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill); + ret = true; + } + up_read(&oom_sem); + + return ret; +} + /* * The pagefault handler calls here because it is out of memory, so kill a * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a @@ -727,12 +806,25 @@ void pagefault_out_of_memory(void) { struct zonelist *zonelist; + down_read(&oom_sem); if (mem_cgroup_oom_synchronize(true)) - return; + goto unlock; zonelist = node_zonelist(first_memory_node, GFP_KERNEL); if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) { - out_of_memory(NULL, 0, 0, NULL, false); + if (!oom_killer_disabled) + __out_of_memory(NULL, 0, 0, NULL, false); + else + /* + * There shouldn't be any user tasks runable while the + * OOM killer is disabled so the current task has to + * be a racing OOM victim for which oom_killer_disable() + * is waiting for. + */ + WARN_ON(test_thread_flag(TIF_MEMDIE)); + oom_zonelist_unlock(zonelist, GFP_KERNEL); } +unlock: + up_read(&oom_sem); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 641d5a9a8617..134e25525044 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -244,8 +244,6 @@ void set_pageblock_migratetype(struct page *page, int migratetype) PB_migrate, PB_migrate_end); } -bool oom_killer_disabled __read_mostly; - #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { @@ -2317,9 +2315,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, *did_some_progress = 0; - if (oom_killer_disabled) - return NULL; - /* * Acquire the per-zone oom lock for each zone. If that * fails, somebody else is making progress for us. @@ -2330,14 +2325,6 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, return NULL; } - /* - * PM-freezer should be notified that there might be an OOM killer on - * its way to kill and wake somebody up. This is too early and we might - * end up not killing anything but false positives are acceptable. - * See freeze_processes. - */ - note_oom_kill(); - /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if @@ -2372,8 +2359,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false); - *did_some_progress = 1; + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + *did_some_progress = 1; out: oom_zonelist_unlock(ac->zonelist, gfp_mask); return page; -- cgit v1.2.3 From 4155b8e0a79570d41ae77b5bf7df375bd4c36610 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:26:44 -0800 Subject: mm, asm-generic: define PUD_SHIFT in If an architecure uses , build fails if we try to use PUD_SHIFT in generic code: In file included from arch/microblaze/include/asm/bug.h:1:0, from include/linux/bug.h:4, from include/linux/thread_info.h:11, from include/asm-generic/preempt.h:4, from arch/microblaze/include/generated/asm/preempt.h:1, from include/linux/preempt.h:18, from include/linux/spinlock.h:50, from include/linux/mmzone.h:7, from include/linux/gfp.h:5, from include/linux/slab.h:14, from mm/mmap.c:12: mm/mmap.c: In function 'exit_mmap': >> mm/mmap.c:2858:46: error: 'PUD_SHIFT' undeclared (first use in this function) round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT); ^ include/asm-generic/bug.h:86:25: note: in definition of macro 'WARN_ON' int __ret_warn_on = !!(condition); \ ^ mm/mmap.c:2858:46: note: each undeclared identifier is reported only once for each function it appears in round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT); ^ include/asm-generic/bug.h:86:25: note: in definition of macro 'WARN_ON' int __ret_warn_on = !!(condition); \ ^ As with , let's define PUD_SHIFT to PGDIR_SHIFT. Signed-off-by: Kirill A. Shutemov Reported-by: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/4level-fixup.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 77ff547730af..5bdab6bffd23 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -4,6 +4,7 @@ #define __ARCH_HAS_4LEVEL_HACK #define __PAGETABLE_PUD_FOLDED +#define PUD_SHIFT PGDIR_SHIFT #define PUD_SIZE PGDIR_SIZE #define PUD_MASK PGDIR_MASK #define PTRS_PER_PUD 1 -- cgit v1.2.3 From dc6c9a35b66b520cf67e05d8ca60ebecad3b0479 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 11 Feb 2015 15:26:50 -0800 Subject: mm: account pmd page tables to the process Dave noticed that unprivileged process can allocate significant amount of memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and memory cgroup. The trick is to allocate a lot of PMD page tables. Linux kernel doesn't account PMD tables to the process, only PTE. The use-cases below use few tricks to allocate a lot of PMD page tables while keeping VmRSS and VmPTE low. oom_score for the process will be 0. #include #include #include #include #include #include #define PUD_SIZE (1UL << 30) #define PMD_SIZE (1UL << 21) #define NR_PUD 130000 int main(void) { char *addr = NULL; unsigned long i; prctl(PR_SET_THP_DISABLE); for (i = 0; i < NR_PUD ; i++) { addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0); if (addr == MAP_FAILED) { perror("mmap"); break; } *addr = 'x'; munmap(addr, PMD_SIZE); mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ, MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0); if (addr == MAP_FAILED) perror("re-mmap"), exit(1); } printf("PID %d consumed %lu KiB in PMD page tables\n", getpid(), i * 4096 >> 10); return pause(); } The patch addresses the issue by account PMD tables to the process the same way we account PTE. The main place where PMD tables is accounted is __pmd_alloc() and free_pmd_range(). But there're few corner cases: - HugeTLB can share PMD page tables. The patch handles by accounting the table to all processes who share it. - x86 PAE pre-allocates few PMD tables on fork. - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity check on exit(2). Accounting only happens on configuration where PMD page table's level is present (PMD is not folded). As with nr_ptes we use per-mm counter. The counter value is used to calculate baseline for badness score by oom-killer. Signed-off-by: Kirill A. Shutemov Reported-by: Dave Hansen Cc: Hugh Dickins Reviewed-by: Cyrill Gorcunov Cc: Pavel Emelyanov Cc: David Rientjes Tested-by: Sedat Dilek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 12 ++++++------ arch/x86/mm/pgtable.c | 14 +++++++++----- fs/proc/task_mmu.c | 9 ++++++--- include/linux/mm.h | 24 ++++++++++++++++++++++++ include/linux/mm_types.h | 3 ++- kernel/fork.c | 3 +++ mm/debug.c | 3 ++- mm/hugetlb.c | 8 ++++++-- mm/memory.c | 15 +++++++++------ mm/mmap.c | 4 +++- mm/oom_kill.c | 9 +++++---- 11 files changed, 75 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 4415aa915681..e9c706e4627a 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -555,12 +555,12 @@ this is causing problems for your system/application. oom_dump_tasks -Enables a system-wide task dump (excluding kernel threads) to be -produced when the kernel performs an OOM-killing and includes such -information as pid, uid, tgid, vm size, rss, nr_ptes, swapents, -oom_score_adj score, and name. This is helpful to determine why the -OOM killer was invoked, to identify the rogue task that caused it, -and to determine why the OOM killer chose the task it did to kill. +Enables a system-wide task dump (excluding kernel threads) to be produced +when the kernel performs an OOM-killing and includes such information as +pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, swapents, oom_score_adj +score, and name. This is helpful to determine why the OOM killer was +invoked, to identify the rogue task that caused it, and to determine why +the OOM killer chose the task it did to kill. If this is set to zero, this information is suppressed. On very large systems with thousands of tasks it may not be feasible to dump diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 6fb6927f9e76..7b22adaad4f1 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd) #endif /* CONFIG_X86_PAE */ -static void free_pmds(pmd_t *pmds[]) +static void free_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; @@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[]) if (pmds[i]) { pgtable_pmd_page_dtor(virt_to_page(pmds[i])); free_page((unsigned long)pmds[i]); + mm_dec_nr_pmds(mm); } } -static int preallocate_pmds(pmd_t *pmds[]) +static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[]) { int i; bool failed = false; @@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[]) pmd = NULL; failed = true; } + if (pmd) + mm_inc_nr_pmds(mm); pmds[i] = pmd; } if (failed) { - free_pmds(pmds); + free_pmds(mm, pmds); return -ENOMEM; } @@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); + mm_dec_nr_pmds(mm); } } } @@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) mm->pgd = pgd; - if (preallocate_pmds(pmds) != 0) + if (preallocate_pmds(mm, pmds) != 0) goto out_free_pgd; if (paravirt_pgd_alloc(mm) != 0) @@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; out_free_pmds: - free_pmds(pmds); + free_pmds(mm, pmds); out_free_pgd: free_page((unsigned long)pgd); out: diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6396f88c6687..e6e0abeb5d12 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -21,7 +21,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) { - unsigned long data, text, lib, swap; + unsigned long data, text, lib, swap, ptes, pmds; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; /* @@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10; lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text; swap = get_mm_counter(mm, MM_SWAPENTS); + ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes); + pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm); seq_printf(m, "VmPeak:\t%8lu kB\n" "VmSize:\t%8lu kB\n" @@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmExe:\t%8lu kB\n" "VmLib:\t%8lu kB\n" "VmPTE:\t%8lu kB\n" + "VmPMD:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), total_vm << (PAGE_SHIFT-10), @@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) total_rss << (PAGE_SHIFT-10), data << (PAGE_SHIFT-10), mm->stack_vm << (PAGE_SHIFT-10), text, lib, - (PTRS_PER_PTE * sizeof(pte_t) * - atomic_long_read(&mm->nr_ptes)) >> 10, + ptes >> 10, + pmds >> 10, swap << (PAGE_SHIFT-10)); } diff --git a/include/linux/mm.h b/include/linux/mm.h index c6bf813a6b3d..644990b83cda 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, { return 0; } + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return 0; +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) {} +static inline void mm_dec_nr_pmds(struct mm_struct *mm) {} + #else int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); + +static inline unsigned long mm_nr_pmds(struct mm_struct *mm) +{ + return atomic_long_read(&mm->nr_pmds); +} + +static inline void mm_inc_nr_pmds(struct mm_struct *mm) +{ + atomic_long_inc(&mm->nr_pmds); +} + +static inline void mm_dec_nr_pmds(struct mm_struct *mm) +{ + atomic_long_dec(&mm->nr_pmds); +} #endif int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 20ff2105b564..199a03aab8dc 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -363,7 +363,8 @@ struct mm_struct { pgd_t * pgd; atomic_t mm_users; /* How many users with user space? */ atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ - atomic_long_t nr_ptes; /* Page table pages */ + atomic_long_t nr_ptes; /* PTE page table pages */ + atomic_long_t nr_pmds; /* PMD page table pages */ int map_count; /* number of VMAs */ spinlock_t page_table_lock; /* Protects page tables and some counters */ diff --git a/kernel/fork.c b/kernel/fork.c index b379d9abddc7..c99098c52641 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -555,6 +555,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) INIT_LIST_HEAD(&mm->mmlist); mm->core_state = NULL; atomic_long_set(&mm->nr_ptes, 0); +#ifndef __PAGETABLE_PMD_FOLDED + atomic_long_set(&mm->nr_pmds, 0); +#endif mm->map_count = 0; mm->locked_vm = 0; mm->pinned_vm = 0; diff --git a/mm/debug.c b/mm/debug.c index d69cb5a7ba9a..3eb3ac2fcee7 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -173,7 +173,7 @@ void dump_mm(const struct mm_struct *mm) "get_unmapped_area %p\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n" + "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" @@ -206,6 +206,7 @@ void dump_mm(const struct mm_struct *mm) mm->pgd, atomic_read(&mm->mm_users), atomic_read(&mm->mm_count), atomic_long_read((atomic_long_t *)&mm->nr_ptes), + mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index fd28d6ba5e5d..0a9ac6c26832 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3598,6 +3598,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { + mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -3609,11 +3610,13 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); spin_lock(ptl); - if (pud_none(*pud)) + if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else + } else { put_page(virt_to_page(spte)); + mm_inc_nr_pmds(mm); + } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -3644,6 +3647,7 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); + mm_dec_nr_pmds(mm); *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } diff --git a/mm/memory.c b/mm/memory.c index d63849b5188f..bbe6a73a899d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -3322,15 +3323,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) /* Another has populated it */ - pmd_free(mm, new); - else + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); -#else - if (pgd_present(*pud)) /* Another has populated it */ + } else /* Another has populated it */ pmd_free(mm, new); - else +#else + if (!pgd_present(*pud)) { + mm_inc_nr_pmds(mm); pgd_populate(mm, pud, new); + } else /* Another has populated it */ + pmd_free(mm, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; diff --git a/mm/mmap.c b/mm/mmap.c index 14d84666e8ba..6a7d36d133fb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2853,7 +2853,9 @@ void exit_mmap(struct mm_struct *mm) vm_unacct_memory(nr_accounted); WARN_ON(atomic_long_read(&mm->nr_ptes) > - (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); + round_up(FIRST_USER_ADDRESS, PMD_SIZE) >> PMD_SHIFT); + WARN_ON(mm_nr_pmds(mm) > + round_up(FIRST_USER_ADDRESS, PUD_SIZE) >> PUD_SHIFT); } /* Insert vm structure into process list sorted by address diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b8df76ee2be3..642f38cb175a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -169,8 +169,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + - get_mm_counter(p->mm, MM_SWAPENTS); + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm); task_unlock(p); /* @@ -351,7 +351,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n"); rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) @@ -367,10 +367,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), atomic_long_read(&task->mm->nr_ptes), + mm_nr_pmds(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); -- cgit v1.2.3 From 4645f06334be1ad0eb61aa182c7999fe51bc1ba6 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:26:58 -0800 Subject: mm/compaction: change tracepoint format from decimal to hexadecimal To check the range that compaction is working, tracepoint print start/end pfn of zone and start pfn of both scanner with decimal format. Since we manage all pages in order of 2 and it is well represented by hexadecimal, this patch change the tracepoint format from decimal to hexadecimal. This would improve readability. For example, it makes us easily notice whether current scanner try to compact previously attempted pageblock or not. Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/compaction.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index c6814b917bdf..1337d9e01e3d 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -104,7 +104,7 @@ TRACE_EVENT(mm_compaction_begin, __entry->zone_end = zone_end; ), - TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu", + TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx", __entry->zone_start, __entry->migrate_start, __entry->free_start, -- cgit v1.2.3 From 16c4a097a035c01809aa0c0abd458ca1fe4ff3d0 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:01 -0800 Subject: mm/compaction: enhance tracepoint output for compaction begin/end We now have tracepoint for begin event of compaction and it prints start position of both scanners, but, tracepoint for end event of compaction doesn't print finish position of both scanners. It'd be also useful to know finish position of both scanners so this patch add it. It will help to find odd behavior or problem on compaction internal logic. And mode is added to both begin/end tracepoint output, since according to mode, compaction behavior is quite different. And lastly, status format is changed to string rather than status number for readability. [akpm@linux-foundation.org: fix sparse warning] Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 1 + include/trace/events/compaction.h | 49 ++++++++++++++++++++++++++++----------- mm/compaction.c | 15 ++++++++++-- 3 files changed, 49 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index f2efda2e6ac6..db64cae06530 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,7 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ /* No contention detected */ diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 1337d9e01e3d..839f6fac921a 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -85,46 +85,67 @@ TRACE_EVENT(mm_compaction_migratepages, ); TRACE_EVENT(mm_compaction_begin, - TP_PROTO(unsigned long zone_start, unsigned long migrate_start, - unsigned long free_start, unsigned long zone_end), + TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, + unsigned long free_pfn, unsigned long zone_end, bool sync), - TP_ARGS(zone_start, migrate_start, free_start, zone_end), + TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync), TP_STRUCT__entry( __field(unsigned long, zone_start) - __field(unsigned long, migrate_start) - __field(unsigned long, free_start) + __field(unsigned long, migrate_pfn) + __field(unsigned long, free_pfn) __field(unsigned long, zone_end) + __field(bool, sync) ), TP_fast_assign( __entry->zone_start = zone_start; - __entry->migrate_start = migrate_start; - __entry->free_start = free_start; + __entry->migrate_pfn = migrate_pfn; + __entry->free_pfn = free_pfn; __entry->zone_end = zone_end; + __entry->sync = sync; ), - TP_printk("zone_start=0x%lx migrate_start=0x%lx free_start=0x%lx zone_end=0x%lx", + TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s", __entry->zone_start, - __entry->migrate_start, - __entry->free_start, - __entry->zone_end) + __entry->migrate_pfn, + __entry->free_pfn, + __entry->zone_end, + __entry->sync ? "sync" : "async") ); TRACE_EVENT(mm_compaction_end, - TP_PROTO(int status), + TP_PROTO(unsigned long zone_start, unsigned long migrate_pfn, + unsigned long free_pfn, unsigned long zone_end, bool sync, + int status), - TP_ARGS(status), + TP_ARGS(zone_start, migrate_pfn, free_pfn, zone_end, sync, status), TP_STRUCT__entry( + __field(unsigned long, zone_start) + __field(unsigned long, migrate_pfn) + __field(unsigned long, free_pfn) + __field(unsigned long, zone_end) + __field(bool, sync) __field(int, status) ), TP_fast_assign( + __entry->zone_start = zone_start; + __entry->migrate_pfn = migrate_pfn; + __entry->free_pfn = free_pfn; + __entry->zone_end = zone_end; + __entry->sync = sync; __entry->status = status; ), - TP_printk("status=%d", __entry->status) + TP_printk("zone_start=0x%lx migrate_pfn=0x%lx free_pfn=0x%lx zone_end=0x%lx, mode=%s status=%s", + __entry->zone_start, + __entry->migrate_pfn, + __entry->free_pfn, + __entry->zone_end, + __entry->sync ? "sync" : "async", + compaction_status_string[__entry->status]) ); #endif /* _TRACE_COMPACTION_H */ diff --git a/mm/compaction.c b/mm/compaction.c index 9c7e6909dd29..66f7c365e888 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -34,6 +34,15 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA +#ifdef CONFIG_TRACEPOINTS +static const char *const compaction_status_string[] = { + "deferred", + "skipped", + "continue", + "partial", + "complete", +}; +#endif #define CREATE_TRACE_POINTS #include @@ -1197,7 +1206,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } - trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync); migrate_prep_local(); @@ -1299,7 +1309,8 @@ out: zone->compact_cached_free_pfn = free_pfn; } - trace_mm_compaction_end(ret); + trace_mm_compaction_end(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync, ret); return ret; } -- cgit v1.2.3 From e34d85f0e3c60f7226e5589898b7c7c5cd2a4f02 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:04 -0800 Subject: mm/compaction: print current range where compaction work It'd be useful to know current range where compaction work for detailed analysis. With it, we can know pageblock where we actually scan and isolate, and, how much pages we try in that pageblock and can guess why it doesn't become freepage with pageblock order roughly. Signed-off-by: Joonsoo Kim Acked-by: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/compaction.h | 30 +++++++++++++++++++++++------- mm/compaction.c | 9 ++++++--- 2 files changed, 29 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 839f6fac921a..139020b55612 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -11,39 +11,55 @@ DECLARE_EVENT_CLASS(mm_compaction_isolate_template, - TP_PROTO(unsigned long nr_scanned, + TP_PROTO( + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long nr_scanned, unsigned long nr_taken), - TP_ARGS(nr_scanned, nr_taken), + TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken), TP_STRUCT__entry( + __field(unsigned long, start_pfn) + __field(unsigned long, end_pfn) __field(unsigned long, nr_scanned) __field(unsigned long, nr_taken) ), TP_fast_assign( + __entry->start_pfn = start_pfn; + __entry->end_pfn = end_pfn; __entry->nr_scanned = nr_scanned; __entry->nr_taken = nr_taken; ), - TP_printk("nr_scanned=%lu nr_taken=%lu", + TP_printk("range=(0x%lx ~ 0x%lx) nr_scanned=%lu nr_taken=%lu", + __entry->start_pfn, + __entry->end_pfn, __entry->nr_scanned, __entry->nr_taken) ); DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_migratepages, - TP_PROTO(unsigned long nr_scanned, + TP_PROTO( + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long nr_scanned, unsigned long nr_taken), - TP_ARGS(nr_scanned, nr_taken) + TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken) ); DEFINE_EVENT(mm_compaction_isolate_template, mm_compaction_isolate_freepages, - TP_PROTO(unsigned long nr_scanned, + + TP_PROTO( + unsigned long start_pfn, + unsigned long end_pfn, + unsigned long nr_scanned, unsigned long nr_taken), - TP_ARGS(nr_scanned, nr_taken) + TP_ARGS(start_pfn, end_pfn, nr_scanned, nr_taken) ); TRACE_EVENT(mm_compaction_migratepages, diff --git a/mm/compaction.c b/mm/compaction.c index 66f7c365e888..b12df9fe10b4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -430,11 +430,12 @@ isolate_fail: } + trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn, + nr_scanned, total_isolated); + /* Record how far we have got within the block */ *start_pfn = blockpfn; - trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); - /* * If strict isolation is requested by CMA then check that all the * pages requested were isolated. If there were any failures, 0 is @@ -590,6 +591,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long flags = 0; bool locked = false; struct page *page = NULL, *valid_page = NULL; + unsigned long start_pfn = low_pfn; /* * Ensure that there are not too many pages isolated from the LRU @@ -750,7 +752,8 @@ isolate_success: if (low_pfn == end_pfn) update_pageblock_skip(cc, valid_page, nr_isolated, true); - trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); + trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, + nr_scanned, nr_isolated); count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned); if (nr_isolated) -- cgit v1.2.3 From 837d026d560c5ef26abeca0441713d82e4e82cad Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:06 -0800 Subject: mm/compaction: more trace to understand when/why compaction start/finish It is not well analyzed that when/why compaction start/finish or not. With these new tracepoints, we can know much more about start/finish reason of compaction. I can find following bug with these tracepoint. http://www.spinics.net/lists/linux-mm/msg81582.html Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 3 ++ include/trace/events/compaction.h | 74 +++++++++++++++++++++++++++++++++++++++ mm/compaction.c | 38 +++++++++++++++++--- 3 files changed, 111 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index db64cae06530..501d7513aac1 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -12,6 +12,9 @@ #define COMPACT_PARTIAL 3 /* The full zone was compacted */ #define COMPACT_COMPLETE 4 +/* For more detailed tracepoint output */ +#define COMPACT_NO_SUITABLE_PAGE 5 +#define COMPACT_NOT_SUITABLE_ZONE 6 /* When adding new state, please change compaction_status_string, too */ /* Used to signal whether compaction detected need_sched() or lock contention */ diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index 139020b55612..d46535801f63 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -164,6 +164,80 @@ TRACE_EVENT(mm_compaction_end, compaction_status_string[__entry->status]) ); +TRACE_EVENT(mm_compaction_try_to_compact_pages, + + TP_PROTO( + int order, + gfp_t gfp_mask, + enum migrate_mode mode), + + TP_ARGS(order, gfp_mask, mode), + + TP_STRUCT__entry( + __field(int, order) + __field(gfp_t, gfp_mask) + __field(enum migrate_mode, mode) + ), + + TP_fast_assign( + __entry->order = order; + __entry->gfp_mask = gfp_mask; + __entry->mode = mode; + ), + + TP_printk("order=%d gfp_mask=0x%x mode=%d", + __entry->order, + __entry->gfp_mask, + (int)__entry->mode) +); + +DECLARE_EVENT_CLASS(mm_compaction_suitable_template, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret), + + TP_STRUCT__entry( + __field(int, nid) + __field(char *, name) + __field(int, order) + __field(int, ret) + ), + + TP_fast_assign( + __entry->nid = zone_to_nid(zone); + __entry->name = (char *)zone->name; + __entry->order = order; + __entry->ret = ret; + ), + + TP_printk("node=%d zone=%-8s order=%d ret=%s", + __entry->nid, + __entry->name, + __entry->order, + compaction_status_string[__entry->ret]) +); + +DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_finished, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret) +); + +DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable, + + TP_PROTO(struct zone *zone, + int order, + int ret), + + TP_ARGS(zone, order, ret) +); + #endif /* _TRACE_COMPACTION_H */ /* This part must be outside protection */ diff --git a/mm/compaction.c b/mm/compaction.c index b12df9fe10b4..b6ede459c1bb 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -41,6 +41,8 @@ static const char *const compaction_status_string[] = { "continue", "partial", "complete", + "no_suitable_page", + "not_suitable_zone", }; #endif @@ -1049,7 +1051,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } -static int compact_finished(struct zone *zone, struct compact_control *cc, +static int __compact_finished(struct zone *zone, struct compact_control *cc, const int migratetype) { unsigned int order; @@ -1104,7 +1106,20 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, return COMPACT_PARTIAL; } - return COMPACT_CONTINUE; + return COMPACT_NO_SUITABLE_PAGE; +} + +static int compact_finished(struct zone *zone, struct compact_control *cc, + const int migratetype) +{ + int ret; + + ret = __compact_finished(zone, cc, migratetype); + trace_mm_compaction_finished(zone, cc->order, ret); + if (ret == COMPACT_NO_SUITABLE_PAGE) + ret = COMPACT_CONTINUE; + + return ret; } /* @@ -1114,7 +1129,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, * COMPACT_PARTIAL - If the allocation would succeed without compaction * COMPACT_CONTINUE - If compaction should run now */ -unsigned long compaction_suitable(struct zone *zone, int order, +static unsigned long __compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx) { int fragindex; @@ -1158,11 +1173,24 @@ unsigned long compaction_suitable(struct zone *zone, int order, */ fragindex = fragmentation_index(zone, order); if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - return COMPACT_SKIPPED; + return COMPACT_NOT_SUITABLE_ZONE; return COMPACT_CONTINUE; } +unsigned long compaction_suitable(struct zone *zone, int order, + int alloc_flags, int classzone_idx) +{ + unsigned long ret; + + ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx); + trace_mm_compaction_suitable(zone, order, ret); + if (ret == COMPACT_NOT_SUITABLE_ZONE) + ret = COMPACT_SKIPPED; + + return ret; +} + static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; @@ -1376,6 +1404,8 @@ unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, if (!order || !may_enter_fs || !may_perform_io) return COMPACT_SKIPPED; + trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode); + /* Compact each zone in the list */ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, ac->nodemask) { -- cgit v1.2.3 From 24e2716f63e613cf15d3beba3faa0711bcacc427 Mon Sep 17 00:00:00 2001 From: Joonsoo Kim Date: Wed, 11 Feb 2015 15:27:09 -0800 Subject: mm/compaction: add tracepoint to observe behaviour of compaction defer Compaction deferring logic is heavy hammer that block the way to the compaction. It doesn't consider overall system state, so it could prevent user from doing compaction falsely. In other words, even if system has enough range of memory to compact, compaction would be skipped due to compaction deferring logic. This patch add new tracepoint to understand work of deferring logic. This will also help to check compaction success and fail. Signed-off-by: Joonsoo Kim Cc: Vlastimil Babka Cc: Mel Gorman Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compaction.h | 65 +++-------------------------------- include/trace/events/compaction.h | 56 ++++++++++++++++++++++++++++++ mm/compaction.c | 71 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 132 insertions(+), 60 deletions(-) (limited to 'include') diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 501d7513aac1..a014559e4a49 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -44,66 +44,11 @@ extern void reset_isolation_suitable(pg_data_t *pgdat); extern unsigned long compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx); -/* Do not skip compaction more than 64 times */ -#define COMPACT_MAX_DEFER_SHIFT 6 - -/* - * Compaction is deferred when compaction fails to result in a page - * allocation success. 1 << compact_defer_limit compactions are skipped up - * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT - */ -static inline void defer_compaction(struct zone *zone, int order) -{ - zone->compact_considered = 0; - zone->compact_defer_shift++; - - if (order < zone->compact_order_failed) - zone->compact_order_failed = order; - - if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) - zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; -} - -/* Returns true if compaction should be skipped this time */ -static inline bool compaction_deferred(struct zone *zone, int order) -{ - unsigned long defer_limit = 1UL << zone->compact_defer_shift; - - if (order < zone->compact_order_failed) - return false; - - /* Avoid possible overflow */ - if (++zone->compact_considered > defer_limit) - zone->compact_considered = defer_limit; - - return zone->compact_considered < defer_limit; -} - -/* - * Update defer tracking counters after successful compaction of given order, - * which means an allocation either succeeded (alloc_success == true) or is - * expected to succeed. - */ -static inline void compaction_defer_reset(struct zone *zone, int order, - bool alloc_success) -{ - if (alloc_success) { - zone->compact_considered = 0; - zone->compact_defer_shift = 0; - } - if (order >= zone->compact_order_failed) - zone->compact_order_failed = order + 1; -} - -/* Returns true if restarting compaction after many failures */ -static inline bool compaction_restarting(struct zone *zone, int order) -{ - if (order < zone->compact_order_failed) - return false; - - return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && - zone->compact_considered >= 1UL << zone->compact_defer_shift; -} +extern void defer_compaction(struct zone *zone, int order); +extern bool compaction_deferred(struct zone *zone, int order); +extern void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success); +extern bool compaction_restarting(struct zone *zone, int order); #else static inline unsigned long try_to_compact_pages(gfp_t gfp_mask, diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index d46535801f63..9a6a3fe0fb51 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -238,6 +238,62 @@ DEFINE_EVENT(mm_compaction_suitable_template, mm_compaction_suitable, TP_ARGS(zone, order, ret) ); +#ifdef CONFIG_COMPACTION +DECLARE_EVENT_CLASS(mm_compaction_defer_template, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order), + + TP_STRUCT__entry( + __field(int, nid) + __field(char *, name) + __field(int, order) + __field(unsigned int, considered) + __field(unsigned int, defer_shift) + __field(int, order_failed) + ), + + TP_fast_assign( + __entry->nid = zone_to_nid(zone); + __entry->name = (char *)zone->name; + __entry->order = order; + __entry->considered = zone->compact_considered; + __entry->defer_shift = zone->compact_defer_shift; + __entry->order_failed = zone->compact_order_failed; + ), + + TP_printk("node=%d zone=%-8s order=%d order_failed=%d consider=%u limit=%lu", + __entry->nid, + __entry->name, + __entry->order, + __entry->order_failed, + __entry->considered, + 1UL << __entry->defer_shift) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_deferred, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_compaction, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); + +DEFINE_EVENT(mm_compaction_defer_template, mm_compaction_defer_reset, + + TP_PROTO(struct zone *zone, int order), + + TP_ARGS(zone, order) +); +#endif + #endif /* _TRACE_COMPACTION_H */ /* This part must be outside protection */ diff --git a/mm/compaction.c b/mm/compaction.c index b6ede459c1bb..b68736c8a1ce 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -124,6 +124,77 @@ static struct page *pageblock_pfn_to_page(unsigned long start_pfn, } #ifdef CONFIG_COMPACTION + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * allocation success. 1 << compact_defer_limit compactions are skipped up + * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT + */ +void defer_compaction(struct zone *zone, int order) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + if (order < zone->compact_order_failed) + zone->compact_order_failed = order; + + if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) + zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; + + trace_mm_compaction_defer_compaction(zone, order); +} + +/* Returns true if compaction should be skipped this time */ +bool compaction_deferred(struct zone *zone, int order) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + if (order < zone->compact_order_failed) + return false; + + /* Avoid possible overflow */ + if (++zone->compact_considered > defer_limit) + zone->compact_considered = defer_limit; + + if (zone->compact_considered >= defer_limit) + return false; + + trace_mm_compaction_deferred(zone, order); + + return true; +} + +/* + * Update defer tracking counters after successful compaction of given order, + * which means an allocation either succeeded (alloc_success == true) or is + * expected to succeed. + */ +void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success) +{ + if (alloc_success) { + zone->compact_considered = 0; + zone->compact_defer_shift = 0; + } + if (order >= zone->compact_order_failed) + zone->compact_order_failed = order + 1; + + trace_mm_compaction_defer_reset(zone, order); +} + +/* Returns true if restarting compaction after many failures */ +bool compaction_restarting(struct zone *zone, int order) +{ + if (order < zone->compact_order_failed) + return false; + + return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && + zone->compact_considered >= 1UL << zone->compact_defer_shift; +} + /* Returns true if the pageblock should be scanned for pages to isolate. */ static inline bool isolation_suitable(struct compact_control *cc, struct page *page) -- cgit v1.2.3 From 077fcf116c8c2bd7ee9487b645aa3b50368db7e1 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 11 Feb 2015 15:27:12 -0800 Subject: mm/thp: allocate transparent hugepages on local node This make sure that we try to allocate hugepages from local node if allowed by mempolicy. If we can't, we fallback to small page allocation based on mempolicy. This is based on the observation that allocating pages on local node is more beneficial than allocating hugepages on remote node. With this patch applied we may find transparent huge page allocation failures if the current node doesn't have enough freee hugepages. Before this patch such failures result in us retrying the allocation on other nodes in the numa node mask. [akpm@linux-foundation.org: fix comment, add CONFIG_TRANSPARENT_HUGEPAGE dependency] Signed-off-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++ mm/huge_memory.c | 24 +++++++----------- mm/mempolicy.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 85 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b840e3b2770d..60110e06419d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -335,11 +335,15 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node); +extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) #define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ alloc_pages(gfp_mask, order) +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 889713180980..0531ea7dd7cf 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -761,15 +761,6 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp) return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp; } -static inline struct page *alloc_hugepage_vma(int defrag, - struct vm_area_struct *vma, - unsigned long haddr, int nd, - gfp_t extra_gfp) -{ - return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp), - HPAGE_PMD_ORDER, vma, haddr, nd); -} - /* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, @@ -790,6 +781,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { + gfp_t gfp; struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; @@ -824,8 +816,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, } return 0; } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1113,10 +1105,12 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && - !transparent_hugepage_debug_cow()) - new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - else + !transparent_hugepage_debug_cow()) { + gfp_t gfp; + + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + } else new_page = NULL; if (unlikely(!new_page)) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e0961b8c39c..8a32873fdbf7 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2030,6 +2030,78 @@ retry_cpuset: return page; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/** + * alloc_hugepage_vma: Allocate a hugepage for a VMA + * @gfp: + * %GFP_USER user allocation. + * %GFP_KERNEL kernel allocations, + * %GFP_HIGHMEM highmem/user allocations, + * %GFP_FS allocation should not call back into a file system. + * %GFP_ATOMIC don't sleep. + * + * @vma: Pointer to VMA or NULL if not available. + * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @order: Order of the hugepage for gfp allocation. + * + * This functions allocate a huge page from the kernel page pool and applies + * a NUMA policy associated with the VMA or the current process. + * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage + * only from the current node if the current node is part of the node mask. + * If we can't allocate a hugepage we fail the allocation and don' try to fallback + * to other nodes in the node mask. If the current node is not part of node mask + * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can + * fallback to nodes in the policy node mask. + * + * When VMA is not NULL caller must hold down_read on the mmap_sem of the + * mm_struct of the VMA to prevent it from going away. Should be used for + * all allocations for pages that will be mapped into + * user space. Returns NULL when no page can be allocated. + * + * Should be called with vma->vm_mm->mmap_sem held. + * + */ +struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, + unsigned long addr, int order) +{ + struct page *page; + nodemask_t *nmask; + struct mempolicy *pol; + int node = numa_node_id(); + unsigned int cpuset_mems_cookie; + +retry_cpuset: + pol = get_vma_policy(vma, addr); + cpuset_mems_cookie = read_mems_allowed_begin(); + /* + * For interleave policy, we don't worry about + * current node. Otherwise if current node is + * in nodemask, try to allocate hugepage from + * the current node. Don't fall back to other nodes + * for THP. + */ + if (unlikely(pol->mode == MPOL_INTERLEAVE)) + goto alloc_with_fallback; + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + if (unlikely(!page && + read_mems_allowed_retry(cpuset_mems_cookie))) + goto retry_cpuset; + return page; + } +alloc_with_fallback: + mpol_cond_put(pol); + /* + * if current node is not part of node mask, try + * the allocation from any node, and we can do retry + * in that case. + */ + return alloc_pages_vma(gfp, order, vma, addr, node); +} +#endif + /** * alloc_pages_current - Allocate pages. * -- cgit v1.2.3 From be97a41b291e495d6cb767b3ee0f84ed05804892 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:27:15 -0800 Subject: mm/mempolicy.c: merge alloc_hugepage_vma to alloc_pages_vma The previous commit ("mm/thp: Allocate transparent hugepages on local node") introduced alloc_hugepage_vma() to mm/mempolicy.c to perform a special policy for THP allocations. The function has the same interface as alloc_pages_vma(), shares a lot of boilerplate code and a long comment. This patch merges the hugepage special case into alloc_pages_vma. The extra if condition should be cheap enough price to pay. We also prevent a (however unlikely) race with parallel mems_allowed update, which could make hugepage allocation restart only within the fallback call to alloc_hugepage_vma() and not reconsider the special rule in alloc_hugepage_vma(). Also by making sure mpol_cond_put(pol) is always called before actual allocation attempt, we can use a single exit path within the function. Also update the comment for missing node parameter and obsolete reference to mm_sem. Signed-off-by: Vlastimil Babka Cc: Aneesh Kumar K.V Cc: Kirill A. Shutemov Cc: Vlastimil Babka Cc: David Rientjes Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 +++--- mm/mempolicy.c | 118 +++++++++++++++------------------------------------- 2 files changed, 39 insertions(+), 91 deletions(-) (limited to 'include') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 60110e06419d..51bd1e72a917 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -334,22 +334,22 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node); -extern struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, - unsigned long addr, int order); + int node, bool hugepage); +#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ + alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node) + alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) extern struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order); extern struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8a32873fdbf7..acbbf4c821e2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1988,120 +1988,68 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must hold down_read on the mmap_sem of the * mm_struct of the VMA to prevent it from going away. Should be used for - * all allocations for pages that will be mapped into - * user space. Returns NULL when no page can be allocated. - * - * Should be called with the mm_sem of the vma hold. + * all allocations for pages that will be mapped into user space. Returns + * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; unsigned int cpuset_mems_cookie; + struct zonelist *zl; + nodemask_t *nmask; retry_cpuset: pol = get_vma_policy(vma, addr); cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(pol->mode == MPOL_INTERLEAVE)) { + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage && + pol->mode != MPOL_INTERLEAVE)) { + /* + * For hugepage allocation and non-interleave policy which + * allows the current node, we only try to allocate from the + * current node and don't fall back to other nodes, as the + * cost of remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + goto out; + } + } + + if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - - return page; + goto out; } - page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol, node), - policy_nodemask(gfp, pol)); + + nmask = policy_nodemask(gfp, pol); + zl = policy_zonelist(gfp, pol, node); mpol_cond_put(pol); + page = __alloc_pages_nodemask(gfp, order, zl, nmask); +out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; } -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -/** - * alloc_hugepage_vma: Allocate a hugepage for a VMA - * @gfp: - * %GFP_USER user allocation. - * %GFP_KERNEL kernel allocations, - * %GFP_HIGHMEM highmem/user allocations, - * %GFP_FS allocation should not call back into a file system. - * %GFP_ATOMIC don't sleep. - * - * @vma: Pointer to VMA or NULL if not available. - * @addr: Virtual Address of the allocation. Must be inside the VMA. - * @order: Order of the hugepage for gfp allocation. - * - * This functions allocate a huge page from the kernel page pool and applies - * a NUMA policy associated with the VMA or the current process. - * For policy other than %MPOL_INTERLEAVE, we make sure we allocate hugepage - * only from the current node if the current node is part of the node mask. - * If we can't allocate a hugepage we fail the allocation and don' try to fallback - * to other nodes in the node mask. If the current node is not part of node mask - * or if the NUMA policy is MPOL_INTERLEAVE we use the allocator that can - * fallback to nodes in the policy node mask. - * - * When VMA is not NULL caller must hold down_read on the mmap_sem of the - * mm_struct of the VMA to prevent it from going away. Should be used for - * all allocations for pages that will be mapped into - * user space. Returns NULL when no page can be allocated. - * - * Should be called with vma->vm_mm->mmap_sem held. - * - */ -struct page *alloc_hugepage_vma(gfp_t gfp, struct vm_area_struct *vma, - unsigned long addr, int order) -{ - struct page *page; - nodemask_t *nmask; - struct mempolicy *pol; - int node = numa_node_id(); - unsigned int cpuset_mems_cookie; - -retry_cpuset: - pol = get_vma_policy(vma, addr); - cpuset_mems_cookie = read_mems_allowed_begin(); - /* - * For interleave policy, we don't worry about - * current node. Otherwise if current node is - * in nodemask, try to allocate hugepage from - * the current node. Don't fall back to other nodes - * for THP. - */ - if (unlikely(pol->mode == MPOL_INTERLEAVE)) - goto alloc_with_fallback; - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(node, *nmask)) { - mpol_cond_put(pol); - page = alloc_pages_exact_node(node, gfp, order); - if (unlikely(!page && - read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - return page; - } -alloc_with_fallback: - mpol_cond_put(pol); - /* - * if current node is not part of node mask, try - * the allocation from any node, and we can do retry - * in that case. - */ - return alloc_pages_vma(gfp, order, vma, addr, node); -} -#endif - /** * alloc_pages_current - Allocate pages. * -- cgit v1.2.3 From f0818f472d8d527a96ec9cc2c3a56223497f9dd3 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:17 -0800 Subject: mm: gup: add get_user_pages_locked and get_user_pages_unlocked FAULT_FOLL_ALLOW_RETRY allows the page fault to drop the mmap_sem for reading to reduce the mmap_sem contention (for writing), like while waiting for I/O completion. The problem is that right now practically no get_user_pages call uses FAULT_FOLL_ALLOW_RETRY, so we're not leveraging that nifty feature. Andres fixed it for the KVM page fault. However get_user_pages_fast remains uncovered, and 99% of other get_user_pages aren't using it either (the only exception being FOLL_NOWAIT in KVM which is really nonblocking and in fact it doesn't even release the mmap_sem). So this patchsets extends the optimization Andres did in the KVM page fault to the whole kernel. It makes most important places (including gup_fast) to use FAULT_FOLL_ALLOW_RETRY to reduce the mmap_sem hold times during I/O. The only few places that remains uncovered are drivers like v4l and other exceptions that tends to work on their own memory and they're not working on random user memory (for example like O_DIRECT that uses gup_fast and is fully covered by this patch). A follow up patch should probably also add a printk_once warning to get_user_pages that should go obsolete and be phased out eventually. The "vmas" parameter of get_user_pages makes it fundamentally incompatible with FAULT_FOLL_ALLOW_RETRY (vmas array becomes meaningless the moment the mmap_sem is released). While this is just an optimization, this becomes an absolute requirement for the userfaultfd feature http://lwn.net/Articles/615086/ . The userfaultfd allows to block the page fault, and in order to do so I need to drop the mmap_sem first. So this patch also ensures that all memory where userfaultfd could be registered by KVM, the very first fault (no matter if it is a regular page fault, or a get_user_pages) always has FAULT_FOLL_ALLOW_RETRY set. Then the userfaultfd blocks and it is waken only when the pagetable is already mapped. The second fault attempt after the wakeup doesn't need FAULT_FOLL_ALLOW_RETRY, so it's ok to retry without it. This patch (of 5): We can leverage the VM_FAULT_RETRY functionality in the page fault paths better by using either get_user_pages_locked or get_user_pages_unlocked. The former allows conversion of get_user_pages invocations that will have to pass a "&locked" parameter to know if the mmap_sem was dropped during the call. Example from: down_read(&mm->mmap_sem); do_something() get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); to: int locked = 1; down_read(&mm->mmap_sem); do_something() get_user_pages_locked(tsk, mm, ..., pages, &locked); if (locked) up_read(&mm->mmap_sem); The latter is suitable only as a drop in replacement of the form: down_read(&mm->mmap_sem); get_user_pages(tsk, mm, ..., pages, NULL); up_read(&mm->mmap_sem); into: get_user_pages_unlocked(tsk, mm, ..., pages); Where tsk, mm, the intermediate "..." paramters and "pages" can be any value as before. Just the last parameter of get_user_pages (vmas) must be NULL for get_user_pages_locked|unlocked to be usable (the latter original form wouldn't have been safe anyway if vmas wasn't null, for the former we just make it explicit by dropping the parameter). If vmas is not NULL these two methods cannot be used. Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Peter Feiner Reviewed-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 7 +++ mm/gup.c | 177 +++++++++++++++++++++++++++++++++++++++++++++++++---- mm/nommu.c | 23 +++++++ 3 files changed, 196 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 644990b83cda..fc499e675475 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1261,6 +1261,13 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked); +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); struct kvec; diff --git a/mm/gup.c b/mm/gup.c index 1a8ab05918e0..71a37738a326 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -575,6 +575,165 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return 0; } +static __always_inline long __get_user_pages_locked(struct task_struct *tsk, + struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + int write, int force, + struct page **pages, + struct vm_area_struct **vmas, + int *locked, bool notify_drop) +{ + int flags = FOLL_TOUCH; + long ret, pages_done; + bool lock_dropped; + + if (locked) { + /* if VM_FAULT_RETRY can be returned, vmas become invalid */ + BUG_ON(vmas); + /* check caller initialized locked */ + BUG_ON(*locked != 1); + } + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + pages_done = 0; + lock_dropped = false; + for (;;) { + ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages, + vmas, locked); + if (!locked) + /* VM_FAULT_RETRY couldn't trigger, bypass */ + return ret; + + /* VM_FAULT_RETRY cannot return errors */ + if (!*locked) { + BUG_ON(ret < 0); + BUG_ON(ret >= nr_pages); + } + + if (!pages) + /* If it's a prefault don't insist harder */ + return ret; + + if (ret > 0) { + nr_pages -= ret; + pages_done += ret; + if (!nr_pages) + break; + } + if (*locked) { + /* VM_FAULT_RETRY didn't trigger */ + if (!pages_done) + pages_done = ret; + break; + } + /* VM_FAULT_RETRY triggered, so seek to the faulting offset */ + pages += ret; + start += ret << PAGE_SHIFT; + + /* + * Repeat on the address that fired VM_FAULT_RETRY + * without FAULT_FLAG_ALLOW_RETRY but with + * FAULT_FLAG_TRIED. + */ + *locked = 1; + lock_dropped = true; + down_read(&mm->mmap_sem); + ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED, + pages, NULL, NULL); + if (ret != 1) { + BUG_ON(ret > 1); + if (!pages_done) + pages_done = ret; + break; + } + nr_pages--; + pages_done++; + if (!nr_pages) + break; + pages++; + start += PAGE_SIZE; + } + if (notify_drop && lock_dropped && *locked) { + /* + * We must let the caller know we temporarily dropped the lock + * and so the critical section protected by it was lost. + */ + up_read(&mm->mmap_sem); + *locked = 0; + } + return pages_done; +} + +/* + * We can leverage the VM_FAULT_RETRY functionality in the page fault + * paths better by using either get_user_pages_locked() or + * get_user_pages_unlocked(). + * + * get_user_pages_locked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * to: + * + * int locked = 1; + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * if (locked) + * up_read(&mm->mmap_sem); + */ +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, locked, true); +} +EXPORT_SYMBOL(get_user_pages_locked); + +/* + * get_user_pages_unlocked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * with: + * + * get_user_pages_unlocked(tsk, mm, ..., pages); + * + * It is functionally equivalent to get_user_pages_fast so + * get_user_pages_fast should be used instead, if the two parameters + * "tsk" and "mm" are respectively equal to current and current->mm, + * or if "force" shall be set to 1 (get_user_pages_fast misses the + * "force" parameter). + */ +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + long ret; + int locked = 1; + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, &locked, false); + if (locked) + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /* * get_user_pages() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or @@ -624,22 +783,18 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, * use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. + * + * get_user_pages should be phased out in favor of + * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing + * should use get_user_pages because it cannot pass + * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, vmas, NULL, false); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/nommu.c b/mm/nommu.c index 541bed64e348..bfb690b0f986 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -214,6 +214,29 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); +} +EXPORT_SYMBOL(get_user_pages_locked); + +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + long ret; + down_read(&mm->mmap_sem); + ret = get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping -- cgit v1.2.3 From 0fd71a56f41d4ffabeda1dae9ff5ed4f34d4e935 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:20 -0800 Subject: mm: gup: add __get_user_pages_unlocked to customize gup_flags Some callers (like KVM) may want to set the gup_flags like FOLL_HWPOSION to get a proper -EHWPOSION retval instead of -EFAULT to take a more appropriate action if get_user_pages runs into a memory failure. Signed-off-by: Andrea Arcangeli Reviewed-by: Kirill A. Shutemov Cc: Andres Lagar-Cavilla Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ mm/gup.c | 44 ++++++++++++++++++++++++++++++++------------ mm/nommu.c | 16 +++++++++++++--- 3 files changed, 49 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index fc499e675475..3696b3bd1d7e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1265,6 +1265,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, int *locked); +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags); long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages); diff --git a/mm/gup.c b/mm/gup.c index 71a37738a326..dad5875fb766 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -582,9 +582,9 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk, int write, int force, struct page **pages, struct vm_area_struct **vmas, - int *locked, bool notify_drop) + int *locked, bool notify_drop, + unsigned int flags) { - int flags = FOLL_TOUCH; long ret, pages_done; bool lock_dropped; @@ -698,10 +698,36 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, int *locked) { return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, locked, true); + pages, NULL, locked, true, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages_locked); +/* + * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to + * pass additional gup_flags as last parameter (like FOLL_HWPOISON). + * + * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the + * caller if required (just like with __get_user_pages). "FOLL_GET", + * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed + * according to the parameters "pages", "write", "force" + * respectively. + */ +__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) +{ + long ret; + int locked = 1; + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, &locked, false, gup_flags); + if (locked) + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(__get_user_pages_unlocked); + /* * get_user_pages_unlocked() is suitable to replace the form: * @@ -723,14 +749,8 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages) { - long ret; - int locked = 1; - down_read(&mm->mmap_sem); - ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, NULL, &locked, false); - if (locked) - up_read(&mm->mmap_sem); - return ret; + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages_unlocked); @@ -794,7 +814,7 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int force, struct page **pages, struct vm_area_struct **vmas) { return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, - pages, vmas, NULL, false); + pages, vmas, NULL, false, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); diff --git a/mm/nommu.c b/mm/nommu.c index bfb690b0f986..4d1b8a199867 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -224,9 +224,10 @@ long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages_locked); -long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages) +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) { long ret; down_read(&mm->mmap_sem); @@ -235,6 +236,15 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, up_read(&mm->mmap_sem); return ret; } +EXPORT_SYMBOL(__get_user_pages_unlocked); + +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, 0); +} EXPORT_SYMBOL(get_user_pages_unlocked); /** -- cgit v1.2.3 From 0664e57ff0c68cbca012a45a38288fa277eb6795 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Wed, 11 Feb 2015 15:27:28 -0800 Subject: mm: gup: kvm use get_user_pages_unlocked Use the more generic get_user_pages_unlocked which has the additional benefit of passing FAULT_FLAG_ALLOW_RETRY at the very first page fault (which allows the first page fault in an unmapped area to be always able to block indefinitely by being allowed to release the mmap_sem). Signed-off-by: Andrea Arcangeli Reviewed-by: Andres Lagar-Cavilla Reviewed-by: Kirill A. Shutemov Cc: Peter Feiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kvm_host.h | 11 ----------- virt/kvm/async_pf.c | 2 +- virt/kvm/kvm_main.c | 50 ++++-------------------------------------------- 3 files changed, 5 insertions(+), 58 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 26f106022c88..d189ee098aa2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -200,17 +200,6 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -/* - * Carry out a gup that requires IO. Allow the mm to relinquish the mmap - * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL - * controls whether we retry the gup one more time to completion in that case. - * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp - * handler. - */ -int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, bool write_fault, - struct page **pagep); - enum { OUTSIDE_GUEST_MODE, IN_GUEST_MODE, diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 5ff7f7f2689a..44660aee335f 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -80,7 +80,7 @@ static void async_pf_execute(struct work_struct *work) might_sleep(); - kvm_get_user_page_io(NULL, mm, addr, 1, NULL); + get_user_pages_unlocked(NULL, mm, addr, 1, 1, 0, NULL); kvm_async_page_present_sync(vcpu, apf); spin_lock(&vcpu->async_pf.lock); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1cc6e2e19982..458b9b14b15c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1128,43 +1128,6 @@ static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL); } -int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm, - unsigned long addr, bool write_fault, - struct page **pagep) -{ - int npages; - int locked = 1; - int flags = FOLL_TOUCH | FOLL_HWPOISON | - (pagep ? FOLL_GET : 0) | - (write_fault ? FOLL_WRITE : 0); - - /* - * If retrying the fault, we get here *not* having allowed the filemap - * to wait on the page lock. We should now allow waiting on the IO with - * the mmap semaphore released. - */ - down_read(&mm->mmap_sem); - npages = __get_user_pages(tsk, mm, addr, 1, flags, pagep, NULL, - &locked); - if (!locked) { - VM_BUG_ON(npages); - - if (!pagep) - return 0; - - /* - * The previous call has now waited on the IO. Now we can - * retry and complete. Pass TRIED to ensure we do not re - * schedule async IO (see e.g. filemap_fault). - */ - down_read(&mm->mmap_sem); - npages = __get_user_pages(tsk, mm, addr, 1, flags | FOLL_TRIED, - pagep, NULL, NULL); - } - up_read(&mm->mmap_sem); - return npages; -} - static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE; @@ -1227,15 +1190,10 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, npages = get_user_page_nowait(current, current->mm, addr, write_fault, page); up_read(¤t->mm->mmap_sem); - } else { - /* - * By now we have tried gup_fast, and possibly async_pf, and we - * are certainly not atomic. Time to retry the gup, allowing - * mmap semaphore to be relinquished in the case of IO. - */ - npages = kvm_get_user_page_io(current, current->mm, addr, - write_fault, page); - } + } else + npages = __get_user_pages_unlocked(current, current->mm, addr, 1, + write_fault, 0, page, + FOLL_TOUCH|FOLL_HWPOISON); if (npages != 1) return npages; -- cgit v1.2.3 From 0b1fbfe50006c41014cc25660c0e735d21c34939 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:34 -0800 Subject: mm/pagewalk: remove pgd_entry() and pud_entry() Currently no user of page table walker sets ->pgd_entry() or ->pud_entry(), so checking their existence in each loop is just wasting CPU cycle. So let's remove it to reduce overhead. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Kirill A. Shutemov Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 ------ mm/pagewalk.c | 9 ++------- 2 files changed, 2 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3696b3bd1d7e..f6106d3f3dab 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1164,8 +1164,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, /** * mm_walk - callbacks for walk_page_range - * @pgd_entry: if set, called for each non-empty PGD (top-level) entry - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to @@ -1179,10 +1177,6 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *pgd, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pud_entry)(pud_t *pud, unsigned long addr, - unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pte_entry)(pte_t *pte, unsigned long addr, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index b264bda46e1b..b793ef149da2 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -86,9 +86,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, break; continue; } - if (walk->pud_entry) - err = walk->pud_entry(pud, addr, next, walk); - if (!err && (walk->pmd_entry || walk->pte_entry)) + if (walk->pmd_entry || walk->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) break; @@ -237,10 +235,7 @@ int walk_page_range(unsigned long addr, unsigned long end, pgd++; continue; } - if (walk->pgd_entry) - err = walk->pgd_entry(pgd, addr, next, walk); - if (!err && - (walk->pud_entry || walk->pmd_entry || walk->pte_entry)) + if (walk->pmd_entry || walk->pte_entry) err = walk_pud_range(pgd, addr, next, walk); if (err) break; -- cgit v1.2.3 From fafaa4264eba49fd10695c193a82760558d093f4 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:37 -0800 Subject: pagewalk: improve vma handling Current implementation of page table walker has a fundamental problem in vma handling, which started when we tried to handle vma(VM_HUGETLB). Because it's done in pgd loop, considering vma boundary makes code complicated and bug-prone. From the users viewpoint, some user checks some vma-related condition to determine whether the user really does page walk over the vma. In order to solve these, this patch moves vma check outside pgd loop and introduce a new callback ->test_walk(). Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +++- mm/pagewalk.c | 206 ++++++++++++++++++++++++++++++----------------------- 2 files changed, 129 insertions(+), 92 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index f6106d3f3dab..3891a368e5e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1171,10 +1171,16 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry - * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry - * is used. + * @test_walk: caller specific callback function to determine whether + * we walk over the current vma or not. A positive returned + * value means "do page table walk over the current vma," + * and a negative one means "abort current page table walk + * right now." 0 means "skip the current vma." + * @mm: mm_struct representing the target process of page table walk + * @vma: vma currently walked (NULL if walking outside vmas) + * @private: private data for callbacks' usage * - * (see walk_page_range for more details) + * (see the comment on walk_page_range() for more details) */ struct mm_walk { int (*pmd_entry)(pmd_t *pmd, unsigned long addr, @@ -1186,7 +1192,10 @@ struct mm_walk { int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long next, struct mm_walk *walk); + int (*test_walk)(unsigned long addr, unsigned long next, + struct mm_walk *walk); struct mm_struct *mm; + struct vm_area_struct *vma; void *private; }; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index b793ef149da2..d9cc3caae802 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -59,7 +59,7 @@ again: continue; split_huge_page_pmd_mm(walk->mm, addr, pmd); - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + if (pmd_trans_unstable(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); if (err) @@ -95,6 +95,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_pgd_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pgd_t *pgd; + unsigned long next; + int err = 0; + + pgd = pgd_offset(walk->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(pgd, addr, next, walk); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + return err; +} + #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, unsigned long end) @@ -103,10 +129,10 @@ static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, return boundary < end ? boundary : end; } -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { + struct vm_area_struct *vma = walk->vma; struct hstate *h = hstate_vma(vma); unsigned long next; unsigned long hmask = huge_page_mask(h); @@ -119,15 +145,14 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, if (pte && walk->hugetlb_entry) err = walk->hugetlb_entry(pte, hmask, addr, next, walk); if (err) - return err; + break; } while (addr = next, addr != end); - return 0; + return err; } #else /* CONFIG_HUGETLB_PAGE */ -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; @@ -135,112 +160,115 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, #endif /* CONFIG_HUGETLB_PAGE */ +/* + * Decide whether we really walk over the current vma on [@start, @end) + * or skip it via the returned value. Return 0 if we do walk over the + * current vma, and return 1 if we skip the vma. Negative values means + * error, where we abort the current walk. + * + * Default check (only VM_PFNMAP check for now) is used when the caller + * doesn't define test_walk() callback. + */ +static int walk_page_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + if (walk->test_walk) + return walk->test_walk(start, end, walk); + + /* + * Do not walk over vma(VM_PFNMAP), because we have no valid struct + * page backing a VM_PFNMAP range. See also commit a9ff785e4437. + */ + if (vma->vm_flags & VM_PFNMAP) + return 1; + return 0; +} + +static int __walk_page_range(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + int err = 0; + struct vm_area_struct *vma = walk->vma; + + if (vma && is_vm_hugetlb_page(vma)) { + if (walk->hugetlb_entry) + err = walk_hugetlb_range(start, end, walk); + } else + err = walk_pgd_range(start, end, walk); + + return err; +} /** - * walk_page_range - walk a memory map's page tables with a callback - * @addr: starting address - * @end: ending address - * @walk: set of callbacks to invoke for each level of the tree - * - * Recursively walk the page table for the memory area in a VMA, - * calling supplied callbacks. Callbacks are called in-order (first - * PGD, first PUD, first PMD, first PTE, second PTE... second PMD, - * etc.). If lower-level callbacks are omitted, walking depth is reduced. + * walk_page_range - walk page table with caller specific callbacks * - * Each callback receives an entry pointer and the start and end of the - * associated range, and a copy of the original mm_walk for access to - * the ->private or ->mm fields. + * Recursively walk the page table tree of the process represented by @walk->mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. * - * Usually no locks are taken, but splitting transparent huge page may - * take page table lock. And the bottom level iterator will map PTE - * directories from highmem if necessary. + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @walk->test_walk() are used for this + * purpose. * - * If any callback returns a non-zero value, the walk is aborted and - * the return value is propagated back to the caller. Otherwise 0 is returned. + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @walk->private should be helpful. * - * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry - * is !NULL. + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold + * @walk->mm->mmap_sem, because these function traverse vma list and/or + * access to vma's data. */ -int walk_page_range(unsigned long addr, unsigned long end, +int walk_page_range(unsigned long start, unsigned long end, struct mm_walk *walk) { - pgd_t *pgd; - unsigned long next; int err = 0; + unsigned long next; + struct vm_area_struct *vma; - if (addr >= end) - return err; + if (start >= end) + return -EINVAL; if (!walk->mm) return -EINVAL; VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm); - pgd = pgd_offset(walk->mm, addr); + vma = find_vma(walk->mm, start); do { - struct vm_area_struct *vma = NULL; + if (!vma) { /* after the last vma */ + walk->vma = NULL; + next = end; + } else if (start < vma->vm_start) { /* outside vma */ + walk->vma = NULL; + next = min(end, vma->vm_start); + } else { /* inside vma */ + walk->vma = vma; + next = min(end, vma->vm_end); + vma = vma->vm_next; - next = pgd_addr_end(addr, end); - - /* - * This function was not intended to be vma based. - * But there are vma special cases to be handled: - * - hugetlb vma's - * - VM_PFNMAP vma's - */ - vma = find_vma(walk->mm, addr); - if (vma) { - /* - * There are no page structures backing a VM_PFNMAP - * range, so do not allow split_huge_page_pmd(). - */ - if ((vma->vm_start <= addr) && - (vma->vm_flags & VM_PFNMAP)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); + err = walk_page_test(start, next, walk); + if (err > 0) continue; - } - /* - * Handle hugetlb vma individually because pagetable - * walk for the hugetlb page is dependent on the - * architecture and we can't handled it in the same - * manner as non-huge pages. - */ - if (walk->hugetlb_entry && (vma->vm_start <= addr) && - is_vm_hugetlb_page(vma)) { - if (vma->vm_end < next) - next = vma->vm_end; - /* - * Hugepage is very tightly coupled with vma, - * so walk through hugetlb entries within a - * given vma. - */ - err = walk_hugetlb_range(vma, addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); - continue; - } - } - - if (pgd_none_or_clear_bad(pgd)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); - if (err) + if (err < 0) break; - pgd++; - continue; } - if (walk->pmd_entry || walk->pte_entry) - err = walk_pud_range(pgd, addr, next, walk); + if (walk->vma || walk->pte_hole) + err = __walk_page_range(start, next, walk); if (err) break; - pgd++; - } while (addr = next, addr < end); - + } while (start = next, start < end); return err; } -- cgit v1.2.3 From 900fc5f197b05253ae9433fb9a066c3f37d08f69 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Wed, 11 Feb 2015 15:27:40 -0800 Subject: pagewalk: add walk_page_vma() Introduce walk_page_vma(), which is useful for the callers which want to walk over a given vma. It's used by later patches. Signed-off-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: Pavel Emelyanov Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/pagewalk.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3891a368e5e0..a4d24f3c5430 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1201,6 +1201,7 @@ struct mm_walk { int walk_page_range(unsigned long addr, unsigned long end, struct mm_walk *walk); +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d9cc3caae802..4c9a653ba563 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -272,3 +272,21 @@ int walk_page_range(unsigned long start, unsigned long end, } while (start = next, start < end); return err; } + +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk) +{ + int err; + + if (!walk->mm) + return -EINVAL; + + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + VM_BUG_ON(!vma); + walk->vma = vma; + err = walk_page_test(vma->vm_start, vma->vm_end, walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(vma->vm_start, vma->vm_end, walk); +} -- cgit v1.2.3 From 99592d598eca62bdbbf62b59941c189176dfc614 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 11 Feb 2015 15:28:15 -0800 Subject: mm: when stealing freepages, also take pages created by splitting buddy page When studying page stealing, I noticed some weird looking decisions in try_to_steal_freepages(). The first I assume is a bug (Patch 1), the following two patches were driven by evaluation. Testing was done with stress-highalloc of mmtests, using the mm_page_alloc_extfrag tracepoint and postprocessing to get counts of how often page stealing occurs for individual migratetypes, and what migratetypes are used for fallbacks. Arguably, the worst case of page stealing is when UNMOVABLE allocation steals from MOVABLE pageblock. RECLAIMABLE allocation stealing from MOVABLE allocation is also not ideal, so the goal is to minimize these two cases. The evaluation of v2 wasn't always clear win and Joonsoo questioned the results. Here I used different baseline which includes RFC compaction improvements from [1]. I found that the compaction improvements reduce variability of stress-highalloc, so there's less noise in the data. First, let's look at stress-highalloc configured to do sync compaction, and how these patches reduce page stealing events during the test. First column is after fresh reboot, other two are reiterations of test without reboot. That was all accumulater over 5 re-iterations (so the benchmark was run 5x3 times with 5 fresh restarts). Baseline: 3.19-rc4 3.19-rc4 3.19-rc4 5-nothp-1 5-nothp-2 5-nothp-3 Page alloc extfrag event 10264225 8702233 10244125 Extfrag fragmenting 10263271 8701552 10243473 Extfrag fragmenting for unmovable 13595 17616 15960 Extfrag fragmenting unmovable placed with movable 7989 12193 8447 Extfrag fragmenting for reclaimable 658 1840 1817 Extfrag fragmenting reclaimable placed with movable 558 1677 1679 Extfrag fragmenting for movable 10249018 8682096 10225696 With Patch 1: 3.19-rc4 3.19-rc4 3.19-rc4 6-nothp-1 6-nothp-2 6-nothp-3 Page alloc extfrag event 11834954 9877523 9774860 Extfrag fragmenting 11833993 9876880 9774245 Extfrag fragmenting for unmovable 7342 16129 11712 Extfrag fragmenting unmovable placed with movable 4191 10547 6270 Extfrag fragmenting for reclaimable 373 1130 923 Extfrag fragmenting reclaimable placed with movable 302 906 738 Extfrag fragmenting for movable 11826278 9859621 9761610 With Patch 2: 3.19-rc4 3.19-rc4 3.19-rc4 7-nothp-1 7-nothp-2 7-nothp-3 Page alloc extfrag event 4725990 3668793 3807436 Extfrag fragmenting 4725104 3668252 3806898 Extfrag fragmenting for unmovable 6678 7974 7281 Extfrag fragmenting unmovable placed with movable 2051 3829 4017 Extfrag fragmenting for reclaimable 429 1208 1278 Extfrag fragmenting reclaimable placed with movable 369 976 1034 Extfrag fragmenting for movable 4717997 3659070 3798339 With Patch 3: 3.19-rc4 3.19-rc4 3.19-rc4 8-nothp-1 8-nothp-2 8-nothp-3 Page alloc extfrag event 5016183 4700142 3850633 Extfrag fragmenting 5015325 4699613 3850072 Extfrag fragmenting for unmovable 1312 3154 3088 Extfrag fragmenting unmovable placed with movable 1115 2777 2714 Extfrag fragmenting for reclaimable 437 1193 1097 Extfrag fragmenting reclaimable placed with movable 330 969 879 Extfrag fragmenting for movable 5013576 4695266 3845887 In v2 we've seen apparent regression with Patch 1 for unmovable events, this is now gone, suggesting it was indeed noise. Here, each patch improves the situation for unmovable events. Reclaimable is improved by patch 1 and then either the same modulo noise, or perhaps sligtly worse - a small price for unmovable improvements, IMHO. The number of movable allocations falling back to other migratetypes is most noisy, but it's reduced to half at Patch 2 nevertheless. These are least critical as compaction can move them around. If we look at success rates, the patches don't affect them, that didn't change. Baseline: 3.19-rc4 3.19-rc4 3.19-rc4 5-nothp-1 5-nothp-2 5-nothp-3 Success 1 Min 49.00 ( 0.00%) 42.00 ( 14.29%) 41.00 ( 16.33%) Success 1 Mean 51.00 ( 0.00%) 45.00 ( 11.76%) 42.60 ( 16.47%) Success 1 Max 55.00 ( 0.00%) 51.00 ( 7.27%) 46.00 ( 16.36%) Success 2 Min 53.00 ( 0.00%) 47.00 ( 11.32%) 44.00 ( 16.98%) Success 2 Mean 59.60 ( 0.00%) 50.80 ( 14.77%) 48.20 ( 19.13%) Success 2 Max 64.00 ( 0.00%) 56.00 ( 12.50%) 52.00 ( 18.75%) Success 3 Min 84.00 ( 0.00%) 82.00 ( 2.38%) 78.00 ( 7.14%) Success 3 Mean 85.60 ( 0.00%) 82.80 ( 3.27%) 79.40 ( 7.24%) Success 3 Max 86.00 ( 0.00%) 83.00 ( 3.49%) 80.00 ( 6.98%) Patch 1: 3.19-rc4 3.19-rc4 3.19-rc4 6-nothp-1 6-nothp-2 6-nothp-3 Success 1 Min 49.00 ( 0.00%) 44.00 ( 10.20%) 44.00 ( 10.20%) Success 1 Mean 51.80 ( 0.00%) 46.00 ( 11.20%) 45.80 ( 11.58%) Success 1 Max 54.00 ( 0.00%) 49.00 ( 9.26%) 49.00 ( 9.26%) Success 2 Min 58.00 ( 0.00%) 49.00 ( 15.52%) 48.00 ( 17.24%) Success 2 Mean 60.40 ( 0.00%) 51.80 ( 14.24%) 50.80 ( 15.89%) Success 2 Max 63.00 ( 0.00%) 54.00 ( 14.29%) 55.00 ( 12.70%) Success 3 Min 84.00 ( 0.00%) 81.00 ( 3.57%) 79.00 ( 5.95%) Success 3 Mean 85.00 ( 0.00%) 81.60 ( 4.00%) 79.80 ( 6.12%) Success 3 Max 86.00 ( 0.00%) 82.00 ( 4.65%) 82.00 ( 4.65%) Patch 2: 3.19-rc4 3.19-rc4 3.19-rc4 7-nothp-1 7-nothp-2 7-nothp-3 Success 1 Min 50.00 ( 0.00%) 44.00 ( 12.00%) 39.00 ( 22.00%) Success 1 Mean 52.80 ( 0.00%) 45.60 ( 13.64%) 42.40 ( 19.70%) Success 1 Max 55.00 ( 0.00%) 46.00 ( 16.36%) 47.00 ( 14.55%) Success 2 Min 52.00 ( 0.00%) 48.00 ( 7.69%) 45.00 ( 13.46%) Success 2 Mean 53.40 ( 0.00%) 49.80 ( 6.74%) 48.80 ( 8.61%) Success 2 Max 57.00 ( 0.00%) 52.00 ( 8.77%) 52.00 ( 8.77%) Success 3 Min 84.00 ( 0.00%) 81.00 ( 3.57%) 79.00 ( 5.95%) Success 3 Mean 85.00 ( 0.00%) 82.40 ( 3.06%) 79.60 ( 6.35%) Success 3 Max 86.00 ( 0.00%) 83.00 ( 3.49%) 80.00 ( 6.98%) Patch 3: 3.19-rc4 3.19-rc4 3.19-rc4 8-nothp-1 8-nothp-2 8-nothp-3 Success 1 Min 46.00 ( 0.00%) 44.00 ( 4.35%) 42.00 ( 8.70%) Success 1 Mean 50.20 ( 0.00%) 45.60 ( 9.16%) 44.00 ( 12.35%) Success 1 Max 52.00 ( 0.00%) 47.00 ( 9.62%) 47.00 ( 9.62%) Success 2 Min 53.00 ( 0.00%) 49.00 ( 7.55%) 48.00 ( 9.43%) Success 2 Mean 55.80 ( 0.00%) 50.60 ( 9.32%) 49.00 ( 12.19%) Success 2 Max 59.00 ( 0.00%) 52.00 ( 11.86%) 51.00 ( 13.56%) Success 3 Min 84.00 ( 0.00%) 80.00 ( 4.76%) 79.00 ( 5.95%) Success 3 Mean 85.40 ( 0.00%) 81.60 ( 4.45%) 80.40 ( 5.85%) Success 3 Max 87.00 ( 0.00%) 83.00 ( 4.60%) 82.00 ( 5.75%) While there's no improvement here, I consider reduced fragmentation events to be worth on its own. Patch 2 also seems to reduce scanning for free pages, and migrations in compaction, suggesting it has somewhat less work to do: Patch 1: Compaction stalls 4153 3959 3978 Compaction success 1523 1441 1446 Compaction failures 2630 2517 2531 Page migrate success 4600827 4943120 5104348 Page migrate failure 19763 16656 17806 Compaction pages isolated 9597640 10305617 10653541 Compaction migrate scanned 77828948 86533283 87137064 Compaction free scanned 517758295 521312840 521462251 Compaction cost 5503 5932 6110 Patch 2: Compaction stalls 3800 3450 3518 Compaction success 1421 1316 1317 Compaction failures 2379 2134 2201 Page migrate success 4160421 4502708 4752148 Page migrate failure 19705 14340 14911 Compaction pages isolated 8731983 9382374 9910043 Compaction migrate scanned 98362797 96349194 98609686 Compaction free scanned 496512560 469502017 480442545 Compaction cost 5173 5526 5811 As with v2, /proc/pagetypeinfo appears unaffected with respect to numbers of unmovable and reclaimable pageblocks. Configuring the benchmark to allocate like THP page fault (i.e. no sync compaction) gives much noisier results for iterations 2 and 3 after reboot. This is not so surprising given how [1] offers lower improvements in this scenario due to less restarts after deferred compaction which would change compaction pivot. Baseline: 3.19-rc4 3.19-rc4 3.19-rc4 5-thp-1 5-thp-2 5-thp-3 Page alloc extfrag event 8148965 6227815 6646741 Extfrag fragmenting 8147872 6227130 6646117 Extfrag fragmenting for unmovable 10324 12942 15975 Extfrag fragmenting unmovable placed with movable 5972 8495 10907 Extfrag fragmenting for reclaimable 601 1707 2210 Extfrag fragmenting reclaimable placed with movable 520 1570 2000 Extfrag fragmenting for movable 8136947 6212481 6627932 Patch 1: 3.19-rc4 3.19-rc4 3.19-rc4 6-thp-1 6-thp-2 6-thp-3 Page alloc extfrag event 8345457 7574471 7020419 Extfrag fragmenting 8343546 7573777 7019718 Extfrag fragmenting for unmovable 10256 18535 30716 Extfrag fragmenting unmovable placed with movable 6893 11726 22181 Extfrag fragmenting for reclaimable 465 1208 1023 Extfrag fragmenting reclaimable placed with movable 353 996 843 Extfrag fragmenting for movable 8332825 7554034 6987979 Patch 2: 3.19-rc4 3.19-rc4 3.19-rc4 7-thp-1 7-thp-2 7-thp-3 Page alloc extfrag event 3512847 3020756 2891625 Extfrag fragmenting 3511940 3020185 2891059 Extfrag fragmenting for unmovable 9017 6892 6191 Extfrag fragmenting unmovable placed with movable 1524 3053 2435 Extfrag fragmenting for reclaimable 445 1081 1160 Extfrag fragmenting reclaimable placed with movable 375 918 986 Extfrag fragmenting for movable 3502478 3012212 2883708 Patch 3: 3.19-rc4 3.19-rc4 3.19-rc4 8-thp-1 8-thp-2 8-thp-3 Page alloc extfrag event 3181699 3082881 2674164 Extfrag fragmenting 3180812 3082303 2673611 Extfrag fragmenting for unmovable 1201 4031 4040 Extfrag fragmenting unmovable placed with movable 974 3611 3645 Extfrag fragmenting for reclaimable 478 1165 1294 Extfrag fragmenting reclaimable placed with movable 387 985 1030 Extfrag fragmenting for movable 3179133 3077107 2668277 The improvements for first iteration are clear, the rest is much noisier and can appear like regression for Patch 1. Anyway, patch 2 rectifies it. Allocation success rates are again unaffected so there's no point in making this e-mail any longer. [1] http://marc.info/?l=linux-mm&m=142166196321125&w=2 This patch (of 3): When __rmqueue_fallback() is called to allocate a page of order X, it will find a page of order Y >= X of a fallback migratetype, which is different from the desired migratetype. With the help of try_to_steal_freepages(), it may change the migratetype (to the desired one) also of: 1) all currently free pages in the pageblock containing the fallback page 2) the fallback pageblock itself 3) buddy pages created by splitting the fallback page (when Y > X) These decisions take the order Y into account, as well as the desired migratetype, with the goal of preventing multiple fallback allocations that could e.g. distribute UNMOVABLE allocations among multiple pageblocks. Originally, decision for 1) has implied the decision for 3). Commit 47118af076f6 ("mm: mmzone: MIGRATE_CMA migration type added") changed that (probably unintentionally) so that the buddy pages in case 3) are always changed to the desired migratetype, except for CMA pageblocks. Commit fef903efcf0c ("mm/page_allo.c: restructure free-page stealing code and fix a bug") did some refactoring and added a comment that the case of 3) is intended. Commit 0cbef29a7821 ("mm: __rmqueue_fallback() should respect pageblock type") removed the comment and tried to restore the original behavior where 1) implies 3), but due to the previous refactoring, the result is instead that only 2) implies 3) - and the conditions for 2) are less frequently met than conditions for 1). This may increase fragmentation in situations where the code decides to steal all free pages from the pageblock (case 1)), but then gives back the buddy pages produced by splitting. This patch restores the original intended logic where 1) implies 3). During testing with stress-highalloc from mmtests, this has shown to decrease the number of events where UNMOVABLE and RECLAIMABLE allocations steal from MOVABLE pageblocks, which can lead to permanent fragmentation. In some cases it has increased the number of events when MOVABLE allocations steal from UNMOVABLE or RECLAIMABLE pageblocks, but these are fixable by sync compaction and thus less harmful. Note that evaluation has shown that the behavior introduced by 47118af076f6 for buddy pages in case 3) is actually even better than the original logic, so the following patch will introduce it properly once again. For stable backports of this patch it makes thus sense to only fix versions containing 0cbef29a7821. [iamjoonsoo.kim@lge.com: tracepoint fix] Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Cc: Zhang Yanfei Acked-by: Minchan Kim Cc: David Rientjes Cc: Rik van Riel Cc: "Aneesh Kumar K.V" Cc: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Michal Hocko Cc: KOSAKI Motohiro Cc: [3.13+ containing 0cbef29a7821] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/kmem.h | 7 ++++--- mm/page_alloc.c | 12 +++++------- 2 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index aece1346ceb7..4ad10baecd4d 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -268,11 +268,11 @@ TRACE_EVENT(mm_page_alloc_extfrag, TP_PROTO(struct page *page, int alloc_order, int fallback_order, - int alloc_migratetype, int fallback_migratetype, int new_migratetype), + int alloc_migratetype, int fallback_migratetype), TP_ARGS(page, alloc_order, fallback_order, - alloc_migratetype, fallback_migratetype, new_migratetype), + alloc_migratetype, fallback_migratetype), TP_STRUCT__entry( __field( struct page *, page ) @@ -289,7 +289,8 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->fallback_order = fallback_order; __entry->alloc_migratetype = alloc_migratetype; __entry->fallback_migratetype = fallback_migratetype; - __entry->change_ownership = (new_migratetype == alloc_migratetype); + __entry->change_ownership = (alloc_migratetype == + get_pageblock_migratetype(page)); ), TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d", diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 134e25525044..b7a881019352 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1131,8 +1131,8 @@ static void change_pageblock_range(struct page *pageblock_page, * nor move CMA pages to different free lists. We don't want unmovable pages * to be allocated from MIGRATE_CMA areas. * - * Returns the new migratetype of the pageblock (or the same old migratetype - * if it was unchanged). + * Returns the allocation migratetype if free pages were stolen, or the + * fallback migratetype if it was decided not to steal. */ static int try_to_steal_freepages(struct zone *zone, struct page *page, int start_type, int fallback_type) @@ -1163,12 +1163,10 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Claim the whole block if over half of it is free */ if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) { - + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_type); - return start_type; - } + return start_type; } return fallback_type; @@ -1220,7 +1218,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) set_freepage_migratetype(page, new_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype, new_type); + start_migratetype, migratetype); return page; } -- cgit v1.2.3 From 94f759d62b2c6a9d124b0622077b1ddcfac43fb5 Mon Sep 17 00:00:00 2001 From: Sergei Rogachev Date: Wed, 11 Feb 2015 15:28:34 -0800 Subject: mm/page_owner.c: remove unnecessary stack_trace field Page owner uses the page_ext structure to keep meta-information for every page in the system. The structure also contains a field of type 'struct stack_trace', page owner uses this field during invocation of the function save_stack_trace. It is easy to notice that keeping a copy of this structure for every page in the system is very inefficiently in terms of memory. The patch removes this unnecessary field of page_ext and forces page owner to use a stack_trace structure allocated on the stack. [akpm@linux-foundation.org: use struct initializers] Signed-off-by: Sergei Rogachev Acked-by: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 2 +- mm/page_owner.c | 26 ++++++++++++++------------ 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index d2a2c84c72d0..c42981cd99aa 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -40,7 +40,7 @@ struct page_ext { #ifdef CONFIG_PAGE_OWNER unsigned int order; gfp_t gfp_mask; - struct stack_trace trace; + unsigned int nr_entries; unsigned long trace_entries[8]; #endif }; diff --git a/mm/page_owner.c b/mm/page_owner.c index 9ab4a9b5bc09..0993f5f36b01 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -59,20 +59,19 @@ void __reset_page_owner(struct page *page, unsigned int order) void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { - struct page_ext *page_ext; - struct stack_trace *trace; - - page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(page); + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = ARRAY_SIZE(page_ext->trace_entries), + .entries = &page_ext->trace_entries[0], + .skip = 3, + }; - trace = &page_ext->trace; - trace->nr_entries = 0; - trace->max_entries = ARRAY_SIZE(page_ext->trace_entries); - trace->entries = &page_ext->trace_entries[0]; - trace->skip = 3; - save_stack_trace(&page_ext->trace); + save_stack_trace(&trace); page_ext->order = order; page_ext->gfp_mask = gfp_mask; + page_ext->nr_entries = trace.nr_entries; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } @@ -84,6 +83,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, int ret; int pageblock_mt, page_mt; char *kbuf; + struct stack_trace trace = { + .nr_entries = page_ext->nr_entries, + .entries = &page_ext->trace_entries[0], + }; kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) @@ -121,8 +124,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; - ret += snprint_stack_trace(kbuf + ret, count - ret, - &page_ext->trace, 0); + ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0); if (ret >= count) goto err; -- cgit v1.2.3