From a09233f3e1b77dbf50851660533e008056553a2a Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:46:58 -0700 Subject: mm/memory-failure: unlock_page before put_page Recently I addressed a few of hwpoison race problems and the patches are merged on v4.2-rc1. It made progress, but unfortunately some problems still remain due to less coverage of my testing. So I'm trying to fix or avoid them in this series. One point I'm expecting to discuss is that patch 4/5 changes the page flag set to be checked on free time. In current behavior, __PG_HWPOISON is not supposed to be set when the page is freed. I think that there is no strong reason for this behavior, and it causes a problem hard to fix only in error handler side (because __PG_HWPOISON could be set at arbitrary timing.) So I suggest to change it. With this patchset, hwpoison stress testing in official mce-test testsuite (which previously failed) passes. This patch (of 5): In "just unpoisoned" path, we do put_page and then unlock_page, which is a wrong order and causes "freeing locked page" bug. So let's fix it. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index c53543d89282..04d677048af7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1209,9 +1209,9 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); atomic_long_sub(nr_pages, &num_poisoned_pages); + unlock_page(hpage); put_page(hpage); - res = 0; - goto out; + return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) -- cgit v1.2.3-70-g09d2 From a209ef09af0dc921311d0cc4a1d4f926321d91b8 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:01 -0700 Subject: mm/memory-failure: fix race in counting num_poisoned_pages When memory_failure() is called on a page which are just freed after page migration from soft offlining, the counter num_poisoned_pages is raised twi= ce. So let's fix it with using TestSetPageHWPoison. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 04d677048af7..f72d2fad0b90 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1671,8 +1671,8 @@ static int __soft_offline_page(struct page *page, int flags) if (ret > 0) ret = -EIO; } else { - SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", -- cgit v1.2.3-70-g09d2 From 98ed2b0052e68420f1bad6c81e3f2600d25023e7 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:04 -0700 Subject: mm/memory-failure: give up error handling for non-tail-refcounted thp "non anonymous thp" case is still racy with freeing thp, which causes panic due to put_page() for refcount-0 page. It seems that closing up this race might be hard (and/or not worth doing,) so let's give up the error handling for this case. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index f72d2fad0b90..cd985530f102 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -909,6 +909,18 @@ int get_hwpoison_page(struct page *page) * directly for tail pages. */ if (PageTransHuge(head)) { + /* + * Non anonymous thp exists only in allocation/free time. We + * can't handle such a case correctly, so let's give it up. + * This should be better than triggering BUG_ON when kernel + * tries to touch the "partially handled" page. + */ + if (!PageAnon(head)) { + pr_err("MCE: %#lx: non anonymous thp\n", + page_to_pfn(page)); + return 0; + } + if (get_page_unless_zero(head)) { if (PageTail(page)) get_page(page); @@ -1134,15 +1146,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { - if (!PageAnon(hpage)) { - pr_err("MCE: %#lx: non anonymous thp\n", pfn); - if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &num_poisoned_pages); - put_page(p); - if (p != hpage) - put_page(hpage); - return -EBUSY; - } if (unlikely(split_huge_page(hpage))) { pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) -- cgit v1.2.3-70-g09d2 From 4491f7126063ef51081f5662bd4fcae31621a333 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 6 Aug 2015 15:47:11 -0700 Subject: mm/memory-failure: set PageHWPoison before migrate_pages() Now page freeing code doesn't consider PageHWPoison as a bad page, so by setting it before completing the page containment, we can prevent the error page from being reused just after successful page migration. I added TTU_IGNORE_HWPOISON for try_to_unmap() to make sure that the page table entry is transformed into migration entry, not to hwpoison entry. Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Dean Nelson Cc: Tony Luck Cc: "Kirill A. Shutemov" Cc: Hugh Dickins Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 7 ++++--- mm/migrate.c | 3 ++- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index cd985530f102..ea5a93659488 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1659,6 +1659,8 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); + if (!TestSetPageHWPoison(page)) + atomic_long_inc(&num_poisoned_pages); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { @@ -1673,9 +1675,8 @@ static int __soft_offline_page(struct page *page, int flags) pfn, ret, page->flags); if (ret > 0) ret = -EIO; - } else { - if (!TestSetPageHWPoison(page)) - atomic_long_inc(&num_poisoned_pages); + if (TestClearPageHWPoison(page)) + atomic_long_dec(&num_poisoned_pages); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", diff --git a/mm/migrate.c b/mm/migrate.c index f2415be7d93b..eb4267107d1f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -880,7 +880,8 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes or remove ptes */ if (page_mapped(page)) { try_to_unmap(page, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| + TTU_IGNORE_HWPOISON); page_was_mapped = 1; } -- cgit v1.2.3-70-g09d2 From 4f32be677b124a49459e2603321c7a5605ceb9f8 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 14 Aug 2015 15:34:56 -0700 Subject: mm/hwpoison: fix page refcount of unknown non LRU page After trying to drain pages from pagevec/pageset, we try to get reference count of the page again, however, the reference count of the page is not reduced if the page is still not on LRU list. Fix it by adding the put_page() to drop the page reference which is from __get_any_page(). Signed-off-by: Wanpeng Li Acked-by: Naoya Horiguchi Cc: [3.9+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index ea5a93659488..81c20a7c9fa7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1538,6 +1538,8 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) */ ret = __get_any_page(page, pfn, 0); if (!PageLRU(page)) { + /* Drop page reference which is from __get_any_page() */ + put_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", pfn, page->flags); return -EIO; -- cgit v1.2.3-70-g09d2 From 036138080a4376e5f3e5d0cca8ac99084c5cf06e Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 14 Aug 2015 15:34:59 -0700 Subject: mm/hwpoison: fix fail isolate hugetlbfs page w/ refcount held Hugetlbfs pages will get a refcount in get_any_page() or madvise_hwpoison() if soft offlining through madvise. The refcount which is held by the soft offline path should be released if we fail to isolate hugetlbfs pages. Fix it by reducing the refcount for both isolation success and failure. Signed-off-by: Wanpeng Li Acked-by: Naoya Horiguchi Cc: [3.9+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 81c20a7c9fa7..dba52ee31bd4 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1569,13 +1569,12 @@ static int soft_offline_huge_page(struct page *page, int flags) unlock_page(hpage); ret = isolate_huge_page(hpage, &pagelist); - if (ret) { - /* - * get_any_page() and isolate_huge_page() takes a refcount each, - * so need to drop one here. - */ - put_page(hpage); - } else { + /* + * get_any_page() and isolate_huge_page() takes a refcount each, + * so need to drop one here. + */ + put_page(hpage); + if (!ret) { pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); return -EBUSY; } -- cgit v1.2.3-70-g09d2 From 7f6bf39bbdd1dcccd103ba7dce8496a8e72e7df4 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 14 Aug 2015 15:35:08 -0700 Subject: mm/hwpoison: fix panic due to split huge zero page Bug: ------------[ cut here ]------------ kernel BUG at mm/huge_memory.c:1957! invalid opcode: 0000 [#1] SMP Modules linked in: snd_hda_codec_hdmi i915 rpcsec_gss_krb5 snd_hda_codec_realtek snd_hda_codec_generic nfsv4 dns_re CPU: 2 PID: 2576 Comm: test_huge Not tainted 4.2.0-rc5-mm1+ #27 Hardware name: Dell Inc. OptiPlex 7020/0F5C5X, BIOS A03 01/08/2015 task: ffff880204e3d600 ti: ffff8800db16c000 task.ti: ffff8800db16c000 RIP: split_huge_page_to_list+0xdb/0x120 Call Trace: memory_failure+0x32e/0x7c0 madvise_hwpoison+0x8b/0x160 SyS_madvise+0x40/0x240 ? do_page_fault+0x37/0x90 entry_SYSCALL_64_fastpath+0x12/0x71 Code: ff f0 41 ff 4c 24 30 74 0d 31 c0 48 83 c4 08 5b 41 5c 41 5d c9 c3 4c 89 e7 e8 e2 58 fd ff 48 83 c4 08 31 c0 RIP split_huge_page_to_list+0xdb/0x120 RSP ---[ end trace aee7ce0df8e44076 ]--- Testcase: #define _GNU_SOURCE #include #include #include #include #include #include #include #include #define MB 1024*1024 int main(void) { char *mem; posix_memalign((void **)&mem, 2 * MB, 200 * MB); madvise(mem, 200 * MB, MADV_HWPOISON); free(mem); return 0; } Huge zero page is allocated if page fault w/o FAULT_FLAG_WRITE flag. The get_user_pages_fast() which called in madvise_hwpoison() will get huge zero page if the page is not allocated before. Huge zero page is a tranparent huge page, however, it is not an anonymous page. memory_failure will split the huge zero page and trigger BUG_ON(is_huge_zero_page(page)); After commit 98ed2b0052e6 ("mm/memory-failure: give up error handling for non-tail-refcounted thp"), memory_failure will not catch non anon thp from madvise_hwpoison path and this bug occur. Fix it by catching non anon thp in memory_failure in order to not split huge zero page in madvise_hwpoison path. After this patch: Injecting memory failure for page 0x202800 at 0x7fd8ae800000 MCE: 0x202800: non anonymous thp [...] [akpm@linux-foundation.org: remove second split, per Wanpeng] Signed-off-by: Wanpeng Li Acked-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index dba52ee31bd4..1f4446a90cef 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1146,8 +1146,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags) } if (!PageHuge(p) && PageTransHuge(hpage)) { - if (unlikely(split_huge_page(hpage))) { - pr_err("MCE: %#lx: thp split failed\n", pfn); + if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) { + if (!PageAnon(hpage)) + pr_err("MCE: %#lx: non anonymous thp\n", pfn); + else + pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) atomic_long_sub(nr_pages, &num_poisoned_pages); put_page(p); -- cgit v1.2.3-70-g09d2 From 33398cf2f360c5ce24c8a22436d52a06ad4e5eb5 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 8 Sep 2015 15:01:02 -0700 Subject: memcg: export struct mem_cgroup mem_cgroup structure is defined in mm/memcontrol.c currently which means that the code outside of this file has to use external API even for trivial access stuff. This patch exports mm_struct with its dependencies and makes some of the exported functions inlines. This even helps to reduce the code size a bit (make defconfig + CONFIG_MEMCG=y) text data bss dec hex filename 12355346 1823792 1089536 15268674 e8fb42 vmlinux.before 12354970 1823792 1089536 15268298 e8f9ca vmlinux.after This is not much (370B) but better than nothing. We also save a function call in some hot paths like callers of mem_cgroup_count_vm_event which is used for accounting. The patch doesn't introduce any functional changes. [vdavykov@parallels.com: inline memcg_kmem_is_active] [vdavykov@parallels.com: do not expose type outside of CONFIG_MEMCG] [akpm@linux-foundation.org: memcontrol.h needs eventfd.h for eventfd_ctx] [akpm@linux-foundation.org: export mem_cgroup_from_task() to modules] Signed-off-by: Michal Hocko Reviewed-by: Vladimir Davydov Suggested-by: Johannes Weiner Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 370 +++++++++++++++++++++++++++++++++++++++++---- include/linux/swap.h | 10 +- include/net/sock.h | 28 ---- mm/memcontrol.c | 315 +------------------------------------- mm/memory-failure.c | 2 +- mm/slab_common.c | 2 +- mm/vmscan.c | 2 +- 7 files changed, 351 insertions(+), 378 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 73b02b0a8f60..ab2f6880e27b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -23,6 +23,11 @@ #include #include #include +#include +#include +#include +#include +#include struct mem_cgroup; struct page; @@ -67,12 +72,221 @@ enum mem_cgroup_events_index { MEMCG_NR_EVENTS, }; +/* + * Per memcg event counter is incremented at every pagein/pageout. With THP, + * it will be incremated by the number of pages. This counter is used for + * for trigger some periodic events. This is straightforward and better + * than using jiffies etc. to handle periodic memcg event. + */ +enum mem_cgroup_events_target { + MEM_CGROUP_TARGET_THRESH, + MEM_CGROUP_TARGET_SOFTLIMIT, + MEM_CGROUP_TARGET_NUMAINFO, + MEM_CGROUP_NTARGETS, +}; + +/* + * Bits in struct cg_proto.flags + */ +enum cg_proto_flags { + /* Currently active and new sockets should be assigned to cgroups */ + MEMCG_SOCK_ACTIVE, + /* It was ever activated; we must disarm static keys on destruction */ + MEMCG_SOCK_ACTIVATED, +}; + +struct cg_proto { + struct page_counter memory_allocated; /* Current allocated memory. */ + struct percpu_counter sockets_allocated; /* Current number of sockets. */ + int memory_pressure; + long sysctl_mem[3]; + unsigned long flags; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; +}; + #ifdef CONFIG_MEMCG +struct mem_cgroup_stat_cpu { + long count[MEM_CGROUP_STAT_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + +struct mem_cgroup_reclaim_iter { + struct mem_cgroup *position; + /* scan generation, increased every round-trip */ + unsigned int generation; +}; + +/* + * per-zone information in memory controller. + */ +struct mem_cgroup_per_zone { + struct lruvec lruvec; + unsigned long lru_size[NR_LRU_LISTS]; + + struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + + struct rb_node tree_node; /* RB tree node */ + unsigned long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ +}; + +struct mem_cgroup_per_node { + struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; +}; + +struct mem_cgroup_threshold { + struct eventfd_ctx *eventfd; + unsigned long threshold; +}; + +/* For threshold */ +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below or equal to usage. */ + int current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +struct mem_cgroup_thresholds { + /* Primary thresholds array */ + struct mem_cgroup_threshold_ary *primary; + /* + * Spare threshold array. + * This is needed to make mem_cgroup_unregister_event() "never fail". + * It must be able to store at least primary->size - 1 entries. + */ + struct mem_cgroup_threshold_ary *spare; +}; + +/* + * The memory controller data structure. The memory controller controls both + * page cache and RSS per cgroup. We would eventually like to provide + * statistics based on the statistics developed by Rik Van Riel for clock-pro, + * to help the administrator determine what knobs to tune. + */ +struct mem_cgroup { + struct cgroup_subsys_state css; + + /* Accounted resources */ + struct page_counter memory; + struct page_counter memsw; + struct page_counter kmem; + + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + + unsigned long soft_limit; + + /* vmpressure notifications */ + struct vmpressure vmpressure; + + /* css_online() has been completed */ + int initialized; + + /* + * Should the accounting and control be hierarchical, per subtree? + */ + bool use_hierarchy; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + int swappiness; + /* OOM-Killer disable */ + int oom_kill_disable; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; + /* + * percpu counter. + */ + struct mem_cgroup_stat_cpu __percpu *stat; + spinlock_t pcp_counter_lock; + +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) + struct cg_proto tcp_mem; +#endif +#if defined(CONFIG_MEMCG_KMEM) + /* Index in the kmem_cache->memcg_params.memcg_caches array */ + int kmemcg_id; + bool kmem_acct_activated; + bool kmem_acct_active; +#endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + + struct mem_cgroup_per_node *nodeinfo[0]; + /* WARNING: nodeinfo must be the last member here */ +}; extern struct cgroup_subsys_state *mem_cgroup_root_css; -void mem_cgroup_events(struct mem_cgroup *memcg, +/** + * 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 + */ +static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, - unsigned int nr); + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); +} bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -90,15 +304,31 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); -bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, - struct mem_cgroup *root); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ + return css ? container_of(css, struct mem_cgroup, css) : NULL; +} + +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); +void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); + +static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, + struct mem_cgroup *root) +{ + if (root == memcg) + return true; + if (!root->use_hierarchy) + return false; + return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); +} static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) @@ -114,22 +344,65 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); -void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +static inline bool mem_cgroup_disabled(void) +{ + if (memory_cgrp_subsys.disabled) + return true; + return false; +} /* * 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); + +void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, + int nr_pages); + +static inline 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); +} + +static inline +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +{ + struct mem_cgroup_per_zone *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + return mz->lru_size[lru]; +} + +static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) +{ + unsigned long inactive_ratio; + unsigned long inactive; + unsigned long active; + unsigned long gb; + + inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); + active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + return inactive * inactive_ratio < active; +} + extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p); @@ -156,18 +429,26 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -static inline bool mem_cgroup_disabled(void) -{ - if (memory_cgrp_subsys.disabled) - return true; - return false; -} - 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); +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, + enum mem_cgroup_stat_index idx, int val) +{ + VM_BUG_ON(!rcu_read_lock_held()); + + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); +} + static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { @@ -184,13 +465,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - __mem_cgroup_count_vm_event(mm, idx); + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + goto out; + + switch (idx) { + case PGFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); + break; + case PGMAJFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); + break; + default: + BUG(); + } +out: + rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); @@ -275,12 +574,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } -static inline struct cgroup_subsys_state - *mem_cgroup_css(struct mem_cgroup *memcg) -{ - return NULL; -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -444,7 +737,10 @@ static inline bool memcg_kmem_enabled(void) return static_key_false(&memcg_kmem_enabled_key); } -bool memcg_kmem_is_active(struct mem_cgroup *memcg); +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return memcg->kmem_acct_active; +} /* * In general, we'll do everything in our power to not incur in any overhead @@ -463,7 +759,15 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order); void __memcg_kmem_uncharge_pages(struct page *page, int order); -int memcg_cache_id(struct mem_cgroup *memcg); +/* + * helper for acessing a memcg's index. It will be used as an index in the + * child cache array in kmem_cache, and also to derive its name. This function + * will return -1 when this is not a kmem-limited memcg. + */ +static inline int memcg_cache_id(struct mem_cgroup *memcg) +{ + return memcg ? memcg->kmemcg_id : -1; +} struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); diff --git a/include/linux/swap.h b/include/linux/swap.h index 6282f1eb3d6a..2ce190709280 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -351,7 +351,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages); extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_MEMCG -extern int mem_cgroup_swappiness(struct mem_cgroup *mem); +static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) +{ + /* root ? */ + if (mem_cgroup_disabled() || !memcg->css.parent) + return vm_swappiness; + + return memcg->swappiness; +} + #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { diff --git a/include/net/sock.h b/include/net/sock.h index 43c6abcf06ab..a98c71ea40c5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1042,34 +1042,6 @@ struct proto { #endif }; -/* - * Bits in struct cg_proto.flags - */ -enum cg_proto_flags { - /* Currently active and new sockets should be assigned to cgroups */ - MEMCG_SOCK_ACTIVE, - /* It was ever activated; we must disarm static keys on destruction */ - MEMCG_SOCK_ACTIVATED, -}; - -struct cg_proto { - struct page_counter memory_allocated; /* Current allocated memory. */ - struct percpu_counter sockets_allocated; /* Current number of sockets. */ - int memory_pressure; - long sysctl_mem[3]; - unsigned long flags; - /* - * memcg field is used to find which memcg we belong directly - * Each memcg struct can hold more than one cg_proto, so container_of - * won't really cut. - * - * The elegant solution would be having an inverse function to - * proto_cgroup in struct proto, but that means polluting the structure - * for everybody, instead of just for memcg users. - */ - struct mem_cgroup *memcg; -}; - int proto_register(struct proto *prot, int alloc_slab); void proto_unregister(struct proto *prot); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9871f13fc35b..6935f77589e7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -111,56 +111,10 @@ static const char * const mem_cgroup_lru_names[] = { "unevictable", }; -/* - * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremated by the number of pages. This counter is used for - * for trigger some periodic events. This is straightforward and better - * than using jiffies etc. to handle periodic memcg event. - */ -enum mem_cgroup_events_target { - MEM_CGROUP_TARGET_THRESH, - MEM_CGROUP_TARGET_SOFTLIMIT, - MEM_CGROUP_TARGET_NUMAINFO, - MEM_CGROUP_NTARGETS, -}; #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 #define NUMAINFO_EVENTS_TARGET 1024 -struct mem_cgroup_stat_cpu { - long count[MEM_CGROUP_STAT_NSTATS]; - unsigned long events[MEMCG_NR_EVENTS]; - unsigned long nr_page_events; - unsigned long targets[MEM_CGROUP_NTARGETS]; -}; - -struct reclaim_iter { - struct mem_cgroup *position; - /* scan generation, increased every round-trip */ - unsigned int generation; -}; - -/* - * per-zone information in memory controller. - */ -struct mem_cgroup_per_zone { - struct lruvec lruvec; - unsigned long lru_size[NR_LRU_LISTS]; - - struct reclaim_iter iter[DEF_PRIORITY + 1]; - - struct rb_node tree_node; /* RB tree node */ - unsigned long usage_in_excess;/* Set to the value by which */ - /* the soft limit is exceeded*/ - bool on_tree; - struct mem_cgroup *memcg; /* Back pointer, we cannot */ - /* use container_of */ -}; - -struct mem_cgroup_per_node { - struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; -}; - /* * Cgroups above their limits are maintained in a RB-Tree, independent of * their hierarchy representation @@ -181,32 +135,6 @@ struct mem_cgroup_tree { static struct mem_cgroup_tree soft_limit_tree __read_mostly; -struct mem_cgroup_threshold { - struct eventfd_ctx *eventfd; - unsigned long threshold; -}; - -/* For threshold */ -struct mem_cgroup_threshold_ary { - /* An array index points to threshold just below or equal to usage. */ - int current_threshold; - /* Size of entries[] */ - unsigned int size; - /* Array of thresholds */ - struct mem_cgroup_threshold entries[0]; -}; - -struct mem_cgroup_thresholds { - /* Primary thresholds array */ - struct mem_cgroup_threshold_ary *primary; - /* - * Spare threshold array. - * This is needed to make mem_cgroup_unregister_event() "never fail". - * It must be able to store at least primary->size - 1 entries. - */ - struct mem_cgroup_threshold_ary *spare; -}; - /* for OOM */ struct mem_cgroup_eventfd_list { struct list_head list; @@ -256,113 +184,6 @@ struct mem_cgroup_event { static void mem_cgroup_threshold(struct mem_cgroup *memcg); static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); -/* - * The memory controller data structure. The memory controller controls both - * page cache and RSS per cgroup. We would eventually like to provide - * statistics based on the statistics developed by Rik Van Riel for clock-pro, - * to help the administrator determine what knobs to tune. - */ -struct mem_cgroup { - struct cgroup_subsys_state css; - - /* Accounted resources */ - struct page_counter memory; - struct page_counter memsw; - struct page_counter kmem; - - /* Normal memory consumption range */ - unsigned long low; - unsigned long high; - - unsigned long soft_limit; - - /* vmpressure notifications */ - struct vmpressure vmpressure; - - /* css_online() has been completed */ - int initialized; - - /* - * Should the accounting and control be hierarchical, per subtree? - */ - bool use_hierarchy; - - /* protected by memcg_oom_lock */ - bool oom_lock; - int under_oom; - - int swappiness; - /* OOM-Killer disable */ - int oom_kill_disable; - - /* protect arrays of thresholds */ - struct mutex thresholds_lock; - - /* thresholds for memory usage. RCU-protected */ - struct mem_cgroup_thresholds thresholds; - - /* thresholds for mem+swap usage. RCU-protected */ - struct mem_cgroup_thresholds memsw_thresholds; - - /* For oom notifier event fd */ - struct list_head oom_notify; - - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; - struct task_struct *move_lock_task; - unsigned long move_lock_flags; - /* - * percpu counter. - */ - struct mem_cgroup_stat_cpu __percpu *stat; - spinlock_t pcp_counter_lock; - -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) - struct cg_proto tcp_mem; -#endif -#if defined(CONFIG_MEMCG_KMEM) - /* Index in the kmem_cache->memcg_params.memcg_caches array */ - int kmemcg_id; - bool kmem_acct_activated; - bool kmem_acct_active; -#endif - - int last_scanned_node; -#if MAX_NUMNODES > 1 - nodemask_t scan_nodes; - atomic_t numainfo_events; - atomic_t numainfo_updating; -#endif - -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; - struct wb_domain cgwb_domain; -#endif - - /* List of events which userspace want to receive */ - struct list_head event_list; - spinlock_t event_list_lock; - - struct mem_cgroup_per_node *nodeinfo[0]; - /* WARNING: nodeinfo must be the last member here */ -}; - -#ifdef CONFIG_MEMCG_KMEM -bool memcg_kmem_is_active(struct mem_cgroup *memcg) -{ - return memcg->kmem_acct_active; -} -#endif - /* Stuffs for move charges at task migration. */ /* * Types of charges to be moved. @@ -423,11 +244,6 @@ enum res_type { */ static DEFINE_MUTEX(memcg_create_mutex); -struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) -{ - return s ? container_of(s, struct mem_cgroup, css) : NULL; -} - /* Some nice accessors for the vmpressure. */ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) { @@ -593,11 +409,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) return &memcg->nodeinfo[nid]->zoneinfo[zid]; } -struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg) -{ - return &memcg->css; -} - /** * mem_cgroup_css_from_page - css of the memcg associated with a page * @page: page of interest @@ -876,14 +687,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, __this_cpu_add(memcg->stat->nr_page_events, nr_pages); } -unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) -{ - struct mem_cgroup_per_zone *mz; - - mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); - return mz->lru_size[lru]; -} - static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int nid, unsigned int lru_mask) @@ -986,6 +789,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p) return mem_cgroup_from_css(task_css(p, memory_cgrp_id)); } +EXPORT_SYMBOL(mem_cgroup_from_task); static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { @@ -1031,7 +835,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { - struct reclaim_iter *uninitialized_var(iter); + struct mem_cgroup_reclaim_iter *uninitialized_var(iter); struct cgroup_subsys_state *css = NULL; struct mem_cgroup *memcg = NULL; struct mem_cgroup *pos = NULL; @@ -1173,30 +977,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *root, iter != NULL; \ iter = mem_cgroup_iter(NULL, iter, NULL)) -void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) -{ - struct mem_cgroup *memcg; - - rcu_read_lock(); - memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); - if (unlikely(!memcg)) - goto out; - - switch (idx) { - case PGFAULT: - this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); - break; - case PGMAJFAULT: - this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); - break; - default: - BUG(); - } -out: - rcu_read_unlock(); -} -EXPORT_SYMBOL(__mem_cgroup_count_vm_event); - /** * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg * @zone: zone of the wanted lruvec @@ -1295,15 +1075,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, VM_BUG_ON((long)(*lru_size) < 0); } -bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) -{ - if (root == memcg) - return true; - if (!root->use_hierarchy) - return false; - return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); -} - bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; @@ -1330,39 +1101,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg) return ret; } -int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) -{ - unsigned long inactive_ratio; - unsigned long inactive; - unsigned long active; - unsigned long gb; - - inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); - active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); - - gb = (inactive + active) >> (30 - PAGE_SHIFT); - if (gb) - inactive_ratio = int_sqrt(10 * gb); - else - inactive_ratio = 1; - - 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) @@ -1394,15 +1132,6 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) return margin; } -int mem_cgroup_swappiness(struct mem_cgroup *memcg) -{ - /* root ? */ - if (mem_cgroup_disabled() || !memcg->css.parent) - return vm_swappiness; - - return memcg->swappiness; -} - /* * A routine for checking "mem" is under move_account() or not. * @@ -2067,23 +1796,6 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) } EXPORT_SYMBOL(mem_cgroup_end_page_stat); -/** - * mem_cgroup_update_page_stat - update page state statistics - * @memcg: memcg to account against - * @idx: page state item to account - * @val: number of pages (positive or negative) - * - * See mem_cgroup_begin_page_stat() for locking requirements. - */ -void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, - enum mem_cgroup_stat_index idx, int val) -{ - VM_BUG_ON(!rcu_read_lock_held()); - - if (memcg) - this_cpu_add(memcg->stat->count[idx], val); -} - /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. @@ -2509,16 +2221,6 @@ void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages) css_put_many(&memcg->css, nr_pages); } -/* - * helper for acessing a memcg's index. It will be used as an index in the - * child cache array in kmem_cache, and also to derive its name. This function - * will return -1 when this is not a kmem-limited memcg. - */ -int memcg_cache_id(struct mem_cgroup *memcg) -{ - return memcg ? memcg->kmemcg_id : -1; -} - static int memcg_alloc_cache_id(void) { int id, size; @@ -5525,19 +5227,6 @@ struct cgroup_subsys memory_cgrp_subsys = { .early_init = 0, }; -/** - * 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 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 1f4446a90cef..016c814101ed 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -146,7 +146,7 @@ static int hwpoison_filter_task(struct page *p) if (!mem) return -EINVAL; - css = mem_cgroup_css(mem); + css = &mem->css; ino = cgroup_ino(css->cgroup); css_put(css); diff --git a/mm/slab_common.c b/mm/slab_common.c index bde04a699ab6..5ce4faeb16fb 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -500,7 +500,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, struct kmem_cache *root_cache) { static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ - struct cgroup_subsys_state *css = mem_cgroup_css(memcg); + struct cgroup_subsys_state *css = &memcg->css; struct memcg_cache_array *arr; struct kmem_cache *s = NULL; char *cache_name; diff --git a/mm/vmscan.c b/mm/vmscan.c index b1139039122a..bf23c88621ce 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -175,7 +175,7 @@ static bool sane_reclaim(struct scan_control *sc) if (!memcg) return true; #ifdef CONFIG_CGROUP_WRITEBACK - if (cgroup_on_dfl(mem_cgroup_css(memcg)->cgroup)) + if (memcg->css.cgroup) return true; #endif return false; -- cgit v1.2.3-70-g09d2 From 7d1900c744b2e4687b3e467edf58373c02bcf22d Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 8 Sep 2015 15:03:10 -0700 Subject: mm/hwpoison: fix failure to split thp w/ refcount held THP pages will get a refcount in madvise_hwpoison() w/ MF_COUNT_INCREASED flag, however, the refcount is still held when fail to split THP pages. Fix it by reducing the refcount of THP pages when fail to split THP. Signed-off-by: Wanpeng Li Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 016c814101ed..8ad923a93539 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1725,6 +1725,8 @@ int soft_offline_page(struct page *page, int flags) if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) { pr_info("soft offline: %#lx: failed to split THP\n", pfn); + if (flags & MF_COUNT_INCREASED) + put_page(page); return -EBUSY; } } -- cgit v1.2.3-70-g09d2 From 1e0e635be82132167a134b5a9c884e70e61f8373 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 8 Sep 2015 15:03:13 -0700 Subject: mm/hwpoison: fix PageHWPoison test/set race There is a race between madvise_hwpoison path and memory_failure: CPU0 CPU1 madvise_hwpoison get_user_pages_fast PageHWPoison check (false) memory_failure TestSetPageHWPoison soft_offline_page PageHWPoison check (true) return -EBUSY (without put_page) Signed-off-by: Wanpeng Li Suggested-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8ad923a93539..863544d84a09 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1719,6 +1719,8 @@ int soft_offline_page(struct page *page, int flags) if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); + if (flags & MF_COUNT_INCREASED) + put_page(page); return -EBUSY; } if (!PageHuge(page) && PageTransHuge(hpage)) { -- cgit v1.2.3-70-g09d2 From 94bf4ec84a84d3ab2513b4e681fd3d083328d76d Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 8 Sep 2015 15:03:15 -0700 Subject: mm/hwpoison: introduce put_hwpoison_page to put refcount for memory error handling Introduce put_hwpoison_page to put refcount for memory error handling. Signed-off-by: Wanpeng Li Suggested-by: Naoya Horiguchi Acked-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/memory-failure.c | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/include/linux/mm.h b/include/linux/mm.h index bab8ff89da50..11df1a8ea38b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2169,6 +2169,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); +extern void put_hwpoison_page(struct page *page); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 863544d84a09..5ceb8253e33b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -934,6 +934,27 @@ int get_hwpoison_page(struct page *page) } EXPORT_SYMBOL_GPL(get_hwpoison_page); +/** + * put_hwpoison_page() - Put refcount for memory error handling: + * @page: raw error page (hit by memory error) + */ +void put_hwpoison_page(struct page *page) +{ + struct page *head = compound_head(page); + + if (PageHuge(head)) { + put_page(head); + return; + } + + if (PageTransHuge(head)) + if (page != head) + put_page(head); + + put_page(page); +} +EXPORT_SYMBOL_GPL(put_hwpoison_page); + /* * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. -- cgit v1.2.3-70-g09d2 From 665d9da7f0a9bd80b64d0024630806e45c7ff7d7 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 8 Sep 2015 15:03:21 -0700 Subject: mm/hwpoison: replace most of put_page in memory error handling by put_hwpoison_page Replace most instances of put_page() in memory error handling with put_hwpoison_page(). Signed-off-by: Wanpeng Li Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5ceb8253e33b..5420d3819adf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1174,9 +1174,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) atomic_long_sub(nr_pages, &num_poisoned_pages); - put_page(p); - if (p != hpage) - put_page(hpage); + put_hwpoison_page(p); return -EBUSY; } VM_BUG_ON_PAGE(!page_count(p), p); @@ -1237,14 +1235,14 @@ int memory_failure(unsigned long pfn, int trapno, int flags) printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); atomic_long_sub(nr_pages, &num_poisoned_pages); unlock_page(hpage); - put_page(hpage); + put_hwpoison_page(hpage); return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) atomic_long_sub(nr_pages, &num_poisoned_pages); unlock_page(hpage); - put_page(hpage); + put_hwpoison_page(hpage); return 0; } @@ -1258,7 +1256,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) { action_result(pfn, MF_MSG_POISONED_HUGE, MF_IGNORED); unlock_page(hpage); - put_page(hpage); + put_hwpoison_page(hpage); return 0; } /* @@ -1492,9 +1490,9 @@ int unpoison_memory(unsigned long pfn) } unlock_page(page); - put_page(page); + put_hwpoison_page(page); if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) - put_page(page); + put_hwpoison_page(page); return 0; } @@ -1554,7 +1552,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) /* * Try to free it. */ - put_page(page); + put_hwpoison_page(page); shake_page(page, 1); /* @@ -1563,7 +1561,7 @@ static int get_any_page(struct page *page, unsigned long pfn, int flags) ret = __get_any_page(page, pfn, 0); if (!PageLRU(page)) { /* Drop page reference which is from __get_any_page() */ - put_page(page); + put_hwpoison_page(page); pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n", pfn, page->flags); return -EIO; @@ -1586,7 +1584,7 @@ static int soft_offline_huge_page(struct page *page, int flags) lock_page(hpage); if (PageHWPoison(hpage)) { unlock_page(hpage); - put_page(hpage); + put_hwpoison_page(hpage); pr_info("soft offline: %#lx hugepage already poisoned\n", pfn); return -EBUSY; } @@ -1597,7 +1595,7 @@ static int soft_offline_huge_page(struct page *page, int flags) * get_any_page() and isolate_huge_page() takes a refcount each, * so need to drop one here. */ - put_page(hpage); + put_hwpoison_page(hpage); if (!ret) { pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn); return -EBUSY; @@ -1646,7 +1644,7 @@ static int __soft_offline_page(struct page *page, int flags) wait_on_page_writeback(page); if (PageHWPoison(page)) { unlock_page(page); - put_page(page); + put_hwpoison_page(page); pr_info("soft offline: %#lx page already poisoned\n", pfn); return -EBUSY; } @@ -1661,7 +1659,7 @@ static int __soft_offline_page(struct page *page, int flags) * would need to fix isolation locking first. */ if (ret == 1) { - put_page(page); + put_hwpoison_page(page); pr_info("soft_offline: %#lx: invalidated\n", pfn); SetPageHWPoison(page); atomic_long_inc(&num_poisoned_pages); @@ -1678,7 +1676,7 @@ static int __soft_offline_page(struct page *page, int flags) * Drop page reference which is came from get_any_page() * successful isolate_lru_page() already took another one. */ - put_page(page); + put_hwpoison_page(page); if (!ret) { LIST_HEAD(pagelist); inc_zone_page_state(page, NR_ISOLATED_ANON + @@ -1741,7 +1739,7 @@ int soft_offline_page(struct page *page, int flags) if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); if (flags & MF_COUNT_INCREASED) - put_page(page); + put_hwpoison_page(page); return -EBUSY; } if (!PageHuge(page) && PageTransHuge(hpage)) { @@ -1749,7 +1747,7 @@ int soft_offline_page(struct page *page, int flags) pr_info("soft offline: %#lx: failed to split THP\n", pfn); if (flags & MF_COUNT_INCREASED) - put_page(page); + put_hwpoison_page(page); return -EBUSY; } } -- cgit v1.2.3-70-g09d2 From 8e30456b6c56029ecbb43b777519175e478adfbf Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 8 Sep 2015 15:03:24 -0700 Subject: mm/hwpoison: introduce num_poisoned_pages wrappers num_poisoned_pages counter will be changed outside mm/memory-failure.c by a subsequent patch, so this patch prepares wrappers to manipulate it. Signed-off-by: Naoya Horiguchi Tested-by: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 23 +++++++++++++++++++++++ mm/memory-failure.c | 30 ++++++++++++++---------------- 2 files changed, 37 insertions(+), 16 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cedf3d3c373f..ec04669f2a3b 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -164,6 +164,9 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif #ifdef CONFIG_MEMORY_FAILURE + +extern atomic_long_t num_poisoned_pages __read_mostly; + /* * Support for hardware poisoned pages */ @@ -177,6 +180,26 @@ static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } + +static inline void num_poisoned_pages_inc(void) +{ + atomic_long_inc(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_dec(void) +{ + atomic_long_dec(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_add(long num) +{ + atomic_long_add(num, &num_poisoned_pages); +} + +static inline void num_poisoned_pages_sub(long num) +{ + atomic_long_sub(num, &num_poisoned_pages); +} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5420d3819adf..393ea13b0754 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1121,7 +1121,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) nr_pages = 1 << compound_order(hpage); else /* normal page or thp */ nr_pages = 1; - atomic_long_add(nr_pages, &num_poisoned_pages); + num_poisoned_pages_add(nr_pages); /* * We need/can do nothing about count=0 pages. @@ -1149,7 +1149,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (PageHWPoison(hpage)) { if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) || (p != hpage && TestSetPageHWPoison(hpage))) { - atomic_long_sub(nr_pages, &num_poisoned_pages); + num_poisoned_pages_sub(nr_pages); unlock_page(hpage); return 0; } @@ -1173,7 +1173,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) else pr_err("MCE: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &num_poisoned_pages); + num_poisoned_pages_sub(nr_pages); put_hwpoison_page(p); return -EBUSY; } @@ -1233,14 +1233,14 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (!PageHWPoison(p)) { printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn); - atomic_long_sub(nr_pages, &num_poisoned_pages); + num_poisoned_pages_sub(nr_pages); unlock_page(hpage); put_hwpoison_page(hpage); return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) - atomic_long_sub(nr_pages, &num_poisoned_pages); + num_poisoned_pages_sub(nr_pages); unlock_page(hpage); put_hwpoison_page(hpage); return 0; @@ -1469,7 +1469,7 @@ int unpoison_memory(unsigned long pfn) return 0; } if (TestClearPageHWPoison(p)) - atomic_long_dec(&num_poisoned_pages); + num_poisoned_pages_dec(); pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn); return 0; } @@ -1483,7 +1483,7 @@ int unpoison_memory(unsigned long pfn) */ if (TestClearPageHWPoison(page)) { pr_info("MCE: Software-unpoisoned page %#lx\n", pfn); - atomic_long_sub(nr_pages, &num_poisoned_pages); + num_poisoned_pages_sub(nr_pages); freeit = 1; if (PageHuge(page)) clear_page_hwpoison_huge_page(page); @@ -1619,11 +1619,10 @@ static int soft_offline_huge_page(struct page *page, int flags) if (PageHuge(page)) { set_page_hwpoison_huge_page(hpage); dequeue_hwpoisoned_huge_page(hpage); - atomic_long_add(1 << compound_order(hpage), - &num_poisoned_pages); + num_poisoned_pages_add(1 << compound_order(hpage)); } else { SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); + num_poisoned_pages_inc(); } } return ret; @@ -1662,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags) put_hwpoison_page(page); pr_info("soft_offline: %#lx: invalidated\n", pfn); SetPageHWPoison(page); - atomic_long_inc(&num_poisoned_pages); + num_poisoned_pages_inc(); return 0; } @@ -1683,7 +1682,7 @@ static int __soft_offline_page(struct page *page, int flags) page_is_file_cache(page)); list_add(&page->lru, &pagelist); if (!TestSetPageHWPoison(page)) - atomic_long_inc(&num_poisoned_pages); + num_poisoned_pages_dec(); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { @@ -1699,7 +1698,7 @@ static int __soft_offline_page(struct page *page, int flags) if (ret > 0) ret = -EIO; if (TestClearPageHWPoison(page)) - atomic_long_dec(&num_poisoned_pages); + num_poisoned_pages_dec(); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", @@ -1765,11 +1764,10 @@ int soft_offline_page(struct page *page, int flags) if (PageHuge(page)) { set_page_hwpoison_huge_page(hpage); if (!dequeue_hwpoisoned_huge_page(hpage)) - atomic_long_add(1 << compound_order(hpage), - &num_poisoned_pages); + num_poisoned_pages_add(1 << compound_order(hpage)); } else { if (!TestSetPageHWPoison(page)) - atomic_long_inc(&num_poisoned_pages); + num_poisoned_pages_inc(); } } return ret; -- cgit v1.2.3-70-g09d2 From da1b13ccfbebe0b9d69b5d61eff0a675e19e69a5 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Tue, 8 Sep 2015 15:03:27 -0700 Subject: mm/hwpoison: fix race between soft_offline_page and unpoison_memory Wanpeng Li reported a race between soft_offline_page() and unpoison_memory(), which causes the following kernel panic: BUG: Bad page state in process bash pfn:97000 page:ffffea00025c0000 count:0 mapcount:1 mapping: (null) index:0x7f4fdbe00 flags: 0x1fffff80080048(uptodate|active|swapbacked) page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set bad because of flags: flags: 0x40(active) Modules linked in: snd_hda_codec_hdmi i915 rpcsec_gss_krb5 nfsv4 dns_resolver bnep rfcomm nfsd bluetooth auth_rpcgss nfs_acl nfs rfkill lockd grace sunrpc i2c_algo_bit drm_kms_helper snd_hda_codec_realtek snd_hda_codec_generic drm snd_hda_intel fscache snd_hda_codec x86_pkg_temp_thermal coretemp kvm_intel snd_hda_core snd_hwdep kvm snd_pcm snd_seq_dummy snd_seq_oss crct10dif_pclmul snd_seq_midi crc32_pclmul snd_seq_midi_event ghash_clmulni_intel snd_rawmidi aesni_intel lrw gf128mul snd_seq glue_helper ablk_helper snd_seq_device cryptd fuse snd_timer dcdbas serio_raw mei_me parport_pc snd mei ppdev i2c_core video lp soundcore parport lpc_ich shpchp mfd_core ext4 mbcache jbd2 sd_mod e1000e ahci ptp libahci crc32c_intel libata pps_core CPU: 3 PID: 2211 Comm: bash Not tainted 4.2.0-rc5-mm1+ #45 Hardware name: Dell Inc. OptiPlex 7020/0F5C5X, BIOS A03 01/08/2015 Call Trace: dump_stack+0x48/0x5c bad_page+0xe6/0x140 free_pages_prepare+0x2f9/0x320 ? uncharge_list+0xdd/0x100 free_hot_cold_page+0x40/0x170 __put_single_page+0x20/0x30 put_page+0x25/0x40 unmap_and_move+0x1a6/0x1f0 migrate_pages+0x100/0x1d0 ? kill_procs+0x100/0x100 ? unlock_page+0x6f/0x90 __soft_offline_page+0x127/0x2a0 soft_offline_page+0xa6/0x200 This race is explained like below: CPU0 CPU1 soft_offline_page __soft_offline_page TestSetPageHWPoison unpoison_memory PageHWPoison check (true) TestClearPageHWPoison put_page -> release refcount held by get_hwpoison_page in unpoison_memory put_page -> release refcount held by isolate_lru_page in __soft_offline_page migrate_pages The second put_page() releases refcount held by isolate_lru_page() which will lead to unmap_and_move() releases the last refcount of page and w/ mapcount still 1 since try_to_unmap() is not called if there is only one user map the page. Anyway, the page refcount and mapcount will still mess if the page is mapped by multiple users. This race was introduced by commit 4491f71260 ("mm/memory-failure: set PageHWPoison before migrate_pages()"), which focuses on preventing the reuse of successfully migrated page. Before this commit we prevent the reuse by changing the migratetype to MIGRATE_ISOLATE during soft offlining, which has the following problems, so simply reverting the commit is not a best option: 1) it doesn't eliminate the reuse completely, because set_migratetype_isolate() can fail to set MIGRATE_ISOLATE to the target page if the pageblock of the page contains one or more unmovable pages (i.e. has_unmovable_pages() returns true). 2) the original code changes migratetype to MIGRATE_ISOLATE forcibly, and sets it to MIGRATE_MOVABLE forcibly after soft offline, regardless of the original migratetype state, which could impact other subsystems like memory hotplug or compaction. This patch moves PageSetHWPoison just after put_page() in unmap_and_move(), which closes up the reported race window and minimizes another race window b/w SetPageHWPoison and reallocation (which causes the reuse of soft-offlined page.) The latter race window still exists but it's acceptable, because it's rare and effectively the same as ordinary "containment failure" case even if it happens, so keep the window open is acceptable. Fixes: 4491f71260 ("mm/memory-failure: set PageHWPoison before migrate_pages()") Signed-off-by: Wanpeng Li Signed-off-by: Naoya Horiguchi Reported-by: Wanpeng Li Tested-by: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapops.h | 14 ++++++++++++++ mm/memory-failure.c | 4 ---- mm/migrate.c | 9 +++++---- 3 files changed, 19 insertions(+), 8 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index ec04669f2a3b..5c3a5f3e7eec 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -181,6 +181,11 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } +static inline bool test_set_page_hwpoison(struct page *page) +{ + return TestSetPageHWPoison(page); +} + static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); @@ -211,6 +216,15 @@ static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } + +static inline bool test_set_page_hwpoison(struct page *page) +{ + return false; +} + +static inline void num_poisoned_pages_inc(void) +{ +} #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 393ea13b0754..b0664c23838b 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1681,8 +1681,6 @@ static int __soft_offline_page(struct page *page, int flags) inc_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); list_add(&page->lru, &pagelist); - if (!TestSetPageHWPoison(page)) - num_poisoned_pages_dec(); ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL, MIGRATE_SYNC, MR_MEMORY_FAILURE); if (ret) { @@ -1697,8 +1695,6 @@ static int __soft_offline_page(struct page *page, int flags) pfn, ret, page->flags); if (ret > 0) ret = -EIO; - if (TestClearPageHWPoison(page)) - num_poisoned_pages_dec(); } } else { pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n", diff --git a/mm/migrate.c b/mm/migrate.c index 5c08cab5419e..918defbdda0e 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -880,8 +880,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, /* Establish migration ptes or remove ptes */ if (page_mapped(page)) { try_to_unmap(page, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| - TTU_IGNORE_HWPOISON); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); page_was_mapped = 1; } @@ -952,9 +951,11 @@ out: dec_zone_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); /* Soft-offlined page shouldn't go through lru cache list */ - if (reason == MR_MEMORY_FAILURE) + if (reason == MR_MEMORY_FAILURE) { put_page(page); - else + if (!test_set_page_hwpoison(page)) + num_poisoned_pages_inc(); + } else putback_lru_page(page); } -- cgit v1.2.3-70-g09d2 From 230ac719c500e58e71342be381ad2042a8cffc42 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Tue, 8 Sep 2015 15:03:29 -0700 Subject: mm/hwpoison: don't try to unpoison containment-failed pages memory_failure() can be called at any page at any time, which means that we can't eliminate the possibility of containment failure. In such case the best option is to leak the page intentionally (and never touch it later.) We have an unpoison function for testing, and it cannot handle such containment-failed pages, which results in kernel panic (visible with various calltraces.) So this patch suggests that we limit the unpoisonable pages to properly contained pages and ignore any other ones. Testers are recommended to keep in mind that there're un-unpoisonable pages when writing test programs. Signed-off-by: Naoya Horiguchi Tested-by: Wanpeng Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'mm/memory-failure.c') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index b0664c23838b..bba2d7c2c9ce 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1445,6 +1445,22 @@ int unpoison_memory(unsigned long pfn) return 0; } + if (page_count(page) > 1) { + pr_info("MCE: Someone grabs the hwpoison page %#lx\n", pfn); + return 0; + } + + if (page_mapped(page)) { + pr_info("MCE: Someone maps the hwpoison page %#lx\n", pfn); + return 0; + } + + if (page_mapping(page)) { + pr_info("MCE: the hwpoison page has non-NULL mapping %#lx\n", + pfn); + return 0; + } + /* * unpoison_memory() can encounter thp only when the thp is being * worked by memory_failure() and the page lock is not held yet. -- cgit v1.2.3-70-g09d2 From 96db800f5d73cd5c49461253d45766e094f0f8c2 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 8 Sep 2015 15:03:50 -0700 Subject: mm: rename alloc_pages_exact_node() to __alloc_pages_node() alloc_pages_exact_node() was introduced in commit 6484eb3e2a81 ("page allocator: do not check NUMA node ID when the caller knows the node is valid") as an optimized variant of alloc_pages_node(), that doesn't fallback to current node for nid == NUMA_NO_NODE. Unfortunately the name of the function can easily suggest that the allocation is restricted to the given node and fails otherwise. In truth, the node is only preferred, unless __GFP_THISNODE is passed among the gfp flags. The misleading name has lead to mistakes in the past, see for example commits 5265047ac301 ("mm, thp: really limit transparent hugepage allocation to local node") and b360edb43f8e ("mm, mempolicy: migrate_to_node should only migrate to node"). Another issue with the name is that there's a family of alloc_pages_exact*() functions where 'exact' means exact size (instead of page order), which leads to more confusion. To prevent further mistakes, this patch effectively renames alloc_pages_exact_node() to __alloc_pages_node() to better convey that it's an optimized variant of alloc_pages_node() not intended for general usage. Both functions get described in comments. It has been also considered to really provide a convenience function for allocations restricted to a node, but the major opinion seems to be that __GFP_THISNODE already provides that functionality and we shouldn't duplicate the API needlessly. The number of users would be small anyway. Existing callers of alloc_pages_exact_node() are simply converted to call __alloc_pages_node(), with the exception of sba_alloc_coherent() which open-codes the check for NUMA_NO_NODE, so it is converted to use alloc_pages_node() instead. This means it no longer performs some VM_BUG_ON checks, and since the current check for nid in alloc_pages_node() uses a 'nid < 0' comparison (which includes NUMA_NO_NODE), it may hide wrong values which would be previously exposed. Both differences will be rectified by the next patch. To sum up, this patch makes no functional changes, except temporarily hiding potentially buggy callers. Restricting the checks in alloc_pages_node() is left for the next patch which can in turn expose more existing buggy callers. Signed-off-by: Vlastimil Babka Acked-by: Johannes Weiner Acked-by: Robin Holt Acked-by: Michal Hocko Acked-by: Christoph Lameter Acked-by: Michael Ellerman Cc: Mel Gorman Cc: David Rientjes Cc: Greg Thelen Cc: Aneesh Kumar K.V Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Naoya Horiguchi Cc: Tony Luck Cc: Fenghua Yu Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Gleb Natapov Cc: Paolo Bonzini Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Cliff Whickman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/hp/common/sba_iommu.c | 6 +----- arch/ia64/kernel/uncached.c | 2 +- arch/ia64/sn/pci/pci_dma.c | 2 +- arch/powerpc/platforms/cell/ras.c | 2 +- arch/x86/kvm/vmx.c | 2 +- drivers/misc/sgi-xp/xpc_uv.c | 2 +- include/linux/gfp.h | 23 +++++++++++++++-------- kernel/profile.c | 8 ++++---- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/hugetlb.c | 4 ++-- mm/memory-failure.c | 2 +- mm/mempolicy.c | 4 ++-- mm/migrate.c | 4 ++-- mm/page_alloc.c | 2 -- mm/slab.c | 2 +- mm/slob.c | 4 ++-- mm/slub.c | 2 +- 18 files changed, 38 insertions(+), 37 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c index 344387a55406..a6d6190c9d24 100644 --- a/arch/ia64/hp/common/sba_iommu.c +++ b/arch/ia64/hp/common/sba_iommu.c @@ -1140,13 +1140,9 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, #ifdef CONFIG_NUMA { - int node = ioc->node; struct page *page; - if (node == NUMA_NO_NODE) - node = numa_node_id(); - - page = alloc_pages_exact_node(node, flags, get_order(size)); + page = alloc_pages_node(ioc->node, flags, get_order(size)); if (unlikely(!page)) return NULL; diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c index 20e8a9b21d75..f3976da36721 100644 --- a/arch/ia64/kernel/uncached.c +++ b/arch/ia64/kernel/uncached.c @@ -97,7 +97,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid) /* attempt to allocate a granule's worth of cached memory pages */ - page = alloc_pages_exact_node(nid, + page = __alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, IA64_GRANULE_SHIFT-PAGE_SHIFT); if (!page) { diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c index d0853e8e8623..8f59907007cb 100644 --- a/arch/ia64/sn/pci/pci_dma.c +++ b/arch/ia64/sn/pci/pci_dma.c @@ -92,7 +92,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size, */ node = pcibus_to_node(pdev->bus); if (likely(node >=0)) { - struct page *p = alloc_pages_exact_node(node, + struct page *p = __alloc_pages_node(node, flags, get_order(size)); if (likely(p)) diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c index e865d748179b..2d4f60c0119a 100644 --- a/arch/powerpc/platforms/cell/ras.c +++ b/arch/powerpc/platforms/cell/ras.c @@ -123,7 +123,7 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order) area->nid = nid; area->order = order; - area->pages = alloc_pages_exact_node(area->nid, + area->pages = __alloc_pages_node(area->nid, GFP_KERNEL|__GFP_THISNODE, area->order); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4a4eec30cc08..148ea2016022 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -3150,7 +3150,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu) struct page *pages; struct vmcs *vmcs; - pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order); + pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order); if (!pages) return NULL; vmcs = page_address(pages); diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 95c894482fdd..340b44d9e8cf 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -239,7 +239,7 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name, mq->mmr_blade = uv_cpu_to_blade_id(cpu); nid = cpu_to_node(cpu); - page = alloc_pages_exact_node(nid, + page = __alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, pg_order); if (page == NULL) { diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 3bd64b115999..d2c142bc872e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -303,20 +303,28 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); } -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +/* + * Allocate pages, preferring the node given as nid. The node must be valid and + * online. For more general interface, see alloc_pages_node(). + */ +static inline struct page * +__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - /* Unknown node is current node */ - if (nid < 0) - nid = numa_node_id(); + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid)); return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } -static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask, +/* + * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, + * prefer the current CPU's node. + */ +static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid)); + /* Unknown node is current node */ + if (nid < 0) + nid = numa_node_id(); return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } @@ -357,7 +365,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); -/* This is different from alloc_pages_exact_node !!! */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ diff --git a/kernel/profile.c b/kernel/profile.c index a7bcd28d6e9f..99513e1160e5 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -339,7 +339,7 @@ static int profile_cpu_callback(struct notifier_block *info, node = cpu_to_mem(cpu); per_cpu(cpu_profile_flip, cpu) = 0; if (!per_cpu(cpu_profile_hits, cpu)[1]) { - page = alloc_pages_exact_node(node, + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -347,7 +347,7 @@ static int profile_cpu_callback(struct notifier_block *info, per_cpu(cpu_profile_hits, cpu)[1] = page_address(page); } if (!per_cpu(cpu_profile_hits, cpu)[0]) { - page = alloc_pages_exact_node(node, + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); if (!page) @@ -543,14 +543,14 @@ static int create_hash_tables(void) int node = cpu_to_mem(cpu); struct page *page; - page = alloc_pages_exact_node(node, + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) goto out_cleanup; per_cpu(cpu_profile_hits, cpu)[1] = (struct profile_hit *)page_address(page); - page = alloc_pages_exact_node(node, + page = __alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE, 0); if (!page) diff --git a/mm/filemap.c b/mm/filemap.c index 30d69c0c5a38..72940fb38666 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -674,7 +674,7 @@ struct page *__page_cache_alloc(gfp_t gfp) do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - page = alloc_pages_exact_node(n, gfp, 0); + page = __alloc_pages_node(n, gfp, 0); } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); return page; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 71a4822c832b..883f613ada7e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2414,7 +2414,7 @@ khugepaged_alloc_page(struct page **hpage, gfp_t gfp, struct mm_struct *mm, */ up_read(&mm->mmap_sem); - *hpage = alloc_pages_exact_node(node, gfp, HPAGE_PMD_ORDER); + *hpage = __alloc_pages_node(node, gfp, HPAGE_PMD_ORDER); if (unlikely(!*hpage)) { count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cd1280c487ff..999fb0aef8f1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1331,7 +1331,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; - page = alloc_pages_exact_node(nid, + page = __alloc_pages_node(nid, htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); @@ -1483,7 +1483,7 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid) __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); else - page = alloc_pages_exact_node(nid, + page = __alloc_pages_node(nid, htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE| __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h)); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bba2d7c2c9ce..eeda6485e76c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1521,7 +1521,7 @@ static struct page *new_page(struct page *p, unsigned long private, int **x) return alloc_huge_page_node(page_hstate(compound_head(p)), nid); else - return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0); + return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0); } /* diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d6f2caee28c0..87a177917cb2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -942,7 +942,7 @@ static struct page *new_node_page(struct page *page, unsigned long node, int **x return alloc_huge_page_node(page_hstate(compound_head(page)), node); else - return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE | + return __alloc_pages_node(node, GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } @@ -1998,7 +1998,7 @@ retry_cpuset: nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); - page = alloc_pages_exact_node(hpage_node, + page = __alloc_pages_node(hpage_node, gfp | __GFP_THISNODE, order); goto out; } diff --git a/mm/migrate.c b/mm/migrate.c index 918defbdda0e..02ce25df16c2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1195,7 +1195,7 @@ static struct page *new_page_node(struct page *p, unsigned long private, return alloc_huge_page_node(page_hstate(compound_head(p)), pm->node); else - return alloc_pages_exact_node(pm->node, + return __alloc_pages_node(pm->node, GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } @@ -1555,7 +1555,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, int nid = (int) data; struct page *newpage; - newpage = alloc_pages_exact_node(nid, + newpage = __alloc_pages_node(nid, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 252665d553b4..bdaa0cf8fd41 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3511,8 +3511,6 @@ EXPORT_SYMBOL(alloc_pages_exact); * * Like alloc_pages_exact(), but try to allocate on node nid first before falling * back. - * Note this is not alloc_pages_exact_node() which allocates on a specific node, - * but is not exact. */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) { diff --git a/mm/slab.c b/mm/slab.c index 60c936938b84..c77ebe6cc87c 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1595,7 +1595,7 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, if (memcg_charge_slab(cachep, flags, cachep->gfporder)) return NULL; - page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); + page = __alloc_pages_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); if (!page) { memcg_uncharge_slab(cachep, cachep->gfporder); slab_out_of_memory(cachep, flags, nodeid); diff --git a/mm/slob.c b/mm/slob.c index 165bbd3cd606..0d7e5df74d1f 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -45,7 +45,7 @@ * NUMA support in SLOB is fairly simplistic, pushing most of the real * logic down to the page allocator, and simply doing the node accounting * on the upper levels. In the event that a node id is explicitly - * provided, alloc_pages_exact_node() with the specified node id is used + * provided, __alloc_pages_node() with the specified node id is used * instead. The common case (or when the node id isn't explicitly provided) * will default to the current node, as per numa_node_id(). * @@ -193,7 +193,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) #ifdef CONFIG_NUMA if (node != NUMA_NO_NODE) - page = alloc_pages_exact_node(node, gfp, order); + page = __alloc_pages_node(node, gfp, order); else #endif page = alloc_pages(gfp, order); diff --git a/mm/slub.c b/mm/slub.c index 084184e706c6..f614b5dc396b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1334,7 +1334,7 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s, if (node == NUMA_NO_NODE) page = alloc_pages(flags, order); else - page = alloc_pages_exact_node(node, flags, order); + page = __alloc_pages_node(node, flags, order); if (!page) memcg_uncharge_slab(s, order); -- cgit v1.2.3-70-g09d2 From 94a59fb36ee91b3f977a9b914ec701efe40041de Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Wed, 9 Sep 2015 15:35:31 -0700 Subject: hwpoison: use page_cgroup_ino for filtering by memcg Hwpoison allows to filter pages by memory cgroup ino. Currently, it calls try_get_mem_cgroup_from_page to obtain the cgroup from a page and then its ino using cgroup_ino, but now we have a helper method for that, page_cgroup_ino, so use it instead. This patch also loosens the hwpoison memcg filter dependency rules - it makes it depend on CONFIG_MEMCG instead of CONFIG_MEMCG_SWAP, because hwpoison memcg filter does not require anything (nor it used to) from CONFIG_MEMCG_SWAP side. Signed-off-by: Vladimir Davydov Reviewed-by: Andres Lagar-Cavilla Cc: Minchan Kim Cc: Raghavendra K T Cc: Johannes Weiner Cc: Michal Hocko Cc: Greg Thelen Cc: Michel Lespinasse Cc: David Rientjes Cc: Pavel Emelyanov Cc: Cyrill Gorcunov Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hwpoison-inject.c | 5 +---- mm/memory-failure.c | 16 ++-------------- 2 files changed, 3 insertions(+), 18 deletions(-) (limited to 'mm/memory-failure.c') diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index aeba0edd6e44..9d26fd9fefe4 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -45,12 +45,9 @@ static int hwpoison_inject(void *data, u64 val) /* * do a racy check with elevated page count, to make sure PG_hwpoison * will only be set for the targeted owner (or on a free page). - * We temporarily take page lock for try_get_mem_cgroup_from_page(). * memory_failure() will redo the check reliably inside page lock. */ - lock_page(hpage); err = hwpoison_filter(hpage); - unlock_page(hpage); if (err) goto put_out; @@ -126,7 +123,7 @@ static int pfn_inject_init(void) if (!dentry) goto fail; -#ifdef CONFIG_MEMCG_SWAP +#ifdef CONFIG_MEMCG dentry = debugfs_create_u64("corrupt-filter-memcg", 0600, hwpoison_dir, &hwpoison_filter_memcg); if (!dentry) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index eeda6485e76c..95882692e747 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -130,27 +130,15 @@ static int hwpoison_filter_flags(struct page *p) * can only guarantee that the page either belongs to the memcg tasks, or is * a freed page. */ -#ifdef CONFIG_MEMCG_SWAP +#ifdef CONFIG_MEMCG u64 hwpoison_filter_memcg; EXPORT_SYMBOL_GPL(hwpoison_filter_memcg); static int hwpoison_filter_task(struct page *p) { - struct mem_cgroup *mem; - struct cgroup_subsys_state *css; - unsigned long ino; - if (!hwpoison_filter_memcg) return 0; - mem = try_get_mem_cgroup_from_page(p); - if (!mem) - return -EINVAL; - - css = &mem->css; - ino = cgroup_ino(css->cgroup); - css_put(css); - - if (ino != hwpoison_filter_memcg) + if (page_cgroup_ino(p) != hwpoison_filter_memcg) return -EINVAL; return 0; -- cgit v1.2.3-70-g09d2