From 264a0ae164bc0e9144bebcd25ff030d067b1a878 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 Apr 2016 19:09:02 -0400 Subject: memcg: relocate charge moving from ->attach to ->post_attach Hello, So, this ended up a lot simpler than I originally expected. I tested it lightly and it seems to work fine. Petr, can you please test these two patches w/o the lru drain drop patch and see whether the problem is gone? Thanks. ------ 8< ------ If charge moving is used, memcg performs relabeling of the affected pages from its ->attach callback which is called under both cgroup_threadgroup_rwsem and thus can't create new kthreads. This is fragile as various operations may depend on workqueues making forward progress which relies on the ability to create new kthreads. There's no reason to perform charge moving from ->attach which is deep in the task migration path. Move it to ->post_attach which is called after the actual migration is finished and cgroup_threadgroup_rwsem is dropped. * move_charge_struct->mm is added and ->can_attach is now responsible for pinning and recording the target mm. mem_cgroup_clear_mc() is updated accordingly. This also simplifies mem_cgroup_move_task(). * mem_cgroup_move_task() is now called from ->post_attach instead of ->attach. Signed-off-by: Tejun Heo Cc: Johannes Weiner Acked-by: Michal Hocko Debugged-and-tested-by: Petr Mladek Reported-by: Cyril Hrubis Reported-by: Johannes Weiner Fixes: 1ed1328792ff ("sched, cgroup: replace signal_struct->group_rwsem with a global percpu_rwsem") Cc: # 4.4+ --- mm/memcontrol.c | 37 +++++++++++++++++++------------------ 1 file changed, 19 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 36db05fa8acb..fe787f5c41bd 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -207,6 +207,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg); /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ + struct mm_struct *mm; struct mem_cgroup *from; struct mem_cgroup *to; unsigned long flags; @@ -4667,6 +4668,8 @@ static void __mem_cgroup_clear_mc(void) static void mem_cgroup_clear_mc(void) { + struct mm_struct *mm = mc.mm; + /* * we must clear moving_task before waking up waiters at the end of * task migration. @@ -4676,7 +4679,10 @@ static void mem_cgroup_clear_mc(void) spin_lock(&mc.lock); mc.from = NULL; mc.to = NULL; + mc.mm = NULL; spin_unlock(&mc.lock); + + mmput(mm); } static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4733,6 +4739,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) VM_BUG_ON(mc.moved_swap); spin_lock(&mc.lock); + mc.mm = mm; mc.from = from; mc.to = memcg; mc.flags = move_flags; @@ -4742,8 +4749,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) ret = mem_cgroup_precharge_mc(mm); if (ret) mem_cgroup_clear_mc(); + } else { + mmput(mm); } - mmput(mm); return ret; } @@ -4852,11 +4860,11 @@ put: /* get_mctgt_type() gets the page */ return ret; } -static void mem_cgroup_move_charge(struct mm_struct *mm) +static void mem_cgroup_move_charge(void) { struct mm_walk mem_cgroup_move_charge_walk = { .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, + .mm = mc.mm, }; lru_add_drain_all(); @@ -4868,7 +4876,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) atomic_inc(&mc.from->moving_account); synchronize_rcu(); retry: - if (unlikely(!down_read_trylock(&mm->mmap_sem))) { + if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) { /* * Someone who are holding the mmap_sem might be waiting in * waitq. So we cancel all extra charges, wake up all waiters, @@ -4885,23 +4893,16 @@ retry: * additional charge, the page walk just aborts. */ walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); - up_read(&mm->mmap_sem); + up_read(&mc.mm->mmap_sem); atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { - struct cgroup_subsys_state *css; - struct task_struct *p = cgroup_taskset_first(tset, &css); - struct mm_struct *mm = get_task_mm(p); - - if (mm) { - if (mc.to) - mem_cgroup_move_charge(mm); - mmput(mm); - } - if (mc.to) + if (mc.to) { + mem_cgroup_move_charge(); mem_cgroup_clear_mc(); + } } #else /* !CONFIG_MMU */ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) @@ -4911,7 +4912,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_taskset *tset) +static void mem_cgroup_move_task(void) { } #endif @@ -5195,7 +5196,7 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, + .post_attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, .legacy_cftypes = mem_cgroup_legacy_files, -- cgit v1.2.3 From aa88b68c3b1dce8bc3fd54c8a7372a777ff265cd Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Thu, 28 Apr 2016 16:18:27 -0700 Subject: thp: keep huge zero page pinned until tlb flush Andrea has found[1] a race condition on MMU-gather based TLB flush vs split_huge_page() or shrinker which frees huge zero under us (patch 1/2 and 2/2 respectively). With new THP refcounting, we don't need patch 1/2: mmu_gather keeps the page pinned until flush is complete and the pin prevents the page from being split under us. We still need patch 2/2. This is simplified version of Andrea's patch. We don't need fancy encoding. [1] http://lkml.kernel.org/r/1447938052-22165-1-git-send-email-aarcange@redhat.com Signed-off-by: Kirill A. Shutemov Reported-by: Andrea Arcangeli Reviewed-by: Andrea Arcangeli Cc: "Aneesh Kumar K.V" Cc: Mel Gorman Cc: Hugh Dickins Cc: Johannes Weiner Cc: Dave Hansen Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 6 +++--- mm/swap.c | 5 +++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 86f9f8b82f8e..5346de05f471 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -232,7 +232,7 @@ retry: return READ_ONCE(huge_zero_page); } -static void put_huge_zero_page(void) +void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put @@ -1684,12 +1684,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, if (vma_is_dax(vma)) { spin_unlock(ptl); if (is_huge_zero_pmd(orig_pmd)) - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else if (is_huge_zero_pmd(orig_pmd)) { pte_free(tlb->mm, pgtable_trans_huge_withdraw(tlb->mm, pmd)); atomic_long_dec(&tlb->mm->nr_ptes); spin_unlock(ptl); - put_huge_zero_page(); + tlb_remove_page(tlb, pmd_page(orig_pmd)); } else { struct page *page = pmd_page(orig_pmd); page_remove_rmap(page, true); diff --git a/mm/swap.c b/mm/swap.c index a0bc206b4ac6..03aacbcb013f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -728,6 +728,11 @@ void release_pages(struct page **pages, int nr, bool cold) zone = NULL; } + if (is_huge_zero_page(page)) { + put_huge_zero_page(); + continue; + } + page = compound_head(page); if (!put_page_testzero(page)) continue; -- cgit v1.2.3 From 3486b85a29c1741db99d0c522211c82d2b7a56d0 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 28 Apr 2016 16:18:32 -0700 Subject: mm/huge_memory: replace VM_NO_THP VM_BUG_ON with actual VMA check Khugepaged detects own VMAs by checking vm_file and vm_ops but this way it cannot distinguish private /dev/zero mappings from other special mappings like /dev/hpet which has no vm_ops and popultes PTEs in mmap. This fixes false-positive VM_BUG_ON and prevents installing THP where they are not expected. Link: http://lkml.kernel.org/r/CACT4Y+ZmuZMV5CjSFOeXviwQdABAgT7T+StKfTqan9YDtgEi5g@mail.gmail.com Fixes: 78f11a255749 ("mm: thp: fix /dev/zero MAP_PRIVATE and vm_flags cleanups") Signed-off-by: Konstantin Khlebnikov Reported-by: Dmitry Vyukov Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Dmitry Vyukov Cc: Andrea Arcangeli Cc: stable Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5346de05f471..df67b53ae3c5 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1960,10 +1960,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma, * page fault if needed. */ return 0; - if (vma->vm_ops) + if (vma->vm_ops || (vm_flags & VM_NO_THP)) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -2352,8 +2351,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma) return false; if (is_vma_temporary_stack(vma)) return false; - VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma); - return true; + return !(vma->vm_flags & VM_NO_THP); } static void collapse_huge_page(struct mm_struct *mm, -- cgit v1.2.3 From 28093f9f34cedeaea0f481c58446d9dac6dd620f Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 28 Apr 2016 16:18:35 -0700 Subject: numa: fix /proc//numa_maps for THP In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer Cc: Naoya Horiguchi Cc: "Kirill A . Shutemov" Cc: Konstantin Khlebnikov Cc: Michal Hocko Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Johannes Weiner Cc: Dave Hansen Cc: Mel Gorman Cc: Dan Williams Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michael Holzheu Cc: [4.3+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 93897f23cc11..305537fc8640 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -789,6 +789,46 @@ out: return pfn_to_page(pfn); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd) +{ + unsigned long pfn = pmd_pfn(pmd); + + /* + * There is no pmd_special() but there may be special pmds, e.g. + * in a direct-access (dax) mapping, so let's just replicate the + * !HAVE_PTE_SPECIAL case from vm_normal_page() here. + */ + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + if (is_zero_pfn(pfn)) + return NULL; + if (unlikely(pfn > highest_memmap_pfn)) + return NULL; + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} +#endif + /* * copy one vm_area from one task to the other. Assumes the page tables * already present in the new task to be cleared in the whole range -- cgit v1.2.3 From 7bf52fb891b64b8d61caf0b82060adb9db761aec Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:38 -0700 Subject: mm: vmscan: reclaim highmem zone if buffer_heads is over limit We have been reclaimed highmem zone if buffer_heads is over limit but commit 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") changed the behavior so it doesn't reclaim highmem zone although buffer_heads is over the limit. This patch restores the logic. Fixes: 6b4f7799c6a5 ("mm: vmscan: invoke slab shrinkers from shrink_zone()") Signed-off-by: Minchan Kim Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index b934223eaa45..c638b28310fc 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2553,7 +2553,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) sc->gfp_mask |= __GFP_HIGHMEM; for_each_zone_zonelist_nodemask(zone, z, zonelist, - requested_highidx, sc->nodemask) { + gfp_zone(sc->gfp_mask), sc->nodemask) { enum zone_type classzone_idx; if (!populated_zone(zone)) -- cgit v1.2.3 From b06bad17c7435b600a1d7a35b56eff25e1d3dbc0 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:41 -0700 Subject: mm: call swap_slot_free_notify() with page lock held Kyeongdon reported below error which is BUG_ON(!PageSwapCache(page)) in page_swap_info. The reason is that page_endio in rw_page unlocks the page if read I/O is completed so we need to hold a PG_lock again to check PageSwapCache. Otherwise, the page can be removed from swapcache. Kernel BUG at c00f9040 [verbose debug info unavailable] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM Modules linked in: CPU: 4 PID: 13446 Comm: RenderThread Tainted: G W 3.10.84-g9f14aec-dirty #73 task: c3b73200 ti: dd192000 task.ti: dd192000 PC is at page_swap_info+0x10/0x2c LR is at swap_slot_free_notify+0x18/0x6c pc : [] lr : [] psr: 400f0113 sp : dd193d78 ip : c2deb1e4 fp : da015180 r10: 00000000 r9 : 000200da r8 : c120fe08 r7 : 00000000 r6 : 00000000 r5 : c249a6c0 r4 : = c249a6c0 r3 : 00000000 r2 : 40080009 r1 : 200f0113 r0 : = c249a6c0 .. .. Call Trace: page_swap_info+0x10/0x2c swap_slot_free_notify+0x18/0x6c swap_readpage+0x90/0x11c read_swap_cache_async+0x134/0x1ac swapin_readahead+0x70/0xb0 handle_pte_fault+0x320/0x6fc handle_mm_fault+0xc0/0xf0 do_page_fault+0x11c/0x36c do_DataAbort+0x34/0x118 Fixes: 3f2b1a04f44933f2 ("zram: revive swap_slot_free_notify") Signed-off-by: Minchan Kim Tested-by: Kyeongdon Kim Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_io.c b/mm/page_io.c index cd92e3d67a32..985f23cfa79b 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -353,7 +353,11 @@ int swap_readpage(struct page *page) ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - swap_slot_free_notify(page); + if (trylock_page(page)) { + swap_slot_free_notify(page); + unlock_page(page); + } + count_vm_event(PSWPIN); return 0; } -- cgit v1.2.3 From d7e69488bd04de165667f6bc741c1c0ec6042ab9 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 28 Apr 2016 16:18:44 -0700 Subject: mm/hwpoison: fix wrong num_poisoned_pages accounting Currently, migration code increses num_poisoned_pages on *failed* migration page as well as successfully migrated one at the trial of memory-failure. It will make the stat wrong. As well, it marks the page as PG_HWPoison even if the migration trial failed. It would mean we cannot recover the corrupted page using memory-failure facility. This patches fixes it. Signed-off-by: Minchan Kim Reported-by: Vlastimil Babka Acked-by: Naoya Horiguchi Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 6c822a7b27e0..f9dfb18a4eba 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -975,7 +975,13 @@ 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 && rc == MIGRATEPAGE_SUCCESS) { + /* + * With this release, we free successfully migrated + * page and set PG_HWPoison on just freed page + * intentionally. Although it's rather weird, it's how + * HWPoison flag works at the moment. + */ put_page(page); if (!test_set_page_hwpoison(page)) num_poisoned_pages_inc(); -- cgit v1.2.3 From fd901c95388b3bd5a6f749ed1d677a672b992298 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 28 Apr 2016 16:18:49 -0700 Subject: mm: wake kcompactd before kswapd's short sleep When kswapd goes to sleep it checks if the node is balanced and at first it sleeps only for HZ/10 time, then rechecks if the node is still balanced and nobody has woken it during the initial sleep. Only then it goes fully sleep until an allocation slowpath wakes it up again. For higher-order allocations, waking up kcompactd is done only before the full sleep. This turns out to be an issue in case another high-order allocation fails during the initial sleep. It will wake kswapd up, however kswapd considers the zone balanced from the order-0 perspective, and will just quickly try to sleep again. So if there's a longer stream of high-order allocations hitting the slowpath and waking up kswapd, it might never actually wake up kcompactd, which may be considered a regression from kswapd-based compaction. In the worst case, it might be that a single allocation that cannot direct reclaim/compact itself is waking kswapd in the retry loop and preventing kcompactd from being woken up and unblocking it. This patch makes sure kcompactd is woken up in such situations by simply moving the wakeup before the short initial sleep. More efficient solution would be to wake kcompactd immediately instead of kswapd if the node is already order-0 balanced, but in that case we should also move reset_isolation_suitable() call to kcompactd so it's not adding to the allocator's latency. Since it's late in the 4.6 cycle, let's go with the simpler change for now. Fixes: accf62422b3a ("mm, kswapd: replace kswapd compaction with waking up kcompactd") Signed-off-by: Vlastimil Babka Cc: Andrea Arcangeli Cc: "Kirill A. Shutemov" Cc: Rik van Riel Cc: Joonsoo Kim Cc: Mel Gorman Cc: David Rientjes Cc: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmscan.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index c638b28310fc..142cb61f4822 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3318,6 +3318,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, /* Try to sleep for a short interval */ if (prepare_kswapd_sleep(pgdat, order, remaining, balanced_classzone_idx)) { + /* + * Compaction records what page blocks it recently failed to + * isolate pages from and skips them in the future scanning. + * When kswapd is going to sleep, it is reasonable to assume + * that pages and compaction may succeed so reset the cache. + */ + reset_isolation_suitable(pgdat); + + /* + * We have freed the memory, now we should compact it to make + * allocation of the requested order possible. + */ + wakeup_kcompactd(pgdat, order, classzone_idx); + remaining = schedule_timeout(HZ/10); finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); @@ -3341,20 +3355,6 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold); - /* - * Compaction records what page blocks it recently failed to - * isolate pages from and skips them in the future scanning. - * When kswapd is going to sleep, it is reasonable to assume - * that pages and compaction may succeed so reset the cache. - */ - reset_isolation_suitable(pgdat); - - /* - * We have freed the memory, now we should compact it to make - * allocation of the requested order possible. - */ - wakeup_kcompactd(pgdat, order, classzone_idx); - if (!kthread_should_stop()) schedule(); -- cgit v1.2.3 From c2e7e00b715d3c65f301bec8559d6af4ef8098ab Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Thu, 28 Apr 2016 16:19:03 -0700 Subject: mm/memory-failure: fix race with compound page split/merge get_hwpoison_page() must recheck relation between head and tail pages. n-horiguchi said: without this recheck, the race causes kernel to pin an irrelevant page, and finally makes kernel crash for refcount mismatch. Signed-off-by: Konstantin Khlebnikov Acked-by: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 78f5f2641b91..ca5acee53b7a 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -888,7 +888,15 @@ int get_hwpoison_page(struct page *page) } } - return get_page_unless_zero(head); + if (get_page_unless_zero(head)) { + if (head == compound_head(page)) + return 1; + + pr_info("MCE: %#lx cannot catch tail\n", page_to_pfn(page)); + put_page(head); + } + + return 0; } EXPORT_SYMBOL_GPL(get_hwpoison_page); -- cgit v1.2.3