From 1ff6bbfd13ca2c114a5cb58e1a92d1e5d68ce0b7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 28 Jan 2014 18:10:37 -0500 Subject: arm, pm, vmpressure: add missing slab.h includes arch/arm/mach-tegra/pm.c, kernel/power/console.c and mm/vmpressure.c were somehow getting slab.h indirectly through cgroup.h which in turn was getting it indirectly through xattr.h. A scheduled cgroup change drops xattr.h inclusion from cgroup.h and breaks compilation of these three files. Add explicit slab.h includes to the three files. A pending cgroup patch depends on this change and it'd be great if this can be routed through cgroup/for-3.14-fixes branch. Signed-off-by: Tejun Heo Acked-by: Stephen Warren Cc: Thierry Reding Cc: linux-tegra@vger.kernel.org Cc: "Rafael J. Wysocki" Cc: linux-pm@vger.kernel.org Cc: Johannes Weiner Cc: Michal Hocko Cc: Balbir Singh Cc: KAMEZAWA Hiroyuki Cc: cgroups@vger.kernel.org --- mm/vmpressure.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 196970a4541f..d4042e75f7c7 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 255d0884f5635122adb23866b242b4ca112f4bc8 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 10 Feb 2014 14:25:39 -0800 Subject: mm/slub.c: list_lock may not be held in some circumstances Commit c65c1877bd68 ("slub: use lockdep_assert_held") incorrectly required that add_full() and remove_full() hold n->list_lock. The lock is only taken when kmem_cache_debug(s), since that's the only time it actually does anything. Require that the lock only be taken under such a condition. Reported-by: Larry Finger Tested-by: Larry Finger Tested-by: Paul E. McKenney Acked-by: Christoph Lameter Cc: Pekka Enberg Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 7e3e0458bce4..3d3a8a7a0f8c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1004,21 +1004,19 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) static void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_add(&page->lru, &n->full); } static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) { - lockdep_assert_held(&n->list_lock); - if (!(s->flags & SLAB_STORE_USER)) return; + lockdep_assert_held(&n->list_lock); list_del(&page->lru); } -- cgit v1.2.3 From 1e4dd9461fabfbc780cdfaf103cec790f3a53325 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 10 Feb 2014 14:25:46 -0800 Subject: slub: do not assert not having lock in removing freed partial Vladimir reported the following issue: Commit c65c1877bd68 ("slub: use lockdep_assert_held") requires remove_partial() to be called with n->list_lock held, but free_partial() called from kmem_cache_close() on cache destruction does not follow this rule, leading to a warning: WARNING: CPU: 0 PID: 2787 at mm/slub.c:1536 __kmem_cache_shutdown+0x1b2/0x1f0() Modules linked in: CPU: 0 PID: 2787 Comm: modprobe Tainted: G W 3.14.0-rc1-mm1+ #1 Hardware name: 0000000000000600 ffff88003ae1dde8 ffffffff816d9583 0000000000000600 0000000000000000 ffff88003ae1de28 ffffffff8107c107 0000000000000000 ffff880037ab2b00 ffff88007c240d30 ffffea0001ee5280 ffffea0001ee52a0 Call Trace: __kmem_cache_shutdown+0x1b2/0x1f0 kmem_cache_destroy+0x43/0xf0 xfs_destroy_zones+0x103/0x110 [xfs] exit_xfs_fs+0x38/0x4e4 [xfs] SyS_delete_module+0x19a/0x1f0 system_call_fastpath+0x16/0x1b His solution was to add a spinlock in order to quiet lockdep. Although there would be no contention to adding the lock, that lock also requires disabling of interrupts which will have a larger impact on the system. Instead of adding a spinlock to a location where it is not needed for lockdep, make a __remove_partial() function that does not test if the list_lock is held, as no one should have it due to it being freed. Also added a __add_partial() function that does not do the lock validation either, as it is not needed for the creation of the cache. Signed-off-by: Steven Rostedt Reported-by: Vladimir Davydov Suggested-by: David Rientjes Acked-by: David Rientjes Acked-by: Vladimir Davydov Acked-by: Christoph Lameter Cc: Pekka Enberg Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 3d3a8a7a0f8c..25f14ad8f817 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1518,11 +1518,9 @@ static void discard_slab(struct kmem_cache *s, struct page *page) /* * Management of partially allocated slabs. */ -static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) +static inline void +__add_partial(struct kmem_cache_node *n, struct page *page, int tail) { - lockdep_assert_held(&n->list_lock); - n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) list_add_tail(&page->lru, &n->partial); @@ -1530,15 +1528,27 @@ static inline void add_partial(struct kmem_cache_node *n, list_add(&page->lru, &n->partial); } -static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) +static inline void add_partial(struct kmem_cache_node *n, + struct page *page, int tail) { lockdep_assert_held(&n->list_lock); + __add_partial(n, page, tail); +} +static inline void +__remove_partial(struct kmem_cache_node *n, struct page *page) +{ list_del(&page->lru); n->nr_partial--; } +static inline void remove_partial(struct kmem_cache_node *n, + struct page *page) +{ + lockdep_assert_held(&n->list_lock); + __remove_partial(n, page); +} + /* * Remove slab from the partial list, freeze it and * return the pointer to the freelist. @@ -2904,12 +2914,10 @@ static void early_kmem_cache_node_alloc(int node) inc_slabs_node(kmem_cache_node, node, page->objects); /* - * the lock is for lockdep's sake, not for any actual - * race protection + * No locks need to be taken here as it has just been + * initialized and there is no concurrent access. */ - spin_lock(&n->list_lock); - add_partial(n, page, DEACTIVATE_TO_HEAD); - spin_unlock(&n->list_lock); + __add_partial(n, page, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -3195,7 +3203,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - remove_partial(n, page); + __remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, -- cgit v1.2.3 From 8d547ff4ac5927245e0833ac18528f939da0ee0e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 10 Feb 2014 14:25:50 -0800 Subject: mm/memory-failure.c: move refcount only in !MF_COUNT_INCREASED mce-test detected a test failure when injecting error to a thp tail page. This is because we take page refcount of the tail page in madvise_hwpoison() while the fix in commit a3e0f9e47d5e ("mm/memory-failure.c: transfer page count from head page to tail page after split thp") assumes that we always take refcount on the head page. When a real memory error happens we take refcount on the head page where memory_failure() is called without MF_COUNT_INCREASED set, so it seems to me that testing memory error on thp tail page using madvise makes little sense. This patch cancels moving refcount in !MF_COUNT_INCREASED for valid testing. [akpm@linux-foundation.org: s/&&/&/] Signed-off-by: Naoya Horiguchi Cc: Andi Kleen Cc: Wanpeng Li Cc: Chen Gong Cc: [3.9+: a3e0f9e47d5e] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 4f08a2d61487..2f2f34a4e77d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -945,8 +945,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * to it. Similarly, page lock is shifted. */ if (hpage != p) { - put_page(hpage); - get_page(p); + if (!(flags & MF_COUNT_INCREASED)) { + put_page(hpage); + get_page(p); + } lock_page(p); unlock_page(hpage); *hpagep = p; -- cgit v1.2.3 From 9d85d5863fa4818eb7fa306563bf830c0210c3a6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:37 +0530 Subject: mm: Dirty accountable change only apply to non prot numa case So move it within the if loop Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- mm/mprotect.c | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/mprotect.c b/mm/mprotect.c index 7332c1785744..33eab902f10e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -58,6 +58,13 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (pte_numa(ptent)) ptent = pte_mknonnuma(ptent); ptent = pte_modify(ptent, newprot); + /* + * Avoid taking write faults for pages we + * know to be dirty. + */ + if (dirty_accountable && pte_dirty(ptent)) + ptent = pte_mkwrite(ptent); + ptep_modify_prot_commit(mm, addr, pte, ptent); updated = true; } else { struct page *page; @@ -72,22 +79,8 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } } } - - /* - * Avoid taking write faults for pages we know to be - * dirty. - */ - if (dirty_accountable && pte_dirty(ptent)) { - ptent = pte_mkwrite(ptent); - updated = true; - } - if (updated) pages++; - - /* Only !prot_numa always clears the pte */ - if (!prot_numa) - ptep_modify_prot_commit(mm, addr, pte, ptent); } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); -- cgit v1.2.3 From 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 12 Feb 2014 09:13:38 +0530 Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using a hash table MMU for various reasons (the flush is handled as part of the PTE modification when necessary). ppc64 thus doesn't implement flush_tlb_range for hash based MMUs. Additionally ppc64 require the tlb flushing to be batched within ptl locks. The reason to do that is to ensure that the hash page table is in sync with linux page table. We track the hpte index in linux pte and if we clear them without flushing hash and drop the ptl lock, we can have another cpu update the pte and can end up with duplicate entry in the hash table, which is fatal. We also want to keep set_pte_at simpler by not requiring them to do hash flush for performance reason. We do that by assuming that set_pte_at() is never *ever* called on a PTE that is already valid. This was the case until the NUMA code went in which broke that assumption. Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a way similar to ptep/pmdp_set_wrprotect(), with a generic implementation using set_pte_at() and a powerpc specific one using the appropriate mechanism needed to keep the hash table in sync. Acked-by: Mel Gorman Reviewed-by: Rik van Riel Signed-off-by: Aneesh Kumar K.V Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++ include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++ mm/huge_memory.c | 9 ++------- mm/mprotect.c | 4 +--- 4 files changed, 64 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index f83b6f3e1b39..3ebb188c3ff5 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +#define ptep_set_numa ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if ((pte_val(*ptep) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0); + return; +} + #define pmd_numa pmd_numa static inline int pmd_numa(pmd_t pmd) { return pte_numa(pmd_pte(pmd)); } +#define pmdp_set_numa pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0) + VM_BUG_ON(1); + + pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA); + return; +} + #define pmd_mknonnuma pmd_mknonnuma static inline pmd_t pmd_mknonnuma(pmd_t pmd) { diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 8e4f41d9af4d..34c7bdc06014 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte) } #endif +#ifndef ptep_set_numa +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_t ptent = *ptep; + + ptent = pte_mknuma(ptent); + set_pte_at(mm, addr, ptep, ptent); + return; +} +#endif + #ifndef pmd_mknuma static inline pmd_t pmd_mknuma(pmd_t pmd) { @@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } #endif + +#ifndef pmdp_set_numa +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + pmd_t pmd = *pmdp; + + pmd = pmd_mknuma(pmd); + set_pmd_at(mm, addr, pmdp, pmd); + return; +} +#endif #else extern int pte_numa(pte_t pte); extern int pmd_numa(pmd_t pmd); @@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte); extern pmd_t pmd_mknonnuma(pmd_t pmd); extern pte_t pte_mknuma(pte_t pte); extern pmd_t pmd_mknuma(pmd_t pmd); +extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp); #endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */ #else static inline int pmd_numa(pmd_t pmd) @@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte) return pte; } +static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + return; +} + + static inline pmd_t pmd_mknuma(pmd_t pmd) { return pmd; } + +static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + return ; +} #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_MMU */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 82166bf974e1..da23eb96779f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; + set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); } else { struct page *page = pmd_page(*pmd); @@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, */ if (!is_huge_zero_page(page) && !pmd_numa(*pmd)) { - entry = *pmd; - entry = pmd_mknuma(entry); + pmdp_set_numa(mm, addr, pmd); ret = HPAGE_PMD_NR; } } - - /* Set PMD if cleared earlier */ - if (ret == HPAGE_PMD_NR) - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(ptl); } diff --git a/mm/mprotect.c b/mm/mprotect.c index 33eab902f10e..769a67a15803 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } else { struct page *page; - ptent = *pte; page = vm_normal_page(vma, addr, oldpte); if (page && !PageKsm(page)) { if (!pte_numa(oldpte)) { - ptent = pte_mknuma(ptent); - set_pte_at(mm, addr, pte, ptent); + ptep_set_numa(mm, addr, pte); updated = true; } } -- cgit v1.2.3 From 33b6c7765f0c20da9d61246a095acad0f98a1da5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 25 Feb 2014 15:01:39 -0800 Subject: mm, hwpoison: release page on PageHWPoison() in __do_fault() It seems we forget to release page after detecting HW error. Signed-off-by: Kirill A. Shutemov Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: Matthew Wilcox Cc: Dave Hansen Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index be6a0c0d4ae0..5f2001a7ab31 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3348,6 +3348,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); ret = VM_FAULT_HWPOISON; + page_cache_release(vmf.page); goto uncharge_out; } -- cgit v1.2.3 From 9845cbbd113fbb5b769a45d8e88dc47bc12df4e0 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 25 Feb 2014 15:01:42 -0800 Subject: mm, thp: fix infinite loop on memcg OOM Masayoshi Mizuma reported a bug with the hang of an application under the memcg limit. It happens on write-protection fault to huge zero page If we successfully allocate a huge page to replace zero page but hit the memcg limit we need to split the zero page with split_huge_page_pmd() and fallback to small pages. The other part of the problem is that VM_FAULT_OOM has special meaning in do_huge_pmd_wp_page() context. __handle_mm_fault() expects the page to be split if it sees VM_FAULT_OOM and it will will retry page fault handling. This causes an infinite loop if the page was not split. do_huge_pmd_wp_zero_page_fallback() can return VM_FAULT_OOM if it failed to allocate one small page, so fallback to small pages will not help. The solution for this part is to replace VM_FAULT_OOM with VM_FAULT_FALLBACK is fallback required. Signed-off-by: Kirill A. Shutemov Reported-by: Masayoshi Mizuma Reviewed-by: Michal Hocko Cc: Johannes Weiner Cc: Andrea Arcangeli Cc: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 ++++++--- mm/memory.c | 14 +++----------- 2 files changed, 9 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index da23eb96779f..4df39b1bde91 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1166,8 +1166,10 @@ alloc: } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) + if (ret & VM_FAULT_OOM) { split_huge_page(page); + ret |= VM_FAULT_FALLBACK; + } put_page(page); } count_vm_event(THP_FAULT_FALLBACK); @@ -1179,9 +1181,10 @@ alloc: if (page) { split_huge_page(page); put_page(page); - } + } else + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); - ret |= VM_FAULT_OOM; goto out; } diff --git a/mm/memory.c b/mm/memory.c index 5f2001a7ab31..22dfa617bddb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3704,7 +3704,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3742,20 +3741,13 @@ retry: if (dirty && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { huge_pmd_set_accessed(mm, vma, address, pmd, orig_pmd, dirty); + return 0; } - - return 0; } } -- cgit v1.2.3 From 08088cb9ac0a9c28d4cf3efa4f6848a9b053ccfd Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 25 Feb 2014 15:01:44 -0800 Subject: memcg: change oom_info_lock to mutex Kirill has reported the following: Task in /test killed as a result of limit of /test memory: usage 10240kB, limit 10240kB, failcnt 51 memory+swap: usage 10240kB, limit 10240kB, failcnt 0 kmem: usage 0kB, limit 18014398509481983kB, failcnt 0 Memory cgroup stats for /test: BUG: sleeping function called from invalid context at kernel/cpu.c:68 in_atomic(): 1, irqs_disabled(): 0, pid: 66, name: memcg_test 2 locks held by memcg_test/66: #0: (memcg_oom_lock#2){+.+...}, at: [] pagefault_out_of_memory+0x14/0x90 #1: (oom_info_lock){+.+...}, at: [] mem_cgroup_print_oom_info+0x2a/0x390 CPU: 2 PID: 66 Comm: memcg_test Not tainted 3.14.0-rc1-dirty #745 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Bochs 01/01/2011 Call Trace: __might_sleep+0x16a/0x210 get_online_cpus+0x1c/0x60 mem_cgroup_read_stat+0x27/0xb0 mem_cgroup_print_oom_info+0x260/0x390 dump_header+0x88/0x251 ? trace_hardirqs_on+0xd/0x10 oom_kill_process+0x258/0x3d0 mem_cgroup_oom_synchronize+0x656/0x6c0 ? mem_cgroup_charge_common+0xd0/0xd0 pagefault_out_of_memory+0x14/0x90 mm_fault_error+0x91/0x189 __do_page_fault+0x48e/0x580 do_page_fault+0xe/0x10 page_fault+0x22/0x30 which complains that mem_cgroup_read_stat cannot be called from an atomic context but mem_cgroup_print_oom_info takes a spinlock. Change oom_info_lock to a mutex. This was introduced by 947b3dd1a84b ("memcg, oom: lock mem_cgroup_print_oom_info"). Signed-off-by: Michal Hocko Reported-by: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53385cd4e6f0..ce7a8cc7b404 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1687,7 +1687,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) * protects memcg_name and makes sure that parallel ooms do not * interleave */ - static DEFINE_SPINLOCK(oom_info_lock); + static DEFINE_MUTEX(oom_info_lock); struct cgroup *task_cgrp; struct cgroup *mem_cgrp; static char memcg_name[PATH_MAX]; @@ -1698,7 +1698,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) if (!p) return; - spin_lock(&oom_info_lock); + mutex_lock(&oom_info_lock); rcu_read_lock(); mem_cgrp = memcg->css.cgroup; @@ -1767,7 +1767,7 @@ done: pr_cont("\n"); } - spin_unlock(&oom_info_lock); + mutex_unlock(&oom_info_lock); } /* -- cgit v1.2.3