From a88c769548047b21f76fd71e04b6a3300ff17160 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 11 Dec 2015 13:40:24 -0800 Subject: mm: hugetlb: fix hugepage memory leak caused by wrong reserve count When dequeue_huge_page_vma() in alloc_huge_page() fails, we fall back on alloc_buddy_huge_page() to directly create a hugepage from the buddy allocator. In that case, however, if alloc_buddy_huge_page() succeeds we don't decrement h->resv_huge_pages, which means that successful hugetlb_fault() returns without releasing the reserve count. As a result, subsequent hugetlb_fault() might fail despite that there are still free hugepages. This patch simply adds decrementing code on that code path. I reproduced this problem when testing v4.3 kernel in the following situation: - the test machine/VM is a NUMA system, - hugepage overcommiting is enabled, - most of hugepages are allocated and there's only one free hugepage which is on node 0 (for example), - another program, which calls set_mempolicy(MPOL_BIND) to bind itself to node 1, tries to allocate a hugepage, - the allocation should fail but the reserve count is still hold. Signed-off-by: Naoya Horiguchi Cc: David Rientjes Cc: Dave Hansen Cc: Mel Gorman Cc: Joonsoo Kim Cc: Hillf Danton Cc: Mike Kravetz Cc: [3.16+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 827bb02a43a4..4fe4340ed9b7 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1886,7 +1886,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = __alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; - + if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { + SetPagePrivate(page); + h->resv_huge_pages--; + } spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ -- cgit v1.2.3 From 9516a18a9a253a94292e74f11f92083126c5a237 Mon Sep 17 00:00:00 2001 From: Vladimir Davydov Date: Fri, 11 Dec 2015 13:40:24 -0800 Subject: memcg: fix memory.high target When the memory.high threshold is exceeded, try_charge() schedules a task_work to reclaim the excess. The reclaim target is set to the number of pages requested by try_charge(). This is wrong, because try_charge() usually charges more pages than requested (batch > nr_pages) in order to refill per cpu stocks. As a result, a process in a cgroup can easily exceed memory.high significantly when doing a lot of charges w/o returning to userspace (e.g. reading a file in big chunks). Fix this issue by assuring that when exceeding memory.high a process reclaims as many pages as were actually charged (i.e. batch). Signed-off-by: Vladimir Davydov Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c92a65b2b4ab..32259e37a66b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2128,7 +2128,7 @@ done_restock: */ do { if (page_counter_read(&memcg->memory) > memcg->high) { - current->memcg_nr_pages_over_high += nr_pages; + current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; } -- cgit v1.2.3 From 475a2f905d5a41d5fc569ef21841be67d0a7f788 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 11 Dec 2015 13:40:29 -0800 Subject: mm: fix swapped Movable and Reclaimable in /proc/pagetypeinfo Commit 016c13daa5c9 ("mm, page_alloc: use masks and shifts when converting GFP flags to migrate types") has swapped MIGRATE_MOVABLE and MIGRATE_RECLAIMABLE in the enum definition. However, migratetype_names wasn't updated to reflect that. As a result, the file /proc/pagetypeinfo shows the counts for Movable as Reclaimable and vice versa. Additionally, commit 0aaa29a56e4f ("mm, page_alloc: reserve pageblocks for high-order atomic allocations on demand") introduced MIGRATE_HIGHATOMIC, but did not add a letter to distinguish it into show_migration_types(), so it doesn't appear in the listing of free areas during page alloc failures or oom kills. This patch fixes both problems. The atomic reserves will show with a letter 'H' in the free areas listings. Fixes: 016c13daa5c9 ("mm, page_alloc: use masks and shifts when converting GFP flags to migrate types") Fixes: 0aaa29a56e4f ("mm, page_alloc: reserve pageblocks for high-order atomic allocations on demand") Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 3 ++- mm/vmstat.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 17a3c66639a9..9d666df5ef95 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_MOVABLE] = 'M', + [MIGRATE_RECLAIMABLE] = 'E', + [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif diff --git a/mm/vmstat.c b/mm/vmstat.c index 879a2be23325..2ec34342a87b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, #ifdef CONFIG_PROC_FS static char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", - "Reclaimable", "Movable", + "Reclaimable", "HighAtomic", #ifdef CONFIG_CMA "CMA", -- cgit v1.2.3 From 373ccbe5927034b55bdc80b0f8b54d6e13fe8d12 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 11 Dec 2015 13:40:32 -0800 Subject: mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress Tetsuo Handa has reported that the system might basically livelock in OOM condition without triggering the OOM killer. The issue is caused by internal dependency of the direct reclaim on vmstat counter updates (via zone_reclaimable) which are performed from the workqueue context. If all the current workers get assigned to an allocation request, though, they will be looping inside the allocator trying to reclaim memory but zone_reclaimable can see stalled numbers so it will consider a zone reclaimable even though it has been scanned way too much. WQ concurrency logic will not consider this situation as a congested workqueue because it relies that worker would have to sleep in such a situation. This also means that it doesn't try to spawn new workers or invoke the rescuer thread if the one is assigned to the queue. In order to fix this issue we need to do two things. First we have to let wq concurrency code know that we are in trouble so we have to do a short sleep. In order to prevent from issues handled by 0e093d99763e ("writeback: do not sleep on the congestion queue if there are no congested BDIs or if significant congestion is not being encountered in the current zone") we limit the sleep only to worker threads which are the ones of the interest anyway. The second thing to do is to create a dedicated workqueue for vmstat and mark it WQ_MEM_RECLAIM to note it participates in the reclaim and to have a spare worker thread for it. Signed-off-by: Michal Hocko Reported-by: Tetsuo Handa Cc: Tejun Heo Cc: Cristopher Lameter Cc: Joonsoo Kim Cc: Arkadiusz Miskiewicz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/backing-dev.c | 19 ++++++++++++++++--- mm/vmstat.c | 6 ++++-- 2 files changed, 20 insertions(+), 5 deletions(-) diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8ed2ffd963c5..7340353f8aea 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait); * jiffies for either a BDI to exit congestion of the given @sync queue * or a write to complete. * - * In the absence of zone congestion, cond_resched() is called to yield - * the processor if necessary but otherwise does not sleep. + * In the absence of zone congestion, a short sleep or a cond_resched is + * performed to yield the processor and to allow other subsystems to make + * a forward progress. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function @@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) */ if (atomic_read(&nr_wb_congested[sync]) == 0 || !test_bit(ZONE_CONGESTED, &zone->flags)) { - cond_resched(); + + /* + * Memory allocation/reclaim might be called from a WQ + * context and the current implementation of the WQ + * concurrency control doesn't recognize that a particular + * WQ is congested if the worker thread is looping without + * ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout(1); + else + cond_resched(); /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); diff --git a/mm/vmstat.c b/mm/vmstat.c index 2ec34342a87b..0d5712b0206c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP +static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; static cpumask_var_t cpu_stat_off; @@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - schedule_delayed_work_on(smp_processor_id(), + queue_delayed_work_on(smp_processor_id(), vmstat_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } else { @@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w) if (need_update(cpu) && cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - schedule_delayed_work_on(cpu, + queue_delayed_work_on(cpu, vmstat_wq, &per_cpu(vmstat_work, cpu), 0); put_online_cpus(); @@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void) start_shepherd_timer(); cpu_notifier_register_done(); + vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); -- cgit v1.2.3 From ed0f1e2102b6f245210be5f93a08d708b6ac070f Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 11 Dec 2015 13:40:35 -0800 Subject: MAINTAINERS: make Vladimir co-maintainer of the memory controller Vladimir architected and authored much of the current state of the memcg's slab memory accounting and tracking. Make sure he gets CC'd on bug reports ;-) Signed-off-by: Johannes Weiner Acked-by: Vladimir Davydov Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 38df53f828e1..9bff63cf326e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2975,6 +2975,7 @@ F: kernel/cpuset.c CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG) M: Johannes Weiner M: Michal Hocko +M: Vladimir Davydov L: cgroups@vger.kernel.org L: linux-mm@kvack.org S: Maintained -- cgit v1.2.3 From 3066a9670ba6f57dd5046640a2494912a2110f1e Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 11 Dec 2015 13:40:38 -0800 Subject: osd fs: __r4w_get_page rely on PageUptodate for uptodate Commit 42cb14b110a5 ("mm: migrate dirty page without clear_page_dirty_for_io etc") simplified the migration of a PageDirty pagecache page: one stat needs moving from zone to zone and that's about all. It's convenient and safest for it to shift the PageDirty bit from old page to new, just before updating the zone stats: before copying data and marking the new PageUptodate. This is all done while both pages are isolated and locked, just as before; and just as before, there's a moment when the new page is visible in the radix_tree, but not yet PageUptodate. What's new is that it may now be briefly visible as PageDirty before it is PageUptodate. When I scoured the tree to see if this could cause a problem anywhere, the only places I found were in two similar functions __r4w_get_page(): which look up a page with find_get_page() (not using page lock), then claim it's uptodate if it's PageDirty or PageWriteback or PageUptodate. I'm not sure whether that was right before, but now it might be wrong (on rare occasions): only claim the page is uptodate if PageUptodate. Or perhaps the page in question could never be migratable anyway? Signed-off-by: Hugh Dickins Tested-by: Boaz Harrosh Cc: Benny Halevy Cc: Trond Myklebust Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exofs/inode.c | 5 +---- fs/nfs/objlayout/objio_osd.c | 5 +---- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 73c64daa0f55..60f03b78914e 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate); return page; } else { diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 5c0c6b58157f..9aebffb40505 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) } unlock_page(page); } - if (PageDirty(page) || PageWriteback(page)) - *uptodate = true; - else - *uptodate = PageUptodate(page); + *uptodate = PageUptodate(page); dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate); return page; } -- cgit v1.2.3 From 25be6a659598791d511c09ed71dca24e4844d128 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 11 Dec 2015 13:40:40 -0800 Subject: mm: fix kerneldoc on mem_cgroup_replace_page Whoops, I missed removing the kerneldoc comment of the lrucare arg removed from mem_cgroup_replace_page; but it's a good comment, keep it. Signed-off-by: Hugh Dickins Acked-by: Michal Hocko Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 32259e37a66b..e234c21a5e6c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5512,11 +5512,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_replace_page - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * * Both pages must be locked, @newpage->mapping must be set up. + * Either or both pages might be on the LRU already. */ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) { -- cgit v1.2.3 From 98e89cf02aed11166698dd53c6f14865613babb3 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Fri, 11 Dec 2015 13:40:43 -0800 Subject: mm: kmemleak: mark kmemleak_init prototype as __init The kmemleak_init() definition in mm/kmemleak.c is marked __init but its prototype in include/linux/kmemleak.h is marked __ref since commit a6186d89c913 ("kmemleak: Mark the early log buffer as __initdata"). This causes a section mismatch which is reported as a warning when building with clang -Wsection, because kmemleak_init() is declared in section .ref.text but defined in .init.text. Fix this by marking kmemleak_init() prototype __init. Signed-off-by: Nicolas Iooss Signed-off-by: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmemleak.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index d0a1f99e24e3..4894c6888bc6 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -25,7 +25,7 @@ #ifdef CONFIG_DEBUG_KMEMLEAK -extern void kmemleak_init(void) __ref; +extern void kmemleak_init(void) __init; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, -- cgit v1.2.3 From 86fffe4a61dd972d5a4e23260d530be6da02f614 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 11 Dec 2015 13:40:46 -0800 Subject: kernel: remove stop_machine() Kconfig dependency Currently the full stop_machine() routine is only enabled on SMP if module unloading is enabled, or if the CPUs are hotpluggable. This leads to configurations where stop_machine() is broken as it will then only run the callback on the local CPU with irqs disabled, and not stop the other CPUs or run the callback on them. For example, this breaks MTRR setup on x86 in certain configs since ea8596bb2d8d379 ("kprobes/x86: Remove unused text_poke_smp() and text_poke_smp_batch() functions") as the MTRR is only established on the boot CPU. This patch removes the Kconfig option for STOP_MACHINE and uses the SMP and HOTPLUG_CPU config options to compile the correct stop_machine() for the architecture, removing the false dependency on MODULE_UNLOAD in the process. Link: https://lkml.org/lkml/2014/10/8/124 References: https://bugs.freedesktop.org/show_bug.cgi?id=84794 Signed-off-by: Chris Wilson Acked-by: Ingo Molnar Cc: "Paul E. McKenney" Cc: Pranith Kumar Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Cc: H. Peter Anvin Cc: Tejun Heo Cc: Iulia Manda Cc: Andy Lutomirski Cc: Rusty Russell Cc: Peter Zijlstra Cc: Chuck Ebbert Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stop_machine.h | 6 +++--- init/Kconfig | 7 ------- kernel/stop_machine.c | 4 ++-- 3 files changed, 5 insertions(+), 12 deletions(-) diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0adedca24c5b..0e1b1540597a 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * grabbing every spinlock (and more). So the "read" side to such a * lock is anything which disables preemption. */ -#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) /** * stop_machine: freeze the machine on all CPUs and run this function @@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); -#else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ static inline int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) @@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return stop_machine(fn, data, cpus); } -#endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/init/Kconfig b/init/Kconfig index c24b6f767bf0..235c7a2c0d20 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE it was better to provide this option than to break all the archs and have several arch maintainers pursuing me down dark alleys. -config STOP_MACHINE - bool - default y - depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU - help - Need stop_machine() primitive. - source "block/Kconfig" config PREEMPT_NOTIFIERS diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 867bc20e1ef1..a3bbaee77c58 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -531,7 +531,7 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#ifdef CONFIG_STOP_MACHINE +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { @@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return ret ?: done.ret; } -#endif /* CONFIG_STOP_MACHINE */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From 0d777df5d8953293be090d9ab5a355db893e8357 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 11 Dec 2015 13:40:49 -0800 Subject: mm: hugetlb: call huge_pte_alloc() only if ptep is null Currently at the beginning of hugetlb_fault(), we call huge_pte_offset() and check whether the obtained *ptep is a migration/hwpoison entry or not. And if not, then we get to call huge_pte_alloc(). This is racy because the *ptep could turn into migration/hwpoison entry after the huge_pte_offset() check. This race results in BUG_ON in huge_pte_alloc(). We don't have to call huge_pte_alloc() when the huge_pte_offset() returns non-NULL, so let's fix this bug with moving the code into else block. Note that the *ptep could turn into a migration/hwpoison entry after this block, but that's not a problem because we have another !pte_present check later (we never go into hugetlb_no_page() in that case.) Fixes: 290408d4a250 ("hugetlb: hugepage migration core") Signed-off-by: Naoya Horiguchi Acked-by: Hillf Danton Acked-by: David Rientjes Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Joonsoo Kim Cc: Mike Kravetz Cc: [2.6.36+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 4fe4340ed9b7..9e3fa71b1e18 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3696,12 +3696,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); + } else { + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); + if (!ptep) + return VM_FAULT_OOM; } - ptep = huge_pte_alloc(mm, address, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; - mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); -- cgit v1.2.3 From dbe409e4f5e5075bd9ff7f8dd5c627abf3ee38c1 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 11 Dec 2015 13:40:52 -0800 Subject: mm/hugetlb.c: fix resv map memory leak for placeholder entries Dmitry Vyukov reported the following memory leak unreferenced object 0xffff88002eaafd88 (size 32): comm "a.out", pid 5063, jiffies 4295774645 (age 15.810s) hex dump (first 32 bytes): 28 e9 4e 63 00 88 ff ff 28 e9 4e 63 00 88 ff ff (.Nc....(.Nc.... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: kmalloc include/linux/slab.h:458 region_chg+0x2d4/0x6b0 mm/hugetlb.c:398 __vma_reservation_common+0x2c3/0x390 mm/hugetlb.c:1791 vma_needs_reservation mm/hugetlb.c:1813 alloc_huge_page+0x19e/0xc70 mm/hugetlb.c:1845 hugetlb_no_page mm/hugetlb.c:3543 hugetlb_fault+0x7a1/0x1250 mm/hugetlb.c:3717 follow_hugetlb_page+0x339/0xc70 mm/hugetlb.c:3880 __get_user_pages+0x542/0xf30 mm/gup.c:497 populate_vma_page_range+0xde/0x110 mm/gup.c:919 __mm_populate+0x1c7/0x310 mm/gup.c:969 do_mlock+0x291/0x360 mm/mlock.c:637 SYSC_mlock2 mm/mlock.c:658 SyS_mlock2+0x4b/0x70 mm/mlock.c:648 Dmitry identified a potential memory leak in the routine region_chg, where a region descriptor is not free'ed on an error path. However, the root cause for the above memory leak resides in region_del. In this specific case, a "placeholder" entry is created in region_chg. The associated page allocation fails, and the placeholder entry is left in the reserve map. This is "by design" as the entry should be deleted when the map is released. The bug is in the region_del routine which is used to delete entries within a specific range (and when the map is released). region_del did not handle the case where a placeholder entry exactly matched the start of the range range to be deleted. In this case, the entry would not be deleted and leaked. The fix is to take these special placeholder entries into account in region_del. The region_chg error path leak is also fixed. Fixes: feba16e25a57 ("mm/hugetlb: add region_del() to delete a specific range of entries") Signed-off-by: Mike Kravetz Reported-by: Dmitry Vyukov Acked-by: Hillf Danton Cc: [4.3+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9e3fa71b1e18..ef6963b577fd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -372,8 +372,10 @@ retry_locked: spin_unlock(&resv->lock); trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) + if (!trg) { + kfree(nrg); return -ENOMEM; + } spin_lock(&resv->lock); list_add(&trg->link, &resv->region_cache); @@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t) retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { - if (rg->to <= f) + /* + * Skip regions before the range to be deleted. file_region + * ranges are normally of the form [from, to). However, there + * may be a "placeholder" entry in the map which is of the form + * (from, to) with from == to. Check for placeholder entries + * at the beginning of the range to be deleted. + */ + if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; + if (rg->from >= t) break; -- cgit v1.2.3 From 267a4c76bbdb950688d3aeb020976c2918064584 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 11 Dec 2015 13:40:55 -0800 Subject: tmpfs: fix shmem_evict_inode() warnings on i_blocks Dmitry Vyukov provides a little program, autogenerated by syzkaller, which races a fault on a mapping of a sparse memfd object, against truncation of that object below the fault address: run repeatedly for a few minutes, it reliably generates shmem_evict_inode()'s WARN_ON(inode->i_blocks). (But there's nothing specific to memfd here, nor to the fstat which it happened to use to generate the fault: though that looked suspicious, since a shmem_recalc_inode() had been added there recently. The same problem can be reproduced with open+unlink in place of memfd_create, and with fstatfs in place of fstat.) v3.7 commit 0f3c42f522dc ("tmpfs: change final i_blocks BUG to WARNING") explains one cause of such a warning (a race with shmem_writepage to swap), and possible solutions; but we never took it further, and this syzkaller incident turns out to have a different cause. shmem_getpage_gfp()'s error recovery, when a freshly allocated page is then found to be beyond eof, looks plausible - decrementing the alloced count that was just before incremented - but in fact can go wrong, if a racing thread (the truncator, for example) gets its shmem_recalc_inode() in just after our delete_from_page_cache(). delete_from_page_cache() decrements nrpages, that shmem_recalc_inode() will balance the books by decrementing alloced itself, then our decrement of alloced take it one too low: leading to the WARNING when the object is finally evicted. Once the new page has been exposed in the page cache, shmem_getpage_gfp() must leave it to shmem_recalc_inode() itself to get the accounting right in all cases (and not fall through from "trunc:" to "decused:"). Adjust that error recovery block; and the reinitialization of info and sbinfo can be removed too. While we're here, fix shmem_writepage() to avoid the original issue: it will be safe against a racing shmem_recalc_inode(), if it merely increments swapped before the shmem_delete_from_page_cache() which decrements nrpages (but it must then do its own shmem_recalc_inode() before that, while still in balance, instead of after). (Aside: why do we shmem_recalc_inode() here in the swap path? Because its raison d'etre is to cope with clean sparse shmem pages being reclaimed behind our back: so here when swapping is a good place to look for that case.) But I've not now managed to reproduce this bug, even without the patch. I don't see why I didn't do that earlier: perhaps inhibited by the preference to eliminate shmem_recalc_inode() altogether. Driven by this incident, I do now have a patch to do so at last; but still want to sit on it for a bit, there's a couple of questions yet to be resolved. Signed-off-by: Hugh Dickins Reported-by: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 9187eee4128b..2afcdbbdb685 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) list_add_tail(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - swap_shmem_alloc(swap); - shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); - spin_lock(&info->lock); - info->swapped++; shmem_recalc_inode(inode); + info->swapped++; spin_unlock(&info->lock); + swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); @@ -1078,7 +1078,7 @@ repeat: if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; - goto failed; + goto unlock; } if (page && sgp == SGP_WRITE) @@ -1246,11 +1246,15 @@ clear: /* Perhaps the file has been truncated since we checked */ if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + if (alloced) { + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock(&info->lock); + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + } error = -EINVAL; - if (alloced) - goto trunc; - else - goto failed; + goto unlock; } *pagep = page; return 0; @@ -1258,23 +1262,13 @@ clear: /* * Error recovery. */ -trunc: - info = SHMEM_I(inode); - ClearPageDirty(page); - delete_from_page_cache(page); - spin_lock(&info->lock); - info->alloced--; - inode->i_blocks -= BLOCKS_PER_PAGE; - spin_unlock(&info->lock); decused: - sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_add(&sbinfo->used_blocks, -1); unacct: shmem_unacct_blocks(info->flags, 1); failed: - if (swap.val && error != -EINVAL && - !shmem_confirm_swap(mapping, index, swap)) + if (swap.val && !shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { -- cgit v1.2.3 From 26bbe7ef6d5cdc7ec08cba6d433fca4060f258f3 Mon Sep 17 00:00:00 2001 From: Seth Jennings Date: Fri, 11 Dec 2015 13:40:57 -0800 Subject: drivers/base/memory.c: prohibit offlining of memory blocks with missing sections Commit bdee237c0343 ("x86: mm: Use 2GB memory block size on large-memory x86-64 systems") and 982792c782ef ("x86, mm: probe memory block size for generic x86 64bit") introduced large block sizes for x86. This made it possible to have multiple sections per memory block where previously, there was a only every one section per block. Since blocks consist of contiguous ranges of section, there can be holes in the blocks where sections are not present. If one attempts to offline such a block, a crash occurs since the code is not designed to deal with this. This patch is a quick fix to gaurd against the crash by not allowing blocks with non-present sections to be offlined. Addresses https://bugzilla.kernel.org/show_bug.cgi?id=107781 Signed-off-by: Seth Jennings Reported-by: Andrew Banman Cc: Daniel J Blueman Cc: Yinghai Lu Cc: Greg KH Cc: Russ Anderson Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 2804aed3f416..25425d3f2575 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -303,6 +303,10 @@ static int memory_subsys_offline(struct device *dev) if (mem->state == MEM_OFFLINE) return 0; + /* Can't offline block with non-present sections */ + if (mem->section_count != sections_per_block) + return -EINVAL; + return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); } -- cgit v1.2.3 From a2b829d95958da2025ef844c0f53ac15ad720fac Mon Sep 17 00:00:00 2001 From: Chen Jie Date: Fri, 11 Dec 2015 13:41:00 -0800 Subject: mm/oom_kill.c: avoid attempting to kill init sharing same memory It's possible that an oom killed victim shares an ->mm with the init process and thus oom_kill_process() would end up trying to kill init as well. This has been shown in practice: Out of memory: Kill process 9134 (init) score 3 or sacrifice child Killed process 9134 (init) total-vm:1868kB, anon-rss:84kB, file-rss:572kB Kill process 1 (init) sharing same memory ... Kernel panic - not syncing: Attempted to kill init! exitcode=0x00000009 And this will result in a kernel panic. If a process is forked by init and selected for oom kill while still sharing init_mm, then it's likely this system is in a recoverable state. However, it's better not to try to kill init and allow the machine to panic due to unkillable processes. [rientjes@google.com: rewrote changelog] [akpm@linux-foundation.org: fix inverted test, per Ben] Signed-off-by: Chen Jie Signed-off-by: David Rientjes Acked-by: Michal Hocko Acked-by: Hillf Danton Cc: Ben Hutchings Cc: Li Zefan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d13a33918fa2..c12680993ff3 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, continue; if (unlikely(p->flags & PF_KTHREAD)) continue; + if (is_global_init(p)) + continue; if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) continue; -- cgit v1.2.3 From 854ee2e944b4daf795e32562a7d2f9e90ab5a6a8 Mon Sep 17 00:00:00 2001 From: Junxiao Bi Date: Fri, 11 Dec 2015 13:41:03 -0800 Subject: ocfs2: fix SGID not inherited issue Commit 8f1eb48758aa ("ocfs2: fix umask ignored issue") introduced an issue, SGID of sub dir was not inherited from its parents dir. It is because SGID is set into "inode->i_mode" in ocfs2_get_init_inode(), but is overwritten by "mode" which don't have SGID set later. Fixes: 8f1eb48758aa ("ocfs2: fix umask ignored issue") Signed-off-by: Junxiao Bi Cc: Mark Fasheh Cc: Joel Becker Acked-by: Srinivas Eeda Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/namei.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index a03f6f433075..3123408da935 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -367,13 +367,11 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } - status = posix_acl_create(dir, &mode, &default_acl, &acl); + status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl); if (status) { mlog_errno(status); goto leave; } - /* update inode->i_mode after mask with "umask". */ - inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), -- cgit v1.2.3 From 2d33fa1059da4c8e816627a688d950b613ec0474 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Fri, 11 Dec 2015 13:41:06 -0800 Subject: sh64: fix __NR_fgetxattr According to arch/sh/kernel/syscalls_64.S and common sense, __NR_fgetxattr has to be defined to 259, but it doesn't. Instead, it's defined to 269, which is of course used by another syscall, __NR_sched_setaffinity in this case. This bug was found by strace test suite. Signed-off-by: Dmitry V. Levin Acked-by: Geert Uytterhoeven Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sh/include/uapi/asm/unistd_64.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h index e6820c86e8c7..47ebd5b5ed55 100644 --- a/arch/sh/include/uapi/asm/unistd_64.h +++ b/arch/sh/include/uapi/asm/unistd_64.h @@ -278,7 +278,7 @@ #define __NR_fsetxattr 256 #define __NR_getxattr 257 #define __NR_lgetxattr 258 -#define __NR_fgetxattr 269 +#define __NR_fgetxattr 259 #define __NR_listxattr 260 #define __NR_llistxattr 261 #define __NR_flistxattr 262 -- cgit v1.2.3 From 9530d0fe129c0197d5df13319ccefd08a827383b Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Fri, 11 Dec 2015 13:41:09 -0800 Subject: MIPS: fix DMA contiguous allocation Recent changes to how GFP_ATOMIC is defined seems to have broken the condition to use mips_alloc_from_contiguous() in mips_dma_alloc_coherent(). I couldn't bottom out the exact change but I think it's this commit d0164adc89f6 ("mm, page_alloc: distinguish between being unable to sleep, unwilling to sleep and avoiding waking kswapd"). GFP_ATOMIC has multiple bits set and the check for !(gfp & GFP_ATOMIC) isn't enough. The reason behind this condition is to check whether we can potentially do a sleeping memory allocation. Use gfpflags_allow_blocking() instead which should be more robust. Signed-off-by: Qais Yousef Acked-by: Mel Gorman Cc: Ralf Baechle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/dma-default.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c index d8117be729a2..730d394ce5f0 100644 --- a/arch/mips/mm/dma-default.c +++ b/arch/mips/mm/dma-default.c @@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size, gfp = massage_gfp_flags(dev, gfp); - if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC)) + if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp)) page = dma_alloc_from_contiguous(dev, count, get_order(size)); if (!page) -- cgit v1.2.3