talos-op-linux/mm, branch v4.4.4

make sure that freeing shmem fast symlinks is RCU-delayed

2016-03-03T23:07:23+00:00

commit 3ed47db34f480df7caf44436e3e63e555351ae9a upstream. Signed-off-by: Al Viro Signed-off-by: Greg Kroah-Hartman

virtio_balloon: fix race between migration and ballooning

2016-03-03T23:07:18+00:00

commit 21ea9fb69e7c4b1b1559c3e410943d3ff248ffcb upstream. In balloon_page_dequeue, pages_lock should cover the loop (ie, list_for_each_entry_safe). Otherwise, the cursor page could be isolated by compaction and then list_del by isolation could poison the page->lru.{prev,next} so the loop finally could access wrong address like this. This patch fixes the bug. general protection fault: 0000 [#1] SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 2 PID: 82 Comm: vballoon Not tainted 4.4.0-rc5-mm1-access_bit+ #1906 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 task: ffff8800a7ff0000 ti: ffff8800a7fec000 task.ti: ffff8800a7fec000 RIP: 0010:[] [] balloon_page_dequeue+0x54/0x130 RSP: 0018:ffff8800a7fefdc0 EFLAGS: 00010246 RAX: ffff88013fff9a70 RBX: ffffea000056fe00 RCX: 0000000000002b7d RDX: ffff88013fff9a70 RSI: ffffea000056fe00 RDI: ffff88013fff9a68 RBP: ffff8800a7fefde8 R08: ffffea000056fda0 R09: 0000000000000000 R10: ffff8800a7fefd90 R11: 0000000000000001 R12: dead0000000000e0 R13: ffffea000056fe20 R14: ffff880138809070 R15: ffff880138809060 FS: 0000000000000000(0000) GS:ffff88013fc40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f229c10e000 CR3: 00000000b8b53000 CR4: 00000000000006a0 Stack: 0000000000000100 ffff880138809088 ffff880138809000 ffff880138809060 0000000000000046 ffff8800a7fefe28 ffffffff812c86d3 ffff880138809020 ffff880138809000 fffffffffff91900 0000000000000100 ffff880138809060 Call Trace: [] leak_balloon+0x93/0x1a0 [] balloon+0x217/0x2a0 [] ? __schedule+0x31e/0x8b0 [] ? abort_exclusive_wait+0xb0/0xb0 [] ? update_balloon_stats+0xf0/0xf0 [] kthread+0xc9/0xe0 [] ? kthread_park+0x60/0x60 [] ret_from_fork+0x3f/0x70 [] ? kthread_park+0x60/0x60 Code: 8d 60 e0 0f 84 af 00 00 00 48 8b 43 20 a8 01 75 3b 48 89 d8 f0 0f ba 28 00 72 10 48 8b 03 f6 c4 08 75 2f 48 89 df e8 8c 83 f9 ff <49> 8b 44 24 20 4d 8d 6c 24 20 48 83 e8 20 4d 39 f5 74 7a 4c 89 RIP [] balloon_page_dequeue+0x54/0x130 RSP ---[ end trace 43cf28060d708d5f ]--- Kernel panic - not syncing: Fatal exception Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Signed-off-by: Minchan Kim Signed-off-by: Michael S. Tsirkin Acked-by: Rafael Aquini Signed-off-by: Greg Kroah-Hartman

mm: numa: quickly fail allocations for NUMA balancing on full nodes

2016-03-03T23:07:11+00:00

commit 8479eba7781fa9ffb28268840de6facfc12c35a7 upstream. Commit 4167e9b2cf10 ("mm: remove GFP_THISNODE") removed the GFP_THISNODE flag combination due to confusing semantics. It noted that alloc_misplaced_dst_page() was one such user after changes made by commit e97ca8e5b864 ("mm: fix GFP_THISNODE callers and clarify"). Unfortunately when GFP_THISNODE was removed, users of alloc_misplaced_dst_page() started waking kswapd and entering direct reclaim because the wrong GFP flags are cleared. The consequence is that workloads that used to fit into memory now get reclaimed which is addressed by this patch. The problem can be demonstrated with "mutilate" that exercises memcached which is software dedicated to memory object caching. The configuration uses 80% of memory and is run 3 times for varying numbers of clients. The results on a 4-socket NUMA box are mutilate 4.4.0 4.4.0 vanilla numaswap-v1 Hmean 1 8394.71 ( 0.00%) 8395.32 ( 0.01%) Hmean 4 30024.62 ( 0.00%) 34513.54 ( 14.95%) Hmean 7 32821.08 ( 0.00%) 70542.96 (114.93%) Hmean 12 55229.67 ( 0.00%) 93866.34 ( 69.96%) Hmean 21 39438.96 ( 0.00%) 85749.21 (117.42%) Hmean 30 37796.10 ( 0.00%) 50231.49 ( 32.90%) Hmean 47 18070.91 ( 0.00%) 38530.13 (113.22%) The metric is queries/second with the more the better. The results are way outside of the noise and the reason for the improvement is obvious from some of the vmstats 4.4.0 4.4.0 vanillanumaswap-v1r1 Minor Faults 1929399272 2146148218 Major Faults 19746529 3567 Swap Ins 57307366 9913 Swap Outs 50623229 17094 Allocation stalls 35909 443 DMA allocs 0 0 DMA32 allocs 72976349 170567396 Normal allocs 5306640898 5310651252 Movable allocs 0 0 Direct pages scanned 404130893 799577 Kswapd pages scanned 160230174 0 Kswapd pages reclaimed 55928786 0 Direct pages reclaimed 1843936 41921 Page writes file 2391 0 Page writes anon 50623229 17094 The vanilla kernel is swapping like crazy with large amounts of direct reclaim and kswapd activity. The figures are aggregate but it's known that the bad activity is throughout the entire test. Note that simple streaming anon/file memory consumers also see this problem but it's not as obvious. In those cases, kswapd is awake when it should not be. As there are at least two reclaim-related bugs out there, it's worth spelling out the user-visible impact. This patch only addresses bugs related to excessive reclaim on NUMA hardware when the working set is larger than a NUMA node. There is a bug related to high kswapd CPU usage but the reports are against laptops and other UMA hardware and is not addressed by this patch. Signed-off-by: Mel Gorman Cc: Vlastimil Babka Cc: Johannes Weiner Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED

2016-03-03T23:07:10+00:00

commit ad33bb04b2a6cee6c1f99fabb15cddbf93ff0433 upstream. pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were introduced to locklessy (but atomically) detect when a pmd is a regular (stable) pmd or when the pmd is unstable and can infinitely transition from pmd_none() and pmd_trans_huge() from under us, while only holding the mmap_sem for reading (for writing not). While holding the mmap_sem only for reading, MADV_DONTNEED can run from under us and so before we can assume the pmd to be a regular stable pmd we need to compare it against pmd_none() and pmd_trans_huge() in an atomic way, with pmd_trans_unstable(). The old pmd_trans_huge() left a tiny window for a race. Useful applications are unlikely to notice the difference as doing MADV_DONTNEED concurrently with a page fault would lead to undefined behavior. [akpm@linux-foundation.org: tidy up comment grammar/layout] Signed-off-by: Andrea Arcangeli Reported-by: Kirill A. Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm,thp: khugepaged: call pte flush at the time of collapse

2016-02-25T20:01:23+00:00

commit 6a6ac72fd6ea32594b316513e1826c3f6db4cc93 upstream. This showed up on ARC when running LMBench bw_mem tests as Overlapping TLB Machine Check Exception triggered due to STLB entry (2M pages) overlapping some NTLB entry (regular 8K page). bw_mem 2m touches a large chunk of vaddr creating NTLB entries. In the interim khugepaged kicks in, collapsing the contiguous ptes into a single pmd. pmdp_collapse_flush()->flush_pmd_tlb_range() is called to flush out NTLB entries for the ptes. This for ARC (by design) can only shootdown STLB entries (for pmd). The stray NTLB entries cause the overlap with the subsequent STLB entry for collapsed page. So make pmdp_collapse_flush() call pte flush interface not pmd flush. Note that originally all thp flush call sites in generic code called flush_tlb_range() leaving it to architecture to implement the flush for pte and/or pmd. Commit 12ebc1581ad11454 changed this by calling a new opt-in API flush_pmd_tlb_range() which made the semantics more explicit but failed to distinguish the pte vs pmd flush in generic code, which is what this patch fixes. Note that ARC can fixed w/o touching the generic pmdp_collapse_flush() by defining a ARC version, but that defeats the purpose of generic version, plus sementically this is the right thing to do. Fixes STAR 9000961194: LMBench on AXS103 triggering duplicate TLB exceptions with super pages Fixes: 12ebc1581ad11454 ("mm,thp: introduce flush_pmd_tlb_range") Signed-off-by: Vineet Gupta Reviewed-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

memcg: only free spare array when readers are done

2016-02-25T20:01:22+00:00

commit 6611d8d76132f86faa501de9451a89bf23fb2371 upstream. A spare array holding mem cgroup threshold events is kept around to make sure we can always safely deregister an event and have an array to store the new set of events in. In the scenario where we're going from 1 to 0 registered events, the pointer to the primary array containing 1 event is copied to the spare slot, and then the spare slot is freed because no events are left. However, it is freed before calling synchronize_rcu(), which means readers may still be accessing threshold->primary after it is freed. Fixed by only freeing after synchronize_rcu(). Signed-off-by: Martijn Coenen Cc: Johannes Weiner Acked-by: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm: fix regression in remap_file_pages() emulation

2016-02-25T20:01:21+00:00

commit 48f7df329474b49d83d0dffec1b6186647f11976 upstream. Grazvydas Ignotas has reported a regression in remap_file_pages() emulation. Testcase: #define _GNU_SOURCE #include #include #include #include #define SIZE (4096 * 3) int main(int argc, char **argv) { unsigned long *p; long i; p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (p == MAP_FAILED) { perror("mmap"); return -1; } for (i = 0; i < SIZE / 4096; i++) p[i * 4096 / sizeof(*p)] = i; if (remap_file_pages(p, 4096, 0, 1, 0)) { perror("remap_file_pages"); return -1; } if (remap_file_pages(p, 4096 * 2, 0, 1, 0)) { perror("remap_file_pages"); return -1; } assert(p[0] == 1); munmap(p, SIZE); return 0; } The second remap_file_pages() fails with -EINVAL. The reason is that remap_file_pages() emulation assumes that the target vma covers whole area we want to over map. That assumption is broken by first remap_file_pages() call: it split the area into two vma. The solution is to check next adjacent vmas, if they map the same file with the same flags. Fixes: c8d78c1823f4 ("mm: replace remap_file_pages() syscall with emulation") Signed-off-by: Kirill A. Shutemov Reported-by: Grazvydas Ignotas Tested-by: Grazvydas Ignotas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm: replace vma_lock_anon_vma with anon_vma_lock_read/write

2016-02-25T20:01:21+00:00

commit 12352d3cae2cebe18805a91fab34b534d7444231 upstream. Sequence vma_lock_anon_vma() - vma_unlock_anon_vma() isn't safe if anon_vma appeared between lock and unlock. We have to check anon_vma first or call anon_vma_prepare() to be sure that it's here. There are only few users of these legacy helpers. Let's get rid of them. This patch fixes anon_vma lock imbalance in validate_mm(). Write lock isn't required here, read lock is enough. And reorders expand_downwards/expand_upwards: security_mmap_addr() and wrapping-around check don't have to be under anon vma lock. Link: https://lkml.kernel.org/r/CACT4Y+Y908EjM2z=706dv4rV6dWtxTLK9nFg9_7DhRMLppBo2g@mail.gmail.com Signed-off-by: Konstantin Khlebnikov Reported-by: Dmitry Vyukov Acked-by: Kirill A. Shutemov Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm: fix mlock accouting

2016-02-25T20:01:21+00:00

commit 7162a1e87b3e380133dadc7909081bb70d0a7041 upstream. Tetsuo Handa reported underflow of NR_MLOCK on munlock. Testcase: #include #include #include #define BASE ((void *)0x400000000000) #define SIZE (1UL << 21) int main(int argc, char *argv[]) { void *addr; system("grep Mlocked /proc/meminfo"); addr = mmap(BASE, SIZE, PROT_READ | PROT_WRITE, MAP_ANONYMOUS | MAP_PRIVATE | MAP_LOCKED | MAP_FIXED, -1, 0); if (addr == MAP_FAILED) printf("mmap() failed\n"), exit(1); munmap(addr, SIZE); system("grep Mlocked /proc/meminfo"); return 0; } It happens on munlock_vma_page() due to unfortunate choice of nr_pages data type: __mod_zone_page_state(zone, NR_MLOCK, -nr_pages); For unsigned int nr_pages, implicitly casted to long in __mod_zone_page_state(), it becomes something around UINT_MAX. munlock_vma_page() usually called for THP as small pages go though pagevec. Let's make nr_pages signed int. Similar fixes in 6cdb18ad98a4 ("mm/vmstat: fix overflow in mod_zone_page_state()") used `long' type, but `int' here is OK for a count of the number of sub-pages in a huge page. Fixes: ff6a6da60b89 ("mm: accelerate munlock() treatment of THP pages") Signed-off-by: Kirill A. Shutemov Reported-by: Tetsuo Handa Tested-by: Tetsuo Handa Cc: Michel Lespinasse Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman

mm: soft-offline: check return value in second __get_any_page() call

2016-02-25T20:01:21+00:00

commit d96b339f453997f2f08c52da3f41423be48c978f upstream. I saw the following BUG_ON triggered in a testcase where a process calls madvise(MADV_SOFT_OFFLINE) on thps, along with a background process that calls migratepages command repeatedly (doing ping-pong among different NUMA nodes) for the first process: Soft offlining page 0x60000 at 0x700000600000 __get_any_page: 0x60000 free buddy page page:ffffea0001800000 count:0 mapcount:-127 mapping: (null) index:0x1 flags: 0x1fffc0000000000() page dumped because: VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0) ------------[ cut here ]------------ kernel BUG at /src/linux-dev/include/linux/mm.h:342! invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC Modules linked in: cfg80211 rfkill crc32c_intel serio_raw virtio_balloon i2c_piix4 virtio_blk virtio_net ata_generic pata_acpi CPU: 3 PID: 3035 Comm: test_alloc_gene Tainted: G O 4.4.0-rc8-v4.4-rc8-160107-1501-00000-rc8+ #74 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff88007c63d5c0 ti: ffff88007c210000 task.ti: ffff88007c210000 RIP: 0010:[] [] put_page+0x5c/0x60 RSP: 0018:ffff88007c213e00 EFLAGS: 00010246 Call Trace: put_hwpoison_page+0x4e/0x80 soft_offline_page+0x501/0x520 SyS_madvise+0x6bc/0x6f0 entry_SYSCALL_64_fastpath+0x12/0x6a Code: 8b fc ff ff 5b 5d c3 48 89 df e8 b0 fa ff ff 48 89 df 31 f6 e8 c6 7d ff ff 5b 5d c3 48 c7 c6 08 54 a2 81 48 89 df e8 a4 c5 01 00 <0f> 0b 66 90 66 66 66 66 90 55 48 89 e5 41 55 41 54 53 48 8b 47 RIP [] put_page+0x5c/0x60 RSP The root cause resides in get_any_page() which retries to get a refcount of the page to be soft-offlined. This function calls put_hwpoison_page(), expecting that the target page is putback to LRU list. But it can be also freed to buddy. So the second check need to care about such case. Fixes: af8fae7c0886 ("mm/memory-failure.c: clean up soft_offline_page()") Signed-off-by: Naoya Horiguchi Cc: Sasha Levin Cc: Aneesh Kumar K.V Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Andrea Arcangeli Cc: Hugh Dickins Cc: Dave Hansen Cc: Mel Gorman Cc: Rik van Riel Cc: Steve Capper Cc: Johannes Weiner Cc: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman