korg/linux
0
0
Fork 0
mirror of https://mirrors.bfsu.edu.cn/git/linux.git synced 2024-11-11 12:28:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

btrfs: fix lockdep splat in btrfs_alloc_subvolume_writers

Browse Source 
While running btrfs/011, I hit the following lockdep splat.

This is the important bit:
   pcpu_alloc+0x1ac/0x5e0
   __percpu_counter_init+0x4e/0xb0
   btrfs_init_fs_root+0x99/0x1c0 [btrfs]
   btrfs_get_fs_root.part.54+0x5b/0x150 [btrfs]
   resolve_indirect_refs+0x130/0x830 [btrfs]
   find_parent_nodes+0x69e/0xff0 [btrfs]
   btrfs_find_all_roots_safe+0xa0/0x110 [btrfs]
   btrfs_find_all_roots+0x50/0x70 [btrfs]
   btrfs_qgroup_prepare_account_extents+0x53/0x90 [btrfs]
   btrfs_commit_transaction+0x3ce/0x9b0 [btrfs]

The percpu_counter_init call in btrfs_alloc_subvolume_writers
uses GFP_KERNEL, which we can't do during transaction commit.

This switches it to GFP_NOFS.

========================================================
WARNING: possible irq lock inversion dependency detected
4.12.14-kvmsmall #8 Tainted: G        W
--------------------------------------------------------
kswapd0/50 just changed the state of lock:
 (&delayed_node->mutex){+.+.-.}, at: [<ffffffffc06994fa>] __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
but this lock took another, RECLAIM_FS-unsafe lock in the past:
 (pcpu_alloc_mutex){+.+.+.}

and interrupts could create inverse lock ordering between them.

other info that might help us debug this:
Chain exists of:
  &delayed_node->mutex --> &found->groups_sem --> pcpu_alloc_mutex

 Possible interrupt unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(pcpu_alloc_mutex);
                               local_irq_disable();
                               lock(&delayed_node->mutex);
                               lock(&found->groups_sem);
  <Interrupt>
    lock(&delayed_node->mutex);

 *** DEADLOCK ***

2 locks held by kswapd0/50:
 #0:  (shrinker_rwsem){++++..}, at: [<ffffffff811dc11f>] shrink_slab+0x7f/0x5b0
 #1:  (&type->s_umount_key#30){+++++.}, at: [<ffffffff8126dec6>] trylock_super+0x16/0x50

the shortest dependencies between 2nd lock and 1st lock:
   -> (pcpu_alloc_mutex){+.+.+.} ops: 4904 {
      HARDIRQ-ON-W at:
                          __mutex_lock+0x4e/0x8c0
                          pcpu_alloc+0x1ac/0x5e0
                          alloc_kmem_cache_cpus.isra.70+0x25/0xa0
                          __do_tune_cpucache+0x2c/0x220
                          do_tune_cpucache+0x26/0xc0
                          enable_cpucache+0x6d/0xf0
                          kmem_cache_init_late+0x42/0x75
                          start_kernel+0x343/0x4cb
                          x86_64_start_kernel+0x127/0x134
                          secondary_startup_64+0xa5/0xb0
      SOFTIRQ-ON-W at:
                          __mutex_lock+0x4e/0x8c0
                          pcpu_alloc+0x1ac/0x5e0
                          alloc_kmem_cache_cpus.isra.70+0x25/0xa0
                          __do_tune_cpucache+0x2c/0x220
                          do_tune_cpucache+0x26/0xc0
                          enable_cpucache+0x6d/0xf0
                          kmem_cache_init_late+0x42/0x75
                          start_kernel+0x343/0x4cb
                          x86_64_start_kernel+0x127/0x134
                          secondary_startup_64+0xa5/0xb0
      RECLAIM_FS-ON-W at:
                             __kmalloc+0x47/0x310
                             pcpu_extend_area_map+0x2b/0xc0
                             pcpu_alloc+0x3ec/0x5e0
                             alloc_kmem_cache_cpus.isra.70+0x25/0xa0
                             __do_tune_cpucache+0x2c/0x220
                             do_tune_cpucache+0x26/0xc0
                             enable_cpucache+0x6d/0xf0
                             __kmem_cache_create+0x1bf/0x390
                             create_cache+0xba/0x1b0
                             kmem_cache_create+0x1f8/0x2b0
                             ksm_init+0x6f/0x19d
                             do_one_initcall+0x50/0x1b0
                             kernel_init_freeable+0x201/0x289
                             kernel_init+0xa/0x100
                             ret_from_fork+0x3a/0x50
      INITIAL USE at:
                         __mutex_lock+0x4e/0x8c0
                         pcpu_alloc+0x1ac/0x5e0
                         alloc_kmem_cache_cpus.isra.70+0x25/0xa0
                         setup_cpu_cache+0x2f/0x1f0
                         __kmem_cache_create+0x1bf/0x390
                         create_boot_cache+0x8b/0xb1
                         kmem_cache_init+0xa1/0x19e
                         start_kernel+0x270/0x4cb
                         x86_64_start_kernel+0x127/0x134
                         secondary_startup_64+0xa5/0xb0
    }
    ... key      at: [<ffffffff821d8e70>] pcpu_alloc_mutex+0x70/0xa0
    ... acquired at:
   pcpu_alloc+0x1ac/0x5e0
   __percpu_counter_init+0x4e/0xb0
   btrfs_init_fs_root+0x99/0x1c0 [btrfs]
   btrfs_get_fs_root.part.54+0x5b/0x150 [btrfs]
   resolve_indirect_refs+0x130/0x830 [btrfs]
   find_parent_nodes+0x69e/0xff0 [btrfs]
   btrfs_find_all_roots_safe+0xa0/0x110 [btrfs]
   btrfs_find_all_roots+0x50/0x70 [btrfs]
   btrfs_qgroup_prepare_account_extents+0x53/0x90 [btrfs]
   btrfs_commit_transaction+0x3ce/0x9b0 [btrfs]
   transaction_kthread+0x176/0x1b0 [btrfs]
   kthread+0x102/0x140
   ret_from_fork+0x3a/0x50

  -> (&fs_info->commit_root_sem){++++..} ops: 1566382 {
     HARDIRQ-ON-W at:
                        down_write+0x3e/0xa0
                        cache_block_group+0x287/0x420 [btrfs]
                        find_free_extent+0x106c/0x12d0 [btrfs]
                        btrfs_reserve_extent+0xd8/0x170 [btrfs]
                        cow_file_range.isra.66+0x133/0x470 [btrfs]
                        run_delalloc_range+0x121/0x410 [btrfs]
                        writepage_delalloc.isra.50+0xfe/0x180 [btrfs]
                        __extent_writepage+0x19a/0x360 [btrfs]
                        extent_write_cache_pages.constprop.56+0x249/0x3e0 [btrfs]
                        extent_writepages+0x4d/0x60 [btrfs]
                        do_writepages+0x1a/0x70
                        __filemap_fdatawrite_range+0xa7/0xe0
                        btrfs_rename+0x5ee/0xdb0 [btrfs]
                        vfs_rename+0x52a/0x7e0
                        SyS_rename+0x351/0x3b0
                        do_syscall_64+0x79/0x1e0
                        entry_SYSCALL_64_after_hwframe+0x42/0xb7
     HARDIRQ-ON-R at:
                        down_read+0x35/0x90
                        caching_thread+0x57/0x560 [btrfs]
                        normal_work_helper+0x1c0/0x5e0 [btrfs]
                        process_one_work+0x1e0/0x5c0
                        worker_thread+0x44/0x390
                        kthread+0x102/0x140
                        ret_from_fork+0x3a/0x50
     SOFTIRQ-ON-W at:
                        down_write+0x3e/0xa0
                        cache_block_group+0x287/0x420 [btrfs]
                        find_free_extent+0x106c/0x12d0 [btrfs]
                        btrfs_reserve_extent+0xd8/0x170 [btrfs]
                        cow_file_range.isra.66+0x133/0x470 [btrfs]
                        run_delalloc_range+0x121/0x410 [btrfs]
                        writepage_delalloc.isra.50+0xfe/0x180 [btrfs]
                        __extent_writepage+0x19a/0x360 [btrfs]
                        extent_write_cache_pages.constprop.56+0x249/0x3e0 [btrfs]
                        extent_writepages+0x4d/0x60 [btrfs]
                        do_writepages+0x1a/0x70
                        __filemap_fdatawrite_range+0xa7/0xe0
                        btrfs_rename+0x5ee/0xdb0 [btrfs]
                        vfs_rename+0x52a/0x7e0
                        SyS_rename+0x351/0x3b0
                        do_syscall_64+0x79/0x1e0
                        entry_SYSCALL_64_after_hwframe+0x42/0xb7
     SOFTIRQ-ON-R at:
                        down_read+0x35/0x90
                        caching_thread+0x57/0x560 [btrfs]
                        normal_work_helper+0x1c0/0x5e0 [btrfs]
                        process_one_work+0x1e0/0x5c0
                        worker_thread+0x44/0x390
                        kthread+0x102/0x140
                        ret_from_fork+0x3a/0x50
     INITIAL USE at:
                       down_write+0x3e/0xa0
                       cache_block_group+0x287/0x420 [btrfs]
                       find_free_extent+0x106c/0x12d0 [btrfs]
                       btrfs_reserve_extent+0xd8/0x170 [btrfs]
                       cow_file_range.isra.66+0x133/0x470 [btrfs]
                       run_delalloc_range+0x121/0x410 [btrfs]
                       writepage_delalloc.isra.50+0xfe/0x180 [btrfs]
                       __extent_writepage+0x19a/0x360 [btrfs]
                       extent_write_cache_pages.constprop.56+0x249/0x3e0 [btrfs]
                       extent_writepages+0x4d/0x60 [btrfs]
                       do_writepages+0x1a/0x70
                       __filemap_fdatawrite_range+0xa7/0xe0
                       btrfs_rename+0x5ee/0xdb0 [btrfs]
                       vfs_rename+0x52a/0x7e0
                       SyS_rename+0x351/0x3b0
                       do_syscall_64+0x79/0x1e0
                       entry_SYSCALL_64_after_hwframe+0x42/0xb7
   }
   ... key      at: [<ffffffffc0729578>] __key.61970+0x0/0xfffffffffff9aa88 [btrfs]
   ... acquired at:
   cache_block_group+0x287/0x420 [btrfs]
   find_free_extent+0x106c/0x12d0 [btrfs]
   btrfs_reserve_extent+0xd8/0x170 [btrfs]
   btrfs_alloc_tree_block+0x12f/0x4c0 [btrfs]
   btrfs_create_tree+0xbb/0x2a0 [btrfs]
   btrfs_create_uuid_tree+0x37/0x140 [btrfs]
   open_ctree+0x23c0/0x2660 [btrfs]
   btrfs_mount+0xd36/0xf90 [btrfs]
   mount_fs+0x3a/0x160
   vfs_kern_mount+0x66/0x150
   btrfs_mount+0x18c/0xf90 [btrfs]
   mount_fs+0x3a/0x160
   vfs_kern_mount+0x66/0x150
   do_mount+0x1c1/0xcc0
   SyS_mount+0x7e/0xd0
   do_syscall_64+0x79/0x1e0
   entry_SYSCALL_64_after_hwframe+0x42/0xb7

 -> (&found->groups_sem){++++..} ops: 2134587 {
    HARDIRQ-ON-W at:
                      down_write+0x3e/0xa0
                      __link_block_group+0x34/0x130 [btrfs]
                      btrfs_read_block_groups+0x33d/0x7b0 [btrfs]
                      open_ctree+0x2054/0x2660 [btrfs]
                      btrfs_mount+0xd36/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      btrfs_mount+0x18c/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      do_mount+0x1c1/0xcc0
                      SyS_mount+0x7e/0xd0
                      do_syscall_64+0x79/0x1e0
                      entry_SYSCALL_64_after_hwframe+0x42/0xb7
    HARDIRQ-ON-R at:
                      down_read+0x35/0x90
                      btrfs_calc_num_tolerated_disk_barrier_failures+0x113/0x1f0 [btrfs]
                      open_ctree+0x207b/0x2660 [btrfs]
                      btrfs_mount+0xd36/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      btrfs_mount+0x18c/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      do_mount+0x1c1/0xcc0
                      SyS_mount+0x7e/0xd0
                      do_syscall_64+0x79/0x1e0
                      entry_SYSCALL_64_after_hwframe+0x42/0xb7
    SOFTIRQ-ON-W at:
                      down_write+0x3e/0xa0
                      __link_block_group+0x34/0x130 [btrfs]
                      btrfs_read_block_groups+0x33d/0x7b0 [btrfs]
                      open_ctree+0x2054/0x2660 [btrfs]
                      btrfs_mount+0xd36/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      btrfs_mount+0x18c/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      do_mount+0x1c1/0xcc0
                      SyS_mount+0x7e/0xd0
                      do_syscall_64+0x79/0x1e0
                      entry_SYSCALL_64_after_hwframe+0x42/0xb7
    SOFTIRQ-ON-R at:
                      down_read+0x35/0x90
                      btrfs_calc_num_tolerated_disk_barrier_failures+0x113/0x1f0 [btrfs]
                      open_ctree+0x207b/0x2660 [btrfs]
                      btrfs_mount+0xd36/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      btrfs_mount+0x18c/0xf90 [btrfs]
                      mount_fs+0x3a/0x160
                      vfs_kern_mount+0x66/0x150
                      do_mount+0x1c1/0xcc0
                      SyS_mount+0x7e/0xd0
                      do_syscall_64+0x79/0x1e0
                      entry_SYSCALL_64_after_hwframe+0x42/0xb7
    INITIAL USE at:
                     down_write+0x3e/0xa0
                     __link_block_group+0x34/0x130 [btrfs]
                     btrfs_read_block_groups+0x33d/0x7b0 [btrfs]
                     open_ctree+0x2054/0x2660 [btrfs]
                     btrfs_mount+0xd36/0xf90 [btrfs]
                     mount_fs+0x3a/0x160
                     vfs_kern_mount+0x66/0x150
                     btrfs_mount+0x18c/0xf90 [btrfs]
                     mount_fs+0x3a/0x160
                     vfs_kern_mount+0x66/0x150
                     do_mount+0x1c1/0xcc0
                     SyS_mount+0x7e/0xd0
                     do_syscall_64+0x79/0x1e0
                     entry_SYSCALL_64_after_hwframe+0x42/0xb7
  }
  ... key      at: [<ffffffffc0729488>] __key.59101+0x0/0xfffffffffff9ab78 [btrfs]
  ... acquired at:
   find_free_extent+0xcb4/0x12d0 [btrfs]
   btrfs_reserve_extent+0xd8/0x170 [btrfs]
   btrfs_alloc_tree_block+0x12f/0x4c0 [btrfs]
   __btrfs_cow_block+0x110/0x5b0 [btrfs]
   btrfs_cow_block+0xd7/0x290 [btrfs]
   btrfs_search_slot+0x1f6/0x960 [btrfs]
   btrfs_lookup_inode+0x2a/0x90 [btrfs]
   __btrfs_update_delayed_inode+0x65/0x210 [btrfs]
   btrfs_commit_inode_delayed_inode+0x121/0x130 [btrfs]
   btrfs_evict_inode+0x3fe/0x6a0 [btrfs]
   evict+0xc4/0x190
   __dentry_kill+0xbf/0x170
   dput+0x2ae/0x2f0
   SyS_rename+0x2a6/0x3b0
   do_syscall_64+0x79/0x1e0
   entry_SYSCALL_64_after_hwframe+0x42/0xb7

-> (&delayed_node->mutex){+.+.-.} ops: 5580204 {
   HARDIRQ-ON-W at:
                    __mutex_lock+0x4e/0x8c0
                    btrfs_delayed_update_inode+0x46/0x6e0 [btrfs]
                    btrfs_update_inode+0x83/0x110 [btrfs]
                    btrfs_dirty_inode+0x62/0xe0 [btrfs]
                    touch_atime+0x8c/0xb0
                    do_generic_file_read+0x818/0xb10
                    __vfs_read+0xdc/0x150
                    vfs_read+0x8a/0x130
                    SyS_read+0x45/0xa0
                    do_syscall_64+0x79/0x1e0
                    entry_SYSCALL_64_after_hwframe+0x42/0xb7
   SOFTIRQ-ON-W at:
                    __mutex_lock+0x4e/0x8c0
                    btrfs_delayed_update_inode+0x46/0x6e0 [btrfs]
                    btrfs_update_inode+0x83/0x110 [btrfs]
                    btrfs_dirty_inode+0x62/0xe0 [btrfs]
                    touch_atime+0x8c/0xb0
                    do_generic_file_read+0x818/0xb10
                    __vfs_read+0xdc/0x150
                    vfs_read+0x8a/0x130
                    SyS_read+0x45/0xa0
                    do_syscall_64+0x79/0x1e0
                    entry_SYSCALL_64_after_hwframe+0x42/0xb7
   IN-RECLAIM_FS-W at:
                       __mutex_lock+0x4e/0x8c0
                       __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
                       btrfs_evict_inode+0x22c/0x6a0 [btrfs]
                       evict+0xc4/0x190
                       dispose_list+0x35/0x50
                       prune_icache_sb+0x42/0x50
                       super_cache_scan+0x139/0x190
                       shrink_slab+0x262/0x5b0
                       shrink_node+0x2eb/0x2f0
                       kswapd+0x2eb/0x890
                       kthread+0x102/0x140
                       ret_from_fork+0x3a/0x50
   INITIAL USE at:
                   __mutex_lock+0x4e/0x8c0
                   btrfs_delayed_update_inode+0x46/0x6e0 [btrfs]
                   btrfs_update_inode+0x83/0x110 [btrfs]
                   btrfs_dirty_inode+0x62/0xe0 [btrfs]
                   touch_atime+0x8c/0xb0
                   do_generic_file_read+0x818/0xb10
                   __vfs_read+0xdc/0x150
                   vfs_read+0x8a/0x130
                   SyS_read+0x45/0xa0
                   do_syscall_64+0x79/0x1e0
                   entry_SYSCALL_64_after_hwframe+0x42/0xb7
 }
 ... key      at: [<ffffffffc072d488>] __key.56935+0x0/0xfffffffffff96b78 [btrfs]
 ... acquired at:
   __lock_acquire+0x264/0x11c0
   lock_acquire+0xbd/0x1e0
   __mutex_lock+0x4e/0x8c0
   __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
   btrfs_evict_inode+0x22c/0x6a0 [btrfs]
   evict+0xc4/0x190
   dispose_list+0x35/0x50
   prune_icache_sb+0x42/0x50
   super_cache_scan+0x139/0x190
   shrink_slab+0x262/0x5b0
   shrink_node+0x2eb/0x2f0
   kswapd+0x2eb/0x890
   kthread+0x102/0x140
   ret_from_fork+0x3a/0x50

stack backtrace:
CPU: 1 PID: 50 Comm: kswapd0 Tainted: G        W        4.12.14-kvmsmall #8 SLE15 (unreleased)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
 dump_stack+0x78/0xb7
 print_irq_inversion_bug.part.38+0x19f/0x1aa
 check_usage_forwards+0x102/0x120
 ? ret_from_fork+0x3a/0x50
 ? check_usage_backwards+0x110/0x110
 mark_lock+0x16c/0x270
 __lock_acquire+0x264/0x11c0
 ? pagevec_lookup_entries+0x1a/0x30
 ? truncate_inode_pages_range+0x2b3/0x7f0
 lock_acquire+0xbd/0x1e0
 ? __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
 __mutex_lock+0x4e/0x8c0
 ? __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
 ? __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
 ? btrfs_evict_inode+0x1f6/0x6a0 [btrfs]
 __btrfs_release_delayed_node+0x3a/0x1f0 [btrfs]
 btrfs_evict_inode+0x22c/0x6a0 [btrfs]
 evict+0xc4/0x190
 dispose_list+0x35/0x50
 prune_icache_sb+0x42/0x50
 super_cache_scan+0x139/0x190
 shrink_slab+0x262/0x5b0
 shrink_node+0x2eb/0x2f0
 kswapd+0x2eb/0x890
 kthread+0x102/0x140
 ? mem_cgroup_shrink_node+0x2c0/0x2c0
 ? kthread_create_on_node+0x40/0x40
 ret_from_fork+0x3a/0x50

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: David Sterba <dsterba@suse.com>
This commit is contained in:
Jeff Mahoney 2018-03-16 14:36:27 -04:00 committed by David Sterba
parent 8ba0ae7821
commit 8a5a916d9a
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
fs/btrfs/disk-io.c
View File

@ -1095,7 +1095,7 @@ static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
if (!writers)
return ERR_PTR(-ENOMEM);
ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
ret = percpu_counter_init(&writers->counter, 0, GFP_NOFS);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);