From 9fecd13202f520f3f25d5b1c313adb740fe19773 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 1 Jun 2020 19:12:06 +0100 Subject: [PATCH 01/10] btrfs: fix a block group ref counter leak after failure to remove block group When removing a block group, if we fail to delete the block group's item from the extent tree, we jump to the 'out' label and end up decrementing the block group's reference count once only (by 1), resulting in a counter leak because the block group at that point was already removed from the block group cache rbtree - so we have to decrement the reference count twice, once for the rbtree and once for our lookup at the start of the function. There is a second bug where if removing the free space tree entries (the call to remove_block_group_free_space()) fails we end up jumping to the 'out_put_group' label but end up decrementing the reference count only once, when we should have done it twice, since we have already removed the block group from the block group cache rbtree. This happens because the reference count decrement for the rbtree reference happens after attempting to remove the free space tree entries, which is far away from the place where we remove the block group from the rbtree. To make things less error prone, decrement the reference count for the rbtree immediately after removing the block group from it. This also eleminates the need for two different exit labels on error, renaming 'out_put_label' to just 'out' and removing the old 'out'. Fixes: f6033c5e333238 ("btrfs: fix block group leak when removing fails") CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 176e8a292fd1..6462dd0b155c 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -940,7 +940,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; - goto out_put_group; + goto out; } /* @@ -978,7 +978,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(inode); - goto out_put_group; + goto out; } clear_nlink(inode); /* One for the block groups ref */ @@ -1001,13 +1001,13 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); if (ret < 0) - goto out_put_group; + goto out; if (ret > 0) btrfs_release_path(path); if (ret == 0) { ret = btrfs_del_item(trans, tree_root, path); if (ret) - goto out_put_group; + goto out; btrfs_release_path(path); } @@ -1016,6 +1016,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, &fs_info->block_group_cache_tree); RB_CLEAR_NODE(&block_group->cache_node); + /* Once for the block groups rbtree */ + btrfs_put_block_group(block_group); + if (fs_info->first_logical_byte == block_group->start) fs_info->first_logical_byte = (u64)-1; spin_unlock(&fs_info->block_group_cache_lock); @@ -1125,10 +1128,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, ret = remove_block_group_free_space(trans, block_group); if (ret) - goto out_put_group; - - /* Once for the block groups rbtree */ - btrfs_put_block_group(block_group); + goto out; ret = remove_block_group_item(trans, path, block_group); if (ret < 0) @@ -1145,10 +1145,9 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, free_extent_map(em); } -out_put_group: +out: /* Once for the lookup reference */ btrfs_put_block_group(block_group); -out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); btrfs_free_path(path); From ffcb9d44572afbaf8fa6dbf5115bff6dab7b299e Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 1 Jun 2020 19:12:19 +0100 Subject: [PATCH 02/10] btrfs: fix race between block group removal and block group creation There is a race between block group removal and block group creation when the removal is completed by a task running fitrim or scrub. When this happens we end up failing the block group creation with an error -EEXIST since we attempt to insert a duplicate block group item key in the extent tree. That results in a transaction abort. The race happens like this: 1) Task A is doing a fitrim, and at btrfs_trim_block_group() it freezes block group X with btrfs_freeze_block_group() (until very recently that was named btrfs_get_block_group_trimming()); 2) Task B starts removing block group X, either because it's now unused or due to relocation for example. So at btrfs_remove_block_group(), while holding the chunk mutex and the block group's lock, it sets the 'removed' flag of the block group and it sets the local variable 'remove_em' to false, because the block group is currently frozen (its 'frozen' counter is > 0, until very recently this counter was named 'trimming'); 3) Task B unlocks the block group and the chunk mutex; 4) Task A is done trimming the block group and unfreezes the block group by calling btrfs_unfreeze_block_group() (until very recently this was named btrfs_put_block_group_trimming()). In this function we lock the block group and set the local variable 'cleanup' to true because we were able to decrement the block group's 'frozen' counter down to 0 and the flag 'removed' is set in the block group. Since 'cleanup' is set to true, it locks the chunk mutex and removes the extent mapping representing the block group from the mapping tree; 5) Task C allocates a new block group Y and it picks up the logical address that block group X had as the logical address for Y, because X was the block group with the highest logical address and now the second block group with the highest logical address, the last in the fs mapping tree, ends at an offset corresponding to block group X's logical address (this logical address selection is done at volumes.c:find_next_chunk()). At this point the new block group Y does not have yet its item added to the extent tree (nor the corresponding device extent items and chunk item in the device and chunk trees). The new group Y is added to the list of pending block groups in the transaction handle; 6) Before task B proceeds to removing the block group item for block group X from the extent tree, which has a key matching: (X logical offset, BTRFS_BLOCK_GROUP_ITEM_KEY, length) task C while ending its transaction handle calls btrfs_create_pending_block_groups(), which finds block group Y and tries to insert the block group item for Y into the exten tree, which fails with -EEXIST since logical offset is the same that X had and task B hasn't yet deleted the key from the extent tree. This failure results in a transaction abort, producing a stack like the following: ------------[ cut here ]------------ BTRFS: Transaction aborted (error -17) WARNING: CPU: 2 PID: 19736 at fs/btrfs/block-group.c:2074 btrfs_create_pending_block_groups+0x1eb/0x260 [btrfs] Modules linked in: btrfs blake2b_generic xor raid6_pq (...) CPU: 2 PID: 19736 Comm: fsstress Tainted: G W 5.6.0-rc7-btrfs-next-58 #5 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 RIP: 0010:btrfs_create_pending_block_groups+0x1eb/0x260 [btrfs] Code: ff ff ff 48 8b 55 50 f0 48 (...) RSP: 0018:ffffa4160a1c7d58 EFLAGS: 00010286 RAX: 0000000000000000 RBX: ffff961581909d98 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffffffffb3d63990 RDI: 0000000000000001 RBP: ffff9614f3356a58 R08: 0000000000000000 R09: 0000000000000001 R10: ffff9615b65b0040 R11: 0000000000000000 R12: ffff961581909c10 R13: ffff9615b0c32000 R14: ffff9614f3356ab0 R15: ffff9614be779000 FS: 00007f2ce2841e80(0000) GS:ffff9615bae00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000555f18780000 CR3: 0000000131d34005 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: btrfs_start_dirty_block_groups+0x398/0x4e0 [btrfs] btrfs_commit_transaction+0xd0/0xc50 [btrfs] ? btrfs_attach_transaction_barrier+0x1e/0x50 [btrfs] ? __ia32_sys_fdatasync+0x20/0x20 iterate_supers+0xdb/0x180 ksys_sync+0x60/0xb0 __ia32_sys_sync+0xa/0x10 do_syscall_64+0x5c/0x280 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7f2ce1d4d5b7 Code: 83 c4 08 48 3d 01 (...) RSP: 002b:00007ffd8b558c58 EFLAGS: 00000202 ORIG_RAX: 00000000000000a2 RAX: ffffffffffffffda RBX: 000000000000002c RCX: 00007f2ce1d4d5b7 RDX: 00000000ffffffff RSI: 00000000186ba07b RDI: 000000000000002c RBP: 0000555f17b9e520 R08: 0000000000000012 R09: 000000000000ce00 R10: 0000000000000078 R11: 0000000000000202 R12: 0000000000000032 R13: 0000000051eb851f R14: 00007ffd8b558cd0 R15: 0000555f1798ec20 irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [] copy_process+0x74f/0x2020 softirqs last enabled at (0): [] copy_process+0x74f/0x2020 softirqs last disabled at (0): [<0000000000000000>] 0x0 ---[ end trace bd7c03622e0b0a9c ]--- Fix this simply by making btrfs_remove_block_group() remove the block group's item from the extent tree before it flags the block group as removed. Also make the free space deletion from the free space tree before flagging the block group as removed, to avoid a similar race with adding and removing free space entries for the free space tree. Fixes: 04216820fe83d5 ("Btrfs: fix race between fs trimming and block group remove/allocation") CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/block-group.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 6462dd0b155c..c037ef514b64 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1092,6 +1092,25 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, spin_unlock(&block_group->space_info->lock); + /* + * Remove the free space for the block group from the free space tree + * and the block group's item from the extent tree before marking the + * block group as removed. This is to prevent races with tasks that + * freeze and unfreeze a block group, this task and another task + * allocating a new block group - the unfreeze task ends up removing + * the block group's extent map before the task calling this function + * deletes the block group item from the extent tree, allowing for + * another task to attempt to create another block group with the same + * item key (and failing with -EEXIST and a transaction abort). + */ + ret = remove_block_group_free_space(trans, block_group); + if (ret) + goto out; + + ret = remove_block_group_item(trans, path, block_group); + if (ret < 0) + goto out; + mutex_lock(&fs_info->chunk_mutex); spin_lock(&block_group->lock); block_group->removed = 1; @@ -1126,14 +1145,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, mutex_unlock(&fs_info->chunk_mutex); - ret = remove_block_group_free_space(trans, block_group); - if (ret) - goto out; - - ret = remove_block_group_item(trans, path, block_group); - if (ret < 0) - goto out; - if (remove_em) { struct extent_map_tree *em_tree; From 432cd2a10f1c10cead91fe706ff5dc52f06d642a Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 8 Jun 2020 13:32:55 +0100 Subject: [PATCH 03/10] btrfs: fix data block group relocation failure due to concurrent scrub When running relocation of a data block group while scrub is running in parallel, it is possible that the relocation will fail and abort the current transaction with an -EINVAL error: [134243.988595] BTRFS info (device sdc): found 14 extents, stage: move data extents [134243.999871] ------------[ cut here ]------------ [134244.000741] BTRFS: Transaction aborted (error -22) [134244.001692] WARNING: CPU: 0 PID: 26954 at fs/btrfs/ctree.c:1071 __btrfs_cow_block+0x6a7/0x790 [btrfs] [134244.003380] Modules linked in: btrfs blake2b_generic xor raid6_pq (...) [134244.012577] CPU: 0 PID: 26954 Comm: btrfs Tainted: G W 5.6.0-rc7-btrfs-next-58 #5 [134244.014162] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [134244.016184] RIP: 0010:__btrfs_cow_block+0x6a7/0x790 [btrfs] [134244.017151] Code: 48 c7 c7 (...) [134244.020549] RSP: 0018:ffffa41607863888 EFLAGS: 00010286 [134244.021515] RAX: 0000000000000000 RBX: ffff9614bdfe09c8 RCX: 0000000000000000 [134244.022822] RDX: 0000000000000001 RSI: ffffffffb3d63980 RDI: 0000000000000001 [134244.024124] RBP: ffff961589e8c000 R08: 0000000000000000 R09: 0000000000000001 [134244.025424] R10: ffffffffc0ae5955 R11: 0000000000000000 R12: ffff9614bd530d08 [134244.026725] R13: ffff9614ced41b88 R14: ffff9614bdfe2a48 R15: 0000000000000000 [134244.028024] FS: 00007f29b63c08c0(0000) GS:ffff9615ba600000(0000) knlGS:0000000000000000 [134244.029491] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [134244.030560] CR2: 00007f4eb339b000 CR3: 0000000130d6e006 CR4: 00000000003606f0 [134244.031997] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [134244.033153] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [134244.034484] Call Trace: [134244.034984] btrfs_cow_block+0x12b/0x2b0 [btrfs] [134244.035859] do_relocation+0x30b/0x790 [btrfs] [134244.036681] ? do_raw_spin_unlock+0x49/0xc0 [134244.037460] ? _raw_spin_unlock+0x29/0x40 [134244.038235] relocate_tree_blocks+0x37b/0x730 [btrfs] [134244.039245] relocate_block_group+0x388/0x770 [btrfs] [134244.040228] btrfs_relocate_block_group+0x161/0x2e0 [btrfs] [134244.041323] btrfs_relocate_chunk+0x36/0x110 [btrfs] [134244.041345] btrfs_balance+0xc06/0x1860 [btrfs] [134244.043382] ? btrfs_ioctl_balance+0x27c/0x310 [btrfs] [134244.045586] btrfs_ioctl_balance+0x1ed/0x310 [btrfs] [134244.045611] btrfs_ioctl+0x1880/0x3760 [btrfs] [134244.049043] ? do_raw_spin_unlock+0x49/0xc0 [134244.049838] ? _raw_spin_unlock+0x29/0x40 [134244.050587] ? __handle_mm_fault+0x11b3/0x14b0 [134244.051417] ? ksys_ioctl+0x92/0xb0 [134244.052070] ksys_ioctl+0x92/0xb0 [134244.052701] ? trace_hardirqs_off_thunk+0x1a/0x1c [134244.053511] __x64_sys_ioctl+0x16/0x20 [134244.054206] do_syscall_64+0x5c/0x280 [134244.054891] entry_SYSCALL_64_after_hwframe+0x49/0xbe [134244.055819] RIP: 0033:0x7f29b51c9dd7 [134244.056491] Code: 00 00 00 (...) [134244.059767] RSP: 002b:00007ffcccc1dd08 EFLAGS: 00000202 ORIG_RAX: 0000000000000010 [134244.061168] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00007f29b51c9dd7 [134244.062474] RDX: 00007ffcccc1dda0 RSI: 00000000c4009420 RDI: 0000000000000003 [134244.063771] RBP: 0000000000000003 R08: 00005565cea4b000 R09: 0000000000000000 [134244.065032] R10: 0000000000000541 R11: 0000000000000202 R12: 00007ffcccc2060a [134244.066327] R13: 00007ffcccc1dda0 R14: 0000000000000002 R15: 00007ffcccc1dec0 [134244.067626] irq event stamp: 0 [134244.068202] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [134244.069351] hardirqs last disabled at (0): [] copy_process+0x74f/0x2020 [134244.070909] softirqs last enabled at (0): [] copy_process+0x74f/0x2020 [134244.072392] softirqs last disabled at (0): [<0000000000000000>] 0x0 [134244.073432] ---[ end trace bd7c03622e0b0a99 ]--- The -EINVAL error comes from the following chain of function calls: __btrfs_cow_block() <-- aborts the transaction btrfs_reloc_cow_block() replace_file_extents() get_new_location() <-- returns -EINVAL When relocating a data block group, for each allocated extent of the block group, we preallocate another extent (at prealloc_file_extent_cluster()), associated with the data relocation inode, and then dirty all its pages. These preallocated extents have, and must have, the same size that extents from the data block group being relocated have. Later before we start the relocation stage that updates pointers (bytenr field of file extent items) to point to the the new extents, we trigger writeback for the data relocation inode. The expectation is that writeback will write the pages to the previously preallocated extents, that it follows the NOCOW path. That is generally the case, however, if a scrub is running it may have turned the block group that contains those extents into RO mode, in which case writeback falls back to the COW path. However in the COW path instead of allocating exactly one extent with the expected size, the allocator may end up allocating several smaller extents due to free space fragmentation - because we tell it at cow_file_range() that the minimum allocation size can match the filesystem's sector size. This later breaks the relocation's expectation that an extent associated to a file extent item in the data relocation inode has the same size as the respective extent pointed by a file extent item in another tree - in this case the extent to which the relocation inode poins to is smaller, causing relocation.c:get_new_location() to return -EINVAL. For example, if we are relocating a data block group X that has a logical address of X and the block group has an extent allocated at the logical address X + 128KiB with a size of 64KiB: 1) At prealloc_file_extent_cluster() we allocate an extent for the data relocation inode with a size of 64KiB and associate it to the file offset 128KiB (X + 128KiB - X) of the data relocation inode. This preallocated extent was allocated at block group Z; 2) A scrub running in parallel turns block group Z into RO mode and starts scrubing its extents; 3) Relocation triggers writeback for the data relocation inode; 4) When running delalloc (btrfs_run_delalloc_range()), we try first the NOCOW path because the data relocation inode has BTRFS_INODE_PREALLOC set in its flags. However, because block group Z is in RO mode, the NOCOW path (run_delalloc_nocow()) falls back into the COW path, by calling cow_file_range(); 5) At cow_file_range(), in the first iteration of the while loop we call btrfs_reserve_extent() to allocate a 64KiB extent and pass it a minimum allocation size of 4KiB (fs_info->sectorsize). Due to free space fragmentation, btrfs_reserve_extent() ends up allocating two extents of 32KiB each, each one on a different iteration of that while loop; 6) Writeback of the data relocation inode completes; 7) Relocation proceeds and ends up at relocation.c:replace_file_extents(), with a leaf which has a file extent item that points to the data extent from block group X, that has a logical address (bytenr) of X + 128KiB and a size of 64KiB. Then it calls get_new_location(), which does a lookup in the data relocation tree for a file extent item starting at offset 128KiB (X + 128KiB - X) and belonging to the data relocation inode. It finds a corresponding file extent item, however that item points to an extent that has a size of 32KiB, which doesn't match the expected size of 64KiB, resuling in -EINVAL being returned from this function and propagated up to __btrfs_cow_block(), which aborts the current transaction. To fix this make sure that at cow_file_range() when we call the allocator we pass it a minimum allocation size corresponding the desired extent size if the inode belongs to the data relocation tree, otherwise pass it the filesystem's sector size as the minimum allocation size. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/inode.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 12b5d61f23bb..62c3f4972ff6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -985,6 +985,7 @@ static noinline int cow_file_range(struct inode *inode, u64 num_bytes; unsigned long ram_size; u64 cur_alloc_size = 0; + u64 min_alloc_size; u64 blocksize = fs_info->sectorsize; struct btrfs_key ins; struct extent_map *em; @@ -1035,10 +1036,26 @@ static noinline int cow_file_range(struct inode *inode, btrfs_drop_extent_cache(BTRFS_I(inode), start, start + num_bytes - 1, 0); + /* + * Relocation relies on the relocated extents to have exactly the same + * size as the original extents. Normally writeback for relocation data + * extents follows a NOCOW path because relocation preallocates the + * extents. However, due to an operation such as scrub turning a block + * group to RO mode, it may fallback to COW mode, so we must make sure + * an extent allocated during COW has exactly the requested size and can + * not be split into smaller extents, otherwise relocation breaks and + * fails during the stage where it updates the bytenr of file extent + * items. + */ + if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID) + min_alloc_size = num_bytes; + else + min_alloc_size = fs_info->sectorsize; + while (num_bytes > 0) { cur_alloc_size = num_bytes; ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, - fs_info->sectorsize, 0, alloc_hint, + min_alloc_size, 0, alloc_hint, &ins, 1, 1); if (ret < 0) goto out_unlock; From 6bd335b469f945f75474c11e3f577f85409f39c3 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 8 Jun 2020 13:33:05 +0100 Subject: [PATCH 04/10] btrfs: fix bytes_may_use underflow when running balance and scrub in parallel When balance and scrub are running in parallel it is possible to end up with an underflow of the bytes_may_use counter of the data space_info object, which triggers a warning like the following: [134243.793196] BTRFS info (device sdc): relocating block group 1104150528 flags data [134243.806891] ------------[ cut here ]------------ [134243.807561] WARNING: CPU: 1 PID: 26884 at fs/btrfs/space-info.h:125 btrfs_add_reserved_bytes+0x1da/0x280 [btrfs] [134243.808819] Modules linked in: btrfs blake2b_generic xor (...) [134243.815779] CPU: 1 PID: 26884 Comm: kworker/u8:8 Tainted: G W 5.6.0-rc7-btrfs-next-58 #5 [134243.816944] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [134243.818389] Workqueue: writeback wb_workfn (flush-btrfs-108483) [134243.819186] RIP: 0010:btrfs_add_reserved_bytes+0x1da/0x280 [btrfs] [134243.819963] Code: 0b f2 85 (...) [134243.822271] RSP: 0018:ffffa4160aae7510 EFLAGS: 00010287 [134243.822929] RAX: 000000000000c000 RBX: ffff96159a8c1000 RCX: 0000000000000000 [134243.823816] RDX: 0000000000008000 RSI: 0000000000000000 RDI: ffff96158067a810 [134243.824742] RBP: ffff96158067a800 R08: 0000000000000001 R09: 0000000000000000 [134243.825636] R10: ffff961501432a40 R11: 0000000000000000 R12: 000000000000c000 [134243.826532] R13: 0000000000000001 R14: ffffffffffff4000 R15: ffff96158067a810 [134243.827432] FS: 0000000000000000(0000) GS:ffff9615baa00000(0000) knlGS:0000000000000000 [134243.828451] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [134243.829184] CR2: 000055bd7e414000 CR3: 00000001077be004 CR4: 00000000003606e0 [134243.830083] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [134243.830975] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [134243.831867] Call Trace: [134243.832211] find_free_extent+0x4a0/0x16c0 [btrfs] [134243.832846] btrfs_reserve_extent+0x91/0x180 [btrfs] [134243.833487] cow_file_range+0x12d/0x490 [btrfs] [134243.834080] fallback_to_cow+0x82/0x1b0 [btrfs] [134243.834689] ? release_extent_buffer+0x121/0x170 [btrfs] [134243.835370] run_delalloc_nocow+0x33f/0xa30 [btrfs] [134243.836032] btrfs_run_delalloc_range+0x1ea/0x6d0 [btrfs] [134243.836725] ? find_lock_delalloc_range+0x221/0x250 [btrfs] [134243.837450] writepage_delalloc+0xe8/0x150 [btrfs] [134243.838059] __extent_writepage+0xe8/0x4c0 [btrfs] [134243.838674] extent_write_cache_pages+0x237/0x530 [btrfs] [134243.839364] extent_writepages+0x44/0xa0 [btrfs] [134243.839946] do_writepages+0x23/0x80 [134243.840401] __writeback_single_inode+0x59/0x700 [134243.841006] writeback_sb_inodes+0x267/0x5f0 [134243.841548] __writeback_inodes_wb+0x87/0xe0 [134243.842091] wb_writeback+0x382/0x590 [134243.842574] ? wb_workfn+0x4a2/0x6c0 [134243.843030] wb_workfn+0x4a2/0x6c0 [134243.843468] process_one_work+0x26d/0x6a0 [134243.843978] worker_thread+0x4f/0x3e0 [134243.844452] ? process_one_work+0x6a0/0x6a0 [134243.844981] kthread+0x103/0x140 [134243.845400] ? kthread_create_worker_on_cpu+0x70/0x70 [134243.846030] ret_from_fork+0x3a/0x50 [134243.846494] irq event stamp: 0 [134243.846892] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [134243.847682] hardirqs last disabled at (0): [] copy_process+0x74f/0x2020 [134243.848687] softirqs last enabled at (0): [] copy_process+0x74f/0x2020 [134243.849913] softirqs last disabled at (0): [<0000000000000000>] 0x0 [134243.850698] ---[ end trace bd7c03622e0b0a96 ]--- [134243.851335] ------------[ cut here ]------------ When relocating a data block group, for each extent allocated in the block group we preallocate another extent with the same size for the data relocation inode (we do it at prealloc_file_extent_cluster()). We reserve space by calling btrfs_check_data_free_space(), which ends up incrementing the data space_info's bytes_may_use counter, and then call btrfs_prealloc_file_range() to allocate the extent, which always decrements the bytes_may_use counter by the same amount. The expectation is that writeback of the data relocation inode always follows a NOCOW path, by writing into the preallocated extents. However, when starting writeback we might end up falling back into the COW path, because the block group that contains the preallocated extent was turned into RO mode by a scrub running in parallel. The COW path then calls the extent allocator which ends up calling btrfs_add_reserved_bytes(), and this function decrements the bytes_may_use counter of the data space_info object by an amount corresponding to the size of the allocated extent, despite we haven't previously incremented it. When the counter currently has a value smaller then the allocated extent we reset the counter to 0 and emit a warning, otherwise we just decrement it and slowly mess up with this counter which is crucial for space reservation, the end result can be granting reserved space to tasks when there isn't really enough free space, and having the tasks fail later in critical places where error handling consists of a transaction abort or hitting a BUG_ON(). Fix this by making sure that if we fallback to the COW path for a data relocation inode, we increment the bytes_may_use counter of the data space_info object. The COW path will then decrement it at btrfs_add_reserved_bytes() on success or through its error handling part by a call to extent_clear_unlock_delalloc() (which ends up calling btrfs_clear_delalloc_extent() that does the decrement operation) in case of an error. Test case btrfs/061 from fstests could sporadically trigger this. CC: stable@vger.kernel.org # 4.4+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/inode.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 62c3f4972ff6..62b49d2db928 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1378,6 +1378,8 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, int *page_started, unsigned long *nr_written) { const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode)); + const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid == + BTRFS_DATA_RELOC_TREE_OBJECTID); const u64 range_bytes = end + 1 - start; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; u64 range_start = start; @@ -1408,18 +1410,23 @@ static int fallback_to_cow(struct inode *inode, struct page *locked_page, * data space info, which we incremented in the step above. * * If we need to fallback to cow and the inode corresponds to a free - * space cache inode, we must also increment bytes_may_use of the data - * space_info for the same reason. Space caches always get a prealloc + * space cache inode or an inode of the data relocation tree, we must + * also increment bytes_may_use of the data space_info for the same + * reason. Space caches and relocated data extents always get a prealloc * extent for them, however scrub or balance may have set the block - * group that contains that extent to RO mode. + * group that contains that extent to RO mode and therefore force COW + * when starting writeback. */ count = count_range_bits(io_tree, &range_start, end, range_bytes, EXTENT_NORESERVE, 0); - if (count > 0 || is_space_ino) { - const u64 bytes = is_space_ino ? range_bytes : count; + if (count > 0 || is_space_ino || is_reloc_ino) { + u64 bytes = count; struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info; struct btrfs_space_info *sinfo = fs_info->data_sinfo; + if (is_space_ino || is_reloc_ino) + bytes = range_bytes; + spin_lock(&sinfo->lock); btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes); spin_unlock(&sinfo->lock); From e7a79811d0db136dc2d336b56d54cf1b774ce972 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Jun 2020 10:38:44 +0100 Subject: [PATCH 05/10] btrfs: check if a log root exists before locking the log_mutex on unlink This brings back an optimization that commit e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans") removed, but in a different form. So it's almost equivalent to a revert. That commit removed an optimization where we avoid locking a root's log_mutex when there is no log tree created in the current transaction. The affected code path is triggered through unlink operations. That commit was based on the assumption that the optimization was not necessary because we used to have the following checks when the patch was authored: int btrfs_del_dir_entries_in_log(...) { (...) if (dir->logged_trans < trans->transid) return 0; ret = join_running_log_trans(root); (...) } int btrfs_del_inode_ref_in_log(...) { (...) if (inode->logged_trans < trans->transid) return 0; ret = join_running_log_trans(root); (...) } However before that patch was merged, another patch was merged first which replaced those checks because they were buggy. That other patch corresponds to commit 803f0f64d17769 ("Btrfs: fix fsync not persisting dentry deletions due to inode evictions"). The assumption that if the logged_trans field of an inode had a smaller value then the current transaction's generation (transid) meant that the inode was not logged in the current transaction was only correct if the inode was not evicted and reloaded in the current transaction. So the corresponding bug fix changed those checks and replaced them with the following helper function: static bool inode_logged(struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { if (inode->logged_trans == trans->transid) return true; if (inode->last_trans == trans->transid && test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) && !test_bit(BTRFS_FS_LOG_RECOVERING, &trans->fs_info->flags)) return true; return false; } So if we have a subvolume without a log tree in the current transaction (because we had no fsyncs), every time we unlink an inode we can end up trying to lock the log_mutex of the root through join_running_log_trans() twice, once for the inode being unlinked (by btrfs_del_inode_ref_in_log()) and once for the parent directory (with btrfs_del_dir_entries_in_log()). This means if we have several unlink operations happening in parallel for inodes in the same subvolume, and the those inodes and/or their parent inode were changed in the current transaction, we end up having a lot of contention on the log_mutex. The test robots from intel reported a -30.7% performance regression for a REAIM test after commit e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans"). So just bring back the optimization to join_running_log_trans() where we check first if a log root exists before trying to lock the log_mutex. This is done by checking for a bit that is set on the root when a log tree is created and removed when a log tree is freed (at transaction commit time). Commit e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans") was merged in the 5.4 merge window while commit 803f0f64d17769 ("Btrfs: fix fsync not persisting dentry deletions due to inode evictions") was merged in the 5.3 merge window. But the first commit was actually authored before the second commit (May 23 2019 vs June 19 2019). Reported-by: kernel test robot Link: https://lore.kernel.org/lkml/20200611090233.GL12456@shao2-debian/ Fixes: e678934cbe5f02 ("btrfs: Remove unnecessary check from join_running_log_trans") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 ++ fs/btrfs/tree-log.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 30ce7039bc27..d404cce8ae40 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1009,6 +1009,8 @@ enum { BTRFS_ROOT_DEAD_RELOC_TREE, /* Mark dead root stored on device whose cleanup needs to be resumed */ BTRFS_ROOT_DEAD_TREE, + /* The root has a log tree. Used only for subvolume roots. */ + BTRFS_ROOT_HAS_LOG_TREE, }; /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 920cee312f4e..cd5348f352dd 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -169,6 +169,7 @@ static int start_log_trans(struct btrfs_trans_handle *trans, if (ret) goto out; + set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state); root->log_start_pid = current->pid; } @@ -195,6 +196,9 @@ static int join_running_log_trans(struct btrfs_root *root) { int ret = -ENOENT; + if (!test_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state)) + return ret; + mutex_lock(&root->log_mutex); if (root->log_root) { ret = 0; @@ -3303,6 +3307,7 @@ int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root) if (root->log_root) { free_log_tree(trans, root->log_root); root->log_root = NULL; + clear_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state); } return 0; } From f2cb2f39ccc30fa13d3ac078d461031a63960e5b Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Jun 2020 18:46:01 +0100 Subject: [PATCH 06/10] btrfs: fix hang on snapshot creation after RWF_NOWAIT write If we do a successful RWF_NOWAIT write we end up locking the snapshot lock of the inode, through a call to check_can_nocow(), but we never unlock it. This means the next attempt to create a snapshot on the subvolume will hang forever. Trivial reproducer: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/foobar $ chattr +C /mnt/foobar $ xfs_io -d -c "pwrite -S 0xab 0 64K" /mnt/foobar $ xfs_io -d -c "pwrite -N -V 1 -S 0xfe 0 64K" /mnt/foobar $ btrfs subvolume snapshot -r /mnt /mnt/snap --> hangs Fix this by unlocking the snapshot lock if check_can_nocow() returned success. Fixes: edf064e7c6fec3 ("btrfs: nowait aio support") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/file.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 2c14312b05e8..04faa04fccd1 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1914,6 +1914,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, inode_unlock(inode); return -EAGAIN; } + /* check_can_nocow() locks the snapshot lock on success */ + btrfs_drew_write_unlock(&root->snapshot_lock); } current->backing_dev_info = inode_to_bdi(inode); From 4b1946284dd6641afdb9457101056d9e6ee6204c Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Jun 2020 18:48:58 +0100 Subject: [PATCH 07/10] btrfs: fix failure of RWF_NOWAIT write into prealloc extent beyond eof If we attempt to write to prealloc extent located after eof using a RWF_NOWAIT write, we always fail with -EAGAIN. We do actually check if we have an allocated extent for the write at the start of btrfs_file_write_iter() through a call to check_can_nocow(), but later when we go into the actual direct IO write path we simply return -EAGAIN if the write starts at or beyond EOF. Trivial to reproduce: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/foo $ chattr +C /mnt/foo $ xfs_io -d -c "pwrite -S 0xab 0 64K" /mnt/foo wrote 65536/65536 bytes at offset 0 64 KiB, 16 ops; 0.0004 sec (135.575 MiB/sec and 34707.1584 ops/sec) $ xfs_io -c "falloc -k 64K 1M" /mnt/foo $ xfs_io -d -c "pwrite -N -V 1 -S 0xfe -b 64K 64K 64K" /mnt/foo pwrite: Resource temporarily unavailable On xfs and ext4 the write succeeds, as expected. Fix this by removing the wrong check at btrfs_direct_IO(). Fixes: edf064e7c6fec3 ("btrfs: nowait aio support") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 62b49d2db928..cfa863d2d97c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7889,9 +7889,6 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.overwrite = 1; inode_unlock(inode); relock = true; - } else if (iocb->ki_flags & IOCB_NOWAIT) { - ret = -EAGAIN; - goto out; } ret = btrfs_delalloc_reserve_space(inode, &data_reserved, offset, count); From 260a63395f90f67d6ab89e4266af9e3dc34a77e9 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Jun 2020 18:49:13 +0100 Subject: [PATCH 08/10] btrfs: fix RWF_NOWAIT write not failling when we need to cow If we attempt to do a RWF_NOWAIT write against a file range for which we can only do NOCOW for a part of it, due to the existence of holes or shared extents for example, we proceed with the write as if it were possible to NOCOW the whole range. Example: $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt $ touch /mnt/sdj/bar $ chattr +C /mnt/sdj/bar $ xfs_io -d -c "pwrite -S 0xab -b 256K 0 256K" /mnt/bar wrote 262144/262144 bytes at offset 0 256 KiB, 1 ops; 0.0003 sec (694.444 MiB/sec and 2777.7778 ops/sec) $ xfs_io -c "fpunch 64K 64K" /mnt/bar $ sync $ xfs_io -d -c "pwrite -N -V 1 -b 128K -S 0xfe 0 128K" /mnt/bar wrote 131072/131072 bytes at offset 0 128 KiB, 1 ops; 0.0007 sec (160.051 MiB/sec and 1280.4097 ops/sec) This last write should fail with -EAGAIN since the file range from 64K to 128K is a hole. On xfs it fails, as expected, but on ext4 it currently succeeds because apparently it is expensive to check if there are extents allocated for the whole range, but I'll check with the ext4 people. Fix the issue by checking if check_can_nocow() returns a number of NOCOW'able bytes smaller then the requested number of bytes, and if it does return -EAGAIN. Fixes: edf064e7c6fec3 ("btrfs: nowait aio support") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/file.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 04faa04fccd1..6d5d905281c6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1904,18 +1904,29 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, pos = iocb->ki_pos; count = iov_iter_count(from); if (iocb->ki_flags & IOCB_NOWAIT) { + size_t nocow_bytes = count; + /* * We will allocate space in case nodatacow is not set, * so bail */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) { + check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes) <= 0) { inode_unlock(inode); return -EAGAIN; } /* check_can_nocow() locks the snapshot lock on success */ btrfs_drew_write_unlock(&root->snapshot_lock); + /* + * There are holes in the range or parts of the range that must + * be COWed (shared extents, RO block groups, etc), so just bail + * out. + */ + if (nocow_bytes < count) { + inode_unlock(inode); + return -EAGAIN; + } } current->backing_dev_info = inode_to_bdi(inode); From 5dbb75ed6900048e146247b6325742d92c892548 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Jun 2020 18:49:39 +0100 Subject: [PATCH 09/10] btrfs: fix RWF_NOWAIT writes blocking on extent locks and waiting for IO A RWF_NOWAIT write is not supposed to wait on filesystem locks that can be held for a long time or for ongoing IO to complete. However when calling check_can_nocow(), if the inode has prealloc extents or has the NOCOW flag set, we can block on extent (file range) locks through the call to btrfs_lock_and_flush_ordered_range(). Such lock can take a significant amount of time to be available. For example, a fiemap task may be running, and iterating through the entire file range checking all extents and doing backref walking to determine if they are shared, or a readpage operation may be in progress. Also at btrfs_lock_and_flush_ordered_range(), called by check_can_nocow(), after locking the file range we wait for any existing ordered extent that is in progress to complete. Another operation that can take a significant amount of time and defeat the purpose of RWF_NOWAIT. So fix this by trying to lock the file range and if it's currently locked return -EAGAIN to user space. If we are able to lock the file range without waiting and there is an ordered extent in the range, return -EAGAIN as well, instead of waiting for it to complete. Finally, don't bother trying to lock the snapshot lock of the root when attempting a RWF_NOWAIT write, as that is only important for buffered writes. Fixes: edf064e7c6fec3 ("btrfs: nowait aio support") Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/file.c | 39 +++++++++++++++++++++++++++------------ 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 6d5d905281c6..2520605afc25 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1533,7 +1533,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages, } static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, - size_t *write_bytes) + size_t *write_bytes, bool nowait) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; @@ -1541,27 +1541,43 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos, u64 num_bytes; int ret; - if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) + if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock)) return -EAGAIN; lockstart = round_down(pos, fs_info->sectorsize); lockend = round_up(pos + *write_bytes, fs_info->sectorsize) - 1; - - btrfs_lock_and_flush_ordered_range(inode, lockstart, - lockend, NULL); - num_bytes = lockend - lockstart + 1; + + if (nowait) { + struct btrfs_ordered_extent *ordered; + + if (!try_lock_extent(&inode->io_tree, lockstart, lockend)) + return -EAGAIN; + + ordered = btrfs_lookup_ordered_range(inode, lockstart, + num_bytes); + if (ordered) { + btrfs_put_ordered_extent(ordered); + ret = -EAGAIN; + goto out_unlock; + } + } else { + btrfs_lock_and_flush_ordered_range(inode, lockstart, + lockend, NULL); + } + ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes, NULL, NULL, NULL); if (ret <= 0) { ret = 0; - btrfs_drew_write_unlock(&root->snapshot_lock); + if (!nowait) + btrfs_drew_write_unlock(&root->snapshot_lock); } else { *write_bytes = min_t(size_t, *write_bytes , num_bytes - pos + lockstart); } - +out_unlock: unlock_extent(&inode->io_tree, lockstart, lockend); return ret; @@ -1633,7 +1649,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) && check_can_nocow(BTRFS_I(inode), pos, - &write_bytes) > 0) { + &write_bytes, false) > 0) { /* * For nodata cow case, no need to reserve * data space. @@ -1912,12 +1928,11 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb, */ if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) || - check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes) <= 0) { + check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes, + true) <= 0) { inode_unlock(inode); return -EAGAIN; } - /* check_can_nocow() locks the snapshot lock on success */ - btrfs_drew_write_unlock(&root->snapshot_lock); /* * There are holes in the range or parts of the range that must * be COWed (shared extents, RO block groups, etc), so just bail From b091f7fede97cc64f7aaad3eeb37965aebee3082 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Tue, 16 Jun 2020 11:31:59 -0400 Subject: [PATCH 10/10] btrfs: use kfree() in btrfs_ioctl_get_subvol_info() In btrfs_ioctl_get_subvol_info(), there is a classic case where kzalloc() was incorrectly paired with kzfree(). According to David Sterba, there isn't any sensitive information in the subvol_info that needs to be cleared before freeing. So kzfree() isn't really needed, use kfree() instead. Signed-off-by: Waiman Long Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 168deb8ef68a..e8f7c5f00894 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2692,7 +2692,7 @@ out: btrfs_put_root(root); out_free: btrfs_free_path(path); - kzfree(subvol_info); + kfree(subvol_info); return ret; }