From c334730988ee07908ba4eb816ce78d3fe06fecaa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Wed, 4 Nov 2020 11:07:31 +0000 Subject: btrfs: fix missing delalloc new bit for new delalloc ranges When doing a buffered write, through one of the write family syscalls, we look for ranges which currently don't have allocated extents and set the 'delalloc new' bit on them, so that we can report a correct number of used blocks to the stat(2) syscall until delalloc is flushed and ordered extents complete. However there are a few other places where we can do a buffered write against a range that is mapped to a hole (no extent allocated) and where we do not set the 'new delalloc' bit. Those places are: - Doing a memory mapped write against a hole; - Cloning an inline extent into a hole starting at file offset 0; - Calling btrfs_cont_expand() when the i_size of the file is not aligned to the sector size and is located in a hole. For example when cloning to a destination offset beyond EOF. So after such cases, until the corresponding delalloc range is flushed and the respective ordered extents complete, we can report an incorrect number of blocks used through the stat(2) syscall. In some cases we can end up reporting 0 used blocks to stat(2), which is a particular bad value to report as it may mislead tools to think a file is completely sparse when its i_size is not zero, making them skip reading any data, an undesired consequence for tools such as archivers and other backup tools, as reported a long time ago in the following thread (and other past threads): https://lists.gnu.org/archive/html/bug-tar/2016-07/msg00001.html Example reproducer: $ cat reproducer.sh #!/bin/bash MNT=/mnt/sdi DEV=/dev/sdi mkfs.btrfs -f $DEV > /dev/null # mkfs.xfs -f $DEV > /dev/null # mkfs.ext4 -F $DEV > /dev/null # mkfs.f2fs -f $DEV > /dev/null mount $DEV $MNT xfs_io -f -c "truncate 64K" \ -c "mmap -w 0 64K" \ -c "mwrite -S 0xab 0 64K" \ -c "munmap" \ $MNT/foo blocks_used=$(stat -c %b $MNT/foo) echo "blocks used: $blocks_used" if [ $blocks_used -eq 0 ]; then echo "ERROR: blocks used is 0" fi umount $DEV $ ./reproducer.sh blocks used: 0 ERROR: blocks used is 0 So move the logic that decides to set the 'delalloc bit' bit into the function btrfs_set_extent_delalloc(), since that is what we use for all those missing cases as well as for the cases that currently work well. This change is also preparatory work for an upcoming patch that fixes other problems related to tracking and reporting the number of bytes used by an inode. CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/file.c | 57 ------------------------------------------- fs/btrfs/inode.c | 58 ++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/tests/inode-tests.c | 12 ++++++--- 3 files changed, 66 insertions(+), 61 deletions(-) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 87355a38a654..4373da7bcc0d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -452,46 +452,6 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of @@ -528,23 +488,6 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(inode)) { - if (start_pos >= isize && - !(inode->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(inode, start_pos, - num_bytes, cached); - if (err) - return err; - } - } - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da58c58ef9aa..7e8d8169779d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2253,11 +2253,69 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, + NULL, cached_state, GFP_NOFS); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); + + if (start >= i_size_read(&inode->vfs_inode) && + !(inode->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case so just + * set the delalloc new bit for the range directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + int ret; + + ret = btrfs_find_new_delalloc_bytes(inode, start, + end + 1 - start, + cached_state); + if (ret) + return ret; + } + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, cached_state); } diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index e6719f7db386..04022069761d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -983,7 +983,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1050,7 +1051,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1082,7 +1084,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1097,7 +1100,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); iput(inode); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); -- cgit 1.4.1 From 6f23277a49e68f8a9355385c846939ad0b1261e7 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Wed, 11 Nov 2020 19:38:18 +0800 Subject: btrfs: qgroup: don't commit transaction when we already hold the handle [BUG] When running the following script, btrfs will trigger an ASSERT(): #/bin/bash mkfs.btrfs -f $dev mount $dev $mnt xfs_io -f -c "pwrite 0 1G" $mnt/file sync btrfs quota enable $mnt btrfs quota rescan -w $mnt # Manually set the limit below current usage btrfs qgroup limit 512M $mnt $mnt # Crash happens touch $mnt/file The dmesg looks like this: assertion failed: refcount_read(&trans->use_count) == 1, in fs/btrfs/transaction.c:2022 ------------[ cut here ]------------ kernel BUG at fs/btrfs/ctree.h:3230! invalid opcode: 0000 [#1] SMP PTI RIP: 0010:assertfail.constprop.0+0x18/0x1a [btrfs] btrfs_commit_transaction.cold+0x11/0x5d [btrfs] try_flush_qgroup+0x67/0x100 [btrfs] __btrfs_qgroup_reserve_meta+0x3a/0x60 [btrfs] btrfs_delayed_update_inode+0xaa/0x350 [btrfs] btrfs_update_inode+0x9d/0x110 [btrfs] btrfs_dirty_inode+0x5d/0xd0 [btrfs] touch_atime+0xb5/0x100 iterate_dir+0xf1/0x1b0 __x64_sys_getdents64+0x78/0x110 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fb5afe588db [CAUSE] In try_flush_qgroup(), we assume we don't hold a transaction handle at all. This is true for data reservation and mostly true for metadata. Since data space reservation always happens before we start a transaction, and for most metadata operation we reserve space in start_transaction(). But there is an exception, btrfs_delayed_inode_reserve_metadata(). It holds a transaction handle, while still trying to reserve extra metadata space. When we hit EDQUOT inside btrfs_delayed_inode_reserve_metadata(), we will join current transaction and commit, while we still have transaction handle from qgroup code. [FIX] Let's check current->journal before we join the transaction. If current->journal is unset or BTRFS_SEND_TRANS_STUB, it means we are not holding a transaction, thus are able to join and then commit transaction. If current->journal is a valid transaction handle, we avoid committing transaction and just end it This is less effective than committing current transaction, as it won't free metadata reserved space, but we may still free some data space before new data writes. Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1178634 Fixes: c53e9653605d ("btrfs: qgroup: try to flush qgroup space when we get -EDQUOT") Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 77c54749f432..4621b8043021 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3512,6 +3512,7 @@ static int try_flush_qgroup(struct btrfs_root *root) { struct btrfs_trans_handle *trans; int ret; + bool can_commit = true; /* * We don't want to run flush again and again, so if there is a running @@ -3523,6 +3524,20 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } + /* + * If current process holds a transaction, we shouldn't flush, as we + * assume all space reservation happens before a transaction handle is + * held. + * + * But there are cases like btrfs_delayed_item_reserve_metadata() where + * we try to reserve space with one transction handle already held. + * In that case we can't commit transaction, but at least try to end it + * and hope the started data writes can free some space. + */ + if (current->journal_info && + current->journal_info != BTRFS_SEND_TRANS_STUB) + can_commit = false; + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; @@ -3534,7 +3549,10 @@ static int try_flush_qgroup(struct btrfs_root *root) goto out; } - ret = btrfs_commit_transaction(trans); + if (can_commit) + ret = btrfs_commit_transaction(trans); + else + ret = btrfs_end_transaction(trans); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); -- cgit 1.4.1 From 1a49a97df657c63a4e8ffcd1ea9b6ed95581789b Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Thu, 12 Nov 2020 17:55:06 -0800 Subject: btrfs: tree-checker: add missing return after error in root_item There's a missing return statement after an error is found in the root_item, this can cause further problems when a crafted image triggers the error. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=210181 Fixes: 259ee7754b67 ("btrfs: tree-checker: Add ROOT_ITEM check") CC: stable@vger.kernel.org # 5.4+ Reviewed-by: Qu Wenruo Signed-off-by: Daniel Xu Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 8784b74f5232..6cefabd27209 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1068,6 +1068,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, "invalid root item size, have %u expect %zu or %u", btrfs_item_size_nr(leaf, slot), sizeof(ri), btrfs_legacy_root_item_size()); + return -EUCLEAN; } /* -- cgit 1.4.1 From 0697d9a610998b8bdee6b2390836cb2391d8fd1a Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 18 Nov 2020 18:03:26 +0900 Subject: btrfs: don't access possibly stale fs_info data for printing duplicate device Syzbot reported a possible use-after-free when printing a duplicate device warning device_list_add(). At this point it can happen that a btrfs_device::fs_info is not correctly setup yet, so we're accessing stale data, when printing the warning message using the btrfs_printk() wrappers. ================================================================== BUG: KASAN: use-after-free in btrfs_printk+0x3eb/0x435 fs/btrfs/super.c:245 Read of size 8 at addr ffff8880878e06a8 by task syz-executor225/7068 CPU: 1 PID: 7068 Comm: syz-executor225 Not tainted 5.9.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1d6/0x29e lib/dump_stack.c:118 print_address_description+0x66/0x620 mm/kasan/report.c:383 __kasan_report mm/kasan/report.c:513 [inline] kasan_report+0x132/0x1d0 mm/kasan/report.c:530 btrfs_printk+0x3eb/0x435 fs/btrfs/super.c:245 device_list_add+0x1a88/0x1d60 fs/btrfs/volumes.c:943 btrfs_scan_one_device+0x196/0x490 fs/btrfs/volumes.c:1359 btrfs_mount_root+0x48f/0xb60 fs/btrfs/super.c:1634 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x44840a RSP: 002b:00007ffedfffd608 EFLAGS: 00000293 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 00007ffedfffd670 RCX: 000000000044840a RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffedfffd630 RBP: 00007ffedfffd630 R08: 00007ffedfffd670 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000293 R12: 000000000000001a R13: 0000000000000004 R14: 0000000000000003 R15: 0000000000000003 Allocated by task 6945: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc+0x100/0x130 mm/kasan/common.c:461 kmalloc_node include/linux/slab.h:577 [inline] kvmalloc_node+0x81/0x110 mm/util.c:574 kvmalloc include/linux/mm.h:757 [inline] kvzalloc include/linux/mm.h:765 [inline] btrfs_mount_root+0xd0/0xb60 fs/btrfs/super.c:1613 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Freed by task 6945: kasan_save_stack mm/kasan/common.c:48 [inline] kasan_set_track+0x3d/0x70 mm/kasan/common.c:56 kasan_set_free_info+0x17/0x30 mm/kasan/generic.c:355 __kasan_slab_free+0xdd/0x110 mm/kasan/common.c:422 __cache_free mm/slab.c:3418 [inline] kfree+0x113/0x200 mm/slab.c:3756 deactivate_locked_super+0xa7/0xf0 fs/super.c:335 btrfs_mount_root+0x72b/0xb60 fs/btrfs/super.c:1678 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 fc_mount fs/namespace.c:978 [inline] vfs_kern_mount+0xc9/0x160 fs/namespace.c:1008 btrfs_mount+0x33c/0xae0 fs/btrfs/super.c:1732 legacy_get_tree+0xea/0x180 fs/fs_context.c:592 vfs_get_tree+0x88/0x270 fs/super.c:1547 do_new_mount fs/namespace.c:2875 [inline] path_mount+0x179d/0x29e0 fs/namespace.c:3192 do_mount fs/namespace.c:3205 [inline] __do_sys_mount fs/namespace.c:3413 [inline] __se_sys_mount+0x126/0x180 fs/namespace.c:3390 do_syscall_64+0x31/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The buggy address belongs to the object at ffff8880878e0000 which belongs to the cache kmalloc-16k of size 16384 The buggy address is located 1704 bytes inside of 16384-byte region [ffff8880878e0000, ffff8880878e4000) The buggy address belongs to the page: page:0000000060704f30 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x878e0 head:0000000060704f30 order:3 compound_mapcount:0 compound_pincount:0 flags: 0xfffe0000010200(slab|head) raw: 00fffe0000010200 ffffea00028e9a08 ffffea00021e3608 ffff8880aa440b00 raw: 0000000000000000 ffff8880878e0000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880878e0580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880878e0600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880878e0680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880878e0700: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880878e0780: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== The syzkaller reproducer for this use-after-free crafts a filesystem image and loop mounts it twice in a loop. The mount will fail as the crafted image has an invalid chunk tree. When this happens btrfs_mount_root() will call deactivate_locked_super(), which then cleans up fs_info and fs_info::sb. If a second thread now adds the same block-device to the filesystem, it will get detected as a duplicate device and device_list_add() will reject the duplicate and print a warning. But as the fs_info pointer passed in is non-NULL this will result in a use-after-free. Instead of printing possibly uninitialized or already freed memory in btrfs_printk(), explicitly pass in a NULL fs_info so the printing of the device name will be skipped altogether. There was a slightly different approach discussed in https://lore.kernel.org/linux-btrfs/20200114060920.4527-1-anand.jain@oracle.com/t/#u Link: https://lore.kernel.org/linux-btrfs/000000000000c9e14b05afcc41ba@google.com Reported-by: syzbot+582e66e5edf36a22c7b0@syzkaller.appspotmail.com CC: stable@vger.kernel.org # 4.19+ Reviewed-by: Nikolay Borisov Reviewed-by: Anand Jain Signed-off-by: Johannes Thumshirn Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/volumes.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a6406b3b8c2b..78637665166e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -940,7 +940,13 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (device->bdev != path_bdev) { bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", path, devid, found_transid, current->comm, -- cgit 1.4.1 From 6d06b0ad94d3dd7e3503d8ad39c39c4634884611 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 16 Nov 2020 19:53:52 +0100 Subject: btrfs: tree-checker: add missing returns after data_ref alignment checks There are sectorsize alignment checks that are reported but then check_extent_data_ref continues. This was not intended, wrong alignment is not a minor problem and we should return with error. CC: stable@vger.kernel.org # 5.4+ Fixes: 0785a9aacf9d ("btrfs: tree-checker: Add EXTENT_DATA_REF check") Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/tree-checker.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 6cefabd27209..ea2bb4cb5890 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1424,6 +1424,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, "invalid item size, have %u expect aligned to %zu for key type %u", btrfs_item_size_nr(leaf, slot), sizeof(*dref), key->type); + return -EUCLEAN; } if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { generic_err(leaf, slot, @@ -1452,6 +1453,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", offset, leaf->fs_info->sectorsize); + return -EUCLEAN; } } return 0; -- cgit 1.4.1 From 3d05cad3c357a2b749912914356072b38435edfa Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 14:28:44 +0000 Subject: btrfs: fix lockdep splat when reading qgroup config on mount Lockdep reported the following splat when running test btrfs/190 from fstests: [ 9482.126098] ====================================================== [ 9482.126184] WARNING: possible circular locking dependency detected [ 9482.126281] 5.10.0-rc4-btrfs-next-73 #1 Not tainted [ 9482.126365] ------------------------------------------------------ [ 9482.126456] mount/24187 is trying to acquire lock: [ 9482.126534] ffffa0c869a7dac0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}, at: qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.126647] but task is already holding lock: [ 9482.126777] ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.126886] which lock already depends on the new lock. [ 9482.127078] the existing dependency chain (in reverse order) is: [ 9482.127213] -> #1 (btrfs-quota-00){++++}-{3:3}: [ 9482.127366] lock_acquire+0xd8/0x490 [ 9482.127436] down_read_nested+0x45/0x220 [ 9482.127528] __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.127613] btrfs_read_lock_root_node+0x41/0x130 [btrfs] [ 9482.127702] btrfs_search_slot+0x514/0xc30 [btrfs] [ 9482.127788] update_qgroup_status_item+0x72/0x140 [btrfs] [ 9482.127877] btrfs_qgroup_rescan_worker+0xde/0x680 [btrfs] [ 9482.127964] btrfs_work_helper+0xf1/0x600 [btrfs] [ 9482.128039] process_one_work+0x24e/0x5e0 [ 9482.128110] worker_thread+0x50/0x3b0 [ 9482.128181] kthread+0x153/0x170 [ 9482.128256] ret_from_fork+0x22/0x30 [ 9482.128327] -> #0 (&fs_info->qgroup_rescan_lock){+.+.}-{3:3}: [ 9482.128464] check_prev_add+0x91/0xc60 [ 9482.128551] __lock_acquire+0x1740/0x3110 [ 9482.128623] lock_acquire+0xd8/0x490 [ 9482.130029] __mutex_lock+0xa3/0xb30 [ 9482.130590] qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.131577] btrfs_read_qgroup_config+0x43a/0x550 [btrfs] [ 9482.132175] open_ctree+0x1228/0x18a0 [btrfs] [ 9482.132756] btrfs_mount_root.cold+0x13/0xed [btrfs] [ 9482.133325] legacy_get_tree+0x30/0x60 [ 9482.133866] vfs_get_tree+0x28/0xe0 [ 9482.134392] fc_mount+0xe/0x40 [ 9482.134908] vfs_kern_mount.part.0+0x71/0x90 [ 9482.135428] btrfs_mount+0x13b/0x3e0 [btrfs] [ 9482.135942] legacy_get_tree+0x30/0x60 [ 9482.136444] vfs_get_tree+0x28/0xe0 [ 9482.136949] path_mount+0x2d7/0xa70 [ 9482.137438] do_mount+0x75/0x90 [ 9482.137923] __x64_sys_mount+0x8e/0xd0 [ 9482.138400] do_syscall_64+0x33/0x80 [ 9482.138873] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 9482.139346] other info that might help us debug this: [ 9482.140735] Possible unsafe locking scenario: [ 9482.141594] CPU0 CPU1 [ 9482.142011] ---- ---- [ 9482.142411] lock(btrfs-quota-00); [ 9482.142806] lock(&fs_info->qgroup_rescan_lock); [ 9482.143216] lock(btrfs-quota-00); [ 9482.143629] lock(&fs_info->qgroup_rescan_lock); [ 9482.144056] *** DEADLOCK *** [ 9482.145242] 2 locks held by mount/24187: [ 9482.145637] #0: ffffa0c8411c40e8 (&type->s_umount_key#44/1){+.+.}-{3:3}, at: alloc_super+0xb9/0x400 [ 9482.146061] #1: ffffa0c892ebd3a0 (btrfs-quota-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.146509] stack backtrace: [ 9482.147350] CPU: 1 PID: 24187 Comm: mount Not tainted 5.10.0-rc4-btrfs-next-73 #1 [ 9482.147788] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 9482.148709] Call Trace: [ 9482.149169] dump_stack+0x8d/0xb5 [ 9482.149628] check_noncircular+0xff/0x110 [ 9482.150090] check_prev_add+0x91/0xc60 [ 9482.150561] ? kvm_clock_read+0x14/0x30 [ 9482.151017] ? kvm_sched_clock_read+0x5/0x10 [ 9482.151470] __lock_acquire+0x1740/0x3110 [ 9482.151941] ? __btrfs_tree_read_lock+0x27/0x120 [btrfs] [ 9482.152402] lock_acquire+0xd8/0x490 [ 9482.152887] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.153354] __mutex_lock+0xa3/0xb30 [ 9482.153826] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.154301] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.154768] ? qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.155226] qgroup_rescan_init+0x43/0xf0 [btrfs] [ 9482.155690] btrfs_read_qgroup_config+0x43a/0x550 [btrfs] [ 9482.156160] open_ctree+0x1228/0x18a0 [btrfs] [ 9482.156643] btrfs_mount_root.cold+0x13/0xed [btrfs] [ 9482.157108] ? rcu_read_lock_sched_held+0x5d/0x90 [ 9482.157567] ? kfree+0x31f/0x3e0 [ 9482.158030] legacy_get_tree+0x30/0x60 [ 9482.158489] vfs_get_tree+0x28/0xe0 [ 9482.158947] fc_mount+0xe/0x40 [ 9482.159403] vfs_kern_mount.part.0+0x71/0x90 [ 9482.159875] btrfs_mount+0x13b/0x3e0 [btrfs] [ 9482.160335] ? rcu_read_lock_sched_held+0x5d/0x90 [ 9482.160805] ? kfree+0x31f/0x3e0 [ 9482.161260] ? legacy_get_tree+0x30/0x60 [ 9482.161714] legacy_get_tree+0x30/0x60 [ 9482.162166] vfs_get_tree+0x28/0xe0 [ 9482.162616] path_mount+0x2d7/0xa70 [ 9482.163070] do_mount+0x75/0x90 [ 9482.163525] __x64_sys_mount+0x8e/0xd0 [ 9482.163986] do_syscall_64+0x33/0x80 [ 9482.164437] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 9482.164902] RIP: 0033:0x7f51e907caaa This happens because at btrfs_read_qgroup_config() we can call qgroup_rescan_init() while holding a read lock on a quota btree leaf, acquired by the previous call to btrfs_search_slot_for_read(), and qgroup_rescan_init() acquires the mutex qgroup_rescan_lock. A qgroup rescan worker does the opposite: it acquires the mutex qgroup_rescan_lock, at btrfs_qgroup_rescan_worker(), and then tries to update the qgroup status item in the quota btree through the call to update_qgroup_status_item(). This inversion of locking order between the qgroup_rescan_lock mutex and quota btree locks causes the splat. Fix this simply by releasing and freeing the path before calling qgroup_rescan_init() at btrfs_read_qgroup_config(). CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4621b8043021..a3f0d209fce5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -497,13 +497,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); -- cgit 1.4.1 From 7aa6d359845a9dbf7ad90b0b1b6347ef4764621f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 18:30:54 +0000 Subject: btrfs: do nofs allocations when adding and removing qgroup relations When adding or removing a qgroup relation we are doing a GFP_KERNEL allocation which is not safe because we are holding a transaction handle open and that can make us deadlock if the allocator needs to recurse into the filesystem. So just surround those calls with a nofs context. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a3f0d209fce5..d690ef702522 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,6 +11,7 @@ #include #include #include +#include #include "ctree.h" #include "transaction.h" @@ -1324,13 +1325,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; struct ulist *tmp; + unsigned int nofs_flag; int ret = 0; /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1387,10 +1392,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup_list *list; struct ulist *tmp; bool found = false; + unsigned int nofs_flag; int ret = 0; int ret2; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; -- cgit 1.4.1 From a855fbe69229078cd8aecd8974fb996a5ca651e6 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 23 Nov 2020 18:31:02 +0000 Subject: btrfs: fix lockdep splat when enabling and disabling qgroups When running test case btrfs/017 from fstests, lockdep reported the following splat: [ 1297.067385] ====================================================== [ 1297.067708] WARNING: possible circular locking dependency detected [ 1297.068022] 5.10.0-rc4-btrfs-next-73 #1 Not tainted [ 1297.068322] ------------------------------------------------------ [ 1297.068629] btrfs/189080 is trying to acquire lock: [ 1297.068929] ffff9f2725731690 (sb_internal#2){.+.+}-{0:0}, at: btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.069274] but task is already holding lock: [ 1297.069868] ffff9f2702b61a08 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}, at: btrfs_quota_enable+0x3b/0xa70 [btrfs] [ 1297.070219] which lock already depends on the new lock. [ 1297.071131] the existing dependency chain (in reverse order) is: [ 1297.071721] -> #1 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}: [ 1297.072375] lock_acquire+0xd8/0x490 [ 1297.072710] __mutex_lock+0xa3/0xb30 [ 1297.073061] btrfs_qgroup_inherit+0x59/0x6a0 [btrfs] [ 1297.073421] create_subvol+0x194/0x990 [btrfs] [ 1297.073780] btrfs_mksubvol+0x3fb/0x4a0 [btrfs] [ 1297.074133] __btrfs_ioctl_snap_create+0x119/0x1a0 [btrfs] [ 1297.074498] btrfs_ioctl_snap_create+0x58/0x80 [btrfs] [ 1297.074872] btrfs_ioctl+0x1a90/0x36f0 [btrfs] [ 1297.075245] __x64_sys_ioctl+0x83/0xb0 [ 1297.075617] do_syscall_64+0x33/0x80 [ 1297.075993] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.076380] -> #0 (sb_internal#2){.+.+}-{0:0}: [ 1297.077166] check_prev_add+0x91/0xc60 [ 1297.077572] __lock_acquire+0x1740/0x3110 [ 1297.077984] lock_acquire+0xd8/0x490 [ 1297.078411] start_transaction+0x3c5/0x760 [btrfs] [ 1297.078853] btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.079323] btrfs_ioctl+0x2c60/0x36f0 [btrfs] [ 1297.079789] __x64_sys_ioctl+0x83/0xb0 [ 1297.080232] do_syscall_64+0x33/0x80 [ 1297.080680] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.081139] other info that might help us debug this: [ 1297.082536] Possible unsafe locking scenario: [ 1297.083510] CPU0 CPU1 [ 1297.084005] ---- ---- [ 1297.084500] lock(&fs_info->qgroup_ioctl_lock); [ 1297.084994] lock(sb_internal#2); [ 1297.085485] lock(&fs_info->qgroup_ioctl_lock); [ 1297.085974] lock(sb_internal#2); [ 1297.086454] *** DEADLOCK *** [ 1297.087880] 3 locks held by btrfs/189080: [ 1297.088324] #0: ffff9f2725731470 (sb_writers#14){.+.+}-{0:0}, at: btrfs_ioctl+0xa73/0x36f0 [btrfs] [ 1297.088799] #1: ffff9f2702b60cc0 (&fs_info->subvol_sem){++++}-{3:3}, at: btrfs_ioctl+0x1f4d/0x36f0 [btrfs] [ 1297.089284] #2: ffff9f2702b61a08 (&fs_info->qgroup_ioctl_lock){+.+.}-{3:3}, at: btrfs_quota_enable+0x3b/0xa70 [btrfs] [ 1297.089771] stack backtrace: [ 1297.090662] CPU: 5 PID: 189080 Comm: btrfs Not tainted 5.10.0-rc4-btrfs-next-73 #1 [ 1297.091132] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 [ 1297.092123] Call Trace: [ 1297.092629] dump_stack+0x8d/0xb5 [ 1297.093115] check_noncircular+0xff/0x110 [ 1297.093596] check_prev_add+0x91/0xc60 [ 1297.094076] ? kvm_clock_read+0x14/0x30 [ 1297.094553] ? kvm_sched_clock_read+0x5/0x10 [ 1297.095029] __lock_acquire+0x1740/0x3110 [ 1297.095510] lock_acquire+0xd8/0x490 [ 1297.095993] ? btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.096476] start_transaction+0x3c5/0x760 [btrfs] [ 1297.096962] ? btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.097451] btrfs_quota_enable+0xaf/0xa70 [btrfs] [ 1297.097941] ? btrfs_ioctl+0x1f4d/0x36f0 [btrfs] [ 1297.098429] btrfs_ioctl+0x2c60/0x36f0 [btrfs] [ 1297.098904] ? do_user_addr_fault+0x20c/0x430 [ 1297.099382] ? kvm_clock_read+0x14/0x30 [ 1297.099854] ? kvm_sched_clock_read+0x5/0x10 [ 1297.100328] ? sched_clock+0x5/0x10 [ 1297.100801] ? sched_clock_cpu+0x12/0x180 [ 1297.101272] ? __x64_sys_ioctl+0x83/0xb0 [ 1297.101739] __x64_sys_ioctl+0x83/0xb0 [ 1297.102207] do_syscall_64+0x33/0x80 [ 1297.102673] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 1297.103148] RIP: 0033:0x7f773ff65d87 This is because during the quota enable ioctl we lock first the mutex qgroup_ioctl_lock and then start a transaction, and starting a transaction acquires a fs freeze semaphore (at the VFS level). However, every other code path, except for the quota disable ioctl path, we do the opposite: we start a transaction and then lock the mutex. So fix this by making the quota enable and disable paths to start the transaction without having the mutex locked, and then, after starting the transaction, lock the mutex and check if some other task already enabled or disabled the quotas, bailing with success if that was the case. Signed-off-by: Filipe Manana Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 5 ++++- fs/btrfs/qgroup.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 53 insertions(+), 9 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0378933d163c..0b29bdb25105 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -878,7 +878,10 @@ struct btrfs_fs_info { */ struct ulist *qgroup_ulist; - /* protect user change for quota operations */ + /* + * Protect user change for quota operations. If a transaction is needed, + * it must be started before locking this lock. + */ struct mutex qgroup_ioctl_lock; /* list of dirty qgroups to be written at next commit */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d690ef702522..87bd37b70738 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -937,6 +937,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_trans_handle *trans = NULL; + struct ulist *ulist = NULL; int ret = 0; int slot; @@ -944,8 +945,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) if (fs_info->quota_root) goto out; - fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); - if (!fs_info->qgroup_ulist) { + ulist = ulist_alloc(GFP_KERNEL); + if (!ulist) { ret = -ENOMEM; goto out; } @@ -953,6 +954,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; + + /* + * Unlock qgroup_ioctl_lock before starting the transaction. This is to + * avoid lock acquisition inversion problems (reported by lockdep) between + * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we + * start a transaction. + * After we started the transaction lock qgroup_ioctl_lock again and + * check if someone else created the quota root in the meanwhile. If so, + * just return success and release the transaction handle. + * + * Also we don't need to worry about someone else calling + * btrfs_sysfs_add_qgroups() after we unlock and getting an error because + * that function returns 0 (success) when the sysfs entries already exist. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -962,12 +979,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } + if (fs_info->quota_root) + goto out; + + fs_info->qgroup_ulist = ulist; + ulist = NULL; + /* * initially create the quota tree */ @@ -1125,11 +1150,14 @@ out: if (ret) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; - if (trans) - btrfs_end_transaction(trans); btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + ulist_free(ulist); return ret; } @@ -1142,19 +1170,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. + * + * Also, we must always start a transaction without holding the mutex + * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; goto out; } + if (!fs_info->quota_root) + goto out; + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); @@ -1168,13 +1206,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } list_del("a_root->dirty_list); @@ -1186,10 +1224,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_put_root(quota_root); -end_trans: - ret = btrfs_end_transaction(trans); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + return ret; } -- cgit 1.4.1