From f135cea30de5f74d5bfb5116682073841fb4af8f Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Thu, 23 Apr 2020 16:30:53 +0100 Subject: btrfs: fix partial loss of prealloc extent past i_size after fsync When we have an inode with a prealloc extent that starts at an offset lower than the i_size and there is another prealloc extent that starts at an offset beyond i_size, we can end up losing part of the first prealloc extent (the part that starts at i_size) and have an implicit hole if we fsync the file and then have a power failure. Consider the following example with comments explaining how and why it happens. $ mkfs.btrfs -f /dev/sdb $ mount /dev/sdb /mnt # Create our test file with 2 consecutive prealloc extents, each with a # size of 128Kb, and covering the range from 0 to 256Kb, with a file # size of 0. $ xfs_io -f -c "falloc -k 0 128K" /mnt/foo $ xfs_io -c "falloc -k 128K 128K" /mnt/foo # Fsync the file to record both extents in the log tree. $ xfs_io -c "fsync" /mnt/foo # Now do a redudant extent allocation for the range from 0 to 64Kb. # This will merely increase the file size from 0 to 64Kb. Instead we # could also do a truncate to set the file size to 64Kb. $ xfs_io -c "falloc 0 64K" /mnt/foo # Fsync the file, so we update the inode item in the log tree with the # new file size (64Kb). This also ends up setting the number of bytes # for the first prealloc extent to 64Kb. This is done by the truncation # at btrfs_log_prealloc_extents(). # This means that if a power failure happens after this, a write into # the file range 64Kb to 128Kb will not use the prealloc extent and # will result in allocation of a new extent. $ xfs_io -c "fsync" /mnt/foo # Now set the file size to 256K with a truncate and then fsync the file. # Since no changes happened to the extents, the fsync only updates the # i_size in the inode item at the log tree. This results in an implicit # hole for the file range from 64Kb to 128Kb, something which fsck will # complain when not using the NO_HOLES feature if we replay the log # after a power failure. $ xfs_io -c "truncate 256K" -c "fsync" /mnt/foo So instead of always truncating the log to the inode's current i_size at btrfs_log_prealloc_extents(), check first if there's a prealloc extent that starts at an offset lower than the i_size and with a length that crosses the i_size - if there is one, just make sure we truncate to a size that corresponds to the end offset of that prealloc extent, so that we don't lose the part of that extent that starts at i_size if a power failure happens. A test case for fstests follows soon. Fixes: 31d11b83b96f ("Btrfs: fix duplicate extents after fsync of file with prealloc extents") CC: stable@vger.kernel.org # 4.14+ Signed-off-by: Filipe Manana Signed-off-by: David Sterba --- fs/btrfs/tree-log.c | 43 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 40 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ec36a7c6ba3d..02ebdd9edc19 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4226,6 +4226,9 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, const u64 ino = btrfs_ino(inode); struct btrfs_path *dst_path = NULL; bool dropped_extents = false; + u64 truncate_offset = i_size; + struct extent_buffer *leaf; + int slot; int ins_nr = 0; int start_slot; int ret; @@ -4240,9 +4243,43 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, if (ret < 0) goto out; + /* + * We must check if there is a prealloc extent that starts before the + * i_size and crosses the i_size boundary. This is to ensure later we + * truncate down to the end of that extent and not to the i_size, as + * otherwise we end up losing part of the prealloc extent after a log + * replay and with an implicit hole if there is another prealloc extent + * that starts at an offset beyond i_size. + */ + ret = btrfs_previous_item(root, path, ino, BTRFS_EXTENT_DATA_KEY); + if (ret < 0) + goto out; + + if (ret == 0) { + struct btrfs_file_extent_item *ei; + + leaf = path->nodes[0]; + slot = path->slots[0]; + ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); + + if (btrfs_file_extent_type(leaf, ei) == + BTRFS_FILE_EXTENT_PREALLOC) { + u64 extent_end; + + btrfs_item_key_to_cpu(leaf, &key, slot); + extent_end = key.offset + + btrfs_file_extent_num_bytes(leaf, ei); + + if (extent_end > i_size) + truncate_offset = extent_end; + } + } else { + ret = 0; + } + while (true) { - struct extent_buffer *leaf = path->nodes[0]; - int slot = path->slots[0]; + leaf = path->nodes[0]; + slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { if (ins_nr > 0) { @@ -4280,7 +4317,7 @@ static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans, ret = btrfs_truncate_inode_items(trans, root->log_root, &inode->vfs_inode, - i_size, + truncate_offset, BTRFS_EXTENT_DATA_KEY); } while (ret == -EAGAIN); if (ret) -- cgit v1.2.3 From fcc99734d1d4ced30167eb02e17f656735cb9928 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Mon, 27 Apr 2020 14:50:14 +0800 Subject: btrfs: transaction: Avoid deadlock due to bad initialization timing of fs_info::journal_info [BUG] One run of btrfs/063 triggered the following lockdep warning: ============================================ WARNING: possible recursive locking detected 5.6.0-rc7-custom+ #48 Not tainted -------------------------------------------- kworker/u24:0/7 is trying to acquire lock: ffff88817d3a46e0 (sb_internal#2){.+.+}, at: start_transaction+0x66c/0x890 [btrfs] but task is already holding lock: ffff88817d3a46e0 (sb_internal#2){.+.+}, at: start_transaction+0x66c/0x890 [btrfs] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(sb_internal#2); lock(sb_internal#2); *** DEADLOCK *** May be due to missing lock nesting notation 4 locks held by kworker/u24:0/7: #0: ffff88817b495948 ((wq_completion)btrfs-endio-write){+.+.}, at: process_one_work+0x557/0xb80 #1: ffff888189ea7db8 ((work_completion)(&work->normal_work)){+.+.}, at: process_one_work+0x557/0xb80 #2: ffff88817d3a46e0 (sb_internal#2){.+.+}, at: start_transaction+0x66c/0x890 [btrfs] #3: ffff888174ca4da8 (&fs_info->reloc_mutex){+.+.}, at: btrfs_record_root_in_trans+0x83/0xd0 [btrfs] stack backtrace: CPU: 0 PID: 7 Comm: kworker/u24:0 Not tainted 5.6.0-rc7-custom+ #48 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 Workqueue: btrfs-endio-write btrfs_work_helper [btrfs] Call Trace: dump_stack+0xc2/0x11a __lock_acquire.cold+0xce/0x214 lock_acquire+0xe6/0x210 __sb_start_write+0x14e/0x290 start_transaction+0x66c/0x890 [btrfs] btrfs_join_transaction+0x1d/0x20 [btrfs] find_free_extent+0x1504/0x1a50 [btrfs] btrfs_reserve_extent+0xd5/0x1f0 [btrfs] btrfs_alloc_tree_block+0x1ac/0x570 [btrfs] btrfs_copy_root+0x213/0x580 [btrfs] create_reloc_root+0x3bd/0x470 [btrfs] btrfs_init_reloc_root+0x2d2/0x310 [btrfs] record_root_in_trans+0x191/0x1d0 [btrfs] btrfs_record_root_in_trans+0x90/0xd0 [btrfs] start_transaction+0x16e/0x890 [btrfs] btrfs_join_transaction+0x1d/0x20 [btrfs] btrfs_finish_ordered_io+0x55d/0xcd0 [btrfs] finish_ordered_fn+0x15/0x20 [btrfs] btrfs_work_helper+0x116/0x9a0 [btrfs] process_one_work+0x632/0xb80 worker_thread+0x80/0x690 kthread+0x1a3/0x1f0 ret_from_fork+0x27/0x50 It's pretty hard to reproduce, only one hit so far. [CAUSE] This is because we're calling btrfs_join_transaction() without re-using the current running one: btrfs_finish_ordered_io() |- btrfs_join_transaction() <<< Call #1 |- btrfs_record_root_in_trans() |- btrfs_reserve_extent() |- btrfs_join_transaction() <<< Call #2 Normally such btrfs_join_transaction() call should re-use the existing one, without trying to re-start a transaction. But the problem is, in btrfs_join_transaction() call #1, we call btrfs_record_root_in_trans() before initializing current::journal_info. And in btrfs_join_transaction() call #2, we're relying on current::journal_info to avoid such deadlock. [FIX] Call btrfs_record_root_in_trans() after we have initialized current::journal_info. CC: stable@vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/transaction.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 8cede6eb9843..2d5498136e5e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -662,10 +662,19 @@ again: } got_it: - btrfs_record_root_in_trans(h, root); - if (!current->journal_info) current->journal_info = h; + + /* + * btrfs_record_root_in_trans() needs to alloc new extents, and may + * call btrfs_join_transaction() while we're also starting a + * transaction. + * + * Thus it need to be called after current->journal_info initialized, + * or we can deadlock. + */ + btrfs_record_root_in_trans(h, root); + return h; join_fail: -- cgit v1.2.3 From 9c6c723f48f5f05eab133b4fee8f2a2b7ec57a15 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 29 Apr 2020 15:27:32 +0200 Subject: btrfs: fix gcc-4.8 build warning for struct initializer Some older compilers like gcc-4.8 warn about mismatched curly braces in a initializer: fs/btrfs/backref.c: In function 'is_shared_data_backref': fs/btrfs/backref.c:394:9: error: missing braces around initializer [-Werror=missing-braces] struct prelim_ref target = {0}; ^ fs/btrfs/backref.c:394:9: error: (near initialization for 'target.rbnode') [-Werror=missing-braces] Use the GNU empty initializer extension to avoid this. Fixes: ed58f2e66e84 ("btrfs: backref, don't add refs from shared block when resolving normal backref") Reviewed-by: Qu Wenruo Signed-off-by: Arnd Bergmann Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/backref.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 9c380e7edf62..0cc02577577b 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -391,7 +391,7 @@ static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr) struct rb_node **p = &preftrees->direct.root.rb_root.rb_node; struct rb_node *parent = NULL; struct prelim_ref *ref = NULL; - struct prelim_ref target = {0}; + struct prelim_ref target = {}; int result; target.parent = bytenr; -- cgit v1.2.3