From 31890da0bfdd24b135a258404b93c58a65510c7a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 21 Nov 2018 14:05:41 -0500 Subject: btrfs: handle delayed ref head accounting cleanup in abort We weren't doing any of the accounting cleanup when we aborted transactions. Fix this by making cleanup_ref_head_accounting global and calling it from the abort code, this fixes the issue where our accounting was all wrong after the fs aborts. The test generic/475 on a 2G VM can trigger the problems eg.: [ 8502.136957] WARNING: CPU: 0 PID: 11064 at fs/btrfs/extent-tree.c:5986 btrfs_free_block_grou +ps+0x3dc/0x410 [btrfs] [ 8502.148372] CPU: 0 PID: 11064 Comm: umount Not tainted 5.0.0-rc1-default+ #394 [ 8502.150807] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626 +cc-prebuilt.qemu-project.org 04/01/2014 [ 8502.154317] RIP: 0010:btrfs_free_block_groups+0x3dc/0x410 [btrfs] [ 8502.160623] RSP: 0018:ffffb1ab84b93de8 EFLAGS: 00010206 [ 8502.161906] RAX: 0000000001000000 RBX: ffff9f34b1756400 RCX: 0000000000000000 [ 8502.163448] RDX: 0000000000000002 RSI: 0000000000000001 RDI: ffff9f34b1755400 [ 8502.164906] RBP: ffff9f34b7e8c000 R08: 0000000000000001 R09: 0000000000000000 [ 8502.166716] R10: 0000000000000000 R11: 0000000000000001 R12: ffff9f34b7e8c108 [ 8502.168498] R13: ffff9f34b7e8c158 R14: 0000000000000000 R15: dead000000000100 [ 8502.170296] FS: 00007fb1cf15ffc0(0000) GS:ffff9f34bd400000(0000) knlGS:0000000000000000 [ 8502.172439] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 8502.173669] CR2: 00007fb1ced507b0 CR3: 000000002f7a6000 CR4: 00000000000006f0 [ 8502.175094] Call Trace: [ 8502.175759] close_ctree+0x17f/0x350 [btrfs] [ 8502.176721] generic_shutdown_super+0x64/0x100 [ 8502.177702] kill_anon_super+0x14/0x30 [ 8502.178607] btrfs_kill_super+0x12/0xa0 [btrfs] [ 8502.179602] deactivate_locked_super+0x29/0x60 [ 8502.180595] cleanup_mnt+0x3b/0x70 [ 8502.181406] task_work_run+0x98/0xc0 [ 8502.182255] exit_to_usermode_loop+0x83/0x90 [ 8502.183113] do_syscall_64+0x15b/0x180 [ 8502.183919] entry_SYSCALL_64_after_hwframe+0x49/0xbe Corresponding to release_global_block_rsv() { ... WARN_ON(fs_info->delayed_refs_rsv.reserved > 0); CC: stable@vger.kernel.org Signed-off-by: Josef Bacik [ add log dump ] Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b15afeae16df..6f6fae410fc1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2456,12 +2456,10 @@ static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans, return ret ? ret : 1; } -static void cleanup_ref_head_accounting(struct btrfs_trans_handle *trans, - struct btrfs_delayed_ref_head *head) +void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head) { - struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_delayed_ref_root *delayed_refs = - &trans->transaction->delayed_refs; int nr_items = 1; /* Dropping this ref head update. */ if (head->total_ref_mod < 0) { @@ -2544,7 +2542,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans, } } - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head); trace_run_delayed_ref_head(fs_info, head, 0); btrfs_delayed_ref_unlock(head); @@ -7188,7 +7186,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, if (head->must_insert_reserved) ret = 1; - cleanup_ref_head_accounting(trans, head); + btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); return ret; -- cgit v1.2.3 From 3ec9a4c81c8cc2a8d9673588dd84d9cc7c31019b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 11 Jan 2019 10:21:01 -0500 Subject: btrfs: run delayed iputs before committing Delayed iputs means we can have final iputs of deleted inodes in the queue, which could potentially generate a lot of pinned space that could be free'd. So before we decide to commit the transaction for ENOPSC reasons, run the delayed iputs so that any potential space is free'd up. If there is and we freed enough we can then commit the transaction and potentially be able to make our reservation. Reviewed-by: Omar Sandoval Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/extent-tree.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'fs/btrfs/extent-tree.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6f6fae410fc1..d81035b7ea7d 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4952,6 +4952,15 @@ static void flush_space(struct btrfs_fs_info *fs_info, ret = 0; break; case COMMIT_TRANS: + /* + * If we have pending delayed iputs then we could free up a + * bunch of pinned space, so make sure we run the iputs before + * we do our pinned bytes check below. + */ + mutex_lock(&fs_info->cleaner_delayed_iput_mutex); + btrfs_run_delayed_iputs(fs_info); + mutex_unlock(&fs_info->cleaner_delayed_iput_mutex); + ret = may_commit_transaction(fs_info, space_info); break; default: -- cgit v1.2.3