From ae5e070eaca9dbebde3459dd8f4c2756f8c097d0 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 4 Dec 2020 09:24:47 +0800 Subject: [PATCH] btrfs: qgroup: don't try to wait flushing if we're already holding a transaction There is a chance of racing for qgroup flushing which may lead to deadlock: Thread A | Thread B (not holding trans handle) | (holding a trans handle) --------------------------------+-------------------------------- __btrfs_qgroup_reserve_meta() | __btrfs_qgroup_reserve_meta() |- try_flush_qgroup() | |- try_flush_qgroup() |- QGROUP_FLUSHING bit set | | | | |- test_and_set_bit() | | |- wait_event() |- btrfs_join_transaction() | |- btrfs_commit_transaction()| !!! DEAD LOCK !!! Since thread A wants to commit transaction, but thread B is holding a transaction handle, blocking the commit. At the same time, thread B is waiting for thread A to finish its commit. This is just a hot fix, and would lead to more EDQUOT when we're near the qgroup limit. The proper fix would be to make all metadata/data reservations happen without holding a transaction handle. CC: stable@vger.kernel.org # 5.9+ Reviewed-by: Filipe Manana Signed-off-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/qgroup.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index fe30460..47f2765 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3531,16 +3531,6 @@ static int try_flush_qgroup(struct btrfs_root *root) bool can_commit = true; /* - * We don't want to run flush again and again, so if there is a running - * one, we won't try to start a new flush, but exit directly. - */ - if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { - wait_event(root->qgroup_flush_wait, - !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); - 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. @@ -3554,6 +3544,26 @@ static int try_flush_qgroup(struct btrfs_root *root) current->journal_info != BTRFS_SEND_TRANS_STUB) can_commit = false; + /* + * We don't want to run flush again and again, so if there is a running + * one, we won't try to start a new flush, but exit directly. + */ + if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) { + /* + * We are already holding a transaction, thus we can block other + * threads from flushing. So exit right now. This increases + * the chance of EDQUOT for heavy load and near limit cases. + * But we can argue that if we're already near limit, EDQUOT is + * unavoidable anyway. + */ + if (!can_commit) + return 0; + + wait_event(root->qgroup_flush_wait, + !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)); + return 0; + } + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; -- 2.7.4