From 570dd45042a7c8a7aba1ee029c5dd0f5ccf41b9b Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 27 Oct 2016 10:42:20 -0700 Subject: [PATCH] btrfs: fix races on root_log_ctx lists btrfs_remove_all_log_ctxs takes a shortcut where it avoids walking the list because it knows all of the waiters are patiently waiting for the commit to finish. But, there's a small race where btrfs_sync_log can remove itself from the list if it finds a log commit is already done. Also, it uses list_del_init() to remove itself from the list, but there's no way to know if btrfs_remove_all_log_ctxs has already run, so we don't know for sure if it is safe to call list_del_init(). This gets rid of all the shortcuts for btrfs_remove_all_log_ctxs(), and just calls it with the proper locking. This is part two of the corruption fixed by cbd60aa7cd1. I should have done this in the first place, but convinced myself the optimizations were safe. A 12 hour run of dbench 2048 will eventually trigger a list debug WARN_ON for the list_del_init() in btrfs_sync_log(). Fixes: d1433debe7f4346cf9fc0dafc71c3137d2a97bc4 Reported-by: Dave Jones cc: stable@vger.kernel.org # 3.15+ Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 688df71c1bf7..4b1c0a6eee04 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2713,14 +2713,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; + struct btrfs_log_ctx *safe; - if (!error) { - INIT_LIST_HEAD(&root->log_ctxs[index]); - return; - } - - list_for_each_entry(ctx, &root->log_ctxs[index], list) + list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { + list_del_init(&ctx->list); ctx->log_ret = error; + } INIT_LIST_HEAD(&root->log_ctxs[index]); } @@ -2961,13 +2959,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&root->log_mutex); out_wake_log_root: - /* - * We needn't get log_mutex here because we are sure all - * the other tasks are blocked. - */ + mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); - mutex_lock(&log_root_tree->log_mutex); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); @@ -2978,10 +2972,8 @@ out_wake_log_root: if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: - /* See above. */ - btrfs_remove_all_log_ctxs(root, index1, ret); - mutex_lock(&root->log_mutex); + btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); -- 2.39.5