Btrfs: fix heavy delalloc related deadlock

I added a patch where we started taking the ordered operations mutex when we
waited on ordered extents.  We need this because we splice the list and process
it, so if a flusher came in during this scenario it would think the list was
empty and we'd usually get an early ENOSPC.  The problem with this is that this
lock is used in transaction committing.  So we end up with something like this

Transaction commit
	-> wait on writers

Delalloc flusher
	-> run_ordered_operations (holds mutex)
		->wait for filemap-flush to do its thing

flush task
	-> cow_file_range
		->wait on btrfs_join_transaction because we're commiting

some other task
	-> commit_transaction because we notice trans->transaction->flush is set
		-> run_ordered_operations (hang on mutex)

We need to disentangle the ordered operations flushing from the delalloc
flushing, since they are separate things.  This solves the deadlock issue I was
seeing.  Thanks,

Signed-off-by: Josef Bacik <jbacik@fusionio.com>
Signed-off-by: Chris Mason <chris.mason@fusionio.com>

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0632832d4446673c52fe549217a28f632a6ceb49..063e48587126db0530c3ba0ca4940e0613ca882a 100644 (file)
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1413,6 +1413,13 @@ struct btrfs_fs_info {
         * before jumping into the main commit.
         */
        struct mutex ordered_operations_mutex;
+
+       /*
+        * Same as ordered_operations_mutex except this is for ordered extents
+        * and not the operations.
+        */
+       struct mutex ordered_extent_flush_mutex;
+
        struct rw_semaphore extent_commit_sem;
 
        struct rw_semaphore cleanup_work_sem;

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 572e21eb644cff4616e57781e7d49f238aba249e..68391ecf2c5909ed24b87c77359b7b709b2bf251 100644 (file)
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2277,6 +2277,7 @@ int open_ctree(struct super_block *sb,
 
 
        mutex_init(&fs_info->ordered_operations_mutex);
+       mutex_init(&fs_info->ordered_extent_flush_mutex);
        mutex_init(&fs_info->tree_log_mutex);
        mutex_init(&fs_info->chunk_mutex);
        mutex_init(&fs_info->transaction_kthread_mutex);

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 81369827e5146552edd7428911faef52ca3e1de6..b52b2c4010c214740647e15897c5733ad87f72af 100644 (file)
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -671,7 +671,7 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
        INIT_LIST_HEAD(&splice);
        INIT_LIST_HEAD(&works);
 
-       mutex_lock(&root->fs_info->ordered_operations_mutex);
+       mutex_lock(&root->fs_info->ordered_extent_flush_mutex);
        spin_lock(&root->fs_info->ordered_root_lock);
        list_splice_init(&cur_trans->ordered_operations, &splice);
        while (!list_empty(&splice)) {
@@ -718,7 +718,7 @@ out:
                list_del_init(&work->list);
                btrfs_wait_and_free_delalloc_work(work);
        }
-       mutex_unlock(&root->fs_info->ordered_operations_mutex);
+       mutex_unlock(&root->fs_info->ordered_extent_flush_mutex);
        return ret;
 }