Btrfs: place ordered operations on a per transaction list

Miao made the ordered operations stuff run async, which introduced a
deadlock where we could get somebody (sync) racing in and committing the
transaction while a commit was already happening.  The new committer would
try and flush ordered operations which would hang waiting for the commit to
finish because it is done asynchronously and no longer inherits the callers
trans handle.  To fix this we need to make the ordered operations list a per
transaction list.  We can get new inodes added to the ordered operation list
by truncating them and then having another process writing to them, so this
makes it so that anybody trying to add an ordered operation _must_ start a
transaction in order to add itself to the list, which will keep new inodes
from getting added to the ordered operations list after we start committing.
This should fix the deadlock and also keeps us from doing a lot more work
than we need to during commit.  Thanks,

Signed-off-by: Josef Bacik <jbacik@fusionio.com>

1 files changed, 8 insertions, 5 deletions

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 9489fa96e3ed..dc08d77b717e 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -612,10 +612,12 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput)
  * extra check to make sure the ordered operation list really is empty
  * before we return
  */
-int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
+int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
+                                 struct btrfs_root *root, int wait)
 {
         struct btrfs_inode *btrfs_inode;
         struct inode *inode;
+        struct btrfs_transaction *cur_trans = trans->transaction;
         struct list_head splice;
         struct list_head works;
         struct btrfs_delalloc_work *work, *next;
@@ -626,7 +628,7 @@ int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
 
         mutex_lock(&root->fs_info->ordered_operations_mutex);
         spin_lock(&root->fs_info->ordered_extent_lock);
-        list_splice_init(&root->fs_info->ordered_operations, &splice);
+        list_splice_init(&cur_trans->ordered_operations, &splice);
         while (!list_empty(&splice)) {
                 btrfs_inode = list_entry(splice.next, struct btrfs_inode,
                                    ordered_operations);
@@ -643,7 +645,7 @@ int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
 
                 if (!wait)
                         list_add_tail(&BTRFS_I(inode)->ordered_operations,
-                                      &root->fs_info->ordered_operations);
+                                      &cur_trans->ordered_operations);
                 spin_unlock(&root->fs_info->ordered_extent_lock);
 
                 work = btrfs_alloc_delalloc_work(inode, wait, 1);
@@ -653,7 +655,7 @@ int btrfs_run_ordered_operations(struct btrfs_root *root, int wait)
                                 list_add_tail(&btrfs_inode->ordered_operations,
                                               &splice);
                         list_splice_tail(&splice,
-                                         &root->fs_info->ordered_operations);
+                                         &cur_trans->ordered_operations);
                         spin_unlock(&root->fs_info->ordered_extent_lock);
                         ret = -ENOMEM;
                         goto out;
@@ -1033,6 +1035,7 @@ out:
 void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root, struct inode *inode)
 {
+        struct btrfs_transaction *cur_trans = trans->transaction;
         u64 last_mod;
 
         last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans);
@@ -1047,7 +1050,7 @@ void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
         spin_lock(&root->fs_info->ordered_extent_lock);
         if (list_empty(&BTRFS_I(inode)->ordered_operations)) {
                 list_add_tail(&BTRFS_I(inode)->ordered_operations,
-                              &root->fs_info->ordered_operations);
+                              &cur_trans->ordered_operations);
         }
         spin_unlock(&root->fs_info->ordered_extent_lock);
 }