Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull second set of btrfs updates from Chris Mason:
 "The most important changes here are from Josef, fixing a btrfs
  regression in 3.14 that can cause corruptions in the extent allocation
  tree when snapshots are in use.

  Josef also fixed some deadlocks in send/recv and other assorted races
  when balance is running"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (23 commits)
  Btrfs: fix compile warnings on on avr32 platform
  btrfs: allow mounting btrfs subvolumes with different ro/rw options
  btrfs: export global block reserve size as space_info
  btrfs: fix crash in remount(thread_pool=) case
  Btrfs: abort the transaction when we don't find our extent ref
  Btrfs: fix EINVAL checks in btrfs_clone
  Btrfs: fix unlock in __start_delalloc_inodes()
  Btrfs: scrub raid56 stripes in the right way
  Btrfs: don't compress for a small write
  Btrfs: more efficient io tree navigation on wait_extent_bit
  Btrfs: send, build path string only once in send_hole
  btrfs: filter invalid arg for btrfs resize
  Btrfs: send, fix data corruption due to incorrect hole detection
  Btrfs: kmalloc() doesn't return an ERR_PTR
  Btrfs: fix snapshot vs nocow writting
  btrfs: Change the expanding write sequence to fix snapshot related bug.
  btrfs: make device scan less noisy
  btrfs: fix lockdep warning with reclaim lock inversion
  Btrfs: hold the commit_root_sem when getting the commit root during send
  Btrfs: remove transaction from send
  ...

1 files changed, 20 insertions, 3 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index bd0f752b797b..029d46c2e170 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -329,6 +329,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 {
 	struct extent_state *cached_state = NULL;
 	int ret;
+	bool need_lock = (current->journal_info ==
+			  (void *)BTRFS_SEND_TRANS_STUB);
 
 	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
 		return 0;
@@ -336,6 +338,11 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 	if (atomic)
 		return -EAGAIN;
 
+	if (need_lock) {
+		btrfs_tree_read_lock(eb);
+		btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+	}
+
 	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
 			 0, &cached_state);
 	if (extent_buffer_uptodate(eb) &&
@@ -347,10 +354,21 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		       "found %llu\n",
 		       eb->start, parent_transid, btrfs_header_generation(eb));
 	ret = 1;
-	clear_extent_buffer_uptodate(eb);
+
+	/*
+	 * Things reading via commit roots that don't have normal protection,
+	 * like send, can have a really old block in cache that may point at a
+	 * block that has been free'd and re-allocated.  So don't clear uptodate
+	 * if we find an eb that is under IO (dirty/writeback) because we could
+	 * end up reading in the stale data and then writing it back out and
+	 * making everybody very sad.
+	 */
+	if (!extent_buffer_under_io(eb))
+		clear_extent_buffer_uptodate(eb);
 out:
 	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
 			     &cached_state, GFP_NOFS);
+	btrfs_tree_read_unlock_blocking(eb);
 	return ret;
 }
 
@@ -1546,7 +1564,6 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	root->subv_writers = writers;
 
 	btrfs_init_free_ino_ctl(root);
-	mutex_init(&root->fs_commit_mutex);
 	spin_lock_init(&root->cache_lock);
 	init_waitqueue_head(&root->cache_wait);
 
@@ -2324,7 +2341,7 @@ int open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->transaction_kthread_mutex);
 	mutex_init(&fs_info->cleaner_mutex);
 	mutex_init(&fs_info->volume_mutex);
-	init_rwsem(&fs_info->extent_commit_sem);
+	init_rwsem(&fs_info->commit_root_sem);
 	init_rwsem(&fs_info->cleanup_work_sem);
 	init_rwsem(&fs_info->subvol_sem);
 	sema_init(&fs_info->uuid_tree_rescan_sem, 1);