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

Pull btrfs fixes from Chris Mason:
 "Most of these are fixing extent reservation accounting, or corners
  with tree writeback during commit.

  Josef's set does add a test, which isn't strictly a fix, but it'll
  keep us from making this same mistake again"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: fix outstanding_extents accounting in DIO
  Btrfs: add sanity test for outstanding_extents accounting
  Btrfs: just free dummy extent buffers
  Btrfs: account merges/splits properly
  Btrfs: prepare block group cache before writing
  Btrfs: fix ASSERT(list_empty(&cur_trans->dirty_bgs_list)
  Btrfs: account for the correct number of extents for delalloc reservations
  Btrfs: fix merge delalloc logic
  Btrfs: fix comp_oper to get right order
  Btrfs: catch transaction abortion after waiting for it
  btrfs: fix sizeof format specifier in btrfs_check_super_valid()

1 files changed, 84 insertions, 28 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index da828cf5e8f8..d2e732d7af52 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -108,6 +108,13 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 
 static int btrfs_dirty_inode(struct inode *inode);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
 static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 				     struct inode *inode,  struct inode *dir,
 				     const struct qstr *qstr)
@@ -1542,30 +1549,17 @@ static void btrfs_split_extent_hook(struct inode *inode,
 		u64 new_size;
 
 		/*
-		 * We need the largest size of the remaining extent to see if we
-		 * need to add a new outstanding extent.  Think of the following
-		 * case
-		 *
-		 * [MEAX_EXTENT_SIZEx2 - 4k][4k]
-		 *
-		 * The new_size would just be 4k and we'd think we had enough
-		 * outstanding extents for this if we only took one side of the
-		 * split, same goes for the other direction.  We need to see if
-		 * the larger size still is the same amount of extents as the
-		 * original size, because if it is we need to add a new
-		 * outstanding extent.  But if we split up and the larger size
-		 * is less than the original then we are good to go since we've
-		 * already accounted for the extra extent in our original
-		 * accounting.
+		 * See the explanation in btrfs_merge_extent_hook, the same
+		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		if ((split - orig->start) > new_size)
-			new_size = split - orig->start;
-
-		num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+		num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
 					BTRFS_MAX_EXTENT_SIZE);
-		if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-			      BTRFS_MAX_EXTENT_SIZE) < num_extents)
+		new_size = split - orig->start;
+		num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+					BTRFS_MAX_EXTENT_SIZE);
+		if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+			      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 			return;
 	}
 
@@ -1591,8 +1585,10 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 	if (!(other->state & EXTENT_DELALLOC))
 		return;
 
-	old_size = other->end - other->start + 1;
-	new_size = old_size + (new->end - new->start + 1);
+	if (new->start > other->start)
+		new_size = new->end - other->start + 1;
+	else
+		new_size = other->end - new->start + 1;
 
 	/* we're not bigger than the max, unreserve the space and go */
 	if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
@@ -1603,13 +1599,32 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 	}
 
 	/*
-	 * If we grew by another max_extent, just return, we want to keep that
-	 * reserved amount.
+	 * We have to add up either side to figure out how many extents were
+	 * accounted for before we merged into one big extent.  If the number of
+	 * extents we accounted for is <= the amount we need for the new range
+	 * then we can return, otherwise drop.  Think of it like this
+	 *
+	 * [ 4k][MAX_SIZE]
+	 *
+	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
+	 * need 2 outstanding extents, on one side we have 1 and the other side
+	 * we have 1 so they are == and we can return.  But in this case
+	 *
+	 * [MAX_SIZE+4k][MAX_SIZE+4k]
+	 *
+	 * Each range on their own accounts for 2 extents, but merged together
+	 * they are only 3 extents worth of accounting, so we need to drop in
+	 * this case.
 	 */
+	old_size = other->end - other->start + 1;
 	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
 				BTRFS_MAX_EXTENT_SIZE);
+	old_size = new->end - new->start + 1;
+	num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+				 BTRFS_MAX_EXTENT_SIZE);
+
 	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-		      BTRFS_MAX_EXTENT_SIZE) > num_extents)
+		      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -1686,6 +1701,10 @@ static void btrfs_set_bit_hook(struct inode *inode,
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
 
+		/* For sanity tests */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
 				     root->fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
@@ -1741,6 +1760,10 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		    root != root->fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len);
 
+		/* For sanity tests. */
+		if (btrfs_test_is_dummy_root(root))
+			return;
+
 		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 		    && do_list && !(state->state & EXTENT_NORESERVE))
 			btrfs_free_reserved_data_space(inode, len);
@@ -7213,7 +7236,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	u64 start = iblock << inode->i_blkbits;
 	u64 lockstart, lockend;
 	u64 len = bh_result->b_size;
-	u64 orig_len = len;
+	u64 *outstanding_extents = NULL;
 	int unlock_bits = EXTENT_LOCKED;
 	int ret = 0;
 
@@ -7225,6 +7248,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	lockstart = start;
 	lockend = start + len - 1;
 
+	if (current->journal_info) {
+		/*
+		 * Need to pull our outstanding extents and set journal_info to NULL so
+		 * that anything that needs to check if there's a transction doesn't get
+		 * confused.
+		 */
+		outstanding_extents = current->journal_info;
+		current->journal_info = NULL;
+	}
+
 	/*
 	 * If this errors out it's because we couldn't invalidate pagecache for
 	 * this range and we need to fallback to buffered.
@@ -7348,11 +7381,20 @@ unlock:
 		if (start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
-		if (len < orig_len) {
+		/*
+		 * If we have an outstanding_extents count still set then we're
+		 * within our reservation, otherwise we need to adjust our inode
+		 * counter appropriately.
+		 */
+		if (*outstanding_extents) {
+			(*outstanding_extents)--;
+		} else {
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
 		}
+
+		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
 	}
 
@@ -7376,6 +7418,8 @@ unlock:
 unlock_err:
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
 			 unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+	if (outstanding_extents)
+		current->journal_info = outstanding_extents;
 	return ret;
 }
 
@@ -8075,6 +8119,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
+	u64 outstanding_extents = 0;
 	size_t count = 0;
 	int flags = 0;
 	bool wakeup = true;
@@ -8112,6 +8157,16 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		ret = btrfs_delalloc_reserve_space(inode, count);
 		if (ret)
 			goto out;
+		outstanding_extents = div64_u64(count +
+						BTRFS_MAX_EXTENT_SIZE - 1,
+						BTRFS_MAX_EXTENT_SIZE);
+
+		/*
+		 * We need to know how many extents we reserved so that we can
+		 * do the accounting properly if we go over the number we
+		 * originally calculated.  Abuse current->journal_info for this.
+		 */
+		current->journal_info = &outstanding_extents;
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_done(inode);
@@ -8124,6 +8179,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 			iter, offset, btrfs_get_blocks_direct, NULL,
 			btrfs_submit_direct, flags);
 	if (rw & WRITE) {
+		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED)
 			btrfs_delalloc_release_space(inode, count);
 		else if (ret >= 0 && (size_t)ret < count)