1 files changed, 51 insertions, 16 deletions

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index a8d0ed91119..77b09750e92 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -71,7 +71,7 @@ xfs_buf_item_log_debug(
 		chunk_num = byte >> XFS_BLF_SHIFT;
 		word_num = chunk_num >> BIT_TO_WORD_SHIFT;
 		bit_num = chunk_num & (NBWORD - 1);
-		wordp = &(bip->bli_format.blf_data_map[word_num]);
+		wordp = &(bip->__bli_format.blf_data_map[word_num]);
 		bit_set = *wordp & (1 << bit_num);
 		ASSERT(bit_set);
 		byte++;
@@ -237,7 +237,7 @@ xfs_buf_item_size(
 		 * cancel flag in it.
 		 */
 		trace_xfs_buf_item_size_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		return bip->bli_format_count;
 	}
 
@@ -278,7 +278,7 @@ xfs_buf_item_format_segment(
 	uint		buffer_offset;
 
 	/* copy the flags across from the base format item */
-	blfp->blf_flags = bip->bli_format.blf_flags;
+	blfp->blf_flags = bip->__bli_format.blf_flags;
 
 	/*
 	 * Base size is the actual size of the ondisk structure - it reflects
@@ -287,6 +287,17 @@ xfs_buf_item_format_segment(
 	 */
 	base_size = offsetof(struct xfs_buf_log_format, blf_data_map) +
 			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
+
+	nvecs = 0;
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (!(bip->bli_flags & XFS_BLI_STALE) && first_bit == -1) {
+		/*
+		 * If the map is not be dirty in the transaction, mark
+		 * the size as zero and do not advance the vector pointer.
+		 */
+		goto out;
+	}
+
 	vecp->i_addr = blfp;
 	vecp->i_len = base_size;
 	vecp->i_type = XLOG_REG_TYPE_BFORMAT;
@@ -301,15 +312,13 @@ xfs_buf_item_format_segment(
 		 */
 		trace_xfs_buf_item_format_stale(bip);
 		ASSERT(blfp->blf_flags & XFS_BLF_CANCEL);
-		blfp->blf_size = nvecs;
-		return vecp;
+		goto out;
 	}
 
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
-	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
-	ASSERT(first_bit != -1);
+
 	last_bit = first_bit;
 	nbits = 1;
 	for (;;) {
@@ -371,7 +380,8 @@ xfs_buf_item_format_segment(
 			nbits++;
 		}
 	}
-	bip->bli_format.blf_size = nvecs;
+out:
+	blfp->blf_size = nvecs;
 	return vecp;
 }
 
@@ -405,7 +415,7 @@ xfs_buf_item_format(
 	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
 		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
 		      xfs_log_item_in_current_chkpt(lip)))
-			bip->bli_format.blf_flags |= XFS_BLF_INODE_BUF;
+			bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
 		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
 	}
 
@@ -485,7 +495,7 @@ xfs_buf_item_unpin(
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
 		ASSERT(xfs_buf_islocked(bp));
 		ASSERT(XFS_BUF_ISSTALE(bp));
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 
 		trace_xfs_buf_item_unpin_stale(bip);
 
@@ -526,7 +536,25 @@ xfs_buf_item_unpin(
 		}
 		xfs_buf_relse(bp);
 	} else if (freed && remove) {
+		/*
+		 * There are currently two references to the buffer - the active
+		 * LRU reference and the buf log item. What we are about to do
+		 * here - simulate a failed IO completion - requires 3
+		 * references.
+		 *
+		 * The LRU reference is removed by the xfs_buf_stale() call. The
+		 * buf item reference is removed by the xfs_buf_iodone()
+		 * callback that is run by xfs_buf_do_callbacks() during ioend
+		 * processing (via the bp->b_iodone callback), and then finally
+		 * the ioend processing will drop the IO reference if the buffer
+		 * is marked XBF_ASYNC.
+		 *
+		 * Hence we need to take an additional reference here so that IO
+		 * completion processing doesn't free the buffer prematurely.
+		 */
 		xfs_buf_lock(bp);
+		xfs_buf_hold(bp);
+		bp->b_flags |= XBF_ASYNC;
 		xfs_buf_ioerror(bp, EIO);
 		XFS_BUF_UNDONE(bp);
 		xfs_buf_stale(bp);
@@ -583,7 +611,7 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	int			aborted;
+	int			aborted, clean, i;
 	uint			hold;
 
 	/* Clear the buffer's association with this transaction. */
@@ -613,7 +641,7 @@ xfs_buf_item_unlock(
 	 */
 	if (bip->bli_flags & XFS_BLI_STALE) {
 		trace_xfs_buf_item_unlock_stale(bip);
-		ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
+		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		if (!aborted) {
 			atomic_dec(&bip->bli_refcount);
 			return;
@@ -626,8 +654,15 @@ xfs_buf_item_unlock(
 	 * If the buf item isn't tracking any data, free it, otherwise drop the
 	 * reference we hold to it.
 	 */
-	if (xfs_bitmap_empty(bip->bli_format.blf_data_map,
-			     bip->bli_format.blf_map_size))
+	clean = 1;
+	for (i = 0; i < bip->bli_format_count; i++) {
+		if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
+			     bip->bli_formats[i].blf_map_size)) {
+			clean = 0;
+			break;
+		}
+	}
+	if (clean)
 		xfs_buf_item_relse(bp);
 	else
 		atomic_dec(&bip->bli_refcount);
@@ -698,7 +733,7 @@ xfs_buf_item_get_format(
 	bip->bli_format_count = count;
 
 	if (count == 1) {
-		bip->bli_formats = &bip->bli_format;
+		bip->bli_formats = &bip->__bli_format;
 		return 0;
 	}
 
@@ -713,7 +748,7 @@ STATIC void
 xfs_buf_item_free_format(
 	struct xfs_buf_log_item	*bip)
 {
-	if (bip->bli_formats != &bip->bli_format) {
+	if (bip->bli_formats != &bip->__bli_format) {
 		kmem_free(bip->bli_formats);
 		bip->bli_formats = NULL;
 	}