1 files changed, 92 insertions, 48 deletions

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 99e91a0e554e..e455f9098d49 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -359,7 +359,7 @@ xfs_buf_item_format(
 	for (i = 0; i < bip->bli_format_count; i++) {
 		xfs_buf_item_format_segment(bip, lv, &vecp, offset,
 					    &bip->bli_formats[i]);
-		offset += bp->b_maps[i].bm_len;
+		offset += BBTOB(bp->b_maps[i].bm_len);
 	}
 
 	/*
@@ -915,20 +915,28 @@ xfs_buf_item_log(
 	for (i = 0; i < bip->bli_format_count; i++) {
 		if (start > last)
 			break;
-		end = start + BBTOB(bp->b_maps[i].bm_len);
+		end = start + BBTOB(bp->b_maps[i].bm_len) - 1;
+
+		/* skip to the map that includes the first byte to log */
 		if (first > end) {
 			start += BBTOB(bp->b_maps[i].bm_len);
 			continue;
 		}
+
+		/*
+		 * Trim the range to this segment and mark it in the bitmap.
+		 * Note that we must convert buffer offsets to segment relative
+		 * offsets (e.g., the first byte of each segment is byte 0 of
+		 * that segment).
+		 */
 		if (first < start)
 			first = start;
 		if (end > last)
 			end = last;
-
-		xfs_buf_item_log_segment(first, end,
+		xfs_buf_item_log_segment(first - start, end - start,
 					 &bip->bli_formats[i].blf_data_map[0]);
 
-		start += bp->b_maps[i].bm_len;
+		start += BBTOB(bp->b_maps[i].bm_len);
 	}
 }
 
@@ -949,6 +957,7 @@ xfs_buf_item_free(
 	xfs_buf_log_item_t	*bip)
 {
 	xfs_buf_item_free_format(bip);
+	kmem_free(bip->bli_item.li_lv_shadow);
 	kmem_zone_free(xfs_buf_item_zone, bip);
 }
 
@@ -1042,35 +1051,22 @@ xfs_buf_do_callbacks(
 	}
 }
 
-/*
- * This is the iodone() function for buffers which have had callbacks
- * attached to them by xfs_buf_attach_iodone().  It should remove each
- * log item from the buffer's list and call the callback of each in turn.
- * When done, the buffer's fsprivate field is set to NULL and the buffer
- * is unlocked with a call to iodone().
- */
-void
-xfs_buf_iodone_callbacks(
+static bool
+xfs_buf_iodone_callback_error(
 	struct xfs_buf		*bp)
 {
 	struct xfs_log_item	*lip = bp->b_fspriv;
 	struct xfs_mount	*mp = lip->li_mountp;
 	static ulong		lasttime;
 	static xfs_buftarg_t	*lasttarg;
-
-	if (likely(!bp->b_error))
-		goto do_callbacks;
+	struct xfs_error_cfg	*cfg;
 
 	/*
 	 * If we've already decided to shutdown the filesystem because of
 	 * I/O errors, there's no point in giving this a retry.
 	 */
-	if (XFS_FORCED_SHUTDOWN(mp)) {
-		xfs_buf_stale(bp);
-		bp->b_flags |= XBF_DONE;
-		trace_xfs_buf_item_iodone(bp, _RET_IP_);
-		goto do_callbacks;
-	}
+	if (XFS_FORCED_SHUTDOWN(mp))
+		goto out_stale;
 
 	if (bp->b_target != lasttarg ||
 	    time_after(jiffies, (lasttime + 5*HZ))) {
@@ -1079,45 +1075,93 @@ xfs_buf_iodone_callbacks(
 	}
 	lasttarg = bp->b_target;
 
+	/* synchronous writes will have callers process the error */
+	if (!(bp->b_flags & XBF_ASYNC))
+		goto out_stale;
+
+	trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+	ASSERT(bp->b_iodone != NULL);
+
+	cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error);
+
 	/*
 	 * If the write was asynchronous then no one will be looking for the
-	 * error.  Clear the error state and write the buffer out again.
-	 *
-	 * XXX: This helps against transient write errors, but we need to find
-	 * a way to shut the filesystem down if the writes keep failing.
-	 *
-	 * In practice we'll shut the filesystem down soon as non-transient
-	 * errors tend to affect the whole device and a failing log write
-	 * will make us give up.  But we really ought to do better here.
+	 * error.  If this is the first failure of this type, clear the error
+	 * state and write the buffer out again. This means we always retry an
+	 * async write failure at least once, but we also need to set the buffer
+	 * up to behave correctly now for repeated failures.
 	 */
-	if (bp->b_flags & XBF_ASYNC) {
-		ASSERT(bp->b_iodone != NULL);
+	if (!(bp->b_flags & (XBF_STALE | XBF_WRITE_FAIL)) ||
+	     bp->b_last_error != bp->b_error) {
+		bp->b_flags |= (XBF_WRITE | XBF_DONE | XBF_WRITE_FAIL);
+		bp->b_last_error = bp->b_error;
+		if (cfg->retry_timeout && !bp->b_first_retry_time)
+			bp->b_first_retry_time = jiffies;
+
+		xfs_buf_ioerror(bp, 0);
+		xfs_buf_submit(bp);
+		return true;
+	}
 
-		trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+	/*
+	 * Repeated failure on an async write. Take action according to the
+	 * error configuration we have been set up to use.
+	 */
 
-		xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
+	if (cfg->max_retries != XFS_ERR_RETRY_FOREVER &&
+	    ++bp->b_retries > cfg->max_retries)
+			goto permanent_error;
+	if (cfg->retry_timeout &&
+	    time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time))
+			goto permanent_error;
 
-		if (!(bp->b_flags & (XBF_STALE|XBF_WRITE_FAIL))) {
-			bp->b_flags |= XBF_WRITE | XBF_ASYNC |
-				       XBF_DONE | XBF_WRITE_FAIL;
-			xfs_buf_submit(bp);
-		} else {
-			xfs_buf_relse(bp);
-		}
+	/* At unmount we may treat errors differently */
+	if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount)
+		goto permanent_error;
 
-		return;
-	}
+	/* still a transient error, higher layers will retry */
+	xfs_buf_ioerror(bp, 0);
+	xfs_buf_relse(bp);
+	return true;
 
 	/*
-	 * If the write of the buffer was synchronous, we want to make
-	 * sure to return the error to the caller of xfs_bwrite().
+	 * Permanent error - we need to trigger a shutdown if we haven't already
+	 * to indicate that inconsistency will result from this action.
 	 */
+permanent_error:
+	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+out_stale:
 	xfs_buf_stale(bp);
 	bp->b_flags |= XBF_DONE;
-
 	trace_xfs_buf_error_relse(bp, _RET_IP_);
+	return false;
+}
+
+/*
+ * This is the iodone() function for buffers which have had callbacks attached
+ * to them by xfs_buf_attach_iodone(). We need to iterate the items on the
+ * callback list, mark the buffer as having no more callbacks and then push the
+ * buffer through IO completion processing.
+ */
+void
+xfs_buf_iodone_callbacks(
+	struct xfs_buf		*bp)
+{
+	/*
+	 * If there is an error, process it. Some errors require us
+	 * to run callbacks after failure processing is done so we
+	 * detect that and take appropriate action.
+	 */
+	if (bp->b_error && xfs_buf_iodone_callback_error(bp))
+		return;
+
+	/*
+	 * Successful IO or permanent error. Either way, we can clear the
+	 * retry state here in preparation for the next error that may occur.
+	 */
+	bp->b_last_error = 0;
+	bp->b_retries = 0;
 
-do_callbacks:
 	xfs_buf_do_callbacks(bp);
 	bp->b_fspriv = NULL;
 	bp->b_iodone = NULL;