xfs: xfs_iflush() is no longer necessary

Now we have a cached buffer on inode log items, we don't need
to do buffer lookups when flushing inodes anymore - all we need
to do is lock the buffer and we are ready to go.

This largely gets rid of the need for xfs_iflush(), which is
essentially just a mechanism to look up the buffer and flush the
inode to it. Instead, we can just call xfs_iflush_cluster() with a
few modifications to ensure it also flushes the inode we already
hold locked.

This allows the AIL inode item pushing to be almost entirely
non-blocking in XFS - we won't block unless memory allocation
for the cluster inode lookup blocks or the block device queues are
full.

Writeback during inode reclaim becomes a little more complex because
we now have to lock the buffer ourselves, but otherwise this change
is largely a functional no-op that removes a whole lot of code.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

1 files changed, 14 insertions, 93 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c4586ac3656a..4a9539048639 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3450,7 +3450,18 @@ out_release_wip:
 	return error;
 }
 
-STATIC int
+/*
+ * Non-blocking flush of dirty inode metadata into the backing buffer.
+ *
+ * The caller must have a reference to the inode and hold the cluster buffer
+ * locked. The function will walk across all the inodes on the cluster buffer it
+ * can find and lock without blocking, and flush them to the cluster buffer.
+ *
+ * On success, the caller must write out the buffer returned in *bp and
+ * release it. On failure, the filesystem will be shut down, the buffer will
+ * have been unlocked and released, and EFSCORRUPTED will be returned.
+ */
+int
 xfs_iflush_cluster(
 	struct xfs_inode	*ip,
 	struct xfs_buf		*bp)
@@ -3485,8 +3496,6 @@ xfs_iflush_cluster(
 
 	for (i = 0; i < nr_found; i++) {
 		cip = cilist[i];
-		if (cip == ip)
-			continue;
 
 		/*
 		 * because this is an RCU protected lookup, we could find a
@@ -3577,99 +3586,11 @@ out_free:
 	kmem_free(cilist);
 out_put:
 	xfs_perag_put(pag);
-	return error;
-}
-
-/*
- * Flush dirty inode metadata into the backing buffer.
- *
- * The caller must have the inode lock and the inode flush lock held.  The
- * inode lock will still be held upon return to the caller, and the inode
- * flush lock will be released after the inode has reached the disk.
- *
- * The caller must write out the buffer returned in *bpp and release it.
- */
-int
-xfs_iflush(
-	struct xfs_inode	*ip,
-	struct xfs_buf		**bpp)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_buf		*bp = NULL;
-	struct xfs_dinode	*dip;
-	int			error;
-
-	XFS_STATS_INC(mp, xs_iflush_count);
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(xfs_isiflocked(ip));
-	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
-	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-
-	*bpp = NULL;
-
-	xfs_iunpin_wait(ip);
-
-	/*
-	 * For stale inodes we cannot rely on the backing buffer remaining
-	 * stale in cache for the remaining life of the stale inode and so
-	 * xfs_imap_to_bp() below may give us a buffer that no longer contains
-	 * inodes below. We have to check this after ensuring the inode is
-	 * unpinned so that it is safe to reclaim the stale inode after the
-	 * flush call.
-	 */
-	if (xfs_iflags_test(ip, XFS_ISTALE)) {
-		xfs_ifunlock(ip);
-		return 0;
-	}
-
-	/*
-	 * Get the buffer containing the on-disk inode. We are doing a try-lock
-	 * operation here, so we may get an EAGAIN error. In that case, return
-	 * leaving the inode dirty.
-	 *
-	 * If we get any other error, we effectively have a corruption situation
-	 * and we cannot flush the inode. Abort the flush and shut down.
-	 */
-	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK);
-	if (error == -EAGAIN) {
-		xfs_ifunlock(ip);
-		return error;
-	}
-	if (error)
-		goto abort;
-
-	/*
-	 * If the buffer is pinned then push on the log now so we won't
-	 * get stuck waiting in the write for too long.
-	 */
-	if (xfs_buf_ispinned(bp))
-		xfs_log_force(mp, 0);
-
-	/*
-	 * Flush the provided inode then attempt to gather others from the
-	 * cluster into the write.
-	 *
-	 * Note: Once we attempt to flush an inode, we must run buffer
-	 * completion callbacks on any failure. If this fails, simulate an I/O
-	 * failure on the buffer and shut down.
-	 */
-	error = xfs_iflush_int(ip, bp);
-	if (!error)
-		error = xfs_iflush_cluster(ip, bp);
 	if (error) {
 		bp->b_flags |= XBF_ASYNC;
 		xfs_buf_ioend_fail(bp);
-		goto shutdown;
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	}
-
-	*bpp = bp;
-	return 0;
-
-abort:
-	xfs_iflush_abort(ip);
-shutdown:
-	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 	return error;
 }
 
@@ -3687,7 +3608,7 @@ xfs_iflush_int(
 	ASSERT(xfs_isiflocked(ip));
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
-	ASSERT(iip != NULL && iip->ili_fields != 0);
+	ASSERT(iip->ili_item.li_buf == bp);
 
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);