Merge tag 'xfs-buf-lockless-lookup-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs into xfs-5.20-mergeB

xfs: lockless buffer cache lookups

Current work to merge the XFS inode life cycle with the VFS inode
life cycle is finding some interesting issues. If we have a path
that hits buffer trylocks fairly hard (e.g. a non-blocking
background inode freeing function), we end up hitting massive
contention on the buffer cache hash locks:

-   92.71%     0.05%  [kernel]                  [k] xfs_inodegc_worker
   - 92.67% xfs_inodegc_worker
      - 92.13% xfs_inode_unlink
         - 91.52% xfs_inactive_ifree
            - 85.63% xfs_read_agi
               - 85.61% xfs_trans_read_buf_map
                  - 85.59% xfs_buf_read_map
                     - xfs_buf_get_map
                        - 85.55% xfs_buf_find
                           - 72.87% _raw_spin_lock
                              - do_raw_spin_lock
                                   71.86% __pv_queued_spin_lock_slowpath
                           - 8.74% xfs_buf_rele
                              - 7.88% _raw_spin_lock
                                 - 7.88% do_raw_spin_lock
                                      7.63% __pv_queued_spin_lock_slowpath
                           - 1.70% xfs_buf_trylock
                              - 1.68% down_trylock
                                 - 1.41% _raw_spin_lock_irqsave
                                    - 1.39% do_raw_spin_lock
                                         __pv_queued_spin_lock_slowpath
                           - 0.76% _raw_spin_unlock
                                0.75% do_raw_spin_unlock

This is basically hammering the pag->pag_buf_lock from lots of CPUs
doing trylocks at the same time. Most of the buffer trylock
operations ultimately fail after we've done the lookup, so we're
really hammering the buf hash lock whilst making no progress.

We can also see significant spinlock traffic on the same lock just
under normal operation when lots of tasks are accessing metadata
from the same AG, so let's avoid all this by creating a lookup fast
path which leverages the rhashtable's ability to do RCU protected
lookups.

Signed-off-by: Dave Chinner <[email protected]>
Signed-off-by: Darrick J. Wong <[email protected]>

* tag 'xfs-buf-lockless-lookup-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs:
  xfs: lockless buffer lookup
  xfs: remove a superflous hash lookup when inserting new buffers
  xfs: reduce the number of atomic when locking a buffer after lookup
  xfs: merge xfs_buf_find() and xfs_buf_get_map()
  xfs: break up xfs_buf_find() into individual pieces
  xfs: rework xfs_buf_incore() API

Author: Darrick J. Wong

fs/xfs/libxfs/xfs_attr_remote.c

@@ -543,21 +543,26 @@ xfs_attr_rmtval_stale(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_buf		*bp;
+	int			error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
 	    XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
 		return -EFSCORRUPTED;
 
-	bp = xfs_buf_incore(mp->m_ddev_targp,
+	error = xfs_buf_incore(mp->m_ddev_targp,
 			XFS_FSB_TO_DADDR(mp, map->br_startblock),
-			XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags);
-	if (bp) {
-		xfs_buf_stale(bp);
-		xfs_buf_relse(bp);
+			XFS_FSB_TO_BB(mp, map->br_blockcount),
+			incore_flags, &bp);
+	if (error) {
+		if (error == -ENOENT)
+			return 0;
+		return error;
 	}
 
+	xfs_buf_stale(bp);
+	xfs_buf_relse(bp);
 	return 0;
 }
 

fs/xfs/scrub/repair.c

@@ -454,16 +454,19 @@ xrep_invalidate_blocks(
 	 * assume it's owned by someone else.
 	 */
 	for_each_xbitmap_block(fsbno, bmr, n, bitmap) {
+		int		error;
+
 		/* Skip AG headers and post-EOFS blocks */
 		if (!xfs_verify_fsbno(sc->mp, fsbno))
 			continue;
-		bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+		error = xfs_buf_incore(sc->mp->m_ddev_targp,
 				XFS_FSB_TO_DADDR(sc->mp, fsbno),
-				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
-		if (bp) {
-			xfs_trans_bjoin(sc->tp, bp);
-			xfs_trans_binval(sc->tp, bp);
-		}
+				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK, &bp);
+		if (error)
+			continue;
+
+		xfs_trans_bjoin(sc->tp, bp);
+		xfs_trans_binval(sc->tp, bp);
 	}
 
 	return 0;