xfs: convert inode cache lookups to use RCU locking

With delayed logging greatly increasing the sustained parallelism of inode
operations, the inode cache locking is showing significant read vs write
contention when inode reclaim runs at the same time as lookups. There is
also a lot more write lock acquistions than there are read locks (4:1 ratio)
so the read locking is not really buying us much in the way of parallelism.

To avoid the read vs write contention, change the cache to use RCU locking on
the read side. To avoid needing to RCU free every single inode, use the built
in slab RCU freeing mechanism. This requires us to be able to detect lookups of
freed inodes, so enѕure that ever freed inode has an inode number of zero and
the XFS_IRECLAIM flag set. We already check the XFS_IRECLAIM flag in cache hit
lookup path, but also add a check for a zero inode number as well.

We canthen convert all the read locking lockups to use RCU read side locking
and hence remove all read side locking.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Alex Elder <aelder@sgi.com>

1 files changed, 35 insertions, 12 deletions

diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 9fae475..04ed09b 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -80,6 +80,7 @@ xfs_inode_alloc(
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(completion_done(&ip->i_flush));
+	ASSERT(ip->i_ino == 0);
 
 	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
 	lockdep_set_class_and_name(&ip->i_iolock.mr_lock,
@@ -98,9 +99,6 @@ xfs_inode_alloc(
 	ip->i_size = 0;
 	ip->i_new_size = 0;
 
-	/* prevent anyone from using this yet */
-	VFS_I(ip)->i_state = I_NEW;
-
 	return ip;
 }
 
@@ -159,6 +157,16 @@ xfs_inode_free(
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(completion_done(&ip->i_flush));
 
+	/*
+	 * Because we use RCU freeing we need to ensure the inode always
+	 * appears to be reclaimed with an invalid inode number when in the
+	 * free state. The ip->i_flags_lock provides the barrier against lookup
+	 * races.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	ip->i_flags = XFS_IRECLAIM;
+	ip->i_ino = 0;
+	spin_unlock(&ip->i_flags_lock);
 	call_rcu((struct rcu_head *)&VFS_I(ip)->i_dentry, __xfs_inode_free);
 }
 
@@ -169,14 +177,29 @@ static int
 xfs_iget_cache_hit(
 	struct xfs_perag	*pag,
 	struct xfs_inode	*ip,
+	xfs_ino_t		ino,
 	int			flags,
-	int			lock_flags) __releases(pag->pag_ici_lock)
+	int			lock_flags) __releases(RCU)
 {
 	struct inode		*inode = VFS_I(ip);
 	struct xfs_mount	*mp = ip->i_mount;
 	int			error;
 
+	/*
+	 * check for re-use of an inode within an RCU grace period due to the
+	 * radix tree nodes not being updated yet. We monitor for this by
+	 * setting the inode number to zero before freeing the inode structure.
+	 * If the inode has been reallocated and set up, then the inode number
+	 * will not match, so check for that, too.
+	 */
 	spin_lock(&ip->i_flags_lock);
+	if (ip->i_ino != ino) {
+		trace_xfs_iget_skip(ip);
+		XFS_STATS_INC(xs_ig_frecycle);
+		error = EAGAIN;
+		goto out_error;
+	}
+
 
 	/*
 	 * If we are racing with another cache hit that is currently
@@ -219,7 +242,7 @@ xfs_iget_cache_hit(
 		ip->i_flags |= XFS_IRECLAIM;
 
 		spin_unlock(&ip->i_flags_lock);
-		read_unlock(&pag->pag_ici_lock);
+		rcu_read_unlock();
 
 		error = -inode_init_always(mp->m_super, inode);
 		if (error) {
@@ -227,7 +250,7 @@ xfs_iget_cache_hit(
 			 * Re-initializing the inode failed, and we are in deep
 			 * trouble.  Try to re-add it to the reclaim list.
 			 */
-			read_lock(&pag->pag_ici_lock);
+			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
 
 			ip->i_flags &= ~XFS_INEW;
@@ -261,7 +284,7 @@ xfs_iget_cache_hit(
 
 		/* We've got a live one. */
 		spin_unlock(&ip->i_flags_lock);
-		read_unlock(&pag->pag_ici_lock);
+		rcu_read_unlock();
 		trace_xfs_iget_hit(ip);
 	}
 
@@ -275,7 +298,7 @@ xfs_iget_cache_hit(
 
 out_error:
 	spin_unlock(&ip->i_flags_lock);
-	read_unlock(&pag->pag_ici_lock);
+	rcu_read_unlock();
 	return error;
 }
 
@@ -397,7 +420,7 @@ xfs_iget(
 	xfs_agino_t	agino;
 
 	/* reject inode numbers outside existing AGs */
-	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
+	if (!ino || XFS_INO_TO_AGNO(mp, ino) >= mp->m_sb.sb_agcount)
 		return EINVAL;
 
 	/* get the perag structure and ensure that it's inode capable */
@@ -406,15 +429,15 @@ xfs_iget(
 
 again:
 	error = 0;
-	read_lock(&pag->pag_ici_lock);
+	rcu_read_lock();
 	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
 
 	if (ip) {
-		error = xfs_iget_cache_hit(pag, ip, flags, lock_flags);
+		error = xfs_iget_cache_hit(pag, ip, ino, flags, lock_flags);
 		if (error)
 			goto out_error_or_again;
 	} else {
-		read_unlock(&pag->pag_ici_lock);
+		rcu_read_unlock();
 		XFS_STATS_INC(xs_ig_missed);
 
 		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,