[PATCH RFC 2/4] xfs: tag reclaimable inodes with pending RCU grace periods as busy

[Brian Foster <bfoster@xxxxxxxxxx>]

In order to avoid aggressive recycling of in-core xfs_inode objects with
pending grace periods and the subsequent RCU sync stalls involved with
recycling, we must be able to identify them quickly and reliably at
allocation time. Claim a new tag for the in-core inode radix tree and
tag all inodes with a still pending grace period cookie as busy at the
time they are made reclaimable.

Note that it is not necessary to maintain consistency between the tag
and grace period status once the tag is set. The busy tag simply
reflects that the grace period had not expired by the time the inode was
set reclaimable and therefore any reuse of the inode must first poll the
RCU subsystem for subsequent expiration of the grace period. Clear the
tag when the inode is recycled or reclaimed.

Signed-off-by: Brian Foster <bfoster@xxxxxxxxxx>
---
 fs/xfs/xfs_icache.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 693896bc690f..245ee0f6670b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -32,6 +32,8 @@
 #define XFS_ICI_RECLAIM_TAG	0
 /* Inode has speculative preallocations (posteof or cow) to clean. */
 #define XFS_ICI_BLOCKGC_TAG	1
+/* inode has pending RCU grace period when set reclaimable  */
+#define XFS_ICI_BUSY_TAG	2
 
 /*
  * The goal for walking incore inodes.  These can correspond with incore inode
@@ -274,7 +276,7 @@ xfs_perag_clear_inode_tag(
 	if (agino != NULLAGINO)
 		radix_tree_tag_clear(&pag->pag_ici_root, agino, tag);
 	else
-		ASSERT(tag == XFS_ICI_RECLAIM_TAG);
+		ASSERT(tag == XFS_ICI_RECLAIM_TAG || tag == XFS_ICI_BUSY_TAG);
 
 	if (tag == XFS_ICI_RECLAIM_TAG)
 		pag->pag_ici_reclaimable--;
@@ -336,6 +338,7 @@ xfs_iget_recycle(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
 	int			error;
 
 	trace_xfs_iget_recycle(ip);
@@ -392,8 +395,9 @@ xfs_iget_recycle(
 	 */
 	ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
 	ip->i_flags |= XFS_INEW;
-	xfs_perag_clear_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino),
-			XFS_ICI_RECLAIM_TAG);
+
+	xfs_perag_clear_inode_tag(pag, agino, XFS_ICI_BUSY_TAG);
+	xfs_perag_clear_inode_tag(pag, agino, XFS_ICI_RECLAIM_TAG);
 	inode->i_state = I_NEW;
 	spin_unlock(&ip->i_flags_lock);
 	spin_unlock(&pag->pag_ici_lock);
@@ -931,6 +935,7 @@ xfs_reclaim_inode(
 	if (!radix_tree_delete(&pag->pag_ici_root,
 				XFS_INO_TO_AGINO(ip->i_mount, ino)))
 		ASSERT(0);
+	xfs_perag_clear_inode_tag(pag, NULLAGINO, XFS_ICI_BUSY_TAG);
 	xfs_perag_clear_inode_tag(pag, NULLAGINO, XFS_ICI_RECLAIM_TAG);
 	spin_unlock(&pag->pag_ici_lock);
 
@@ -1807,6 +1812,7 @@ xfs_inodegc_set_reclaimable(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_perag	*pag;
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
 
 	if (!xfs_is_shutdown(mp) && ip->i_delayed_blks) {
 		xfs_check_delalloc(ip, XFS_DATA_FORK);
@@ -1821,10 +1827,12 @@ xfs_inodegc_set_reclaimable(
 	trace_xfs_inode_set_reclaimable(ip);
 	if (destroy_gp)
 		ip->i_destroy_gp = destroy_gp;
+	if (!poll_state_synchronize_rcu(ip->i_destroy_gp))
+		xfs_perag_set_inode_tag(pag, agino, XFS_ICI_BUSY_TAG);
+
 	ip->i_flags &= ~(XFS_NEED_INACTIVE | XFS_INACTIVATING);
 	ip->i_flags |= XFS_IRECLAIMABLE;
-	xfs_perag_set_inode_tag(pag, XFS_INO_TO_AGINO(mp, ip->i_ino),
-			XFS_ICI_RECLAIM_TAG);
+	xfs_perag_set_inode_tag(pag, agino, XFS_ICI_RECLAIM_TAG);
 
 	spin_unlock(&ip->i_flags_lock);
 	spin_unlock(&pag->pag_ici_lock);
-- 
2.31.1