1 files changed, 70 insertions, 16 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 351849fc18ff..453890942d9f 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -435,18 +435,44 @@ xfs_iget_check_free_state(
 }
 
 /* Make all pending inactivation work start immediately. */
-static void
+static bool
 xfs_inodegc_queue_all(
 	struct xfs_mount	*mp)
 {
 	struct xfs_inodegc	*gc;
 	int			cpu;
+	bool			ret = false;
 
 	for_each_online_cpu(cpu) {
 		gc = per_cpu_ptr(mp->m_inodegc, cpu);
-		if (!llist_empty(&gc->list))
+		if (!llist_empty(&gc->list)) {
 			mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
+			ret = true;
+		}
+	}
+
+	return ret;
+}
+
+/* Wait for all queued work and collect errors */
+static int
+xfs_inodegc_wait_all(
+	struct xfs_mount	*mp)
+{
+	int			cpu;
+	int			error = 0;
+
+	flush_workqueue(mp->m_inodegc_wq);
+	for_each_online_cpu(cpu) {
+		struct xfs_inodegc	*gc;
+
+		gc = per_cpu_ptr(mp->m_inodegc, cpu);
+		if (gc->error && !error)
+			error = gc->error;
+		gc->error = 0;
 	}
+
+	return error;
 }
 
 /*
@@ -1486,15 +1512,14 @@ xfs_blockgc_free_space(
 	if (error)
 		return error;
 
-	xfs_inodegc_flush(mp);
-	return 0;
+	return xfs_inodegc_flush(mp);
 }
 
 /*
  * Reclaim all the free space that we can by scheduling the background blockgc
  * and inodegc workers immediately and waiting for them all to clear.
  */
-void
+int
 xfs_blockgc_flush_all(
 	struct xfs_mount	*mp)
 {
@@ -1515,7 +1540,7 @@ xfs_blockgc_flush_all(
 	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
 		flush_delayed_work(&pag->pag_blockgc_work);
 
-	xfs_inodegc_flush(mp);
+	return xfs_inodegc_flush(mp);
 }
 
 /*
@@ -1837,13 +1862,17 @@ xfs_inodegc_set_reclaimable(
  * This is the last chance to make changes to an otherwise unreferenced file
  * before incore reclamation happens.
  */
-static void
+static int
 xfs_inodegc_inactivate(
 	struct xfs_inode	*ip)
 {
+	int			error;
+
 	trace_xfs_inode_inactivating(ip);
-	xfs_inactive(ip);
+	error = xfs_inactive(ip);
 	xfs_inodegc_set_reclaimable(ip);
+	return error;
+
 }
 
 void
@@ -1856,6 +1885,8 @@ xfs_inodegc_worker(
 	struct xfs_inode	*ip, *n;
 	unsigned int		nofs_flag;
 
+	ASSERT(gc->cpu == smp_processor_id());
+
 	WRITE_ONCE(gc->items, 0);
 
 	if (!node)
@@ -1873,8 +1904,12 @@ xfs_inodegc_worker(
 
 	WRITE_ONCE(gc->shrinker_hits, 0);
 	llist_for_each_entry_safe(ip, n, node, i_gclist) {
+		int	error;
+
 		xfs_iflags_set(ip, XFS_INACTIVATING);
-		xfs_inodegc_inactivate(ip);
+		error = xfs_inodegc_inactivate(ip);
+		if (error && !gc->error)
+			gc->error = error;
 	}
 
 	memalloc_nofs_restore(nofs_flag);
@@ -1898,35 +1933,52 @@ xfs_inodegc_push(
  * Force all currently queued inode inactivation work to run immediately and
  * wait for the work to finish.
  */
-void
+int
 xfs_inodegc_flush(
 	struct xfs_mount	*mp)
 {
 	xfs_inodegc_push(mp);
 	trace_xfs_inodegc_flush(mp, __return_address);
-	flush_workqueue(mp->m_inodegc_wq);
+	return xfs_inodegc_wait_all(mp);
 }
 
 /*
  * Flush all the pending work and then disable the inode inactivation background
- * workers and wait for them to stop.
+ * workers and wait for them to stop.  Caller must hold sb->s_umount to
+ * coordinate changes in the inodegc_enabled state.
  */
 void
 xfs_inodegc_stop(
 	struct xfs_mount	*mp)
 {
+	bool			rerun;
+
 	if (!xfs_clear_inodegc_enabled(mp))
 		return;
 
+	/*
+	 * Drain all pending inodegc work, including inodes that could be
+	 * queued by racing xfs_inodegc_queue or xfs_inodegc_shrinker_scan
+	 * threads that sample the inodegc state just prior to us clearing it.
+	 * The inodegc flag state prevents new threads from queuing more
+	 * inodes, so we queue pending work items and flush the workqueue until
+	 * all inodegc lists are empty.  IOWs, we cannot use drain_workqueue
+	 * here because it does not allow other unserialized mechanisms to
+	 * reschedule inodegc work while this draining is in progress.
+	 */
 	xfs_inodegc_queue_all(mp);
-	drain_workqueue(mp->m_inodegc_wq);
+	do {
+		flush_workqueue(mp->m_inodegc_wq);
+		rerun = xfs_inodegc_queue_all(mp);
+	} while (rerun);
 
 	trace_xfs_inodegc_stop(mp, __return_address);
 }
 
 /*
  * Enable the inode inactivation background workers and schedule deferred inode
- * inactivation work if there is any.
+ * inactivation work if there is any.  Caller must hold sb->s_umount to
+ * coordinate changes in the inodegc_enabled state.
  */
 void
 xfs_inodegc_start(
@@ -2069,7 +2121,8 @@ xfs_inodegc_queue(
 		queue_delay = 0;
 
 	trace_xfs_inodegc_queue(mp, __return_address);
-	mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay);
+	mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
+			queue_delay);
 	put_cpu_ptr(gc);
 
 	if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) {
@@ -2113,7 +2166,8 @@ xfs_inodegc_cpu_dead(
 
 	if (xfs_is_inodegc_enabled(mp)) {
 		trace_xfs_inodegc_queue(mp, __return_address);
-		mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0);
+		mod_delayed_work_on(current_cpu(), mp->m_inodegc_wq, &gc->work,
+				0);
 	}
 	put_cpu_ptr(gc);
 }