1 files changed, 65 insertions, 0 deletions

diff --git a/sys/contrib/openzfs/module/os/linux/zfs/zfs_vfsops.c b/sys/contrib/openzfs/module/os/linux/zfs/zfs_vfsops.c
index a3837f784668..396faef8f646 100644
--- a/sys/contrib/openzfs/module/os/linux/zfs/zfs_vfsops.c
+++ b/sys/contrib/openzfs/module/os/linux/zfs/zfs_vfsops.c
@@ -1217,6 +1217,63 @@ zfs_root(zfsvfs_t *zfsvfs, struct inode **ipp)
 }
 
 /*
+ * Dentry and inode caches referenced by a task in non-root memcg are
+ * not going to be scanned by the kernel-provided shrinker. So, if
+ * kernel prunes nothing, fall back to this manual walk to free dnodes.
+ * To avoid scanning the same znodes multiple times they are always rotated
+ * to the end of the z_all_znodes list. New znodes are inserted at the
+ * end of the list so we're always scanning the oldest znodes first.
+ */
+static int
+zfs_prune_aliases(zfsvfs_t *zfsvfs, unsigned long nr_to_scan)
+{
+	znode_t **zp_array, *zp;
+	int max_array = MIN(nr_to_scan, PAGE_SIZE * 8 / sizeof (znode_t *));
+	int objects = 0;
+	int i = 0, j = 0;
+
+	zp_array = vmem_zalloc(max_array * sizeof (znode_t *), KM_SLEEP);
+
+	mutex_enter(&zfsvfs->z_znodes_lock);
+	while ((zp = list_head(&zfsvfs->z_all_znodes)) != NULL) {
+
+		if ((i++ > nr_to_scan) || (j >= max_array))
+			break;
+
+		ASSERT(list_link_active(&zp->z_link_node));
+		list_remove(&zfsvfs->z_all_znodes, zp);
+		list_insert_tail(&zfsvfs->z_all_znodes, zp);
+
+		/* Skip active znodes and .zfs entries */
+		if (MUTEX_HELD(&zp->z_lock) || zp->z_is_ctldir)
+			continue;
+
+		if (igrab(ZTOI(zp)) == NULL)
+			continue;
+
+		zp_array[j] = zp;
+		j++;
+	}
+	mutex_exit(&zfsvfs->z_znodes_lock);
+
+	for (i = 0; i < j; i++) {
+		zp = zp_array[i];
+
+		ASSERT3P(zp, !=, NULL);
+		d_prune_aliases(ZTOI(zp));
+
+		if (atomic_read(&ZTOI(zp)->i_count) == 1)
+			objects++;
+
+		zrele(zp);
+	}
+
+	vmem_free(zp_array, max_array * sizeof (znode_t *));
+
+	return (objects);
+}
+
+/*
  * The ARC has requested that the filesystem drop entries from the dentry
  * and inode caches.  This can occur when the ARC needs to free meta data
  * blocks but can't because they are all pinned by entries in these caches.
@@ -1267,6 +1324,14 @@ zfs_prune(struct super_block *sb, unsigned long nr_to_scan, int *objects)
 	*objects = (*shrinker->scan_objects)(shrinker, &sc);
 #endif
 
+	/*
+	 * Fall back to zfs_prune_aliases if kernel's shrinker did nothing
+	 * due to dentry and inode caches being referenced by a task running
+	 * in non-root memcg.
+	 */
+	if (*objects == 0)
+		*objects = zfs_prune_aliases(zfsvfs, nr_to_scan);
+
 	zfs_exit(zfsvfs, FTAG);
 
 	dprintf_ds(zfsvfs->z_os->os_dsl_dataset,