Merge tag 'for-4.15/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper fixes from Mike Snitzer:

 - fix a particularly nasty DM core bug in a 4.15 refcount_t conversion.

 - fix various targets to dm_register_target after module __init
   resources created; otherwise racing lvm2 commands could result in a
   NULL pointer during initialization of associated DM kernel module.

 - fix regression in bio-based DM multipath queue_if_no_path handling.

 - fix DM bufio's shrinker to reclaim more than one buffer per scan.

* tag 'for-4.15/dm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm bufio: fix shrinker scans when (nr_to_scan < retain_target)
  dm mpath: fix bio-based multipath queue_if_no_path handling
  dm: fix various targets to dm_register_target after module __init resources created
  dm table: fix regression from improper dm_dev_internal.count refcount_t conversion

drivers/md/dm-bufio.c

@@ -1611,7 +1611,8 @@ static unsigned long __scan(struct dm_bufio_client *c, unsigned long nr_to_scan,
 	int l;
 	struct dm_buffer *b, *tmp;
 	unsigned long freed = 0;
-	unsigned long count = nr_to_scan;
+	unsigned long count = c->n_buffers[LIST_CLEAN] +
+			      c->n_buffers[LIST_DIRTY];
 	unsigned long retain_target = get_retain_buffers(c);
 
 	for (l = 0; l < LIST_SIZE; l++) {
@@ -1647,8 +1648,11 @@ static unsigned long
 dm_bufio_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct dm_bufio_client *c = container_of(shrink, struct dm_bufio_client, shrinker);
+	unsigned long count = READ_ONCE(c->n_buffers[LIST_CLEAN]) +
+			      READ_ONCE(c->n_buffers[LIST_DIRTY]);
+	unsigned long retain_target = get_retain_buffers(c);
 
-	return READ_ONCE(c->n_buffers[LIST_CLEAN]) + READ_ONCE(c->n_buffers[LIST_DIRTY]);
+	return (count < retain_target) ? 0 : (count - retain_target);
 }
 
 /*

drivers/md/dm-cache-target.c

@@ -3472,18 +3472,18 @@ static int __init dm_cache_init(void)
 {
 	int r;
 
-	r = dm_register_target(&cache_target);
-	if (r) {
-		DMERR("cache target registration failed: %d", r);
-		return r;
-	}
-
 	migration_cache = KMEM_CACHE(dm_cache_migration, 0);
 	if (!migration_cache) {
 		dm_unregister_target(&cache_target);
 		return -ENOMEM;
 	}
 
+	r = dm_register_target(&cache_target);
+	if (r) {
+		DMERR("cache target registration failed: %d", r);
+		return r;
+	}
+
 	return 0;
 }
 

drivers/md/dm-mpath.c

@@ -457,6 +457,38 @@ do {									\
 		 dm_noflush_suspending((m)->ti));			\
 } while (0)
 
+/*
+ * Check whether bios must be queued in the device-mapper core rather
+ * than here in the target.
+ *
+ * If MPATHF_QUEUE_IF_NO_PATH and MPATHF_SAVED_QUEUE_IF_NO_PATH hold
+ * the same value then we are not between multipath_presuspend()
+ * and multipath_resume() calls and we have no need to check
+ * for the DMF_NOFLUSH_SUSPENDING flag.
+ */
+static bool __must_push_back(struct multipath *m, unsigned long flags)
+{
+	return ((test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) !=
+		 test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &flags)) &&
+		dm_noflush_suspending(m->ti));
+}
+
+/*
+ * Following functions use READ_ONCE to get atomic access to
+ * all m->flags to avoid taking spinlock
+ */
+static bool must_push_back_rq(struct multipath *m)
+{
+	unsigned long flags = READ_ONCE(m->flags);
+	return test_bit(MPATHF_QUEUE_IF_NO_PATH, &flags) || __must_push_back(m, flags);
+}
+
+static bool must_push_back_bio(struct multipath *m)
+{
+	unsigned long flags = READ_ONCE(m->flags);
+	return __must_push_back(m, flags);
+}
+
 /*
  * Map cloned requests (request-based multipath)
  */
@@ -478,7 +510,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
 		pgpath = choose_pgpath(m, nr_bytes);
 
 	if (!pgpath) {
-		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
+		if (must_push_back_rq(m))
 			return DM_MAPIO_DELAY_REQUEUE;
 		dm_report_EIO(m);	/* Failed */
 		return DM_MAPIO_KILL;
@@ -553,7 +585,7 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 	}
 
 	if (!pgpath) {
-		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
+		if (must_push_back_bio(m))
 			return DM_MAPIO_REQUEUE;
 		dm_report_EIO(m);
 		return DM_MAPIO_KILL;
@@ -651,8 +683,7 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 	assign_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags,
 		   (save_old_value && test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) ||
 		   (!save_old_value && queue_if_no_path));
-	assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags,
-		   queue_if_no_path || dm_noflush_suspending(m->ti));
+	assign_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags, queue_if_no_path);
 	spin_unlock_irqrestore(&m->lock, flags);
 
 	if (!queue_if_no_path) {
@@ -1486,7 +1517,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 			fail_path(pgpath);
 
 		if (atomic_read(&m->nr_valid_paths) == 0 &&
-		    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
+		    !must_push_back_rq(m)) {
 			if (error == BLK_STS_IOERR)
 				dm_report_EIO(m);
 			/* complete with the original error */
@@ -1521,8 +1552,12 @@ static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone,
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
 	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
-		dm_report_EIO(m);
-		*error = BLK_STS_IOERR;
+		if (must_push_back_bio(m)) {
+			r = DM_ENDIO_REQUEUE;
+		} else {
+			dm_report_EIO(m);
+			*error = BLK_STS_IOERR;
+		}
 		goto done;
 	}
 
@@ -1957,13 +1992,6 @@ static int __init dm_multipath_init(void)
 {
 	int r;
 
-	r = dm_register_target(&multipath_target);
-	if (r < 0) {
-		DMERR("request-based register failed %d", r);
-		r = -EINVAL;
-		goto bad_register_target;
-	}
-
 	kmultipathd = alloc_workqueue("kmpathd", WQ_MEM_RECLAIM, 0);
 	if (!kmultipathd) {
 		DMERR("failed to create workqueue kmpathd");
@@ -1985,13 +2013,20 @@ static int __init dm_multipath_init(void)
 		goto bad_alloc_kmpath_handlerd;
 	}
 
+	r = dm_register_target(&multipath_target);
+	if (r < 0) {
+		DMERR("request-based register failed %d", r);
+		r = -EINVAL;
+		goto bad_register_target;
+	}
+
 	return 0;
 
+bad_register_target:
+	destroy_workqueue(kmpath_handlerd);
 bad_alloc_kmpath_handlerd:
 	destroy_workqueue(kmultipathd);
 bad_alloc_kmultipathd:
-	dm_unregister_target(&multipath_target);
-bad_register_target:
 	return r;
 }
 

drivers/md/dm-snap.c

@@ -2411,24 +2411,6 @@ static int __init dm_snapshot_init(void)
 		return r;
 	}
 
-	r = dm_register_target(&snapshot_target);
-	if (r < 0) {
-		DMERR("snapshot target register failed %d", r);
-		goto bad_register_snapshot_target;
-	}
-
-	r = dm_register_target(&origin_target);
-	if (r < 0) {
-		DMERR("Origin target register failed %d", r);
-		goto bad_register_origin_target;
-	}
-
-	r = dm_register_target(&merge_target);
-	if (r < 0) {
-		DMERR("Merge target register failed %d", r);
-		goto bad_register_merge_target;
-	}
-
 	r = init_origin_hash();
 	if (r) {
 		DMERR("init_origin_hash failed.");
@@ -2449,19 +2431,37 @@ static int __init dm_snapshot_init(void)
 		goto bad_pending_cache;
 	}
 
+	r = dm_register_target(&snapshot_target);
+	if (r < 0) {
+		DMERR("snapshot target register failed %d", r);
+		goto bad_register_snapshot_target;
+	}
+
+	r = dm_register_target(&origin_target);
+	if (r < 0) {
+		DMERR("Origin target register failed %d", r);
+		goto bad_register_origin_target;
+	}
+
+	r = dm_register_target(&merge_target);
+	if (r < 0) {
+		DMERR("Merge target register failed %d", r);
+		goto bad_register_merge_target;
+	}
+
 	return 0;
 
-bad_pending_cache:
-	kmem_cache_destroy(exception_cache);
-bad_exception_cache:
-	exit_origin_hash();
-bad_origin_hash:
-	dm_unregister_target(&merge_target);
 bad_register_merge_target:
 	dm_unregister_target(&origin_target);
 bad_register_origin_target:
 	dm_unregister_target(&snapshot_target);
 bad_register_snapshot_target:
+	kmem_cache_destroy(pending_cache);
+bad_pending_cache:
+	kmem_cache_destroy(exception_cache);
+bad_exception_cache:
+	exit_origin_hash();
+bad_origin_hash:
 	dm_exception_store_exit();
 
 	return r;

drivers/md/dm-table.c

@@ -453,14 +453,15 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
 
 		refcount_set(&dd->count, 1);
 		list_add(&dd->list, &t->devices);
+		goto out;
 
 	} else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) {
 		r = upgrade_mode(dd, mode, t->md);
 		if (r)
 			return r;
-		refcount_inc(&dd->count);
 	}
-
+	refcount_inc(&dd->count);
+out:
 	*result = dd->dm_dev;
 	return 0;
 }

drivers/md/dm-thin.c

@@ -4355,30 +4355,28 @@ static struct target_type thin_target = {
 
 static int __init dm_thin_init(void)
 {
-	int r;
+	int r = -ENOMEM;
 
 	pool_table_init();
 
+	_new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0);
+	if (!_new_mapping_cache)
+		return r;
+
 	r = dm_register_target(&thin_target);
 	if (r)
-		return r;
+		goto bad_new_mapping_cache;
 
 	r = dm_register_target(&pool_target);
 	if (r)
-		goto bad_pool_target;
-
-	r = -ENOMEM;
-
-	_new_mapping_cache = KMEM_CACHE(dm_thin_new_mapping, 0);
-	if (!_new_mapping_cache)
-		goto bad_new_mapping_cache;
+		goto bad_thin_target;
 
 	return 0;
 
-bad_new_mapping_cache:
-	dm_unregister_target(&pool_target);
-bad_pool_target:
+bad_thin_target:
 	dm_unregister_target(&thin_target);
+bad_new_mapping_cache:
+	kmem_cache_destroy(_new_mapping_cache);
 
 	return r;
 }