1 files changed, 70 insertions, 7 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ef7bf1dd6900..c5522551122f 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -21,6 +21,7 @@
 #include <linux/delay.h>
 #include <linux/wait.h>
 #include <linux/pr.h>
+#include <linux/vmalloc.h>
 
 #define DM_MSG_PREFIX "core"
 
@@ -972,10 +973,64 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
+/*
+ * Flush current->bio_list when the target map method blocks.
+ * This fixes deadlocks in snapshot and possibly in other targets.
+ */
+struct dm_offload {
+	struct blk_plug plug;
+	struct blk_plug_cb cb;
+};
+
+static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
+	struct bio_list list;
+	struct bio *bio;
+	int i;
+
+	INIT_LIST_HEAD(&o->cb.list);
+
+	if (unlikely(!current->bio_list))
+		return;
+
+	for (i = 0; i < 2; i++) {
+		list = current->bio_list[i];
+		bio_list_init(&current->bio_list[i]);
+
+		while ((bio = bio_list_pop(&list))) {
+			struct bio_set *bs = bio->bi_pool;
+			if (unlikely(!bs) || bs == fs_bio_set) {
+				bio_list_add(&current->bio_list[i], bio);
+				continue;
+			}
+
+			spin_lock(&bs->rescue_lock);
+			bio_list_add(&bs->rescue_list, bio);
+			queue_work(bs->rescue_workqueue, &bs->rescue_work);
+			spin_unlock(&bs->rescue_lock);
+		}
+	}
+}
+
+static void dm_offload_start(struct dm_offload *o)
+{
+	blk_start_plug(&o->plug);
+	o->cb.callback = flush_current_bio_list;
+	list_add(&o->cb.list, &current->plug->cb_list);
+}
+
+static void dm_offload_end(struct dm_offload *o)
+{
+	list_del(&o->cb.list);
+	blk_finish_plug(&o->plug);
+}
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
 	sector_t sector;
+	struct dm_offload o;
 	struct bio *clone = &tio->clone;
 	struct dm_target *ti = tio->ti;
 
@@ -988,7 +1043,11 @@ static void __map_bio(struct dm_target_io *tio)
 	 */
 	atomic_inc(&tio->io->io_count);
 	sector = clone->bi_iter.bi_sector;
+
+	dm_offload_start(&o);
 	r = ti->type->map(ti, clone);
+	dm_offload_end(&o);
+
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
 
@@ -1453,7 +1512,7 @@ static struct mapped_device *alloc_dev(int minor)
 	struct mapped_device *md;
 	void *old_md;
 
-	md = kzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id);
+	md = vzalloc_node(sizeof(*md), numa_node_id);
 	if (!md) {
 		DMWARN("unable to allocate device, out of memory.");
 		return NULL;
@@ -1547,7 +1606,7 @@ bad_io_barrier:
 bad_minor:
 	module_put(THIS_MODULE);
 bad_module_get:
-	kfree(md);
+	kvfree(md);
 	return NULL;
 }
 
@@ -1566,7 +1625,7 @@ static void free_dev(struct mapped_device *md)
 	free_minor(minor);
 
 	module_put(THIS_MODULE);
-	kfree(md);
+	kvfree(md);
 }
 
 static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
@@ -2456,11 +2515,15 @@ struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 
 	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
-	if (test_bit(DMF_FREEING, &md->flags) ||
-	    dm_deleting_md(md))
-		return NULL;
-
+	spin_lock(&_minor_lock);
+	if (test_bit(DMF_FREEING, &md->flags) || dm_deleting_md(md)) {
+		md = NULL;
+		goto out;
+	}
 	dm_get(md);
+out:
+	spin_unlock(&_minor_lock);
+
 	return md;
 }