blk: Ensure users for current->bio_list can see the full list.

commit f5fe1b51 upstream.

Commit 79bd9959 ("blk: improve order of bio handling in generic_make_request()")
changed current->bio_list so that it did not contain *all* of the
queued bios, but only those submitted by the currently running
make_request_fn.

There are two places which walk the list and requeue selected bios,
and others that check if the list is empty.  These are no longer
correct.

So redefine current->bio_list to point to an array of two lists, which
contain all queued bios, and adjust various code to test or walk both
lists.
Signed-off-by: NeilBrown <neilb@suse.com>
Fixes: 79bd9959 ("blk: improve order of bio handling in generic_make_request()")
Signed-off-by: Jens Axboe <axboe@fb.com>
[jwang: backport to 4.4]
Signed-off-by: Jack Wang <jinpu.wang@profitbricks.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[bwh: Restore changes in device-mapper from upstream version]
Signed-off-by: Ben Hutchings <ben.hutchings@codethink.co.uk>

block/bio.c

@@ -373,10 +373,14 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	bio_list_init(&punt);
 	bio_list_init(&nopunt);
 
-	while ((bio = bio_list_pop(current->bio_list)))
+	while ((bio = bio_list_pop(&current->bio_list[0])))
 		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[0] = nopunt;
 
-	*current->bio_list = nopunt;
+	bio_list_init(&nopunt);
+	while ((bio = bio_list_pop(&current->bio_list[1])))
+		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
+	current->bio_list[1] = nopunt;
 
 	spin_lock(&bs->rescue_lock);
 	bio_list_merge(&bs->rescue_list, &punt);
@@ -464,7 +468,9 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
 		 * we retry with the original gfp_flags.
 		 */
 
-		if (current->bio_list && !bio_list_empty(current->bio_list))
+		if (current->bio_list &&
+		    (!bio_list_empty(&current->bio_list[0]) ||
+		     !bio_list_empty(&current->bio_list[1])))
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);

block/blk-core.c

@@ -2021,7 +2021,14 @@ generic_make_request_checks(struct bio *bio)
  */
 blk_qc_t generic_make_request(struct bio *bio)
 {
-	struct bio_list bio_list_on_stack;
+	/*
+	 * bio_list_on_stack[0] contains bios submitted by the current
+	 * make_request_fn.
+	 * bio_list_on_stack[1] contains bios that were submitted before
+	 * the current make_request_fn, but that haven't been processed
+	 * yet.
+	 */
+	struct bio_list bio_list_on_stack[2];
 	blk_qc_t ret = BLK_QC_T_NONE;
 
 	if (!generic_make_request_checks(bio))
@@ -2038,7 +2045,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * should be added at the tail
 	 */
 	if (current->bio_list) {
-		bio_list_add(current->bio_list, bio);
+		bio_list_add(&current->bio_list[0], bio);
 		goto out;
 	}
 
@@ -2057,17 +2064,17 @@ blk_qc_t generic_make_request(struct bio *bio)
 	 * bio_list, and call into ->make_request() again.
 	 */
 	BUG_ON(bio->bi_next);
-	bio_list_init(&bio_list_on_stack);
-	current->bio_list = &bio_list_on_stack;
+	bio_list_init(&bio_list_on_stack[0]);
+	current->bio_list = bio_list_on_stack;
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
 		if (likely(blk_queue_enter(q, __GFP_DIRECT_RECLAIM) == 0)) {
-			struct bio_list lower, same, hold;
+			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
-			hold = bio_list_on_stack;
-			bio_list_init(&bio_list_on_stack);
+			bio_list_on_stack[1] = bio_list_on_stack[0];
+			bio_list_init(&bio_list_on_stack[0]);
 
 			ret = q->make_request_fn(q, bio);
 
@@ -2077,19 +2084,19 @@ blk_qc_t generic_make_request(struct bio *bio)
 			 */
 			bio_list_init(&lower);
 			bio_list_init(&same);
-			while ((bio = bio_list_pop(&bio_list_on_stack)) != NULL)
+			while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL)
 				if (q == bdev_get_queue(bio->bi_bdev))
 					bio_list_add(&same, bio);
 				else
 					bio_list_add(&lower, bio);
 			/* now assemble so we handle the lowest level first */
-			bio_list_merge(&bio_list_on_stack, &lower);
-			bio_list_merge(&bio_list_on_stack, &same);
-			bio_list_merge(&bio_list_on_stack, &hold);
+			bio_list_merge(&bio_list_on_stack[0], &lower);
+			bio_list_merge(&bio_list_on_stack[0], &same);
+			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
 			bio_io_error(bio);
 		}
-		bio = bio_list_pop(current->bio_list);
+		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 

drivers/md/dm.c

@@ -1481,26 +1481,29 @@ 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;
 
-	list = *current->bio_list;
-	bio_list_init(current->bio_list);
-
-	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, bio);
-			continue;
+	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);
 		}
-
-		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);
 	}
 }
 

drivers/md/raid1.c

@@ -877,7 +877,8 @@ static sector_t wait_barrier(struct r1conf *conf, struct bio *bio)
 				     ((conf->start_next_window <
 				       conf->next_resync + RESYNC_SECTORS) &&
 				      current->bio_list &&
-				      !bio_list_empty(current->bio_list))),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1])))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}

drivers/md/raid10.c

@@ -946,7 +946,8 @@ static void wait_barrier(struct r10conf *conf)
 				    !conf->barrier ||
 				    (conf->nr_pending &&
 				     current->bio_list &&
-				     !bio_list_empty(current->bio_list)),
+				     (!bio_list_empty(&current->bio_list[0]) ||
+				      !bio_list_empty(&current->bio_list[1]))),
 				    conf->resync_lock);
 		conf->nr_waiting--;
 	}