block: generic request_queue reference counting

Allow pmem, and other synchronous/bio-based block drivers, to fallback
on a per-cpu reference count managed by the core for tracking queue
live/dead state.

The existing per-cpu reference count for the blk_mq case is promoted to
be used in all block i/o scenarios.  This involves initializing it by
default, waiting for it to drop to zero at exit, and holding a live
reference over the invocation of q->make_request_fn() in
generic_make_request().  The blk_mq code continues to take its own
reference per blk_mq request and retains the ability to freeze the
queue, but the check that the queue is frozen is moved to
generic_make_request().

This fixes crash signatures like the following:

 BUG: unable to handle kernel paging request at ffff880140000000
 [..]
 Call Trace:
  [<ffffffff8145e8bf>] ? copy_user_handle_tail+0x5f/0x70
  [<ffffffffa004e1e0>] pmem_do_bvec.isra.11+0x70/0xf0 [nd_pmem]
  [<ffffffffa004e331>] pmem_make_request+0xd1/0x200 [nd_pmem]
  [<ffffffff811c3162>] ? mempool_alloc+0x72/0x1a0
  [<ffffffff8141f8b6>] generic_make_request+0xd6/0x110
  [<ffffffff8141f966>] submit_bio+0x76/0x170
  [<ffffffff81286dff>] submit_bh_wbc+0x12f/0x160
  [<ffffffff81286e62>] submit_bh+0x12/0x20
  [<ffffffff813395bd>] jbd2_write_superblock+0x8d/0x170
  [<ffffffff8133974d>] jbd2_mark_journal_empty+0x5d/0x90
  [<ffffffff813399cb>] jbd2_journal_destroy+0x24b/0x270
  [<ffffffff810bc4ca>] ? put_pwq_unlocked+0x2a/0x30
  [<ffffffff810bc6f5>] ? destroy_workqueue+0x225/0x250
  [<ffffffff81303494>] ext4_put_super+0x64/0x360
  [<ffffffff8124ab1a>] generic_shutdown_super+0x6a/0xf0

Cc: Jens Axboe <axboe@kernel.dk>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

1 files changed, 62 insertions, 9 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 2eb722d48773..9b4d735cb5b8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -554,13 +554,10 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
-	if (q->mq_ops) {
-		blk_mq_freeze_queue(q);
-		spin_lock_irq(lock);
-	} else {
-		spin_lock_irq(lock);
+	blk_freeze_queue(q);
+	spin_lock_irq(lock);
+	if (!q->mq_ops)
 		__blk_drain_queue(q, true);
-	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
@@ -570,6 +567,7 @@ void blk_cleanup_queue(struct request_queue *q)
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
+	percpu_ref_exit(&q->q_usage_counter);
 
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
@@ -629,6 +627,40 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
+int blk_queue_enter(struct request_queue *q, gfp_t gfp)
+{
+	while (true) {
+		int ret;
+
+		if (percpu_ref_tryget_live(&q->q_usage_counter))
+			return 0;
+
+		if (!(gfp & __GFP_WAIT))
+			return -EBUSY;
+
+		ret = wait_event_interruptible(q->mq_freeze_wq,
+				!atomic_read(&q->mq_freeze_depth) ||
+				blk_queue_dying(q));
+		if (blk_queue_dying(q))
+			return -ENODEV;
+		if (ret)
+			return ret;
+	}
+}
+
+void blk_queue_exit(struct request_queue *q)
+{
+	percpu_ref_put(&q->q_usage_counter);
+}
+
+static void blk_queue_usage_counter_release(struct percpu_ref *ref)
+{
+	struct request_queue *q =
+		container_of(ref, struct request_queue, q_usage_counter);
+
+	wake_up_all(&q->mq_freeze_wq);
+}
+
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
@@ -690,11 +722,22 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	init_waitqueue_head(&q->mq_freeze_wq);
 
-	if (blkcg_init_queue(q))
+	/*
+	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
+	 * See blk_register_queue() for details.
+	 */
+	if (percpu_ref_init(&q->q_usage_counter,
+				blk_queue_usage_counter_release,
+				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto fail_bdi;
 
+	if (blkcg_init_queue(q))
+		goto fail_ref;
+
 	return q;
 
+fail_ref:
+	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
 fail_split:
@@ -1966,9 +2009,19 @@ void generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
-		q->make_request_fn(q, bio);
+		if (likely(blk_queue_enter(q, __GFP_WAIT) == 0)) {
+
+			q->make_request_fn(q, bio);
+
+			blk_queue_exit(q);
 
-		bio = bio_list_pop(current->bio_list);
+			bio = bio_list_pop(current->bio_list);
+		} else {
+			struct bio *bio_next = bio_list_pop(current->bio_list);
+
+			bio_io_error(bio);
+			bio = bio_next;
+		}
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 }