Merge branch 'for-4.14/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the first pull request for 4.14, containing most of the code
  changes. It's a quiet series this round, which I think we needed after
  the churn of the last few series. This contains:

   - Fix for a registration race in loop, from Anton Volkov.

   - Overflow complaint fix from Arnd for DAC960.

   - Series of drbd changes from the usual suspects.

   - Conversion of the stec/skd driver to blk-mq. From Bart.

   - A few BFQ improvements/fixes from Paolo.

   - CFQ improvement from Ritesh, allowing idling for group idle.

   - A few fixes found by Dan's smatch, courtesy of Dan.

   - A warning fixup for a race between changing the IO scheduler and
     device remova. From David Jeffery.

   - A few nbd fixes from Josef.

   - Support for cgroup info in blktrace, from Shaohua.

   - Also from Shaohua, new features in the null_blk driver to allow it
     to actually hold data, among other things.

   - Various corner cases and error handling fixes from Weiping Zhang.

   - Improvements to the IO stats tracking for blk-mq from me. Can
     drastically improve performance for fast devices and/or big
     machines.

   - Series from Christoph removing bi_bdev as being needed for IO
     submission, in preparation for nvme multipathing code.

   - Series from Bart, including various cleanups and fixes for switch
     fall through case complaints"

* 'for-4.14/block' of git://git.kernel.dk/linux-block: (162 commits)
  kernfs: checking for IS_ERR() instead of NULL
  drbd: remove BIOSET_NEED_RESCUER flag from drbd_{md_,}io_bio_set
  drbd: Fix allyesconfig build, fix recent commit
  drbd: switch from kmalloc() to kmalloc_array()
  drbd: abort drbd_start_resync if there is no connection
  drbd: move global variables to drbd namespace and make some static
  drbd: rename "usermode_helper" to "drbd_usermode_helper"
  drbd: fix race between handshake and admin disconnect/down
  drbd: fix potential deadlock when trying to detach during handshake
  drbd: A single dot should be put into a sequence.
  drbd: fix rmmod cleanup, remove _all_ debugfs entries
  drbd: Use setup_timer() instead of init_timer() to simplify the code.
  drbd: fix potential get_ldev/put_ldev refcount imbalance during attach
  drbd: new disk-option disable-write-same
  drbd: Fix resource role for newly created resources in events2
  drbd: mark symbols static where possible
  drbd: Send P_NEG_ACK upon write error in protocol != C
  drbd: add explicit plugging when submitting batches
  drbd: change list_for_each_safe to while(list_first_entry_or_null)
  drbd: introduce drbd_recv_header_maybe_unplug
  ...

1 files changed, 49 insertions, 5 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4603b115e234..3f18cff80050 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -83,6 +83,41 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
 }
 
+struct mq_inflight {
+	struct hd_struct *part;
+	unsigned int *inflight;
+};
+
+static void blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
+				  struct request *rq, void *priv,
+				  bool reserved)
+{
+	struct mq_inflight *mi = priv;
+
+	if (test_bit(REQ_ATOM_STARTED, &rq->atomic_flags) &&
+	    !test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) {
+		/*
+		 * index[0] counts the specific partition that was asked
+		 * for. index[1] counts the ones that are active on the
+		 * whole device, so increment that if mi->part is indeed
+		 * a partition, and not a whole device.
+		 */
+		if (rq->part == mi->part)
+			mi->inflight[0]++;
+		if (mi->part->partno)
+			mi->inflight[1]++;
+	}
+}
+
+void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
+		      unsigned int inflight[2])
+{
+	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+
+	inflight[0] = inflight[1] = 0;
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+}
+
 void blk_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
@@ -624,11 +659,10 @@ static void blk_mq_requeue_work(struct work_struct *work)
 		container_of(work, struct request_queue, requeue_work.work);
 	LIST_HEAD(rq_list);
 	struct request *rq, *next;
-	unsigned long flags;
 
-	spin_lock_irqsave(&q->requeue_lock, flags);
+	spin_lock_irq(&q->requeue_lock);
 	list_splice_init(&q->requeue_list, &rq_list);
-	spin_unlock_irqrestore(&q->requeue_lock, flags);
+	spin_unlock_irq(&q->requeue_lock);
 
 	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
 		if (!(rq->rq_flags & RQF_SOFTBARRIER))
@@ -1102,9 +1136,19 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
 
+	/*
+	 * We should be running this queue from one of the CPUs that
+	 * are mapped to it.
+	 */
 	WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
 		cpu_online(hctx->next_cpu));
 
+	/*
+	 * We can't run the queue inline with ints disabled. Ensure that
+	 * we catch bad users of this early.
+	 */
+	WARN_ON_ONCE(in_interrupt());
+
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
 		blk_mq_sched_dispatch_requests(hctx);
@@ -1218,7 +1262,7 @@ EXPORT_SYMBOL(blk_mq_queue_stopped);
 /*
  * This function is often used for pausing .queue_rq() by driver when
  * there isn't enough resource or some conditions aren't satisfied, and
- * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ * BLK_STS_RESOURCE is usually returned.
  *
  * We do not guarantee that dispatch can be drained or blocked
  * after blk_mq_stop_hw_queue() returns. Please use
@@ -1235,7 +1279,7 @@ EXPORT_SYMBOL(blk_mq_stop_hw_queue);
 /*
  * This function is often used for pausing .queue_rq() by driver when
  * there isn't enough resource or some conditions aren't satisfied, and
- * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ * BLK_STS_RESOURCE is usually returned.
  *
  * We do not guarantee that dispatch can be drained or blocked
  * after blk_mq_stop_hw_queues() returns. Please use