Merge tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "This is the main pull request for block/storage for 4.21.

  Larger than usual, it was a busy round with lots of goodies queued up.
  Most notable is the removal of the old IO stack, which has been a long
  time coming. No new features for a while, everything coming in this
  week has all been fixes for things that were previously merged.

  This contains:

   - Use atomic counters instead of semaphores for mtip32xx (Arnd)

   - Cleanup of the mtip32xx request setup (Christoph)

   - Fix for circular locking dependency in loop (Jan, Tetsuo)

   - bcache (Coly, Guoju, Shenghui)
      * Optimizations for writeback caching
      * Various fixes and improvements

   - nvme (Chaitanya, Christoph, Sagi, Jay, me, Keith)
      * host and target support for NVMe over TCP
      * Error log page support
      * Support for separate read/write/poll queues
      * Much improved polling
      * discard OOM fallback
      * Tracepoint improvements

   - lightnvm (Hans, Hua, Igor, Matias, Javier)
      * Igor added packed metadata to pblk. Now drives without metadata
        per LBA can be used as well.
      * Fix from Geert on uninitialized value on chunk metadata reads.
      * Fixes from Hans and Javier to pblk recovery and write path.
      * Fix from Hua Su to fix a race condition in the pblk recovery
        code.
      * Scan optimization added to pblk recovery from Zhoujie.
      * Small geometry cleanup from me.

   - Conversion of the last few drivers that used the legacy path to
     blk-mq (me)

   - Removal of legacy IO path in SCSI (me, Christoph)

   - Removal of legacy IO stack and schedulers (me)

   - Support for much better polling, now without interrupts at all.
     blk-mq adds support for multiple queue maps, which enables us to
     have a map per type. This in turn enables nvme to have separate
     completion queues for polling, which can then be interrupt-less.
     Also means we're ready for async polled IO, which is hopefully
     coming in the next release.

   - Killing of (now) unused block exports (Christoph)

   - Unification of the blk-rq-qos and blk-wbt wait handling (Josef)

   - Support for zoned testing with null_blk (Masato)

   - sx8 conversion to per-host tag sets (Christoph)

   - IO priority improvements (Damien)

   - mq-deadline zoned fix (Damien)

   - Ref count blkcg series (Dennis)

   - Lots of blk-mq improvements and speedups (me)

   - sbitmap scalability improvements (me)

   - Make core inflight IO accounting per-cpu (Mikulas)

   - Export timeout setting in sysfs (Weiping)

   - Cleanup the direct issue path (Jianchao)

   - Export blk-wbt internals in block debugfs for easier debugging
     (Ming)

   - Lots of other fixes and improvements"

* tag 'for-4.21/block-20181221' of git://git.kernel.dk/linux-block: (364 commits)
  kyber: use sbitmap add_wait_queue/list_del wait helpers
  sbitmap: add helpers for add/del wait queue handling
  block: save irq state in blkg_lookup_create()
  dm: don't reuse bio for flushes
  nvme-pci: trace SQ status on completions
  nvme-rdma: implement polling queue map
  nvme-fabrics: allow user to pass in nr_poll_queues
  nvme-fabrics: allow nvmf_connect_io_queue to poll
  nvme-core: optionally poll sync commands
  block: make request_to_qc_t public
  nvme-tcp: fix spelling mistake "attepmpt" -> "attempt"
  nvme-tcp: fix endianess annotations
  nvmet-tcp: fix endianess annotations
  nvme-pci: refactor nvme_poll_irqdisable to make sparse happy
  nvme-pci: only set nr_maps to 2 if poll queues are supported
  nvmet: use a macro for default error location
  nvmet: fix comparison of a u16 with -1
  blk-mq: enable IO poll if .nr_queues of type poll > 0
  blk-mq: change blk_mq_queue_busy() to blk_mq_queue_inflight()
  blk-mq: skip zero-queue maps in blk_mq_map_swqueue
  ...

1 files changed, 14 insertions, 61 deletions

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 38c35c32aff2..fc714ef402a6 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -262,29 +262,25 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat,
 				   stat->rqs.mean);
 }
 
-static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
-				       wait_queue_entry_t *wait,
-				       bool first_block)
+static void iolat_cleanup_cb(struct rq_wait *rqw, void *private_data)
 {
-	struct rq_wait *rqw = &iolat->rq_wait;
+	atomic_dec(&rqw->inflight);
+	wake_up(&rqw->wait);
+}
 
-	if (first_block && waitqueue_active(&rqw->wait) &&
-	    rqw->wait.head.next != &wait->entry)
-		return false;
+static bool iolat_acquire_inflight(struct rq_wait *rqw, void *private_data)
+{
+	struct iolatency_grp *iolat = private_data;
 	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
 }
 
 static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
 				       struct iolatency_grp *iolat,
-				       spinlock_t *lock, bool issue_as_root,
+				       bool issue_as_root,
 				       bool use_memdelay)
-	__releases(lock)
-	__acquires(lock)
 {
 	struct rq_wait *rqw = &iolat->rq_wait;
 	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
-	DEFINE_WAIT(wait);
-	bool first_block = true;
 
 	if (use_delay)
 		blkcg_schedule_throttle(rqos->q, use_memdelay);
@@ -301,27 +297,7 @@ static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
 		return;
 	}
 
-	if (iolatency_may_queue(iolat, &wait, first_block))
-		return;
-
-	do {
-		prepare_to_wait_exclusive(&rqw->wait, &wait,
-					  TASK_UNINTERRUPTIBLE);
-
-		if (iolatency_may_queue(iolat, &wait, first_block))
-			break;
-		first_block = false;
-
-		if (lock) {
-			spin_unlock_irq(lock);
-			io_schedule();
-			spin_lock_irq(lock);
-		} else {
-			io_schedule();
-		}
-	} while (1);
-
-	finish_wait(&rqw->wait, &wait);
+	rq_qos_wait(rqw, iolat, iolat_acquire_inflight, iolat_cleanup_cb);
 }
 
 #define SCALE_DOWN_FACTOR 2
@@ -478,38 +454,15 @@ static void check_scale_change(struct iolatency_grp *iolat)
 	scale_change(iolat, direction > 0);
 }
 
-static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
-				     spinlock_t *lock)
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio)
 {
 	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
-	struct blkcg *blkcg;
-	struct blkcg_gq *blkg;
-	struct request_queue *q = rqos->q;
+	struct blkcg_gq *blkg = bio->bi_blkg;
 	bool issue_as_root = bio_issue_as_root_blkg(bio);
 
 	if (!blk_iolatency_enabled(blkiolat))
 		return;
 
-	rcu_read_lock();
-	blkcg = bio_blkcg(bio);
-	bio_associate_blkcg(bio, &blkcg->css);
-	blkg = blkg_lookup(blkcg, q);
-	if (unlikely(!blkg)) {
-		if (!lock)
-			spin_lock_irq(q->queue_lock);
-		blkg = blkg_lookup_create(blkcg, q);
-		if (IS_ERR(blkg))
-			blkg = NULL;
-		if (!lock)
-			spin_unlock_irq(q->queue_lock);
-	}
-	if (!blkg)
-		goto out;
-
-	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
-	bio_associate_blkg(bio, blkg);
-out:
-	rcu_read_unlock();
 	while (blkg && blkg->parent) {
 		struct iolatency_grp *iolat = blkg_to_lat(blkg);
 		if (!iolat) {
@@ -518,7 +471,7 @@ out:
 		}
 
 		check_scale_change(iolat);
-		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+		__blkcg_iolatency_throttle(rqos, iolat, issue_as_root,
 				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
 		blkg = blkg->parent;
 	}
@@ -640,7 +593,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
 	bool enabled = false;
 
 	blkg = bio->bi_blkg;
-	if (!blkg)
+	if (!blkg || !bio_flagged(bio, BIO_TRACKED))
 		return;
 
 	iolat = blkg_to_lat(bio->bi_blkg);
@@ -730,7 +683,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 		 * We could be exiting, don't access the pd unless we have a
 		 * ref on the blkg.
 		 */
-		if (!blkg_try_get(blkg))
+		if (!blkg_tryget(blkg))
 			continue;
 
 		iolat = blkg_to_lat(blkg);