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, 40 deletions

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 01580f88fcb3..5ed59ac6ae58 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -28,7 +28,6 @@ void get_io_context(struct io_context *ioc)
 	BUG_ON(atomic_long_read(&ioc->refcount) <= 0);
 	atomic_long_inc(&ioc->refcount);
 }
-EXPORT_SYMBOL(get_io_context);
 
 static void icq_free_icq_rcu(struct rcu_head *head)
 {
@@ -48,10 +47,8 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->uses_mq && et->ops.mq.exit_icq)
-		et->ops.mq.exit_icq(icq);
-	else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
-		et->ops.sq.elevator_exit_icq_fn(icq);
+	if (et->ops.exit_icq)
+		et->ops.exit_icq(icq);
 
 	icq->flags |= ICQ_EXITED;
 }
@@ -113,9 +110,9 @@ static void ioc_release_fn(struct work_struct *work)
 						struct io_cq, ioc_node);
 		struct request_queue *q = icq->q;
 
-		if (spin_trylock(q->queue_lock)) {
+		if (spin_trylock(&q->queue_lock)) {
 			ioc_destroy_icq(icq);
-			spin_unlock(q->queue_lock);
+			spin_unlock(&q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
 			cpu_relax();
@@ -162,7 +159,6 @@ void put_io_context(struct io_context *ioc)
 	if (free_ioc)
 		kmem_cache_free(iocontext_cachep, ioc);
 }
-EXPORT_SYMBOL(put_io_context);
 
 /**
  * put_io_context_active - put active reference on ioc
@@ -173,7 +169,6 @@ EXPORT_SYMBOL(put_io_context);
  */
 void put_io_context_active(struct io_context *ioc)
 {
-	struct elevator_type *et;
 	unsigned long flags;
 	struct io_cq *icq;
 
@@ -187,25 +182,12 @@ void put_io_context_active(struct io_context *ioc)
 	 * reverse double locking.  Read comment in ioc_release_fn() for
 	 * explanation on the nested locking annotation.
 	 */
-retry:
 	spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 	hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
 		if (icq->flags & ICQ_EXITED)
 			continue;
 
-		et = icq->q->elevator->type;
-		if (et->uses_mq) {
-			ioc_exit_icq(icq);
-		} else {
-			if (spin_trylock(icq->q->queue_lock)) {
-				ioc_exit_icq(icq);
-				spin_unlock(icq->q->queue_lock);
-			} else {
-				spin_unlock_irqrestore(&ioc->lock, flags);
-				cpu_relax();
-				goto retry;
-			}
-		}
+		ioc_exit_icq(icq);
 	}
 	spin_unlock_irqrestore(&ioc->lock, flags);
 
@@ -232,7 +214,7 @@ static void __ioc_clear_queue(struct list_head *icq_list)
 
 	while (!list_empty(icq_list)) {
 		struct io_cq *icq = list_entry(icq_list->next,
-					       struct io_cq, q_node);
+						struct io_cq, q_node);
 		struct io_context *ioc = icq->ioc;
 
 		spin_lock_irqsave(&ioc->lock, flags);
@@ -251,16 +233,11 @@ void ioc_clear_queue(struct request_queue *q)
 {
 	LIST_HEAD(icq_list);
 
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	list_splice_init(&q->icq_list, &icq_list);
+	spin_unlock_irq(&q->queue_lock);
 
-	if (q->mq_ops) {
-		spin_unlock_irq(q->queue_lock);
-		__ioc_clear_queue(&icq_list);
-	} else {
-		__ioc_clear_queue(&icq_list);
-		spin_unlock_irq(q->queue_lock);
-	}
+	__ioc_clear_queue(&icq_list);
 }
 
 int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
@@ -336,7 +313,6 @@ struct io_context *get_task_io_context(struct task_struct *task,
 
 	return NULL;
 }
-EXPORT_SYMBOL(get_task_io_context);
 
 /**
  * ioc_lookup_icq - lookup io_cq from ioc
@@ -350,7 +326,7 @@ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q)
 {
 	struct io_cq *icq;
 
-	lockdep_assert_held(q->queue_lock);
+	lockdep_assert_held(&q->queue_lock);
 
 	/*
 	 * icq's are indexed from @ioc using radix tree and hint pointer,
@@ -409,16 +385,14 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	INIT_HLIST_NODE(&icq->ioc_node);
 
 	/* lock both q and ioc and try to link @icq */
-	spin_lock_irq(q->queue_lock);
+	spin_lock_irq(&q->queue_lock);
 	spin_lock(&ioc->lock);
 
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->uses_mq && et->ops.mq.init_icq)
-			et->ops.mq.init_icq(icq);
-		else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
-			et->ops.sq.elevator_init_icq_fn(icq);
+		if (et->ops.init_icq)
+			et->ops.init_icq(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);
 		icq = ioc_lookup_icq(ioc, q);
@@ -427,7 +401,7 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	}
 
 	spin_unlock(&ioc->lock);
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock_irq(&q->queue_lock);
 	radix_tree_preload_end();
 	return icq;
 }