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, 11 insertions, 106 deletions

diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index f2cfd56e1606..124c26128bf6 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -68,80 +68,6 @@ ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
 
 #endif /* CONFIG_FAIL_IO_TIMEOUT */
 
-/*
- * blk_delete_timer - Delete/cancel timer for a given function.
- * @req:	request that we are canceling timer for
- *
- */
-void blk_delete_timer(struct request *req)
-{
-	list_del_init(&req->timeout_list);
-}
-
-static void blk_rq_timed_out(struct request *req)
-{
-	struct request_queue *q = req->q;
-	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
-
-	if (q->rq_timed_out_fn)
-		ret = q->rq_timed_out_fn(req);
-	switch (ret) {
-	case BLK_EH_RESET_TIMER:
-		blk_add_timer(req);
-		blk_clear_rq_complete(req);
-		break;
-	case BLK_EH_DONE:
-		/*
-		 * LLD handles this for now but in the future
-		 * we can send a request msg to abort the command
-		 * and we can move more of the generic scsi eh code to
-		 * the blk layer.
-		 */
-		break;
-	default:
-		printk(KERN_ERR "block: bad eh return: %d\n", ret);
-		break;
-	}
-}
-
-static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
-			  unsigned int *next_set)
-{
-	const unsigned long deadline = blk_rq_deadline(rq);
-
-	if (time_after_eq(jiffies, deadline)) {
-		list_del_init(&rq->timeout_list);
-
-		/*
-		 * Check if we raced with end io completion
-		 */
-		if (!blk_mark_rq_complete(rq))
-			blk_rq_timed_out(rq);
-	} else if (!*next_set || time_after(*next_timeout, deadline)) {
-		*next_timeout = deadline;
-		*next_set = 1;
-	}
-}
-
-void blk_timeout_work(struct work_struct *work)
-{
-	struct request_queue *q =
-		container_of(work, struct request_queue, timeout_work);
-	unsigned long flags, next = 0;
-	struct request *rq, *tmp;
-	int next_set = 0;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-
-	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
-		blk_rq_check_expired(rq, &next, &next_set);
-
-	if (next_set)
-		mod_timer(&q->timeout, round_jiffies_up(next));
-
-	spin_unlock_irqrestore(q->queue_lock, flags);
-}
-
 /**
  * blk_abort_request -- Request request recovery for the specified command
  * @req:	pointer to the request of interest
@@ -149,24 +75,17 @@ void blk_timeout_work(struct work_struct *work)
  * This function requests that the block layer start recovery for the
  * request by deleting the timer and calling the q's timeout function.
  * LLDDs who implement their own error recovery MAY ignore the timeout
- * event if they generated blk_abort_req. Must hold queue lock.
+ * event if they generated blk_abort_request.
  */
 void blk_abort_request(struct request *req)
 {
-	if (req->q->mq_ops) {
-		/*
-		 * All we need to ensure is that timeout scan takes place
-		 * immediately and that scan sees the new timeout value.
-		 * No need for fancy synchronizations.
-		 */
-		blk_rq_set_deadline(req, jiffies);
-		kblockd_schedule_work(&req->q->timeout_work);
-	} else {
-		if (blk_mark_rq_complete(req))
-			return;
-		blk_delete_timer(req);
-		blk_rq_timed_out(req);
-	}
+	/*
+	 * All we need to ensure is that timeout scan takes place
+	 * immediately and that scan sees the new timeout value.
+	 * No need for fancy synchronizations.
+	 */
+	WRITE_ONCE(req->deadline, jiffies);
+	kblockd_schedule_work(&req->q->timeout_work);
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
@@ -194,15 +113,6 @@ void blk_add_timer(struct request *req)
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
-	if (!q->mq_ops)
-		lockdep_assert_held(q->queue_lock);
-
-	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
-	if (!q->mq_ops && !q->rq_timed_out_fn)
-		return;
-
-	BUG_ON(!list_empty(&req->timeout_list));
-
 	/*
 	 * Some LLDs, like scsi, peek at the timeout to prevent a
 	 * command from being retried forever.
@@ -211,21 +121,16 @@ void blk_add_timer(struct request *req)
 		req->timeout = q->rq_timeout;
 
 	req->rq_flags &= ~RQF_TIMED_OUT;
-	blk_rq_set_deadline(req, jiffies + req->timeout);
 
-	/*
-	 * Only the non-mq case needs to add the request to a protected list.
-	 * For the mq case we simply scan the tag map.
-	 */
-	if (!q->mq_ops)
-		list_add_tail(&req->timeout_list, &req->q->timeout_list);
+	expiry = jiffies + req->timeout;
+	WRITE_ONCE(req->deadline, expiry);
 
 	/*
 	 * If the timer isn't already pending or this timeout is earlier
 	 * than an existing one, modify the timer. Round up to next nearest
 	 * second.
 	 */
-	expiry = blk_rq_timeout(round_jiffies_up(blk_rq_deadline(req)));
+	expiry = blk_rq_timeout(round_jiffies_up(expiry));
 
 	if (!timer_pending(&q->timeout) ||
 	    time_before(expiry, q->timeout.expires)) {