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, 52 insertions, 27 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 63a7c416b224..a4a06982ed91 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -646,26 +646,38 @@ static void free_tio(struct dm_target_io *tio)
 	bio_put(&tio->clone);
 }
 
-int md_in_flight(struct mapped_device *md)
+static bool md_in_flight_bios(struct mapped_device *md)
 {
-	return atomic_read(&md->pending[READ]) +
-	       atomic_read(&md->pending[WRITE]);
+	int cpu;
+	struct hd_struct *part = &dm_disk(md)->part0;
+	long sum = 0;
+
+	for_each_possible_cpu(cpu) {
+		sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
+		sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
+	}
+
+	return sum != 0;
+}
+
+static bool md_in_flight(struct mapped_device *md)
+{
+	if (queue_is_mq(md->queue))
+		return blk_mq_queue_inflight(md->queue);
+	else
+		return md_in_flight_bios(md);
 }
 
 static void start_io_acct(struct dm_io *io)
 {
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->orig_bio;
-	int rw = bio_data_dir(bio);
 
 	io->start_time = jiffies;
 
 	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
 			      &dm_disk(md)->part0);
 
-	atomic_set(&dm_disk(md)->part0.in_flight[rw],
-		   atomic_inc_return(&md->pending[rw]));
-
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
 				    bio->bi_iter.bi_sector, bio_sectors(bio),
@@ -677,8 +689,6 @@ static void end_io_acct(struct dm_io *io)
 	struct mapped_device *md = io->md;
 	struct bio *bio = io->orig_bio;
 	unsigned long duration = jiffies - io->start_time;
-	int pending;
-	int rw = bio_data_dir(bio);
 
 	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
 			    io->start_time);
@@ -688,16 +698,8 @@ static void end_io_acct(struct dm_io *io)
 				    bio->bi_iter.bi_sector, bio_sectors(bio),
 				    true, duration, &io->stats_aux);
 
-	/*
-	 * After this is decremented the bio must not be touched if it is
-	 * a flush.
-	 */
-	pending = atomic_dec_return(&md->pending[rw]);
-	atomic_set(&dm_disk(md)->part0.in_flight[rw], pending);
-	pending += atomic_read(&md->pending[rw^0x1]);
-
 	/* nudge anyone waiting on suspend queue */
-	if (!pending)
+	if (unlikely(waitqueue_active(&md->wait)))
 		wake_up(&md->wait);
 }
 
@@ -1417,10 +1419,21 @@ static int __send_empty_flush(struct clone_info *ci)
 	unsigned target_nr = 0;
 	struct dm_target *ti;
 
+	/*
+	 * Empty flush uses a statically initialized bio, as the base for
+	 * cloning.  However, blkg association requires that a bdev is
+	 * associated with a gendisk, which doesn't happen until the bdev is
+	 * opened.  So, blkg association is done at issue time of the flush
+	 * rather than when the device is created in alloc_dev().
+	 */
+	bio_set_dev(ci->bio, ci->io->md->bdev);
+
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
 		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
 
+	bio_disassociate_blkg(ci->bio);
+
 	return 0;
 }
 
@@ -1598,7 +1611,16 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 	init_clone_info(&ci, md, map, bio);
 
 	if (bio->bi_opf & REQ_PREFLUSH) {
-		ci.bio = &ci.io->md->flush_bio;
+		struct bio flush_bio;
+
+		/*
+		 * Use an on-stack bio for this, it's safe since we don't
+		 * need to reference it after submit. It's just used as
+		 * the basis for the clone(s).
+		 */
+		bio_init(&flush_bio, NULL, 0);
+		flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+		ci.bio = &flush_bio;
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
@@ -1654,7 +1676,16 @@ static blk_qc_t __process_bio(struct mapped_device *md,
 	init_clone_info(&ci, md, map, bio);
 
 	if (bio->bi_opf & REQ_PREFLUSH) {
-		ci.bio = &ci.io->md->flush_bio;
+		struct bio flush_bio;
+
+		/*
+		 * Use an on-stack bio for this, it's safe since we don't
+		 * need to reference it after submit. It's just used as
+		 * the basis for the clone(s).
+		 */
+		bio_init(&flush_bio, NULL, 0);
+		flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
+		ci.bio = &flush_bio;
 		ci.sector_count = 0;
 		error = __send_empty_flush(&ci);
 		/* dec_pending submits any data associated with flush */
@@ -1898,7 +1929,7 @@ static struct mapped_device *alloc_dev(int minor)
 	INIT_LIST_HEAD(&md->table_devices);
 	spin_lock_init(&md->uevent_lock);
 
-	md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id, NULL);
+	md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id);
 	if (!md->queue)
 		goto bad;
 	md->queue->queuedata = md;
@@ -1908,8 +1939,6 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->disk)
 		goto bad;
 
-	atomic_set(&md->pending[0], 0);
-	atomic_set(&md->pending[1], 0);
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
@@ -1940,10 +1969,6 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->bdev)
 		goto bad;
 
-	bio_init(&md->flush_bio, NULL, 0);
-	bio_set_dev(&md->flush_bio, md->bdev);
-	md->flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
-
 	dm_stats_init(&md->stats);
 
 	/* Populate the mapping, nobody knows we exist yet */