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, 51 insertions, 18 deletions

diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 3b75a7b7a284..63627be0811a 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -746,10 +746,16 @@ static void ide_initialize_rq(struct request *rq)
 {
 	struct ide_request *req = blk_mq_rq_to_pdu(rq);
 
+	req->special = NULL;
 	scsi_req_init(&req->sreq);
 	req->sreq.sense = req->sense;
 }
 
+static const struct blk_mq_ops ide_mq_ops = {
+	.queue_rq		= ide_queue_rq,
+	.initialize_rq_fn	= ide_initialize_rq,
+};
+
 /*
  * init request queue
  */
@@ -759,6 +765,7 @@ static int ide_init_queue(ide_drive_t *drive)
 	ide_hwif_t *hwif = drive->hwif;
 	int max_sectors = 256;
 	int max_sg_entries = PRD_ENTRIES;
+	struct blk_mq_tag_set *set;
 
 	/*
 	 *	Our default set up assumes the normal IDE case,
@@ -767,19 +774,26 @@ static int ide_init_queue(ide_drive_t *drive)
 	 *	limits and LBA48 we could raise it but as yet
 	 *	do not.
 	 */
-	q = blk_alloc_queue_node(GFP_KERNEL, hwif_to_node(hwif), NULL);
-	if (!q)
+
+	set = &drive->tag_set;
+	set->ops = &ide_mq_ops;
+	set->nr_hw_queues = 1;
+	set->queue_depth = 32;
+	set->reserved_tags = 1;
+	set->cmd_size = sizeof(struct ide_request);
+	set->numa_node = hwif_to_node(hwif);
+	set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
+	if (blk_mq_alloc_tag_set(set))
 		return 1;
 
-	q->request_fn = do_ide_request;
-	q->initialize_rq_fn = ide_initialize_rq;
-	q->cmd_size = sizeof(struct ide_request);
-	blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
-	if (blk_init_allocated_queue(q) < 0) {
-		blk_cleanup_queue(q);
+	q = blk_mq_init_queue(set);
+	if (IS_ERR(q)) {
+		blk_mq_free_tag_set(set);
 		return 1;
 	}
 
+	blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
+
 	q->queuedata = drive;
 	blk_queue_segment_boundary(q, 0xffff);
 
@@ -965,8 +979,12 @@ static void drive_release_dev (struct device *dev)
 
 	ide_proc_unregister_device(drive);
 
+	if (drive->sense_rq)
+		blk_mq_free_request(drive->sense_rq);
+
 	blk_cleanup_queue(drive->queue);
 	drive->queue = NULL;
+	blk_mq_free_tag_set(&drive->tag_set);
 
 	drive->dev_flags &= ~IDE_DFLAG_PRESENT;
 
@@ -1133,6 +1151,28 @@ static void ide_port_cable_detect(ide_hwif_t *hwif)
 	}
 }
 
+/*
+ * Deferred request list insertion handler
+ */
+static void drive_rq_insert_work(struct work_struct *work)
+{
+	ide_drive_t *drive = container_of(work, ide_drive_t, rq_work);
+	ide_hwif_t *hwif = drive->hwif;
+	struct request *rq;
+	LIST_HEAD(list);
+
+	spin_lock_irq(&hwif->lock);
+	if (!list_empty(&drive->rq_list))
+		list_splice_init(&drive->rq_list, &list);
+	spin_unlock_irq(&hwif->lock);
+
+	while (!list_empty(&list)) {
+		rq = list_first_entry(&list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL);
+	}
+}
+
 static const u8 ide_hwif_to_major[] =
 	{ IDE0_MAJOR, IDE1_MAJOR, IDE2_MAJOR, IDE3_MAJOR, IDE4_MAJOR,
 	  IDE5_MAJOR, IDE6_MAJOR, IDE7_MAJOR, IDE8_MAJOR, IDE9_MAJOR };
@@ -1145,12 +1185,10 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif)
 	ide_port_for_each_dev(i, drive, hwif) {
 		u8 j = (hwif->index * MAX_DRIVES) + i;
 		u16 *saved_id = drive->id;
-		struct request *saved_sense_rq = drive->sense_rq;
 
 		memset(drive, 0, sizeof(*drive));
 		memset(saved_id, 0, SECTOR_SIZE);
 		drive->id = saved_id;
-		drive->sense_rq = saved_sense_rq;
 
 		drive->media			= ide_disk;
 		drive->select			= (i << 4) | ATA_DEVICE_OBS;
@@ -1166,6 +1204,9 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif)
 
 		INIT_LIST_HEAD(&drive->list);
 		init_completion(&drive->gendev_rel_comp);
+
+		INIT_WORK(&drive->rq_work, drive_rq_insert_work);
+		INIT_LIST_HEAD(&drive->rq_list);
 	}
 }
 
@@ -1255,7 +1296,6 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
 	int i;
 
 	ide_port_for_each_dev(i, drive, hwif) {
-		kfree(drive->sense_rq);
 		kfree(drive->id);
 		kfree(drive);
 	}
@@ -1283,17 +1323,10 @@ static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
 		if (drive->id == NULL)
 			goto out_free_drive;
 
-		drive->sense_rq = kmalloc(sizeof(struct request) +
-				sizeof(struct ide_request), GFP_KERNEL);
-		if (!drive->sense_rq)
-			goto out_free_id;
-
 		hwif->devices[i] = drive;
 	}
 	return 0;
 
-out_free_id:
-	kfree(drive->id);
 out_free_drive:
 	kfree(drive);
 out_nomem: