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
  ...

12 files changed, 259 insertions, 209 deletions

diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 8b2b72b93885..da58020a144e 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -94,7 +94,7 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_MISC;
-	rq->special = (char *)pc;
+	ide_req(rq)->special = pc;
 
 	if (buf && bufflen) {
 		error = blk_rq_map_kern(drive->queue, rq, buf, bufflen,
@@ -172,8 +172,8 @@ EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
 void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 {
 	struct request_sense *sense = &drive->sense_data;
-	struct request *sense_rq = drive->sense_rq;
-	struct scsi_request *req = scsi_req(sense_rq);
+	struct request *sense_rq;
+	struct scsi_request *req;
 	unsigned int cmd_len, sense_len;
 	int err;
 
@@ -196,9 +196,16 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	if (ata_sense_request(rq) || drive->sense_rq_armed)
 		return;
 
+	sense_rq = drive->sense_rq;
+	if (!sense_rq) {
+		sense_rq = blk_mq_alloc_request(drive->queue, REQ_OP_DRV_IN,
+					BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+		drive->sense_rq = sense_rq;
+	}
+	req = scsi_req(sense_rq);
+
 	memset(sense, 0, sizeof(*sense));
 
-	blk_rq_init(rq->q, sense_rq);
 	scsi_req_init(req);
 
 	err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
@@ -207,6 +214,8 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 		if (printk_ratelimit())
 			printk(KERN_WARNING PFX "%s: failed to map sense "
 					    "buffer\n", drive->name);
+		blk_mq_free_request(sense_rq);
+		drive->sense_rq = NULL;
 		return;
 	}
 
@@ -226,6 +235,8 @@ EXPORT_SYMBOL_GPL(ide_prep_sense);
 
 int ide_queue_sense_rq(ide_drive_t *drive, void *special)
 {
+	struct request *sense_rq = drive->sense_rq;
+
 	/* deferred failure from ide_prep_sense() */
 	if (!drive->sense_rq_armed) {
 		printk(KERN_WARNING PFX "%s: error queuing a sense request\n",
@@ -233,12 +244,12 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special)
 		return -ENOMEM;
 	}
 
-	drive->sense_rq->special = special;
+	ide_req(sense_rq)->special = special;
 	drive->sense_rq_armed = false;
 
 	drive->hwif->rq = NULL;
 
-	elv_add_request(drive->queue, drive->sense_rq, ELEVATOR_INSERT_FRONT);
+	ide_insert_request_head(drive, sense_rq);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
@@ -270,10 +281,8 @@ void ide_retry_pc(ide_drive_t *drive)
 	 */
 	drive->hwif->rq = NULL;
 	ide_requeue_and_plug(drive, failed_rq);
-	if (ide_queue_sense_rq(drive, pc)) {
-		blk_start_request(failed_rq);
+	if (ide_queue_sense_rq(drive, pc))
 		ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(failed_rq));
-	}
 }
 EXPORT_SYMBOL_GPL(ide_retry_pc);
 
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index f9b59d41813f..1f03884a6808 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -211,12 +211,12 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For ATA_PRIV_SENSE, "rq->special" points to the original
+	 * For ATA_PRIV_SENSE, "ide_req(rq)->special" points to the original
 	 * failed request.  Also, the sense data should be read
 	 * directly from rq which might be different from the original
 	 * sense buffer if it got copied during mapping.
 	 */
-	struct request *failed = (struct request *)rq->special;
+	struct request *failed = ide_req(rq)->special;
 	void *sense = bio_data(rq->bio);
 
 	if (failed) {
@@ -258,11 +258,22 @@ static int ide_cd_breathe(ide_drive_t *drive, struct request *rq)
 		/*
 		 * take a breather
 		 */
-		blk_delay_queue(drive->queue, 1);
+		blk_mq_requeue_request(rq, false);
+		blk_mq_delay_kick_requeue_list(drive->queue, 1);
 		return 1;
 	}
 }
 
+static void ide_cd_free_sense(ide_drive_t *drive)
+{
+	if (!drive->sense_rq)
+		return;
+
+	blk_mq_free_request(drive->sense_rq);
+	drive->sense_rq = NULL;
+	drive->sense_rq_armed = false;
+}
+
 /**
  * Returns:
  * 0: if the request should be continued.
@@ -516,6 +527,82 @@ static bool ide_cd_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd)
 	return false;
 }
 
+/* standard prep_rq that builds 10 byte cmds */
+static bool ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
+{
+	int hard_sect = queue_logical_block_size(q);
+	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
+	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
+	struct scsi_request *req = scsi_req(rq);
+
+	if (rq_data_dir(rq) == READ)
+		req->cmd[0] = GPCMD_READ_10;
+	else
+		req->cmd[0] = GPCMD_WRITE_10;
+
+	/*
+	 * fill in lba
+	 */
+	req->cmd[2] = (block >> 24) & 0xff;
+	req->cmd[3] = (block >> 16) & 0xff;
+	req->cmd[4] = (block >>  8) & 0xff;
+	req->cmd[5] = block & 0xff;
+
+	/*
+	 * and transfer length
+	 */
+	req->cmd[7] = (blocks >> 8) & 0xff;
+	req->cmd[8] = blocks & 0xff;
+	req->cmd_len = 10;
+	return true;
+}
+
+/*
+ * Most of the SCSI commands are supported directly by ATAPI devices.
+ * This transform handles the few exceptions.
+ */
+static bool ide_cdrom_prep_pc(struct request *rq)
+{
+	u8 *c = scsi_req(rq)->cmd;
+
+	/* transform 6-byte read/write commands to the 10-byte version */
+	if (c[0] == READ_6 || c[0] == WRITE_6) {
+		c[8] = c[4];
+		c[5] = c[3];
+		c[4] = c[2];
+		c[3] = c[1] & 0x1f;
+		c[2] = 0;
+		c[1] &= 0xe0;
+		c[0] += (READ_10 - READ_6);
+		scsi_req(rq)->cmd_len = 10;
+		return true;
+	}
+
+	/*
+	 * it's silly to pretend we understand 6-byte sense commands, just
+	 * reject with ILLEGAL_REQUEST and the caller should take the
+	 * appropriate action
+	 */
+	if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
+		scsi_req(rq)->result = ILLEGAL_REQUEST;
+		return false;
+	}
+
+	return true;
+}
+
+static bool ide_cdrom_prep_rq(ide_drive_t *drive, struct request *rq)
+{
+	if (!blk_rq_is_passthrough(rq)) {
+		scsi_req_init(scsi_req(rq));
+
+		return ide_cdrom_prep_fs(drive->queue, rq);
+	} else if (blk_rq_is_scsi(rq))
+		return ide_cdrom_prep_pc(rq);
+
+	return true;
+}
+
 static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
@@ -675,7 +762,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 out_end:
 	if (blk_rq_is_scsi(rq) && rc == 0) {
 		scsi_req(rq)->resid_len = 0;
-		blk_end_request_all(rq, BLK_STS_OK);
+		blk_mq_end_request(rq, BLK_STS_OK);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
@@ -705,6 +792,8 @@ out_end:
 		if (sense && rc == 2)
 			ide_error(drive, "request sense failure", stat);
 	}
+
+	ide_cd_free_sense(drive);
 	return ide_stopped;
 }
 
@@ -729,7 +818,7 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq)
 		 * We may be retrying this request after an error.  Fix up any
 		 * weirdness which might be present in the request packet.
 		 */
-		q->prep_rq_fn(q, rq);
+		ide_cdrom_prep_rq(drive, rq);
 	}
 
 	/* fs requests *must* be hardware frame aligned */
@@ -1323,82 +1412,6 @@ static int ide_cdrom_probe_capabilities(ide_drive_t *drive)
 	return nslots;
 }
 
-/* standard prep_rq_fn that builds 10 byte cmds */
-static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
-{
-	int hard_sect = queue_logical_block_size(q);
-	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
-	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
-	struct scsi_request *req = scsi_req(rq);
-
-	q->initialize_rq_fn(rq);
-
-	if (rq_data_dir(rq) == READ)
-		req->cmd[0] = GPCMD_READ_10;
-	else
-		req->cmd[0] = GPCMD_WRITE_10;
-
-	/*
-	 * fill in lba
-	 */
-	req->cmd[2] = (block >> 24) & 0xff;
-	req->cmd[3] = (block >> 16) & 0xff;
-	req->cmd[4] = (block >>  8) & 0xff;
-	req->cmd[5] = block & 0xff;
-
-	/*
-	 * and transfer length
-	 */
-	req->cmd[7] = (blocks >> 8) & 0xff;
-	req->cmd[8] = blocks & 0xff;
-	req->cmd_len = 10;
-	return BLKPREP_OK;
-}
-
-/*
- * Most of the SCSI commands are supported directly by ATAPI devices.
- * This transform handles the few exceptions.
- */
-static int ide_cdrom_prep_pc(struct request *rq)
-{
-	u8 *c = scsi_req(rq)->cmd;
-
-	/* transform 6-byte read/write commands to the 10-byte version */
-	if (c[0] == READ_6 || c[0] == WRITE_6) {
-		c[8] = c[4];
-		c[5] = c[3];
-		c[4] = c[2];
-		c[3] = c[1] & 0x1f;
-		c[2] = 0;
-		c[1] &= 0xe0;
-		c[0] += (READ_10 - READ_6);
-		scsi_req(rq)->cmd_len = 10;
-		return BLKPREP_OK;
-	}
-
-	/*
-	 * it's silly to pretend we understand 6-byte sense commands, just
-	 * reject with ILLEGAL_REQUEST and the caller should take the
-	 * appropriate action
-	 */
-	if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
-		scsi_req(rq)->result = ILLEGAL_REQUEST;
-		return BLKPREP_KILL;
-	}
-
-	return BLKPREP_OK;
-}
-
-static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq)
-{
-	if (!blk_rq_is_passthrough(rq))
-		return ide_cdrom_prep_fs(q, rq);
-	else if (blk_rq_is_scsi(rq))
-		return ide_cdrom_prep_pc(rq);
-
-	return 0;
-}
-
 struct cd_list_entry {
 	const char	*id_model;
 	const char	*id_firmware;
@@ -1508,7 +1521,7 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 
 	ide_debug_log(IDE_DBG_PROBE, "enter");
 
-	blk_queue_prep_rq(q, ide_cdrom_prep_fn);
+	drive->prep_rq = ide_cdrom_prep_rq;
 	blk_queue_dma_alignment(q, 31);
 	blk_queue_update_dma_pad(q, 15);
 
@@ -1569,7 +1582,7 @@ static void ide_cd_release(struct device *dev)
 	if (devinfo->handle == drive)
 		unregister_cdrom(devinfo);
 	drive->driver_data = NULL;
-	blk_queue_prep_rq(drive->queue, NULL);
+	drive->prep_rq = NULL;
 	g->private_data = NULL;
 	put_disk(g);
 	kfree(info);
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index f4f8afdf8bbe..f2f93ed40356 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -171,7 +171,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	scsi_req(rq)->cmd_len = 5;
 	scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
 	*(int *)&scsi_req(rq)->cmd[1] = arg;
-	rq->special = setting->set;
+	ide_req(rq)->special = setting->set;
 
 	blk_execute_rq(q, NULL, rq, 0);
 	ret = scsi_req(rq)->result;
@@ -182,7 +182,7 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 
 ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 {
-	int err, (*setfunc)(ide_drive_t *, int) = rq->special;
+	int err, (*setfunc)(ide_drive_t *, int) = ide_req(rq)->special;
 
 	err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
 	if (err)
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index e3b4e659082d..197912af5c2f 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -427,16 +427,15 @@ static void ide_disk_unlock_native_capacity(ide_drive_t *drive)
 		drive->dev_flags |= IDE_DFLAG_NOHPA; /* disable HPA on resume */
 }
 
-static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
+static bool idedisk_prep_rq(ide_drive_t *drive, struct request *rq)
 {
-	ide_drive_t *drive = q->queuedata;
 	struct ide_cmd *cmd;
 
 	if (req_op(rq) != REQ_OP_FLUSH)
-		return BLKPREP_OK;
+		return true;
 
-	if (rq->special) {
-		cmd = rq->special;
+	if (ide_req(rq)->special) {
+		cmd = ide_req(rq)->special;
 		memset(cmd, 0, sizeof(*cmd));
 	} else {
 		cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC);
@@ -456,10 +455,10 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	rq->cmd_flags &= ~REQ_OP_MASK;
 	rq->cmd_flags |= REQ_OP_DRV_OUT;
 	ide_req(rq)->type = ATA_PRIV_TASKFILE;
-	rq->special = cmd;
+	ide_req(rq)->special = cmd;
 	cmd->rq = rq;
 
-	return BLKPREP_OK;
+	return true;
 }
 
 ide_devset_get(multcount, mult_count);
@@ -548,7 +547,7 @@ static void update_flush(ide_drive_t *drive)
 
 		if (barrier) {
 			wc = true;
-			blk_queue_prep_rq(drive->queue, idedisk_prep_fn);
+			drive->prep_rq = idedisk_prep_rq;
 		}
 	}
 
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index 47d5f3379748..e1323e058454 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -125,7 +125,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 	/* retry only "normal" I/O: */
 	if (blk_rq_is_passthrough(rq)) {
 		if (ata_taskfile_request(rq)) {
-			struct ide_cmd *cmd = rq->special;
+			struct ide_cmd *cmd = ide_req(rq)->special;
 
 			if (cmd)
 				ide_complete_cmd(drive, cmd, stat, err);
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index a8df300f949c..780d33ccc5d8 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -276,7 +276,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		switch (ide_req(rq)->type) {
 		case ATA_PRIV_MISC:
 		case ATA_PRIV_SENSE:
-			pc = (struct ide_atapi_pc *)rq->special;
+			pc = (struct ide_atapi_pc *)ide_req(rq)->special;
 			break;
 		default:
 			BUG();
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 0d93e0cfbeaf..8445b484ae69 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -67,7 +67,15 @@ int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error,
 		ide_dma_on(drive);
 	}
 
-	return blk_end_request(rq, error, nr_bytes);
+	if (!blk_update_request(rq, error, nr_bytes)) {
+		if (rq == drive->sense_rq)
+			drive->sense_rq = NULL;
+
+		__blk_mq_end_request(rq, error);
+		return 0;
+	}
+
+	return 1;
 }
 EXPORT_SYMBOL_GPL(ide_end_rq);
 
@@ -103,7 +111,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 	}
 
 	if (rq && ata_taskfile_request(rq)) {
-		struct ide_cmd *orig_cmd = rq->special;
+		struct ide_cmd *orig_cmd = ide_req(rq)->special;
 
 		if (cmd->tf_flags & IDE_TFLAG_DYN)
 			kfree(orig_cmd);
@@ -253,7 +261,7 @@ EXPORT_SYMBOL_GPL(ide_init_sg_cmd);
 static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 		struct request *rq)
 {
-	struct ide_cmd *cmd = rq->special;
+	struct ide_cmd *cmd = ide_req(rq)->special;
 
 	if (cmd) {
 		if (cmd->protocol == ATA_PROT_PIO) {
@@ -307,8 +315,6 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 {
 	ide_startstop_t startstop;
 
-	BUG_ON(!(rq->rq_flags & RQF_STARTED));
-
 #ifdef DEBUG
 	printk("%s: start_request: current=0x%08lx\n",
 		drive->hwif->name, (unsigned long) rq);
@@ -320,6 +326,9 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		goto kill_rq;
 	}
 
+	if (drive->prep_rq && !drive->prep_rq(drive, rq))
+		return ide_stopped;
+
 	if (ata_pm_request(rq))
 		ide_check_pm_state(drive, rq);
 
@@ -343,7 +352,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		if (ata_taskfile_request(rq))
 			return execute_drive_cmd(drive, rq);
 		else if (ata_pm_request(rq)) {
-			struct ide_pm_state *pm = rq->special;
+			struct ide_pm_state *pm = ide_req(rq)->special;
 #ifdef DEBUG_PM
 			printk("%s: start_power_step(step: %d)\n",
 				drive->name, pm->pm_step);
@@ -430,44 +439,42 @@ static inline void ide_unlock_host(struct ide_host *host)
 	}
 }
 
-static void __ide_requeue_and_plug(struct request_queue *q, struct request *rq)
-{
-	if (rq)
-		blk_requeue_request(q, rq);
-	if (rq || blk_peek_request(q)) {
-		/* Use 3ms as that was the old plug delay */
-		blk_delay_queue(q, 3);
-	}
-}
-
 void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
-	unsigned long flags;
 
-	spin_lock_irqsave(q->queue_lock, flags);
-	__ide_requeue_and_plug(q, rq);
-	spin_unlock_irqrestore(q->queue_lock, flags);
+	/* Use 3ms as that was the old plug delay */
+	if (rq) {
+		blk_mq_requeue_request(rq, false);
+		blk_mq_delay_kick_requeue_list(q, 3);
+	} else
+		blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3);
 }
 
 /*
  * Issue a new request to a device.
  */
-void do_ide_request(struct request_queue *q)
+blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx,
+			  const struct blk_mq_queue_data *bd)
 {
-	ide_drive_t	*drive = q->queuedata;
+	ide_drive_t	*drive = hctx->queue->queuedata;
 	ide_hwif_t	*hwif = drive->hwif;
 	struct ide_host *host = hwif->host;
-	struct request	*rq = NULL;
+	struct request	*rq = bd->rq;
 	ide_startstop_t	startstop;
 
-	spin_unlock_irq(q->queue_lock);
+	if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) {
+		rq->rq_flags |= RQF_DONTPREP;
+		ide_req(rq)->special = NULL;
+	}
 
 	/* HLD do_request() callback might sleep, make sure it's okay */
 	might_sleep();
 
 	if (ide_lock_host(host, hwif))
-		goto plug_device_2;
+		return BLK_STS_DEV_RESOURCE;
+
+	blk_mq_start_request(rq);
 
 	spin_lock_irq(&hwif->lock);
 
@@ -503,21 +510,16 @@ repeat:
 		hwif->cur_dev = drive;
 		drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED);
 
-		spin_unlock_irq(&hwif->lock);
-		spin_lock_irq(q->queue_lock);
 		/*
 		 * we know that the queue isn't empty, but this can happen
-		 * if the q->prep_rq_fn() decides to kill a request
+		 * if ->prep_rq() decides to kill a request
 		 */
-		if (!rq)
-			rq = blk_fetch_request(drive->queue);
-
-		spin_unlock_irq(q->queue_lock);
-		spin_lock_irq(&hwif->lock);
-
 		if (!rq) {
-			ide_unlock_port(hwif);
-			goto out;
+			rq = bd->rq;
+			if (!rq) {
+				ide_unlock_port(hwif);
+				goto out;
+			}
 		}
 
 		/*
@@ -551,23 +553,24 @@ repeat:
 		if (startstop == ide_stopped) {
 			rq = hwif->rq;
 			hwif->rq = NULL;
-			goto repeat;
+			if (rq)
+				goto repeat;
+			ide_unlock_port(hwif);
+			goto out;
 		}
-	} else
-		goto plug_device;
+	} else {
+plug_device:
+		spin_unlock_irq(&hwif->lock);
+		ide_unlock_host(host);
+		ide_requeue_and_plug(drive, rq);
+		return BLK_STS_OK;
+	}
+
 out:
 	spin_unlock_irq(&hwif->lock);
 	if (rq == NULL)
 		ide_unlock_host(host);
-	spin_lock_irq(q->queue_lock);
-	return;
-
-plug_device:
-	spin_unlock_irq(&hwif->lock);
-	ide_unlock_host(host);
-plug_device_2:
-	spin_lock_irq(q->queue_lock);
-	__ide_requeue_and_plug(q, rq);
+	return BLK_STS_OK;
 }
 
 static int drive_is_ready(ide_drive_t *drive)
@@ -887,3 +890,16 @@ void ide_pad_transfer(ide_drive_t *drive, int write, int len)
 	}
 }
 EXPORT_SYMBOL_GPL(ide_pad_transfer);
+
+void ide_insert_request_head(ide_drive_t *drive, struct request *rq)
+{
+	ide_hwif_t *hwif = drive->hwif;
+	unsigned long flags;
+
+	spin_lock_irqsave(&hwif->lock, flags);
+	list_add_tail(&rq->queuelist, &drive->rq_list);
+	spin_unlock_irqrestore(&hwif->lock, flags);
+
+	kblockd_schedule_work(&drive->rq_work);
+}
+EXPORT_SYMBOL_GPL(ide_insert_request_head);
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 622f0edb3945..102aa3bc3e7f 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -27,7 +27,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 		spin_unlock_irq(&hwif->lock);
 
 		if (start_queue)
-			blk_run_queue(q);
+			blk_mq_run_hw_queues(q, true);
 		return;
 	}
 	spin_unlock_irq(&hwif->lock);
@@ -36,7 +36,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
-	rq->special = &timeout;
+	ide_req(rq)->special = &timeout;
 	blk_execute_rq(q, NULL, rq, 1);
 	rc = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
@@ -54,7 +54,7 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS;
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
-	elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
+	ide_insert_request_head(drive, rq);
 
 out:
 	return;
@@ -67,7 +67,7 @@ ide_startstop_t ide_do_park_unpark(ide_drive_t *drive, struct request *rq)
 
 	memset(&cmd, 0, sizeof(cmd));
 	if (scsi_req(rq)->cmd[0] == REQ_PARK_HEADS) {
-		drive->sleep = *(unsigned long *)rq->special;
+		drive->sleep = *(unsigned long *)ide_req(rq)->special;
 		drive->dev_flags |= IDE_DFLAG_SLEEPING;
 		tf->command = ATA_CMD_IDLEIMMEDIATE;
 		tf->feature = 0x44;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index 59217aa1d1fb..192e6c65d34e 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -21,7 +21,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, 0);
 	ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
-	rq->special = &rqpm;
+	ide_req(rq)->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
 		mesg.event = PM_EVENT_FREEZE;
@@ -40,32 +40,17 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	return ret;
 }
 
-static void ide_end_sync_rq(struct request *rq, blk_status_t error)
-{
-	complete(rq->end_io_data);
-}
-
 static int ide_pm_execute_rq(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	DECLARE_COMPLETION_ONSTACK(wait);
 
-	rq->end_io_data = &wait;
-	rq->end_io = ide_end_sync_rq;
-
-	spin_lock_irq(q->queue_lock);
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
 		scsi_req(rq)->result = -ENXIO;
-		__blk_end_request_all(rq, BLK_STS_OK);
-		spin_unlock_irq(q->queue_lock);
+		blk_mq_end_request(rq, BLK_STS_OK);
 		return -ENXIO;
 	}
-	__elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
-	__blk_run_queue_uncond(q);
-	spin_unlock_irq(q->queue_lock);
-
-	wait_for_completion_io(&wait);
+	blk_execute_rq(q, NULL, rq, true);
 
 	return scsi_req(rq)->result ? -EIO : 0;
 }
@@ -79,6 +64,8 @@ int generic_ide_resume(struct device *dev)
 	struct ide_pm_state rqpm;
 	int err;
 
+	blk_mq_start_stopped_hw_queues(drive->queue, true);
+
 	if (ide_port_acpi(hwif)) {
 		/* call ACPI _PS0 / _STM only once */
 		if ((drive->dn & 1) == 0 || pair == NULL) {
@@ -92,7 +79,7 @@ int generic_ide_resume(struct device *dev)
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, BLK_MQ_REQ_PREEMPT);
 	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
-	rq->special = &rqpm;
+	ide_req(rq)->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
 	rqpm.pm_state = PM_EVENT_ON;
 
@@ -111,7 +98,7 @@ int generic_ide_resume(struct device *dev)
 
 void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct ide_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = ide_req(rq)->special;
 
 #ifdef DEBUG_PM
 	printk(KERN_INFO "%s: complete_power_step(step: %d)\n",
@@ -141,7 +128,7 @@ void ide_complete_power_step(ide_drive_t *drive, struct request *rq)
 
 ide_startstop_t ide_start_power_step(ide_drive_t *drive, struct request *rq)
 {
-	struct ide_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = ide_req(rq)->special;
 	struct ide_cmd cmd = { };
 
 	switch (pm->pm_step) {
@@ -213,8 +200,7 @@ out_do_tf:
 void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 {
 	struct request_queue *q = drive->queue;
-	struct ide_pm_state *pm = rq->special;
-	unsigned long flags;
+	struct ide_pm_state *pm = ide_req(rq)->special;
 
 	ide_complete_power_step(drive, rq);
 	if (pm->pm_step != IDE_PM_COMPLETED)
@@ -224,22 +210,19 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 	printk("%s: completing PM request, %s\n", drive->name,
 	       (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND) ? "suspend" : "resume");
 #endif
-	spin_lock_irqsave(q->queue_lock, flags);
 	if (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND)
-		blk_stop_queue(q);
+		blk_mq_stop_hw_queues(q);
 	else
 		drive->dev_flags &= ~IDE_DFLAG_BLOCKED;
-	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	drive->hwif->rq = NULL;
 
-	if (blk_end_request(rq, BLK_STS_OK, 0))
-		BUG();
+	blk_mq_end_request(rq, BLK_STS_OK);
 }
 
 void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
-	struct ide_pm_state *pm = rq->special;
+	struct ide_pm_state *pm = ide_req(rq)->special;
 
 	if (blk_rq_is_private(rq) &&
 	    ide_req(rq)->type == ATA_PRIV_PM_SUSPEND &&
@@ -260,7 +243,6 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 		ide_hwif_t *hwif = drive->hwif;
 		const struct ide_tp_ops *tp_ops = hwif->tp_ops;
 		struct request_queue *q = drive->queue;
-		unsigned long flags;
 		int rc;
 #ifdef DEBUG_PM
 		printk("%s: Wakeup request inited, waiting for !BSY...\n", drive->name);
@@ -274,8 +256,6 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 		if (rc)
 			printk(KERN_WARNING "%s: drive not ready on wakeup\n", drive->name);
 
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_start_queue(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
+		blk_mq_start_hw_queues(q);
 	}
 }
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:
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 34c1165226a4..db1a65f4b490 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -639,7 +639,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		goto out;
 	}
 	if (req->cmd[13] & REQ_IDETAPE_PC1) {
-		pc = (struct ide_atapi_pc *)rq->special;
+		pc = (struct ide_atapi_pc *)ide_req(rq)->special;
 		req->cmd[13] &= ~(REQ_IDETAPE_PC1);
 		req->cmd[13] |= REQ_IDETAPE_PC2;
 		goto out;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index c21d5c50ae3a..17b2e379e872 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -440,7 +440,7 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 			goto put_req;
 	}
 
-	rq->special = cmd;
+	ide_req(rq)->special = cmd;
 	cmd->rq = rq;
 
 	blk_execute_rq(drive->queue, NULL, rq, 0);