Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

drivers/scsi/scsi_lib.c

@@ -1089,6 +1089,18 @@ static void scsi_initialize_rq(struct request *rq)
 	cmd->retries = 0;
 }
 
+/*
+ * Only called when the request isn't completed by SCSI, and not freed by
+ * SCSI
+ */
+static void scsi_cleanup_rq(struct request *rq)
+{
+	if (rq->rq_flags & RQF_DONTPREP) {
+		scsi_mq_uninit_cmd(blk_mq_rq_to_pdu(rq));
+		rq->rq_flags &= ~RQF_DONTPREP;
+	}
+}
+
 /* Add a command to the list used by the aacraid and dpt_i2o drivers */
 void scsi_add_cmd_to_list(struct scsi_cmnd *cmd)
 {
@@ -1821,6 +1833,7 @@ static const struct blk_mq_ops scsi_mq_ops = {
 	.init_request	= scsi_mq_init_request,
 	.exit_request	= scsi_mq_exit_request,
 	.initialize_rq_fn = scsi_initialize_rq,
+	.cleanup_rq	= scsi_cleanup_rq,
 	.busy		= scsi_mq_lld_busy,
 	.map_queues	= scsi_map_queues,
 };

drivers/scsi/scsi_pm.c

@@ -94,8 +94,7 @@ static int scsi_dev_type_resume(struct device *dev,
 		if (!err && scsi_is_sdev_device(dev)) {
 			struct scsi_device *sdev = to_scsi_device(dev);
 
-			if (sdev->request_queue->dev)
-				blk_set_runtime_active(sdev->request_queue);
+			blk_set_runtime_active(sdev->request_queue);
 		}
 	}
 

drivers/scsi/sd.c

@@ -1293,7 +1293,9 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
-		return sd_zbc_setup_reset_cmnd(cmd);
+		return sd_zbc_setup_reset_cmnd(cmd, false);
+	case REQ_OP_ZONE_RESET_ALL:
+		return sd_zbc_setup_reset_cmnd(cmd, true);
 	default:
 		WARN_ON_ONCE(1);
 		return BLK_STS_NOTSUPP;
@@ -1959,6 +1961,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE_SAME:
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
 		if (!result) {
 			good_bytes = blk_rq_bytes(req);
 			scsi_set_resid(SCpnt, 0);

drivers/scsi/sd.h

@@ -209,7 +209,7 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
+extern blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
 extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
@@ -225,7 +225,8 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
 
 static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
 
-static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+static inline blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd,
+						   bool all)
 {
 	return BLK_STS_TARGET;
 }

drivers/scsi/sd_zbc.c

@@ -209,10 +209,11 @@ static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
 /**
  * sd_zbc_setup_reset_cmnd - Prepare a RESET WRITE POINTER scsi command.
  * @cmd: the command to setup
+ * @all: Reset all zones control.
  *
  * Called from sd_init_command() for a REQ_OP_ZONE_RESET request.
  */
-blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
+blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd, bool all)
 {
 	struct request *rq = cmd->request;
 	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
@@ -234,7 +235,10 @@ blk_status_t sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 	memset(cmd->cmnd, 0, cmd->cmd_len);
 	cmd->cmnd[0] = ZBC_OUT;
 	cmd->cmnd[1] = ZO_RESET_WRITE_POINTER;
-	put_unaligned_be64(block, &cmd->cmnd[2]);
+	if (all)
+		cmd->cmnd[14] = 0x1;
+	else
+		put_unaligned_be64(block, &cmd->cmnd[2]);
 
 	rq->timeout = SD_TIMEOUT;
 	cmd->sc_data_direction = DMA_NONE;
@@ -261,6 +265,7 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 
 	switch (req_op(rq)) {
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
 
 		if (result &&
 		    sshdr->sense_key == ILLEGAL_REQUEST &&
@@ -487,6 +492,9 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	/* The drive satisfies the kernel restrictions: set it up */
 	blk_queue_chunk_sectors(sdkp->disk->queue,
 			logical_to_sectors(sdkp->device, zone_blocks));
+	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, sdkp->disk->queue);
+	blk_queue_required_elevator_features(sdkp->disk->queue,
+					     ELEVATOR_F_ZBD_SEQ_WRITE);
 	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
 
 	/* READ16/WRITE16 is mandatory for ZBC disks */