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
  ...

5 files changed, 15 insertions, 28 deletions

diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index c891ada3c5c2..d85e6befa26b 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -61,6 +61,9 @@ struct scsi_pointer {
 /* flags preserved across unprep / reprep */
 #define SCMD_PRESERVED_FLAGS	(SCMD_UNCHECKED_ISA_DMA | SCMD_INITIALIZED)
 
+/* for scmd->state */
+#define SCMD_STATE_COMPLETE	0
+
 struct scsi_cmnd {
 	struct scsi_request req;
 	struct scsi_device *device;
@@ -145,6 +148,7 @@ struct scsi_cmnd {
 
 	int result;		/* Status code from lower level driver */
 	int flags;		/* Command flags */
+	unsigned long state;	/* Command completion state */
 
 	unsigned char tag;	/* SCSI-II queued command tag */
 };
@@ -171,7 +175,7 @@ extern void *scsi_kmap_atomic_sg(struct scatterlist *sg, int sg_count,
 				 size_t *offset, size_t *len);
 extern void scsi_kunmap_atomic_sg(void *virt);
 
-extern int scsi_init_io(struct scsi_cmnd *cmd);
+extern blk_status_t scsi_init_io(struct scsi_cmnd *cmd);
 
 #ifdef CONFIG_SCSI_DMA
 extern int scsi_dma_map(struct scsi_cmnd *cmd);
diff --git a/include/scsi/scsi_dh.h b/include/scsi/scsi_dh.h
index c7bba2b24849..a862dc23c68d 100644
--- a/include/scsi/scsi_dh.h
+++ b/include/scsi/scsi_dh.h
@@ -69,7 +69,7 @@ struct scsi_device_handler {
 	int (*attach)(struct scsi_device *);
 	void (*detach)(struct scsi_device *);
 	int (*activate)(struct scsi_device *, activate_complete, void *);
-	int (*prep_fn)(struct scsi_device *, struct request *);
+	blk_status_t (*prep_fn)(struct scsi_device *, struct request *);
 	int (*set_params)(struct scsi_device *, const char *);
 	void (*rescan)(struct scsi_device *);
 };
diff --git a/include/scsi/scsi_driver.h b/include/scsi/scsi_driver.h
index fae8b465233e..6dffa8555a39 100644
--- a/include/scsi/scsi_driver.h
+++ b/include/scsi/scsi_driver.h
@@ -2,6 +2,7 @@
 #ifndef _SCSI_SCSI_DRIVER_H
 #define _SCSI_SCSI_DRIVER_H
 
+#include <linux/blk_types.h>
 #include <linux/device.h>
 
 struct module;
@@ -13,7 +14,7 @@ struct scsi_driver {
 	struct device_driver	gendrv;
 
 	void (*rescan)(struct device *);
-	int (*init_command)(struct scsi_cmnd *);
+	blk_status_t (*init_command)(struct scsi_cmnd *);
 	void (*uninit_command)(struct scsi_cmnd *);
 	int (*done)(struct scsi_cmnd *);
 	int (*eh_action)(struct scsi_cmnd *, int);
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 5ea06d310a25..aa760df8c6b3 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -11,7 +11,6 @@
 #include <linux/blk-mq.h>
 #include <scsi/scsi.h>
 
-struct request_queue;
 struct block_device;
 struct completion;
 struct module;
@@ -22,7 +21,6 @@ struct scsi_target;
 struct Scsi_Host;
 struct scsi_host_cmd_pool;
 struct scsi_transport_template;
-struct blk_queue_tags;
 
 
 /*
@@ -547,14 +545,8 @@ struct Scsi_Host {
 	struct scsi_host_template *hostt;
 	struct scsi_transport_template *transportt;
 
-	/*
-	 * Area to keep a shared tag map (if needed, will be
-	 * NULL if not).
-	 */
-	union {
-		struct blk_queue_tag	*bqt;
-		struct blk_mq_tag_set	tag_set;
-	};
+	/* Area to keep a shared tag map */
+	struct blk_mq_tag_set	tag_set;
 
 	atomic_t host_busy;		   /* commands actually active on low-level */
 	atomic_t host_blocked;
@@ -648,7 +640,6 @@ struct Scsi_Host {
 	/* The controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
-	unsigned use_blk_mq:1;
 	unsigned use_cmd_list:1;
 
 	/* Host responded with short (<36 bytes) INQUIRY result */
@@ -742,11 +733,6 @@ static inline int scsi_host_in_recovery(struct Scsi_Host *shost)
 		shost->tmf_in_progress;
 }
 
-static inline bool shost_use_blk_mq(struct Scsi_Host *shost)
-{
-	return shost->use_blk_mq;
-}
-
 extern int scsi_queue_work(struct Scsi_Host *, struct work_struct *);
 extern void scsi_flush_work(struct Scsi_Host *);
 
diff --git a/include/scsi/scsi_tcq.h b/include/scsi/scsi_tcq.h
index e192a0caa850..6053d46e794e 100644
--- a/include/scsi/scsi_tcq.h
+++ b/include/scsi/scsi_tcq.h
@@ -23,19 +23,15 @@ static inline struct scsi_cmnd *scsi_host_find_tag(struct Scsi_Host *shost,
 		int tag)
 {
 	struct request *req = NULL;
+	u16 hwq;
 
 	if (tag == SCSI_NO_TAG)
 		return NULL;
 
-	if (shost_use_blk_mq(shost)) {
-		u16 hwq = blk_mq_unique_tag_to_hwq(tag);
-
-		if (hwq < shost->tag_set.nr_hw_queues) {
-			req = blk_mq_tag_to_rq(shost->tag_set.tags[hwq],
-				blk_mq_unique_tag_to_tag(tag));
-		}
-	} else {
-		req = blk_map_queue_find_tag(shost->bqt, tag);
+	hwq = blk_mq_unique_tag_to_hwq(tag);
+	if (hwq < shost->tag_set.nr_hw_queues) {
+		req = blk_mq_tag_to_rq(shost->tag_set.tags[hwq],
+					blk_mq_unique_tag_to_tag(tag));
 	}
 
 	if (!req)