scsi: add support for a blk-mq based I/O path.

This patch adds support for an alternate I/O path in the scsi midlayer
which uses the blk-mq infrastructure instead of the legacy request code.

Use of blk-mq is fully transparent to drivers, although for now a host
template field is provided to opt out of blk-mq usage in case any unforseen
incompatibilities arise.

In general replacing the legacy request code with blk-mq is a simple and
mostly mechanical transformation.  The biggest exception is the new code
that deals with the fact the I/O submissions in blk-mq must happen from
process context, which slightly complicates the I/O completion handler.
The second biggest differences is that blk-mq is build around the concept
of preallocated requests that also include driver specific data, which
in SCSI context means the scsi_cmnd structure.  This completely avoids
dynamic memory allocations for the fast path through I/O submission.

Due the preallocated requests the MQ code path exclusively uses the
host-wide shared tag allocator instead of a per-LUN one.  This only
affects drivers actually using the block layer provided tag allocator
instead of their own.  Unlike the old path blk-mq always provides a tag,
although drivers don't have to use it.

For now the blk-mq path is disable by defauly and must be enabled using
the "use_blk_mq" module parameter.  Once the remaining work in the block
layer to make blk-mq more suitable for slow devices is complete I hope
to make it the default and eventually even remove the old code path.

Based on the earlier scsi-mq prototype by Nicholas Bellinger.

Thanks to Bart Van Assche and Robert Elliot for testing, benchmarking and
various sugestions and code contributions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Webb Scales <webbnh@hp.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Tested-by: Robert Elliott <elliott@hp.com>

drivers/scsi/hosts.c

@@ -213,9 +213,24 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 		goto fail;
 	}
 
+	if (shost_use_blk_mq(shost)) {
+		error = scsi_mq_setup_tags(shost);
+		if (error)
+			goto fail;
+	}
+
+	/*
+	 * Note that we allocate the freelist even for the MQ case for now,
+	 * as we need a command set aside for scsi_reset_provider.  Having
+	 * the full host freelist and one command available for that is a
+	 * little heavy-handed, but avoids introducing a special allocator
+	 * just for this.  Eventually the structure of scsi_reset_provider
+	 * will need a major overhaul.
+	 */
 	error = scsi_setup_command_freelist(shost);
 	if (error)
-		goto fail;
+		goto out_destroy_tags;
+
 
 	if (!shost->shost_gendev.parent)
 		shost->shost_gendev.parent = dev ? dev : &platform_bus;
@@ -226,7 +241,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	error = device_add(&shost->shost_gendev);
 	if (error)
-		goto out;
+		goto out_destroy_freelist;
 
 	pm_runtime_set_active(&shost->shost_gendev);
 	pm_runtime_enable(&shost->shost_gendev);
@@ -279,8 +294,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	device_del(&shost->shost_dev);
  out_del_gendev:
 	device_del(&shost->shost_gendev);
- out:
+ out_destroy_freelist:
 	scsi_destroy_command_freelist(shost);
+ out_destroy_tags:
+	if (shost_use_blk_mq(shost))
+		scsi_mq_destroy_tags(shost);
  fail:
 	return error;
 }
@@ -309,8 +327,13 @@ static void scsi_host_dev_release(struct device *dev)
 	}
 
 	scsi_destroy_command_freelist(shost);
-	if (shost->bqt)
-		blk_free_tags(shost->bqt);
+	if (shost_use_blk_mq(shost)) {
+		if (shost->tag_set.tags)
+			scsi_mq_destroy_tags(shost);
+	} else {
+		if (shost->bqt)
+			blk_free_tags(shost->bqt);
+	}
 
 	kfree(shost->shost_data);
 
@@ -436,6 +459,8 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	else
 		shost->dma_boundary = 0xffffffff;
 
+	shost->use_blk_mq = scsi_use_blk_mq && !shost->hostt->disable_blk_mq;
+
 	device_initialize(&shost->shost_gendev);
 	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
 	shost->shost_gendev.bus = &scsi_bus_type;

drivers/scsi/scsi.c

@@ -805,7 +805,7 @@ void scsi_adjust_queue_depth(struct scsi_device *sdev, int tagged, int tags)
 	 * is more IO than the LLD's can_queue (so there are not enuogh
 	 * tags) request_fn's host queue ready check will handle it.
 	 */
-	if (!sdev->host->bqt) {
+	if (!shost_use_blk_mq(sdev->host) && !sdev->host->bqt) {
 		if (blk_queue_tagged(sdev->request_queue) &&
 		    blk_queue_resize_tags(sdev->request_queue, tags) != 0)
 			goto out;
@@ -1361,6 +1361,9 @@ MODULE_LICENSE("GPL");
 module_param(scsi_logging_level, int, S_IRUGO|S_IWUSR);
 MODULE_PARM_DESC(scsi_logging_level, "a bit mask of logging levels");
 
+bool scsi_use_blk_mq = false;
+module_param_named(use_blk_mq, scsi_use_blk_mq, bool, S_IWUSR | S_IRUGO);
+
 static int __init init_scsi(void)
 {
 	int error;

drivers/scsi/scsi_priv.h

@@ -88,6 +88,9 @@ extern void scsi_next_command(struct scsi_cmnd *cmd);
 extern void scsi_io_completion(struct scsi_cmnd *, unsigned int);
 extern void scsi_run_host_queues(struct Scsi_Host *shost);
 extern struct request_queue *scsi_alloc_queue(struct scsi_device *sdev);
+extern struct request_queue *scsi_mq_alloc_queue(struct scsi_device *sdev);
+extern int scsi_mq_setup_tags(struct Scsi_Host *shost);
+extern void scsi_mq_destroy_tags(struct Scsi_Host *shost);
 extern int scsi_init_queue(void);
 extern void scsi_exit_queue(void);
 struct request_queue;

drivers/scsi/scsi_scan.c

@@ -273,7 +273,10 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	 */
 	sdev->borken = 1;
 
-	sdev->request_queue = scsi_alloc_queue(sdev);
+	if (shost_use_blk_mq(shost))
+		sdev->request_queue = scsi_mq_alloc_queue(sdev);
+	else
+		sdev->request_queue = scsi_alloc_queue(sdev);
 	if (!sdev->request_queue) {
 		/* release fn is set up in scsi_sysfs_device_initialise, so
 		 * have to free and put manually here */

drivers/scsi/scsi_sysfs.c

@@ -333,6 +333,7 @@ store_shost_eh_deadline(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR(eh_deadline, S_IRUGO | S_IWUSR, show_shost_eh_deadline, store_shost_eh_deadline);
 
+shost_rd_attr(use_blk_mq, "%d\n");
 shost_rd_attr(unique_id, "%u\n");
 shost_rd_attr(cmd_per_lun, "%hd\n");
 shost_rd_attr(can_queue, "%hd\n");
@@ -352,6 +353,7 @@ show_host_busy(struct device *dev, struct device_attribute *attr, char *buf)
 static DEVICE_ATTR(host_busy, S_IRUGO, show_host_busy, NULL);
 
 static struct attribute *scsi_sysfs_shost_attrs[] = {
+	&dev_attr_use_blk_mq.attr,
 	&dev_attr_unique_id.attr,
 	&dev_attr_host_busy.attr,
 	&dev_attr_cmd_per_lun.attr,

include/scsi/scsi_host.h

@@ -7,6 +7,7 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <linux/seq_file.h>
+#include <linux/blk-mq.h>
 #include <scsi/scsi.h>
 
 struct request_queue;
@@ -510,6 +511,9 @@ struct scsi_host_template {
 	 */
 	unsigned int cmd_size;
 	struct scsi_host_cmd_pool *cmd_pool;
+
+	/* temporary flag to disable blk-mq I/O path */
+	bool disable_blk_mq;
 };
 
 /*
@@ -580,7 +584,10 @@ struct Scsi_Host {
 	 * Area to keep a shared tag map (if needed, will be
 	 * NULL if not).
 	 */
-	struct blk_queue_tag	*bqt;
+	union {
+		struct blk_queue_tag	*bqt;
+		struct blk_mq_tag_set	tag_set;
+	};
 
 	atomic_t host_busy;		   /* commands actually active on low-level */
 	atomic_t host_blocked;
@@ -672,6 +679,8 @@ struct Scsi_Host {
 	/* The controller does not support WRITE SAME */
 	unsigned no_write_same:1;
 
+	unsigned use_blk_mq:1;
+
 	/*
 	 * Optional work queue to be utilized by the transport
 	 */
@@ -772,6 +781,13 @@ static inline int scsi_host_in_recovery(struct Scsi_Host *shost)
 		shost->tmf_in_progress;
 }
 
+extern bool scsi_use_blk_mq;
+
+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 *);
 

include/scsi/scsi_tcq.h

@@ -67,7 +67,8 @@ static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
 	if (!sdev->tagged_supported)
 		return;
 
-	if (!blk_queue_tagged(sdev->request_queue))
+	if (!shost_use_blk_mq(sdev->host) &&
+	    blk_queue_tagged(sdev->request_queue))
 		blk_queue_init_tags(sdev->request_queue, depth,
 				    sdev->host->bqt);
 
@@ -80,7 +81,8 @@ static inline void scsi_activate_tcq(struct scsi_device *sdev, int depth)
  **/
 static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
 {
-	if (blk_queue_tagged(sdev->request_queue))
+	if (!shost_use_blk_mq(sdev->host) &&
+	    blk_queue_tagged(sdev->request_queue))
 		blk_queue_free_tags(sdev->request_queue);
 	scsi_adjust_queue_depth(sdev, 0, depth);
 }
@@ -108,6 +110,15 @@ static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 	return 0;
 }
 
+static inline struct scsi_cmnd *scsi_mq_find_tag(struct Scsi_Host *shost,
+		unsigned int hw_ctx, int tag)
+{
+	struct request *req;
+
+	req = blk_mq_tag_to_rq(shost->tag_set.tags[hw_ctx], tag);
+	return req ? (struct scsi_cmnd *)req->special : NULL;
+}
+
 /**
  * scsi_find_tag - find a tagged command by device
  * @SDpnt:	pointer to the ScSI device
@@ -118,10 +129,12 @@ static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
  **/
 static inline struct scsi_cmnd *scsi_find_tag(struct scsi_device *sdev, int tag)
 {
-
         struct request *req;
 
         if (tag != SCSI_NO_TAG) {
+		if (shost_use_blk_mq(sdev->host))
+			return scsi_mq_find_tag(sdev->host, 0, tag);
+
         	req = blk_queue_find_tag(sdev->request_queue, tag);
 	        return req ? (struct scsi_cmnd *)req->special : NULL;
 	}
@@ -130,6 +143,7 @@ static inline struct scsi_cmnd *scsi_find_tag(struct scsi_device *sdev, int tag)
 	return sdev->current_cmnd;
 }
 
+
 /**
  * scsi_init_shared_tag_map - create a shared tag map
  * @shost:	the host to share the tag map among all devices
@@ -137,6 +151,12 @@ static inline struct scsi_cmnd *scsi_find_tag(struct scsi_device *sdev, int tag)
  */
 static inline int scsi_init_shared_tag_map(struct Scsi_Host *shost, int depth)
 {
+	/*
+	 * We always have a shared tag map around when using blk-mq.
+	 */
+	if (shost_use_blk_mq(shost))
+		return 0;
+
 	/*
 	 * If the shared tag map isn't already initialized, do it now.
 	 * This saves callers from having to check ->bqt when setting up
@@ -165,6 +185,8 @@ static inline struct scsi_cmnd *scsi_host_find_tag(struct Scsi_Host *shost,
 	struct request *req;
 
 	if (tag != SCSI_NO_TAG) {
+		if (shost_use_blk_mq(shost))
+			return scsi_mq_find_tag(shost, 0, tag);
 		req = blk_map_queue_find_tag(shost->bqt, tag);
 		return req ? (struct scsi_cmnd *)req->special : NULL;
 	}