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 <[email protected]>
Reviewed-by: Martin K. Petersen <[email protected]>
Reviewed-by: Hannes Reinecke <[email protected]>
Reviewed-by: Webb Scales <[email protected]>
Acked-by: Jens Axboe <[email protected]>
Tested-by: Bart Van Assche <[email protected]>
Tested-by: Robert Elliott <[email protected]>

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;