# git diff
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..92d60a5e1d15 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1465,7 +1465,13 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
        if (unlikely(blk_mq_hctx_stopped(hctx)))
                return;
 
-       if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
+       /*
+        * Some single-queue devices may need to dispatch IO in order
+        * which was guaranteed for the legacy queue via the big queue
+        * lock. Now we reply on single hctx->run_work for that.
+        */
+       if (!async && !(hctx->flags & (BLK_MQ_F_BLOCKING |
+                                       BLK_MQ_F_STRICT_DISPATCH_ORDER))) {
                int cpu = get_cpu();
                if (cpumask_test_cpu(cpu, hctx->cpumask)) {
                        __blk_mq_run_hw_queue(hctx);
@@ -3055,6 +3061,10 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
        if (!set->ops->get_budget ^ !set->ops->put_budget)
                return -EINVAL;
 
+       if (set->queue_depth > 1 && (set->flags &
+                               BLK_MQ_F_STRICT_DISPATCH_ORDER))
+               return -EINVAL;
+
        if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
                pr_info("blk-mq: reduced tag depth to %u\n",
                        BLK_MQ_MAX_DEPTH);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 91c007d26c1e..f013630275c9 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1902,6 +1902,9 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
        shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
        shost->tag_set.flags |=
                BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
+       if (shost->hostt->strict_dispatch_order)
+               shost->tag_set.flags |= BLK_MQ_F_STRICT_DISPATCH_ORDER;
+
        shost->tag_set.driver_data = shost;
 
        return blk_mq_alloc_tag_set(&shost->tag_set);
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 54a3c8195c96..df1674d7f0fc 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -651,6 +651,18 @@ static const struct scsi_host_template usb_stor_host_template = {
        /* we do our own delay after a device or bus reset */
        .skip_settle_delay =            1,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..92d60a5e1d15 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1465,7 +1465,13 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
        if (unlikely(blk_mq_hctx_stopped(hctx)))
                return;
 
-       if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
+       /*
+        * Some single-queue devices may need to dispatch IO in order
+        * which was guaranteed for the legacy queue via the big queue
+        * lock. Now we reply on single hctx->run_work for that.
+        */
+       if (!async && !(hctx->flags & (BLK_MQ_F_BLOCKING |
+                                       BLK_MQ_F_STRICT_DISPATCH_ORDER))) {
                int cpu = get_cpu();
                if (cpumask_test_cpu(cpu, hctx->cpumask)) {
                        __blk_mq_run_hw_queue(hctx);
@@ -3055,6 +3061,10 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
        if (!set->ops->get_budget ^ !set->ops->put_budget)
                return -EINVAL;
 
+       if (set->queue_depth > 1 && (set->flags &
+                               BLK_MQ_F_STRICT_DISPATCH_ORDER))
+               return -EINVAL;
+
        if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
                pr_info("blk-mq: reduced tag depth to %u\n",
                        BLK_MQ_MAX_DEPTH);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 91c007d26c1e..f013630275c9 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1902,6 +1902,9 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
        shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
        shost->tag_set.flags |=
                BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy);
+       if (shost->hostt->strict_dispatch_order)
+               shost->tag_set.flags |= BLK_MQ_F_STRICT_DISPATCH_ORDER;
+
        shost->tag_set.driver_data = shost;
 
        return blk_mq_alloc_tag_set(&shost->tag_set);
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 54a3c8195c96..df1674d7f0fc 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -651,6 +651,18 @@ static const struct scsi_host_template usb_stor_host_template = {
        /* we do our own delay after a device or bus reset */
        .skip_settle_delay =            1,
 
+
+       /*
+        * Some USB storage, such as Kingston Technology DataTraveler 100
+        * G3/G4/SE9 G2(ID 0951:1666), requires IO dispatched in the
+        * sequential order, otherwise IO performance may drop drastically.
+        *
+        * can_queue is always 1, so we set .strict_dispatch_order for
+        * USB mass storage HBA. Another reason is that there can be such
+        * kind of devices too.
+        */
+       .strict_dispatch_order =        1,
+
        /* sysfs device attributes */
        .sdev_attrs =                   sysfs_device_attr_list,
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 0bf056de5cc3..89b1c28da36a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -226,6 +226,7 @@ struct blk_mq_ops {
 enum {
        BLK_MQ_F_SHOULD_MERGE   = 1 << 0,
        BLK_MQ_F_TAG_SHARED     = 1 << 1,
+       BLK_MQ_F_STRICT_DISPATCH_ORDER  = 1 << 2,
        BLK_MQ_F_BLOCKING       = 1 << 5,
        BLK_MQ_F_NO_SCHED       = 1 << 6,
        BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 31e0d6ca1eba..dbcbc9ef6993 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -442,6 +442,13 @@ struct scsi_host_template {
        /* True if the low-level driver supports blk-mq only */
        unsigned force_blk_mq:1;
 
+       /*
+        * True if the low-level driver needs IO to be dispatched in
+        * the order provided by legacy IO path. The flag is only
+        * valid for single queue device.
+        */
+       unsigned strict_dispatch_order:1;
+
        /*
         * Countdown for host blocking with no commands outstanding.
         */