[PATCH 0/5] Multiqueue virtio-scsi

@@ -296,7 +296,7 @@ static struct virtqueue *lg_find_vq(struct virtio_device *vdev,
 	 * to 'true': the host just a(nother) SMP CPU, so we only need inter-cpu
 	 * barriers.
 	 */
-	vq = vring_new_virtqueue(lvq->config.num, LGUEST_VRING_ALIGN, vdev,
+	vq = vring_new_virtqueue(index, lvq->config.num, LGUEST_VRING_ALIGN, vdev,
 				 true, lvq->pages, lg_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;

@@ -103,7 +103,7 @@ static struct virtqueue *rp_find_vq(struct virtio_device *vdev,
 	 * Create the new vq, and tell virtio we're not interested in
 	 * the 'weak' smp barriers, since we're talking with a real device.
 	 */
-	vq = vring_new_virtqueue(len, rvring->align, vdev, false, addr,
+	vq = vring_new_virtqueue(id, len, rvring->align, vdev, false, addr,
 					rproc_virtio_notify, callback, name);
 	if (!vq) {
 		dev_err(dev, "vring_new_virtqueue %s failed\n", name);

@@ -198,7 +198,7 @@ static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
 	if (err)
 		goto out;
 
-	vq = vring_new_virtqueue(config->num, KVM_S390_VIRTIO_RING_ALIGN,
+	vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN,
 				 vdev, true, (void *) config->address,
 				 kvm_notify, callback, name);
 	if (!vq) {

@@ -131,9 +131,6 @@ struct virtio_mmio_vq_info {
 	/* the number of entries in the queue */
 	unsigned int num;
 
-	/* the index of the queue */
-	int queue_index;
-
 	/* the virtual address of the ring queue */
 	void *queue;
 

@@ -225,11 +222,10 @@ static void vm_reset(struct virtio_device *vdev)
 static void vm_notify(struct virtqueue *vq)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
-	struct virtio_mmio_vq_info *info = vq->priv;
 
 	/* We write the queue's selector into the notification register to
 	 * signal the other end */
-	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
+	writel(virtqueue_get_queue_index(vq), vm_dev->base + VIRTIO_MMIO_QUEUE_NOTIFY);
 }
 
 /* Notify all virtqueues on an interrupt. */

@@ -270,6 +266,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
 	struct virtio_mmio_vq_info *info = vq->priv;
 	unsigned long flags, size;
+	unsigned int index = virtqueue_get_queue_index(vq);
 
 	spin_lock_irqsave(&vm_dev->lock, flags);
 	list_del(&info->node);

@@ -278,7 +275,7 @@ static void vm_del_vq(struct virtqueue *vq)
 	vring_del_virtqueue(vq);
 
 	/* Select and deactivate the queue */
-	writel(info->queue_index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
+	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
 	writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 
 	size = PAGE_ALIGN(vring_size(info->num, VIRTIO_MMIO_VRING_ALIGN));

@@ -324,7 +321,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 		err = -ENOMEM;
 		goto error_kmalloc;
 	}
-	info->queue_index = index;
 
 	/* Allocate pages for the queue - start with a queue as big as
 	 * possible (limited by maximum size allowed by device), drop down

@@ -356,7 +352,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 			vm_dev->base + VIRTIO_MMIO_QUEUE_PFN);
 
 	/* Create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_MMIO_VRING_ALIGN, vdev,
 				 true, info->queue, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;

@@ -79,9 +79,6 @@ struct virtio_pci_vq_info
 	/* the number of entries in the queue */
 	int num;
 
-	/* the index of the queue */
-	int queue_index;
-
 	/* the virtual address of the ring queue */
 	void *queue;
 

@@ -202,11 +199,11 @@ static void vp_reset(struct virtio_device *vdev)
 static void vp_notify(struct virtqueue *vq)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
-	struct virtio_pci_vq_info *info = vq->priv;
 
 	/* we write the queue's selector into the notification register to
 	 * signal the other end */
-	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
+	iowrite16(virtqueue_get_queue_index(vq),
+		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY);
 }
 
 /* Handle a configuration change: Tell driver if it wants to know. */

@@ -402,7 +399,6 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	info->queue_index = index;
 	info->num = num;
 	info->msix_vector = msix_vec;
 

@@ -418,7 +414,7 @@ static struct virtqueue *setup_vq(struct virtio_device *vdev, unsigned index,
 		  vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
 
 	/* create the vring */
-	vq = vring_new_virtqueue(info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
+	vq = vring_new_virtqueue(index, info->num, VIRTIO_PCI_VRING_ALIGN, vdev,
 				 true, info->queue, vp_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;

@@ -467,7 +463,8 @@ static void vp_del_vq(struct virtqueue *vq)
 	list_del(&info->node);
 	spin_unlock_irqrestore(&vp_dev->lock, flags);
 
-	iowrite16(info->queue_index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+	iowrite16(virtqueue_get_queue_index(vq),
+		vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
 
 	if (vp_dev->msix_enabled) {
 		iowrite16(VIRTIO_MSI_NO_VECTOR,

@@ -106,6 +106,9 @@ struct vring_virtqueue
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	void (*notify)(struct virtqueue *vq);
 
+	/* Index of the queue */
+	int queue_index;
+
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
 	unsigned int in_use;

@@ -171,6 +174,13 @@ static int vring_add_indirect(struct vring_virtqueue *vq,
 	return head;
 }
 
+int virtqueue_get_queue_index(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	return vq->queue_index;
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_queue_index);
+
 /**
  * virtqueue_add_buf - expose buffer to other end
  * @vq: the struct virtqueue we're talking about.

@@ -616,7 +626,8 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
-struct virtqueue *vring_new_virtqueue(unsigned int num,
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,

@@ -647,6 +658,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 	vq->broken = false;
 	vq->last_used_idx = 0;
 	vq->num_added = 0;
+	vq->queue_index = index;
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;

@@ -50,6 +50,8 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
 
+int virtqueue_get_queue_index(struct virtqueue *vq);
+
 /**
  * virtio_device - representation of a device using virtio
  * @index: unique position on the virtio bus

@@ -165,7 +165,8 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
 struct virtio_device;
 struct virtqueue;
 
-struct virtqueue *vring_new_virtqueue(unsigned int num,
+struct virtqueue *vring_new_virtqueue(unsigned int index,
+				      unsigned int num,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,

@@ -48,6 +48,7 @@ struct virtio_pci_device
 	int msix_enabled;
 	int intx_enabled;
 	struct msix_entry *msix_entries;
+	cpumask_var_t *msix_affinity_masks;
 	/* Name strings for interrupts. This size should be enough,
 	 * and I'm too lazy to allocate each name separately. */
 	char (*msix_names)[256];

@@ -276,6 +277,10 @@ static void vp_free_vectors(struct virtio_device *vdev)
 	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
 		free_irq(vp_dev->msix_entries[i].vector, vp_dev);
 
+	for (i = 0; i < vp_dev->msix_vectors; i++)
+		if (vp_dev->msix_affinity_masks[i])
+			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+
 	if (vp_dev->msix_enabled) {
 		/* Disable the vector used for configuration */
 		iowrite16(VIRTIO_MSI_NO_VECTOR,

@@ -293,6 +298,8 @@ static void vp_free_vectors(struct virtio_device *vdev)
 	vp_dev->msix_names = NULL;
 	kfree(vp_dev->msix_entries);
 	vp_dev->msix_entries = NULL;
+	kfree(vp_dev->msix_affinity_masks);
+	vp_dev->msix_affinity_masks = NULL;
 }
 
 static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,

@@ -311,6 +318,15 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors,
 				     GFP_KERNEL);
 	if (!vp_dev->msix_names)
 		goto error;
+	vp_dev->msix_affinity_masks
+		= kzalloc(nvectors * sizeof *vp_dev->msix_affinity_masks,
+			  GFP_KERNEL);
+	if (!vp_dev->msix_affinity_masks)
+		goto error;
+	for (i = 0; i < nvectors; ++i)
+		if (!alloc_cpumask_var(&vp_dev->msix_affinity_masks[i],
+					GFP_KERNEL))
+			goto error;
 
 	for (i = 0; i < nvectors; ++i)
 		vp_dev->msix_entries[i].entry = i;

@@ -607,6 +623,35 @@ static const char *vp_bus_name(struct virtio_device *vdev)
 	return pci_name(vp_dev->pci_dev);
 }
 
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+{
+	struct virtio_device *vdev = vq->vdev;
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtio_pci_vq_info *info = vq->priv;
+	struct cpumask *mask;
+	unsigned int irq;
+
+	if (!vq->callback)
+		return -EINVAL;
+
+	if (vp_dev->msix_enabled) {
+		mask = vp_dev->msix_affinity_masks[info->msix_vector];
+		irq = vp_dev->msix_entries[info->msix_vector].vector;
+		if (cpu == -1)
+			irq_set_affinity_hint(irq, NULL);
+		else {
+			cpumask_set_cpu(cpu, mask);
+			irq_set_affinity_hint(irq, mask);
+		}
+	}
+	return 0;
+}
+
 static struct virtio_config_ops virtio_pci_config_ops = {
 	.get		= vp_get,
 	.set		= vp_set,

@@ -618,6 +663,7 @@ static struct virtio_config_ops virtio_pci_config_ops = {
 	.get_features	= vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
+	.set_vq_affinity = vp_set_vq_affinity,
 };
 
 static void virtio_pci_release_dev(struct device *_d)

@@ -98,6 +98,7 @@
  *	vdev: the virtio_device
  *      This returns a pointer to the bus name a la pci_name from which
  *      the caller can then copy.
+ * @set_vq_affinity: set the affinity for a virtqueue.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {

@@ -116,6 +117,7 @@ struct virtio_config_ops {
 	u32 (*get_features)(struct virtio_device *vdev);
 	void (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
+	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */

@@ -190,5 +192,24 @@ const char *virtio_bus_name(struct virtio_device *vdev)
 	return vdev->config->bus_name(vdev);
 }
 
+/**
+ * virtqueue_set_affinity - setting affinity for a virtqueue
+ * @vq: the virtqueue
+ * @cpu: the cpu no.
+ *
+ * Pay attention the function are best-effort: the affinity hint may not be set
+ * due to config support, irq type and sharing.
+ *
+ */
+static inline
+int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
+{
+	struct virtio_device *vdev = vq->vdev;
+	if (vdev->config->set_vq_affinity)
+		return vdev->config->set_vq_affinity(vq, cpu);
+	return 0;
+}
+
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_VIRTIO_CONFIG_H */

@@ -77,7 +77,7 @@ struct virtio_scsi {
 	/* Get some buffers ready for event vq */
 	struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN];
 
-	struct virtio_scsi_target_state *tgt[];
+	struct virtio_scsi_target_state **tgt;
 };
 
 static struct kmem_cache *virtscsi_cmd_cache;

@@ -615,10 +615,13 @@ static void virtscsi_remove_vqs(struct virtio_device *vdev)
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	num_targets = sh->max_id;
-	for (i = 0; i < num_targets; i++) {
-		kfree(vscsi->tgt[i]);
-		vscsi->tgt[i] = NULL;
+	if (vscsi->tgt) {
+		num_targets = sh->max_id;
+		for (i = 0; i < num_targets; i++) {
+			kfree(vscsi->tgt[i]);
+			vscsi->tgt[i] = NULL;
+		}
+		kfree(vscsi->tgt);
 	}
 
 	vdev->config->del_vqs(vdev);

@@ -660,6 +663,12 @@ static int virtscsi_init(struct virtio_device *vdev,
 	/* We need to know how many segments before we allocate.  */
 	sg_elems = virtscsi_config_get(vdev, seg_max) ?: 1;
 
+	vscsi->tgt = kmalloc(num_targets *
+			sizeof(struct virtio_scsi_target_state *), GFP_KERNEL);
+	if (!vscsi->tgt) {
+		err = -ENOMEM;
+		goto out;
+	}
 	for (i = 0; i < num_targets; i++) {
 		vscsi->tgt[i] = virtscsi_alloc_tgt(vdev, sg_elems);
 		if (!vscsi->tgt[i]) {

@@ -685,9 +694,7 @@ static int __devinit virtscsi_probe(struct virtio_device *vdev)
 
 	/* Allocate memory and link the structs together.  */
 	num_targets = virtscsi_config_get(vdev, max_target) + 1;
-	shost = scsi_host_alloc(&virtscsi_host_template,
-		sizeof(*vscsi)
-		+ num_targets * sizeof(struct virtio_scsi_target_state));
+	shost = scsi_host_alloc(&virtscsi_host_template, sizeof(*vscsi));
 
 	if (!shost)
 		return -ENOMEM;

@@ -107,7 +107,7 @@ static void virtscsi_compute_resid(struct scsi_cmnd *sc, u32 resid)
  *
  * Called with vq_lock held.
  */
-static void virtscsi_complete_cmd(void *buf)
+static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_cmd *cmd = buf;
 	struct scsi_cmnd *sc = cmd->sc;

@@ -168,7 +168,8 @@ static void virtscsi_complete_cmd(void *buf)
 	sc->scsi_done(sc);
 }
 
-static void virtscsi_vq_done(struct virtqueue *vq, void (*fn)(void *buf))
+static void virtscsi_vq_done(struct virtio_scsi *vscsi, struct virtqueue *vq,
+			     void (*fn)(struct virtio_scsi *vscsi, void *buf))
 {
 	void *buf;
 	unsigned int len;

@@ -176,7 +177,7 @@ static void virtscsi_vq_done(struct virtqueue *vq, void (*fn)(void *buf))
 	do {
 		virtqueue_disable_cb(vq);
 		while ((buf = virtqueue_get_buf(vq, &len)) != NULL)
-			fn(buf);
+			fn(vscsi, buf);
 	} while (!virtqueue_enable_cb(vq));
 }
 

@@ -187,11 +188,11 @@ static void virtscsi_req_done(struct virtqueue *vq)
 	unsigned long flags;
 
 	spin_lock_irqsave(&vscsi->req_vq.vq_lock, flags);
-	virtscsi_vq_done(vq, virtscsi_complete_cmd);
+	virtscsi_vq_done(vscsi, vq, virtscsi_complete_cmd);
 	spin_unlock_irqrestore(&vscsi->req_vq.vq_lock, flags);
 };
 
-static void virtscsi_complete_free(void *buf)
+static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_cmd *cmd = buf;
 

@@ -208,7 +209,7 @@ static void virtscsi_ctrl_done(struct virtqueue *vq)
 	unsigned long flags;
 
 	spin_lock_irqsave(&vscsi->ctrl_vq.vq_lock, flags);
-	virtscsi_vq_done(vq, virtscsi_complete_free);
+	virtscsi_vq_done(vscsi, vq, virtscsi_complete_free);
 	spin_unlock_irqrestore(&vscsi->ctrl_vq.vq_lock, flags);
 };
 

@@ -331,7 +332,7 @@ static void virtscsi_handle_event(struct work_struct *work)
 	virtscsi_kick_event(vscsi, event_node);
 }
 
-static void virtscsi_complete_event(void *buf)
+static void virtscsi_complete_event(struct virtio_scsi *vscsi, void *buf)
 {
 	struct virtio_scsi_event_node *event_node = buf;
 

@@ -346,7 +347,7 @@ static void virtscsi_event_done(struct virtqueue *vq)
 	unsigned long flags;
 
 	spin_lock_irqsave(&vscsi->event_vq.vq_lock, flags);
-	virtscsi_vq_done(vq, virtscsi_complete_event);
+	virtscsi_vq_done(vscsi, vq, virtscsi_complete_event);
 	spin_unlock_irqrestore(&vscsi->event_vq.vq_lock, flags);
 };
 

@@ -26,6 +26,7 @@
 
 #define VIRTIO_SCSI_MEMPOOL_SZ 64
 #define VIRTIO_SCSI_EVENT_LEN 8
+#define VIRTIO_SCSI_VQ_BASE 2
 
 /* Command queue element */
 struct virtio_scsi_cmd {

@@ -59,9 +60,13 @@ struct virtio_scsi_vq {
 
 /* Per-target queue state */
 struct virtio_scsi_target_state {
-	/* Protects sg.  Lock hierarchy is tgt_lock -> vq_lock.  */
+	/* Protects sg, req_vq.  Lock hierarchy is tgt_lock -> vq_lock.  */
 	spinlock_t tgt_lock;
 
+	struct virtio_scsi_vq *req_vq;
+
+	atomic_t reqs;
+
 	/* For sglist construction when adding commands to the virtqueue.  */
 	struct scatterlist sg[];
 };

@@ -70,14 +75,15 @@ struct virtio_scsi_target_state {
 struct virtio_scsi {
 	struct virtio_device *vdev;
 
-	struct virtio_scsi_vq ctrl_vq;
-	struct virtio_scsi_vq event_vq;
-	struct virtio_scsi_vq req_vq;
-
 	/* Get some buffers ready for event vq */
 	struct virtio_scsi_event_node event_list[VIRTIO_SCSI_EVENT_LEN];
 
+	u32 num_queues;
 	struct virtio_scsi_target_state **tgt;
+
+	struct virtio_scsi_vq ctrl_vq;
+	struct virtio_scsi_vq event_vq;
+	struct virtio_scsi_vq req_vqs[];
 };
 
 static struct kmem_cache *virtscsi_cmd_cache;

@@ -112,6 +118,9 @@ static void virtscsi_complete_cmd(struct virtio_scsi *vscsi, void *buf)
 	struct virtio_scsi_cmd *cmd = buf;
 	struct scsi_cmnd *sc = cmd->sc;
 	struct virtio_scsi_cmd_resp *resp = &cmd->resp.cmd;
+	struct virtio_scsi_target_state *tgt = vscsi->tgt[sc->device->id];
+
+	atomic_dec(&tgt->reqs);
 
 	dev_dbg(&sc->device->sdev_gendev,
 		"cmd %p response %u status %#02x sense_len %u\n",

@@ -185,11 +194,13 @@ static void virtscsi_req_done(struct virtqueue *vq)
 {
 	struct Scsi_Host *sh = virtio_scsi_host(vq->vdev);
 	struct virtio_scsi *vscsi = shost_priv(sh);
+	int index = virtqueue_get_queue_index(vq) - VIRTIO_SCSI_VQ_BASE;
+	struct virtio_scsi_vq *req_vq = &vscsi->req_vqs[index];
 	unsigned long flags;
 
-	spin_lock_irqsave(&vscsi->req_vq.vq_lock, flags);
+	spin_lock_irqsave(&req_vq->vq_lock, flags);
 	virtscsi_vq_done(vscsi, vq, virtscsi_complete_cmd);
-	spin_unlock_irqrestore(&vscsi->req_vq.vq_lock, flags);
+	spin_unlock_irqrestore(&req_vq->vq_lock, flags);
 };
 
 static void virtscsi_complete_free(struct virtio_scsi *vscsi, void *buf)

@@ -429,10 +440,10 @@ static int virtscsi_kick_cmd(struct virtio_scsi_target_state *tgt,
 	return ret;
 }
 
-static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
+static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
+				 struct virtio_scsi_target_state *tgt,
+				 struct scsi_cmnd *sc)
 {
-	struct virtio_scsi *vscsi = shost_priv(sh);
-	struct virtio_scsi_target_state *tgt = vscsi->tgt[sc->device->id];
 	struct virtio_scsi_cmd *cmd;
 	int ret;
 

@@ -466,7 +477,7 @@ static int virtscsi_queuecommand(struct Scsi_Host *sh, struct scsi_cmnd *sc)
 	BUG_ON(sc->cmd_len > VIRTIO_SCSI_CDB_SIZE);
 	memcpy(cmd->req.cmd.cdb, sc->cmnd, sc->cmd_len);
 
-	if (virtscsi_kick_cmd(tgt, &vscsi->req_vq, cmd,
+	if (virtscsi_kick_cmd(tgt, tgt->req_vq, cmd,
 			      sizeof cmd->req.cmd, sizeof cmd->resp.cmd,
 			      GFP_ATOMIC) >= 0)
 		ret = 0;

@@ -475,6 +486,38 @@ out:
 	return ret;
 }
 
+static int virtscsi_queuecommand_single(struct Scsi_Host *sh,
+					struct scsi_cmnd *sc)
+{
+	struct virtio_scsi *vscsi = shost_priv(sh);
+	struct virtio_scsi_target_state *tgt = vscsi->tgt[sc->device->id];
+
+	atomic_inc(&tgt->reqs);
+	return virtscsi_queuecommand(vscsi, tgt, sc);
+}
+
+static int virtscsi_queuecommand_multi(struct Scsi_Host *sh,
+				       struct scsi_cmnd *sc)
+{
+	struct virtio_scsi *vscsi = shost_priv(sh);
+	struct virtio_scsi_target_state *tgt = vscsi->tgt[sc->device->id];
+	unsigned long flags;
+	u32 queue_num;
+
+	/* Using an atomic_t for tgt->reqs lets the virtqueue handler
+	 * decrement it without taking the spinlock.
+	 */
+	spin_lock_irqsave(&tgt->tgt_lock, flags);
+	if (atomic_inc_return(&tgt->reqs) == 1) {
+		queue_num = smp_processor_id();
+		while (unlikely(queue_num >= vscsi->num_queues))
+			queue_num -= vscsi->num_queues;
+		tgt->req_vq = &vscsi->req_vqs[queue_num];
+	}
+	spin_unlock_irqrestore(&tgt->tgt_lock, flags);
+	return virtscsi_queuecommand(vscsi, tgt, sc);
+}
+
 static int virtscsi_tmf(struct virtio_scsi *vscsi, struct virtio_scsi_cmd *cmd)
 {
 	DECLARE_COMPLETION_ONSTACK(comp);

@@ -544,12 +585,26 @@ static int virtscsi_abort(struct scsi_cmnd *sc)
 	return virtscsi_tmf(vscsi, cmd);
 }
 
-static struct scsi_host_template virtscsi_host_template = {
+static struct scsi_host_template virtscsi_host_template_single = {
 	.module = THIS_MODULE,
 	.name = "Virtio SCSI HBA",
 	.proc_name = "virtio_scsi",
-	.queuecommand = virtscsi_queuecommand,
 	.this_id = -1,
+	.queuecommand = virtscsi_queuecommand_single,
+	.eh_abort_handler = virtscsi_abort,
+	.eh_device_reset_handler = virtscsi_device_reset,
+
+	.can_queue = 1024,
+	.dma_boundary = UINT_MAX,
+	.use_clustering = ENABLE_CLUSTERING,
+};
+
+static struct scsi_host_template virtscsi_host_template_multi = {
+	.module = THIS_MODULE,
+	.name = "Virtio SCSI HBA",
+	.proc_name = "virtio_scsi",
+	.this_id = -1,
+	.queuecommand = virtscsi_queuecommand_multi,
 	.eh_abort_handler = virtscsi_abort,
 	.eh_device_reset_handler = virtscsi_device_reset,
 

@@ -575,15 +630,19 @@ static struct scsi_host_template virtscsi_host_template = {
 				  &__val, sizeof(__val)); \
 	})
 
+
 static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
-			     struct virtqueue *vq)
+			     struct virtqueue *vq, bool affinity)
 {
 	spin_lock_init(&virtscsi_vq->vq_lock);
 	virtscsi_vq->vq = vq;
+	if (affinity)
+		virtqueue_set_affinity(vq, virtqueue_get_queue_index(vq) -
+				       VIRTIO_SCSI_VQ_BASE);
 }
 
 static struct virtio_scsi_target_state *virtscsi_alloc_tgt(
-	struct virtio_device *vdev, int sg_elems)
+	struct virtio_scsi *vscsi, u32 sg_elems)
 {
 	struct virtio_scsi_target_state *tgt;
 	gfp_t gfp_mask = GFP_KERNEL;

@@ -597,6 +656,13 @@ static struct virtio_scsi_target_state *virtscsi_alloc_tgt(
 
 	spin_lock_init(&tgt->tgt_lock);
 	sg_init_table(tgt->sg, sg_elems + 2);
+	atomic_set(&tgt->reqs, 0);
+
+	/*
+	 * The default is unused for multiqueue, but with a single queue
+	 * or target we use it in virtscsi_queuecommand.
+	 */
+	tgt->req_vq = &vscsi->req_vqs[0];
 	return tgt;
 }
 

@@ -632,28 +698,41 @@ static int virtscsi_init(struct virtio_device *vdev,
 			 struct virtio_scsi *vscsi, int num_targets)
 {
 	int err;
-	struct virtqueue *vqs[3];
 	u32 i, sg_elems;
+	u32 num_vqs;
+	vq_callback_t **callbacks;
+	const char **names;
+	struct virtqueue **vqs;
 
-	vq_callback_t *callbacks[] = {
-		virtscsi_ctrl_done,
-		virtscsi_event_done,
-		virtscsi_req_done
-	};
-	const char *names[] = {
-		"control",
-		"event",
-		"request"
-	};
+	num_vqs = vscsi->num_queues + VIRTIO_SCSI_VQ_BASE;
+	vqs = kmalloc(num_vqs * sizeof(struct virtqueue *), GFP_KERNEL);
+	callbacks = kmalloc(num_vqs * sizeof(vq_callback_t *), GFP_KERNEL);
+	names = kmalloc(num_vqs * sizeof(char *), GFP_KERNEL);
+
+	if (!callbacks || !vqs || !names) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	callbacks[0] = virtscsi_ctrl_done;
+	callbacks[1] = virtscsi_event_done;
+	names[0] = "control";
+	names[1] = "event";
+	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++) {
+		callbacks[i] = virtscsi_req_done;
+		names[i] = "request";
+	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, 3, vqs, callbacks, names);
+	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
 	if (err)
 		return err;
 
-	virtscsi_init_vq(&vscsi->ctrl_vq, vqs[0]);
-	virtscsi_init_vq(&vscsi->event_vq, vqs[1]);
-	virtscsi_init_vq(&vscsi->req_vq, vqs[2]);
+	virtscsi_init_vq(&vscsi->ctrl_vq, vqs[0], false);
+	virtscsi_init_vq(&vscsi->event_vq, vqs[1], false);
+	for (i = VIRTIO_SCSI_VQ_BASE; i < num_vqs; i++)
+		virtscsi_init_vq(&vscsi->req_vqs[i - VIRTIO_SCSI_VQ_BASE],
+				 vqs[i], vscsi->num_queues > 1);
 
 	virtscsi_config_set(vdev, cdb_size, VIRTIO_SCSI_CDB_SIZE);
 	virtscsi_config_set(vdev, sense_size, VIRTIO_SCSI_SENSE_SIZE);

@@ -671,7 +750,7 @@ static int virtscsi_init(struct virtio_device *vdev,
 		goto out;
 	}
 	for (i = 0; i < num_targets; i++) {
-		vscsi->tgt[i] = virtscsi_alloc_tgt(vdev, sg_elems);
+		vscsi->tgt[i] = virtscsi_alloc_tgt(vscsi, sg_elems);
 		if (!vscsi->tgt[i]) {
 			err = -ENOMEM;
 			goto out;

@@ -680,6 +759,9 @@ static int virtscsi_init(struct virtio_device *vdev,
 	err = 0;
 
 out:
+	kfree(names);
+	kfree(callbacks);
+	kfree(vqs);
 	if (err)
 		virtscsi_remove_vqs(vdev);
 	return err;

@@ -692,11 +774,26 @@ static int __devinit virtscsi_probe(struct virtio_device *vdev)
 	int err;
 	u32 sg_elems, num_targets;
 	u32 cmd_per_lun;
+	u32 num_queues;
+	struct scsi_host_template *hostt;
+
+	/* We need to know how many queues before we allocate.  */
+	num_queues = virtscsi_config_get(vdev, num_queues) ?: 1;
 
 	/* Allocate memory and link the structs together.  */
 	num_targets = virtscsi_config_get(vdev, max_target) + 1;
-	shost = scsi_host_alloc(&virtscsi_host_template, sizeof(*vscsi));
 
+	/* Multiqueue is not beneficial with a single target.  */
+	if (num_targets == 1)
+		num_queues = 1;
+
+	if (num_queues == 1)
+		hostt = &virtscsi_host_template_single;
+	else
+		hostt = &virtscsi_host_template_multi;
+
+	shost = scsi_host_alloc(hostt,
+		sizeof(*vscsi) + sizeof(vscsi->req_vqs[0]) * num_queues);
 	if (!shost)
 		return -ENOMEM;
 

@@ -704,6 +801,7 @@ static int __devinit virtscsi_probe(struct virtio_device *vdev)
 	shost->sg_tablesize = sg_elems;
 	vscsi = shost_priv(shost);
 	vscsi->vdev = vdev;
+	vscsi->num_queues = num_queues;
 	vdev->priv = shost;
 
 	err = virtscsi_init(vdev, vscsi, num_targets);