Merge branch 'virtio-support-packed-ring'

Tiwei Bie says:

====================
virtio: support packed ring

This patch set implements packed ring support in virtio driver.

A performance test between pktgen (pktgen_sample03_burst_single_flow.sh)
and DPDK vhost (testpmd/rxonly/vhost-PMD) has been done, I saw
~30% performance gain in packed ring in this case.

To make this patch set work with below patch set for vhost,
some hacks are needed to set the _F_NEXT flag in indirect
descriptors (this should be fixed in vhost):

https://lkml.org/lkml/2018/7/3/33

v2 -> v3:
- Use leXX instead of virtioXX (MST);
- Refactor split ring first (MST);
- Add debug helpers (MST);
- Put split/packed ring specific fields in sub structures (MST);
- Handle normal descriptors and indirect descriptors differently (MST);
- Track the DMA addr/len related info in a separate structure (MST);
- Calculate AVAIL/USED flags only when wrap counter wraps (MST);
- Define a struct/union to read event structure (MST);
- Define a macro for wrap counter bit in uapi (MST);
- Define the AVAIL/USED bits as shifts instead of values (MST);
- s/_F_/_FLAG_/ in VRING_PACKED_EVENT_* as they are values (MST);
- Drop the notify workaround for QEMU's tx-timer in packed ring (MST);

v1 -> v2:
- Use READ_ONCE() to read event off_wrap and flags together (Jason);
- Add comments related to ccw (Jason);

RFC v6 -> v1:
- Avoid extra virtio_wmb() in virtqueue_enable_cb_delayed_packed()
  when event idx is off (Jason);
- Fix bufs calculation in virtqueue_enable_cb_delayed_packed() (Jason);
- Test the state of the desc at used_idx instead of last_used_idx
  in virtqueue_enable_cb_delayed_packed() (Jason);
- Save wrap counter (as part of queue state) in the return value
  of virtqueue_enable_cb_prepare_packed();
- Refine the packed ring definitions in uapi;
- Rebase on the net-next tree;

RFC v5 -> RFC v6:
- Avoid tracking addr/len/flags when DMA API isn't used (MST/Jason);
- Define wrap counter as bool (Jason);
- Use ALIGN() in vring_init_packed() (Jason);
- Avoid using pointer to track `next` in detach_buf_packed() (Jason);
- Add comments for barriers (Jason);
- Don't enable RING_PACKED on ccw for now (noticed by Jason);
- Refine the memory barrier in virtqueue_poll();
- Add a missing memory barrier in virtqueue_enable_cb_delayed_packed();
- Remove the hacks in virtqueue_enable_cb_prepare_packed();

RFC v4 -> RFC v5:
- Save DMA addr, etc in desc state (Jason);
- Track used wrap counter;

RFC v3 -> RFC v4:
- Make ID allocation support out-of-order (Jason);
- Various fixes for EVENT_IDX support;

RFC v2 -> RFC v3:
- Split into small patches (Jason);
- Add helper virtqueue_use_indirect() (Jason);
- Just set id for the last descriptor of a list (Jason);
- Calculate the prev in virtqueue_add_packed() (Jason);
- Fix/improve desc suppression code (Jason/MST);
- Refine the code layout for XXX_split/packed and wrappers (MST);
- Fix the comments and API in uapi (MST);
- Remove the BUG_ON() for indirect (Jason);
- Some other refinements and bug fixes;

RFC v1 -> RFC v2:
- Add indirect descriptor support - compile test only;
- Add event suppression supprt - compile test only;
- Move vring_packed_init() out of uapi (Jason, MST);
- Merge two loops into one in virtqueue_add_packed() (Jason);
- Split vring_unmap_one() for packed ring and split ring (Jason);
- Avoid using '%' operator (Jason);
- Rename free_head -> next_avail_idx (Jason);
- Add comments for virtio_wmb() in virtqueue_add_packed() (Jason);
- Some other refinements and bug fixes;
====================
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/misc/mic/vop/vop_main.c

@@ -129,6 +129,16 @@ static u64 vop_get_features(struct virtio_device *vdev)
 	return features;
 }
 
+static void vop_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on virtio_vop for now,
+	 * because virtio_vop uses vring_new_virtqueue() which
+	 * creates virtio rings on preallocated memory.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int vop_finalize_features(struct virtio_device *vdev)
 {
 	unsigned int i, bits;
@@ -141,6 +151,9 @@ static int vop_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Give virtio_vop a chance to accept features. */
+	vop_transport_features(vdev);
+
 	memset_io(out_features, 0, feature_len);
 	bits = min_t(unsigned, feature_len,
 		     sizeof(vdev->features)) * 8;

drivers/remoteproc/remoteproc_virtio.c

@@ -214,6 +214,16 @@ static u64 rproc_virtio_get_features(struct virtio_device *vdev)
 	return rsc->dfeatures;
 }
 
+static void rproc_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on remoteproc for now,
+	 * because remoteproc uses vring_new_virtqueue() which
+	 * creates virtio rings on preallocated memory.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int rproc_virtio_finalize_features(struct virtio_device *vdev)
 {
 	struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
@@ -224,6 +234,9 @@ static int rproc_virtio_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features */
 	vring_transport_features(vdev);
 
+	/* Give virtio_rproc a chance to accept features. */
+	rproc_transport_features(vdev);
+
 	/* Make sure we don't have any features > 32 bits! */
 	BUG_ON((u32)vdev->features != vdev->features);
 

drivers/s390/virtio/virtio_ccw.c

@@ -765,6 +765,17 @@ static u64 virtio_ccw_get_features(struct virtio_device *vdev)
 	return rc;
 }
 
+static void ccw_transport_features(struct virtio_device *vdev)
+{
+	/*
+	 * Packed ring isn't enabled on virtio_ccw for now,
+	 * because virtio_ccw uses some legacy accessors,
+	 * e.g. virtqueue_get_avail() and virtqueue_get_used()
+	 * which aren't available in packed ring currently.
+	 */
+	__virtio_clear_bit(vdev, VIRTIO_F_RING_PACKED);
+}
+
 static int virtio_ccw_finalize_features(struct virtio_device *vdev)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
@@ -791,6 +802,9 @@ static int virtio_ccw_finalize_features(struct virtio_device *vdev)
 	/* Give virtio_ring a chance to accept features. */
 	vring_transport_features(vdev);
 
+	/* Give virtio_ccw a chance to accept features. */
+	ccw_transport_features(vdev);
+
 	features->index = 0;
 	features->features = cpu_to_le32((u32)vdev->features);
 	/* Write the first half of the feature bits to the host. */

drivers/virtio/virtio_ring.c

@@ -44,6 +44,26 @@
 	} while (0)
 #define END_USE(_vq) \
 	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
+#define LAST_ADD_TIME_UPDATE(_vq)				\
+	do {							\
+		ktime_t now = ktime_get();			\
+								\
+		/* No kick or get, with .1 second between?  Warn. */ \
+		if ((_vq)->last_add_time_valid)			\
+			WARN_ON(ktime_to_ms(ktime_sub(now,	\
+				(_vq)->last_add_time)) > 100);	\
+		(_vq)->last_add_time = now;			\
+		(_vq)->last_add_time_valid = true;		\
+	} while (0)
+#define LAST_ADD_TIME_CHECK(_vq)				\
+	do {							\
+		if ((_vq)->last_add_time_valid) {		\
+			WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), \
+				      (_vq)->last_add_time)) > 100); \
+		}						\
+	} while (0)
+#define LAST_ADD_TIME_INVALID(_vq)				\
+	((_vq)->last_add_time_valid = false)
 #else
 #define BAD_RING(_vq, fmt, args...)				\
 	do {							\
@@ -53,18 +73,38 @@
 	} while (0)
 #define START_USE(vq)
 #define END_USE(vq)
+#define LAST_ADD_TIME_UPDATE(vq)
+#define LAST_ADD_TIME_CHECK(vq)
+#define LAST_ADD_TIME_INVALID(vq)
 #endif
 
-struct vring_desc_state {
+struct vring_desc_state_split {
 	void *data;			/* Data for callback. */
 	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
 };
 
+struct vring_desc_state_packed {
+	void *data;			/* Data for callback. */
+	struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
+	u16 num;			/* Descriptor list length. */
+	u16 next;			/* The next desc state in a list. */
+	u16 last;			/* The last desc state in a list. */
+};
+
+struct vring_desc_extra_packed {
+	dma_addr_t addr;		/* Buffer DMA addr. */
+	u32 len;			/* Buffer length. */
+	u16 flags;			/* Descriptor flags. */
+};
+
 struct vring_virtqueue {
 	struct virtqueue vq;
 
-	/* Actual memory layout for this queue */
-	struct vring vring;
+	/* Is this a packed ring? */
+	bool packed_ring;
+
+	/* Is DMA API used? */
+	bool use_dma_api;
 
 	/* Can we use weak barriers? */
 	bool weak_barriers;
@@ -86,19 +126,70 @@ struct vring_virtqueue {
 	/* Last used index we've seen. */
 	u16 last_used_idx;
 
-	/* Last written value to avail->flags */
-	u16 avail_flags_shadow;
+	union {
+		/* Available for split ring */
+		struct {
+			/* Actual memory layout for this queue. */
+			struct vring vring;
+
+			/* Last written value to avail->flags */
+			u16 avail_flags_shadow;
+
+			/*
+			 * Last written value to avail->idx in
+			 * guest byte order.
+			 */
+			u16 avail_idx_shadow;
+
+			/* Per-descriptor state. */
+			struct vring_desc_state_split *desc_state;
 
-	/* Last written value to avail->idx in guest byte order */
-	u16 avail_idx_shadow;
+			/* DMA address and size information */
+			dma_addr_t queue_dma_addr;
+			size_t queue_size_in_bytes;
+		} split;
+
+		/* Available for packed ring */
+		struct {
+			/* Actual memory layout for this queue. */
+			struct vring_packed vring;
+
+			/* Driver ring wrap counter. */
+			bool avail_wrap_counter;
+
+			/* Device ring wrap counter. */
+			bool used_wrap_counter;
+
+			/* Avail used flags. */
+			u16 avail_used_flags;
+
+			/* Index of the next avail descriptor. */
+			u16 next_avail_idx;
+
+			/*
+			 * Last written value to driver->flags in
+			 * guest byte order.
+			 */
+			u16 event_flags_shadow;
+
+			/* Per-descriptor state. */
+			struct vring_desc_state_packed *desc_state;
+			struct vring_desc_extra_packed *desc_extra;
+
+			/* DMA address and size information */
+			dma_addr_t ring_dma_addr;
+			dma_addr_t driver_event_dma_addr;
+			dma_addr_t device_event_dma_addr;
+			size_t ring_size_in_bytes;
+			size_t event_size_in_bytes;
+		} packed;
+	};
 
 	/* How to notify other side. FIXME: commonalize hcalls! */
 	bool (*notify)(struct virtqueue *vq);
 
 	/* DMA, allocation, and size information */
 	bool we_own_ring;
-	size_t queue_size_in_bytes;
-	dma_addr_t queue_dma_addr;
 
 #ifdef DEBUG
 	/* They're supposed to lock for us. */
@@ -108,13 +199,27 @@ struct vring_virtqueue {
 	bool last_add_time_valid;
 	ktime_t last_add_time;
 #endif
-
-	/* Per-descriptor state. */
-	struct vring_desc_state desc_state[];
 };
 
+
+/*
+ * Helpers.
+ */
+
 #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
 
+static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
+					  unsigned int total_sg)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	/*
+	 * If the host supports indirect descriptor tables, and we have multiple
+	 * buffers, then go indirect. FIXME: tune this threshold
+	 */
+	return (vq->indirect && total_sg > 1 && vq->vq.num_free);
+}
+
 /*
  * Modern virtio devices have feature bits to specify whether they need a
  * quirk and bypass the IOMMU. If not there, just use the DMA API.
@@ -161,6 +266,48 @@ static bool vring_use_dma_api(struct virtio_device *vdev)
 	return false;
 }
 
+static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
+			      dma_addr_t *dma_handle, gfp_t flag)
+{
+	if (vring_use_dma_api(vdev)) {
+		return dma_alloc_coherent(vdev->dev.parent, size,
+					  dma_handle, flag);
+	} else {
+		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
+
+		if (queue) {
+			phys_addr_t phys_addr = virt_to_phys(queue);
+			*dma_handle = (dma_addr_t)phys_addr;
+
+			/*
+			 * Sanity check: make sure we dind't truncate
+			 * the address.  The only arches I can find that
+			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
+			 * are certain non-highmem MIPS and x86
+			 * configurations, but these configurations
+			 * should never allocate physical pages above 32
+			 * bits, so this is fine.  Just in case, throw a
+			 * warning and abort if we end up with an
+			 * unrepresentable address.
+			 */
+			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
+				free_pages_exact(queue, PAGE_ALIGN(size));
+				return NULL;
+			}
+		}
+		return queue;
+	}
+}
+
+static void vring_free_queue(struct virtio_device *vdev, size_t size,
+			     void *queue, dma_addr_t dma_handle)
+{
+	if (vring_use_dma_api(vdev))
+		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
+	else
+		free_pages_exact(queue, PAGE_ALIGN(size));
+}
+
 /*
  * The DMA ops on various arches are rather gnarly right now, and
  * making all of the arch DMA ops work on the vring device itself
@@ -176,7 +323,7 @@ static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
 				   struct scatterlist *sg,
 				   enum dma_data_direction direction)
 {
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return (dma_addr_t)sg_phys(sg);
 
 	/*
@@ -193,19 +340,33 @@ static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
 				   void *cpu_addr, size_t size,
 				   enum dma_data_direction direction)
 {
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return (dma_addr_t)virt_to_phys(cpu_addr);
 
 	return dma_map_single(vring_dma_dev(vq),
 			      cpu_addr, size, direction);
 }
 
-static void vring_unmap_one(const struct vring_virtqueue *vq,
-			    struct vring_desc *desc)
+static int vring_mapping_error(const struct vring_virtqueue *vq,
+			       dma_addr_t addr)
+{
+	if (!vq->use_dma_api)
+		return 0;
+
+	return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+
+
+/*
+ * Split ring specific functions - *_split().
+ */
+
+static void vring_unmap_one_split(const struct vring_virtqueue *vq,
+				  struct vring_desc *desc)
 {
 	u16 flags;
 
-	if (!vring_use_dma_api(vq->vq.vdev))
+	if (!vq->use_dma_api)
 		return;
 
 	flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
@@ -225,17 +386,9 @@ static void vring_unmap_one(const struct vring_virtqueue *vq,
 	}
 }
 
-static int vring_mapping_error(const struct vring_virtqueue *vq,
-			       dma_addr_t addr)
-{
-	if (!vring_use_dma_api(vq->vq.vdev))
-		return 0;
-
-	return dma_mapping_error(vring_dma_dev(vq), addr);
-}
-
-static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
-					 unsigned int total_sg, gfp_t gfp)
+static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
+					       unsigned int total_sg,
+					       gfp_t gfp)
 {
 	struct vring_desc *desc;
 	unsigned int i;
@@ -256,14 +409,14 @@ static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
 	return desc;
 }
 
-static inline int virtqueue_add(struct virtqueue *_vq,
-				struct scatterlist *sgs[],
-				unsigned int total_sg,
-				unsigned int out_sgs,
-				unsigned int in_sgs,
-				void *data,
-				void *ctx,
-				gfp_t gfp)
+static inline int virtqueue_add_split(struct virtqueue *_vq,
+				      struct scatterlist *sgs[],
+				      unsigned int total_sg,
+				      unsigned int out_sgs,
+				      unsigned int in_sgs,
+				      void *data,
+				      void *ctx,
+				      gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	struct scatterlist *sg;
@@ -282,30 +435,17 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		return -EIO;
 	}
 
-#ifdef DEBUG
-	{
-		ktime_t now = ktime_get();
-
-		/* No kick or get, with .1 second between?  Warn. */
-		if (vq->last_add_time_valid)
-			WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
-					    > 100);
-		vq->last_add_time = now;
-		vq->last_add_time_valid = true;
-	}
-#endif
+	LAST_ADD_TIME_UPDATE(vq);
 
 	BUG_ON(total_sg == 0);
 
 	head = vq->free_head;
 
-	/* If the host supports indirect descriptor tables, and we have multiple
-	 * buffers, then go indirect. FIXME: tune this threshold */
-	if (vq->indirect && total_sg > 1 && vq->vq.num_free)
-		desc = alloc_indirect(_vq, total_sg, gfp);
+	if (virtqueue_use_indirect(_vq, total_sg))
+		desc = alloc_indirect_split(_vq, total_sg, gfp);
 	else {
 		desc = NULL;
-		WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
+		WARN_ON_ONCE(total_sg > vq->split.vring.num && !vq->indirect);
 	}
 
 	if (desc) {
@@ -316,7 +456,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		descs_used = 1;
 	} else {
 		indirect = false;
-		desc = vq->vring.desc;
+		desc = vq->split.vring.desc;
 		i = head;
 		descs_used = total_sg;
 	}
@@ -372,10 +512,13 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 		if (vring_mapping_error(vq, addr))
 			goto unmap_release;
 
-		vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
-		vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr);
+		vq->split.vring.desc[head].flags = cpu_to_virtio16(_vq->vdev,
+				VRING_DESC_F_INDIRECT);
+		vq->split.vring.desc[head].addr = cpu_to_virtio64(_vq->vdev,
+				addr);
 
-		vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
+		vq->split.vring.desc[head].len = cpu_to_virtio32(_vq->vdev,
+				total_sg * sizeof(struct vring_desc));
 	}
 
 	/* We're using some buffers from the free list. */
@@ -383,27 +526,29 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 
 	/* Update free pointer */
 	if (indirect)
-		vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
+		vq->free_head = virtio16_to_cpu(_vq->vdev,
+					vq->split.vring.desc[head].next);
 	else
 		vq->free_head = i;
 
 	/* Store token and indirect buffer state. */
-	vq->desc_state[head].data = data;
+	vq->split.desc_state[head].data = data;
 	if (indirect)
-		vq->desc_state[head].indir_desc = desc;
+		vq->split.desc_state[head].indir_desc = desc;
 	else
-		vq->desc_state[head].indir_desc = ctx;
+		vq->split.desc_state[head].indir_desc = ctx;
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
-	avail = vq->avail_idx_shadow & (vq->vring.num - 1);
-	vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
+	avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
+	vq->split.vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
 
 	/* Descriptors and available array need to be set before we expose the
 	 * new available array entries. */
 	virtio_wmb(vq->weak_barriers);
-	vq->avail_idx_shadow++;
-	vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
+	vq->split.avail_idx_shadow++;
+	vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_idx_shadow);
 	vq->num_added++;
 
 	pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -423,8 +568,8 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	for (n = 0; n < total_sg; n++) {
 		if (i == err_idx)
 			break;
-		vring_unmap_one(vq, &desc[i]);
-		i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
+		vring_unmap_one_split(vq, &desc[i]);
+		i = virtio16_to_cpu(_vq->vdev, vq->split.vring.desc[i].next);
 	}
 
 	if (indirect)
@@ -434,6 +579,1122 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	return -EIO;
 }
 
+static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old;
+	bool needs_kick;
+
+	START_USE(vq);
+	/* We need to expose available array entries before checking avail
+	 * event. */
+	virtio_mb(vq->weak_barriers);
+
+	old = vq->split.avail_idx_shadow - vq->num_added;
+	new = vq->split.avail_idx_shadow;
+	vq->num_added = 0;
+
+	LAST_ADD_TIME_CHECK(vq);
+	LAST_ADD_TIME_INVALID(vq);
+
+	if (vq->event) {
+		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev,
+					vring_avail_event(&vq->split.vring)),
+					      new, old);
+	} else {
+		needs_kick = !(vq->split.vring.used->flags &
+					cpu_to_virtio16(_vq->vdev,
+						VRING_USED_F_NO_NOTIFY));
+	}
+	END_USE(vq);
+	return needs_kick;
+}
+
+static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
+			     void **ctx)
+{
+	unsigned int i, j;
+	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
+
+	/* Clear data ptr. */
+	vq->split.desc_state[head].data = NULL;
+
+	/* Put back on free list: unmap first-level descriptors and find end */
+	i = head;
+
+	while (vq->split.vring.desc[i].flags & nextflag) {
+		vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+		i = virtio16_to_cpu(vq->vq.vdev, vq->split.vring.desc[i].next);
+		vq->vq.num_free++;
+	}
+
+	vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+	vq->split.vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev,
+						vq->free_head);
+	vq->free_head = head;
+
+	/* Plus final descriptor */
+	vq->vq.num_free++;
+
+	if (vq->indirect) {
+		struct vring_desc *indir_desc =
+				vq->split.desc_state[head].indir_desc;
+		u32 len;
+
+		/* Free the indirect table, if any, now that it's unmapped. */
+		if (!indir_desc)
+			return;
+
+		len = virtio32_to_cpu(vq->vq.vdev,
+				vq->split.vring.desc[head].len);
+
+		BUG_ON(!(vq->split.vring.desc[head].flags &
+			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
+
+		for (j = 0; j < len / sizeof(struct vring_desc); j++)
+			vring_unmap_one_split(vq, &indir_desc[j]);
+
+		kfree(indir_desc);
+		vq->split.desc_state[head].indir_desc = NULL;
+	} else if (ctx) {
+		*ctx = vq->split.desc_state[head].indir_desc;
+	}
+}
+
+static inline bool more_used_split(const struct vring_virtqueue *vq)
+{
+	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev,
+			vq->split.vring.used->idx);
+}
+
+static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
+					 unsigned int *len,
+					 void **ctx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	void *ret;
+	unsigned int i;
+	u16 last_used;
+
+	START_USE(vq);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return NULL;
+	}
+
+	if (!more_used_split(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	/* Only get used array entries after they have been exposed by host. */
+	virtio_rmb(vq->weak_barriers);
+
+	last_used = (vq->last_used_idx & (vq->split.vring.num - 1));
+	i = virtio32_to_cpu(_vq->vdev,
+			vq->split.vring.used->ring[last_used].id);
+	*len = virtio32_to_cpu(_vq->vdev,
+			vq->split.vring.used->ring[last_used].len);
+
+	if (unlikely(i >= vq->split.vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", i);
+		return NULL;
+	}
+	if (unlikely(!vq->split.desc_state[i].data)) {
+		BAD_RING(vq, "id %u is not a head!\n", i);
+		return NULL;
+	}
+
+	/* detach_buf_split clears data, so grab it now. */
+	ret = vq->split.desc_state[i].data;
+	detach_buf_split(vq, i, ctx);
+	vq->last_used_idx++;
+	/* If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call. */
+	if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
+		virtio_store_mb(vq->weak_barriers,
+				&vring_used_event(&vq->split.vring),
+				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
+
+	LAST_ADD_TIME_INVALID(vq);
+
+	END_USE(vq);
+	return ret;
+}
+
+static void virtqueue_disable_cb_split(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+		vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		if (!vq->event)
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
+	}
+}
+
+static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 last_used_idx;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always do both to keep code simple. */
+	if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+		if (!vq->event)
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
+	}
+	vring_used_event(&vq->split.vring) = cpu_to_virtio16(_vq->vdev,
+			last_used_idx = vq->last_used_idx);
+	END_USE(vq);
+	return last_used_idx;
+}
+
+static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev,
+			vq->split.vring.used->idx);
+}
+
+static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 bufs;
+
+	START_USE(vq);
+
+	/* We optimistically turn back on interrupts, then check if there was
+	 * more to do. */
+	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+	 * either clear the flags bit or point the event index at the next
+	 * entry. Always update the event index to keep code simple. */
+	if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+		vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+		if (!vq->event)
+			vq->split.vring.avail->flags =
+				cpu_to_virtio16(_vq->vdev,
+						vq->split.avail_flags_shadow);
+	}
+	/* TODO: tune this threshold */
+	bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) * 3 / 4;
+
+	virtio_store_mb(vq->weak_barriers,
+			&vring_used_event(&vq->split.vring),
+			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
+
+	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx)
+					- vq->last_used_idx) > bufs)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
+static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+	void *buf;
+
+	START_USE(vq);
+
+	for (i = 0; i < vq->split.vring.num; i++) {
+		if (!vq->split.desc_state[i].data)
+			continue;
+		/* detach_buf_split clears data, so grab it now. */
+		buf = vq->split.desc_state[i].data;
+		detach_buf_split(vq, i, NULL);
+		vq->split.avail_idx_shadow--;
+		vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+				vq->split.avail_idx_shadow);
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->vq.num_free != vq->split.vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+
+static struct virtqueue *vring_create_virtqueue_split(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct virtqueue *vq;
+	void *queue = NULL;
+	dma_addr_t dma_addr;
+	size_t queue_size_in_bytes;
+	struct vring vring;
+
+	/* We assume num is a power of 2. */
+	if (num & (num - 1)) {
+		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+		return NULL;
+	}
+
+	/* TODO: allocate each queue chunk individually */
+	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr,
+					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+		if (queue)
+			break;
+	}
+
+	if (!num)
+		return NULL;
+
+	if (!queue) {
+		/* Try to get a single page. You are my only hope! */
+		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
+	}
+	if (!queue)
+		return NULL;
+
+	queue_size_in_bytes = vring_size(num, vring_align);
+	vring_init(&vring, num, queue, vring_align);
+
+	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
+				   notify, callback, name);
+	if (!vq) {
+		vring_free_queue(vdev, queue_size_in_bytes, queue,
+				 dma_addr);
+		return NULL;
+	}
+
+	to_vvq(vq)->split.queue_dma_addr = dma_addr;
+	to_vvq(vq)->split.queue_size_in_bytes = queue_size_in_bytes;
+	to_vvq(vq)->we_own_ring = true;
+
+	return vq;
+}
+
+
+/*
+ * Packed ring specific functions - *_packed().
+ */
+
+static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
+				     struct vring_desc_extra_packed *state)
+{
+	u16 flags;
+
+	if (!vq->use_dma_api)
+		return;
+
+	flags = state->flags;
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 state->addr, state->len,
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       state->addr, state->len,
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
+				   struct vring_packed_desc *desc)
+{
+	u16 flags;
+
+	if (!vq->use_dma_api)
+		return;
+
+	flags = le16_to_cpu(desc->flags);
+
+	if (flags & VRING_DESC_F_INDIRECT) {
+		dma_unmap_single(vring_dma_dev(vq),
+				 le64_to_cpu(desc->addr),
+				 le32_to_cpu(desc->len),
+				 (flags & VRING_DESC_F_WRITE) ?
+				 DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	} else {
+		dma_unmap_page(vring_dma_dev(vq),
+			       le64_to_cpu(desc->addr),
+			       le32_to_cpu(desc->len),
+			       (flags & VRING_DESC_F_WRITE) ?
+			       DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+}
+
+static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
+						       gfp_t gfp)
+{
+	struct vring_packed_desc *desc;
+
+	/*
+	 * We require lowmem mappings for the descriptors because
+	 * otherwise virt_to_phys will give us bogus addresses in the
+	 * virtqueue.
+	 */
+	gfp &= ~__GFP_HIGHMEM;
+
+	desc = kmalloc_array(total_sg, sizeof(struct vring_packed_desc), gfp);
+
+	return desc;
+}
+
+static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
+				       struct scatterlist *sgs[],
+				       unsigned int total_sg,
+				       unsigned int out_sgs,
+				       unsigned int in_sgs,
+				       void *data,
+				       gfp_t gfp)
+{
+	struct vring_packed_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i, n, err_idx;
+	u16 head, id;
+	dma_addr_t addr;
+
+	head = vq->packed.next_avail_idx;
+	desc = alloc_indirect_packed(total_sg, gfp);
+
+	if (unlikely(vq->vq.num_free < 1)) {
+		pr_debug("Can't add buf len 1 - avail = 0\n");
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	i = 0;
+	id = vq->free_head;
+	BUG_ON(id == vq->packed.vring.num);
+
+	for (n = 0; n < out_sgs + in_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+					DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
+			desc[i].flags = cpu_to_le16(n < out_sgs ?
+						0 : VRING_DESC_F_WRITE);
+			desc[i].addr = cpu_to_le64(addr);
+			desc[i].len = cpu_to_le32(sg->length);
+			i++;
+		}
+	}
+
+	/* Now that the indirect table is filled in, map it. */
+	addr = vring_map_single(vq, desc,
+			total_sg * sizeof(struct vring_packed_desc),
+			DMA_TO_DEVICE);
+	if (vring_mapping_error(vq, addr))
+		goto unmap_release;
+
+	vq->packed.vring.desc[head].addr = cpu_to_le64(addr);
+	vq->packed.vring.desc[head].len = cpu_to_le32(total_sg *
+				sizeof(struct vring_packed_desc));
+	vq->packed.vring.desc[head].id = cpu_to_le16(id);
+
+	if (vq->use_dma_api) {
+		vq->packed.desc_extra[id].addr = addr;
+		vq->packed.desc_extra[id].len = total_sg *
+				sizeof(struct vring_packed_desc);
+		vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
+						  vq->packed.avail_used_flags;
+	}
+
+	/*
+	 * A driver MUST NOT make the first descriptor in the list
+	 * available before all subsequent descriptors comprising
+	 * the list are made available.
+	 */
+	virtio_wmb(vq->weak_barriers);
+	vq->packed.vring.desc[head].flags = cpu_to_le16(VRING_DESC_F_INDIRECT |
+						vq->packed.avail_used_flags);
+
+	/* We're using some buffers from the free list. */
+	vq->vq.num_free -= 1;
+
+	/* Update free pointer */
+	n = head + 1;
+	if (n >= vq->packed.vring.num) {
+		n = 0;
+		vq->packed.avail_wrap_counter ^= 1;
+		vq->packed.avail_used_flags ^=
+				1 << VRING_PACKED_DESC_F_AVAIL |
+				1 << VRING_PACKED_DESC_F_USED;
+	}
+	vq->packed.next_avail_idx = n;
+	vq->free_head = vq->packed.desc_state[id].next;
+
+	/* Store token and indirect buffer state. */
+	vq->packed.desc_state[id].num = 1;
+	vq->packed.desc_state[id].data = data;
+	vq->packed.desc_state[id].indir_desc = desc;
+	vq->packed.desc_state[id].last = id;
+
+	vq->num_added += 1;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return 0;
+
+unmap_release:
+	err_idx = i;
+
+	for (i = 0; i < err_idx; i++)
+		vring_unmap_desc_packed(vq, &desc[i]);
+
+	kfree(desc);
+
+	END_USE(vq);
+	return -EIO;
+}
+
+static inline int virtqueue_add_packed(struct virtqueue *_vq,
+				       struct scatterlist *sgs[],
+				       unsigned int total_sg,
+				       unsigned int out_sgs,
+				       unsigned int in_sgs,
+				       void *data,
+				       void *ctx,
+				       gfp_t gfp)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	struct vring_packed_desc *desc;
+	struct scatterlist *sg;
+	unsigned int i, n, c, descs_used, err_idx;
+	__le16 uninitialized_var(head_flags), flags;
+	u16 head, id, uninitialized_var(prev), curr, avail_used_flags;
+
+	START_USE(vq);
+
+	BUG_ON(data == NULL);
+	BUG_ON(ctx && vq->indirect);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return -EIO;
+	}
+
+	LAST_ADD_TIME_UPDATE(vq);
+
+	BUG_ON(total_sg == 0);
+
+	if (virtqueue_use_indirect(_vq, total_sg))
+		return virtqueue_add_indirect_packed(vq, sgs, total_sg,
+				out_sgs, in_sgs, data, gfp);
+
+	head = vq->packed.next_avail_idx;
+	avail_used_flags = vq->packed.avail_used_flags;
+
+	WARN_ON_ONCE(total_sg > vq->packed.vring.num && !vq->indirect);
+
+	desc = vq->packed.vring.desc;
+	i = head;
+	descs_used = total_sg;
+
+	if (unlikely(vq->vq.num_free < descs_used)) {
+		pr_debug("Can't add buf len %i - avail = %i\n",
+			 descs_used, vq->vq.num_free);
+		END_USE(vq);
+		return -ENOSPC;
+	}
+
+	id = vq->free_head;
+	BUG_ON(id == vq->packed.vring.num);
+
+	curr = id;
+	c = 0;
+	for (n = 0; n < out_sgs + in_sgs; n++) {
+		for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+			dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+					DMA_TO_DEVICE : DMA_FROM_DEVICE);
+			if (vring_mapping_error(vq, addr))
+				goto unmap_release;
+
+			flags = cpu_to_le16(vq->packed.avail_used_flags |
+				    (++c == total_sg ? 0 : VRING_DESC_F_NEXT) |
+				    (n < out_sgs ? 0 : VRING_DESC_F_WRITE));
+			if (i == head)
+				head_flags = flags;
+			else
+				desc[i].flags = flags;
+
+			desc[i].addr = cpu_to_le64(addr);
+			desc[i].len = cpu_to_le32(sg->length);
+			desc[i].id = cpu_to_le16(id);
+
+			if (unlikely(vq->use_dma_api)) {
+				vq->packed.desc_extra[curr].addr = addr;
+				vq->packed.desc_extra[curr].len = sg->length;
+				vq->packed.desc_extra[curr].flags =
+					le16_to_cpu(flags);
+			}
+			prev = curr;
+			curr = vq->packed.desc_state[curr].next;
+
+			if ((unlikely(++i >= vq->packed.vring.num))) {
+				i = 0;
+				vq->packed.avail_used_flags ^=
+					1 << VRING_PACKED_DESC_F_AVAIL |
+					1 << VRING_PACKED_DESC_F_USED;
+			}
+		}
+	}
+
+	if (i < head)
+		vq->packed.avail_wrap_counter ^= 1;
+
+	/* We're using some buffers from the free list. */
+	vq->vq.num_free -= descs_used;
+
+	/* Update free pointer */
+	vq->packed.next_avail_idx = i;
+	vq->free_head = curr;
+
+	/* Store token. */
+	vq->packed.desc_state[id].num = descs_used;
+	vq->packed.desc_state[id].data = data;
+	vq->packed.desc_state[id].indir_desc = ctx;
+	vq->packed.desc_state[id].last = prev;
+
+	/*
+	 * A driver MUST NOT make the first descriptor in the list
+	 * available before all subsequent descriptors comprising
+	 * the list are made available.
+	 */
+	virtio_wmb(vq->weak_barriers);
+	vq->packed.vring.desc[head].flags = head_flags;
+	vq->num_added += descs_used;
+
+	pr_debug("Added buffer head %i to %p\n", head, vq);
+	END_USE(vq);
+
+	return 0;
+
+unmap_release:
+	err_idx = i;
+	i = head;
+
+	vq->packed.avail_used_flags = avail_used_flags;
+
+	for (n = 0; n < total_sg; n++) {
+		if (i == err_idx)
+			break;
+		vring_unmap_desc_packed(vq, &desc[i]);
+		i++;
+		if (i >= vq->packed.vring.num)
+			i = 0;
+	}
+
+	END_USE(vq);
+	return -EIO;
+}
+
+static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 new, old, off_wrap, flags, wrap_counter, event_idx;
+	bool needs_kick;
+	union {
+		struct {
+			__le16 off_wrap;
+			__le16 flags;
+		};
+		u32 u32;
+	} snapshot;
+
+	START_USE(vq);
+
+	/*
+	 * We need to expose the new flags value before checking notification
+	 * suppressions.
+	 */
+	virtio_mb(vq->weak_barriers);
+
+	old = vq->packed.next_avail_idx - vq->num_added;
+	new = vq->packed.next_avail_idx;
+	vq->num_added = 0;
+
+	snapshot.u32 = *(u32 *)vq->packed.vring.device;
+	flags = le16_to_cpu(snapshot.flags);
+
+	LAST_ADD_TIME_CHECK(vq);
+	LAST_ADD_TIME_INVALID(vq);
+
+	if (flags != VRING_PACKED_EVENT_FLAG_DESC) {
+		needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE);
+		goto out;
+	}
+
+	off_wrap = le16_to_cpu(snapshot.off_wrap);
+
+	wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+	event_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+	if (wrap_counter != vq->packed.avail_wrap_counter)
+		event_idx -= vq->packed.vring.num;
+
+	needs_kick = vring_need_event(event_idx, new, old);
+out:
+	END_USE(vq);
+	return needs_kick;
+}
+
+static void detach_buf_packed(struct vring_virtqueue *vq,
+			      unsigned int id, void **ctx)
+{
+	struct vring_desc_state_packed *state = NULL;
+	struct vring_packed_desc *desc;
+	unsigned int i, curr;
+
+	state = &vq->packed.desc_state[id];
+
+	/* Clear data ptr. */
+	state->data = NULL;
+
+	vq->packed.desc_state[state->last].next = vq->free_head;
+	vq->free_head = id;
+	vq->vq.num_free += state->num;
+
+	if (unlikely(vq->use_dma_api)) {
+		curr = id;
+		for (i = 0; i < state->num; i++) {
+			vring_unmap_state_packed(vq,
+				&vq->packed.desc_extra[curr]);
+			curr = vq->packed.desc_state[curr].next;
+		}
+	}
+
+	if (vq->indirect) {
+		u32 len;
+
+		/* Free the indirect table, if any, now that it's unmapped. */
+		desc = state->indir_desc;
+		if (!desc)
+			return;
+
+		if (vq->use_dma_api) {
+			len = vq->packed.desc_extra[id].len;
+			for (i = 0; i < len / sizeof(struct vring_packed_desc);
+					i++)
+				vring_unmap_desc_packed(vq, &desc[i]);
+		}
+		kfree(desc);
+		state->indir_desc = NULL;
+	} else if (ctx) {
+		*ctx = state->indir_desc;
+	}
+}
+
+static inline bool is_used_desc_packed(const struct vring_virtqueue *vq,
+				       u16 idx, bool used_wrap_counter)
+{
+	bool avail, used;
+	u16 flags;
+
+	flags = le16_to_cpu(vq->packed.vring.desc[idx].flags);
+	avail = !!(flags & (1 << VRING_PACKED_DESC_F_AVAIL));
+	used = !!(flags & (1 << VRING_PACKED_DESC_F_USED));
+
+	return avail == used && used == used_wrap_counter;
+}
+
+static inline bool more_used_packed(const struct vring_virtqueue *vq)
+{
+	return is_used_desc_packed(vq, vq->last_used_idx,
+			vq->packed.used_wrap_counter);
+}
+
+static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
+					  unsigned int *len,
+					  void **ctx)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 last_used, id;
+	void *ret;
+
+	START_USE(vq);
+
+	if (unlikely(vq->broken)) {
+		END_USE(vq);
+		return NULL;
+	}
+
+	if (!more_used_packed(vq)) {
+		pr_debug("No more buffers in queue\n");
+		END_USE(vq);
+		return NULL;
+	}
+
+	/* Only get used elements after they have been exposed by host. */
+	virtio_rmb(vq->weak_barriers);
+
+	last_used = vq->last_used_idx;
+	id = le16_to_cpu(vq->packed.vring.desc[last_used].id);
+	*len = le32_to_cpu(vq->packed.vring.desc[last_used].len);
+
+	if (unlikely(id >= vq->packed.vring.num)) {
+		BAD_RING(vq, "id %u out of range\n", id);
+		return NULL;
+	}
+	if (unlikely(!vq->packed.desc_state[id].data)) {
+		BAD_RING(vq, "id %u is not a head!\n", id);
+		return NULL;
+	}
+
+	/* detach_buf_packed clears data, so grab it now. */
+	ret = vq->packed.desc_state[id].data;
+	detach_buf_packed(vq, id, ctx);
+
+	vq->last_used_idx += vq->packed.desc_state[id].num;
+	if (unlikely(vq->last_used_idx >= vq->packed.vring.num)) {
+		vq->last_used_idx -= vq->packed.vring.num;
+		vq->packed.used_wrap_counter ^= 1;
+	}
+
+	/*
+	 * If we expect an interrupt for the next entry, tell host
+	 * by writing event index and flush out the write before
+	 * the read in the next get_buf call.
+	 */
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DESC)
+		virtio_store_mb(vq->weak_barriers,
+				&vq->packed.vring.driver->off_wrap,
+				cpu_to_le16(vq->last_used_idx |
+					(vq->packed.used_wrap_counter <<
+					 VRING_PACKED_EVENT_F_WRAP_CTR)));
+
+	LAST_ADD_TIME_INVALID(vq);
+
+	END_USE(vq);
+	return ret;
+}
+
+static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+		vq->packed.vring.driver->flags =
+			cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+}
+
+static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	START_USE(vq);
+
+	/*
+	 * We optimistically turn back on interrupts, then check if there was
+	 * more to do.
+	 */
+
+	if (vq->event) {
+		vq->packed.vring.driver->off_wrap =
+			cpu_to_le16(vq->last_used_idx |
+				(vq->packed.used_wrap_counter <<
+				 VRING_PACKED_EVENT_F_WRAP_CTR));
+		/*
+		 * We need to update event offset and event wrap
+		 * counter first before updating event flags.
+		 */
+		virtio_wmb(vq->weak_barriers);
+	}
+
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = vq->event ?
+				VRING_PACKED_EVENT_FLAG_DESC :
+				VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.vring.driver->flags =
+				cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	END_USE(vq);
+	return vq->last_used_idx | ((u16)vq->packed.used_wrap_counter <<
+			VRING_PACKED_EVENT_F_WRAP_CTR);
+}
+
+static bool virtqueue_poll_packed(struct virtqueue *_vq, u16 off_wrap)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	bool wrap_counter;
+	u16 used_idx;
+
+	wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+	used_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+
+	return is_used_desc_packed(vq, used_idx, wrap_counter);
+}
+
+static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	u16 used_idx, wrap_counter;
+	u16 bufs;
+
+	START_USE(vq);
+
+	/*
+	 * We optimistically turn back on interrupts, then check if there was
+	 * more to do.
+	 */
+
+	if (vq->event) {
+		/* TODO: tune this threshold */
+		bufs = (vq->packed.vring.num - vq->vq.num_free) * 3 / 4;
+		wrap_counter = vq->packed.used_wrap_counter;
+
+		used_idx = vq->last_used_idx + bufs;
+		if (used_idx >= vq->packed.vring.num) {
+			used_idx -= vq->packed.vring.num;
+			wrap_counter ^= 1;
+		}
+
+		vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx |
+			(wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR));
+
+		/*
+		 * We need to update event offset and event wrap
+		 * counter first before updating event flags.
+		 */
+		virtio_wmb(vq->weak_barriers);
+	} else {
+		used_idx = vq->last_used_idx;
+		wrap_counter = vq->packed.used_wrap_counter;
+	}
+
+	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+		vq->packed.event_flags_shadow = vq->event ?
+				VRING_PACKED_EVENT_FLAG_DESC :
+				VRING_PACKED_EVENT_FLAG_ENABLE;
+		vq->packed.vring.driver->flags =
+				cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	/*
+	 * We need to update event suppression structure first
+	 * before re-checking for more used buffers.
+	 */
+	virtio_mb(vq->weak_barriers);
+
+	if (is_used_desc_packed(vq, used_idx, wrap_counter)) {
+		END_USE(vq);
+		return false;
+	}
+
+	END_USE(vq);
+	return true;
+}
+
+static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+	unsigned int i;
+	void *buf;
+
+	START_USE(vq);
+
+	for (i = 0; i < vq->packed.vring.num; i++) {
+		if (!vq->packed.desc_state[i].data)
+			continue;
+		/* detach_buf clears data, so grab it now. */
+		buf = vq->packed.desc_state[i].data;
+		detach_buf_packed(vq, i, NULL);
+		END_USE(vq);
+		return buf;
+	}
+	/* That should have freed everything. */
+	BUG_ON(vq->vq.num_free != vq->packed.vring.num);
+
+	END_USE(vq);
+	return NULL;
+}
+
+static struct virtqueue *vring_create_virtqueue_packed(
+	unsigned int index,
+	unsigned int num,
+	unsigned int vring_align,
+	struct virtio_device *vdev,
+	bool weak_barriers,
+	bool may_reduce_num,
+	bool context,
+	bool (*notify)(struct virtqueue *),
+	void (*callback)(struct virtqueue *),
+	const char *name)
+{
+	struct vring_virtqueue *vq;
+	struct vring_packed_desc *ring;
+	struct vring_packed_desc_event *driver, *device;
+	dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
+	size_t ring_size_in_bytes, event_size_in_bytes;
+	unsigned int i;
+
+	ring_size_in_bytes = num * sizeof(struct vring_packed_desc);
+
+	ring = vring_alloc_queue(vdev, ring_size_in_bytes,
+				 &ring_dma_addr,
+				 GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!ring)
+		goto err_ring;
+
+	event_size_in_bytes = sizeof(struct vring_packed_desc_event);
+
+	driver = vring_alloc_queue(vdev, event_size_in_bytes,
+				   &driver_event_dma_addr,
+				   GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!driver)
+		goto err_driver;
+
+	device = vring_alloc_queue(vdev, event_size_in_bytes,
+				   &device_event_dma_addr,
+				   GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+	if (!device)
+		goto err_device;
+
+	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
+	if (!vq)
+		goto err_vq;
+
+	vq->vq.callback = callback;
+	vq->vq.vdev = vdev;
+	vq->vq.name = name;
+	vq->vq.num_free = num;
+	vq->vq.index = index;
+	vq->we_own_ring = true;
+	vq->notify = notify;
+	vq->weak_barriers = weak_barriers;
+	vq->broken = false;
+	vq->last_used_idx = 0;
+	vq->num_added = 0;
+	vq->packed_ring = true;
+	vq->use_dma_api = vring_use_dma_api(vdev);
+	list_add_tail(&vq->vq.list, &vdev->vqs);
+#ifdef DEBUG
+	vq->in_use = false;
+	vq->last_add_time_valid = false;
+#endif
+
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+		!context;
+	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+	vq->packed.ring_dma_addr = ring_dma_addr;
+	vq->packed.driver_event_dma_addr = driver_event_dma_addr;
+	vq->packed.device_event_dma_addr = device_event_dma_addr;
+
+	vq->packed.ring_size_in_bytes = ring_size_in_bytes;
+	vq->packed.event_size_in_bytes = event_size_in_bytes;
+
+	vq->packed.vring.num = num;
+	vq->packed.vring.desc = ring;
+	vq->packed.vring.driver = driver;
+	vq->packed.vring.device = device;
+
+	vq->packed.next_avail_idx = 0;
+	vq->packed.avail_wrap_counter = 1;
+	vq->packed.used_wrap_counter = 1;
+	vq->packed.event_flags_shadow = 0;
+	vq->packed.avail_used_flags = 1 << VRING_PACKED_DESC_F_AVAIL;
+
+	vq->packed.desc_state = kmalloc_array(num,
+			sizeof(struct vring_desc_state_packed),
+			GFP_KERNEL);
+	if (!vq->packed.desc_state)
+		goto err_desc_state;
+
+	memset(vq->packed.desc_state, 0,
+		num * sizeof(struct vring_desc_state_packed));
+
+	/* Put everything in free lists. */
+	vq->free_head = 0;
+	for (i = 0; i < num-1; i++)
+		vq->packed.desc_state[i].next = i + 1;
+
+	vq->packed.desc_extra = kmalloc_array(num,
+			sizeof(struct vring_desc_extra_packed),
+			GFP_KERNEL);
+	if (!vq->packed.desc_extra)
+		goto err_desc_extra;
+
+	memset(vq->packed.desc_extra, 0,
+		num * sizeof(struct vring_desc_extra_packed));
+
+	/* No callback?  Tell other side not to bother us. */
+	if (!callback) {
+		vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+		vq->packed.vring.driver->flags =
+			cpu_to_le16(vq->packed.event_flags_shadow);
+	}
+
+	return &vq->vq;
+
+err_desc_extra:
+	kfree(vq->packed.desc_state);
+err_desc_state:
+	kfree(vq);
+err_vq:
+	vring_free_queue(vdev, event_size_in_bytes, device, ring_dma_addr);
+err_device:
+	vring_free_queue(vdev, event_size_in_bytes, driver, ring_dma_addr);
+err_driver:
+	vring_free_queue(vdev, ring_size_in_bytes, ring, ring_dma_addr);
+err_ring:
+	return NULL;
+}
+
+
+/*
+ * Generic functions and exported symbols.
+ */
+
+static inline int virtqueue_add(struct virtqueue *_vq,
+				struct scatterlist *sgs[],
+				unsigned int total_sg,
+				unsigned int out_sgs,
+				unsigned int in_sgs,
+				void *data,
+				void *ctx,
+				gfp_t gfp)
+{
+	struct vring_virtqueue *vq = to_vvq(_vq);
+
+	return vq->packed_ring ? virtqueue_add_packed(_vq, sgs, total_sg,
+					out_sgs, in_sgs, data, ctx, gfp) :
+				 virtqueue_add_split(_vq, sgs, total_sg,
+					out_sgs, in_sgs, data, ctx, gfp);
+}
+
 /**
  * virtqueue_add_sgs - expose buffers to other end
  * @vq: the struct virtqueue we're talking about.
@@ -460,6 +1721,7 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
 	/* Count them first. */
 	for (i = 0; i < out_sgs + in_sgs; i++) {
 		struct scatterlist *sg;
+
 		for (sg = sgs[i]; sg; sg = sg_next(sg))
 			total_sg++;
 	}
@@ -550,34 +1812,9 @@ EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
 bool virtqueue_kick_prepare(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	u16 new, old;
-	bool needs_kick;
-
-	START_USE(vq);
-	/* We need to expose available array entries before checking avail
-	 * event. */
-	virtio_mb(vq->weak_barriers);
 
-	old = vq->avail_idx_shadow - vq->num_added;
-	new = vq->avail_idx_shadow;
-	vq->num_added = 0;
-
-#ifdef DEBUG
-	if (vq->last_add_time_valid) {
-		WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
-					      vq->last_add_time)) > 100);
-	}
-	vq->last_add_time_valid = false;
-#endif
-
-	if (vq->event) {
-		needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
-					      new, old);
-	} else {
-		needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
-	}
-	END_USE(vq);
-	return needs_kick;
+	return vq->packed_ring ? virtqueue_kick_prepare_packed(_vq) :
+				 virtqueue_kick_prepare_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
 
@@ -625,60 +1862,6 @@ bool virtqueue_kick(struct virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
-		       void **ctx)
-{
-	unsigned int i, j;
-	__virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
-
-	/* Clear data ptr. */
-	vq->desc_state[head].data = NULL;
-
-	/* Put back on free list: unmap first-level descriptors and find end */
-	i = head;
-
-	while (vq->vring.desc[i].flags & nextflag) {
-		vring_unmap_one(vq, &vq->vring.desc[i]);
-		i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
-		vq->vq.num_free++;
-	}
-
-	vring_unmap_one(vq, &vq->vring.desc[i]);
-	vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
-	vq->free_head = head;
-
-	/* Plus final descriptor */
-	vq->vq.num_free++;
-
-	if (vq->indirect) {
-		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
-		u32 len;
-
-		/* Free the indirect table, if any, now that it's unmapped. */
-		if (!indir_desc)
-			return;
-
-		len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
-
-		BUG_ON(!(vq->vring.desc[head].flags &
-			 cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
-		BUG_ON(len == 0 || len % sizeof(struct vring_desc));
-
-		for (j = 0; j < len / sizeof(struct vring_desc); j++)
-			vring_unmap_one(vq, &indir_desc[j]);
-
-		kfree(indir_desc);
-		vq->desc_state[head].indir_desc = NULL;
-	} else if (ctx) {
-		*ctx = vq->desc_state[head].indir_desc;
-	}
-}
-
-static inline bool more_used(const struct vring_virtqueue *vq)
-{
-	return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
-}
-
 /**
  * virtqueue_get_buf - get the next used buffer
  * @vq: the struct virtqueue we're talking about.
@@ -699,57 +1882,9 @@ void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
 			    void **ctx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	void *ret;
-	unsigned int i;
-	u16 last_used;
-
-	START_USE(vq);
-
-	if (unlikely(vq->broken)) {
-		END_USE(vq);
-		return NULL;
-	}
-
-	if (!more_used(vq)) {
-		pr_debug("No more buffers in queue\n");
-		END_USE(vq);
-		return NULL;
-	}
-
-	/* Only get used array entries after they have been exposed by host. */
-	virtio_rmb(vq->weak_barriers);
-
-	last_used = (vq->last_used_idx & (vq->vring.num - 1));
-	i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
-	*len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
-
-	if (unlikely(i >= vq->vring.num)) {
-		BAD_RING(vq, "id %u out of range\n", i);
-		return NULL;
-	}
-	if (unlikely(!vq->desc_state[i].data)) {
-		BAD_RING(vq, "id %u is not a head!\n", i);
-		return NULL;
-	}
-
-	/* detach_buf clears data, so grab it now. */
-	ret = vq->desc_state[i].data;
-	detach_buf(vq, i, ctx);
-	vq->last_used_idx++;
-	/* If we expect an interrupt for the next entry, tell host
-	 * by writing event index and flush out the write before
-	 * the read in the next get_buf call. */
-	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
-		virtio_store_mb(vq->weak_barriers,
-				&vring_used_event(&vq->vring),
-				cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
-
-#ifdef DEBUG
-	vq->last_add_time_valid = false;
-#endif
 
-	END_USE(vq);
-	return ret;
+	return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
+				 virtqueue_get_buf_ctx_split(_vq, len, ctx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
 
@@ -771,12 +1906,10 @@ void virtqueue_disable_cb(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
-		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
-		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
-	}
-
+	if (vq->packed_ring)
+		virtqueue_disable_cb_packed(_vq);
+	else
+		virtqueue_disable_cb_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 
@@ -795,23 +1928,9 @@ EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
 unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	u16 last_used_idx;
-
-	START_USE(vq);
 
-	/* We optimistically turn back on interrupts, then check if there was
-	 * more to do. */
-	/* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
-	 * either clear the flags bit or point the event index at the next
-	 * entry. Always do both to keep code simple. */
-	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
-		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
-	}
-	vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
-	END_USE(vq);
-	return last_used_idx;
+	return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) :
+				 virtqueue_enable_cb_prepare_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
 
@@ -829,7 +1948,8 @@ bool virtqueue_poll(struct virtqueue *_vq, unsigned last_used_idx)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	virtio_mb(vq->weak_barriers);
-	return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
+	return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) :
+				 virtqueue_poll_split(_vq, last_used_idx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_poll);
 
@@ -847,6 +1967,7 @@ EXPORT_SYMBOL_GPL(virtqueue_poll);
 bool virtqueue_enable_cb(struct virtqueue *_vq)
 {
 	unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
+
 	return !virtqueue_poll(_vq, last_used_idx);
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
@@ -867,34 +1988,9 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	u16 bufs;
-
-	START_USE(vq);
-
-	/* We optimistically turn back on interrupts, then check if there was
-	 * more to do. */
-	/* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
-	 * either clear the flags bit or point the event index at the next
-	 * entry. Always update the event index to keep code simple. */
-	if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
-		vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
-		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
-	}
-	/* TODO: tune this threshold */
-	bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
-
-	virtio_store_mb(vq->weak_barriers,
-			&vring_used_event(&vq->vring),
-			cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
-
-	if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
-		END_USE(vq);
-		return false;
-	}
 
-	END_USE(vq);
-	return true;
+	return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
+				 virtqueue_enable_cb_delayed_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 
@@ -909,30 +2005,17 @@ EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
-	unsigned int i;
-	void *buf;
-
-	START_USE(vq);
-
-	for (i = 0; i < vq->vring.num; i++) {
-		if (!vq->desc_state[i].data)
-			continue;
-		/* detach_buf clears data, so grab it now. */
-		buf = vq->desc_state[i].data;
-		detach_buf(vq, i, NULL);
-		vq->avail_idx_shadow--;
-		vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
-		END_USE(vq);
-		return buf;
-	}
-	/* That should have freed everything. */
-	BUG_ON(vq->vq.num_free != vq->vring.num);
 
-	END_USE(vq);
-	return NULL;
+	return vq->packed_ring ? virtqueue_detach_unused_buf_packed(_vq) :
+				 virtqueue_detach_unused_buf_split(_vq);
 }
 EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
 
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+	return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq);
+}
+
 irqreturn_t vring_interrupt(int irq, void *_vq)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -953,6 +2036,7 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
 }
 EXPORT_SYMBOL_GPL(vring_interrupt);
 
+/* Only available for split ring */
 struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					struct vring vring,
 					struct virtio_device *vdev,
@@ -965,27 +2049,26 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	unsigned int i;
 	struct vring_virtqueue *vq;
 
-	vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
-		     GFP_KERNEL);
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return NULL;
+
+	vq = kmalloc(sizeof(*vq), GFP_KERNEL);
 	if (!vq)
 		return NULL;
 
-	vq->vring = vring;
+	vq->packed_ring = false;
 	vq->vq.callback = callback;
 	vq->vq.vdev = vdev;
 	vq->vq.name = name;
 	vq->vq.num_free = vring.num;
 	vq->vq.index = index;
 	vq->we_own_ring = false;
-	vq->queue_dma_addr = 0;
-	vq->queue_size_in_bytes = 0;
 	vq->notify = notify;
 	vq->weak_barriers = weak_barriers;
 	vq->broken = false;
 	vq->last_used_idx = 0;
-	vq->avail_flags_shadow = 0;
-	vq->avail_idx_shadow = 0;
 	vq->num_added = 0;
+	vq->use_dma_api = vring_use_dma_api(vdev);
 	list_add_tail(&vq->vq.list, &vdev->vqs);
 #ifdef DEBUG
 	vq->in_use = false;
@@ -996,65 +2079,39 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 		!context;
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
+	vq->split.queue_dma_addr = 0;
+	vq->split.queue_size_in_bytes = 0;
+
+	vq->split.vring = vring;
+	vq->split.avail_flags_shadow = 0;
+	vq->split.avail_idx_shadow = 0;
+
 	/* No callback?  Tell other side not to bother us. */
 	if (!callback) {
-		vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+		vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
 		if (!vq->event)
-			vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+			vq->split.vring.avail->flags = cpu_to_virtio16(vdev,
+					vq->split.avail_flags_shadow);
+	}
+
+	vq->split.desc_state = kmalloc_array(vring.num,
+			sizeof(struct vring_desc_state_split), GFP_KERNEL);
+	if (!vq->split.desc_state) {
+		kfree(vq);
+		return NULL;
 	}
 
 	/* Put everything in free lists. */
 	vq->free_head = 0;
 	for (i = 0; i < vring.num-1; i++)
-		vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
-	memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
+		vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
+	memset(vq->split.desc_state, 0, vring.num *
+			sizeof(struct vring_desc_state_split));
 
 	return &vq->vq;
 }
 EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
 
-static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
-			      dma_addr_t *dma_handle, gfp_t flag)
-{
-	if (vring_use_dma_api(vdev)) {
-		return dma_alloc_coherent(vdev->dev.parent, size,
-					  dma_handle, flag);
-	} else {
-		void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
-		if (queue) {
-			phys_addr_t phys_addr = virt_to_phys(queue);
-			*dma_handle = (dma_addr_t)phys_addr;
-
-			/*
-			 * Sanity check: make sure we dind't truncate
-			 * the address.  The only arches I can find that
-			 * have 64-bit phys_addr_t but 32-bit dma_addr_t
-			 * are certain non-highmem MIPS and x86
-			 * configurations, but these configurations
-			 * should never allocate physical pages above 32
-			 * bits, so this is fine.  Just in case, throw a
-			 * warning and abort if we end up with an
-			 * unrepresentable address.
-			 */
-			if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
-				free_pages_exact(queue, PAGE_ALIGN(size));
-				return NULL;
-			}
-		}
-		return queue;
-	}
-}
-
-static void vring_free_queue(struct virtio_device *vdev, size_t size,
-			     void *queue, dma_addr_t dma_handle)
-{
-	if (vring_use_dma_api(vdev)) {
-		dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
-	} else {
-		free_pages_exact(queue, PAGE_ALIGN(size));
-	}
-}
-
 struct virtqueue *vring_create_virtqueue(
 	unsigned int index,
 	unsigned int num,
@@ -1067,57 +2124,19 @@ struct virtqueue *vring_create_virtqueue(
 	void (*callback)(struct virtqueue *),
 	const char *name)
 {
-	struct virtqueue *vq;
-	void *queue = NULL;
-	dma_addr_t dma_addr;
-	size_t queue_size_in_bytes;
-	struct vring vring;
-
-	/* We assume num is a power of 2. */
-	if (num & (num - 1)) {
-		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
-		return NULL;
-	}
-
-	/* TODO: allocate each queue chunk individually */
-	for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
-		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
-					  &dma_addr,
-					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
-		if (queue)
-			break;
-	}
 
-	if (!num)
-		return NULL;
-
-	if (!queue) {
-		/* Try to get a single page. You are my only hope! */
-		queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
-					  &dma_addr, GFP_KERNEL|__GFP_ZERO);
-	}
-	if (!queue)
-		return NULL;
-
-	queue_size_in_bytes = vring_size(num, vring_align);
-	vring_init(&vring, num, queue, vring_align);
-
-	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
-				   notify, callback, name);
-	if (!vq) {
-		vring_free_queue(vdev, queue_size_in_bytes, queue,
-				 dma_addr);
-		return NULL;
-	}
-
-	to_vvq(vq)->queue_dma_addr = dma_addr;
-	to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes;
-	to_vvq(vq)->we_own_ring = true;
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return vring_create_virtqueue_packed(index, num, vring_align,
+				vdev, weak_barriers, may_reduce_num,
+				context, notify, callback, name);
 
-	return vq;
+	return vring_create_virtqueue_split(index, num, vring_align,
+			vdev, weak_barriers, may_reduce_num,
+			context, notify, callback, name);
 }
 EXPORT_SYMBOL_GPL(vring_create_virtqueue);
 
+/* Only available for split ring */
 struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int num,
 				      unsigned int vring_align,
@@ -1130,6 +2149,10 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      const char *name)
 {
 	struct vring vring;
+
+	if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+		return NULL;
+
 	vring_init(&vring, num, pages, vring_align);
 	return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
 				     notify, callback, name);
@@ -1141,8 +2164,32 @@ void vring_del_virtqueue(struct virtqueue *_vq)
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
 	if (vq->we_own_ring) {
-		vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
-				 vq->vring.desc, vq->queue_dma_addr);
+		if (vq->packed_ring) {
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.ring_size_in_bytes,
+					 vq->packed.vring.desc,
+					 vq->packed.ring_dma_addr);
+
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.event_size_in_bytes,
+					 vq->packed.vring.driver,
+					 vq->packed.driver_event_dma_addr);
+
+			vring_free_queue(vq->vq.vdev,
+					 vq->packed.event_size_in_bytes,
+					 vq->packed.vring.device,
+					 vq->packed.device_event_dma_addr);
+
+			kfree(vq->packed.desc_state);
+			kfree(vq->packed.desc_extra);
+		} else {
+			vring_free_queue(vq->vq.vdev,
+					 vq->split.queue_size_in_bytes,
+					 vq->split.vring.desc,
+					 vq->split.queue_dma_addr);
+
+			kfree(vq->split.desc_state);
+		}
 	}
 	list_del(&_vq->list);
 	kfree(vq);
@@ -1164,6 +2211,8 @@ void vring_transport_features(struct virtio_device *vdev)
 			break;
 		case VIRTIO_F_IOMMU_PLATFORM:
 			break;
+		case VIRTIO_F_RING_PACKED:
+			break;
 		default:
 			/* We don't understand this bit. */
 			__virtio_clear_bit(vdev, i);
@@ -1184,7 +2233,7 @@ unsigned int virtqueue_get_vring_size(struct virtqueue *_vq)
 
 	struct vring_virtqueue *vq = to_vvq(_vq);
 
-	return vq->vring.num;
+	return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
 
@@ -1217,7 +2266,10 @@ dma_addr_t virtqueue_get_desc_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr;
+	if (vq->packed_ring)
+		return vq->packed.ring_dma_addr;
+
+	return vq->split.queue_dma_addr;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);
 
@@ -1227,8 +2279,11 @@ dma_addr_t virtqueue_get_avail_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr +
-		((char *)vq->vring.avail - (char *)vq->vring.desc);
+	if (vq->packed_ring)
+		return vq->packed.driver_event_dma_addr;
+
+	return vq->split.queue_dma_addr +
+		((char *)vq->split.vring.avail - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);
 
@@ -1238,14 +2293,18 @@ dma_addr_t virtqueue_get_used_addr(struct virtqueue *_vq)
 
 	BUG_ON(!vq->we_own_ring);
 
-	return vq->queue_dma_addr +
-		((char *)vq->vring.used - (char *)vq->vring.desc);
+	if (vq->packed_ring)
+		return vq->packed.device_event_dma_addr;
+
+	return vq->split.queue_dma_addr +
+		((char *)vq->split.vring.used - (char *)vq->split.vring.desc);
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
 
+/* Only available for split ring */
 const struct vring *virtqueue_get_vring(struct virtqueue *vq)
 {
-	return &to_vvq(vq)->vring;
+	return &to_vvq(vq)->split.vring;
 }
 EXPORT_SYMBOL_GPL(virtqueue_get_vring);
 

include/uapi/linux/virtio_config.h

@@ -75,6 +75,9 @@
  */
 #define VIRTIO_F_IOMMU_PLATFORM		33
 
+/* This feature indicates support for the packed virtqueue layout. */
+#define VIRTIO_F_RING_PACKED		34
+
 /*
  * Does the device support Single Root I/O Virtualization?
  */

include/uapi/linux/virtio_ring.h

@@ -44,6 +44,13 @@
 /* This means the buffer contains a list of buffer descriptors. */
 #define VRING_DESC_F_INDIRECT	4
 
+/*
+ * Mark a descriptor as available or used in packed ring.
+ * Notice: they are defined as shifts instead of shifted values.
+ */
+#define VRING_PACKED_DESC_F_AVAIL	7
+#define VRING_PACKED_DESC_F_USED	15
+
 /* The Host uses this in used->flags to advise the Guest: don't kick me when
  * you add a buffer.  It's unreliable, so it's simply an optimization.  Guest
  * will still kick if it's out of buffers. */
@@ -53,6 +60,23 @@
  * optimization.  */
 #define VRING_AVAIL_F_NO_INTERRUPT	1
 
+/* Enable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_ENABLE	0x0
+/* Disable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_DISABLE	0x1
+/*
+ * Enable events for a specific descriptor in packed ring.
+ * (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
+ * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated.
+ */
+#define VRING_PACKED_EVENT_FLAG_DESC	0x2
+
+/*
+ * Wrap counter bit shift in event suppression structure
+ * of packed ring.
+ */
+#define VRING_PACKED_EVENT_F_WRAP_CTR	15
+
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
@@ -171,4 +195,32 @@ static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
 	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
+struct vring_packed_desc_event {
+	/* Descriptor Ring Change Event Offset/Wrap Counter. */
+	__le16 off_wrap;
+	/* Descriptor Ring Change Event Flags. */
+	__le16 flags;
+};
+
+struct vring_packed_desc {
+	/* Buffer Address. */
+	__le64 addr;
+	/* Buffer Length. */
+	__le32 len;
+	/* Buffer ID. */
+	__le16 id;
+	/* The flags depending on descriptor type. */
+	__le16 flags;
+};
+
+struct vring_packed {
+	unsigned int num;
+
+	struct vring_packed_desc *desc;
+
+	struct vring_packed_desc_event *driver;
+
+	struct vring_packed_desc_event *device;
+};
+
 #endif /* _UAPI_LINUX_VIRTIO_RING_H */