Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:
 "Fixes, cleanups, performance

  A bunch of changes to virtio, most affecting virtio net. Also ptr_ring
  batched zeroing - first of batching enhancements that seems ready."

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  s390/virtio: change maintainership
  tools/virtio: fix spelling mistake: "wakeus" -> "wakeups"
  virtio_net: tidy a couple debug statements
  ptr_ring: support testing different batching sizes
  ringtest: support test specific parameters
  ptr_ring: batch ring zeroing
  virtio: virtio_driver doc
  virtio_net: don't reset twice on XDP on/off
  virtio_net: fix support for small rings
  virtio_net: reduce alignment for buffers
  virtio_net: rework mergeable buffer handling
  virtio_net: allow specifying context for rx
  virtio: allow extra context per descriptor
  tools/virtio: fix build breakage
  virtio: add context flag to find vqs
  virtio: wrap find_vqs
  ringtest: fix an assert statement

MAINTAINERS

@@ -13556,8 +13556,8 @@ F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
 
 VIRTIO DRIVERS FOR S390
-M:	Christian Borntraeger <borntraeger@de.ibm.com>
 M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+M:	Halil Pasic <pasic@linux.vnet.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	virtualization@lists.linux-foundation.org
 L:	kvm@vger.kernel.org

drivers/block/virtio_blk.c

@@ -452,8 +452,7 @@ static int init_vq(struct virtio_blk *vblk)
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
-			&desc);
+	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
 	if (err)
 		goto out;
 

drivers/char/virtio_console.c

@@ -1945,9 +1945,9 @@ static int init_vqs(struct ports_device *portdev)
 		}
 	}
 	/* Find the queues. */
-	err = portdev->vdev->config->find_vqs(portdev->vdev, nr_queues, vqs,
-					      io_callbacks,
-					      (const char **)io_names, NULL);
+	err = virtio_find_vqs(portdev->vdev, nr_queues, vqs,
+			      io_callbacks,
+			      (const char **)io_names, NULL);
 	if (err)
 		goto free;
 

drivers/crypto/virtio/virtio_crypto_core.c

@@ -119,8 +119,7 @@ static int virtcrypto_find_vqs(struct virtio_crypto *vi)
 		names[i] = vi->data_vq[i].name;
 	}
 
-	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names, NULL);
+	ret = virtio_find_vqs(vi->vdev, total_vqs, vqs, callbacks, names, NULL);
 	if (ret)
 		goto err_find;
 

drivers/gpu/drm/virtio/virtgpu_kms.c

@@ -175,8 +175,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags)
 	DRM_INFO("virgl 3d acceleration not supported by guest\n");
 #endif
 
-	ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs,
-					    callbacks, names, NULL);
+	ret = virtio_find_vqs(vgdev->vdev, 2, vqs, callbacks, names, NULL);
 	if (ret) {
 		DRM_ERROR("failed to find virt queues\n");
 		goto err_vqs;

drivers/misc/mic/vop/vop_main.c

@@ -278,7 +278,7 @@ static void vop_del_vqs(struct virtio_device *dev)
 static struct virtqueue *vop_find_vq(struct virtio_device *dev,
 				     unsigned index,
 				     void (*callback)(struct virtqueue *vq),
-				     const char *name)
+				     const char *name, bool ctx)
 {
 	struct _vop_vdev *vdev = to_vopvdev(dev);
 	struct vop_device *vpdev = vdev->vpdev;
@@ -314,6 +314,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev,
 				le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN,
 				dev,
 				false,
+				ctx,
 				(void __force *)va, vop_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
@@ -374,7 +375,8 @@ unmap:
 static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
-			const char * const names[], struct irq_affinity *desc)
+			const char * const names[], const bool *ctx,
+			struct irq_affinity *desc)
 {
 	struct _vop_vdev *vdev = to_vopvdev(dev);
 	struct vop_device *vpdev = vdev->vpdev;
@@ -388,7 +390,8 @@ static int vop_find_vqs(struct virtio_device *dev, unsigned nvqs,
 	for (i = 0; i < nvqs; ++i) {
 		dev_dbg(_vop_dev(vdev), "%s: %d: %s\n",
 			__func__, i, names[i]);
-		vqs[i] = vop_find_vq(dev, i, callbacks[i], names[i]);
+		vqs[i] = vop_find_vq(dev, i, callbacks[i], names[i],
+				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
 			goto error;

drivers/net/caif/caif_virtio.c

@@ -679,8 +679,7 @@ static int cfv_probe(struct virtio_device *vdev)
 		goto err;
 
 	/* Get the TX virtio ring. This is a "guest side vring". */
-	err = vdev->config->find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names,
-			NULL);
+	err = virtio_find_vqs(vdev, 1, &cfv->vq_tx, &vq_cbs, &names, NULL);
 	if (err)
 		goto err;
 

drivers/net/virtio_net.c

@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/cpu.h>
 #include <linux/average.h>
+#include <net/route.h>
 
 static int napi_weight = NAPI_POLL_WEIGHT;
 module_param(napi_weight, int, 0444);
@@ -54,17 +55,6 @@ module_param(napi_tx, bool, 0644);
  */
 DECLARE_EWMA(pkt_len, 0, 64)
 
-/* With mergeable buffers we align buffer address and use the low bits to
- * encode its true size. Buffer size is up to 1 page so we need to align to
- * square root of page size to ensure we reserve enough bits to encode the true
- * size.
- */
-#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
-
-/* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
-				   1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
-
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
 struct virtnet_stats {
@@ -112,6 +102,9 @@ struct receive_queue {
 	/* RX: fragments + linear part + virtio header */
 	struct scatterlist sg[MAX_SKB_FRAGS + 2];
 
+	/* Min single buffer size for mergeable buffers case. */
+	unsigned int min_buf_len;
+
 	/* Name of this receive queue: input.$index */
 	char name[40];
 };
@@ -277,24 +270,6 @@ static void skb_xmit_done(struct virtqueue *vq)
 		netif_wake_subqueue(vi->dev, vq2txq(vq));
 }
 
-static unsigned int mergeable_ctx_to_buf_truesize(unsigned long mrg_ctx)
-{
-	unsigned int truesize = mrg_ctx & (MERGEABLE_BUFFER_ALIGN - 1);
-	return (truesize + 1) * MERGEABLE_BUFFER_ALIGN;
-}
-
-static void *mergeable_ctx_to_buf_address(unsigned long mrg_ctx)
-{
-	return (void *)(mrg_ctx & -MERGEABLE_BUFFER_ALIGN);
-
-}
-
-static unsigned long mergeable_buf_to_ctx(void *buf, unsigned int truesize)
-{
-	unsigned int size = truesize / MERGEABLE_BUFFER_ALIGN;
-	return (unsigned long)buf | (size - 1);
-}
-
 /* Called from bottom half context */
 static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 				   struct receive_queue *rq,
@@ -538,15 +513,13 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 
 	while (--*num_buf) {
 		unsigned int buflen;
-		unsigned long ctx;
 		void *buf;
 		int off;
 
-		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &buflen);
-		if (unlikely(!ctx))
+		buf = virtqueue_get_buf(rq->vq, &buflen);
+		if (unlikely(!buf))
 			goto err_buf;
 
-		buf = mergeable_ctx_to_buf_address(ctx);
 		p = virt_to_head_page(buf);
 		off = buf - page_address(p);
 
@@ -575,10 +548,10 @@ err_buf:
 static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 struct virtnet_info *vi,
 					 struct receive_queue *rq,
-					 unsigned long ctx,
+					 void *buf,
+					 void *ctx,
 					 unsigned int len)
 {
-	void *buf = mergeable_ctx_to_buf_address(ctx);
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
 	struct page *page = virt_to_head_page(buf);
@@ -666,7 +639,13 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	}
 	rcu_read_unlock();
 
-	truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
+	if (unlikely(len > (unsigned long)ctx)) {
+		pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+			 dev->name, len, (unsigned long)ctx);
+		dev->stats.rx_length_errors++;
+		goto err_skb;
+	}
+	truesize = (unsigned long)ctx;
 	head_skb = page_to_skb(vi, rq, page, offset, len, truesize);
 	curr_skb = head_skb;
 
@@ -675,7 +654,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	while (--num_buf) {
 		int num_skb_frags;
 
-		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
+		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
 		if (unlikely(!ctx)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, num_buf,
@@ -685,8 +664,14 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
-		buf = mergeable_ctx_to_buf_address(ctx);
 		page = virt_to_head_page(buf);
+		if (unlikely(len > (unsigned long)ctx)) {
+			pr_debug("%s: rx error: len %u exceeds truesize %lu\n",
+				 dev->name, len, (unsigned long)ctx);
+			dev->stats.rx_length_errors++;
+			goto err_skb;
+		}
+		truesize = (unsigned long)ctx;
 
 		num_skb_frags = skb_shinfo(curr_skb)->nr_frags;
 		if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) {
@@ -702,7 +687,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			head_skb->truesize += nskb->truesize;
 			num_skb_frags = 0;
 		}
-		truesize = max(len, mergeable_ctx_to_buf_truesize(ctx));
 		if (curr_skb != head_skb) {
 			head_skb->data_len += len;
 			head_skb->len += len;
@@ -727,14 +711,14 @@ err_xdp:
 err_skb:
 	put_page(page);
 	while (--num_buf) {
-		ctx = (unsigned long)virtqueue_get_buf(rq->vq, &len);
-		if (unlikely(!ctx)) {
+		buf = virtqueue_get_buf(rq->vq, &len);
+		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
 				 dev->name, num_buf);
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		page = virt_to_head_page(mergeable_ctx_to_buf_address(ctx));
+		page = virt_to_head_page(buf);
 		put_page(page);
 	}
 err_buf:
@@ -745,7 +729,7 @@ xdp_xmit:
 }
 
 static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len)
+		       void *buf, unsigned int len, void **ctx)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -756,9 +740,7 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		pr_debug("%s: short packet %i\n", dev->name, len);
 		dev->stats.rx_length_errors++;
 		if (vi->mergeable_rx_bufs) {
-			unsigned long ctx = (unsigned long)buf;
-			void *base = mergeable_ctx_to_buf_address(ctx);
-			put_page(virt_to_head_page(base));
+			put_page(virt_to_head_page(buf));
 		} else if (vi->big_packets) {
 			give_pages(rq, buf);
 		} else {
@@ -768,7 +750,7 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, (unsigned long)buf, len);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len);
 	else if (vi->big_packets)
 		skb = receive_big(dev, vi, rq, buf, len);
 	else
@@ -880,14 +862,15 @@ static int add_recvbuf_big(struct virtnet_info *vi, struct receive_queue *rq,
 	return err;
 }
 
-static unsigned int get_mergeable_buf_len(struct ewma_pkt_len *avg_pkt_len)
+static unsigned int get_mergeable_buf_len(struct receive_queue *rq,
+					  struct ewma_pkt_len *avg_pkt_len)
 {
 	const size_t hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
 	unsigned int len;
 
 	len = hdr_len + clamp_t(unsigned int, ewma_pkt_len_read(avg_pkt_len),
-			GOOD_PACKET_LEN, PAGE_SIZE - hdr_len);
-	return ALIGN(len, MERGEABLE_BUFFER_ALIGN);
+				rq->min_buf_len - hdr_len, PAGE_SIZE - hdr_len);
+	return ALIGN(len, L1_CACHE_BYTES);
 }
 
 static int add_recvbuf_mergeable(struct virtnet_info *vi,
@@ -896,17 +879,17 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	struct page_frag *alloc_frag = &rq->alloc_frag;
 	unsigned int headroom = virtnet_get_headroom(vi);
 	char *buf;
-	unsigned long ctx;
+	void *ctx;
 	int err;
 	unsigned int len, hole;
 
-	len = get_mergeable_buf_len(&rq->mrg_avg_pkt_len);
+	len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len);
 	if (unlikely(!skb_page_frag_refill(len + headroom, alloc_frag, gfp)))
 		return -ENOMEM;
 
 	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
 	buf += headroom; /* advance address leaving hole at front of pkt */
-	ctx = mergeable_buf_to_ctx(buf, len);
+	ctx = (void *)(unsigned long)len;
 	get_page(alloc_frag->page);
 	alloc_frag->offset += len + headroom;
 	hole = alloc_frag->size - alloc_frag->offset;
@@ -921,7 +904,7 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	}
 
 	sg_init_one(rq->sg, buf, len);
-	err = virtqueue_add_inbuf(rq->vq, rq->sg, 1, (void *)ctx, gfp);
+	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0)
 		put_page(virt_to_head_page(buf));
 
@@ -1032,10 +1015,20 @@ static int virtnet_receive(struct receive_queue *rq, int budget)
 	void *buf;
 	struct virtnet_stats *stats = this_cpu_ptr(vi->stats);
 
-	while (received < budget &&
-	       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-		bytes += receive_buf(vi, rq, buf, len);
-		received++;
+	if (vi->mergeable_rx_bufs) {
+		void *ctx;
+
+		while (received < budget &&
+		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
+			bytes += receive_buf(vi, rq, buf, len, ctx);
+			received++;
+		}
+	} else {
+		while (received < budget &&
+		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+			bytes += receive_buf(vi, rq, buf, len, NULL);
+			received++;
+		}
 	}
 
 	if (rq->vq->num_free > virtqueue_get_vring_size(rq->vq) / 2) {
@@ -1854,7 +1847,6 @@ static int virtnet_reset(struct virtnet_info *vi, int curr_qp, int xdp_qp)
 	virtnet_freeze_down(dev);
 	_remove_vq_common(vi);
 
-	dev->config->reset(dev);
 	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
 	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
 
@@ -2118,9 +2110,7 @@ static void free_unused_bufs(struct virtnet_info *vi)
 
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
 			if (vi->mergeable_rx_bufs) {
-				unsigned long ctx = (unsigned long)buf;
-				void *base = mergeable_ctx_to_buf_address(ctx);
-				put_page(virt_to_head_page(base));
+				put_page(virt_to_head_page(buf));
 			} else if (vi->big_packets) {
 				give_pages(&vi->rq[i], buf);
 			} else {
@@ -2141,6 +2131,21 @@ static void virtnet_del_vqs(struct virtnet_info *vi)
 	virtnet_free_queues(vi);
 }
 
+/* How large should a single buffer be so a queue full of these can fit at
+ * least one full packet?
+ * Logic below assumes the mergeable buffer header is used.
+ */
+static unsigned int mergeable_min_buf_len(struct virtnet_info *vi, struct virtqueue *vq)
+{
+	const unsigned int hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	unsigned int rq_size = virtqueue_get_vring_size(vq);
+	unsigned int packet_len = vi->big_packets ? IP_MAX_MTU : vi->dev->max_mtu;
+	unsigned int buf_len = hdr_len + ETH_HLEN + VLAN_HLEN + packet_len;
+	unsigned int min_buf_len = DIV_ROUND_UP(buf_len, rq_size);
+
+	return max(min_buf_len, hdr_len);
+}
+
 static int virtnet_find_vqs(struct virtnet_info *vi)
 {
 	vq_callback_t **callbacks;
@@ -2148,6 +2153,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	int ret = -ENOMEM;
 	int i, total_vqs;
 	const char **names;
+	bool *ctx;
 
 	/* We expect 1 RX virtqueue followed by 1 TX virtqueue, followed by
 	 * possible N-1 RX/TX queue pairs used in multiqueue mode, followed by
@@ -2166,6 +2172,13 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	names = kmalloc(total_vqs * sizeof(*names), GFP_KERNEL);
 	if (!names)
 		goto err_names;
+	if (vi->mergeable_rx_bufs) {
+		ctx = kzalloc(total_vqs * sizeof(*ctx), GFP_KERNEL);
+		if (!ctx)
+			goto err_ctx;
+	} else {
+		ctx = NULL;
+	}
 
 	/* Parameters for control virtqueue, if any */
 	if (vi->has_cvq) {
@@ -2181,10 +2194,12 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 		sprintf(vi->sq[i].name, "output.%d", i);
 		names[rxq2vq(i)] = vi->rq[i].name;
 		names[txq2vq(i)] = vi->sq[i].name;
+		if (ctx)
+			ctx[rxq2vq(i)] = true;
 	}
 
 	ret = vi->vdev->config->find_vqs(vi->vdev, total_vqs, vqs, callbacks,
-					 names, NULL);
+					 names, ctx, NULL);
 	if (ret)
 		goto err_find;
 
@@ -2196,6 +2211,7 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		vi->rq[i].vq = vqs[rxq2vq(i)];
+		vi->rq[i].min_buf_len = mergeable_min_buf_len(vi, vi->rq[i].vq);
 		vi->sq[i].vq = vqs[txq2vq(i)];
 	}
 
@@ -2206,6 +2222,8 @@ static int virtnet_find_vqs(struct virtnet_info *vi)
 	return 0;
 
 err_find:
+	kfree(ctx);
+err_ctx:
 	kfree(names);
 err_names:
 	kfree(callbacks);
@@ -2282,7 +2300,8 @@ static ssize_t mergeable_rx_buffer_size_show(struct netdev_rx_queue *queue,
 
 	BUG_ON(queue_index >= vi->max_queue_pairs);
 	avg = &vi->rq[queue_index].mrg_avg_pkt_len;
-	return sprintf(buf, "%u\n", get_mergeable_buf_len(avg));
+	return sprintf(buf, "%u\n",
+		       get_mergeable_buf_len(&vi->rq[queue_index], avg));
 }
 
 static struct rx_queue_attribute mergeable_rx_buffer_size_attribute =

drivers/remoteproc/remoteproc_virtio.c

@@ -71,7 +71,7 @@ EXPORT_SYMBOL(rproc_vq_interrupt);
 static struct virtqueue *rp_find_vq(struct virtio_device *vdev,
 				    unsigned int id,
 				    void (*callback)(struct virtqueue *vq),
-				    const char *name)
+				    const char *name, bool ctx)
 {
 	struct rproc_vdev *rvdev = vdev_to_rvdev(vdev);
 	struct rproc *rproc = vdev_to_rproc(vdev);
@@ -103,8 +103,8 @@ 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(id, len, rvring->align, vdev, false, addr,
-				 rproc_virtio_notify, callback, name);
+	vq = vring_new_virtqueue(id, len, rvring->align, vdev, false, ctx,
+				 addr, rproc_virtio_notify, callback, name);
 	if (!vq) {
 		dev_err(dev, "vring_new_virtqueue %s failed\n", name);
 		rproc_free_vring(rvring);
@@ -138,12 +138,14 @@ static int rproc_virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs,
 				 struct virtqueue *vqs[],
 				 vq_callback_t *callbacks[],
 				 const char * const names[],
+				 const bool * ctx,
 				 struct irq_affinity *desc)
 {
 	int i, ret;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = rp_find_vq(vdev, i, callbacks[i], names[i]);
+		vqs[i] = rp_find_vq(vdev, i, callbacks[i], names[i],
+				    ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			ret = PTR_ERR(vqs[i]);
 			goto error;

drivers/rpmsg/virtio_rpmsg_bus.c

@@ -869,7 +869,7 @@ static int rpmsg_probe(struct virtio_device *vdev)
 	init_waitqueue_head(&vrp->sendq);
 
 	/* We expect two virtqueues, rx and tx (and in this order) */
-	err = vdev->config->find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
+	err = virtio_find_vqs(vdev, 2, vqs, vq_cbs, names, NULL);
 	if (err)
 		goto free_vrp;
 

drivers/s390/virtio/kvm_virtio.c

@@ -189,7 +189,7 @@ static bool kvm_notify(struct virtqueue *vq)
 static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
 				     unsigned index,
 				     void (*callback)(struct virtqueue *vq),
-				     const char *name)
+				     const char *name, bool ctx)
 {
 	struct kvm_device *kdev = to_kvmdev(vdev);
 	struct kvm_vqconfig *config;
@@ -211,7 +211,7 @@ static struct virtqueue *kvm_find_vq(struct virtio_device *vdev,
 		goto out;
 
 	vq = vring_new_virtqueue(index, config->num, KVM_S390_VIRTIO_RING_ALIGN,
-				 vdev, true, (void *) config->address,
+				 vdev, true, ctx, (void *) config->address,
 				 kvm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
@@ -256,6 +256,7 @@ static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			struct virtqueue *vqs[],
 			vq_callback_t *callbacks[],
 			const char * const names[],
+			const bool *ctx,
 			struct irq_affinity *desc)
 {
 	struct kvm_device *kdev = to_kvmdev(vdev);
@@ -266,7 +267,8 @@ static int kvm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		return -ENOENT;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i]);
+		vqs[i] = kvm_find_vq(vdev, i, callbacks[i], names[i],
+				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i]))
 			goto error;
 	}

drivers/s390/virtio/virtio_ccw.c

@@ -484,7 +484,7 @@ static void virtio_ccw_del_vqs(struct virtio_device *vdev)
 
 static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
 					     int i, vq_callback_t *callback,
-					     const char *name,
+					     const char *name, bool ctx,
 					     struct ccw1 *ccw)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
@@ -522,7 +522,7 @@ static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
 	}
 
 	vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev,
-				 true, info->queue, virtio_ccw_kvm_notify,
+				 true, ctx, info->queue, virtio_ccw_kvm_notify,
 				 callback, name);
 	if (!vq) {
 		/* For now, we fail if we can't get the requested size. */
@@ -629,6 +629,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
 			       const char * const names[],
+			       const bool *ctx,
 			       struct irq_affinity *desc)
 {
 	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
@@ -642,7 +643,7 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 
 	for (i = 0; i < nvqs; ++i) {
 		vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i],
-					     ccw);
+					     ctx ? ctx[i] : false, ccw);
 		if (IS_ERR(vqs[i])) {
 			ret = PTR_ERR(vqs[i]);
 			vqs[i] = NULL;

drivers/scsi/virtio_scsi.c

@@ -894,8 +894,7 @@ static int virtscsi_init(struct virtio_device *vdev,
 	}
 
 	/* Discover virtqueues and write information to configuration.  */
-	err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names,
-			&desc);
+	err = virtio_find_vqs(vdev, num_vqs, vqs, callbacks, names, &desc);
 	if (err)
 		goto out;
 

drivers/virtio/virtio_balloon.c

@@ -418,8 +418,7 @@ static int init_vqs(struct virtio_balloon *vb)
 	 * optionally stat.
 	 */
 	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
-	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks, names,
-			NULL);
+	err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
 	if (err)
 		return err;
 

drivers/virtio/virtio_input.c

@@ -173,8 +173,7 @@ static int virtinput_init_vqs(struct virtio_input *vi)
 	static const char * const names[] = { "events", "status" };
 	int err;
 
-	err = vi->vdev->config->find_vqs(vi->vdev, 2, vqs, cbs, names,
-			NULL);
+	err = virtio_find_vqs(vi->vdev, 2, vqs, cbs, names, NULL);
 	if (err)
 		return err;
 	vi->evt = vqs[0];

drivers/virtio/virtio_mmio.c

@@ -351,7 +351,7 @@ static void vm_del_vqs(struct virtio_device *vdev)
 
 static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 				  void (*callback)(struct virtqueue *vq),
-				  const char *name)
+				  const char *name, bool ctx)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	struct virtio_mmio_vq_info *info;
@@ -388,7 +388,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned index,
 
 	/* Create the vring */
 	vq = vring_create_virtqueue(index, num, VIRTIO_MMIO_VRING_ALIGN, vdev,
-				 true, true, vm_notify, callback, name);
+				 true, true, ctx, vm_notify, callback, name);
 	if (!vq) {
 		err = -ENOMEM;
 		goto error_new_virtqueue;
@@ -447,6 +447,7 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
 		       const char * const names[],
+		       const bool *ctx,
 		       struct irq_affinity *desc)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
@@ -459,7 +460,8 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		return err;
 
 	for (i = 0; i < nvqs; ++i) {
-		vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i]);
+		vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i],
+				     ctx ? ctx[i] : false);
 		if (IS_ERR(vqs[i])) {
 			vm_del_vqs(vdev);
 			return PTR_ERR(vqs[i]);

drivers/virtio/virtio_pci_common.c

@@ -172,6 +172,7 @@ error:
 static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
 				     void (*callback)(struct virtqueue *vq),
 				     const char *name,
+				     bool ctx,
 				     u16 msix_vec)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -183,7 +184,7 @@ static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned index,
 	if (!info)
 		return ERR_PTR(-ENOMEM);
 
-	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name,
+	vq = vp_dev->setup_vq(vp_dev, info, index, callback, name, ctx,
 			      msix_vec);
 	if (IS_ERR(vq))
 		goto out_info;
@@ -274,6 +275,7 @@ void vp_del_vqs(struct virtio_device *vdev)
 static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
 		const char * const names[], bool per_vq_vectors,
+		const bool *ctx,
 		struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -315,6 +317,7 @@ static int vp_find_vqs_msix(struct virtio_device *vdev, unsigned nvqs,
 		else
 			msix_vec = VP_MSIX_VQ_VECTOR;
 		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+				     ctx ? ctx[i] : false,
 				     msix_vec);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
@@ -345,7 +348,7 @@ error_find:
 
 static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[])
+		const char * const names[], const bool *ctx)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	int i, err;
@@ -367,6 +370,7 @@ static int vp_find_vqs_intx(struct virtio_device *vdev, unsigned nvqs,
 			continue;
 		}
 		vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+				     ctx ? ctx[i] : false,
 				     VIRTIO_MSI_NO_VECTOR);
 		if (IS_ERR(vqs[i])) {
 			err = PTR_ERR(vqs[i]);
@@ -383,20 +387,21 @@ out_del_vqs:
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], struct irq_affinity *desc)
+		const char * const names[], const bool *ctx,
+		struct irq_affinity *desc)
 {
 	int err;
 
 	/* Try MSI-X with one vector per queue. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, true, ctx, desc);
 	if (!err)
 		return 0;
 	/* Fallback: MSI-X with one vector for config, one shared for queues. */
-	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, desc);
+	err = vp_find_vqs_msix(vdev, nvqs, vqs, callbacks, names, false, ctx, desc);
 	if (!err)
 		return 0;
 	/* Finally fall back to regular interrupts. */
-	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names);
+	return vp_find_vqs_intx(vdev, nvqs, vqs, callbacks, names, ctx);
 }
 
 const char *vp_bus_name(struct virtio_device *vdev)

drivers/virtio/virtio_pci_common.h

@@ -102,6 +102,7 @@ struct virtio_pci_device {
 				      unsigned idx,
 				      void (*callback)(struct virtqueue *vq),
 				      const char *name,
+				      bool ctx,
 				      u16 msix_vec);
 	void (*del_vq)(struct virtio_pci_vq_info *info);
 
@@ -131,7 +132,8 @@ void vp_del_vqs(struct virtio_device *vdev);
 /* the config->find_vqs() implementation */
 int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], struct irq_affinity *desc);
+		const char * const names[], const bool *ctx,
+		struct irq_affinity *desc);
 const char *vp_bus_name(struct virtio_device *vdev);
 
 /* Setup the affinity for a virtqueue:

drivers/virtio/virtio_pci_legacy.c

@@ -116,6 +116,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
+				  bool ctx,
 				  u16 msix_vec)
 {
 	struct virtqueue *vq;
@@ -135,7 +136,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
-				    true, false, vp_notify, callback, name);
+				    true, false, ctx,
+				    vp_notify, callback, name);
 	if (!vq)
 		return ERR_PTR(-ENOMEM);
 

drivers/virtio/virtio_pci_modern.c

@@ -297,6 +297,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 				  unsigned index,
 				  void (*callback)(struct virtqueue *vq),
 				  const char *name,
+				  bool ctx,
 				  u16 msix_vec)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
@@ -328,7 +329,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
 	/* create the vring */
 	vq = vring_create_virtqueue(index, num,
 				    SMP_CACHE_BYTES, &vp_dev->vdev,
-				    true, true, vp_notify, callback, name);
+				    true, true, ctx,
+				    vp_notify, callback, name);
 	if (!vq)
 		return ERR_PTR(-ENOMEM);
 
@@ -387,12 +389,14 @@ err_map_notify:
 }
 
 static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
-		struct virtqueue *vqs[], vq_callback_t *callbacks[],
-		const char * const names[], struct irq_affinity *desc)
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char * const names[], const bool *ctx,
+			      struct irq_affinity *desc)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	struct virtqueue *vq;
-	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, desc);
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, desc);
 
 	if (rc)
 		return rc;

drivers/virtio/virtio_ring.c

@@ -263,6 +263,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 				unsigned int out_sgs,
 				unsigned int in_sgs,
 				void *data,
+				void *ctx,
 				gfp_t gfp)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
@@ -275,6 +276,7 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	START_USE(vq);
 
 	BUG_ON(data == NULL);
+	BUG_ON(ctx && vq->indirect);
 
 	if (unlikely(vq->broken)) {
 		END_USE(vq);
@@ -389,6 +391,8 @@ static inline int virtqueue_add(struct virtqueue *_vq,
 	vq->desc_state[head].data = data;
 	if (indirect)
 		vq->desc_state[head].indir_desc = desc;
+	if (ctx)
+		vq->desc_state[head].indir_desc = ctx;
 
 	/* Put entry in available array (but don't update avail->idx until they
 	 * do sync). */
@@ -461,7 +465,8 @@ int virtqueue_add_sgs(struct virtqueue *_vq,
 		for (sg = sgs[i]; sg; sg = sg_next(sg))
 			total_sg++;
 	}
-	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs, data, gfp);
+	return virtqueue_add(_vq, sgs, total_sg, out_sgs, in_sgs,
+			     data, NULL, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_sgs);
 
@@ -483,7 +488,7 @@ int virtqueue_add_outbuf(struct virtqueue *vq,
 			 void *data,
 			 gfp_t gfp)
 {
-	return virtqueue_add(vq, &sg, num, 1, 0, data, gfp);
+	return virtqueue_add(vq, &sg, num, 1, 0, data, NULL, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_outbuf);
 
@@ -505,10 +510,34 @@ int virtqueue_add_inbuf(struct virtqueue *vq,
 			void *data,
 			gfp_t gfp)
 {
-	return virtqueue_add(vq, &sg, num, 0, 1, data, gfp);
+	return virtqueue_add(vq, &sg, num, 0, 1, data, NULL, gfp);
 }
 EXPORT_SYMBOL_GPL(virtqueue_add_inbuf);
 
+/**
+ * virtqueue_add_inbuf_ctx - expose input buffers to other end
+ * @vq: the struct virtqueue we're talking about.
+ * @sg: scatterlist (must be well-formed and terminated!)
+ * @num: the number of entries in @sg writable by other side
+ * @data: the token identifying the buffer.
+ * @ctx: extra context for the token
+ * @gfp: how to do memory allocations (if necessary).
+ *
+ * Caller must ensure we don't call this with other virtqueue operations
+ * at the same time (except where noted).
+ *
+ * Returns zero or a negative error (ie. ENOSPC, ENOMEM, EIO).
+ */
+int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
+			struct scatterlist *sg, unsigned int num,
+			void *data,
+			void *ctx,
+			gfp_t gfp)
+{
+	return virtqueue_add(vq, &sg, num, 0, 1, data, ctx, gfp);
+}
+EXPORT_SYMBOL_GPL(virtqueue_add_inbuf_ctx);
+
 /**
  * virtqueue_kick_prepare - first half of split virtqueue_kick call.
  * @vq: the struct virtqueue
@@ -598,7 +627,8 @@ bool virtqueue_kick(struct virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_kick);
 
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
+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);
@@ -622,10 +652,15 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 	/* Plus final descriptor */
 	vq->vq.num_free++;
 
-	/* Free the indirect table, if any, now that it's unmapped. */
-	if (vq->desc_state[head].indir_desc) {
+	if (vq->indirect) {
 		struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
-		u32 len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
+		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)));
@@ -634,8 +669,10 @@ static void detach_buf(struct vring_virtqueue *vq, unsigned int head)
 		for (j = 0; j < len / sizeof(struct vring_desc); j++)
 			vring_unmap_one(vq, &indir_desc[j]);
 
-		kfree(vq->desc_state[head].indir_desc);
+		kfree(indir_desc);
 		vq->desc_state[head].indir_desc = NULL;
+	} else if (ctx) {
+		*ctx = vq->desc_state[head].indir_desc;
 	}
 }
 
@@ -660,7 +697,8 @@ static inline bool more_used(const struct vring_virtqueue *vq)
  * Returns NULL if there are no used buffers, or the "data" token
  * handed to virtqueue_add_*().
  */
-void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+void *virtqueue_get_buf_ctx(struct virtqueue *_vq, unsigned int *len,
+			    void **ctx)
 {
 	struct vring_virtqueue *vq = to_vvq(_vq);
 	void *ret;
@@ -698,7 +736,7 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 
 	/* detach_buf clears data, so grab it now. */
 	ret = vq->desc_state[i].data;
-	detach_buf(vq, i);
+	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
@@ -715,8 +753,13 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
 	END_USE(vq);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(virtqueue_get_buf);
+EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
 
+void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
+{
+	return virtqueue_get_buf_ctx(_vq, len, NULL);
+}
+EXPORT_SYMBOL_GPL(virtqueue_get_buf);
 /**
  * virtqueue_disable_cb - disable callbacks
  * @vq: the struct virtqueue we're talking about.
@@ -878,7 +921,7 @@ void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 			continue;
 		/* detach_buf clears data, so grab it now. */
 		buf = vq->desc_state[i].data;
-		detach_buf(vq, i);
+		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);
@@ -916,6 +959,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					struct vring vring,
 					struct virtio_device *vdev,
 					bool weak_barriers,
+					bool context,
 					bool (*notify)(struct virtqueue *),
 					void (*callback)(struct virtqueue *),
 					const char *name)
@@ -950,7 +994,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 	vq->last_add_time_valid = false;
 #endif
 
-	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+	vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+		!context;
 	vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
 	/* No callback?  Tell other side not to bother us. */
@@ -1019,6 +1064,7 @@ struct virtqueue *vring_create_virtqueue(
 	struct virtio_device *vdev,
 	bool weak_barriers,
 	bool may_reduce_num,
+	bool context,
 	bool (*notify)(struct virtqueue *),
 	void (*callback)(struct virtqueue *),
 	const char *name)
@@ -1058,7 +1104,7 @@ struct virtqueue *vring_create_virtqueue(
 	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,
+	vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
 				   notify, callback, name);
 	if (!vq) {
 		vring_free_queue(vdev, queue_size_in_bytes, queue,
@@ -1079,6 +1125,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
+				      bool context,
 				      void *pages,
 				      bool (*notify)(struct virtqueue *vq),
 				      void (*callback)(struct virtqueue *vq),
@@ -1086,7 +1133,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 {
 	struct vring vring;
 	vring_init(&vring, num, pages, vring_align);
-	return __vring_new_virtqueue(index, vring, vdev, weak_barriers,
+	return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
 				     notify, callback, name);
 }
 EXPORT_SYMBOL_GPL(vring_new_virtqueue);

include/linux/ptr_ring.h

@@ -34,11 +34,13 @@
 struct ptr_ring {
 	int producer ____cacheline_aligned_in_smp;
 	spinlock_t producer_lock;
-	int consumer ____cacheline_aligned_in_smp;
+	int consumer_head ____cacheline_aligned_in_smp; /* next valid entry */
+	int consumer_tail; /* next entry to invalidate */
 	spinlock_t consumer_lock;
 	/* Shared consumer/producer data */
 	/* Read-only by both the producer and the consumer */
 	int size ____cacheline_aligned_in_smp; /* max entries in queue */
+	int batch; /* number of entries to consume in a batch */
 	void **queue;
 };
 
@@ -170,7 +172,7 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
 static inline void *__ptr_ring_peek(struct ptr_ring *r)
 {
 	if (likely(r->size))
-		return r->queue[r->consumer];
+		return r->queue[r->consumer_head];
 	return NULL;
 }
 
@@ -231,9 +233,38 @@ static inline bool ptr_ring_empty_bh(struct ptr_ring *r)
 /* Must only be called after __ptr_ring_peek returned !NULL */
 static inline void __ptr_ring_discard_one(struct ptr_ring *r)
 {
-	r->queue[r->consumer++] = NULL;
-	if (unlikely(r->consumer >= r->size))
-		r->consumer = 0;
+	/* Fundamentally, what we want to do is update consumer
+	 * index and zero out the entry so producer can reuse it.
+	 * Doing it naively at each consume would be as simple as:
+	 *       r->queue[r->consumer++] = NULL;
+	 *       if (unlikely(r->consumer >= r->size))
+	 *               r->consumer = 0;
+	 * but that is suboptimal when the ring is full as producer is writing
+	 * out new entries in the same cache line.  Defer these updates until a
+	 * batch of entries has been consumed.
+	 */
+	int head = r->consumer_head++;
+
+	/* Once we have processed enough entries invalidate them in
+	 * the ring all at once so producer can reuse their space in the ring.
+	 * We also do this when we reach end of the ring - not mandatory
+	 * but helps keep the implementation simple.
+	 */
+	if (unlikely(r->consumer_head - r->consumer_tail >= r->batch ||
+		     r->consumer_head >= r->size)) {
+		/* Zero out entries in the reverse order: this way we touch the
+		 * cache line that producer might currently be reading the last;
+		 * producer won't make progress and touch other cache lines
+		 * besides the first one until we write out all entries.
+		 */
+		while (likely(head >= r->consumer_tail))
+			r->queue[head--] = NULL;
+		r->consumer_tail = r->consumer_head;
+	}
+	if (unlikely(r->consumer_head >= r->size)) {
+		r->consumer_head = 0;
+		r->consumer_tail = 0;
+	}
 }
 
 static inline void *__ptr_ring_consume(struct ptr_ring *r)
@@ -345,14 +376,27 @@ static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp)
 	return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp);
 }
 
+static inline void __ptr_ring_set_size(struct ptr_ring *r, int size)
+{
+	r->size = size;
+	r->batch = SMP_CACHE_BYTES * 2 / sizeof(*(r->queue));
+	/* We need to set batch at least to 1 to make logic
+	 * in __ptr_ring_discard_one work correctly.
+	 * Batching too much (because ring is small) would cause a lot of
+	 * burstiness. Needs tuning, for now disable batching.
+	 */
+	if (r->batch > r->size / 2 || !r->batch)
+		r->batch = 1;
+}
+
 static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp)
 {
 	r->queue = __ptr_ring_init_queue_alloc(size, gfp);
 	if (!r->queue)
 		return -ENOMEM;
 
-	r->size = size;
-	r->producer = r->consumer = 0;
+	__ptr_ring_set_size(r, size);
+	r->producer = r->consumer_head = r->consumer_tail = 0;
 	spin_lock_init(&r->producer_lock);
 	spin_lock_init(&r->consumer_lock);
 
@@ -373,9 +417,10 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue,
 		else if (destroy)
 			destroy(ptr);
 
-	r->size = size;
+	__ptr_ring_set_size(r, size);
 	r->producer = producer;
-	r->consumer = 0;
+	r->consumer_head = 0;
+	r->consumer_tail = 0;
 	old = r->queue;
 	r->queue = queue;
 

include/linux/virtio.h

@@ -44,6 +44,12 @@ int virtqueue_add_inbuf(struct virtqueue *vq,
 			void *data,
 			gfp_t gfp);
 
+int virtqueue_add_inbuf_ctx(struct virtqueue *vq,
+			    struct scatterlist sg[], unsigned int num,
+			    void *data,
+			    void *ctx,
+			    gfp_t gfp);
+
 int virtqueue_add_sgs(struct virtqueue *vq,
 		      struct scatterlist *sgs[],
 		      unsigned int out_sgs,
@@ -59,6 +65,9 @@ bool virtqueue_notify(struct virtqueue *vq);
 
 void *virtqueue_get_buf(struct virtqueue *vq, unsigned int *len);
 
+void *virtqueue_get_buf_ctx(struct virtqueue *vq, unsigned int *len,
+			    void **ctx);
+
 void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
@@ -156,9 +165,13 @@ int virtio_device_restore(struct virtio_device *dev);
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
+ * @scan: optional function to call after successful probe; intended
+ *    for virtio-scsi to invoke a scan.
  * @remove: the function to call when a device is removed.
  * @config_changed: optional function to call when the device configuration
  *    changes; may be called in interrupt context.
+ * @freeze: optional function to call during suspend/hibernation.
+ * @restore: optional function to call on resume.
  */
 struct virtio_driver {
 	struct device_driver driver;

include/linux/virtio_config.h

@@ -72,7 +72,8 @@ struct virtio_config_ops {
 	void (*reset)(struct virtio_device *vdev);
 	int (*find_vqs)(struct virtio_device *, unsigned nvqs,
 			struct virtqueue *vqs[], vq_callback_t *callbacks[],
-			const char * const names[], struct irq_affinity *desc);
+			const char * const names[], const bool *ctx,
+			struct irq_affinity *desc);
 	void (*del_vqs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
 	int (*finalize_features)(struct virtio_device *vdev);
@@ -173,12 +174,32 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 	vq_callback_t *callbacks[] = { c };
 	const char *names[] = { n };
 	struct virtqueue *vq;
-	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL);
+	int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL,
+					 NULL);
 	if (err < 0)
 		return ERR_PTR(err);
 	return vq;
 }
 
+static inline
+int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			struct virtqueue *vqs[], vq_callback_t *callbacks[],
+			const char * const names[],
+			struct irq_affinity *desc)
+{
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc);
+}
+
+static inline
+int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs,
+			struct virtqueue *vqs[], vq_callback_t *callbacks[],
+			const char * const names[], const bool *ctx,
+			struct irq_affinity *desc)
+{
+	return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx,
+				      desc);
+}
+
 /**
  * virtio_device_ready - enable vq use in probe function
  * @vdev: the device

include/linux/virtio_ring.h

@@ -71,6 +71,7 @@ struct virtqueue *vring_create_virtqueue(unsigned int index,
 					 struct virtio_device *vdev,
 					 bool weak_barriers,
 					 bool may_reduce_num,
+					 bool ctx,
 					 bool (*notify)(struct virtqueue *vq),
 					 void (*callback)(struct virtqueue *vq),
 					 const char *name);
@@ -80,6 +81,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index,
 					struct vring vring,
 					struct virtio_device *vdev,
 					bool weak_barriers,
+					bool ctx,
 					bool (*notify)(struct virtqueue *),
 					void (*callback)(struct virtqueue *),
 					const char *name);
@@ -93,6 +95,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
+				      bool ctx,
 				      void *pages,
 				      bool (*notify)(struct virtqueue *vq),
 				      void (*callback)(struct virtqueue *vq),

net/vmw_vsock/virtio_transport.c

@@ -576,9 +576,9 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
 
 	vsock->vdev = vdev;
 
-	ret = vsock->vdev->config->find_vqs(vsock->vdev, VSOCK_VQ_MAX,
-					    vsock->vqs, callbacks, names,
-					    NULL);
+	ret = virtio_find_vqs(vsock->vdev, VSOCK_VQ_MAX,
+			      vsock->vqs, callbacks, names,
+			      NULL);
 	if (ret < 0)
 		goto out;
 

tools/virtio/linux/virtio.h

@@ -57,6 +57,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int index,
 				      unsigned int vring_align,
 				      struct virtio_device *vdev,
 				      bool weak_barriers,
+				      bool ctx,
 				      void *pages,
 				      bool (*notify)(struct virtqueue *vq),
 				      void (*callback)(struct virtqueue *vq),

tools/virtio/ringtest/main.c

@@ -20,6 +20,7 @@
 int runcycles = 10000000;
 int max_outstanding = INT_MAX;
 int batch = 1;
+int param = 0;
 
 bool do_sleep = false;
 bool do_relax = false;
@@ -86,7 +87,7 @@ void set_affinity(const char *arg)
 	cpu = strtol(arg, &endptr, 0);
 	assert(!*endptr);
 
-	assert(cpu >= 0 || cpu < CPU_SETSIZE);
+	assert(cpu >= 0 && cpu < CPU_SETSIZE);
 
 	self = pthread_self();
 	CPU_ZERO(&cpuset);
@@ -246,6 +247,11 @@ static const struct option longopts[] = {
 		.has_arg = required_argument,
 		.val = 'b',
 	},
+	{
+		.name = "param",
+		.has_arg = required_argument,
+		.val = 'p',
+	},
 	{
 		.name = "sleep",
 		.has_arg = no_argument,
@@ -274,6 +280,7 @@ static void help(void)
 		" [--run-cycles C (default: %d)]"
 		" [--batch b]"
 		" [--outstanding o]"
+		" [--param p]"
 		" [--sleep]"
 		" [--relax]"
 		" [--exit]"
@@ -328,6 +335,12 @@ int main(int argc, char **argv)
 			assert(c > 0 && c < INT_MAX);
 			max_outstanding = c;
 			break;
+		case 'p':
+			c = strtol(optarg, &endptr, 0);
+			assert(!*endptr);
+			assert(c > 0 && c < INT_MAX);
+			param = c;
+			break;
 		case 'b':
 			c = strtol(optarg, &endptr, 0);
 			assert(!*endptr);

tools/virtio/ringtest/main.h

@@ -10,6 +10,8 @@
 
 #include <stdbool.h>
 
+extern int param;
+
 extern bool do_exit;
 
 #if defined(__x86_64__) || defined(__i386__)

tools/virtio/ringtest/ptr_ring.c

@@ -97,6 +97,9 @@ void alloc_ring(void)
 {
 	int ret = ptr_ring_init(&array, ring_size, 0);
 	assert(!ret);
+	/* Hacky way to poke at ring internals. Useful for testing though. */
+	if (param)
+		array.batch = param;
 }
 
 /* guest side */

tools/virtio/virtio_test.c

@@ -100,7 +100,7 @@ static void vq_info_add(struct vdev_info *dev, int num)
 	vring_init(&info->vring, num, info->ring, 4096);
 	info->vq = vring_new_virtqueue(info->idx,
 				       info->vring.num, 4096, &dev->vdev,
-				       true, info->ring,
+				       true, false, info->ring,
 				       vq_notify, vq_callback, "test");
 	assert(info->vq);
 	info->vq->priv = info;
@@ -202,7 +202,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 	test = 0;
 	r = ioctl(dev->control, VHOST_TEST_RUN, &test);
 	assert(r >= 0);
-	fprintf(stderr, "spurious wakeus: 0x%llx\n", spurious);
+	fprintf(stderr, "spurious wakeups: 0x%llx\n", spurious);
 }
 
 const char optstring[] = "h";

tools/virtio/vringh_test.c

@@ -314,7 +314,8 @@ static int parallel_test(u64 features,
 			err(1, "Could not set affinity to cpu %u", first_cpu);
 
 		vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &gvdev.vdev, true,
-					 guest_map, fast_vringh ? no_notify_host
+					 false, guest_map,
+					 fast_vringh ? no_notify_host
 					 : parallel_notify_host,
 					 never_callback_guest, "guest vq");
 
@@ -479,7 +480,7 @@ int main(int argc, char *argv[])
 	memset(__user_addr_min, 0, vring_size(RINGSIZE, ALIGN));
 
 	/* Set up guest side. */
-	vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
+	vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true, false,
 				 __user_addr_min,
 				 never_notify_host, never_callback_guest,
 				 "guest vq");
@@ -663,7 +664,7 @@ int main(int argc, char *argv[])
 		/* Force creation of direct, which we modify. */
 		__virtio_clear_bit(&vdev, VIRTIO_RING_F_INDIRECT_DESC);
 		vq = vring_new_virtqueue(0, RINGSIZE, ALIGN, &vdev, true,
-					 __user_addr_min,
+					 false, __user_addr_min,
 					 never_notify_host,
 					 never_callback_guest,
 					 "guest vq");