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

Pull virtio updates from Michael Tsirkin:
 "A small pull request this time around, mostly because the vduse
  network got postponed to next relase so we can be sure we got the
  security store right"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_ring: fix avail_wrap_counter in virtqueue_add_packed
  virtio_vdpa: build affinity masks conditionally
  virtio_net: merge dma operations when filling mergeable buffers
  virtio_ring: introduce dma sync api for virtqueue
  virtio_ring: introduce dma map api for virtqueue
  virtio_ring: introduce virtqueue_reset()
  virtio_ring: separate the logic of reset/enable from virtqueue_resize
  virtio_ring: correct the expression of the description of virtqueue_resize()
  virtio_ring: skip unmap for premapped
  virtio_ring: introduce virtqueue_dma_dev()
  virtio_ring: support add premapped buf
  virtio_ring: introduce virtqueue_set_dma_premapped()
  virtio_ring: put mapping error check in vring_map_one_sg
  virtio_ring: check use_dma_api before unmap desc for indirect
  vdpa_sim: offer VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK
  vdpa: add get_backend_features vdpa operation
  vdpa: accept VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK backend feature
  vdpa: add VHOST_BACKEND_F_ENABLE_AFTER_DRIVER_OK flag
  vdpa/mlx5: Remove unused function declarations

1 files changed, 202 insertions, 26 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 231ad91a919d..fe7f314d65c9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -132,6 +132,14 @@ struct virtnet_interrupt_coalesce {
 	u32 max_usecs;
 };
 
+/* The dma information of pages allocated at a time. */
+struct virtnet_rq_dma {
+	dma_addr_t addr;
+	u32 ref;
+	u16 len;
+	u16 need_sync;
+};
+
 /* Internal representation of a send virtqueue */
 struct send_queue {
 	/* Virtqueue associated with this send _queue */
@@ -185,6 +193,12 @@ struct receive_queue {
 	char name[16];
 
 	struct xdp_rxq_info xdp_rxq;
+
+	/* Record the last dma info to free after new pages is allocated. */
+	struct virtnet_rq_dma *last_dma;
+
+	/* Do dma by self */
+	bool do_dma;
 };
 
 /* This structure can contain rss message with maximum settings for indirection table and keysize
@@ -580,6 +594,156 @@ ok:
 	return skb;
 }
 
+static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len)
+{
+	struct page *page = virt_to_head_page(buf);
+	struct virtnet_rq_dma *dma;
+	void *head;
+	int offset;
+
+	head = page_address(page);
+
+	dma = head;
+
+	--dma->ref;
+
+	if (dma->ref) {
+		if (dma->need_sync && len) {
+			offset = buf - (head + sizeof(*dma));
+
+			virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset,
+								len, DMA_FROM_DEVICE);
+		}
+
+		return;
+	}
+
+	virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len,
+					 DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+	put_page(page);
+}
+
+static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, void **ctx)
+{
+	void *buf;
+
+	buf = virtqueue_get_buf_ctx(rq->vq, len, ctx);
+	if (buf && rq->do_dma)
+		virtnet_rq_unmap(rq, buf, *len);
+
+	return buf;
+}
+
+static void *virtnet_rq_detach_unused_buf(struct receive_queue *rq)
+{
+	void *buf;
+
+	buf = virtqueue_detach_unused_buf(rq->vq);
+	if (buf && rq->do_dma)
+		virtnet_rq_unmap(rq, buf, 0);
+
+	return buf;
+}
+
+static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
+{
+	struct virtnet_rq_dma *dma;
+	dma_addr_t addr;
+	u32 offset;
+	void *head;
+
+	if (!rq->do_dma) {
+		sg_init_one(rq->sg, buf, len);
+		return;
+	}
+
+	head = page_address(rq->alloc_frag.page);
+
+	offset = buf - head;
+
+	dma = head;
+
+	addr = dma->addr - sizeof(*dma) + offset;
+
+	sg_init_table(rq->sg, 1);
+	rq->sg[0].dma_address = addr;
+	rq->sg[0].length = len;
+}
+
+static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
+{
+	struct page_frag *alloc_frag = &rq->alloc_frag;
+	struct virtnet_rq_dma *dma;
+	void *buf, *head;
+	dma_addr_t addr;
+
+	if (unlikely(!skb_page_frag_refill(size, alloc_frag, gfp)))
+		return NULL;
+
+	head = page_address(alloc_frag->page);
+
+	if (rq->do_dma) {
+		dma = head;
+
+		/* new pages */
+		if (!alloc_frag->offset) {
+			if (rq->last_dma) {
+				/* Now, the new page is allocated, the last dma
+				 * will not be used. So the dma can be unmapped
+				 * if the ref is 0.
+				 */
+				virtnet_rq_unmap(rq, rq->last_dma, 0);
+				rq->last_dma = NULL;
+			}
+
+			dma->len = alloc_frag->size - sizeof(*dma);
+
+			addr = virtqueue_dma_map_single_attrs(rq->vq, dma + 1,
+							      dma->len, DMA_FROM_DEVICE, 0);
+			if (virtqueue_dma_mapping_error(rq->vq, addr))
+				return NULL;
+
+			dma->addr = addr;
+			dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
+
+			/* Add a reference to dma to prevent the entire dma from
+			 * being released during error handling. This reference
+			 * will be freed after the pages are no longer used.
+			 */
+			get_page(alloc_frag->page);
+			dma->ref = 1;
+			alloc_frag->offset = sizeof(*dma);
+
+			rq->last_dma = dma;
+		}
+
+		++dma->ref;
+	}
+
+	buf = head + alloc_frag->offset;
+
+	get_page(alloc_frag->page);
+	alloc_frag->offset += size;
+
+	return buf;
+}
+
+static void virtnet_rq_set_premapped(struct virtnet_info *vi)
+{
+	int i;
+
+	/* disable for big mode */
+	if (!vi->mergeable_rx_bufs && vi->big_packets)
+		return;
+
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (virtqueue_set_dma_premapped(vi->rq[i].vq))
+			continue;
+
+		vi->rq[i].do_dma = true;
+	}
+}
+
 static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi)
 {
 	unsigned int len;
@@ -935,7 +1099,7 @@ static struct page *xdp_linearize_page(struct receive_queue *rq,
 		void *buf;
 		int off;
 
-		buf = virtqueue_get_buf(rq->vq, &buflen);
+		buf = virtnet_rq_get_buf(rq, &buflen, NULL);
 		if (unlikely(!buf))
 			goto err_buf;
 
@@ -1155,7 +1319,7 @@ static void mergeable_buf_free(struct receive_queue *rq, int num_buf,
 	int len;
 
 	while (num_buf-- > 1) {
-		buf = virtqueue_get_buf(rq->vq, &len);
+		buf = virtnet_rq_get_buf(rq, &len, NULL);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers missing\n",
 				 dev->name, num_buf);
@@ -1263,7 +1427,7 @@ static int virtnet_build_xdp_buff_mrg(struct net_device *dev,
 		return -EINVAL;
 
 	while (--*num_buf > 0) {
-		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+		buf = virtnet_rq_get_buf(rq, &len, &ctx);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, *num_buf,
@@ -1492,7 +1656,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	while (--num_buf) {
 		int num_skb_frags;
 
-		buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx);
+		buf = virtnet_rq_get_buf(rq, &len, &ctx);
 		if (unlikely(!buf)) {
 			pr_debug("%s: rx error: %d buffers out of %d missing\n",
 				 dev->name, num_buf,
@@ -1651,7 +1815,6 @@ frame_err:
 static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 			     gfp_t gfp)
 {
-	struct page_frag *alloc_frag = &rq->alloc_frag;
 	char *buf;
 	unsigned int xdp_headroom = virtnet_get_headroom(vi);
 	void *ctx = (void *)(unsigned long)xdp_headroom;
@@ -1660,17 +1823,21 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 
 	len = SKB_DATA_ALIGN(len) +
 	      SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	if (unlikely(!skb_page_frag_refill(len, alloc_frag, gfp)))
+
+	buf = virtnet_rq_alloc(rq, len, gfp);
+	if (unlikely(!buf))
 		return -ENOMEM;
 
-	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
-	get_page(alloc_frag->page);
-	alloc_frag->offset += len;
-	sg_init_one(rq->sg, buf + VIRTNET_RX_PAD + xdp_headroom,
-		    vi->hdr_len + GOOD_PACKET_LEN);
+	virtnet_rq_init_one_sg(rq, buf + VIRTNET_RX_PAD + xdp_headroom,
+			       vi->hdr_len + GOOD_PACKET_LEN);
+
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
-	if (err < 0)
+	if (err < 0) {
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
+	}
+
 	return err;
 }
 
@@ -1747,23 +1914,22 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	unsigned int headroom = virtnet_get_headroom(vi);
 	unsigned int tailroom = headroom ? sizeof(struct skb_shared_info) : 0;
 	unsigned int room = SKB_DATA_ALIGN(headroom + tailroom);
-	char *buf;
+	unsigned int len, hole;
 	void *ctx;
+	char *buf;
 	int err;
-	unsigned int len, hole;
 
 	/* Extra tailroom is needed to satisfy XDP's assumption. This
 	 * means rx frags coalescing won't work, but consider we've
 	 * disabled GSO for XDP, it won't be a big issue.
 	 */
 	len = get_mergeable_buf_len(rq, &rq->mrg_avg_pkt_len, room);
-	if (unlikely(!skb_page_frag_refill(len + room, alloc_frag, gfp)))
+
+	buf = virtnet_rq_alloc(rq, len + room, gfp);
+	if (unlikely(!buf))
 		return -ENOMEM;
 
-	buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
 	buf += headroom; /* advance address leaving hole at front of pkt */
-	get_page(alloc_frag->page);
-	alloc_frag->offset += len + room;
 	hole = alloc_frag->size - alloc_frag->offset;
 	if (hole < len + room) {
 		/* To avoid internal fragmentation, if there is very likely not
@@ -1777,11 +1943,15 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 		alloc_frag->offset += hole;
 	}
 
-	sg_init_one(rq->sg, buf, len);
+	virtnet_rq_init_one_sg(rq, buf, len);
+
 	ctx = mergeable_len_to_ctx(len + room, headroom);
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
-	if (err < 0)
+	if (err < 0) {
+		if (rq->do_dma)
+			virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
+	}
 
 	return err;
 }
@@ -1902,13 +2072,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 		void *ctx;
 
 		while (stats.packets < budget &&
-		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
+		       (buf = virtnet_rq_get_buf(rq, &len, &ctx))) {
 			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
 			stats.packets++;
 		}
 	} else {
 		while (stats.packets < budget &&
-		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
+		       (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) {
 			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
 			stats.packets++;
 		}
@@ -3808,8 +3978,11 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 {
 	int i;
 	for (i = 0; i < vi->max_queue_pairs; i++)
-		if (vi->rq[i].alloc_frag.page)
+		if (vi->rq[i].alloc_frag.page) {
+			if (vi->rq[i].do_dma && vi->rq[i].last_dma)
+				virtnet_rq_unmap(&vi->rq[i], vi->rq[i].last_dma, 0);
 			put_page(vi->rq[i].alloc_frag.page);
+		}
 }
 
 static void virtnet_sq_free_unused_buf(struct virtqueue *vq, void *buf)
@@ -3846,9 +4019,10 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	}
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		struct virtqueue *vq = vi->rq[i].vq;
-		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL)
-			virtnet_rq_free_unused_buf(vq, buf);
+		struct receive_queue *rq = &vi->rq[i];
+
+		while ((buf = virtnet_rq_detach_unused_buf(rq)) != NULL)
+			virtnet_rq_free_unused_buf(rq->vq, buf);
 		cond_resched();
 	}
 }
@@ -4022,6 +4196,8 @@ static int init_vqs(struct virtnet_info *vi)
 	if (ret)
 		goto err_free;
 
+	virtnet_rq_set_premapped(vi);
+
 	cpus_read_lock();
 	virtnet_set_affinity(vi);
 	cpus_read_unlock();