Merge branch 'virtio_net-rx-enable-premapped-mode-by-default'

Xuan Zhuo says:

====================
virtio_net: rx enable premapped mode by default

Actually, for the virtio drivers, we can enable premapped mode whatever
the value of use_dma_api. Because we provide the virtio dma apis.
So the driver can enable premapped mode unconditionally.

This patch set makes the big mode of virtio-net to support premapped mode.
And enable premapped mode for rx by default.

Based on the following points, we do not use page pool to manage these
    pages:

    1. virtio-net uses the DMA APIs wrapped by virtio core. Therefore,
       we can only prevent the page pool from performing DMA operations, and
       let the driver perform DMA operations on the allocated pages.
    2. But when the page pool releases the page, we have no chance to
       execute dma unmap.
    3. A solution to #2 is to execute dma unmap every time before putting
       the page back to the page pool. (This is actually a waste, we don't
       execute unmap so frequently.)
    4. But there is another problem, we still need to use page.dma_addr to
       save the dma address. Using page.dma_addr while using page pool is
       unsafe behavior.
    5. And we need space the chain the pages submitted once to virtio core.

    More:
        https://lore.kernel.org/all/CACGkMEu=Aok9z2imB_c5qVuujSh=vjj1kx12fy9N7hqyi+M5Ow@mail.gmail.com/

Why we do not use the page space to store the dma?

    http://lore.kernel.org/all/CACGkMEuyeJ9mMgYnnB42=hw6umNuo=agn7VBqBqYPd7GN=+39Q@mail.gmail.com
====================

Link: https://lore.kernel.org/r/20240511031404.30903-1-xuanzhuo@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 38 insertions, 59 deletions

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 42da535913ed3b..19a9b50646c75d 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -348,9 +348,6 @@ struct receive_queue {
 
 	/* 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
@@ -746,7 +743,6 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
 
 	shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	/* copy small packet so we can reuse these pages */
 	if (!NET_IP_ALIGN && len > GOOD_COPY_LEN && tailroom >= shinfo_size) {
 		skb = virtnet_build_skb(buf, truesize, p - buf, len);
 		if (unlikely(!skb))
@@ -850,7 +846,7 @@ 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)
+	if (buf)
 		virtnet_rq_unmap(rq, buf, *len);
 
 	return buf;
@@ -863,11 +859,6 @@ static void virtnet_rq_init_one_sg(struct receive_queue *rq, void *buf, u32 len)
 	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;
@@ -893,44 +884,42 @@ static void *virtnet_rq_alloc(struct receive_queue *rq, u32 size, gfp_t gfp)
 
 	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 = head;
 
-			dma->len = alloc_frag->size - sizeof(*dma);
+	/* 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;
+		}
 
-			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->len = alloc_frag->size - sizeof(*dma);
 
-			dma->addr = addr;
-			dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
+		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;
 
-			/* 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);
+		dma->addr = addr;
+		dma->need_sync = virtqueue_dma_need_sync(rq->vq, addr);
 
-			rq->last_dma = dma;
-		}
+		/* 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);
 
-		++dma->ref;
+		rq->last_dma = dma;
 	}
 
+	++dma->ref;
+
 	buf = head + alloc_frag->offset;
 
 	get_page(alloc_frag->page);
@@ -947,12 +936,9 @@ static void virtnet_rq_set_premapped(struct virtnet_info *vi)
 	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;
-	}
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		/* error should never happen */
+		BUG_ON(virtqueue_set_dma_premapped(vi->rq[i].vq));
 }
 
 static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
@@ -963,7 +949,7 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
 
 	rq = &vi->rq[i];
 
-	if (rq->do_dma)
+	if (!vi->big_packets || vi->mergeable_rx_bufs)
 		virtnet_rq_unmap(rq, buf, 0);
 
 	virtnet_rq_free_buf(vi, rq, buf);
@@ -2030,8 +2016,7 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
 
 	err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
 	if (err < 0) {
-		if (rq->do_dma)
-			virtnet_rq_unmap(rq, buf, 0);
+		virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
 	}
 
@@ -2145,8 +2130,7 @@ static int add_recvbuf_mergeable(struct virtnet_info *vi,
 	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 (rq->do_dma)
-			virtnet_rq_unmap(rq, buf, 0);
+		virtnet_rq_unmap(rq, buf, 0);
 		put_page(virt_to_head_page(buf));
 	}
 
@@ -2277,7 +2261,7 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 		}
 	} else {
 		while (packets < budget &&
-		       (buf = virtnet_rq_get_buf(rq, &len, NULL)) != NULL) {
+		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
 			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
 			packets++;
 		}
@@ -5229,7 +5213,7 @@ 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].do_dma && vi->rq[i].last_dma)
+			if (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);
 		}
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 6f7e5010a6735d..2a972752ff1bc4 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -2782,7 +2782,7 @@ EXPORT_SYMBOL_GPL(virtqueue_resize);
  *
  * Returns zero or a negative error.
  * 0: success.
- * -EINVAL: vring does not use the dma api, so we can not enable premapped mode.
+ * -EINVAL: too late to enable premapped mode, the vq already contains buffers.
  */
 int virtqueue_set_dma_premapped(struct virtqueue *_vq)
 {
@@ -2798,11 +2798,6 @@ int virtqueue_set_dma_premapped(struct virtqueue *_vq)
 		return -EINVAL;
 	}
 
-	if (!vq->use_dma_api) {
-		END_USE(vq);
-		return -EINVAL;
-	}
-
 	vq->premapped = true;
 	vq->do_unmap = false;