diff mbox series

[net-next,v3,2/4] vsock/virtio: support to send non-linear skb

Message ID 20230720214245.457298-3-AVKrasnov@sberdevices.ru
State New
Headers
Series vsock/virtio/vhost: MSG_ZEROCOPY preparations |

Commit Message

Arseniy Krasnov July 20, 2023, 9:42 p.m. UTC 
  For non-linear skb use its pages from fragment array as buffers in
virtio tx queue. These pages are already pinned by 'get_user_pages()'
during such skb creation.

Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
---
 Changelog:
 v2 -> v3:
  * Comment about 'page_to_virt()' is updated. I don't remove R-b,
    as this change is quiet small I guess.

 net/vmw_vsock/virtio_transport.c | 41 +++++++++++++++++++++++++++-----
 1 file changed, 35 insertions(+), 6 deletions(-)

Comments

Stefano Garzarella July 25, 2023, 8:17 a.m. UTC | #1 
On Fri, Jul 21, 2023 at 12:42:43AM +0300, Arseniy Krasnov wrote:
>For non-linear skb use its pages from fragment array as buffers in
>virtio tx queue. These pages are already pinned by 'get_user_pages()'
>during such skb creation.
>
>Signed-off-by: Arseniy Krasnov <AVKrasnov@sberdevices.ru>
>Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
>---
> Changelog:
> v2 -> v3:
>  * Comment about 'page_to_virt()' is updated. I don't remove R-b,
>    as this change is quiet small I guess.

Ack!

Thanks,
Stefano

>
> net/vmw_vsock/virtio_transport.c | 41 +++++++++++++++++++++++++++-----
> 1 file changed, 35 insertions(+), 6 deletions(-)
>
>diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>index e95df847176b..7bbcc8093e51 100644
>--- a/net/vmw_vsock/virtio_transport.c
>+++ b/net/vmw_vsock/virtio_transport.c
>@@ -100,7 +100,9 @@ virtio_transport_send_pkt_work(struct work_struct *work)
> 	vq = vsock->vqs[VSOCK_VQ_TX];
>
> 	for (;;) {
>-		struct scatterlist hdr, buf, *sgs[2];
>+		/* +1 is for packet header. */
>+		struct scatterlist *sgs[MAX_SKB_FRAGS + 1];
>+		struct scatterlist bufs[MAX_SKB_FRAGS + 1];
> 		int ret, in_sg = 0, out_sg = 0;
> 		struct sk_buff *skb;
> 		bool reply;
>@@ -111,12 +113,39 @@ virtio_transport_send_pkt_work(struct work_struct *work)
>
> 		virtio_transport_deliver_tap_pkt(skb);
> 		reply = virtio_vsock_skb_reply(skb);
>+		sg_init_one(&bufs[out_sg], virtio_vsock_hdr(skb),
>+			    sizeof(*virtio_vsock_hdr(skb)));
>+		sgs[out_sg] = &bufs[out_sg];
>+		out_sg++;
>+
>+		if (!skb_is_nonlinear(skb)) {
>+			if (skb->len > 0) {
>+				sg_init_one(&bufs[out_sg], skb->data, skb->len);
>+				sgs[out_sg] = &bufs[out_sg];
>+				out_sg++;
>+			}
>+		} else {
>+			struct skb_shared_info *si;
>+			int i;
>+
>+			si = skb_shinfo(skb);
>+
>+			for (i = 0; i < si->nr_frags; i++) {
>+				skb_frag_t *skb_frag = &si->frags[i];
>+				void *va;
>
>-		sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb)));
>-		sgs[out_sg++] = &hdr;
>-		if (skb->len > 0) {
>-			sg_init_one(&buf, skb->data, skb->len);
>-			sgs[out_sg++] = &buf;
>+				/* We will use 'page_to_virt()' for the userspace page
>+				 * here, because virtio or dma-mapping layers will call
>+				 * 'virt_to_phys()' later to fill the buffer descriptor.
>+				 * We don't touch memory at "virtual" address of this page.
>+				 */
>+				va = page_to_virt(skb_frag->bv_page);
>+				sg_init_one(&bufs[out_sg],
>+					    va + skb_frag->bv_offset,
>+					    skb_frag->bv_len);
>+				sgs[out_sg] = &bufs[out_sg];
>+				out_sg++;
>+			}
> 		}
>
> 		ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL);
>-- 
>2.25.1
>
diff mbox series

Patch

diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index e95df847176b..7bbcc8093e51 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -100,7 +100,9 @@  virtio_transport_send_pkt_work(struct work_struct *work)
 	vq = vsock->vqs[VSOCK_VQ_TX];
 
 	for (;;) {
-		struct scatterlist hdr, buf, *sgs[2];
+		/* +1 is for packet header. */
+		struct scatterlist *sgs[MAX_SKB_FRAGS + 1];
+		struct scatterlist bufs[MAX_SKB_FRAGS + 1];
 		int ret, in_sg = 0, out_sg = 0;
 		struct sk_buff *skb;
 		bool reply;
@@ -111,12 +113,39 @@  virtio_transport_send_pkt_work(struct work_struct *work)
 
 		virtio_transport_deliver_tap_pkt(skb);
 		reply = virtio_vsock_skb_reply(skb);
+		sg_init_one(&bufs[out_sg], virtio_vsock_hdr(skb),
+			    sizeof(*virtio_vsock_hdr(skb)));
+		sgs[out_sg] = &bufs[out_sg];
+		out_sg++;
+
+		if (!skb_is_nonlinear(skb)) {
+			if (skb->len > 0) {
+				sg_init_one(&bufs[out_sg], skb->data, skb->len);
+				sgs[out_sg] = &bufs[out_sg];
+				out_sg++;
+			}
+		} else {
+			struct skb_shared_info *si;
+			int i;
+
+			si = skb_shinfo(skb);
+
+			for (i = 0; i < si->nr_frags; i++) {
+				skb_frag_t *skb_frag = &si->frags[i];
+				void *va;
 
-		sg_init_one(&hdr, virtio_vsock_hdr(skb), sizeof(*virtio_vsock_hdr(skb)));
-		sgs[out_sg++] = &hdr;
-		if (skb->len > 0) {
-			sg_init_one(&buf, skb->data, skb->len);
-			sgs[out_sg++] = &buf;
+				/* We will use 'page_to_virt()' for the userspace page
+				 * here, because virtio or dma-mapping layers will call
+				 * 'virt_to_phys()' later to fill the buffer descriptor.
+				 * We don't touch memory at "virtual" address of this page.
+				 */
+				va = page_to_virt(skb_frag->bv_page);
+				sg_init_one(&bufs[out_sg],
+					    va + skb_frag->bv_offset,
+					    skb_frag->bv_len);
+				sgs[out_sg] = &bufs[out_sg];
+				out_sg++;
+			}
 		}
 
 		ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, skb, GFP_KERNEL);