[PATCH bpf-next] net: veth: account total xdp_frame len running ndo_xdp_xmit

Introduce xdp_get_frame_len utility routine to get the xdp_frame full
length and account total frame size running XDP_REDIRECT of a
non-linear xdp frame into a veth device.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/veth.c |  4 ++--
 include/net/xdp.h  | 14 ++++++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 354a963075c5..22ecaf8b8f98 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c

@@ -493,7 +493,7 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
 		struct xdp_frame *frame = frames[i];
 		void *ptr = veth_xdp_to_ptr(frame);
 
-		if (unlikely(frame->len > max_len ||
+		if (unlikely(xdp_get_frame_len(frame) > max_len ||
 			     __ptr_ring_produce(&rq->xdp_ring, ptr)))
 			break;
 		nxmit++;

@@ -854,7 +854,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
 			/* ndo_xdp_xmit */
 			struct xdp_frame *frame = veth_ptr_to_xdp(ptr);
 
-			stats->xdp_bytes += frame->len;
+			stats->xdp_bytes += xdp_get_frame_len(frame);
 			frame = veth_xdp_rcv_one(rq, frame, bq, stats);
 			if (frame) {
 				/* XDP_PASS */

diff --git a/include/net/xdp.h b/include/net/xdp.h
index b7721c3e4d1f..04c852c7a77f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h

@@ -343,6 +343,20 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf)
 	__xdp_release_frame(xdpf->data, mem);
 }
 
+static __always_inline unsigned int xdp_get_frame_len(struct xdp_frame *xdpf)
+{
+	struct skb_shared_info *sinfo;
+	unsigned int len = xdpf->len;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	len += sinfo->xdp_frags_size;
+out:
+	return len;
+}
+
 int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 		       struct net_device *dev, u32 queue_index,
 		       unsigned int napi_id, u32 frag_size);

-- 
2.34.1

On Tue, Feb 1, 2022 at 2:46 AM Lorenzo Bianconi [off-list ref] wrote:

Looks correct, but could you explain what happens without this fix?

Any other drivers might have the same issue?

On Tue, Feb 1, 2022 at 2:46 AM Lorenzo Bianconi [off-list ref] wrote:

quoted

Introduce xdp_get_frame_len utility routine to get the xdp_frame full
length and account total frame size running XDP_REDIRECT of a
non-linear xdp frame into a veth device.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 drivers/net/veth.c |  4 ++--
 include/net/xdp.h  | 14 ++++++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 354a963075c5..22ecaf8b8f98 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c

@@ -493,7 +493,7 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
                struct xdp_frame *frame = frames[i];
                void *ptr = veth_xdp_to_ptr(frame);

-               if (unlikely(frame->len > max_len ||
+               if (unlikely(xdp_get_frame_len(frame) > max_len ||
                             __ptr_ring_produce(&rq->xdp_ring, ptr)))
                        break;

Looks correct, but could you explain what happens without this fix?

I guess this is just a theoretical issue, since at the moment we can't perform
a XDP_REDIRECT with a non-linear xdp buffer, but without this patch we will fail
to account peer max packet size since we take care of just the linear part of
the xdp_buff.
I am working on adding xdp multi-buff support to veth driver so I will repost this
patch into the series.

Any other drivers might have the same issue?

I do not think so since other drivers are not able to map multi-frags yet (veth
already support it since we run __xdp_build_skb_from_frame()).

Regards,
Lorenzo