[PATCH v4 bpf-next 3/3] veth: allow jumbo frames in xdp mode

[Lorenzo Bianconi <lorenzo@xxxxxxxxxx>]

Allow increasing the MTU over page boundaries on veth devices
if the attached xdp program declares to support xdp fragments.
Enable NETIF_F_ALL_TSO when the device is running in xdp mode.

Signed-off-by: Lorenzo Bianconi <lorenzo@xxxxxxxxxx>
---
 drivers/net/veth.c | 28 +++++++++++++++++-----------
 1 file changed, 17 insertions(+), 11 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 47b21b1d2fd9..c5a2dc2b2e4b 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -293,8 +293,7 @@ static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
 /* return true if the specified skb has chances of GRO aggregation
  * Don't strive for accuracy, but try to avoid GRO overhead in the most
  * common scenarios.
- * When XDP is enabled, all traffic is considered eligible, as the xmit
- * device has TSO off.
+ * When XDP is enabled, all traffic is considered eligible.
  * When TSO is enabled on the xmit device, we are likely interested only
  * in UDP aggregation, explicitly check for that if the skb is suspected
  * - the sock_wfree destructor is used by UDP, ICMP and XDP sockets -
@@ -302,11 +301,13 @@ static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
  */
 static bool veth_skb_is_eligible_for_gro(const struct net_device *dev,
 					 const struct net_device *rcv,
+					 const struct veth_rq *rq,
 					 const struct sk_buff *skb)
 {
-	return !(dev->features & NETIF_F_ALL_TSO) ||
-		(skb->destructor == sock_wfree &&
-		 rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD));
+	return rcu_access_pointer(rq->xdp_prog) ||
+	       !(dev->features & NETIF_F_ALL_TSO) ||
+	       (skb->destructor == sock_wfree &&
+		rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD));
 }
 
 static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -335,7 +336,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		 * Don't bother with napi/GRO if the skb can't be aggregated
 		 */
 		use_napi = rcu_access_pointer(rq->napi) &&
-			   veth_skb_is_eligible_for_gro(dev, rcv, skb);
+			   veth_skb_is_eligible_for_gro(dev, rcv, rq, skb);
 	}
 
 	skb_tx_timestamp(skb);
@@ -1525,9 +1526,14 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			goto err;
 		}
 
-		max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM -
-			  peer->hard_header_len -
-			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		max_mtu = SKB_WITH_OVERHEAD(PAGE_SIZE - VETH_XDP_HEADROOM) -
+			  peer->hard_header_len;
+		/* Allow increasing the max_mtu if the program supports
+		 * XDP fragments.
+		 */
+		if (prog->aux->xdp_has_frags)
+			max_mtu += PAGE_SIZE * MAX_SKB_FRAGS;
+
 		if (peer->mtu > max_mtu) {
 			NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
 			err = -ERANGE;
@@ -1549,7 +1555,7 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		}
 
 		if (!old_prog) {
-			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+			peer->hw_features &= ~NETIF_F_GSO_FRAGLIST;
 			peer->max_mtu = max_mtu;
 		}
 	}
@@ -1560,7 +1566,7 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 				veth_disable_xdp(dev);
 
 			if (peer) {
-				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
+				peer->hw_features |= NETIF_F_GSO_FRAGLIST;
 				peer->max_mtu = ETH_MAX_MTU;
 			}
 		}
-- 
2.35.1