Skip to contentSkip to conversation

myri10ge: Add vlan rx for better GRO perf.

PATCH RESEND Superseded Andrew Gallatin 3 participants 5 messages Nov 28, 2012 – Nov 29, 2012

Subsystems (3)

v1 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH RESEND 2/3 myri10ge: Add vlan rx for better GRO perf.

Unlike LRO, GRO requires that vlan tags be removed before aggregation can occur. Since the myri10ge NIC does not support hardware vlan tag offload, we must remove the tag in the driver to achieve performance comparable to LRO for vlan tagged frames.

Thanks to Eric Duzamet for his help simplifying the original patch.

---
 drivers/net/ethernet/myricom/myri10ge/myri10ge.c |   40 
++++++++++++++++++++++
 1 file changed, 40 insertions(+)
drivers/net/ethernet/myricom/myri10ge/myri10ge.c +40 -0
index a5ab2f2..93ed089 100644
@@ -1264,6 +1264,41 @@ myri10ge_unmap_rx_page(struct pci_dev *pdev,
 	}
 }
 
+/*
+ * GRO does not support acceleration of tagged vlan frames, and
+ * this NIC does not support vlan tag offload, so we must pop
+ * the tag ourselves to be able to achieve GRO performance that
+ * is comparable to LRO.
+ */
+
+static inline void
+myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb)
+{
+	u8 *va;
+	struct vlan_ethhdr *veh;
+	struct skb_frag_struct *frag;
+
+	va = addr;
+	va += MXGEFW_PAD;
+	veh = (struct vlan_ethhdr *) va;
+	if ((dev->features & (NETIF_F_HW_VLAN_RX)) == NETIF_F_HW_VLAN_RX &&
+	    (veh->h_vlan_proto == ntohs(ETH_P_8021Q))) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_sub(skb->csum,
+					     csum_partial(va + ETH_HLEN,
+							  VLAN_HLEN, 0));
+		/* pop tag */
+		__vlan_hwaccel_put_tag(skb, ntohs(veh->h_vlan_TCI));
+		memmove(va + VLAN_HLEN, va, 2 * ETH_ALEN);
+		skb->len -= VLAN_HLEN;
+		skb->data_len -= VLAN_HLEN;
+		frag = skb_shinfo(skb)->frags;
+		frag->page_offset += VLAN_HLEN;
+		skb_frag_size_set(frag, skb_frag_size(frag) - VLAN_HLEN);
+	}
+}
+
 static inline int
 myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum)
 {
@@ -1329,6 +1364,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum)
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = csum;
 	}
+	myri10ge_vlan_rx(mgp->dev, va, skb);
 	skb_record_rx_queue(skb, ss - &mgp->ss[0]);
 
 	napi_gro_frags(&ss->napi);
@@ -3854,6 +3890,10 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	netdev->netdev_ops = &myri10ge_netdev_ops;
 	netdev->mtu = myri10ge_initial_mtu;
 	netdev->hw_features = mgp->features | NETIF_F_RXCSUM;
+
+	/* fake NETIF_F_HW_VLAN_RX for good GRO performance */
+	netdev->hw_features |= NETIF_F_HW_VLAN_RX;
+
 	netdev->features = netdev->hw_features;
 
 	if (dac_enabled)
Signature · 1 line
1.7.9.5
maintainer
#1 lore raw

From: Andrew Gallatin <[email protected]>
Date: Wed, 28 Nov 2012 16:20:56 -0500

drivers/net/ethernet/myricom/myri10ge/myri10ge.c myri10ge_unmap_rx_page(struct pci_dev *pdev, · line 1290

Quoted 7 lines

+ if ((dev->features & (NETIF_F_HW_VLAN_RX)) == NETIF_F_HW_VLAN_RX &&

drivers/net/ethernet/myricom/myri10ge/myri10ge.c +6 -0
+	    (veh->h_vlan_proto == ntohs(ETH_P_8021Q))) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_sub(skb->csum,
+ csum_partial(va + ETH_HLEN,
+ VLAN_HLEN, 0));

This indentation looks like spaghetti, verify that this kind of error doesn't exist in the rest of your patches, and resend the series.

#2 lore raw
Quoted 14 lines · David Miller

From: Andrew Gallatin <[email protected]>
Date: Wed, 28 Nov 2012 16:20:56 -0500

drivers/net/ethernet/myricom/myri10ge/myri10ge.c myri10ge_unmap_rx_page(struct pci_dev *pdev, · line 1290

Quoted 7 lines

+ if ((dev->features & (NETIF_F_HW_VLAN_RX)) == NETIF_F_HW_VLAN_RX &&

drivers/net/ethernet/myricom/myri10ge/myri10ge.c +6 -0
+	    (veh->h_vlan_proto == ntohs(ETH_P_8021Q))) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_sub(skb->csum,
+ csum_partial(va + ETH_HLEN,
+ VLAN_HLEN, 0));

This indentation looks like spaghetti, verify that this kind of error doesn't exist in the rest of your patches, and resend the series.

Sorry. Emacs victim... I'll clean it up & re-submit. I'd stupidly assumed that checkpatch would verify indentation. :(

Drew

#3 lore raw
Quoted 16 lines · Andrew Gallatin
Quoted 14 lines · David Miller

From: Andrew Gallatin <[email protected]>
Date: Wed, 28 Nov 2012 16:20:56 -0500

drivers/net/ethernet/myricom/myri10ge/myri10ge.c myri10ge_unmap_rx_page(struct pci_dev *pdev, · line 1290

Quoted 7 lines

+ if ((dev->features & (NETIF_F_HW_VLAN_RX)) == NETIF_F_HW_VLAN_RX &&

drivers/net/ethernet/myricom/myri10ge/myri10ge.c +6 -0
+	    (veh->h_vlan_proto == ntohs(ETH_P_8021Q))) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_sub(skb->csum,
+ csum_partial(va + ETH_HLEN,
+ VLAN_HLEN, 0));

This indentation looks like spaghetti, verify that this kind of error doesn't exist in the rest of your patches, and resend the series.

Quoted 2 lines

Sorry. Emacs victim... I'll clean it up & re-submit. I'd stupidly assumed that checkpatch would verify indentation. :(

checkpatch --strict

#4 lore raw
Quoted 17 lines · Joe Perches
Quoted 16 lines · Andrew Gallatin
Quoted 14 lines · David Miller

From: Andrew Gallatin <[email protected]>
Date: Wed, 28 Nov 2012 16:20:56 -0500

drivers/net/ethernet/myricom/myri10ge/myri10ge.c myri10ge_unmap_rx_page(struct pci_dev *pdev, · line 1290

Quoted 7 lines

+ if ((dev->features & (NETIF_F_HW_VLAN_RX)) == NETIF_F_HW_VLAN_RX &&

drivers/net/ethernet/myricom/myri10ge/myri10ge.c +6 -0
+	    (veh->h_vlan_proto == ntohs(ETH_P_8021Q))) {
+		/* fixup csum if needed */
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_sub(skb->csum,
+ csum_partial(va + ETH_HLEN,
+ VLAN_HLEN, 0));

This indentation looks like spaghetti, verify that this kind of error doesn't exist in the rest of your patches, and resend the series.

Quoted 5 lines
Quoted 2 lines

Sorry. Emacs victim... I'll clean it up & re-submit. I'd stupidly assumed that checkpatch would verify indentation. :(

checkpatch --strict

That catches one formatting error in the patch, but does not complain about the indentation issues.

Drew