Hello.
On 02/28/2015 10:58 PM, Shrikrishna Khare wrote:
Allows for packet parsing to be done by the fast path. This performance
optimization already exists for IPv4. Add similar logic for IPv6.
Signed-off-by: Amitabha Banerjee <banerj...@vmware.com>
Signed-off-by: Shrikrishna Khare <skh...@vmware.com>
---
drivers/net/vmxnet3/vmxnet3_drv.c | 26 ++++++++++++++++----------
drivers/net/vmxnet3/vmxnet3_int.h | 5 +++--
2 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c
b/drivers/net/vmxnet3/vmxnet3_drv.c
index 294214c..9216e6a 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
[...]
@@ -831,16 +832,20 @@ vmxnet3_parse_and_copy_hdr(struct sk_buff *skb, struct
vmxnet3_tx_queue *tq,
if (ctx->ipv4) {
const struct iphdr *iph = ip_hdr(skb);
- if (iph->protocol == IPPROTO_TCP)
- ctx->l4_hdr_size = tcp_hdrlen(skb);
- else if (iph->protocol == IPPROTO_UDP)
- ctx->l4_hdr_size = sizeof(struct
udphdr);
- else
- ctx->l4_hdr_size = 0;
- } else {
- /* for simplicity, don't copy L4 headers */
- ctx->l4_hdr_size = 0;
+ protocol = iph->protocol;
+ } else if (ctx->ipv6) {
+ const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
+ protocol = ipv6h->nexthdr;
}
+
+ if (protocol == IPPROTO_TCP)
+ ctx->l4_hdr_size = tcp_hdrlen(skb);
+ else if (protocol == IPPROTO_UDP)
+ ctx->l4_hdr_size = sizeof(struct udphdr);
+ else
+ ctx->l4_hdr_size = 0;
+
I think the above is asking to be a 'switch (protocol)' instead.
WBR, Sergei
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
