gro: __napi_gro_receive() optimizations
compare_ether_header() can have a special implementation on 64 bit
arches if CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is defined.
__napi_gro_receive() and vlan_gro_common() can avoid a conditional
branch to perform device match.
On x86_64, __napi_gro_receive() has now 38 instructions instead of 53
As gcc-4.4.3 still choose to not inline it, add inline keyword to this
performance critical function.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/dev.c b/net/core/dev.c
index 859e30f..63bd20a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3169,16 +3169,18 @@
}
EXPORT_SYMBOL(dev_gro_receive);
-static gro_result_t
+static inline gro_result_t
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
for (p = napi->gro_list; p; p = p->next) {
- NAPI_GRO_CB(p)->same_flow =
- (p->dev == skb->dev) &&
- !compare_ether_header(skb_mac_header(p),
+ unsigned long diffs;
+
+ diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
+ diffs |= compare_ether_header(skb_mac_header(p),
skb_gro_mac_header(skb));
+ NAPI_GRO_CB(p)->same_flow = !diffs;
NAPI_GRO_CB(p)->flush = 0;
}
