| commit | 0b215b9798640a542c526e3ae69dee83861a4aee | [log] [tgz] |
|---|---|---|
| author | Eric Dumazet <edumazet@google.com> | Tue Nov 06 14:25:52 2018 -0800 |
| committer | David S. Miller <davem@davemloft.net> | Tue Nov 06 14:59:27 2018 -0800 |
| tree | 8fd33e25e96051f31213de5f5f02ec2f03417a93 | |
| parent | 5e1abdc3fe56939d9ac34209706b1a527b77b61b [diff] |
ipv6: gro: do not use slow memcmp() in ipv6_gro_receive() ipv6_gro_receive() compares 34 bytes using slow memcmp(), while handcoding with a couple of ipv6_addr_equal() is much faster. Before this patch, "perf top -e cycles:pp -C <cpu>" would see memcmp() using ~10% of cpu cycles on a 40Gbit NIC receiving IPv6 TCP traffic. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>