diff options
| author | Eric Dumazet <edumazet@google.com> | 2015-05-26 08:55:28 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-05-26 23:21:29 -0400 |
| commit | d6a4e26afb80c049e7f94e1b7b506dcda61eee88 (patch) | |
| tree | 809c23a70ad711aa0f1456068cb73f9c1ac11da9 /net/core | |
| parent | 095dc8e0c3686d586a01a50abc3e1bb9ac633054 (diff) | |
| download | op-kernel-dev-d6a4e26afb80c049e7f94e1b7b506dcda61eee88.zip op-kernel-dev-d6a4e26afb80c049e7f94e1b7b506dcda61eee88.tar.gz | |
tcp: tcp_tso_autosize() minimum is one packet
By making sure sk->sk_gso_max_segs minimal value is one,
and sysctl_tcp_min_tso_segs minimal value is one as well,
tcp_tso_autosize() will return a non zero value.
We can then revert 843925f33fcc293d80acf2c5c8a78adf3344d49b
("tcp: Do not apply TSO segment limit to non-TSO packets")
and save few cpu cycles in fast path.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/sock.c | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/net/core/sock.c b/net/core/sock.c index 29124fc..e72633c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1581,6 +1581,8 @@ EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { + u32 max_segs = 1; + __sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) @@ -1592,9 +1594,10 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; sk->sk_gso_max_size = dst->dev->gso_max_size; - sk->sk_gso_max_segs = dst->dev->gso_max_segs; + max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } + sk->sk_gso_max_segs = max_segs; } EXPORT_SYMBOL_GPL(sk_setup_caps); |
