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>

1 files changed, 4 insertions, 1 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 29124fcdc42a..e72633c346b1 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);