aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/tcp.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp.c')
-rw-r--r--net/ipv4/tcp.c49
1 files changed, 33 insertions, 16 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ab450c099aa..1a2e249cef4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,6 +282,8 @@
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -786,14 +788,24 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
xmit_size_goal = mss_now;
if (large_allowed && sk_can_gso(sk)) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
+ u32 gso_size, hlen;
+
+ /* Maybe we should/could use sk->sk_prot->max_header here ? */
+ hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+ inet_csk(sk)->icsk_ext_hdr_len +
+ tp->tcp_header_len;
+
+ /* Goal is to send at least one packet per ms,
+ * not one big TSO packet every 100 ms.
+ * This preserves ACK clocking and is consistent
+ * with tcp_tso_should_defer() heuristic.
+ */
+ gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+ gso_size = max_t(u32, gso_size,
+ sysctl_tcp_min_tso_segs * mss_now);
- /* TSQ : try to have two TSO segments in flight */
- xmit_size_goal = min_t(u32, xmit_size_goal,
- sysctl_tcp_limit_output_bytes >> 1);
+ xmit_size_goal = min_t(u32, gso_size,
+ sk->sk_gso_max_size - 1 - hlen);
xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
@@ -1118,6 +1130,13 @@ new_segment:
goto wait_for_memory;
/*
+ * All packets are restored as if they have
+ * already been sent.
+ */
+ if (tp->repair)
+ TCP_SKB_CB(skb)->when = tcp_time_stamp;
+
+ /*
* Check whether we can use HW checksum.
*/
if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
@@ -2440,10 +2459,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_THIN_DUPACK:
if (val < 0 || val > 1)
err = -EINVAL;
- else
+ else {
tp->thin_dupack = val;
if (tp->thin_dupack)
tcp_disable_early_retrans(tp);
+ }
break;
case TCP_REPAIR:
@@ -2879,6 +2899,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
netdev_features_t features)
{
struct sk_buff *segs = ERR_PTR(-EINVAL);
+ unsigned int sum_truesize = 0;
struct tcphdr *th;
unsigned int thlen;
unsigned int seq;
@@ -2962,13 +2983,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
skb->destructor = gso_skb->destructor;
skb->sk = gso_skb->sk;
- /* {tcp|sock}_wfree() use exact truesize accounting :
- * sum(skb->truesize) MUST be exactly be gso_skb->truesize
- * So we account mss bytes of 'true size' for each segment.
- * The last segment will contain the remaining.
- */
- skb->truesize = mss;
- gso_skb->truesize -= mss;
+ sum_truesize += skb->truesize;
}
skb = skb->next;
th = tcp_hdr(skb);
@@ -2985,7 +3000,9 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
if (copy_destructor) {
swap(gso_skb->sk, skb->sk);
swap(gso_skb->destructor, skb->destructor);
- swap(gso_skb->truesize, skb->truesize);
+ sum_truesize += skb->truesize;
+ atomic_add(sum_truesize - gso_skb->truesize,
+ &skb->sk->sk_wmem_alloc);
}
delta = htonl(oldlen + (skb->tail - skb->transport_header) +