summaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_output.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_output.c')
-rw-r--r--net/ipv4/tcp_output.c118
1 files changed, 82 insertions, 36 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8b45794eb6b2..896e9dfbdb5c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -734,9 +734,16 @@ static void tcp_tsq_handler(struct sock *sk)
{
if ((1 << sk->sk_state) &
(TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING |
- TCPF_CLOSE_WAIT | TCPF_LAST_ACK))
- tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+ TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) {
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->lost_out > tp->retrans_out &&
+ tp->snd_cwnd > tcp_packets_in_flight(tp))
+ tcp_xmit_retransmit_queue(sk);
+
+ tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle,
0, GFP_ATOMIC);
+ }
}
/*
* One tasklet per cpu tries to send more skbs.
@@ -918,6 +925,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_mstamp_get(&skb->skb_mstamp);
TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq
- tp->snd_una;
+ tcp_rate_skb_sent(sk, skb);
if (unlikely(skb_cloned(skb)))
skb = pskb_copy(skb, gfp_mask);
@@ -1213,6 +1221,9 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
tcp_set_skb_tso_segs(skb, mss_now);
tcp_set_skb_tso_segs(buff, mss_now);
+ /* Update delivered info for the new segment */
+ TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx;
+
/* If this packet has been sent out already, we must
* adjust the various packet counters.
*/
@@ -1358,6 +1369,7 @@ int tcp_mss_to_mtu(struct sock *sk, int mss)
}
return mtu;
}
+EXPORT_SYMBOL(tcp_mss_to_mtu);
/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
@@ -1545,7 +1557,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp,
/* Return how many segs we'd like on a TSO packet,
* to send one TSO packet per ms
*/
-static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
+u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
+ int min_tso_segs)
{
u32 bytes, segs;
@@ -1557,10 +1570,23 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now)
* This preserves ACK clocking and is consistent
* with tcp_tso_should_defer() heuristic.
*/
- segs = max_t(u32, bytes / mss_now, sysctl_tcp_min_tso_segs);
+ segs = max_t(u32, bytes / mss_now, min_tso_segs);
return min_t(u32, segs, sk->sk_gso_max_segs);
}
+EXPORT_SYMBOL(tcp_tso_autosize);
+
+/* Return the number of segments we want in the skb we are transmitting.
+ * See if congestion control module wants to decide; otherwise, autosize.
+ */
+static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
+{
+ const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
+ u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0;
+
+ return tso_segs ? :
+ tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs);
+}
/* Returns the portion of skb which can be sent right away */
static unsigned int tcp_mss_split_point(const struct sock *sk,
@@ -1966,12 +1992,14 @@ static int tcp_mtu_probe(struct sock *sk)
len = 0;
tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
- if (nskb->ip_summed)
+ if (nskb->ip_summed) {
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
- else
- nskb->csum = skb_copy_and_csum_bits(skb, 0,
- skb_put(nskb, copy),
- copy, nskb->csum);
+ } else {
+ __wsum csum = skb_copy_and_csum_bits(skb, 0,
+ skb_put(nskb, copy),
+ copy, 0);
+ nskb->csum = csum_block_add(nskb->csum, csum, len);
+ }
if (skb->len <= copy) {
/* We've eaten all the data from this skb.
@@ -2020,6 +2048,39 @@ static int tcp_mtu_probe(struct sock *sk)
return -1;
}
+/* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * (These limits are doubled for retransmits)
+ * This allows for :
+ * - better RTT estimation and ACK scheduling
+ * - faster recovery
+ * - high rates
+ * Alas, some drivers / subsystems require a fair amount
+ * of queued bytes to ensure line rate.
+ * One example is wifi aggregation (802.11 AMPDU)
+ */
+static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
+ unsigned int factor)
+{
+ unsigned int limit;
+
+ limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
+ limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
+ limit <<= factor;
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+ set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags);
+ /* It is possible TX completion already happened
+ * before we set TSQ_THROTTLED, so we must
+ * test again the condition.
+ */
+ smp_mb__after_atomic();
+ if (atomic_read(&sk->sk_wmem_alloc) > limit)
+ return true;
+ }
+ return false;
+}
+
/* This routine writes packets to the network. It advances the
* send_head. This happens as incoming acks open up the remote
* window for us.
@@ -2057,7 +2118,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
}
}
- max_segs = tcp_tso_autosize(sk, mss_now);
+ max_segs = tcp_tso_segs(sk, mss_now);
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
@@ -2106,29 +2167,8 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
break;
- /* TCP Small Queues :
- * Control number of packets in qdisc/devices to two packets / or ~1 ms.
- * This allows for :
- * - better RTT estimation and ACK scheduling
- * - faster recovery
- * - high rates
- * Alas, some drivers / subsystems require a fair amount
- * of queued bytes to ensure line rate.
- * One example is wifi aggregation (802.11 AMPDU)
- */
- limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);
- limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes);
-
- if (atomic_read(&sk->sk_wmem_alloc) > limit) {
- set_bit(TSQ_THROTTLED, &tp->tsq_flags);
- /* It is possible TX completion already happened
- * before we set TSQ_THROTTLED, so we must
- * test again the condition.
- */
- smp_mb__after_atomic();
- if (atomic_read(&sk->sk_wmem_alloc) > limit)
- break;
- }
+ if (tcp_small_queue_check(sk, skb, 0))
+ break;
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
@@ -2605,7 +2645,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
* copying overhead: fragmentation, tunneling, mangling etc.
*/
if (atomic_read(&sk->sk_wmem_alloc) >
- min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+ min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+ sk->sk_sndbuf))
return -EAGAIN;
if (skb_still_in_host_queue(sk, skb))
@@ -2774,7 +2815,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
last_lost = tp->snd_una;
}
- max_segs = tcp_tso_autosize(sk, tcp_current_mss(sk));
+ max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
tcp_for_write_queue_from(skb, sk) {
__u8 sacked;
int segs;
@@ -2828,10 +2869,13 @@ begin_fwd:
if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
continue;
+ if (tcp_small_queue_check(sk, skb, 1))
+ return;
+
if (tcp_retransmit_skb(sk, skb, segs))
return;
- NET_INC_STATS(sock_net(sk), mib_idx);
+ NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb));
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += tcp_skb_pcount(skb);
@@ -3568,6 +3612,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
if (!res) {
__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ if (unlikely(tcp_passive_fastopen(sk)))
+ tcp_sk(sk)->total_retrans++;
}
return res;
}