aboutsummaryrefslogtreecommitdiff
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.c76
1 files changed, 56 insertions, 20 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0145ce7e6098..11ef25c9cf43 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -686,7 +686,8 @@ 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), 0, 0, GFP_ATOMIC);
+ tcp_write_xmit(sk, tcp_current_mss(sk), tcp_sk(sk)->nonagle,
+ 0, GFP_ATOMIC);
}
/*
* One tasklest per cpu tries to send more skbs.
@@ -754,6 +755,17 @@ void tcp_release_cb(struct sock *sk)
if (flags & (1UL << TCP_TSQ_DEFERRED))
tcp_tsq_handler(sk);
+ /* Here begins the tricky part :
+ * We are called from release_sock() with :
+ * 1) BH disabled
+ * 2) sk_lock.slock spinlock held
+ * 3) socket owned by us (sk->sk_lock.owned == 1)
+ *
+ * But following code is meant to be called from BH handlers,
+ * so we should keep BH disabled, but early release socket ownership
+ */
+ sock_release_ownership(sk);
+
if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
tcp_write_timer_handler(sk);
__sock_put(sk);
@@ -763,7 +775,7 @@ void tcp_release_cb(struct sock *sk)
__sock_put(sk);
}
if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
- sk->sk_prot->mtu_reduced(sk);
+ inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
__sock_put(sk);
}
}
@@ -887,8 +899,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_orphan(skb);
skb->sk = sk;
- skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
- tcp_wfree : sock_wfree;
+ skb->destructor = tcp_wfree;
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
/* Build TCP header and checksum it. */
@@ -977,6 +988,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1058,9 +1072,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -1623,7 +1635,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
- sk->sk_gso_max_segs * tp->mss_cache))
+ tp->xmit_size_goal_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1844,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
-
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
@@ -1861,13 +1872,32 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
break;
}
- /* TSQ : sk_wmem_alloc accounts skb truesize,
- * including skb overhead. But thats OK.
+ /* 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)
*/
- if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+ limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
+ sk->sk_pacing_rate >> 10);
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
- break;
+ /* It is possible TX completion already happened
+ * before we set TSQ_THROTTLED, so we must
+ * test again the condition.
+ * We abuse smp_mb__after_clear_bit() because
+ * there is no smp_mb__after_set_bit() yet
+ */
+ smp_mb__after_clear_bit();
+ if (atomic_read(&sk->sk_wmem_alloc) > limit)
+ break;
}
+
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2006,9 +2036,7 @@ void tcp_send_loss_probe(struct sock *sk)
if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
goto rearm_timer;
- /* Probe with zero data doesn't trigger fast recovery. */
- if (skb->len > 0)
- err = __tcp_retransmit_skb(sk, skb);
+ err = __tcp_retransmit_skb(sk, skb);
/* Record snd_nxt for loss detection. */
if (likely(!err))
@@ -2329,6 +2357,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
@@ -2396,13 +2426,15 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
- tp->undo_retrans += tcp_skb_pcount(skb);
-
/* snd_nxt is stored to detect loss of retransmitted segment,
* see tcp_input.c tcp_sacktag_write_queue().
*/
TCP_SKB_CB(skb)->ack_seq = tp->snd_nxt;
}
+
+ if (tp->undo_retrans < 0)
+ tp->undo_retrans = 0;
+ tp->undo_retrans += tcp_skb_pcount(skb);
return err;
}
@@ -2871,7 +2903,12 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
- syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+ space = min_t(size_t, space, fo->size);
+
+ /* limit to order-0 allocations */
+ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER));
+
+ syn_data = skb_copy_expand(syn, MAX_TCP_HEADER, space,
sk->sk_allocation);
if (syn_data == NULL)
goto fallback;
@@ -3090,7 +3127,6 @@ void tcp_send_window_probe(struct sock *sk)
{
if (sk->sk_state == TCP_ESTABLISHED) {
tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
- tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
tcp_xmit_probe_skb(sk, 0);
}
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-27 02:19:31 +0000