}
/* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+ u32 rcv_nxt)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (unlikely(rcv_nxt != tp->rcv_nxt))
+ return; /* Special ACK sent by DCTCP to reflect ECN */
tcp_dec_quickack_mode(sk, pkts);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}
* We are working here with either a clone of the original
* SKB, or a fresh unique copy made by the retransmit engine.
*/
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
- gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+ int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet;
th->source = inet->inet_sport;
th->dest = inet->inet_dport;
th->seq = htonl(tcb->seq);
- th->ack_seq = htonl(tp->rcv_nxt);
+ th->ack_seq = htonl(rcv_nxt);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->tcp_flags);
icsk->icsk_af_ops->send_check(sk, skb);
if (likely(tcb->tcp_flags & TCPHDR_ACK))
- tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+ tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
return err;
}
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+ gfp_t gfp_mask)
+{
+ return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+ tcp_sk(sk)->rcv_nxt);
+}
+
/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
if (nsize < 0)
nsize = 0;
+ if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf)) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
+ return -ENOMEM;
+ }
+
if (skb_unclone(skb, gfp))
return -ENOMEM;
mss_now -= icsk->icsk_ext_hdr_len;
/* Then reserve room for full set of TCP options and 8 bytes of data */
- if (mss_now < 48)
- mss_now = 48;
+ if (mss_now < TCP_MIN_SND_MSS)
+ mss_now = TCP_MIN_SND_MSS;
return mss_now;
}
*/
segs = max_t(u32, bytes / mss_now, min_tso_segs);
- return min_t(u32, segs, sk->sk_gso_max_segs);
+ return segs;
}
EXPORT_SYMBOL(tcp_tso_autosize);
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,
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+ if (!tso_segs)
+ tso_segs = tcp_tso_autosize(sk, mss_now,
+ sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
+ return min_t(u32, tso_segs, sk->sk_gso_max_segs);
}
/* Returns the portion of skb which can be sent right away */
}
}
+static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
+{
+ struct sk_buff *skb, *next;
+
+ skb = tcp_send_head(sk);
+ tcp_for_write_queue_from_safe(skb, next, sk) {
+ if (len <= skb->len)
+ break;
+
+ if (unlikely(TCP_SKB_CB(skb)->eor))
+ return false;
+
+ len -= skb->len;
+ }
+
+ return true;
+}
+
/* Create a new MTU probe if we are ready.
* MTU probe is regularly attempting to increase the path MTU by
* deliberately sending larger packets. This discovers routing
return 0;
}
+ if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
+ return -1;
+
/* We're allowed to probe. Build it now. */
nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
if (!nskb)
/* We've eaten all the data from this skb.
* Throw it away. */
TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ /* If this is the last SKB we copy and eor is set
+ * we need to propagate it to the new skb.
+ */
+ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor;
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
} else {
early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
/* Schedule a loss probe in 2*RTT for SACK capable connections
- * in Open state, that are either limited by cwnd or application.
+ * not in loss recovery, that are either limited by cwnd or application.
*/
if ((early_retrans != 3 && early_retrans != 4) ||
!tp->packets_out || !tcp_is_sack(tp) ||
- icsk->icsk_ca_state != TCP_CA_Open)
- return false;
-
- if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
- !tcp_write_queue_empty(sk))
+ (icsk->icsk_ca_state != TCP_CA_Open &&
+ icsk->icsk_ca_state != TCP_CA_CWR))
return false;
/* Probe timeout is 2*rtt. Add minimum RTO to account
if (next_skb_size <= skb_availroom(skb))
skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size),
next_skb_size);
- else if (!skb_shift(skb, next_skb, next_skb_size))
+ else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size))
return false;
}
tcp_highest_sack_replace(sk, next_skb, skb);
return -EBUSY;
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
- if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
- BUG();
+ if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
tcp_init_wl(tp, 0);
+ tcp_write_queue_purge(sk);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
tp->snd_up = tp->write_seq;
}
/* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
{
struct sk_buff *buff;
skb_set_tcp_pure_ack(buff);
/* Send it off, this clears delayed acks for us. */
- tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+ __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
}
-EXPORT_SYMBOL_GPL(tcp_send_ack);
/* This routine sends a packet with an out of date sequence
* number. It assumes the other end will try to ack it.