#include <linux/compiler.h>
#include <linux/module.h>
-#include <linux/smp_lock.h>
/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_retrans_collapse __read_mostly = 1;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
-static void update_send_head(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb)
+static void update_send_head(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
tcp_advance_send_head(sk, skb);
tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
- tcp_packets_out_inc(sk, tp, skb);
+ tcp_packets_out_inc(sk, skb);
}
/* SND.NXT, if window was not shrunk.
* Anything in between SND.UNA...SND.UNA+SND.WND also can be already
* invalid. OK, let's make this for now:
*/
-static inline __u32 tcp_acceptable_seq(struct sock *sk, struct tcp_sock *tp)
+static inline __u32 tcp_acceptable_seq(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (!before(tp->snd_una+tp->snd_wnd, tp->snd_nxt))
return tp->snd_nxt;
else
u32 new_win = __tcp_select_window(sk);
/* Never shrink the offered window */
- if(new_win < cur_win) {
+ if (new_win < cur_win) {
/* Danger Will Robinson!
* Don't update rcv_wup/rcv_wnd here or else
* we will not be able to advertise a zero
(TCPOPT_SACK << 8) |
(TCPOLEN_SACK_BASE + (tp->rx_opt.eff_sacks *
TCPOLEN_SACK_PERBLOCK)));
- for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
+
+ for (this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
*ptr++ = htonl(sp[this_sack].start_seq);
*ptr++ = htonl(sp[this_sack].end_seq);
}
+
if (tp->rx_opt.dsack) {
tp->rx_opt.dsack = 0;
tp->rx_opt.eff_sacks--;
*/
*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
if (ts) {
- if(sack)
+ if (sack)
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp); /* TSVAL */
*ptr++ = htonl(ts_recent); /* TSECR */
- } else if(sack)
+ } else if (sack)
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
/* If congestion control is doing timestamping, we must
* take such a timestamp before we potentially clone/copy.
*/
- if (icsk->icsk_ca_ops->rtt_sample)
+ if (icsk->icsk_ca_ops->flags & TCP_CONG_RTT_STAMP)
__net_timestamp(skb);
if (likely(clone_it)) {
sysctl_flags = 0;
if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
- if(sysctl_tcp_timestamps) {
+ if (sysctl_tcp_timestamps) {
tcp_header_size += TCPOLEN_TSTAMP_ALIGNED;
sysctl_flags |= SYSCTL_FLAG_TSTAMPS;
}
tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif
- th = (struct tcphdr *) skb_push(skb, tcp_header_size);
- skb->h.th = th;
+ skb_push(skb, tcp_header_size);
+ skb_reset_transport_header(skb);
skb_set_owner_w(skb, sk);
/* Build TCP header and checksum it. */
+ th = tcp_hdr(skb);
th->source = inet->sport;
th->dest = inet->dport;
th->seq = htonl(tcb->seq);
md5 ? &md5_hash_location :
#endif
NULL);
- TCP_ECN_send(sk, tp, skb, tcp_header_size);
+ TCP_ECN_send(sk, skb, tcp_header_size);
}
#ifdef CONFIG_TCP_MD5SIG
tp->af_specific->calc_md5_hash(md5_hash_location,
md5,
sk, NULL, NULL,
- skb->h.th,
+ tcp_hdr(skb),
sk->sk_protocol,
skb->len);
}
}
skb_shinfo(skb)->nr_frags = k;
- skb->tail = skb->data;
+ skb_reset_tail_pointer(skb);
skb->data_len -= len;
skb->len = skb->data_len;
}
/* Congestion window validation. (RFC2861) */
-static void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
+static void tcp_cwnd_validate(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out = tp->packets_out;
if (packets_out >= tp->snd_cwnd) {
if (nonagle & TCP_NAGLE_PUSH)
return 1;
- /* Don't use the nagle rule for urgent data (or for the final FIN). */
- if (tp->urg_mode ||
+ /* Don't use the nagle rule for urgent data (or for the final FIN).
+ * Nagle can be ignored during F-RTO too (see RFC4138).
+ */
+ if (tp->urg_mode || (tp->frto_counter == 2) ||
(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
return 1;
return cwnd_quota;
}
-int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp)
+int tcp_may_send_now(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = tcp_send_head(sk);
return (skb &&
*
* This algorithm is from John Heffner.
*/
-static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 send_win, cong_win, limit, in_flight;
/* Decrement cwnd here because we are sending
* effectively two packets. */
tp->snd_cwnd--;
- update_send_head(sk, tp, nskb);
+ update_send_head(sk, nskb);
icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
nonagle : TCP_NAGLE_PUSH))))
break;
} else {
- if (tcp_tso_should_defer(sk, tp, skb))
+ if (tcp_tso_should_defer(sk, skb))
break;
}
/* Advance the send_head. This one is sent out.
* This call will increment packets_out.
*/
- update_send_head(sk, tp, skb);
+ update_send_head(sk, skb);
tcp_minshall_update(tp, mss_now, skb);
sent_pkts++;
}
if (likely(sent_pkts)) {
- tcp_cwnd_validate(sk, tp);
+ tcp_cwnd_validate(sk);
return 0;
}
return !tp->packets_out && tcp_send_head(sk);
* TCP_CORK or attempt at coalescing tiny packets.
* The socket must be locked by the caller.
*/
-void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
- unsigned int cur_mss, int nonagle)
+void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
+ int nonagle)
{
struct sk_buff *skb = tcp_send_head(sk);
if (skb) {
if (tcp_write_xmit(sk, cur_mss, nonagle))
- tcp_check_probe_timer(sk, tp);
+ tcp_check_probe_timer(sk);
}
}
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
- update_send_head(sk, tp, skb);
- tcp_cwnd_validate(sk, tp);
+ update_send_head(sk, skb);
+ tcp_cwnd_validate(sk);
return;
}
}
u16 flags = TCP_SKB_CB(skb)->flags;
/* Also punt if next skb has been SACK'd. */
- if(TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
+ if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
return;
/* Next skb is out of window. */
/* Ok. We will be able to collapse the packet. */
tcp_unlink_write_queue(next_skb, sk);
- memcpy(skb_put(skb, next_skb_size), next_skb->data, next_skb_size);
+ skb_copy_from_linear_data(next_skb,
+ skb_put(skb, next_skb_size),
+ next_skb_size);
if (next_skb->ip_summed == CHECKSUM_PARTIAL)
skb->ip_summed = CHECKSUM_PARTIAL;
}
/* Collapse two adjacent packets if worthwhile and we can. */
- if(!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
- (skb->len < (cur_mss >> 1)) &&
- (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
- (!tcp_skb_is_last(sk, skb)) &&
- (skb_shinfo(skb)->nr_frags == 0 && skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) &&
- (tcp_skb_pcount(skb) == 1 && tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) &&
- (sysctl_tcp_retrans_collapse != 0))
+ if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) &&
+ (skb->len < (cur_mss >> 1)) &&
+ (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) &&
+ (!tcp_skb_is_last(sk, skb)) &&
+ (skb_shinfo(skb)->nr_frags == 0 && skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) &&
+ (tcp_skb_pcount(skb) == 1 && tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) &&
+ (sysctl_tcp_retrans_collapse != 0))
tcp_retrans_try_collapse(sk, skb, cur_mss);
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
* retransmit when old data is attached. So strip it off
* since it is cheap to do so and saves bytes on the network.
*/
- if(skb->len > 0 &&
- (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
- tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
+ if (skb->len > 0 &&
+ (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
+ tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1;
skb_shinfo(skb)->gso_segs = 1;
* segments to send.
*/
- if (tcp_may_send_now(sk, tp))
+ if (tcp_may_send_now(sk))
return;
if (tp->forward_skb_hint) {
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1;
tcp_queue_skb(sk, skb);
}
- __tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_OFF);
+ __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
}
/* We get here when a process closes a file descriptor (either due to
* an explicit close() or as a byproduct of exit()'ing) and there
* was unread data in the receive queue. This behavior is recommended
- * by draft-ietf-tcpimpl-prob-03.txt section 3.10. -DaveM
+ * by RFC 2525, section 2.17. -DaveM
*/
void tcp_send_active_reset(struct sock *sk, gfp_t priority)
{
- struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
/* NOTE: No TCP options attached and we never retransmit this. */
skb_shinfo(skb)->gso_type = 0;
/* Send it off. */
- TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp);
+ TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk);
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
if (md5)
tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
#endif
- skb->h.th = th = (struct tcphdr *) skb_push(skb, tcp_header_size);
+ skb_push(skb, tcp_header_size);
+ skb_reset_transport_header(skb);
+ th = tcp_hdr(skb);
memset(th, 0, sizeof(struct tcphdr));
th->syn = 1;
th->ack = 1;
tp->af_specific->calc_md5_hash(md5_hash_location,
md5,
NULL, dst, req,
- skb->h.th, sk->sk_protocol,
+ tcp_hdr(skb), sk->sk_protocol,
skb->len);
}
#endif
skb_reserve(buff, MAX_TCP_HEADER);
TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN;
- TCP_ECN_send_syn(sk, tp, buff);
+ TCP_ECN_send_syn(sk, buff);
TCP_SKB_CB(buff)->sacked = 0;
skb_shinfo(buff)->gso_segs = 1;
skb_shinfo(buff)->gso_size = 0;
{
/* If we have been reset, we may not send again. */
if (sk->sk_state != TCP_CLOSE) {
- struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
/* We are not putting this on the write queue, so
skb_shinfo(buff)->gso_type = 0;
/* Send it off, this clears delayed acks for us. */
- TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp);
+ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk);
TCP_SKB_CB(buff)->when = tcp_time_stamp;
tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
}
TCP_SKB_CB(skb)->when = tcp_time_stamp;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
if (!err) {
- update_send_head(sk, tp, skb);
+ update_send_head(sk, skb);
}
return err;
} else {