*
* "len" is invariant segment length, including TCP header.
*/
- len += skb->data - skb->h.raw;
+ len += skb->data - skb_transport_header(skb);
if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* to handle super-low mtu links fairly.
*/
(len >= TCP_MIN_MSS + sizeof(struct tcphdr) &&
- !(tcp_flag_word(skb->h.th)&TCP_REMNANT))) {
+ !(tcp_flag_word(tcp_hdr(skb)) & TCP_REMNANT))) {
/* Subtract also invariant (if peer is RFC compliant),
* tcp header plus fixed timestamp option length.
* Resulting "len" is MSS free of SACK jitter.
*/
/* Slow part of check#2. */
-static int __tcp_grow_window(const struct sock *sk, struct tcp_sock *tp,
- const struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(skb->truesize)/2;
int window = tcp_win_from_space(sysctl_tcp_rmem[2])/2;
return 0;
}
-static void tcp_grow_window(struct sock *sk, struct tcp_sock *tp,
+static void tcp_grow_window(struct sock *sk,
struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
/* Check #1 */
if (tp->rcv_ssthresh < tp->window_clamp &&
(int)tp->rcv_ssthresh < tcp_space(sk) &&
if (tcp_win_from_space(skb->truesize) <= skb->len)
incr = 2*tp->advmss;
else
- incr = __tcp_grow_window(sk, tp, skb);
+ incr = __tcp_grow_window(sk, skb);
if (incr) {
tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr, tp->window_clamp);
}
/* 5. Recalculate window clamp after socket hit its memory bounds. */
-static void tcp_clamp_window(struct sock *sk, struct tcp_sock *tp)
+static void tcp_clamp_window(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_ack.quick = 0;
* each ACK we send, he increments snd_cwnd and transmits more of his
* queue. -DaveM
*/
-static void tcp_event_data_recv(struct sock *sk, struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
u32 now;
TCP_ECN_check_ce(tp, skb);
if (skb->len >= 128)
- tcp_grow_window(sk, tp, skb);
+ tcp_grow_window(sk, skb);
}
/* Called to compute a smoothed rtt estimate. The data fed to this
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- unsigned char *ptr = ack_skb->h.raw + TCP_SKB_CB(ack_skb)->sacked;
+ unsigned char *ptr = (skb_transport_header(ack_skb) +
+ TCP_SKB_CB(ack_skb)->sacked);
struct tcp_sack_block_wire *sp = (struct tcp_sack_block_wire *)(ptr+2);
struct sk_buff *cached_skb;
int num_sacks = (ptr[1] - TCPOLEN_SACK_BASE)>>3;
int prior_fackets;
u32 lost_retrans = 0;
int flag = 0;
- int dup_sack = 0;
+ int found_dup_sack = 0;
int cached_fack_count;
int i;
int first_sack_index;
/* Check for D-SACK. */
if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
- dup_sack = 1;
+ found_dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1 &&
!after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
!before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
- dup_sack = 1;
+ found_dup_sack = 1;
tp->rx_opt.sack_ok |= 4;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
}
/* D-SACK for already forgotten data...
* Do dumb counting. */
- if (dup_sack &&
+ if (found_dup_sack &&
!after(ntohl(sp[0].end_seq), prior_snd_una) &&
after(ntohl(sp[0].end_seq), tp->undo_marker))
tp->undo_retrans--;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
+ int dup_sack = (found_dup_sack && (i == first_sack_index));
skb = cached_skb;
fack_count = cached_fack_count;
return flag;
}
-/* F-RTO can only be used if these conditions are satisfied:
- * - there must be some unsent new data
- * - the advertised window should allow sending it
- * - TCP has never retransmitted anything other than head (SACK enhanced
- * variant from Appendix B of RFC4138 is more robust here)
+/* F-RTO can only be used if TCP has never retransmitted anything other than
+ * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
*/
int tcp_use_frto(struct sock *sk)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- if (!sysctl_tcp_frto || !tcp_send_head(sk) ||
- after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
- tp->snd_una + tp->snd_wnd))
+ if (!sysctl_tcp_frto)
return 0;
if (IsSackFrto())
* waiting for the first ACK and did not get it)...
*/
if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) {
- tp->retrans_out += tcp_skb_pcount(skb);
+ /* For some reason this R-bit might get cleared? */
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
+ tp->retrans_out += tcp_skb_pcount(skb);
/* ...enter this if branch just for the first segment */
flag |= FLAG_DATA_ACKED;
} else {
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
+ /* Abort FRTO algorithm if one is in progress */
+ tp->frto_counter = 0;
clear_all_retrans_hints(tp);
}
return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto);
}
-static inline int tcp_head_timedout(struct sock *sk, struct tcp_sock *tp)
+static inline int tcp_head_timedout(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
return tp->packets_out &&
tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}
* Main question: may we further continue forward transmission
* with the same cwnd?
*/
-static int tcp_time_to_recover(struct sock *sk, struct tcp_sock *tp)
+static int tcp_time_to_recover(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
/* Do not perform any recovery during FRTO algorithm */
/* Trick#3 : when we use RFC2988 timer restart, fast
* retransmit can be triggered by timeout of queue head.
*/
- if (tcp_head_timedout(sk, tp))
+ if (tcp_head_timedout(sk))
return 1;
/* Trick#4: It is still not OK... But will it be useful to delay
packets_out = tp->packets_out;
if (packets_out <= tp->reordering &&
tp->sacked_out >= max_t(__u32, packets_out/2, sysctl_tcp_reordering) &&
- !tcp_may_send_now(sk, tp)) {
+ !tcp_may_send_now(sk)) {
/* We have nothing to send. This connection is limited
* either by receiver window or by application.
*/
/* Account for ACK, ACKing some data in Reno Recovery phase. */
-static void tcp_remove_reno_sacks(struct sock *sk, struct tcp_sock *tp, int acked)
+static void tcp_remove_reno_sacks(struct sock *sk, int acked)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (acked > 0) {
/* One ACK acked hole. The rest eat duplicate ACKs. */
if (acked-1 >= tp->sacked_out)
}
/* Mark head of queue up as lost. */
-static void tcp_mark_head_lost(struct sock *sk, struct tcp_sock *tp,
+static void tcp_mark_head_lost(struct sock *sk,
int packets, u32 high_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cnt;
/* Account newly detected lost packet(s) */
-static void tcp_update_scoreboard(struct sock *sk, struct tcp_sock *tp)
+static void tcp_update_scoreboard(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (IsFack(tp)) {
int lost = tp->fackets_out - tp->reordering;
if (lost <= 0)
lost = 1;
- tcp_mark_head_lost(sk, tp, lost, tp->high_seq);
+ tcp_mark_head_lost(sk, lost, tp->high_seq);
} else {
- tcp_mark_head_lost(sk, tp, 1, tp->high_seq);
+ tcp_mark_head_lost(sk, 1, tp->high_seq);
}
/* New heuristics: it is possible only after we switched
* Hence, we can detect timed out packets during fast
* retransmit without falling to slow start.
*/
- if (!IsReno(tp) && tcp_head_timedout(sk, tp)) {
+ if (!IsReno(tp) && tcp_head_timedout(sk)) {
struct sk_buff *skb;
skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
/* Undo procedures. */
#if FASTRETRANS_DEBUG > 1
-static void DBGUNDO(struct sock *sk, struct tcp_sock *tp, const char *msg)
+static void DBGUNDO(struct sock *sk, const char *msg)
{
+ struct tcp_sock *tp = tcp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
+
printk(KERN_DEBUG "Undo %s %u.%u.%u.%u/%u c%u l%u ss%u/%u p%u\n",
msg,
NIPQUAD(inet->daddr), ntohs(inet->dport),
}
/* People celebrate: "We love our President!" */
-static int tcp_try_undo_recovery(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_recovery(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
/* Happy end! We did not retransmit anything
* or our original transmission succeeded.
*/
- DBGUNDO(sk, tp, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
+ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
tcp_undo_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk, struct tcp_sock *tp)
+static void tcp_try_undo_dsack(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tp->undo_marker && !tp->undo_retrans) {
- DBGUNDO(sk, tp, "D-SACK");
+ DBGUNDO(sk, "D-SACK");
tcp_undo_cwr(sk, 1);
tp->undo_marker = 0;
NET_INC_STATS_BH(LINUX_MIB_TCPDSACKUNDO);
/* Undo during fast recovery after partial ACK. */
-static int tcp_try_undo_partial(struct sock *sk, struct tcp_sock *tp,
- int acked)
+static int tcp_try_undo_partial(struct sock *sk, int acked)
{
+ struct tcp_sock *tp = tcp_sk(sk);
/* Partial ACK arrived. Force Hoe's retransmit. */
int failed = IsReno(tp) || tp->fackets_out>tp->reordering;
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
- DBGUNDO(sk, tp, "Hoe");
+ DBGUNDO(sk, "Hoe");
tcp_undo_cwr(sk, 0);
NET_INC_STATS_BH(LINUX_MIB_TCPPARTIALUNDO);
}
/* Undo during loss recovery after partial ACK. */
-static int tcp_try_undo_loss(struct sock *sk, struct tcp_sock *tp)
+static int tcp_try_undo_loss(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (tcp_may_undo(tp)) {
struct sk_buff *skb;
tcp_for_write_queue(skb, sk) {
clear_all_retrans_hints(tp);
- DBGUNDO(sk, tp, "partial loss");
+ DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
tp->left_out = tp->sacked_out;
tcp_undo_cwr(sk, 1);
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
-static void tcp_try_to_open(struct sock *sk, struct tcp_sock *tp, int flag)
+static void tcp_try_to_open(struct sock *sk, int flag)
{
- tp->left_out = tp->sacked_out;
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tcp_sync_left_out(tp);
if (tp->retrans_out == 0)
tp->retrans_stamp = 0;
before(tp->snd_una, tp->high_seq) &&
icsk->icsk_ca_state != TCP_CA_Open &&
tp->fackets_out > tp->reordering) {
- tcp_mark_head_lost(sk, tp, tp->fackets_out-tp->reordering, tp->high_seq);
+ tcp_mark_head_lost(sk, tp->fackets_out-tp->reordering, tp->high_seq);
NET_INC_STATS_BH(LINUX_MIB_TCPLOSS);
}
switch (icsk->icsk_ca_state) {
case TCP_CA_Loss:
icsk->icsk_retransmits = 0;
- if (tcp_try_undo_recovery(sk, tp))
+ if (tcp_try_undo_recovery(sk))
return;
break;
break;
case TCP_CA_Disorder:
- tcp_try_undo_dsack(sk, tp);
+ tcp_try_undo_dsack(sk);
if (!tp->undo_marker ||
/* For SACK case do not Open to allow to undo
* catching for all duplicate ACKs. */
case TCP_CA_Recovery:
if (IsReno(tp))
tcp_reset_reno_sack(tp);
- if (tcp_try_undo_recovery(sk, tp))
+ if (tcp_try_undo_recovery(sk))
return;
tcp_complete_cwr(sk);
break;
} else {
int acked = prior_packets - tp->packets_out;
if (IsReno(tp))
- tcp_remove_reno_sacks(sk, tp, acked);
- is_dupack = tcp_try_undo_partial(sk, tp, acked);
+ tcp_remove_reno_sacks(sk, acked);
+ is_dupack = tcp_try_undo_partial(sk, acked);
}
break;
case TCP_CA_Loss:
if (flag&FLAG_DATA_ACKED)
icsk->icsk_retransmits = 0;
- if (!tcp_try_undo_loss(sk, tp)) {
+ if (!tcp_try_undo_loss(sk)) {
tcp_moderate_cwnd(tp);
tcp_xmit_retransmit_queue(sk);
return;
}
if (icsk->icsk_ca_state == TCP_CA_Disorder)
- tcp_try_undo_dsack(sk, tp);
+ tcp_try_undo_dsack(sk);
- if (!tcp_time_to_recover(sk, tp)) {
- tcp_try_to_open(sk, tp, flag);
+ if (!tcp_time_to_recover(sk)) {
+ tcp_try_to_open(sk, flag);
return;
}
tcp_set_ca_state(sk, TCP_CA_Recovery);
}
- if (is_dupack || tcp_head_timedout(sk, tp))
- tcp_update_scoreboard(sk, tp);
+ if (is_dupack || tcp_head_timedout(sk))
+ tcp_update_scoreboard(sk);
tcp_cwnd_down(sk);
tcp_xmit_retransmit_queue(sk);
}
tcp_ack_no_tstamp(sk, seq_rtt, flag);
}
-static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 rtt,
+static void tcp_cong_avoid(struct sock *sk, u32 ack,
u32 in_flight, int good)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
- icsk->icsk_ca_ops->cong_avoid(sk, ack, rtt, in_flight, good);
+ icsk->icsk_ca_ops->cong_avoid(sk, ack, in_flight, good);
tcp_sk(sk)->snd_cwnd_stamp = tcp_time_stamp;
}
* RFC2988 recommends to restart timer to now+rto.
*/
-static void tcp_ack_packets_out(struct sock *sk, struct tcp_sock *tp)
+static void tcp_ack_packets_out(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (!tp->packets_out) {
inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
} else {
return acked;
}
-static u32 tcp_usrtt(struct timeval *tv)
-{
- struct timeval now;
-
- do_gettimeofday(&now);
- return (now.tv_sec - tv->tv_sec) * 1000000 + (now.tv_usec - tv->tv_usec);
-}
-
/* Remove acknowledged frames from the retransmission queue. */
static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
{
struct sk_buff *skb;
__u32 now = tcp_time_stamp;
int acked = 0;
+ int prior_packets = tp->packets_out;
__s32 seq_rtt = -1;
- u32 pkts_acked = 0;
- void (*rtt_sample)(struct sock *sk, u32 usrtt)
- = icsk->icsk_ca_ops->rtt_sample;
- struct timeval tv = { .tv_sec = 0, .tv_usec = 0 };
+ ktime_t last_ackt = net_invalid_timestamp();
while ((skb = tcp_write_queue_head(sk)) &&
skb != tcp_send_head(sk)) {
*/
if (!(scb->flags & TCPCB_FLAG_SYN)) {
acked |= FLAG_DATA_ACKED;
- ++pkts_acked;
} else {
acked |= FLAG_SYN_ACKED;
tp->retrans_stamp = 0;
seq_rtt = -1;
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- skb_get_timestamp(skb, &tv);
+ last_ackt = skb->tstamp;
}
if (sacked & TCPCB_SACKED_ACKED)
tp->sacked_out -= tcp_skb_pcount(skb);
}
} else if (seq_rtt < 0) {
seq_rtt = now - scb->when;
- skb_get_timestamp(skb, &tv);
+ last_ackt = skb->tstamp;
}
tcp_dec_pcount_approx(&tp->fackets_out, skb);
tcp_packets_out_dec(tp, skb);
}
if (acked&FLAG_ACKED) {
+ u32 pkts_acked = prior_packets - tp->packets_out;
+ const struct tcp_congestion_ops *ca_ops
+ = inet_csk(sk)->icsk_ca_ops;
+
tcp_ack_update_rtt(sk, acked, seq_rtt);
- tcp_ack_packets_out(sk, tp);
- if (rtt_sample && !(acked & FLAG_RETRANS_DATA_ACKED))
- (*rtt_sample)(sk, tcp_usrtt(&tv));
+ tcp_ack_packets_out(sk);
+
+ /* Is the ACK triggering packet unambiguous? */
+ if (acked & FLAG_RETRANS_DATA_ACKED)
+ last_ackt = net_invalid_timestamp();
- if (icsk->icsk_ca_ops->pkts_acked)
- icsk->icsk_ca_ops->pkts_acked(sk, pkts_acked);
+ if (ca_ops->pkts_acked)
+ ca_ops->pkts_acked(sk, pkts_acked, last_ackt);
}
#if FASTRETRANS_DEBUG > 0
* Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2
* and in FreeBSD. NetBSD's one is even worse.) is wrong.
*/
-static int tcp_ack_update_window(struct sock *sk, struct tcp_sock *tp,
- struct sk_buff *skb, u32 ack, u32 ack_seq)
+static int tcp_ack_update_window(struct sock *sk, struct sk_buff *skb, u32 ack,
+ u32 ack_seq)
{
+ struct tcp_sock *tp = tcp_sk(sk);
int flag = 0;
- u32 nwin = ntohs(skb->h.th->window);
+ u32 nwin = ntohs(tcp_hdr(skb)->window);
- if (likely(!skb->h.th->syn))
+ if (likely(!tcp_hdr(skb)->syn))
nwin <<= tp->rx_opt.snd_wscale;
if (tcp_may_update_window(tp, ack, ack_seq, nwin)) {
* fast path is recovered for sending TCP.
*/
tp->pred_flags = 0;
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
if (nwin > tp->max_window) {
tp->max_window = nwin;
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
+ TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
* algorithm is not part of the F-RTO detection algorithm
* given in RFC4138 but can be selected separately).
* Otherwise (basically on duplicate ACK), RTO was (likely) caused by a loss
- * and TCP falls back to conventional RTO recovery.
+ * and TCP falls back to conventional RTO recovery. F-RTO allows overriding
+ * of Nagle, this is done using frto_counter states 2 and 3, when a new data
+ * segment of any size sent during F-RTO, state 2 is upgraded to 3.
*
* Rationale: if the RTO was spurious, new ACKs should arrive from the
* original window even after we transmit two new data segments.
inet_csk(sk)->icsk_retransmits = 0;
if (!before(tp->snd_una, tp->frto_highmark)) {
- tcp_enter_frto_loss(sk, tp->frto_counter + 1, flag);
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3), flag);
return 1;
}
return 1;
}
- if ((tp->frto_counter == 2) &&
+ if ((tp->frto_counter >= 2) &&
(!(flag&FLAG_FORWARD_PROGRESS) ||
((flag&FLAG_DATA_SACKED) && !(flag&FLAG_ONLY_ORIG_SACKED)))) {
/* RFC4138 shortcoming (see comment above) */
}
if (tp->frto_counter == 1) {
+ /* Sending of the next skb must be allowed or no FRTO */
+ if (!tcp_send_head(sk) ||
+ after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
+ tp->snd_una + tp->snd_wnd)) {
+ tcp_enter_frto_loss(sk, (tp->frto_counter == 1 ? 2 : 3),
+ flag);
+ return 1;
+ }
+
tp->snd_cwnd = tcp_packets_in_flight(tp) + 2;
tp->frto_counter = 2;
return 1;
- } else /* frto_counter == 2 */ {
+ } else {
switch (sysctl_tcp_frto_response) {
case 2:
tcp_undo_spur_to_response(sk, flag);
default:
tcp_ratehalving_spur_to_response(sk);
break;
- };
+ }
tp->frto_counter = 0;
}
return 0;
else
NET_INC_STATS_BH(LINUX_MIB_TCPPUREACKS);
- flag |= tcp_ack_update_window(sk, tp, skb, ack, ack_seq);
+ flag |= tcp_ack_update_window(sk, skb, ack, ack_seq);
if (TCP_SKB_CB(skb)->sacked)
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- if (TCP_ECN_rcv_ecn_echo(tp, skb->h.th))
+ if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb)))
flag |= FLAG_ECE;
tcp_ca_event(sk, CA_EVENT_SLOW_ACK);
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
tcp_may_raise_cwnd(sk, flag))
- tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 0);
+ tcp_cong_avoid(sk, ack, prior_in_flight, 0);
tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
} else {
if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
- tcp_cong_avoid(sk, ack, seq_rtt, prior_in_flight, 1);
+ tcp_cong_avoid(sk, ack, prior_in_flight, 1);
}
if ((flag & FLAG_FORWARD_PROGRESS) || !(flag&FLAG_NOT_DUP))
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab)
{
unsigned char *ptr;
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
int length=(th->doff*4)-sizeof(struct tcphdr);
ptr = (unsigned char *)(th + 1);
opt_rx->sack_ok) {
TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
}
+ break;
#ifdef CONFIG_TCP_MD5SIG
case TCPOPT_MD5SIG:
/*
*/
break;
#endif
- };
+ }
+
ptr+=opsize-2;
length-=opsize;
- };
+ }
}
}
static int tcp_disordered_ack(const struct sock *sk, const struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
u32 seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
printk(KERN_ERR "%s: Impossible, sk->sk_state=%d\n",
__FUNCTION__, sk->sk_state);
break;
- };
+ }
/* It _is_ possible, that we have something out-of-order _after_ FIN.
* Probably, we should reset in this case. For now drop them.
__skb_unlink(skb, &tp->out_of_order_queue);
__skb_queue_tail(&sk->sk_receive_queue, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- if (skb->h.th->fin)
- tcp_fin(skb, sk, skb->h.th);
+ if (tcp_hdr(skb)->fin)
+ tcp_fin(skb, sk, tcp_hdr(skb));
}
}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
- struct tcphdr *th = skb->h.th;
+ struct tcphdr *th = tcp_hdr(skb);
struct tcp_sock *tp = tcp_sk(sk);
int eaten = -1;
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (skb->len)
- tcp_event_data_recv(sk, tp, skb);
+ tcp_event_data_recv(sk, skb);
if (th->fin)
tcp_fin(skb, sk, th);
if (tp->rx_opt.num_sacks)
tcp_sack_remove(tp);
- tcp_fast_path_check(sk, tp);
+ tcp_fast_path_check(sk);
if (eaten > 0)
__kfree_skb(skb);
* - bloated or contains data before "start" or
* overlaps to the next one.
*/
- if (!skb->h.th->syn && !skb->h.th->fin &&
+ if (!tcp_hdr(skb)->syn && !tcp_hdr(skb)->fin &&
(tcp_win_from_space(skb->truesize) > skb->len ||
before(TCP_SKB_CB(skb)->seq, start) ||
(skb->next != tail &&
start = TCP_SKB_CB(skb)->end_seq;
skb = skb->next;
}
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail || tcp_hdr(skb)->syn || tcp_hdr(skb)->fin)
return;
while (before(start, end)) {
if (!nskb)
return;
- nskb->mac.raw = nskb->data + (skb->mac.raw - skb->head);
- nskb->nh.raw = nskb->data + (skb->nh.raw - skb->head);
- nskb->h.raw = nskb->data + (skb->h.raw - skb->head);
-
+ skb_set_mac_header(nskb, skb_mac_header(skb) - skb->head);
+ skb_set_network_header(nskb, (skb_network_header(skb) -
+ skb->head));
+ skb_set_transport_header(nskb, (skb_transport_header(skb) -
+ skb->head));
skb_reserve(nskb, header);
memcpy(nskb->head, skb->head, header);
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
__kfree_skb(skb);
NET_INC_STATS_BH(LINUX_MIB_TCPRCVCOLLAPSED);
skb = next;
- if (skb == tail || skb->h.th->syn || skb->h.th->fin)
+ if (skb == tail ||
+ tcp_hdr(skb)->syn ||
+ tcp_hdr(skb)->fin)
return;
}
}
NET_INC_STATS_BH(LINUX_MIB_PRUNECALLED);
if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
- tcp_clamp_window(sk, tp);
+ tcp_clamp_window(sk);
else if (tcp_memory_pressure)
tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
-static int tcp_should_expand_sndbuf(struct sock *sk, struct tcp_sock *tp)
+static int tcp_should_expand_sndbuf(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
/* If the user specified a specific send buffer setting, do
* not modify it.
*/
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_should_expand_sndbuf(sk, tp)) {
+ if (tcp_should_expand_sndbuf(sk)) {
int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
MAX_TCP_HEADER + 16 + sizeof(struct sk_buff),
demanded = max_t(unsigned int, tp->snd_cwnd,
}
}
-static inline void tcp_data_snd_check(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_data_snd_check(struct sock *sk)
{
- tcp_push_pending_frames(sk, tp);
+ tcp_push_pending_frames(sk);
tcp_check_space(sk);
}
int err;
local_bh_enable();
- if (skb->ip_summed==CHECKSUM_UNNECESSARY)
+ if (skb_csum_unnecessary(skb))
err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk);
else
err = skb_copy_and_csum_datagram_iovec(skb, hlen,
static inline int tcp_checksum_complete_user(struct sock *sk, struct sk_buff *skb)
{
- return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+ return !skb_csum_unnecessary(skb) &&
__tcp_checksum_complete_user(sk, skb);
}
if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
tp->ucopy.dma_chan = get_softnet_dma();
- if (tp->ucopy.dma_chan && skb->ip_summed == CHECKSUM_UNNECESSARY) {
+ if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
dma_cookie = dma_skb_copy_datagram_iovec(tp->ucopy.dma_chan,
skb, hlen, tp->ucopy.iov, chunk, tp->ucopy.pinned_list);
tcp_rcv_space_adjust(sk);
if ((tp->ucopy.len == 0) ||
- (tcp_flag_word(skb->h.th) & TCP_FLAG_PSH) ||
+ (tcp_flag_word(tcp_hdr(skb)) & TCP_FLAG_PSH) ||
(atomic_read(&sk->sk_rmem_alloc) > (sk->sk_rcvbuf >> 1))) {
tp->ucopy.wakeup = 1;
sk->sk_data_ready(sk, 0);
*/
tcp_ack(sk, skb, 0);
__kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
return 0;
} else { /* Header too small */
TCP_INC_STATS_BH(TCP_MIB_INERRS);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
}
- tcp_event_data_recv(sk, tp, skb);
+ tcp_event_data_recv(sk, skb);
if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
/* Well, only one small jumplet in fast path... */
tcp_ack(sk, skb, FLAG_DATA);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
if (!inet_csk_ack_scheduled(sk))
goto no_ack;
}
/* step 7: process the segment text */
tcp_data_queue(sk, skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
return 0;
/* Do step6 onward by hand. */
tcp_urg(sk, skb, th);
__kfree_skb(skb);
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
return 0;
}
/* tcp_data could move socket to TIME-WAIT */
if (sk->sk_state != TCP_CLOSE) {
- tcp_data_snd_check(sk, tp);
+ tcp_data_snd_check(sk);
tcp_ack_snd_check(sk);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff