*
* "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.
* does not matter how to _calculate_ it. Seems, it was trap
* that VJ failed to avoid. 8)
*/
- if(m == 0)
+ if (m == 0)
m = 1;
if (tp->srtt != 0) {
m -= (tp->srtt >> 3); /* m is now error in rtt est */
{
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;
cached_skb = tp->fastpath_skb_hint;
cached_fack_count = tp->fastpath_cnt_hint;
if (!cached_skb) {
- cached_skb = sk->sk_write_queue.next;
+ cached_skb = tcp_write_queue_head(sk);
cached_fack_count = 0;
}
if (after(end_seq, tp->high_seq))
flag |= FLAG_DATA_LOST;
- sk_stream_for_retrans_queue_from(skb, sk) {
+ tcp_for_write_queue_from(skb, sk) {
int in_sack, pcount;
u8 sacked;
+ if (skb == tcp_send_head(sk))
+ break;
+
cached_skb = skb;
cached_fack_count = fack_count;
if (i == first_sack_index) {
if (lost_retrans && icsk->icsk_ca_state == TCP_CA_Recovery) {
struct sk_buff *skb;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
if (after(TCP_SKB_CB(skb)->seq, lost_retrans))
break;
if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
const struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- if (!sysctl_tcp_frto || !sk->sk_send_head ||
- after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
+ if (!sysctl_tcp_frto || !tcp_send_head(sk) ||
+ after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd))
return 0;
if (tp->retrans_out > 1)
return 0;
- skb = skb_peek(&sk->sk_write_queue)->next; /* Skips head */
- sk_stream_for_retrans_queue_from(skb, sk) {
+ skb = tcp_write_queue_head(sk);
+ skb = tcp_write_queue_next(sk, skb); /* Skips head */
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
return 0;
/* Short-circuit when first non-SACKed skb has been checked */
tp->undo_marker = tp->snd_una;
tp->undo_retrans = 0;
- skb = skb_peek(&sk->sk_write_queue);
+ skb = tcp_write_queue_head(sk);
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
tp->retrans_out -= tcp_skb_pcount(skb);
tp->fackets_out = 0;
tp->retrans_out = 0;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
cnt += tcp_skb_pcount(skb);
/*
* Count the retransmission made on RTO correctly (only when
if (!how)
tp->undo_marker = tp->snd_una;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
cnt += tcp_skb_pcount(skb);
if (TCP_SKB_CB(skb)->sacked&TCPCB_RETRANS)
tp->undo_marker = 0;
* receiver _host_ is heavily congested (or buggy).
* Do processing similar to RTO timeout.
*/
- if ((skb = skb_peek(&sk->sk_write_queue)) != NULL &&
+ if ((skb = tcp_write_queue_head(sk)) != NULL &&
(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
struct inet_connection_sock *icsk = inet_csk(sk);
NET_INC_STATS_BH(LINUX_MIB_TCPSACKRENEGING);
tcp_enter_loss(sk, 1);
icsk->icsk_retransmits++;
- tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue));
+ tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
icsk->icsk_rto, TCP_RTO_MAX);
return 1;
static inline int tcp_head_timedout(struct sock *sk, struct tcp_sock *tp)
{
return tp->packets_out &&
- tcp_skb_timedout(sk, skb_peek(&sk->sk_write_queue));
+ tcp_skb_timedout(sk, tcp_write_queue_head(sk));
}
/* Linux NewReno/SACK/FACK/ECN state machine.
skb = tp->lost_skb_hint;
cnt = tp->lost_cnt_hint;
} else {
- skb = sk->sk_write_queue.next;
+ skb = tcp_write_queue_head(sk);
cnt = 0;
}
- sk_stream_for_retrans_queue_from(skb, sk) {
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
/* TODO: do this better */
/* this is not the most efficient way to do this... */
tp->lost_skb_hint = skb;
/* clear xmit_retransmit_queue hints
* if this is beyond hint */
- if(tp->retransmit_skb_hint != NULL &&
- before(TCP_SKB_CB(skb)->seq,
- TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) {
-
+ if (tp->retransmit_skb_hint != NULL &&
+ before(TCP_SKB_CB(skb)->seq,
+ TCP_SKB_CB(tp->retransmit_skb_hint)->seq))
tp->retransmit_skb_hint = NULL;
- }
+
}
}
tcp_sync_left_out(tp);
struct sk_buff *skb;
skb = tp->scoreboard_skb_hint ? tp->scoreboard_skb_hint
- : sk->sk_write_queue.next;
+ : tcp_write_queue_head(sk);
- sk_stream_for_retrans_queue_from(skb, sk) {
+ tcp_for_write_queue_from(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
if (!tcp_skb_timedout(sk, skb))
break;
{
if (tcp_may_undo(tp)) {
struct sk_buff *skb;
- sk_stream_for_retrans_queue(skb, sk) {
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
}
= icsk->icsk_ca_ops->rtt_sample;
struct timeval tv = { .tv_sec = 0, .tv_usec = 0 };
- while ((skb = skb_peek(&sk->sk_write_queue)) &&
- skb != sk->sk_send_head) {
+ while ((skb = tcp_write_queue_head(sk)) &&
+ skb != tcp_send_head(sk)) {
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
__u8 sacked = scb->sacked;
if (sacked) {
if (sacked & TCPCB_RETRANS) {
- if(sacked & TCPCB_SACKED_RETRANS)
+ if (sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= tcp_skb_pcount(skb);
acked |= FLAG_RETRANS_DATA_ACKED;
seq_rtt = -1;
}
tcp_dec_pcount_approx(&tp->fackets_out, skb);
tcp_packets_out_dec(tp, skb);
- __skb_unlink(skb, &sk->sk_write_queue);
+ tcp_unlink_write_queue(skb, sk);
sk_stream_free_skb(sk, skb);
clear_all_retrans_hints(tp);
}
/* Was it a usable window open? */
- if (!after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
+ if (!after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
icsk->icsk_backoff = 0;
inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
struct sk_buff *skb, u32 ack, u32 ack_seq)
{
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)) {
*/
static void tcp_ratehalving_spur_to_response(struct sock *sk)
{
- struct tcp_sock *tp = tcp_sk(sk);
tcp_enter_cwr(sk, 0);
- tp->high_seq = tp->frto_highmark; /* Smoother w/o this? - ij */
}
-static void tcp_undo_spur_to_response(struct sock *sk)
+static void tcp_undo_spur_to_response(struct sock *sk, int flag)
{
- tcp_undo_cwr(sk, 1);
+ if (flag&FLAG_ECE)
+ tcp_ratehalving_spur_to_response(sk);
+ else
+ tcp_undo_cwr(sk, 1);
}
/* F-RTO spurious RTO detection algorithm (RFC4138)
} else /* frto_counter == 2 */ {
switch (sysctl_tcp_frto_response) {
case 2:
- tcp_undo_spur_to_response(sk);
+ tcp_undo_spur_to_response(sk, flag);
break;
case 1:
tcp_conservative_spur_to_response(tp);
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);
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
*/
- if (sk->sk_send_head)
+ if (tcp_send_head(sk))
tcp_ack_probe(sk);
return 1;
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->saw_tstamp = 0;
- while(length>0) {
+ while (length > 0) {
int opcode=*ptr++;
int opsize;
return;
if (opsize > length)
return; /* don't parse partial options */
- switch(opcode) {
+ switch (opcode) {
case TCPOPT_MSS:
- if(opsize==TCPOLEN_MSS && th->syn && !estab) {
+ if (opsize==TCPOLEN_MSS && th->syn && !estab) {
u16 in_mss = ntohs(get_unaligned((__be16 *)ptr));
if (in_mss) {
if (opt_rx->user_mss && opt_rx->user_mss < in_mss)
}
break;
case TCPOPT_WINDOW:
- if(opsize==TCPOLEN_WINDOW && th->syn && !estab)
+ if (opsize==TCPOLEN_WINDOW && th->syn && !estab)
if (sysctl_tcp_window_scaling) {
__u8 snd_wscale = *(__u8 *) ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
- if(net_ratelimit())
+ if (net_ratelimit())
printk(KERN_INFO "tcp_parse_options: Illegal window "
"scaling value %d >14 received.\n",
snd_wscale);
}
break;
case TCPOPT_TIMESTAMP:
- if(opsize==TCPOLEN_TIMESTAMP) {
+ if (opsize==TCPOLEN_TIMESTAMP) {
if ((estab && opt_rx->tstamp_ok) ||
(!estab && sysctl_tcp_timestamps)) {
opt_rx->saw_tstamp = 1;
}
break;
case TCPOPT_SACK_PERM:
- if(opsize==TCPOLEN_SACK_PERM && th->syn && !estab) {
+ if (opsize==TCPOLEN_SACK_PERM && th->syn && !estab) {
if (sysctl_tcp_sack) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
break;
case TCPOPT_SACK:
- if((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
+ if ((opsize >= (TCPOLEN_SACK_BASE + TCPOLEN_SACK_PERBLOCK)) &&
!((opsize - TCPOLEN_SACK_BASE) % TCPOLEN_SACK_PERBLOCK) &&
opt_rx->sack_ok) {
TCP_SKB_CB(skb)->sacked = (ptr - 2) - (unsigned char *)th;
static inline void tcp_store_ts_recent(struct tcp_sock *tp)
{
tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
- tp->rx_opt.ts_recent_stamp = xtime.tv_sec;
+ tp->rx_opt.ts_recent_stamp = get_seconds();
}
static inline void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
* Not only, also it occurs for expired timestamps.
*/
- if((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
- xtime.tv_sec >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
+ if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) >= 0 ||
+ get_seconds() >= tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS)
tcp_store_ts_recent(tp);
}
}
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;
{
const struct tcp_sock *tp = tcp_sk(sk);
return ((s32)(tp->rx_opt.ts_recent - tp->rx_opt.rcv_tsval) > TCP_PAWS_WINDOW &&
- xtime.tv_sec < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
+ get_seconds() < tp->rx_opt.ts_recent_stamp + TCP_PAWS_24DAYS &&
!tcp_disordered_ack(sk, skb));
}
*/
tp->rx_opt.num_sacks--;
tp->rx_opt.eff_sacks = min(tp->rx_opt.num_sacks + tp->rx_opt.dsack, 4 - tp->rx_opt.tstamp_ok);
- for(i=this_sack; i < tp->rx_opt.num_sacks; i++)
+ for (i=this_sack; i < tp->rx_opt.num_sacks; i++)
sp[i] = sp[i+1];
continue;
}
tp->rx_opt.num_sacks--;
sp--;
}
- for(; this_sack > 0; this_sack--, sp--)
+ for (; this_sack > 0; this_sack--, sp--)
*sp = *(sp-1);
new_sack:
return;
}
- for(this_sack = 0; this_sack < num_sacks; ) {
+ for (this_sack = 0; this_sack < num_sacks; ) {
/* Check if the start of the sack is covered by RCV.NXT. */
if (!before(tp->rcv_nxt, sp->start_seq)) {
int i;
__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;
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
- if(skb->len)
+ if (skb->len)
tcp_event_data_recv(sk, tp, skb);
- if(th->fin)
+ if (th->fin)
tcp_fin(skb, sk, th);
if (!skb_queue_empty(&tp->out_of_order_queue)) {
* - 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)) {
nskb = alloc_skb(copy+header, GFP_ATOMIC);
if (!nskb)
return;
+
+ 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);
- nskb->nh.raw = nskb->head + (skb->nh.raw-skb->head);
- nskb->h.raw = nskb->head + (skb->h.raw-skb->head);
- nskb->mac.raw = nskb->head + (skb->mac.raw-skb->head);
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
__skb_insert(nskb, skb->prev, skb, list);
__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;
}
}
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);
goto discard;
}
- if(th->rst) {
+ if (th->rst) {
tcp_reset(sk);
goto discard;
}
}
step5:
- if(th->ack)
+ if (th->ack)
tcp_ack(sk, skb, FLAG_SLOWPATH);
tcp_rcv_rtt_measure_ts(sk, skb);
goto discard;
case TCP_LISTEN:
- if(th->ack)
+ if (th->ack)
return 1;
- if(th->rst)
+ if (th->rst)
goto discard;
- if(th->syn) {
+ if (th->syn) {
if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
return 1;
}
/* step 2: check RST bit */
- if(th->rst) {
+ if (th->rst) {
tcp_reset(sk);
goto discard;
}
if (th->ack) {
int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH);
- switch(sk->sk_state) {
+ switch (sk->sk_state) {
case TCP_SYN_RECV:
if (acceptable) {
tp->copied_seq = tp->rcv_nxt;
projects / deliverable / linux.git / blobdiff