#include <net/tcp.h>
#include <linux/compiler.h>
+#include <linux/gfp.h>
#include <linux/module.h>
/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_tso_win_divisor __read_mostly = 3;
int sysctl_tcp_mtu_probing __read_mostly = 0;
-int sysctl_tcp_base_mss __read_mostly = 512;
+int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
+EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
/* Account for new data that has been sent to the network. */
tcp_advance_send_head(sk, skb);
tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
- /* Don't override Nagle indefinately with F-RTO */
+ /* Don't override Nagle indefinitely with F-RTO */
if (tp->frto_counter == 2)
tp->frto_counter = 3;
struct dst_entry *dst = __sk_dst_get(sk);
int mss = tp->advmss;
- if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) {
- mss = dst_metric(dst, RTAX_ADVMSS);
- tp->advmss = mss;
+ if (dst) {
+ unsigned int metric = dst_metric_advmss(dst);
+
+ if (metric < mss) {
+ mss = metric;
+ tp->advmss = mss;
+ }
}
return (__u16)mss;
*/
void tcp_select_initial_window(int __space, __u32 mss,
__u32 *rcv_wnd, __u32 *window_clamp,
- int wscale_ok, __u8 *rcv_wscale)
+ int wscale_ok, __u8 *rcv_wscale,
+ __u32 init_rcv_wnd)
{
unsigned int space = (__space < 0 ? 0 : __space);
}
}
- /* Set initial window to value enough for senders,
- * following RFC2414. Senders, not following this RFC,
- * will be satisfied with 2.
+ /* Set initial window to a value enough for senders starting with
+ * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place
+ * a limit on the initial window when mss is larger than 1460.
*/
if (mss > (1 << *rcv_wscale)) {
- int init_cwnd = 4;
- if (mss > 1460 * 3)
- init_cwnd = 2;
- else if (mss > 1460)
- init_cwnd = 3;
- if (*rcv_wnd > init_cwnd * mss)
- *rcv_wnd = init_cwnd * mss;
+ int init_cwnd = TCP_DEFAULT_INIT_RCVWND;
+ if (mss > 1460)
+ init_cwnd =
+ max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
+ /* when initializing use the value from init_rcv_wnd
+ * rather than the default from above
+ */
+ if (init_rcv_wnd)
+ *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss);
+ else
+ *rcv_wnd = min(*rcv_wnd, init_cwnd * mss);
}
/* Set the clamp no higher than max representable value */
(*window_clamp) = min(65535U << (*rcv_wscale), *window_clamp);
}
+EXPORT_SYMBOL(tcp_select_initial_window);
/* Chose a new window to advertise, update state in tcp_sock for the
* socket, and return result with RFC1323 scaling applied. The return
/* Packet ECN state for a SYN-ACK */
static inline void TCP_ECN_send_synack(struct tcp_sock *tp, struct sk_buff *skb)
{
- TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_CWR;
+ TCP_SKB_CB(skb)->flags &= ~TCPHDR_CWR;
if (!(tp->ecn_flags & TCP_ECN_OK))
- TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_ECE;
+ TCP_SKB_CB(skb)->flags &= ~TCPHDR_ECE;
}
/* Packet ECN state for a SYN. */
tp->ecn_flags = 0;
if (sysctl_tcp_ecn == 1) {
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE | TCPCB_FLAG_CWR;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_ECE | TCPHDR_CWR;
tp->ecn_flags = TCP_ECN_OK;
}
}
*/
static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
{
+ skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
TCP_SKB_CB(skb)->flags = flags;
skb_shinfo(skb)->gso_type = 0;
TCP_SKB_CB(skb)->seq = seq;
- if (flags & (TCPCB_FLAG_SYN | TCPCB_FLAG_FIN))
+ if (flags & (TCPHDR_SYN | TCPHDR_FIN))
seq++;
TCP_SKB_CB(skb)->end_seq = seq;
}
*/
static u8 tcp_cookie_size_check(u8 desired)
{
- if (desired > 0) {
+ int cookie_size;
+
+ if (desired > 0)
/* previously specified */
return desired;
- }
- if (sysctl_tcp_cookie_size <= 0) {
+
+ cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size);
+ if (cookie_size <= 0)
/* no default specified */
return 0;
- }
- if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) {
+
+ if (cookie_size <= TCP_COOKIE_MIN)
/* value too small, specify minimum */
return TCP_COOKIE_MIN;
- }
- if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) {
+
+ if (cookie_size >= TCP_COOKIE_MAX)
/* value too large, specify maximum */
return TCP_COOKIE_MAX;
- }
- if (0x1 & sysctl_tcp_cookie_size) {
+
+ if (cookie_size & 1)
/* 8-bit multiple, illegal, fix it */
- return (u8)(sysctl_tcp_cookie_size + 0x1);
- }
- return (u8)sysctl_tcp_cookie_size;
+ cookie_size++;
+
+ return (u8)cookie_size;
}
/* Write previously computed TCP options to the packet.
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
- struct dst_entry *dst = __sk_dst_get(sk);
unsigned remaining = MAX_TCP_OPTION_SPACE;
u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
tcp_cookie_size_check(cvp->cookie_desired) :
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
- if (likely(sysctl_tcp_timestamps &&
- !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
- *md5 == NULL)) {
+ if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
+ if (likely(sysctl_tcp_window_scaling)) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sysctl_tcp_sack &&
- !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
+ if (likely(sysctl_tcp_sack)) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ?
xvp->cookie_plus :
0;
- bool doing_ts = ireq->tstamp_ok;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
* rather than TS in order to fit in better with old,
* buggy kernels, but that was deemed to be unnecessary.
*/
- doing_ts &= !ireq->sack_ok;
+ ireq->tstamp_ok &= !ireq->sack_ok;
}
#else
*md5 = NULL;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(doing_ts)) {
+ if (likely(ireq->tstamp_ok)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = req->ts_recent;
}
if (likely(ireq->sack_ok)) {
opts->options |= OPTION_SACK_ADVERTISE;
- if (unlikely(!doing_ts))
+ if (unlikely(!ireq->tstamp_ok))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
}
* If the <SYN> options fit, the same options should fit now!
*/
if (*md5 == NULL &&
- doing_ts &&
+ ireq->tstamp_ok &&
cookie_plus > TCPOLEN_COOKIE_BASE) {
int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
tcb = TCP_SKB_CB(skb);
memset(&opts, 0, sizeof(opts));
- if (unlikely(tcb->flags & TCPCB_FLAG_SYN))
+ if (unlikely(tcb->flags & TCPHDR_SYN))
tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5);
else
tcp_options_size = tcp_established_options(sk, skb, &opts,
&md5);
tcp_header_size = tcp_options_size + sizeof(struct tcphdr);
- if (tcp_packets_in_flight(tp) == 0)
+ if (tcp_packets_in_flight(tp) == 0) {
tcp_ca_event(sk, CA_EVENT_TX_START);
+ skb->ooo_okay = 1;
+ } else
+ skb->ooo_okay = 0;
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
*(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) |
tcb->flags);
- if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
+ if (unlikely(tcb->flags & TCPHDR_SYN)) {
/* RFC1323: The window in SYN & SYN/ACK segments
* is never scaled.
*/
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
- th->urg_ptr = 0xFFFF;
+ th->urg_ptr = htons(0xFFFF);
th->urg = 1;
}
}
tcp_options_write((__be32 *)(th + 1), tp, &opts);
- if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0))
+ if (likely((tcb->flags & TCPHDR_SYN) == 0))
TCP_ECN_send(sk, skb, tcp_header_size);
#ifdef CONFIG_TCP_MD5SIG
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
- sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
+ sk_nocaps_add(sk, NETIF_F_GSO_MASK);
tp->af_specific->calc_md5_hash(opts.hash_location,
md5, sk, NULL, skb);
}
#endif
- icsk->icsk_af_ops->send_check(sk, skb->len, skb);
+ icsk->icsk_af_ops->send_check(sk, skb);
- if (likely(tcb->flags & TCPCB_FLAG_ACK))
+ if (likely(tcb->flags & TCPHDR_ACK))
tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
if (skb->len != tcp_header_size)
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
+ tcp_skb_pcount(skb));
- err = icsk->icsk_af_ops->queue_xmit(skb, 0);
+ err = icsk->icsk_af_ops->queue_xmit(skb, &inet->cork.fl);
if (likely(err <= 0))
return err;
int nlen;
u8 flags;
- BUG_ON(len > skb->len);
+ if (WARN_ON(len > skb->len))
+ return -EINVAL;
nsize = skb_headlen(skb) - len;
if (nsize < 0)
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->flags;
- TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN | TCPCB_FLAG_PSH);
+ TCP_SKB_CB(skb)->flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
TCP_SKB_CB(buff)->flags = flags;
TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
sk_mem_uncharge(sk, len);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
- /* Any change of skb->len requires recalculation of tso
- * factor and mss.
- */
+ /* Any change of skb->len requires recalculation of tso factor. */
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
+ tcp_set_skb_tso_segs(sk, skb, tcp_skb_mss(skb));
return 0;
}
icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, sysctl_tcp_base_mss);
icsk->icsk_mtup.probe_size = 0;
}
+EXPORT_SYMBOL(tcp_mtup_init);
/* This function synchronize snd mss to current pmtu/exthdr set.
return mss_now;
}
+EXPORT_SYMBOL(tcp_sync_mss);
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
u32 in_flight, cwnd;
/* Don't be strict about the congestion window for the final FIN. */
- if ((TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN) &&
- tcp_skb_pcount(skb) == 1)
+ if ((TCP_SKB_CB(skb)->flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1)
return 1;
in_flight = tcp_packets_in_flight(tp);
return 0;
}
-/* Intialize TSO state of a skb.
+/* Initialize TSO state of a skb.
* This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
const struct sk_buff *skb,
unsigned mss_now, int nonagle)
{
- return (skb->len < mss_now &&
+ return skb->len < mss_now &&
((nonagle & TCP_NAGLE_CORK) ||
- (!nonagle && tp->packets_out && tcp_minshall_check(tp))));
+ (!nonagle && tp->packets_out && tcp_minshall_check(tp)));
}
/* Return non-zero if the Nagle test allows this packet to be
* Nagle can be ignored during F-RTO too (see RFC4138).
*/
if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
- (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
+ (TCP_SKB_CB(skb)->flags & TCPHDR_FIN))
return 1;
if (!tcp_nagle_check(tp, skb, cur_mss, nonagle))
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = tcp_send_head(sk);
- return (skb &&
+ return skb &&
tcp_snd_test(sk, skb, tcp_current_mss(sk),
(tcp_skb_is_last(sk, skb) ?
- tp->nonagle : TCP_NAGLE_PUSH)));
+ tp->nonagle : TCP_NAGLE_PUSH));
}
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
* packet has never been sent out before (and thus is not cloned).
*/
static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
- unsigned int mss_now)
+ unsigned int mss_now, gfp_t gfp)
{
struct sk_buff *buff;
int nlen = skb->len - len;
if (skb->len != skb->data_len)
return tcp_fragment(sk, skb, len, mss_now);
- buff = sk_stream_alloc_skb(sk, 0, GFP_ATOMIC);
+ buff = sk_stream_alloc_skb(sk, 0, gfp);
if (unlikely(buff == NULL))
return -ENOMEM;
/* PSH and FIN should only be set in the second packet. */
flags = TCP_SKB_CB(skb)->flags;
- TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN | TCPCB_FLAG_PSH);
+ TCP_SKB_CB(skb)->flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH);
TCP_SKB_CB(buff)->flags = flags;
/* This packet was never sent out yet, so no SACK bits. */
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 send_win, cong_win, limit, in_flight;
+ int win_divisor;
- if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
+ if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN)
goto send_now;
if (icsk->icsk_ca_state != TCP_CA_Open)
if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
goto send_now;
- if (sysctl_tcp_tso_win_divisor) {
+ win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor);
+ if (win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
/* If at least some fraction of a window is available,
* just use it.
*/
- chunk /= sysctl_tcp_tso_win_divisor;
+ chunk /= win_divisor;
if (limit >= chunk)
goto send_now;
} else {
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
- TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK;
+ TCP_SKB_CB(nskb)->flags = TCPHDR_ACK;
TCP_SKB_CB(nskb)->sacked = 0;
nskb->csum = 0;
nskb->ip_summed = skb->ip_summed;
sk_wmem_free_skb(sk, skb);
} else {
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
- ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
+ ~(TCPHDR_FIN|TCPHDR_PSH);
if (!skb_shinfo(skb)->nr_frags) {
skb_pull(skb, copy);
if (skb->ip_summed != CHECKSUM_PARTIAL)
cwnd_quota);
if (skb->len > limit &&
- unlikely(tso_fragment(sk, skb, limit, mss_now)))
+ unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
break;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle)
{
- struct sk_buff *skb = tcp_send_head(sk);
-
- if (!skb)
- return;
-
/* If we are closed, the bytes will have to remain here.
* In time closedown will finish, we empty the write queue and
* all will be happy.
if (!sysctl_tcp_retrans_collapse)
return;
- if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)
+ if (TCP_SKB_CB(skb)->flags & TCPHDR_SYN)
return;
tcp_for_write_queue_from_safe(skb, tmp, sk) {
* 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) &&
+ (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) &&
tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) {
if (!pskb_trim(skb, 0)) {
/* Reuse, even though it does some unnecessary work */
if (!tp->retrans_stamp)
tp->retrans_stamp = TCP_SKB_CB(skb)->when;
- tp->undo_retrans++;
+ 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().
int mib_idx;
int fwd_rexmitting = 0;
+ if (!tp->packets_out)
+ return;
+
if (!tp->lost_out)
tp->retransmit_high = tp->snd_una;
mss_now = tcp_current_mss(sk);
if (tcp_send_head(sk) != NULL) {
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_FIN;
TCP_SKB_CB(skb)->end_seq++;
tp->write_seq++;
} else {
skb_reserve(skb, MAX_TCP_HEADER);
/* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */
tcp_init_nondata_skb(skb, tp->write_seq,
- TCPCB_FLAG_ACK | TCPCB_FLAG_FIN);
+ TCPHDR_ACK | TCPHDR_FIN);
tcp_queue_skb(sk, skb);
}
__tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_OFF);
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, MAX_TCP_HEADER);
tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
- TCPCB_FLAG_ACK | TCPCB_FLAG_RST);
+ TCPHDR_ACK | TCPHDR_RST);
/* Send it off. */
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
struct sk_buff *skb;
skb = tcp_write_queue_head(sk);
- if (skb == NULL || !(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)) {
+ if (skb == NULL || !(TCP_SKB_CB(skb)->flags & TCPHDR_SYN)) {
printk(KERN_DEBUG "tcp_send_synack: wrong queue state\n");
return -EFAULT;
}
- if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_ACK)) {
+ if (!(TCP_SKB_CB(skb)->flags & TCPHDR_ACK)) {
if (skb_cloned(skb)) {
struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC);
if (nskb == NULL)
skb = nskb;
}
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ACK;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_ACK;
TCP_ECN_send_synack(tcp_sk(sk), skb);
}
TCP_SKB_CB(skb)->when = tcp_time_stamp;
struct tcp_extend_values *xvp = tcp_xv(rvp);
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
+ const struct tcp_cookie_values *cvp = tp->cookie_values;
struct tcphdr *th;
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
int tcp_header_size;
int mss;
+ int s_data_desired = 0;
- skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
+ if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
+ s_data_desired = cvp->s_data_desired;
+ skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15 + s_data_desired, 1, GFP_ATOMIC);
if (skb == NULL)
return NULL;
skb_dst_set(skb, dst_clone(dst));
- mss = dst_metric(dst, RTAX_ADVMSS);
+ mss = dst_metric_advmss(dst);
if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
mss = tp->rx_opt.user_mss;
__u8 rcv_wscale;
/* Set this up on the first call only */
req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+ req->window_clamp = tcp_full_space(sk);
+
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(tcp_full_space(sk),
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rcv_wnd,
&req->window_clamp,
ireq->wscale_ok,
- &rcv_wscale);
+ &rcv_wscale,
+ dst_metric(dst, RTAX_INITRWND));
ireq->rcv_wscale = rcv_wscale;
}
* not even correctly set)
*/
tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
- TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
+ TCPHDR_SYN | TCPHDR_ACK);
if (OPTION_COOKIE_EXTENSION & opts.options) {
- const struct tcp_cookie_values *cvp = tp->cookie_values;
-
- if (cvp != NULL &&
- cvp->s_data_constant &&
- cvp->s_data_desired > 0) {
- u8 *buf = skb_put(skb, cvp->s_data_desired);
+ if (s_data_desired) {
+ u8 *buf = skb_put(skb, s_data_desired);
/* copy data directly from the listening socket. */
- memcpy(buf, cvp->s_data_payload, cvp->s_data_desired);
- TCP_SKB_CB(skb)->end_seq += cvp->s_data_desired;
+ memcpy(buf, cvp->s_data_payload, s_data_desired);
+ TCP_SKB_CB(skb)->end_seq += s_data_desired;
}
if (opts.hash_size > 0) {
*tail-- ^= TCP_SKB_CB(skb)->seq + 1;
/* recommended */
- *tail-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
sha_transform((__u32 *)&xvp->cookie_bakery[0],
th->window = htons(min(req->rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
return skb;
}
+EXPORT_SYMBOL(tcp_make_synack);
/* Do all connect socket setups that can be done AF independent. */
static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr) +
- (sysctl_tcp_timestamps &&
- (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
- TCPOLEN_TSTAMP_ALIGNED : 0));
+ (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk) != NULL)
if (!tp->window_clamp)
tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
- tp->advmss = dst_metric(dst, RTAX_ADVMSS);
+ tp->advmss = dst_metric_advmss(dst);
if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss)
tp->advmss = tp->rx_opt.user_mss;
tcp_initialize_rcv_mss(sk);
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
+ tp->window_clamp = tcp_full_space(sk);
+
tcp_select_initial_window(tcp_full_space(sk),
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- (sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
- &rcv_wscale);
+ sysctl_tcp_window_scaling,
+ &rcv_wscale,
+ dst_metric(dst, RTAX_INITRWND));
tp->rx_opt.rcv_wscale = rcv_wscale;
tp->rcv_ssthresh = tp->rcv_wnd;
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
+ int err;
tcp_connect_init(sk);
skb_reserve(buff, MAX_TCP_HEADER);
tp->snd_nxt = tp->write_seq;
- tcp_init_nondata_skb(buff, tp->write_seq++, TCPCB_FLAG_SYN);
+ tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
TCP_ECN_send_syn(sk, buff);
/* Send it off. */
sk->sk_wmem_queued += buff->truesize;
sk_mem_charge(sk, buff->truesize);
tp->packets_out += tcp_skb_pcount(buff);
- tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+ err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+ if (err == -ECONNREFUSED)
+ return err;
/* We change tp->snd_nxt after the tcp_transmit_skb() call
* in order to make this packet get counted in tcpOutSegs.
inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
return 0;
}
+EXPORT_SYMBOL(tcp_connect);
/* Send out a delayed ack, the caller does the policy checking
* to see if we should even be here. See tcp_input.c:tcp_ack_snd_check()
/* Reserve space for headers and prepare control bits. */
skb_reserve(buff, MAX_TCP_HEADER);
- tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPCB_FLAG_ACK);
+ tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
/* Send it off, this clears delayed acks for us. */
TCP_SKB_CB(buff)->when = tcp_time_stamp;
* end to send an ack. Don't queue or clone SKB, just
* send it.
*/
- tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPCB_FLAG_ACK);
+ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK);
TCP_SKB_CB(skb)->when = tcp_time_stamp;
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq ||
skb->len > mss) {
seg_size = min(seg_size, mss);
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_PSH;
if (tcp_fragment(sk, skb, seg_size, mss))
return -1;
} else if (!tcp_skb_pcount(skb))
tcp_set_skb_tso_segs(sk, skb, mss);
- TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
+ TCP_SKB_CB(skb)->flags |= TCPHDR_PSH;
TCP_SKB_CB(skb)->when = tcp_time_stamp;
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
if (!err)
TCP_RTO_MAX);
}
}
-
-EXPORT_SYMBOL(tcp_select_initial_window);
-EXPORT_SYMBOL(tcp_connect);
-EXPORT_SYMBOL(tcp_make_synack);
-EXPORT_SYMBOL(tcp_simple_retransmit);
-EXPORT_SYMBOL(tcp_sync_mss);
-EXPORT_SYMBOL(tcp_mtup_init);
Code Review / linux-2.6.git / blobdiff