*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
/* People can turn this off for buggy TCP's found in printers etc. */
int sysctl_tcp_retrans_collapse __read_mostly = 1;
-/* People can turn this on to work with those rare, broken TCPs that
+/* People can turn this on to work with those rare, broken TCPs that
* interpret the window field as a signed quantity.
*/
int sysctl_tcp_workaround_signed_windows __read_mostly = 0;
TCP_SKB_CB(skb)->end_seq = seq;
}
-static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
- __u32 tstamp, __u8 **md5_hash)
+static inline int tcp_urg_mode(const struct tcp_sock *tp)
{
- if (tp->rx_opt.tstamp_ok) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
- *ptr++ = htonl(tstamp);
- *ptr++ = htonl(tp->rx_opt.ts_recent);
- }
- if (tp->rx_opt.eff_sacks) {
- struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
- int this_sack;
-
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (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++) {
- *ptr++ = htonl(sp[this_sack].start_seq);
- *ptr++ = htonl(sp[this_sack].end_seq);
- }
+ return tp->snd_una != tp->snd_up;
+}
- if (tp->rx_opt.dsack) {
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks--;
- }
- }
-#ifdef CONFIG_TCP_MD5SIG
- if (md5_hash) {
+#define OPTION_SACK_ADVERTISE (1 << 0)
+#define OPTION_TS (1 << 1)
+#define OPTION_MD5 (1 << 2)
+
+struct tcp_out_options {
+ u8 options; /* bit field of OPTION_* */
+ u8 ws; /* window scale, 0 to disable */
+ u8 num_sack_blocks; /* number of SACK blocks to include */
+ u16 mss; /* 0 to disable */
+ __u32 tsval, tsecr; /* need to include OPTION_TS */
+};
+
+/* Beware: Something in the Internet is very sensitive to the ordering of
+ * TCP options, we learned this through the hard way, so be careful here.
+ * Luckily we can at least blame others for their non-compliance but from
+ * inter-operatibility perspective it seems that we're somewhat stuck with
+ * the ordering which we have been using if we want to keep working with
+ * those broken things (not that it currently hurts anybody as there isn't
+ * particular reason why the ordering would need to be changed).
+ *
+ * At least SACK_PERM as the first option is known to lead to a disaster
+ * (but it may well be that other scenarios fail similarly).
+ */
+static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
+ const struct tcp_out_options *opts,
+ __u8 **md5_hash) {
+ if (unlikely(OPTION_MD5 & opts->options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
*md5_hash = (__u8 *)ptr;
+ ptr += 4;
+ } else {
+ *md5_hash = NULL;
}
-#endif
-}
-/* Construct a tcp options header for a SYN or SYN_ACK packet.
- * If this is every changed make sure to change the definition of
- * MAX_SYN_SIZE to match the new maximum number of options that you
- * can generate.
- *
- * Note - that with the RFC2385 TCP option, we make room for the
- * 16 byte MD5 hash. This will be filled in later, so the pointer for the
- * location to be filled is passed back up.
- */
-static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack,
- int offer_wscale, int wscale, __u32 tstamp,
- __u32 ts_recent, __u8 **md5_hash)
-{
- /* We always get an MSS option.
- * The option bytes which will be seen in normal data
- * packets should timestamps be used, must be in the MSS
- * advertised. But we subtract them from tp->mss_cache so
- * that calculations in tcp_sendmsg are simpler etc.
- * So account for this fact here if necessary. If we
- * don't do this correctly, as a receiver we won't
- * recognize data packets as being full sized when we
- * should, and thus we won't abide by the delayed ACK
- * rules correctly.
- * SACKs don't matter, we never delay an ACK when we
- * have any of those going out.
- */
- *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
- if (ts) {
- if (sack)
+ if (unlikely(opts->mss)) {
+ *ptr++ = htonl((TCPOPT_MSS << 24) |
+ (TCPOLEN_MSS << 16) |
+ opts->mss);
+ }
+
+ if (likely(OPTION_TS & opts->options)) {
+ if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
- else
+ } else {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
- *ptr++ = htonl(tstamp); /* TSVAL */
- *ptr++ = htonl(ts_recent); /* TSECR */
- } else if (sack)
+ }
+ *ptr++ = htonl(opts->tsval);
+ *ptr++ = htonl(opts->tsecr);
+ }
+
+ if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
+ !(OPTION_TS & opts->options))) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
- if (offer_wscale)
+ }
+
+ if (unlikely(opts->ws)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
- (wscale));
+ opts->ws);
+ }
+
+ if (unlikely(opts->num_sack_blocks)) {
+ struct tcp_sack_block *sp = tp->rx_opt.dsack ?
+ tp->duplicate_sack : tp->selective_acks;
+ int this_sack;
+
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_SACK << 8) |
+ (TCPOLEN_SACK_BASE + (opts->num_sack_blocks *
+ TCPOLEN_SACK_PERBLOCK)));
+
+ for (this_sack = 0; this_sack < opts->num_sack_blocks;
+ ++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 = tp->rx_opt.num_sacks;
+ }
+ }
+}
+
+static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
+ struct tcp_out_options *opts,
+ struct tcp_md5sig_key **md5) {
+ struct tcp_sock *tp = tcp_sk(sk);
+ unsigned size = 0;
+
#ifdef CONFIG_TCP_MD5SIG
- /*
- * If MD5 is enabled, then we set the option, and include the size
- * (always 18). The actual MD5 hash is added just before the
- * packet is sent.
- */
- if (md5_hash) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- *md5_hash = (__u8 *)ptr;
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ size += TCPOLEN_MD5SIG_ALIGNED;
}
+#else
+ *md5 = NULL;
#endif
+
+ /* We always get an MSS option. The option bytes which will be seen in
+ * normal data packets should timestamps be used, must be in the MSS
+ * advertised. But we subtract them from tp->mss_cache so that
+ * calculations in tcp_sendmsg are simpler etc. So account for this
+ * fact here if necessary. If we don't do this correctly, as a
+ * receiver we won't recognize data packets as being full sized when we
+ * should, and thus we won't abide by the delayed ACK rules correctly.
+ * SACKs don't matter, we never delay an ACK when we have any of those
+ * going out. */
+ opts->mss = tcp_advertise_mss(sk);
+ size += TCPOLEN_MSS_ALIGNED;
+
+ 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;
+ size += TCPOLEN_TSTAMP_ALIGNED;
+ }
+ if (likely(sysctl_tcp_window_scaling)) {
+ opts->ws = tp->rx_opt.rcv_wscale;
+ if (likely(opts->ws))
+ size += TCPOLEN_WSCALE_ALIGNED;
+ }
+ if (likely(sysctl_tcp_sack)) {
+ opts->options |= OPTION_SACK_ADVERTISE;
+ if (unlikely(!(OPTION_TS & opts->options)))
+ size += TCPOLEN_SACKPERM_ALIGNED;
+ }
+
+ return size;
+}
+
+static unsigned tcp_synack_options(struct sock *sk,
+ struct request_sock *req,
+ unsigned mss, struct sk_buff *skb,
+ struct tcp_out_options *opts,
+ struct tcp_md5sig_key **md5) {
+ unsigned size = 0;
+ struct inet_request_sock *ireq = inet_rsk(req);
+ char doing_ts;
+
+#ifdef CONFIG_TCP_MD5SIG
+ *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
+ if (*md5) {
+ opts->options |= OPTION_MD5;
+ size += TCPOLEN_MD5SIG_ALIGNED;
+ }
+#else
+ *md5 = NULL;
+#endif
+
+ /* we can't fit any SACK blocks in a packet with MD5 + TS
+ options. There was discussion about disabling SACK rather than TS in
+ order to fit in better with old, buggy kernels, but that was deemed
+ to be unnecessary. */
+ doing_ts = ireq->tstamp_ok && !(*md5 && ireq->sack_ok);
+
+ opts->mss = mss;
+ size += TCPOLEN_MSS_ALIGNED;
+
+ if (likely(ireq->wscale_ok)) {
+ opts->ws = ireq->rcv_wscale;
+ if (likely(opts->ws))
+ size += TCPOLEN_WSCALE_ALIGNED;
+ }
+ if (likely(doing_ts)) {
+ opts->options |= OPTION_TS;
+ opts->tsval = TCP_SKB_CB(skb)->when;
+ opts->tsecr = req->ts_recent;
+ size += TCPOLEN_TSTAMP_ALIGNED;
+ }
+ if (likely(ireq->sack_ok)) {
+ opts->options |= OPTION_SACK_ADVERTISE;
+ if (unlikely(!doing_ts))
+ size += TCPOLEN_SACKPERM_ALIGNED;
+ }
+
+ return size;
+}
+
+static unsigned tcp_established_options(struct sock *sk, struct sk_buff *skb,
+ struct tcp_out_options *opts,
+ struct tcp_md5sig_key **md5) {
+ struct tcp_skb_cb *tcb = skb ? TCP_SKB_CB(skb) : NULL;
+ struct tcp_sock *tp = tcp_sk(sk);
+ unsigned size = 0;
+
+#ifdef CONFIG_TCP_MD5SIG
+ *md5 = tp->af_specific->md5_lookup(sk, sk);
+ if (unlikely(*md5)) {
+ opts->options |= OPTION_MD5;
+ size += TCPOLEN_MD5SIG_ALIGNED;
+ }
+#else
+ *md5 = NULL;
+#endif
+
+ if (likely(tp->rx_opt.tstamp_ok)) {
+ opts->options |= OPTION_TS;
+ opts->tsval = tcb ? tcb->when : 0;
+ opts->tsecr = tp->rx_opt.ts_recent;
+ size += TCPOLEN_TSTAMP_ALIGNED;
+ }
+
+ if (unlikely(tp->rx_opt.eff_sacks)) {
+ const unsigned remaining = MAX_TCP_OPTION_SPACE - size;
+ opts->num_sack_blocks =
+ min_t(unsigned, tp->rx_opt.eff_sacks,
+ (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
+ TCPOLEN_SACK_PERBLOCK);
+ size += TCPOLEN_SACK_BASE_ALIGNED +
+ opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+ }
+
+ return size;
}
/* This routine actually transmits TCP packets queued in by
struct inet_sock *inet;
struct tcp_sock *tp;
struct tcp_skb_cb *tcb;
- int tcp_header_size;
-#ifdef CONFIG_TCP_MD5SIG
+ struct tcp_out_options opts;
+ unsigned tcp_options_size, tcp_header_size;
struct tcp_md5sig_key *md5;
__u8 *md5_hash_location;
-#endif
struct tcphdr *th;
- int sysctl_flags;
int err;
BUG_ON(!skb || !tcp_skb_pcount(skb));
inet = inet_sk(sk);
tp = tcp_sk(sk);
tcb = TCP_SKB_CB(skb);
- tcp_header_size = tp->tcp_header_len;
+ memset(&opts, 0, sizeof(opts));
-#define SYSCTL_FLAG_TSTAMPS 0x1
-#define SYSCTL_FLAG_WSCALE 0x2
-#define SYSCTL_FLAG_SACK 0x4
-
- sysctl_flags = 0;
- if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
- tcp_header_size = sizeof(struct tcphdr) + TCPOLEN_MSS;
- if (sysctl_tcp_timestamps) {
- tcp_header_size += TCPOLEN_TSTAMP_ALIGNED;
- sysctl_flags |= SYSCTL_FLAG_TSTAMPS;
- }
- if (sysctl_tcp_window_scaling) {
- tcp_header_size += TCPOLEN_WSCALE_ALIGNED;
- sysctl_flags |= SYSCTL_FLAG_WSCALE;
- }
- if (sysctl_tcp_sack) {
- sysctl_flags |= SYSCTL_FLAG_SACK;
- if (!(sysctl_flags & SYSCTL_FLAG_TSTAMPS))
- tcp_header_size += TCPOLEN_SACKPERM_ALIGNED;
- }
- } else if (unlikely(tp->rx_opt.eff_sacks)) {
- /* A SACK is 2 pad bytes, a 2 byte header, plus
- * 2 32-bit sequence numbers for each SACK block.
- */
- tcp_header_size += (TCPOLEN_SACK_BASE_ALIGNED +
- (tp->rx_opt.eff_sacks *
- TCPOLEN_SACK_PERBLOCK));
- }
+ if (unlikely(tcb->flags & TCPCB_FLAG_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)
tcp_ca_event(sk, CA_EVENT_TX_START);
-#ifdef CONFIG_TCP_MD5SIG
- /*
- * Are we doing MD5 on this segment? If so - make
- * room for it.
- */
- md5 = tp->af_specific->md5_lookup(sk, sk);
- if (md5)
- tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
-#endif
-
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
skb_set_owner_w(skb, sk);
th->check = 0;
th->urg_ptr = 0;
- if (unlikely(tp->urg_mode &&
+ /* The urg_mode check is necessary during a below snd_una win probe */
+ if (unlikely(tcp_urg_mode(tp) &&
between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
}
- if (unlikely(tcb->flags & TCPCB_FLAG_SYN)) {
- tcp_syn_build_options((__be32 *)(th + 1),
- tcp_advertise_mss(sk),
- (sysctl_flags & SYSCTL_FLAG_TSTAMPS),
- (sysctl_flags & SYSCTL_FLAG_SACK),
- (sysctl_flags & SYSCTL_FLAG_WSCALE),
- tp->rx_opt.rcv_wscale,
- tcb->when,
- tp->rx_opt.ts_recent,
-
-#ifdef CONFIG_TCP_MD5SIG
- md5 ? &md5_hash_location :
-#endif
- NULL);
- } else {
- tcp_build_and_update_options((__be32 *)(th + 1),
- tp, tcb->when,
-#ifdef CONFIG_TCP_MD5SIG
- md5 ? &md5_hash_location :
-#endif
- NULL);
+ tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+ if (likely((tcb->flags & TCPCB_FLAG_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;
tp->af_specific->calc_md5_hash(md5_hash_location,
- md5,
- sk, NULL, NULL,
- tcp_hdr(skb),
- sk->sk_protocol,
- skb->len);
+ md5, sk, NULL, skb);
}
#endif
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
- TCP_INC_STATS(TCP_MIB_OUTSEGS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
err = icsk->icsk_af_ops->queue_xmit(skb, 0);
if (likely(err <= 0))
tcp_enter_cwr(sk, 1);
return net_xmit_eval(err);
-
-#undef SYSCTL_FLAG_TSTAMPS
-#undef SYSCTL_FLAG_WSCALE
-#undef SYSCTL_FLAG_SACK
}
/* This routine just queue's the buffer
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
- *
- * LARGESEND note: !urg_mode is overkill, only frames up to snd_up
- * cannot be large. However, taking into account rare use of URG, this
- * is not a big flaw.
*/
unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
{
u32 mss_now;
u16 xmit_size_goal;
int doing_tso = 0;
+ unsigned header_len;
+ struct tcp_out_options opts;
+ struct tcp_md5sig_key *md5;
mss_now = tp->mss_cache;
- if (large_allowed && sk_can_gso(sk) && !tp->urg_mode)
+ if (large_allowed && sk_can_gso(sk))
doing_tso = 1;
if (dst) {
mss_now = tcp_sync_mss(sk, mtu);
}
- if (tp->rx_opt.eff_sacks)
- mss_now -= (TCPOLEN_SACK_BASE_ALIGNED +
- (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK));
-
-#ifdef CONFIG_TCP_MD5SIG
- if (tp->af_specific->md5_lookup(sk, sk))
- mss_now -= TCPOLEN_MD5SIG_ALIGNED;
-#endif
+ header_len = tcp_established_options(sk, NULL, &opts, &md5) +
+ sizeof(struct tcphdr);
+ /* The mss_cache is sized based on tp->tcp_header_len, which assumes
+ * some common options. If this is an odd packet (because we have SACK
+ * blocks etc) then our calculated header_len will be different, and
+ * we have to adjust mss_now correspondingly */
+ if (header_len != tp->tcp_header_len) {
+ int delta = (int) header_len - tp->tcp_header_len;
+ mss_now -= delta;
+ }
xmit_size_goal = mss_now;
static inline int tcp_minshall_check(const struct tcp_sock *tp)
{
- return after(tp->snd_sml,tp->snd_una) &&
+ return after(tp->snd_sml, tp->snd_una) &&
!after(tp->snd_sml, tp->snd_nxt);
}
/* 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) ||
+ if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
return 1;
/* Defer for less than two clock ticks. */
if (tp->tso_deferred &&
- ((jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
+ (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
goto send_now;
in_flight = tcp_packets_in_flight(tp);
* send_head. This happens as incoming acks open up the remote
* window for us.
*
+ * LARGESEND note: !tcp_urg_mode is overkill, only frames between
+ * snd_up-64k-mss .. snd_up cannot be large. However, taking into
+ * account rare use of URG, this is not a big flaw.
+ *
* Returns 1, if no segments are in flight and we have queued segments, but
* cannot send anything now because of SWS or another problem.
*/
-static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
+static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
+ int push_one, gfp_t gfp)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
int cwnd_quota;
int result;
- /* 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 (unlikely(sk->sk_state == TCP_CLOSE))
- return 0;
-
sent_pkts = 0;
- /* Do MTU probing. */
- if ((result = tcp_mtu_probe(sk)) == 0) {
- return 0;
- } else if (result > 0) {
- sent_pkts = 1;
+ if (!push_one) {
+ /* Do MTU probing. */
+ result = tcp_mtu_probe(sk);
+ if (!result) {
+ return 0;
+ } else if (result > 0) {
+ sent_pkts = 1;
+ }
}
while ((skb = tcp_send_head(sk))) {
nonagle : TCP_NAGLE_PUSH))))
break;
} else {
- if (tcp_tso_should_defer(sk, skb))
+ if (!push_one && tcp_tso_should_defer(sk, skb))
break;
}
limit = mss_now;
- if (tso_segs > 1)
+ if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
cwnd_quota);
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC)))
+ if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
/* Advance the send_head. This one is sent out.
tcp_minshall_update(tp, mss_now, skb);
sent_pkts++;
+
+ if (push_one)
+ break;
}
if (likely(sent_pkts)) {
{
struct sk_buff *skb = tcp_send_head(sk);
- if (skb) {
- if (tcp_write_xmit(sk, cur_mss, nonagle))
- tcp_check_probe_timer(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 (unlikely(sk->sk_state == TCP_CLOSE))
+ return;
+
+ if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC))
+ tcp_check_probe_timer(sk);
}
/* Send _single_ skb sitting at the send head. This function requires
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
struct sk_buff *skb = tcp_send_head(sk);
- unsigned int tso_segs, cwnd_quota;
BUG_ON(!skb || skb->len < mss_now);
- tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
- cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);
-
- if (likely(cwnd_quota)) {
- unsigned int limit;
-
- BUG_ON(!tso_segs);
-
- limit = mss_now;
- if (tso_segs > 1)
- limit = tcp_mss_split_point(sk, skb, mss_now,
- cwnd_quota);
-
- if (skb->len > limit &&
- unlikely(tso_fragment(sk, skb, limit, mss_now)))
- return;
-
- /* Send it out now. */
- TCP_SKB_CB(skb)->when = tcp_time_stamp;
-
- if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
- tcp_event_new_data_sent(sk, skb);
- tcp_cwnd_validate(sk);
- return;
- }
- }
+ tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation);
}
/* This function returns the amount that we can raise the
return window;
}
-/* Attempt to collapse two adjacent SKB's during retransmission. */
-static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb,
- int mss_now)
+/* Collapses two adjacent SKB's during retransmission. */
+static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);
int skb_size, next_skb_size;
u16 flags;
- /* The first test we must make is that neither of these two
- * SKB's are still referenced by someone else.
- */
- if (skb_cloned(skb) || skb_cloned(next_skb))
- return;
-
skb_size = skb->len;
next_skb_size = next_skb->len;
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)
- return;
-
- /* Next skb is out of window. */
- if (after(TCP_SKB_CB(next_skb)->end_seq, tcp_wnd_end(tp)))
- return;
-
- /* Punt if not enough space exists in the first SKB for
- * the data in the second, or the total combined payload
- * would exceed the MSS.
- */
- if ((next_skb_size > skb_tailroom(skb)) ||
- ((skb_size + next_skb_size) > mss_now))
- return;
-
BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
tcp_highest_sack_combine(sk, next_skb, skb);
- /* Ok. We will be able to collapse the packet. */
tcp_unlink_write_queue(next_skb, sk);
skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size),
/* changed transmit queue under us so clear hints */
tcp_clear_retrans_hints_partial(tp);
+ if (next_skb == tp->retransmit_skb_hint)
+ tp->retransmit_skb_hint = skb;
sk_wmem_free_skb(sk, next_skb);
}
-/* Do a simple retransmit without using the backoff mechanisms in
- * tcp_timer. This is used for path mtu discovery.
- * The socket is already locked here.
- */
-void tcp_simple_retransmit(struct sock *sk)
+static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb)
+{
+ if (tcp_skb_pcount(skb) > 1)
+ return 0;
+ /* TODO: SACK collapsing could be used to remove this condition */
+ if (skb_shinfo(skb)->nr_frags != 0)
+ return 0;
+ if (skb_cloned(skb))
+ return 0;
+ if (skb == tcp_send_head(sk))
+ return 0;
+ /* Some heurestics for collapsing over SACK'd could be invented */
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+ return 0;
+
+ return 1;
+}
+
+static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
+ int space)
{
- const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
- unsigned int mss = tcp_current_mss(sk, 0);
- int lost = 0;
+ struct sk_buff *skb = to, *tmp;
+ int first = 1;
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
+ if (!sysctl_tcp_retrans_collapse)
+ return;
+ if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN)
+ return;
+
+ tcp_for_write_queue_from_safe(skb, tmp, sk) {
+ if (!tcp_can_collapse(sk, skb))
break;
- if (skb->len > mss &&
- !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
- tp->retrans_out -= tcp_skb_pcount(skb);
- }
- if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST)) {
- TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
- tp->lost_out += tcp_skb_pcount(skb);
- lost = 1;
- }
- }
- }
- tcp_clear_all_retrans_hints(tp);
+ space -= skb->len;
- if (!lost)
- return;
+ if (first) {
+ first = 0;
+ continue;
+ }
- if (tcp_is_reno(tp))
- tcp_limit_reno_sacked(tp);
+ if (space < 0)
+ break;
+ /* Punt if not enough space exists in the first SKB for
+ * the data in the second
+ */
+ if (skb->len > skb_tailroom(to))
+ break;
- tcp_verify_left_out(tp);
+ if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))
+ break;
- /* Don't muck with the congestion window here.
- * Reason is that we do not increase amount of _data_
- * in network, but units changed and effective
- * cwnd/ssthresh really reduced now.
- */
- if (icsk->icsk_ca_state != TCP_CA_Loss) {
- tp->high_seq = tp->snd_nxt;
- tp->snd_ssthresh = tcp_current_ssthresh(sk);
- tp->prior_ssthresh = 0;
- tp->undo_marker = 0;
- tcp_set_ca_state(sk, TCP_CA_Loss);
+ tcp_collapse_retrans(sk, to);
}
- tcp_xmit_retransmit_queue(sk);
}
/* This retransmits one SKB. Policy decisions and retransmit queue
return -ENOMEM; /* We'll try again later. */
}
- /* 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))
- tcp_retrans_try_collapse(sk, skb, cur_mss);
+ tcp_retrans_try_collapse(sk, skb, cur_mss);
/* Some Solaris stacks overoptimize and ignore the FIN on a
* retransmit when old data is attached. So strip it off
if (err == 0) {
/* Update global TCP statistics. */
- TCP_INC_STATS(TCP_MIB_RETRANSSEGS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
tp->total_retrans++;
return err;
}
-/* This gets called after a retransmit timeout, and the initially
- * retransmitted data is acknowledged. It tries to continue
- * resending the rest of the retransmit queue, until either
- * we've sent it all or the congestion window limit is reached.
- * If doing SACK, the first ACK which comes back for a timeout
- * based retransmit packet might feed us FACK information again.
- * If so, we use it to avoid unnecessarily retransmissions.
- */
-void tcp_xmit_retransmit_queue(struct sock *sk)
+static int tcp_can_forward_retransmit(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
- int packet_cnt;
-
- if (tp->retransmit_skb_hint) {
- skb = tp->retransmit_skb_hint;
- packet_cnt = tp->retransmit_cnt_hint;
- } else {
- skb = tcp_write_queue_head(sk);
- packet_cnt = 0;
- }
-
- /* First pass: retransmit lost packets. */
- if (tp->lost_out) {
- tcp_for_write_queue_from(skb, sk) {
- __u8 sacked = TCP_SKB_CB(skb)->sacked;
-
- if (skb == tcp_send_head(sk))
- break;
- /* we could do better than to assign each time */
- tp->retransmit_skb_hint = skb;
- tp->retransmit_cnt_hint = packet_cnt;
-
- /* Assume this retransmit will generate
- * only one packet for congestion window
- * calculation purposes. This works because
- * tcp_retransmit_skb() will chop up the
- * packet to be MSS sized and all the
- * packet counting works out.
- */
- if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
- return;
-
- if (sacked & TCPCB_LOST) {
- if (!(sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) {
- if (tcp_retransmit_skb(sk, skb)) {
- tp->retransmit_skb_hint = NULL;
- return;
- }
- if (icsk->icsk_ca_state != TCP_CA_Loss)
- NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS);
- else
- NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS);
-
- if (skb == tcp_write_queue_head(sk))
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- inet_csk(sk)->icsk_rto,
- TCP_RTO_MAX);
- }
-
- packet_cnt += tcp_skb_pcount(skb);
- if (packet_cnt >= tp->lost_out)
- break;
- }
- }
- }
-
- /* OK, demanded retransmission is finished. */
/* Forward retransmissions are possible only during Recovery. */
if (icsk->icsk_ca_state != TCP_CA_Recovery)
- return;
+ return 0;
/* No forward retransmissions in Reno are possible. */
if (tcp_is_reno(tp))
- return;
+ return 0;
/* Yeah, we have to make difficult choice between forward transmission
* and retransmission... Both ways have their merits...
*/
if (tcp_may_send_now(sk))
- return;
+ return 0;
- /* If nothing is SACKed, highest_sack in the loop won't be valid */
- if (!tp->sacked_out)
- return;
+ return 1;
+}
- if (tp->forward_skb_hint)
- skb = tp->forward_skb_hint;
- else
+/* This gets called after a retransmit timeout, and the initially
+ * retransmitted data is acknowledged. It tries to continue
+ * resending the rest of the retransmit queue, until either
+ * we've sent it all or the congestion window limit is reached.
+ * If doing SACK, the first ACK which comes back for a timeout
+ * based retransmit packet might feed us FACK information again.
+ * If so, we use it to avoid unnecessarily retransmissions.
+ */
+void tcp_xmit_retransmit_queue(struct sock *sk)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+ struct sk_buff *hole = NULL;
+ u32 last_lost;
+ int mib_idx;
+ int fwd_rexmitting = 0;
+
+ if (!tp->lost_out)
+ tp->retransmit_high = tp->snd_una;
+
+ if (tp->retransmit_skb_hint) {
+ skb = tp->retransmit_skb_hint;
+ last_lost = TCP_SKB_CB(skb)->end_seq;
+ if (after(last_lost, tp->retransmit_high))
+ last_lost = tp->retransmit_high;
+ } else {
skb = tcp_write_queue_head(sk);
+ last_lost = tp->snd_una;
+ }
tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- tp->forward_skb_hint = skb;
+ __u8 sacked = TCP_SKB_CB(skb)->sacked;
- if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
+ if (skb == tcp_send_head(sk))
break;
+ /* we could do better than to assign each time */
+ if (hole == NULL)
+ tp->retransmit_skb_hint = skb;
+ /* Assume this retransmit will generate
+ * only one packet for congestion window
+ * calculation purposes. This works because
+ * tcp_retransmit_skb() will chop up the
+ * packet to be MSS sized and all the
+ * packet counting works out.
+ */
if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
- break;
+ return;
+
+ if (fwd_rexmitting) {
+begin_fwd:
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
+ break;
+ mib_idx = LINUX_MIB_TCPFORWARDRETRANS;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS)
+ } else if (!before(TCP_SKB_CB(skb)->seq, tp->retransmit_high)) {
+ tp->retransmit_high = last_lost;
+ if (!tcp_can_forward_retransmit(sk))
+ break;
+ /* Backtrack if necessary to non-L'ed skb */
+ if (hole != NULL) {
+ skb = hole;
+ hole = NULL;
+ }
+ fwd_rexmitting = 1;
+ goto begin_fwd;
+
+ } else if (!(sacked & TCPCB_LOST)) {
+ if (hole == NULL && !(sacked & TCPCB_SACKED_RETRANS))
+ hole = skb;
continue;
- /* Ok, retransmit it. */
- if (tcp_retransmit_skb(sk, skb)) {
- tp->forward_skb_hint = NULL;
- break;
+ } else {
+ last_lost = TCP_SKB_CB(skb)->end_seq;
+ if (icsk->icsk_ca_state != TCP_CA_Loss)
+ mib_idx = LINUX_MIB_TCPFASTRETRANS;
+ else
+ mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS;
}
+ if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))
+ continue;
+
+ if (tcp_retransmit_skb(sk, skb))
+ return;
+ NET_INC_STATS_BH(sock_net(sk), mib_idx);
+
if (skb == tcp_write_queue_head(sk))
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto,
TCP_RTO_MAX);
-
- NET_INC_STATS_BH(LINUX_MIB_TCPFORWARDRETRANS);
}
}
/* NOTE: No TCP options attached and we never retransmit this. */
skb = alloc_skb(MAX_TCP_HEADER, priority);
if (!skb) {
- NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
return;
}
/* Send it off. */
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (tcp_transmit_skb(sk, skb, 0, priority))
- NET_INC_STATS(LINUX_MIB_TCPABORTFAILED);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
+
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
/* WARNING: This routine must only be called when we have already sent
struct tcp_sock *tp = tcp_sk(sk);
struct tcphdr *th;
int tcp_header_size;
+ struct tcp_out_options opts;
struct sk_buff *skb;
-#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *md5;
__u8 *md5_hash_location;
-#endif
+ int mss;
skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
if (skb == NULL)
skb->dst = dst_clone(dst);
- tcp_header_size = (sizeof(struct tcphdr) + TCPOLEN_MSS +
- (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0) +
- (ireq->wscale_ok ? TCPOLEN_WSCALE_ALIGNED : 0) +
- /* SACK_PERM is in the place of NOP NOP of TS */
- ((ireq->sack_ok && !ireq->tstamp_ok) ? TCPOLEN_SACKPERM_ALIGNED : 0));
-
-#ifdef CONFIG_TCP_MD5SIG
- /* Are we doing MD5 on this segment? If so - make room for it */
- md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
- if (md5)
- tcp_header_size += TCPOLEN_MD5SIG_ALIGNED;
-#endif
- skb_push(skb, tcp_header_size);
- skb_reset_transport_header(skb);
+ mss = dst_metric(dst, RTAX_ADVMSS);
+ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+ mss = tp->rx_opt.user_mss;
- th = tcp_hdr(skb);
- memset(th, 0, sizeof(struct tcphdr));
- th->syn = 1;
- th->ack = 1;
- TCP_ECN_make_synack(req, th);
- th->source = inet_sk(sk)->sport;
- th->dest = ireq->rmt_port;
- /* Setting of flags are superfluous here for callers (and ECE is
- * not even correctly set)
- */
- tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
- TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
- th->seq = htonl(TCP_SKB_CB(skb)->seq);
- th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
__u8 rcv_wscale;
/* Set this up on the first call only */
req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(tcp_full_space(sk),
- dst_metric(dst, RTAX_ADVMSS) - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
+ mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
&req->rcv_wnd,
&req->window_clamp,
ireq->wscale_ok,
ireq->rcv_wscale = rcv_wscale;
}
- /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
- th->window = htons(min(req->rcv_wnd, 65535U));
+ memset(&opts, 0, sizeof(opts));
#ifdef CONFIG_SYN_COOKIES
if (unlikely(req->cookie_ts))
TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
else
#endif
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_syn_build_options((__be32 *)(th + 1), dst_metric(dst, RTAX_ADVMSS), ireq->tstamp_ok,
- ireq->sack_ok, ireq->wscale_ok, ireq->rcv_wscale,
- TCP_SKB_CB(skb)->when,
- req->ts_recent,
- (
-#ifdef CONFIG_TCP_MD5SIG
- md5 ? &md5_hash_location :
-#endif
- NULL)
- );
+ tcp_header_size = tcp_synack_options(sk, req, mss,
+ skb, &opts, &md5) +
+ sizeof(struct tcphdr);
+ 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;
+ TCP_ECN_make_synack(req, th);
+ th->source = ireq->loc_port;
+ th->dest = ireq->rmt_port;
+ /* Setting of flags are superfluous here for callers (and ECE is
+ * not even correctly set)
+ */
+ tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
+ TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
+ th->seq = htonl(TCP_SKB_CB(skb)->seq);
+ th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
+
+ /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
+ th->window = htons(min(req->rcv_wnd, 65535U));
+ tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
th->doff = (tcp_header_size >> 2);
- TCP_INC_STATS(TCP_MIB_OUTSEGS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5) {
tp->af_specific->calc_md5_hash(md5_hash_location,
- md5,
- NULL, dst, req,
- tcp_hdr(skb), sk->sk_protocol,
- skb->len);
+ md5, NULL, req, skb);
}
#endif
if (!tp->window_clamp)
tp->window_clamp = dst_metric(dst, RTAX_WINDOW);
tp->advmss = dst_metric(dst, RTAX_ADVMSS);
+ 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);
tcp_select_initial_window(tcp_full_space(sk),
tcp_init_wl(tp, tp->write_seq, 0);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
+ tp->snd_up = tp->write_seq;
tp->rcv_nxt = 0;
tp->rcv_wup = 0;
tp->copied_seq = 0;
*/
tp->snd_nxt = tp->write_seq;
tp->pushed_seq = tp->write_seq;
- TCP_INC_STATS(TCP_MIB_ACTIVEOPENS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
tcp_event_new_data_sent(sk, skb);
return err;
} else {
- if (tp->urg_mode &&
- between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
+ if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
tcp_xmit_probe_skb(sk, 1);
return tcp_xmit_probe_skb(sk, 0);
}