/* 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;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+/* Account for new data that has been sent to the network. */
static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->snd_cwnd_used = 0;
}
+/* Congestion state accounting after a packet has been sent. */
static void tcp_event_data_sent(struct tcp_sock *tp,
struct sk_buff *skb, struct sock *sk)
{
icsk->icsk_ack.pingpong = 1;
}
+/* Account for an ACK we sent. */
static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
{
tcp_dec_quickack_mode(sk, pkts);
return new_win;
}
+/* 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 &= ~TCPCB_FLAG_ECE;
}
+/* Packet ECN state for a SYN. */
static inline void TCP_ECN_send_syn(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
tp->ecn_flags = 0;
- if (sysctl_tcp_ecn) {
+ if (sysctl_tcp_ecn == 1) {
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_ECE | TCPCB_FLAG_CWR;
tp->ecn_flags = TCP_ECN_OK;
}
th->ece = 1;
}
+/* Set up ECN state for a packet on a ESTABLISHED socket that is about to
+ * be sent.
+ */
static inline void TCP_ECN_send(struct sock *sk, struct sk_buff *skb,
int tcp_header_len)
{
TCP_SKB_CB(skb)->end_seq = seq;
}
+static inline int tcp_urg_mode(const struct tcp_sock *tp)
+{
+ return tp->snd_una != tp->snd_up;
+}
+
#define OPTION_SACK_ADVERTISE (1 << 0)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
+#define OPTION_WSCALE (1 << 3)
struct tcp_out_options {
u8 options; /* bit field of OPTION_* */
__u32 tsval, tsecr; /* need to include OPTION_TS */
};
+/* Write previously computed TCP options to the packet.
+ *
+ * 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) {
*md5_hash = NULL;
}
+ 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) |
*ptr++ = htonl(opts->tsecr);
}
- if (unlikely(opts->mss)) {
- *ptr++ = htonl((TCPOPT_MSS << 24) |
- (TCPOLEN_MSS << 16) |
- opts->mss);
- }
-
if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
!(OPTION_TS & opts->options))) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
TCPOLEN_SACK_PERM);
}
- if (unlikely(opts->ws)) {
+ if (unlikely(OPTION_WSCALE & opts->options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
*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.dsack = 0;
}
}
+/* Compute TCP options for SYN packets. This is not the final
+ * network wire format yet.
+ */
static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5) {
}
if (likely(sysctl_tcp_window_scaling)) {
opts->ws = tp->rx_opt.rcv_wscale;
+ opts->options |= OPTION_WSCALE;
size += TCPOLEN_WSCALE_ALIGNED;
}
if (likely(sysctl_tcp_sack)) {
return size;
}
+/* Set up TCP options for SYN-ACKs. */
static unsigned tcp_synack_options(struct sock *sk,
struct request_sock *req,
unsigned mss, struct sk_buff *skb,
if (likely(ireq->wscale_ok)) {
opts->ws = ireq->rcv_wscale;
+ opts->options |= OPTION_WSCALE;
size += TCPOLEN_WSCALE_ALIGNED;
}
if (likely(doing_ts)) {
return size;
}
+/* Compute TCP options for ESTABLISHED sockets. This is not the
+ * final wire format yet.
+ */
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;
+ unsigned int eff_sacks;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
size += TCPOLEN_TSTAMP_ALIGNED;
}
- if (unlikely(tp->rx_opt.eff_sacks)) {
+ eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
+ if (unlikely(eff_sacks)) {
const unsigned remaining = MAX_TCP_OPTION_SPACE - size;
opts->num_sack_blocks =
- min_t(unsigned, tp->rx_opt.eff_sacks,
+ min_t(unsigned, eff_sacks,
(remaining - TCPOLEN_SACK_BASE_ALIGNED) /
TCPOLEN_SACK_PERBLOCK);
size += TCPOLEN_SACK_BASE_ALIGNED +
th->check = 0;
th->urg_ptr = 0;
- if (unlikely(tp->urg_mode &&
- between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
- th->urg_ptr = htons(tp->snd_up - tcb->seq);
- th->urg = 1;
+ /* The urg_mode check is necessary during a below snd_una win probe */
+ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) {
+ if (before(tp->snd_up, tcb->seq + 0x10000)) {
+ 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 = 1;
+ }
}
tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
return net_xmit_eval(err);
}
-/* This routine just queue's the buffer
+/* This routine just queues the buffer for sending.
*
* NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
* otherwise socket can stall.
sk_mem_charge(sk, skb->truesize);
}
+/* Initialize TSO segments for a packet. */
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
- if (skb->len <= mss_now || !sk_can_gso(sk)) {
+ if (skb->len <= mss_now || !sk_can_gso(sk) ||
+ skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
tp->fackets_out -= decr;
}
+/* Pcount in the middle of the write queue got changed, we need to do various
+ * tweaks to fix counters
+ */
+static void tcp_adjust_pcount(struct sock *sk, struct sk_buff *skb, int decr)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ tp->packets_out -= decr;
+
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+ tp->sacked_out -= decr;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
+ tp->retrans_out -= decr;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
+ tp->lost_out -= decr;
+
+ /* Reno case is special. Sigh... */
+ if (tcp_is_reno(tp) && decr > 0)
+ tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
+
+ tcp_adjust_fackets_out(sk, skb, decr);
+
+ if (tp->lost_skb_hint &&
+ before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
+ (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)))
+ tp->lost_cnt_hint -= decr;
+
+ tcp_verify_left_out(tp);
+}
+
/* Function to create two new TCP segments. Shrinks the given segment
* to the specified size and appends a new segment with the rest of the
* packet to the list. This won't be called frequently, I hope.
struct sk_buff *buff;
int nsize, old_factor;
int nlen;
- u16 flags;
+ u8 flags;
BUG_ON(len > skb->len);
- tcp_clear_retrans_hints_partial(tp);
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
int diff = old_factor - tcp_skb_pcount(skb) -
tcp_skb_pcount(buff);
- tp->packets_out -= diff;
-
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
- tp->sacked_out -= diff;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out -= diff;
-
- if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
- tp->lost_out -= diff;
-
- /* Adjust Reno SACK estimate. */
- if (tcp_is_reno(tp) && diff > 0) {
- tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
- tcp_verify_left_out(tp);
- }
- tcp_adjust_fackets_out(sk, skb, diff);
+ if (diff)
+ tcp_adjust_pcount(sk, skb, diff);
}
/* Link BUFF into the send queue. */
skb->len = skb->data_len;
}
+/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
* factor and mss.
*/
if (tcp_skb_pcount(skb) > 1)
- tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk, 1));
+ tcp_set_skb_tso_segs(sk, skb, tcp_current_mss(sk));
return 0;
}
-/* Not accounting for SACKs here. */
+/* Calculate MSS. Not accounting for SACKs here. */
int tcp_mtu_to_mss(struct sock *sk, int pmtu)
{
struct tcp_sock *tp = tcp_sk(sk);
return mtu;
}
+/* MTU probing init per socket */
void tcp_mtup_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
icsk->icsk_mtup.probe_size = 0;
}
-/* Bound MSS / TSO packet size with the half of the window */
-static int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
-{
- if (tp->max_window && pktsize > (tp->max_window >> 1))
- return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
- else
- return pktsize;
-}
-
/* This function synchronize snd mss to current pmtu/exthdr set.
tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts
/* 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)
+unsigned int tcp_current_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
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)
- doing_tso = 1;
-
if (dst) {
u32 mtu = dst_mtu(dst);
if (mtu != inet_csk(sk)->icsk_pmtu_cookie)
mss_now -= delta;
}
- xmit_size_goal = mss_now;
-
- if (doing_tso) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
-
- xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
- xmit_size_goal -= (xmit_size_goal % mss_now);
- }
- tp->xmit_size_goal = xmit_size_goal;
-
return mss_now;
}
return 0;
}
-/* This must be invoked the first time we consider transmitting
+/* Intialize TSO state of a skb.
+ * This must be invoked the first time we consider transmitting
* SKB onto the wire.
*/
static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
return tso_segs;
}
+/* Minshall's variant of the Nagle send check. */
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;
return cwnd_quota;
}
+/* Test if sending is allowed right now. */
int tcp_may_send_now(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = tcp_send_head(sk);
return (skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
+ tcp_snd_test(sk, skb, tcp_current_mss(sk),
(tcp_skb_is_last(sk, skb) ?
tp->nonagle : TCP_NAGLE_PUSH)));
}
{
struct sk_buff *buff;
int nlen = skb->len - len;
- u16 flags;
+ u8 flags;
/* All of a TSO frame must be composed of paged data. */
if (skb->len != skb->data_len)
/* 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);
if (limit >= sk->sk_gso_max_size)
goto send_now;
+ /* Middle in queue won't get any more data, full sendable already? */
+ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len))
+ goto send_now;
+
if (sysctl_tcp_tso_win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
}
/* Create a new MTU probe if we are ready.
+ * MTU probe is regularly attempting to increase the path MTU by
+ * deliberately sending larger packets. This discovers routing
+ * changes resulting in larger path MTUs.
+ *
* Returns 0 if we should wait to probe (no cwnd available),
* 1 if a probe was sent,
* -1 otherwise
icsk->icsk_mtup.probe_size ||
inet_csk(sk)->icsk_ca_state != TCP_CA_Open ||
tp->snd_cwnd < 11 ||
- tp->rx_opt.eff_sacks)
+ tp->rx_opt.num_sacks || tp->rx_opt.dsack)
return -1;
/* Very simple search strategy: just double the MSS. */
- mss_now = tcp_current_mss(sk, 0);
+ mss_now = tcp_current_mss(sk);
probe_size = 2 * tp->mss_cache;
size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high)) {
* 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),
/* Update sequence range on original skb. */
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
- /* Merge over control information. */
- flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
- TCP_SKB_CB(skb)->flags = flags;
+ /* Merge over control information. This moves PSH/FIN etc. over */
+ TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(next_skb)->flags;
/* All done, get rid of second SKB and account for it so
* packet counting does not break.
*/
TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS;
- if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_RETRANS)
- tp->retrans_out -= tcp_skb_pcount(next_skb);
- if (TCP_SKB_CB(next_skb)->sacked & TCPCB_LOST)
- tp->lost_out -= tcp_skb_pcount(next_skb);
- /* Reno case is special. Sigh... */
- if (tcp_is_reno(tp) && tp->sacked_out)
- tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
-
- tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb));
- tp->packets_out -= tcp_skb_pcount(next_skb);
/* 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;
+
+ tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_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.
+/* Check if coalescing SKBs is legal. */
+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;
+}
+
+/* Collapse packets in the retransmit queue to make to create
+ * less packets on the wire. This is only done on retransmission.
*/
-void tcp_simple_retransmit(struct sock *sk)
+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
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
- cur_mss = tcp_current_mss(sk, 0);
+ cur_mss = tcp_current_mss(sk);
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
if (skb->len > cur_mss) {
if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
+ } else {
+ int oldpcount = tcp_skb_pcount(skb);
+
+ if (unlikely(oldpcount > 1)) {
+ tcp_init_tso_segs(sk, skb, cur_mss);
+ tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
+ }
}
- /* 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
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.
+/* Check if we forward retransmits are possible in the current
+ * window/congestion state.
*/
-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))) {
- int mib_idx;
-
- if (tcp_retransmit_skb(sk, skb)) {
- tp->retransmit_skb_hint = NULL;
- return;
- }
- if (icsk->icsk_ca_state != TCP_CA_Loss)
- mib_idx = LINUX_MIB_TCPFASTRETRANS;
- else
- mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS;
- 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);
- }
-
- 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 (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS)
+ if (fwd_rexmitting) {
+begin_fwd:
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
+ break;
+ mib_idx = LINUX_MIB_TCPFORWARDRETRANS;
+
+ } 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|TCPCB_SACKED_ACKED)))
+ 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(sock_net(sk), LINUX_MIB_TCPFORWARDRETRANS);
}
}
* unsent frames. But be careful about outgoing SACKS
* and IP options.
*/
- mss_now = tcp_current_mss(sk, 1);
+ mss_now = tcp_current_mss(sk);
if (tcp_send_head(sk) != NULL) {
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_FIN;
} else {
/* Socket is locked, keep trying until memory is available. */
for (;;) {
- skb = alloc_skb_fclone(MAX_TCP_HEADER, GFP_KERNEL);
+ skb = alloc_skb_fclone(MAX_TCP_HEADER,
+ sk->sk_allocation);
if (skb)
break;
yield();
TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS);
}
-/* WARNING: This routine must only be called when we have already sent
+/* Send a crossed SYN-ACK during socket establishment.
+ * WARNING: This routine must only be called when we have already sent
* a SYN packet that crossed the incoming SYN that caused this routine
* to get called. If this assumption fails then the initial rcv_wnd
* and rcv_wscale values will not be correct.
return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
-/*
- * Prepare a SYN-ACK.
- */
+/* Prepare a SYN-ACK. */
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req)
{
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
__u8 *md5_hash_location;
+ int mss;
skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
if (skb == NULL)
/* Reserve space for headers. */
skb_reserve(skb, MAX_TCP_HEADER);
- skb->dst = dst_clone(dst);
+ skb_dst_set(skb, dst_clone(dst));
+
+ mss = dst_metric(dst, RTAX_ADVMSS);
+ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss)
+ mss = tp->rx_opt.user_mss;
if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */
__u8 rcv_wscale;
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,
}
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_header_size = tcp_synack_options(sk, req,
- dst_metric(dst, RTAX_ADVMSS),
+ tcp_header_size = tcp_synack_options(sk, req, mss,
skb, &opts, &md5) +
sizeof(struct tcphdr);
th->syn = 1;
th->ack = 1;
TCP_ECN_make_synack(req, th);
- th->source = inet_sk(sk)->sport;
+ 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)
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(min(req->rcv_wnd, 65535U));
-#ifdef CONFIG_SYN_COOKIES
- if (unlikely(req->cookie_ts))
- TCP_SKB_CB(skb)->when = cookie_init_timestamp(req);
- else
-#endif
tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
th->doff = (tcp_header_size >> 2);
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,
+ tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location,
md5, NULL, req, skb);
}
#endif
return skb;
}
-/*
- * Do all connect socket setups that can be done AF independent.
- */
+/* Do all connect socket setups that can be done AF independent. */
static void tcp_connect_init(struct sock *sk)
{
struct dst_entry *dst = __sk_dst_get(sk);
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),
sk->sk_err = 0;
sock_reset_flag(sk, SOCK_DONE);
tp->snd_wnd = 0;
- tcp_init_wl(tp, tp->write_seq, 0);
+ tcp_init_wl(tp, 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;
tcp_clear_retrans(tp);
}
-/*
- * Build a SYN and send it off.
- */
+/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
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, GFP_KERNEL);
+ tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
/* We change tp->snd_nxt after the tcp_transmit_skb() call
* in order to make this packet get counted in tcpOutSegs.
return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
}
+/* Initiate keepalive or window probe from timer. */
int tcp_write_wakeup(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if ((skb = tcp_send_head(sk)) != NULL &&
before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) {
int err;
- unsigned int mss = tcp_current_mss(sk, 0);
+ unsigned int mss = tcp_current_mss(sk);
unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
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);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff