/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
-static void update_send_head(struct sock *sk, struct sk_buff *skb)
+static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
+ unsigned int prior_packets = tp->packets_out;
tcp_advance_send_head(sk, skb);
tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
- tcp_packets_out_inc(sk, skb);
+
+ /* Don't override Nagle indefinately with F-RTO */
+ if (tp->frto_counter == 2)
+ tp->frto_counter = 3;
+
+ tp->packets_out += tcp_skb_pcount(skb);
+ if (!prior_packets)
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+ inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
}
/* SND.NXT, if window was not shrunk.
{
struct tcp_sock *tp = tcp_sk(sk);
- if (!before(tp->snd_una+tp->snd_wnd, tp->snd_nxt))
+ if (!before(tcp_wnd_end(tp), tp->snd_nxt))
return tp->snd_nxt;
else
- return tp->snd_una+tp->snd_wnd;
+ return tcp_wnd_end(tp);
}
/* Calculate mss to advertise in SYN segment.
tp->write_seq = TCP_SKB_CB(skb)->end_seq;
skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
- sk_charge_skb(sk, skb);
+ sk->sk_wmem_queued += skb->truesize;
+ sk_mem_charge(sk, skb->truesize);
}
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
} else {
- unsigned int factor;
-
- factor = skb->len + (mss_now - 1);
- factor /= mss_now;
- skb_shinfo(skb)->gso_segs = factor;
+ skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
skb_shinfo(skb)->gso_size = mss_now;
skb_shinfo(skb)->gso_type = sk->sk_gso_type;
}
}
+/* When a modification to fackets out becomes necessary, we need to check
+ * skb is counted to fackets_out or not.
+ */
+static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb,
+ int decr)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (!tp->sacked_out || tcp_is_reno(tp))
+ return;
+
+ if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq))
+ tp->fackets_out -= decr;
+}
+
/* 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.
BUG_ON(len > skb->len);
- clear_all_retrans_hints(tp);
+ tcp_clear_retrans_hints_partial(tp);
nsize = skb_headlen(skb) - len;
if (nsize < 0)
nsize = 0;
if (buff == NULL)
return -ENOMEM; /* We'll just try again later. */
- sk_charge_skb(sk, buff);
+ sk->sk_wmem_queued += buff->truesize;
+ sk_mem_charge(sk, buff->truesize);
nlen = skb->len - len - nsize;
buff->truesize += nlen;
skb->truesize -= nlen;
TCP_SKB_CB(skb)->flags = flags & ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
TCP_SKB_CB(buff)->flags = flags;
TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked;
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_AT_TAIL;
if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) {
/* Copy and checksum data tail into the new buffer. */
if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
tp->retrans_out -= diff;
- if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
tp->lost_out -= diff;
- tp->left_out -= diff;
- }
- if (diff > 0) {
- /* Adjust Reno SACK estimate. */
- if (!tp->rx_opt.sack_ok) {
- tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
- tcp_sync_left_out(tp);
- }
-
- tcp_dec_pcount_approx_int(&tp->fackets_out, diff);
- /* SACK fastpath might overwrite it unless dealt with */
- if (tp->fastpath_skb_hint != NULL &&
- after(TCP_SKB_CB(tp->fastpath_skb_hint)->seq,
- TCP_SKB_CB(skb)->seq)) {
- tcp_dec_pcount_approx_int(&tp->fastpath_cnt_hint, 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);
}
/* Link BUFF into the send queue. */
skb->truesize -= len;
sk->sk_wmem_queued -= len;
- sk->sk_forward_alloc += len;
+ sk_mem_uncharge(sk, len);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
/* Any change of skb->len requires recalculation of tso
}
}
-static unsigned int tcp_window_allows(struct tcp_sock *tp, struct sk_buff *skb, unsigned int mss_now, unsigned int cwnd)
+/* Returns the portion of skb which can be sent right away without
+ * introducing MSS oddities to segment boundaries. In rare cases where
+ * mss_now != mss_cache, we will request caller to create a small skb
+ * per input skb which could be mostly avoided here (if desired).
+ */
+static unsigned int tcp_mss_split_point(struct sock *sk, struct sk_buff *skb,
+ unsigned int mss_now,
+ unsigned int cwnd)
{
- u32 window, cwnd_len;
+ struct tcp_sock *tp = tcp_sk(sk);
+ u32 needed, window, cwnd_len;
- window = (tp->snd_una + tp->snd_wnd - TCP_SKB_CB(skb)->seq);
+ window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
cwnd_len = mss_now * cwnd;
- return min(window, cwnd_len);
+
+ if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk)))
+ return cwnd_len;
+
+ if (skb == tcp_write_queue_tail(sk) && cwnd_len <= skb->len)
+ return cwnd_len;
+
+ needed = min(skb->len, window);
+ return needed - needed % mss_now;
}
/* Can at least one segment of SKB be sent right now, according to the
if (skb->len > cur_mss)
end_seq = TCP_SKB_CB(skb)->seq + cur_mss;
- return !after(end_seq, tp->snd_una + tp->snd_wnd);
+ return !after(end_seq, tcp_wnd_end(tp));
}
/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
return (skb &&
tcp_snd_test(sk, skb, tcp_current_mss(sk, 1),
(tcp_skb_is_last(sk, skb) ?
- TCP_NAGLE_PUSH :
- tp->nonagle)));
+ tp->nonagle : TCP_NAGLE_PUSH)));
}
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
if (skb->len != skb->data_len)
return tcp_fragment(sk, skb, len, mss_now);
- buff = sk_stream_alloc_pskb(sk, 0, 0, GFP_ATOMIC);
+ buff = sk_stream_alloc_skb(sk, 0, GFP_ATOMIC);
if (unlikely(buff == NULL))
return -ENOMEM;
- sk_charge_skb(sk, buff);
+ sk->sk_wmem_queued += buff->truesize;
+ sk_mem_charge(sk, buff->truesize);
buff->truesize += nlen;
skb->truesize -= nlen;
goto send_now;
/* Defer for less than two clock ticks. */
- if (!tp->tso_deferred && ((jiffies<<1)>>1) - (tp->tso_deferred>>1) > 1)
+ if (tp->tso_deferred &&
+ ((jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1)
goto send_now;
in_flight = tcp_packets_in_flight(tp);
BUG_ON(tcp_skb_pcount(skb) <= 1 ||
(tp->snd_cwnd <= in_flight));
- send_win = (tp->snd_una + tp->snd_wnd) - TCP_SKB_CB(skb)->seq;
+ send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* From in_flight test above, we know that cwnd > in_flight. */
cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache;
struct sk_buff *skb, *nskb, *next;
int len;
int probe_size;
- unsigned int pif;
+ int size_needed;
int copy;
int mss_now;
/* Very simple search strategy: just double the MSS. */
mss_now = tcp_current_mss(sk, 0);
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)) {
/* TODO: set timer for probe_converge_event */
return -1;
}
/* Have enough data in the send queue to probe? */
- len = 0;
- if ((skb = tcp_send_head(sk)) == NULL)
- return -1;
- while ((len += skb->len) < probe_size && !tcp_skb_is_last(sk, skb))
- skb = tcp_write_queue_next(sk, skb);
- if (len < probe_size)
+ if (tp->write_seq - tp->snd_nxt < size_needed)
return -1;
- /* Receive window check. */
- if (after(TCP_SKB_CB(skb)->seq + probe_size, tp->snd_una + tp->snd_wnd)) {
- if (tp->snd_wnd < probe_size)
- return -1;
- else
- return 0;
- }
+ if (tp->snd_wnd < size_needed)
+ return -1;
+ if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp)))
+ return 0;
- /* Do we need to wait to drain cwnd? */
- pif = tcp_packets_in_flight(tp);
- if (pif + 2 > tp->snd_cwnd) {
- /* With no packets in flight, don't stall. */
- if (pif == 0)
+ /* Do we need to wait to drain cwnd? With none in flight, don't stall */
+ if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) {
+ if (!tcp_packets_in_flight(tp))
return -1;
else
return 0;
/* We're allowed to probe. Build it now. */
if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
return -1;
- sk_charge_skb(sk, nskb);
+ sk->sk_wmem_queued += nskb->truesize;
+ sk_mem_charge(sk, nskb->truesize);
skb = tcp_send_head(sk);
- tcp_insert_write_queue_before(nskb, skb, sk);
- tcp_advance_send_head(sk, skb);
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
nskb->csum = 0;
nskb->ip_summed = skb->ip_summed;
- len = 0;
- while (len < probe_size) {
- next = tcp_write_queue_next(sk, skb);
+ tcp_insert_write_queue_before(nskb, skb, sk);
+ len = 0;
+ tcp_for_write_queue_from_safe(skb, next, sk) {
copy = min_t(int, skb->len, probe_size - len);
if (nskb->ip_summed)
skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
* Throw it away. */
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags;
tcp_unlink_write_queue(skb, sk);
- sk_stream_free_skb(sk, skb);
+ sk_wmem_free_skb(sk, skb);
} else {
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
}
len += copy;
- skb = next;
+
+ if (len >= probe_size)
+ break;
}
tcp_init_tso_segs(sk, nskb, nskb->len);
/* Decrement cwnd here because we are sending
* effectively two packets. */
tp->snd_cwnd--;
- update_send_head(sk, nskb);
+ tcp_event_new_data_sent(sk, nskb);
icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
}
limit = mss_now;
- if (tso_segs > 1) {
- limit = tcp_window_allows(tp, skb,
- mss_now, cwnd_quota);
-
- if (skb->len < limit) {
- unsigned int trim = skb->len % mss_now;
-
- if (trim)
- limit = skb->len - trim;
- }
- }
+ 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)))
/* Advance the send_head. This one is sent out.
* This call will increment packets_out.
*/
- update_send_head(sk, skb);
+ tcp_event_new_data_sent(sk, skb);
tcp_minshall_update(tp, mss_now, skb);
sent_pkts++;
*/
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
- struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb = tcp_send_head(sk);
unsigned int tso_segs, cwnd_quota;
BUG_ON(!tso_segs);
limit = mss_now;
- if (tso_segs > 1) {
- limit = tcp_window_allows(tp, skb,
- mss_now, cwnd_quota);
-
- if (skb->len < limit) {
- unsigned int trim = skb->len % mss_now;
-
- if (trim)
- limit = skb->len - trim;
- }
- }
+ 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)))
TCP_SKB_CB(skb)->when = tcp_time_stamp;
if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
- update_send_head(sk, skb);
+ tcp_event_new_data_sent(sk, skb);
tcp_cwnd_validate(sk);
return;
}
if (mss > full_space)
mss = full_space;
- if (free_space < full_space/2) {
+ if (free_space < (full_space >> 1)) {
icsk->icsk_ack.quick = 0;
if (tcp_memory_pressure)
if (window <= free_space - mss || window > free_space)
window = (free_space/mss)*mss;
else if (mss == full_space &&
- free_space > window + full_space/2)
+ free_space > window + (full_space >> 1))
window = free_space;
}
{
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)) {
- int skb_size = skb->len, next_skb_size = next_skb->len;
- u16 flags = TCP_SKB_CB(skb)->flags;
+ if (skb_cloned(skb) || skb_cloned(next_skb))
+ return;
- /* Also punt if next skb has been SACK'd. */
- if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
- return;
+ skb_size = skb->len;
+ next_skb_size = next_skb->len;
+ flags = TCP_SKB_CB(skb)->flags;
- /* Next skb is out of window. */
- if (after(TCP_SKB_CB(next_skb)->end_seq, tp->snd_una+tp->snd_wnd))
- return;
+ /* Also punt if next skb has been SACK'd. */
+ if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
+ 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;
+ /* Next skb is out of window. */
+ if (after(TCP_SKB_CB(next_skb)->end_seq, tcp_wnd_end(tp)))
+ return;
- BUG_ON(tcp_skb_pcount(skb) != 1 ||
- tcp_skb_pcount(next_skb) != 1);
+ /* 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;
- /* changing transmit queue under us so clear hints */
- clear_all_retrans_hints(tp);
+ BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
- /* Ok. We will be able to collapse the packet. */
- tcp_unlink_write_queue(next_skb, sk);
+ tcp_highest_sack_combine(sk, next_skb, skb);
- skb_copy_from_linear_data(next_skb,
- skb_put(skb, next_skb_size),
- next_skb_size);
+ /* Ok. We will be able to collapse the packet. */
+ tcp_unlink_write_queue(next_skb, sk);
- if (next_skb->ip_summed == CHECKSUM_PARTIAL)
- skb->ip_summed = CHECKSUM_PARTIAL;
+ skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size),
+ next_skb_size);
- if (skb->ip_summed != CHECKSUM_PARTIAL)
- skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);
+ if (next_skb->ip_summed == CHECKSUM_PARTIAL)
+ skb->ip_summed = CHECKSUM_PARTIAL;
- /* Update sequence range on original skb. */
- TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);
- /* Merge over control information. */
- flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
- TCP_SKB_CB(skb)->flags = flags;
+ /* Update sequence range on original skb. */
+ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;
- /* 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|TCPCB_AT_TAIL);
- 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);
- tp->left_out -= tcp_skb_pcount(next_skb);
- }
- /* Reno case is special. Sigh... */
- if (!tp->rx_opt.sack_ok && tp->sacked_out) {
- tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
- tp->left_out -= tcp_skb_pcount(next_skb);
- }
+ /* Merge over control information. */
+ flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
+ TCP_SKB_CB(skb)->flags = flags;
- /* Not quite right: it can be > snd.fack, but
- * it is better to underestimate fackets.
- */
- tcp_dec_pcount_approx(&tp->fackets_out, next_skb);
- tcp_packets_out_dec(tp, next_skb);
- sk_stream_free_skb(sk, next_skb);
- }
+ /* 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);
+
+ sk_wmem_free_skb(sk, next_skb);
}
/* Do a simple retransmit without using the backoff mechanisms in
}
}
- clear_all_retrans_hints(tp);
+ tcp_clear_all_retrans_hints(tp);
if (!lost)
return;
- tcp_sync_left_out(tp);
+ tcp_verify_left_out(tp);
/* Don't muck with the congestion window here.
* Reason is that we do not increase amount of _data_
* case, when window is shrunk to zero. In this case
* our retransmit serves as a zero window probe.
*/
- if (!before(TCP_SKB_CB(skb)->seq, tp->snd_una+tp->snd_wnd)
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))
&& TCP_SKB_CB(skb)->seq != tp->snd_una)
return -EAGAIN;
printk(KERN_DEBUG "retrans_out leaked.\n");
}
#endif
+ if (!tp->retrans_out)
+ tp->lost_retrans_low = tp->snd_nxt;
TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS;
tp->retrans_out += tcp_skb_pcount(skb);
return;
/* No forward retransmissions in Reno are possible. */
- if (!tp->rx_opt.sack_ok)
+ if (tcp_is_reno(tp))
return;
/* Yeah, we have to make difficult choice between forward transmission
break;
tp->forward_skb_hint = skb;
- if (after(TCP_SKB_CB(skb)->seq, tp->highest_sack))
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
break;
if (tcp_packets_in_flight(tp) >= tp->snd_cwnd)
tcp_unlink_write_queue(skb, sk);
skb_header_release(nskb);
__tcp_add_write_queue_head(sk, nskb);
- sk_stream_free_skb(sk, skb);
- sk_charge_skb(sk, nskb);
+ sk_wmem_free_skb(sk, skb);
+ sk->sk_wmem_queued += nskb->truesize;
+ sk_mem_charge(sk, nskb->truesize);
skb = nskb;
}
tp->retrans_stamp = TCP_SKB_CB(buff)->when;
skb_header_release(buff);
__tcp_add_write_queue_tail(sk, buff);
- sk_charge_skb(sk, buff);
+ 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);
/* This routine sends an ack and also updates the window. */
void tcp_send_ack(struct sock *sk)
{
- /* If we have been reset, we may not send again. */
- if (sk->sk_state != TCP_CLOSE) {
- struct sk_buff *buff;
+ struct sk_buff *buff;
- /* We are not putting this on the write queue, so
- * tcp_transmit_skb() will set the ownership to this
- * sock.
- */
- buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
- if (buff == NULL) {
- inet_csk_schedule_ack(sk);
- inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
- TCP_DELACK_MAX, TCP_RTO_MAX);
- return;
- }
+ /* If we have been reset, we may not send again. */
+ if (sk->sk_state == TCP_CLOSE)
+ return;
- /* Reserve space for headers and prepare control bits. */
- skb_reserve(buff, MAX_TCP_HEADER);
- buff->csum = 0;
- TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
- TCP_SKB_CB(buff)->sacked = 0;
- skb_shinfo(buff)->gso_segs = 1;
- skb_shinfo(buff)->gso_size = 0;
- skb_shinfo(buff)->gso_type = 0;
-
- /* Send it off, this clears delayed acks for us. */
- TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk);
- TCP_SKB_CB(buff)->when = tcp_time_stamp;
- tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
+ /* We are not putting this on the write queue, so
+ * tcp_transmit_skb() will set the ownership to this
+ * sock.
+ */
+ buff = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC);
+ if (buff == NULL) {
+ inet_csk_schedule_ack(sk);
+ inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
+ TCP_DELACK_MAX, TCP_RTO_MAX);
+ return;
}
+
+ /* Reserve space for headers and prepare control bits. */
+ skb_reserve(buff, MAX_TCP_HEADER);
+ buff->csum = 0;
+ TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK;
+ TCP_SKB_CB(buff)->sacked = 0;
+ skb_shinfo(buff)->gso_segs = 1;
+ skb_shinfo(buff)->gso_size = 0;
+ skb_shinfo(buff)->gso_type = 0;
+
+ /* Send it off, this clears delayed acks for us. */
+ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk);
+ TCP_SKB_CB(buff)->when = tcp_time_stamp;
+ tcp_transmit_skb(sk, buff, 0, GFP_ATOMIC);
}
/* This routine sends a packet with an out of date sequence
skb_reserve(skb, MAX_TCP_HEADER);
skb->csum = 0;
TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
- TCP_SKB_CB(skb)->sacked = urgent;
+ TCP_SKB_CB(skb)->sacked = 0;
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
skb_shinfo(skb)->gso_type = 0;
int tcp_write_wakeup(struct sock *sk)
{
- if (sk->sk_state != TCP_CLOSE) {
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- if ((skb = tcp_send_head(sk)) != NULL &&
- before(TCP_SKB_CB(skb)->seq, tp->snd_una+tp->snd_wnd)) {
- int err;
- unsigned int mss = tcp_current_mss(sk, 0);
- unsigned int seg_size = tp->snd_una+tp->snd_wnd-TCP_SKB_CB(skb)->seq;
-
- if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
- tp->pushed_seq = TCP_SKB_CB(skb)->end_seq;
-
- /* We are probing the opening of a window
- * but the window size is != 0
- * must have been a result SWS avoidance ( sender )
- */
- 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;
- if (tcp_fragment(sk, skb, seg_size, mss))
- return -1;
- } else if (!tcp_skb_pcount(skb))
- tcp_set_skb_tso_segs(sk, skb, mss);
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *skb;
+
+ if (sk->sk_state == TCP_CLOSE)
+ return -1;
+
+ 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 seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
+
+ if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq))
+ tp->pushed_seq = TCP_SKB_CB(skb)->end_seq;
+ /* We are probing the opening of a window
+ * but the window size is != 0
+ * must have been a result SWS avoidance ( sender )
+ */
+ 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)->when = tcp_time_stamp;
- err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
- if (!err) {
- update_send_head(sk, skb);
- }
- return err;
- } else {
- if (tp->urg_mode &&
- between(tp->snd_up, tp->snd_una+1, tp->snd_una+0xFFFF))
- tcp_xmit_probe_skb(sk, TCPCB_URG);
- return tcp_xmit_probe_skb(sk, 0);
- }
+ 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)->when = tcp_time_stamp;
+ err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+ if (!err)
+ 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))
+ tcp_xmit_probe_skb(sk, 1);
+ return tcp_xmit_probe_skb(sk, 0);
}
- return -1;
}
/* A window probe timeout has occurred. If window is not closed send