if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = prev;
- if (skb == tp->scoreboard_skb_hint)
- tp->scoreboard_skb_hint = prev;
if (skb == tp->lost_skb_hint) {
tp->lost_skb_hint = prev;
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
return true;
}
-static inline int tcp_skb_timedout(const struct sock *sk,
- const struct sk_buff *skb)
-{
- return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto;
-}
-
-static inline int tcp_head_timedout(const struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
-
- return tp->packets_out &&
- tcp_skb_timedout(sk, tcp_write_queue_head(sk));
-}
-
/* Linux NewReno/SACK/FACK/ECN state machine.
* --------------------------------------
*
if (tcp_dupack_heuristics(tp) > tp->reordering)
return true;
- /* Trick#3 : when we use RFC2988 timer restart, fast
- * retransmit can be triggered by timeout of queue head.
- */
- if (tcp_is_fack(tp) && tcp_head_timedout(sk))
- return true;
-
/* Trick#4: It is still not OK... But will it be useful to delay
* recovery more?
*/
return false;
}
-/* New heuristics: it is possible only after we switched to restart timer
- * each time when something is ACKed. Hence, we can detect timed out packets
- * during fast retransmit without falling to slow start.
- *
- * Usefulness of this as is very questionable, since we should know which of
- * the segments is the next to timeout which is relatively expensive to find
- * in general case unless we add some data structure just for that. The
- * current approach certainly won't find the right one too often and when it
- * finally does find _something_ it usually marks large part of the window
- * right away (because a retransmission with a larger timestamp blocks the
- * loop from advancing). -ij
- */
-static void tcp_timeout_skbs(struct sock *sk)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- if (!tcp_is_fack(tp) || !tcp_head_timedout(sk))
- return;
-
- skb = tp->scoreboard_skb_hint;
- if (tp->scoreboard_skb_hint == NULL)
- skb = tcp_write_queue_head(sk);
-
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- if (!tcp_skb_timedout(sk, skb))
- break;
-
- tcp_skb_mark_lost(tp, skb);
- }
-
- tp->scoreboard_skb_hint = skb;
-
- tcp_verify_left_out(tp);
-}
-
/* Detect loss in event "A" above by marking head of queue up as lost.
* For FACK or non-SACK(Reno) senders, the first "packets" number of segments
* are considered lost. For RFC3517 SACK, a segment is considered lost if it
else if (fast_rexmit)
tcp_mark_head_lost(sk, 1, 1);
}
-
- tcp_timeout_skbs(sk);
}
/* CWND moderation, preventing bursts due to too big ACKs
#define DBGUNDO(x...) do { } while (0)
#endif
-static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
+static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
struct tcp_sock *tp = tcp_sk(sk);
+ if (unmark_loss) {
+ struct sk_buff *skb;
+
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
+ }
+ tp->lost_out = 0;
+ tcp_clear_all_retrans_hints(tp);
+ }
+
if (tp->prior_ssthresh) {
const struct inet_connection_sock *icsk = inet_csk(sk);
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
- if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
+ if (tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->undo_marker = 0;
}
static inline bool tcp_may_undo(const struct tcp_sock *tp)
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(sk, true);
+ tcp_undo_cwnd_reduction(sk, false);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
mib_idx = LINUX_MIB_TCPFULLUNDO;
NET_INC_STATS_BH(sock_net(sk), mib_idx);
- tp->undo_marker = 0;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk)
+static bool tcp_try_undo_dsack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
- tcp_undo_cwr(sk, true);
- tp->undo_marker = 0;
+ tcp_undo_cwnd_reduction(sk, false);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
+ return true;
}
+ return false;
}
/* We can clear retrans_stamp when there are no retransmissions in the
return false;
}
-/* Undo during fast recovery after partial ACK. */
-
-static int tcp_try_undo_partial(struct sock *sk, int acked)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- /* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = tcp_is_reno(tp) || (tcp_fackets_out(tp) > tp->reordering);
-
- if (tcp_may_undo(tp)) {
- /* Plain luck! Hole if filled with delayed
- * packet, rather than with a retransmit.
- */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
-
- tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
-
- DBGUNDO(sk, "Hoe");
- tcp_undo_cwr(sk, false);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
-
- /* So... Do not make Hoe's retransmit yet.
- * If the first packet was delayed, the rest
- * ones are most probably delayed as well.
- */
- failed = 0;
- }
- return failed;
-}
-
/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
struct tcp_sock *tp = tcp_sk(sk);
if (frto_undo || tcp_may_undo(tp)) {
- struct sk_buff *skb;
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- }
-
- tcp_clear_all_retrans_hints(tp);
+ tcp_undo_cwnd_reduction(sk, true);
DBGUNDO(sk, "partial loss");
- tp->lost_out = 0;
- tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
if (frto_undo)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- tp->undo_marker = 0;
if (frto_undo || tcp_is_sack(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return true;
TCP_ECN_queue_cwr(tp);
}
-static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
+static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
int fast_rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
+ int newly_acked_sacked = prior_unsacked -
+ (tp->packets_out - tp->sacked_out);
tp->prr_delivered += newly_acked_sacked;
if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) {
}
}
-static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
+static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
{
struct tcp_sock *tp = tcp_sk(sk);
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_reduction(sk, newly_acked_sacked, 0);
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
}
}
tcp_xmit_retransmit_queue(sk);
}
+/* Undo during fast recovery after partial ACK. */
+static bool tcp_try_undo_partial(struct sock *sk, const int acked,
+ const int prior_unsacked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->undo_marker && tcp_packet_delayed(tp)) {
+ /* Plain luck! Hole if filled with delayed
+ * packet, rather than with a retransmit.
+ */
+ tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
+
+ /* We are getting evidence that the reordering degree is higher
+ * than we realized. If there are no retransmits out then we
+ * can undo. Otherwise we clock out new packets but do not
+ * mark more packets lost or retransmit more.
+ */
+ if (tp->retrans_out) {
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
+ return true;
+ }
+
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+
+ DBGUNDO(sk, "partial recovery");
+ tcp_undo_cwnd_reduction(sk, true);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
+ tcp_try_keep_open(sk);
+ return true;
+ }
+ return false;
+}
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
-static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int prior_sacked, bool is_dupack,
- int flag)
+static void tcp_fastretrans_alert(struct sock *sk, const int acked,
+ const int prior_unsacked,
+ bool is_dupack, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
+ bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- int newly_acked_sacked = 0;
int fast_rexmit = 0;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
- } else
- do_lost = tcp_try_undo_partial(sk, pkts_acked);
- newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
+ } else {
+ if (tcp_try_undo_partial(sk, acked, prior_unsacked))
+ return;
+ /* Partial ACK arrived. Force fast retransmit. */
+ do_lost = tcp_is_reno(tp) ||
+ tcp_fackets_out(tp) > tp->reordering;
+ }
+ if (tcp_try_undo_dsack(sk)) {
+ tcp_try_keep_open(sk);
+ return;
+ }
break;
case TCP_CA_Loss:
tcp_process_loss(sk, flag, is_dupack);
if (is_dupack)
tcp_add_reno_sack(sk);
}
- newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk, flag)) {
- tcp_try_to_open(sk, flag, newly_acked_sacked);
+ tcp_try_to_open(sk, flag, prior_unsacked);
return;
}
fast_rexmit = 1;
}
- if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk)))
+ if (do_lost)
tcp_update_scoreboard(sk, fast_rexmit);
- tcp_cwnd_reduction(sk, newly_acked_sacked, fast_rexmit);
+ tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit);
tcp_xmit_retransmit_queue(sk);
}
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
- tp->scoreboard_skb_hint = NULL;
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = NULL;
if (skb == tp->lost_skb_hint)
bool is_dupack = false;
u32 prior_in_flight;
u32 prior_fackets;
- int prior_packets;
- int prior_sacked = tp->sacked_out;
- int pkts_acked = 0;
+ int prior_packets = tp->packets_out;
+ const int prior_unsacked = tp->packets_out - tp->sacked_out;
+ int acked = 0; /* Number of packets newly acked */
/* If the ack is older than previous acks
* then we can probably ignore it.
sk->sk_err_soft = 0;
icsk->icsk_probes_out = 0;
tp->rcv_tstamp = tcp_time_stamp;
- prior_packets = tp->packets_out;
if (!prior_packets)
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
+ acked = tp->packets_out;
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
-
- pkts_acked = prior_packets - tp->packets_out;
+ acked -= tp->packets_out;
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
} else {
if (flag & FLAG_DATA_ACKED)
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
is_dupack, flag);
}
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock *req;
int queued = 0;
+ bool acceptable;
tp->rx_opt.saw_tstamp = 0;
return 0;
/* step 5: check the ACK field */
- if (true) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
- FLAG_UPDATE_TS_RECENT) > 0;
-
- switch (sk->sk_state) {
- case TCP_SYN_RECV:
- if (acceptable) {
- /* Once we leave TCP_SYN_RECV, we no longer
- * need req so release it.
- */
- if (req) {
- tcp_synack_rtt_meas(sk, req);
- tp->total_retrans = req->num_retrans;
-
- reqsk_fastopen_remove(sk, req, false);
- } else {
- /* Make sure socket is routed, for
- * correct metrics.
- */
- icsk->icsk_af_ops->rebuild_header(sk);
- tcp_init_congestion_control(sk);
+ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
+ FLAG_UPDATE_TS_RECENT) > 0;
- tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
- tp->copied_seq = tp->rcv_nxt;
- }
- smp_mb();
- tcp_set_state(sk, TCP_ESTABLISHED);
- sk->sk_state_change(sk);
-
- /* Note, that this wakeup is only for marginal
- * crossed SYN case. Passively open sockets
- * are not waked up, because sk->sk_sleep ==
- * NULL and sk->sk_socket == NULL.
- */
- if (sk->sk_socket)
- sk_wake_async(sk,
- SOCK_WAKE_IO, POLL_OUT);
-
- tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
- tp->snd_wnd = ntohs(th->window) <<
- tp->rx_opt.snd_wscale;
- tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
-
- if (tp->rx_opt.tstamp_ok)
- tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
-
- if (req) {
- /* Re-arm the timer because data may
- * have been sent out. This is similar
- * to the regular data transmission case
- * when new data has just been ack'ed.
- *
- * (TFO) - we could try to be more
- * aggressive and retranmitting any data
- * sooner based on when they were sent
- * out.
- */
- tcp_rearm_rto(sk);
- } else
- tcp_init_metrics(sk);
+ switch (sk->sk_state) {
+ case TCP_SYN_RECV:
+ if (!acceptable)
+ return 1;
- /* Prevent spurious tcp_cwnd_restart() on
- * first data packet.
- */
- tp->lsndtime = tcp_time_stamp;
+ /* Once we leave TCP_SYN_RECV, we no longer need req
+ * so release it.
+ */
+ if (req) {
+ tcp_synack_rtt_meas(sk, req);
+ tp->total_retrans = req->num_retrans;
- tcp_initialize_rcv_mss(sk);
- tcp_fast_path_on(tp);
- } else {
- return 1;
- }
- break;
+ reqsk_fastopen_remove(sk, req, false);
+ } else {
+ /* Make sure socket is routed, for correct metrics. */
+ icsk->icsk_af_ops->rebuild_header(sk);
+ tcp_init_congestion_control(sk);
+
+ tcp_mtup_init(sk);
+ tcp_init_buffer_space(sk);
+ tp->copied_seq = tp->rcv_nxt;
+ }
+ smp_mb();
+ tcp_set_state(sk, TCP_ESTABLISHED);
+ sk->sk_state_change(sk);
+
+ /* Note, that this wakeup is only for marginal crossed SYN case.
+ * Passively open sockets are not waked up, because
+ * sk->sk_sleep == NULL and sk->sk_socket == NULL.
+ */
+ if (sk->sk_socket)
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
+
+ tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
+ tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
+
+ if (tp->rx_opt.tstamp_ok)
+ tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
- case TCP_FIN_WAIT1:
- /* If we enter the TCP_FIN_WAIT1 state and we are a
- * Fast Open socket and this is the first acceptable
- * ACK we have received, this would have acknowledged
- * our SYNACK so stop the SYNACK timer.
+ if (req) {
+ /* Re-arm the timer because data may have been sent out.
+ * This is similar to the regular data transmission case
+ * when new data has just been ack'ed.
+ *
+ * (TFO) - we could try to be more aggressive and
+ * retransmitting any data sooner based on when they
+ * are sent out.
*/
- if (req != NULL) {
- /* Return RST if ack_seq is invalid.
- * Note that RFC793 only says to generate a
- * DUPACK for it but for TCP Fast Open it seems
- * better to treat this case like TCP_SYN_RECV
- * above.
- */
- if (!acceptable)
- return 1;
- /* We no longer need the request sock. */
- reqsk_fastopen_remove(sk, req, false);
- tcp_rearm_rto(sk);
- }
- if (tp->snd_una == tp->write_seq) {
- struct dst_entry *dst;
-
- tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
-
- dst = __sk_dst_get(sk);
- if (dst)
- dst_confirm(dst);
-
- if (!sock_flag(sk, SOCK_DEAD))
- /* Wake up lingering close() */
- sk->sk_state_change(sk);
- else {
- int tmo;
-
- if (tp->linger2 < 0 ||
- (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
- after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
- tcp_done(sk);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
- return 1;
- }
+ tcp_rearm_rto(sk);
+ } else
+ tcp_init_metrics(sk);
- tmo = tcp_fin_time(sk);
- if (tmo > TCP_TIMEWAIT_LEN) {
- inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
- } else if (th->fin || sock_owned_by_user(sk)) {
- /* Bad case. We could lose such FIN otherwise.
- * It is not a big problem, but it looks confusing
- * and not so rare event. We still can lose it now,
- * if it spins in bh_lock_sock(), but it is really
- * marginal case.
- */
- inet_csk_reset_keepalive_timer(sk, tmo);
- } else {
- tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
- goto discard;
- }
- }
- }
- break;
+ /* Prevent spurious tcp_cwnd_restart() on first data packet */
+ tp->lsndtime = tcp_time_stamp;
- case TCP_CLOSING:
- if (tp->snd_una == tp->write_seq) {
- tcp_time_wait(sk, TCP_TIME_WAIT, 0);
- goto discard;
- }
+ tcp_initialize_rcv_mss(sk);
+ tcp_fast_path_on(tp);
+ break;
+
+ case TCP_FIN_WAIT1: {
+ struct dst_entry *dst;
+ int tmo;
+
+ /* If we enter the TCP_FIN_WAIT1 state and we are a
+ * Fast Open socket and this is the first acceptable
+ * ACK we have received, this would have acknowledged
+ * our SYNACK so stop the SYNACK timer.
+ */
+ if (req != NULL) {
+ /* Return RST if ack_seq is invalid.
+ * Note that RFC793 only says to generate a
+ * DUPACK for it but for TCP Fast Open it seems
+ * better to treat this case like TCP_SYN_RECV
+ * above.
+ */
+ if (!acceptable)
+ return 1;
+ /* We no longer need the request sock. */
+ reqsk_fastopen_remove(sk, req, false);
+ tcp_rearm_rto(sk);
+ }
+ if (tp->snd_una != tp->write_seq)
break;
- case TCP_LAST_ACK:
- if (tp->snd_una == tp->write_seq) {
- tcp_update_metrics(sk);
- tcp_done(sk);
- goto discard;
- }
+ tcp_set_state(sk, TCP_FIN_WAIT2);
+ sk->sk_shutdown |= SEND_SHUTDOWN;
+
+ dst = __sk_dst_get(sk);
+ if (dst)
+ dst_confirm(dst);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ /* Wake up lingering close() */
+ sk->sk_state_change(sk);
break;
}
+
+ if (tp->linger2 < 0 ||
+ (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
+ after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
+ tcp_done(sk);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
+ return 1;
+ }
+
+ tmo = tcp_fin_time(sk);
+ if (tmo > TCP_TIMEWAIT_LEN) {
+ inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
+ } else if (th->fin || sock_owned_by_user(sk)) {
+ /* Bad case. We could lose such FIN otherwise.
+ * It is not a big problem, but it looks confusing
+ * and not so rare event. We still can lose it now,
+ * if it spins in bh_lock_sock(), but it is really
+ * marginal case.
+ */
+ inet_csk_reset_keepalive_timer(sk, tmo);
+ } else {
+ tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
+ goto discard;
+ }
+ break;
+ }
+
+ case TCP_CLOSING:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_time_wait(sk, TCP_TIME_WAIT, 0);
+ goto discard;
+ }
+ break;
+
+ case TCP_LAST_ACK:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_update_metrics(sk);
+ tcp_done(sk);
+ goto discard;
+ }
+ break;
}
/* step 6: check the URG bit */
projects / deliverable / linux.git / blobdiff