tcp FRTO: Fix fallback to conventional recovery

[linux-2.6-omap-h63xx.git] / net / ipv4 / tcp_input.c

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ac9b8482f702eae07f6f66b935b36f986354d91f..d6edb98fd526b6471c34dd197d8c429a5c9ffb9f 100644 (file)
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -66,6 +66,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
+#include <net/dst.h>
 #include <net/tcp.h>
 #include <net/inet_common.h>
 #include <linux/ipsec.h>
@@ -113,8 +114,6 @@ int sysctl_tcp_abc __read_mostly;
 #define FLAG_FORWARD_PROGRESS  (FLAG_ACKED|FLAG_DATA_SACKED)
 #define FLAG_ANY_PROGRESS      (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
 
-#define IsSackFrto() (sysctl_tcp_frto == 0x2)
-
 #define TCP_REMNANT (TCP_FLAG_FIN|TCP_FLAG_URG|TCP_FLAG_SYN|TCP_FLAG_PSH)
 #define TCP_HP_BITS (~(TCP_RESERVED_BITS|TCP_FLAG_PSH))
 
@@ -605,7 +604,7 @@ static u32 tcp_rto_min(struct sock *sk)
        u32 rto_min = TCP_RTO_MIN;
 
        if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
-               rto_min = dst->metrics[RTAX_RTO_MIN - 1];
+               rto_min = dst_metric(dst, RTAX_RTO_MIN);
        return rto_min;
 }
 
@@ -769,7 +768,7 @@ void tcp_update_metrics(struct sock *sk)
                                dst->metrics[RTAX_RTTVAR - 1] = m;
                        else
                                dst->metrics[RTAX_RTTVAR-1] -=
-                                       (dst->metrics[RTAX_RTTVAR-1] - m)>>2;
+                                       (dst_metric(dst, RTAX_RTTVAR) - m)>>2;
                }
 
                if (tp->snd_ssthresh >= 0xFFFF) {
@@ -788,21 +787,21 @@ void tcp_update_metrics(struct sock *sk)
                                dst->metrics[RTAX_SSTHRESH-1] =
                                        max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
                        if (!dst_metric_locked(dst, RTAX_CWND))
-                               dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_cwnd) >> 1;
+                               dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1;
                } else {
                        /* Else slow start did not finish, cwnd is non-sense,
                           ssthresh may be also invalid.
                         */
                        if (!dst_metric_locked(dst, RTAX_CWND))
-                               dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_ssthresh) >> 1;
-                       if (dst->metrics[RTAX_SSTHRESH-1] &&
+                               dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1;
+                       if (dst_metric(dst, RTAX_SSTHRESH) &&
                            !dst_metric_locked(dst, RTAX_SSTHRESH) &&
-                           tp->snd_ssthresh > dst->metrics[RTAX_SSTHRESH-1])
+                           tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH))
                                dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
                }
 
                if (!dst_metric_locked(dst, RTAX_REORDERING)) {
-                       if (dst->metrics[RTAX_REORDERING-1] < tp->reordering &&
+                       if (dst_metric(dst, RTAX_REORDERING) < tp->reordering &&
                            tp->reordering != sysctl_tcp_reordering)
                                dst->metrics[RTAX_REORDERING-1] = tp->reordering;
                }
@@ -1172,8 +1171,8 @@ static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
                           struct tcp_sack_block_wire *sp, int num_sacks,
                           u32 prior_snd_una)
 {
-       u32 start_seq_0 = ntohl(get_unaligned(&sp[0].start_seq));
-       u32 end_seq_0 = ntohl(get_unaligned(&sp[0].end_seq));
+       u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
+       u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
        int dup_sack = 0;
 
        if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
@@ -1181,8 +1180,8 @@ static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
                tcp_dsack_seen(tp);
                NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
        } else if (num_sacks > 1) {
-               u32 end_seq_1 = ntohl(get_unaligned(&sp[1].end_seq));
-               u32 start_seq_1 = ntohl(get_unaligned(&sp[1].start_seq));
+               u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
+               u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);
 
                if (!after(end_seq_0, end_seq_1) &&
                    !before(start_seq_0, start_seq_1)) {
@@ -1453,8 +1452,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb,
        for (i = 0; i < num_sacks; i++) {
                int dup_sack = !i && found_dup_sack;
 
-               sp[used_sacks].start_seq = ntohl(get_unaligned(&sp_wire[i].start_seq));
-               sp[used_sacks].end_seq = ntohl(get_unaligned(&sp_wire[i].end_seq));
+               sp[used_sacks].start_seq = get_unaligned_be32(&sp_wire[i].start_seq);
+               sp[used_sacks].end_seq = get_unaligned_be32(&sp_wire[i].end_seq);
 
                if (!tcp_is_sackblock_valid(tp, dup_sack,
                                            sp[used_sacks].start_seq,
@@ -1685,6 +1684,11 @@ static inline void tcp_reset_reno_sack(struct tcp_sock *tp)
        tp->sacked_out = 0;
 }
 
+static int tcp_is_sackfrto(const struct tcp_sock *tp)
+{
+       return (sysctl_tcp_frto == 0x2) && !tcp_is_reno(tp);
+}
+
 /* F-RTO can only be used if TCP has never retransmitted anything other than
  * head (SACK enhanced variant from Appendix B of RFC4138 is more robust here)
  */
@@ -1701,7 +1705,7 @@ int tcp_use_frto(struct sock *sk)
        if (icsk->icsk_mtup.probe_size)
                return 0;
 
-       if (IsSackFrto())
+       if (tcp_is_sackfrto(tp))
                return 1;
 
        /* Avoid expensive walking of rexmit queue if possible */
@@ -1791,7 +1795,7 @@ void tcp_enter_frto(struct sock *sk)
        /* Earlier loss recovery underway (see RFC4138; Appendix B).
         * The last condition is necessary at least in tp->frto_counter case.
         */
-       if (IsSackFrto() && (tp->frto_counter ||
+       if (tcp_is_sackfrto(tp) && (tp->frto_counter ||
            ((1 << icsk->icsk_ca_state) & (TCPF_CA_Recovery|TCPF_CA_Loss))) &&
            after(tp->high_seq, tp->snd_una)) {
                tp->frto_highmark = tp->high_seq;
@@ -2478,7 +2482,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
 
        tcp_verify_left_out(tp);
 
-       if (tp->retrans_out == 0)
+       if (!tp->frto_counter && tp->retrans_out == 0)
                tp->retrans_stamp = 0;
 
        if (flag & FLAG_ECE)
@@ -3123,7 +3127,7 @@ static int tcp_process_frto(struct sock *sk, int flag)
                return 1;
        }
 
-       if (!IsSackFrto() || tcp_is_reno(tp)) {
+       if (!tcp_is_sackfrto(tp)) {
                /* RFC4138 shortcoming in step 2; should also have case c):
                 * ACK isn't duplicate nor advances window, e.g., opposite dir
                 * data, winupdate
@@ -3340,7 +3344,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
                        switch (opcode) {
                        case TCPOPT_MSS:
                                if (opsize == TCPOLEN_MSS && th->syn && !estab) {
-                                       u16 in_mss = ntohs(get_unaligned((__be16 *)ptr));
+                                       u16 in_mss = get_unaligned_be16(ptr);
                                        if (in_mss) {
                                                if (opt_rx->user_mss &&
                                                    opt_rx->user_mss < in_mss)
@@ -3369,8 +3373,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
                                    ((estab && opt_rx->tstamp_ok) ||
                                     (!estab && sysctl_tcp_timestamps))) {
                                        opt_rx->saw_tstamp = 1;
-                                       opt_rx->rcv_tsval = ntohl(get_unaligned((__be32 *)ptr));
-                                       opt_rx->rcv_tsecr = ntohl(get_unaligned((__be32 *)(ptr+4)));
+                                       opt_rx->rcv_tsval = get_unaligned_be32(ptr);
+                                       opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
                                }
                                break;
                        case TCPOPT_SACK_PERM:
@@ -4925,8 +4929,7 @@ step5:
        tcp_data_snd_check(sk);
        tcp_ack_snd_check(sk);
 
-       if (tcp_defer_accept_check(sk))
-               return -1;
+       tcp_defer_accept_check(sk);
        return 0;
 
 csum_error: