14 files changed, 81 insertions, 79 deletions

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index abf6352f990f..5b77bdaa57dd 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1056,10 +1056,9 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
         if (!in_dev) {
                 if (event == NETDEV_REGISTER) {
                         in_dev = inetdev_init(dev);
+                        if (!in_dev)
+                                return notifier_from_errno(-ENOMEM);
                         if (dev == &loopback_dev) {
-                                if (!in_dev)
-                                        panic("devinet: "
-                                              "Failed to create loopback\n");
                                 IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
                                 IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
                         }
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 251346828cb4..2f14745a9e1f 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -513,11 +513,8 @@ void ip_options_undo(struct ip_options * opt)
 
 static struct ip_options *ip_options_get_alloc(const int optlen)
 {
-        struct ip_options *opt = kmalloc(sizeof(*opt) + ((optlen + 3) & ~3),
-                                         GFP_KERNEL);
-        if (opt)
-                memset(opt, 0, sizeof(*opt));
-        return opt;
+        return kzalloc(sizeof(struct ip_options) + ((optlen + 3) & ~3),
+                       GFP_KERNEL);
 }
 
 static int ip_options_get_finish(struct ip_options **optp,
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index 900ce29db382..666e080a74a3 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -128,7 +128,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
 #define IP_VS_XMIT(skb, rt)                             \
 do {                                                    \
         (skb)->ipvs_property = 1;                       \
-        (skb)->ip_summed = CHECKSUM_NONE;               \
+        skb_forward_csum(skb);                          \
         NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, (skb), NULL,  \
                 (rt)->u.dst.dev, dst_output);           \
 } while (0)
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index 519de091a94d..4586211e3757 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -206,7 +206,7 @@ static void bictcp_state(struct sock *sk, u8 new_state)
 /* Track delayed acknowledgment ratio using sliding window
  * ratio = (15*ratio + sample) / 16
  */
-static void bictcp_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index d17da30d82d6..485d7ea35f75 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -246,38 +246,12 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
                 ca->cnt = 1;
 }
 
-
-/* Keep track of minimum rtt */
-static inline void measure_delay(struct sock *sk)
-{
-        const struct tcp_sock *tp = tcp_sk(sk);
-        struct bictcp *ca = inet_csk_ca(sk);
-        u32 delay;
-
-        /* No time stamp */
-        if (!(tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) ||
-             /* Discard delay samples right after fast recovery */
-            (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
-                return;
-
-        delay = (tcp_time_stamp - tp->rx_opt.rcv_tsecr)<<3;
-        if (delay == 0)
-                delay = 1;
-
-        /* first time call or link delay decreases */
-        if (ca->delay_min == 0 || ca->delay_min > delay)
-                ca->delay_min = delay;
-}
-
 static void bictcp_cong_avoid(struct sock *sk, u32 ack,
                               u32 in_flight, int data_acked)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct bictcp *ca = inet_csk_ca(sk);
 
-        if (data_acked)
-                measure_delay(sk);
-
         if (!tcp_is_cwnd_limited(sk, in_flight))
                 return;
 
@@ -334,17 +308,33 @@ static void bictcp_state(struct sock *sk, u8 new_state)
 /* Track delayed acknowledgment ratio using sliding window
  * ratio = (15*ratio + sample) / 16
  */
-static void bictcp_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
+        struct bictcp *ca = inet_csk_ca(sk);
+        u32 delay;
 
         if (cnt > 0 && icsk->icsk_ca_state == TCP_CA_Open) {
-                struct bictcp *ca = inet_csk_ca(sk);
                 cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
                 ca->delayed_ack += cnt;
         }
-}
 
+        /* Some calls are for duplicates without timetamps */
+        if (rtt_us < 0)
+                return;
+
+        /* Discard delay samples right after fast recovery */
+        if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+                return;
+
+        delay = usecs_to_jiffies(rtt_us) << 3;
+        if (delay == 0)
+                delay = 1;
+
+        /* first time call or link delay decreases */
+        if (ca->delay_min == 0 || ca->delay_min > delay)
+                ca->delay_min = delay;
+}
 
 static struct tcp_congestion_ops cubictcp = {
         .init           = bictcp_init,
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 08a02e6045c9..b66556c0a5bd 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -76,12 +76,11 @@ static u32 htcp_cwnd_undo(struct sock *sk)
         return max(tp->snd_cwnd, (tp->snd_ssthresh << 7) / ca->beta);
 }
 
-static inline void measure_rtt(struct sock *sk)
+static inline void measure_rtt(struct sock *sk, u32 srtt)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
         const struct tcp_sock *tp = tcp_sk(sk);
         struct htcp *ca = inet_csk_ca(sk);
-        u32 srtt = tp->srtt >> 3;
 
         /* keep track of minimum RTT seen so far, minRTT is zero at first */
         if (ca->minRTT > srtt || !ca->minRTT)
@@ -98,7 +97,7 @@ static inline void measure_rtt(struct sock *sk)
         }
 }
 
-static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
         const struct tcp_sock *tp = tcp_sk(sk);
@@ -108,6 +107,9 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, ktime_t
         if (icsk->icsk_ca_state == TCP_CA_Open)
                 ca->pkts_acked = pkts_acked;
 
+        if (rtt > 0)
+                measure_rtt(sk, usecs_to_jiffies(rtt));
+
         if (!use_bandwidth_switch)
                 return;
 
@@ -237,8 +239,6 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack,
         if (tp->snd_cwnd <= tp->snd_ssthresh)
                 tcp_slow_start(tp);
         else {
-                measure_rtt(sk);
-
                 /* In dangerous area, increase slowly.
                  * In theory this is tp->snd_cwnd += alpha / tp->snd_cwnd
                  */
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index cc5de6f69d46..64f1cbaf96e8 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -83,18 +83,16 @@ static void tcp_illinois_init(struct sock *sk)
 }
 
 /* Measure RTT for each ack. */
-static void tcp_illinois_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void tcp_illinois_acked(struct sock *sk, u32 pkts_acked, s32 rtt)
 {
         struct illinois *ca = inet_csk_ca(sk);
-        u32 rtt;
 
         ca->acked = pkts_acked;
 
-        if (ktime_equal(last, net_invalid_timestamp()))
+        /* dup ack, no rtt sample */
+        if (rtt < 0)
                 return;
 
-        rtt = ktime_to_us(net_timedelta(last));
-
         /* ignore bogus values, this prevents wraparound in alpha math */
         if (rtt > RTT_MAX)
                 rtt = RTT_MAX;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fec8a7a4dbaf..378ca8a086a3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1851,19 +1851,22 @@ static inline u32 tcp_cwnd_min(const struct sock *sk)
 }
 
 /* Decrease cwnd each second ack. */
-static void tcp_cwnd_down(struct sock *sk)
+static void tcp_cwnd_down(struct sock *sk, int flag)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         int decr = tp->snd_cwnd_cnt + 1;
 
-        tp->snd_cwnd_cnt = decr&1;
-        decr >>= 1;
+        if ((flag&FLAG_FORWARD_PROGRESS) ||
+            (IsReno(tp) && !(flag&FLAG_NOT_DUP))) {
+                tp->snd_cwnd_cnt = decr&1;
+                decr >>= 1;
 
-        if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
-                tp->snd_cwnd -= decr;
+                if (decr && tp->snd_cwnd > tcp_cwnd_min(sk))
+                        tp->snd_cwnd -= decr;
 
-        tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
-        tp->snd_cwnd_stamp = tcp_time_stamp;
+                tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp)+1);
+                tp->snd_cwnd_stamp = tcp_time_stamp;
+        }
 }
 
 /* Nothing was retransmitted or returned timestamp is less
@@ -2060,7 +2063,7 @@ static void tcp_try_to_open(struct sock *sk, int flag)
                 }
                 tcp_moderate_cwnd(tp);
         } else {
-                tcp_cwnd_down(sk);
+                tcp_cwnd_down(sk, flag);
         }
 }
 
@@ -2109,7 +2112,10 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
 {
         struct inet_connection_sock *icsk = inet_csk(sk);
         struct tcp_sock *tp = tcp_sk(sk);
-        int is_dupack = (tp->snd_una == prior_snd_una && !(flag&FLAG_NOT_DUP));
+        int is_dupack = (tp->snd_una == prior_snd_una &&
+                         (!(flag&FLAG_NOT_DUP) ||
+                          ((flag&FLAG_DATA_SACKED) &&
+                           (tp->fackets_out > tp->reordering))));
 
         /* Some technical things:
          * 1. Reno does not count dupacks (sacked_out) automatically. */
@@ -2260,7 +2266,7 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
 
         if (is_dupack || tcp_head_timedout(sk))
                 tcp_update_scoreboard(sk);
-        tcp_cwnd_down(sk);
+        tcp_cwnd_down(sk, flag);
         tcp_xmit_retransmit_queue(sk);
 }
 
@@ -2490,12 +2496,23 @@ static int tcp_clean_rtx_queue(struct sock *sk, __s32 *seq_rtt_p)
                 tcp_ack_update_rtt(sk, acked, seq_rtt);
                 tcp_ack_packets_out(sk);
 
-                /* Is the ACK triggering packet unambiguous? */
-                if (acked & FLAG_RETRANS_DATA_ACKED)
-                        last_ackt = net_invalid_timestamp();
+                if (ca_ops->pkts_acked) {
+                        s32 rtt_us = -1;
+
+                        /* Is the ACK triggering packet unambiguous? */
+                        if (!(acked & FLAG_RETRANS_DATA_ACKED)) {
+                                /* High resolution needed and available? */
+                                if (ca_ops->flags & TCP_CONG_RTT_STAMP &&
+                                    !ktime_equal(last_ackt,
+                                                 net_invalid_timestamp()))
+                                        rtt_us = ktime_us_delta(ktime_get_real(),
+                                                                last_ackt);
+                                else if (seq_rtt > 0)
+                                        rtt_us = jiffies_to_usecs(seq_rtt);
+                        }
 
-                if (ca_ops->pkts_acked)
-                        ca_ops->pkts_acked(sk, pkts_acked, last_ackt);
+                        ca_ops->pkts_acked(sk, pkts_acked, rtt_us);
+                }
         }
 
 #if FASTRETRANS_DEBUG > 0
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 80e140e3ec2d..e7f5ef92cbd8 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -260,13 +260,13 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt)
  * newReno in increase case.
  * We work it out by following the idea from TCP-LP's paper directly
  */
-static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, ktime_t last)
+static void tcp_lp_pkts_acked(struct sock *sk, u32 num_acked, s32 rtt_us)
 {
         struct tcp_sock *tp = tcp_sk(sk);
         struct lp *lp = inet_csk_ca(sk);
 
-        if (!ktime_equal(last, net_invalid_timestamp()))
-                tcp_lp_rtt_sample(sk,  ktime_to_us(net_timedelta(last)));
+        if (rtt_us > 0)
+                tcp_lp_rtt_sample(sk, rtt_us);
 
         /* calc inference */
         if (tcp_time_stamp > tp->rx_opt.rcv_tsecr)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 914e0307f7af..b49dedcda52d 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -112,16 +112,16 @@ EXPORT_SYMBOL_GPL(tcp_vegas_init);
  *   o min-filter RTT samples from a much longer window (forever for now)
  *     to find the propagation delay (baseRTT)
  */
-void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
         struct vegas *vegas = inet_csk_ca(sk);
         u32 vrtt;
 
-        if (ktime_equal(last, net_invalid_timestamp()))
+        if (rtt_us < 0)
                 return;
 
         /* Never allow zero rtt or baseRTT */
-        vrtt = ktime_to_us(net_timedelta(last)) + 1;
+        vrtt = rtt_us + 1;
 
         /* Filter to find propagation delay: */
         if (vrtt < vegas->baseRTT)
diff --git a/net/ipv4/tcp_vegas.h b/net/ipv4/tcp_vegas.h
index 502fa8183634..6c0eea2f8249 100644
--- a/net/ipv4/tcp_vegas.h
+++ b/net/ipv4/tcp_vegas.h
@@ -17,7 +17,7 @@ struct vegas {
 
 extern void tcp_vegas_init(struct sock *sk);
 extern void tcp_vegas_state(struct sock *sk, u8 ca_state);
-extern void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, ktime_t last);
+extern void tcp_vegas_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us);
 extern void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event);
 extern void tcp_vegas_get_info(struct sock *sk, u32 ext, struct sk_buff *skb);
 
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 7a55ddf86032..8fb2aee0b1a4 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -69,16 +69,16 @@ static void tcp_veno_init(struct sock *sk)
 }
 
 /* Do rtt sampling needed for Veno. */
-static void tcp_veno_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void tcp_veno_pkts_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
         struct veno *veno = inet_csk_ca(sk);
         u32 vrtt;
 
-        if (ktime_equal(last, net_invalid_timestamp()))
+        if (rtt_us < 0)
                 return;
 
         /* Never allow zero rtt or baseRTT */
-        vrtt = ktime_to_us(net_timedelta(last)) + 1;
+        vrtt = rtt_us + 1;
 
         /* Filter to find propagation delay: */
         if (vrtt < veno->basertt)
diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c
index e61e09dd513e..20151d6a6241 100644
--- a/net/ipv4/tcp_westwood.c
+++ b/net/ipv4/tcp_westwood.c
@@ -100,11 +100,12 @@ static void westwood_filter(struct westwood *w, u32 delta)
  * Called after processing group of packets.
  * but all westwood needs is the last sample of srtt.
  */
-static void tcp_westwood_pkts_acked(struct sock *sk, u32 cnt, ktime_t last)
+static void tcp_westwood_pkts_acked(struct sock *sk, u32 cnt, s32 rtt)
 {
         struct westwood *w = inet_csk_ca(sk);
-        if (cnt > 0)
-                w->rtt = tcp_sk(sk)->srtt >> 3;
+
+        if (rtt > 0)
+                w->rtt = usecs_to_jiffies(rtt);
 }
 
 /*
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index c04b7c6ec702..c107fba7430e 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -58,7 +58,7 @@ static void tcp_yeah_init(struct sock *sk)
 }
 
 
-static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
+static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, s32 rtt_us)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
         struct yeah *yeah = inet_csk_ca(sk);
@@ -66,7 +66,7 @@ static void tcp_yeah_pkts_acked(struct sock *sk, u32 pkts_acked, ktime_t last)
         if (icsk->icsk_ca_state == TCP_CA_Open)
                 yeah->pkts_acked = pkts_acked;
 
-        tcp_vegas_pkts_acked(sk, pkts_acked, last);
+        tcp_vegas_pkts_acked(sk, pkts_acked, rtt_us);
 }
 
 static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack,