Pull bugzilla-7880 into release branch

[pandora-kernel.git] / net / ipv4 / tcp_cong.c

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 5c8caf4..55fca18 100644 (file)
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -12,6 +12,8 @@
 #include <linux/list.h>
 #include <net/tcp.h>
 
+int sysctl_tcp_max_ssthresh = 0;
+
 static DEFINE_SPINLOCK(tcp_cong_list_lock);
 static LIST_HEAD(tcp_cong_list);
 
@@ -77,18 +79,19 @@ void tcp_init_congestion_control(struct sock *sk)
        struct inet_connection_sock *icsk = inet_csk(sk);
        struct tcp_congestion_ops *ca;
 
-       if (icsk->icsk_ca_ops != &tcp_init_congestion_ops)
-               return;
+       /* if no choice made yet assign the current value set as default */
+       if (icsk->icsk_ca_ops == &tcp_init_congestion_ops) {
+               rcu_read_lock();
+               list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
+                       if (try_module_get(ca->owner)) {
+                               icsk->icsk_ca_ops = ca;
+                               break;
+                       }
 
-       rcu_read_lock();
-       list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
-               if (try_module_get(ca->owner)) {
-                       icsk->icsk_ca_ops = ca;
-                       break;
+                       /* fallback to next available */
                }
-
+               rcu_read_unlock();
        }
-       rcu_read_unlock();
 
        if (icsk->icsk_ca_ops->init)
                icsk->icsk_ca_ops->init(sk);
@@ -123,7 +126,7 @@ int tcp_set_default_congestion_control(const char *name)
 #endif
 
        if (ca) {
-               ca->non_restricted = 1; /* default is always allowed */
+               ca->flags |= TCP_CONG_NON_RESTRICTED;   /* default is always allowed */
                list_move(&ca->list, &tcp_cong_list);
                ret = 0;
        }
@@ -178,7 +181,7 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen)
        *buf = '\0';
        rcu_read_lock();
        list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
-               if (!ca->non_restricted)
+               if (!(ca->flags & TCP_CONG_NON_RESTRICTED))
                        continue;
                offs += snprintf(buf + offs, maxlen - offs,
                                 "%s%s",
@@ -209,16 +212,16 @@ int tcp_set_allowed_congestion_control(char *val)
                }
        }
 
-       /* pass 2 clear */
+       /* pass 2 clear old values */
        list_for_each_entry_rcu(ca, &tcp_cong_list, list)
-               ca->non_restricted = 0;
+               ca->flags &= ~TCP_CONG_NON_RESTRICTED;
 
        /* pass 3 mark as allowed */
        while ((name = strsep(&val, " ")) && *name) {
                ca = tcp_ca_find(name);
                WARN_ON(!ca);
                if (ca)
-                       ca->non_restricted = 1;
+                       ca->flags |= TCP_CONG_NON_RESTRICTED;
        }
 out:
        spin_unlock(&tcp_cong_list_lock);
@@ -236,6 +239,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 
        rcu_read_lock();
        ca = tcp_ca_find(name);
+
        /* no change asking for existing value */
        if (ca == icsk->icsk_ca_ops)
                goto out;
@@ -252,7 +256,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
        if (!ca)
                err = -ENOENT;
 
-       else if (!(ca->non_restricted || capable(CAP_NET_ADMIN)))
+       else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || capable(CAP_NET_ADMIN)))
                err = -EPERM;
 
        else if (!try_module_get(ca->owner))
@@ -261,7 +265,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
        else {
                tcp_cleanup_congestion_control(sk);
                icsk->icsk_ca_ops = ca;
-               if (icsk->icsk_ca_ops->init)
+
+               if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
                        icsk->icsk_ca_ops->init(sk);
        }
  out:
@@ -271,29 +276,44 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
 
 
 /*
- * Linear increase during slow start
+ * Slow start is used when congestion window is less than slow start
+ * threshold. This version implements the basic RFC2581 version
+ * and optionally supports:
+ *     RFC3742 Limited Slow Start        - growth limited to max_ssthresh
+ *     RFC3465 Appropriate Byte Counting - growth limited by bytes acknowledged
  */
 void tcp_slow_start(struct tcp_sock *tp)
 {
-       if (sysctl_tcp_abc) {
-               /* RFC3465: Slow Start
-                * TCP sender SHOULD increase cwnd by the number of
-                * previously unacknowledged bytes ACKed by each incoming
-                * acknowledgment, provided the increase is not more than L
-                */
-               if (tp->bytes_acked < tp->mss_cache)
-                       return;
+       int cnt; /* increase in packets */
+
+       /* RFC3465: ABC Slow start
+        * Increase only after a full MSS of bytes is acked
+        *
+        * TCP sender SHOULD increase cwnd by the number of
+        * previously unacknowledged bytes ACKed by each incoming
+        * acknowledgment, provided the increase is not more than L
+        */
+       if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache)
+               return;
 
-               /* We MAY increase by 2 if discovered delayed ack */
-               if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache) {
-                       if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-                               tp->snd_cwnd++;
-               }
-       }
+       if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
+               cnt = sysctl_tcp_max_ssthresh >> 1;     /* limited slow start */
+       else
+               cnt = tp->snd_cwnd;                     /* exponential increase */
+
+       /* RFC3465: ABC
+        * We MAY increase by 2 if discovered delayed ack
+        */
+       if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache)
+               cnt <<= 1;
        tp->bytes_acked = 0;
 
-       if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-               tp->snd_cwnd++;
+       tp->snd_cwnd_cnt += cnt;
+       while (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
+               tp->snd_cwnd_cnt -= tp->snd_cwnd;
+               if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+                       tp->snd_cwnd++;
+       }
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
@@ -304,8 +324,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start);
 /* This is Jacobson's slow start and congestion avoidance.
  * SIGCOMM '88, p. 328.
  */
-void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 rtt, u32 in_flight,
-                        int flag)
+void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight, int flag)
 {
        struct tcp_sock *tp = tcp_sk(sk);
 
@@ -355,8 +374,8 @@ u32 tcp_reno_min_cwnd(const struct sock *sk)
 EXPORT_SYMBOL_GPL(tcp_reno_min_cwnd);
 
 struct tcp_congestion_ops tcp_reno = {
+       .flags          = TCP_CONG_NON_RESTRICTED,
        .name           = "reno",
-       .non_restricted = 1,
        .owner          = THIS_MODULE,
        .ssthresh       = tcp_reno_ssthresh,
        .cong_avoid     = tcp_reno_cong_avoid,