net: compat_mmsghdr must be used in sys_recvmmsg

[safe/jmp/linux-2.6] / net / ipv4 / tcp_cong.c

diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index ccd8840..6428b34 100644 (file)
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -115,8 +115,8 @@ int tcp_set_default_congestion_control(const char *name)
 
        spin_lock(&tcp_cong_list_lock);
        ca = tcp_ca_find(name);
-#ifdef CONFIG_KMOD
-       if (!ca && capable(CAP_SYS_MODULE)) {
+#ifdef CONFIG_MODULES
+       if (!ca && capable(CAP_NET_ADMIN)) {
                spin_unlock(&tcp_cong_list_lock);
 
                request_module("tcp_%s", name);
@@ -126,7 +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;
        }
@@ -181,7 +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",
@@ -212,16 +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);
@@ -244,9 +244,9 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
        if (ca == icsk->icsk_ca_ops)
                goto out;
 
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
        /* not found attempt to autoload module */
-       if (!ca && capable(CAP_SYS_MODULE)) {
+       if (!ca && capable(CAP_NET_ADMIN)) {
                rcu_read_unlock();
                request_module("tcp_%s", name);
                rcu_read_lock();
@@ -256,7 +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))
@@ -274,32 +274,55 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
        return err;
 }
 
+/* RFC2861 Check whether we are limited by application or congestion window
+ * This is the inverse of cwnd check in tcp_tso_should_defer
+ */
+int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
+{
+       const struct tcp_sock *tp = tcp_sk(sk);
+       u32 left;
+
+       if (in_flight >= tp->snd_cwnd)
+               return 1;
+
+       left = tp->snd_cwnd - in_flight;
+       if (sk_can_gso(sk) &&
+           left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
+           left * tp->mss_cache < sk->sk_gso_max_size)
+               return 1;
+       return left <= tcp_max_burst(tp);
+}
+EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
 
 /*
- * Slow start (exponential increase) with
- * RFC3742 Limited Slow Start (fast linear increase) support.
+ * 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)
 {
-       int cnt = 0;
-
-       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;
 
-       if (sysctl_tcp_max_ssthresh > 0 &&
-           tp->snd_cwnd > sysctl_tcp_max_ssthresh)
-               cnt += sysctl_tcp_max_ssthresh>>1;
+       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;
+               cnt = tp->snd_cwnd;                     /* exponential increase */
 
-       /* RFC3465: We MAY increase by 2 if discovered delayed ack */
+       /* 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;
@@ -313,6 +336,19 @@ void tcp_slow_start(struct tcp_sock *tp)
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+{
+       if (tp->snd_cwnd_cnt >= w) {
+               if (tp->snd_cwnd < tp->snd_cwnd_clamp)
+                       tp->snd_cwnd++;
+               tp->snd_cwnd_cnt = 0;
+       } else {
+               tp->snd_cwnd_cnt++;
+       }
+}
+EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
+
 /*
  * TCP Reno congestion control
  * This is special case used for fallback as well.
@@ -320,8 +356,7 @@ 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)
 {
        struct tcp_sock *tp = tcp_sk(sk);
 
@@ -343,13 +378,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 rtt, u32 in_flight,
                                tp->snd_cwnd++;
                }
        } else {
-               /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd */
-               if (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
-                       if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-                               tp->snd_cwnd++;
-                       tp->snd_cwnd_cnt = 0;
-               } else
-                       tp->snd_cwnd_cnt++;
+               tcp_cong_avoid_ai(tp, tp->snd_cwnd);
        }
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
@@ -371,8 +400,8 @@ 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,