Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

4 files changed, 38 insertions, 15 deletions

diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index a5badd0..7370d14 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -375,12 +375,12 @@ static void br_make_forwarding(struct net_bridge_port *p)
 	if (p->state != BR_STATE_BLOCKING)
 		return;
 
-	if (br->forward_delay == 0) {
+	if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) {
 		p->state = BR_STATE_FORWARDING;
 		br_topology_change_detection(br);
 		del_timer(&p->forward_delay_timer);
 	}
-	else if (p->br->stp_enabled == BR_KERNEL_STP)
+	else if (br->stp_enabled == BR_KERNEL_STP)
 		p->state = BR_STATE_LISTENING;
 	else
 		p->state = BR_STATE_LEARNING;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 62f775c..34340c9 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -39,7 +39,7 @@
 
 /* Number of delay samples for detecting the increase of delay */
 #define HYSTART_MIN_SAMPLES	8
-#define HYSTART_DELAY_MIN	(2U<<3)
+#define HYSTART_DELAY_MIN	(4U<<3)
 #define HYSTART_DELAY_MAX	(16U<<3)
 #define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
 
@@ -52,6 +52,7 @@ static int tcp_friendliness __read_mostly = 1;
 static int hystart __read_mostly = 1;
 static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY;
 static int hystart_low_window __read_mostly = 16;
+static int hystart_ack_delta __read_mostly = 2;
 
 static u32 cube_rtt_scale __read_mostly;
 static u32 beta_scale __read_mostly;
@@ -75,6 +76,8 @@ MODULE_PARM_DESC(hystart_detect, "hyrbrid slow start detection mechanisms"
 		 " 1: packet-train 2: delay 3: both packet-train and delay");
 module_param(hystart_low_window, int, 0644);
 MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start");
+module_param(hystart_ack_delta, int, 0644);
+MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)");
 
 /* BIC TCP Parameters */
 struct bictcp {
@@ -85,7 +88,7 @@ struct bictcp {
 	u32	last_time;	/* time when updated last_cwnd */
 	u32	bic_origin_point;/* origin point of bic function */
 	u32	bic_K;		/* time to origin point from the beginning of the current epoch */
-	u32	delay_min;	/* min delay */
+	u32	delay_min;	/* min delay (msec << 3) */
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
@@ -95,7 +98,7 @@ struct bictcp {
 	u8	found;		/* the exit point is found? */
 	u32	round_start;	/* beginning of each round */
 	u32	end_seq;	/* end_seq of the round */
-	u32	last_jiffies;	/* last time when the ACK spacing is close */
+	u32	last_ack;	/* last time when the ACK spacing is close */
 	u32	curr_rtt;	/* the minimum rtt of current round */
 };
 
@@ -116,12 +119,21 @@ static inline void bictcp_reset(struct bictcp *ca)
 	ca->found = 0;
 }
 
+static inline u32 bictcp_clock(void)
+{
+#if HZ < 1000
+	return ktime_to_ms(ktime_get_real());
+#else
+	return jiffies_to_msecs(jiffies);
+#endif
+}
+
 static inline void bictcp_hystart_reset(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 
-	ca->round_start = ca->last_jiffies = jiffies;
+	ca->round_start = ca->last_ack = bictcp_clock();
 	ca->end_seq = tp->snd_nxt;
 	ca->curr_rtt = 0;
 	ca->sample_cnt = 0;
@@ -236,8 +248,8 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 	 */
 
 	/* change the unit from HZ to bictcp_HZ */
-	t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
-	     << BICTCP_HZ) / HZ;
+	t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3)
+	      - ca->epoch_start) << BICTCP_HZ) / HZ;
 
 	if (t < ca->bic_K)		/* t - K */
 		offs = ca->bic_K - t;
@@ -258,6 +270,13 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
 		ca->cnt = 100 * cwnd;              /* very small increment*/
 	}
 
+	/*
+	 * The initial growth of cubic function may be too conservative
+	 * when the available bandwidth is still unknown.
+	 */
+	if (ca->loss_cwnd == 0 && ca->cnt > 20)
+		ca->cnt = 20;	/* increase cwnd 5% per RTT */
+
 	/* TCP Friendly */
 	if (tcp_friendliness) {
 		u32 scale = beta_scale;
@@ -339,12 +358,12 @@ static void hystart_update(struct sock *sk, u32 delay)
 	struct bictcp *ca = inet_csk_ca(sk);
 
 	if (!(ca->found & hystart_detect)) {
-		u32 curr_jiffies = jiffies;
+		u32 now = bictcp_clock();
 
 		/* first detection parameter - ack-train detection */
-		if (curr_jiffies - ca->last_jiffies <= msecs_to_jiffies(2)) {
-			ca->last_jiffies = curr_jiffies;
-			if (curr_jiffies - ca->round_start >= ca->delay_min>>4)
+		if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
+			ca->last_ack = now;
+			if ((s32)(now - ca->round_start) > ca->delay_min >> 4)
 				ca->found |= HYSTART_ACK_TRAIN;
 		}
 
@@ -391,7 +410,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 	if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
 		return;
 
-	delay = usecs_to_jiffies(rtt_us) << 3;
+	delay = (rtt_us << 3) / USEC_PER_MSEC;
 	if (delay == 0)
 		delay = 1;
 
@@ -447,6 +466,10 @@ static int __init cubictcp_register(void)
 	/* divide by bic_scale and by constant Srtt (100ms) */
 	do_div(cube_factor, bic_scale * 10);
 
+	/* hystart needs ms clock resolution */
+	if (hystart && HZ < 1000)
+		cubictcp.flags |= TCP_CONG_RTT_STAMP;
+
 	return tcp_register_congestion_control(&cubictcp);
 }
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 08ea735..da782e7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3350,7 +3350,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
 						 net_invalid_timestamp()))
 					rtt_us = ktime_us_delta(ktime_get_real(),
 								last_ackt);
-				else if (ca_seq_rtt > 0)
+				else if (ca_seq_rtt >= 0)
 					rtt_us = jiffies_to_usecs(ca_seq_rtt);
 			}
 
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index de87018..ef70615 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1124,7 +1124,7 @@ restart:
 
 	/* Latch our state.
 
-	   It is tricky place. We need to grab write lock and cannot
+	   It is tricky place. We need to grab our state lock and cannot
 	   drop lock on peer. It is dangerous because deadlock is
 	   possible. Connect to self case and simultaneous
 	   attempt to connect are eliminated by checking socket