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

Conflicts:
	drivers/net/sh_eth.c

4 files changed, 82 insertions, 23 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f6a0af7..26fb50e 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -447,6 +447,28 @@ extern int sysctl_tcp_synack_retries;
 
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
+/* Decide when to expire the request and when to resend SYN-ACK */
+static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
+				  const int max_retries,
+				  const u8 rskq_defer_accept,
+				  int *expire, int *resend)
+{
+	if (!rskq_defer_accept) {
+		*expire = req->retrans >= thresh;
+		*resend = 1;
+		return;
+	}
+	*expire = req->retrans >= thresh &&
+		  (!inet_rsk(req)->acked || req->retrans >= max_retries);
+	/*
+	 * Do not resend while waiting for data after ACK,
+	 * start to resend on end of deferring period to give
+	 * last chance for data or ACK to create established socket.
+	 */
+	*resend = !inet_rsk(req)->acked ||
+		  req->retrans >= rskq_defer_accept - 1;
+}
+
 void inet_csk_reqsk_queue_prune(struct sock *parent,
 				const unsigned long interval,
 				const unsigned long timeout,
@@ -502,9 +524,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if ((req->retrans < thresh ||
-				     (inet_rsk(req)->acked && req->retrans < max_retries))
-				    && !req->rsk_ops->rtx_syn_ack(parent, req)) {
+				int expire = 0, resend = 0;
+
+				syn_ack_recalc(req, thresh, max_retries,
+					       queue->rskq_defer_accept,
+					       &expire, &resend);
+				if (!expire &&
+				    (!resend ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req) ||
+				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 2445fed..a72f43c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -634,17 +634,16 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 				break;
 			}
 			dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr);
-			if (dev) {
+			if (dev)
 				mreq.imr_ifindex = dev->ifindex;
-				dev_put(dev);
-			}
 		} else
-			dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
+			dev = dev_get_by_index(sock_net(sk), mreq.imr_ifindex);
 
 
 		err = -EADDRNOTAVAIL;
 		if (!dev)
 			break;
+		dev_put(dev);
 
 		err = -EINVAL;
 		if (sk->sk_bound_dev_if &&
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 206a291..e0cfa63 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,6 +326,43 @@ void tcp_enter_memory_pressure(struct sock *sk)
 
 EXPORT_SYMBOL(tcp_enter_memory_pressure);
 
+/* Convert seconds to retransmits based on initial and max timeout */
+static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
+{
+	u8 res = 0;
+
+	if (seconds > 0) {
+		int period = timeout;
+
+		res = 1;
+		while (seconds > period && res < 255) {
+			res++;
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return res;
+}
+
+/* Convert retransmits to seconds based on initial and max timeout */
+static int retrans_to_secs(u8 retrans, int timeout, int rto_max)
+{
+	int period = 0;
+
+	if (retrans > 0) {
+		period = timeout;
+		while (--retrans) {
+			timeout <<= 1;
+			if (timeout > rto_max)
+				timeout = rto_max;
+			period += timeout;
+		}
+	}
+	return period;
+}
+
 /*
  *	Wait for a TCP event.
  *
@@ -1405,7 +1442,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				goto found_ok_skb;
 			if (tcp_hdr(skb)->fin)
 				goto found_fin_ok;
-			WARN_ON(!(flags & MSG_PEEK));
+			WARN(!(flags & MSG_PEEK), KERN_INFO "recvmsg bug 2: "
+					"copied %X seq %X\n", *seq,
+					TCP_SKB_CB(skb)->seq);
 		}
 
 		/* Well, if we have backlog, try to process it now yet. */
@@ -2163,16 +2202,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_DEFER_ACCEPT:
-		icsk->icsk_accept_queue.rskq_defer_accept = 0;
-		if (val > 0) {
-			/* Translate value in seconds to number of
-			 * retransmits */
-			while (icsk->icsk_accept_queue.rskq_defer_accept < 32 &&
-			       val > ((TCP_TIMEOUT_INIT / HZ) <<
-				       icsk->icsk_accept_queue.rskq_defer_accept))
-				icsk->icsk_accept_queue.rskq_defer_accept++;
-			icsk->icsk_accept_queue.rskq_defer_accept++;
-		}
+		/* Translate value in seconds to number of retransmits */
+		icsk->icsk_accept_queue.rskq_defer_accept =
+			secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+					TCP_RTO_MAX / HZ);
 		break;
 
 	case TCP_WINDOW_CLAMP:
@@ -2353,8 +2386,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 			val = (val ? : sysctl_tcp_fin_timeout) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
-		val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 :
-			((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1));
+		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
+				      TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e320afe..4c03598 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -641,10 +641,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!(flg & TCP_FLAG_ACK))
 		return NULL;
 
-	/* If TCP_DEFER_ACCEPT is set, drop bare ACK. */
-	if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
+	/* While TCP_DEFER_ACCEPT is active, drop bare ACK. */
+	if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept &&
 	    TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) {
-		inet_csk(sk)->icsk_accept_queue.rskq_defer_accept--;
 		inet_rsk(req)->acked = 1;
 		return NULL;
 	}