Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	drivers/net/bonding/bond_3ad.h
	drivers/net/bonding/bond_main.c

Two minor conflicts in bonding, both of which were overlapping
changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 67 insertions, 90 deletions

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5ae609200674..f558433537b8 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1367,44 +1367,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc)
 	return false;
 }
 
-/* Increase asoc's rwnd by len and send any window update SACK if needed. */
-void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
+/* Update asoc's rwnd for the approximated state in the buffer,
+ * and check whether SACK needs to be sent.
+ */
+void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer)
 {
+	int rx_count;
 	struct sctp_chunk *sack;
 	struct timer_list *timer;
 
-	if (asoc->rwnd_over) {
-		if (asoc->rwnd_over >= len) {
-			asoc->rwnd_over -= len;
-		} else {
-			asoc->rwnd += (len - asoc->rwnd_over);
-			asoc->rwnd_over = 0;
-		}
-	} else {
-		asoc->rwnd += len;
-	}
+	if (asoc->ep->rcvbuf_policy)
+		rx_count = atomic_read(&asoc->rmem_alloc);
+	else
+		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
 
-	/* If we had window pressure, start recovering it
-	 * once our rwnd had reached the accumulated pressure
-	 * threshold.  The idea is to recover slowly, but up
-	 * to the initial advertised window.
-	 */
-	if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) {
-		int change = min(asoc->pathmtu, asoc->rwnd_press);
-		asoc->rwnd += change;
-		asoc->rwnd_press -= change;
-	}
+	if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0)
+		asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1;
+	else
+		asoc->rwnd = 0;
 
-	pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n",
-		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-		 asoc->a_rwnd);
+	pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n",
+		 __func__, asoc, asoc->rwnd, rx_count,
+		 asoc->base.sk->sk_rcvbuf);
 
 	/* Send a window update SACK if the rwnd has increased by at least the
 	 * minimum of the association's PMTU and half of the receive buffer.
 	 * The algorithm used is similar to the one described in
 	 * Section 4.2.3.3 of RFC 1122.
 	 */
-	if (sctp_peer_needs_update(asoc)) {
+	if (update_peer && sctp_peer_needs_update(asoc)) {
 		asoc->a_rwnd = asoc->rwnd;
 
 		pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u "
@@ -1426,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len)
 	}
 }
 
-/* Decrease asoc's rwnd by len. */
-void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
-{
-	int rx_count;
-	int over = 0;
-
-	if (unlikely(!asoc->rwnd || asoc->rwnd_over))
-		pr_debug("%s: association:%p has asoc->rwnd:%u, "
-			 "asoc->rwnd_over:%u!\n", __func__, asoc,
-			 asoc->rwnd, asoc->rwnd_over);
-
-	if (asoc->ep->rcvbuf_policy)
-		rx_count = atomic_read(&asoc->rmem_alloc);
-	else
-		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);
-
-	/* If we've reached or overflowed our receive buffer, announce
-	 * a 0 rwnd if rwnd would still be positive.  Store the
-	 * the potential pressure overflow so that the window can be restored
-	 * back to original value.
-	 */
-	if (rx_count >= asoc->base.sk->sk_rcvbuf)
-		over = 1;
-
-	if (asoc->rwnd >= len) {
-		asoc->rwnd -= len;
-		if (over) {
-			asoc->rwnd_press += asoc->rwnd;
-			asoc->rwnd = 0;
-		}
-	} else {
-		asoc->rwnd_over = len - asoc->rwnd;
-		asoc->rwnd = 0;
-	}
-
-	pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n",
-		 __func__, asoc, len, asoc->rwnd, asoc->rwnd_over,
-		 asoc->rwnd_press);
-}
 
 /* Build the bind address list for the association based on info from the
  * local endpoint and the remote peer.
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 483dcd71b3c5..591b44d3b7de 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -6176,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc,
 	 * PMTU.  In cases, such as loopback, this might be a rather
 	 * large spill over.
 	 */
-	if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over ||
+	if ((!chunk->data_accepted) && (!asoc->rwnd ||
 	    (datalen > asoc->rwnd + asoc->frag_point))) {
 
 		/* If this is the next TSN, consider reneging to make
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 9e91d6e5df63..981aaf8b6ace 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -64,6 +64,7 @@
 #include <linux/crypto.h>
 #include <linux/slab.h>
 #include <linux/file.h>
+#include <linux/compat.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -1368,11 +1369,19 @@ static int sctp_setsockopt_connectx(struct sock *sk,
 /*
  * New (hopefully final) interface for the API.
  * We use the sctp_getaddrs_old structure so that use-space library
- * can avoid any unnecessary allocations.   The only defferent part
+ * can avoid any unnecessary allocations. The only different part
  * is that we store the actual length of the address buffer into the
- * addrs_num structure member.  That way we can re-use the existing
+ * addrs_num structure member. That way we can re-use the existing
  * code.
  */
+#ifdef CONFIG_COMPAT
+struct compat_sctp_getaddrs_old {
+	sctp_assoc_t	assoc_id;
+	s32		addr_num;
+	compat_uptr_t	addrs;		/* struct sockaddr * */
+};
+#endif
+
 static int sctp_getsockopt_connectx3(struct sock *sk, int len,
 				     char __user *optval,
 				     int __user *optlen)
@@ -1381,16 +1390,30 @@ static int sctp_getsockopt_connectx3(struct sock *sk, int len,
 	sctp_assoc_t assoc_id = 0;
 	int err = 0;
 
-	if (len < sizeof(param))
-		return -EINVAL;
+#ifdef CONFIG_COMPAT
+	if (is_compat_task()) {
+		struct compat_sctp_getaddrs_old param32;
 
-	if (copy_from_user(&param, optval, sizeof(param)))
-		return -EFAULT;
+		if (len < sizeof(param32))
+			return -EINVAL;
+		if (copy_from_user(&param32, optval, sizeof(param32)))
+			return -EFAULT;
 
-	err = __sctp_setsockopt_connectx(sk,
-			(struct sockaddr __user *)param.addrs,
-			param.addr_num, &assoc_id);
+		param.assoc_id = param32.assoc_id;
+		param.addr_num = param32.addr_num;
+		param.addrs = compat_ptr(param32.addrs);
+	} else
+#endif
+	{
+		if (len < sizeof(param))
+			return -EINVAL;
+		if (copy_from_user(&param, optval, sizeof(param)))
+			return -EFAULT;
+	}
 
+	err = __sctp_setsockopt_connectx(sk, (struct sockaddr __user *)
+					 param.addrs, param.addr_num,
+					 &assoc_id);
 	if (err == 0 || err == -EINPROGRESS) {
 		if (copy_to_user(optval, &assoc_id, sizeof(assoc_id)))
 			return -EFAULT;
@@ -2092,12 +2115,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 		sctp_skb_pull(skb, copied);
 		skb_queue_head(&sk->sk_receive_queue, skb);
 
-		/* When only partial message is copied to the user, increase
-		 * rwnd by that amount. If all the data in the skb is read,
-		 * rwnd is updated when the event is freed.
-		 */
-		if (!sctp_ulpevent_is_notification(event))
-			sctp_assoc_rwnd_increase(event->asoc, copied);
 		goto out;
 	} else if ((event->msg_flags & MSG_NOTIFICATION) ||
 		   (event->msg_flags & MSG_EOR))
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7135e617ab0f..35c8923b5554 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -151,6 +151,7 @@ static struct ctl_table sctp_net_table[] = {
 	},
 	{
 		.procname	= "cookie_hmac_alg",
+		.data		= &init_net.sctp.sctp_hmac_alg,
 		.maxlen		= 8,
 		.mode		= 0644,
 		.proc_handler	= proc_sctp_do_hmac_alg,
@@ -401,15 +402,18 @@ static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write,
 
 int sctp_sysctl_net_register(struct net *net)
 {
-	struct ctl_table *table;
-	int i;
+	struct ctl_table *table = sctp_net_table;
+
+	if (!net_eq(net, &init_net)) {
+		int i;
 
-	table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
-	if (!table)
-		return -ENOMEM;
+		table = kmemdup(sctp_net_table, sizeof(sctp_net_table), GFP_KERNEL);
+		if (!table)
+			return -ENOMEM;
 
-	for (i = 0; table[i].data; i++)
-		table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+		for (i = 0; table[i].data; i++)
+			table[i].data += (char *)(&net->sctp) - (char *)&init_net.sctp;
+	}
 
 	net->sctp.sysctl_header = register_net_sysctl(net, "net/sctp", table);
 	return 0;
diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c
index 85c64658bd0b..8d198ae03606 100644
--- a/net/sctp/ulpevent.c
+++ b/net/sctp/ulpevent.c
@@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event,
 	skb = sctp_event2skb(event);
 	/* Set the owner and charge rwnd for bytes received.  */
 	sctp_ulpevent_set_owner(event, asoc);
-	sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb));
+	sctp_assoc_rwnd_update(asoc, false);
 
 	if (!skb->data_len)
 		return;
@@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 {
 	struct sk_buff *skb, *frag;
 	unsigned int	len;
+	struct sctp_association *asoc;
 
 	/* Current stack structures assume that the rcv buffer is
 	 * per socket.   For UDP style sockets this is not true as
@@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event)
 	}
 
 done:
-	sctp_assoc_rwnd_increase(event->asoc, len);
+	asoc = event->asoc;
+	sctp_association_hold(asoc);
 	sctp_ulpevent_release_owner(event);
+	sctp_assoc_rwnd_update(asoc, true);
+	sctp_association_put(asoc);
 }
 
 static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event)