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

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 44 insertions, 59 deletions

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 9b4e483..a9622b6 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -43,7 +43,8 @@
 #define SS_LISTENING	-1	/* socket is listening */
 #define SS_READY	-2	/* socket is connectionless */
 
-#define OVERLOAD_LIMIT_BASE	10000
+#define CONN_OVERLOAD_LIMIT	((TIPC_FLOW_CONTROL_WIN * 2 + 1) * \
+				SKB_TRUESIZE(TIPC_MAX_USER_MSG_SIZE))
 #define CONN_TIMEOUT_DEFAULT	8000	/* default connect timeout = 8s */
 
 struct tipc_sock {
@@ -129,19 +130,6 @@ static void advance_rx_queue(struct sock *sk)
 }
 
 /**
- * discard_rx_queue - discard all buffers in socket receive queue
- *
- * Caller must hold socket lock
- */
-static void discard_rx_queue(struct sock *sk)
-{
-	struct sk_buff *buf;
-
-	while ((buf = __skb_dequeue(&sk->sk_receive_queue)))
-		kfree_skb(buf);
-}
-
-/**
  * reject_rx_queue - reject all buffers in socket receive queue
  *
  * Caller must hold socket lock
@@ -215,7 +203,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol,
 
 	sock_init_data(sock, sk);
 	sk->sk_backlog_rcv = backlog_rcv;
-	sk->sk_rcvbuf = TIPC_FLOW_CONTROL_WIN * 2 * TIPC_MAX_USER_MSG_SIZE * 2;
 	sk->sk_data_ready = tipc_data_ready;
 	sk->sk_write_space = tipc_write_space;
 	tipc_sk(sk)->p = tp_ptr;
@@ -292,7 +279,7 @@ static int release(struct socket *sock)
 	res = tipc_deleteport(tport->ref);
 
 	/* Discard any remaining (connection-based) messages in receive queue */
-	discard_rx_queue(sk);
+	__skb_queue_purge(&sk->sk_receive_queue);
 
 	/* Reject any messages that accumulated in backlog queue */
 	sock->state = SS_DISCONNECTING;
@@ -516,8 +503,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock,
 	if (unlikely((m->msg_namelen < sizeof(*dest)) ||
 		     (dest->family != AF_TIPC)))
 		return -EINVAL;
-	if ((total_len > TIPC_MAX_USER_MSG_SIZE) ||
-	    (m->msg_iovlen > (unsigned int)INT_MAX))
+	if (total_len > TIPC_MAX_USER_MSG_SIZE)
 		return -EMSGSIZE;
 
 	if (iocb)
@@ -625,8 +611,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock,
 	if (unlikely(dest))
 		return send_msg(iocb, sock, m, total_len);
 
-	if ((total_len > TIPC_MAX_USER_MSG_SIZE) ||
-	    (m->msg_iovlen > (unsigned int)INT_MAX))
+	if (total_len > TIPC_MAX_USER_MSG_SIZE)
 		return -EMSGSIZE;
 
 	if (iocb)
@@ -711,8 +696,7 @@ static int send_stream(struct kiocb *iocb, struct socket *sock,
 		goto exit;
 	}
 
-	if ((total_len > (unsigned int)INT_MAX) ||
-	    (m->msg_iovlen > (unsigned int)INT_MAX)) {
+	if (total_len > (unsigned int)INT_MAX) {
 		res = -EMSGSIZE;
 		goto exit;
 	}
@@ -1155,34 +1139,6 @@ static void tipc_data_ready(struct sock *sk, int len)
 }
 
 /**
- * rx_queue_full - determine if receive queue can accept another message
- * @msg: message to be added to queue
- * @queue_size: current size of queue
- * @base: nominal maximum size of queue
- *
- * Returns 1 if queue is unable to accept message, 0 otherwise
- */
-static int rx_queue_full(struct tipc_msg *msg, u32 queue_size, u32 base)
-{
-	u32 threshold;
-	u32 imp = msg_importance(msg);
-
-	if (imp == TIPC_LOW_IMPORTANCE)
-		threshold = base;
-	else if (imp == TIPC_MEDIUM_IMPORTANCE)
-		threshold = base * 2;
-	else if (imp == TIPC_HIGH_IMPORTANCE)
-		threshold = base * 100;
-	else
-		return 0;
-
-	if (msg_connected(msg))
-		threshold *= 4;
-
-	return queue_size >= threshold;
-}
-
-/**
  * filter_connect - Handle all incoming messages for a connection-based socket
  * @tsock: TIPC socket
  * @msg: message
@@ -1260,6 +1216,36 @@ static u32 filter_connect(struct tipc_sock *tsock, struct sk_buff **buf)
 }
 
 /**
+ * rcvbuf_limit - get proper overload limit of socket receive queue
+ * @sk: socket
+ * @buf: message
+ *
+ * For all connection oriented messages, irrespective of importance,
+ * the default overload value (i.e. 67MB) is set as limit.
+ *
+ * For all connectionless messages, by default new queue limits are
+ * as belows:
+ *
+ * TIPC_LOW_IMPORTANCE       (5MB)
+ * TIPC_MEDIUM_IMPORTANCE    (10MB)
+ * TIPC_HIGH_IMPORTANCE      (20MB)
+ * TIPC_CRITICAL_IMPORTANCE  (40MB)
+ *
+ * Returns overload limit according to corresponding message importance
+ */
+static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *buf)
+{
+	struct tipc_msg *msg = buf_msg(buf);
+	unsigned int limit;
+
+	if (msg_connected(msg))
+		limit = CONN_OVERLOAD_LIMIT;
+	else
+		limit = sk->sk_rcvbuf << (msg_importance(msg) + 5);
+	return limit;
+}
+
+/**
  * filter_rcv - validate incoming message
  * @sk: socket
  * @buf: message
@@ -1275,7 +1261,7 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 {
 	struct socket *sock = sk->sk_socket;
 	struct tipc_msg *msg = buf_msg(buf);
-	u32 recv_q_len;
+	unsigned int limit = rcvbuf_limit(sk, buf);
 	u32 res = TIPC_OK;
 
 	/* Reject message if it is wrong sort of message for socket */
@@ -1292,15 +1278,13 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
 	}
 
 	/* Reject message if there isn't room to queue it */
-	recv_q_len = skb_queue_len(&sk->sk_receive_queue);
-	if (unlikely(recv_q_len >= (OVERLOAD_LIMIT_BASE / 2))) {
-		if (rx_queue_full(msg, recv_q_len, OVERLOAD_LIMIT_BASE / 2))
-			return TIPC_ERR_OVERLOAD;
-	}
+	if (sk_rmem_alloc_get(sk) + buf->truesize >= limit)
+		return TIPC_ERR_OVERLOAD;
 
-	/* Enqueue message (finally!) */
+	/* Enqueue message */
 	TIPC_SKB_CB(buf)->handle = 0;
 	__skb_queue_tail(&sk->sk_receive_queue, buf);
+	skb_set_owner_r(buf, sk);
 
 	sk->sk_data_ready(sk, 0);
 	return TIPC_OK;
@@ -1349,7 +1333,7 @@ static u32 dispatch(struct tipc_port *tport, struct sk_buff *buf)
 	if (!sock_owned_by_user(sk)) {
 		res = filter_rcv(sk, buf);
 	} else {
-		if (sk_add_backlog(sk, buf, sk->sk_rcvbuf))
+		if (sk_add_backlog(sk, buf, rcvbuf_limit(sk, buf)))
 			res = TIPC_ERR_OVERLOAD;
 		else
 			res = TIPC_OK;
@@ -1583,6 +1567,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
 	} else {
 		__skb_dequeue(&sk->sk_receive_queue);
 		__skb_queue_head(&new_sk->sk_receive_queue, buf);
+		skb_set_owner_r(buf, new_sk);
 	}
 	release_sock(new_sk);
 
@@ -1637,7 +1622,7 @@ restart:
 	case SS_DISCONNECTING:
 
 		/* Discard any unreceived messages */
-		discard_rx_queue(sk);
+		__skb_queue_purge(&sk->sk_receive_queue);
 
 		/* Wake up anyone sleeping in poll */
 		sk->sk_state_change(sk);