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

Pull networking updates from David Miller:

 1) Make syn floods consume significantly less resources by

    a) Not pre-COW'ing routing metrics for SYN/ACKs
    b) Mirroring the device queue mapping of the SYN for the SYN/ACK
       reply.

    Both from Eric Dumazet.

 2) Fix calculation errors in Byte Queue Limiting, from Hiroaki SHIMODA.

 3) Validate the length requested when building a paged SKB for a
    socket, so we don't overrun the page vector accidently.  From Jason
    Wang.

 4) When netlabel is disabled, we abort all IP option processing when we
    see a CIPSO option.  This isn't the right thing to do, we should
    simply skip over it and continue processing the remaining options
    (if any).  Fix from Paul Moore.

 5) SRIOV fixes for the mellanox driver from Jack orgenstein and Marcel
    Apfelbaum.

 6) 8139cp enables the receiver before the ring address is properly
    programmed, which potentially lets the device crap over random
    memory.  Fix from Jason Wang.

 7) e1000/e1000e fixes for i217 RST handling, and an improper buffer
    address reference in jumbo RX frame processing from Bruce Allan and
    Sebastian Andrzej Siewior, respectively.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
  fec_mpc52xx: fix timestamp filtering
  mcs7830: Implement link state detection
  e1000e: fix Rapid Start Technology support for i217
  e1000: look into the page instead of skb->data for e1000_tbi_adjust_stats()
  r8169: call netif_napi_del at errpaths and at driver unload
  tcp: reflect SYN queue_mapping into SYNACK packets
  tcp: do not create inetpeer on SYNACK message
  8139cp/8139too: terminate the eeprom access with the right opmode
  8139cp: set ring address before enabling receiver
  cipso: handle CIPSO options correctly when NetLabel is disabled
  net: sock: validate data_len before allocating skb in sock_alloc_send_pskb()
  bql: Avoid possible inconsistent calculation.
  bql: Avoid unneeded limit decrement.
  bql: Fix POSDIFF() to integer overflow aware.
  net/mlx4_core: Fix obscure mlx4_cmd_box parameter in QUERY_DEV_CAP
  net/mlx4_core: Check port out-of-range before using in mlx4_slave_cap
  net/mlx4_core: Fixes for VF / Guest startup flow
  net/mlx4_en: Fix improper use of "port" parameter in mlx4_en_event
  net/mlx4_core: Fix number of EQs used in ICM initialisation
  net/mlx4_core: Fix the slave_id out-of-range test in mlx4_eq_int

4 files changed, 19 insertions, 9 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index 653f8c0..9e5b71f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1592,6 +1592,11 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 	gfp_t gfp_mask;
 	long timeo;
 	int err;
+	int npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
+
+	err = -EMSGSIZE;
+	if (npages > MAX_SKB_FRAGS)
+		goto failure;
 
 	gfp_mask = sk->sk_allocation;
 	if (gfp_mask & __GFP_WAIT)
@@ -1610,14 +1615,12 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
 		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
 			skb = alloc_skb(header_len, gfp_mask);
 			if (skb) {
-				int npages;
 				int i;
 
 				/* No pages, we're done... */
 				if (!data_len)
 					break;
 
-				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 				skb->truesize += data_len;
 				skb_shinfo(skb)->nr_frags = npages;
 				for (i = 0; i < npages; i++) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 95e61596..f9ee741 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -377,7 +377,8 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 
 	flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
-			   sk->sk_protocol, inet_sk_flowi_flags(sk),
+			   sk->sk_protocol,
+			   inet_sk_flowi_flags(sk) & ~FLOWI_FLAG_PRECOW_METRICS,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->rmt_addr,
 			   ireq->loc_addr, ireq->rmt_port, inet_sk(sk)->inet_sport);
 	security_req_classify_flow(req, flowi4_to_flowi(fl4));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a43b87d..c8d28c4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -824,7 +824,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
  */
 static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 			      struct request_sock *req,
-			      struct request_values *rvp)
+			      struct request_values *rvp,
+			      u16 queue_mapping)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
@@ -840,6 +841,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
 
+		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
 					    ireq->rmt_addr,
 					    ireq->opt);
@@ -854,7 +856,7 @@ static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
 			      struct request_values *rvp)
 {
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v4_send_synack(sk, NULL, req, rvp);
+	return tcp_v4_send_synack(sk, NULL, req, rvp, 0);
 }
 
 /*
@@ -1422,7 +1424,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_rsk(req)->snt_synack = tcp_time_stamp;
 
 	if (tcp_v4_send_synack(sk, dst, req,
-			       (struct request_values *)&tmp_ext) ||
+			       (struct request_values *)&tmp_ext,
+			       skb_get_queue_mapping(skb)) ||
 	    want_cookie)
 		goto drop_and_free;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 554d599..3a9aec2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -476,7 +476,8 @@ out:
 
 
 static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
-			      struct request_values *rvp)
+			      struct request_values *rvp,
+			      u16 queue_mapping)
 {
 	struct inet6_request_sock *treq = inet6_rsk(req);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -513,6 +514,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
 		fl6.daddr = treq->rmt_addr;
+		skb_set_queue_mapping(skb, queue_mapping);
 		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
@@ -528,7 +530,7 @@ static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
 			     struct request_values *rvp)
 {
 	TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
-	return tcp_v6_send_synack(sk, req, rvp);
+	return tcp_v6_send_synack(sk, req, rvp, 0);
 }
 
 static void tcp_v6_reqsk_destructor(struct request_sock *req)
@@ -1213,7 +1215,8 @@ have_isn:
 	security_inet_conn_request(sk, skb, req);
 
 	if (tcp_v6_send_synack(sk, req,
-			       (struct request_values *)&tmp_ext) ||
+			       (struct request_values *)&tmp_ext,
+			       skb_get_queue_mapping(skb)) ||
 	    want_cookie)
 		goto drop_and_free;