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

Pull networking fixes from David Miller:

 1) Stretch ACKs can kill performance with Reno and CUBIC congestion
    control, largely due to LRO and GRO.  Fix from Neal Cardwell.

 2) Fix userland breakage because we accidently emit zero length netlink
    messages from the bridging code.  From Roopa Prabhu.

 3) Carry handling in generic csum_tcpudp_nofold is broken, fix from
    Karl Beldan.

 4) Remove bogus dev_set_net() calls from CAIF driver, from Nicolas
    Dichtel.

 5) Make sure PPP deflation never returns a length greater then the
    output buffer, otherwise we overflow and trigger skb_over_panic().
    Fix from Florian Westphal.

 6) COSA driver needs VIRT_TO_BUS Kconfig dependencies, from Arnd
    Bergmann.

 7) Don't increase route cached MTU on datagram too big ICMPs.  From Li
    Wei.

 8) Fix error path leaks in nf_tables, from Pablo Neira Ayuso.

 9) Fix bitmask handling regression in netlink that broke things like
    acpi userland tools.  From Pablo Neira Ayuso.

10) Wrong header pointer passed to param_type2af() in SCTP code, from
    Saran Maruti Ramanara.

11) Stacked vlans not handled correctly by vlan_get_protocol(), from
    Toshiaki Makita.

12) Add missing DMA memory barrier to xgene driver, from Iyappan
    Subramanian.

13) Fix crash in rate estimators, from Eric Dumazet.

14) We've been adding various workarounds, one after another, for the
    change which added the per-net tcp_sock.  It was meant to reduce
    socket contention but added lots of problems.

    Reduce this instead to a proper per-cpu socket and that rids us of
    all the daemons.

    From Eric Dumazet.

15) Fix memory corruption and OOPS in mlx4 driver, from Jack
    Morgenstein.

16) When we disabled UFO in the virtio_net device, it introduces some
    serious performance regressions.  The orignal problem was IPV6
    fragment ID generation, so fix that properly instead.  From Vlad
    Yasevich.

17) sr9700 driver build breaks on xtensa because it defines macros with
    the same name as those used by the arch code.  Use more unique
    names.  From Chen Gang.

18) Fix endianness in new virio 1.0 mode of the vhost net driver, from
    Michael S Tsirkin.

19) Several sysctls were setting the maxlen attribute incorrectly, from
    Sasha Levin.

20) Don't accept an FQ scheduler quantum of zero, that leads to crashes.
    From Kenneth Klette Jonassen.

21) Fix dumping of non-existing actions in the packet scheduler
    classifier.  From Ignacy Gawędzki.

22) Return the write work_done value when doing TX work in the qlcnic
    driver.

23) ip6gre_err accesses the info field with the wrong endianness, from
    Sabrina Dubroca.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (54 commits)
  sit: fix some __be16/u16 mismatches
  ipv6: fix sparse errors in ip6_make_flowlabel()
  net: remove some sparse warnings
  flow_keys: n_proto type should be __be16
  ip6_gre: fix endianness errors in ip6gre_err
  qlcnic: Fix NAPI poll routine for Tx completion
  amd-xgbe: Set RSS enablement based on hardware features
  amd-xgbe: Adjust for zero-based traffic class count
  cls_api.c: Fix dumping of non-existing actions' stats.
  pkt_sched: fq: avoid hang when quantum 0
  net: rds: use correct size for max unacked packets and bytes
  vhost/net: fix up num_buffers endian-ness
  gianfar: correct the bad expression while writing bit-pattern
  net: usb: sr9700: Use 'SR_' prefix for the common register macros
  Revert "drivers/net: Disable UFO through virtio"
  Revert "drivers/net, ipv6: Select IPv6 fragment idents for virtio UFO packets"
  ipv6: Select fragment id during UFO segmentation if not set.
  xen-netback: stop the guest rx thread after a fatal error
  net/mlx4_core: Fix kernel Oops (mem corruption) when working with more than 80 VFs
  isdn: off by one in connect_res()
  ...

5 files changed, 50 insertions, 27 deletions

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 13cda4c6313b..01ccc28a686f 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -417,7 +417,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
 
-		if (teli && teli == info - 2) {
+		if (teli && teli == be32_to_cpu(info) - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
 				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
@@ -429,7 +429,7 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = info - offset;
+		mtu = be32_to_cpu(info) - offset;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ce69a12ae48c..d28f2a2efb32 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -537,20 +537,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	skb_copy_secmark(to, from);
 }
 
-static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static u32 ip6_idents_hashrnd __read_mostly;
-	u32 hash, id;
-
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
-
-	id = ip_idents_reserve(hash, 1);
-	fhdr->identification = htonl(id);
-}
-
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 97f41a3e68d9..54520a0bd5e3 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,6 +9,24 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -22,7 +40,7 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +52,25 @@ void ipv6_proxy_select_ident(struct sk_buff *skb)
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	skb_shinfo(skb)->ip6_frag_id = id;
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 213546bd6d5d..cdbfe5af6187 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1506,12 +1506,12 @@ static bool ipip6_netlink_encap_parms(struct nlattr *data[],
 
 	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -1707,9 +1707,9 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
 			tunnel->encap.type) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
 			tunnel->encap.sport) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
 			tunnel->encap.dport) ||
 	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
 			tunnel->encap.flags))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b6aa8ed18257..a56276996b72 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -52,6 +52,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,7 +112,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		if (skb_shinfo(skb)->ip6_frag_id)
+			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		else
+			ipv6_select_ident(fptr,
+					  (struct rt6_info *)skb_dst(skb));
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()