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

Pull networking updates from David Miller:
 "Highlights:

   1) Steady transitioning of the BPF instructure to a generic spot so
      all kernel subsystems can make use of it, from Alexei Starovoitov.

   2) SFC driver supports busy polling, from Alexandre Rames.

   3) Take advantage of hash table in UDP multicast delivery, from David
      Held.

   4) Lighten locking, in particular by getting rid of the LRU lists, in
      inet frag handling.  From Florian Westphal.

   5) Add support for various RFC6458 control messages in SCTP, from
      Geir Ola Vaagland.

   6) Allow to filter bridge forwarding database dumps by device, from
      Jamal Hadi Salim.

   7) virtio-net also now supports busy polling, from Jason Wang.

   8) Some low level optimization tweaks in pktgen from Jesper Dangaard
      Brouer.

   9) Add support for ipv6 address generation modes, so that userland
      can have some input into the process.  From Jiri Pirko.

  10) Consolidate common TCP connection request code in ipv4 and ipv6,
      from Octavian Purdila.

  11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.

  12) Generic resizable RCU hash table, with intial users in netlink and
      nftables.  From Thomas Graf.

  13) Maintain a name assignment type so that userspace can see where a
      network device name came from (enumerated by kernel, assigned
      explicitly by userspace, etc.) From Tom Gundersen.

  14) Automatic flow label generation on transmit in ipv6, from Tom
      Herbert.

  15) New packet timestamping facilities from Willem de Bruijn, meant to
      assist in measuring latencies going into/out-of the packet
      scheduler, latency from TCP data transmission to ACK, etc"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
  cxgb4 : Disable recursive mailbox commands when enabling vi
  net: reduce USB network driver config options.
  tg3: Modify tg3_tso_bug() to handle multiple TX rings
  amd-xgbe: Perform phy connect/disconnect at dev open/stop
  amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
  net: sun4i-emac: fix memory leak on bad packet
  sctp: fix possible seqlock seadlock in sctp_packet_transmit()
  Revert "net: phy: Set the driver when registering an MDIO bus device"
  cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
  team: Simplify return path of team_newlink
  bridge: Update outdated comment on promiscuous mode
  net-timestamp: ACK timestamp for bytestreams
  net-timestamp: TCP timestamping
  net-timestamp: SCHED timestamp on entering packet scheduler
  net-timestamp: add key to disambiguate concurrent datagrams
  net-timestamp: move timestamp flags out of sk_flags
  net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
  cxgb4i : Move stray CPL definitions to cxgb4 driver
  tcp: reduce spurious retransmits due to transient SACK reneging
  qlcnic: Initialize dcbnl_ops before register_netdev
  ...

1 files changed, 48 insertions, 42 deletions

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index cc85a9ba5010..c6557d9f7808 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -60,6 +60,8 @@
 #include <net/inet_frag.h>
 #include <net/inet_ecn.h>
 
+static const char ip6_frag_cache_name[] = "ip6-frags";
+
 struct ip6frag_skb_cb
 {
 	struct inet6_skb_parm	h;
@@ -85,27 +87,23 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr,
 				    const struct in6_addr *daddr)
 {
-	u32 c;
-
 	net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd));
-	c = jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
-			 (__force u32)id, ip6_frags.rnd);
-
-	return c & (INETFRAGS_HASHSZ - 1);
+	return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr),
+			    (__force u32)id, ip6_frags.rnd);
 }
 
-static unsigned int ip6_hashfn(struct inet_frag_queue *q)
+static unsigned int ip6_hashfn(const struct inet_frag_queue *q)
 {
-	struct frag_queue *fq;
+	const struct frag_queue *fq;
 
 	fq = container_of(q, struct frag_queue, q);
 	return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr);
 }
 
-bool ip6_frag_match(struct inet_frag_queue *q, void *a)
+bool ip6_frag_match(const struct inet_frag_queue *q, const void *a)
 {
-	struct frag_queue *fq;
-	struct ip6_create_arg *arg = a;
+	const struct frag_queue *fq;
+	const struct ip6_create_arg *arg = a;
 
 	fq = container_of(q, struct frag_queue, q);
 	return	fq->id == arg->id &&
@@ -115,10 +113,10 @@ bool ip6_frag_match(struct inet_frag_queue *q, void *a)
 }
 EXPORT_SYMBOL(ip6_frag_match);
 
-void ip6_frag_init(struct inet_frag_queue *q, void *a)
+void ip6_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	struct ip6_create_arg *arg = a;
+	const struct ip6_create_arg *arg = a;
 
 	fq->id = arg->id;
 	fq->user = arg->user;
@@ -135,7 +133,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
 
 	spin_lock(&fq->q.lock);
 
-	if (fq->q.last_in & INET_FRAG_COMPLETE)
+	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
 	inet_frag_kill(&fq->q, frags);
@@ -145,17 +143,20 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
 	if (!dev)
 		goto out_rcu_unlock;
 
-	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
 
+	if (fq->q.flags & INET_FRAG_EVICTED)
+		goto out_rcu_unlock;
+
+	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+
 	/* Don't send error if the first segment did not arrive. */
-	if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments)
+	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments)
 		goto out_rcu_unlock;
 
-	/*
-	   But use as source device on which LAST ARRIVED
-	   segment was received. And do not use fq->dev
-	   pointer directly, device might already disappeared.
+	/* But use as source device on which LAST ARRIVED
+	 * segment was received. And do not use fq->dev
+	 * pointer directly, device might already disappeared.
 	 */
 	fq->q.fragments->dev = dev;
 	icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
@@ -192,7 +193,6 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src,
 	arg.dst = dst;
 	arg.ecn = ecn;
 
-	read_lock(&ip6_frags.lock);
 	hash = inet6_hash_frag(id, src, dst);
 
 	q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash);
@@ -212,7 +212,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	u8 ecn;
 
-	if (fq->q.last_in & INET_FRAG_COMPLETE)
+	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto err;
 
 	offset = ntohs(fhdr->frag_off) & ~0x7;
@@ -243,9 +243,9 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		 * or have different end, the segment is corrupted.
 		 */
 		if (end < fq->q.len ||
-		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len))
+		    ((fq->q.flags & INET_FRAG_LAST_IN) && end != fq->q.len))
 			goto err;
-		fq->q.last_in |= INET_FRAG_LAST_IN;
+		fq->q.flags |= INET_FRAG_LAST_IN;
 		fq->q.len = end;
 	} else {
 		/* Check if the fragment is rounded to 8 bytes.
@@ -263,7 +263,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		}
 		if (end > fq->q.len) {
 			/* Some bits beyond end -> corruption. */
-			if (fq->q.last_in & INET_FRAG_LAST_IN)
+			if (fq->q.flags & INET_FRAG_LAST_IN)
 				goto err;
 			fq->q.len = end;
 		}
@@ -338,10 +338,10 @@ found:
 	 */
 	if (offset == 0) {
 		fq->nhoffset = nhoff;
-		fq->q.last_in |= INET_FRAG_FIRST_IN;
+		fq->q.flags |= INET_FRAG_FIRST_IN;
 	}
 
-	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    fq->q.meat == fq->q.len) {
 		int res;
 		unsigned long orefdst = skb->_skb_refdst;
@@ -353,14 +353,13 @@ found:
 	}
 
 	skb_dst_drop(skb);
-	inet_frag_lru_move(&fq->q);
 	return -1;
 
 discard_fq:
 	inet_frag_kill(&fq->q, &ip6_frags);
 err:
-	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
-		      IPSTATS_MIB_REASMFAILS);
+	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+			 IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
 	return -1;
 }
@@ -523,7 +522,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
-	int evicted;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
 		goto fail_hdr;
@@ -552,11 +550,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
-	evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false);
-	if (evicted)
-		IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
-				 IPSTATS_MIB_REASMFAILS, evicted);
-
 	fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr,
 		     ip6_frag_ecn(hdr));
 	if (fq != NULL) {
@@ -576,7 +569,8 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	return -1;
 
 fail_hdr:
-	IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS);
+	IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)),
+			 IPSTATS_MIB_INHDRERRORS);
 	icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb));
 	return -1;
 }
@@ -588,20 +582,25 @@ static const struct inet6_protocol frag_protocol =
 };
 
 #ifdef CONFIG_SYSCTL
+static int zero;
+
 static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{
 		.procname	= "ip6frag_high_thresh",
 		.data		= &init_net.ipv6.frags.high_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.ipv6.frags.low_thresh
 	},
 	{
 		.procname	= "ip6frag_low_thresh",
 		.data		= &init_net.ipv6.frags.low_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.ipv6.frags.high_thresh
 	},
 	{
 		.procname	= "ip6frag_time",
@@ -613,10 +612,12 @@ static struct ctl_table ip6_frags_ns_ctl_table[] = {
 	{ }
 };
 
+/* secret interval has been deprecated */
+static int ip6_frags_secret_interval_unused;
 static struct ctl_table ip6_frags_ctl_table[] = {
 	{
 		.procname	= "ip6frag_secret_interval",
-		.data		= &ip6_frags.secret_interval,
+		.data		= &ip6_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -636,7 +637,10 @@ static int __net_init ip6_frags_ns_sysctl_register(struct net *net)
 			goto err_alloc;
 
 		table[0].data = &net->ipv6.frags.high_thresh;
+		table[0].extra1 = &net->ipv6.frags.low_thresh;
+		table[0].extra2 = &init_net.ipv6.frags.high_thresh;
 		table[1].data = &net->ipv6.frags.low_thresh;
+		table[1].extra2 = &net->ipv6.frags.high_thresh;
 		table[2].data = &net->ipv6.frags.timeout;
 
 		/* Don't export sysctls to unprivileged users */
@@ -746,8 +750,10 @@ int __init ipv6_frag_init(void)
 	ip6_frags.qsize = sizeof(struct frag_queue);
 	ip6_frags.match = ip6_frag_match;
 	ip6_frags.frag_expire = ip6_frag_expire;
-	ip6_frags.secret_interval = 10 * 60 * HZ;
-	inet_frags_init(&ip6_frags);
+	ip6_frags.frags_cache_name = ip6_frag_cache_name;
+	ret = inet_frags_init(&ip6_frags);
+	if (ret)
+		goto err_pernet;
 out:
 	return ret;