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  bridge: Update outdated comment on promiscuous mode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, 38 insertions, 49 deletions

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index ed32313e307c..15f0e2bad7ad 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -55,6 +55,7 @@
  */
 
 static int sysctl_ipfrag_max_dist __read_mostly = 64;
+static const char ip_frag_cache_name[] = "ip4-frags";
 
 struct ipfrag_skb_cb
 {
@@ -86,11 +87,6 @@ static inline u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-int ip_frag_nqueues(struct net *net)
-{
-	return net->ipv4.frags.nqueues;
-}
-
 int ip_frag_mem(struct net *net)
 {
 	return sum_frag_mem_limit(&net->ipv4.frags);
@@ -109,21 +105,21 @@ static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
 	net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
 	return jhash_3words((__force u32)id << 16 | prot,
 			    (__force u32)saddr, (__force u32)daddr,
-			    ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1);
+			    ip4_frags.rnd);
 }
 
-static unsigned int ip4_hashfn(struct inet_frag_queue *q)
+static unsigned int ip4_hashfn(const struct inet_frag_queue *q)
 {
-	struct ipq *ipq;
+	const struct ipq *ipq;
 
 	ipq = container_of(q, struct ipq, q);
 	return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol);
 }
 
-static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
+static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a)
 {
-	struct ipq *qp;
-	struct ip4_create_arg *arg = a;
+	const struct ipq *qp;
+	const struct ip4_create_arg *arg = a;
 
 	qp = container_of(q, struct ipq, q);
 	return	qp->id == arg->iph->id &&
@@ -133,14 +129,14 @@ static bool ip4_frag_match(struct inet_frag_queue *q, void *a)
 		qp->user == arg->user;
 }
 
-static void ip4_frag_init(struct inet_frag_queue *q, void *a)
+static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	struct ipq *qp = container_of(q, struct ipq, q);
 	struct netns_ipv4 *ipv4 = container_of(q->net, struct netns_ipv4,
 					       frags);
 	struct net *net = container_of(ipv4, struct net, ipv4);
 
-	struct ip4_create_arg *arg = a;
+	const struct ip4_create_arg *arg = a;
 
 	qp->protocol = arg->iph->protocol;
 	qp->id = arg->iph->id;
@@ -177,18 +173,6 @@ static void ipq_kill(struct ipq *ipq)
 	inet_frag_kill(&ipq->q, &ip4_frags);
 }
 
-/* Memory limiting on fragments.  Evictor trashes the oldest
- * fragment queue until we are back under the threshold.
- */
-static void ip_evictor(struct net *net)
-{
-	int evicted;
-
-	evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false);
-	if (evicted)
-		IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted);
-}
-
 /*
  * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
  */
@@ -202,19 +186,22 @@ static void ip_expire(unsigned long arg)
 
 	spin_lock(&qp->q.lock);
 
-	if (qp->q.last_in & INET_FRAG_COMPLETE)
+	if (qp->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
 	ipq_kill(qp);
-
-	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
-	if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
+	if (!(qp->q.flags & INET_FRAG_EVICTED)) {
 		struct sk_buff *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
 
+		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
+
+		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
+			goto out;
+
 		rcu_read_lock();
 		head->dev = dev_get_by_index_rcu(net, qp->iif);
 		if (!head->dev)
@@ -227,8 +214,7 @@ static void ip_expire(unsigned long arg)
 		if (err)
 			goto out_rcu_unlock;
 
-		/*
-		 * Only an end host needs to send an ICMP
+		/* Only an end host needs to send an ICMP
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (qp->user == IP_DEFRAG_AF_PACKET ||
@@ -237,7 +223,6 @@ static void ip_expire(unsigned long arg)
 		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
 			goto out_rcu_unlock;
 
-
 		/* Send an ICMP "Fragment Reassembly Timeout" message. */
 		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
 out_rcu_unlock:
@@ -260,7 +245,6 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user)
 	arg.iph = iph;
 	arg.user = user;
 
-	read_lock(&ip4_frags.lock);
 	hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol);
 
 	q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash);
@@ -319,7 +303,7 @@ static int ip_frag_reinit(struct ipq *qp)
 	} while (fp);
 	sub_frag_mem_limit(&qp->q, sum_truesize);
 
-	qp->q.last_in = 0;
+	qp->q.flags = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
 	qp->q.fragments = NULL;
@@ -340,7 +324,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	int err = -ENOENT;
 	u8 ecn;
 
-	if (qp->q.last_in & INET_FRAG_COMPLETE)
+	if (qp->q.flags & INET_FRAG_COMPLETE)
 		goto err;
 
 	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
@@ -367,9 +351,9 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		 * or have different end, the segment is corrupted.
 		 */
 		if (end < qp->q.len ||
-		    ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len))
+		    ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len))
 			goto err;
-		qp->q.last_in |= INET_FRAG_LAST_IN;
+		qp->q.flags |= INET_FRAG_LAST_IN;
 		qp->q.len = end;
 	} else {
 		if (end&7) {
@@ -379,7 +363,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		}
 		if (end > qp->q.len) {
 			/* Some bits beyond end -> corruption. */
-			if (qp->q.last_in & INET_FRAG_LAST_IN)
+			if (qp->q.flags & INET_FRAG_LAST_IN)
 				goto err;
 			qp->q.len = end;
 		}
@@ -488,13 +472,13 @@ found:
 	qp->ecn |= ecn;
 	add_frag_mem_limit(&qp->q, skb->truesize);
 	if (offset == 0)
-		qp->q.last_in |= INET_FRAG_FIRST_IN;
+		qp->q.flags |= INET_FRAG_FIRST_IN;
 
 	if (ip_hdr(skb)->frag_off & htons(IP_DF) &&
 	    skb->len + ihl > qp->q.max_size)
 		qp->q.max_size = skb->len + ihl;
 
-	if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	if (qp->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    qp->q.meat == qp->q.len) {
 		unsigned long orefdst = skb->_skb_refdst;
 
@@ -505,7 +489,6 @@ found:
 	}
 
 	skb_dst_drop(skb);
-	inet_frag_lru_move(&qp->q);
 	return -EINPROGRESS;
 
 err:
@@ -655,9 +638,6 @@ int ip_defrag(struct sk_buff *skb, u32 user)
 	net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
 
-	/* Start by cleaning up the memory. */
-	ip_evictor(net);
-
 	/* Lookup (or create) queue header */
 	if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) {
 		int ret;
@@ -721,14 +701,17 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
 		.data		= &init_net.ipv4.frags.high_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &init_net.ipv4.frags.low_thresh
 	},
 	{
 		.procname	= "ipfrag_low_thresh",
 		.data		= &init_net.ipv4.frags.low_thresh,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &init_net.ipv4.frags.high_thresh
 	},
 	{
 		.procname	= "ipfrag_time",
@@ -740,10 +723,12 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = {
 	{ }
 };
 
+/* secret interval has been deprecated */
+static int ip4_frags_secret_interval_unused;
 static struct ctl_table ip4_frags_ctl_table[] = {
 	{
 		.procname	= "ipfrag_secret_interval",
-		.data		= &ip4_frags.secret_interval,
+		.data		= &ip4_frags_secret_interval_unused,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -771,7 +756,10 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net)
 			goto err_alloc;
 
 		table[0].data = &net->ipv4.frags.high_thresh;
+		table[0].extra1 = &net->ipv4.frags.low_thresh;
+		table[0].extra2 = &init_net.ipv4.frags.high_thresh;
 		table[1].data = &net->ipv4.frags.low_thresh;
+		table[1].extra2 = &net->ipv4.frags.high_thresh;
 		table[2].data = &net->ipv4.frags.timeout;
 
 		/* Don't export sysctls to unprivileged users */
@@ -873,6 +861,7 @@ void __init ipfrag_init(void)
 	ip4_frags.qsize = sizeof(struct ipq);
 	ip4_frags.match = ip4_frag_match;
 	ip4_frags.frag_expire = ip_expire;
-	ip4_frags.secret_interval = 10 * 60 * HZ;
-	inet_frags_init(&ip4_frags);
+	ip4_frags.frags_cache_name = ip_frag_cache_name;
+	if (inet_frags_init(&ip4_frags))
+		panic("IP: failed to allocate ip4_frags cache\n");
 }