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

Pull networking fixes from David Miller:

 1) Must teardown SR-IOV before unregistering netdev in igb driver, from
    Alex Williamson.

 2) Fix ipv6 route unreachable crash in IPVS, from Alex Gartrell.

 3) Default route selection in ipv4 should take the prefix length, table
    ID, and TOS into account, from Julian Anastasov.

 4) sch_plug must have a reset method in order to purge all buffered
    packets when the qdisc is reset, likewise for sch_choke, from WANG
    Cong.

 5) Fix deadlock and races in slave_changelink/br_setport in bridging.
    From Nikolay Aleksandrov.

 6) mlx4 bug fixes (wrong index in port even propagation to VFs,
    overzealous BUG_ON assertion, etc.) from Ido Shamay, Jack
    Morgenstein, and Or Gerlitz.

 7) Turn off klog message about SCTP userspace interface compat that
    makes no sense at all, from Daniel Borkmann.

 8) Fix unbounded restarts of inet frag eviction process, causing NMI
    watchdog soft lockup messages, from Florian Westphal.

 9) Suspend/resume fixes for r8152 from Hayes Wang.

10) Fix busy loop when MSG_WAITALL|MSG_PEEK is used in TCP recv, from
    Sabrina Dubroca.

11) Fix performance regression when removing a lot of routes from the
    ipv4 routing tables, from Alexander Duyck.

12) Fix device leak in AF_PACKET, from Lars Westerhoff.

13) AF_PACKET also has a header length comparison bug due to signedness,
    from Alexander Drozdov.

14) Fix bug in EBPF tail call generation on x86, from Daniel Borkmann.

15) Memory leaks, TSO stats, watchdog timeout and other fixes to
    thunderx driver from Sunil Goutham and Thanneeru Srinivasulu.

16) act_bpf can leak memory when replacing programs, from Daniel
    Borkmann.

17) WOL packet fixes in gianfar driver, from Claudiu Manoil.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (79 commits)
  stmmac: fix missing MODULE_LICENSE in stmmac_platform
  gianfar: Enable device wakeup when appropriate
  gianfar: Fix suspend/resume for wol magic packet
  gianfar: Fix warning when CONFIG_PM off
  act_pedit: check binding before calling tcf_hash_release()
  net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket
  net: sched: fix refcount imbalance in actions
  r8152: reset device when tx timeout
  r8152: add pre_reset and post_reset
  qlcnic: Fix corruption while copying
  act_bpf: fix memory leaks when replacing bpf programs
  net: thunderx: Fix for crash while BGX teardown
  net: thunderx: Add PCI driver shutdown routine
  net: thunderx: Fix crash when changing rss with mutliple traffic flows
  net: thunderx: Set watchdog timeout value
  net: thunderx: Wakeup TXQ only if CQE_TX are processed
  net: thunderx: Suppress alloc_pages() failure warnings
  net: thunderx: Fix TSO packet statistic
  net: thunderx: Fix memory leak when changing queue count
  net: thunderx: Fix RQ_DROP miscalculation
  ...

5 files changed, 110 insertions, 39 deletions

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5d2b806a862e..38fbc194b9cb 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -319,7 +319,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
 		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
 		sched = rcu_dereference(svc->scheduler);
-		dest = sched->schedule(svc, skb, iph);
+		if (sched) {
+			/* read svc->sched_data after svc->scheduler */
+			smp_rmb();
+			dest = sched->schedule(svc, skb, iph);
+		} else {
+			dest = NULL;
+		}
 		if (!dest) {
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
@@ -467,7 +473,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
 	}
 
 	sched = rcu_dereference(svc->scheduler);
-	dest = sched->schedule(svc, skb, iph);
+	if (sched) {
+		/* read svc->sched_data after svc->scheduler */
+		smp_rmb();
+		dest = sched->schedule(svc, skb, iph);
+	} else {
+		dest = NULL;
+	}
 	if (dest == NULL) {
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
 		return NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 285eae3a1454..24c554201a76 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -842,15 +842,16 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	__ip_vs_dst_cache_reset(dest);
 	spin_unlock_bh(&dest->dst_lock);
 
-	sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (add) {
 		ip_vs_start_estimator(svc->net, &dest->stats);
 		list_add_rcu(&dest->n_list, &svc->destinations);
 		svc->num_dests++;
-		if (sched->add_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->add_dest)
 			sched->add_dest(svc, dest);
 	} else {
-		if (sched->upd_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->upd_dest)
 			sched->upd_dest(svc, dest);
 	}
 }
@@ -1084,7 +1085,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 		struct ip_vs_scheduler *sched;
 
 		sched = rcu_dereference_protected(svc->scheduler, 1);
-		if (sched->del_dest)
+		if (sched && sched->del_dest)
 			sched->del_dest(svc, dest);
 	}
 }
@@ -1175,11 +1176,14 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	ip_vs_use_count_inc();
 
 	/* Lookup the scheduler by 'u->sched_name' */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		ret = -ENOENT;
-		goto out_err;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			ret = -ENOENT;
+			goto out_err;
+		}
 	}
 
 	if (u->pe_name && *u->pe_name) {
@@ -1240,10 +1244,12 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 	spin_lock_init(&svc->stats.lock);
 
 	/* Bind the scheduler */
-	ret = ip_vs_bind_scheduler(svc, sched);
-	if (ret)
-		goto out_err;
-	sched = NULL;
+	if (sched) {
+		ret = ip_vs_bind_scheduler(svc, sched);
+		if (ret)
+			goto out_err;
+		sched = NULL;
+	}
 
 	/* Bind the ct retriever */
 	RCU_INIT_POINTER(svc->pe, pe);
@@ -1291,17 +1297,20 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
 static int
 ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 {
-	struct ip_vs_scheduler *sched, *old_sched;
+	struct ip_vs_scheduler *sched = NULL, *old_sched;
 	struct ip_vs_pe *pe = NULL, *old_pe = NULL;
 	int ret = 0;
 
 	/*
 	 * Lookup the scheduler, by 'u->sched_name'
 	 */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		return -ENOENT;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			return -ENOENT;
+		}
 	}
 	old_sched = sched;
 
@@ -1329,14 +1338,20 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (sched != old_sched) {
+		if (old_sched) {
+			ip_vs_unbind_scheduler(svc, old_sched);
+			RCU_INIT_POINTER(svc->scheduler, NULL);
+			/* Wait all svc->sched_data users */
+			synchronize_rcu();
+		}
 		/* Bind the new scheduler */
-		ret = ip_vs_bind_scheduler(svc, sched);
-		if (ret) {
-			old_sched = sched;
-			goto out;
+		if (sched) {
+			ret = ip_vs_bind_scheduler(svc, sched);
+			if (ret) {
+				ip_vs_scheduler_put(sched);
+				goto out;
+			}
 		}
-		/* Unbind the old scheduler on success */
-		ip_vs_unbind_scheduler(svc, old_sched);
 	}
 
 	/*
@@ -1982,6 +1997,7 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
 		const struct ip_vs_iter *iter = seq->private;
 		const struct ip_vs_dest *dest;
 		struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+		char *sched_name = sched ? sched->name : "none";
 
 		if (iter->table == ip_vs_svc_table) {
 #ifdef CONFIG_IP_VS_IPV6
@@ -1990,18 +2006,18 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
 					   ip_vs_proto_name(svc->protocol),
 					   &svc->addr.in6,
 					   ntohs(svc->port),
-					   sched->name);
+					   sched_name);
 			else
 #endif
 				seq_printf(seq, "%s  %08X:%04X %s %s ",
 					   ip_vs_proto_name(svc->protocol),
 					   ntohl(svc->addr.ip),
 					   ntohs(svc->port),
-					   sched->name,
+					   sched_name,
 					   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		} else {
 			seq_printf(seq, "FWM  %08X %s %s",
-				   svc->fwmark, sched->name,
+				   svc->fwmark, sched_name,
 				   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		}
 
@@ -2427,13 +2443,15 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
 {
 	struct ip_vs_scheduler *sched;
 	struct ip_vs_kstats kstats;
+	char *sched_name;
 
 	sched = rcu_dereference_protected(src->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	dst->protocol = src->protocol;
 	dst->addr = src->addr.ip;
 	dst->port = src->port;
 	dst->fwmark = src->fwmark;
-	strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
+	strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
 	dst->flags = src->flags;
 	dst->timeout = src->timeout / HZ;
 	dst->netmask = src->netmask;
@@ -2892,6 +2910,7 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	struct ip_vs_flags flags = { .flags = svc->flags,
 				     .mask = ~0 };
 	struct ip_vs_kstats kstats;
+	char *sched_name;
 
 	nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
 	if (!nl_service)
@@ -2910,8 +2929,9 @@ static int ip_vs_genl_fill_service(struct sk_buff *skb,
 	}
 
 	sched = rcu_dereference_protected(svc->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	pe = rcu_dereference_protected(svc->pe, 1);
-	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
 	    (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
 	    nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
 	    nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 199760c71f39..7e8141647943 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -74,7 +74,7 @@ void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
 
 	if (sched->done_service)
 		sched->done_service(svc);
-	/* svc->scheduler can not be set to NULL */
+	/* svc->scheduler can be set to NULL only by caller */
 }
 
 
@@ -147,21 +147,21 @@ void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler)
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 {
-	struct ip_vs_scheduler *sched;
+	struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+	char *sched_name = sched ? sched->name : "none";
 
-	sched = rcu_dereference(svc->scheduler);
 	if (svc->fwmark) {
 		IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
-			     sched->name, svc->fwmark, svc->fwmark, msg);
+			     sched_name, svc->fwmark, svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
 		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);
 #endif
 	} else {
 		IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.ip, ntohs(svc->port), msg);
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index b08ba9538d12..d99ad93eb855 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -612,7 +612,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp,
 			pkts = atomic_add_return(1, &cp->in_pkts);
 		else
 			pkts = sysctl_sync_threshold(ipvs);
-		ip_vs_sync_conn(net, cp->control, pkts);
+		ip_vs_sync_conn(net, cp, pkts);
 	}
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index bf66a8657a5f..258a0b0e82a2 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -130,7 +130,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
-	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
 	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
 			   FLOWI_FLAG_KNOWN_NH : 0;
 
@@ -505,6 +504,13 @@ err_put:
 	return -1;
 
 err_unreach:
+	/* The ip6_link_failure function requires the dev field to be set
+	 * in order to get the net (further for the sake of fwmark
+	 * reflection).
+	 */
+	if (!skb->dev)
+		skb->dev = skb_dst(skb)->dev;
+
 	dst_link_failure(skb);
 	return -1;
 }
@@ -523,10 +529,27 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
 	if (ret == NF_ACCEPT) {
 		nf_reset(skb);
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 	}
 	return ret;
 }
 
+/* In the event of a remote destination, it's possible that we would have
+ * matches against an old socket (particularly a TIME-WAIT socket). This
+ * causes havoc down the line (ip_local_out et. al. expect regular sockets
+ * and invalid memory accesses will happen) so simply drop the association
+ * in this case.
+*/
+static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb)
+{
+	/* If dev is set, the packet came from the LOCAL_IN callback and
+	 * not from a local TCP socket.
+	 */
+	if (skb->dev)
+		skb_orphan(skb);
+}
+
 /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
 static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 					 struct ip_vs_conn *cp, int local)
@@ -538,12 +561,23 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 1);
+
+	/* Remove the early_demux association unless it's bound for the
+	 * exact same port and address on this host after translation.
+	 */
+	if (!local || cp->vport != cp->dport ||
+	    !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
+		ip_vs_drop_early_demux_sk(skb);
+
 	if (!local) {
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
 		ret = NF_ACCEPT;
+
 	return ret;
 }
 
@@ -557,7 +591,10 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
 	if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
 		ip_vs_notrack(skb);
 	if (!local) {
+		ip_vs_drop_early_demux_sk(skb);
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
@@ -845,6 +882,8 @@ ip_vs_prepare_tunneled_skb(struct sk_buff *skb, int skb_af,
 	struct ipv6hdr *old_ipv6h = NULL;
 #endif
 
+	ip_vs_drop_early_demux_sk(skb);
+
 	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
 		new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb)