Merge branch 'WIP.sched/core' into sched/core

 Conflicts:
	kernel/sched/Makefile

Pick up the waitqueue related renames - it didn't get much feedback,
so it appears to be uncontroversial. Famous last words? ;-)

Signed-off-by: Ingo Molnar <mingo@kernel.org>

9 files changed, 96 insertions, 30 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index db1866f2ffcf..34678828e2bb 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -68,7 +68,7 @@ static inline int connection_based(struct sock *sk)
 	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
 }
 
-static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync,
+static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, int sync,
 				  void *key)
 {
 	unsigned long bits = (unsigned long)key;
diff --git a/net/core/dev.c b/net/core/dev.c
index fca407b4a6ea..6d60149287a1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1253,8 +1253,9 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 	if (!new_ifalias)
 		return -ENOMEM;
 	dev->ifalias = new_ifalias;
+	memcpy(dev->ifalias, alias, len);
+	dev->ifalias[len] = 0;
 
-	strlcpy(dev->ifalias, alias, len+1);
 	return len;
 }
 
@@ -4948,6 +4949,19 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(__skb_gro_checksum_complete);
 
+static void net_rps_send_ipi(struct softnet_data *remsd)
+{
+#ifdef CONFIG_RPS
+	while (remsd) {
+		struct softnet_data *next = remsd->rps_ipi_next;
+
+		if (cpu_online(remsd->cpu))
+			smp_call_function_single_async(remsd->cpu, &remsd->csd);
+		remsd = next;
+	}
+#endif
+}
+
 /*
  * net_rps_action_and_irq_enable sends any pending IPI's for rps.
  * Note: called with local irq disabled, but exits with local irq enabled.
@@ -4963,14 +4977,7 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd)
 		local_irq_enable();
 
 		/* Send pending IPI's to kick RPS processing on remote cpus. */
-		while (remsd) {
-			struct softnet_data *next = remsd->rps_ipi_next;
-
-			if (cpu_online(remsd->cpu))
-				smp_call_function_single_async(remsd->cpu,
-							   &remsd->csd);
-			remsd = next;
-		}
+		net_rps_send_ipi(remsd);
 	} else
 #endif
 		local_irq_enable();
@@ -7501,6 +7508,8 @@ out:
 err_uninit:
 	if (dev->netdev_ops->ndo_uninit)
 		dev->netdev_ops->ndo_uninit(dev);
+	if (dev->priv_destructor)
+		dev->priv_destructor(dev);
 	goto out;
 }
 EXPORT_SYMBOL(register_netdevice);
@@ -7708,8 +7717,10 @@ void netdev_run_todo(void)
 		WARN_ON(rcu_access_pointer(dev->ip6_ptr));
 		WARN_ON(dev->dn_ptr);
 
-		if (dev->destructor)
-			dev->destructor(dev);
+		if (dev->priv_destructor)
+			dev->priv_destructor(dev);
+		if (dev->needs_free_netdev)
+			free_netdev(dev);
 
 		/* Report a network device has been unregistered */
 		rtnl_lock();
@@ -8192,7 +8203,7 @@ static int dev_cpu_dead(unsigned int oldcpu)
 	struct sk_buff **list_skb;
 	struct sk_buff *skb;
 	unsigned int cpu;
-	struct softnet_data *sd, *oldsd;
+	struct softnet_data *sd, *oldsd, *remsd = NULL;
 
 	local_irq_disable();
 	cpu = smp_processor_id();
@@ -8233,6 +8244,13 @@ static int dev_cpu_dead(unsigned int oldcpu)
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_enable();
 
+#ifdef CONFIG_RPS
+	remsd = oldsd->rps_ipi_list;
+	oldsd->rps_ipi_list = NULL;
+#endif
+	/* send out pending IPI's on offline CPU */
+	net_rps_send_ipi(remsd);
+
 	/* Process offline CPU's input_pkt_queue */
 	while ((skb = __skb_dequeue(&oldsd->process_queue))) {
 		netif_rx_ni(skb);
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b0b87a292e7c..a0adfc31a3fe 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1680,8 +1680,10 @@ start_again:
 
 	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
 			  &devlink_nl_family, NLM_F_MULTI, cmd);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(skb);
 		return -EMSGSIZE;
+	}
 
 	if (devlink_nl_put_handle(skb, devlink))
 		goto nla_put_failure;
@@ -2098,8 +2100,10 @@ start_again:
 
 	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq,
 			  &devlink_nl_family, NLM_F_MULTI, cmd);
-	if (!hdr)
+	if (!hdr) {
+		nlmsg_free(skb);
 		return -EMSGSIZE;
+	}
 
 	if (devlink_nl_put_handle(skb, devlink))
 		goto nla_put_failure;
diff --git a/net/core/dst.c b/net/core/dst.c
index 960e503b5a52..13ba4a090c41 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -151,13 +151,13 @@ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dst_discard_out);
 
-const u32 dst_default_metrics[RTAX_MAX + 1] = {
+const struct dst_metrics dst_default_metrics = {
 	/* This initializer is needed to force linker to place this variable
 	 * into const section. Otherwise it might end into bss section.
 	 * We really want to avoid false sharing on this variable, and catch
 	 * any writes on it.
 	 */
-	[RTAX_MAX] = 0xdeadbeef,
+	.refcnt = ATOMIC_INIT(1),
 };
 
 void dst_init(struct dst_entry *dst, struct dst_ops *ops,
@@ -169,7 +169,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
 	if (dev)
 		dev_hold(dev);
 	dst->ops = ops;
-	dst_init_metrics(dst, dst_default_metrics, true);
+	dst_init_metrics(dst, dst_default_metrics.metrics, true);
 	dst->expires = 0UL;
 	dst->path = dst;
 	dst->from = NULL;
@@ -314,25 +314,30 @@ EXPORT_SYMBOL(dst_release);
 
 u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
-	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+	struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC);
 
 	if (p) {
-		u32 *old_p = __DST_METRICS_PTR(old);
+		struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old);
 		unsigned long prev, new;
 
-		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+		atomic_set(&p->refcnt, 1);
+		memcpy(p->metrics, old_p->metrics, sizeof(p->metrics));
 
 		new = (unsigned long) p;
 		prev = cmpxchg(&dst->_metrics, old, new);
 
 		if (prev != old) {
 			kfree(p);
-			p = __DST_METRICS_PTR(prev);
+			p = (struct dst_metrics *)__DST_METRICS_PTR(prev);
 			if (prev & DST_METRICS_READ_ONLY)
 				p = NULL;
+		} else if (prev & DST_METRICS_REFCOUNTED) {
+			if (atomic_dec_and_test(&old_p->refcnt))
+				kfree(old_p);
 		}
 	}
-	return p;
+	BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0);
+	return (u32 *)p;
 }
 EXPORT_SYMBOL(dst_cow_metrics_generic);
 
@@ -341,7 +346,7 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
 {
 	unsigned long prev, new;
 
-	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY;
 	prev = cmpxchg(&dst->_metrics, old, new);
 	if (prev == old)
 		kfree(__DST_METRICS_PTR(old));
@@ -464,6 +469,20 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event,
 		spin_lock_bh(&dst_garbage.lock);
 		dst = dst_garbage.list;
 		dst_garbage.list = NULL;
+		/* The code in dst_ifdown places a hold on the loopback device.
+		 * If the gc entry processing is set to expire after a lengthy
+		 * interval, this hold can cause netdev_wait_allrefs() to hang
+		 * out and wait for a long time -- until the the loopback
+		 * interface is released.  If we're really unlucky, it'll emit
+		 * pr_emerg messages to console too.  Reset the interval here,
+		 * so dst cleanups occur in a more timely fashion.
+		 */
+		if (dst_garbage.timer_inc > DST_GC_INC) {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+			mod_delayed_work(system_wq, &dst_gc_work,
+					 dst_garbage.timer_expires);
+		}
 		spin_unlock_bh(&dst_garbage.lock);
 
 		if (last)
diff --git a/net/core/filter.c b/net/core/filter.c
index a253a6197e6b..a6bb95fa87b2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2281,6 +2281,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_change_head ||
 	    func == bpf_skb_change_tail ||
 	    func == bpf_skb_pull_data ||
+	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
 	    func == bpf_xdp_adjust_head)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 1934efd4a9d4..26bbfababff2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -315,6 +315,25 @@ out_undo:
 	goto out;
 }
 
+static int __net_init net_defaults_init_net(struct net *net)
+{
+	net->core.sysctl_somaxconn = SOMAXCONN;
+	return 0;
+}
+
+static struct pernet_operations net_defaults_ops = {
+	.init = net_defaults_init_net,
+};
+
+static __init int net_defaults_init(void)
+{
+	if (register_pernet_subsys(&net_defaults_ops))
+		panic("Cannot initialize net default settings");
+
+	return 0;
+}
+
+core_initcall(net_defaults_init);
 
 #ifdef CONFIG_NET_NS
 static struct ucounts *inc_net_namespaces(struct user_namespace *ns)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 49a279a7cc15..5e61456f6bc7 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1124,6 +1124,8 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	struct ifla_vf_mac vf_mac;
 	struct ifla_vf_info ivi;
 
+	memset(&ivi, 0, sizeof(ivi));
+
 	/* Not all SR-IOV capable drivers support the
 	 * spoofcheck and "RSS query enable" query.  Preset to
 	 * -1 so the user space tool can detect that the driver
@@ -1132,7 +1134,6 @@ static noinline_for_stack int rtnl_fill_vfinfo(struct sk_buff *skb,
 	ivi.spoofchk = -1;
 	ivi.rss_query_en = -1;
 	ivi.trusted = -1;
-	memset(ivi.mac, 0, sizeof(ivi.mac));
 	/* The default value for VF link state is "auto"
 	 * IFLA_VF_LINK_STATE_AUTO which equals zero
 	 */
@@ -3231,8 +3232,11 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int err = 0;
 	int fidx = 0;
 
-	if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
-			IFLA_MAX, ifla_policy, NULL) == 0) {
+	err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
+			  IFLA_MAX, ifla_policy, NULL);
+	if (err < 0) {
+		return -EINVAL;
+	} else if (err == 0) {
 		if (tb[IFLA_MASTER])
 			br_idx = nla_get_u32(tb[IFLA_MASTER]);
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 346d3e85dfbc..b1be7c01efe2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3754,8 +3754,11 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 
 	spin_lock_irqsave(&q->lock, flags);
 	skb = __skb_dequeue(q);
-	if (skb && (skb_next = skb_peek(q)))
+	if (skb && (skb_next = skb_peek(q))) {
 		icmp_next = is_icmp_err_skb(skb_next);
+		if (icmp_next)
+			sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin;
+	}
 	spin_unlock_irqrestore(&q->lock, flags);
 
 	if (is_icmp_err_skb(skb) && !icmp_next)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index ea23254b2457..b7cd9aafe99e 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -479,8 +479,6 @@ static __net_init int sysctl_core_net_init(struct net *net)
 {
 	struct ctl_table *tbl;
 
-	net->core.sysctl_somaxconn = SOMAXCONN;
-
 	tbl = netns_core_table;
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);