1 files changed, 76 insertions, 60 deletions

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 4701edffb1f7..b52afe316dc4 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -230,8 +230,8 @@ static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index)
  * Since those fields can change at any moment, use READ_ONCE to
  * access both.
  */
-static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
-					     struct sk_buff *skb)
+static const struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
+						   struct sk_buff *skb)
 {
 	u32 hash = 0;
 	int nh_index = 0;
@@ -343,8 +343,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 {
 	struct net *net = dev_net(dev);
 	struct mpls_shim_hdr *hdr;
+	const struct mpls_nh *nh;
 	struct mpls_route *rt;
-	struct mpls_nh *nh;
 	struct mpls_entry_decoded dec;
 	struct net_device *out_dev;
 	struct mpls_dev *out_mdev;
@@ -377,6 +377,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	if (!pskb_may_pull(skb, sizeof(*hdr)))
 		goto err;
 
+	skb_dst_drop(skb);
+
 	/* Read and decode the label */
 	hdr = mpls_hdr(skb);
 	dec = mpls_entry_decode(hdr);
@@ -405,10 +407,9 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	/* Verify ttl is valid */
 	if (dec.ttl <= 1)
 		goto err;
-	dec.ttl -= 1;
 
 	/* Find the output device */
-	out_dev = rcu_dereference(nh->nh_dev);
+	out_dev = nh->nh_dev;
 	if (!mpls_output_possible(out_dev))
 		goto tx_err;
 
@@ -429,6 +430,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	skb->dev = out_dev;
 	skb->protocol = htons(ETH_P_MPLS_UC);
 
+	dec.ttl -= 1;
 	if (unlikely(!new_header_size && dec.bos)) {
 		/* Penultimate hop popping */
 		if (!mpls_egress(dev_net(out_dev), rt, skb, dec))
@@ -696,7 +698,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
 	    (dev->addr_len != nh->nh_via_alen))
 		goto errout;
 
-	RCU_INIT_POINTER(nh->nh_dev, dev);
+	nh->nh_dev = dev;
 
 	if (!(dev->flags & IFF_UP)) {
 		nh->nh_flags |= RTNH_F_DEAD;
@@ -1017,7 +1019,6 @@ static int mpls_route_add(struct mpls_route_config *cfg,
 		goto errout;
 	}
 
-	err = -ENOMEM;
 	rt = mpls_rt_alloc(nhs, max_via_alen, max_labels);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
@@ -1078,9 +1079,9 @@ static void mpls_get_stats(struct mpls_dev *mdev,
 
 		p = per_cpu_ptr(mdev->stats, i);
 		do {
-			start = u64_stats_fetch_begin(&p->syncp);
+			start = u64_stats_fetch_begin_irq(&p->syncp);
 			local = p->stats;
-		} while (u64_stats_fetch_retry(&p->syncp, start));
+		} while (u64_stats_fetch_retry_irq(&p->syncp, start));
 
 		stats->rx_packets	+= local.rx_packets;
 		stats->rx_bytes		+= local.rx_bytes;
@@ -1362,8 +1363,7 @@ done:
 	(&((struct mpls_dev *)0)->field)
 
 static int mpls_conf_proc(struct ctl_table *ctl, int write,
-			  void __user *buffer,
-			  size_t *lenp, loff_t *ppos)
+			  void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int oval = *(int *)ctl->data;
 	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
@@ -1491,55 +1491,80 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head)
 	kfree(mdev);
 }
 
-static void mpls_ifdown(struct net_device *dev, int event)
+static int mpls_ifdown(struct net_device *dev, int event)
 {
 	struct mpls_route __rcu **platform_label;
 	struct net *net = dev_net(dev);
-	u8 alive, deleted;
 	unsigned index;
 
 	platform_label = rtnl_dereference(net->mpls.platform_label);
 	for (index = 0; index < net->mpls.platform_labels; index++) {
 		struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+		bool nh_del = false;
+		u8 alive = 0;
 
 		if (!rt)
 			continue;
 
-		alive = 0;
-		deleted = 0;
+		if (event == NETDEV_UNREGISTER) {
+			u8 deleted = 0;
+
+			for_nexthops(rt) {
+				if (!nh->nh_dev || nh->nh_dev == dev)
+					deleted++;
+				if (nh->nh_dev == dev)
+					nh_del = true;
+			} endfor_nexthops(rt);
+
+			/* if there are no more nexthops, delete the route */
+			if (deleted == rt->rt_nhn) {
+				mpls_route_update(net, index, NULL, NULL);
+				continue;
+			}
+
+			if (nh_del) {
+				size_t size = sizeof(*rt) + rt->rt_nhn *
+					rt->rt_nh_size;
+				struct mpls_route *orig = rt;
+
+				rt = kmemdup(orig, size, GFP_KERNEL);
+				if (!rt)
+					return -ENOMEM;
+			}
+		}
+
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
 
-			if (rtnl_dereference(nh->nh_dev) != dev)
+			if (nh->nh_dev != dev)
 				goto next;
 
 			switch (event) {
 			case NETDEV_DOWN:
 			case NETDEV_UNREGISTER:
 				nh_flags |= RTNH_F_DEAD;
-				/* fall through */
+				fallthrough;
 			case NETDEV_CHANGE:
 				nh_flags |= RTNH_F_LINKDOWN;
 				break;
 			}
 			if (event == NETDEV_UNREGISTER)
-				RCU_INIT_POINTER(nh->nh_dev, NULL);
+				nh->nh_dev = NULL;
 
 			if (nh->nh_flags != nh_flags)
 				WRITE_ONCE(nh->nh_flags, nh_flags);
 next:
 			if (!(nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)))
 				alive++;
-			if (!rtnl_dereference(nh->nh_dev))
-				deleted++;
 		} endfor_nexthops(rt);
 
 		WRITE_ONCE(rt->rt_nhn_alive, alive);
 
-		/* if there are no more nexthops, delete the route */
-		if (event == NETDEV_UNREGISTER && deleted == rt->rt_nhn)
-			mpls_route_update(net, index, NULL, NULL);
+		if (nh_del)
+			mpls_route_update(net, index, rt, NULL);
 	}
+
+	return 0;
 }
 
 static void mpls_ifup(struct net_device *dev, unsigned int flags)
@@ -1559,14 +1584,12 @@ static void mpls_ifup(struct net_device *dev, unsigned int flags)
 		alive = 0;
 		change_nexthops(rt) {
 			unsigned int nh_flags = nh->nh_flags;
-			struct net_device *nh_dev =
-				rtnl_dereference(nh->nh_dev);
 
 			if (!(nh_flags & flags)) {
 				alive++;
 				continue;
 			}
-			if (nh_dev != dev)
+			if (nh->nh_dev != dev)
 				continue;
 			alive++;
 			nh_flags &= ~flags;
@@ -1583,22 +1606,13 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mpls_dev *mdev;
 	unsigned int flags;
+	int err;
 
 	if (event == NETDEV_REGISTER) {
+		mdev = mpls_add_dev(dev);
+		if (IS_ERR(mdev))
+			return notifier_from_errno(PTR_ERR(mdev));
 
-		/* For now just support Ethernet, IPGRE, IP6GRE, SIT and
-		 * IPIP devices
-		 */
-		if (dev->type == ARPHRD_ETHER ||
-		    dev->type == ARPHRD_LOOPBACK ||
-		    dev->type == ARPHRD_IPGRE ||
-		    dev->type == ARPHRD_IP6GRE ||
-		    dev->type == ARPHRD_SIT ||
-		    dev->type == ARPHRD_TUNNEL) {
-			mdev = mpls_add_dev(dev);
-			if (IS_ERR(mdev))
-				return notifier_from_errno(PTR_ERR(mdev));
-		}
 		return NOTIFY_OK;
 	}
 
@@ -1607,8 +1621,11 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		return NOTIFY_OK;
 
 	switch (event) {
+
 	case NETDEV_DOWN:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
 		flags = dev_get_flags(dev);
@@ -1619,13 +1636,18 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 		break;
 	case NETDEV_CHANGE:
 		flags = dev_get_flags(dev);
-		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
-		else
-			mpls_ifdown(dev, event);
+		} else {
+			err = mpls_ifdown(dev, event);
+			if (err)
+				return notifier_from_errno(err);
+		}
 		break;
 	case NETDEV_UNREGISTER:
-		mpls_ifdown(dev, event);
+		err = mpls_ifdown(dev, event);
+		if (err)
+			return notifier_from_errno(err);
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
 			mpls_dev_sysctl_unregister(dev, mdev);
@@ -1636,8 +1658,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	case NETDEV_CHANGENAME:
 		mdev = mpls_dev_get(dev);
 		if (mdev) {
-			int err;
-
 			mpls_dev_sysctl_unregister(dev, mdev);
 			err = mpls_dev_sysctl_register(dev, mdev);
 			if (err)
@@ -2004,7 +2024,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 		    nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
 				nh->nh_via_alen))
 			goto nla_put_failure;
-		dev = rtnl_dereference(nh->nh_dev);
+		dev = nh->nh_dev;
 		if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 			goto nla_put_failure;
 		if (nh->nh_flags & RTNH_F_LINKDOWN)
@@ -2022,7 +2042,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 
 		for_nexthops(rt) {
-			dev = rtnl_dereference(nh->nh_dev);
+			dev = nh->nh_dev;
 			if (!dev)
 				continue;
 
@@ -2133,18 +2153,14 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 static bool mpls_rt_uses_dev(struct mpls_route *rt,
 			     const struct net_device *dev)
 {
-	struct net_device *nh_dev;
-
 	if (rt->rt_nhn == 1) {
 		struct mpls_nh *nh = rt->rt_nh;
 
-		nh_dev = rtnl_dereference(nh->nh_dev);
-		if (dev == nh_dev)
+		if (nh->nh_dev == dev)
 			return true;
 	} else {
 		for_nexthops(rt) {
-			nh_dev = rtnl_dereference(nh->nh_dev);
-			if (nh_dev == dev)
+			if (nh->nh_dev == dev)
 				return true;
 		} endfor_nexthops(rt);
 	}
@@ -2232,7 +2248,7 @@ static inline size_t lfib_nlmsg_size(struct mpls_route *rt)
 		size_t nhsize = 0;
 
 		for_nexthops(rt) {
-			if (!rtnl_dereference(nh->nh_dev))
+			if (!nh->nh_dev)
 				continue;
 			nhsize += nla_total_size(sizeof(struct rtnexthop));
 			/* RTA_VIA */
@@ -2343,12 +2359,12 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 	u32 labels[MAX_NEW_LABELS];
 	struct mpls_shim_hdr *hdr;
 	unsigned int hdr_size = 0;
+	const struct mpls_nh *nh;
 	struct net_device *dev;
 	struct mpls_route *rt;
 	struct rtmsg *rtm, *r;
 	struct nlmsghdr *nlh;
 	struct sk_buff *skb;
-	struct mpls_nh *nh;
 	u8 n_labels;
 	int err;
 
@@ -2478,7 +2494,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh,
 	    nla_put_via(skb, nh->nh_via_table, mpls_nh_via(rt, nh),
 			nh->nh_via_alen))
 		goto nla_put_failure;
-	dev = rtnl_dereference(nh->nh_dev);
+	dev = nh->nh_dev;
 	if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
 		goto nla_put_failure;
 
@@ -2517,7 +2533,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 		rt0 = mpls_rt_alloc(1, lo->addr_len, 0);
 		if (IS_ERR(rt0))
 			goto nort0;
-		RCU_INIT_POINTER(rt0->rt_nh->nh_dev, lo);
+		rt0->rt_nh->nh_dev = lo;
 		rt0->rt_protocol = RTPROT_KERNEL;
 		rt0->rt_payload_type = MPT_IPV4;
 		rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
@@ -2531,7 +2547,7 @@ static int resize_platform_label_table(struct net *net, size_t limit)
 		rt2 = mpls_rt_alloc(1, lo->addr_len, 0);
 		if (IS_ERR(rt2))
 			goto nort2;
-		RCU_INIT_POINTER(rt2->rt_nh->nh_dev, lo);
+		rt2->rt_nh->nh_dev = lo;
 		rt2->rt_protocol = RTPROT_KERNEL;
 		rt2->rt_payload_type = MPT_IPV6;
 		rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT;
@@ -2594,7 +2610,7 @@ nolabels:
 }
 
 static int mpls_platform_labels(struct ctl_table *table, int write,
-				void __user *buffer, size_t *lenp, loff_t *ppos)
+				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct net *net = table->data;
 	int platform_labels = net->mpls.platform_labels;