Merge: [9.6 P2] IPv6: stable backport from upstream

emmil · emmil · commit dc42504e0e4e · 2025-01-23T13:15:13.000Z
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6127 JIRA: https://issues.redhat.com/browse/RHEL-73281 Signed-off-by: Hangbin Liu <haliu@redhat.com> Approved-by: Florian Westphal <fwestpha@redhat.com> Approved-by: Marcelo Ricardo Leitner <mleitner@redhat.com> Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com> Merged-by: Rado Vrbovsky <rvrbovsk@redhat.com>
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
@@ -132,18 +132,26 @@ void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
 
 static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i,
 				      const struct in6_addr *daddr,
-				      unsigned int prefs,
+				      unsigned int prefs, int l3mdev_index,
 				      struct in6_addr *saddr)
 {
+	struct net_device *l3mdev;
+	struct net_device *dev;
+	bool same_vrf;
 	int err = 0;
 
-	if (f6i && f6i->fib6_prefsrc.plen) {
+	rcu_read_lock();
+
+	l3mdev = dev_get_by_index_rcu(net, l3mdev_index);
+	if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev)
+		dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
+	same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev;
+	if (f6i && f6i->fib6_prefsrc.plen && same_vrf)
 		*saddr = f6i->fib6_prefsrc.addr;
-	} else {
-		struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
+	else
+		err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr);
 
-		err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr);
-	}
+	rcu_read_unlock();
 
 	return err;
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
@@ -1823,7 +1823,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
 							    master, &dst,
 							    scores, hiscore_idx);
 
-			if (scores[hiscore_idx].ifa)
+			if (scores[hiscore_idx].ifa &&
+			    scores[hiscore_idx].scopedist >= 0)
 				goto out;
 		}
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
@@ -1183,8 +1183,8 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 		while (sibling) {
 			if (sibling->fib6_metric == rt->fib6_metric &&
 			    rt6_qualify_for_ecmp(sibling)) {
-				list_add_tail(&rt->fib6_siblings,
-					      &sibling->fib6_siblings);
+				list_add_tail_rcu(&rt->fib6_siblings,
+						  &sibling->fib6_siblings);
 				break;
 			}
 			sibling = rcu_dereference_protected(sibling->fib6_next,
@@ -1245,7 +1245,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 							 fib6_siblings)
 					sibling->fib6_nsiblings--;
 				rt->fib6_nsiblings = 0;
-				list_del_init(&rt->fib6_siblings);
+				list_del_rcu(&rt->fib6_siblings);
 				rt6_multipath_rebalance(next_sibling);
 				return err;
 			}
@@ -1959,7 +1959,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 					 &rt->fib6_siblings, fib6_siblings)
 			sibling->fib6_nsiblings--;
 		rt->fib6_nsiblings = 0;
-		list_del_init(&rt->fib6_siblings);
+		list_del_rcu(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
@@ -1130,6 +1130,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		from = rt ? rcu_dereference(rt->from) : NULL;
 		err = ip6_route_get_saddr(net, from, &fl6->daddr,
 					  sk ? inet6_sk(sk)->srcprefs : 0,
+					  fl6->flowi6_l3mdev,
 					  &fl6->saddr);
 		rcu_read_unlock();
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
@@ -377,6 +377,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 {
 	struct rt6_info *rt = (struct rt6_info *)dst;
 	struct inet6_dev *idev = rt->rt6i_idev;
+	struct fib6_info *from;
 
 	if (idev && idev->dev != blackhole_netdev) {
 		struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
@@ -386,6 +387,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 			in6_dev_put(idev);
 		}
 	}
+	from = unrcu_pointer(xchg(&rt->from, NULL));
+	fib6_info_release(from);
 }
 
 static bool __rt6_check_expired(const struct rt6_info *rt)
@@ -416,8 +419,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 		      struct flowi6 *fl6, int oif, bool have_oif_match,
 		      const struct sk_buff *skb, int strict)
 {
-	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
+	struct fib6_info *sibling;
 
 	if (!match->nh && (!match->fib6_nsiblings || have_oif_match))
 		goto out;
@@ -443,8 +446,8 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
 		goto out;
 
-	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
-				 fib6_siblings) {
+	list_for_each_entry_rcu(sibling, &match->fib6_siblings,
+				fib6_siblings) {
 		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
@@ -1449,7 +1452,6 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
 static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 				 struct rt6_exception *rt6_ex)
 {
-	struct fib6_info *from;
 	struct net *net;
 
 	if (!bucket || !rt6_ex)
@@ -1461,8 +1463,6 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
-	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
 	hlist_del_rcu(&rt6_ex->hlist);
@@ -5216,14 +5216,18 @@ static void ip6_route_mpath_notify(struct fib6_info *rt,
 	 * nexthop. Since sibling routes are always added at the end of
 	 * the list, find the first sibling of the last route appended
 	 */
+	rcu_read_lock();
+
 	if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
-		rt = list_first_entry(&rt_last->fib6_siblings,
-				      struct fib6_info,
-				      fib6_siblings);
+		rt = list_first_or_null_rcu(&rt_last->fib6_siblings,
+					    struct fib6_info,
+					    fib6_siblings);
 	}
 
 	if (rt)
 		inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
+
+	rcu_read_unlock();
 }
 
 static bool ip6_route_mpath_should_notify(const struct fib6_info *rt)
@@ -5568,17 +5572,21 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i)
 		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
 					 &nexthop_len);
 	} else {
-		struct fib6_info *sibling, *next_sibling;
 		struct fib6_nh *nh = f6i->fib6_nh;
+		struct fib6_info *sibling;
 
 		nexthop_len = 0;
 		if (f6i->fib6_nsiblings) {
 			rt6_nh_nlmsg_size(nh, &nexthop_len);
 
-			list_for_each_entry_safe(sibling, next_sibling,
-						 &f6i->fib6_siblings, fib6_siblings) {
+			rcu_read_lock();
+
+			list_for_each_entry_rcu(sibling, &f6i->fib6_siblings,
+						fib6_siblings) {
 				rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len);
 			}
+
+			rcu_read_unlock();
 		}
 		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
@@ -5708,7 +5716,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				goto nla_put_failure;
 	} else if (dest) {
 		struct in6_addr saddr_buf;
-		if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
+		if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
 		    nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
 			goto nla_put_failure;
 	}
@@ -5742,7 +5750,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		    lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
 			goto nla_put_failure;
 	} else if (rt->fib6_nsiblings) {
-		struct fib6_info *sibling, *next_sibling;
+		struct fib6_info *sibling;
 		struct nlattr *mp;
 
 		mp = nla_nest_start_noflag(skb, RTA_MULTIPATH);
@@ -5754,14 +5762,21 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 				    0) < 0)
 			goto nla_put_failure;
 
-		list_for_each_entry_safe(sibling, next_sibling,
-					 &rt->fib6_siblings, fib6_siblings) {
+		rcu_read_lock();
+
+		list_for_each_entry_rcu(sibling, &rt->fib6_siblings,
+					fib6_siblings) {
 			if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
 					    sibling->fib6_nh->fib_nh_weight,
-					    AF_INET6, 0) < 0)
+					    AF_INET6, 0) < 0) {
+				rcu_read_unlock();
+
 				goto nla_put_failure;
+			}
 		}
 
+		rcu_read_unlock();
+
 		nla_nest_end(skb, mp);
 	} else if (rt->nh) {
 		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
@@ -6198,7 +6213,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 	err = -ENOBUFS;
 	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
-	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+	skb = nlmsg_new(rt6_nlmsg_size(rt), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
@@ -6211,7 +6226,7 @@ void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
 		goto errout;
 	}
 	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
-		    info->nlh, gfp_any());
+		    info->nlh, GFP_ATOMIC);
 	return;
 errout:
 	if (err < 0)
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
@@ -64,6 +64,7 @@ TEST_PROGS += test_vxlan_mdb.sh
 TEST_PROGS += test_bridge_neigh_suppress.sh
 TEST_PROGS += test_vxlan_nolocalbypass.sh
 TEST_PROGS += test_bridge_backup_port.sh
+TEST_PROGS += ipv6_route_update_soft_lockup.sh
 
 TEST_FILES := settings
 TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
diff --git a/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh b/tools/testing/selftests/net/ipv6_route_update_soft_lockup.sh
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
diff --git a/tools/testing/selftests/net/vrf_route_leaking.sh b/tools/testing/selftests/net/vrf_route_leaking.sh

Original file line number	Diff line number	Diff line change
`@@ -1823,7 +1823,8 @@ int ipv6_dev_get_saddr(struct net net, const struct net_device dst_dev,`
`1823`	`1823`	`master, &dst,`
`1824`	`1824`	`scores, hiscore_idx);`
`1825`	`1825`
`1826`		`- if (scores[hiscore_idx].ifa)`
	`1826`	`+ if (scores[hiscore_idx].ifa &&`
	`1827`	`+ scores[hiscore_idx].scopedist >= 0)`
`1827`	`1828`	`goto out;`
`1828`	`1829`	`}`
`1829`	`1830`