Merge branch 'nexthop-convert-rtm_-new-del-nexthop-to-per-netns-rtnl'

Kuniyuki Iwashima says:

====================
nexthop: Convert RTM_{NEW,DEL}NEXTHOP to per-netns RTNL.

Patch 1 - 5 move some validation for RTM_NEWNEXTHOP so that it can be
called without RTNL.

Patch 6 & 7 converts RTM_NEWNEXTHOP and RTM_DELNEXTHOP to per-netns RTNL.

Note that RTM_GETNEXTHOP and RTM_GETNEXTHOPBUCKET are not touched in
this series.

rtm_get_nexthop() can be easily converted to RCU, but rtm_dump_nexthop()
needs more work due to the left-to-right rbtree walk, which looks prone
to node deletion and tree rotation without a retry mechanism.

v1: https://lore.kernel.org/netdev/20250318233240.53946-1-kuniyu@amazon.com/
====================

Link: https://patch.msgid.link/20250319230743.65267-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 112 insertions, 71 deletions

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 01df7dd795f0..467151517023 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1272,10 +1272,8 @@ static int nh_check_attr_group(struct net *net,
 			       u16 nh_grp_type, struct netlink_ext_ack *extack)
 {
 	unsigned int len = nla_len(tb[NHA_GROUP]);
-	u8 nh_family = AF_UNSPEC;
 	struct nexthop_grp *nhg;
 	unsigned int i, j;
-	u8 nhg_fdb = 0;
 
 	if (!len || len & (sizeof(struct nexthop_grp) - 1)) {
 		NL_SET_ERR_MSG(extack,
@@ -1307,10 +1305,41 @@ static int nh_check_attr_group(struct net *net,
 		}
 	}
 
-	if (tb[NHA_FDB])
-		nhg_fdb = 1;
 	nhg = nla_data(tb[NHA_GROUP]);
-	for (i = 0; i < len; ++i) {
+	for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) {
+		if (!tb[i])
+			continue;
+		switch (i) {
+		case NHA_HW_STATS_ENABLE:
+		case NHA_FDB:
+			continue;
+		case NHA_RES_GROUP:
+			if (nh_grp_type == NEXTHOP_GRP_TYPE_RES)
+				continue;
+			break;
+		}
+		NL_SET_ERR_MSG(extack,
+			       "No other attributes can be set in nexthop groups");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nh_check_attr_group_rtnl(struct net *net, struct nlattr *tb[],
+				    struct netlink_ext_ack *extack)
+{
+	u8 nh_family = AF_UNSPEC;
+	struct nexthop_grp *nhg;
+	unsigned int len;
+	unsigned int i;
+	u8 nhg_fdb;
+
+	len = nla_len(tb[NHA_GROUP]) / sizeof(*nhg);
+	nhg = nla_data(tb[NHA_GROUP]);
+	nhg_fdb = !!tb[NHA_FDB];
+
+	for (i = 0; i < len; i++) {
 		struct nexthop *nh;
 		bool is_fdb_nh;
 
@@ -1330,22 +1359,6 @@ static int nh_check_attr_group(struct net *net,
 			return -EINVAL;
 		}
 	}
-	for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) {
-		if (!tb[i])
-			continue;
-		switch (i) {
-		case NHA_HW_STATS_ENABLE:
-		case NHA_FDB:
-			continue;
-		case NHA_RES_GROUP:
-			if (nh_grp_type == NEXTHOP_GRP_TYPE_RES)
-				continue;
-			break;
-		}
-		NL_SET_ERR_MSG(extack,
-			       "No other attributes can be set in nexthop groups");
-		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -2679,9 +2692,6 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	int err;
 	int i;
 
-	if (WARN_ON(!num_nh))
-		return ERR_PTR(-EINVAL);
-
 	nh = nexthop_alloc();
 	if (!nh)
 		return ERR_PTR(-ENOMEM);
@@ -2915,11 +2925,6 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg,
 	struct nexthop *nh;
 	int err;
 
-	if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) {
-		NL_SET_ERR_MSG(extack, "Replace requires nexthop id");
-		return ERR_PTR(-EINVAL);
-	}
-
 	if (!cfg->nh_id) {
 		cfg->nh_id = nh_find_unused_id(net);
 		if (!cfg->nh_id) {
@@ -3016,19 +3021,13 @@ static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg,
 }
 
 static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
-			    struct nlmsghdr *nlh, struct nh_config *cfg,
+			    struct nlmsghdr *nlh, struct nlattr **tb,
+			    struct nh_config *cfg,
 			    struct netlink_ext_ack *extack)
 {
 	struct nhmsg *nhm = nlmsg_data(nlh);
-	struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)];
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*nhm), tb,
-			  ARRAY_SIZE(rtm_nh_policy_new) - 1,
-			  rtm_nh_policy_new, extack);
-	if (err < 0)
-		return err;
-
 	err = -EINVAL;
 	if (nhm->resvd || nhm->nh_scope) {
 		NL_SET_ERR_MSG(extack, "Invalid values in ancillary header");
@@ -3093,7 +3092,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 			NL_SET_ERR_MSG(extack, "Invalid group type");
 			goto out;
 		}
-		err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb),
+
+		err = nh_check_attr_group(net, tb, ARRAY_SIZE(rtm_nh_policy_new),
 					  cfg->nh_grp_type, extack);
 		if (err)
 			goto out;
@@ -3126,25 +3126,6 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 		goto out;
 	}
 
-	if (!cfg->nh_fdb && tb[NHA_OIF]) {
-		cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]);
-		if (cfg->nh_ifindex)
-			cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex);
-
-		if (!cfg->dev) {
-			NL_SET_ERR_MSG(extack, "Invalid device index");
-			goto out;
-		} else if (!(cfg->dev->flags & IFF_UP)) {
-			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-			err = -ENETDOWN;
-			goto out;
-		} else if (!netif_carrier_ok(cfg->dev)) {
-			NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down");
-			err = -ENETDOWN;
-			goto out;
-		}
-	}
-
 	err = -EINVAL;
 	if (tb[NHA_GATEWAY]) {
 		struct nlattr *gwa = tb[NHA_GATEWAY];
@@ -3188,7 +3169,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 
 		cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]);
 		err = lwtunnel_valid_encap_type(cfg->nh_encap_type,
-						extack, true);
+						extack, false);
 		if (err < 0)
 			goto out;
 
@@ -3207,22 +3188,76 @@ out:
 	return err;
 }
 
+static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb,
+				 struct nh_config *cfg,
+				 struct netlink_ext_ack *extack)
+{
+	if (tb[NHA_GROUP])
+		return nh_check_attr_group_rtnl(net, tb, extack);
+
+	if (tb[NHA_OIF]) {
+		cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]);
+		if (cfg->nh_ifindex)
+			cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex);
+
+		if (!cfg->dev) {
+			NL_SET_ERR_MSG(extack, "Invalid device index");
+			return -EINVAL;
+		}
+
+		if (!(cfg->dev->flags & IFF_UP)) {
+			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+			return -ENETDOWN;
+		}
+
+		if (!netif_carrier_ok(cfg->dev)) {
+			NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down");
+			return -ENETDOWN;
+		}
+	}
+
+	return 0;
+}
+
 /* rtnl */
 static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 			   struct netlink_ext_ack *extack)
 {
+	struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)];
 	struct net *net = sock_net(skb->sk);
 	struct nh_config cfg;
 	struct nexthop *nh;
 	int err;
 
-	err = rtm_to_nh_config(net, skb, nlh, &cfg, extack);
-	if (!err) {
-		nh = nexthop_add(net, &cfg, extack);
-		if (IS_ERR(nh))
-			err = PTR_ERR(nh);
+	err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb,
+			  ARRAY_SIZE(rtm_nh_policy_new) - 1,
+			  rtm_nh_policy_new, extack);
+	if (err < 0)
+		goto out;
+
+	err = rtm_to_nh_config(net, skb, nlh, tb, &cfg, extack);
+	if (err)
+		goto out;
+
+	if (cfg.nlflags & NLM_F_REPLACE && !cfg.nh_id) {
+		NL_SET_ERR_MSG(extack, "Replace requires nexthop id");
+		err = -EINVAL;
+		goto out;
 	}
 
+	rtnl_net_lock(net);
+
+	err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack);
+	if (err)
+		goto unlock;
+
+	nh = nexthop_add(net, &cfg, extack);
+	if (IS_ERR(nh))
+		err = PTR_ERR(nh);
+
+unlock:
+	rtnl_net_unlock(net);
+out:
 	return err;
 }
 
@@ -3279,13 +3314,17 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
+	rtnl_net_lock(net);
+
 	nh = nexthop_find_by_id(net, id);
-	if (!nh)
-		return -ENOENT;
+	if (nh)
+		remove_nexthop(net, nh, &nlinfo);
+	else
+		err = -ENOENT;
 
-	remove_nexthop(net, nh, &nlinfo);
+	rtnl_net_unlock(net);
 
-	return 0;
+	return err;
 }
 
 /* rtnl */
@@ -4037,18 +4076,20 @@ static struct pernet_operations nexthop_net_ops = {
 };
 
 static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = {
-	{.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop},
-	{.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop},
+	{.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
+	{.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
 	{.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop,
 	 .dumpit = rtm_dump_nexthop},
 	{.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket,
 	 .dumpit = rtm_dump_nexthop_bucket},
 	{.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP,
-	 .doit = rtm_new_nexthop},
+	 .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP,
 	 .dumpit = rtm_dump_nexthop},
 	{.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP,
-	 .doit = rtm_new_nexthop},
+	 .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP,
 	 .dumpit = rtm_dump_nexthop},
 };