diff mbox series

[v1,net-next,02/13] ipv6: Get rid of RTNL for SIOCDELRT and RTM_DELROUTE.

Message ID 20250321040131.21057-3-kuniyu@amazon.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series ipv6: No RTNL for IPv6 routing table. | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 0 this patch: 0
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 0 this patch: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 1 this patch: 1
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 99 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest fail net-next-2025-03-21--12-00 (tests: 862)

Commit Message

Kuniyuki Iwashima March 21, 2025, 4 a.m. UTC
Basically, removing an IPv6 route does not require RTNL because
the IPv6 routing tables are protected by per table lock.  Also,
ip6_route_del() already relies on RCU and the table lock.

inet6_rtm_delroute() calls nexthop_find_by_id() to check if the
nexthop specified by RTA_NH_ID exists.  nexthop uses rbtree and
the top-down walk can be safely performed under RCU.

Let's call nexthop_find_by_id() under RCU and get rid of RTNL
from inet6_rtm_delroute() and SIOCDELRT.

Even if the nexthop is removed after rcu_read_unlock() in
inet6_rtm_delroute(), __remove_nexthop_fib() cleans up the routes
tied to the nexthop, and ip6_route_del() returns -ESRCH.  So the
request was at least valid as of nexthop_find_by_id(), and it's just
a matter of timing.

Note that we need to pass false to lwtunnel_valid_encap_type_attr().
The following patches also use the newroute bool.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
 net/ipv6/route.c | 36 ++++++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 14 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6c9c99fb02fe..b737b242079e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4482,19 +4482,20 @@  int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
 
 	rtmsg_to_fib6_config(net, rtmsg, &cfg);
 
-	rtnl_lock();
 	switch (cmd) {
 	case SIOCADDRT:
+		rtnl_lock();
 		/* Only do the default setting of fc_metric in route adding */
 		if (cfg.fc_metric == 0)
 			cfg.fc_metric = IP6_RT_PRIO_USER;
 		err = ip6_route_add(&cfg, GFP_KERNEL, NULL);
+		rtnl_unlock();
 		break;
 	case SIOCDELRT:
 		err = ip6_route_del(&cfg, NULL);
 		break;
 	}
-	rtnl_unlock();
+
 	return err;
 }
 
@@ -5017,7 +5018,8 @@  static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 };
 
 static int rtm_to_fib6_multipath_config(struct fib6_config *cfg,
-					struct netlink_ext_ack *extack)
+					struct netlink_ext_ack *extack,
+					bool newroute)
 {
 	struct rtnexthop *rtnh;
 	int remaining;
@@ -5051,15 +5053,16 @@  static int rtm_to_fib6_multipath_config(struct fib6_config *cfg,
 	} while (rtnh_ok(rtnh, remaining));
 
 	return lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len,
-					      extack, true);
+					      extack, newroute);
 }
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 			      struct fib6_config *cfg,
 			      struct netlink_ext_ack *extack)
 {
-	struct rtmsg *rtm;
+	bool newroute = nlh->nlmsg_type == RTM_NEWROUTE;
 	struct nlattr *tb[RTA_MAX+1];
+	struct rtmsg *rtm;
 	unsigned int pref;
 	int err;
 
@@ -5168,7 +5171,7 @@  static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
 
-		err = rtm_to_fib6_multipath_config(cfg, extack);
+		err = rtm_to_fib6_multipath_config(cfg, extack, newroute);
 		if (err < 0)
 			goto errout;
 	}
@@ -5188,7 +5191,7 @@  static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
 		err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
-						extack, true);
+						extack, newroute);
 		if (err < 0)
 			goto errout;
 	}
@@ -5511,15 +5514,20 @@  static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
-	if (cfg.fc_nh_id &&
-	    !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
-		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
-		return -EINVAL;
+	if (cfg.fc_nh_id) {
+		rcu_read_lock();
+		err = !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id);
+		rcu_read_unlock();
+
+		if (err) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			return -EINVAL;
+		}
 	}
 
-	if (cfg.fc_mp)
+	if (cfg.fc_mp) {
 		return ip6_route_multipath_del(&cfg, extack);
-	else {
+	} else {
 		cfg.fc_delete_all_nh = 1;
 		return ip6_route_del(&cfg, extack);
 	}
@@ -6731,7 +6739,7 @@  static const struct rtnl_msg_handler ip6_route_rtnl_msg_handlers[] __initconst_o
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_NEWROUTE,
 	 .doit = inet6_rtm_newroute},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_DELROUTE,
-	 .doit = inet6_rtm_delroute},
+	 .doit = inet6_rtm_delroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.owner = THIS_MODULE, .protocol = PF_INET6, .msgtype = RTM_GETROUTE,
 	 .doit = inet6_rtm_getroute, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 };