From: David Ahern <dsahern@kernel.org>
To: netdev@vger.kernel.org
Cc: ralf@mandelbit.com, David Ahern <dahern@nvidia.com>,
David Ahern <dsahern@kernel.org>,
Ido Schimmel <idosch@nvidia.com>,
"David S . Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@kernel.org>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Simon Horman <horms@kernel.org>,
"Claude Sonnet 5 . 5" <noreply@anthropic.com>
Subject: [RFC net-next 1/6] ipv6: validate dsts against the netns route generation
Date: Sun, 22 Nov 2026 15:26:59 -0700 [thread overview]
Message-ID: <20261122222717.126333-3-dsahern@kernel.org> (raw)
In-Reply-To: <20261122222717.126333-1-dsahern@kernel.org>
From: David Ahern <dahern@nvidia.com>
An rt6_info never carried the fib6 serial number it was created
under. rt6_get_cookie() read fn->fn_sernum through rt->from at the time a
socket, dst_cache or xfrm bundle stored its cookie, so a change that
landed between route lookup and cookie capture was folded into the
cookie and a stale dst looked valid. Only nexthop-object pcpu routes
were stamped at creation, with the same counter.
net->ipv6.fib6_sernum is already the counter that rt_genid_ipv6()
reads and that every FIB change bumps. Stamp every dst with it in
ip6_dst_alloc() and validate with a plain comparison in
ip6_dst_check(); the remaining checks are that the fib6_info is still
in the tree and not expired. rt6_get_cookie() now returns rt->sernum
and fib6_get_cookie_safe() goes away. fn_sernum stays for route dump
consistency.
Because validity now lives in the dst, long-lived dsts must be
re-stamped when a lookup finds them again, or they would stay invalid
forever:
- pcpu dsts of routes with an embedded fib6_nh are re-stamped in
rt6_get_pcpu_route(); nexthop-object pcpu dsts are still dropped
and rebuilt.
- exception dsts are re-stamped by rt6_find_cached_rt().
The smp_wmb() in __fib6_update_sernum_upto_root() paired with the
smp_rmb() in fib6_get_cookie_safe(), so that a lockless reader that saw
a new fn_sernum also saw the route inserted before it. That reader is
gone. The remaining fn_sernum readers, the route dumps, take tb6_lock
after reading it and the writers hold it, so drop the barrier.
ip6_link_failure() still writes fn_sernum, which no longer
invalidates anything; that is addressed in the next patch.
Signed-off-by: David Ahern <dahern@nvidia.com>
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
---
include/net/ip6_fib.h | 42 +++------------------------
net/ipv6/ip6_fib.c | 2 --
net/ipv6/route.c | 66 +++++++++++++++++++++++++------------------
3 files changed, 43 insertions(+), 67 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 232289b439c3..ecce7ab007a5 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -273,46 +273,12 @@ static inline bool fib6_check_expired(const struct fib6_info *f6i)
return false;
}
-/* Function to safely get fn->fn_sernum for passed in rt
- * and store result in passed in cookie.
- * Return true if we can get cookie safely
- * Return false if not
- */
-static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i,
- u32 *cookie)
-{
- struct fib6_node *fn;
- bool status = false;
-
- fn = rcu_dereference(f6i->fib6_node);
-
- if (fn) {
- *cookie = READ_ONCE(fn->fn_sernum);
- /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */
- smp_rmb();
- status = true;
- }
-
- return status;
-}
-
static inline u32 rt6_get_cookie(const struct rt6_info *rt)
{
- struct fib6_info *from;
- u32 cookie = 0;
-
- if (rt->sernum)
- return rt->sernum;
-
- rcu_read_lock();
-
- from = rcu_dereference(rt->from);
- if (from)
- fib6_get_cookie_safe(from, &cookie);
-
- rcu_read_unlock();
-
- return cookie;
+ /* sernum is the netns route generation the dst was created or last
+ * revalidated under; ip6_dst_check() compares it to the current one.
+ */
+ return READ_ONCE(rt->sernum);
}
static inline void ip6_rt_put(struct rt6_info *rt)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index e1d49897d6ab..d465ac6ffbc6 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1432,8 +1432,6 @@ static void __fib6_update_sernum_upto_root(struct fib6_info *rt,
struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
lockdep_is_held(&rt->fib6_table->tb6_lock));
- /* paired with smp_rmb() in fib6_get_cookie_safe() */
- smp_wmb();
while (fn) {
WRITE_ONCE(fn->fn_sernum, sernum);
fn = rcu_dereference_protected(fn->parent,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4a4c5ace63c5..1f7b2cdc1d9f 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -367,6 +367,7 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
if (rt) {
rt6_info_init(rt);
+ rt->sernum = rt_genid_ipv6(net);
atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc);
}
@@ -1458,15 +1459,24 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
ip6_rt_copy_init(pcpu_rt, res);
pcpu_rt->rt6i_flags |= RTF_PCPU;
- if (f6i->nh)
- pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));
-
return pcpu_rt;
}
static bool rt6_is_valid(const struct rt6_info *rt6)
{
- return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));
+ return READ_ONCE(rt6->sernum) == rt_genid_ipv6(dev_net(rt6->dst.dev));
+}
+
+/* @rt was just found by a lookup against the current FIB, so it is as
+ * valid as a freshly allocated dst. Call with rcu_read_lock() held.
+ */
+static void rt6_refresh_sernum(struct rt6_info *rt,
+ const struct fib6_result *res)
+{
+ int genid = rt_genid_ipv6(dev_net(ip6_rt_get_dev_rcu(res)));
+
+ if (READ_ONCE(rt->sernum) != genid)
+ WRITE_ONCE(rt->sernum, genid);
}
/* It should be called with rcu_read_lock() acquired */
@@ -1476,7 +1486,14 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
- if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) {
+ /* Routes with an embedded fib6_nh keep their pcpu dsts across FIB
+ * changes; nexthop objects can change under them, so those are
+ * dropped and rebuilt.
+ */
+ if (pcpu_rt && !rt6_is_valid(pcpu_rt) && !res->f6i->nh)
+ rt6_refresh_sernum(pcpu_rt, res);
+
+ if (pcpu_rt && !rt6_is_valid(pcpu_rt)) {
struct rt6_info *prev, **p;
p = this_cpu_ptr(res->nh->rt6i_pcpu);
@@ -1878,8 +1895,10 @@ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
bucket = fib6_nh_get_excptn_bucket(res->nh, NULL);
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
- if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+ if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) {
ret = rt6_ex->rt6i;
+ rt6_refresh_sernum(ret, res);
+ }
#ifdef CONFIG_IPV6_SUBTREES
/* Use fib6_src as src_key and redo lookup */
@@ -2767,27 +2786,18 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
-static bool fib6_check(struct fib6_info *f6i, u32 cookie)
+static bool fib6_check(struct fib6_info *f6i)
{
- u32 rt_cookie = 0;
-
- if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie)
- return false;
-
- if (fib6_check_expired(f6i))
+ if (!rcu_access_pointer(f6i->fib6_node))
return false;
- return true;
+ return !fib6_check_expired(f6i);
}
static struct dst_entry *rt6_check(struct rt6_info *rt,
- struct fib6_info *from,
- u32 cookie)
+ struct fib6_info *from)
{
- u32 rt_cookie = 0;
-
- if (!from || !fib6_get_cookie_safe(from, &rt_cookie) ||
- rt_cookie != cookie)
+ if (!from || !rcu_access_pointer(from->fib6_node))
return NULL;
if (rt6_check_expired(rt))
@@ -2797,12 +2807,11 @@ static struct dst_entry *rt6_check(struct rt6_info *rt,
}
static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt,
- struct fib6_info *from,
- u32 cookie)
+ struct fib6_info *from)
{
if (!__rt6_check_expired(rt) &&
READ_ONCE(rt->dst.obsolete) == DST_OBSOLETE_FORCE_CHK &&
- fib6_check(from, cookie))
+ fib6_check(from))
return &rt->dst;
return NULL;
}
@@ -2816,8 +2825,11 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
rt = dst_rt6_info(dst);
- if (rt->sernum)
- return rt6_is_valid(rt) ? dst : NULL;
+ /* Any FIB change bumps the netns generation, which invalidates
+ * every dst created under an older one.
+ */
+ if (!rt6_is_valid(rt))
+ return NULL;
rcu_read_lock();
@@ -2830,9 +2842,9 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst,
if (from && (rt->rt6i_flags & RTF_PCPU ||
unlikely(rt->dst.rt_uncached_list)))
- dst_ret = rt6_dst_from_check(rt, from, cookie);
+ dst_ret = rt6_dst_from_check(rt, from);
else
- dst_ret = rt6_check(rt, from, cookie);
+ dst_ret = rt6_check(rt, from);
rcu_read_unlock();
--
2.43.0
next prev parent reply other threads:[~2026-11-22 22:27 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-22 22:26 David Ahern
2026-11-22 22:26 ` [RFC net-next 0/6] ipv6: validate dsts against the netns route generation David Ahern
2026-11-22 22:30 ` David Ahern
2026-11-22 22:26 ` David Ahern [this message]
2026-11-22 22:27 ` [RFC net-next 2/6] ipv6: invalidate the failing dst in ip6_link_failure() David Ahern
2026-11-22 22:27 ` [RFC net-next 3/6] nexthop: factor out nh_has_f6i() David Ahern
2026-11-22 22:27 ` [RFC net-next 4/6] nexthop: bump the IPv6 route generation on group changes David Ahern
2026-11-22 22:27 ` [RFC net-next 5/6] ipv6: scope exception invalidation to the affected nexthop David Ahern
2026-11-22 22:27 ` [RFC net-next 6/6] ipv6: make rt_genid_bump_ipv6() a plain counter increment David Ahern
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261122222717.126333-3-dsahern@kernel.org \
--to=dsahern@kernel.org \
--cc=dahern@nvidia.com \
--cc=davem@davemloft.net \
--cc=edumazet@kernel.org \
--cc=horms@kernel.org \
--cc=idosch@nvidia.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=noreply@anthropic.com \
--cc=pabeni@redhat.com \
--cc=ralf@mandelbit.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox