summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHerbert Xu <herbert@gondor.apana.org.au>2026-06-12 12:58:59 +0800
committerSteffen Klassert <steffen.klassert@secunet.com>2026-06-17 11:17:17 +0200
commitddd3d0132920319ac426e12456013eadbae67e15 (patch)
treee1c8e4a41d57ef1408cac1ee61f8c2a7d4d405d1
parent8045c0df98d4f14c54e5cb875f1c9c0ce89fe4ff (diff)
downloadlinux-next-ddd3d0132920319ac426e12456013eadbae67e15.tar.gz
linux-next-ddd3d0132920319ac426e12456013eadbae67e15.zip
xfrm: Fix xfrm state cache insertion race
The xfrm input state cache insertion code checks the validity of the state before acquiring the global xfrm_state_lock. Thus it's possible for someone else to kill the state after it passed the validity check, and then the insertion will add the dead state to the cache. Fix this by moving the validity check inside the lock. This entire function is called on the input path, where BH must be off (e.g., the caller of this function xfrm_input acquires its spinlocks without disabling BH). So there is no need to disable BH here or take the RCU read lock. Remove both and replace them with an assertion that trips if BH is accidentally enabled on some future calling path. Fixes: 81a331a0e72d ("xfrm: Add an inbound percpu state cache.") Reported-by: Zero Day Initiative <zdi-disclosures@trendmicro.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Reviewed-by: Simon Horman <horms@kernel.org> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
-rw-r--r--net/xfrm/xfrm_state.c21
1 files changed, 14 insertions, 7 deletions
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index d8457ceaf28c..9e87f7028201 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1207,9 +1207,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
struct hlist_head *state_cache_input;
struct xfrm_state *x = NULL;
+ /* BH is always disabled on the input path. */
+ lockdep_assert_in_softirq();
+
state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input);
- rcu_read_lock();
hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) {
if (x->props.family != family ||
x->id.spi != spi ||
@@ -1227,20 +1229,25 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark,
xfrm_hash_ptrs_get(net, &state_ptrs);
x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family);
-
- if (x && x->km.state == XFRM_STATE_VALID) {
- spin_lock_bh(&net->xfrm.xfrm_state_lock);
- if (hlist_unhashed(&x->state_cache_input)) {
+ if (x) {
+ spin_lock(&net->xfrm.xfrm_state_lock);
+ if (x->km.state != XFRM_STATE_VALID) {
+ /*
+ * The state is about to be destroyed.
+ *
+ * Don't add it to the cache but still
+ * return it to the caller.
+ */
+ } else if (hlist_unhashed(&x->state_cache_input)) {
hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
} else {
hlist_del_rcu(&x->state_cache_input);
hlist_add_head_rcu(&x->state_cache_input, state_cache_input);
}
- spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+ spin_unlock(&net->xfrm.xfrm_state_lock);
}
out:
- rcu_read_unlock();
return x;
}
EXPORT_SYMBOL(xfrm_input_state_lookup);