From 5057e1aca011e51ef51498c940ef96f3d3e8a305 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sun, 31 May 2026 12:08:12 -0400 Subject: [PATCH] net/sched: act_api: use RCU with deferred freeing for action lifecycle When NEWTFILTER and DELFILTER are run concurrently it is possible to create a race with an associated action. Let's illustrate with CPU0 running NEWTFILTER and CPU1 running DELFILTER: 0: mutex_lock() <-- holds the idr lock 0: rcu_read_lock() 0: p = idr_find(idr, index) <-- action p is valid (RCU protects IDR) 0: mutex_unlock() <-- releases the idr lock 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) <-- Action removed from IDR 1: mutex_unlock() <-- mutex released allowing us to delete the action 1: tcf_action_cleanup(p); kfree(p) <-- Kfrees p immediately, no deferral 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- ouch, UAF p points to freed memory This patch fixes the race condition between NEWTFILTER and DELFILTER by adding struct rcu_head to tc_action used in the deferral and introducing a call_rcu() in the delete path to defer the final kfree(). Note: this is a revert of commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") but also modernization/simplification to directly use kfree_rcu(). Let's illustrate the new restored code path: 0: rcu_read_lock() 1: refcount_dec_and_mutex_lock() <-- refcnt 1->0, mutex held 1: idr_remove(idr, index) 1: mutex_unlock() 1: call_rcu(&p->tcfa_rcu, tcf_action_rcu_free) <-- defer kfree after grace period 0: p = idr_find(idr, index) 0: refcount_inc_not_zero(&p->tcfa_refcnt) <-- fails, refcnt already 0 1: rcu_read_unlock() <-- release so freeing can run after grace period After CPU1 calls idr_remove(), the object is no longer reachable through the IDR. CPU0's subsequent idr_find() will return NULL, and even if it still held a stale pointer, the immediate kfree() is now deferred until after the RCU grace period, so no UAF can occur. Fixes: d7fb60b9cafb ("net_sched: get rid of tcfa_rcu") Suggested-by: Jakub Kicinski Reported-by: Kyle Zeng Tested-by: Victor Nogueira Tested-by: syzbot@syzkaller.appspotmail.com Signed-off-by: Jamal Hadi Salim Tested-by: Kyle Zeng Reviewed-by: Pedro Tammela Reviewed-by: Eric Dumazet Reviewed-by: Victor Nogueira Link: https://patch.msgid.link/20260531160812.68020-1-jhs@mojatatu.com Signed-off-by: Jakub Kicinski --- include/net/act_api.h | 1 + net/sched/act_api.c | 7 +------ 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/include/net/act_api.h b/include/net/act_api.h index d11b79107930..fd2967ee08f7 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -45,6 +45,7 @@ struct tc_action { struct tc_cookie __rcu *user_cookie; struct tcf_chain __rcu *goto_chain; u32 tcfa_flags; + struct rcu_head tcfa_rcu; u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 332fd9695e54..04ea11c90e03 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -112,11 +112,6 @@ struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, } EXPORT_SYMBOL(tcf_action_set_ctrlact); -/* XXX: For standalone actions, we don't need a RCU grace period either, because - * actions are always connected to filters and filters are already destroyed in - * RCU callbacks, so after a RCU grace period actions are already disconnected - * from filters. Readers later can not find us. - */ static void free_tcf(struct tc_action *p) { struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1); @@ -129,7 +124,7 @@ static void free_tcf(struct tc_action *p) if (chain) tcf_chain_put_by_act(chain); - kfree(p); + kfree_rcu(p, tcfa_rcu); } static void offload_action_hw_count_set(struct tc_action *act, -- 2.47.3