In reuseport_array_free(), the rcu_read_lock() cannot ensure sk is still
valid.  It is because bpf_sk_reuseport_detach() can be called from
__sk_destruct() which is invoked through call_rcu(..., __sk_destruct).

This patch takes the reuseport_lock in reuseport_array_free() which
is not the fast path.  The lock is taken inside the loop in case
that the bpf map is big.

Signed-off-by: Martin KaFai Lau <ka...@fb.com>
---
 kernel/bpf/reuseport_array.c | 27 +++++----------------------
 1 file changed, 5 insertions(+), 22 deletions(-)

diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 50c083ba978c..9e593ac31ad7 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -103,29 +103,11 @@ static void reuseport_array_free(struct bpf_map *map)
         * array now. Hence, this function only races with
         * bpf_sk_reuseport_detach() which was triggerred by
         * close() or disconnect().
-        *
-        * This function and bpf_sk_reuseport_detach() are
-        * both removing sk from "array".  Who removes it
-        * first does not matter.
-        *
-        * The only concern here is bpf_sk_reuseport_detach()
-        * may access "array" which is being freed here.
-        * bpf_sk_reuseport_detach() access this "array"
-        * through sk->sk_user_data _and_ with sk->sk_callback_lock
-        * held which is enough because this "array" is not freed
-        * until all sk->sk_user_data has stopped referencing this "array".
-        *
-        * Hence, due to the above, taking "reuseport_lock" is not
-        * needed here.
         */
-
-       /*
-        * Since reuseport_lock is not taken, sk is accessed under
-        * rcu_read_lock()
-        */
-       rcu_read_lock();
        for (i = 0; i < map->max_entries; i++) {
-               sk = rcu_dereference(array->ptrs[i]);
+               spin_lock_bh(&reuseport_lock);
+               sk = rcu_dereference_protected(array->ptrs[i],
+                                       lockdep_is_held(&reuseport_lock));
                if (sk) {
                        write_lock_bh(&sk->sk_callback_lock);
                        /*
@@ -137,8 +119,9 @@ static void reuseport_array_free(struct bpf_map *map)
                        write_unlock_bh(&sk->sk_callback_lock);
                        RCU_INIT_POINTER(array->ptrs[i], NULL);
                }
+               spin_unlock_bh(&reuseport_lock);
+               cond_resched();
        }
-       rcu_read_unlock();
 
        /*
         * Once reaching here, all sk->sk_user_data is not
-- 
2.17.1

Reply via email to