xsk: do not call synchronize_net() under RCU read lock

The XSKMAP update and delete functions called synchronize_net(), which
can sleep. It is not allowed to sleep during an RCU read section.

Instead we need to make sure that the sock sk_destruct (xsk_destruct)
function is asynchronously called after an RCU grace period. Setting
the SOCK_RCU_FREE flag for XDP sockets takes care of this.

Fixes: fbfc504a24f5 ("bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 9f8463a..47147c9 100644 (file)
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -192,11 +192,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
        sock_hold(sock->sk);
 
        old_xs = xchg(&m->xsk_map[i], xs);
-       if (old_xs) {
-               /* Make sure we've flushed everything. */
-               synchronize_net();
+       if (old_xs)
                sock_put((struct sock *)old_xs);
-       }
 
        sockfd_put(sock);
        return 0;
@@ -212,11 +209,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key)
                return -EINVAL;
 
        old_xs = xchg(&m->xsk_map[k], NULL);
-       if (old_xs) {
-               /* Make sure we've flushed everything. */
-               synchronize_net();
+       if (old_xs)
                sock_put((struct sock *)old_xs);
-       }
 
        return 0;
 }

diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4e937cd..6615040 100644 (file)
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -744,6 +744,8 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
        sk->sk_destruct = xsk_destruct;
        sk_refcnt_debug_inc(sk);
 
+       sock_set_flag(sk, SOCK_RCU_FREE);
+
        xs = xdp_sk(sk);
        mutex_init(&xs->mutex);
        spin_lock_init(&xs->tx_completion_lock);