diff mbox series

[bpf-next,v6,09/12] bpf: Allow selecting reuseport socket from a SOCKMAP

Message ID 20200127131057.150941-10-jakub@cloudflare.com
State Awaiting Upstream
Delegated to: BPF Maintainers
Headers show
Series Extend SOCKMAP to store listening sockets | expand

Commit Message

Jakub Sitnicki Jan. 27, 2020, 1:10 p.m. UTC 
SOCKMAP now supports storing references to listening sockets. Nothing keeps
us from using it as an array of sockets to select from in BPF reuseport
programs. Whitelist the map type with the bpf_sk_select_reuseport helper.

The restriction that the socket has to be a member of a reuseport group
still applies. Socket from a SOCKMAP that does not have sk_reuseport_cb set
is not a valid target and we signal it with -EINVAL.

This lifts the restriction that SOCKARRAY imposes, if SOCKMAP is used with
reuseport BPF, the listening sockets can exist in more than one BPF map at
the same time.

Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 kernel/bpf/verifier.c |  6 ++++--
 net/core/filter.c     | 15 ++++++++++-----
 2 files changed, 14 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1cc945daa9c8..9def066e6847 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3693,7 +3693,8 @@  static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_sk_redirect_map &&
 		    func_id != BPF_FUNC_sock_map_update &&
 		    func_id != BPF_FUNC_map_delete_elem &&
-		    func_id != BPF_FUNC_msg_redirect_map)
+		    func_id != BPF_FUNC_msg_redirect_map &&
+		    func_id != BPF_FUNC_sk_select_reuseport)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_SOCKHASH:
@@ -3774,7 +3775,8 @@  static int check_map_func_compatibility(struct bpf_verifier_env *env,
 			goto error;
 		break;
 	case BPF_FUNC_sk_select_reuseport:
-		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
+		    map->map_type != BPF_MAP_TYPE_SOCKMAP)
 			goto error;
 		break;
 	case BPF_FUNC_map_peek_elem:
diff --git a/net/core/filter.c b/net/core/filter.c
index 792e3744b915..6922f1a55383 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8620,6 +8620,7 @@  struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
 BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 	   struct bpf_map *, map, void *, key, u32, flags)
 {
+	bool is_sockarray = map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
 	struct sock_reuseport *reuse;
 	struct sock *selected_sk;
 
@@ -8628,12 +8629,16 @@  BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
 		return -ENOENT;
 
 	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
-	if (!reuse)
-		/* selected_sk is unhashed (e.g. by close()) after the
-		 * above map_lookup_elem().  Treat selected_sk has already
-		 * been removed from the map.
+	if (!reuse) {
+		/* reuseport_array has only sk with non NULL sk_reuseport_cb.
+		 * The only (!reuse) case here is - the sk has already been
+		 * unhashed (e.g. by close()), so treat it as -ENOENT.
+		 *
+		 * Other maps (e.g. sock_map) do not provide this guarantee and
+		 * the sk may never be in the reuseport group to begin with.
 		 */
-		return -ENOENT;
+		return is_sockarray ? -ENOENT : -EINVAL;
+	}
 
 	if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) {
 		struct sock *sk;