diff mbox series

[bpf-next,v6,06/12] bpf, sockmap: Don't set up sockmap progs for listening sockets

Message ID 20200127131057.150941-7-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 
Now that sockmap can hold listening sockets, when setting up the psock we
will (i) grab references to verdict/parser progs, and (2) override socket
upcalls sk_data_ready and sk_write_space.

We cannot redirect to listening sockets so we don't need to link the socket
to the BPF progs, but more importantly we don't want the listening socket
to have overridden upcalls because they would get inherited by child
sockets cloned from it.

Introduce a separate initialization path for listening sockets that does
not change the upcalls and ignores the BPF progs.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
---
 net/core/sock_map.c | 45 ++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 38 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 954c4d23bc01..cadae12bb3d4 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -228,6 +228,30 @@  static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 	return ret;
 }
 
+static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk)
+{
+	struct sk_psock *psock;
+	int ret;
+
+	psock = sk_psock_get_checked(sk);
+	if (IS_ERR(psock))
+		return PTR_ERR(psock);
+
+	if (psock) {
+		tcp_bpf_reinit(sk);
+		return 0;
+	}
+
+	psock = sk_psock_init(sk, map->numa_node);
+	if (!psock)
+		return -ENOMEM;
+
+	ret = tcp_bpf_init(sk);
+	if (ret < 0)
+		sk_psock_put(sk, psock);
+	return ret;
+}
+
 static void sock_map_free(struct bpf_map *map)
 {
 	struct bpf_stab *stab = container_of(map, struct bpf_stab, map);
@@ -333,6 +357,12 @@  static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next)
 	return 0;
 }
 
+/* Is sock in a state that allows redirecting from/into it? */
+static bool sock_map_redirect_okay(const struct sock *sk)
+{
+	return sk->sk_state != TCP_LISTEN;
+}
+
 static int sock_map_update_common(struct bpf_map *map, u32 idx,
 				  struct sock *sk, u64 flags)
 {
@@ -355,7 +385,14 @@  static int sock_map_update_common(struct bpf_map *map, u32 idx,
 	if (!link)
 		return -ENOMEM;
 
-	ret = sock_map_link(map, &stab->progs, sk);
+	/* Only sockets we can redirect into/from in BPF need to hold
+	 * refs to parser/verdict progs and have their sk_data_ready
+	 * and sk_write_space callbacks overridden.
+	 */
+	if (sock_map_redirect_okay(sk))
+		ret = sock_map_link(map, &stab->progs, sk);
+	else
+		ret = sock_map_link_no_progs(map, sk);
 	if (ret < 0)
 		goto out_free;
 
@@ -422,12 +459,6 @@  static bool sock_hash_sk_is_suitable(const struct sock *sk)
 				      TCPF_SYN_RECV);
 }
 
-/* Is sock in a state that allows redirecting into it? */
-static bool sock_map_redirect_okay(const struct sock *sk)
-{
-	return sk->sk_state != TCP_LISTEN;
-}
-
 static int sock_map_update_elem(struct bpf_map *map, void *key,
 				void *value, u64 flags)
 {