skmsg: Teach sk_psock_verdict_apply() to return errors

Currently sk_psock_verdict_apply() is void, but it handles some
error conditions too. Its caller is impossible to learn whether
it succeeds or fails, especially sk_psock_verdict_recv().

Make it return int to indicate error cases and propagate errors
to callers properly.

Fixes: ef5659280eb1 ("bpf, sockmap: Allow skipping sk_skb parser program")
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20210615021342.7416-7-xiyou.wangcong@gmail.com

diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 5464477..e3d2108 100644 (file)
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -824,7 +824,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
 
-static void sk_psock_skb_redirect(struct sk_buff *skb)
+static int sk_psock_skb_redirect(struct sk_buff *skb)
 {
        struct sk_psock *psock_other;
        struct sock *sk_other;
@@ -835,7 +835,7 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
         */
        if (unlikely(!sk_other)) {
                kfree_skb(skb);
-               return;
+               return -EIO;
        }
        psock_other = sk_psock(sk_other);
        /* This error indicates the socket is being torn down or had another
@@ -845,19 +845,20 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
        if (!psock_other || sock_flag(sk_other, SOCK_DEAD)) {
                skb_bpf_redirect_clear(skb);
                kfree_skb(skb);
-               return;
+               return -EIO;
        }
        spin_lock_bh(&psock_other->ingress_lock);
        if (!sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
                spin_unlock_bh(&psock_other->ingress_lock);
                skb_bpf_redirect_clear(skb);
                kfree_skb(skb);
-               return;
+               return -EIO;
        }
 
        skb_queue_tail(&psock_other->ingress_skb, skb);
        schedule_work(&psock_other->work);
        spin_unlock_bh(&psock_other->ingress_lock);
+       return 0;
 }
 
 static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
@@ -894,14 +895,15 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
 
-static void sk_psock_verdict_apply(struct sk_psock *psock,
-                                  struct sk_buff *skb, int verdict)
+static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
+                                 int verdict)
 {
        struct sock *sk_other;
-       int err = -EIO;
+       int err = 0;
 
        switch (verdict) {
        case __SK_PASS:
+               err = -EIO;
                sk_other = psock->sk;
                if (sock_flag(sk_other, SOCK_DEAD) ||
                    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
@@ -934,13 +936,15 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
                }
                break;
        case __SK_REDIRECT:
-               sk_psock_skb_redirect(skb);
+               err = sk_psock_skb_redirect(skb);
                break;
        case __SK_DROP:
        default:
 out_free:
                kfree_skb(skb);
        }
+
+       return err;
 }
 
 static void sk_psock_write_space(struct sock *sk)
@@ -1107,7 +1111,8 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
                ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb));
                skb->sk = NULL;
        }
-       sk_psock_verdict_apply(psock, skb, ret);
+       if (sk_psock_verdict_apply(psock, skb, ret) < 0)
+               len = 0;
 out:
        rcu_read_unlock();
        return len;