Commit 7ae215d2 authored by Joe Stringer's avatar Joe Stringer Committed by Alexei Starovoitov
Browse files

bpf: Don't refcount LISTEN sockets in sk_assign() 



Avoid taking a reference on listen sockets by checking the socket type
in the sk_assign and in the corresponding skb_steal_sock() code in the
the transport layer, and by ensuring that the prefetch free (sock_pfree)
function uses the same logic to check whether the socket is refcounted.

Suggested-by: default avatarMartin KaFai Lau <kafai@fb.com>
Signed-off-by: default avatarJoe Stringer <joe@wand.net.nz>
Signed-off-by: default avatarAlexei Starovoitov <ast@kernel.org>
Acked-by: default avatarMartin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200329225342.16317-4-joe@wand.net.nz
parent 71489e21

include/net/sock.h

+17 −8
Original line number Diff line number Diff line
@@ -2537,6 +2537,21 @@ skb_sk_is_prefetched(struct sk_buff *skb) 
#endif /* CONFIG_INET */

}



/* This helper checks if a socket is a full socket,

 * ie _not_ a timewait or request socket.

 */

static inline bool sk_fullsock(const struct sock *sk)

{

	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);

}



static inline bool

sk_is_refcounted(struct sock *sk)

{

	/* Only full sockets have sk->sk_flags. */

	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);

}



/**

 * skb_steal_sock

 * @skb to steal the socket from
@@ -2549,6 +2564,8 @@ skb_steal_sock(struct sk_buff *skb, bool *refcounted) 
		struct sock *sk = skb->sk;



		*refcounted = true;

		if (skb_sk_is_prefetched(skb))

			*refcounted = sk_is_refcounted(sk);

		skb->destructor = NULL;

		skb->sk = NULL;

		return sk;
@@ -2557,14 +2574,6 @@ skb_steal_sock(struct sk_buff *skb, bool *refcounted) 
	return NULL;

}



/* This helper checks if a socket is a full socket,

 * ie _not_ a timewait or request socket.

 */

static inline bool sk_fullsock(const struct sock *sk)

{

	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);

}



/* Checks if this SKB belongs to an HW offloaded socket

 * and whether any SW fallbacks are required based on dev.

 * Check decrypted mark in case skb_orphan() cleared socket.

net/core/filter.c

+3 −3
Original line number Diff line number Diff line
@@ -5401,8 +5401,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { 


BPF_CALL_1(bpf_sk_release, struct sock *, sk)

{

	/* Only full sockets have sk->sk_flags. */

	if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))

	if (sk_is_refcounted(sk))

		sock_gen_put(sk);

	return 0;

}
@@ -5928,7 +5927,8 @@ BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) 
		return -ENETUNREACH;

	if (unlikely(sk->sk_reuseport))

		return -ESOCKTNOSUPPORT;

	if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))

	if (sk_is_refcounted(sk) &&

	    unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))

		return -ENOENT;



	skb_orphan(skb);

net/core/sock.c

+2 −1
Original line number Diff line number Diff line
@@ -2077,6 +2077,7 @@ EXPORT_SYMBOL(sock_efree); 
#ifdef CONFIG_INET

void sock_pfree(struct sk_buff *skb)

{

	if (sk_is_refcounted(skb->sk))

		sock_gen_put(skb->sk);

}

EXPORT_SYMBOL(sock_pfree);

CRA Git | Maintained and supported by SUSTech CRA and CCSE