linux/net/ipv4/udp_bpf.c
Jakub Sitnicki 54ea2f49fd bpf, sockmap, udp: sk_prot needs inuse_idx set for proc stats
The proc socket stats use sk_prot->inuse_idx value to record inuse sock
stats. We currently do not set this correctly from sockmap side. The
result is reading sock stats '/proc/net/sockstat' gives incorrect values.
The socket counter is incremented correctly, but because we don't set the
counter correctly when we replace sk_prot we may omit the decrement.

To get the correct inuse_idx value move the core_initcall that initializes
the UDP proto handlers to late_initcall. This way it is initialized after
UDP has the chance to assign the inuse_idx value from the register protocol
handler.

Fixes: edc6741cc6 ("bpf: Add sockmap hooks for UDP sockets")
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210714154750.528206-1-jakub@cloudflare.com
2021-07-15 19:54:36 +02:00

156 lines
3.7 KiB
C

// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2020 Cloudflare Ltd https://cloudflare.com */
#include <linux/skmsg.h>
#include <net/sock.h>
#include <net/udp.h>
#include <net/inet_common.h>
#include "udp_impl.h"
static struct proto *udpv6_prot_saved __read_mostly;
static int sk_udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int noblock, int flags, int *addr_len)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
return udpv6_prot_saved->recvmsg(sk, msg, len, noblock, flags,
addr_len);
#endif
return udp_prot.recvmsg(sk, msg, len, noblock, flags, addr_len);
}
static bool udp_sk_has_data(struct sock *sk)
{
return !skb_queue_empty(&udp_sk(sk)->reader_queue) ||
!skb_queue_empty(&sk->sk_receive_queue);
}
static bool psock_has_data(struct sk_psock *psock)
{
return !skb_queue_empty(&psock->ingress_skb) ||
!sk_psock_queue_empty(psock);
}
#define udp_msg_has_data(__sk, __psock) \
({ udp_sk_has_data(__sk) || psock_has_data(__psock); })
static int udp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
long timeo)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
int ret = 0;
if (sk->sk_shutdown & RCV_SHUTDOWN)
return 1;
if (!timeo)
return ret;
add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
ret = udp_msg_has_data(sk, psock);
if (!ret) {
wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
ret = udp_msg_has_data(sk, psock);
}
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
return ret;
}
static int udp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len)
{
struct sk_psock *psock;
int copied, ret;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len, addr_len);
psock = sk_psock_get(sk);
if (unlikely(!psock))
return sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
if (!psock_has_data(psock)) {
ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
goto out;
}
msg_bytes_ready:
copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
if (!copied) {
long timeo;
int data;
timeo = sock_rcvtimeo(sk, nonblock);
data = udp_msg_wait_data(sk, psock, timeo);
if (data) {
if (psock_has_data(psock))
goto msg_bytes_ready;
ret = sk_udp_recvmsg(sk, msg, len, nonblock, flags, addr_len);
goto out;
}
copied = -EAGAIN;
}
ret = copied;
out:
sk_psock_put(sk, psock);
return ret;
}
enum {
UDP_BPF_IPV4,
UDP_BPF_IPV6,
UDP_BPF_NUM_PROTS,
};
static DEFINE_SPINLOCK(udpv6_prot_lock);
static struct proto udp_bpf_prots[UDP_BPF_NUM_PROTS];
static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
{
*prot = *base;
prot->unhash = sock_map_unhash;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
}
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
{
if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
spin_lock_bh(&udpv6_prot_lock);
if (likely(ops != udpv6_prot_saved)) {
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
smp_store_release(&udpv6_prot_saved, ops);
}
spin_unlock_bh(&udpv6_prot_lock);
}
}
static int __init udp_bpf_v4_build_proto(void)
{
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
return 0;
}
late_initcall(udp_bpf_v4_build_proto);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
if (restore) {
sk->sk_write_space = psock->saved_write_space;
WRITE_ONCE(sk->sk_prot, psock->sk_proto);
return 0;
}
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
return 0;
}
EXPORT_SYMBOL_GPL(udp_bpf_update_proto);