Files
linux/net/ipv4/udp_bpf.c
Eric Dumazet 8341c989ac net: remove addr_len argument of recvmsg() handlers
Use msg->msg_namelen as a place holder instead of a
temporary variable, notably in inet[6]_recvmsg().

This removes stack canaries and allows tail-calls.

$ scripts/bloat-o-meter -t vmlinux.old vmlinux
add/remove: 0/0 grow/shrink: 2/19 up/down: 26/-532 (-506)
Function                                     old     new   delta
rawv6_recvmsg                                744     767     +23
vsock_dgram_recvmsg                           55      58      +3
vsock_connectible_recvmsg                     50      47      -3
unix_stream_recvmsg                          161     158      -3
unix_seqpacket_recvmsg                        62      59      -3
unix_dgram_recvmsg                            42      39      -3
tcp_recvmsg                                  546     543      -3
mptcp_recvmsg                               1568    1565      -3
ping_recvmsg                                 806     800      -6
tcp_bpf_recvmsg_parser                       983     974      -9
ip_recv_error                                588     576     -12
ipv6_recv_rxpmtu                             442     428     -14
udp_recvmsg                                 1243    1224     -19
ipv6_recv_error                             1046    1024     -22
udpv6_recvmsg                               1487    1461     -26
raw_recvmsg                                  465     437     -28
udp_bpf_recvmsg                             1027     984     -43
sock_common_recvmsg                          103      27     -76
inet_recvmsg                                 257     175     -82
inet6_recvmsg                                257     175     -82
tcp_bpf_recvmsg                              663     568     -95
Total: Before=25143834, After=25143328, chg -0.00%

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20260227151120.1346573-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2026-03-02 18:17:17 -08:00

173 lines
4.0 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 <asm/ioctls.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 flags)
{
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family == AF_INET6)
return udpv6_prot_saved->recvmsg(sk, msg, len, flags);
#endif
return udp_prot.recvmsg(sk, msg, len, flags);
}
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 flags)
{
struct sk_psock *psock;
int copied, ret;
if (unlikely(flags & MSG_ERRQUEUE))
return inet_recv_error(sk, msg, len);
if (!len)
return 0;
psock = sk_psock_get(sk);
if (unlikely(!psock))
return sk_udp_recvmsg(sk, msg, len, flags);
if (!psock_has_data(psock)) {
ret = sk_udp_recvmsg(sk, msg, len, flags);
goto out;
}
msg_bytes_ready:
copied = sk_msg_recvmsg(sk, psock, msg, len, flags);
if (!copied) {
long timeo;
int data;
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
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, flags);
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 int udp_bpf_ioctl(struct sock *sk, int cmd, int *karg)
{
if (cmd != SIOCINQ)
return udp_ioctl(sk, cmd, karg);
/* Since we don't hold a lock, sk_receive_queue may contain data.
* BPF might only be processing this data at the moment. We only
* care about the data in the ingress_msg here.
*/
*karg = sk_msg_first_len(sk);
return 0;
}
static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
{
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
prot->sock_is_readable = sk_msg_is_readable;
prot->ioctl = udp_bpf_ioctl;
}
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;
sock_replace_proto(sk, psock->sk_proto);
return 0;
}
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
sock_replace_proto(sk, &udp_bpf_prots[family]);
return 0;
}
EXPORT_SYMBOL_GPL(udp_bpf_update_proto);