Re: [PATCH v6 1/2] bpf, sockmap: handle spurious tcp_msg_wait_data() wakeup

[Nnamdi Onyeyiri <nnamdio@gmail.com>]

On Mon, Jul 20, 2026 at 05:16:08PM -0400, Emil Tsalapatis wrote:
> On Mon Jul 20, 2026 at 1:15 PM EDT, Nnamdi Onyeyiri wrote:
> > recvfrom()/recv() are documented as only returning EAGAIN for blocking sockets
> > when they have a receive timeout configured.  However, adding a blocking
> > ipv4 tcp socket without a receive timeout to a sockmap will cause EAGAIN errors
> > sporadically.  A socket with a receive timeout may return EAGAIN before the
> > timeout expires.
> >
> > There are 2 code paths affected by this:
> >
> >   1. tcp_bpf_recvmsg() - Used when the socket has been added to a sockmap
> >      that has no verdict program attached.
> >
> >   2. tcp_bpf_recvmsg_parser() - Used when the socket has been added to a
> >      sockmap that has a verdict program.  To reproduce this issue, it is
> >      enough for the verdict program to do nothing but return SK_PASS.
> >
> > In both cases this happens when tcp_msg_wait_data() wakes spuriously
> > (returning 0).  To fix it, we now loop back to msg_bytes_ready instead
> > of returning -EAGAIN on spurious wakeup.
> >
> > To ensure the looping does not cause sockets with a SO_RCVTIMEO set to
> > wait excessively long, tcp_msg_wait_data() now takes a pointer to timeo,
> > allowing sk_wait_event() to update it as appropriate.
> >
> > The logic in tcp_bpf_recvmsg_parser() that allow it to handle signals,
> > socket errors and closuers in its loop was also added to tcp_bpf_recvmsg().
> >
> > Signed-off-by: Nnamdi Onyeyiri <nnamdio@gmail.com>
> > ---
> >  net/ipv4/tcp_bpf.c | 69 ++++++++++++++++++++++++++++++++++++++++------
> >  1 file changed, 60 insertions(+), 9 deletions(-)
> >
> > diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
> > index cc0bd73f36b6..aa5c5d741599 100644
> > --- a/net/ipv4/tcp_bpf.c
> > +++ b/net/ipv4/tcp_bpf.c
> > @@ -179,7 +179,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
> >  
> >  #ifdef CONFIG_BPF_SYSCALL
> >  static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
> > -			     long timeo)
> > +			     long *timeo)
> >  {
> >  	DEFINE_WAIT_FUNC(wait, woken_wake_function);
> >  	int ret = 0;
> > @@ -187,12 +187,12 @@ static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
> >  	if (sk->sk_shutdown & RCV_SHUTDOWN)
> >  		return 1;
> >  
> > -	if (!timeo)
> > +	if (!*timeo)
> >  		return ret;
> >  
> >  	add_wait_queue(sk_sleep(sk), &wait);
> >  	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
> > -	ret = sk_wait_event(sk, &timeo,
> > +	ret = sk_wait_event(sk, timeo,
> >  			    !list_empty(&psock->ingress_msg) ||
> >  			    !skb_queue_empty_lockless(&sk->sk_receive_queue), &wait);
> >  	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
> > @@ -229,6 +229,7 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
> >  	int copied_from_self = 0;
> >  	int copied = 0;
> >  	u32 seq;
> > +	long timeo;
> >  
> >  	if (unlikely(flags & MSG_ERRQUEUE))
> >  		return inet_recv_error(sk, msg, len);
> > @@ -262,6 +263,8 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
> >  		}
> >  	}
> >  
> > +	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
> > +
> >  msg_bytes_ready:
> >  	copied = __sk_msg_recvmsg(sk, psock, msg, len, flags, &copied_from_self);
> >  	/* The typical case for EFAULT is the socket was gracefully
> > @@ -280,7 +283,6 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
> >  	}
> >  	seq += copied_from_self;
> >  	if (!copied) {
> > -		long timeo;
> >  		int data;
> >  
> >  		if (sock_flag(sk, SOCK_DONE))
> > @@ -299,7 +301,6 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
> >  			goto out;
> >  		}
> >  
> > -		timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
> >  		if (!timeo) {
> >  			copied = -EAGAIN;
> >  			goto out;
> > @@ -310,13 +311,15 @@ static int tcp_bpf_recvmsg_parser(struct sock *sk,
> >  			goto out;
> >  		}
> >  
> > -		data = tcp_msg_wait_data(sk, psock, timeo);
> > +		data = tcp_msg_wait_data(sk, psock, &timeo);
> >  		if (data < 0) {
> >  			copied = data;
> >  			goto unlock;
> >  		}
> >  		if (data && !sk_psock_queue_empty(psock))
> >  			goto msg_bytes_ready;
> > +		if (!data && timeo > 0)
> > +			goto msg_bytes_ready;
> >  		copied = -EAGAIN;
> >  	}
> >  out:
> > @@ -355,6 +358,7 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
> >  {
> >  	struct sk_psock *psock;
> >  	int copied, ret;
> > +	long timeo;
> >  
> >  	if (unlikely(flags & MSG_ERRQUEUE))
> >  		return inet_recv_error(sk, msg, len);
> > @@ -371,14 +375,59 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
> >  		return tcp_recvmsg(sk, msg, len, flags);
> >  	}
> >  	lock_sock(sk);
> > +
> > +	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
> > +
> >  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 = tcp_msg_wait_data(sk, psock, timeo);
> > +		if (sock_flag(sk, SOCK_DONE)) {
> > +			ret = 0;
> > +			goto unlock;
> > +		}
> > +
> > +		if (sk->sk_err) {
> > +			if (!sk_psock_queue_empty(psock))
> > +				goto msg_bytes_ready;
> > +			if (!skb_queue_empty(&sk->sk_receive_queue)) {
> > +				release_sock(sk);
> > +				sk_psock_put(sk, psock);
> > +				return tcp_recvmsg(sk, msg, len, flags);
> > +			}
> > +			ret = sock_error(sk);
> > +			goto unlock;
> > +		}
> > +
> > +		if (sk->sk_shutdown & RCV_SHUTDOWN) {
> > +			if (!sk_psock_queue_empty(psock))
> > +				goto msg_bytes_ready;
> > +			if (!skb_queue_empty(&sk->sk_receive_queue)) {
> > +				release_sock(sk);
> > +				sk_psock_put(sk, psock);
> > +				return tcp_recvmsg(sk, msg, len, flags);
> > +			}
> > +			ret = 0;
> > +			goto unlock;
> 
> These two error handling routines above look identical. Can you refactor
> them?
>

Will do.  My understanding is the same logic is needed to address the
issue Sashiko raised with the SOCK_DONE check as well.

> > +		}
> > +
> > +		if (sk->sk_state == TCP_CLOSE) {
> > +			ret = -ENOTCONN;
> > +			goto unlock;
> > +		}
> > +
> > +		if (!timeo) {
> > +			ret = -EAGAIN;
> > +			goto unlock;
> > +		}
> > +
> 
> Since this handling (which Sashiko flags by the way, correctly AFAICT) 
> are taken from tcp_bpf_recvmsg, there is obvious overlap between the two
> functions. Please factor those out so that they share the logic between
> them.
> 
> pw-bot: cr
> 

Sashiko highlighted the "if (!timeo)" and signal_pending early returns
when MSG_DONTWAIT is set, but I think I'm missing part of the picture.
By the time we reach these branches, haven't we already checked for data
in sk_receive_queue (line 372, after the patch is applied to 7.2-rc2)
[copied below for ease of viewing]:

    if (!skb_queue_empty(&sk->sk_receive_queue) &&
        sk_psock_queue_empty(psock)) {
        sk_psock_put(sk, psock);
        return tcp_recvmsg(sk, msg, len, flags);
    }

and in the psock (line 382) [again copied below for viewing]:

    copied = sk_msg_recvmsg(sk, psock, msg, len, flags);

> > +		if (signal_pending(current)) {
> > +			ret = sock_intr_errno(timeo);
> > +			goto unlock;
> > +		}
> > +
> > +		data = tcp_msg_wait_data(sk, psock, &timeo);
> >  		if (data < 0) {
> >  			ret = data;
> >  			goto unlock;
> > @@ -390,6 +439,8 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
> >  			sk_psock_put(sk, psock);
> >  			return tcp_recvmsg(sk, msg, len, flags);
> >  		}
> > +		if (!data && timeo > 0)
> > +			goto msg_bytes_ready;
> >  		copied = -EAGAIN;
> >  	}
> >  	ret = copied;
>