Re: [PATCH 14/32] net/tcp: convert to ->poll_mask

[Eric Dumazet <eric.dumazet@gmail.com>]

On 05/11/2018 04:07 AM, Christoph Hellwig wrote:
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  include/net/tcp.h   |  4 ++--
>  net/ipv4/af_inet.c  |  3 ++-
>  net/ipv4/tcp.c      | 31 ++++++++++++++-----------------
>  net/ipv6/af_inet6.c |  3 ++-
>  4 files changed, 20 insertions(+), 21 deletions(-)
> 
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 9c9b3768b350..d4d72ea9128d 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -388,8 +388,8 @@ bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst);
>  void tcp_close(struct sock *sk, long timeout);
>  void tcp_init_sock(struct sock *sk);
>  void tcp_init_transfer(struct sock *sk, int bpf_op);
> -__poll_t tcp_poll(struct file *file, struct socket *sock,
> -		      struct poll_table_struct *wait);
> +struct wait_queue_head *tcp_get_poll_head(struct socket *sock, __poll_t events);
> +__poll_t tcp_poll_mask(struct socket *sock, __poll_t events);
>  int tcp_getsockopt(struct sock *sk, int level, int optname,
>  		   char __user *optval, int __user *optlen);
>  int tcp_setsockopt(struct sock *sk, int level, int optname,
> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> index eaed0367e669..220b51347526 100644
> --- a/net/ipv4/af_inet.c
> +++ b/net/ipv4/af_inet.c
> @@ -986,7 +986,8 @@ const struct proto_ops inet_stream_ops = {
>  	.socketpair	   = sock_no_socketpair,
>  	.accept		   = inet_accept,
>  	.getname	   = inet_getname,
> -	.poll		   = tcp_poll,
> +	.get_poll_head	   = tcp_get_poll_head,
> +	.poll_mask	   = tcp_poll_mask,
>  	.ioctl		   = inet_ioctl,
>  	.listen		   = inet_listen,
>  	.shutdown	   = inet_shutdown,
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 9ce1c726185e..6ec0e7a13581 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -493,33 +493,30 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
>  		sk->sk_prot->stream_memory_read(sk) : false);
>  }
>  
> +struct wait_queue_head *tcp_get_poll_head(struct socket *sock, __poll_t events)
> +{
> +	sock_poll_busy_loop(sock, events);
> +	sock_rps_record_flow(sock->sk);

Why are you adding sock_rps_record_flow() ?



> +	return sk_sleep(sock->sk);
> +}
> +EXPORT_SYMBOL(tcp_get_poll_head);
> +
>  /*
> - *	Wait for a TCP event.
> - *
> - *	Note that we don't need to lock the socket, as the upper poll layers
> - *	take care of normal races (between the test and the event) and we don't
> - *	go look at any of the socket buffers directly.
> + * Socket is not locked. We are protected from async events by poll logic and
> + * correct handling of state changes made by other threads is impossible in
> + * any case.
>   */
> -__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
> +__poll_t tcp_poll_mask(struct socket *sock, __poll_t events)
>  {
> -	__poll_t mask;
>  	struct sock *sk = sock->sk;
>  	const struct tcp_sock *tp = tcp_sk(sk);
> +	__poll_t mask = 0;
>  	int state;
>  
> -	sock_poll_wait(file, sk_sleep(sk), wait);
> -
>  	state = inet_sk_state_load(sk);
>  	if (state == TCP_LISTEN)
>  		return inet_csk_listen_poll(sk);
>  
> -	/* Socket is not locked. We are protected from async events
> -	 * by poll logic and correct handling of state changes
> -	 * made by other threads is impossible in any case.
> -	 */
> -
> -	mask = 0;
> -
>  	/*
>  	 * EPOLLHUP is certainly not done right. But poll() doesn't
>  	 * have a notion of HUP in just one direction, and for a
> @@ -600,7 +597,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
>  
>  	return mask;
>  }
> -EXPORT_SYMBOL(tcp_poll);
> +EXPORT_SYMBOL(tcp_poll_mask);
>  
>  int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
>  {
> diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
> index 8da0b513f188..a43d967eeca5 100644
> --- a/net/ipv6/af_inet6.c
> +++ b/net/ipv6/af_inet6.c
> @@ -571,7 +571,8 @@ const struct proto_ops inet6_stream_ops = {
>  	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
>  	.accept		   = inet_accept,		/* ok		*/
>  	.getname	   = inet6_getname,
> -	.poll		   = tcp_poll,			/* ok		*/
> +	.get_poll_head	   = tcp_get_poll_head,
> +	.poll_mask	   = tcp_poll_mask,		/* ok		*/
>  	.ioctl		   = inet6_ioctl,		/* must change  */
>  	.listen		   = inet_listen,		/* ok		*/
>  	.shutdown	   = inet_shutdown,		/* ok		*/
>