netdev - Re: [PATCH net-next 2/2] tcp: factorize logic into tcp_epollin

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CAEA6p_A0g-7WMfyQbw55wdAKkFkEbW2A-XwTNziP9XyD3MjmCA@mail.gmail.com>
Date:   Fri, 12 Feb 2021 16:30:33 -0800
From:   Wei Wang <weiwan@...gle.com>
To:     Eric Dumazet <eric.dumazet@...il.com>
Cc:     "David S . Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>,
        netdev <netdev@...r.kernel.org>,
        Eric Dumazet <edumazet@...gle.com>,
        Arjun Roy <arjunroy@...gle.com>
Subject: Re: [PATCH net-next 2/2] tcp: factorize logic into tcp_epollin_ready()

On Fri, Feb 12, 2021 at 3:22 PM Eric Dumazet <eric.dumazet@...il.com> wrote:
>
> From: Eric Dumazet <edumazet@...gle.com>
>
> Both tcp_data_ready() and tcp_stream_is_readable() share the same logic.
>
> Add tcp_epollin_ready() helper to avoid duplication.
>
> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
> Cc: Arjun Roy <arjunroy@...gle.com>
> Cc: Wei Wang <weiwan@...gle.com>
> ---
>  include/net/tcp.h    | 12 ++++++++++++
>  net/ipv4/tcp.c       | 16 ++++------------
>  net/ipv4/tcp_input.c | 11 ++---------
>  3 files changed, 18 insertions(+), 21 deletions(-)
>
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 244208f6f6c2ace87920b633e469421f557427a6..484eb2362645fd478f59b26b42457ecf4510eb14 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -1442,6 +1442,18 @@ static inline bool tcp_rmem_pressure(const struct sock *sk)
>         return atomic_read(&sk->sk_rmem_alloc) > threshold;
>  }
>
> +static inline bool tcp_epollin_ready(const struct sock *sk, int target)
> +{
> +       const struct tcp_sock *tp = tcp_sk(sk);
> +       int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
> +
> +       if (avail <= 0)
> +               return false;
> +
> +       return (avail >= target) || tcp_rmem_pressure(sk) ||
> +              (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss);
> +}
> +
>  extern void tcp_openreq_init_rwin(struct request_sock *req,
>                                   const struct sock *sk_listener,
>                                   const struct dst_entry *dst);
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 9896ca10bb340924b779cb6a7606d57fdd5c3357..7a6b58ae408d1fb1e5536ccfed8215be123f3b57 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -481,19 +481,11 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
>         }
>  }
>
> -static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
> -                                         int target, struct sock *sk)
> +static bool tcp_stream_is_readable(struct sock *sk, int target)
>  {
> -       int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);
> +       if (tcp_epollin_ready(sk, target))
> +               return true;
>
> -       if (avail > 0) {
> -               if (avail >= target)
> -                       return true;
> -               if (tcp_rmem_pressure(sk))
> -                       return true;
> -               if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)
> -                       return true;
> -       }
>         if (sk->sk_prot->stream_memory_read)
>                 return sk->sk_prot->stream_memory_read(sk);
>         return false;
> @@ -568,7 +560,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
>                     tp->urg_data)
>                         target++;
>
> -               if (tcp_stream_is_readable(tp, target, sk))
> +               if (tcp_stream_is_readable(sk, target))
>                         mask |= EPOLLIN | EPOLLRDNORM;
>
>                 if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> index a8f8f98159531e5d1c80660972148986f6acd20a..e32a7056cb7640c67ef2d6a4d9484684d2602fcd 100644
> --- a/net/ipv4/tcp_input.c
> +++ b/net/ipv4/tcp_input.c
> @@ -4924,15 +4924,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
>
>  void tcp_data_ready(struct sock *sk)
>  {
> -       const struct tcp_sock *tp = tcp_sk(sk);
> -       int avail = tp->rcv_nxt - tp->copied_seq;
> -
> -       if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
> -           !sock_flag(sk, SOCK_DONE) &&

Seems "!sock_flag(sk, SOCK_DONE)" is not checked in
tcp_epollin_read(). Does it matter?

> -           tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)
> -               return;
> -
> -       sk->sk_data_ready(sk);
> +       if (tcp_epollin_ready(sk, sk->sk_rcvlowat))
> +               sk->sk_data_ready(sk);
>  }
>
>  static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
> --
> 2.30.0.478.g8a0d178c01-goog
>