mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Soheil Hassas Yeganeh <soheil@google.com>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: linux-fsdevel@vger.kernel.org,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Al Viro <viro@zeniv.linux.org.uk>, Arnd Bergmann <arnd@arndb.de>,
	Willem de Bruijn <willemb@google.com>
Subject: Re: [PATCH] epoll: add nsec timeout support
Date: Mon, 26 Oct 2020 12:13:39 -0400	[thread overview]
Message-ID: <CACSApvYv1OWLExUcFu0j9VuWS6uMMb2r0B3FqPEsapy9EK9kfg@mail.gmail.com> (raw)
In-Reply-To: <20201026160810.2503534-1-willemdebruijn.kernel@gmail.com>

On Mon, Oct 26, 2020 at 12:08 PM Willem de Bruijn
<willemdebruijn.kernel@gmail.com> wrote:
>
> From: Willem de Bruijn <willemb@google.com>
>
> The underlying hrtimer is programmed with nanosecond resolution.
>
> Use cases such as datacenter networking operate on timescales well
> below milliseconds. Setting shorter timeouts bounds tail latency.
>
> Add epoll_create1 flag EPOLL_NSTIMEO. When passed, this changes the
> interpretation of argument timeout in epoll_wait from msec to nsec.
>
> The new eventpoll state fits in existing 4B of padding when busy poll
> is compiled in (the default), and reads the same cacheline.
>
> Signed-off-by: Willem de Bruijn <willemb@google.com>

Acked-by: Soheil Hassas Yeganeh <soheil@google.com>

Thanks for adding the feature!

> ---
>
> Selftest for now at github. Can follow-up for kselftests.
> https://github.com/wdebruij/kerneltools/blob/master/tests/epoll_nstimeo.c
> ---
>  fs/eventpoll.c                 | 26 +++++++++++++++++++-------
>  include/uapi/linux/eventpoll.h |  1 +
>  2 files changed, 20 insertions(+), 7 deletions(-)
>
> diff --git a/fs/eventpoll.c b/fs/eventpoll.c
> index 4df61129566d..1216b909d155 100644
> --- a/fs/eventpoll.c
> +++ b/fs/eventpoll.c
> @@ -225,6 +225,9 @@ struct eventpoll {
>         unsigned int napi_id;
>  #endif
>
> +       /* Accept timeout in ns resolution (EPOLL_NSTIMEO) */
> +       unsigned int nstimeout:1;
> +
>  #ifdef CONFIG_DEBUG_LOCK_ALLOC
>         /* tracks wakeup nests for lockdep validation */
>         u8 nests;
> @@ -1787,17 +1790,20 @@ static int ep_send_events(struct eventpoll *ep,
>         return esed.res;
>  }
>
> -static inline struct timespec64 ep_set_mstimeout(long ms)
> +static inline struct timespec64 ep_set_nstimeout(long ns)
>  {
> -       struct timespec64 now, ts = {
> -               .tv_sec = ms / MSEC_PER_SEC,
> -               .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
> -       };
> +       struct timespec64 now, ts;
>
> +       ts = ns_to_timespec64(ns);
>         ktime_get_ts64(&now);
>         return timespec64_add_safe(now, ts);
>  }
>
> +static inline struct timespec64 ep_set_mstimeout(long ms)
> +{
> +       return ep_set_nstimeout(NSEC_PER_MSEC * ms);
> +}
> +
>  /**
>   * ep_poll - Retrieves ready events, and delivers them to the caller supplied
>   *           event buffer.
> @@ -1826,7 +1832,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
>         lockdep_assert_irqs_enabled();
>
>         if (timeout > 0) {
> -               struct timespec64 end_time = ep_set_mstimeout(timeout);
> +               struct timespec64 end_time;
> +
> +               end_time = ep->nstimeout ? ep_set_nstimeout(timeout) :
> +                                          ep_set_mstimeout(timeout);
>
>                 slack = select_estimate_accuracy(&end_time);
>                 to = &expires;
> @@ -2046,7 +2055,7 @@ static int do_epoll_create(int flags)
>         /* Check the EPOLL_* constant for consistency.  */
>         BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
>
> -       if (flags & ~EPOLL_CLOEXEC)
> +       if (flags & ~(EPOLL_CLOEXEC | EPOLL_NSTIMEO))
>                 return -EINVAL;
>         /*
>          * Create the internal data structure ("struct eventpoll").
> @@ -2054,6 +2063,9 @@ static int do_epoll_create(int flags)
>         error = ep_alloc(&ep);
>         if (error < 0)
>                 return error;
> +
> +       ep->nstimeout = !!(flags & EPOLL_NSTIMEO);
> +
>         /*
>          * Creates all the items needed to setup an eventpoll file. That is,
>          * a file structure and a free file descriptor.
> diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
> index 8a3432d0f0dc..f6ef9c9f8ac2 100644
> --- a/include/uapi/linux/eventpoll.h
> +++ b/include/uapi/linux/eventpoll.h
> @@ -21,6 +21,7 @@
>
>  /* Flags for epoll_create1.  */
>  #define EPOLL_CLOEXEC O_CLOEXEC
> +#define EPOLL_NSTIMEO 0x1
>
>  /* Valid opcodes to issue to sys_epoll_ctl() */
>  #define EPOLL_CTL_ADD 1
> --
> 2.29.0.rc1.297.gfa9743e501-goog
>

      reply	other threads:[~2020-10-26 16:14 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-26 16:08 Willem de Bruijn
2020-10-26 16:13 ` Soheil Hassas Yeganeh [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CACSApvYv1OWLExUcFu0j9VuWS6uMMb2r0B3FqPEsapy9EK9kfg@mail.gmail.com \
    --to=soheil@google.com \
    --cc=arnd@arndb.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willemb@google.com \
    --cc=willemdebruijn.kernel@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®