public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@elte.hu>
To: Andy Lutomirski <luto@MIT.EDU>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
	John Stultz <johnstul@us.ibm.com>,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 4/6] x86-64: vclock_gettime(CLOCK_MONOTONIC) can't ever see nsec < 0
Date: Tue, 29 Mar 2011 08:21:12 +0200	[thread overview]
Message-ID: <20110329062112.GC27398@elte.hu> (raw)
In-Reply-To: <75824c7636ab74a71598080867c927d313c8ab66.1301324270.git.luto@mit.edu>


* Andy Lutomirski <luto@MIT.EDU> wrote:

> vclock_gettime's do_monotonic helper can't ever generate a negative
> nsec value, so it doesn't need to check whether it's negative.  This
> saves a single easily-predicted branch.
> 
> Signed-off-by: Andy Lutomirski <luto@mit.edu>
> ---
>  arch/x86/vdso/vclock_gettime.c |   40 ++++++++++++++++++++++------------------
>  1 files changed, 22 insertions(+), 18 deletions(-)
> 
> diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
> index ee55754..67d54bb 100644
> --- a/arch/x86/vdso/vclock_gettime.c
> +++ b/arch/x86/vdso/vclock_gettime.c
> @@ -56,22 +56,6 @@ notrace static noinline int do_realtime(struct timespec *ts)
>  	return 0;
>  }
>  
> -/* Copy of the version in kernel/time.c which we cannot directly access */
> -notrace static void
> -vset_normalized_timespec(struct timespec *ts, long sec, long nsec)
> -{
> -	while (nsec >= NSEC_PER_SEC) {
> -		nsec -= NSEC_PER_SEC;
> -		++sec;
> -	}
> -	while (nsec < 0) {
> -		nsec += NSEC_PER_SEC;
> -		--sec;
> -	}
> -	ts->tv_sec = sec;
> -	ts->tv_nsec = nsec;
> -}
> -
>  notrace static noinline int do_monotonic(struct timespec *ts)
>  {
>  	unsigned long seq, ns, secs;
> @@ -82,7 +66,17 @@ notrace static noinline int do_monotonic(struct timespec *ts)
>  		secs += gtod->wall_to_monotonic.tv_sec;
>  		ns += gtod->wall_to_monotonic.tv_nsec;
>  	} while (unlikely(read_seqretry(&gtod->lock, seq)));
> -	vset_normalized_timespec(ts, secs, ns);
> +
> +	/* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec
> +	 * are all guaranteed to be nonnegative.
> +	 */
> +	while (ns >= NSEC_PER_SEC) {
> +		ns -= NSEC_PER_SEC;
> +		++secs;
> +	}
> +	ts->tv_sec = secs;
> +	ts->tv_nsec = ns;
> +
>  	return 0;
>  }
>  
> @@ -107,7 +101,17 @@ notrace static noinline int do_monotonic_coarse(struct timespec *ts)
>  		secs += gtod->wall_to_monotonic.tv_sec;
>  		ns += gtod->wall_to_monotonic.tv_nsec;
>  	} while (unlikely(read_seqretry(&gtod->lock, seq)));
> -	vset_normalized_timespec(ts, secs, ns);
> +
> +	/* wall_time_nsec and wall_to_monotonic.tv_nsec are
> +	 * guaranteed to be between 0 and NSEC_PER_SEC.
> +	 */
> +	if (ns >= NSEC_PER_SEC) {
> +		ns -= NSEC_PER_SEC;
> +		++secs;
> +	}
> +	ts->tv_sec = secs;
> +	ts->tv_nsec = ns;
> +
>  	return 0;

Beyond the change you describe in the changelog, you also uninlined the helper 
function.

You can use __always_inline instead and still keep the code maintainable.

Thanks,

	Ingo

  reply	other threads:[~2011-03-29  6:21 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-28 15:06 [PATCH 0/6] x86-64: Micro-optimize vclock_gettime Andy Lutomirski
2011-03-28 15:06 ` [PATCH 1/6] x86-64: Optimize vread_tsc's barriers Andy Lutomirski
2011-03-29  6:18   ` Ingo Molnar
2011-03-28 15:06 ` [PATCH 2/6] x86-64: Don't generate cmov in vread_tsc Andy Lutomirski
2011-03-29  6:15   ` Ingo Molnar
2011-03-29 11:52     ` Andrew Lutomirski
2011-03-28 15:06 ` [PATCH 3/6] x86-64: Put vsyscall_gtod_data at a fixed virtual address Andy Lutomirski
2011-03-28 17:49   ` Thomas Gleixner
2011-03-28 18:09     ` Andrew Lutomirski
2011-03-28 21:35     ` Andrew Lutomirski
2011-03-28 23:13       ` Thomas Gleixner
2011-03-28 15:06 ` [PATCH 4/6] x86-64: vclock_gettime(CLOCK_MONOTONIC) can't ever see nsec < 0 Andy Lutomirski
2011-03-29  6:21   ` Ingo Molnar [this message]
2011-03-29 11:54     ` Andrew Lutomirski
2011-03-28 15:06 ` [PATCH 5/6] x86-64: Omit frame pointers on vread_tsc Andy Lutomirski
2011-03-29  6:24   ` Ingo Molnar
2011-03-28 15:06 ` [PATCH 6/6] x86-64: Turn off -pg and turn on -foptimize-sibling-calls for vDSO Andy Lutomirski
2011-03-29  6:27 ` [PATCH 0/6] x86-64: Micro-optimize vclock_gettime Ingo Molnar
2011-04-06 18:20 ` Andi Kleen
2011-04-06 20:10   ` Andrew Lutomirski
2011-04-06 20:14     ` Andi Kleen
2011-04-06 20:49       ` Andrew Lutomirski

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=20110329062112.GC27398@elte.hu \
    --to=mingo@elte.hu \
    --cc=johnstul@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@MIT.EDU \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /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