From: Thomas Gleixner <tglx@linutronix.de>
To: Felipe Balbi <felipe.balbi@linux.intel.com>
Cc: Richard Cochran <richardcochran@gmail.com>,
netdev@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>, "H . Peter Anvin" <hpa@zytor.com>,
x86@kernel.org, linux-kernel@vger.kernel.org,
"Christopher S . Hall" <christopher.s.hall@intel.com>
Subject: Re: [RFC PATCH 1/5] x86: tsc: add tsc to art helpers
Date: Thu, 17 Oct 2019 13:15:15 +0200 (CEST) [thread overview]
Message-ID: <alpine.DEB.2.21.1910171256580.1824@nanos.tec.linutronix.de> (raw)
In-Reply-To: <87y2y4vk4g.fsf@gmail.com>
Hi,
On Tue, 1 Oct 2019, Felipe Balbi wrote:
> (sorry for the long delay, got caught up in other tasks)
Delayed by vacation :)
> Thomas Gleixner <tglx@linutronix.de> writes:
> > On Thu, 15 Aug 2019, Felipe Balbi wrote:
> >> Thomas Gleixner <tglx@linutronix.de> writes:
> >> > On Tue, 16 Jul 2019, Felipe Balbi wrote:
> >> >
> >> > So some information what those interfaces are used for and why they are
> >> > needed would be really helpful.
> >>
> >> Okay, I have some more details about this. The TGPIO device itself uses
> >> ART since TSC is not directly available to anything other than the
> >> CPU. The 'problem' here is that reading ART incurs extra latency which
> >> we would like to avoid. Therefore, we use TSC and scale it to
> >> nanoseconds which, would be the same as ART to ns.
> >
> > Fine. But that's not really correct:
> >
> > TSC = art_to_tsc_offset + ART * scale;
>
> From silicon folks I got the equation:
>
> ART = ECX * EBX / EAX;
What is the content of ECX/EBX/EAX and where is it coming from?
> If I'm reading this correctly, that's basically what
> native_calibrate_tsc() does (together with some error checking the safe
> defaults). Couldn't we, instead, just have a single function like below?
>
> u64 convert_tsc_to_art_ns()
> {
> return x86_platform.calibrate_tsc();
> }
Huch? How is that supposed to work? calibrate_tsc() returns the TSC
frequency.
> Another way would be extract the important parts from
> native_calibrate_tsc() into a separate helper. This would safe another
> call to cpuid(0x15,...);
What for?
The relation between TSC and ART is already established via detect_art()
which reads all relevant data out of CPUID(ART_CPUID_LEAF).
We use exactly that information for convert_art_to_tsc() so the obvious
solution for calculating ART from TSC is to do the reverse operation.
convert_art_to_tsc()
{
rem = do_div(art, art_to_tsc_denominator);
res = art * art_to_tsc_numerator;
tmp = rem * art_to_tsc_numerator;
do_div(tmp, art_to_tsc_denominator);
res += tmp + art_to_tsc_offset;
}
which is translated into math:
TSC = ART * SCALE + OFFSET
where
SCALE = N / D
and
N = CPUID(ART_CPUID_LEAF).EAX
D = CPUID(ART_CPUID_LEAF).EBX
So the obvious reverse operation is:
ART = (TSC - OFFSET) / SCALE;
Translating that into code should not be rocket science.
Thanks,
tglx
next prev parent reply other threads:[~2019-10-17 11:15 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-16 7:20 [RFC PATCH 0/5] PTP: add support for Intel's TGPIO controller Felipe Balbi
2019-07-16 7:20 ` [RFC PATCH 1/5] x86: tsc: add tsc to art helpers Felipe Balbi
2019-07-16 7:57 ` Thomas Gleixner
2019-08-15 5:57 ` Felipe Balbi
2019-08-15 14:16 ` Thomas Gleixner
2019-10-01 10:24 ` Felipe Balbi
2019-10-17 11:15 ` Thomas Gleixner [this message]
2019-10-17 12:01 ` Felipe Balbi
2019-07-16 7:20 ` [RFC PATCH 2/5] PTP: add a callback for counting timestamp events Felipe Balbi
2019-07-16 7:20 ` [RFC PATCH 3/5] PTP: implement PTP_EVENT_COUNT_TSTAMP ioctl Felipe Balbi
2019-07-16 7:20 ` [RFC PATCH 4/5] PTP: Add flag for non-periodic output Felipe Balbi
2019-07-16 16:39 ` Richard Cochran
2019-07-17 6:49 ` Felipe Balbi
2019-07-17 17:36 ` Richard Cochran
2019-07-18 8:59 ` Felipe Balbi
2019-07-18 16:41 ` Richard Cochran
2019-08-13 7:53 ` Felipe Balbi
2019-08-13 17:48 ` Richard Cochran
2019-08-13 18:06 ` Richard Cochran
2019-08-14 7:05 ` Felipe Balbi
2019-07-16 7:20 ` [RFC PATCH 5/5] PTP: Add support for Intel PMC Timed GPIO Controller Felipe Balbi
2019-07-16 19:14 ` Shannon Nelson
2019-07-17 6:51 ` Felipe Balbi
2019-07-16 16:41 ` [RFC PATCH 0/5] PTP: add support for Intel's TGPIO controller Richard Cochran
2019-07-17 6:52 ` Felipe Balbi
2019-07-17 17:39 ` Richard Cochran
2019-07-18 8:58 ` Felipe Balbi
2019-07-18 19:50 ` Andrew Lunn
2019-07-19 7:35 ` Felipe Balbi
2019-07-19 13:20 ` Andrew Lunn
2019-08-13 7:50 ` Felipe Balbi
2019-08-13 17:49 ` Richard Cochran
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=alpine.DEB.2.21.1910171256580.1824@nanos.tec.linutronix.de \
--to=tglx@linutronix.de \
--cc=bp@alien8.de \
--cc=christopher.s.hall@intel.com \
--cc=felipe.balbi@linux.intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=richardcochran@gmail.com \
--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;
as well as URLs for NNTP newsgroup(s).