From: Kasper Pedersen <kernel@kasperkp.dk>
To: linux-kernel@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
x86@kernel.org, John Stultz <johnstul@us.ibm.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Suresh Siddha <suresh.b.siddha@intel.com>,
Kasper Pedersen <kernel@kasperkp.dk>
Subject: x86: tsc: make TSC calibration more immune to interrupts
Date: Wed, 20 Apr 2011 20:52:07 +0200 [thread overview]
Message-ID: <4DAF2B57.6010100@kasperkp.dk> (raw)
When a SMI or plain interrupt occurs during the delayed part
of TSC calibration, and the SMI/irq handler is good and fast
so that is does not exceed SMI_TRESHOLD, tsc_khz can be a bit
off (10-30ppm).
We should not depend on interrupts being longer than 50000
clocks, so always do the 5 tries, and use the best sample we
get.
This should work always for any four periodic or rate-limited
interrupt sources. If we get 5 interrupts with 500ns gaps in
a row, behaviour should be as without this patch.
This costs us 20-100 microseconds in startup time, as
tsc_read_refs is called 8 times.
measurements:
On a 700MHz P3 I see t2-t1=~22000, and 31ppm error.
A Core2 is similar: http://n1.taur.dk/tscdeviat.png
(while mostly t2-t1=~1000, in about 1 of 3000 tests
I see t2-t1=~20000 for both machines.)
vmware ESX4 has t2-t1=~8000 and up.
Signed-off-by: Kasper Pedersen <kernel@kasperkp.dk>
---
arch/x86/kernel/tsc.c | 24 +++++++++++++++++-------
1 files changed, 17 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ffe5755..e916f99 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -117,7 +117,7 @@ static int __init tsc_setup(char *str)
__setup("tsc=", tsc_setup);
-#define MAX_RETRIES 5
+#define BESTOF_SAMPLES 5
#define SMI_TRESHOLD 50000
/*
@@ -125,19 +125,29 @@ __setup("tsc=", tsc_setup);
*/
static u64 tsc_read_refs(u64 *p, int hpet)
{
- u64 t1, t2;
+ u64 t1, t2, tp, best_uncertainty, uncertainty, best_t2;
int i;
- for (i = 0; i < MAX_RETRIES; i++) {
+ best_uncertainty = SMI_TRESHOLD;
+ best_t2 = 0;
+ for (i = 0; i < BESTOF_SAMPLES; i++) {
t1 = get_cycles();
if (hpet)
- *p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
+ tp = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF;
else
- *p = acpi_pm_read_early();
+ tp = acpi_pm_read_early();
t2 = get_cycles();
- if ((t2 - t1) < SMI_TRESHOLD)
- return t2;
+ uncertainty = t2 - t1;
+ if (uncertainty < best_uncertainty) {
+ best_uncertainty = uncertainty;
+ best_t2 = t2;
+ *p = tp;
+ }
}
+ if (best_uncertainty < SMI_TRESHOLD)
+ return best_t2;
+
+ *p = tp;
return ULLONG_MAX;
}
next reply other threads:[~2011-04-20 19:41 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-20 18:52 Kasper Pedersen [this message]
2011-04-20 19:15 ` x86: tsc: make TSC calibration more immune to interrupts john stultz
2011-04-20 19:44 ` Kasper Pedersen
2011-04-20 20:28 ` john stultz
2011-04-20 21:22 ` x86: tsc: v2 " Kasper Pedersen
2011-04-20 22:39 ` Josh Triplett
2011-04-21 2:19 ` john stultz
2011-04-21 4:32 ` Josh Triplett
2011-04-21 19:46 ` Kasper Pedersen
2011-04-23 1:38 ` john stultz
2011-04-21 19:52 ` x86: tsc: v3 " Kasper Pedersen
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=4DAF2B57.6010100@kasperkp.dk \
--to=kernel@kasperkp.dk \
--cc=a.p.zijlstra@chello.nl \
--cc=hpa@zytor.com \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=suresh.b.siddha@intel.com \
--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