From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Linus Torvalds <torvalds@osdl.org>, Ingo Molnar <mingo@elte.hu>,
Alok Kataria <akataria@vmware.com>,
Arjan van de Veen <arjan@infradead.org>
Subject: [RFC patch 1/4] x86: TSC: define the PIT latch value separate
Date: Thu, 04 Sep 2008 15:18:44 -0000 [thread overview]
Message-ID: <20080904151249.615344193@linutronix.de> (raw)
In-Reply-To: <20080904150339.896115280@linutronix.de>
[-- Attachment #1: tsc-define-latch-value.patch --]
[-- Type: text/plain, Size: 1592 bytes --]
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
arch/x86/kernel/tsc.c | 14 +++++++++-----
1 file changed, 9 insertions(+), 5 deletions(-)
Index: linux-2.6/arch/x86/kernel/tsc.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/tsc.c
+++ linux-2.6/arch/x86/kernel/tsc.c
@@ -122,6 +122,10 @@ static u64 tsc_read_refs(u64 *pm, u64 *h
return ULLONG_MAX;
}
+#define CAL_MS 50
+#define CAL_LATCH (CLOCK_TICK_RATE / (1000 / CAL_MS))
+#define CAL_PIT_LOOPS 5000
+
/*
* Try to calibrate the TSC against the Programmable
* Interrupt Timer and return the frequency of the TSC
@@ -144,8 +148,8 @@ static unsigned long pit_calibrate_tsc(v
* (LSB then MSB) to begin countdown.
*/
outb(0xb0, 0x43);
- outb((CLOCK_TICK_RATE / (1000 / 50)) & 0xff, 0x42);
- outb((CLOCK_TICK_RATE / (1000 / 50)) >> 8, 0x42);
+ outb(CAL_LATCH & 0xff, 0x42);
+ outb(CAL_LATCH >> 8, 0x42);
tsc = t1 = t2 = get_cycles();
@@ -166,18 +170,18 @@ static unsigned long pit_calibrate_tsc(v
/*
* Sanity checks:
*
- * If we were not able to read the PIT more than 5000
+ * If we were not able to read the PIT more than PIT_MIN_LOOPS
* times, then we have been hit by a massive SMI
*
* If the maximum is 10 times larger than the minimum,
* then we got hit by an SMI as well.
*/
- if (pitcnt < 5000 || tscmax > 10 * tscmin)
+ if (pitcnt < CAL_PIT_LOOPS || tscmax > 10 * tscmin)
return ULONG_MAX;
/* Calculate the PIT value */
delta = t2 - t1;
- do_div(delta, 50);
+ do_div(delta, CAL_MS);
return delta;
}
--
next prev parent reply other threads:[~2008-09-04 15:19 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-09-04 15:18 [RFC patch 0/4] TSC calibration improvements Thomas Gleixner
2008-09-04 15:18 ` Thomas Gleixner [this message]
2008-09-04 15:18 ` [RFC patch 2/4] x86: TSC: separate hpet/pmtimer calculation out Thomas Gleixner
2008-09-04 15:18 ` [RFC patch 3/4] x86: TSC: use one set of reference variables Thomas Gleixner
2008-09-04 15:18 ` [RFC patch 4/4] x86: TSC make the calibration loop smarter Thomas Gleixner
2008-09-04 15:36 ` [RFC patch 0/4] TSC calibration improvements Ingo Molnar
2008-09-04 15:45 ` Linus Torvalds
2008-09-04 16:00 ` Ingo Molnar
2008-09-04 16:21 ` Linus Torvalds
2008-09-04 16:36 ` Ingo Molnar
2008-09-04 17:41 ` Linus Torvalds
2008-09-04 18:07 ` Alan Cox
2008-09-04 18:26 ` Linus Torvalds
2008-09-04 18:30 ` H. Peter Anvin
2008-09-04 20:09 ` Linus Torvalds
2008-09-04 20:43 ` Ingo Molnar
2008-09-04 20:52 ` Ingo Molnar
2008-09-04 21:09 ` Linus Torvalds
2008-09-04 21:21 ` Ingo Molnar
2008-09-04 21:30 ` Linus Torvalds
2008-09-04 21:34 ` Linus Torvalds
2008-09-04 21:39 ` Ingo Molnar
2008-09-04 21:33 ` Ingo Molnar
2008-09-05 22:18 ` Alok Kataria
2008-09-05 22:34 ` Linus Torvalds
2008-09-06 20:03 ` Thomas Gleixner
2008-09-06 20:29 ` Linus Torvalds
2008-09-06 20:37 ` Thomas Gleixner
2008-09-06 20:50 ` Linus Torvalds
2008-09-06 20:55 ` Linus Torvalds
2008-09-06 21:15 ` Thomas Gleixner
2008-09-06 21:22 ` Linus Torvalds
2008-09-06 21:30 ` Thomas Gleixner
2008-09-06 22:40 ` Ingo Molnar
2008-09-06 20:58 ` Thomas Gleixner
2008-09-06 21:10 ` Linus Torvalds
2008-09-07 6:01 ` Willy Tarreau
2008-09-06 20:52 ` Thomas Gleixner
2008-09-06 20:59 ` Linus Torvalds
2008-09-06 21:07 ` Thomas Gleixner
2008-09-06 21:15 ` Linus Torvalds
2008-09-06 21:26 ` Thomas Gleixner
2008-09-06 21:32 ` Linus Torvalds
2008-09-04 20:53 ` Linus Torvalds
2008-09-04 21:38 ` Alok Kataria
2008-09-04 21:52 ` Linus Torvalds
2008-09-04 22:09 ` Alok Kataria
2008-09-04 17:39 ` Alok Kataria
2008-09-04 17:53 ` Linus Torvalds
2008-09-04 18:31 ` Alok Kataria
2008-09-04 18:34 ` H. Peter Anvin
2008-09-04 21:00 ` Valdis.Kletnieks
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=20080904151249.615344193@linutronix.de \
--to=tglx@linutronix.de \
--cc=akataria@vmware.com \
--cc=arjan@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=torvalds@osdl.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
all inboxes | Powered by JetHome®