From: Ingo Molnar <mingo@elte.hu>
To: Jiri Slaby <jirislaby@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, "Rafael J. Wysocki" <rjw@sisk.pl>,
Arjan van de Ven <arjan@linux.intel.com>,
Thomas Gleixner <tglx@linutronix.de>,
Linux-pm mailing list <linux-pm@lists.linux-foundation.org>
Subject: Re: broken suspend (sched related) [Was: 2.6.24-rc4-mm1]
Date: Sun, 9 Dec 2007 09:06:19 +0100 [thread overview]
Message-ID: <20071209080619.GA682@elte.hu> (raw)
In-Reply-To: <475AD7D0.8040905@gmail.com>
* Jiri Slaby <jirislaby@gmail.com> wrote:
> On 12/08/2007 04:24 PM, Ingo Molnar wrote:
> > i'm wondering why it had no effect now - the new code is in essence a
> > NOP over what we had.
>
> Maybe a dumb question. Why those changes in process_32.c in the patch
> and not in process_64.c?
not a dumb question at all - i forgot about it. Find the updated patch
below.
( sidenote: this shows the x86 unification concept in action. You
noticed the missing _64.c probably because you saw a _32.c file
modified in the patch and the rule is that if we modify a _32.c file
then the matching _64.c file needs to be updated too. If this had been
an old-style pre-unification arch/i386/kernel/process.c file you'd not
have been able to tell this from just looking at the patch file - and
we'd possibly have missed to include a fix on the 64-bit side. With
the unification of files we are realizing it how many times this
happened in the past (and went unnoticed). )
Ingo
--------------------->
Subject: x86: idle wakeup event in the HLT loop
From: Ingo Molnar <mingo@elte.hu>
do a proper idle-wakeup event on HLT as well - some CPUs stop the TSC
in HLT too, not just when going through the ACPI methods.
(the ACPI idle code already does this.)
[ update the 64-bit side too, as noticed by Jiri Slaby. ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/kernel/process_32.c | 15 ++++++++++++---
arch/x86/kernel/process_64.c | 13 ++++++++++---
2 files changed, 22 insertions(+), 6 deletions(-)
Index: linux-x86.q/arch/x86/kernel/process_32.c
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/process_32.c
+++ linux-x86.q/arch/x86/kernel/process_32.c
@@ -113,10 +113,19 @@ void default_idle(void)
smp_mb();
local_irq_disable();
- if (!need_resched())
+ if (!need_resched()) {
+ ktime_t t0, t1;
+ u64 t0n, t1n;
+
+ t0 = ktime_get();
+ t0n = ktime_to_ns(t0);
safe_halt(); /* enables interrupts racelessly */
- else
- local_irq_enable();
+ local_irq_disable();
+ t1 = ktime_get();
+ t1n = ktime_to_ns(t1);
+ sched_clock_idle_wakeup_event(t1n - t0n);
+ }
+ local_irq_enable();
current_thread_info()->status |= TS_POLLING;
} else {
/* loop is done by the caller */
Index: linux-x86.q/arch/x86/kernel/process_64.c
===================================================================
--- linux-x86.q.orig/arch/x86/kernel/process_64.c
+++ linux-x86.q/arch/x86/kernel/process_64.c
@@ -116,9 +116,16 @@ static void default_idle(void)
smp_mb();
local_irq_disable();
if (!need_resched()) {
- /* Enables interrupts one instruction before HLT.
- x86 special cases this so there is no race. */
- safe_halt();
+ ktime_t t0, t1;
+ u64 t0n, t1n;
+
+ t0 = ktime_get();
+ t0n = ktime_to_ns(t0);
+ safe_halt(); /* enables interrupts racelessly */
+ local_irq_disable();
+ t1 = ktime_get();
+ t1n = ktime_to_ns(t1);
+ sched_clock_idle_wakeup_event(t1n - t0n);
} else
local_irq_enable();
current_thread_info()->status |= TS_POLLING;
next prev parent reply other threads:[~2007-12-09 8:07 UTC|newest]
Thread overview: 112+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-05 5:17 2.6.24-rc4-mm1 Andrew Morton
2007-12-05 9:15 ` 2.6.24-rc4-mm1: kobj changes fallout on powerpc Olof Johansson
2007-12-05 13:11 ` Kamalesh Babulal
2007-12-05 15:46 ` Greg KH
2007-12-05 14:12 ` 2.6.24-rc4-mm1 kobject changes broken with hvcs driver " Kamalesh Babulal
2007-12-05 15:47 ` Greg KH
2007-12-06 18:19 ` Balbir Singh
2007-12-06 18:50 ` Greg KH
2007-12-06 18:49 ` Kamalesh Babulal
2007-12-06 18:58 ` Balbir Singh
2007-12-06 19:21 ` Badari Pulavarty
2007-12-07 1:29 ` Balbir Singh
2007-12-06 20:31 ` Greg KH
2007-12-06 23:54 ` Badari Pulavarty
2007-12-07 0:32 ` Greg KH
2007-12-07 3:02 ` Kamalesh Babulal
2007-12-07 5:14 ` Greg KH
2007-12-07 22:01 ` Balbir Singh
2007-12-05 23:41 ` 2.6.24-rc4-mm1: hostbyte=0x01 driverbyte=0x00 (now bisected) Alexey Dobriyan
2007-12-06 7:52 ` Hannes Reinecke
2007-12-06 12:08 ` Jens Axboe
2007-12-06 19:19 ` Alexey Dobriyan
2007-12-06 3:15 ` 2.6.24-rc4-mm1 Kernel build fails on S390x Kamalesh Babulal
2007-12-06 7:19 ` Andrew Morton
2007-12-06 6:59 ` 2.6.24-rc4-mm1 Reuben Farrelly
2007-12-06 7:09 ` 2.6.24-rc4-mm1 David Miller
2007-12-07 13:16 ` 2.6.24-rc4-mm1 Ilpo Järvinen
2007-12-12 17:57 ` 2.6.24-rc4-mm1 Cedric Le Goater
2007-12-06 7:35 ` 2.6.24-rc4-mm1 Andrew Morton
2007-12-10 12:24 ` 2.6.24-rc4-mm1 Ilpo Järvinen
2007-12-10 20:05 ` 2.6.24-rc4-mm1 Ilpo Järvinen
2007-12-12 19:21 ` 2.6.24-rc4-mm1 Cedric Le Goater
2007-12-13 17:38 ` tcp_sacktag_one() WARNING (was Re: 2.6.24-rc4-mm1) Cedric Le Goater
2007-12-06 11:49 ` 2.6.24-rc4-mm1 Valdis.Kletnieks
2007-12-06 12:04 ` 2.6.24-rc4-mm1 Andrew Morton
2007-12-06 19:18 ` 2.6.24-rc4-mm1 Valdis.Kletnieks
2007-12-06 19:38 ` 2.6.24-rc4-mm1 Greg KH
2007-12-06 20:04 ` 2.6.24-rc4-mm1 Valdis.Kletnieks
2007-12-06 22:04 ` [dm-devel] 2.6.24-rc4-mm1 Kay Sievers
2007-12-06 22:12 ` Alasdair G Kergon
2007-12-06 23:12 ` Valdis.Kletnieks
2007-12-06 23:24 ` Kay Sievers
2007-12-07 18:20 ` Valdis.Kletnieks
2007-12-07 18:44 ` Kay Sievers
2007-12-07 20:28 ` Valdis.Kletnieks
2007-12-07 20:49 ` Kay Sievers
2007-12-06 22:28 ` 2.6.24-rc4-mm1: VDSOSYM build error Laurent Riffard
2007-12-06 22:37 ` Andrew Morton
2007-12-06 23:28 ` Miles Lane
2007-12-06 23:34 ` Andrew Morton
2007-12-06 23:47 ` Miles Lane
2007-12-07 10:36 ` Ingo Molnar
2007-12-07 1:14 ` [PATCH x86/mm] x86 vDSO: canonicalize sysenter .eh_frame Roland McGrath
2007-12-07 1:27 ` Harvey Harrison
2007-12-07 3:27 ` Miles Lane
2007-12-07 9:44 ` Ingo Molnar
2007-12-07 2:12 ` 2.6.24-rc4-mm1 Dave Young
2007-12-07 22:22 ` 2.6.24-rc4-mm1 Luis R. Rodriguez
2007-12-10 1:07 ` 2.6.24-rc4-mm1 Dave Young
2007-12-09 17:55 ` 2.6.24-rc4-mm1 Nick Kossifidis
[not found] ` <E1J0Yfy-0001V7-Rr@localhost>
2007-12-07 8:35 ` [PATCH BUGFIX] hid: the `bit' in hidinput_mapping_quirks() is an out parameter Fengguang Wu
2007-12-10 10:03 ` Jiri Kosina
2007-12-07 14:34 ` broken suspend (sched related) [Was: 2.6.24-rc4-mm1] Jiri Slaby
2007-12-07 15:11 ` Ingo Molnar
2007-12-07 17:51 ` Ingo Molnar
2007-12-08 8:10 ` Jiri Slaby
2007-12-08 8:39 ` Ingo Molnar
2007-12-08 9:23 ` Jiri Slaby
2007-12-08 15:24 ` Ingo Molnar
2007-12-08 17:34 ` Jiri Slaby
2007-12-08 17:43 ` Jiri Slaby
2007-12-09 8:06 ` Ingo Molnar [this message]
2007-12-08 23:12 ` Jiri Slaby
2007-12-09 7:46 ` Ingo Molnar
2007-12-09 9:09 ` Jiri Slaby
2007-12-10 8:19 ` Gautham R Shenoy
2007-12-10 8:55 ` Jiri Slaby
2007-12-10 9:10 ` Ingo Molnar
2007-12-10 10:15 ` Gautham R Shenoy
2007-12-10 10:21 ` Ingo Molnar
2007-12-10 11:08 ` Gautham R Shenoy
2007-12-10 11:28 ` Ingo Molnar
2007-12-10 11:49 ` Gautham R Shenoy
2007-12-10 9:29 ` Ingo Molnar
2007-12-07 18:20 ` [PATCH] md: balance braces in raid5 debug code Mariusz Kozlowski
2007-12-08 0:04 ` 2.6.24-rc4-mm1: undefined reference to `compat_sys_timerfd' on sparc64 Mariusz Kozlowski
2007-12-08 0:08 ` Andrew Morton
2007-12-08 9:17 ` Mariusz Kozlowski
2007-12-11 10:15 ` David Miller
2007-12-08 18:20 ` 2.6.24-rc4-mm1: some issues " Mariusz Kozlowski
2007-12-08 18:22 ` Andrew Morton
2007-12-09 8:45 ` David Miller
2007-12-09 9:03 ` Andrew Morton
2007-12-10 14:48 ` 2.6.24-rc4-mm1 Reuben Farrelly
2007-12-10 21:11 ` 2.6.24-rc4-mm1 Andrew Morton
2007-12-11 14:12 ` 2.6.24-rc4-mm1 Reuben Farrelly
2007-12-11 16:20 ` 2.6.24-rc4-mm1 Martin Bligh
2007-12-11 16:59 ` 2.6.24-rc4-mm1 Randy Dunlap
2007-12-11 17:50 ` 2.6.24-rc4-mm1 Martin Bligh
[not found] ` <33307c790712110813h23def95dvd068b7226e9fcd36@mail.gmail.com>
2007-12-11 20:37 ` 2.6.24-rc4-mm1 Andrew Morton
2007-12-11 21:20 ` 2.6.24-rc4-mm1 Ingo Molnar
2007-12-11 21:26 ` 2.6.24-rc4-mm1 Kok, Auke
2007-12-11 21:59 ` 2.6.24-rc4-mm1 Kok, Auke
2007-12-11 22:10 ` 2.6.24-rc4-mm1 Andrew Morton
2007-12-11 22:17 ` 2.6.24-rc4-mm1 Kok, Auke
2007-12-11 23:15 ` 2.6.24-rc4-mm1 Randy Dunlap
2007-12-12 4:16 ` 2.6.24-rc4-mm1 Rik van Riel
2007-12-13 17:45 ` 2.6.24-rc4-mm1 - BUG in tcp_fragment Cedric Le Goater
2007-12-13 23:00 ` Ilpo Järvinen
2007-12-14 6:52 ` Cedric Le Goater
2007-12-14 20:14 ` [PATCH net-2.6.25] Revert recent TCP work Ilpo Järvinen
2007-12-16 22:21 ` David Miller
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=20071209080619.GA682@elte.hu \
--to=mingo@elte.hu \
--cc=akpm@linux-foundation.org \
--cc=arjan@linux.intel.com \
--cc=jirislaby@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@lists.linux-foundation.org \
--cc=rjw@sisk.pl \
--cc=tglx@linutronix.de \
/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).