From: Shaohua Li <shaohua.li@intel.com>
To: Miles Lane <miles.lane@gmail.com>
Cc: Andrew Morton <akpm@osdl.org>,
Jeremy Fitzhardinge <jeremy@goop.org>,
linux-kernel@vger.kernel.org, dzickus@redhat.com, ak@suse.de
Subject: Re: [2.6.17-rc5-mm2] crash when doing second suspend: BUG in arch/i386/kernel/nmi.c:174
Date: Tue, 06 Jun 2006 14:44:06 +0800 [thread overview]
Message-ID: <1149576246.32046.166.camel@sli10-desk.sh.intel.com> (raw)
In-Reply-To: <a44ae5cd0606050135w66c2abeu698394b4268e4790@mail.gmail.com>
On Mon, 2006-06-05 at 16:35 +0800, Miles Lane wrote:
> On 6/5/06, Andrew Morton <akpm@osdl.org> wrote:
>
> > Do you think the suspend breakage is related to that patch?
> >
> > Miles also reports that every second suspend fails for him. Miles,
> does
> > 'nmi_watchdog=0' make it better?
>
> I tried using that as an appended boot option, but it didn't change
> the
> behavior.
Does below patch help? The nmi suspend/resume doesn't look good to me.
Only CPU0 uses the suspend/resume code path. Other CPUs run the CPU
hotplug code path.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
---
linux-2.6.17-rc5-mm3-root/arch/i386/kernel/nmi.c | 14 +++++++++-----
linux-2.6.17-rc5-mm3-root/arch/i386/kernel/smpboot.c | 3 ++-
linux-2.6.17-rc5-mm3-root/arch/x86_64/kernel/nmi.c | 14 +++++++++-----
linux-2.6.17-rc5-mm3-root/arch/x86_64/kernel/smpboot.c | 2 ++
linux-2.6.17-rc5-mm3-root/include/asm-i386/nmi.h | 1 +
linux-2.6.17-rc5-mm3-root/include/asm-x86_64/nmi.h | 1 +
6 files changed, 24 insertions(+), 11 deletions(-)
diff -puN arch/i386/kernel/nmi.c~nmi arch/i386/kernel/nmi.c
--- linux-2.6.17-rc5-mm3/arch/i386/kernel/nmi.c~nmi 2006-06-04 15:22:06.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/arch/i386/kernel/nmi.c 2006-06-05 12:28:17.000000000 +0800
@@ -65,7 +65,6 @@ struct nmi_watchdog_ctlblk {
static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
/* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
extern void show_registers(struct pt_regs *regs);
@@ -377,15 +376,20 @@ static int nmi_pm_active; /* nmi_active
static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
{
+ /* only CPU0 goes here, other CPUs should be offline */
nmi_pm_active = atomic_read(&nmi_active);
- disable_lapic_nmi_watchdog();
+ stop_apic_nmi_watchdog(NULL);
+ BUG_ON(atomic_read(&nmi_active) != 0);
return 0;
}
static int lapic_nmi_resume(struct sys_device *dev)
{
- if (nmi_pm_active > 0)
- enable_lapic_nmi_watchdog();
+ /* only CPU0 goes here, other CPUs should be offline */
+ if (nmi_pm_active > 0) {
+ setup_apic_nmi_watchdog(NULL);
+ touch_nmi_watchdog();
+ }
return 0;
}
@@ -798,7 +802,7 @@ void setup_apic_nmi_watchdog (void *unus
atomic_inc(&nmi_active);
}
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
{
/* only support LOCAL and IO APICs for now */
if ((nmi_watchdog != NMI_LOCAL_APIC) &&
diff -puN arch/i386/kernel/smpboot.c~nmi arch/i386/kernel/smpboot.c
--- linux-2.6.17-rc5-mm3/arch/i386/kernel/smpboot.c~nmi 2006-06-04 15:26:47.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/arch/i386/kernel/smpboot.c 2006-06-05 08:51:16.000000000 +0800
@@ -1368,7 +1368,8 @@ int __cpu_disable(void)
*/
if (cpu == 0)
return -EBUSY;
-
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ stop_apic_nmi_watchdog(NULL);
clear_local_APIC();
/* Allow any queued timer interrupts to get serviced */
local_irq_enable();
diff -puN include/asm-i386/nmi.h~nmi include/asm-i386/nmi.h
--- linux-2.6.17-rc5-mm3/include/asm-i386/nmi.h~nmi 2006-06-05 08:50:23.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/include/asm-i386/nmi.h 2006-06-05 08:50:33.000000000 +0800
@@ -23,6 +23,7 @@ extern int reserve_evntsel_nmi(unsigned
extern void release_evntsel_nmi(unsigned int);
extern void setup_apic_nmi_watchdog (void *);
+extern void stop_apic_nmi_watchdog (void *);
extern void disable_timer_nmi_watchdog(void);
extern void enable_timer_nmi_watchdog(void);
extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
diff -puN arch/x86_64/kernel/nmi.c~nmi arch/x86_64/kernel/nmi.c
--- linux-2.6.17-rc5-mm3/arch/x86_64/kernel/nmi.c~nmi 2006-06-05 12:24:03.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/arch/x86_64/kernel/nmi.c 2006-06-05 12:26:00.000000000 +0800
@@ -65,7 +65,6 @@ struct nmi_watchdog_ctlblk {
static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
/* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
/* converts an msr to an appropriate reservation bit */
@@ -363,15 +362,20 @@ static int nmi_pm_active; /* nmi_active
static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
{
+ /* only CPU0 goes here, other CPUs should be offline */
nmi_pm_active = atomic_read(&nmi_active);
- disable_lapic_nmi_watchdog();
+ stop_apic_nmi_watchdog(NULL);
+ BUG_ON(atomic_read(&nmi_active) != 0);
return 0;
}
static int lapic_nmi_resume(struct sys_device *dev)
{
- if (nmi_pm_active > 0)
- enable_lapic_nmi_watchdog();
+ /* only CPU0 goes here, other CPUs should be offline */
+ if (nmi_pm_active > 0) {
+ setup_apic_nmi_watchdog(NULL);
+ touch_nmi_watchdog();
+ }
return 0;
}
@@ -709,7 +713,7 @@ void setup_apic_nmi_watchdog(void *unuse
atomic_inc(&nmi_active);
}
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
{
/* only support LOCAL and IO APICs for now */
if ((nmi_watchdog != NMI_LOCAL_APIC) &&
diff -puN include/asm-x86_64/nmi.h~nmi include/asm-x86_64/nmi.h
--- linux-2.6.17-rc5-mm3/include/asm-x86_64/nmi.h~nmi 2006-06-05 12:34:27.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/include/asm-x86_64/nmi.h 2006-06-05 12:34:41.000000000 +0800
@@ -54,6 +54,7 @@ extern int reserve_evntsel_nmi(unsigned
extern void release_evntsel_nmi(unsigned int);
extern void setup_apic_nmi_watchdog (void *);
+extern void stop_apic_nmi_watchdog (void *);
extern void disable_timer_nmi_watchdog(void);
extern void enable_timer_nmi_watchdog(void);
extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
diff -puN arch/x86_64/kernel/smpboot.c~nmi arch/x86_64/kernel/smpboot.c
--- linux-2.6.17-rc5-mm3/arch/x86_64/kernel/smpboot.c~nmi 2006-06-05 12:34:56.000000000 +0800
+++ linux-2.6.17-rc5-mm3-root/arch/x86_64/kernel/smpboot.c 2006-06-05 12:45:58.000000000 +0800
@@ -1232,6 +1232,8 @@ int __cpu_disable(void)
if (cpu == 0)
return -EBUSY;
+ if (nmi_watchdog == NMI_LOCAL_APIC)
+ stop_apic_nmi_watchdog(NULL);
clear_local_APIC();
/*
_
next prev parent reply other threads:[~2006-06-06 7:05 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-06-02 22:51 Jeremy Fitzhardinge
2006-06-04 11:47 ` Rafael J. Wysocki
2006-06-05 7:21 ` Jeremy Fitzhardinge
2006-06-05 7:37 ` Jeremy Fitzhardinge
2006-06-05 7:48 ` Andrew Morton
2006-06-05 7:59 ` Jeremy Fitzhardinge
2006-06-05 8:35 ` Miles Lane
2006-06-06 6:44 ` Shaohua Li [this message]
2006-06-06 14:17 ` Don Zickus
2006-06-06 14:18 ` Andi Kleen
2006-06-06 21:45 ` Don Zickus
2006-06-06 22:15 ` Andrew Morton
2006-06-06 23:05 ` Don Zickus
2006-06-06 23:22 ` Andrew Morton
2006-06-06 23:27 ` Jeremy Fitzhardinge
2006-06-06 23:32 ` Andi Kleen
2006-06-06 23:42 ` Don Zickus
2006-06-08 20:11 ` Pavel Machek
2006-06-06 23:38 ` Nigel Cunningham
2006-06-07 0:06 ` Jeremy Fitzhardinge
2006-06-07 0:13 ` Nigel Cunningham
2006-06-07 0:24 ` Andrew Morton
2006-06-07 0:29 ` Jeremy Fitzhardinge
2006-06-07 0:31 ` Nigel Cunningham
2006-06-07 0:33 ` Andi Kleen
2006-06-07 0:40 ` Nigel Cunningham
2006-06-07 0:26 ` Jeremy Fitzhardinge
2006-06-07 0:33 ` Nigel Cunningham
2006-06-07 0:56 ` Jeremy Fitzhardinge
2006-06-08 20:13 ` Pavel Machek
2006-06-08 12:45 ` Pavel Machek
2006-06-06 23:34 ` Andi Kleen
2006-06-06 23:55 ` Don Zickus
2006-06-07 0:04 ` Andi Kleen
2006-06-07 0:05 ` Nigel Cunningham
2006-06-07 0:42 ` Don Zickus
2006-06-07 0:50 ` Nigel Cunningham
2006-06-07 3:29 ` [linux-pm] " David Brownell
2006-06-07 9:55 ` Rafael J. Wysocki
2006-06-08 20:27 ` Pavel Machek
2006-06-06 16:23 ` Jeremy Fitzhardinge
2006-06-06 16:51 ` Don Zickus
2006-06-07 2:49 ` Don Zickus
2006-06-07 16:33 ` Andi Kleen
2006-06-07 17:07 ` Jeremy Fitzhardinge
2006-06-07 17:50 ` Don Zickus
2006-06-07 18:53 ` Jeremy Fitzhardinge
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=1149576246.32046.166.camel@sli10-desk.sh.intel.com \
--to=shaohua.li@intel.com \
--cc=ak@suse.de \
--cc=akpm@osdl.org \
--cc=dzickus@redhat.com \
--cc=jeremy@goop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miles.lane@gmail.com \
/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®