On Thursday, 22 March 2007 00:53, Rafael J. Wysocki wrote:
> On Thursday, 22 March 2007 00:39, Maxim wrote:
> > On Thursday 22 March 2007 01:24:25 Rafael J. Wysocki wrote:
> > > On Thursday, 22 March 2007 00:09, Maxim wrote:
> > > > On Thursday 22 March 2007 00:39:02 you wrote:
> > > > > On Wednesday, 21 March 2007 23:21, Pavel Machek wrote:
> > > > > > Hi!
> > > > > >
> > > > > > > Starting with 2.6.21-rc1 suspend to ram and disk doesn't work
> > > > > > > anymore on my system.
> > > > > > >
> > > > > > > I did a git-bisect and found that those commits break it:
> > > > > > >
> > > > > > > e3c7db621bed4afb8e231cb005057f2feb5db557 - [PATCH] [PATCH] PM:
> > > > > > > Change code ordering in main.c
> > > > > > > ed746e3b18f4df18afa3763155972c5835f284c5 - [PATCH] [PATCH]
> > > > > > > swsusp: Change code ordering in disk.c
> > > > > > > 259130526c267550bc365d3015917d90667732f1 - [PATCH] [PATCH]
> > > > > > > swsusp: Change code ordering in user.c
> > > > > > >
> > > > > >
> > > > > > (Yep, it was in my "to analyze" queue).
> > > > > >
> > > > > > > I already reported about it, but now i know the reason why
> > > > > > > suspend breaks.
> > > > > > >
> > > > > > > The problem is that both cpu_up/cpu_down were allowed to sleep
> > > > > > > until now,
> > > > > > > and it did work because those functions could be called only in
> > > > > > > process context
> > > > > > > (the one that writes to /sys/devices/system/cpu/cpu*/online) or
> > > > > > > idle thread that does smp_init()).
> > > > > > >
> > > > > > > But now they are called _after_ all tasks were suspended, so if
> > > > > > > cpu_down tries for example to take a lock
> > > > > > > that is taken by different process, it can't since the different
> > > > > > > proccess is frozen and can't release the lock.
> > > > > > >
> > > > > >
> > > > > > Thanks for detailed explanation.
> > > > > >
> > > > > > ...but, on my machine suspend works ok in -rc4. I'm not seeing this.
> > > > > >
> > > > > > ...by design, "frozen" tasks must not hold any locks. If frozen task
> > > > > > holds a lock, that's a bug.
> > > > > >
> > > > > > > Or, it is also possible to revert this change.
> > > > > >
> > > > > > Are you using xfs?
> > > > >
> > > > > Well, this is the only case that can trigger it. There are no other
> > > > > freezable
> > > > > workqueues.
> > > > >
> > > > > Greetings,
> > > > > Rafael
> > > > >
> > > >
> > > > Hello,
> > > >
> > > > Yes, you are right and it is XFS
> > > >
> > > > System suspends and resumes with xfs and your patch correctly,
> > >
> > > Could you please sent this information to the list? I'd like it to reach
> > > all
> > > of the CCed parites. ;-)
> >
> > I did now ( sorry I just keep using this Answer command, instead of Answer
> > to everybody)
> > I didn't intend to send private email.
> > >
> > > > Of course I need to mention that I had to unload microcode
> > > > update driver because it prevented resume,
> > > > because it calls firmware loader helper, and again sleeps on
> > > > lock
> > >
> > > This is interesting. Did it happen before or is it a regression?
> >
> > It is from the same group of bugs , I mean hang because cpu_up/down is
> > called with frozen tasks
> > Of course it didn't happen before those reordering commits were introduced
>
> Well, we want cpu_up/down to be called after processes have been frozen, for
> various reasons (one of them being that applications shouldn't see us playing
> with the CPUs).
>
> Thanks for reporting this, I'll have a look at the microcode update driver.
Well, I have invented the appended workaround, but I'm not sure how much
sense it makes with respect to the microcode driver. At least, it doesn't
break my AMD64 SMP setup. ;-)
Greetings,
Rafael
---
arch/i386/kernel/microcode.c | 23 +++++++++++++++++++++--
include/linux/cpu.h | 2 ++
kernel/cpu.c | 20 +++++++++++++++-----
3 files changed, 38 insertions(+), 7 deletions(-)
Index: linux-2.6.21-rc4/arch/i386/kernel/microcode.c
===================================================================
--- linux-2.6.21-rc4.orig/arch/i386/kernel/microcode.c 2007-03-16
21:51:23.000000000 +0100
+++ linux-2.6.21-rc4/arch/i386/kernel/microcode.c 2007-03-22
23:55:40.000000000 +0100
@@ -703,6 +703,16 @@ static struct sysdev_driver mc_sysdev_dr
.resume = mc_sysdev_resume,
};
+static __cpuinit void apply_microcode_on_cpu(int cpu)
+{
+ cpumask_t old;
+
+ old = current->cpus_allowed;
+ set_cpus_allowed(current, cpumask_of_cpu(cpu));
+ apply_microcode(cpu);
+ set_cpus_allowed(current, old);
+}
+
static __cpuinit int
mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
{
@@ -713,10 +723,19 @@ mc_cpu_callback(struct notifier_block *n
switch (action) {
case CPU_ONLINE:
case CPU_DOWN_FAILED:
- mc_sysdev_add(sys_dev);
+ if (suspend_cpu_hotplug)
+ /* This means we have been called during the resume.
+ * This is not the real CPU hotplug and we don't need
+ * to register the sysdev
+ */
+ apply_microcode_on_cpu(cpu);
+ else
+ mc_sysdev_add(sys_dev);
break;
case CPU_DOWN_PREPARE:
- mc_sysdev_remove(sys_dev);
+ /* During the suspend there is no need to remove the sysdev */
+ if (!suspend_cpu_hotplug)
+ mc_sysdev_remove(sys_dev);
break;
}
return NOTIFY_OK;
Index: linux-2.6.21-rc4/include/linux/cpu.h
===================================================================
--- linux-2.6.21-rc4.orig/include/linux/cpu.h 2007-03-16 21:51:34.000000000
+0100
+++ linux-2.6.21-rc4/include/linux/cpu.h 2007-03-22 23:55:54.000000000
+0100
@@ -127,6 +127,8 @@ static inline int cpu_is_offline(int cpu
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_SUSPEND_SMP
+extern int suspend_cpu_hotplug;
+
extern int disable_nonboot_cpus(void);
extern void enable_nonboot_cpus(void);
#else
Index: linux-2.6.21-rc4/kernel/cpu.c
===================================================================
--- linux-2.6.21-rc4.orig/kernel/cpu.c 2007-03-16 21:51:35.000000000 +0100
+++ linux-2.6.21-rc4/kernel/cpu.c 2007-03-23 00:05:41.000000000 +0100
@@ -254,6 +254,12 @@ int __cpuinit cpu_up(unsigned int cpu)
}
#ifdef CONFIG_SUSPEND_SMP
+/* Needed to prevent the microcode driver from playing with sysfs in its CPU
+ * hotplug notifier.
+ */
+int suspend_cpu_hotplug;
+EXPORT_SYMBOL(suspend_cpu_hotplug);
+
static cpumask_t frozen_cpus;
int disable_nonboot_cpus(void)
@@ -261,6 +267,7 @@ int disable_nonboot_cpus(void)
int cpu, first_cpu, error = 0;
mutex_lock(&cpu_add_remove_lock);
+ suspend_cpu_hotplug = 1;
first_cpu = first_cpu(cpu_present_map);
if (!cpu_online(first_cpu)) {
error = _cpu_up(first_cpu);
@@ -297,6 +304,7 @@ int disable_nonboot_cpus(void)
printk(KERN_ERR "Non-boot CPUs are not disabled\n");
}
out:
+ suspend_cpu_hotplug = 0;
mutex_unlock(&cpu_add_remove_lock);
return error;
}
@@ -308,20 +316,22 @@ void enable_nonboot_cpus(void)
/* Allow everyone to use the CPU hotplug again */
mutex_lock(&cpu_add_remove_lock);
cpu_hotplug_disabled = 0;
- mutex_unlock(&cpu_add_remove_lock);
if (cpus_empty(frozen_cpus))
- return;
+ goto out;
+ suspend_cpu_hotplug = 1;
printk("Enabling non-boot CPUs ...\n");
for_each_cpu_mask(cpu, frozen_cpus) {
- error = cpu_up(cpu);
+ error = _cpu_up(cpu);
if (!error) {
printk("CPU%d is up\n", cpu);
continue;
}
- printk(KERN_WARNING "Error taking CPU%d up: %d\n",
- cpu, error);
+ printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
}
cpus_clear(frozen_cpus);
+ suspend_cpu_hotplug = 0;
+out:
+ mutex_unlock(&cpu_add_remove_lock);
}
#endif
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
