Re: cpu hotplug support broken in 2.6.23-rc3

[Andrew Morton <akpm@linux-foundation.org>]

On Sat, 15 Sep 2007 11:49:41 +0200 Thomas Gleixner <tglx@linutronix.de> wrote:

> On Fri, 2007-09-14 at 15:15 +0200, Thomas Gleixner wrote:
> > > Venki sent me an initial patch, but it has issues with the notify
> > > ordering. Find below my "cache the broadcast flags" version for testing.
> > 
> > Hmmpf, the flag is still cleared when the cpu goes offline. Need to take
> > a closer look.
> 
> I finally tracked it down. There were several ways to turn the box into
> a brick. Sigh !
> 
> Can you please test the combo patch below ?
> 
> The details are available from the for-2.6.23 branch of my hrt git repo:
> 
> http://git.kernel.org/?p=linux/kernel/git/tglx/linux-2.6-hrt.git;a=shortlog;h=for-2.6.23
> 

That patch fixes the resume-from-ram and suspend-to-ram regressions on the
Vaio.

I dropped the timekeeping.c hunks because they are an older version of
timekeeping-prevent-time-going-backwards-on-resume.patch which I already
had.

Is this good to go?  Needs a bit of changelogging.


 drivers/acpi/processor_core.c |   21 +++++++++++++++++++++
 kernel/time/tick-broadcast.c  |   24 ++++++++++++++++--------
 kernel/time/tick-sched.c      |   12 ++++++++++++
 3 files changed, 49 insertions(+), 8 deletions(-)

diff -puN drivers/acpi/processor_core.c~cpu-hotplug-support-broken-in-2623-rc3 drivers/acpi/processor_core.c
--- a/drivers/acpi/processor_core.c~cpu-hotplug-support-broken-in-2623-rc3
+++ a/drivers/acpi/processor_core.c
@@ -724,6 +724,25 @@ static void acpi_processor_notify(acpi_h
 	return;
 }
 
+static int acpi_cpu_soft_notify(struct notifier_block *nfb,
+		unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	struct acpi_processor *pr = processors[cpu];
+
+	if (action == CPU_ONLINE && pr) {
+		acpi_processor_ppc_has_changed(pr);
+		acpi_processor_cst_has_changed(pr);
+		acpi_processor_tstate_has_changed(pr);
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block acpi_cpu_notifier =
+{
+	    .notifier_call = acpi_cpu_soft_notify,
+};
+
 static int acpi_processor_add(struct acpi_device *device)
 {
 	struct acpi_processor *pr = NULL;
@@ -987,6 +1006,7 @@ void acpi_processor_install_hotplug_noti
 			    ACPI_UINT32_MAX,
 			    processor_walk_namespace_cb, &action, NULL);
 #endif
+	register_hotcpu_notifier(&acpi_cpu_notifier);
 }
 
 static
@@ -999,6 +1019,7 @@ void acpi_processor_uninstall_hotplug_no
 			    ACPI_UINT32_MAX,
 			    processor_walk_namespace_cb, &action, NULL);
 #endif
+	unregister_hotcpu_notifier(&acpi_cpu_notifier);
 }
 
 /*
diff -puN kernel/time/tick-broadcast.c~cpu-hotplug-support-broken-in-2623-rc3 kernel/time/tick-broadcast.c
--- a/kernel/time/tick-broadcast.c~cpu-hotplug-support-broken-in-2623-rc3
+++ a/kernel/time/tick-broadcast.c
@@ -382,12 +382,23 @@ static int tick_broadcast_set_event(ktim
 
 int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
 {
+	int cpu = smp_processor_id();
+
+	/*
+	 * If the CPU is marked for broadcast, enforce oneshot
+	 * broadcast mode. The jinxed VAIO does not resume otherwise.
+	 * No idea why it ends up in a lower C State during resume
+	 * without notifying the clock events layer.
+	 */
+	if (cpu_isset(cpu, tick_broadcast_mask))
+		cpu_set(cpu, tick_broadcast_oneshot_mask);
+
 	clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
 
 	if(!cpus_empty(tick_broadcast_oneshot_mask))
 		tick_broadcast_set_event(ktime_get(), 1);
 
-	return cpu_isset(smp_processor_id(), tick_broadcast_oneshot_mask);
+	return cpu_isset(cpu, tick_broadcast_oneshot_mask);
 }
 
 /*
@@ -549,20 +560,17 @@ void tick_broadcast_switch_to_oneshot(vo
  */
 void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
 {
-	struct clock_event_device *bc;
 	unsigned long flags;
 	unsigned int cpu = *cpup;
 
 	spin_lock_irqsave(&tick_broadcast_lock, flags);
 
-	bc = tick_broadcast_device.evtdev;
+	/*
+	 * Clear the broadcast mask flag for the dead cpu, but do not
+	 * stop the broadcast device!
+	 */
 	cpu_clear(cpu, tick_broadcast_oneshot_mask);
 
-	if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT) {
-		if (bc && cpus_empty(tick_broadcast_oneshot_mask))
-			clockevents_set_mode(bc, CLOCK_EVT_MODE_SHUTDOWN);
-	}
-
 	spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 
diff -puN kernel/time/tick-sched.c~cpu-hotplug-support-broken-in-2623-rc3 kernel/time/tick-sched.c
--- a/kernel/time/tick-sched.c~cpu-hotplug-support-broken-in-2623-rc3
+++ a/kernel/time/tick-sched.c
@@ -160,6 +160,18 @@ void tick_nohz_stop_sched_tick(void)
 	cpu = smp_processor_id();
 	ts = &per_cpu(tick_cpu_sched, cpu);
 
+	/*
+	 * If this cpu is offline and it is the one which updates
+	 * jiffies, then give up the assignment and let it be taken by
+	 * the cpu which runs the tick timer next. If we don't drop
+	 * this here the jiffies might be stale and do_timer() never
+	 * invoked.
+	 */
+	if (unlikely(!cpu_online(cpu))) {
+		if (cpu == tick_do_timer_cpu)
+			tick_do_timer_cpu = -1;
+	}
+
 	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
 		goto end;
 
_