[PATCH 5/7 v2] x86/mcheck: reorganize the hotplug callbacks

[Sebastian Andrzej Siewior]

Initially I wanted to remove mcheck_cpu_init() from identify_cpu() and let it
become an independent early hotplug callback. The main problem here was that
the init on the boot CPU may happen too late
(device_initcall_sync(mcheck_init_device)) and nobody wanted to risk receiving
and MCE event at boot time leading to a shutdown (if the MCE feature is not yet
enabled).

Here is attempt two: the timing stays as-is but the ordering of the functions
is changed:
- mcheck_cpu_init() (which is run from identify_cpu()) will setup the timer
  struct but won't fire the timer. This is moved to CPU_ONLINE since its
  cleanup part is in CPU_DOWN_PREPARE. So if it is okay to stop the timer early
  in the shutdown phase, it should be okay to start it late in the bring up phase.

- CPU_DOWN_PREPARE disables the MCE feature flags for !INTEL CPUs in
  mce_disable_cpu(). If a failure occurs it would be re-enabled on all vendor
  CPUs (including Intel where it was not disabled during shutdown). To keep this
  working I am moving it to CPU_ONLINE. smp_call_function_single() is dropped
  because the notifier runs on the target CPU (since core code rework).

- CPU_ONLINE is invoking mce_device_create() + mce_threshold_create_device()
  but its cleanup part is in CPU_DEAD (mce_threshold_remove_device() and
  mce_device_remove()). In order to keep this symmetrical I am moving the clean
  up from CPU_DEAD to CPU_DOWN_PREPARE.

Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: linux-edac@xxxxxxxxxxxxxxx
Cc: x86@xxxxxxxxxx
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
On 2016-11-11 20:57:37 [+0100], Borislav Petkov wrote:
> Then please do it right:
> 
> static void __mcheck_cap_setup_timer(void)
> {
>         struct timer_list *t = this_cpu_ptr(&mce_timer);
>         unsigned int cpu = smp_processor_id();
> 
>         setup_pinned_timer(t, mce_timer_fn, cpu);
> }
> 
> and call that function then.

I can't believe that you ask for this but here it is.

 arch/x86/kernel/cpu/mcheck/mce.c |   36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1745,6 +1745,14 @@ static void mce_start_timer(unsigned int
 	add_timer_on(t, cpu);
 }
 
+static void __mcheck_cap_setup_timer(void)
+{
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	unsigned int cpu = smp_processor_id();
+
+	setup_pinned_timer(t, mce_timer_fn, cpu);
+}
+
 static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
@@ -1796,7 +1804,7 @@ void mcheck_cpu_init(struct cpuinfo_x86
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_init_timer();
+	__mcheck_cap_setup_timer();
 }
 
 /*
@@ -2470,28 +2478,25 @@ static void mce_device_remove(unsigned i
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void mce_disable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
-
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_clear();
 
 	vendor_disable_error_reporting();
 }
 
-static void mce_reenable_cpu(void *h)
+static void mce_reenable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
 	for (i = 0; i < mca_cfg.banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -2510,6 +2515,7 @@ mce_cpu_callback(struct notifier_block *
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
 
 		mce_device_create(cpu);
 
@@ -2517,11 +2523,10 @@ mce_cpu_callback(struct notifier_block *
 			mce_device_remove(cpu);
 			return NOTIFY_BAD;
 		}
-
+		mce_reenable_cpu();
+		mce_start_timer(cpu, t);
 		break;
 	case CPU_DEAD:
-		mce_threshold_remove_device(cpu);
-		mce_device_remove(cpu);
 		mce_intel_hcpu_update(cpu);
 
 		/* intentionally ignoring frozen here */
@@ -2529,12 +2534,11 @@ mce_cpu_callback(struct notifier_block *
 			cmci_rediscover();
 		break;
 	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
+		mce_disable_cpu();
 		del_timer_sync(t);
-		break;
-	case CPU_DOWN_FAILED:
-		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
-		mce_start_timer(cpu, t);
+
+		mce_threshold_remove_device(cpu);
+		mce_device_remove(cpu);
 		break;
 	}