Re: [PATCH 21/25] x86/mcheck: Split threshold_cpu_callback into two callbacks

From: Sebastian Andrzej Siewior
Date: Mon Nov 07 2016 - 12:26:31 EST


On 2016-11-07 16:07:45 [+0100], Borislav Petkov wrote:
> On Mon, Nov 07, 2016 at 02:25:01PM +0100, Sebastian Andrzej Siewior wrote:
> > This moves it 1:1 (well, more or less). Wouldn't you prefer doing it as
> > separate patch/change?
>
> Ontop of all of yours so that you don't have to redo yours?
>
> > CONFIG_X86_MCE_AMD is where the callback is implemented. Wouldn't that
> > be broken now?
>
> Yeah, fixed.

included (slightly adjusted to get fit on top of -rc4):

Subject: x86/mcheck: Split threshold_cpu_callback into two callbacks
From: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
Date: Tue, 25 Oct 2016 18:04:25 +0200

The threshold_cpu_callback callbacks looks like one of the notifier and
its arguments are almost the same. Split this out and have one ONLINE
and one DEAD callback. This will come handy later once the main code
gets changed to use the callback mechanism.
Also, handle threshold_cpu_callback_online() return value so we don't
continue if the function fails.

Boris Petkov removed the callback pointer and replaced it with proper
functions.

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>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -293,9 +293,7 @@ void do_machine_check(struct pt_regs *,
/*
* Threshold handler
*/
-
extern void (*mce_threshold_vector)(void);
-extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);

/* Deferred error interrupt handler */
extern void (*deferred_error_int_vector)(void);
@@ -377,7 +375,12 @@ struct smca_bank_info {
};

extern struct smca_bank_info smca_banks[MAX_NR_BANKS];
+extern int mce_threshold_create_device(unsigned int cpu);
+extern int mce_threshold_remove_device(unsigned int cpu);
+#else

+static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
+static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
#endif

#endif /* _ASM_X86_MCE_H */
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2255,8 +2255,6 @@ static struct bus_type mce_subsys = {

DEFINE_PER_CPU(struct device *, mce_device);

-void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-
static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
{
return container_of(attr, struct mce_bank, attr);
@@ -2512,13 +2510,17 @@ mce_cpu_callback(struct notifier_block *

switch (action & ~CPU_TASKS_FROZEN) {
case CPU_ONLINE:
+
mce_device_create(cpu);
- if (threshold_cpu_callback)
- threshold_cpu_callback(action, cpu);
+
+ if (mce_threshold_create_device(cpu)) {
+ mce_device_remove(cpu);
+ return NOTIFY_BAD;
+ }
+
break;
case CPU_DEAD:
- if (threshold_cpu_callback)
- threshold_cpu_callback(action, cpu);
+ mce_threshold_remove_device(cpu);
mce_device_remove(cpu);
mce_intel_hcpu_update(cpu);

--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -55,6 +55,8 @@
/* Threshold LVT offset is at MSR0xC0000410[15:12] */
#define SMCA_THR_LVT_OFF 0xF000

+static bool thresholding_en;
+
static const char * const th_names[] = {
"load_store",
"insn_fetch",
@@ -1077,10 +1079,13 @@ static void threshold_remove_bank(unsign
per_cpu(threshold_banks, cpu)[bank] = NULL;
}

-static void threshold_remove_device(unsigned int cpu)
+int mce_threshold_remove_device(unsigned int cpu)
{
unsigned int bank;

+ if (!thresholding_en)
+ return 0;
+
for (bank = 0; bank < mca_cfg.banks; ++bank) {
if (!(per_cpu(bank_map, cpu) & (1 << bank)))
continue;
@@ -1088,15 +1093,19 @@ static void threshold_remove_device(unsi
}
kfree(per_cpu(threshold_banks, cpu));
per_cpu(threshold_banks, cpu) = NULL;
+ return 0;
}

/* create dir/files for all valid threshold banks */
-static int threshold_create_device(unsigned int cpu)
+int mce_threshold_create_device(unsigned int cpu)
{
unsigned int bank;
struct threshold_bank **bp;
int err = 0;

+ if (!thresholding_en)
+ return 0;
+
bp = per_cpu(threshold_banks, cpu);
if (bp)
return 0;
@@ -1117,40 +1126,23 @@ static int threshold_create_device(unsig
}
return err;
err:
- threshold_remove_device(cpu);
+ mce_threshold_remove_device(cpu);
return err;
}

-/* get notified when a cpu comes on/off */
-static void
-amd_64_threshold_cpu_callback(unsigned long action, unsigned int cpu)
-{
- switch (action) {
- case CPU_ONLINE:
- case CPU_ONLINE_FROZEN:
- threshold_create_device(cpu);
- break;
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- threshold_remove_device(cpu);
- break;
- default:
- break;
- }
-}
-
static __init int threshold_init_device(void)
{
unsigned lcpu = 0;

/* to hit CPUs online before the notifier is up */
for_each_online_cpu(lcpu) {
- int err = threshold_create_device(lcpu);
+ int err = mce_threshold_create_device(lcpu);

if (err)
return err;
}
- threshold_cpu_callback = amd_64_threshold_cpu_callback;
+
+ thresholding_en = true;

return 0;
}


Sebastian