x86, mce: make polling timer interval per CPU

The polling timer while running per CPU still uses a global next_interval
variable, which lead to some CPUs either polling too fast or too slow.   
This was not a serious problem because all errors get picked up eventually,
but it's still better to avoid it. Turn next_interval into a per cpu variable.

v2: Fix check_interval == 0 case (Hidetoshi Seto)

[ Impact: minor bug fix ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
This commit is contained in:
Andi Kleen 2009-04-09 12:28:22 +02:00 коммит произвёл H. Peter Anvin
Родитель a939b96ccc
Коммит 6298c512bc
1 изменённых файлов: 12 добавлений и 12 удалений

Просмотреть файл

@ -452,13 +452,14 @@ void mce_log_therm_throt_event(__u64 status)
*/ */
static int check_interval = 5 * 60; /* 5 minutes */ static int check_interval = 5 * 60; /* 5 minutes */
static int next_interval; /* in jiffies */ static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
static void mcheck_timer(unsigned long); static void mcheck_timer(unsigned long);
static DEFINE_PER_CPU(struct timer_list, mce_timer); static DEFINE_PER_CPU(struct timer_list, mce_timer);
static void mcheck_timer(unsigned long data) static void mcheck_timer(unsigned long data)
{ {
struct timer_list *t = &per_cpu(mce_timer, data); struct timer_list *t = &per_cpu(mce_timer, data);
int *n;
WARN_ON(smp_processor_id() != data); WARN_ON(smp_processor_id() != data);
@ -470,14 +471,14 @@ static void mcheck_timer(unsigned long data)
* Alert userspace if needed. If we logged an MCE, reduce the * Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval. * polling interval, otherwise increase the polling interval.
*/ */
n = &__get_cpu_var(next_interval);
if (mce_notify_user()) { if (mce_notify_user()) {
next_interval = max(next_interval/2, HZ/100); *n = max(*n/2, HZ/100);
} else { } else {
next_interval = min(next_interval * 2, *n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
(int)round_jiffies_relative(check_interval*HZ));
} }
t->expires = jiffies + next_interval; t->expires = jiffies + *n;
add_timer(t); add_timer(t);
} }
@ -632,14 +633,13 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
static void mce_init_timer(void) static void mce_init_timer(void)
{ {
struct timer_list *t = &__get_cpu_var(mce_timer); struct timer_list *t = &__get_cpu_var(mce_timer);
int *n = &__get_cpu_var(next_interval);
/* data race harmless because everyone sets to the same value */ *n = check_interval * HZ;
if (!next_interval) if (!*n)
next_interval = check_interval * HZ;
if (!next_interval)
return; return;
setup_timer(t, mcheck_timer, smp_processor_id()); setup_timer(t, mcheck_timer, smp_processor_id());
t->expires = round_jiffies(jiffies + next_interval); t->expires = round_jiffies(jiffies + *n);
add_timer(t); add_timer(t);
} }
@ -907,7 +907,6 @@ static void mce_cpu_restart(void *data)
/* Reinit MCEs after user configuration changes */ /* Reinit MCEs after user configuration changes */
static void mce_restart(void) static void mce_restart(void)
{ {
next_interval = check_interval * HZ;
on_each_cpu(mce_cpu_restart, NULL, 1); on_each_cpu(mce_cpu_restart, NULL, 1);
} }
@ -1110,7 +1109,8 @@ static int __cpuinit mce_cpu_callback(struct notifier_block *nfb,
break; break;
case CPU_DOWN_FAILED: case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN: case CPU_DOWN_FAILED_FROZEN:
t->expires = round_jiffies(jiffies + next_interval); t->expires = round_jiffies(jiffies +
__get_cpu_var(next_interval));
add_timer_on(t, cpu); add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1); smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break; break;