summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu/mcheck
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu/mcheck')
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c59
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c10
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c23
3 files changed, 59 insertions, 33 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 325559d..2f5aab2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -165,6 +165,11 @@ void mce_log(struct mce *mce)
set_bit(0, &mce_need_notify);
}
+void __weak decode_mce(struct mce *m)
+{
+ return;
+}
+
static void print_mce(struct mce *m)
{
printk(KERN_EMERG
@@ -176,28 +181,33 @@ static void print_mce(struct mce *m)
m->cs, m->ip);
if (m->cs == __KERNEL_CS)
print_symbol("{%s}", m->ip);
- printk("\n");
+ printk(KERN_CONT "\n");
}
printk(KERN_EMERG "TSC %llx ", m->tsc);
if (m->addr)
- printk("ADDR %llx ", m->addr);
+ printk(KERN_CONT "ADDR %llx ", m->addr);
if (m->misc)
- printk("MISC %llx ", m->misc);
- printk("\n");
+ printk(KERN_CONT "MISC %llx ", m->misc);
+ printk(KERN_CONT "\n");
printk(KERN_EMERG "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid,
m->apicid);
+
+ decode_mce(m);
}
static void print_mce_head(void)
{
- printk(KERN_EMERG "\n" KERN_EMERG "HARDWARE ERROR\n");
+ printk(KERN_EMERG "\nHARDWARE ERROR\n");
}
static void print_mce_tail(void)
{
printk(KERN_EMERG "This is not a software problem!\n"
- KERN_EMERG "Run through mcelog --ascii to decode and contact your hardware vendor\n");
+#if (!defined(CONFIG_EDAC) || !defined(CONFIG_CPU_SUP_AMD))
+ "Run through mcelog --ascii to decode and contact your hardware vendor\n"
+#endif
+ );
}
#define PANIC_TIMEOUT 5 /* 5 seconds */
@@ -1085,7 +1095,7 @@ void mce_log_therm_throt_event(__u64 status)
*/
static int check_interval = 5 * 60; /* 5 minutes */
-static DEFINE_PER_CPU(int, next_interval); /* in jiffies */
+static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
static DEFINE_PER_CPU(struct timer_list, mce_timer);
static void mcheck_timer(unsigned long data)
@@ -1104,14 +1114,14 @@ static void mcheck_timer(unsigned long data)
* Alert userspace if needed. If we logged an MCE, reduce the
* polling interval, otherwise increase the polling interval.
*/
- n = &__get_cpu_var(next_interval);
+ n = &__get_cpu_var(mce_next_interval);
if (mce_notify_irq())
*n = max(*n/2, HZ/100);
else
*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
t->expires = jiffies + *n;
- add_timer(t);
+ add_timer_on(t, smp_processor_id());
}
static void mce_do_trigger(struct work_struct *work)
@@ -1235,8 +1245,13 @@ static void mce_init(void)
}
/* Add per CPU specific workarounds here */
-static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
+static int __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
{
+ if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
+ pr_info("MCE: unknown CPU type - not enabling MCE support.\n");
+ return -EOPNOTSUPP;
+ }
+
/* This should be disabled by the BIOS, but isn't always */
if (c->x86_vendor == X86_VENDOR_AMD) {
if (c->x86 == 15 && banks > 4) {
@@ -1283,14 +1298,19 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
monarch_timeout < 0)
monarch_timeout = USEC_PER_SEC;
- /* There are also broken BIOSes on some Pentium M systems. */
- if (c->x86 == 6 && c->x86_model == 13 && mce_bootlog < 0)
+ /*
+ * There are also broken BIOSes on some Pentium M and
+ * earlier systems:
+ */
+ if (c->x86 == 6 && c->x86_model <= 13 && mce_bootlog < 0)
mce_bootlog = 0;
}
if (monarch_timeout < 0)
monarch_timeout = 0;
if (mce_bootlog != 0)
mce_panic_timeout = 30;
+
+ return 0;
}
static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
@@ -1324,7 +1344,7 @@ static void mce_cpu_features(struct cpuinfo_x86 *c)
static void mce_init_timer(void)
{
struct timer_list *t = &__get_cpu_var(mce_timer);
- int *n = &__get_cpu_var(next_interval);
+ int *n = &__get_cpu_var(mce_next_interval);
if (mce_ignore_ce)
return;
@@ -1334,7 +1354,7 @@ static void mce_init_timer(void)
return;
setup_timer(t, mcheck_timer, smp_processor_id());
t->expires = round_jiffies(jiffies + *n);
- add_timer(t);
+ add_timer_on(t, smp_processor_id());
}
/* Handle unconfigured int18 (should never happen) */
@@ -1362,11 +1382,10 @@ void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
if (!mce_available(c))
return;
- if (mce_cap_init() < 0) {
+ if (mce_cap_init() < 0 || mce_cpu_quirks(c) < 0) {
mce_disabled = 1;
return;
}
- mce_cpu_quirks(c);
machine_check_vector = do_machine_check;
@@ -1720,17 +1739,15 @@ static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
const char *buf, size_t siz)
{
char *p;
- int len;
strncpy(mce_helper, buf, sizeof(mce_helper));
mce_helper[sizeof(mce_helper)-1] = 0;
- len = strlen(mce_helper);
p = strchr(mce_helper, '\n');
- if (*p)
+ if (p)
*p = 0;
- return len;
+ return strlen(mce_helper) + !!p;
}
static ssize_t set_ignore_ce(struct sys_device *s,
@@ -1944,7 +1961,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
t->expires = round_jiffies(jiffies +
- __get_cpu_var(next_interval));
+ __get_cpu_var(mce_next_interval));
add_timer_on(t, cpu);
smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
break;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ddae216..8cd5224 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -69,7 +69,7 @@ struct threshold_bank {
struct threshold_block *blocks;
cpumask_var_t cpus;
};
-static DEFINE_PER_CPU(struct threshold_bank *, threshold_banks[NR_BANKS]);
+static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks);
#ifdef CONFIG_SMP
static unsigned char shared_bank[NR_BANKS] = {
@@ -489,12 +489,14 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
int i, err = 0;
struct threshold_bank *b = NULL;
char name[32];
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
sprintf(name, "threshold_bank%i", bank);
#ifdef CONFIG_SMP
if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) { /* symlink */
- i = cpumask_first(cpu_core_mask(cpu));
+ i = cpumask_first(c->llc_shared_map);
/* first core not up yet */
if (cpu_data(i).cpu_core_id)
@@ -514,7 +516,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
if (err)
goto out;
- cpumask_copy(b->cpus, cpu_core_mask(cpu));
+ cpumask_copy(b->cpus, c->llc_shared_map);
per_cpu(threshold_banks, cpu)[bank] = b;
goto out;
@@ -539,7 +541,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
#ifndef CONFIG_SMP
cpumask_setall(b->cpus);
#else
- cpumask_copy(b->cpus, cpu_core_mask(cpu));
+ cpumask_copy(b->cpus, c->llc_shared_map);
#endif
per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 15f2bc0..63a56d1 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -36,6 +36,7 @@
static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
+static DEFINE_PER_CPU(bool, thermal_throttle_active);
static atomic_t therm_throt_en = ATOMIC_INIT(0);
@@ -96,27 +97,33 @@ static int therm_throt_process(int curr)
{
unsigned int cpu = smp_processor_id();
__u64 tmp_jiffs = get_jiffies_64();
+ bool was_throttled = __get_cpu_var(thermal_throttle_active);
+ bool is_throttled = __get_cpu_var(thermal_throttle_active) = curr;
- if (curr)
+ if (is_throttled)
__get_cpu_var(thermal_throttle_count)++;
- if (time_before64(tmp_jiffs, __get_cpu_var(next_check)))
+ if (!(was_throttled ^ is_throttled) &&
+ time_before64(tmp_jiffs, __get_cpu_var(next_check)))
return 0;
__get_cpu_var(next_check) = tmp_jiffs + CHECK_INTERVAL;
/* if we just entered the thermal event */
- if (curr) {
+ if (is_throttled) {
printk(KERN_CRIT "CPU%d: Temperature above threshold, "
- "cpu clock throttled (total events = %lu)\n", cpu,
- __get_cpu_var(thermal_throttle_count));
+ "cpu clock throttled (total events = %lu)\n",
+ cpu, __get_cpu_var(thermal_throttle_count));
add_taint(TAINT_MACHINE_CHECK);
- } else {
- printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu);
+ return 1;
+ }
+ if (was_throttled) {
+ printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
+ return 1;
}
- return 1;
+ return 0;
}
#ifdef CONFIG_SYSFS
generated by cgit v0.10.2 at 2024-08-04 03:39:45 (GMT)