summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/include/asm/mce.h20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-genpool.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h2
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c57
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c9
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c30
-rw-r--r--arch/x86/ras/Kconfig2
-rw-r--r--drivers/acpi/acpi_extlog.c1
-rw-r--r--drivers/acpi/nfit/mce.c1
-rw-r--r--drivers/edac/i7core_edac.c1
-rw-r--r--drivers/edac/mce_amd.c8
-rw-r--r--drivers/edac/mce_amd.h1
-rw-r--r--drivers/edac/sb_edac.c3
-rw-r--r--drivers/edac/skx_edac.c3
17 files changed, 59 insertions, 93 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e487493bbd47..7b6fd68b4715 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1070,7 +1070,7 @@ config X86_MCE_THRESHOLD
def_bool y
config X86_MCE_INJECT
- depends on X86_MCE
+ depends on X86_MCE && X86_LOCAL_APIC
tristate "Machine check injector support"
---help---
Provide support for injecting machine checks for testing purposes.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 5132f2a6c0a2..e63873683d4a 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -97,10 +97,6 @@
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
-/* Software defined banks */
-#define MCE_EXTENDED_BANK 128
-#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
-
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
@@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags;
extern struct mca_config mca_cfg;
extern struct mca_msr_regs msr_ops;
+
+enum mce_notifier_prios {
+ MCE_PRIO_SRAO = INT_MAX,
+ MCE_PRIO_EXTLOG = INT_MAX - 1,
+ MCE_PRIO_NFIT = INT_MAX - 2,
+ MCE_PRIO_EDAC = INT_MAX - 3,
+ MCE_PRIO_LOWEST = 0,
+};
+
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);
@@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void);
void intel_init_thermal(struct cpuinfo_x86 *c);
-void mce_log_therm_throt_event(__u64 status);
-
/* Interrupt Handler for core thermal thresholds */
extern int (*platform_thermal_notify)(__u64 msr_val);
@@ -362,12 +365,13 @@ struct smca_hwid {
unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */
u32 hwid_mcatype; /* (hwid,mcatype) tuple */
u32 xec_bitmap; /* Bitmap of valid ExtErrorCodes; current max is 21. */
+ u8 count; /* Number of instances. */
};
struct smca_bank {
struct smca_hwid *hwid;
- /* Instance ID */
- u32 id;
+ u32 id; /* Value of MCA_IPID[InstanceId]. */
+ u8 sysfs_id; /* Value used for sysfs name. */
};
extern struct smca_bank smca_banks[MAX_NR_BANKS];
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 83f1a98d37db..2eee85379689 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
if (severity >= GHES_SEV_RECOVERABLE)
m.status |= MCI_STATUS_UC;
- if (severity >= GHES_SEV_PANIC)
+
+ if (severity >= GHES_SEV_PANIC) {
m.status |= MCI_STATUS_PCC;
+ m.tsc = rdtsc();
+ }
m.addr = mem_err->physical_addr;
mce_log(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 93d824ec3120..1e5a50c11d3c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void)
return new_head.first;
}
-void mce_gen_pool_process(void)
+void mce_gen_pool_process(struct work_struct *__unused)
{
struct llist_node *head;
struct mce_evt_llist *node, *tmp;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 517619ea6498..99165b206df3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -152,7 +152,6 @@ static void raise_mce(struct mce *m)
if (context == MCJ_CTX_RANDOM)
return;
-#ifdef CONFIG_X86_LOCAL_APIC
if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
unsigned long start;
int cpu;
@@ -192,9 +191,7 @@ static void raise_mce(struct mce *m)
raise_local();
put_cpu();
put_online_cpus();
- } else
-#endif
- {
+ } else {
preempt_disable();
raise_local();
preempt_enable();
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index cd74a3f00aea..903043e6a62b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -31,7 +31,7 @@ struct mce_evt_llist {
struct mce mce;
};
-void mce_gen_pool_process(void);
+void mce_gen_pool_process(struct work_struct *__unused);
bool mce_gen_pool_empty(void);
int mce_gen_pool_add(struct mce *mce);
int mce_gen_pool_init(void);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 537c6647d84c..8e9725c607ea 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -128,7 +128,6 @@ void mce_setup(struct mce *m)
{
memset(m, 0, sizeof(struct mce));
m->cpu = m->extcpu = smp_processor_id();
- m->tsc = rdtsc();
/* We hope get_seconds stays lockless */
m->time = get_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb)
{
atomic_inc(&num_notifiers);
- /* Ensure SRAO notifier has the highest priority in the decode chain. */
- if (nb != &mce_srao_nb && nb->priority == INT_MAX)
- nb->priority -= 1;
+ WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
}
@@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
}
static struct notifier_block mce_srao_nb = {
.notifier_call = srao_decode_notifier,
- .priority = INT_MAX,
+ .priority = MCE_PRIO_SRAO,
};
static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
@@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
static struct notifier_block mce_default_nb = {
.notifier_call = mce_default_notifier,
/* lowest prio, we want it to run last. */
- .priority = 0,
+ .priority = MCE_PRIO_LOWEST,
};
/*
@@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
mce_gather_info(&m, NULL);
- /*
- * m.tsc was set in mce_setup(). Clear it if not requested.
- *
- * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid
- * that dance.
- */
- if (!(flags & MCP_TIMESTAMP))
- m.tsc = 0;
+ if (flags & MCP_TIMESTAMP)
+ m.tsc = rdtsc();
for (i = 0; i < mca_cfg.banks; i++) {
if (!mce_banks[i].ctl || !test_bit(i, *b))
@@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
goto out;
mce_gather_info(&m, regs);
+ m.tsc = rdtsc();
final = this_cpu_ptr(&mces_seen);
*final = m;
@@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
#endif
/*
- * Action optional processing happens here (picking up
- * from the list of faulting pages that do_machine_check()
- * placed into the genpool).
- */
-static void mce_process_work(struct work_struct *dummy)
-{
- mce_gen_pool_process();
-}
-
-#ifdef CONFIG_X86_MCE_INTEL
-/***
- * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
- * @cpu: The CPU on which the event occurred.
- * @status: Event status information
- *
- * This function should be called by the thermal interrupt after the
- * event has been processed and the decision was made to log the event
- * further.
- *
- * The status parameter will be saved to the 'status' field of 'struct mce'
- * and historically has been the register value of the
- * MSR_IA32_THERMAL_STATUS (Intel) msr.
- */
-void mce_log_therm_throt_event(__u64 status)
-{
- struct mce m;
-
- mce_setup(&m);
- m.bank = MCE_THERMAL_BANK;
- m.status = status;
- mce_log(&m);
-}
-#endif /* CONFIG_X86_MCE_INTEL */
-
-/*
* Periodic polling timer for "silent" machine check errors. If the
* poller finds an MCE, poll 2x faster. When the poller finds no more
* errors, poll 2x slower (up to check_interval seconds).
@@ -2189,7 +2146,7 @@ int __init mcheck_init(void)
mce_register_decode_chain(&mce_default_nb);
mcheck_vendor_init_severity();
- INIT_WORK(&mce_work, mce_process_work);
+ INIT_WORK(&mce_work, mce_gen_pool_process);
init_irq_work(&mce_irq_work, mce_irq_work_cb);
return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index a5fd137417a2..9e5427df3243 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank)
smca_banks[bank].hwid = s_hwid;
smca_banks[bank].id = instance_id;
+ smca_banks[bank].sysfs_id = s_hwid->count++;
break;
}
}
@@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
mce_setup(&m);
m.status = status;
- m.bank = bank;
+ m.bank = bank;
+ m.tsc = rdtsc();
if (threshold_err)
m.misc = misc;
@@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
return NULL;
}
+ if (smca_banks[bank].hwid->count == 1)
+ return smca_get_name(bank_type);
+
snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
"%s_%x", smca_get_name(bank_type),
- smca_banks[bank].id);
+ smca_banks[bank].sysfs_id);
return buf_mcatype;
}
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 465aca8be009..85469f84c921 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -6,7 +6,7 @@
*
* Maintains a counter in /sys that keeps track of the number of thermal
* events, such that the user knows how bad the thermal problem might be
- * (since the logging to syslog and mcelog is rate limited).
+ * (since the logging to syslog is rate limited).
*
* Author: Dmitriy Zavin (dmitriyz@google.com)
*
@@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = {
* IRQ has been acknowledged.
*
* It will take care of rate limiting and printing messages to the syslog.
- *
- * Returns: 0 : Event should NOT be further logged, i.e. still in
- * "timeout" from previous log message.
- * 1 : Event should be logged further, and a message has been
- * printed to the syslog.
*/
-static int therm_throt_process(bool new_event, int event, int level)
+static void therm_throt_process(bool new_event, int event, int level)
{
struct _thermal_state *state;
unsigned int this_cpu = smp_processor_id();
@@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level)
else if (event == POWER_LIMIT_EVENT)
state = &pstate->core_power_limit;
else
- return 0;
+ return;
} else if (level == PACKAGE_LEVEL) {
if (event == THERMAL_THROTTLING_EVENT)
state = &pstate->package_throttle;
else if (event == POWER_LIMIT_EVENT)
state = &pstate->package_power_limit;
else
- return 0;
+ return;
} else
- return 0;
+ return;
old_event = state->new_event;
state->new_event = new_event;
@@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level)
if (time_before64(now, state->next_check) &&
state->count != state->last_count)
- return 0;
+ return;
state->next_check = now + CHECK_INTERVAL;
state->last_count = state->count;
@@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level)
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
- return 1;
+ return;
}
if (old_event) {
if (event == THERMAL_THROTTLING_EVENT)
pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
level == CORE_LEVEL ? "Core" : "Package");
- return 1;
+ return;
}
-
- return 0;
}
static int thresh_event_valid(int level, int event)
@@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void)
/* Check for violation of core thermal thresholds*/
notify_thresholds(msr_val);
- if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
- THERMAL_THROTTLING_EVENT,
- CORE_LEVEL) != 0)
- mce_log_therm_throt_event(msr_val);
+ therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+ THERMAL_THROTTLING_EVENT,
+ CORE_LEVEL);
if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable)
therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index d957d5f21a86..0bc60a308730 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -1,6 +1,6 @@
config MCE_AMD_INJ
tristate "Simple MCE injection interface for AMD processors"
- depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB
+ depends on RAS && X86_MCE && DEBUG_FS && AMD_NB
default n
help
This is a simple debugfs interface to inject MCEs and test different
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index b3842ffc19ba..a15270a806fc 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -212,6 +212,7 @@ static bool __init extlog_get_l1addr(void)
}
static struct notifier_block extlog_mce_dec = {
.notifier_call = extlog_print,
+ .priority = MCE_PRIO_EXTLOG,
};
static int __init extlog_init(void)
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index e5ce81c38eed..3ba1c3472cf9 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -90,6 +90,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
static struct notifier_block nfit_mce_dec = {
.notifier_call = nfit_handle_mce,
+ .priority = MCE_PRIO_NFIT,
};
void nfit_mce_register(void)
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 69b5adead0ad..75ad847593b7 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1835,6 +1835,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
static struct notifier_block i7_mce_dec = {
.notifier_call = i7core_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
struct memdev_dmi_entry {
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 27513dca8009..ba35b7ea3686 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -942,7 +942,8 @@ static const char *decode_error_status(struct mce *m)
return "Corrected error, no action required.";
}
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
+static int
+amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
{
struct mce *m = (struct mce *)data;
struct cpuinfo_x86 *c = &cpu_data(m->extcpu);
@@ -1005,6 +1006,9 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
goto err_code;
}
+ if (m->tsc)
+ pr_emerg(HW_ERR "TSC: %llu\n", m->tsc);
+
if (!fam_ops)
goto err_code;
@@ -1046,10 +1050,10 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
return NOTIFY_STOP;
}
-EXPORT_SYMBOL_GPL(amd_decode_mce);
static struct notifier_block amd_mce_dec_nb = {
.notifier_call = amd_decode_mce,
+ .priority = MCE_PRIO_EDAC,
};
static int __init mce_amd_init(void)
diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
index c2359a1ea6b3..0b6a68673e0e 100644
--- a/drivers/edac/mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -79,6 +79,5 @@ struct amd_decoder_ops {
void amd_report_gart_errors(bool);
void amd_register_ecc_decoder(void (*f)(int, struct mce *));
void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data);
#endif /* _EDAC_MCE_AMD_H */
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 573be9c0ffb8..a65ea44e3b0b 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3117,7 +3117,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
}
static struct notifier_block sbridge_mce_dec = {
- .notifier_call = sbridge_mce_check_error,
+ .notifier_call = sbridge_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
/****************************************************************************
diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c
index 79ef675e4d6f..1159dba4671f 100644
--- a/drivers/edac/skx_edac.c
+++ b/drivers/edac/skx_edac.c
@@ -1007,7 +1007,8 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
}
static struct notifier_block skx_mce_dec = {
- .notifier_call = skx_mce_check_error,
+ .notifier_call = skx_mce_check_error,
+ .priority = MCE_PRIO_EDAC,
};
static void skx_remove(void)
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-24 19:04:23 +0000