0dc9c639e6
The NFIT MCE handler callback (for handling media errors on NVDIMMs)
takes a mutex to add the location of a memory error to a list. But since
the notifier call chain for machine checks (x86_mce_decoder_chain) is
atomic, we get a lockdep splat like:
BUG: sleeping function called from invalid context at kernel/locking/mutex.c:620
in_atomic(): 1, irqs_disabled(): 0, pid: 4, name: kworker/0:0
[..]
Call Trace:
dump_stack
___might_sleep
__might_sleep
mutex_lock_nested
? __lock_acquire
nfit_handle_mce
notifier_call_chain
atomic_notifier_call_chain
? atomic_notifier_call_chain
mce_gen_pool_process
Convert the notifier to a blocking one which gets to run only in process
context.
Boris: remove the notifier call in atomic context in print_mce(). For
now, let's print the MCE on the atomic path so that we can make sure
they go out and get logged at least.
Fixes: 6839a6d96f ("nfit: do an ARS scrub on hitting a latent media error")
Reported-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: x86-ml <x86@kernel.org>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20170411224457.24777-1-vishal.l.verma@intel.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
99 lines
2.6 KiB
C
99 lines
2.6 KiB
C
#include <linux/device.h>
|
|
#include <asm/mce.h>
|
|
|
|
enum severity_level {
|
|
MCE_NO_SEVERITY,
|
|
MCE_DEFERRED_SEVERITY,
|
|
MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY,
|
|
MCE_KEEP_SEVERITY,
|
|
MCE_SOME_SEVERITY,
|
|
MCE_AO_SEVERITY,
|
|
MCE_UC_SEVERITY,
|
|
MCE_AR_SEVERITY,
|
|
MCE_PANIC_SEVERITY,
|
|
};
|
|
|
|
extern struct blocking_notifier_head x86_mce_decoder_chain;
|
|
|
|
#define ATTR_LEN 16
|
|
#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */
|
|
|
|
/* One object for each MCE bank, shared by all CPUs */
|
|
struct mce_bank {
|
|
u64 ctl; /* subevents to enable */
|
|
unsigned char init; /* initialise bank? */
|
|
struct device_attribute attr; /* device attribute */
|
|
char attrname[ATTR_LEN]; /* attribute name */
|
|
};
|
|
|
|
struct mce_evt_llist {
|
|
struct llist_node llnode;
|
|
struct mce mce;
|
|
};
|
|
|
|
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);
|
|
struct llist_node *mce_gen_pool_prepare_records(void);
|
|
|
|
extern int (*mce_severity)(struct mce *a, int tolerant, char **msg, bool is_excp);
|
|
struct dentry *mce_get_debugfs_dir(void);
|
|
|
|
extern struct mce_bank *mce_banks;
|
|
extern mce_banks_t mce_banks_ce_disabled;
|
|
|
|
#ifdef CONFIG_X86_MCE_INTEL
|
|
unsigned long cmci_intel_adjust_timer(unsigned long interval);
|
|
bool mce_intel_cmci_poll(void);
|
|
void mce_intel_hcpu_update(unsigned long cpu);
|
|
void cmci_disable_bank(int bank);
|
|
#else
|
|
# define cmci_intel_adjust_timer mce_adjust_timer_default
|
|
static inline bool mce_intel_cmci_poll(void) { return false; }
|
|
static inline void mce_intel_hcpu_update(unsigned long cpu) { }
|
|
static inline void cmci_disable_bank(int bank) { }
|
|
#endif
|
|
|
|
void mce_timer_kick(unsigned long interval);
|
|
|
|
#ifdef CONFIG_ACPI_APEI
|
|
int apei_write_mce(struct mce *m);
|
|
ssize_t apei_read_mce(struct mce *m, u64 *record_id);
|
|
int apei_check_mce(void);
|
|
int apei_clear_mce(u64 record_id);
|
|
#else
|
|
static inline int apei_write_mce(struct mce *m)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int apei_check_mce(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int apei_clear_mce(u64 record_id)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
#endif
|
|
|
|
void mce_inject_log(struct mce *m);
|
|
|
|
/*
|
|
* We consider records to be equivalent if bank+status+addr+misc all match.
|
|
* This is only used when the system is going down because of a fatal error
|
|
* to avoid cluttering the console log with essentially repeated information.
|
|
* In normal processing all errors seen are logged.
|
|
*/
|
|
static inline bool mce_cmp(struct mce *m1, struct mce *m2)
|
|
{
|
|
return m1->bank != m2->bank ||
|
|
m1->status != m2->status ||
|
|
m1->addr != m2->addr ||
|
|
m1->misc != m2->misc;
|
|
}
|