static int mce_handle_error(struct rtas_error_log *errp)
{
struct pseries_errorlog *pseries_log;
struct pseries_mc_errorlog *mce_log;
int disposition = rtas_error_disposition(errp);
u8 error_type;
if (!rtas_error_extended(errp))
goto out;
pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
if (pseries_log == NULL)
goto out;
mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
error_type = mce_log->error_type;
#ifdef CONFIG_PPC_BOOK3S_64
if (disposition == RTAS_DISP_NOT_RECOVERED) {
switch (error_type) {
case MC_ERROR_TYPE_SLB:
case MC_ERROR_TYPE_ERAT:
/*
* Store the old slb content in paca before flushing.
* Print this when we go to virtual mode.
* There are chances that we may hit MCE again if there
* is a parity error on the SLB entry we trying to read
* for saving. Hence limit the slb saving to single
* level of recursion.
*/
if (local_paca->in_mce == 1)
slb_save_contents(local_paca->mce_faulty_slbs);
flush_and_reload_slb();
disposition = RTAS_DISP_FULLY_RECOVERED;
rtas_set_disposition_recovered(errp);
break;
default:
break;
}
}
#endif
out:
return disposition;
}
/*
* See if we can recover from a machine check exception.
* This is only called on power4 (or above) and only via
* the Firmware Non-Maskable Interrupts (fwnmi) handler
* which provides the error analysis for us.
*
* Return 1 if corrected (or delivered a signal).
* Return 0 if there is nothing we can do.
*/
static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
{
int recovered = 0;
int disposition = rtas_error_disposition(err);
pseries_print_mce_info(regs, err);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
recovered = 0;
} else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
/* Platform corrected itself but could be degraded */
printk(KERN_ERR "MCE: limited recovery, system may "
"be degraded\n");
recovered = 1;
} else if (user_mode(regs) && !is_global_init(current) &&
rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) {
/*
* If we received a synchronous error when in userspace
* kill the task. Firmware may report details of the fail
* asynchronously, so we can't rely on the target and type
* fields being valid here.
*/
printk(KERN_ERR "MCE: uncorrectable error, killing task "
"%s:%d\n", current->comm, current->pid);
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
pseries_process_ue(regs, err);
/* Queue irq work to log this rtas event later. */
irq_work_queue(&mce_errlog_process_work);
return recovered;
}
/*
* See if we can recover from a machine check exception.
* This is only called on power4 (or above) and only via
* the Firmware Non-Maskable Interrupts (fwnmi) handler
* which provides the error analysis for us.
*
* Return 1 if corrected (or delivered a signal).
* Return 0 if there is nothing we can do.
*/
static int recover_mce(struct pt_regs *regs, struct rtas_error_log *err)
{
int recovered = 0;
int disposition = rtas_error_disposition(err);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
recovered = 0;
} else if (disposition == RTAS_DISP_FULLY_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
} else if (disposition == RTAS_DISP_LIMITED_RECOVERY) {
/* Platform corrected itself but could be degraded */
printk(KERN_ERR "MCE: limited recovery, system may "
"be degraded\n");
recovered = 1;
} else if (user_mode(regs) && !is_global_init(current) &&
rtas_error_severity(err) == RTAS_SEVERITY_ERROR_SYNC) {
/*
* If we received a synchronous error when in userspace
* kill the task. Firmware may report details of the fail
* asynchronously, so we can't rely on the target and type
* fields being valid here.
*/
printk(KERN_ERR "MCE: uncorrectable error, killing task "
"%s:%d\n", current->comm, current->pid);
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
log_error((char *)err, ERR_TYPE_RTAS_LOG, 0);
return recovered;
}
static void pseries_print_mce_info(struct pt_regs *regs,
struct rtas_error_log *errp)
{
const char *level, *sevstr;
struct pseries_errorlog *pseries_log;
struct pseries_mc_errorlog *mce_log;
u8 error_type, err_sub_type;
u64 addr;
u8 initiator = rtas_error_initiator(errp);
int disposition = rtas_error_disposition(errp);
static const char * const initiators[] = {
"Unknown",
"CPU",
"PCI",
"ISA",
"Memory",
"Power Mgmt",
};
static const char * const mc_err_types[] = {
"UE",
"SLB",
"ERAT",
"TLB",
"D-Cache",
"Unknown",
"I-Cache",
};
static const char * const mc_ue_types[] = {
"Indeterminate",
"Instruction fetch",
"Page table walk ifetch",
"Load/Store",
"Page table walk Load/Store",
};
/* SLB sub errors valid values are 0x0, 0x1, 0x2 */
static const char * const mc_slb_types[] = {
"Parity",
"Multihit",
"Indeterminate",
};
/* TLB and ERAT sub errors valid values are 0x1, 0x2, 0x3 */
static const char * const mc_soft_types[] = {
"Unknown",
"Parity",
"Multihit",
"Indeterminate",
};
if (!rtas_error_extended(errp)) {
pr_err("Machine check interrupt: Missing extended error log\n");
return;
}
pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE);
if (pseries_log == NULL)
return;
mce_log = (struct pseries_mc_errorlog *)pseries_log->data;
error_type = mce_log->error_type;
err_sub_type = rtas_mc_error_sub_type(mce_log);
switch (rtas_error_severity(errp)) {
case RTAS_SEVERITY_NO_ERROR:
level = KERN_INFO;
sevstr = "Harmless";
break;
case RTAS_SEVERITY_WARNING:
level = KERN_WARNING;
sevstr = "";
break;
case RTAS_SEVERITY_ERROR:
case RTAS_SEVERITY_ERROR_SYNC:
level = KERN_ERR;
sevstr = "Severe";
break;
case RTAS_SEVERITY_FATAL:
default:
level = KERN_ERR;
sevstr = "Fatal";
break;
}
#ifdef CONFIG_PPC_BOOK3S_64
/* Display faulty slb contents for SLB errors. */
if (error_type == MC_ERROR_TYPE_SLB)
slb_dump_contents(local_paca->mce_faulty_slbs);
#endif
printk("%s%s Machine check interrupt [%s]\n", level, sevstr,
disposition == RTAS_DISP_FULLY_RECOVERED ?
"Recovered" : "Not recovered");
if (user_mode(regs)) {
printk("%s NIP: [%016lx] PID: %d Comm: %s\n", level,
regs->nip, current->pid, current->comm);
} else {
printk("%s NIP [%016lx]: %pS\n", level, regs->nip,
(void *)regs->nip);
}
printk("%s Initiator: %s\n", level,
VAL_TO_STRING(initiators, initiator));
switch (error_type) {
case MC_ERROR_TYPE_UE:
printk("%s Error type: %s [%s]\n", level,
VAL_TO_STRING(mc_err_types, error_type),
VAL_TO_STRING(mc_ue_types, err_sub_type));
break;
case MC_ERROR_TYPE_SLB:
printk("%s Error type: %s [%s]\n", level,
VAL_TO_STRING(mc_err_types, error_type),
VAL_TO_STRING(mc_slb_types, err_sub_type));
break;
case MC_ERROR_TYPE_ERAT:
case MC_ERROR_TYPE_TLB:
printk("%s Error type: %s [%s]\n", level,
VAL_TO_STRING(mc_err_types, error_type),
VAL_TO_STRING(mc_soft_types, err_sub_type));
break;
default:
printk("%s Error type: %s\n", level,
VAL_TO_STRING(mc_err_types, error_type));
break;
}
addr = rtas_mc_get_effective_addr(mce_log);
if (addr)
printk("%s Effective address: %016llx\n", level, addr);
}
