@@ -395,7 +395,6 @@ static int opal_recover_mce(struct pt_regs *regs,
struct machine_check_event *evt)
{
int recovered = 0;
- uint64_t ea = get_mce_fault_addr(evt);
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
@@ -404,26 +403,17 @@ static int opal_recover_mce(struct pt_regs *regs,
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
recovered = 1;
- } else if (ea && !is_kernel_addr(ea)) {
+ } else if (evt->severity == MCE_SEV_FATAL) {
+ /* Async or otherwise fatal machine check */
+ pr_err("Machine check interrupt unrecoverable\n");
+ recovered = 0;
+ } else if (user_mode(regs) && !is_global_init(current)) {
/*
- * Faulting address is not in kernel text. We should be fine.
- * We need to find which process uses this address.
* For now, kill the task if we have received exception when
* in userspace.
*
* TODO: Queue up this address for hwpoisioning later.
*/
- if (user_mode(regs) && !is_global_init(current)) {
- _exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
- recovered = 1;
- } else
- recovered = 0;
- } else if (user_mode(regs) && !is_global_init(current) &&
- evt->severity == MCE_SEV_ERROR_SYNC) {
- /*
- * If we have received a synchronous error when in userspace
- * kill the task.
- */
_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
recovered = 1;
}
Asynchronous machine checks don't correspond to the instruction or even task that is currently running. Therefore only synchronous machine checks should attempt to kill the currently running task to recover. Signed-off-by: Nicholas Piggin <npiggin@gmail.com> --- arch/powerpc/platforms/powernv/opal.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-)