@@ -860,17 +860,13 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
Error *local_err = NULL;
if (spapr->fwnmi_machine_check_addr == -1) {
- /*
- * This implies that we have hit a machine check either when the
- * guest has not registered FWNMI (i.e., "ibm,nmi-register" not
- * called) or between system reset and "ibm,nmi-register".
- * Fall back to the old machine check behavior in such cases.
- */
+ /* Non-FWNMI case, deliver it like an architected CPU interrupt. */
cs->exception_index = POWERPC_EXCP_MCHECK;
ppc_cpu_do_interrupt(cs);
return;
}
+ /* Wait for FWNMI interlock. */
while (spapr->fwnmi_machine_check_interlock != -1) {
/*
* Check whether the same CPU got machine check error
@@ -882,8 +878,13 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
return;
}
qemu_cond_wait_iothread(&spapr->fwnmi_machine_check_interlock_cond);
- /* Meanwhile if the system is reset, then just return */
if (spapr->fwnmi_machine_check_addr == -1) {
+ /*
+ * If the machine was reset while waiting for the interlock,
+ * abort the delivery. The machine check applies to a context
+ * that no longer exists, so it wouldn't make sense to deliver
+ * it now.
+ */
return;
}
}
@@ -894,7 +895,9 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
* We don't want to abort so we let the migration to continue.
* In a rare case, the machine check handler will run on the target.
* Though this is not preferable, it is better than aborting
- * the migration or killing the VM.
+ * the migration or killing the VM. It is okay to call
+ * migrate_del_blocker on a blocker that was not added (which the
+ * nmi-interlock handler would do when it's called after this).
*/
warn_report("Received a fwnmi while migration was in progress");
}