This patch includes migration support for machine check handling. Especially this patch blocks VM migration requests until the machine check error handling is complete as (i) these errors are specific to the source hardware and is irrelevant on the target hardware, (ii) these errors cause data corruption and should be handled before migration.
Signed-off-by: Aravinda Prasad <aravi...@linux.vnet.ibm.com> --- hw/ppc/spapr.c | 27 +++++++++++++++++++++++++++ hw/ppc/spapr_events.c | 14 ++++++++++++++ include/hw/ppc/spapr.h | 2 ++ 3 files changed, 43 insertions(+) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index d61905b..3d6d139 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -42,6 +42,7 @@ #include "migration/misc.h" #include "migration/global_state.h" #include "migration/register.h" +#include "migration/blocker.h" #include "mmu-hash64.h" #include "mmu-book3s-v3.h" #include "cpu-models.h" @@ -1812,6 +1813,8 @@ static void spapr_machine_reset(void) /* Signal all vCPUs waiting on this condition */ qemu_cond_broadcast(&spapr->mc_delivery_cond); + + migrate_del_blocker(spapr->fwnmi_migration_blocker); } static void spapr_create_nvram(SpaprMachineState *spapr) @@ -2102,6 +2105,25 @@ static const VMStateDescription vmstate_spapr_dtb = { }, }; +static bool spapr_fwnmi_needed(void *opaque) +{ + SpaprMachineState *spapr = (SpaprMachineState *)opaque; + + return spapr->guest_machine_check_addr != -1; +} + +static const VMStateDescription vmstate_spapr_machine_check = { + .name = "spapr_machine_check", + .version_id = 1, + .minimum_version_id = 1, + .needed = spapr_fwnmi_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(guest_machine_check_addr, SpaprMachineState), + VMSTATE_INT32(mc_status, SpaprMachineState), + VMSTATE_END_OF_LIST() + }, +}; + static const VMStateDescription vmstate_spapr = { .name = "spapr", .version_id = 3, @@ -2135,6 +2157,7 @@ static const VMStateDescription vmstate_spapr = { &vmstate_spapr_dtb, &vmstate_spapr_cap_large_decr, &vmstate_spapr_cap_ccf_assist, + &vmstate_spapr_machine_check, NULL } }; @@ -2919,6 +2942,10 @@ static void spapr_machine_init(MachineState *machine) /* Resize rtas blob to accommodate error log */ spapr->rtas_size = RTAS_ERROR_LOG_MAX; + + /* Create the error string for live migration blocker */ + error_setg(&spapr->fwnmi_migration_blocker, + "Live migration not supported during machine check handling"); } spapr->rtas_blob = g_malloc(spapr->rtas_size); diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index 51c052e..f8ce7f0 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -41,6 +41,7 @@ #include "qemu/bcd.h" #include "hw/ppc/spapr_ovec.h" #include <libfdt.h> +#include "migration/blocker.h" #define RTAS_LOG_VERSION_MASK 0xff000000 #define RTAS_LOG_VERSION_6 0x06000000 @@ -857,6 +858,19 @@ static void spapr_mce_dispatch_elog(PowerPCCPU *cpu, bool recovered) void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered) { SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + int ret; + Error *local_err = NULL; + + ret = migrate_add_blocker(spapr->fwnmi_migration_blocker, &local_err); + if (ret < 0) { + /* + * We don't want to abort and let the migration to continue. In a + * rare case, the machine check handler will run on the target + * hardware. Though this is not preferable, it is better than aborting + * the migration or killing the VM. + */ + warn_report_err(local_err); + } while (spapr->mc_status != -1) { /* diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index debb57b..0dedf0a 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -214,6 +214,8 @@ struct SpaprMachineState { SpaprCapabilities def, eff, mig; unsigned gpu_numa_id; + + Error *fwnmi_migration_blocker; }; #define H_SUCCESS 0