[PATCH v15 6/7] migration: Include migration support for machine check handling

[Ganesh Goudar]

From: Aravinda Prasad <address@hidden>

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 these errors are specific to the source
hardware and is irrelevant on the target hardware.

[Do not set FWNMI cap in post_load, now its done in .apply hook]
Signed-off-by: Ganesh Goudar <address@hidden>
Signed-off-by: Aravinda Prasad <address@hidden>
---
 hw/ppc/spapr.c         | 41 +++++++++++++++++++++++++++++++++++++++++
 hw/ppc/spapr_events.c  | 16 +++++++++++++++-
 hw/ppc/spapr_rtas.c    |  2 ++
 include/hw/ppc/spapr.h |  2 ++
 4 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index b7b4196545..eb267d4c43 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -46,6 +46,7 @@
 #include "migration/qemu-file-types.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"
@@ -1830,6 +1831,8 @@ static void spapr_machine_reset(MachineState *machine)
 
     /* 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)
@@ -2120,6 +2123,43 @@ 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 int spapr_fwnmi_pre_save(void *opaque)
+{
+    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
+
+    /*
+     * With -only-migratable QEMU option, we cannot block migration.
+     * Hence check if machine check handling is in progress and print
+     * a warning message.
+     */
+    if (spapr->mc_status != -1) {
+        warn_report("A machine check is being handled during migration. The"
+                "handler may run and log hardware error on the destination");
+    }
+
+    return 0;
+}
+
+static const VMStateDescription vmstate_spapr_machine_check = {
+    .name = "spapr_machine_check",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = spapr_fwnmi_needed,
+    .pre_save = spapr_fwnmi_pre_save,
+    .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,
@@ -2153,6 +2193,7 @@ static const VMStateDescription vmstate_spapr = {
         &vmstate_spapr_dtb,
         &vmstate_spapr_cap_large_decr,
         &vmstate_spapr_cap_ccf_assist,
+        &vmstate_spapr_machine_check,
         NULL
     }
 };
diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index 5624bdac6c..ff34c2645a 100644
--- a/hw/ppc/spapr_events.c
+++ b/hw/ppc/spapr_events.c
@@ -43,6 +43,7 @@
 #include "qemu/main-loop.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
@@ -842,6 +843,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
 {
     SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
     CPUState *cs = CPU(cpu);
+    int ret;
+    Error *local_err = NULL;
 
     if (spapr->guest_machine_check_addr == -1) {
         /*
@@ -871,8 +874,19 @@ void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
             return;
         }
     }
-    spapr->mc_status = cpu->vcpu_id;
 
+    ret = migrate_add_blocker(spapr->fwnmi_migration_blocker, &local_err);
+    if (ret == -EBUSY) {
+        /*
+         * 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.
+         */
+        warn_report_err(local_err);
+    }
+
+    spapr->mc_status = cpu->vcpu_id;
     spapr_mce_dispatch_elog(cpu, recovered);
 }
 
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index b56953841a..c652ec3caa 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -50,6 +50,7 @@
 #include "hw/ppc/fdt.h"
 #include "target/ppc/mmu-hash64.h"
 #include "target/ppc/mmu-book3s-v3.h"
+#include "migration/blocker.h"
 
 static void rtas_display_character(PowerPCCPU *cpu, SpaprMachineState *spapr,
                                    uint32_t token, uint32_t nargs,
@@ -446,6 +447,7 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,
      */
     spapr->mc_status = -1;
     qemu_cond_signal(&spapr->mc_delivery_cond);
+    migrate_del_blocker(spapr->fwnmi_migration_blocker);
     rtas_st(rets, 0, RTAS_OUT_SUCCESS);
 }
 
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index dada821d21..ea7625e438 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -217,6 +217,8 @@ struct SpaprMachineState {
 
     unsigned gpu_numa_id;
     SpaprTpmProxy *tpm_proxy;
+
+    Error *fwnmi_migration_blocker;
 };
 
 #define H_SUCCESS         0
-- 
2.17.2