[Qemu-devel] [PATCH v6 6/6] migration: Block migration while handling machine check

[Aravinda Prasad]

Block 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_events.c  |   17 +++++++++++++++++
 hw/ppc/spapr_rtas.c    |    4 ++++
 include/hw/ppc/spapr.h |    3 +++
 3 files changed, 24 insertions(+)

diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index 69e183d..0e90aba 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
@@ -866,6 +867,22 @@ static void spapr_mce_build_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;
+
+    error_setg(&spapr->migration_blocker,
+            "Live migration not supported during machine check handling");
+    ret = migrate_add_blocker(spapr->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.
+         */
+        error_free(spapr->migration_blocker);
+        fprintf(stderr, "Warning: Machine check during VM migration\n");
+    }
 
     while (spapr->mc_status != -1) {
         /*
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index aadd241..b2cad40 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -50,6 +50,7 @@
 #include "target/ppc/mmu-hash64.h"
 #include "target/ppc/mmu-book3s-v3.h"
 #include "kvm_ppc.h"
+#include "migration/blocker.h"
 
 static void rtas_display_character(PowerPCCPU *cpu, sPAPRMachineState *spapr,
                                    uint32_t token, uint32_t nargs,
@@ -391,6 +392,9 @@ static void rtas_ibm_nmi_interlock(PowerPCCPU *cpu,
         spapr->mc_status = -1;
         qemu_cond_signal(&spapr->mc_delivery_cond);
         rtas_st(rets, 0, RTAS_OUT_SUCCESS);
+        migrate_del_blocker(spapr->migration_blocker);
+        error_free(spapr->migration_blocker);
+        spapr->migration_blocker = NULL;
     }
 }
 
diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 3088e7e..00b551b 100644
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -10,6 +10,7 @@
 #include "hw/ppc/spapr_irq.h"
 #include "hw/ppc/spapr_xive.h"  /* For sPAPRXive */
 #include "hw/ppc/xics.h"        /* For ICSState */
+#include "qapi/error.h"
 
 struct VIOsPAPRBus;
 struct sPAPRPHBState;
@@ -200,6 +201,8 @@ struct sPAPRMachineState {
 
     bool cmd_line_caps[SPAPR_CAP_NUM];
     sPAPRCapabilities def, eff, mig;
+
+    Error *migration_blocker;
 };
 
 #define H_SUCCESS         0