[Qemu-devel] [PATCH v3 06/15] spapr/xive: add migration support for KVM

[Cédric Le Goater]

When the VM is stopped, the VM state handler stabilizes the XIVE IC
and marks the EQ pages dirty. These are then transferred to destination
before the transfer of the device vmstates starts.

The SpaprXive interrupt controller model captures the XIVE internal
tables, EAT and ENDT and the XiveTCTX model does the same for the
thread interrupt context registers.

At restart, the SpaprXive 'post_load' method restores all the XIVE
states. It is called by the sPAPR machine 'post_load' method, when all
XIVE states have been transferred and loaded.

Finally, the source states are restored in the VM change state handler
when the machine reaches the running state.

Signed-off-by: Cédric Le Goater <address@hidden>
Reviewed-by: David Gibson <address@hidden>
---

 Changes since v2:

 - added xive_end_is_valid() check

include/hw/ppc/spapr_xive.h |  3 ++
 include/hw/ppc/xive.h       |  1 +
 hw/intc/spapr_xive.c        | 24 ++++++++++
 hw/intc/spapr_xive_kvm.c    | 95 ++++++++++++++++++++++++++++++++++++-
 hw/intc/xive.c              | 17 +++++++
 hw/ppc/spapr_irq.c          |  2 +-
 6 files changed, 140 insertions(+), 2 deletions(-)

diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h
index 734662c12a10..04294b0ca266 100644
--- a/include/hw/ppc/spapr_xive.h
+++ b/include/hw/ppc/spapr_xive.h
@@ -55,6 +55,7 @@ typedef struct SpaprXive {
 bool spapr_xive_irq_claim(SpaprXive *xive, uint32_t lisn, bool lsi);
 bool spapr_xive_irq_free(SpaprXive *xive, uint32_t lisn);
 void spapr_xive_pic_print_info(SpaprXive *xive, Monitor *mon);
+int spapr_xive_post_load(SpaprXive *xive, int version_id);
 
 void spapr_xive_hcall_init(SpaprMachineState *spapr);
 void spapr_dt_xive(SpaprMachineState *spapr, uint32_t nr_servers, void *fdt,
@@ -83,5 +84,7 @@ void kvmppc_xive_get_queue_config(SpaprXive *xive, uint8_t 
end_blk,
                                  uint32_t end_idx, XiveEND *end,
                                  Error **errp);
 void kvmppc_xive_synchronize_state(SpaprXive *xive, Error **errp);
+int kvmppc_xive_pre_save(SpaprXive *xive);
+int kvmppc_xive_post_load(SpaprXive *xive, int version_id);
 
 #endif /* PPC_SPAPR_XIVE_H */
diff --git a/include/hw/ppc/xive.h b/include/hw/ppc/xive.h
index 78c919c4a590..edb8937f17fb 100644
--- a/include/hw/ppc/xive.h
+++ b/include/hw/ppc/xive.h
@@ -436,5 +436,6 @@ void kvmppc_xive_source_reset(XiveSource *xsrc, Error 
**errp);
 void kvmppc_xive_source_set_irq(void *opaque, int srcno, int val);
 void kvmppc_xive_cpu_connect(XiveTCTX *tctx, Error **errp);
 void kvmppc_xive_cpu_synchronize_state(XiveTCTX *tctx, Error **errp);
+void kvmppc_xive_cpu_get_state(XiveTCTX *tctx, Error **errp);
 
 #endif /* PPC_XIVE_H */
diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c
index 4d07140f1078..a3cbbdf7aff0 100644
--- a/hw/intc/spapr_xive.c
+++ b/hw/intc/spapr_xive.c
@@ -471,10 +471,34 @@ static const VMStateDescription vmstate_spapr_xive_eas = {
     },
 };
 
+static int vmstate_spapr_xive_pre_save(void *opaque)
+{
+    if (kvm_irqchip_in_kernel()) {
+        return kvmppc_xive_pre_save(SPAPR_XIVE(opaque));
+    }
+
+    return 0;
+}
+
+/*
+ * Called by the sPAPR IRQ backend 'post_load' method at the machine
+ * level.
+ */
+int spapr_xive_post_load(SpaprXive *xive, int version_id)
+{
+    if (kvm_irqchip_in_kernel()) {
+        return kvmppc_xive_post_load(xive, version_id);
+    }
+
+    return 0;
+}
+
 static const VMStateDescription vmstate_spapr_xive = {
     .name = TYPE_SPAPR_XIVE,
     .version_id = 1,
     .minimum_version_id = 1,
+    .pre_save = vmstate_spapr_xive_pre_save,
+    .post_load = NULL, /* handled at the machine level */
     .fields = (VMStateField[]) {
         VMSTATE_UINT32_EQUAL(nr_irqs, SpaprXive, NULL),
         VMSTATE_STRUCT_VARRAY_POINTER_UINT32(eat, SpaprXive, nr_irqs,
diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c
index a011d415ee51..2fe0106f82a8 100644
--- a/hw/intc/spapr_xive_kvm.c
+++ b/hw/intc/spapr_xive_kvm.c
@@ -15,6 +15,7 @@
 #include "sysemu/cpus.h"
 #include "sysemu/kvm.h"
 #include "hw/ppc/spapr.h"
+#include "hw/ppc/spapr_cpu_core.h"
 #include "hw/ppc/spapr_xive.h"
 #include "hw/ppc/xive.h"
 #include "kvm_ppc.h"
@@ -60,7 +61,24 @@ static void kvm_cpu_enable(CPUState *cs)
 /*
  * XIVE Thread Interrupt Management context (KVM)
  */
-static void kvmppc_xive_cpu_get_state(XiveTCTX *tctx, Error **errp)
+
+static void kvmppc_xive_cpu_set_state(XiveTCTX *tctx, Error **errp)
+{
+    uint64_t state[2];
+    int ret;
+
+    /* word0 and word1 of the OS ring. */
+    state[0] = *((uint64_t *) &tctx->regs[TM_QW1_OS]);
+
+    ret = kvm_set_one_reg(tctx->cs, KVM_REG_PPC_VP_STATE, state);
+    if (ret != 0) {
+        error_setg_errno(errp, errno,
+                         "XIVE: could not restore KVM state of CPU %ld",
+                         kvm_arch_vcpu_id(tctx->cs));
+    }
+}
+
+void kvmppc_xive_cpu_get_state(XiveTCTX *tctx, Error **errp)
 {
     uint64_t state[2] = { 0 };
     int ret;
@@ -532,6 +550,81 @@ void kvmppc_xive_synchronize_state(SpaprXive *xive, Error 
**errp)
     kvmppc_xive_get_queues(xive, errp);
 }
 
+/*
+ * The SpaprXive 'pre_save' method is called by the vmstate handler of
+ * the SpaprXive model, after the XIVE controller is synced in the VM
+ * change handler.
+ */
+int kvmppc_xive_pre_save(SpaprXive *xive)
+{
+    Error *local_err = NULL;
+
+    /* EAT: there is no extra state to query from KVM */
+
+    /* ENDT */
+    kvmppc_xive_get_queues(xive, &local_err);
+    if (local_err) {
+        error_report_err(local_err);
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * The SpaprXive 'post_load' method is not called by a vmstate
+ * handler. It is called at the sPAPR machine level at the end of the
+ * migration sequence by the sPAPR IRQ backend 'post_load' method,
+ * when all XIVE states have been transferred and loaded.
+ */
+int kvmppc_xive_post_load(SpaprXive *xive, int version_id)
+{
+    Error *local_err = NULL;
+    CPUState *cs;
+    int i;
+
+    /* Restore the ENDT first. The targetting depends on it. */
+    for (i = 0; i < xive->nr_ends; i++) {
+        if (!xive_end_is_valid(&xive->endt[i])) {
+            continue;
+        }
+
+        kvmppc_xive_set_queue_config(xive, SPAPR_XIVE_BLOCK_ID, i,
+                                     &xive->endt[i], &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
+    }
+
+    /* Restore the EAT */
+    for (i = 0; i < xive->nr_irqs; i++) {
+        if (!xive_eas_is_valid(&xive->eat[i])) {
+            continue;
+        }
+
+        kvmppc_xive_set_source_config(xive, i, &xive->eat[i], &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
+    }
+
+    /* Restore the thread interrupt contexts */
+    CPU_FOREACH(cs) {
+        PowerPCCPU *cpu = POWERPC_CPU(cs);
+
+        kvmppc_xive_cpu_set_state(spapr_cpu_state(cpu)->tctx, &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
+    }
+
+    /* The source states will be restored when the machine starts running */
+    return 0;
+}
+
 static void *kvmppc_xive_mmap(SpaprXive *xive, int pgoff, size_t len,
                               Error **errp)
 {
diff --git a/hw/intc/xive.c b/hw/intc/xive.c
index 65cb772676a5..901689b0f015 100644
--- a/hw/intc/xive.c
+++ b/hw/intc/xive.c
@@ -582,10 +582,27 @@ static void xive_tctx_unrealize(DeviceState *dev, Error 
**errp)
     qemu_unregister_reset(xive_tctx_reset, dev);
 }
 
+static int vmstate_xive_tctx_pre_save(void *opaque)
+{
+    Error *local_err = NULL;
+
+    if (kvm_irqchip_in_kernel()) {
+        kvmppc_xive_cpu_get_state(XIVE_TCTX(opaque), &local_err);
+        if (local_err) {
+            error_report_err(local_err);
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
 static const VMStateDescription vmstate_xive_tctx = {
     .name = TYPE_XIVE_TCTX,
     .version_id = 1,
     .minimum_version_id = 1,
+    .pre_save = vmstate_xive_tctx_pre_save,
+    .post_load = NULL, /* handled by the sPAPRxive model */
     .fields = (VMStateField[]) {
         VMSTATE_BUFFER(regs, XiveTCTX),
         VMSTATE_END_OF_LIST()
diff --git a/hw/ppc/spapr_irq.c b/hw/ppc/spapr_irq.c
index ec60d0a5ef74..f6db48b4da79 100644
--- a/hw/ppc/spapr_irq.c
+++ b/hw/ppc/spapr_irq.c
@@ -365,7 +365,7 @@ static void 
spapr_irq_cpu_intc_create_xive(SpaprMachineState *spapr,
 
 static int spapr_irq_post_load_xive(SpaprMachineState *spapr, int version_id)
 {
-    return 0;
+    return spapr_xive_post_load(spapr->xive, version_id);
 }
 
 static void spapr_irq_reset_xive(SpaprMachineState *spapr, Error **errp)
-- 
2.20.1