summary refs log tree commit diff stats
path: root/hw/ppc
diff options
context:
space:
mode:
Diffstat (limited to 'hw/ppc')
-rw-r--r--hw/ppc/mpc8544_guts.c3
-rw-r--r--hw/ppc/pnv.c198
-rw-r--r--hw/ppc/pnv_core.c8
-rw-r--r--hw/ppc/pnv_xscom.c5
-rw-r--r--hw/ppc/ppc.c10
-rw-r--r--hw/ppc/ppce500_spin.c3
-rw-r--r--hw/ppc/sam460ex.c24
-rw-r--r--hw/ppc/spapr.c106
-rw-r--r--hw/ppc/spapr_caps.c61
-rw-r--r--hw/ppc/spapr_cpu_core.c8
-rw-r--r--hw/ppc/spapr_hcall.c24
-rw-r--r--hw/ppc/spapr_nested.c1556
12 files changed, 1873 insertions, 133 deletions
diff --git a/hw/ppc/mpc8544_guts.c b/hw/ppc/mpc8544_guts.c
index a26e83d048..e3540b0281 100644
--- a/hw/ppc/mpc8544_guts.c
+++ b/hw/ppc/mpc8544_guts.c
@@ -71,8 +71,7 @@ static uint64_t mpc8544_guts_read(void *opaque, hwaddr addr,
                                   unsigned size)
 {
     uint32_t value = 0;
-    PowerPCCPU *cpu = POWERPC_CPU(current_cpu);
-    CPUPPCState *env = &cpu->env;
+    CPUPPCState *env = cpu_env(current_cpu);
 
     addr &= MPC8544_GUTS_MMIO_SIZE - 1;
     switch (addr) {
diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c
index 0b47b92baa..6e3a5ccdec 100644
--- a/hw/ppc/pnv.c
+++ b/hw/ppc/pnv.c
@@ -133,7 +133,7 @@ static int get_cpus_node(void *fdt)
  * device tree, used in XSCOM to address cores and in interrupt
  * servers.
  */
-static void pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
+static int pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
 {
     PowerPCCPU *cpu = pc->threads[0];
     CPUState *cs = CPU(cpu);
@@ -141,32 +141,31 @@ static void pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
     int smt_threads = CPU_CORE(pc)->nr_threads;
     CPUPPCState *env = &cpu->env;
     PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
+    PnvChipClass *pnv_cc = PNV_CHIP_GET_CLASS(chip);
     g_autofree uint32_t *servers_prop = g_new(uint32_t, smt_threads);
     int i;
+    uint32_t pir;
     uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                        0xffffffff, 0xffffffff};
     uint32_t tbfreq = PNV_TIMEBASE_FREQ;
     uint32_t cpufreq = 1000000000;
     uint32_t page_sizes_prop[64];
     size_t page_sizes_prop_size;
-    const uint8_t pa_features[] = { 24, 0,
-                                    0xf6, 0x3f, 0xc7, 0xc0, 0x80, 0xf0,
-                                    0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
-                                    0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
-                                    0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
     int offset;
     char *nodename;
     int cpus_offset = get_cpus_node(fdt);
 
-    nodename = g_strdup_printf("%s@%x", dc->fw_name, pc->pir);
+    pir = pnv_cc->chip_pir(chip, pc->hwid, 0);
+
+    nodename = g_strdup_printf("%s@%x", dc->fw_name, pir);
     offset = fdt_add_subnode(fdt, cpus_offset, nodename);
     _FDT(offset);
     g_free(nodename);
 
     _FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id", chip->chip_id)));
 
-    _FDT((fdt_setprop_cell(fdt, offset, "reg", pc->pir)));
-    _FDT((fdt_setprop_cell(fdt, offset, "ibm,pir", pc->pir)));
+    _FDT((fdt_setprop_cell(fdt, offset, "reg", pir)));
+    _FDT((fdt_setprop_cell(fdt, offset, "ibm,pir", pir)));
     _FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));
 
     _FDT((fdt_setprop_cell(fdt, offset, "cpu-version", env->spr[SPR_PVR])));
@@ -236,20 +235,21 @@ static void pnv_dt_core(PnvChip *chip, PnvCore *pc, void *fdt)
                            page_sizes_prop, page_sizes_prop_size)));
     }
 
-    _FDT((fdt_setprop(fdt, offset, "ibm,pa-features",
-                       pa_features, sizeof(pa_features))));
-
     /* Build interrupt servers properties */
     for (i = 0; i < smt_threads; i++) {
-        servers_prop[i] = cpu_to_be32(pc->pir + i);
+        servers_prop[i] = cpu_to_be32(pnv_cc->chip_pir(chip, pc->hwid, i));
     }
     _FDT((fdt_setprop(fdt, offset, "ibm,ppc-interrupt-server#s",
                        servers_prop, sizeof(*servers_prop) * smt_threads)));
+
+    return offset;
 }
 
-static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t pir,
+static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t hwid,
                        uint32_t nr_threads)
 {
+    PnvChipClass *pcc = PNV_CHIP_GET_CLASS(chip);
+    uint32_t pir = pcc->chip_pir(chip, hwid, 0);
     uint64_t addr = PNV_ICP_BASE(chip) | (pir << 12);
     char *name;
     const char compat[] = "IBM,power8-icp\0IBM,ppc-xicp";
@@ -263,6 +263,7 @@ static void pnv_dt_icp(PnvChip *chip, void *fdt, uint32_t pir,
     rsize = sizeof(uint64_t) * 2 * nr_threads;
     reg = g_malloc(rsize);
     for (i = 0; i < nr_threads; i++) {
+        /* We know P8 PIR is linear with thread id */
         reg[i * 2] = cpu_to_be64(addr | ((pir + i) * 0x1000));
         reg[i * 2 + 1] = cpu_to_be64(0x1000);
     }
@@ -299,6 +300,17 @@ PnvChip *pnv_chip_add_phb(PnvChip *chip, PnvPHB *phb)
     return chip;
 }
 
+/*
+ * Same as spapr pa_features_207 except pnv always enables CI largepages bit.
+ * HTM is always enabled because TCG does implement HTM, it's just a
+ * degenerate implementation.
+ */
+static const uint8_t pa_features_207[] = { 24, 0,
+                 0xf6, 0x3f, 0xc7, 0xc0, 0x00, 0xf0,
+                 0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
+                 0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
+                 0x80, 0x00, 0x80, 0x00, 0x80, 0x00 };
+
 static void pnv_chip_power8_dt_populate(PnvChip *chip, void *fdt)
 {
     static const char compat[] = "ibm,power8-xscom\0ibm,xscom";
@@ -311,11 +323,15 @@ static void pnv_chip_power8_dt_populate(PnvChip *chip, void *fdt)
 
     for (i = 0; i < chip->nr_cores; i++) {
         PnvCore *pnv_core = chip->cores[i];
+        int offset;
+
+        offset = pnv_dt_core(chip, pnv_core, fdt);
 
-        pnv_dt_core(chip, pnv_core, fdt);
+        _FDT((fdt_setprop(fdt, offset, "ibm,pa-features",
+                           pa_features_207, sizeof(pa_features_207))));
 
         /* Interrupt Control Presenters (ICP). One per core. */
-        pnv_dt_icp(chip, fdt, pnv_core->pir, CPU_CORE(pnv_core)->nr_threads);
+        pnv_dt_icp(chip, fdt, pnv_core->hwid, CPU_CORE(pnv_core)->nr_threads);
     }
 
     if (chip->ram_size) {
@@ -323,6 +339,35 @@ static void pnv_chip_power8_dt_populate(PnvChip *chip, void *fdt)
     }
 }
 
+/*
+ * Same as spapr pa_features_300 except pnv always enables CI largepages bit.
+ */
+static const uint8_t pa_features_300[] = { 66, 0,
+    /* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: CILRG|fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
+    /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, 5: LE|CFAR|EB|LSQ */
+    0xf6, 0x3f, 0xc7, 0xc0, 0x00, 0xf0, /* 0 - 5 */
+    /* 6: DS207 */
+    0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
+    /* 16: Vector */
+    0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
+    /* 18: Vec. Scalar, 20: Vec. XOR, 22: HTM */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 18 - 23 */
+    /* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
+    /* 32: LE atomic, 34: EBB + ext EBB */
+    0x00, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
+    /* 40: Radix MMU */
+    0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 36 - 41 */
+    /* 42: PM, 44: PC RA, 46: SC vec'd */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
+    /* 48: SIMD, 50: QP BFP, 52: String */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 48 - 53 */
+    /* 54: DecFP, 56: DecI, 58: SHA */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 54 - 59 */
+    /* 60: NM atomic, 62: RNG */
+    0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
+};
+
 static void pnv_chip_power9_dt_populate(PnvChip *chip, void *fdt)
 {
     static const char compat[] = "ibm,power9-xscom\0ibm,xscom";
@@ -335,8 +380,12 @@ static void pnv_chip_power9_dt_populate(PnvChip *chip, void *fdt)
 
     for (i = 0; i < chip->nr_cores; i++) {
         PnvCore *pnv_core = chip->cores[i];
+        int offset;
 
-        pnv_dt_core(chip, pnv_core, fdt);
+        offset = pnv_dt_core(chip, pnv_core, fdt);
+
+        _FDT((fdt_setprop(fdt, offset, "ibm,pa-features",
+                           pa_features_300, sizeof(pa_features_300))));
     }
 
     if (chip->ram_size) {
@@ -346,6 +395,40 @@ static void pnv_chip_power9_dt_populate(PnvChip *chip, void *fdt)
     pnv_dt_lpc(chip, fdt, 0, PNV9_LPCM_BASE(chip), PNV9_LPCM_SIZE);
 }
 
+/*
+ * Same as spapr pa_features_31 except pnv always enables CI largepages bit,
+ * always disables copy/paste.
+ */
+static const uint8_t pa_features_31[] = { 74, 0,
+    /* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: CILRG|fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
+    /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, 5: LE|CFAR|EB|LSQ */
+    0xf6, 0x3f, 0xc7, 0xc0, 0x00, 0xf0, /* 0 - 5 */
+    /* 6: DS207 */
+    0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
+    /* 16: Vector */
+    0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
+    /* 18: Vec. Scalar, 20: Vec. XOR */
+    0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 18 - 23 */
+    /* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
+    /* 32: LE atomic, 34: EBB + ext EBB */
+    0x00, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
+    /* 40: Radix MMU */
+    0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 36 - 41 */
+    /* 42: PM, 44: PC RA, 46: SC vec'd */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
+    /* 48: SIMD, 50: QP BFP, 52: String */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 48 - 53 */
+    /* 54: DecFP, 56: DecI, 58: SHA */
+    0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 54 - 59 */
+    /* 60: NM atomic, 62: RNG */
+    0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
+    /* 68: DEXCR[SBHE|IBRTPDUS|SRAPD|NPHIE|PHIE] */
+    0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 66 - 71 */
+    /* 72: [P]HASHST/[P]HASHCHK */
+    0x80, 0x00,                         /* 72 - 73 */
+};
+
 static void pnv_chip_power10_dt_populate(PnvChip *chip, void *fdt)
 {
     static const char compat[] = "ibm,power10-xscom\0ibm,xscom";
@@ -358,8 +441,12 @@ static void pnv_chip_power10_dt_populate(PnvChip *chip, void *fdt)
 
     for (i = 0; i < chip->nr_cores; i++) {
         PnvCore *pnv_core = chip->cores[i];
+        int offset;
+
+        offset = pnv_dt_core(chip, pnv_core, fdt);
 
-        pnv_dt_core(chip, pnv_core, fdt);
+        _FDT((fdt_setprop(fdt, offset, "ibm,pa-features",
+                           pa_features_31, sizeof(pa_features_31))));
     }
 
     if (chip->ram_size) {
@@ -995,9 +1082,10 @@ static void pnv_init(MachineState *machine)
  *   25:28  Core number
  *   29:31  Thread ID
  */
-static uint32_t pnv_chip_core_pir_p8(PnvChip *chip, uint32_t core_id)
+static uint32_t pnv_chip_pir_p8(PnvChip *chip, uint32_t core_id,
+                                uint32_t thread_id)
 {
-    return (chip->chip_id << 7) | (core_id << 3);
+    return (chip->chip_id << 7) | (core_id << 3) | thread_id;
 }
 
 static void pnv_chip_power8_intc_create(PnvChip *chip, PowerPCCPU *cpu,
@@ -1049,14 +1137,37 @@ static void pnv_chip_power8_intc_print_info(PnvChip *chip, PowerPCCPU *cpu,
  *
  * We only care about the lower bits. uint32_t is fine for the moment.
  */
-static uint32_t pnv_chip_core_pir_p9(PnvChip *chip, uint32_t core_id)
+static uint32_t pnv_chip_pir_p9(PnvChip *chip, uint32_t core_id,
+                                uint32_t thread_id)
 {
-    return (chip->chip_id << 8) | (core_id << 2);
+    if (chip->nr_threads == 8) {
+        return (chip->chip_id << 8) | ((thread_id & 1) << 2) | (core_id << 3) |
+               (thread_id >> 1);
+    } else {
+        return (chip->chip_id << 8) | (core_id << 2) | thread_id;
+    }
 }
 
-static uint32_t pnv_chip_core_pir_p10(PnvChip *chip, uint32_t core_id)
+/*
+ *    0:48  Reserved - Read as zeroes
+ *   49:52  Node ID
+ *   53:55  Chip ID
+ *   56     Reserved - Read as zero
+ *   57:59  Quad ID
+ *   60     Core Chiplet Pair ID
+ *   61:63  Thread/Core Chiplet ID t0-t2
+ *
+ * We only care about the lower bits. uint32_t is fine for the moment.
+ */
+static uint32_t pnv_chip_pir_p10(PnvChip *chip, uint32_t core_id,
+                                 uint32_t thread_id)
 {
-    return (chip->chip_id << 8) | (core_id << 2);
+    if (chip->nr_threads == 8) {
+        return (chip->chip_id << 8) | ((core_id / 4) << 4) |
+               ((core_id % 2) << 3) | thread_id;
+    } else {
+        return (chip->chip_id << 8) | (core_id << 2) | thread_id;
+    }
 }
 
 static void pnv_chip_power9_intc_create(PnvChip *chip, PowerPCCPU *cpu,
@@ -1235,7 +1346,7 @@ static void pnv_chip_icp_realize(Pnv8Chip *chip8, Error **errp)
         int core_hwid = CPU_CORE(pnv_core)->core_id;
 
         for (j = 0; j < CPU_CORE(pnv_core)->nr_threads; j++) {
-            uint32_t pir = pcc->core_pir(chip, core_hwid) + j;
+            uint32_t pir = pcc->chip_pir(chip, core_hwid, j);
             PnvICPState *icp = PNV_ICP(xics_icp_get(chip8->xics, pir));
 
             memory_region_add_subregion(&chip8->icp_mmio, pir << 12,
@@ -1265,11 +1376,11 @@ static void pnv_chip_power8_realize(DeviceState *dev, Error **errp)
     }
 
     /* Processor Service Interface (PSI) Host Bridge */
-    object_property_set_int(OBJECT(&chip8->psi), "bar", PNV_PSIHB_BASE(chip),
+    object_property_set_int(OBJECT(psi8), "bar", PNV_PSIHB_BASE(chip),
                             &error_fatal);
-    object_property_set_link(OBJECT(&chip8->psi), ICS_PROP_XICS,
+    object_property_set_link(OBJECT(psi8), ICS_PROP_XICS,
                              OBJECT(chip8->xics), &error_abort);
-    if (!qdev_realize(DEVICE(&chip8->psi), NULL, errp)) {
+    if (!qdev_realize(DEVICE(psi8), NULL, errp)) {
         return;
     }
     pnv_xscom_add_subregion(chip, PNV_XSCOM_PSIHB_BASE,
@@ -1300,7 +1411,7 @@ static void pnv_chip_power8_realize(DeviceState *dev, Error **errp)
     }
     pnv_xscom_add_subregion(chip, PNV_XSCOM_OCC_BASE, &chip8->occ.xscom_regs);
     qdev_connect_gpio_out(DEVICE(&chip8->occ), 0,
-                          qdev_get_gpio_in(DEVICE(&chip8->psi), PSIHB_IRQ_OCC));
+                          qdev_get_gpio_in(DEVICE(psi8), PSIHB_IRQ_OCC));
 
     /* OCC SRAM model */
     memory_region_add_subregion(get_system_memory(), PNV_OCC_SENSOR_BASE(chip),
@@ -1348,7 +1459,7 @@ static void pnv_chip_power8e_class_init(ObjectClass *klass, void *data)
     k->chip_cfam_id = 0x221ef04980000000ull;  /* P8 Murano DD2.1 */
     k->cores_mask = POWER8E_CORE_MASK;
     k->num_phbs = 3;
-    k->core_pir = pnv_chip_core_pir_p8;
+    k->chip_pir = pnv_chip_pir_p8;
     k->intc_create = pnv_chip_power8_intc_create;
     k->intc_reset = pnv_chip_power8_intc_reset;
     k->intc_destroy = pnv_chip_power8_intc_destroy;
@@ -1372,7 +1483,7 @@ static void pnv_chip_power8_class_init(ObjectClass *klass, void *data)
     k->chip_cfam_id = 0x220ea04980000000ull; /* P8 Venice DD2.0 */
     k->cores_mask = POWER8_CORE_MASK;
     k->num_phbs = 3;
-    k->core_pir = pnv_chip_core_pir_p8;
+    k->chip_pir = pnv_chip_pir_p8;
     k->intc_create = pnv_chip_power8_intc_create;
     k->intc_reset = pnv_chip_power8_intc_reset;
     k->intc_destroy = pnv_chip_power8_intc_destroy;
@@ -1396,7 +1507,7 @@ static void pnv_chip_power8nvl_class_init(ObjectClass *klass, void *data)
     k->chip_cfam_id = 0x120d304980000000ull;  /* P8 Naples DD1.0 */
     k->cores_mask = POWER8_CORE_MASK;
     k->num_phbs = 4;
-    k->core_pir = pnv_chip_core_pir_p8;
+    k->chip_pir = pnv_chip_pir_p8;
     k->intc_create = pnv_chip_power8_intc_create;
     k->intc_reset = pnv_chip_power8_intc_reset;
     k->intc_destroy = pnv_chip_power8_intc_destroy;
@@ -1553,12 +1664,12 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp)
                             &chip9->xive.xscom_regs);
 
     /* Processor Service Interface (PSI) Host Bridge */
-    object_property_set_int(OBJECT(&chip9->psi), "bar", PNV9_PSIHB_BASE(chip),
+    object_property_set_int(OBJECT(psi9), "bar", PNV9_PSIHB_BASE(chip),
                             &error_fatal);
     /* This is the only device with 4k ESB pages */
-    object_property_set_int(OBJECT(&chip9->psi), "shift", XIVE_ESB_4K,
+    object_property_set_int(OBJECT(psi9), "shift", XIVE_ESB_4K,
                             &error_fatal);
-    if (!qdev_realize(DEVICE(&chip9->psi), NULL, errp)) {
+    if (!qdev_realize(DEVICE(psi9), NULL, errp)) {
         return;
     }
     pnv_xscom_add_subregion(chip, PNV9_XSCOM_PSIHB_BASE,
@@ -1594,7 +1705,7 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp)
     }
     pnv_xscom_add_subregion(chip, PNV9_XSCOM_OCC_BASE, &chip9->occ.xscom_regs);
     qdev_connect_gpio_out(DEVICE(&chip9->occ), 0, qdev_get_gpio_in(
-                              DEVICE(&chip9->psi), PSIHB9_IRQ_OCC));
+                              DEVICE(psi9), PSIHB9_IRQ_OCC));
 
     /* OCC SRAM model */
     memory_region_add_subregion(get_system_memory(), PNV9_OCC_SENSOR_BASE(chip),
@@ -1609,7 +1720,7 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp)
     pnv_xscom_add_subregion(chip, PNV9_XSCOM_SBE_MBOX_BASE,
                             &chip9->sbe.xscom_mbox_regs);
     qdev_connect_gpio_out(DEVICE(&chip9->sbe), 0, qdev_get_gpio_in(
-                              DEVICE(&chip9->psi), PSIHB9_IRQ_PSU));
+                              DEVICE(psi9), PSIHB9_IRQ_PSU));
 
     /* HOMER */
     object_property_set_link(OBJECT(&chip9->homer), "chip", OBJECT(chip),
@@ -1650,7 +1761,7 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp)
                                         PNV9_XSCOM_I2CM_SIZE,
                                 &chip9->i2c[i].xscom_regs);
         qdev_connect_gpio_out(DEVICE(&chip9->i2c[i]), 0,
-                              qdev_get_gpio_in(DEVICE(&chip9->psi),
+                              qdev_get_gpio_in(DEVICE(psi9),
                                                PSIHB9_IRQ_SBE_I2C));
     }
 }
@@ -1669,7 +1780,7 @@ static void pnv_chip_power9_class_init(ObjectClass *klass, void *data)
 
     k->chip_cfam_id = 0x220d104900008000ull; /* P9 Nimbus DD2.0 */
     k->cores_mask = POWER9_CORE_MASK;
-    k->core_pir = pnv_chip_core_pir_p9;
+    k->chip_pir = pnv_chip_pir_p9;
     k->intc_create = pnv_chip_power9_intc_create;
     k->intc_reset = pnv_chip_power9_intc_reset;
     k->intc_destroy = pnv_chip_power9_intc_destroy;
@@ -1981,7 +2092,7 @@ static void pnv_chip_power10_class_init(ObjectClass *klass, void *data)
 
     k->chip_cfam_id = 0x120da04900008000ull; /* P10 DD1.0 (with NX) */
     k->cores_mask = POWER10_CORE_MASK;
-    k->core_pir = pnv_chip_core_pir_p10;
+    k->chip_pir = pnv_chip_pir_p10;
     k->intc_create = pnv_chip_power10_intc_create;
     k->intc_reset = pnv_chip_power10_intc_reset;
     k->intc_destroy = pnv_chip_power10_intc_destroy;
@@ -2071,8 +2182,8 @@ static void pnv_chip_core_realize(PnvChip *chip, Error **errp)
                                 chip->nr_threads, &error_fatal);
         object_property_set_int(OBJECT(pnv_core), CPU_CORE_PROP_CORE_ID,
                                 core_hwid, &error_fatal);
-        object_property_set_int(OBJECT(pnv_core), "pir",
-                                pcc->core_pir(chip, core_hwid), &error_fatal);
+        object_property_set_int(OBJECT(pnv_core), "hwid", core_hwid,
+                                &error_fatal);
         object_property_set_int(OBJECT(pnv_core), "hrmor", pnv->fw_load_addr,
                                 &error_fatal);
         object_property_set_link(OBJECT(pnv_core), "chip", OBJECT(chip),
@@ -2412,8 +2523,7 @@ static void pnv_machine_set_hb(Object *obj, bool value, Error **errp)
 
 static void pnv_cpu_do_nmi_on_cpu(CPUState *cs, run_on_cpu_data arg)
 {
-    PowerPCCPU *cpu = POWERPC_CPU(cs);
-    CPUPPCState *env = &cpu->env;
+    CPUPPCState *env = cpu_env(cs);
 
     cpu_synchronize_state(cs);
     ppc_cpu_do_system_reset(cs);
diff --git a/hw/ppc/pnv_core.c b/hw/ppc/pnv_core.c
index 8c7afe037f..f40ab721d6 100644
--- a/hw/ppc/pnv_core.c
+++ b/hw/ppc/pnv_core.c
@@ -226,7 +226,7 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
                                  int thread_index)
 {
     CPUPPCState *env = &cpu->env;
-    int core_pir;
+    int core_hwid;
     ppc_spr_t *pir = &env->spr_cb[SPR_PIR];
     ppc_spr_t *tir = &env->spr_cb[SPR_TIR];
     Error *local_err = NULL;
@@ -242,10 +242,10 @@ static void pnv_core_cpu_realize(PnvCore *pc, PowerPCCPU *cpu, Error **errp,
         return;
     }
 
-    core_pir = object_property_get_uint(OBJECT(pc), "pir", &error_abort);
+    core_hwid = object_property_get_uint(OBJECT(pc), "hwid", &error_abort);
 
     tir->default_value = thread_index;
-    pir->default_value = core_pir + thread_index;
+    pir->default_value = pcc->chip_pir(pc->chip, core_hwid, thread_index);
 
     /* Set time-base frequency to 512 MHz */
     cpu_ppc_tb_init(env, PNV_TIMEBASE_FREQ);
@@ -342,7 +342,7 @@ static void pnv_core_unrealize(DeviceState *dev)
 }
 
 static Property pnv_core_properties[] = {
-    DEFINE_PROP_UINT32("pir", PnvCore, pir, 0),
+    DEFINE_PROP_UINT32("hwid", PnvCore, hwid, 0),
     DEFINE_PROP_UINT64("hrmor", PnvCore, hrmor, 0),
     DEFINE_PROP_LINK("chip", PnvCore, chip, TYPE_PNV_CHIP, PnvChip *),
     DEFINE_PROP_END_OF_LIST(),
diff --git a/hw/ppc/pnv_xscom.c b/hw/ppc/pnv_xscom.c
index 805b1d0c87..a17816d072 100644
--- a/hw/ppc/pnv_xscom.c
+++ b/hw/ppc/pnv_xscom.c
@@ -44,15 +44,12 @@ static void xscom_complete(CPUState *cs, uint64_t hmer_bits)
      * passed for the cpu, and no CPU completion is generated.
      */
     if (cs) {
-        PowerPCCPU *cpu = POWERPC_CPU(cs);
-        CPUPPCState *env = &cpu->env;
-
         /*
          * TODO: Need a CPU helper to set HMER, also handle generation
          * of HMIs
          */
         cpu_synchronize_state(cs);
-        env->spr[SPR_HMER] |= hmer_bits;
+        cpu_env(cs)->spr[SPR_HMER] |= hmer_bits;
     }
 }
 
diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c
index fadb8f5239..e6fa5580c0 100644
--- a/hw/ppc/ppc.c
+++ b/hw/ppc/ppc.c
@@ -633,6 +633,16 @@ void cpu_ppc_store_atbu (CPUPPCState *env, uint32_t value)
                      ((uint64_t)value << 32) | tb);
 }
 
+void cpu_ppc_increase_tb_by_offset(CPUPPCState *env, int64_t offset)
+{
+    env->tb_env->tb_offset += offset;
+}
+
+void cpu_ppc_decrease_tb_by_offset(CPUPPCState *env, int64_t offset)
+{
+    env->tb_env->tb_offset -= offset;
+}
+
 uint64_t cpu_ppc_load_vtb(CPUPPCState *env)
 {
     ppc_tb_t *tb_env = env->tb_env;
diff --git a/hw/ppc/ppce500_spin.c b/hw/ppc/ppce500_spin.c
index bbce63e8a4..dfbe759481 100644
--- a/hw/ppc/ppce500_spin.c
+++ b/hw/ppc/ppce500_spin.c
@@ -90,8 +90,7 @@ static void mmubooke_create_initial_mapping(CPUPPCState *env,
 
 static void spin_kick(CPUState *cs, run_on_cpu_data data)
 {
-    PowerPCCPU *cpu = POWERPC_CPU(cs);
-    CPUPPCState *env = &cpu->env;
+    CPUPPCState *env = cpu_env(cs);
     SpinInfo *curspin = data.host_ptr;
     hwaddr map_size = 64 * MiB;
     hwaddr map_start;
diff --git a/hw/ppc/sam460ex.c b/hw/ppc/sam460ex.c
index 7e34b6c5e0..d42b677898 100644
--- a/hw/ppc/sam460ex.c
+++ b/hw/ppc/sam460ex.c
@@ -33,6 +33,7 @@
 #include "hw/char/serial.h"
 #include "hw/i2c/ppc4xx_i2c.h"
 #include "hw/i2c/smbus_eeprom.h"
+#include "hw/ide/pci.h"
 #include "hw/usb/hcd-ehci.h"
 #include "hw/ppc/fdt.h"
 #include "hw/qdev-properties.h"
@@ -449,15 +450,27 @@ static void sam460ex_init(MachineState *machine)
 
     /* PCI devices */
     pci_create_simple(pci_bus, PCI_DEVFN(6, 0), "sm501");
-    /* SoC has a single SATA port but we don't emulate that yet
+    /*
+     * SoC has a single SATA port but we don't emulate that
      * However, firmware and usual clients have driver for SiI311x
-     * so add one for convenience by default */
+     * PCI SATA card so add one for convenience by default
+     */
     if (defaults_enabled()) {
-        pci_create_simple(pci_bus, -1, "sii3112");
+        PCIIDEState *s = PCI_IDE(pci_create_simple(pci_bus, -1, "sii3112"));
+        DriveInfo *di;
+
+        di = drive_get_by_index(IF_IDE, 0);
+        if (di) {
+            ide_bus_create_drive(&s->bus[0], 0, di);
+        }
+        /* Use index 2 only if 1 does not exist, this allows -cdrom */
+        di = drive_get_by_index(IF_IDE, 1) ?: drive_get_by_index(IF_IDE, 2);
+        if (di) {
+            ide_bus_create_drive(&s->bus[1], 0, di);
+        }
     }
 
-    /* SoC has 4 UARTs
-     * but board has only one wired and two are present in fdt */
+    /* SoC has 4 UARTs but board has only one wired and two described in fdt */
     if (serial_hd(0) != NULL) {
         serial_mm_init(get_system_memory(), 0x4ef600300, 0,
                        qdev_get_gpio_in(uic[1], 1),
@@ -531,6 +544,7 @@ static void sam460ex_machine_init(MachineClass *mc)
 {
     mc->desc = "aCube Sam460ex";
     mc->init = sam460ex_init;
+    mc->block_default_type = IF_IDE;
     mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("460exb");
     mc->default_ram_size = 512 * MiB;
     mc->default_ram_id = "ppc4xx.sdram";
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index 55263f0815..c417f9dd52 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -233,29 +233,40 @@ static void spapr_dt_pa_features(SpaprMachineState *spapr,
                                  PowerPCCPU *cpu,
                                  void *fdt, int offset)
 {
+    /*
+     * SSO (SAO) ordering is supported on KVM and thread=single hosts,
+     * but not MTTCG, so disable it. To advertise it, a cap would have
+     * to be added, or support implemented for MTTCG.
+     *
+     * Copy/paste is not supported by TCG, so it is not advertised. KVM
+     * can execute them but it has no accelerator drivers which are usable,
+     * so there isn't much need for it anyway.
+     */
+
+    /* These should be kept in sync with pnv */
     uint8_t pa_features_206[] = { 6, 0,
-        0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
+        0xf6, 0x1f, 0xc7, 0x00, 0x00, 0xc0 };
     uint8_t pa_features_207[] = { 24, 0,
-        0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0,
+        0xf6, 0x1f, 0xc7, 0xc0, 0x00, 0xf0,
         0x80, 0x00, 0x00, 0x00, 0x00, 0x00,
         0x00, 0x00, 0x00, 0x00, 0x80, 0x00,
         0x80, 0x00, 0x80, 0x00, 0x00, 0x00 };
     uint8_t pa_features_300[] = { 66, 0,
         /* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
-        /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, SSO, 5: LE|CFAR|EB|LSQ */
-        0xf6, 0x1f, 0xc7, 0xc0, 0x80, 0xf0, /* 0 - 5 */
+        /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, 5: LE|CFAR|EB|LSQ */
+        0xf6, 0x1f, 0xc7, 0xc0, 0x00, 0xf0, /* 0 - 5 */
         /* 6: DS207 */
         0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
         /* 16: Vector */
         0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
-        /* 18: Vec. Scalar, 20: Vec. XOR, 22: HTM */
+        /* 18: Vec. Scalar, 20: Vec. XOR */
         0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 18 - 23 */
         /* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
         0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
-        /* 30: MMR, 32: LE atomic, 34: EBB + ext EBB */
-        0x80, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
-        /* 36: SPR SO, 38: Copy/Paste, 40: Radix MMU */
-        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 36 - 41 */
+        /* 32: LE atomic, 34: EBB + ext EBB */
+        0x00, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
+        /* 40: Radix MMU */
+        0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 36 - 41 */
         /* 42: PM, 44: PC RA, 46: SC vec'd */
         0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
         /* 48: SIMD, 50: QP BFP, 52: String */
@@ -265,6 +276,36 @@ static void spapr_dt_pa_features(SpaprMachineState *spapr,
         /* 60: NM atomic, 62: RNG */
         0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
     };
+    /* 3.1 removes SAO, HTM support */
+    uint8_t pa_features_31[] = { 74, 0,
+        /* 0: MMU|FPU|SLB|RUN|DABR|NX, 1: fri[nzpm]|DABRX|SPRG3|SLB0|PP110 */
+        /* 2: VPM|DS205|PPR|DS202|DS206, 3: LSD|URG, 5: LE|CFAR|EB|LSQ */
+        0xf6, 0x1f, 0xc7, 0xc0, 0x00, 0xf0, /* 0 - 5 */
+        /* 6: DS207 */
+        0x80, 0x00, 0x00, 0x00, 0x00, 0x00, /* 6 - 11 */
+        /* 16: Vector */
+        0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 12 - 17 */
+        /* 18: Vec. Scalar, 20: Vec. XOR */
+        0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 18 - 23 */
+        /* 24: Ext. Dec, 26: 64 bit ftrs, 28: PM ftrs */
+        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 24 - 29 */
+        /* 32: LE atomic, 34: EBB + ext EBB */
+        0x00, 0x00, 0x80, 0x00, 0xC0, 0x00, /* 30 - 35 */
+        /* 40: Radix MMU */
+        0x00, 0x00, 0x00, 0x00, 0x80, 0x00, /* 36 - 41 */
+        /* 42: PM, 44: PC RA, 46: SC vec'd */
+        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 42 - 47 */
+        /* 48: SIMD, 50: QP BFP, 52: String */
+        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 48 - 53 */
+        /* 54: DecFP, 56: DecI, 58: SHA */
+        0x80, 0x00, 0x80, 0x00, 0x80, 0x00, /* 54 - 59 */
+        /* 60: NM atomic, 62: RNG */
+        0x80, 0x00, 0x80, 0x00, 0x00, 0x00, /* 60 - 65 */
+        /* 68: DEXCR[SBHE|IBRTPDUS|SRAPD|NPHIE|PHIE] */
+        0x00, 0x00, 0xce, 0x00, 0x00, 0x00, /* 66 - 71 */
+        /* 72: [P]HASHST/[P]HASHCHK */
+        0x80, 0x00,                         /* 72 - 73 */
+    };
     uint8_t *pa_features = NULL;
     size_t pa_size;
 
@@ -280,6 +321,10 @@ static void spapr_dt_pa_features(SpaprMachineState *spapr,
         pa_features = pa_features_300;
         pa_size = sizeof(pa_features_300);
     }
+    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0, cpu->compat_pvr)) {
+        pa_features = pa_features_31;
+        pa_size = sizeof(pa_features_31);
+    }
     if (!pa_features) {
         return;
     }
@@ -1362,7 +1407,6 @@ void spapr_init_all_lpcrs(target_ulong value, target_ulong mask)
     }
 }
 
-
 static bool spapr_get_pate(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu,
                            target_ulong lpid, ppc_v3_pate_t *entry)
 {
@@ -1375,33 +1419,16 @@ static bool spapr_get_pate(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu,
         /* Copy PATE1:GR into PATE0:HR */
         entry->dw0 = spapr->patb_entry & PATE0_HR;
         entry->dw1 = spapr->patb_entry;
-
+        return true;
     } else {
-        uint64_t patb, pats;
-
-        assert(lpid != 0);
-
-        patb = spapr->nested_ptcr & PTCR_PATB;
-        pats = spapr->nested_ptcr & PTCR_PATS;
-
-        /* Check if partition table is properly aligned */
-        if (patb & MAKE_64BIT_MASK(0, pats + 12)) {
-            return false;
-        }
-
-        /* Calculate number of entries */
-        pats = 1ull << (pats + 12 - 4);
-        if (pats <= lpid) {
-            return false;
+        if (spapr_nested_api(spapr) == NESTED_API_KVM_HV) {
+            return spapr_get_pate_nested_hv(spapr, cpu, lpid, entry);
+        } else if (spapr_nested_api(spapr) == NESTED_API_PAPR) {
+            return spapr_get_pate_nested_papr(spapr, cpu, lpid, entry);
+        } else {
+            g_assert_not_reached();
         }
-
-        /* Grab entry */
-        patb += 16 * lpid;
-        entry->dw0 = ldq_phys(CPU(cpu)->as, patb);
-        entry->dw1 = ldq_phys(CPU(cpu)->as, patb + 8);
     }
-
-    return true;
 }
 
 #define HPTE(_table, _i)   (void *)(((uint64_t *)(_table)) + ((_i) * 2))
@@ -1689,6 +1716,7 @@ static void spapr_machine_reset(MachineState *machine, ShutdownCause reason)
 
     pef_kvm_reset(machine->cgs, &error_fatal);
     spapr_caps_apply(spapr);
+    spapr_nested_reset(spapr);
 
     first_ppc_cpu = POWERPC_CPU(first_cpu);
     if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
@@ -2138,6 +2166,7 @@ static const VMStateDescription vmstate_spapr = {
         &vmstate_spapr_cap_fwnmi,
         &vmstate_spapr_fwnmi,
         &vmstate_spapr_cap_rpt_invalidate,
+        &vmstate_spapr_cap_nested_papr,
         NULL
     }
 };
@@ -3481,8 +3510,7 @@ static void spapr_machine_finalizefn(Object *obj)
 void spapr_do_system_reset_on_cpu(CPUState *cs, run_on_cpu_data arg)
 {
     SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
-    PowerPCCPU *cpu = POWERPC_CPU(cs);
-    CPUPPCState *env = &cpu->env;
+    CPUPPCState *env = cpu_env(cs);
 
     cpu_synchronize_state(cs);
     /* If FWNMI is inactive, addr will be -1, which will deliver to 0x100 */
@@ -3979,7 +4007,6 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev)
     SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc);
     SpaprCpuCore *core = SPAPR_CPU_CORE(OBJECT(dev));
     CPUCore *cc = CPU_CORE(dev);
-    CPUState *cs;
     SpaprDrc *drc;
     CPUArchId *core_slot;
     int index;
@@ -4013,7 +4040,7 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev)
         }
     }
 
-    core_slot->cpu = OBJECT(dev);
+    core_slot->cpu = CPU(dev);
 
     /*
      * Set compatibility mode to match the boot CPU, which was either set
@@ -4029,7 +4056,7 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev)
 
     if (smc->pre_2_10_has_unused_icps) {
         for (i = 0; i < cc->nr_threads; i++) {
-            cs = CPU(core->threads[i]);
+            CPUState *cs = CPU(core->threads[i]);
             pre_2_10_vmstate_unregister_dummy_icp(cs->cpu_index);
         }
     }
@@ -4704,6 +4731,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data)
     smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_WORKAROUND;
     smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 16; /* 64kiB */
     smc->default_caps.caps[SPAPR_CAP_NESTED_KVM_HV] = SPAPR_CAP_OFF;
+    smc->default_caps.caps[SPAPR_CAP_NESTED_PAPR] = SPAPR_CAP_OFF;
     smc->default_caps.caps[SPAPR_CAP_LARGE_DECREMENTER] = SPAPR_CAP_ON;
     smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_ON;
     smc->default_caps.caps[SPAPR_CAP_FWNMI] = SPAPR_CAP_ON;
diff --git a/hw/ppc/spapr_caps.c b/hw/ppc/spapr_caps.c
index e889244e52..0a15415a1d 100644
--- a/hw/ppc/spapr_caps.c
+++ b/hw/ppc/spapr_caps.c
@@ -194,8 +194,7 @@ static void cap_htm_apply(SpaprMachineState *spapr, uint8_t val, Error **errp)
 static void cap_vsx_apply(SpaprMachineState *spapr, uint8_t val, Error **errp)
 {
     ERRP_GUARD();
-    PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
-    CPUPPCState *env = &cpu->env;
+    CPUPPCState *env = cpu_env(first_cpu);
 
     if (!val) {
         /* TODO: We don't support disabling vsx yet */
@@ -213,14 +212,12 @@ static void cap_vsx_apply(SpaprMachineState *spapr, uint8_t val, Error **errp)
 static void cap_dfp_apply(SpaprMachineState *spapr, uint8_t val, Error **errp)
 {
     ERRP_GUARD();
-    PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
-    CPUPPCState *env = &cpu->env;
 
     if (!val) {
         /* TODO: We don't support disabling dfp yet */
         return;
     }
-    if (!(env->insns_flags2 & PPC2_DFP)) {
+    if (!(cpu_env(first_cpu)->insns_flags2 & PPC2_DFP)) {
         error_setg(errp, "DFP support not available");
         error_append_hint(errp, "Try appending -machine cap-dfp=off\n");
     }
@@ -487,6 +484,50 @@ static void cap_nested_kvm_hv_apply(SpaprMachineState *spapr,
             error_append_hint(errp, "Try appending -machine cap-nested-hv=off "
                                     "or use threads=1 with -smp\n");
         }
+        if (spapr_nested_api(spapr) &&
+            spapr_nested_api(spapr) != NESTED_API_KVM_HV) {
+            error_setg(errp, "Nested-HV APIs are mutually exclusive");
+            error_append_hint(errp, "Please use either cap-nested-hv or "
+                                    "cap-nested-papr to proceed.\n");
+            return;
+        } else {
+            spapr->nested.api = NESTED_API_KVM_HV;
+        }
+    }
+}
+
+static void cap_nested_papr_apply(SpaprMachineState *spapr,
+                                    uint8_t val, Error **errp)
+{
+    ERRP_GUARD();
+    PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
+    CPUPPCState *env = &cpu->env;
+
+    if (!val) {
+        /* capability disabled by default */
+        return;
+    }
+
+    if (tcg_enabled()) {
+        if (!(env->insns_flags2 & PPC2_ISA300)) {
+            error_setg(errp, "Nested-PAPR only supported on POWER9 and later");
+            error_append_hint(errp,
+                              "Try appending -machine cap-nested-papr=off\n");
+            return;
+        }
+        if (spapr_nested_api(spapr) &&
+            spapr_nested_api(spapr) != NESTED_API_PAPR) {
+            error_setg(errp, "Nested-HV APIs are mutually exclusive");
+            error_append_hint(errp, "Please use either cap-nested-hv or "
+                                    "cap-nested-papr to proceed.\n");
+            return;
+        } else {
+            spapr->nested.api = NESTED_API_PAPR;
+        }
+    } else if (kvm_enabled()) {
+        error_setg(errp, "KVM implementation does not support Nested-PAPR");
+        error_append_hint(errp,
+                          "Try appending -machine cap-nested-papr=off\n");
     }
 }
 
@@ -735,6 +776,15 @@ SpaprCapabilityInfo capability_table[SPAPR_CAP_NUM] = {
         .type = "bool",
         .apply = cap_nested_kvm_hv_apply,
     },
+    [SPAPR_CAP_NESTED_PAPR] = {
+        .name = "nested-papr",
+        .description = "Allow Nested HV (PAPR API)",
+        .index = SPAPR_CAP_NESTED_PAPR,
+        .get = spapr_cap_get_bool,
+        .set = spapr_cap_set_bool,
+        .type = "bool",
+        .apply = cap_nested_papr_apply,
+    },
     [SPAPR_CAP_LARGE_DECREMENTER] = {
         .name = "large-decr",
         .description = "Allow Large Decrementer",
@@ -919,6 +969,7 @@ SPAPR_CAP_MIG_STATE(sbbc, SPAPR_CAP_SBBC);
 SPAPR_CAP_MIG_STATE(ibs, SPAPR_CAP_IBS);
 SPAPR_CAP_MIG_STATE(hpt_maxpagesize, SPAPR_CAP_HPT_MAXPAGESIZE);
 SPAPR_CAP_MIG_STATE(nested_kvm_hv, SPAPR_CAP_NESTED_KVM_HV);
+SPAPR_CAP_MIG_STATE(nested_papr, SPAPR_CAP_NESTED_PAPR);
 SPAPR_CAP_MIG_STATE(large_decr, SPAPR_CAP_LARGE_DECREMENTER);
 SPAPR_CAP_MIG_STATE(ccf_assist, SPAPR_CAP_CCF_ASSIST);
 SPAPR_CAP_MIG_STATE(fwnmi, SPAPR_CAP_FWNMI);
diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c
index 40b7c52f7f..e7c9edd033 100644
--- a/hw/ppc/spapr_cpu_core.c
+++ b/hw/ppc/spapr_cpu_core.c
@@ -39,9 +39,13 @@ static void spapr_reset_vcpu(PowerPCCPU *cpu)
 
     /*
      * "PowerPC Processor binding to IEEE 1275" defines the initial MSR state
-     * as 32bit (MSR_SF=0) in "8.2.1. Initial Register Values".
+     * as 32bit (MSR_SF=0) with MSR_ME=1 and MSR_FP=1 in "8.2.1. Initial
+     * Register Values". This can also be found in "LoPAPR 1.1" "C.9.2.1
+     * Initial Register Values".
      */
     env->msr &= ~(1ULL << MSR_SF);
+    env->msr |= (1ULL << MSR_ME) | (1ULL << MSR_FP);
+
     env->spr[SPR_HIOR] = 0;
 
     lpcr = env->spr[SPR_LPCR];
@@ -394,10 +398,8 @@ static const TypeInfo spapr_cpu_core_type_infos[] = {
     DEFINE_SPAPR_CPU_CORE_TYPE("power8_v2.0"),
     DEFINE_SPAPR_CPU_CORE_TYPE("power8e_v2.1"),
     DEFINE_SPAPR_CPU_CORE_TYPE("power8nvl_v1.0"),
-    DEFINE_SPAPR_CPU_CORE_TYPE("power9_v1.0"),
     DEFINE_SPAPR_CPU_CORE_TYPE("power9_v2.0"),
     DEFINE_SPAPR_CPU_CORE_TYPE("power9_v2.2"),
-    DEFINE_SPAPR_CPU_CORE_TYPE("power10_v1.0"),
     DEFINE_SPAPR_CPU_CORE_TYPE("power10_v2.0"),
 #ifdef CONFIG_KVM
     DEFINE_SPAPR_CPU_CORE_TYPE("host"),
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 75c2d12978..5e1d020e3d 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -1525,6 +1525,28 @@ void spapr_register_hypercall(target_ulong opcode, spapr_hcall_fn fn)
     *slot = fn;
 }
 
+void spapr_unregister_hypercall(target_ulong opcode)
+{
+    spapr_hcall_fn *slot;
+
+    if (opcode <= MAX_HCALL_OPCODE) {
+        assert((opcode & 0x3) == 0);
+
+        slot = &papr_hypercall_table[opcode / 4];
+    } else if (opcode >= SVM_HCALL_BASE && opcode <= SVM_HCALL_MAX) {
+        /* we only have SVM-related hcall numbers assigned in multiples of 4 */
+        assert((opcode & 0x3) == 0);
+
+        slot = &svm_hypercall_table[(opcode - SVM_HCALL_BASE) / 4];
+    } else {
+        assert((opcode >= KVMPPC_HCALL_BASE) && (opcode <= KVMPPC_HCALL_MAX));
+
+        slot = &kvmppc_hypercall_table[opcode - KVMPPC_HCALL_BASE];
+    }
+
+    *slot = NULL;
+}
+
 target_ulong spapr_hypercall(PowerPCCPU *cpu, target_ulong opcode,
                              target_ulong *args)
 {
@@ -1638,8 +1660,6 @@ static void hypercall_register_types(void)
     spapr_register_hypercall(KVMPPC_H_CAS, h_client_architecture_support);
 
     spapr_register_hypercall(KVMPPC_H_UPDATE_DT, h_update_dt);
-
-    spapr_register_nested();
 }
 
 type_init(hypercall_register_types)
diff --git a/hw/ppc/spapr_nested.c b/hw/ppc/spapr_nested.c
index 121aa96ddc..936659b4c0 100644
--- a/hw/ppc/spapr_nested.c
+++ b/hw/ppc/spapr_nested.c
@@ -6,8 +6,85 @@
 #include "hw/ppc/spapr.h"
 #include "hw/ppc/spapr_cpu_core.h"
 #include "hw/ppc/spapr_nested.h"
+#include "mmu-book3s-v3.h"
+#include "cpu-models.h"
+#include "qemu/log.h"
+
+void spapr_nested_reset(SpaprMachineState *spapr)
+{
+    if (spapr_get_cap(spapr, SPAPR_CAP_NESTED_KVM_HV)) {
+        spapr_unregister_nested_hv();
+        spapr_register_nested_hv();
+    } else if (spapr_get_cap(spapr, SPAPR_CAP_NESTED_PAPR)) {
+        spapr->nested.capabilities_set = false;
+        spapr_unregister_nested_papr();
+        spapr_register_nested_papr();
+        spapr_nested_gsb_init();
+    } else {
+        spapr->nested.api = 0;
+    }
+}
+
+uint8_t spapr_nested_api(SpaprMachineState *spapr)
+{
+    return spapr->nested.api;
+}
 
 #ifdef CONFIG_TCG
+
+bool spapr_get_pate_nested_hv(SpaprMachineState *spapr, PowerPCCPU *cpu,
+                              target_ulong lpid, ppc_v3_pate_t *entry)
+{
+    uint64_t patb, pats;
+
+    assert(lpid != 0);
+
+    patb = spapr->nested.ptcr & PTCR_PATB;
+    pats = spapr->nested.ptcr & PTCR_PATS;
+
+    /* Check if partition table is properly aligned */
+    if (patb & MAKE_64BIT_MASK(0, pats + 12)) {
+        return false;
+    }
+
+    /* Calculate number of entries */
+    pats = 1ull << (pats + 12 - 4);
+    if (pats <= lpid) {
+        return false;
+    }
+
+    /* Grab entry */
+    patb += 16 * lpid;
+    entry->dw0 = ldq_phys(CPU(cpu)->as, patb);
+    entry->dw1 = ldq_phys(CPU(cpu)->as, patb + 8);
+    return true;
+}
+
+static
+SpaprMachineStateNestedGuest *spapr_get_nested_guest(SpaprMachineState *spapr,
+                                                     target_ulong guestid)
+{
+    SpaprMachineStateNestedGuest *guest;
+
+    guest = g_hash_table_lookup(spapr->nested.guests, GINT_TO_POINTER(guestid));
+    return guest;
+}
+
+bool spapr_get_pate_nested_papr(SpaprMachineState *spapr, PowerPCCPU *cpu,
+                                target_ulong lpid, ppc_v3_pate_t *entry)
+{
+    SpaprMachineStateNestedGuest *guest;
+    assert(lpid != 0);
+    guest = spapr_get_nested_guest(spapr, lpid);
+    if (!guest) {
+        return false;
+    }
+
+    entry->dw0 = guest->parttbl[0];
+    entry->dw1 = guest->parttbl[1];
+    return true;
+}
+
 #define PRTS_MASK      0x1f
 
 static target_ulong h_set_ptbl(PowerPCCPU *cpu,
@@ -25,7 +102,7 @@ static target_ulong h_set_ptbl(PowerPCCPU *cpu,
         return H_PARAMETER;
     }
 
-    spapr->nested_ptcr = ptcr; /* Save new partition table */
+    spapr->nested.ptcr = ptcr; /* Save new partition table */
 
     return H_SUCCESS;
 }
@@ -59,6 +136,7 @@ static target_ulong h_copy_tofrom_guest(PowerPCCPU *cpu,
 static void nested_save_state(struct nested_ppc_state *save, PowerPCCPU *cpu)
 {
     CPUPPCState *env = &cpu->env;
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
 
     memcpy(save->gpr, env->gpr, sizeof(save->gpr));
 
@@ -85,13 +163,79 @@ static void nested_save_state(struct nested_ppc_state *save, PowerPCCPU *cpu)
     save->pidr = env->spr[SPR_BOOKS_PID];
     save->ppr = env->spr[SPR_PPR];
 
-    save->tb_offset = env->tb_env->tb_offset;
+    if (spapr_nested_api(spapr) == NESTED_API_PAPR) {
+        save->amor = env->spr[SPR_AMOR];
+        save->dawr0 = env->spr[SPR_DAWR0];
+        save->dawrx0 = env->spr[SPR_DAWRX0];
+        save->ciabr = env->spr[SPR_CIABR];
+        save->purr = env->spr[SPR_PURR];
+        save->spurr = env->spr[SPR_SPURR];
+        save->ic = env->spr[SPR_IC];
+        save->vtb = env->spr[SPR_VTB];
+        save->hdar = env->spr[SPR_HDAR];
+        save->hdsisr = env->spr[SPR_HDSISR];
+        save->heir = env->spr[SPR_HEIR];
+        save->asdr = env->spr[SPR_ASDR];
+        save->dawr1 = env->spr[SPR_DAWR1];
+        save->dawrx1 = env->spr[SPR_DAWRX1];
+        save->dexcr = env->spr[SPR_DEXCR];
+        save->hdexcr = env->spr[SPR_HDEXCR];
+        save->hashkeyr = env->spr[SPR_HASHKEYR];
+        save->hashpkeyr = env->spr[SPR_HASHPKEYR];
+        memcpy(save->vsr, env->vsr, sizeof(save->vsr));
+        save->ebbhr = env->spr[SPR_EBBHR];
+        save->tar = env->spr[SPR_TAR];
+        save->ebbrr = env->spr[SPR_EBBRR];
+        save->bescr = env->spr[SPR_BESCR];
+        save->iamr = env->spr[SPR_IAMR];
+        save->amr = env->spr[SPR_AMR];
+        save->uamor = env->spr[SPR_UAMOR];
+        save->dscr = env->spr[SPR_DSCR];
+        save->fscr = env->spr[SPR_FSCR];
+        save->pspb = env->spr[SPR_PSPB];
+        save->ctrl = env->spr[SPR_CTRL];
+        save->vrsave = env->spr[SPR_VRSAVE];
+        save->dar = env->spr[SPR_DAR];
+        save->dsisr = env->spr[SPR_DSISR];
+        save->pmc1 = env->spr[SPR_POWER_PMC1];
+        save->pmc2 = env->spr[SPR_POWER_PMC2];
+        save->pmc3 = env->spr[SPR_POWER_PMC3];
+        save->pmc4 = env->spr[SPR_POWER_PMC4];
+        save->pmc5 = env->spr[SPR_POWER_PMC5];
+        save->pmc6 = env->spr[SPR_POWER_PMC6];
+        save->mmcr0 = env->spr[SPR_POWER_MMCR0];
+        save->mmcr1 = env->spr[SPR_POWER_MMCR1];
+        save->mmcr2 = env->spr[SPR_POWER_MMCR2];
+        save->mmcra = env->spr[SPR_POWER_MMCRA];
+        save->sdar = env->spr[SPR_POWER_SDAR];
+        save->siar = env->spr[SPR_POWER_SIAR];
+        save->sier = env->spr[SPR_POWER_SIER];
+        save->vscr = ppc_get_vscr(env);
+        save->fpscr = env->fpscr;
+    } else if (spapr_nested_api(spapr) == NESTED_API_KVM_HV) {
+        save->tb_offset = env->tb_env->tb_offset;
+    }
+}
+
+static void nested_post_load_state(CPUPPCState *env, CPUState *cs)
+{
+    /*
+     * compute hflags and possible interrupts.
+     */
+    hreg_compute_hflags(env);
+    ppc_maybe_interrupt(env);
+    /*
+     * Nested HV does not tag TLB entries between L1 and L2, so must
+     * flush on transition.
+     */
+    tlb_flush(cs);
+    env->reserve_addr = -1; /* Reset the reservation */
 }
 
 static void nested_load_state(PowerPCCPU *cpu, struct nested_ppc_state *load)
 {
-    CPUState *cs = CPU(cpu);
     CPUPPCState *env = &cpu->env;
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
 
     memcpy(env->gpr, load->gpr, sizeof(env->gpr));
 
@@ -118,20 +262,58 @@ static void nested_load_state(PowerPCCPU *cpu, struct nested_ppc_state *load)
     env->spr[SPR_BOOKS_PID] = load->pidr;
     env->spr[SPR_PPR] = load->ppr;
 
-    env->tb_env->tb_offset = load->tb_offset;
-
-    /*
-     * MSR updated, compute hflags and possible interrupts.
-     */
-    hreg_compute_hflags(env);
-    ppc_maybe_interrupt(env);
-
-    /*
-     * Nested HV does not tag TLB entries between L1 and L2, so must
-     * flush on transition.
-     */
-    tlb_flush(cs);
-    env->reserve_addr = -1; /* Reset the reservation */
+    if (spapr_nested_api(spapr) == NESTED_API_PAPR) {
+        env->spr[SPR_AMOR] = load->amor;
+        env->spr[SPR_DAWR0] = load->dawr0;
+        env->spr[SPR_DAWRX0] = load->dawrx0;
+        env->spr[SPR_CIABR] = load->ciabr;
+        env->spr[SPR_PURR] = load->purr;
+        env->spr[SPR_SPURR] = load->purr;
+        env->spr[SPR_IC] = load->ic;
+        env->spr[SPR_VTB] = load->vtb;
+        env->spr[SPR_HDAR] = load->hdar;
+        env->spr[SPR_HDSISR] = load->hdsisr;
+        env->spr[SPR_HEIR] = load->heir;
+        env->spr[SPR_ASDR] = load->asdr;
+        env->spr[SPR_DAWR1] = load->dawr1;
+        env->spr[SPR_DAWRX1] = load->dawrx1;
+        env->spr[SPR_DEXCR] = load->dexcr;
+        env->spr[SPR_HDEXCR] = load->hdexcr;
+        env->spr[SPR_HASHKEYR] = load->hashkeyr;
+        env->spr[SPR_HASHPKEYR] = load->hashpkeyr;
+        memcpy(env->vsr, load->vsr, sizeof(env->vsr));
+        env->spr[SPR_EBBHR] = load->ebbhr;
+        env->spr[SPR_TAR] = load->tar;
+        env->spr[SPR_EBBRR] = load->ebbrr;
+        env->spr[SPR_BESCR] = load->bescr;
+        env->spr[SPR_IAMR] = load->iamr;
+        env->spr[SPR_AMR] = load->amr;
+        env->spr[SPR_UAMOR] = load->uamor;
+        env->spr[SPR_DSCR] = load->dscr;
+        env->spr[SPR_FSCR] = load->fscr;
+        env->spr[SPR_PSPB] = load->pspb;
+        env->spr[SPR_CTRL] = load->ctrl;
+        env->spr[SPR_VRSAVE] = load->vrsave;
+        env->spr[SPR_DAR] = load->dar;
+        env->spr[SPR_DSISR] = load->dsisr;
+        env->spr[SPR_POWER_PMC1] = load->pmc1;
+        env->spr[SPR_POWER_PMC2] = load->pmc2;
+        env->spr[SPR_POWER_PMC3] = load->pmc3;
+        env->spr[SPR_POWER_PMC4] = load->pmc4;
+        env->spr[SPR_POWER_PMC5] = load->pmc5;
+        env->spr[SPR_POWER_PMC6] = load->pmc6;
+        env->spr[SPR_POWER_MMCR0] = load->mmcr0;
+        env->spr[SPR_POWER_MMCR1] = load->mmcr1;
+        env->spr[SPR_POWER_MMCR2] = load->mmcr2;
+        env->spr[SPR_POWER_MMCRA] = load->mmcra;
+        env->spr[SPR_POWER_SDAR] = load->sdar;
+        env->spr[SPR_POWER_SIAR] = load->siar;
+        env->spr[SPR_POWER_SIER] = load->sier;
+        ppc_store_vscr(env, load->vscr);
+        ppc_store_fpscr(env, load->fpscr);
+    } else if (spapr_nested_api(spapr) == NESTED_API_KVM_HV) {
+        env->tb_env->tb_offset = load->tb_offset;
+    }
 }
 
 /*
@@ -146,6 +328,7 @@ static target_ulong h_enter_nested(PowerPCCPU *cpu,
 {
     PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
     CPUPPCState *env = &cpu->env;
+    CPUState *cs = CPU(cpu);
     SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
     struct nested_ppc_state l2_state;
     target_ulong hv_ptr = args[0];
@@ -157,7 +340,7 @@ static target_ulong h_enter_nested(PowerPCCPU *cpu,
     struct kvmppc_pt_regs *regs;
     hwaddr len;
 
-    if (spapr->nested_ptcr == 0) {
+    if (spapr->nested.ptcr == 0) {
         return H_NOT_AVAILABLE;
     }
 
@@ -244,6 +427,7 @@ static target_ulong h_enter_nested(PowerPCCPU *cpu,
      * Switch to the nested guest environment and start the "hdec" timer.
      */
     nested_load_state(cpu, &l2_state);
+    nested_post_load_state(env, cs);
 
     hdec = hv_state.hdec_expiry - now;
     cpu_ppc_hdecr_init(env);
@@ -272,9 +456,10 @@ static target_ulong h_enter_nested(PowerPCCPU *cpu,
     return env->gpr[3];
 }
 
-void spapr_exit_nested(PowerPCCPU *cpu, int excp)
+static void spapr_exit_nested_hv(PowerPCCPU *cpu, int excp)
 {
     CPUPPCState *env = &cpu->env;
+    CPUState *cs = CPU(cpu);
     SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
     struct nested_ppc_state l2_state;
     target_ulong hv_ptr = spapr_cpu->nested_host_state->gpr[4];
@@ -284,8 +469,6 @@ void spapr_exit_nested(PowerPCCPU *cpu, int excp)
     struct kvmppc_pt_regs *regs;
     hwaddr len;
 
-    assert(spapr_cpu->in_nested);
-
     nested_save_state(&l2_state, cpu);
     hsrr0 = env->spr[SPR_HSRR0];
     hsrr1 = env->spr[SPR_HSRR1];
@@ -298,6 +481,7 @@ void spapr_exit_nested(PowerPCCPU *cpu, int excp)
      */
     assert(env->spr[SPR_LPIDR] != 0);
     nested_load_state(cpu, spapr_cpu->nested_host_state);
+    nested_post_load_state(env, cs);
     env->gpr[3] = env->excp_vectors[excp]; /* hcall return value */
 
     cpu_ppc_hdecr_exit(env);
@@ -375,21 +559,1347 @@ void spapr_exit_nested(PowerPCCPU *cpu, int excp)
     address_space_unmap(CPU(cpu)->as, regs, len, len, true);
 }
 
-void spapr_register_nested(void)
+static bool spapr_nested_vcpu_check(SpaprMachineStateNestedGuest *guest,
+                                    target_ulong vcpuid, bool inoutbuf)
+{
+    struct SpaprMachineStateNestedGuestVcpu *vcpu;
+    /*
+     * Perform sanity checks for the provided vcpuid of a guest.
+     * For now, ensure its valid, allocated and enabled for use.
+     */
+
+    if (vcpuid >= PAPR_NESTED_GUEST_VCPU_MAX) {
+        return false;
+    }
+
+    if (!(vcpuid < guest->nr_vcpus)) {
+        return false;
+    }
+
+    vcpu = &guest->vcpus[vcpuid];
+    if (!vcpu->enabled) {
+        return false;
+    }
+
+    if (!inoutbuf) {
+        return true;
+    }
+
+    /* Check to see if the in/out buffers are registered */
+    if (vcpu->runbufin.addr && vcpu->runbufout.addr) {
+        return true;
+    }
+
+    return false;
+}
+
+static void *get_vcpu_state_ptr(SpaprMachineStateNestedGuest *guest,
+                              target_ulong vcpuid)
+{
+    assert(spapr_nested_vcpu_check(guest, vcpuid, false));
+    return &guest->vcpus[vcpuid].state;
+}
+
+static void *get_vcpu_ptr(SpaprMachineStateNestedGuest *guest,
+                                   target_ulong vcpuid)
+{
+    assert(spapr_nested_vcpu_check(guest, vcpuid, false));
+    return &guest->vcpus[vcpuid];
+}
+
+static void *get_guest_ptr(SpaprMachineStateNestedGuest *guest,
+                           target_ulong vcpuid)
+{
+    return guest; /* for GSBE_NESTED */
+}
+
+/*
+ * set=1 means the L1 is trying to set some state
+ * set=0 means the L1 is trying to get some state
+ */
+static void copy_state_8to8(void *a, void *b, bool set)
+{
+    /* set takes from the Big endian element_buf and sets internal buffer */
+
+    if (set) {
+        *(uint64_t *)a = be64_to_cpu(*(uint64_t *)b);
+    } else {
+        *(uint64_t *)b = cpu_to_be64(*(uint64_t *)a);
+    }
+}
+
+static void copy_state_4to4(void *a, void *b, bool set)
+{
+    if (set) {
+        *(uint32_t *)a = be32_to_cpu(*(uint32_t *)b);
+    } else {
+        *(uint32_t *)b = cpu_to_be32(*((uint32_t *)a));
+    }
+}
+
+static void copy_state_16to16(void *a, void *b, bool set)
+{
+    uint64_t *src, *dst;
+
+    if (set) {
+        src = b;
+        dst = a;
+
+        dst[1] = be64_to_cpu(src[0]);
+        dst[0] = be64_to_cpu(src[1]);
+    } else {
+        src = a;
+        dst = b;
+
+        dst[1] = cpu_to_be64(src[0]);
+        dst[0] = cpu_to_be64(src[1]);
+    }
+}
+
+static void copy_state_4to8(void *a, void *b, bool set)
+{
+    if (set) {
+        *(uint64_t *)a  = (uint64_t) be32_to_cpu(*(uint32_t *)b);
+    } else {
+        *(uint32_t *)b = cpu_to_be32((uint32_t) (*((uint64_t *)a)));
+    }
+}
+
+static void copy_state_pagetbl(void *a, void *b, bool set)
+{
+    uint64_t *pagetbl;
+    uint64_t *buf; /* 3 double words */
+    uint64_t rts;
+
+    assert(set);
+
+    pagetbl = a;
+    buf = b;
+
+    *pagetbl = be64_to_cpu(buf[0]);
+    /* as per ISA section 6.7.6.1 */
+    *pagetbl |= PATE0_HR; /* Host Radix bit is 1 */
+
+    /* RTS */
+    rts = be64_to_cpu(buf[1]);
+    assert(rts == 52);
+    rts = rts - 31; /* since radix tree size = 2^(RTS+31) */
+    *pagetbl |=  ((rts & 0x7) << 5); /* RTS2 is bit 56:58 */
+    *pagetbl |=  (((rts >> 3) & 0x3) << 61); /* RTS1 is bit 1:2 */
+
+    /* RPDS {Size = 2^(RPDS+3) , RPDS >=5} */
+    *pagetbl |= 63 - clz64(be64_to_cpu(buf[2])) - 3;
+}
+
+static void copy_state_proctbl(void *a, void *b, bool set)
+{
+    uint64_t *proctbl;
+    uint64_t *buf; /* 2 double words */
+
+    assert(set);
+
+    proctbl = a;
+    buf = b;
+    /* PRTB: Process Table Base */
+    *proctbl = be64_to_cpu(buf[0]);
+    /* PRTS: Process Table Size = 2^(12+PRTS) */
+    if (be64_to_cpu(buf[1]) == (1ULL << 12)) {
+            *proctbl |= 0;
+    } else if (be64_to_cpu(buf[1]) == (1ULL << 24)) {
+            *proctbl |= 12;
+    } else {
+        g_assert_not_reached();
+    }
+}
+
+static void copy_state_runbuf(void *a, void *b, bool set)
+{
+    uint64_t *buf; /* 2 double words */
+    struct SpaprMachineStateNestedGuestVcpuRunBuf *runbuf;
+
+    assert(set);
+
+    runbuf = a;
+    buf = b;
+
+    runbuf->addr = be64_to_cpu(buf[0]);
+    assert(runbuf->addr);
+
+    /* per spec */
+    assert(be64_to_cpu(buf[1]) <= 16384);
+
+    /*
+     * This will also hit in the input buffer but should be fine for
+     * now. If not we can split this function.
+     */
+    assert(be64_to_cpu(buf[1]) >= VCPU_OUT_BUF_MIN_SZ);
+
+    runbuf->size = be64_to_cpu(buf[1]);
+}
+
+/* tell the L1 how big we want the output vcpu run buffer */
+static void out_buf_min_size(void *a, void *b, bool set)
+{
+    uint64_t *buf; /* 1 double word */
+
+    assert(!set);
+
+    buf = b;
+
+    buf[0] = cpu_to_be64(VCPU_OUT_BUF_MIN_SZ);
+}
+
+static void copy_logical_pvr(void *a, void *b, bool set)
+{
+    SpaprMachineStateNestedGuest *guest;
+    uint32_t *buf; /* 1 word */
+    uint32_t *pvr_logical_ptr;
+    uint32_t pvr_logical;
+    target_ulong pcr = 0;
+
+    pvr_logical_ptr = a;
+    buf = b;
+
+    if (!set) {
+        buf[0] = cpu_to_be32(*pvr_logical_ptr);
+        return;
+    }
+
+    pvr_logical = be32_to_cpu(buf[0]);
+
+    *pvr_logical_ptr = pvr_logical;
+
+    if (*pvr_logical_ptr) {
+        switch (*pvr_logical_ptr) {
+        case CPU_POWERPC_LOGICAL_3_10:
+            pcr = PCR_COMPAT_3_10 | PCR_COMPAT_3_00;
+            break;
+        case CPU_POWERPC_LOGICAL_3_00:
+            pcr = PCR_COMPAT_3_00;
+            break;
+        default:
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "Could not set PCR for LPVR=0x%08x\n",
+                          *pvr_logical_ptr);
+            return;
+        }
+    }
+
+    guest = container_of(pvr_logical_ptr,
+                         struct SpaprMachineStateNestedGuest,
+                         pvr_logical);
+    for (int i = 0; i < guest->nr_vcpus; i++) {
+        guest->vcpus[i].state.pcr = ~pcr | HVMASK_PCR;
+    }
+}
+
+static void copy_tb_offset(void *a, void *b, bool set)
+{
+    SpaprMachineStateNestedGuest *guest;
+    uint64_t *buf; /* 1 double word */
+    uint64_t *tb_offset_ptr;
+    uint64_t tb_offset;
+
+    tb_offset_ptr = a;
+    buf = b;
+
+    if (!set) {
+        buf[0] = cpu_to_be64(*tb_offset_ptr);
+        return;
+    }
+
+    tb_offset = be64_to_cpu(buf[0]);
+    /* need to copy this to the individual tb_offset for each vcpu */
+    guest = container_of(tb_offset_ptr,
+                         struct SpaprMachineStateNestedGuest,
+                         tb_offset);
+    for (int i = 0; i < guest->nr_vcpus; i++) {
+        guest->vcpus[i].tb_offset = tb_offset;
+    }
+}
+
+static void copy_state_hdecr(void *a, void *b, bool set)
+{
+    uint64_t *buf; /* 1 double word */
+    uint64_t *hdecr_expiry_tb;
+
+    hdecr_expiry_tb = a;
+    buf = b;
+
+    if (!set) {
+        buf[0] = cpu_to_be64(*hdecr_expiry_tb);
+        return;
+    }
+
+    *hdecr_expiry_tb = be64_to_cpu(buf[0]);
+}
+
+struct guest_state_element_type guest_state_element_types[] = {
+    GUEST_STATE_ELEMENT_NOP(GSB_HV_VCPU_IGNORED_ID, 0),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR0,  gpr[0]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR1,  gpr[1]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR2,  gpr[2]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR3,  gpr[3]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR4,  gpr[4]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR5,  gpr[5]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR6,  gpr[6]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR7,  gpr[7]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR8,  gpr[8]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR9,  gpr[9]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR10, gpr[10]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR11, gpr[11]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR12, gpr[12]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR13, gpr[13]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR14, gpr[14]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR15, gpr[15]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR16, gpr[16]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR17, gpr[17]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR18, gpr[18]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR19, gpr[19]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR20, gpr[20]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR21, gpr[21]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR22, gpr[22]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR23, gpr[23]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR24, gpr[24]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR25, gpr[25]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR26, gpr[26]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR27, gpr[27]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR28, gpr[28]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR29, gpr[29]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR30, gpr[30]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_GPR31, gpr[31]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_NIA, nip),
+    GSE_ENV_DWM(GSB_VCPU_SPR_MSR, msr, HVMASK_MSR),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_CTR, ctr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_LR, lr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_XER, xer),
+    GUEST_STATE_ELEMENT_ENV_WW(GSB_VCPU_SPR_CR, cr),
+    GUEST_STATE_ELEMENT_NOP_DW(GSB_VCPU_SPR_MMCR3),
+    GUEST_STATE_ELEMENT_NOP_DW(GSB_VCPU_SPR_SIER2),
+    GUEST_STATE_ELEMENT_NOP_DW(GSB_VCPU_SPR_SIER3),
+    GUEST_STATE_ELEMENT_NOP_W(GSB_VCPU_SPR_WORT),
+    GSE_ENV_DWM(GSB_VCPU_SPR_LPCR, lpcr, HVMASK_LPCR),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_AMOR, amor),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_HFSCR, hfscr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DAWR0, dawr0),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_DAWRX0, dawrx0),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_CIABR, ciabr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_PURR,  purr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SPURR, spurr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_IC,    ic),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_VTB,   vtb),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_HDAR,  hdar),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_HDSISR, hdsisr),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_HEIR,   heir),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_ASDR,  asdr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SRR0,  srr0),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SRR1,  srr1),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SPRG0, sprg0),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SPRG1, sprg1),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SPRG2, sprg2),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SPRG3, sprg3),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PIDR,   pidr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_CFAR,  cfar),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_PPR,   ppr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DAWR1, dawr1),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_DAWRX1, dawrx1),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DEXCR, dexcr),
+    GSE_ENV_DWM(GSB_VCPU_SPR_HDEXCR, hdexcr, HVMASK_HDEXCR),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_HASHKEYR, hashkeyr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_HASHPKEYR, hashpkeyr),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR0, vsr[0]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR1, vsr[1]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR2, vsr[2]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR3, vsr[3]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR4, vsr[4]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR5, vsr[5]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR6, vsr[6]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR7, vsr[7]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR8, vsr[8]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR9, vsr[9]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR10, vsr[10]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR11, vsr[11]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR12, vsr[12]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR13, vsr[13]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR14, vsr[14]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR15, vsr[15]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR16, vsr[16]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR17, vsr[17]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR18, vsr[18]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR19, vsr[19]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR20, vsr[20]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR21, vsr[21]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR22, vsr[22]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR23, vsr[23]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR24, vsr[24]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR25, vsr[25]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR26, vsr[26]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR27, vsr[27]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR28, vsr[28]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR29, vsr[29]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR30, vsr[30]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR31, vsr[31]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR32, vsr[32]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR33, vsr[33]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR34, vsr[34]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR35, vsr[35]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR36, vsr[36]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR37, vsr[37]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR38, vsr[38]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR39, vsr[39]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR40, vsr[40]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR41, vsr[41]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR42, vsr[42]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR43, vsr[43]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR44, vsr[44]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR45, vsr[45]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR46, vsr[46]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR47, vsr[47]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR48, vsr[48]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR49, vsr[49]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR50, vsr[50]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR51, vsr[51]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR52, vsr[52]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR53, vsr[53]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR54, vsr[54]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR55, vsr[55]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR56, vsr[56]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR57, vsr[57]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR58, vsr[58]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR59, vsr[59]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR60, vsr[60]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR61, vsr[61]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR62, vsr[62]),
+    GUEST_STATE_ELEMENT_ENV_QW(GSB_VCPU_SPR_VSR63, vsr[63]),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_EBBHR, ebbhr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_TAR,   tar),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_EBBRR, ebbrr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_BESCR, bescr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_IAMR,  iamr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_AMR,   amr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_UAMOR, uamor),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DSCR,  dscr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_FSCR,  fscr),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PSPB,   pspb),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_CTRL,  ctrl),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_VRSAVE, vrsave),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DAR,   dar),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_DSISR,  dsisr),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC1,   pmc1),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC2,   pmc2),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC3,   pmc3),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC4,   pmc4),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC5,   pmc5),
+    GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PMC6,   pmc6),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_MMCR0, mmcr0),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_MMCR1, mmcr1),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_MMCR2, mmcr2),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_MMCRA, mmcra),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SDAR , sdar),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SIAR , siar),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_SIER , sier),
+    GUEST_STATE_ELEMENT_ENV_WW(GSB_VCPU_SPR_VSCR,  vscr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_FPSCR, fpscr),
+    GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_DEC_EXPIRE_TB, dec_expiry_tb),
+    GSBE_NESTED(GSB_PART_SCOPED_PAGETBL, 0x18, parttbl[0],  copy_state_pagetbl),
+    GSBE_NESTED(GSB_PROCESS_TBL,         0x10, parttbl[1],  copy_state_proctbl),
+    GSBE_NESTED(GSB_VCPU_LPVR,           0x4,  pvr_logical, copy_logical_pvr),
+    GSBE_NESTED_MSK(GSB_TB_OFFSET, 0x8, tb_offset, copy_tb_offset,
+                    HVMASK_TB_OFFSET),
+    GSBE_NESTED_VCPU(GSB_VCPU_IN_BUFFER, 0x10, runbufin,    copy_state_runbuf),
+    GSBE_NESTED_VCPU(GSB_VCPU_OUT_BUFFER, 0x10, runbufout,   copy_state_runbuf),
+    GSBE_NESTED_VCPU(GSB_VCPU_OUT_BUF_MIN_SZ, 0x8, runbufout, out_buf_min_size),
+    GSBE_NESTED_VCPU(GSB_VCPU_HDEC_EXPIRY_TB, 0x8, hdecr_expiry_tb,
+                     copy_state_hdecr)
+};
+
+void spapr_nested_gsb_init(void)
+{
+    struct guest_state_element_type *type;
+
+    /* Init the guest state elements lookup table, flags for now */
+    for (int i = 0; i < ARRAY_SIZE(guest_state_element_types); i++) {
+        type = &guest_state_element_types[i];
+
+        assert(type->id <= GSB_LAST);
+        if (type->id >= GSB_VCPU_SPR_HDAR)
+            /* 0xf000 - 0xf005 Thread + RO */
+            type->flags = GUEST_STATE_ELEMENT_TYPE_FLAG_READ_ONLY;
+        else if (type->id >= GSB_VCPU_IN_BUFFER)
+            /* 0x0c00 - 0xf000 Thread + RW */
+            type->flags = 0;
+        else if (type->id >= GSB_VCPU_LPVR)
+            /* 0x0003 - 0x0bff Guest + RW */
+            type->flags = GUEST_STATE_ELEMENT_TYPE_FLAG_GUEST_WIDE;
+        else if (type->id >= GSB_HV_VCPU_STATE_SIZE)
+            /* 0x0001 - 0x0002 Guest + RO */
+            type->flags = GUEST_STATE_ELEMENT_TYPE_FLAG_READ_ONLY |
+                          GUEST_STATE_ELEMENT_TYPE_FLAG_GUEST_WIDE;
+    }
+}
+
+static struct guest_state_element *guest_state_element_next(
+    struct guest_state_element *element,
+    int64_t *len,
+    int64_t *num_elements)
+{
+    uint16_t size;
+
+    /* size is of element->value[] only. Not whole guest_state_element */
+    size = be16_to_cpu(element->size);
+
+    if (len) {
+        *len -= size + offsetof(struct guest_state_element, value);
+    }
+
+    if (num_elements) {
+        *num_elements -= 1;
+    }
+
+    return (struct guest_state_element *)(element->value + size);
+}
+
+static
+struct guest_state_element_type *guest_state_element_type_find(uint16_t id)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(guest_state_element_types); i++)
+        if (id == guest_state_element_types[i].id) {
+            return &guest_state_element_types[i];
+        }
+
+    return NULL;
+}
+
+static void log_element(struct guest_state_element *element,
+                        struct guest_state_request *gsr)
+{
+    qemu_log_mask(LOG_GUEST_ERROR, "h_guest_%s_state id:0x%04x size:0x%04x",
+                  gsr->flags & GUEST_STATE_REQUEST_SET ? "set" : "get",
+                  be16_to_cpu(element->id), be16_to_cpu(element->size));
+    qemu_log_mask(LOG_GUEST_ERROR, "buf:0x%016"PRIx64" ...\n",
+                  be64_to_cpu(*(uint64_t *)element->value));
+}
+
+static bool guest_state_request_check(struct guest_state_request *gsr)
+{
+    int64_t num_elements, len = gsr->len;
+    struct guest_state_buffer *gsb = gsr->gsb;
+    struct guest_state_element *element;
+    struct guest_state_element_type *type;
+    uint16_t id, size;
+
+    /* gsb->num_elements = 0 == 32 bits long */
+    assert(len >= 4);
+
+    num_elements = be32_to_cpu(gsb->num_elements);
+    element = gsb->elements;
+    len -= sizeof(gsb->num_elements);
+
+    /* Walk the buffer to validate the length */
+    while (num_elements) {
+
+        id = be16_to_cpu(element->id);
+        size = be16_to_cpu(element->size);
+
+        if (false) {
+            log_element(element, gsr);
+        }
+        /* buffer size too small */
+        if (len < 0) {
+            return false;
+        }
+
+        type = guest_state_element_type_find(id);
+        if (!type) {
+            qemu_log_mask(LOG_GUEST_ERROR, "Element ID %04x unknown\n", id);
+            log_element(element, gsr);
+            return false;
+        }
+
+        if (id == GSB_HV_VCPU_IGNORED_ID) {
+            goto next_element;
+        }
+
+        if (size != type->size) {
+            qemu_log_mask(LOG_GUEST_ERROR, "Size mismatch. Element ID:%04x."
+                          "Size Exp:%i Got:%i\n", id, type->size, size);
+            log_element(element, gsr);
+            return false;
+        }
+
+        if ((type->flags & GUEST_STATE_ELEMENT_TYPE_FLAG_READ_ONLY) &&
+            (gsr->flags & GUEST_STATE_REQUEST_SET)) {
+            qemu_log_mask(LOG_GUEST_ERROR, "Trying to set a read-only Element "
+                          "ID:%04x.\n", id);
+            return false;
+        }
+
+        if (type->flags & GUEST_STATE_ELEMENT_TYPE_FLAG_GUEST_WIDE) {
+            /* guest wide element type */
+            if (!(gsr->flags & GUEST_STATE_REQUEST_GUEST_WIDE)) {
+                qemu_log_mask(LOG_GUEST_ERROR, "trying to set a guest wide "
+                              "Element ID:%04x.\n", id);
+                return false;
+            }
+        } else {
+            /* thread wide element type */
+            if (gsr->flags & GUEST_STATE_REQUEST_GUEST_WIDE) {
+                qemu_log_mask(LOG_GUEST_ERROR, "trying to set a thread wide "
+                              "Element ID:%04x.\n", id);
+                return false;
+            }
+        }
+next_element:
+        element = guest_state_element_next(element, &len, &num_elements);
+
+    }
+    return true;
+}
+
+static bool is_gsr_invalid(struct guest_state_request *gsr,
+                                   struct guest_state_element *element,
+                                   struct guest_state_element_type *type)
+{
+    if ((gsr->flags & GUEST_STATE_REQUEST_SET) &&
+        (*(uint64_t *)(element->value) & ~(type->mask))) {
+        log_element(element, gsr);
+        qemu_log_mask(LOG_GUEST_ERROR, "L1 can't set reserved bits "
+                      "(allowed mask: 0x%08"PRIx64")\n", type->mask);
+        return true;
+    }
+    return false;
+}
+
+static target_ulong h_guest_get_capabilities(PowerPCCPU *cpu,
+                                             SpaprMachineState *spapr,
+                                             target_ulong opcode,
+                                             target_ulong *args)
+{
+    CPUPPCState *env = &cpu->env;
+    target_ulong flags = args[0];
+
+    if (flags) { /* don't handle any flags capabilities for now */
+        return H_PARAMETER;
+    }
+
+    /* P10 capabilities */
+    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0,
+        spapr->max_compat_pvr)) {
+        env->gpr[4] |= H_GUEST_CAPABILITIES_P10_MODE;
+    }
+
+    /* P9 capabilities */
+    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0,
+        spapr->max_compat_pvr)) {
+        env->gpr[4] |= H_GUEST_CAPABILITIES_P9_MODE;
+    }
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_guest_set_capabilities(PowerPCCPU *cpu,
+                                             SpaprMachineState *spapr,
+                                             target_ulong opcode,
+                                              target_ulong *args)
+{
+    CPUPPCState *env = &cpu->env;
+    target_ulong flags = args[0];
+    target_ulong capabilities = args[1];
+    env->gpr[4] = 0;
+
+    if (flags) { /* don't handle any flags capabilities for now */
+        return H_PARAMETER;
+    }
+
+    if (capabilities & H_GUEST_CAPABILITIES_COPY_MEM) {
+        env->gpr[4] = 1;
+        return H_P2; /* isn't supported */
+    }
+
+    /*
+     * If there are no capabilities configured, set the R5 to the index of
+     * the first supported Power Processor Mode
+     */
+    if (!capabilities) {
+        env->gpr[4] = 1;
+
+        /* set R5 to the first supported Power Processor Mode */
+        if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0,
+                             spapr->max_compat_pvr)) {
+            env->gpr[5] = H_GUEST_CAP_P10_MODE_BMAP;
+        } else if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0,
+                                    spapr->max_compat_pvr)) {
+            env->gpr[5] = H_GUEST_CAP_P9_MODE_BMAP;
+        }
+
+        return H_P2;
+    }
+
+    /*
+     * If an invalid capability is set, R5 should contain the index of the
+     * invalid capability bit
+     */
+    if (capabilities & ~H_GUEST_CAP_VALID_MASK) {
+        env->gpr[4] = 1;
+
+        /* Set R5 to the index of the invalid capability */
+        env->gpr[5] = 63 - ctz64(capabilities);
+
+        return H_P2;
+    }
+
+    if (!spapr->nested.capabilities_set) {
+        spapr->nested.capabilities_set = true;
+        spapr->nested.pvr_base = env->spr[SPR_PVR];
+        return H_SUCCESS;
+    } else {
+        return H_STATE;
+    }
+}
+
+static void
+destroy_guest_helper(gpointer value)
+{
+    struct SpaprMachineStateNestedGuest *guest = value;
+    g_free(guest->vcpus);
+    g_free(guest);
+}
+
+static target_ulong h_guest_create(PowerPCCPU *cpu,
+                                   SpaprMachineState *spapr,
+                                   target_ulong opcode,
+                                   target_ulong *args)
+{
+    CPUPPCState *env = &cpu->env;
+    target_ulong flags = args[0];
+    target_ulong continue_token = args[1];
+    uint64_t guestid;
+    int nguests = 0;
+    struct SpaprMachineStateNestedGuest *guest;
+
+    if (flags) { /* don't handle any flags for now */
+        return H_UNSUPPORTED_FLAG;
+    }
+
+    if (continue_token != -1) {
+        return H_P2;
+    }
+
+    if (!spapr->nested.capabilities_set) {
+        return H_STATE;
+    }
+
+    if (!spapr->nested.guests) {
+        spapr->nested.guests = g_hash_table_new_full(NULL,
+                                                     NULL,
+                                                     NULL,
+                                                     destroy_guest_helper);
+    }
+
+    nguests = g_hash_table_size(spapr->nested.guests);
+
+    if (nguests == PAPR_NESTED_GUEST_MAX) {
+        return H_NO_MEM;
+    }
+
+    /* Lookup for available guestid */
+    for (guestid = 1; guestid < PAPR_NESTED_GUEST_MAX; guestid++) {
+        if (!(g_hash_table_lookup(spapr->nested.guests,
+                                  GINT_TO_POINTER(guestid)))) {
+            break;
+        }
+    }
+
+    if (guestid == PAPR_NESTED_GUEST_MAX) {
+        return H_NO_MEM;
+    }
+
+    guest = g_try_new0(struct SpaprMachineStateNestedGuest, 1);
+    if (!guest) {
+        return H_NO_MEM;
+    }
+
+    guest->pvr_logical = spapr->nested.pvr_base;
+    g_hash_table_insert(spapr->nested.guests, GINT_TO_POINTER(guestid), guest);
+    env->gpr[4] = guestid;
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_guest_delete(PowerPCCPU *cpu,
+                                   SpaprMachineState *spapr,
+                                   target_ulong opcode,
+                                   target_ulong *args)
+{
+    target_ulong flags = args[0];
+    target_ulong guestid = args[1];
+    struct SpaprMachineStateNestedGuest *guest;
+
+    /*
+     * handle flag deleteAllGuests, if set:
+     * guestid is ignored and all guests are deleted
+     *
+     */
+    if (flags & ~H_GUEST_DELETE_ALL_FLAG) {
+        return H_UNSUPPORTED_FLAG; /* other flag bits reserved */
+    } else if (flags & H_GUEST_DELETE_ALL_FLAG) {
+        g_hash_table_destroy(spapr->nested.guests);
+        return H_SUCCESS;
+    }
+
+    guest = g_hash_table_lookup(spapr->nested.guests, GINT_TO_POINTER(guestid));
+    if (!guest) {
+        return H_P2;
+    }
+
+    g_hash_table_remove(spapr->nested.guests, GINT_TO_POINTER(guestid));
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_guest_create_vcpu(PowerPCCPU *cpu,
+                                        SpaprMachineState *spapr,
+                                        target_ulong opcode,
+                                        target_ulong *args)
+{
+    target_ulong flags = args[0];
+    target_ulong guestid = args[1];
+    target_ulong vcpuid = args[2];
+    SpaprMachineStateNestedGuest *guest;
+
+    if (flags) { /* don't handle any flags for now */
+        return H_UNSUPPORTED_FLAG;
+    }
+
+    guest = spapr_get_nested_guest(spapr, guestid);
+    if (!guest) {
+        return H_P2;
+    }
+
+    if (vcpuid < guest->nr_vcpus) {
+        qemu_log_mask(LOG_UNIMP, "vcpuid " TARGET_FMT_ld " already in use.",
+                      vcpuid);
+        return H_IN_USE;
+    }
+    /* linear vcpuid allocation only */
+    assert(vcpuid == guest->nr_vcpus);
+
+    if (guest->nr_vcpus >= PAPR_NESTED_GUEST_VCPU_MAX) {
+        return H_P3;
+    }
+
+    SpaprMachineStateNestedGuestVcpu *vcpus, *curr_vcpu;
+    vcpus = g_try_renew(struct SpaprMachineStateNestedGuestVcpu,
+                        guest->vcpus,
+                        guest->nr_vcpus + 1);
+    if (!vcpus) {
+        return H_NO_MEM;
+    }
+    guest->vcpus = vcpus;
+    curr_vcpu = &vcpus[guest->nr_vcpus];
+    memset(curr_vcpu, 0, sizeof(SpaprMachineStateNestedGuestVcpu));
+
+    curr_vcpu->enabled = true;
+    guest->nr_vcpus++;
+
+    return H_SUCCESS;
+}
+
+static target_ulong getset_state(SpaprMachineStateNestedGuest *guest,
+                                 uint64_t vcpuid,
+                                 struct guest_state_request *gsr)
+{
+    void *ptr;
+    uint16_t id;
+    struct guest_state_element *element;
+    struct guest_state_element_type *type;
+    int64_t lenleft, num_elements;
+
+    lenleft = gsr->len;
+
+    if (!guest_state_request_check(gsr)) {
+        return H_P3;
+    }
+
+    num_elements = be32_to_cpu(gsr->gsb->num_elements);
+    element = gsr->gsb->elements;
+    /* Process the elements */
+    while (num_elements) {
+        type = NULL;
+        /* log_element(element, gsr); */
+
+        id = be16_to_cpu(element->id);
+        if (id == GSB_HV_VCPU_IGNORED_ID) {
+            goto next_element;
+        }
+
+        type = guest_state_element_type_find(id);
+        assert(type);
+
+        /* Get pointer to guest data to get/set */
+        if (type->location && type->copy) {
+            ptr = type->location(guest, vcpuid);
+            assert(ptr);
+            if (!~(type->mask) && is_gsr_invalid(gsr, element, type)) {
+                return H_INVALID_ELEMENT_VALUE;
+            }
+            type->copy(ptr + type->offset, element->value,
+                       gsr->flags & GUEST_STATE_REQUEST_SET ? true : false);
+        }
+
+next_element:
+        element = guest_state_element_next(element, &lenleft, &num_elements);
+    }
+
+    return H_SUCCESS;
+}
+
+static target_ulong map_and_getset_state(PowerPCCPU *cpu,
+                                         SpaprMachineStateNestedGuest *guest,
+                                         uint64_t vcpuid,
+                                         struct guest_state_request *gsr)
+{
+    target_ulong rc;
+    int64_t len;
+    bool is_write;
+
+    len = gsr->len;
+    /* only get_state would require write access to the provided buffer */
+    is_write = (gsr->flags & GUEST_STATE_REQUEST_SET) ? false : true;
+    gsr->gsb = address_space_map(CPU(cpu)->as, gsr->buf, (uint64_t *)&len,
+                                 is_write, MEMTXATTRS_UNSPECIFIED);
+    if (!gsr->gsb) {
+        rc = H_P3;
+        goto out1;
+    }
+
+    if (len != gsr->len) {
+        rc = H_P3;
+        goto out1;
+    }
+
+    rc = getset_state(guest, vcpuid, gsr);
+
+out1:
+    address_space_unmap(CPU(cpu)->as, gsr->gsb, len, is_write, len);
+    return rc;
+}
+
+static target_ulong h_guest_getset_state(PowerPCCPU *cpu,
+                                         SpaprMachineState *spapr,
+                                         target_ulong *args,
+                                         bool set)
+{
+    target_ulong flags = args[0];
+    target_ulong lpid = args[1];
+    target_ulong vcpuid = args[2];
+    target_ulong buf = args[3];
+    target_ulong buflen = args[4];
+    struct guest_state_request gsr;
+    SpaprMachineStateNestedGuest *guest;
+
+    guest = spapr_get_nested_guest(spapr, lpid);
+    if (!guest) {
+        return H_P2;
+    }
+    gsr.buf = buf;
+    assert(buflen <= GSB_MAX_BUF_SIZE);
+    gsr.len = buflen;
+    gsr.flags = 0;
+    if (flags & H_GUEST_GETSET_STATE_FLAG_GUEST_WIDE) {
+        gsr.flags |= GUEST_STATE_REQUEST_GUEST_WIDE;
+    }
+    if (flags & !H_GUEST_GETSET_STATE_FLAG_GUEST_WIDE) {
+        return H_PARAMETER; /* flag not supported yet */
+    }
+
+    if (set) {
+        gsr.flags |= GUEST_STATE_REQUEST_SET;
+    }
+    return map_and_getset_state(cpu, guest, vcpuid, &gsr);
+}
+
+static target_ulong h_guest_set_state(PowerPCCPU *cpu,
+                                      SpaprMachineState *spapr,
+                                      target_ulong opcode,
+                                      target_ulong *args)
+{
+    return h_guest_getset_state(cpu, spapr, args, true);
+}
+
+static target_ulong h_guest_get_state(PowerPCCPU *cpu,
+                                      SpaprMachineState *spapr,
+                                      target_ulong opcode,
+                                      target_ulong *args)
+{
+    return h_guest_getset_state(cpu, spapr, args, false);
+}
+
+static void exit_nested_store_l2(PowerPCCPU *cpu, int excp,
+                                 SpaprMachineStateNestedGuestVcpu *vcpu)
+{
+    CPUPPCState *env = &cpu->env;
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+    target_ulong now, hdar, hdsisr, asdr;
+
+    assert(sizeof(env->gpr) == sizeof(vcpu->state.gpr)); /* sanity check */
+
+    now = cpu_ppc_load_tbl(env); /* L2 timebase */
+    now -= vcpu->tb_offset; /* L1 timebase */
+    vcpu->state.dec_expiry_tb = now - cpu_ppc_load_decr(env);
+    cpu_ppc_store_decr(env, spapr_cpu->nested_host_state->dec_expiry_tb - now);
+    /* backup hdar, hdsisr, asdr if reqd later below */
+    hdar   = vcpu->state.hdar;
+    hdsisr = vcpu->state.hdsisr;
+    asdr   = vcpu->state.asdr;
+
+    nested_save_state(&vcpu->state, cpu);
+
+    if (excp == POWERPC_EXCP_MCHECK ||
+        excp == POWERPC_EXCP_RESET ||
+        excp == POWERPC_EXCP_SYSCALL) {
+        vcpu->state.nip = env->spr[SPR_SRR0];
+        vcpu->state.msr = env->spr[SPR_SRR1] & env->msr_mask;
+    } else {
+        vcpu->state.nip = env->spr[SPR_HSRR0];
+        vcpu->state.msr = env->spr[SPR_HSRR1] & env->msr_mask;
+    }
+
+    /* hdar, hdsisr, asdr should be retained unless certain exceptions */
+    if ((excp != POWERPC_EXCP_HDSI) && (excp != POWERPC_EXCP_HISI)) {
+        vcpu->state.asdr = asdr;
+    } else if (excp != POWERPC_EXCP_HDSI) {
+        vcpu->state.hdar   = hdar;
+        vcpu->state.hdsisr = hdsisr;
+    }
+}
+
+static int get_exit_ids(uint64_t srr0, uint16_t ids[16])
+{
+    int nr;
+
+    switch (srr0) {
+    case 0xc00:
+        nr = 10;
+        ids[0] = GSB_VCPU_GPR3;
+        ids[1] = GSB_VCPU_GPR4;
+        ids[2] = GSB_VCPU_GPR5;
+        ids[3] = GSB_VCPU_GPR6;
+        ids[4] = GSB_VCPU_GPR7;
+        ids[5] = GSB_VCPU_GPR8;
+        ids[6] = GSB_VCPU_GPR9;
+        ids[7] = GSB_VCPU_GPR10;
+        ids[8] = GSB_VCPU_GPR11;
+        ids[9] = GSB_VCPU_GPR12;
+        break;
+    case 0xe00:
+        nr = 5;
+        ids[0] = GSB_VCPU_SPR_HDAR;
+        ids[1] = GSB_VCPU_SPR_HDSISR;
+        ids[2] = GSB_VCPU_SPR_ASDR;
+        ids[3] = GSB_VCPU_SPR_NIA;
+        ids[4] = GSB_VCPU_SPR_MSR;
+        break;
+    case 0xe20:
+        nr = 4;
+        ids[0] = GSB_VCPU_SPR_HDAR;
+        ids[1] = GSB_VCPU_SPR_ASDR;
+        ids[2] = GSB_VCPU_SPR_NIA;
+        ids[3] = GSB_VCPU_SPR_MSR;
+        break;
+    case 0xe40:
+        nr = 3;
+        ids[0] = GSB_VCPU_SPR_HEIR;
+        ids[1] = GSB_VCPU_SPR_NIA;
+        ids[2] = GSB_VCPU_SPR_MSR;
+        break;
+    case 0xf80:
+        nr = 3;
+        ids[0] = GSB_VCPU_SPR_HFSCR;
+        ids[1] = GSB_VCPU_SPR_NIA;
+        ids[2] = GSB_VCPU_SPR_MSR;
+        break;
+    default:
+        nr = 0;
+        break;
+    }
+
+    return nr;
+}
+
+static void exit_process_output_buffer(PowerPCCPU *cpu,
+                                       SpaprMachineStateNestedGuest *guest,
+                                       target_ulong vcpuid,
+                                       target_ulong *r3)
+{
+    SpaprMachineStateNestedGuestVcpu *vcpu = &guest->vcpus[vcpuid];
+    struct guest_state_request gsr;
+    struct guest_state_buffer *gsb;
+    struct guest_state_element *element;
+    struct guest_state_element_type *type;
+    int exit_id_count = 0;
+    uint16_t exit_cause_ids[16];
+    hwaddr len;
+
+    len = vcpu->runbufout.size;
+    gsb = address_space_map(CPU(cpu)->as, vcpu->runbufout.addr, &len, true,
+                            MEMTXATTRS_UNSPECIFIED);
+    if (!gsb || len != vcpu->runbufout.size) {
+        address_space_unmap(CPU(cpu)->as, gsb, len, true, len);
+        *r3 = H_P2;
+        return;
+    }
+
+    exit_id_count = get_exit_ids(*r3, exit_cause_ids);
+
+    /* Create a buffer of elements to send back */
+    gsb->num_elements = cpu_to_be32(exit_id_count);
+    element = gsb->elements;
+    for (int i = 0; i < exit_id_count; i++) {
+        type = guest_state_element_type_find(exit_cause_ids[i]);
+        assert(type);
+        element->id = cpu_to_be16(exit_cause_ids[i]);
+        element->size = cpu_to_be16(type->size);
+        element = guest_state_element_next(element, NULL, NULL);
+    }
+    gsr.gsb = gsb;
+    gsr.len = VCPU_OUT_BUF_MIN_SZ;
+    gsr.flags = 0; /* get + never guest wide */
+    getset_state(guest, vcpuid, &gsr);
+
+    address_space_unmap(CPU(cpu)->as, gsb, len, true, len);
+    return;
+}
+
+static
+void spapr_exit_nested_papr(SpaprMachineState *spapr, PowerPCCPU *cpu, int excp)
+{
+    CPUPPCState *env = &cpu->env;
+    CPUState *cs = CPU(cpu);
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+    target_ulong r3_return = env->excp_vectors[excp]; /* hcall return value */
+    target_ulong lpid = 0, vcpuid = 0;
+    struct SpaprMachineStateNestedGuestVcpu *vcpu = NULL;
+    struct SpaprMachineStateNestedGuest *guest = NULL;
+
+    lpid = spapr_cpu->nested_host_state->gpr[5];
+    vcpuid = spapr_cpu->nested_host_state->gpr[6];
+    guest = spapr_get_nested_guest(spapr, lpid);
+    assert(guest);
+    spapr_nested_vcpu_check(guest, vcpuid, false);
+    vcpu = &guest->vcpus[vcpuid];
+
+    exit_nested_store_l2(cpu, excp, vcpu);
+    /* do the output buffer for run_vcpu*/
+    exit_process_output_buffer(cpu, guest, vcpuid, &r3_return);
+
+    assert(env->spr[SPR_LPIDR] != 0);
+    nested_load_state(cpu, spapr_cpu->nested_host_state);
+    cpu_ppc_decrease_tb_by_offset(env, vcpu->tb_offset);
+    env->gpr[3] = H_SUCCESS;
+    env->gpr[4] = r3_return;
+    nested_post_load_state(env, cs);
+    cpu_ppc_hdecr_exit(env);
+
+    spapr_cpu->in_nested = false;
+    g_free(spapr_cpu->nested_host_state);
+    spapr_cpu->nested_host_state = NULL;
+}
+
+void spapr_exit_nested(PowerPCCPU *cpu, int excp)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+
+    assert(spapr_cpu->in_nested);
+    if (spapr_nested_api(spapr) == NESTED_API_KVM_HV) {
+        spapr_exit_nested_hv(cpu, excp);
+    } else if (spapr_nested_api(spapr) == NESTED_API_PAPR) {
+        spapr_exit_nested_papr(spapr, cpu, excp);
+    } else {
+        g_assert_not_reached();
+    }
+}
+
+static void nested_papr_load_l2(PowerPCCPU *cpu,
+                                CPUPPCState *env,
+                                SpaprMachineStateNestedGuestVcpu *vcpu,
+                                target_ulong now)
+{
+    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
+    target_ulong lpcr, lpcr_mask, hdec;
+    lpcr_mask = LPCR_DPFD | LPCR_ILE | LPCR_AIL | LPCR_LD | LPCR_MER;
+
+    assert(vcpu);
+    assert(sizeof(env->gpr) == sizeof(vcpu->state.gpr));
+    nested_load_state(cpu, &vcpu->state);
+    lpcr = (env->spr[SPR_LPCR] & ~lpcr_mask) |
+           (vcpu->state.lpcr & lpcr_mask);
+    lpcr |= LPCR_HR | LPCR_UPRT | LPCR_GTSE | LPCR_HVICE | LPCR_HDICE;
+    lpcr &= ~LPCR_LPES0;
+    env->spr[SPR_LPCR] = lpcr & pcc->lpcr_mask;
+
+    hdec = vcpu->hdecr_expiry_tb - now;
+    cpu_ppc_store_decr(env, vcpu->state.dec_expiry_tb - now);
+    cpu_ppc_hdecr_init(env);
+    cpu_ppc_store_hdecr(env, hdec);
+
+    cpu_ppc_increase_tb_by_offset(env, vcpu->tb_offset);
+}
+
+static void nested_papr_run_vcpu(PowerPCCPU *cpu,
+                                 uint64_t lpid,
+                                 SpaprMachineStateNestedGuestVcpu *vcpu)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    CPUPPCState *env = &cpu->env;
+    CPUState *cs = CPU(cpu);
+    SpaprCpuState *spapr_cpu = spapr_cpu_state(cpu);
+    target_ulong now = cpu_ppc_load_tbl(env);
+
+    assert(env->spr[SPR_LPIDR] == 0);
+    assert(spapr->nested.api); /* ensure API version is initialized */
+    spapr_cpu->nested_host_state = g_try_new(struct nested_ppc_state, 1);
+    assert(spapr_cpu->nested_host_state);
+    nested_save_state(spapr_cpu->nested_host_state, cpu);
+    spapr_cpu->nested_host_state->dec_expiry_tb = now - cpu_ppc_load_decr(env);
+    nested_papr_load_l2(cpu, env, vcpu, now);
+    env->spr[SPR_LPIDR] = lpid; /* post load l2 */
+
+    spapr_cpu->in_nested = true;
+    nested_post_load_state(env, cs);
+}
+
+static target_ulong h_guest_run_vcpu(PowerPCCPU *cpu,
+                                     SpaprMachineState *spapr,
+                                     target_ulong opcode,
+                                     target_ulong *args)
+{
+    CPUPPCState *env = &cpu->env;
+    target_ulong flags = args[0];
+    target_ulong lpid = args[1];
+    target_ulong vcpuid = args[2];
+    struct SpaprMachineStateNestedGuestVcpu *vcpu;
+    struct guest_state_request gsr;
+    SpaprMachineStateNestedGuest *guest;
+    target_ulong rc;
+
+    if (flags) /* don't handle any flags for now */
+        return H_PARAMETER;
+
+    guest = spapr_get_nested_guest(spapr, lpid);
+    if (!guest) {
+        return H_P2;
+    }
+    if (!spapr_nested_vcpu_check(guest, vcpuid, true)) {
+        return H_P3;
+    }
+
+    if (guest->parttbl[0] == 0) {
+        /* At least need a partition scoped radix tree */
+        return H_NOT_AVAILABLE;
+    }
+
+    vcpu = &guest->vcpus[vcpuid];
+
+    /* Read run_vcpu input buffer to update state */
+    gsr.buf = vcpu->runbufin.addr;
+    gsr.len = vcpu->runbufin.size;
+    gsr.flags = GUEST_STATE_REQUEST_SET; /* Thread wide + writing */
+    rc = map_and_getset_state(cpu, guest, vcpuid, &gsr);
+    if (rc == H_SUCCESS) {
+        nested_papr_run_vcpu(cpu, lpid, vcpu);
+    } else {
+        env->gpr[3] = rc;
+    }
+    return env->gpr[3];
+}
+
+void spapr_register_nested_hv(void)
 {
     spapr_register_hypercall(KVMPPC_H_SET_PARTITION_TABLE, h_set_ptbl);
     spapr_register_hypercall(KVMPPC_H_ENTER_NESTED, h_enter_nested);
     spapr_register_hypercall(KVMPPC_H_TLB_INVALIDATE, h_tlb_invalidate);
     spapr_register_hypercall(KVMPPC_H_COPY_TOFROM_GUEST, h_copy_tofrom_guest);
 }
+
+void spapr_unregister_nested_hv(void)
+{
+    spapr_unregister_hypercall(KVMPPC_H_SET_PARTITION_TABLE);
+    spapr_unregister_hypercall(KVMPPC_H_ENTER_NESTED);
+    spapr_unregister_hypercall(KVMPPC_H_TLB_INVALIDATE);
+    spapr_unregister_hypercall(KVMPPC_H_COPY_TOFROM_GUEST);
+}
+
+void spapr_register_nested_papr(void)
+{
+    spapr_register_hypercall(H_GUEST_GET_CAPABILITIES,
+                             h_guest_get_capabilities);
+    spapr_register_hypercall(H_GUEST_SET_CAPABILITIES,
+                             h_guest_set_capabilities);
+    spapr_register_hypercall(H_GUEST_CREATE, h_guest_create);
+    spapr_register_hypercall(H_GUEST_DELETE, h_guest_delete);
+    spapr_register_hypercall(H_GUEST_CREATE_VCPU, h_guest_create_vcpu);
+    spapr_register_hypercall(H_GUEST_SET_STATE, h_guest_set_state);
+    spapr_register_hypercall(H_GUEST_GET_STATE, h_guest_get_state);
+    spapr_register_hypercall(H_GUEST_RUN_VCPU, h_guest_run_vcpu);
+}
+
+void spapr_unregister_nested_papr(void)
+{
+    spapr_unregister_hypercall(H_GUEST_GET_CAPABILITIES);
+    spapr_unregister_hypercall(H_GUEST_SET_CAPABILITIES);
+    spapr_unregister_hypercall(H_GUEST_CREATE);
+    spapr_unregister_hypercall(H_GUEST_DELETE);
+    spapr_unregister_hypercall(H_GUEST_CREATE_VCPU);
+    spapr_unregister_hypercall(H_GUEST_SET_STATE);
+    spapr_unregister_hypercall(H_GUEST_GET_STATE);
+    spapr_unregister_hypercall(H_GUEST_RUN_VCPU);
+}
+
 #else
 void spapr_exit_nested(PowerPCCPU *cpu, int excp)
 {
     g_assert_not_reached();
 }
 
-void spapr_register_nested(void)
+void spapr_register_nested_hv(void)
 {
     /* DO NOTHING */
 }
+
+void spapr_unregister_nested_hv(void)
+{
+    /* DO NOTHING */
+}
+
+bool spapr_get_pate_nested_hv(SpaprMachineState *spapr, PowerPCCPU *cpu,
+                              target_ulong lpid, ppc_v3_pate_t *entry)
+{
+    return false;
+}
+
+bool spapr_get_pate_nested_papr(SpaprMachineState *spapr, PowerPCCPU *cpu,
+                                target_ulong lpid, ppc_v3_pate_t *entry)
+{
+    return false;
+}
+
+void spapr_register_nested_papr(void)
+{
+    /* DO NOTHING */
+}
+
+void spapr_unregister_nested_papr(void)
+{
+    /* DO NOTHING */
+}
+
+void spapr_nested_gsb_init(void)
+{
+    /* DO NOTHING */
+}
+
 #endif