/*
 * QEMU PowerPC pSeries Logical Partition (aka sPAPR) hardware System Emulator
 *
 * Copyright (c) 2004-2007 Fabrice Bellard
 * Copyright (c) 2007 Jocelyn Mayer
 * Copyright (c) 2010 David Gibson, IBM Corporation.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/datadir.h"
#include "qapi/error.h"
#include "qapi/qapi-events-machine.h"
#include "qapi/qapi-events-qdev.h"
#include "qapi/visitor.h"
#include "sysemu/sysemu.h"
#include "sysemu/hostmem.h"
#include "sysemu/numa.h"
#include "sysemu/qtest.h"
#include "sysemu/reset.h"
#include "sysemu/runstate.h"
#include "qemu/log.h"
#include "hw/fw-path-provider.h"
#include "elf.h"
#include "net/net.h"
#include "sysemu/device_tree.h"
#include "sysemu/cpus.h"
#include "sysemu/hw_accel.h"
#include "kvm_ppc.h"
#include "migration/misc.h"
#include "migration/qemu-file-types.h"
#include "migration/global_state.h"
#include "migration/register.h"
#include "migration/blocker.h"
#include "mmu-hash64.h"
#include "mmu-book3s-v3.h"
#include "cpu-models.h"
#include "hw/core/cpu.h"

#include "hw/ppc/ppc.h"
#include "hw/loader.h"

#include "hw/ppc/fdt.h"
#include "hw/ppc/spapr.h"
#include "hw/ppc/spapr_vio.h"
#include "hw/qdev-properties.h"
#include "hw/pci-host/spapr.h"
#include "hw/pci/msi.h"

#include "hw/pci/pci.h"
#include "hw/scsi/scsi.h"
#include "hw/virtio/virtio-scsi.h"
#include "hw/virtio/vhost-scsi-common.h"

#include "exec/ram_addr.h"
#include "hw/usb.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "hw/nmi.h"
#include "hw/intc/intc.h"

#include "hw/ppc/spapr_cpu_core.h"
#include "hw/mem/memory-device.h"
#include "hw/ppc/spapr_tpm_proxy.h"
#include "hw/ppc/spapr_nvdimm.h"
#include "hw/ppc/spapr_numa.h"
#include "hw/ppc/pef.h"

#include "monitor/monitor.h"

#include <libfdt.h>

/* SLOF memory layout:
 *
 * SLOF raw image loaded at 0, copies its romfs right below the flat
 * device-tree, then position SLOF itself 31M below that
 *
 * So we set FW_OVERHEAD to 40MB which should account for all of that
 * and more
 *
 * We load our kernel at 4M, leaving space for SLOF initial image
 */
#define FDT_MAX_ADDR            0x80000000 /* FDT must stay below that */
#define FW_MAX_SIZE             0x400000
#define FW_FILE_NAME            "slof.bin"
#define FW_FILE_NAME_VOF        "vof.bin"
#define FW_OVERHEAD             0x2800000
#define KERNEL_LOAD_ADDR        FW_MAX_SIZE

#define MIN_RMA_SLOF            (128 * MiB)

#define PHANDLE_INTC            0x00001111

/* These two functions implement the VCPU id numbering: one to compute them
 * all and one to identify thread 0 of a VCORE. Any change to the first one
 * is likely to have an impact on the second one, so let's keep them close.
 */
static int spapr_vcpu_id(SpaprMachineState *spapr, int cpu_index)
{
    MachineState *ms = MACHINE(spapr);
    unsigned int smp_threads = ms->smp.threads;

    assert(spapr->vsmt);
    return
        (cpu_index / smp_threads) * spapr->vsmt + cpu_index % smp_threads;
}
static bool spapr_is_thread0_in_vcore(SpaprMachineState *spapr,
                                      PowerPCCPU *cpu)
{
    assert(spapr->vsmt);
    return spapr_get_vcpu_id(cpu) % spapr->vsmt == 0;
}

static bool pre_2_10_vmstate_dummy_icp_needed(void *opaque)
{
    /* Dummy entries correspond to unused ICPState objects in older QEMUs,
     * and newer QEMUs don't even have them. In both cases, we don't want
     * to send anything on the wire.
     */
    return false;
}

static const VMStateDescription pre_2_10_vmstate_dummy_icp = {
    .name = "icp/server",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = pre_2_10_vmstate_dummy_icp_needed,
    .fields = (VMStateField[]) {
        VMSTATE_UNUSED(4), /* uint32_t xirr */
        VMSTATE_UNUSED(1), /* uint8_t pending_priority */
        VMSTATE_UNUSED(1), /* uint8_t mfrr */
        VMSTATE_END_OF_LIST()
    },
};

static void pre_2_10_vmstate_register_dummy_icp(int i)
{
    vmstate_register(NULL, i, &pre_2_10_vmstate_dummy_icp,
                     (void *)(uintptr_t) i);
}

static void pre_2_10_vmstate_unregister_dummy_icp(int i)
{
    vmstate_unregister(NULL, &pre_2_10_vmstate_dummy_icp,
                       (void *)(uintptr_t) i);
}

int spapr_max_server_number(SpaprMachineState *spapr)
{
    MachineState *ms = MACHINE(spapr);

    assert(spapr->vsmt);
    return DIV_ROUND_UP(ms->smp.max_cpus * spapr->vsmt, ms->smp.threads);
}

static int spapr_fixup_cpu_smt_dt(void *fdt, int offset, PowerPCCPU *cpu,
                                  int smt_threads)
{
    int i, ret = 0;
    uint32_t servers_prop[smt_threads];
    uint32_t gservers_prop[smt_threads * 2];
    int index = spapr_get_vcpu_id(cpu);

    if (cpu->compat_pvr) {
        ret = fdt_setprop_cell(fdt, offset, "cpu-version", cpu->compat_pvr);
        if (ret < 0) {
            return ret;
        }
    }

    /* Build interrupt servers and gservers properties */
    for (i = 0; i < smt_threads; i++) {
        servers_prop[i] = cpu_to_be32(index + i);
        /* Hack, direct the group queues back to cpu 0 */
        gservers_prop[i*2] = cpu_to_be32(index + i);
        gservers_prop[i*2 + 1] = 0;
    }
    ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-server#s",
                      servers_prop, sizeof(servers_prop));
    if (ret < 0) {
        return ret;
    }
    ret = fdt_setprop(fdt, offset, "ibm,ppc-interrupt-gserver#s",
                      gservers_prop, sizeof(gservers_prop));

    return ret;
}

static void spapr_dt_pa_features(SpaprMachineState *spapr,
                                 PowerPCCPU *cpu,
                                 void *fdt, int offset)
{
    uint8_t pa_features_206[] = { 6, 0,
        0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
    uint8_t pa_features_207[] = { 24, 0,
        0xf6, 0x1f, 0xc7, 0xc0, 0x80, 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 */
        /* 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, 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 */
        /* 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 */
    };
    uint8_t *pa_features = NULL;
    size_t pa_size;

    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_2_06, 0, cpu->compat_pvr)) {
        pa_features = pa_features_206;
        pa_size = sizeof(pa_features_206);
    }
    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_2_07, 0, cpu->compat_pvr)) {
        pa_features = pa_features_207;
        pa_size = sizeof(pa_features_207);
    }
    if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, cpu->compat_pvr)) {
        pa_features = pa_features_300;
        pa_size = sizeof(pa_features_300);
    }
    if (!pa_features) {
        return;
    }

    if (ppc_hash64_has(cpu, PPC_HASH64_CI_LARGEPAGE)) {
        /*
         * Note: we keep CI large pages off by default because a 64K capable
         * guest provisioned with large pages might otherwise try to map a qemu
         * framebuffer (or other kind of memory mapped PCI BAR) using 64K pages
         * even if that qemu runs on a 4k host.
         * We dd this bit back here if we are confident this is not an issue
         */
        pa_features[3] |= 0x20;
    }
    if ((spapr_get_cap(spapr, SPAPR_CAP_HTM) != 0) && pa_size > 24) {
        pa_features[24] |= 0x80;    /* Transactional memory support */
    }
    if (spapr->cas_pre_isa3_guest && pa_size > 40) {
        /* Workaround for broken kernels that attempt (guest) radix
         * mode when they can't handle it, if they see the radix bit set
         * in pa-features. So hide it from them. */
        pa_features[40 + 2] &= ~0x80; /* Radix MMU */
    }

    _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
}

static hwaddr spapr_node0_size(MachineState *machine)
{
    if (machine->numa_state->num_nodes) {
        int i;
        for (i = 0; i < machine->numa_state->num_nodes; ++i) {
            if (machine->numa_state->nodes[i].node_mem) {
                return MIN(pow2floor(machine->numa_state->nodes[i].node_mem),
                           machine->ram_size);
            }
        }
    }
    return machine->ram_size;
}

static void add_str(GString *s, const gchar *s1)
{
    g_string_append_len(s, s1, strlen(s1) + 1);
}

static int spapr_dt_memory_node(SpaprMachineState *spapr, void *fdt, int nodeid,
                                hwaddr start, hwaddr size)
{
    char mem_name[32];
    uint64_t mem_reg_property[2];
    int off;

    mem_reg_property[0] = cpu_to_be64(start);
    mem_reg_property[1] = cpu_to_be64(size);

    sprintf(mem_name, "memory@%" HWADDR_PRIx, start);
    off = fdt_add_subnode(fdt, 0, mem_name);
    _FDT(off);
    _FDT((fdt_setprop_string(fdt, off, "device_type", "memory")));
    _FDT((fdt_setprop(fdt, off, "reg", mem_reg_property,
                      sizeof(mem_reg_property))));
    spapr_numa_write_associativity_dt(spapr, fdt, off, nodeid);
    return off;
}

static uint32_t spapr_pc_dimm_node(MemoryDeviceInfoList *list, ram_addr_t addr)
{
    MemoryDeviceInfoList *info;

    for (info = list; info; info = info->next) {
        MemoryDeviceInfo *value = info->value;

        if (value && value->type == MEMORY_DEVICE_INFO_KIND_DIMM) {
            PCDIMMDeviceInfo *pcdimm_info = value->u.dimm.data;

            if (addr >= pcdimm_info->addr &&
                addr < (pcdimm_info->addr + pcdimm_info->size)) {
                return pcdimm_info->node;
            }
        }
    }

    return -1;
}

struct sPAPRDrconfCellV2 {
     uint32_t seq_lmbs;
     uint64_t base_addr;
     uint32_t drc_index;
     uint32_t aa_index;
     uint32_t flags;
} QEMU_PACKED;

typedef struct DrconfCellQueue {
    struct sPAPRDrconfCellV2 cell;
    QSIMPLEQ_ENTRY(DrconfCellQueue) entry;
} DrconfCellQueue;

static DrconfCellQueue *
spapr_get_drconf_cell(uint32_t seq_lmbs, uint64_t base_addr,
                      uint32_t drc_index, uint32_t aa_index,
                      uint32_t flags)
{
    DrconfCellQueue *elem;

    elem = g_malloc0(sizeof(*elem));
    elem->cell.seq_lmbs = cpu_to_be32(seq_lmbs);
    elem->cell.base_addr = cpu_to_be64(base_addr);
    elem->cell.drc_index = cpu_to_be32(drc_index);
    elem->cell.aa_index = cpu_to_be32(aa_index);
    elem->cell.flags = cpu_to_be32(flags);

    return elem;
}

static int spapr_dt_dynamic_memory_v2(SpaprMachineState *spapr, void *fdt,
                                      int offset, MemoryDeviceInfoList *dimms)
{
    MachineState *machine = MACHINE(spapr);
    uint8_t *int_buf, *cur_index;
    int ret;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint64_t addr, cur_addr, size;
    uint32_t nr_boot_lmbs = (machine->device_memory->base / lmb_size);
    uint64_t mem_end = machine->device_memory->base +
                       memory_region_size(&machine->device_memory->mr);
    uint32_t node, buf_len, nr_entries = 0;
    SpaprDrc *drc;
    DrconfCellQueue *elem, *next;
    MemoryDeviceInfoList *info;
    QSIMPLEQ_HEAD(, DrconfCellQueue) drconf_queue
        = QSIMPLEQ_HEAD_INITIALIZER(drconf_queue);

    /* Entry to cover RAM and the gap area */
    elem = spapr_get_drconf_cell(nr_boot_lmbs, 0, 0, -1,
                                 SPAPR_LMB_FLAGS_RESERVED |
                                 SPAPR_LMB_FLAGS_DRC_INVALID);
    QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
    nr_entries++;

    cur_addr = machine->device_memory->base;
    for (info = dimms; info; info = info->next) {
        PCDIMMDeviceInfo *di = info->value->u.dimm.data;

        addr = di->addr;
        size = di->size;
        node = di->node;

        /*
         * The NVDIMM area is hotpluggable after the NVDIMM is unplugged. The
         * area is marked hotpluggable in the next iteration for the bigger
         * chunk including the NVDIMM occupied area.
         */
        if (info->value->type == MEMORY_DEVICE_INFO_KIND_NVDIMM)
            continue;

        /* Entry for hot-pluggable area */
        if (cur_addr < addr) {
            drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, cur_addr / lmb_size);
            g_assert(drc);
            elem = spapr_get_drconf_cell((addr - cur_addr) / lmb_size,
                                         cur_addr, spapr_drc_index(drc), -1, 0);
            QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
            nr_entries++;
        }

        /* Entry for DIMM */
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, addr / lmb_size);
        g_assert(drc);
        elem = spapr_get_drconf_cell(size / lmb_size, addr,
                                     spapr_drc_index(drc), node,
                                     (SPAPR_LMB_FLAGS_ASSIGNED |
                                      SPAPR_LMB_FLAGS_HOTREMOVABLE));
        QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
        nr_entries++;
        cur_addr = addr + size;
    }

    /* Entry for remaining hotpluggable area */
    if (cur_addr < mem_end) {
        drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, cur_addr / lmb_size);
        g_assert(drc);
        elem = spapr_get_drconf_cell((mem_end - cur_addr) / lmb_size,
                                     cur_addr, spapr_drc_index(drc), -1, 0);
        QSIMPLEQ_INSERT_TAIL(&drconf_queue, elem, entry);
        nr_entries++;
    }

    buf_len = nr_entries * sizeof(struct sPAPRDrconfCellV2) + sizeof(uint32_t);
    int_buf = cur_index = g_malloc0(buf_len);
    *(uint32_t *)int_buf = cpu_to_be32(nr_entries);
    cur_index += sizeof(nr_entries);

    QSIMPLEQ_FOREACH_SAFE(elem, &drconf_queue, entry, next) {
        memcpy(cur_index, &elem->cell, sizeof(elem->cell));
        cur_index += sizeof(elem->cell);
        QSIMPLEQ_REMOVE(&drconf_queue, elem, DrconfCellQueue, entry);
        g_free(elem);
    }

    ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory-v2", int_buf, buf_len);
    g_free(int_buf);
    if (ret < 0) {
        return -1;
    }
    return 0;
}

static int spapr_dt_dynamic_memory(SpaprMachineState *spapr, void *fdt,
                                   int offset, MemoryDeviceInfoList *dimms)
{
    MachineState *machine = MACHINE(spapr);
    int i, ret;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t device_lmb_start = machine->device_memory->base / lmb_size;
    uint32_t nr_lmbs = (machine->device_memory->base +
                       memory_region_size(&machine->device_memory->mr)) /
                       lmb_size;
    uint32_t *int_buf, *cur_index, buf_len;

    /*
     * Allocate enough buffer size to fit in ibm,dynamic-memory
     */
    buf_len = (nr_lmbs * SPAPR_DR_LMB_LIST_ENTRY_SIZE + 1) * sizeof(uint32_t);
    cur_index = int_buf = g_malloc0(buf_len);
    int_buf[0] = cpu_to_be32(nr_lmbs);
    cur_index++;
    for (i = 0; i < nr_lmbs; i++) {
        uint64_t addr = i * lmb_size;
        uint32_t *dynamic_memory = cur_index;

        if (i >= device_lmb_start) {
            SpaprDrc *drc;

            drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, i);
            g_assert(drc);

            dynamic_memory[0] = cpu_to_be32(addr >> 32);
            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
            dynamic_memory[2] = cpu_to_be32(spapr_drc_index(drc));
            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
            dynamic_memory[4] = cpu_to_be32(spapr_pc_dimm_node(dimms, addr));
            if (memory_region_present(get_system_memory(), addr)) {
                dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED);
            } else {
                dynamic_memory[5] = cpu_to_be32(0);
            }
        } else {
            /*
             * LMB information for RMA, boot time RAM and gap b/n RAM and
             * device memory region -- all these are marked as reserved
             * and as having no valid DRC.
             */
            dynamic_memory[0] = cpu_to_be32(addr >> 32);
            dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff);
            dynamic_memory[2] = cpu_to_be32(0);
            dynamic_memory[3] = cpu_to_be32(0); /* reserved */
            dynamic_memory[4] = cpu_to_be32(-1);
            dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_RESERVED |
                                            SPAPR_LMB_FLAGS_DRC_INVALID);
        }

        cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE;
    }
    ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory", int_buf, buf_len);
    g_free(int_buf);
    if (ret < 0) {
        return -1;
    }
    return 0;
}

/*
 * Adds ibm,dynamic-reconfiguration-memory node.
 * Refer to docs/specs/ppc-spapr-hotplug.txt for the documentation
 * of this device tree node.
 */
static int spapr_dt_dynamic_reconfiguration_memory(SpaprMachineState *spapr,
                                                   void *fdt)
{
    MachineState *machine = MACHINE(spapr);
    int ret, offset;
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t prop_lmb_size[] = {cpu_to_be32(lmb_size >> 32),
                                cpu_to_be32(lmb_size & 0xffffffff)};
    MemoryDeviceInfoList *dimms = NULL;

    /*
     * Don't create the node if there is no device memory
     */
    if (machine->ram_size == machine->maxram_size) {
        return 0;
    }

    offset = fdt_add_subnode(fdt, 0, "ibm,dynamic-reconfiguration-memory");

    ret = fdt_setprop(fdt, offset, "ibm,lmb-size", prop_lmb_size,
                    sizeof(prop_lmb_size));
    if (ret < 0) {
        return ret;
    }

    ret = fdt_setprop_cell(fdt, offset, "ibm,memory-flags-mask", 0xff);
    if (ret < 0) {
        return ret;
    }

    ret = fdt_setprop_cell(fdt, offset, "ibm,memory-preservation-time", 0x0);
    if (ret < 0) {
        return ret;
    }

    /* ibm,dynamic-memory or ibm,dynamic-memory-v2 */
    dimms = qmp_memory_device_list();
    if (spapr_ovec_test(spapr->ov5_cas, OV5_DRMEM_V2)) {
        ret = spapr_dt_dynamic_memory_v2(spapr, fdt, offset, dimms);
    } else {
        ret = spapr_dt_dynamic_memory(spapr, fdt, offset, dimms);
    }
    qapi_free_MemoryDeviceInfoList(dimms);

    if (ret < 0) {
        return ret;
    }

    ret = spapr_numa_write_assoc_lookup_arrays(spapr, fdt, offset);

    return ret;
}

static int spapr_dt_memory(SpaprMachineState *spapr, void *fdt)
{
    MachineState *machine = MACHINE(spapr);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    hwaddr mem_start, node_size;
    int i, nb_nodes = machine->numa_state->num_nodes;
    NodeInfo *nodes = machine->numa_state->nodes;

    for (i = 0, mem_start = 0; i < nb_nodes; ++i) {
        if (!nodes[i].node_mem) {
            continue;
        }
        if (mem_start >= machine->ram_size) {
            node_size = 0;
        } else {
            node_size = nodes[i].node_mem;
            if (node_size > machine->ram_size - mem_start) {
                node_size = machine->ram_size - mem_start;
            }
        }
        if (!mem_start) {
            /* spapr_machine_init() checks for rma_size <= node0_size
             * already */
            spapr_dt_memory_node(spapr, fdt, i, 0, spapr->rma_size);
            mem_start += spapr->rma_size;
            node_size -= spapr->rma_size;
        }
        for ( ; node_size; ) {
            hwaddr sizetmp = pow2floor(node_size);

            /* mem_start != 0 here */
            if (ctzl(mem_start) < ctzl(sizetmp)) {
                sizetmp = 1ULL << ctzl(mem_start);
            }

            spapr_dt_memory_node(spapr, fdt, i, mem_start, sizetmp);
            node_size -= sizetmp;
            mem_start += sizetmp;
        }
    }

    /* Generate ibm,dynamic-reconfiguration-memory node if required */
    if (spapr_ovec_test(spapr->ov5_cas, OV5_DRCONF_MEMORY)) {
        int ret;

        g_assert(smc->dr_lmb_enabled);
        ret = spapr_dt_dynamic_reconfiguration_memory(spapr, fdt);
        if (ret) {
            return ret;
        }
    }

    return 0;
}

static void spapr_dt_cpu(CPUState *cs, void *fdt, int offset,
                         SpaprMachineState *spapr)
{
    MachineState *ms = MACHINE(spapr);
    PowerPCCPU *cpu = POWERPC_CPU(cs);
    CPUPPCState *env = &cpu->env;
    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cs);
    int index = spapr_get_vcpu_id(cpu);
    uint32_t segs[] = {cpu_to_be32(28), cpu_to_be32(40),
                       0xffffffff, 0xffffffff};
    uint32_t tbfreq = kvm_enabled() ? kvmppc_get_tbfreq()
        : SPAPR_TIMEBASE_FREQ;
    uint32_t cpufreq = kvm_enabled() ? kvmppc_get_clockfreq() : 1000000000;
    uint32_t page_sizes_prop[64];
    size_t page_sizes_prop_size;
    unsigned int smp_threads = ms->smp.threads;
    uint32_t vcpus_per_socket = smp_threads * ms->smp.cores;
    uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)};
    int compat_smt = MIN(smp_threads, ppc_compat_max_vthreads(cpu));
    SpaprDrc *drc;
    int drc_index;
    uint32_t radix_AP_encodings[PPC_PAGE_SIZES_MAX_SZ];
    int i;

    drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index);
    if (drc) {
        drc_index = spapr_drc_index(drc);
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index)));
    }

    _FDT((fdt_setprop_cell(fdt, offset, "reg", index)));
    _FDT((fdt_setprop_string(fdt, offset, "device_type", "cpu")));

    _FDT((fdt_setprop_cell(fdt, offset, "cpu-version", env->spr[SPR_PVR])));
    _FDT((fdt_setprop_cell(fdt, offset, "d-cache-block-size",
                           env->dcache_line_size)));
    _FDT((fdt_setprop_cell(fdt, offset, "d-cache-line-size",
                           env->dcache_line_size)));
    _FDT((fdt_setprop_cell(fdt, offset, "i-cache-block-size",
                           env->icache_line_size)));
    _FDT((fdt_setprop_cell(fdt, offset, "i-cache-line-size",
                           env->icache_line_size)));

    if (pcc->l1_dcache_size) {
        _FDT((fdt_setprop_cell(fdt, offset, "d-cache-size",
                               pcc->l1_dcache_size)));
    } else {
        warn_report("Unknown L1 dcache size for cpu");
    }
    if (pcc->l1_icache_size) {
        _FDT((fdt_setprop_cell(fdt, offset, "i-cache-size",
                               pcc->l1_icache_size)));
    } else {
        warn_report("Unknown L1 icache size for cpu");
    }

    _FDT((fdt_setprop_cell(fdt, offset, "timebase-frequency", tbfreq)));
    _FDT((fdt_setprop_cell(fdt, offset, "clock-frequency", cpufreq)));
    _FDT((fdt_setprop_cell(fdt, offset, "slb-size", cpu->hash64_opts->slb_size)));
    _FDT((fdt_setprop_cell(fdt, offset, "ibm,slb-size", cpu->hash64_opts->slb_size)));
    _FDT((fdt_setprop_string(fdt, offset, "status", "okay")));
    _FDT((fdt_setprop(fdt, offset, "64-bit", NULL, 0)));

    if (ppc_has_spr(cpu, SPR_PURR)) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,purr", 1)));
    }
    if (ppc_has_spr(cpu, SPR_PURR)) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,spurr", 1)));
    }

    if (ppc_hash64_has(cpu, PPC_HASH64_1TSEG)) {
        _FDT((fdt_setprop(fdt, offset, "ibm,processor-segment-sizes",
                          segs, sizeof(segs))));
    }

    /* Advertise VSX (vector extensions) if available
     *   1               == VMX / Altivec available
     *   2               == VSX available
     *
     * Only CPUs for which we create core types in spapr_cpu_core.c
     * are possible, and all of those have VMX */
    if (spapr_get_cap(spapr, SPAPR_CAP_VSX) != 0) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", 2)));
    } else {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,vmx", 1)));
    }

    /* Advertise DFP (Decimal Floating Point) if available
     *   0 / no property == no DFP
     *   1               == DFP available */
    if (spapr_get_cap(spapr, SPAPR_CAP_DFP) != 0) {
        _FDT((fdt_setprop_cell(fdt, offset, "ibm,dfp", 1)));
    }

    page_sizes_prop_size = ppc_create_page_sizes_prop(cpu, page_sizes_prop,
                                                      sizeof(page_sizes_prop));
    if (page_sizes_prop_size) {
        _FDT((fdt_setprop(fdt, offset, "ibm,segment-page-sizes",
                          page_sizes_prop, page_sizes_prop_size)));
    }

    spapr_dt_pa_features(spapr, cpu, fdt, offset);

    _FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
                           cs->cpu_index / vcpus_per_socket)));

    _FDT((fdt_setprop(fdt, offset, "ibm,pft-size",
                      pft_size_prop, sizeof(pft_size_prop))));

    if (ms->numa_state->num_nodes > 1) {
        _FDT(spapr_numa_fixup_cpu_dt(spapr, fdt, offset, cpu));
    }

    _FDT(spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt));

    if (pcc->radix_page_info) {
        for (i = 0; i < pcc->radix_page_info->count; i++) {
            radix_AP_encodings[i] =
                cpu_to_be32(pcc->radix_page_info->entries[i]);
        }
        _FDT((fdt_setprop(fdt, offset, "ibm,processor-radix-AP-encodings",
                          radix_AP_encodings,
                          pcc->radix_page_info->count *
                          sizeof(radix_AP_encodings[0]))));
    }

    /*
     * We set this property to let the guest know that it can use the large
     * decrementer and its width in bits.
     */
    if (spapr_get_cap(spapr, SPAPR_CAP_LARGE_DECREMENTER) != SPAPR_CAP_OFF)
        _FDT((fdt_setprop_u32(fdt, offset, "ibm,dec-bits",
                              pcc->lrg_decr_bits)));
}

static void spapr_dt_cpus(void *fdt, SpaprMachineState *spapr)
{
    CPUState **rev;
    CPUState *cs;
    int n_cpus;
    int cpus_offset;
    int i;

    cpus_offset = fdt_add_subnode(fdt, 0, "cpus");
    _FDT(cpus_offset);
    _FDT((fdt_setprop_cell(fdt, cpus_offset, "#address-cells", 0x1)));
    _FDT((fdt_setprop_cell(fdt, cpus_offset, "#size-cells", 0x0)));

    /*
     * We walk the CPUs in reverse order to ensure that CPU DT nodes
     * created by fdt_add_subnode() end up in the right order in FDT
     * for the guest kernel the enumerate the CPUs correctly.
     *
     * The CPU list cannot be traversed in reverse order, so we need
     * to do extra work.
     */
    n_cpus = 0;
    rev = NULL;
    CPU_FOREACH(cs) {
        rev = g_renew(CPUState *, rev, n_cpus + 1);
        rev[n_cpus++] = cs;
    }

    for (i = n_cpus - 1; i >= 0; i--) {
        CPUState *cs = rev[i];
        PowerPCCPU *cpu = POWERPC_CPU(cs);
        int index = spapr_get_vcpu_id(cpu);
        DeviceClass *dc = DEVICE_GET_CLASS(cs);
        g_autofree char *nodename = NULL;
        int offset;

        if (!spapr_is_thread0_in_vcore(spapr, cpu)) {
            continue;
        }

        nodename = g_strdup_printf("%s@%x", dc->fw_name, index);
        offset = fdt_add_subnode(fdt, cpus_offset, nodename);
        _FDT(offset);
        spapr_dt_cpu(cs, fdt, offset, spapr);
    }

    g_free(rev);
}

static int spapr_dt_rng(void *fdt)
{
    int node;
    int ret;

    node = qemu_fdt_add_subnode(fdt, "/ibm,platform-facilities");
    if (node <= 0) {
        return -1;
    }
    ret = fdt_setprop_string(fdt, node, "device_type",
                             "ibm,platform-facilities");
    ret |= fdt_setprop_cell(fdt, node, "#address-cells", 0x1);
    ret |= fdt_setprop_cell(fdt, node, "#size-cells", 0x0);

    node = fdt_add_subnode(fdt, node, "ibm,random-v1");
    if (node <= 0) {
        return -1;
    }
    ret |= fdt_setprop_string(fdt, node, "compatible", "ibm,random");

    return ret ? -1 : 0;
}

static void spapr_dt_rtas(SpaprMachineState *spapr, void *fdt)
{
    MachineState *ms = MACHINE(spapr);
    int rtas;
    GString *hypertas = g_string_sized_new(256);
    GString *qemu_hypertas = g_string_sized_new(256);
    uint64_t max_device_addr = MACHINE(spapr)->device_memory->base +
        memory_region_size(&MACHINE(spapr)->device_memory->mr);
    uint32_t lrdr_capacity[] = {
        cpu_to_be32(max_device_addr >> 32),
        cpu_to_be32(max_device_addr & 0xffffffff),
        cpu_to_be32(SPAPR_MEMORY_BLOCK_SIZE >> 32),
        cpu_to_be32(SPAPR_MEMORY_BLOCK_SIZE & 0xffffffff),
        cpu_to_be32(ms->smp.max_cpus / ms->smp.threads),
    };

    _FDT(rtas = fdt_add_subnode(fdt, 0, "rtas"));

    /* hypertas */
    add_str(hypertas, "hcall-pft");
    add_str(hypertas, "hcall-term");
    add_str(hypertas, "hcall-dabr");
    add_str(hypertas, "hcall-interrupt");
    add_str(hypertas, "hcall-tce");
    add_str(hypertas, "hcall-vio");
    add_str(hypertas, "hcall-splpar");
    add_str(hypertas, "hcall-join");
    add_str(hypertas, "hcall-bulk");
    add_str(hypertas, "hcall-set-mode");
    add_str(hypertas, "hcall-sprg0");
    add_str(hypertas, "hcall-copy");
    add_str(hypertas, "hcall-debug");
    add_str(hypertas, "hcall-vphn");
    if (spapr_get_cap(spapr, SPAPR_CAP_RPT_INVALIDATE) == SPAPR_CAP_ON) {
        add_str(hypertas, "hcall-rpt-invalidate");
    }

    add_str(qemu_hypertas, "hcall-memop1");

    if (!kvm_enabled() || kvmppc_spapr_use_multitce()) {
        add_str(hypertas, "hcall-multi-tce");
    }

    if (spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) {
        add_str(hypertas, "hcall-hpt-resize");
    }

    _FDT(fdt_setprop(fdt, rtas, "ibm,hypertas-functions",
                     hypertas->str, hypertas->len));
    g_string_free(hypertas, TRUE);
    _FDT(fdt_setprop(fdt, rtas, "qemu,hypertas-functions",
                     qemu_hypertas->str, qemu_hypertas->len));
    g_string_free(qemu_hypertas, TRUE);

    spapr_numa_write_rtas_dt(spapr, fdt, rtas);

    /*
     * FWNMI reserves RTAS_ERROR_LOG_MAX for the machine check error log,
     * and 16 bytes per CPU for system reset error log plus an extra 8 bytes.
     *
     * The system reset requirements are driven by existing Linux and PowerVM
     * implementation which (contrary to PAPR) saves r3 in the error log
     * structure like machine check, so Linux expects to find the saved r3
     * value at the address in r3 upon FWNMI-enabled sreset interrupt (and
     * does not look at the error value).
     *
     * System reset interrupts are not subject to interlock like machine
     * check, so this memory area could be corrupted if the sreset is
     * interrupted by a machine check (or vice versa) if it was shared. To
     * prevent this, system reset uses per-CPU areas for the sreset save
     * area. A system reset that interrupts a system reset handler could
     * still overwrite this area, but Linux doesn't try to recover in that
     * case anyway.
     *
     * The extra 8 bytes is required because Linux's FWNMI error log check
     * is off-by-one.
     *
     * RTAS_MIN_SIZE is required for the RTAS blob itself.
     */
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-size", RTAS_MIN_SIZE +
                          RTAS_ERROR_LOG_MAX +
                          ms->smp.max_cpus * sizeof(uint64_t) * 2 +
                          sizeof(uint64_t)));
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-error-log-max",
                          RTAS_ERROR_LOG_MAX));
    _FDT(fdt_setprop_cell(fdt, rtas, "rtas-event-scan-rate",
                          RTAS_EVENT_SCAN_RATE));

    g_assert(msi_nonbroken);
    _FDT(fdt_setprop(fdt, rtas, "ibm,change-msix-capable", NULL, 0));

    /*
     * According to PAPR, rtas ibm,os-term does not guarantee a return
     * back to the guest cpu.
     *
     * While an additional ibm,extended-os-term property indicates
     * that rtas call return will always occur. Set this property.
     */
    _FDT(fdt_setprop(fdt, rtas, "ibm,extended-os-term", NULL, 0));

    _FDT(fdt_setprop(fdt, rtas, "ibm,lrdr-capacity",
                     lrdr_capacity, sizeof(lrdr_capacity)));

    spapr_dt_rtas_tokens(fdt, rtas);
}

/*
 * Prepare ibm,arch-vec-5-platform-support, which indicates the MMU
 * and the XIVE features that the guest may request and thus the valid
 * values for bytes 23..26 of option vector 5:
 */
static void spapr_dt_ov5_platform_support(SpaprMachineState *spapr, void *fdt,
                                          int chosen)
{
    PowerPCCPU *first_ppc_cpu = POWERPC_CPU(first_cpu);

    char val[2 * 4] = {
        23, 0x00, /* XICS / XIVE mode */
        24, 0x00, /* Hash/Radix, filled in below. */
        25, 0x00, /* Hash options: Segment Tables == no, GTSE == no. */
        26, 0x40, /* Radix options: GTSE == yes. */
    };

    if (spapr->irq->xics && spapr->irq->xive) {
        val[1] = SPAPR_OV5_XIVE_BOTH;
    } else if (spapr->irq->xive) {
        val[1] = SPAPR_OV5_XIVE_EXPLOIT;
    } else {
        assert(spapr->irq->xics);
        val[1] = SPAPR_OV5_XIVE_LEGACY;
    }

    if (!ppc_check_compat(first_ppc_cpu, CPU_POWERPC_LOGICAL_3_00, 0,
                          first_ppc_cpu->compat_pvr)) {
        /*
         * If we're in a pre POWER9 compat mode then the guest should
         * do hash and use the legacy interrupt mode
         */
        val[1] = SPAPR_OV5_XIVE_LEGACY; /* XICS */
        val[3] = 0x00; /* Hash */
        spapr_check_mmu_mode(false);
    } else if (kvm_enabled()) {
        if (kvmppc_has_cap_mmu_radix() && kvmppc_has_cap_mmu_hash_v3()) {
            val[3] = 0x80; /* OV5_MMU_BOTH */
        } else if (kvmppc_has_cap_mmu_radix()) {
            val[3] = 0x40; /* OV5_MMU_RADIX_300 */
        } else {
            val[3] = 0x00; /* Hash */
        }

    } else {
        /* V3 MMU supports both hash and radix in tcg (with dynamic switching) */
        val[3] = 0xC0;
    }
    _FDT(fdt_setprop(fdt, chosen, "ibm,arch-vec-5-platform-support",
                     val, sizeof(val)));
}

static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt, bool reset)
{
    MachineState *machine = MACHINE(spapr);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    int chosen;

    _FDT(chosen = fdt_add_subnode(fdt, 0, "chosen"));

    if (reset) {
        const char *boot_device = spapr->boot_device;
        char *stdout_path = spapr_vio_stdout_path(spapr->vio_bus);
        size_t cb = 0;
        char *bootlist = get_boot_devices_list(&cb);

        if (machine->kernel_cmdline && machine->kernel_cmdline[0]) {
            _FDT(fdt_setprop_string(fdt, chosen, "bootargs",
                                    machine->kernel_cmdline));
        }

        if (spapr->initrd_size) {
            _FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-start",
                                  spapr->initrd_base));
            _FDT(fdt_setprop_cell(fdt, chosen, "linux,initrd-end",
                                  spapr->initrd_base + spapr->initrd_size));
        }

        if (spapr->kernel_size) {
            uint64_t kprop[2] = { cpu_to_be64(spapr->kernel_addr),
                                  cpu_to_be64(spapr->kernel_size) };

            _FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel",
                         &kprop, sizeof(kprop)));
            if (spapr->kernel_le) {
                _FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel-le", NULL, 0));
            }
        }
        if (boot_menu) {
            _FDT((fdt_setprop_cell(fdt, chosen, "qemu,boot-menu", boot_menu)));
        }
        _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-width", graphic_width));
        _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-height", graphic_height));
        _FDT(fdt_setprop_cell(fdt, chosen, "qemu,graphic-depth", graphic_depth));

        if (cb && bootlist) {
            int i;

            for (i = 0; i < cb; i++) {
                if (bootlist[i] == '\n') {
                    bootlist[i] = ' ';
                }
            }
            _FDT(fdt_setprop_string(fdt, chosen, "qemu,boot-list", bootlist));
        }

        if (boot_device && strlen(boot_device)) {
            _FDT(fdt_setprop_string(fdt, chosen, "qemu,boot-device", boot_device));
        }

        if (!spapr->has_graphics && stdout_path) {
            /*
             * "linux,stdout-path" and "stdout" properties are
             * deprecated by linux kernel. New platforms should only
             * use the "stdout-path" property. Set the new property
             * and continue using older property to remain compatible
             * with the existing firmware.
             */
            _FDT(fdt_setprop_string(fdt, chosen, "linux,stdout-path", stdout_path));
            _FDT(fdt_setprop_string(fdt, chosen, "stdout-path", stdout_path));
        }

        /*
         * We can deal with BAR reallocation just fine, advertise it
         * to the guest
         */
        if (smc->linux_pci_probe) {
            _FDT(fdt_setprop_cell(fdt, chosen, "linux,pci-probe-only", 0));
        }

        spapr_dt_ov5_platform_support(spapr, fdt, chosen);

        g_free(stdout_path);
        g_free(bootlist);
    }

    _FDT(spapr_dt_ovec(fdt, chosen, spapr->ov5_cas, "ibm,architecture-vec-5"));
}

static void spapr_dt_hypervisor(SpaprMachineState *spapr, void *fdt)
{
    /* The /hypervisor node isn't in PAPR - this is a hack to allow PR
     * KVM to work under pHyp with some guest co-operation */
    int hypervisor;
    uint8_t hypercall[16];

    _FDT(hypervisor = fdt_add_subnode(fdt, 0, "hypervisor"));
    /* indicate KVM hypercall interface */
    _FDT(fdt_setprop_string(fdt, hypervisor, "compatible", "linux,kvm"));
    if (kvmppc_has_cap_fixup_hcalls()) {
        /*
         * Older KVM versions with older guest kernels were broken
         * with the magic page, don't allow the guest to map it.
         */
        if (!kvmppc_get_hypercall(first_cpu->env_ptr, hypercall,
                                  sizeof(hypercall))) {
            _FDT(fdt_setprop(fdt, hypervisor, "hcall-instructions",
                             hypercall, sizeof(hypercall)));
        }
    }
}

void *spapr_build_fdt(SpaprMachineState *spapr, bool reset, size_t space)
{
    MachineState *machine = MACHINE(spapr);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    uint32_t root_drc_type_mask = 0;
    int ret;
    void *fdt;
    SpaprPhbState *phb;
    char *buf;

    fdt = g_malloc0(space);
    _FDT((fdt_create_empty_tree(fdt, space)));

    /* Root node */
    _FDT(fdt_setprop_string(fdt, 0, "device_type", "chrp"));
    _FDT(fdt_setprop_string(fdt, 0, "model", "IBM pSeries (emulated by qemu)"));
    _FDT(fdt_setprop_string(fdt, 0, "compatible", "qemu,pseries"));

    /* Guest UUID & Name*/
    buf = qemu_uuid_unparse_strdup(&qemu_uuid);
    _FDT(fdt_setprop_string(fdt, 0, "vm,uuid", buf));
    if (qemu_uuid_set) {
        _FDT(fdt_setprop_string(fdt, 0, "system-id", buf));
    }
    g_free(buf);

    if (qemu_get_vm_name()) {
        _FDT(fdt_setprop_string(fdt, 0, "ibm,partition-name",
                                qemu_get_vm_name()));
    }

    /* Host Model & Serial Number */
    if (spapr->host_model) {
        _FDT(fdt_setprop_string(fdt, 0, "host-model", spapr->host_model));
    } else if (smc->broken_host_serial_model && kvmppc_get_host_model(&buf)) {
        _FDT(fdt_setprop_string(fdt, 0, "host-model", buf));
        g_free(buf);
    }

    if (spapr->host_serial) {
        _FDT(fdt_setprop_string(fdt, 0, "host-serial", spapr->host_serial));
    } else if (smc->broken_host_serial_model && kvmppc_get_host_serial(&buf)) {
        _FDT(fdt_setprop_string(fdt, 0, "host-serial", buf));
        g_free(buf);
    }

    _FDT(fdt_setprop_cell(fdt, 0, "#address-cells", 2));
    _FDT(fdt_setprop_cell(fdt, 0, "#size-cells", 2));

    /* /interrupt controller */
    spapr_irq_dt(spapr, spapr_max_server_number(spapr), fdt, PHANDLE_INTC);

    ret = spapr_dt_memory(spapr, fdt);
    if (ret < 0) {
        error_report("couldn't setup memory nodes in fdt");
        exit(1);
    }

    /* /vdevice */
    spapr_dt_vdevice(spapr->vio_bus, fdt);

    if (object_resolve_path_type("", TYPE_SPAPR_RNG, NULL)) {
        ret = spapr_dt_rng(fdt);
        if (ret < 0) {
            error_report("could not set up rng device in the fdt");
            exit(1);
        }
    }

    QLIST_FOREACH(phb, &spapr->phbs, list) {
        ret = spapr_dt_phb(spapr, phb, PHANDLE_INTC, fdt, NULL);
        if (ret < 0) {
            error_report("couldn't setup PCI devices in fdt");
            exit(1);
        }
    }

    spapr_dt_cpus(fdt, spapr);

    /* ibm,drc-indexes and friends */
    if (smc->dr_lmb_enabled) {
        root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_LMB;
    }
    if (smc->dr_phb_enabled) {
        root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_PHB;
    }
    if (mc->nvdimm_supported) {
        root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_PMEM;
    }
    if (root_drc_type_mask) {
        _FDT(spapr_dt_drc(fdt, 0, NULL, root_drc_type_mask));
    }

    if (mc->has_hotpluggable_cpus) {
        int offset = fdt_path_offset(fdt, "/cpus");
        ret = spapr_dt_drc(fdt, offset, NULL, SPAPR_DR_CONNECTOR_TYPE_CPU);
        if (ret < 0) {
            error_report("Couldn't set up CPU DR device tree properties");
            exit(1);
        }
    }

    /* /event-sources */
    spapr_dt_events(spapr, fdt);

    /* /rtas */
    spapr_dt_rtas(spapr, fdt);

    /* /chosen */
    spapr_dt_chosen(spapr, fdt, reset);

    /* /hypervisor */
    if (kvm_enabled()) {
        spapr_dt_hypervisor(spapr, fdt);
    }

    /* Build memory reserve map */
    if (reset) {
        if (spapr->kernel_size) {
            _FDT((fdt_add_mem_rsv(fdt, spapr->kernel_addr,
                                  spapr->kernel_size)));
        }
        if (spapr->initrd_size) {
            _FDT((fdt_add_mem_rsv(fdt, spapr->initrd_base,
                                  spapr->initrd_size)));
        }
    }

    /* NVDIMM devices */
    if (mc->nvdimm_supported) {
        spapr_dt_persistent_memory(spapr, fdt);
    }

    return fdt;
}

static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
{
    SpaprMachineState *spapr = opaque;

    return (addr & 0x0fffffff) + spapr->kernel_addr;
}

static void emulate_spapr_hypercall(PPCVirtualHypervisor *vhyp,
                                    PowerPCCPU *cpu)
{
    CPUPPCState *env = &cpu->env;

    /* The TCG path should also be holding the BQL at this point */
    g_assert(qemu_mutex_iothread_locked());

    if (msr_pr) {
        hcall_dprintf("Hypercall made with MSR[PR]=1\n");
        env->gpr[3] = H_PRIVILEGE;
    } else {
        env->gpr[3] = spapr_hypercall(cpu, env->gpr[3], &env->gpr[4]);
    }
}

struct LPCRSyncState {
    target_ulong value;
    target_ulong mask;
};

static void do_lpcr_sync(CPUState *cs, run_on_cpu_data arg)
{
    struct LPCRSyncState *s = arg.host_ptr;
    PowerPCCPU *cpu = POWERPC_CPU(cs);
    CPUPPCState *env = &cpu->env;
    target_ulong lpcr;

    cpu_synchronize_state(cs);
    lpcr = env->spr[SPR_LPCR];
    lpcr &= ~s->mask;
    lpcr |= s->value;
    ppc_store_lpcr(cpu, lpcr);
}

void spapr_set_all_lpcrs(target_ulong value, target_ulong mask)
{
    CPUState *cs;
    struct LPCRSyncState s = {
        .value = value,
        .mask = mask
    };
    CPU_FOREACH(cs) {
        run_on_cpu(cs, do_lpcr_sync, RUN_ON_CPU_HOST_PTR(&s));
    }
}

static void spapr_get_pate(PPCVirtualHypervisor *vhyp, ppc_v3_pate_t *entry)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    /* Copy PATE1:GR into PATE0:HR */
    entry->dw0 = spapr->patb_entry & PATE0_HR;
    entry->dw1 = spapr->patb_entry;
}

#define HPTE(_table, _i)   (void *)(((uint64_t *)(_table)) + ((_i) * 2))
#define HPTE_VALID(_hpte)  (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_VALID)
#define HPTE_DIRTY(_hpte)  (tswap64(*((uint64_t *)(_hpte))) & HPTE64_V_HPTE_DIRTY)
#define CLEAN_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) &= tswap64(~HPTE64_V_HPTE_DIRTY))
#define DIRTY_HPTE(_hpte)  ((*(uint64_t *)(_hpte)) |= tswap64(HPTE64_V_HPTE_DIRTY))

/*
 * Get the fd to access the kernel htab, re-opening it if necessary
 */
static int get_htab_fd(SpaprMachineState *spapr)
{
    Error *local_err = NULL;

    if (spapr->htab_fd >= 0) {
        return spapr->htab_fd;
    }

    spapr->htab_fd = kvmppc_get_htab_fd(false, 0, &local_err);
    if (spapr->htab_fd < 0) {
        error_report_err(local_err);
    }

    return spapr->htab_fd;
}

void close_htab_fd(SpaprMachineState *spapr)
{
    if (spapr->htab_fd >= 0) {
        close(spapr->htab_fd);
    }
    spapr->htab_fd = -1;
}

static hwaddr spapr_hpt_mask(PPCVirtualHypervisor *vhyp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    return HTAB_SIZE(spapr) / HASH_PTEG_SIZE_64 - 1;
}

static target_ulong spapr_encode_hpt_for_kvm_pr(PPCVirtualHypervisor *vhyp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    assert(kvm_enabled());

    if (!spapr->htab) {
        return 0;
    }

    return (target_ulong)(uintptr_t)spapr->htab | (spapr->htab_shift - 18);
}

static const ppc_hash_pte64_t *spapr_map_hptes(PPCVirtualHypervisor *vhyp,
                                                hwaddr ptex, int n)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);
    hwaddr pte_offset = ptex * HASH_PTE_SIZE_64;

    if (!spapr->htab) {
        /*
         * HTAB is controlled by KVM. Fetch into temporary buffer
         */
        ppc_hash_pte64_t *hptes = g_malloc(n * HASH_PTE_SIZE_64);
        kvmppc_read_hptes(hptes, ptex, n);
        return hptes;
    }

    /*
     * HTAB is controlled by QEMU. Just point to the internally
     * accessible PTEG.
     */
    return (const ppc_hash_pte64_t *)(spapr->htab + pte_offset);
}

static void spapr_unmap_hptes(PPCVirtualHypervisor *vhyp,
                              const ppc_hash_pte64_t *hptes,
                              hwaddr ptex, int n)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        g_free((void *)hptes);
    }

    /* Nothing to do for qemu managed HPT */
}

void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
                      uint64_t pte0, uint64_t pte1)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(cpu->vhyp);
    hwaddr offset = ptex * HASH_PTE_SIZE_64;

    if (!spapr->htab) {
        kvmppc_write_hpte(ptex, pte0, pte1);
    } else {
        if (pte0 & HPTE64_V_VALID) {
            stq_p(spapr->htab + offset + HPTE64_DW1, pte1);
            /*
             * When setting valid, we write PTE1 first. This ensures
             * proper synchronization with the reading code in
             * ppc_hash64_pteg_search()
             */
            smp_wmb();
            stq_p(spapr->htab + offset, pte0);
        } else {
            stq_p(spapr->htab + offset, pte0);
            /*
             * When clearing it we set PTE0 first. This ensures proper
             * synchronization with the reading code in
             * ppc_hash64_pteg_search()
             */
            smp_wmb();
            stq_p(spapr->htab + offset + HPTE64_DW1, pte1);
        }
    }
}

static void spapr_hpte_set_c(PPCVirtualHypervisor *vhyp, hwaddr ptex,
                             uint64_t pte1)
{
    hwaddr offset = ptex * HASH_PTE_SIZE_64 + HPTE64_DW1_C;
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        /* There should always be a hash table when this is called */
        error_report("spapr_hpte_set_c called with no hash table !");
        return;
    }

    /* The HW performs a non-atomic byte update */
    stb_p(spapr->htab + offset, (pte1 & 0xff) | 0x80);
}

static void spapr_hpte_set_r(PPCVirtualHypervisor *vhyp, hwaddr ptex,
                             uint64_t pte1)
{
    hwaddr offset = ptex * HASH_PTE_SIZE_64 + HPTE64_DW1_R;
    SpaprMachineState *spapr = SPAPR_MACHINE(vhyp);

    if (!spapr->htab) {
        /* There should always be a hash table when this is called */
        error_report("spapr_hpte_set_r called with no hash table !");
        return;
    }

    /* The HW performs a non-atomic byte update */
    stb_p(spapr->htab + offset, ((pte1 >> 8) & 0xff) | 0x01);
}

int spapr_hpt_shift_for_ramsize(uint64_t ramsize)
{
    int shift;

    /* We aim for a hash table of size 1/128 the size of RAM (rounded
     * up).  The PAPR recommendation is actually 1/64 of RAM size, but
     * that's much more than is needed for Linux guests */
    shift = ctz64(pow2ceil(ramsize)) - 7;
    shift = MAX(shift, 18); /* Minimum architected size */
    shift = MIN(shift, 46); /* Maximum architected size */
    return shift;
}

void spapr_free_hpt(SpaprMachineState *spapr)
{
    g_free(spapr->htab);
    spapr->htab = NULL;
    spapr->htab_shift = 0;
    close_htab_fd(spapr);
}

int spapr_reallocate_hpt(SpaprMachineState *spapr, int shift, Error **errp)
{
    ERRP_GUARD();
    long rc;

    /* Clean up any HPT info from a previous boot */
    spapr_free_hpt(spapr);

    rc = kvmppc_reset_htab(shift);

    if (rc == -EOPNOTSUPP) {
        error_setg(errp, "HPT not supported in nested guests");
        return -EOPNOTSUPP;
    }

    if (rc < 0) {
        /* kernel-side HPT needed, but couldn't allocate one */
        error_setg_errno(errp, errno, "Failed to allocate KVM HPT of order %d",
                         shift);
        error_append_hint(errp, "Try smaller maxmem?\n");
        return -errno;
    } else if (rc > 0) {
        /* kernel-side HPT allocated */
        if (rc != shift) {
            error_setg(errp,
                       "Requested order %d HPT, but kernel allocated order %ld",
                       shift, rc);
            error_append_hint(errp, "Try smaller maxmem?\n");
            return -ENOSPC;
        }

        spapr->htab_shift = shift;
        spapr->htab = NULL;
    } else {
        /* kernel-side HPT not needed, allocate in userspace instead */
        size_t size = 1ULL << shift;
        int i;

        spapr->htab = qemu_memalign(size, size);
        memset(spapr->htab, 0, size);
        spapr->htab_shift = shift;

        for (i = 0; i < size / HASH_PTE_SIZE_64; i++) {
            DIRTY_HPTE(HPTE(spapr->htab, i));
        }
    }
    /* We're setting up a hash table, so that means we're not radix */
    spapr->patb_entry = 0;
    spapr_set_all_lpcrs(0, LPCR_HR | LPCR_UPRT);
    return 0;
}

void spapr_setup_hpt(SpaprMachineState *spapr)
{
    int hpt_shift;

    if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DISABLED) {
        hpt_shift = spapr_hpt_shift_for_ramsize(MACHINE(spapr)->maxram_size);
    } else {
        uint64_t current_ram_size;

        current_ram_size = MACHINE(spapr)->ram_size + get_plugged_memory_size();
        hpt_shift = spapr_hpt_shift_for_ramsize(current_ram_size);
    }
    spapr_reallocate_hpt(spapr, hpt_shift, &error_fatal);

    if (kvm_enabled()) {
        hwaddr vrma_limit = kvmppc_vrma_limit(spapr->htab_shift);

        /* Check our RMA fits in the possible VRMA */
        if (vrma_limit < spapr->rma_size) {
            error_report("Unable to create %" HWADDR_PRIu
                         "MiB RMA (VRMA only allows %" HWADDR_PRIu "MiB",
                         spapr->rma_size / MiB, vrma_limit / MiB);
            exit(EXIT_FAILURE);
        }
    }
}

void spapr_check_mmu_mode(bool guest_radix)
{
    if (guest_radix) {
        if (kvm_enabled() && !kvmppc_has_cap_mmu_radix()) {
            error_report("Guest requested unavailable MMU mode (radix).");
            exit(EXIT_FAILURE);
        }
    } else {
        if (kvm_enabled() && kvmppc_has_cap_mmu_radix()
            && !kvmppc_has_cap_mmu_hash_v3()) {
            error_report("Guest requested unavailable MMU mode (hash).");
            exit(EXIT_FAILURE);
        }
    }
}

static void spapr_machine_reset(MachineState *machine)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(machine);
    PowerPCCPU *first_ppc_cpu;
    hwaddr fdt_addr;
    void *fdt;
    int rc;

    pef_kvm_reset(machine->cgs, &error_fatal);
    spapr_caps_apply(spapr);

    first_ppc_cpu = POWERPC_CPU(first_cpu);
    if (kvm_enabled() && kvmppc_has_cap_mmu_radix() &&
        ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
                              spapr->max_compat_pvr)) {
        /*
         * If using KVM with radix mode available, VCPUs can be started
         * without a HPT because KVM will start them in radix mode.
         * Set the GR bit in PATE so that we know there is no HPT.
         */
        spapr->patb_entry = PATE1_GR;
        spapr_set_all_lpcrs(LPCR_HR | LPCR_UPRT, LPCR_HR | LPCR_UPRT);
    } else {
        spapr_setup_hpt(spapr);
    }

    qemu_devices_reset();

    spapr_ovec_cleanup(spapr->ov5_cas);
    spapr->ov5_cas = spapr_ovec_new();

    ppc_set_compat_all(spapr->max_compat_pvr, &error_fatal);

    /*
     * This is fixing some of the default configuration of the XIVE
     * devices. To be called after the reset of the machine devices.
     */
    spapr_irq_reset(spapr, &error_fatal);

    /*
     * There is no CAS under qtest. Simulate one to please the code that
     * depends on spapr->ov5_cas. This is especially needed to test device
     * unplug, so we do that before resetting the DRCs.
     */
    if (qtest_enabled()) {
        spapr_ovec_cleanup(spapr->ov5_cas);
        spapr->ov5_cas = spapr_ovec_clone(spapr->ov5);
    }

    /* DRC reset may cause a device to be unplugged. This will cause troubles
     * if this device is used by another device (eg, a running vhost backend
     * will crash QEMU if the DIMM holding the vring goes away). To avoid such
     * situations, we reset DRCs after all devices have been reset.
     */
    spapr_drc_reset_all(spapr);

    spapr_clear_pending_events(spapr);

    /*
     * We place the device tree just below either the top of the RMA,
     * or just below 2GB, whichever is lower, so that it can be
     * processed with 32-bit real mode code if necessary
     */
    fdt_addr = MIN(spapr->rma_size, FDT_MAX_ADDR) - FDT_MAX_SIZE;

    fdt = spapr_build_fdt(spapr, true, FDT_MAX_SIZE);
    if (spapr->vof) {
        spapr_vof_reset(spapr, fdt, &error_fatal);
        /*
         * Do not pack the FDT as the client may change properties.
         * VOF client does not expect the FDT so we do not load it to the VM.
         */
    } else {
        rc = fdt_pack(fdt);
        /* Should only fail if we've built a corrupted tree */
        assert(rc == 0);

        spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT,
                                  0, fdt_addr, 0);
        cpu_physical_memory_write(fdt_addr, fdt, fdt_totalsize(fdt));
    }
    qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt));

    g_free(spapr->fdt_blob);
    spapr->fdt_size = fdt_totalsize(fdt);
    spapr->fdt_initial_size = spapr->fdt_size;
    spapr->fdt_blob = fdt;

    /* Set up the entry state */
    first_ppc_cpu->env.gpr[5] = 0;

    spapr->fwnmi_system_reset_addr = -1;
    spapr->fwnmi_machine_check_addr = -1;
    spapr->fwnmi_machine_check_interlock = -1;

    /* Signal all vCPUs waiting on this condition */
    qemu_cond_broadcast(&spapr->fwnmi_machine_check_interlock_cond);

    migrate_del_blocker(spapr->fwnmi_migration_blocker);
}

static void spapr_create_nvram(SpaprMachineState *spapr)
{
    DeviceState *dev = qdev_new("spapr-nvram");
    DriveInfo *dinfo = drive_get(IF_PFLASH, 0, 0);

    if (dinfo) {
        qdev_prop_set_drive_err(dev, "drive", blk_by_legacy_dinfo(dinfo),
                                &error_fatal);
    }

    qdev_realize_and_unref(dev, &spapr->vio_bus->bus, &error_fatal);

    spapr->nvram = (struct SpaprNvram *)dev;
}

static void spapr_rtc_create(SpaprMachineState *spapr)
{
    object_initialize_child_with_props(OBJECT(spapr), "rtc", &spapr->rtc,
                                       sizeof(spapr->rtc), TYPE_SPAPR_RTC,
                                       &error_fatal, NULL);
    qdev_realize(DEVICE(&spapr->rtc), NULL, &error_fatal);
    object_property_add_alias(OBJECT(spapr), "rtc-time", OBJECT(&spapr->rtc),
                              "date");
}

/* Returns whether we want to use VGA or not */
static bool spapr_vga_init(PCIBus *pci_bus, Error **errp)
{
    switch (vga_interface_type) {
    case VGA_NONE:
        return false;
    case VGA_DEVICE:
        return true;
    case VGA_STD:
    case VGA_VIRTIO:
    case VGA_CIRRUS:
        return pci_vga_init(pci_bus) != NULL;
    default:
        error_setg(errp,
                   "Unsupported VGA mode, only -vga std or -vga virtio is supported");
        return false;
    }
}

static int spapr_pre_load(void *opaque)
{
    int rc;

    rc = spapr_caps_pre_load(opaque);
    if (rc) {
        return rc;
    }

    return 0;
}

static int spapr_post_load(void *opaque, int version_id)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
    int err = 0;

    err = spapr_caps_post_migration(spapr);
    if (err) {
        return err;
    }

    /*
     * In earlier versions, there was no separate qdev for the PAPR
     * RTC, so the RTC offset was stored directly in sPAPREnvironment.
     * So when migrating from those versions, poke the incoming offset
     * value into the RTC device
     */
    if (version_id < 3) {
        err = spapr_rtc_import_offset(&spapr->rtc, spapr->rtc_offset);
        if (err) {
            return err;
        }
    }

    if (kvm_enabled() && spapr->patb_entry) {
        PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
        bool radix = !!(spapr->patb_entry & PATE1_GR);
        bool gtse = !!(cpu->env.spr[SPR_LPCR] & LPCR_GTSE);

        /*
         * Update LPCR:HR and UPRT as they may not be set properly in
         * the stream
         */
        spapr_set_all_lpcrs(radix ? (LPCR_HR | LPCR_UPRT) : 0,
                            LPCR_HR | LPCR_UPRT);

        err = kvmppc_configure_v3_mmu(cpu, radix, gtse, spapr->patb_entry);
        if (err) {
            error_report("Process table config unsupported by the host");
            return -EINVAL;
        }
    }

    err = spapr_irq_post_load(spapr, version_id);
    if (err) {
        return err;
    }

    return err;
}

static int spapr_pre_save(void *opaque)
{
    int rc;

    rc = spapr_caps_pre_save(opaque);
    if (rc) {
        return rc;
    }

    return 0;
}

static bool version_before_3(void *opaque, int version_id)
{
    return version_id < 3;
}

static bool spapr_pending_events_needed(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;
    return !QTAILQ_EMPTY(&spapr->pending_events);
}

static const VMStateDescription vmstate_spapr_event_entry = {
    .name = "spapr_event_log_entry",
    .version_id = 1,
    .minimum_version_id = 1,
    .fields = (VMStateField[]) {
        VMSTATE_UINT32(summary, SpaprEventLogEntry),
        VMSTATE_UINT32(extended_length, SpaprEventLogEntry),
        VMSTATE_VBUFFER_ALLOC_UINT32(extended_log, SpaprEventLogEntry, 0,
                                     NULL, extended_length),
        VMSTATE_END_OF_LIST()
    },
};

static const VMStateDescription vmstate_spapr_pending_events = {
    .name = "spapr_pending_events",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_pending_events_needed,
    .fields = (VMStateField[]) {
        VMSTATE_QTAILQ_V(pending_events, SpaprMachineState, 1,
                         vmstate_spapr_event_entry, SpaprEventLogEntry, next),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_ov5_cas_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;
    SpaprOptionVector *ov5_mask = spapr_ovec_new();
    bool cas_needed;

    /* Prior to the introduction of SpaprOptionVector, we had two option
     * vectors we dealt with: OV5_FORM1_AFFINITY, and OV5_DRCONF_MEMORY.
     * Both of these options encode machine topology into the device-tree
     * in such a way that the now-booted OS should still be able to interact
     * appropriately with QEMU regardless of what options were actually
     * negotiatied on the source side.
     *
     * As such, we can avoid migrating the CAS-negotiated options if these
     * are the only options available on the current machine/platform.
     * Since these are the only options available for pseries-2.7 and
     * earlier, this allows us to maintain old->new/new->old migration
     * compatibility.
     *
     * For QEMU 2.8+, there are additional CAS-negotiatable options available
     * via default pseries-2.8 machines and explicit command-line parameters.
     * Some of these options, like OV5_HP_EVT, *do* require QEMU to be aware
     * of the actual CAS-negotiated values to continue working properly. For
     * example, availability of memory unplug depends on knowing whether
     * OV5_HP_EVT was negotiated via CAS.
     *
     * Thus, for any cases where the set of available CAS-negotiatable
     * options extends beyond OV5_FORM1_AFFINITY and OV5_DRCONF_MEMORY, we
     * include the CAS-negotiated options in the migration stream, unless
     * if they affect boot time behaviour only.
     */
    spapr_ovec_set(ov5_mask, OV5_FORM1_AFFINITY);
    spapr_ovec_set(ov5_mask, OV5_DRCONF_MEMORY);
    spapr_ovec_set(ov5_mask, OV5_DRMEM_V2);

    /* We need extra information if we have any bits outside the mask
     * defined above */
    cas_needed = !spapr_ovec_subset(spapr->ov5, ov5_mask);

    spapr_ovec_cleanup(ov5_mask);

    return cas_needed;
}

static const VMStateDescription vmstate_spapr_ov5_cas = {
    .name = "spapr_option_vector_ov5_cas",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_ov5_cas_needed,
    .fields = (VMStateField[]) {
        VMSTATE_STRUCT_POINTER_V(ov5_cas, SpaprMachineState, 1,
                                 vmstate_spapr_ovec, SpaprOptionVector),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_patb_entry_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    return !!spapr->patb_entry;
}

static const VMStateDescription vmstate_spapr_patb_entry = {
    .name = "spapr_patb_entry",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_patb_entry_needed,
    .fields = (VMStateField[]) {
        VMSTATE_UINT64(patb_entry, SpaprMachineState),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_irq_map_needed(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    return spapr->irq_map && !bitmap_empty(spapr->irq_map, spapr->irq_map_nr);
}

static const VMStateDescription vmstate_spapr_irq_map = {
    .name = "spapr_irq_map",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_irq_map_needed,
    .fields = (VMStateField[]) {
        VMSTATE_BITMAP(irq_map, SpaprMachineState, 0, irq_map_nr),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_dtb_needed(void *opaque)
{
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(opaque);

    return smc->update_dt_enabled;
}

static int spapr_dtb_pre_load(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;

    g_free(spapr->fdt_blob);
    spapr->fdt_blob = NULL;
    spapr->fdt_size = 0;

    return 0;
}

static const VMStateDescription vmstate_spapr_dtb = {
    .name = "spapr_dtb",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_dtb_needed,
    .pre_load = spapr_dtb_pre_load,
    .fields = (VMStateField[]) {
        VMSTATE_UINT32(fdt_initial_size, SpaprMachineState),
        VMSTATE_UINT32(fdt_size, SpaprMachineState),
        VMSTATE_VBUFFER_ALLOC_UINT32(fdt_blob, SpaprMachineState, 0, NULL,
                                     fdt_size),
        VMSTATE_END_OF_LIST()
    },
};

static bool spapr_fwnmi_needed(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;

    return spapr->fwnmi_machine_check_addr != -1;
}

static int spapr_fwnmi_pre_save(void *opaque)
{
    SpaprMachineState *spapr = (SpaprMachineState *)opaque;

    /*
     * Check if machine check handling is in progress and print a
     * warning message.
     */
    if (spapr->fwnmi_machine_check_interlock != -1) {
        warn_report("A machine check is being handled during migration. The"
                "handler may run and log hardware error on the destination");
    }

    return 0;
}

static const VMStateDescription vmstate_spapr_fwnmi = {
    .name = "spapr_fwnmi",
    .version_id = 1,
    .minimum_version_id = 1,
    .needed = spapr_fwnmi_needed,
    .pre_save = spapr_fwnmi_pre_save,
    .fields = (VMStateField[]) {
        VMSTATE_UINT64(fwnmi_system_reset_addr, SpaprMachineState),
        VMSTATE_UINT64(fwnmi_machine_check_addr, SpaprMachineState),
        VMSTATE_INT32(fwnmi_machine_check_interlock, SpaprMachineState),
        VMSTATE_END_OF_LIST()
    },

};

static const VMStateDescription vmstate_spapr = {
    .name = "spapr",
    .version_id = 3,
    .minimum_version_id = 1,
    .pre_load = spapr_pre_load,
    .post_load = spapr_post_load,
    .pre_save = spapr_pre_save,
    .fields = (VMStateField[]) {
        /* used to be @next_irq */
        VMSTATE_UNUSED_BUFFER(version_before_3, 0, 4),

        /* RTC offset */
        VMSTATE_UINT64_TEST(rtc_offset, SpaprMachineState, version_before_3),

        VMSTATE_PPC_TIMEBASE_V(tb, SpaprMachineState, 2),
        VMSTATE_END_OF_LIST()
    },
    .subsections = (const VMStateDescription*[]) {
        &vmstate_spapr_ov5_cas,
        &vmstate_spapr_patb_entry,
        &vmstate_spapr_pending_events,
        &vmstate_spapr_cap_htm,
        &vmstate_spapr_cap_vsx,
        &vmstate_spapr_cap_dfp,
        &vmstate_spapr_cap_cfpc,
        &vmstate_spapr_cap_sbbc,
        &vmstate_spapr_cap_ibs,
        &vmstate_spapr_cap_hpt_maxpagesize,
        &vmstate_spapr_irq_map,
        &vmstate_spapr_cap_nested_kvm_hv,
        &vmstate_spapr_dtb,
        &vmstate_spapr_cap_large_decr,
        &vmstate_spapr_cap_ccf_assist,
        &vmstate_spapr_cap_fwnmi,
        &vmstate_spapr_fwnmi,
        &vmstate_spapr_cap_rpt_invalidate,
        NULL
    }
};

static int htab_save_setup(QEMUFile *f, void *opaque)
{
    SpaprMachineState *spapr = opaque;

    /* "Iteration" header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
    } else {
        qemu_put_be32(f, spapr->htab_shift);
    }

    if (spapr->htab) {
        spapr->htab_save_index = 0;
        spapr->htab_first_pass = true;
    } else {
        if (spapr->htab_shift) {
            assert(kvm_enabled());
        }
    }


    return 0;
}

static void htab_save_chunk(QEMUFile *f, SpaprMachineState *spapr,
                            int chunkstart, int n_valid, int n_invalid)
{
    qemu_put_be32(f, chunkstart);
    qemu_put_be16(f, n_valid);
    qemu_put_be16(f, n_invalid);
    qemu_put_buffer(f, HPTE(spapr->htab, chunkstart),
                    HASH_PTE_SIZE_64 * n_valid);
}

static void htab_save_end_marker(QEMUFile *f)
{
    qemu_put_be32(f, 0);
    qemu_put_be16(f, 0);
    qemu_put_be16(f, 0);
}

static void htab_save_first_pass(QEMUFile *f, SpaprMachineState *spapr,
                                 int64_t max_ns)
{
    bool has_timeout = max_ns != -1;
    int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
    int index = spapr->htab_save_index;
    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);

    assert(spapr->htab_first_pass);

    do {
        int chunkstart;

        /* Consume invalid HPTEs */
        while ((index < htabslots)
               && !HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
        }

        /* Consume valid HPTEs */
        chunkstart = index;
        while ((index < htabslots) && (index - chunkstart < USHRT_MAX)
               && HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
        }

        if (index > chunkstart) {
            int n_valid = index - chunkstart;

            htab_save_chunk(f, spapr, chunkstart, n_valid, 0);

            if (has_timeout &&
                (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
                break;
            }
        }
    } while ((index < htabslots) && !qemu_file_rate_limit(f));

    if (index >= htabslots) {
        assert(index == htabslots);
        index = 0;
        spapr->htab_first_pass = false;
    }
    spapr->htab_save_index = index;
}

static int htab_save_later_pass(QEMUFile *f, SpaprMachineState *spapr,
                                int64_t max_ns)
{
    bool final = max_ns < 0;
    int htabslots = HTAB_SIZE(spapr) / HASH_PTE_SIZE_64;
    int examined = 0, sent = 0;
    int index = spapr->htab_save_index;
    int64_t starttime = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);

    assert(!spapr->htab_first_pass);

    do {
        int chunkstart, invalidstart;

        /* Consume non-dirty HPTEs */
        while ((index < htabslots)
               && !HPTE_DIRTY(HPTE(spapr->htab, index))) {
            index++;
            examined++;
        }

        chunkstart = index;
        /* Consume valid dirty HPTEs */
        while ((index < htabslots) && (index - chunkstart < USHRT_MAX)
               && HPTE_DIRTY(HPTE(spapr->htab, index))
               && HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
            examined++;
        }

        invalidstart = index;
        /* Consume invalid dirty HPTEs */
        while ((index < htabslots) && (index - invalidstart < USHRT_MAX)
               && HPTE_DIRTY(HPTE(spapr->htab, index))
               && !HPTE_VALID(HPTE(spapr->htab, index))) {
            CLEAN_HPTE(HPTE(spapr->htab, index));
            index++;
            examined++;
        }

        if (index > chunkstart) {
            int n_valid = invalidstart - chunkstart;
            int n_invalid = index - invalidstart;

            htab_save_chunk(f, spapr, chunkstart, n_valid, n_invalid);
            sent += index - chunkstart;

            if (!final && (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - starttime) > max_ns) {
                break;
            }
        }

        if (examined >= htabslots) {
            break;
        }

        if (index >= htabslots) {
            assert(index == htabslots);
            index = 0;
        }
    } while ((examined < htabslots) && (!qemu_file_rate_limit(f) || final));

    if (index >= htabslots) {
        assert(index == htabslots);
        index = 0;
    }

    spapr->htab_save_index = index;

    return (examined >= htabslots) && (sent == 0) ? 1 : 0;
}

#define MAX_ITERATION_NS    5000000 /* 5 ms */
#define MAX_KVM_BUF_SIZE    2048

static int htab_save_iterate(QEMUFile *f, void *opaque)
{
    SpaprMachineState *spapr = opaque;
    int fd;
    int rc = 0;

    /* Iteration header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
        return 1;
    } else {
        qemu_put_be32(f, 0);
    }

    if (!spapr->htab) {
        assert(kvm_enabled());

        fd = get_htab_fd(spapr);
        if (fd < 0) {
            return fd;
        }

        rc = kvmppc_save_htab(f, fd, MAX_KVM_BUF_SIZE, MAX_ITERATION_NS);
        if (rc < 0) {
            return rc;
        }
    } else  if (spapr->htab_first_pass) {
        htab_save_first_pass(f, spapr, MAX_ITERATION_NS);
    } else {
        rc = htab_save_later_pass(f, spapr, MAX_ITERATION_NS);
    }

    htab_save_end_marker(f);

    return rc;
}

static int htab_save_complete(QEMUFile *f, void *opaque)
{
    SpaprMachineState *spapr = opaque;
    int fd;

    /* Iteration header */
    if (!spapr->htab_shift) {
        qemu_put_be32(f, -1);
        return 0;
    } else {
        qemu_put_be32(f, 0);
    }

    if (!spapr->htab) {
        int rc;

        assert(kvm_enabled());

        fd = get_htab_fd(spapr);
        if (fd < 0) {
            return fd;
        }

        rc = kvmppc_save_htab(f, fd, MAX_KVM_BUF_SIZE, -1);
        if (rc < 0) {
            return rc;
        }
    } else {
        if (spapr->htab_first_pass) {
            htab_save_first_pass(f, spapr, -1);
        }
        htab_save_later_pass(f, spapr, -1);
    }

    /* End marker */
    htab_save_end_marker(f);

    return 0;
}

static int htab_load(QEMUFile *f, void *opaque, int version_id)
{
    SpaprMachineState *spapr = opaque;
    uint32_t section_hdr;
    int fd = -1;
    Error *local_err = NULL;

    if (version_id < 1 || version_id > 1) {
        error_report("htab_load() bad version");
        return -EINVAL;
    }

    section_hdr = qemu_get_be32(f);

    if (section_hdr == -1) {
        spapr_free_hpt(spapr);
        return 0;
    }

    if (section_hdr) {
        int ret;

        /* First section gives the htab size */
        ret = spapr_reallocate_hpt(spapr, section_hdr, &local_err);
        if (ret < 0) {
            error_report_err(local_err);
            return ret;
        }
        return 0;
    }

    if (!spapr->htab) {
        assert(kvm_enabled());

        fd = kvmppc_get_htab_fd(true, 0, &local_err);
        if (fd < 0) {
            error_report_err(local_err);
            return fd;
        }
    }

    while (true) {
        uint32_t index;
        uint16_t n_valid, n_invalid;

        index = qemu_get_be32(f);
        n_valid = qemu_get_be16(f);
        n_invalid = qemu_get_be16(f);

        if ((index == 0) && (n_valid == 0) && (n_invalid == 0)) {
            /* End of Stream */
            break;
        }

        if ((index + n_valid + n_invalid) >
            (HTAB_SIZE(spapr) / HASH_PTE_SIZE_64)) {
            /* Bad index in stream */
            error_report(
                "htab_load() bad index %d (%hd+%hd entries) in htab stream (htab_shift=%d)",
                index, n_valid, n_invalid, spapr->htab_shift);
            return -EINVAL;
        }

        if (spapr->htab) {
            if (n_valid) {
                qemu_get_buffer(f, HPTE(spapr->htab, index),
                                HASH_PTE_SIZE_64 * n_valid);
            }
            if (n_invalid) {
                memset(HPTE(spapr->htab, index + n_valid), 0,
                       HASH_PTE_SIZE_64 * n_invalid);
            }
        } else {
            int rc;

            assert(fd >= 0);

            rc = kvmppc_load_htab_chunk(f, fd, index, n_valid, n_invalid,
                                        &local_err);
            if (rc < 0) {
                error_report_err(local_err);
                return rc;
            }
        }
    }

    if (!spapr->htab) {
        assert(fd >= 0);
        close(fd);
    }

    return 0;
}

static void htab_save_cleanup(void *opaque)
{
    SpaprMachineState *spapr = opaque;

    close_htab_fd(spapr);
}

static SaveVMHandlers savevm_htab_handlers = {
    .save_setup = htab_save_setup,
    .save_live_iterate = htab_save_iterate,
    .save_live_complete_precopy = htab_save_complete,
    .save_cleanup = htab_save_cleanup,
    .load_state = htab_load,
};

static void spapr_boot_set(void *opaque, const char *boot_device,
                           Error **errp)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(opaque);

    g_free(spapr->boot_device);
    spapr->boot_device = g_strdup(boot_device);
}

static void spapr_create_lmb_dr_connectors(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE;
    uint32_t nr_lmbs = (machine->maxram_size - machine->ram_size)/lmb_size;
    int i;

    for (i = 0; i < nr_lmbs; i++) {
        uint64_t addr;

        addr = i * lmb_size + machine->device_memory->base;
        spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_LMB,
                               addr / lmb_size);
    }
}

/*
 * If RAM size, maxmem size and individual node mem sizes aren't aligned
 * to SPAPR_MEMORY_BLOCK_SIZE(256MB), then refuse to start the guest
 * since we can't support such unaligned sizes with DRCONF_MEMORY.
 */
static void spapr_validate_node_memory(MachineState *machine, Error **errp)
{
    int i;

    if (machine->ram_size % SPAPR_MEMORY_BLOCK_SIZE) {
        error_setg(errp, "Memory size 0x" RAM_ADDR_FMT
                   " is not aligned to %" PRIu64 " MiB",
                   machine->ram_size,
                   SPAPR_MEMORY_BLOCK_SIZE / MiB);
        return;
    }

    if (machine->maxram_size % SPAPR_MEMORY_BLOCK_SIZE) {
        error_setg(errp, "Maximum memory size 0x" RAM_ADDR_FMT
                   " is not aligned to %" PRIu64 " MiB",
                   machine->ram_size,
                   SPAPR_MEMORY_BLOCK_SIZE / MiB);
        return;
    }

    for (i = 0; i < machine->numa_state->num_nodes; i++) {
        if (machine->numa_state->nodes[i].node_mem % SPAPR_MEMORY_BLOCK_SIZE) {
            error_setg(errp,
                       "Node %d memory size 0x%" PRIx64
                       " is not aligned to %" PRIu64 " MiB",
                       i, machine->numa_state->nodes[i].node_mem,
                       SPAPR_MEMORY_BLOCK_SIZE / MiB);
            return;
        }
    }
}

/* find cpu slot in machine->possible_cpus by core_id */
static CPUArchId *spapr_find_cpu_slot(MachineState *ms, uint32_t id, int *idx)
{
    int index = id / ms->smp.threads;

    if (index >= ms->possible_cpus->len) {
        return NULL;
    }
    if (idx) {
        *idx = index;
    }
    return &ms->possible_cpus->cpus[index];
}

static void spapr_set_vsmt_mode(SpaprMachineState *spapr, Error **errp)
{
    MachineState *ms = MACHINE(spapr);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    Error *local_err = NULL;
    bool vsmt_user = !!spapr->vsmt;
    int kvm_smt = kvmppc_smt_threads();
    int ret;
    unsigned int smp_threads = ms->smp.threads;

    if (!kvm_enabled() && (smp_threads > 1)) {
        error_setg(errp, "TCG cannot support more than 1 thread/core "
                   "on a pseries machine");
        return;
    }
    if (!is_power_of_2(smp_threads)) {
        error_setg(errp, "Cannot support %d threads/core on a pseries "
                   "machine because it must be a power of 2", smp_threads);
        return;
    }

    /* Detemine the VSMT mode to use: */
    if (vsmt_user) {
        if (spapr->vsmt < smp_threads) {
            error_setg(errp, "Cannot support VSMT mode %d"
                       " because it must be >= threads/core (%d)",
                       spapr->vsmt, smp_threads);
            return;
        }
        /* In this case, spapr->vsmt has been set by the command line */
    } else if (!smc->smp_threads_vsmt) {
        /*
         * Default VSMT value is tricky, because we need it to be as
         * consistent as possible (for migration), but this requires
         * changing it for at least some existing cases.  We pick 8 as
         * the value that we'd get with KVM on POWER8, the
         * overwhelmingly common case in production systems.
         */
        spapr->vsmt = MAX(8, smp_threads);
    } else {
        spapr->vsmt = smp_threads;
    }

    /* KVM: If necessary, set the SMT mode: */
    if (kvm_enabled() && (spapr->vsmt != kvm_smt)) {
        ret = kvmppc_set_smt_threads(spapr->vsmt);
        if (ret) {
            /* Looks like KVM isn't able to change VSMT mode */
            error_setg(&local_err,
                       "Failed to set KVM's VSMT mode to %d (errno %d)",
                       spapr->vsmt, ret);
            /* We can live with that if the default one is big enough
             * for the number of threads, and a submultiple of the one
             * we want.  In this case we'll waste some vcpu ids, but
             * behaviour will be correct */
            if ((kvm_smt >= smp_threads) && ((spapr->vsmt % kvm_smt) == 0)) {
                warn_report_err(local_err);
            } else {
                if (!vsmt_user) {
                    error_append_hint(&local_err,
                                      "On PPC, a VM with %d threads/core"
                                      " on a host with %d threads/core"
                                      " requires the use of VSMT mode %d.\n",
                                      smp_threads, kvm_smt, spapr->vsmt);
                }
                kvmppc_error_append_smt_possible_hint(&local_err);
                error_propagate(errp, local_err);
            }
        }
    }
    /* else TCG: nothing to do currently */
}

static void spapr_init_cpus(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    const char *type = spapr_get_cpu_core_type(machine->cpu_type);
    const CPUArchIdList *possible_cpus;
    unsigned int smp_cpus = machine->smp.cpus;
    unsigned int smp_threads = machine->smp.threads;
    unsigned int max_cpus = machine->smp.max_cpus;
    int boot_cores_nr = smp_cpus / smp_threads;
    int i;

    possible_cpus = mc->possible_cpu_arch_ids(machine);
    if (mc->has_hotpluggable_cpus) {
        if (smp_cpus % smp_threads) {
            error_report("smp_cpus (%u) must be multiple of threads (%u)",
                         smp_cpus, smp_threads);
            exit(1);
        }
        if (max_cpus % smp_threads) {
            error_report("max_cpus (%u) must be multiple of threads (%u)",
                         max_cpus, smp_threads);
            exit(1);
        }
    } else {
        if (max_cpus != smp_cpus) {
            error_report("This machine version does not support CPU hotplug");
            exit(1);
        }
        boot_cores_nr = possible_cpus->len;
    }

    if (smc->pre_2_10_has_unused_icps) {
        int i;

        for (i = 0; i < spapr_max_server_number(spapr); i++) {
            /* Dummy entries get deregistered when real ICPState objects
             * are registered during CPU core hotplug.
             */
            pre_2_10_vmstate_register_dummy_icp(i);
        }
    }

    for (i = 0; i < possible_cpus->len; i++) {
        int core_id = i * smp_threads;

        if (mc->has_hotpluggable_cpus) {
            spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_CPU,
                                   spapr_vcpu_id(spapr, core_id));
        }

        if (i < boot_cores_nr) {
            Object *core  = object_new(type);
            int nr_threads = smp_threads;

            /* Handle the partially filled core for older machine types */
            if ((i + 1) * smp_threads >= smp_cpus) {
                nr_threads = smp_cpus - i * smp_threads;
            }

            object_property_set_int(core, "nr-threads", nr_threads,
                                    &error_fatal);
            object_property_set_int(core, CPU_CORE_PROP_CORE_ID, core_id,
                                    &error_fatal);
            qdev_realize(DEVICE(core), NULL, &error_fatal);

            object_unref(core);
        }
    }
}

static PCIHostState *spapr_create_default_phb(void)
{
    DeviceState *dev;

    dev = qdev_new(TYPE_SPAPR_PCI_HOST_BRIDGE);
    qdev_prop_set_uint32(dev, "index", 0);
    sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);

    return PCI_HOST_BRIDGE(dev);
}

static hwaddr spapr_rma_size(SpaprMachineState *spapr, Error **errp)
{
    MachineState *machine = MACHINE(spapr);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr);
    hwaddr rma_size = machine->ram_size;
    hwaddr node0_size = spapr_node0_size(machine);

    /* RMA has to fit in the first NUMA node */
    rma_size = MIN(rma_size, node0_size);

    /*
     * VRMA access is via a special 1TiB SLB mapping, so the RMA can
     * never exceed that
     */
    rma_size = MIN(rma_size, 1 * TiB);

    /*
     * Clamp the RMA size based on machine type.  This is for
     * migration compatibility with older qemu versions, which limited
     * the RMA size for complicated and mostly bad reasons.
     */
    if (smc->rma_limit) {
        rma_size = MIN(rma_size, smc->rma_limit);
    }

    if (rma_size < MIN_RMA_SLOF) {
        error_setg(errp,
                   "pSeries SLOF firmware requires >= %" HWADDR_PRIx
                   "ldMiB guest RMA (Real Mode Area memory)",
                   MIN_RMA_SLOF / MiB);
        return 0;
    }

    return rma_size;
}

static void spapr_create_nvdimm_dr_connectors(SpaprMachineState *spapr)
{
    MachineState *machine = MACHINE(spapr);
    int i;

    for (i = 0; i < machine->ram_slots; i++) {
        spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_PMEM, i);
    }
}

/* pSeries LPAR / sPAPR hardware init */
static void spapr_machine_init(MachineState *machine)
{
    SpaprMachineState *spapr = SPAPR_MACHINE(machine);
    SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine);
    MachineClass *mc = MACHINE_GET_CLASS(machine);
    const char *bios_default = spapr->vof ? FW_FILE_NAME_VOF : FW_FILE_NAME;
    const char *bios_name = machine->firmware ?: bios_default;
    const char *kernel_filename = machine->kernel_filename;
    const char *initrd_filename = machine->initrd_filename;
    PCIHostState *phb;
    int i;
    MemoryRegion *sysmem = get_system_memory();
    long load_limit, fw_size;
    char *filename;
    Error *resize_hpt_err = NULL;

    /*
     * if Secure VM (PEF) support is configured, then initialize it
     */
    pef_kvm_init(machine->cgs, &error_fatal);

    msi_nonbroken = true;

    QLIST_INIT(&spapr->phbs);
    QTAILQ_INIT(&spapr->pending_dimm_unplugs);

    /* Determine capabilities to run with */
    spapr_caps_init(spapr);

    kvmppc_check_papr_resize_hpt(&resize_hpt_err);
    if (spapr->resize_hpt == SPAPR_RESIZE_HPT_DEFAULT) {
        /*
         * If the user explicitly requested a mode we should either
         * supply it, or fail completely (which we do below).  But if
         * it's not set explicitly, we reset our mode to something
         * that works
         */
        if (resize_hpt_err) {
            spapr->resize_hpt = SPAPR_RESIZE_HPT_DISABLED;
            error_free(resize_hpt_err);
            resize_hpt_err = NULL;
        } else {
            spapr->resize_hpt = smc->resize_hpt_default;
        }
    }

    assert(spapr->resize_hpt != SPAPR_RESIZE_HPT_DEFAULT);

    if ((spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) && resize_hpt_err) {
        /*
         * User requested HPT resize, but this host can't supply it.  Bail out
         */
        error_report_err(resize_hpt_err);
        exit(1);
    }
    error_free(resize_hpt_err);

    spapr->rma_size = spapr_rma_size(spapr, &error_fatal);

    /* Setup a load limit for the ramdisk leaving room for SLOF and FDT */
    load_limit = MIN(spapr->rma_size, FDT_MAX_ADDR) - FW_OVERHEAD;

    /*
     * VSMT must be set in order to be able to compute VCPU ids, ie to
     * call spapr_max_server_number() or spapr_vcpu_id().
     */
    spapr_set_vsmt_mode(spapr, &error_fatal);

    /* Set up Interrupt Controller before we create the VCPUs */
    spapr_irq_init(spapr, &error_fatal);

    /* Set up containers for ibm,client-architecture-support negotiated options
     */
    spapr->ov5 = spapr_ovec_new();
    spapr->ov5_cas = spapr_ovec_new();

    if (smc->dr_lmb_enabled) {
        spapr_ovec_set(spapr->ov5, OV5_DRCONF_MEMORY);
        spapr_validate_node_memory(machine, &error_fatal);
    }

    spapr_ovec_set(spapr->ov5, OV5_FORM1_AFFINITY);

    /* Do not advertise FORM2 NUMA support for pseries-6.1 and older */
    if (!smc->pre_6_2_numa_affinity) {
        spapr_ovec_set(spapr->ov5, OV5_FORM2_AFFINITY);
    }

    /* advertise support for dedicated HP event source to guests */
    if (spapr->use_hotplug_event_source) {
        spapr_ovec_set(spapr->ov5, OV5_HP_EVT);
    }

    /* advertise support for HPT resizing */
    if (spapr->resize_hpt != SPAPR_RESIZE_HPT_DISABLED) {
        spapr_ovec_set(spapr->ov5, OV5_HPT_RESIZE);
    }

    /* advertise support for ibm,dyamic-memory-v2 */
    spapr_ovec_set(spapr->ov5, OV5_DRMEM_V2);

    /* advertise XIVE on POWER9 machines */
    if (spapr->irq->xive) {
        spapr_ovec_set(spapr->ov5, OV5_XIVE_EXPLOIT);
    }

    /* init CPUs */
    spapr_init_cpus(spapr);

    spapr->gpu_numa_id = spapr_numa_initial_nvgpu_numa_id(machine);

    /* Init numa_assoc_array */
    spapr_numa_associativity_init(spapr, machine);

    if ((!kvm_enabled() || kvmppc_has_cap_mmu_radix()) &&
        ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0,
                              spapr->max_compat_pvr)) {
        spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_300);
        /* KVM and TCG always allow GTSE with radix... */
        spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_GTSE);
    }
    /* ... but not with hash (currently). */

    if (kvm_enabled()) {
        /* Enable H_LOGICAL_CI_* so SLOF can talk to in-kernel devices */
        kvmppc_enable_logical_ci_hcalls();
        kvmppc_enable_set_mode_hcall();

        /* H_CLEAR_MOD/_REF are mandatory in PAPR, but off by default */
        kvmppc_enable_clear_ref_mod_hcalls();

        /* Enable H_PAGE_INIT */
        kvmppc_enable_h_page_init();
    }

    /* map RAM */
    memory_region_add_subregion(sysmem, 0, machine->ram);

    /* always allocate the device memory information */
    machine->device_memory = g_malloc0(sizeof(*machine->device_memory));

    /* initialize hotplug memory address space */
    if (machine->ram_size < machine->maxram_size) {
        ram_addr_t device_mem_size = machine->maxram_size - machine->ram_size;
        /*
         * Limit the number of hotpluggable memory slots to half the number
         * slots that KVM supports, leaving the other half for PCI and other
         * devices. However ensure that number of slots doesn't drop below 32.
         */
        int max_memslots = kvm_enabled() ? kvm_get_max_memslots() / 2 :
                           SPAPR_MAX_RAM_SLOTS;

        if (max_memslots < SPAPR_MAX_RAM_SLOTS) {
            max_memslots = SPAPR_MAX_RAM_SLOTS;
        }
        if (machine->ram_slots > max_memslots) {
            error_report("Specified number of memory slots %"
                         PRIu64" exceeds max supported %d",
                         machine->ram_slots, max_memslots);
            exit(1);
        }

        machine->device_memory->base = ROUND_UP(machine->ram_size,
                                                SPAPR_DEVICE_MEM_ALIGN);
        memory_region_init(&machine->device_memory->mr, OBJECT(spapr),
                           "device-memory", device_mem_size);
        memory_region_add_subregion(sysmem, machine->device_memory->base,
                                    &machine->device_memory->mr);
    }

    if (smc->dr_lmb_enabled) {
        spapr_create_lmb_dr_connectors(spapr);
    }

    if (spapr_get_cap(spapr, SPAPR_CAP_FWNMI) == SPAPR_CAP_ON) {
        /* Create the error string for live migration blocker */
        error_setg(&spapr->fwnmi_migration_blocker,
            "A machine check is being handled during migration. The handler"
            "may run and log hardware error on the destination");
    }

    if (mc->nvdimm_supported) {
        spapr_create_nvdimm_dr_connectors(spapr);
    }

    /* Set up RTAS event infrastructure */
    spapr_events_init(spapr);

    /* Set up the RTC RTAS interfaces */
    spapr_rtc_create(spapr);

    /* Set up VIO bus */
    spapr->vio_bus = spapr_vio_bus_init();

    for (i = 0; serial_hd(i); i++) {
        spapr_vty_create(spapr->vio_bus, serial_hd(i));
    }

    /* We always have at least the nvram device on VIO */
    spapr_create_nvram(spapr);

    /*
     * Setup hotplug / dynamic-reconfiguration connectors. top-level
     * connectors (described in root DT node's "ibm,drc-types" property)
     * are pre-initialized here. additional child connectors (such as
     * connectors for a PHBs PCI slots) are added as needed during their
     * parent's realization.
     */
    if (smc->dr_phb_enabled) {
        for (i = 0; i < SPAPR_MAX_PHBS; i++) {
            spapr_dr_connector_new(OBJECT(machine), TYPE_SPAPR_DRC_PHB, i);
        }
    }

    /* Set up PCI */
    spapr_pci_rtas_init();

    phb = spapr_create_default_phb();

    for (i = 0; i < nb_nics; i++) {
        NICInfo *nd = &nd_table[i];

        if (!nd->model) {
            nd->model = g_strdup("spapr-vlan");
        }

        if (g_str_equal(nd->model, "spapr-vlan") ||
            g_str_equal(nd->model, "ibmveth")) {
            spapr_vlan_create(spapr->vio_bus, nd);
        } else {
            pci_nic_init_nofail(&nd_table[i], phb->bus, nd->model, NULL);
        }
    }

    for (i = 0; i <= drive_get_max_bus(IF_SCSI); i++) {
        spapr_vscsi_create(spapr->vio_bus);
    }

    /* Graphics */
    if (spapr_vga_init(phb->bus, &error_fatal)) {
        spapr->has_graphics = true;
        machine->usb |= defaults_enabled() && !machine->usb_disabled;
    }

    if (machine->usb) {
        if (smc->use_ohci_by_default) {
            pci_create_simple(phb->bus, -1, "pci-ohci");
        } else {
            pci_create_simple(phb->bus, -1, "nec-usb-xhci");
        }

        if (spapr->has_graphics) {
            USBBus *usb_bus = usb_bus_find(-1);

            usb_create_simple(usb_bus, "usb-kbd");
            usb_create_simple(usb_bus, "usb-mouse");
        }
    }

    if (kernel_filename) {
        spapr->kernel_size = load_elf(kernel_filename, NULL,
                                      translate_kernel_address, spapr,
                                      NULL, NULL, NULL, NULL, 1,
                                      PPC_ELF_MACHINE, 0, 0);
        if (spapr->kernel_size == ELF_LOAD_WRONG_ENDIAN) {
            spapr->kernel_size = load_elf(kernel_filename, NULL,
                                          translate_kernel_address, spapr,
                                          NULL, NULL, NULL, NULL, 0,
                                          PPC_ELF_MACHINE, 0, 0);
            spapr->kernel_le = spapr->kernel_size > 0;
        }
        if (spapr->kernel_size < 0) {
            error_report("error loading %s: %s", kernel_filename,
                         load_elf_strerror(spapr->kernel_size));
            exit(1);
        }

        /* load initrd */
        if (initrd_filename) {
            /* Try to locate the initrd in the gap between the kernel
             * and the firmware. Add a bit of space just in case
             */
            spapr->initrd_base = (spapr->kernel_addr + spapr->kernel_size
                                  + 0x1ffff) & ~0xffff;
            spapr->initrd_size = load_image_targphys(initrd_filename,
                                                     spapr->initrd_base,
                                                     load_limit
                                                     - spapr->initrd_base);
            if (spapr->initrd_size < 0) {
                error_report("could not load initial ram disk '%s'",
                             initrd_filename);
                exit(1);
            }
        }
    }

    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
    if (!filename) {
        error_report("Could not find LPAR firmware '%s'", bios_name);
        exit(1);
    }
    fw_size = load_image_targphys(filename, 0, FW_MAX_SIZE);
    if (fw_size <= 0) {
        error_report("Could not load LPAR firmware '%s'", filename);
        exit(1);
    }
    g_free(filename);

    /* FIXME: Should register things through the MachineState's qdev
     * interface, this is a legacy from the sPAPREnvironment structure
     * which predated MachineState but had a similar function */
    vmstate_register(NULL, 0, &vmstate_spapr, spapr);
    register_savevm_live("spapr/htab", VMSTATE_INSTANCE_ID_ANY, 1,
                         &savevm_htab_handlers, spapr);

    qbus_set_hotplug_handler(sysbus_get_default(), OBJECT(machine));

    qemu_register_boot_set(spapr_boot_set, spapr);

    /*
     * Nothing needs to be done to resume a suspended guest because
     * suspending does not change the machine state, so no need for
     * a ->wakeup method.
     */
    qemu_register_wakeup_support();

    if (kvm_enabled()) {
        /* to stop and start vmclock */