Archipelago » qemu

/*

 * QEMU PC System Emulator

 *

 * Copyright (c) 2003-2004 Fabrice Bellard

 *

 * 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 "hw/hw.h"

#include "hw/i386/pc.h"

#include "hw/char/serial.h"

#include "hw/i386/apic.h"

#include "hw/block/fdc.h"

#include "hw/ide.h"

#include "hw/pci/pci.h"

#include "monitor/monitor.h"

#include "hw/nvram/fw_cfg.h"

#include "hw/timer/hpet.h"

#include "hw/i386/smbios.h"

#include "hw/loader.h"

#include "elf.h"

#include "multiboot.h"

#include "hw/timer/mc146818rtc.h"

#include "hw/timer/i8254.h"

#include "hw/audio/pcspk.h"

#include "hw/pci/msi.h"

#include "hw/sysbus.h"

#include "sysemu/sysemu.h"

#include "sysemu/kvm.h"

#include "kvm_i386.h"

#include "hw/xen/xen.h"

#include "sysemu/blockdev.h"

#include "hw/block/block.h"

#include "ui/qemu-spice.h"

#include "exec/memory.h"

#include "exec/address-spaces.h"

#include "sysemu/arch_init.h"

#include "qemu/bitmap.h"

#include "qemu/config-file.h"

#include "hw/acpi/acpi.h"

#include "hw/cpu/icc_bus.h"

#include "hw/boards.h"

#include "hw/pci/pci_host.h"

#include "acpi-build.h"

/* debug PC/ISA interrupts */

//#define DEBUG_IRQ

#ifdef DEBUG_IRQ

#define DPRINTF(fmt, ...)                                       \

    do { printf("CPUIRQ: " fmt , ## __VA_ARGS__); } while (0)

#else

#define DPRINTF(fmt, ...)

#endif

/* Leave a chunk of memory at the top of RAM for the BIOS ACPI tables.  */

#define ACPI_DATA_SIZE       0x10000

#define BIOS_CFG_IOPORT 0x510

#define FW_CFG_ACPI_TABLES (FW_CFG_ARCH_LOCAL + 0)

#define FW_CFG_SMBIOS_ENTRIES (FW_CFG_ARCH_LOCAL + 1)

#define FW_CFG_IRQ0_OVERRIDE (FW_CFG_ARCH_LOCAL + 2)

#define FW_CFG_E820_TABLE (FW_CFG_ARCH_LOCAL + 3)

#define FW_CFG_HPET (FW_CFG_ARCH_LOCAL + 4)

#define E820_NR_ENTRIES                16

struct e820_entry {

    uint64_t address;

    uint64_t length;

    uint32_t type;

} QEMU_PACKED __attribute((__aligned__(4)));

struct e820_table {

    uint32_t count;

    struct e820_entry entry[E820_NR_ENTRIES];

} QEMU_PACKED __attribute((__aligned__(4)));

static struct e820_table e820_reserve;

static struct e820_entry *e820_table;

static unsigned e820_entries;

struct hpet_fw_config hpet_cfg = {.count = UINT8_MAX};

void gsi_handler(void *opaque, int n, int level)

{

    GSIState *s = opaque;

    DPRINTF("pc: %s GSI %d\n", level ? "raising" : "lowering", n);

    if (n < ISA_NUM_IRQS) {

        qemu_set_irq(s->i8259_irq[n], level);

    }

    qemu_set_irq(s->ioapic_irq[n], level);

}

static void ioport80_write(void *opaque, hwaddr addr, uint64_t data,

                           unsigned size)

{

}

static uint64_t ioport80_read(void *opaque, hwaddr addr, unsigned size)

{

    return 0xffffffffffffffffULL;

}

/* MSDOS compatibility mode FPU exception support */

static qemu_irq ferr_irq;

void pc_register_ferr_irq(qemu_irq irq)

{

    ferr_irq = irq;

}

/* XXX: add IGNNE support */

void cpu_set_ferr(CPUX86State *s)

{

    qemu_irq_raise(ferr_irq);

}

static void ioportF0_write(void *opaque, hwaddr addr, uint64_t data,

                           unsigned size)

{

    qemu_irq_lower(ferr_irq);

}

static uint64_t ioportF0_read(void *opaque, hwaddr addr, unsigned size)

{

    return 0xffffffffffffffffULL;

}

/* TSC handling */

uint64_t cpu_get_tsc(CPUX86State *env)

{

    return cpu_get_ticks();

}

/* SMM support */

static cpu_set_smm_t smm_set;

static void *smm_arg;

void cpu_smm_register(cpu_set_smm_t callback, void *arg)

{

    assert(smm_set == NULL);

    assert(smm_arg == NULL);

    smm_set = callback;

    smm_arg = arg;

}

void cpu_smm_update(CPUX86State *env)

{

    if (smm_set && smm_arg && CPU(x86_env_get_cpu(env)) == first_cpu) {

        smm_set(!!(env->hflags & HF_SMM_MASK), smm_arg);

    }

}

/* IRQ handling */

int cpu_get_pic_interrupt(CPUX86State *env)

{

    int intno;

    intno = apic_get_interrupt(env->apic_state);

    if (intno >= 0) {

        return intno;

    }

    /* read the irq from the PIC */

    if (!apic_accept_pic_intr(env->apic_state)) {

        return -1;

    }

    intno = pic_read_irq(isa_pic);

    return intno;

}

static void pic_irq_request(void *opaque, int irq, int level)

{

    CPUState *cs = first_cpu;

    X86CPU *cpu = X86_CPU(cs);

    CPUX86State *env = &cpu->env;

    DPRINTF("pic_irqs: %s irq %d\n", level? "raise" : "lower", irq);

    if (env->apic_state) {

        CPU_FOREACH(cs) {

            cpu = X86_CPU(cs);

            env = &cpu->env;

            if (apic_accept_pic_intr(env->apic_state)) {

                apic_deliver_pic_intr(env->apic_state, level);

            }

        }

    } else {

        if (level) {

            cpu_interrupt(cs, CPU_INTERRUPT_HARD);

        } else {

            cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD);

        }

    }

}

/* PC cmos mappings */

#define REG_EQUIPMENT_BYTE          0x14

static int cmos_get_fd_drive_type(FDriveType fd0)

{

    int val;

    switch (fd0) {

    case FDRIVE_DRV_144:

        /* 1.44 Mb 3"5 drive */

        val = 4;

        break;

    case FDRIVE_DRV_288:

        /* 2.88 Mb 3"5 drive */

        val = 5;

        break;

    case FDRIVE_DRV_120:

        /* 1.2 Mb 5"5 drive */

        val = 2;

        break;

    case FDRIVE_DRV_NONE:

    default:

        val = 0;

        break;

    }

    return val;

}

static void cmos_init_hd(ISADevice *s, int type_ofs, int info_ofs,

                         int16_t cylinders, int8_t heads, int8_t sectors)

{

    rtc_set_memory(s, type_ofs, 47);

    rtc_set_memory(s, info_ofs, cylinders);

    rtc_set_memory(s, info_ofs + 1, cylinders >> 8);

    rtc_set_memory(s, info_ofs + 2, heads);

    rtc_set_memory(s, info_ofs + 3, 0xff);

    rtc_set_memory(s, info_ofs + 4, 0xff);

    rtc_set_memory(s, info_ofs + 5, 0xc0 | ((heads > 8) << 3));

    rtc_set_memory(s, info_ofs + 6, cylinders);

    rtc_set_memory(s, info_ofs + 7, cylinders >> 8);

    rtc_set_memory(s, info_ofs + 8, sectors);

}

/* convert boot_device letter to something recognizable by the bios */

static int boot_device2nibble(char boot_device)

{

    switch(boot_device) {

    case 'a':

    case 'b':

        return 0x01; /* floppy boot */

    case 'c':

        return 0x02; /* hard drive boot */

    case 'd':

        return 0x03; /* CD-ROM boot */

    case 'n':

        return 0x04; /* Network boot */

    }

    return 0;

}

static int set_boot_dev(ISADevice *s, const char *boot_device)

{

#define PC_MAX_BOOT_DEVICES 3

    int nbds, bds[3] = { 0, };

    int i;

    nbds = strlen(boot_device);

    if (nbds > PC_MAX_BOOT_DEVICES) {

        error_report("Too many boot devices for PC");

        return(1);

    }

    for (i = 0; i < nbds; i++) {

        bds[i] = boot_device2nibble(boot_device[i]);

        if (bds[i] == 0) {

            error_report("Invalid boot device for PC: '%c'",

                         boot_device[i]);

            return(1);

        }

    }

    rtc_set_memory(s, 0x3d, (bds[1] << 4) | bds[0]);

    rtc_set_memory(s, 0x38, (bds[2] << 4) | (fd_bootchk ? 0x0 : 0x1));

    return(0);

}

static int pc_boot_set(void *opaque, const char *boot_device)

{

    return set_boot_dev(opaque, boot_device);

}

typedef struct pc_cmos_init_late_arg {

    ISADevice *rtc_state;

    BusState *idebus[2];

} pc_cmos_init_late_arg;

static void pc_cmos_init_late(void *opaque)

{

    pc_cmos_init_late_arg *arg = opaque;

    ISADevice *s = arg->rtc_state;

    int16_t cylinders;

    int8_t heads, sectors;

    int val;

    int i, trans;

    val = 0;

    if (ide_get_geometry(arg->idebus[0], 0,

                         &cylinders, &heads, &sectors) >= 0) {

        cmos_init_hd(s, 0x19, 0x1b, cylinders, heads, sectors);

        val |= 0xf0;

    }

    if (ide_get_geometry(arg->idebus[0], 1,

                         &cylinders, &heads, &sectors) >= 0) {

        cmos_init_hd(s, 0x1a, 0x24, cylinders, heads, sectors);

        val |= 0x0f;

    }

    rtc_set_memory(s, 0x12, val);

    val = 0;

    for (i = 0; i < 4; i++) {

        /* NOTE: ide_get_geometry() returns the physical

           geometry.  It is always such that: 1 <= sects <= 63, 1

           <= heads <= 16, 1 <= cylinders <= 16383. The BIOS

           geometry can be different if a translation is done. */

        if (ide_get_geometry(arg->idebus[i / 2], i % 2,

                             &cylinders, &heads, &sectors) >= 0) {

            trans = ide_get_bios_chs_trans(arg->idebus[i / 2], i % 2) - 1;

            assert((trans & ~3) == 0);

            val |= trans << (i * 2);

        }

    }

    rtc_set_memory(s, 0x39, val);

    qemu_unregister_reset(pc_cmos_init_late, opaque);

}

typedef struct RTCCPUHotplugArg {

    Notifier cpu_added_notifier;

    ISADevice *rtc_state;

} RTCCPUHotplugArg;

static void rtc_notify_cpu_added(Notifier *notifier, void *data)

{

    RTCCPUHotplugArg *arg = container_of(notifier, RTCCPUHotplugArg,

                                         cpu_added_notifier);

    ISADevice *s = arg->rtc_state;

    /* increment the number of CPUs */

    rtc_set_memory(s, 0x5f, rtc_get_memory(s, 0x5f) + 1);

}

void pc_cmos_init(ram_addr_t ram_size, ram_addr_t above_4g_mem_size,

                  const char *boot_device,

                  ISADevice *floppy, BusState *idebus0, BusState *idebus1,

                  ISADevice *s)

{

    int val, nb, i;

    FDriveType fd_type[2] = { FDRIVE_DRV_NONE, FDRIVE_DRV_NONE };

    static pc_cmos_init_late_arg arg;

    static RTCCPUHotplugArg cpu_hotplug_cb;

    /* various important CMOS locations needed by PC/Bochs bios */

    /* memory size */

    /* base memory (first MiB) */

    val = MIN(ram_size / 1024, 640);

    rtc_set_memory(s, 0x15, val);

    rtc_set_memory(s, 0x16, val >> 8);

    /* extended memory (next 64MiB) */

    if (ram_size > 1024 * 1024) {

        val = (ram_size - 1024 * 1024) / 1024;

    } else {

        val = 0;

    }

    if (val > 65535)

        val = 65535;

    rtc_set_memory(s, 0x17, val);

    rtc_set_memory(s, 0x18, val >> 8);

    rtc_set_memory(s, 0x30, val);

    rtc_set_memory(s, 0x31, val >> 8);

    /* memory between 16MiB and 4GiB */

    if (ram_size > 16 * 1024 * 1024) {

        val = (ram_size - 16 * 1024 * 1024) / 65536;

    } else {

        val = 0;

    }

    if (val > 65535)

        val = 65535;

    rtc_set_memory(s, 0x34, val);

    rtc_set_memory(s, 0x35, val >> 8);

    /* memory above 4GiB */

    val = above_4g_mem_size / 65536;

    rtc_set_memory(s, 0x5b, val);

    rtc_set_memory(s, 0x5c, val >> 8);

    rtc_set_memory(s, 0x5d, val >> 16);

    /* set the number of CPU */

    rtc_set_memory(s, 0x5f, smp_cpus - 1);

    /* init CPU hotplug notifier */

    cpu_hotplug_cb.rtc_state = s;

    cpu_hotplug_cb.cpu_added_notifier.notify = rtc_notify_cpu_added;

    qemu_register_cpu_added_notifier(&cpu_hotplug_cb.cpu_added_notifier);

    if (set_boot_dev(s, boot_device)) {

        exit(1);

    }

    /* floppy type */

    if (floppy) {

        for (i = 0; i < 2; i++) {

            fd_type[i] = isa_fdc_get_drive_type(floppy, i);

        }

    }

    val = (cmos_get_fd_drive_type(fd_type[0]) << 4) |

        cmos_get_fd_drive_type(fd_type[1]);

    rtc_set_memory(s, 0x10, val);

    val = 0;

    nb = 0;

    if (fd_type[0] < FDRIVE_DRV_NONE) {

        nb++;

    }

    if (fd_type[1] < FDRIVE_DRV_NONE) {

        nb++;

    }

    switch (nb) {

    case 0:

        break;

    case 1:

        val |= 0x01; /* 1 drive, ready for boot */

        break;

    case 2:

        val |= 0x41; /* 2 drives, ready for boot */

        break;

    }

    val |= 0x02; /* FPU is there */

    val |= 0x04; /* PS/2 mouse installed */

    rtc_set_memory(s, REG_EQUIPMENT_BYTE, val);

    /* hard drives */

    arg.rtc_state = s;

    arg.idebus[0] = idebus0;

    arg.idebus[1] = idebus1;

    qemu_register_reset(pc_cmos_init_late, &arg);

}

#define TYPE_PORT92 "port92"

#define PORT92(obj) OBJECT_CHECK(Port92State, (obj), TYPE_PORT92)

/* port 92 stuff: could be split off */

typedef struct Port92State {

    ISADevice parent_obj;

    MemoryRegion io;

    uint8_t outport;

    qemu_irq *a20_out;

} Port92State;

static void port92_write(void *opaque, hwaddr addr, uint64_t val,

                         unsigned size)

{

    Port92State *s = opaque;

    DPRINTF("port92: write 0x%02x\n", val);

    s->outport = val;

    qemu_set_irq(*s->a20_out, (val >> 1) & 1);

    if (val & 1) {

        qemu_system_reset_request();

    }

}

static uint64_t port92_read(void *opaque, hwaddr addr,

                            unsigned size)

{

    Port92State *s = opaque;

    uint32_t ret;

    ret = s->outport;

    DPRINTF("port92: read 0x%02x\n", ret);

    return ret;

}

static void port92_init(ISADevice *dev, qemu_irq *a20_out)

{

    Port92State *s = PORT92(dev);

    s->a20_out = a20_out;

}

static const VMStateDescription vmstate_port92_isa = {

    .name = "port92",

    .version_id = 1,

    .minimum_version_id = 1,

    .minimum_version_id_old = 1,

    .fields      = (VMStateField []) {

        VMSTATE_UINT8(outport, Port92State),

        VMSTATE_END_OF_LIST()

    }

};

static void port92_reset(DeviceState *d)

{

    Port92State *s = PORT92(d);

    s->outport &= ~1;

}

static const MemoryRegionOps port92_ops = {

    .read = port92_read,

    .write = port92_write,

    .impl = {

        .min_access_size = 1,

        .max_access_size = 1,

    },

    .endianness = DEVICE_LITTLE_ENDIAN,

};

static void port92_initfn(Object *obj)

{

    Port92State *s = PORT92(obj);

    memory_region_init_io(&s->io, OBJECT(s), &port92_ops, s, "port92", 1);

    s->outport = 0;

}

static void port92_realizefn(DeviceState *dev, Error **errp)

{

    ISADevice *isadev = ISA_DEVICE(dev);

    Port92State *s = PORT92(dev);

    isa_register_ioport(isadev, &s->io, 0x92);

}

static void port92_class_initfn(ObjectClass *klass, void *data)

{

    DeviceClass *dc = DEVICE_CLASS(klass);

    dc->cannot_instantiate_with_device_add_yet = true; /* FIXME explain why */

    dc->realize = port92_realizefn;

    dc->reset = port92_reset;

    dc->vmsd = &vmstate_port92_isa;

}

static const TypeInfo port92_info = {

    .name          = TYPE_PORT92,

    .parent        = TYPE_ISA_DEVICE,

    .instance_size = sizeof(Port92State),

    .instance_init = port92_initfn,

    .class_init    = port92_class_initfn,

};

static void port92_register_types(void)

{

    type_register_static(&port92_info);

}

type_init(port92_register_types)

static void handle_a20_line_change(void *opaque, int irq, int level)

{

    X86CPU *cpu = opaque;

    /* XXX: send to all CPUs ? */

    /* XXX: add logic to handle multiple A20 line sources */

    x86_cpu_set_a20(cpu, level);

}

int e820_add_entry(uint64_t address, uint64_t length, uint32_t type)

{

    int index = le32_to_cpu(e820_reserve.count);

    struct e820_entry *entry;

    if (type != E820_RAM) {

        /* old FW_CFG_E820_TABLE entry -- reservations only */

        if (index >= E820_NR_ENTRIES) {

            return -EBUSY;

        }

        entry = &e820_reserve.entry[index++];

        entry->address = cpu_to_le64(address);

        entry->length = cpu_to_le64(length);

        entry->type = cpu_to_le32(type);

        e820_reserve.count = cpu_to_le32(index);

    }

    /* new "etc/e820" file -- include ram too */

    e820_table = g_realloc(e820_table,

                           sizeof(struct e820_entry) * (e820_entries+1));

    e820_table[e820_entries].address = cpu_to_le64(address);

    e820_table[e820_entries].length = cpu_to_le64(length);

    e820_table[e820_entries].type = cpu_to_le32(type);

    e820_entries++;

    return e820_entries;

}

/* Calculates the limit to CPU APIC ID values

 *

 * This function returns the limit for the APIC ID value, so that all

 * CPU APIC IDs are < pc_apic_id_limit().

 *

 * This is used for FW_CFG_MAX_CPUS. See comments on bochs_bios_init().

 */

static unsigned int pc_apic_id_limit(unsigned int max_cpus)

{

    return x86_cpu_apic_id_from_index(max_cpus - 1) + 1;

}

static FWCfgState *bochs_bios_init(void)

{

    FWCfgState *fw_cfg;

    uint8_t *smbios_table;

    size_t smbios_len;

    uint64_t *numa_fw_cfg;

    int i, j;

    unsigned int apic_id_limit = pc_apic_id_limit(max_cpus);

    fw_cfg = fw_cfg_init(BIOS_CFG_IOPORT, BIOS_CFG_IOPORT + 1, 0, 0);

    /* FW_CFG_MAX_CPUS is a bit confusing/problematic on x86:

     *

     * SeaBIOS needs FW_CFG_MAX_CPUS for CPU hotplug, but the CPU hotplug

     * QEMU<->SeaBIOS interface is not based on the "CPU index", but on the APIC

     * ID of hotplugged CPUs[1]. This means that FW_CFG_MAX_CPUS is not the

     * "maximum number of CPUs", but the "limit to the APIC ID values SeaBIOS

     * may see".

     *

     * So, this means we must not use max_cpus, here, but the maximum possible

     * APIC ID value, plus one.

     *

     * [1] The only kind of "CPU identifier" used between SeaBIOS and QEMU is

     *     the APIC ID, not the "CPU index"

     */

    fw_cfg_add_i16(fw_cfg, FW_CFG_MAX_CPUS, (uint16_t)apic_id_limit);

    fw_cfg_add_i32(fw_cfg, FW_CFG_ID, 1);

    fw_cfg_add_i64(fw_cfg, FW_CFG_RAM_SIZE, (uint64_t)ram_size);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_ACPI_TABLES,

                     acpi_tables, acpi_tables_len);

    fw_cfg_add_i32(fw_cfg, FW_CFG_IRQ0_OVERRIDE, kvm_allows_irq0_override());

    smbios_table = smbios_get_table(&smbios_len);

    if (smbios_table)

        fw_cfg_add_bytes(fw_cfg, FW_CFG_SMBIOS_ENTRIES,

                         smbios_table, smbios_len);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_E820_TABLE,

                     &e820_reserve, sizeof(e820_reserve));

    fw_cfg_add_file(fw_cfg, "etc/e820", e820_table,

                    sizeof(struct e820_entry) * e820_entries);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_HPET, &hpet_cfg, sizeof(hpet_cfg));

    /* allocate memory for the NUMA channel: one (64bit) word for the number

     * of nodes, one word for each VCPU->node and one word for each node to

     * hold the amount of memory.

     */

    numa_fw_cfg = g_new0(uint64_t, 1 + apic_id_limit + nb_numa_nodes);

    numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);

    for (i = 0; i < max_cpus; i++) {

        unsigned int apic_id = x86_cpu_apic_id_from_index(i);

        assert(apic_id < apic_id_limit);

        for (j = 0; j < nb_numa_nodes; j++) {

            if (test_bit(i, node_cpumask[j])) {

                numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);

                break;

            }

        }

    }

    for (i = 0; i < nb_numa_nodes; i++) {

        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(node_mem[i]);

    }

    fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,

                     (1 + apic_id_limit + nb_numa_nodes) *

                     sizeof(*numa_fw_cfg));

    return fw_cfg;

}

static long get_file_size(FILE *f)

{

    long where, size;

    /* XXX: on Unix systems, using fstat() probably makes more sense */

    where = ftell(f);

    fseek(f, 0, SEEK_END);

    size = ftell(f);

    fseek(f, where, SEEK_SET);

    return size;

}

static void load_linux(FWCfgState *fw_cfg,

                       const char *kernel_filename,

                       const char *initrd_filename,

                       const char *kernel_cmdline,

                       hwaddr max_ram_size)

{

    uint16_t protocol;

    int setup_size, kernel_size, initrd_size = 0, cmdline_size;

    uint32_t initrd_max;

    uint8_t header[8192], *setup, *kernel, *initrd_data;

    hwaddr real_addr, prot_addr, cmdline_addr, initrd_addr = 0;

    FILE *f;

    char *vmode;

    /* Align to 16 bytes as a paranoia measure */

    cmdline_size = (strlen(kernel_cmdline)+16) & ~15;

    /* load the kernel header */

    f = fopen(kernel_filename, "rb");

    if (!f || !(kernel_size = get_file_size(f)) ||

        fread(header, 1, MIN(ARRAY_SIZE(header), kernel_size), f) !=

        MIN(ARRAY_SIZE(header), kernel_size)) {

        fprintf(stderr, "qemu: could not load kernel '%s': %s\n",

                kernel_filename, strerror(errno));

        exit(1);

    }

    /* kernel protocol version */

#if 0

    fprintf(stderr, "header magic: %#x\n", ldl_p(header+0x202));

#endif

    if (ldl_p(header+0x202) == 0x53726448) {

        protocol = lduw_p(header+0x206);

    } else {

        /* This looks like a multiboot kernel. If it is, let's stop

           treating it like a Linux kernel. */

        if (load_multiboot(fw_cfg, f, kernel_filename, initrd_filename,

                           kernel_cmdline, kernel_size, header)) {

            return;

        }

        protocol = 0;

    }

    if (protocol < 0x200 || !(header[0x211] & 0x01)) {

        /* Low kernel */

        real_addr    = 0x90000;

        cmdline_addr = 0x9a000 - cmdline_size;

        prot_addr    = 0x10000;

    } else if (protocol < 0x202) {

        /* High but ancient kernel */

        real_addr    = 0x90000;

        cmdline_addr = 0x9a000 - cmdline_size;

        prot_addr    = 0x100000;

    } else {

        /* High and recent kernel */

        real_addr    = 0x10000;

        cmdline_addr = 0x20000;

        prot_addr    = 0x100000;

    }

#if 0

    fprintf(stderr,

            "qemu: real_addr     = 0x" TARGET_FMT_plx "\n"

            "qemu: cmdline_addr  = 0x" TARGET_FMT_plx "\n"

            "qemu: prot_addr     = 0x" TARGET_FMT_plx "\n",

            real_addr,

            cmdline_addr,

            prot_addr);

#endif

    /* highest address for loading the initrd */

    if (protocol >= 0x203) {

        initrd_max = ldl_p(header+0x22c);

    } else {

        initrd_max = 0x37ffffff;

    }

    if (initrd_max >= max_ram_size-ACPI_DATA_SIZE)

            initrd_max = max_ram_size-ACPI_DATA_SIZE-1;

    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_ADDR, cmdline_addr);

    fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, strlen(kernel_cmdline)+1);

    fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, kernel_cmdline);

    if (protocol >= 0x202) {

        stl_p(header+0x228, cmdline_addr);

    } else {

        stw_p(header+0x20, 0xA33F);

        stw_p(header+0x22, cmdline_addr-real_addr);

    }

    /* handle vga= parameter */

    vmode = strstr(kernel_cmdline, "vga=");

    if (vmode) {

        unsigned int video_mode;

        /* skip "vga=" */

        vmode += 4;

        if (!strncmp(vmode, "normal", 6)) {

            video_mode = 0xffff;

        } else if (!strncmp(vmode, "ext", 3)) {

            video_mode = 0xfffe;

        } else if (!strncmp(vmode, "ask", 3)) {

            video_mode = 0xfffd;

        } else {

            video_mode = strtol(vmode, NULL, 0);

        }

        stw_p(header+0x1fa, video_mode);

    }

    /* loader type */

    /* High nybble = B reserved for QEMU; low nybble is revision number.

       If this code is substantially changed, you may want to consider

       incrementing the revision. */

    if (protocol >= 0x200) {

        header[0x210] = 0xB0;

    }

    /* heap */

    if (protocol >= 0x201) {

        header[0x211] |= 0x80;        /* CAN_USE_HEAP */

        stw_p(header+0x224, cmdline_addr-real_addr-0x200);

    }

    /* load initrd */

    if (initrd_filename) {

        if (protocol < 0x200) {

            fprintf(stderr, "qemu: linux kernel too old to load a ram disk\n");

            exit(1);

        }

        initrd_size = get_image_size(initrd_filename);

        if (initrd_size < 0) {

            fprintf(stderr, "qemu: error reading initrd %s\n",

                    initrd_filename);

            exit(1);

        }

        initrd_addr = (initrd_max-initrd_size) & ~4095;

        initrd_data = g_malloc(initrd_size);

        load_image(initrd_filename, initrd_data);

        fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_ADDR, initrd_addr);

        fw_cfg_add_i32(fw_cfg, FW_CFG_INITRD_SIZE, initrd_size);

        fw_cfg_add_bytes(fw_cfg, FW_CFG_INITRD_DATA, initrd_data, initrd_size);

        stl_p(header+0x218, initrd_addr);

        stl_p(header+0x21c, initrd_size);

    }

    /* load kernel and setup */

    setup_size = header[0x1f1];

    if (setup_size == 0) {

        setup_size = 4;

    }

    setup_size = (setup_size+1)*512;

    kernel_size -= setup_size;

    setup  = g_malloc(setup_size);

    kernel = g_malloc(kernel_size);

    fseek(f, 0, SEEK_SET);

    if (fread(setup, 1, setup_size, f) != setup_size) {

        fprintf(stderr, "fread() failed\n");

        exit(1);

    }

    if (fread(kernel, 1, kernel_size, f) != kernel_size) {

        fprintf(stderr, "fread() failed\n");

        exit(1);

    }

    fclose(f);

    memcpy(setup, header, MIN(sizeof(header), setup_size));

    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_ADDR, prot_addr);

    fw_cfg_add_i32(fw_cfg, FW_CFG_KERNEL_SIZE, kernel_size);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_KERNEL_DATA, kernel, kernel_size);

    fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_ADDR, real_addr);

    fw_cfg_add_i32(fw_cfg, FW_CFG_SETUP_SIZE, setup_size);

    fw_cfg_add_bytes(fw_cfg, FW_CFG_SETUP_DATA, setup, setup_size);

    option_rom[nb_option_roms].name = "linuxboot.bin";

    option_rom[nb_option_roms].bootindex = 0;

    nb_option_roms++;

}

#define NE2000_NB_MAX 6

static const int ne2000_io[NE2000_NB_MAX] = { 0x300, 0x320, 0x340, 0x360,

                                              0x280, 0x380 };

static const int ne2000_irq[NE2000_NB_MAX] = { 9, 10, 11, 3, 4, 5 };

static const int parallel_io[MAX_PARALLEL_PORTS] = { 0x378, 0x278, 0x3bc };

static const int parallel_irq[MAX_PARALLEL_PORTS] = { 7, 7, 7 };

void pc_init_ne2k_isa(ISABus *bus, NICInfo *nd)

{

    static int nb_ne2k = 0;

    if (nb_ne2k == NE2000_NB_MAX)

        return;

    isa_ne2000_init(bus, ne2000_io[nb_ne2k],

                    ne2000_irq[nb_ne2k], nd);

    nb_ne2k++;

}

DeviceState *cpu_get_current_apic(void)

{

    if (current_cpu) {

        X86CPU *cpu = X86_CPU(current_cpu);

        return cpu->env.apic_state;

    } else {

        return NULL;

    }

}

void pc_acpi_smi_interrupt(void *opaque, int irq, int level)

{

    X86CPU *cpu = opaque;

    if (level) {

        cpu_interrupt(CPU(cpu), CPU_INTERRUPT_SMI);

    }

}

static X86CPU *pc_new_cpu(const char *cpu_model, int64_t apic_id,

                          DeviceState *icc_bridge, Error **errp)

{

    X86CPU *cpu;

    Error *local_err = NULL;

    cpu = cpu_x86_create(cpu_model, icc_bridge, &local_err);

    if (local_err != NULL) {

        error_propagate(errp, local_err);

        return NULL;

    }

    object_property_set_int(OBJECT(cpu), apic_id, "apic-id", &local_err);

    object_property_set_bool(OBJECT(cpu), true, "realized", &local_err);

    if (local_err) {

        error_propagate(errp, local_err);

        object_unref(OBJECT(cpu));

        cpu = NULL;

    }

    return cpu;

}

static const char *current_cpu_model;

void pc_hot_add_cpu(const int64_t id, Error **errp)

{

    DeviceState *icc_bridge;

    int64_t apic_id = x86_cpu_apic_id_from_index(id);

    if (id < 0) {

        error_setg(errp, "Invalid CPU id: %" PRIi64, id);

        return;

    }

    if (cpu_exists(apic_id)) {

        error_setg(errp, "Unable to add CPU: %" PRIi64

                   ", it already exists", id);

        return;

    }

    if (id >= max_cpus) {

        error_setg(errp, "Unable to add CPU: %" PRIi64

                   ", max allowed: %d", id, max_cpus - 1);

        return;

    }

    icc_bridge = DEVICE(object_resolve_path_type("icc-bridge",

                                                 TYPE_ICC_BRIDGE, NULL));

    pc_new_cpu(current_cpu_model, apic_id, icc_bridge, errp);

}

void pc_cpus_init(const char *cpu_model, DeviceState *icc_bridge)

{

    int i;

    X86CPU *cpu = NULL;

    Error *error = NULL;

    /* init CPUs */

    if (cpu_model == NULL) {

#ifdef TARGET_X86_64

        cpu_model = "qemu64";

#else

        cpu_model = "qemu32";

#endif

    }

    current_cpu_model = cpu_model;

    for (i = 0; i < smp_cpus; i++) {

        cpu = pc_new_cpu(cpu_model, x86_cpu_apic_id_from_index(i),

                         icc_bridge, &error);

        if (error) {

            error_report("%s", error_get_pretty(error));

            error_free(error);

            exit(1);

        }

    }

    /* map APIC MMIO area if CPU has APIC */

    if (cpu && cpu->env.apic_state) {

        /* XXX: what if the base changes? */

        sysbus_mmio_map_overlap(SYS_BUS_DEVICE(icc_bridge), 0,

                                APIC_DEFAULT_ADDRESS, 0x1000);

    }

}

/* pci-info ROM file. Little endian format */

typedef struct PcRomPciInfo {

    uint64_t w32_min;

    uint64_t w32_max;

    uint64_t w64_min;

    uint64_t w64_max;

} PcRomPciInfo;

static void pc_fw_cfg_guest_info(PcGuestInfo *guest_info)

{

    PcRomPciInfo *info;

    Object *pci_info;

    bool ambiguous = false;

    if (!guest_info->has_pci_info || !guest_info->fw_cfg) {

        return;

    }

    pci_info = object_resolve_path_type("", TYPE_PCI_HOST_BRIDGE, &ambiguous);

    g_assert(!ambiguous);

    if (!pci_info) {

        return;

    }

    info = g_malloc(sizeof *info);

    info->w32_min = cpu_to_le64(object_property_get_int(pci_info,

                                PCI_HOST_PROP_PCI_HOLE_START, NULL));

    info->w32_max = cpu_to_le64(object_property_get_int(pci_info,

                                PCI_HOST_PROP_PCI_HOLE_END, NULL));

    info->w64_min = cpu_to_le64(object_property_get_int(pci_info,

                                PCI_HOST_PROP_PCI_HOLE64_START, NULL));

    info->w64_max = cpu_to_le64(object_property_get_int(pci_info,

                                PCI_HOST_PROP_PCI_HOLE64_END, NULL));

    /* Pass PCI hole info to guest via a side channel.

     * Required so guest PCI enumeration does the right thing. */

    fw_cfg_add_file(guest_info->fw_cfg, "etc/pci-info", info, sizeof *info);

}

typedef struct PcGuestInfoState {

    PcGuestInfo info;

    Notifier machine_done;

} PcGuestInfoState;

static

void pc_guest_info_machine_done(Notifier *notifier, void *data)

{

    PcGuestInfoState *guest_info_state = container_of(notifier,

                                                      PcGuestInfoState,

                                                      machine_done);

    pc_fw_cfg_guest_info(&guest_info_state->info);

    acpi_setup(&guest_info_state->info);

}

PcGuestInfo *pc_guest_info_init(ram_addr_t below_4g_mem_size,

                                ram_addr_t above_4g_mem_size)

{

    PcGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state);

    PcGuestInfo *guest_info = &guest_info_state->info;

    int i, j;

    guest_info->ram_size = below_4g_mem_size + above_4g_mem_size;

    guest_info->apic_id_limit = pc_apic_id_limit(max_cpus);

    guest_info->apic_xrupt_override = kvm_allows_irq0_override();

    guest_info->numa_nodes = nb_numa_nodes;

    guest_info->node_mem = g_memdup(node_mem, guest_info->numa_nodes *

                                    sizeof *guest_info->node_mem);

    guest_info->node_cpu = g_malloc0(guest_info->apic_id_limit *

                                     sizeof *guest_info->node_cpu);

    for (i = 0; i < max_cpus; i++) {

        unsigned int apic_id = x86_cpu_apic_id_from_index(i);

        assert(apic_id < guest_info->apic_id_limit);

        for (j = 0; j < nb_numa_nodes; j++) {

            if (test_bit(i, node_cpumask[j])) {

                guest_info->node_cpu[apic_id] = j;

                break;

            }

        }

    }

    guest_info_state->machine_done.notify = pc_guest_info_machine_done;

    qemu_add_machine_init_done_notifier(&guest_info_state->machine_done);

    return guest_info;

}

/* setup pci memory address space mapping into system address space */

void pc_pci_as_mapping_init(Object *owner, MemoryRegion *system_memory,

                            MemoryRegion *pci_address_space)

{

    /* Set to lower priority than RAM */

    memory_region_add_subregion_overlap(system_memory, 0x0,

                                        pci_address_space, -1);

}

void pc_acpi_init(const char *default_dsdt)

{

    char *filename;

    if (acpi_tables != NULL) {

        /* manually set via -acpitable, leave it alone */

        return;

    }

    filename = qemu_find_file(QEMU_FILE_TYPE_BIOS, default_dsdt);

    if (filename == NULL) {

        fprintf(stderr, "WARNING: failed to find %s\n", default_dsdt);

    } else {

        char *arg;

        QemuOpts *opts;

        Error *err = NULL;

        arg = g_strdup_printf("file=%s", filename);

        /* creates a deep copy of "arg" */

        opts = qemu_opts_parse(qemu_find_opts("acpi"), arg, 0);

        g_assert(opts != NULL);

        acpi_table_add_builtin(opts, &err);

        if (err) {

            error_report("WARNING: failed to load %s: %s", filename,

                         error_get_pretty(err));

            error_free(err);

        }

        g_free(arg);

        g_free(filename);

    }

}

FWCfgState *pc_memory_init(MemoryRegion *system_memory,

                           const char *kernel_filename,

                           const char *kernel_cmdline,

                           const char *initrd_filename,

                           ram_addr_t below_4g_mem_size,

                           ram_addr_t above_4g_mem_size,

                           MemoryRegion *rom_memory,

                           MemoryRegion **ram_memory,

                           PcGuestInfo *guest_info)

{

    int linux_boot, i;

    MemoryRegion *ram, *option_rom_mr;

    MemoryRegion *ram_below_4g, *ram_above_4g;

    FWCfgState *fw_cfg;

    linux_boot = (kernel_filename != NULL);

    /* Allocate RAM.  We allocate it as a single memory region and use

     * aliases to address portions of it, mostly for backwards compatibility

     * with older qemus that used qemu_ram_alloc().

     */

    ram = g_malloc(sizeof(*ram));

    memory_region_init_ram(ram, NULL, "pc.ram",

                           below_4g_mem_size + above_4g_mem_size);

    vmstate_register_ram_global(ram);

    *ram_memory = ram;

    ram_below_4g = g_malloc(sizeof(*ram_below_4g));

    memory_region_init_alias(ram_below_4g, NULL, "ram-below-4g", ram,

                             0, below_4g_mem_size);

    memory_region_add_subregion(system_memory, 0, ram_below_4g);

    e820_add_entry(0, below_4g_mem_size, E820_RAM);

    if (above_4g_mem_size > 0) {

        ram_above_4g = g_malloc(sizeof(*ram_above_4g));

        memory_region_init_alias(ram_above_4g, NULL, "ram-above-4g", ram,

                                 below_4g_mem_size, above_4g_mem_size);

        memory_region_add_subregion(system_memory, 0x100000000ULL,

                                    ram_above_4g);

        e820_add_entry(0x100000000ULL, above_4g_mem_size, E820_RAM);

    }

    /* Initialize PC system firmware */

    pc_system_firmware_init(rom_memory, guest_info->isapc_ram_fw);

    option_rom_mr = g_malloc(sizeof(*option_rom_mr));

    memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE);

    vmstate_register_ram_global(option_rom_mr);

    memory_region_add_subregion_overlap(rom_memory,

                                        PC_ROM_MIN_VGA,

                                        option_rom_mr,

                                        1);

    fw_cfg = bochs_bios_init();

    rom_set_fw(fw_cfg);

    if (linux_boot) {

        load_linux(fw_cfg, kernel_filename, initrd_filename, kernel_cmdline, below_4g_mem_size);

    }

    for (i = 0; i < nb_option_roms; i++) {

        rom_add_option(option_rom[i].name, option_rom[i].bootindex);

    }

    guest_info->fw_cfg = fw_cfg;

    return fw_cfg;

}

qemu_irq *pc_allocate_cpu_irq(void)

{

    return qemu_allocate_irqs(pic_irq_request, NULL, 1);

}

DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus)

{

    DeviceState *dev = NULL;

    if (pci_bus) {

        PCIDevice *pcidev = pci_vga_init(pci_bus);

        dev = pcidev ? &pcidev->qdev : NULL;

    } else if (isa_bus) {

        ISADevice *isadev = isa_vga_init(isa_bus);

        dev = isadev ? DEVICE(isadev) : NULL;

    }

    return dev;

}

static void cpu_request_exit(void *opaque, int irq, int level)

{

    CPUState *cpu = current_cpu;

    if (cpu && level) {

        cpu_exit(cpu);

    }

}

static const MemoryRegionOps ioport80_io_ops = {

    .write = ioport80_write,

    .read = ioport80_read,

    .endianness = DEVICE_NATIVE_ENDIAN,

    .impl = {

        .min_access_size = 1,

        .max_access_size = 1,

    },

};

static const MemoryRegionOps ioportF0_io_ops = {

    .write = ioportF0_write,

    .read = ioportF0_read,

    .endianness = DEVICE_NATIVE_ENDIAN,

    .impl = {

        .min_access_size = 1,

        .max_access_size = 1,

    },

};

void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,

                          ISADevice **rtc_state,

                          ISADevice **floppy,

                          bool no_vmport,

                          uint32 hpet_irqs)

{

    int i;

    DriveInfo *fd[MAX_FD];

    DeviceState *hpet = NULL;

    int pit_isa_irq = 0;

    qemu_irq pit_alt_irq = NULL;

    qemu_irq rtc_irq = NULL;

    qemu_irq *a20_line;

    ISADevice *i8042, *port92, *vmmouse, *pit = NULL;

    qemu_irq *cpu_exit_irq;

    MemoryRegion *ioport80_io = g_new(MemoryRegion, 1);

    MemoryRegion *ioportF0_io = g_new(MemoryRegion, 1);

    memory_region_init_io(ioport80_io, NULL, &ioport80_io_ops, NULL, "ioport80", 1);

    memory_region_add_subregion(isa_bus->address_space_io, 0x80, ioport80_io);

    memory_region_init_io(ioportF0_io, NULL, &ioportF0_io_ops, NULL, "ioportF0", 1);

    memory_region_add_subregion(isa_bus->address_space_io, 0xf0, ioportF0_io);

    /*

     * Check if an HPET shall be created.

     *

     * Without KVM_CAP_PIT_STATE2, we cannot switch off the in-kernel PIT

     * when the HPET wants to take over. Thus we have to disable the latter.

     */

    if (!no_hpet && (!kvm_irqchip_in_kernel() || kvm_has_pit_state2())) {

        /* In order to set property, here not using sysbus_try_create_simple */

        hpet = qdev_try_create(NULL, TYPE_HPET);

        if (hpet) {

            /* For pc-piix-*, hpet's intcap is always IRQ2. For pc-q35-1.7

             * and earlier, use IRQ2 for compat. Otherwise, use IRQ16~23,

             * IRQ8 and IRQ2.

             */

            uint8_t compat = object_property_get_int(OBJECT(hpet),

                    HPET_INTCAP, NULL);

            if (!compat) {

                qdev_prop_set_uint32(hpet, HPET_INTCAP, hpet_irqs);

            }

            qdev_init_nofail(hpet);

            sysbus_mmio_map(SYS_BUS_DEVICE(hpet), 0, HPET_BASE);

            for (i = 0; i < GSI_NUM_PINS; i++) {

                sysbus_connect_irq(SYS_BUS_DEVICE(hpet), i, gsi[i]);

            }

            pit_isa_irq = -1;

            pit_alt_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_PIT_INT);

            rtc_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_RTC_INT);

        }

    }

    *rtc_state = rtc_init(isa_bus, 2000, rtc_irq);

    qemu_register_boot_set(pc_boot_set, *rtc_state);

    if (!xen_enabled()) {

        if (kvm_irqchip_in_kernel()) {

            pit = kvm_pit_init(isa_bus, 0x40);

        } else {

            pit = pit_init(isa_bus, 0x40, pit_isa_irq, pit_alt_irq);

        }

        if (hpet) {

            /* connect PIT to output control line of the HPET */

            qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(DEVICE(pit), 0));

        }

        pcspk_init(isa_bus, pit);

    }

    for(i = 0; i < MAX_SERIAL_PORTS; i++) {

        if (serial_hds[i]) {

            serial_isa_init(isa_bus, i, serial_hds[i]);

        }

    }

    for(i = 0; i < MAX_PARALLEL_PORTS; i++) {

        if (parallel_hds[i]) {

            parallel_init(isa_bus, i, parallel_hds[i]);

        }

    }

    a20_line = qemu_allocate_irqs(handle_a20_line_change, first_cpu, 2);

    i8042 = isa_create_simple(isa_bus, "i8042");

    i8042_setup_a20_line(i8042, &a20_line[0]);

    if (!no_vmport) {

        vmport_init(isa_bus);

        vmmouse = isa_try_create(isa_bus, "vmmouse");