kvm-all.c

/*
 * QEMU KVM support
 *
 * Copyright IBM, Corp. 2008
 *           Red Hat, Inc. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *  Glauber Costa     <gcosta@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 *
 */

#include "qemu/osdep.h"
#include <sys/ioctl.h>

#include <linux/kvm.h>

#include "qemu-common.h"
#include "qemu/atomic.h"
#include "qemu/option.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "hw/hw.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
#include "hw/s390x/adapter.h"
#include "exec/gdbstub.h"
#include "sysemu/kvm_int.h"
#include "sysemu/cpus.h"
#include "qemu/bswap.h"
#include "exec/memory.h"
#include "exec/ram_addr.h"
#include "exec/address-spaces.h"
#include "qemu/event_notifier.h"
#include "trace-root.h"
#include "hw/irq.h"

#include "hw/boards.h"

/* This check must be after config-host.h is included */
#ifdef CONFIG_EVENTFD
#include <sys/eventfd.h>
#endif

/* KVM uses PAGE_SIZE in its definition of KVM_COALESCED_MMIO_MAX. We
 * need to use the real host PAGE_SIZE, as that's what KVM will use.
 */
#define PAGE_SIZE getpagesize()

//#define DEBUG_KVM

#ifdef DEBUG_KVM
#define DPRINTF(fmt, ...) \
    do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
    do { } while (0)
#endif

#define KVM_MSI_HASHTAB_SIZE    256

struct KVMParkedVcpu {
    unsigned long vcpu_id;
    int kvm_fd;
    QLIST_ENTRY(KVMParkedVcpu) node;
};

struct KVMState
{
    AccelState parent_obj;

    int nr_slots;
    int fd;
    int vmfd;
    int coalesced_mmio;
    struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
    bool coalesced_flush_in_progress;
    int broken_set_mem_region;
    int vcpu_events;
    int robust_singlestep;
    int debugregs;
#ifdef KVM_CAP_SET_GUEST_DEBUG
    struct kvm_sw_breakpoint_head kvm_sw_breakpoints;
#endif
    int many_ioeventfds;
    int intx_set_mask;
    /* The man page (and posix) say ioctl numbers are signed int, but
     * they're not.  Linux, glibc and *BSD all treat ioctl numbers as
     * unsigned, and treating them as signed here can break things */
    unsigned irq_set_ioctl;
    unsigned int sigmask_len;
    GHashTable *gsimap;
#ifdef KVM_CAP_IRQ_ROUTING
    struct kvm_irq_routing *irq_routes;
    int nr_allocated_irq_routes;
    unsigned long *used_gsi_bitmap;
    unsigned int gsi_count;
    QTAILQ_HEAD(msi_hashtab, KVMMSIRoute) msi_hashtab[KVM_MSI_HASHTAB_SIZE];
#endif
    KVMMemoryListener memory_listener;
    QLIST_HEAD(, KVMParkedVcpu) kvm_parked_vcpus;
};

KVMState *kvm_state;
bool kvm_kernel_irqchip;
bool kvm_split_irqchip;
bool kvm_async_interrupts_allowed;
bool kvm_halt_in_kernel_allowed;
bool kvm_eventfds_allowed;
bool kvm_irqfds_allowed;
bool kvm_resamplefds_allowed;
bool kvm_msi_via_irqfd_allowed;
bool kvm_gsi_routing_allowed;
bool kvm_gsi_direct_mapping;
bool kvm_allowed;
bool kvm_readonly_mem_allowed;
bool kvm_vm_attributes_allowed;
bool kvm_direct_msi_allowed;
bool kvm_ioeventfd_any_length_allowed;
bool kvm_msi_use_devid;
static bool kvm_immediate_exit;

static const KVMCapabilityInfo kvm_required_capabilites[] = {
    KVM_CAP_INFO(USER_MEMORY),
    KVM_CAP_INFO(DESTROY_MEMORY_REGION_WORKS),
    KVM_CAP_LAST_INFO
};

int kvm_get_max_memslots(void)
{
    KVMState *s = KVM_STATE(current_machine->accelerator);

    return s->nr_slots;
}

static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml)
{
    KVMState *s = kvm_state;
    int i;

    for (i = 0; i < s->nr_slots; i++) {
        if (kml->slots[i].memory_size == 0) {
            return &kml->slots[i];
        }
    }

    return NULL;
}

bool kvm_has_free_slot(MachineState *ms)
{
    KVMState *s = KVM_STATE(ms->accelerator);

    return kvm_get_free_slot(&s->memory_listener);
}

static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml)
{
    KVMSlot *slot = kvm_get_free_slot(kml);

    if (slot) {
        return slot;
    }

    fprintf(stderr, "%s: no free slot available\n", __func__);
    abort();
}

static KVMSlot *kvm_lookup_matching_slot(KVMMemoryListener *kml,
                                         hwaddr start_addr,
                                         hwaddr end_addr)
{
    KVMState *s = kvm_state;
    int i;

    for (i = 0; i < s->nr_slots; i++) {
        KVMSlot *mem = &kml->slots[i];

        if (start_addr == mem->start_addr &&
            end_addr == mem->start_addr + mem->memory_size) {
            return mem;
        }
    }

    return NULL;
}

/*
 * Find overlapping slot with lowest start address
 */
static KVMSlot *kvm_lookup_overlapping_slot(KVMMemoryListener *kml,
                                            hwaddr start_addr,
                                            hwaddr end_addr)
{
    KVMState *s = kvm_state;
    KVMSlot *found = NULL;
    int i;

    for (i = 0; i < s->nr_slots; i++) {
        KVMSlot *mem = &kml->slots[i];

        if (mem->memory_size == 0 ||
            (found && found->start_addr < mem->start_addr)) {
            continue;
        }

        if (end_addr > mem->start_addr &&
            start_addr < mem->start_addr + mem->memory_size) {
            found = mem;
        }
    }

    return found;
}

int kvm_physical_memory_addr_from_host(KVMState *s, void *ram,
                                       hwaddr *phys_addr)
{
    KVMMemoryListener *kml = &s->memory_listener;
    int i;

    for (i = 0; i < s->nr_slots; i++) {
        KVMSlot *mem = &kml->slots[i];

        if (ram >= mem->ram && ram < mem->ram + mem->memory_size) {
            *phys_addr = mem->start_addr + (ram - mem->ram);
            return 1;
        }
    }

    return 0;
}

static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot)
{
    KVMState *s = kvm_state;
    struct kvm_userspace_memory_region mem;

    mem.slot = slot->slot | (kml->as_id << 16);
    mem.guest_phys_addr = slot->start_addr;
    mem.userspace_addr = (unsigned long)slot->ram;
    mem.flags = slot->flags;

    if (slot->memory_size && mem.flags & KVM_MEM_READONLY) {
        /* Set the slot size to 0 before setting the slot to the desired
         * value. This is needed based on KVM commit 75d61fbc. */
        mem.memory_size = 0;
        kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
    }
    mem.memory_size = slot->memory_size;
    return kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem);
}

int kvm_destroy_vcpu(CPUState *cpu)
{
    KVMState *s = kvm_state;
    long mmap_size;
    struct KVMParkedVcpu *vcpu = NULL;
    int ret = 0;

    DPRINTF("kvm_destroy_vcpu\n");

    mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
    if (mmap_size < 0) {
        ret = mmap_size;
        DPRINTF("KVM_GET_VCPU_MMAP_SIZE failed\n");
        goto err;
    }

    ret = munmap(cpu->kvm_run, mmap_size);
    if (ret < 0) {
        goto err;
    }

    vcpu = g_malloc0(sizeof(*vcpu));
    vcpu->vcpu_id = kvm_arch_vcpu_id(cpu);
    vcpu->kvm_fd = cpu->kvm_fd;
    QLIST_INSERT_HEAD(&kvm_state->kvm_parked_vcpus, vcpu, node);
err:
    return ret;
}

static int kvm_get_vcpu(KVMState *s, unsigned long vcpu_id)
{
    struct KVMParkedVcpu *cpu;

    QLIST_FOREACH(cpu, &s->kvm_parked_vcpus, node) {
        if (cpu->vcpu_id == vcpu_id) {
            int kvm_fd;

            QLIST_REMOVE(cpu, node);
            kvm_fd = cpu->kvm_fd;
            g_free(cpu);
            return kvm_fd;
        }
    }

    return kvm_vm_ioctl(s, KVM_CREATE_VCPU, (void *)vcpu_id);
}

int kvm_init_vcpu(CPUState *cpu)
{
    KVMState *s = kvm_state;
    long mmap_size;
    int ret;

    DPRINTF("kvm_init_vcpu\n");

    ret = kvm_get_vcpu(s, kvm_arch_vcpu_id(cpu));
    if (ret < 0) {
        DPRINTF("kvm_create_vcpu failed\n");
        goto err;
    }

    cpu->kvm_fd = ret;
    cpu->kvm_state = s;
    cpu->kvm_vcpu_dirty = true;

    mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
    if (mmap_size < 0) {
        ret = mmap_size;
        DPRINTF("KVM_GET_VCPU_MMAP_SIZE failed\n");
        goto err;
    }

    cpu->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED,
                        cpu->kvm_fd, 0);
    if (cpu->kvm_run == MAP_FAILED) {
        ret = -errno;
        DPRINTF("mmap'ing vcpu state failed\n");
        goto err;
    }

    if (s->coalesced_mmio && !s->coalesced_mmio_ring) {
        s->coalesced_mmio_ring =
            (void *)cpu->kvm_run + s->coalesced_mmio * PAGE_SIZE;
    }

    ret = kvm_arch_init_vcpu(cpu);
err:
    return ret;
}

/*
 * dirty pages logging control
 */

static int kvm_mem_flags(MemoryRegion *mr)
{
    bool readonly = mr->readonly || memory_region_is_romd(mr);
    int flags = 0;

    if (memory_region_get_dirty_log_mask(mr) != 0) {
        flags |= KVM_MEM_LOG_DIRTY_PAGES;
    }
    if (readonly && kvm_readonly_mem_allowed) {
        flags |= KVM_MEM_READONLY;
    }
    return flags;
}

static int kvm_slot_update_flags(KVMMemoryListener *kml, KVMSlot *mem,
                                 MemoryRegion *mr)
{
    int old_flags;

    old_flags = mem->flags;
    mem->flags = kvm_mem_flags(mr);

    /* If nothing changed effectively, no need to issue ioctl */
    if (mem->flags == old_flags) {
        return 0;
    }

    return kvm_set_user_memory_region(kml, mem);
}

static int kvm_section_update_flags(KVMMemoryListener *kml,
                                    MemoryRegionSection *section)
{
    hwaddr phys_addr = section->offset_within_address_space;
    ram_addr_t size = int128_get64(section->size);
    KVMSlot *mem = kvm_lookup_matching_slot(kml, phys_addr, phys_addr + size);

    if (mem == NULL)  {
        return 0;
    } else {
        return kvm_slot_update_flags(kml, mem, section->mr);
    }
}

static void kvm_log_start(MemoryListener *listener,
                          MemoryRegionSection *section,
                          int old, int new)
{
    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
    int r;

    if (old != 0) {
        return;
    }

    r = kvm_section_update_flags(kml, section);
    if (r < 0) {
        abort();
    }
}

static void kvm_log_stop(MemoryListener *listener,
                          MemoryRegionSection *section,
                          int old, int new)
{
    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
    int r;

    if (new != 0) {
        return;
    }

    r = kvm_section_update_flags(kml, section);
    if (r < 0) {
        abort();
    }
}

/* get kvm's dirty pages bitmap and update qemu's */
static int kvm_get_dirty_pages_log_range(MemoryRegionSection *section,
                                         unsigned long *bitmap)
{
    ram_addr_t start = section->offset_within_region +
                       memory_region_get_ram_addr(section->mr);
    ram_addr_t pages = int128_get64(section->size) / getpagesize();

    cpu_physical_memory_set_dirty_lebitmap(bitmap, start, pages);
    return 0;
}

#define ALIGN(x, y)  (((x)+(y)-1) & ~((y)-1))

/**
 * kvm_physical_sync_dirty_bitmap - Grab dirty bitmap from kernel space
 * This function updates qemu's dirty bitmap using
 * memory_region_set_dirty().  This means all bits are set
 * to dirty.
 *
 * @start_add: start of logged region.
 * @end_addr: end of logged region.
 */
static int kvm_physical_sync_dirty_bitmap(KVMMemoryListener *kml,
                                          MemoryRegionSection *section)
{
    KVMState *s = kvm_state;
    unsigned long size, allocated_size = 0;
    struct kvm_dirty_log d = {};
    KVMSlot *mem;
    int ret = 0;
    hwaddr start_addr = section->offset_within_address_space;
    hwaddr end_addr = start_addr + int128_get64(section->size);

    d.dirty_bitmap = NULL;
    while (start_addr < end_addr) {
        mem = kvm_lookup_overlapping_slot(kml, start_addr, end_addr);
        if (mem == NULL) {
            break;
        }

        /* XXX bad kernel interface alert
         * For dirty bitmap, kernel allocates array of size aligned to
         * bits-per-long.  But for case when the kernel is 64bits and
         * the userspace is 32bits, userspace can't align to the same
         * bits-per-long, since sizeof(long) is different between kernel
         * and user space.  This way, userspace will provide buffer which
         * may be 4 bytes less than the kernel will use, resulting in
         * userspace memory corruption (which is not detectable by valgrind
         * too, in most cases).
         * So for now, let's align to 64 instead of HOST_LONG_BITS here, in
         * a hope that sizeof(long) won't become >8 any time soon.
         */
        size = ALIGN(((mem->memory_size) >> TARGET_PAGE_BITS),
                     /*HOST_LONG_BITS*/ 64) / 8;
        if (!d.dirty_bitmap) {
            d.dirty_bitmap = g_malloc(size);
        } else if (size > allocated_size) {
            d.dirty_bitmap = g_realloc(d.dirty_bitmap, size);
        }
        allocated_size = size;
        memset(d.dirty_bitmap, 0, allocated_size);

        d.slot = mem->slot | (kml->as_id << 16);
        if (kvm_vm_ioctl(s, KVM_GET_DIRTY_LOG, &d) == -1) {
            DPRINTF("ioctl failed %d\n", errno);
            ret = -1;
            break;
        }

        kvm_get_dirty_pages_log_range(section, d.dirty_bitmap);
        start_addr = mem->start_addr + mem->memory_size;
    }
    g_free(d.dirty_bitmap);

    return ret;
}

static void kvm_coalesce_mmio_region(MemoryListener *listener,
                                     MemoryRegionSection *secion,
                                     hwaddr start, hwaddr size)
{
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;
        zone.pad = 0;

        (void)kvm_vm_ioctl(s, KVM_REGISTER_COALESCED_MMIO, &zone);
    }
}

static void kvm_uncoalesce_mmio_region(MemoryListener *listener,
                                       MemoryRegionSection *secion,
                                       hwaddr start, hwaddr size)
{
    KVMState *s = kvm_state;

    if (s->coalesced_mmio) {
        struct kvm_coalesced_mmio_zone zone;

        zone.addr = start;
        zone.size = size;
        zone.pad = 0;

        (void)kvm_vm_ioctl(s, KVM_UNREGISTER_COALESCED_MMIO, &zone);
    }
}

int kvm_check_extension(KVMState *s, unsigned int extension)
{
    int ret;

    ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, extension);
    if (ret < 0) {
        ret = 0;
    }

    return ret;
}

int kvm_vm_check_extension(KVMState *s, unsigned int extension)
{
    int ret;

    ret = kvm_vm_ioctl(s, KVM_CHECK_EXTENSION, extension);
    if (ret < 0) {
        /* VM wide version not implemented, use global one instead */
        ret = kvm_check_extension(s, extension);
    }

    return ret;
}

static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size)
{
#if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN)
    /* The kernel expects ioeventfd values in HOST_WORDS_BIGENDIAN
     * endianness, but the memory core hands them in target endianness.
     * For example, PPC is always treated as big-endian even if running
     * on KVM and on PPC64LE.  Correct here.
     */
    switch (size) {
    case 2:
        val = bswap16(val);
        break;
    case 4:
        val = bswap32(val);
        break;
    }
#endif
    return val;
}

static int kvm_set_ioeventfd_mmio(int fd, hwaddr addr, uint32_t val,
                                  bool assign, uint32_t size, bool datamatch)
{
    int ret;
    struct kvm_ioeventfd iofd = {
        .datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0,
        .addr = addr,
        .len = size,
        .flags = 0,
        .fd = fd,
    };

    if (!kvm_enabled()) {
        return -ENOSYS;
    }

    if (datamatch) {
        iofd.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
    }
    if (!assign) {
        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
    }

    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);

    if (ret < 0) {
        return -errno;
    }

    return 0;
}

static int kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint16_t val,
                                 bool assign, uint32_t size, bool datamatch)
{
    struct kvm_ioeventfd kick = {
        .datamatch = datamatch ? adjust_ioeventfd_endianness(val, size) : 0,
        .addr = addr,
        .flags = KVM_IOEVENTFD_FLAG_PIO,
        .len = size,
        .fd = fd,
    };
    int r;
    if (!kvm_enabled()) {
        return -ENOSYS;
    }
    if (datamatch) {
        kick.flags |= KVM_IOEVENTFD_FLAG_DATAMATCH;
    }
    if (!assign) {
        kick.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
    }
    r = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &kick);
    if (r < 0) {
        return r;
    }
    return 0;
}


static int kvm_check_many_ioeventfds(void)
{
    /* Userspace can use ioeventfd for io notification.  This requires a host
     * that supports eventfd(2) and an I/O thread; since eventfd does not
     * support SIGIO it cannot interrupt the vcpu.
     *
     * Older kernels have a 6 device limit on the KVM io bus.  Find out so we
     * can avoid creating too many ioeventfds.
     */
#if defined(CONFIG_EVENTFD)
    int ioeventfds[7];
    int i, ret = 0;
    for (i = 0; i < ARRAY_SIZE(ioeventfds); i++) {
        ioeventfds[i] = eventfd(0, EFD_CLOEXEC);
        if (ioeventfds[i] < 0) {
            break;
        }
        ret = kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, true, 2, true);
        if (ret < 0) {
            close(ioeventfds[i]);
            break;
        }
    }

    /* Decide whether many devices are supported or not */
    ret = i == ARRAY_SIZE(ioeventfds);

    while (i-- > 0) {
        kvm_set_ioeventfd_pio(ioeventfds[i], 0, i, false, 2, true);
        close(ioeventfds[i]);
    }
    return ret;
#else
    return 0;
#endif
}

static const KVMCapabilityInfo *
kvm_check_extension_list(KVMState *s, const KVMCapabilityInfo *list)
{
    while (list->name) {
        if (!kvm_check_extension(s, list->value)) {
            return list;
        }
        list++;
    }
    return NULL;
}

static void kvm_set_phys_mem(KVMMemoryListener *kml,
                             MemoryRegionSection *section, bool add)
{
    KVMState *s = kvm_state;
    KVMSlot *mem, old;
    int err;
    MemoryRegion *mr = section->mr;
    bool writeable = !mr->readonly && !mr->rom_device;
    hwaddr start_addr = section->offset_within_address_space;
    ram_addr_t size = int128_get64(section->size);
    void *ram = NULL;
    unsigned delta;

    /* kvm works in page size chunks, but the function may be called
       with sub-page size and unaligned start address. Pad the start
       address to next and truncate size to previous page boundary. */
    delta = qemu_real_host_page_size - (start_addr & ~qemu_real_host_page_mask);
    delta &= ~qemu_real_host_page_mask;
    if (delta > size) {
        return;
    }
    start_addr += delta;
    size -= delta;
    size &= qemu_real_host_page_mask;
    if (!size || (start_addr & ~qemu_real_host_page_mask)) {
        return;
    }

    if (!memory_region_is_ram(mr)) {
        if (writeable || !kvm_readonly_mem_allowed) {
            return;
        } else if (!mr->romd_mode) {
            /* If the memory device is not in romd_mode, then we actually want
             * to remove the kvm memory slot so all accesses will trap. */
            add = false;
        }
    }

    ram = memory_region_get_ram_ptr(mr) + section->offset_within_region + delta;

    while (1) {
        mem = kvm_lookup_overlapping_slot(kml, start_addr, start_addr + size);
        if (!mem) {
            break;
        }

        if (add && start_addr >= mem->start_addr &&
            (start_addr + size <= mem->start_addr + mem->memory_size) &&
            (ram - start_addr == mem->ram - mem->start_addr)) {
            /* The new slot fits into the existing one and comes with
             * identical parameters - update flags and done. */
            kvm_slot_update_flags(kml, mem, mr);
            return;
        }

        old = *mem;

        if (mem->flags & KVM_MEM_LOG_DIRTY_PAGES) {
            kvm_physical_sync_dirty_bitmap(kml, section);
        }

        /* unregister the overlapping slot */
        mem->memory_size = 0;
        err = kvm_set_user_memory_region(kml, mem);
        if (err) {
            fprintf(stderr, "%s: error unregistering overlapping slot: %s\n",
                    __func__, strerror(-err));
            abort();
        }

        /* Workaround for older KVM versions: we can't join slots, even not by
         * unregistering the previous ones and then registering the larger
         * slot. We have to maintain the existing fragmentation. Sigh.
         *
         * This workaround assumes that the new slot starts at the same
         * address as the first existing one. If not or if some overlapping
         * slot comes around later, we will fail (not seen in practice so far)
         * - and actually require a recent KVM version. */
        if (s->broken_set_mem_region &&
            old.start_addr == start_addr && old.memory_size < size && add) {
            mem = kvm_alloc_slot(kml);
            mem->memory_size = old.memory_size;
            mem->start_addr = old.start_addr;
            mem->ram = old.ram;
            mem->flags = kvm_mem_flags(mr);

            err = kvm_set_user_memory_region(kml, mem);
            if (err) {
                fprintf(stderr, "%s: error updating slot: %s\n", __func__,
                        strerror(-err));
                abort();
            }

            start_addr += old.memory_size;
            ram += old.memory_size;
            size -= old.memory_size;
            continue;
        }

        /* register prefix slot */
        if (old.start_addr < start_addr) {
            mem = kvm_alloc_slot(kml);
            mem->memory_size = start_addr - old.start_addr;
            mem->start_addr = old.start_addr;
            mem->ram = old.ram;
            mem->flags =  kvm_mem_flags(mr);

            err = kvm_set_user_memory_region(kml, mem);
            if (err) {
                fprintf(stderr, "%s: error registering prefix slot: %s\n",
                        __func__, strerror(-err));
#ifdef TARGET_PPC
                fprintf(stderr, "%s: This is probably because your kernel's " \
                                "PAGE_SIZE is too big. Please try to use 4k " \
                                "PAGE_SIZE!\n", __func__);
#endif
                abort();
            }
        }

        /* register suffix slot */
        if (old.start_addr + old.memory_size > start_addr + size) {
            ram_addr_t size_delta;

            mem = kvm_alloc_slot(kml);
            mem->start_addr = start_addr + size;
            size_delta = mem->start_addr - old.start_addr;
            mem->memory_size = old.memory_size - size_delta;
            mem->ram = old.ram + size_delta;
            mem->flags = kvm_mem_flags(mr);

            err = kvm_set_user_memory_region(kml, mem);
            if (err) {
                fprintf(stderr, "%s: error registering suffix slot: %s\n",
                        __func__, strerror(-err));
                abort();
            }
        }
    }

    /* in case the KVM bug workaround already "consumed" the new slot */
    if (!size) {
        return;
    }
    if (!add) {
        return;
    }
    mem = kvm_alloc_slot(kml);
    mem->memory_size = size;
    mem->start_addr = start_addr;
    mem->ram = ram;
    mem->flags = kvm_mem_flags(mr);

    err = kvm_set_user_memory_region(kml, mem);
    if (err) {
        fprintf(stderr, "%s: error registering slot: %s\n", __func__,
                strerror(-err));
        abort();
    }
}

static void kvm_region_add(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);

    memory_region_ref(section->mr);
    kvm_set_phys_mem(kml, section, true);
}

static void kvm_region_del(MemoryListener *listener,
                           MemoryRegionSection *section)
{
    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);

    kvm_set_phys_mem(kml, section, false);
    memory_region_unref(section->mr);
}

static void kvm_log_sync(MemoryListener *listener,
                         MemoryRegionSection *section)
{
    KVMMemoryListener *kml = container_of(listener, KVMMemoryListener, listener);
    int r;

    r = kvm_physical_sync_dirty_bitmap(kml, section);
    if (r < 0) {
        abort();
    }
}

static void kvm_mem_ioeventfd_add(MemoryListener *listener,
                                  MemoryRegionSection *section,
                                  bool match_data, uint64_t data,
                                  EventNotifier *e)
{
    int fd = event_notifier_get_fd(e);
    int r;

    r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
                               data, true, int128_get64(section->size),
                               match_data);
    if (r < 0) {
        fprintf(stderr, "%s: error adding ioeventfd: %s\n",
                __func__, strerror(-r));
        abort();
    }
}

static void kvm_mem_ioeventfd_del(MemoryListener *listener,
                                  MemoryRegionSection *section,
                                  bool match_data, uint64_t data,
                                  EventNotifier *e)
{
    int fd = event_notifier_get_fd(e);
    int r;

    r = kvm_set_ioeventfd_mmio(fd, section->offset_within_address_space,
                               data, false, int128_get64(section->size),
                               match_data);
    if (r < 0) {
        abort();
    }
}

static void kvm_io_ioeventfd_add(MemoryListener *listener,
                                 MemoryRegionSection *section,
                                 bool match_data, uint64_t data,
                                 EventNotifier *e)
{
    int fd = event_notifier_get_fd(e);
    int r;

    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
                              data, true, int128_get64(section->size),
                              match_data);
    if (r < 0) {
        fprintf(stderr, "%s: error adding ioeventfd: %s\n",
                __func__, strerror(-r));
        abort();
    }
}

static void kvm_io_ioeventfd_del(MemoryListener *listener,
                                 MemoryRegionSection *section,
                                 bool match_data, uint64_t data,
                                 EventNotifier *e)

{
    int fd = event_notifier_get_fd(e);
    int r;

    r = kvm_set_ioeventfd_pio(fd, section->offset_within_address_space,
                              data, false, int128_get64(section->size),
                              match_data);
    if (r < 0) {
        abort();
    }
}

void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,
                                  AddressSpace *as, int as_id)
{
    int i;

    kml->slots = g_malloc0(s->nr_slots * sizeof(KVMSlot));
    kml->as_id = as_id;

    for (i = 0; i < s->nr_slots; i++) {
        kml->slots[i].slot = i;
    }

    kml->listener.region_add = kvm_region_add;
    kml->listener.region_del = kvm_region_del;
    kml->listener.log_start = kvm_log_start;
    kml->listener.log_stop = kvm_log_stop;
    kml->listener.log_sync = kvm_log_sync;
    kml->listener.priority = 10;

    memory_listener_register(&kml->listener, as);
}

static MemoryListener kvm_io_listener = {
    .eventfd_add = kvm_io_ioeventfd_add,
    .eventfd_del = kvm_io_ioeventfd_del,
    .priority = 10,
};

static void kvm_handle_interrupt(CPUState *cpu, int mask)
{
    cpu->interrupt_request |= mask;

    if (!qemu_cpu_is_self(cpu)) {
        qemu_cpu_kick(cpu);
    }
}

int kvm_set_irq(KVMState *s, int irq, int level)
{
    struct kvm_irq_level event;
    int ret;

    assert(kvm_async_interrupts_enabled());

    event.level = level;
    event.irq = irq;