memory.c

/*
 * Physical memory management
 *
 * Copyright 2011 Red Hat, Inc. and/or its affiliates
 *
 * Authors:
 *  Avi Kivity <avi@redhat.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "exec/memory.h"
#include "exec/address-spaces.h"
#include "exec/ioport.h"
#include "qemu/bitops.h"
#include "qom/object.h"
#include "sysemu/kvm.h"
#include "trace.h"
#include <assert.h>

#include "exec/memory-internal.h"

//#define DEBUG_UNASSIGNED

static unsigned memory_region_transaction_depth;
static bool memory_region_update_pending;
static bool global_dirty_log = false;

/* flat_view_mutex is taken around reading as->current_map; the critical
 * section is extremely short, so I'm using a single mutex for every AS.
 * We could also RCU for the read-side.
 *
 * The BQL is taken around transaction commits, hence both locks are taken
 * while writing to as->current_map (with the BQL taken outside).
 */
static QemuMutex flat_view_mutex;

static QTAILQ_HEAD(memory_listeners, MemoryListener) memory_listeners
    = QTAILQ_HEAD_INITIALIZER(memory_listeners);

static QTAILQ_HEAD(, AddressSpace) address_spaces
    = QTAILQ_HEAD_INITIALIZER(address_spaces);

static void memory_init(void)
{
    qemu_mutex_init(&flat_view_mutex);
}

typedef struct AddrRange AddrRange;

/*
 * Note using signed integers limits us to physical addresses at most
 * 63 bits wide.  They are needed for negative offsetting in aliases
 * (large MemoryRegion::alias_offset).
 */
struct AddrRange {
    Int128 start;
    Int128 size;
};

static AddrRange addrrange_make(Int128 start, Int128 size)
{
    return (AddrRange) { start, size };
}

static bool addrrange_equal(AddrRange r1, AddrRange r2)
{
    return int128_eq(r1.start, r2.start) && int128_eq(r1.size, r2.size);
}

static Int128 addrrange_end(AddrRange r)
{
    return int128_add(r.start, r.size);
}

static AddrRange addrrange_shift(AddrRange range, Int128 delta)
{
    int128_addto(&range.start, delta);
    return range;
}

static bool addrrange_contains(AddrRange range, Int128 addr)
{
    return int128_ge(addr, range.start)
        && int128_lt(addr, addrrange_end(range));
}

static bool addrrange_intersects(AddrRange r1, AddrRange r2)
{
    return addrrange_contains(r1, r2.start)
        || addrrange_contains(r2, r1.start);
}

static AddrRange addrrange_intersection(AddrRange r1, AddrRange r2)
{
    Int128 start = int128_max(r1.start, r2.start);
    Int128 end = int128_min(addrrange_end(r1), addrrange_end(r2));
    return addrrange_make(start, int128_sub(end, start));
}

enum ListenerDirection { Forward, Reverse };

static bool memory_listener_match(MemoryListener *listener,
                                  MemoryRegionSection *section)
{
    return !listener->address_space_filter
        || listener->address_space_filter == section->address_space;
}

#define MEMORY_LISTENER_CALL_GLOBAL(_callback, _direction, _args...)    \
    do {                                                                \
        MemoryListener *_listener;                                      \
                                                                        \
        switch (_direction) {                                           \
        case Forward:                                                   \
            QTAILQ_FOREACH(_listener, &memory_listeners, link) {        \
                if (_listener->_callback) {                             \
                    _listener->_callback(_listener, ##_args);           \
                }                                                       \
            }                                                           \
            break;                                                      \
        case Reverse:                                                   \
            QTAILQ_FOREACH_REVERSE(_listener, &memory_listeners,        \
                                   memory_listeners, link) {            \
                if (_listener->_callback) {                             \
                    _listener->_callback(_listener, ##_args);           \
                }                                                       \
            }                                                           \
            break;                                                      \
        default:                                                        \
            abort();                                                    \
        }                                                               \
    } while (0)

#define MEMORY_LISTENER_CALL(_callback, _direction, _section, _args...) \
    do {                                                                \
        MemoryListener *_listener;                                      \
                                                                        \
        switch (_direction) {                                           \
        case Forward:                                                   \
            QTAILQ_FOREACH(_listener, &memory_listeners, link) {        \
                if (_listener->_callback                                \
                    && memory_listener_match(_listener, _section)) {    \
                    _listener->_callback(_listener, _section, ##_args); \
                }                                                       \
            }                                                           \
            break;                                                      \
        case Reverse:                                                   \
            QTAILQ_FOREACH_REVERSE(_listener, &memory_listeners,        \
                                   memory_listeners, link) {            \
                if (_listener->_callback                                \
                    && memory_listener_match(_listener, _section)) {    \
                    _listener->_callback(_listener, _section, ##_args); \
                }                                                       \
            }                                                           \
            break;                                                      \
        default:                                                        \
            abort();                                                    \
        }                                                               \
    } while (0)

/* No need to ref/unref .mr, the FlatRange keeps it alive.  */
#define MEMORY_LISTENER_UPDATE_REGION(fr, as, dir, callback)            \
    MEMORY_LISTENER_CALL(callback, dir, (&(MemoryRegionSection) {       \
        .mr = (fr)->mr,                                                 \
        .address_space = (as),                                          \
        .offset_within_region = (fr)->offset_in_region,                 \
        .size = (fr)->addr.size,                                        \
        .offset_within_address_space = int128_get64((fr)->addr.start),  \
        .readonly = (fr)->readonly,                                     \
              }))

struct CoalescedMemoryRange {
    AddrRange addr;
    QTAILQ_ENTRY(CoalescedMemoryRange) link;
};

struct MemoryRegionIoeventfd {
    AddrRange addr;
    bool match_data;
    uint64_t data;
    EventNotifier *e;
};

static bool memory_region_ioeventfd_before(MemoryRegionIoeventfd a,
                                           MemoryRegionIoeventfd b)
{
    if (int128_lt(a.addr.start, b.addr.start)) {
        return true;
    } else if (int128_gt(a.addr.start, b.addr.start)) {
        return false;
    } else if (int128_lt(a.addr.size, b.addr.size)) {
        return true;
    } else if (int128_gt(a.addr.size, b.addr.size)) {
        return false;
    } else if (a.match_data < b.match_data) {
        return true;
    } else  if (a.match_data > b.match_data) {
        return false;
    } else if (a.match_data) {
        if (a.data < b.data) {
            return true;
        } else if (a.data > b.data) {
            return false;
        }
    }
    if (a.e < b.e) {
        return true;
    } else if (a.e > b.e) {
        return false;
    }
    return false;
}

static bool memory_region_ioeventfd_equal(MemoryRegionIoeventfd a,
                                          MemoryRegionIoeventfd b)
{
    return !memory_region_ioeventfd_before(a, b)
        && !memory_region_ioeventfd_before(b, a);
}

typedef struct FlatRange FlatRange;
typedef struct FlatView FlatView;

/* Range of memory in the global map.  Addresses are absolute. */
struct FlatRange {
    MemoryRegion *mr;
    hwaddr offset_in_region;
    AddrRange addr;
    uint8_t dirty_log_mask;
    bool romd_mode;
    bool readonly;
};

/* Flattened global view of current active memory hierarchy.  Kept in sorted
 * order.
 */
struct FlatView {
    unsigned ref;
    FlatRange *ranges;
    unsigned nr;
    unsigned nr_allocated;
};

typedef struct AddressSpaceOps AddressSpaceOps;

#define FOR_EACH_FLAT_RANGE(var, view)          \
    for (var = (view)->ranges; var < (view)->ranges + (view)->nr; ++var)

static bool flatrange_equal(FlatRange *a, FlatRange *b)
{
    return a->mr == b->mr
        && addrrange_equal(a->addr, b->addr)
        && a->offset_in_region == b->offset_in_region
        && a->romd_mode == b->romd_mode
        && a->readonly == b->readonly;
}

static void flatview_init(FlatView *view)
{
    view->ref = 1;
    view->ranges = NULL;
    view->nr = 0;
    view->nr_allocated = 0;
}

/* Insert a range into a given position.  Caller is responsible for maintaining
 * sorting order.
 */
static void flatview_insert(FlatView *view, unsigned pos, FlatRange *range)
{
    if (view->nr == view->nr_allocated) {
        view->nr_allocated = MAX(2 * view->nr, 10);
        view->ranges = g_realloc(view->ranges,
                                    view->nr_allocated * sizeof(*view->ranges));
    }
    memmove(view->ranges + pos + 1, view->ranges + pos,
            (view->nr - pos) * sizeof(FlatRange));
    view->ranges[pos] = *range;
    memory_region_ref(range->mr);
    ++view->nr;
}

static void flatview_destroy(FlatView *view)
{
    int i;

    for (i = 0; i < view->nr; i++) {
        memory_region_unref(view->ranges[i].mr);
    }
    g_free(view->ranges);
    g_free(view);
}

static void flatview_ref(FlatView *view)
{
    atomic_inc(&view->ref);
}

static void flatview_unref(FlatView *view)
{
    if (atomic_fetch_dec(&view->ref) == 1) {
        flatview_destroy(view);
    }
}

static bool can_merge(FlatRange *r1, FlatRange *r2)
{
    return int128_eq(addrrange_end(r1->addr), r2->addr.start)
        && r1->mr == r2->mr
        && int128_eq(int128_add(int128_make64(r1->offset_in_region),
                                r1->addr.size),
                     int128_make64(r2->offset_in_region))
        && r1->dirty_log_mask == r2->dirty_log_mask
        && r1->romd_mode == r2->romd_mode
        && r1->readonly == r2->readonly;
}

/* Attempt to simplify a view by merging adjacent ranges */
static void flatview_simplify(FlatView *view)
{
    unsigned i, j;

    i = 0;
    while (i < view->nr) {
        j = i + 1;
        while (j < view->nr
               && can_merge(&view->ranges[j-1], &view->ranges[j])) {
            int128_addto(&view->ranges[i].addr.size, view->ranges[j].addr.size);
            ++j;
        }
        ++i;
        memmove(&view->ranges[i], &view->ranges[j],
                (view->nr - j) * sizeof(view->ranges[j]));
        view->nr -= j - i;
    }
}

static bool memory_region_big_endian(MemoryRegion *mr)
{
#ifdef TARGET_WORDS_BIGENDIAN
    return mr->ops->endianness != DEVICE_LITTLE_ENDIAN;
#else
    return mr->ops->endianness == DEVICE_BIG_ENDIAN;
#endif
}

static bool memory_region_wrong_endianness(MemoryRegion *mr)
{
#ifdef TARGET_WORDS_BIGENDIAN
    return mr->ops->endianness == DEVICE_LITTLE_ENDIAN;
#else
    return mr->ops->endianness == DEVICE_BIG_ENDIAN;
#endif
}

static void adjust_endianness(MemoryRegion *mr, uint64_t *data, unsigned size)
{
    if (memory_region_wrong_endianness(mr)) {
        switch (size) {
        case 1:
            break;
        case 2:
            *data = bswap16(*data);
            break;
        case 4:
            *data = bswap32(*data);
            break;
        case 8:
            *data = bswap64(*data);
            break;
        default:
            abort();
        }
    }
}

static void memory_region_oldmmio_read_accessor(MemoryRegion *mr,
                                                hwaddr addr,
                                                uint64_t *value,
                                                unsigned size,
                                                unsigned shift,
                                                uint64_t mask)
{
    uint64_t tmp;

    tmp = mr->ops->old_mmio.read[ctz32(size)](mr->opaque, addr);
    trace_memory_region_ops_read(mr, addr, tmp, size);
    *value |= (tmp & mask) << shift;
}

static void memory_region_read_accessor(MemoryRegion *mr,
                                        hwaddr addr,
                                        uint64_t *value,
                                        unsigned size,
                                        unsigned shift,
                                        uint64_t mask)
{
    uint64_t tmp;

    if (mr->flush_coalesced_mmio) {
        qemu_flush_coalesced_mmio_buffer();
    }
    tmp = mr->ops->read(mr->opaque, addr, size);
    trace_memory_region_ops_read(mr, addr, tmp, size);
    *value |= (tmp & mask) << shift;
}

static void memory_region_oldmmio_write_accessor(MemoryRegion *mr,
                                                 hwaddr addr,
                                                 uint64_t *value,
                                                 unsigned size,
                                                 unsigned shift,
                                                 uint64_t mask)
{
    uint64_t tmp;

    tmp = (*value >> shift) & mask;
    trace_memory_region_ops_write(mr, addr, tmp, size);
    mr->ops->old_mmio.write[ctz32(size)](mr->opaque, addr, tmp);
}

static void memory_region_write_accessor(MemoryRegion *mr,
                                         hwaddr addr,
                                         uint64_t *value,
                                         unsigned size,
                                         unsigned shift,
                                         uint64_t mask)
{
    uint64_t tmp;

    if (mr->flush_coalesced_mmio) {
        qemu_flush_coalesced_mmio_buffer();
    }
    tmp = (*value >> shift) & mask;
    trace_memory_region_ops_write(mr, addr, tmp, size);
    mr->ops->write(mr->opaque, addr, tmp, size);
}

static void access_with_adjusted_size(hwaddr addr,
                                      uint64_t *value,
                                      unsigned size,
                                      unsigned access_size_min,
                                      unsigned access_size_max,
                                      void (*access)(MemoryRegion *mr,
                                                     hwaddr addr,
                                                     uint64_t *value,
                                                     unsigned size,
                                                     unsigned shift,
                                                     uint64_t mask),
                                      MemoryRegion *mr)
{
    uint64_t access_mask;
    unsigned access_size;
    unsigned i;

    if (!access_size_min) {
        access_size_min = 1;
    }
    if (!access_size_max) {
        access_size_max = 4;
    }

    /* FIXME: support unaligned access? */
    access_size = MAX(MIN(size, access_size_max), access_size_min);
    access_mask = -1ULL >> (64 - access_size * 8);
    if (memory_region_big_endian(mr)) {
        for (i = 0; i < size; i += access_size) {
            access(mr, addr + i, value, access_size,
                   (size - access_size - i) * 8, access_mask);
        }
    } else {
        for (i = 0; i < size; i += access_size) {
            access(mr, addr + i, value, access_size, i * 8, access_mask);
        }
    }
}

static AddressSpace *memory_region_to_address_space(MemoryRegion *mr)
{
    AddressSpace *as;

    while (mr->parent) {
        mr = mr->parent;
    }
    QTAILQ_FOREACH(as, &address_spaces, address_spaces_link) {
        if (mr == as->root) {
            return as;
        }
    }
    abort();
}

/* Render a memory region into the global view.  Ranges in @view obscure
 * ranges in @mr.
 */
static void render_memory_region(FlatView *view,
                                 MemoryRegion *mr,
                                 Int128 base,
                                 AddrRange clip,
                                 bool readonly)
{
    MemoryRegion *subregion;
    unsigned i;
    hwaddr offset_in_region;
    Int128 remain;
    Int128 now;
    FlatRange fr;
    AddrRange tmp;

    if (!mr->enabled) {
        return;
    }

    int128_addto(&base, int128_make64(mr->addr));
    readonly |= mr->readonly;

    tmp = addrrange_make(base, mr->size);

    if (!addrrange_intersects(tmp, clip)) {
        return;
    }

    clip = addrrange_intersection(tmp, clip);

    if (mr->alias) {
        int128_subfrom(&base, int128_make64(mr->alias->addr));
        int128_subfrom(&base, int128_make64(mr->alias_offset));
        render_memory_region(view, mr->alias, base, clip, readonly);
        return;
    }

    /* Render subregions in priority order. */
    QTAILQ_FOREACH(subregion, &mr->subregions, subregions_link) {
        render_memory_region(view, subregion, base, clip, readonly);
    }

    if (!mr->terminates) {
        return;
    }

    offset_in_region = int128_get64(int128_sub(clip.start, base));
    base = clip.start;
    remain = clip.size;

    fr.mr = mr;
    fr.dirty_log_mask = mr->dirty_log_mask;
    fr.romd_mode = mr->romd_mode;
    fr.readonly = readonly;

    /* Render the region itself into any gaps left by the current view. */
    for (i = 0; i < view->nr && int128_nz(remain); ++i) {
        if (int128_ge(base, addrrange_end(view->ranges[i].addr))) {
            continue;
        }
        if (int128_lt(base, view->ranges[i].addr.start)) {
            now = int128_min(remain,
                             int128_sub(view->ranges[i].addr.start, base));
            fr.offset_in_region = offset_in_region;
            fr.addr = addrrange_make(base, now);
            flatview_insert(view, i, &fr);
            ++i;
            int128_addto(&base, now);
            offset_in_region += int128_get64(now);
            int128_subfrom(&remain, now);
        }
        now = int128_sub(int128_min(int128_add(base, remain),
                                    addrrange_end(view->ranges[i].addr)),
                         base);
        int128_addto(&base, now);
        offset_in_region += int128_get64(now);
        int128_subfrom(&remain, now);
    }
    if (int128_nz(remain)) {
        fr.offset_in_region = offset_in_region;
        fr.addr = addrrange_make(base, remain);
        flatview_insert(view, i, &fr);
    }
}

/* Render a memory topology into a list of disjoint absolute ranges. */
static FlatView *generate_memory_topology(MemoryRegion *mr)
{
    FlatView *view;

    view = g_new(FlatView, 1);
    flatview_init(view);

    if (mr) {
        render_memory_region(view, mr, int128_zero(),
                             addrrange_make(int128_zero(), int128_2_64()), false);
    }
    flatview_simplify(view);

    return view;
}

static void address_space_add_del_ioeventfds(AddressSpace *as,
                                             MemoryRegionIoeventfd *fds_new,
                                             unsigned fds_new_nb,
                                             MemoryRegionIoeventfd *fds_old,
                                             unsigned fds_old_nb)
{
    unsigned iold, inew;
    MemoryRegionIoeventfd *fd;
    MemoryRegionSection section;

    /* Generate a symmetric difference of the old and new fd sets, adding
     * and deleting as necessary.
     */

    iold = inew = 0;
    while (iold < fds_old_nb || inew < fds_new_nb) {
        if (iold < fds_old_nb
            && (inew == fds_new_nb
                || memory_region_ioeventfd_before(fds_old[iold],
                                                  fds_new[inew]))) {
            fd = &fds_old[iold];
            section = (MemoryRegionSection) {
                .address_space = as,
                .offset_within_address_space = int128_get64(fd->addr.start),
                .size = fd->addr.size,
            };
            MEMORY_LISTENER_CALL(eventfd_del, Forward, &section,
                                 fd->match_data, fd->data, fd->e);
            ++iold;
        } else if (inew < fds_new_nb
                   && (iold == fds_old_nb
                       || memory_region_ioeventfd_before(fds_new[inew],
                                                         fds_old[iold]))) {
            fd = &fds_new[inew];
            section = (MemoryRegionSection) {
                .address_space = as,
                .offset_within_address_space = int128_get64(fd->addr.start),
                .size = fd->addr.size,
            };
            MEMORY_LISTENER_CALL(eventfd_add, Reverse, &section,
                                 fd->match_data, fd->data, fd->e);
            ++inew;
        } else {
            ++iold;
            ++inew;
        }
    }
}

static FlatView *address_space_get_flatview(AddressSpace *as)
{
    FlatView *view;

    qemu_mutex_lock(&flat_view_mutex);
    view = as->current_map;
    flatview_ref(view);
    qemu_mutex_unlock(&flat_view_mutex);
    return view;
}

static void address_space_update_ioeventfds(AddressSpace *as)
{
    FlatView *view;
    FlatRange *fr;
    unsigned ioeventfd_nb = 0;
    MemoryRegionIoeventfd *ioeventfds = NULL;
    AddrRange tmp;
    unsigned i;

    view = address_space_get_flatview(as);
    FOR_EACH_FLAT_RANGE(fr, view) {
        for (i = 0; i < fr->mr->ioeventfd_nb; ++i) {
            tmp = addrrange_shift(fr->mr->ioeventfds[i].addr,
                                  int128_sub(fr->addr.start,
                                             int128_make64(fr->offset_in_region)));
            if (addrrange_intersects(fr->addr, tmp)) {
                ++ioeventfd_nb;
                ioeventfds = g_realloc(ioeventfds,
                                          ioeventfd_nb * sizeof(*ioeventfds));
                ioeventfds[ioeventfd_nb-1] = fr->mr->ioeventfds[i];
                ioeventfds[ioeventfd_nb-1].addr = tmp;
            }
        }
    }

    address_space_add_del_ioeventfds(as, ioeventfds, ioeventfd_nb,
                                     as->ioeventfds, as->ioeventfd_nb);

    g_free(as->ioeventfds);
    as->ioeventfds = ioeventfds;
    as->ioeventfd_nb = ioeventfd_nb;
    flatview_unref(view);
}

static void address_space_update_topology_pass(AddressSpace *as,
                                               const FlatView *old_view,
                                               const FlatView *new_view,
                                               bool adding)
{
    unsigned iold, inew;
    FlatRange *frold, *frnew;

    /* Generate a symmetric difference of the old and new memory maps.
     * Kill ranges in the old map, and instantiate ranges in the new map.
     */
    iold = inew = 0;
    while (iold < old_view->nr || inew < new_view->nr) {
        if (iold < old_view->nr) {
            frold = &old_view->ranges[iold];
        } else {
            frold = NULL;
        }
        if (inew < new_view->nr) {
            frnew = &new_view->ranges[inew];
        } else {
            frnew = NULL;
        }

        if (frold
            && (!frnew
                || int128_lt(frold->addr.start, frnew->addr.start)
                || (int128_eq(frold->addr.start, frnew->addr.start)
                    && !flatrange_equal(frold, frnew)))) {
            /* In old but not in new, or in both but attributes changed. */

            if (!adding) {
                MEMORY_LISTENER_UPDATE_REGION(frold, as, Reverse, region_del);
            }

            ++iold;
        } else if (frold && frnew && flatrange_equal(frold, frnew)) {
            /* In both and unchanged (except logging may have changed) */

            if (adding) {
                MEMORY_LISTENER_UPDATE_REGION(frnew, as, Forward, region_nop);
                if (frold->dirty_log_mask && !frnew->dirty_log_mask) {
                    MEMORY_LISTENER_UPDATE_REGION(frnew, as, Reverse, log_stop);
                } else if (frnew->dirty_log_mask && !frold->dirty_log_mask) {
                    MEMORY_LISTENER_UPDATE_REGION(frnew, as, Forward, log_start);
                }
            }

            ++iold;
            ++inew;
        } else {
            /* In new */

            if (adding) {
                MEMORY_LISTENER_UPDATE_REGION(frnew, as, Forward, region_add);
            }

            ++inew;
        }
    }
}


static void address_space_update_topology(AddressSpace *as)
{
    FlatView *old_view = address_space_get_flatview(as);
    FlatView *new_view = generate_memory_topology(as->root);

    address_space_update_topology_pass(as, old_view, new_view, false);
    address_space_update_topology_pass(as, old_view, new_view, true);

    qemu_mutex_lock(&flat_view_mutex);
    flatview_unref(as->current_map);
    as->current_map = new_view;
    qemu_mutex_unlock(&flat_view_mutex);

    /* Note that all the old MemoryRegions are still alive up to this
     * point.  This relieves most MemoryListeners from the need to
     * ref/unref the MemoryRegions they get---unless they use them
     * outside the iothread mutex, in which case precise reference
     * counting is necessary.
     */
    flatview_unref(old_view);

    address_space_update_ioeventfds(as);
}

void memory_region_transaction_begin(void)
{
    qemu_flush_coalesced_mmio_buffer();
    ++memory_region_transaction_depth;
}

void memory_region_transaction_commit(void)
{
    AddressSpace *as;

    assert(memory_region_transaction_depth);
    --memory_region_transaction_depth;
    if (!memory_region_transaction_depth && memory_region_update_pending) {
        memory_region_update_pending = false;
        MEMORY_LISTENER_CALL_GLOBAL(begin, Forward);

        QTAILQ_FOREACH(as, &address_spaces, address_spaces_link) {
            address_space_update_topology(as);
        }

        MEMORY_LISTENER_CALL_GLOBAL(commit, Forward);
    }
}

static void memory_region_destructor_none(MemoryRegion *mr)
{
}

static void memory_region_destructor_ram(MemoryRegion *mr)
{
    qemu_ram_free(mr->ram_addr);
}

static void memory_region_destructor_alias(MemoryRegion *mr)
{
    memory_region_unref(mr->alias);
}

static void memory_region_destructor_ram_from_ptr(MemoryRegion *mr)
{
    qemu_ram_free_from_ptr(mr->ram_addr);
}

static void memory_region_destructor_rom_device(MemoryRegion *mr)
{
    qemu_ram_free(mr->ram_addr & TARGET_PAGE_MASK);
}

void memory_region_init(MemoryRegion *mr,
                        Object *owner,
                        const char *name,
                        uint64_t size)
{
    mr->ops = &unassigned_mem_ops;
    mr->opaque = NULL;
    mr->owner = owner;
    mr->iommu_ops = NULL;
    mr->parent = NULL;
    mr->size = int128_make64(size);
    if (size == UINT64_MAX) {
        mr->size = int128_2_64();
    }
    mr->addr = 0;
    mr->subpage = false;
    mr->enabled = true;
    mr->terminates = false;
    mr->ram = false;
    mr->romd_mode = true;
    mr->readonly = false;
    mr->rom_device = false;
    mr->destructor = memory_region_destructor_none;
    mr->priority = 0;
    mr->may_overlap = false;
    mr->alias = NULL;
    QTAILQ_INIT(&mr->subregions);
    memset(&mr->subregions_link, 0, sizeof mr->subregions_link);
    QTAILQ_INIT(&mr->coalesced);
    mr->name = g_strdup(name);
    mr->dirty_log_mask = 0;
    mr->ioeventfd_nb = 0;
    mr->ioeventfds = NULL;
    mr->flush_coalesced_mmio = false;
}

static uint64_t unassigned_mem_read(void *opaque, hwaddr addr,
                                    unsigned size)
{
#ifdef DEBUG_UNASSIGNED
    printf("Unassigned mem read " TARGET_FMT_plx "\n", addr);
#endif
    if (current_cpu != NULL) {
        cpu_unassigned_access(current_cpu, addr, false, false, 0, size);
    }
    return -1ULL;
}

static void unassigned_mem_write(void *opaque, hwaddr addr,
                                 uint64_t val, unsigned size)
{
#ifdef DEBUG_UNASSIGNED
    printf("Unassigned mem write " TARGET_FMT_plx " = 0x%"PRIx64"\n", addr, val);
#endif
    if (current_cpu != NULL) {
        cpu_unassigned_access(current_cpu, addr, true, false, 0, size);
    }
}

static bool unassigned_mem_accepts(void *opaque, hwaddr addr,
                                   unsigned size, bool is_write)
{
    return false;
}

const MemoryRegionOps unassigned_mem_ops = {
    .valid.accepts = unassigned_mem_accepts,
    .endianness = DEVICE_NATIVE_ENDIAN,
};

bool memory_region_access_valid(MemoryRegion *mr,
                                hwaddr addr,
                                unsigned size,
                                bool is_write)
{
    int access_size_min, access_size_max;
    int access_size, i;

    if (!mr->ops->valid.unaligned && (addr & (size - 1))) {
        return false;
    }

    if (!mr->ops->valid.accepts) {
        return true;
    }

    access_size_min = mr->ops->valid.min_access_size;
    if (!mr->ops->valid.min_access_size) {
        access_size_min = 1;
    }

    access_size_max = mr->ops->valid.max_access_size;
    if (!mr->ops->valid.max_access_size) {
        access_size_max = 4;
    }

    access_size = MAX(MIN(size, access_size_max), access_size_min);
    for (i = 0; i < size; i += access_size) {
        if (!mr->ops->valid.accepts(mr->opaque, addr + i, access_size,
                                    is_write)) {
            return false;
        }
    }

    return true;
}

static uint64_t memory_region_dispatch_read1(MemoryRegion *mr,
                                             hwaddr addr,
                                             unsigned size)
{
    uint64_t data = 0;

    if (mr->ops->read) {
        access_with_adjusted_size(addr, &data, size,
                                  mr->ops->impl.min_access_size,
                                  mr->ops->impl.max_access_size,
                                  memory_region_read_accessor, mr);
    } else {
        access_with_adjusted_size(addr, &data, size, 1, 4,
                                  memory_region_oldmmio_read_accessor, mr);
    }

    return data;
}

static bool memory_region_dispatch_read(MemoryRegion *mr,
                                        hwaddr addr,
                                        uint64_t *pval,
                                        unsigned size)
{
    if (!memory_region_access_valid(mr, addr, size, false)) {
        *pval = unassigned_mem_read(mr, addr, size);
        return true;
    }

    *pval = memory_region_dispatch_read1(mr, addr, size);
    adjust_endianness(mr, pval, size);
    return false;
}

static bool memory_region_dispatch_write(MemoryRegion *mr,
                                         hwaddr addr,
                                         uint64_t data,
                                         unsigned size)
{
    if (!memory_region_access_valid(mr, addr, size, true)) {
        unassigned_mem_write(mr, addr, data, size);
        return true;
    }

    adjust_endianness(mr, &data, size);

    if (mr->ops->write) {
        access_with_adjusted_size(addr, &data, size,
                                  mr->ops->impl.min_access_size,
                                  mr->ops->impl.max_access_size,
                                  memory_region_write_accessor, mr);
    } else {
        access_with_adjusted_size(addr, &data, size, 1, 4,
                                  memory_region_oldmmio_write_accessor, mr);
    }
    return false;
}

void memory_region_init_io(MemoryRegion *mr,
                           Object *owner,
                           const MemoryRegionOps *ops,
                           void *opaque,
                           const char *name,
                           uint64_t size)
{
    memory_region_init(mr, owner, name, size);
    mr->ops = ops;
    mr->opaque = opaque;
    mr->terminates = true;
    mr->ram_addr = ~(ram_addr_t)0;
}

void memory_region_init_ram(MemoryRegion *mr,
                            Object *owner,
                            const char *name,
                            uint64_t size)
{
    memory_region_init(mr, owner, name, size);
    mr->ram = true;
    mr->terminates = true;
    mr->destructor = memory_region_destructor_ram;
    mr->ram_addr = qemu_ram_alloc(size, mr);
}

void memory_region_init_ram_ptr(MemoryRegion *mr,
                                Object *owner,
                                const char *name,
                                uint64_t size,
                                void *ptr)
{
    memory_region_init(mr, owner, name, size);
    mr->ram = true;
    mr->terminates = true;
    mr->destructor = memory_region_destructor_ram_from_ptr;
    mr->ram_addr = qemu_ram_alloc_from_ptr(size, ptr, mr);
}

void memory_region_init_alias(MemoryRegion *mr,
                              Object *owner,
                              const char *name,
                              MemoryRegion *orig,
                              hwaddr offset,
                              uint64_t size)
{
    memory_region_init(mr, owner, name, size);
    memory_region_ref(orig);
    mr->destructor = memory_region_destructor_alias;
    mr->alias = orig;
    mr->alias_offset = offset;
}

void memory_region_init_rom_device(MemoryRegion *mr,
                                   Object *owner,
                                   const MemoryRegionOps *ops,
                                   void *opaque,
                                   const char *name,
                                   uint64_t size)
{
    memory_region_init(mr, owner, name, size);
    mr->ops = ops;
    mr->opaque = opaque;
    mr->terminates = true;
    mr->rom_device = true;
    mr->destructor = memory_region_destructor_rom_device;
    mr->ram_addr = qemu_ram_alloc(size, mr);
}

void memory_region_init_iommu(MemoryRegion *mr,
                              Object *owner,
                              const MemoryRegionIOMMUOps *ops,
                              const char *name,
                              uint64_t size)
{
    memory_region_init(mr, owner, name, size);
    mr->iommu_ops = ops,
    mr->terminates = true;  /* then re-forwards */
    notifier_list_init(&mr->iommu_notify);
}

void memory_region_init_reservation(MemoryRegion *mr,
                                    Object *owner,
                                    const char *name,
                                    uint64_t size)
{
    memory_region_init_io(mr, owner, &unassigned_mem_ops, mr, name, size);
}

void memory_region_destroy(MemoryRegion *mr)
{
    assert(QTAILQ_EMPTY(&mr->subregions));
    assert(memory_region_transaction_depth == 0);
    mr->destructor(mr);
    memory_region_clear_coalescing(mr);
    g_free((char *)mr->name);
    g_free(mr->ioeventfds);
}

Object *memory_region_owner(MemoryRegion *mr)
{
    return mr->owner;
}

void memory_region_ref(MemoryRegion *mr)
{
    if (mr && mr->owner) {
        object_ref(mr->owner);
    }
}

void memory_region_unref(MemoryRegion *mr)
{
    if (mr && mr->owner) {
        object_unref(mr->owner);
    }
}

uint64_t memory_region_size(MemoryRegion *mr)
{
    if (int128_eq(mr->size, int128_2_64())) {
        return UINT64_MAX;
    }
    return int128_get64(mr->size);
}

const char *memory_region_name(MemoryRegion *mr)
{
    return mr->name;
}

bool memory_region_is_ram(MemoryRegion *mr)
{
    return mr->ram;
}

bool memory_region_is_logging(MemoryRegion *mr)
{
    return mr->dirty_log_mask;
}

bool memory_region_is_rom(MemoryRegion *mr)
{
    return mr->ram && mr->readonly;
}

bool memory_region_is_iommu(MemoryRegion *mr)
{
    return mr->iommu_ops;
}

void memory_region_register_iommu_notifier(MemoryRegion *mr, Notifier *n)
{
    notifier_list_add(&mr->iommu_notify, n);
}

void memory_region_unregister_iommu_notifier(Notifier *n)
{
    notifier_remove(n);
}

void memory_region_notify_iommu(MemoryRegion *mr,
                                IOMMUTLBEntry entry)
{
    assert(memory_region_is_iommu(mr));
    notifier_list_notify(&mr->iommu_notify, &entry);
}

void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client)
{
    uint8_t mask = 1 << client;

    memory_region_transaction_begin();
    mr->dirty_log_mask = (mr->dirty_log_mask & ~mask) | (log * mask);
    memory_region_update_pending |= mr->enabled;
    memory_region_transaction_commit();
}

bool memory_region_get_dirty(MemoryRegion *mr, hwaddr addr,
                             hwaddr size, unsigned client)
{
    assert(mr->terminates);
    return cpu_physical_memory_get_dirty(mr->ram_addr + addr, size,
                                         1 << client);
}

void memory_region_set_dirty(MemoryRegion *mr, hwaddr addr,
                             hwaddr size)
{
    assert(mr->terminates);
    return cpu_physical_memory_set_dirty_range(mr->ram_addr + addr, size, -1);
}

bool memory_region_test_and_clear_dirty(MemoryRegion *mr, hwaddr addr,
                                        hwaddr size, unsigned client)
{
    bool ret;
    assert(mr->terminates);
    ret = cpu_physical_memory_get_dirty(mr->ram_addr + addr, size,
                                        1 << client);
    if (ret) {
        cpu_physical_memory_reset_dirty(mr->ram_addr + addr,
                                        mr->ram_addr + addr + size,
                                        1 << client);
    }
    return ret;
}


void memory_region_sync_dirty_bitmap(MemoryRegion *mr)
{
    AddressSpace *as;
    FlatRange *fr;

    QTAILQ_FOREACH(as, &address_spaces, address_spaces_link) {
        FlatView *view = address_space_get_flatview(as);
        FOR_EACH_FLAT_RANGE(fr, view) {
            if (fr->mr == mr) {
                MEMORY_LISTENER_UPDATE_REGION(fr, as, Forward, log_sync);
            }
        }
        flatview_unref(view);
    }
}

void memory_region_set_readonly(MemoryRegion *mr, bool readonly)
{
    if (mr->readonly != readonly) {
        memory_region_transaction_begin();
        mr->readonly = readonly;
        memory_region_update_pending |= mr->enabled;
        memory_region_transaction_commit();
    }
}

void memory_region_rom_device_set_romd(MemoryRegion *mr, bool romd_mode)
{
    if (mr->romd_mode != romd_mode) {
        memory_region_transaction_begin();
        mr->romd_mode = romd_mode;
        memory_region_update_pending |= mr->enabled;
        memory_region_transaction_commit();
    }
}

void memory_region_reset_dirty(MemoryRegion *mr, hwaddr addr,
                               hwaddr size, unsigned client)
{
    assert(mr->terminates);
    cpu_physical_memory_reset_dirty(mr->ram_addr + addr,
                                    mr->ram_addr + addr + size,
                                    1 << client);
}

void *memory_region_get_ram_ptr(MemoryRegion *mr)
{
    if (mr->alias) {
        return memory_region_get_ram_ptr(mr->alias) + mr->alias_offset;
    }

    assert(mr->terminates);

    return qemu_get_ram_ptr(mr->ram_addr & TARGET_PAGE_MASK);
}

static void memory_region_update_coalesced_range_as(MemoryRegion *mr, AddressSpace *as)
{
    FlatView *view;
    FlatRange *fr;
    CoalescedMemoryRange *cmr;
    AddrRange tmp;
    MemoryRegionSection section;

    view = address_space_get_flatview(as);
    FOR_EACH_FLAT_RANGE(fr, view) {
        if (fr->mr == mr) {
            section = (MemoryRegionSection) {
                .address_space = as,
                .offset_within_address_space = int128_get64(fr->addr.start),
                .size = fr->addr.size,
            };

            MEMORY_LISTENER_CALL(coalesced_mmio_del, Reverse, &section,
                                 int128_get64(fr->addr.start),
                                 int128_get64(fr->addr.size));
            QTAILQ_FOREACH(cmr, &mr->coalesced, link) {
                tmp = addrrange_shift(cmr->addr,
                                      int128_sub(fr->addr.start,
                                                 int128_make64(fr->offset_in_region)));
                if (!addrrange_intersects(tmp, fr->addr)) {
                    continue;
                }
                tmp = addrrange_intersection(tmp, fr->addr);
                MEMORY_LISTENER_CALL(coalesced_mmio_add, Forward, &section,
                                     int128_get64(tmp.start),
                                     int128_get64(tmp.size));
            }
        }
    }
    flatview_unref(view);
}

static void memory_region_update_coalesced_range(MemoryRegion *mr)
{
    AddressSpace *as;

    QTAILQ_FOREACH(as, &address_spaces, address_spaces_link) {
        memory_region_update_coalesced_range_as(mr, as);
    }
}

void memory_region_set_coalescing(MemoryRegion *mr)
{
    memory_region_clear_coalescing(mr);
    memory_region_add_coalescing(mr, 0, int128_get64(mr->size));
}

void memory_region_add_coalescing(MemoryRegion *mr,
                                  hwaddr offset,
                                  uint64_t size)
{