Archipelago » qemu

/*

 *  Virtual page mapping

 *

 *  Copyright (c) 2003 Fabrice Bellard

 *

 * This library is free software; you can redistribute it and/or

 * modify it under the terms of the GNU Lesser General Public

 * License as published by the Free Software Foundation; either

 * version 2 of the License, or (at your option) any later version.

 *

 * This library is distributed in the hope that it will be useful,

 * but WITHOUT ANY WARRANTY; without even the implied warranty of

 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU

 * Lesser General Public License for more details.

 *

 * You should have received a copy of the GNU Lesser General Public

 * License along with this library; if not, see <http://www.gnu.org/licenses/>.

 */

#include "config.h"

#ifdef _WIN32

#include <windows.h>

#else

#include <sys/types.h>

#include <sys/mman.h>

#endif

#include "qemu-common.h"

#include "cpu.h"

#include "tcg.h"

#include "hw/hw.h"

#include "hw/qdev.h"

#include "qemu/osdep.h"

#include "sysemu/kvm.h"

#include "hw/xen.h"

#include "qemu/timer.h"

#include "qemu/config-file.h"

#include "exec/memory.h"

#include "sysemu/dma.h"

#include "exec/address-spaces.h"

#if defined(CONFIG_USER_ONLY)

#include <qemu.h>

#else /* !CONFIG_USER_ONLY */

#include "sysemu/xen-mapcache.h"

#include "trace.h"

#endif

#include "exec/cpu-all.h"

#include "exec/cputlb.h"

#include "translate-all.h"

#include "exec/memory-internal.h"

//#define DEBUG_UNASSIGNED

//#define DEBUG_SUBPAGE

#if !defined(CONFIG_USER_ONLY)

int phys_ram_fd;

static int in_migration;

RAMList ram_list = { .blocks = QTAILQ_HEAD_INITIALIZER(ram_list.blocks) };

static MemoryRegion *system_memory;

static MemoryRegion *system_io;

AddressSpace address_space_io;

AddressSpace address_space_memory;

DMAContext dma_context_memory;

MemoryRegion io_mem_ram, io_mem_rom, io_mem_unassigned, io_mem_notdirty;

static MemoryRegion io_mem_subpage_ram;

#endif

CPUArchState *first_cpu;

/* current CPU in the current thread. It is only valid inside

   cpu_exec() */

DEFINE_TLS(CPUArchState *,cpu_single_env);

/* 0 = Do not count executed instructions.

   1 = Precise instruction counting.

   2 = Adaptive rate instruction counting.  */

int use_icount;

#if !defined(CONFIG_USER_ONLY)

static MemoryRegionSection *phys_sections;

static unsigned phys_sections_nb, phys_sections_nb_alloc;

static uint16_t phys_section_unassigned;

static uint16_t phys_section_notdirty;

static uint16_t phys_section_rom;

static uint16_t phys_section_watch;

/* Simple allocator for PhysPageEntry nodes */

static PhysPageEntry (*phys_map_nodes)[L2_SIZE];

static unsigned phys_map_nodes_nb, phys_map_nodes_nb_alloc;

#define PHYS_MAP_NODE_NIL (((uint16_t)~0) >> 1)

static void io_mem_init(void);

static void memory_map_init(void);

static void *qemu_safe_ram_ptr(ram_addr_t addr);

static MemoryRegion io_mem_watch;

#endif

#if !defined(CONFIG_USER_ONLY)

static void phys_map_node_reserve(unsigned nodes)

{

    if (phys_map_nodes_nb + nodes > phys_map_nodes_nb_alloc) {

        typedef PhysPageEntry Node[L2_SIZE];

        phys_map_nodes_nb_alloc = MAX(phys_map_nodes_nb_alloc * 2, 16);

        phys_map_nodes_nb_alloc = MAX(phys_map_nodes_nb_alloc,

                                      phys_map_nodes_nb + nodes);

        phys_map_nodes = g_renew(Node, phys_map_nodes,

                                 phys_map_nodes_nb_alloc);

    }

}

static uint16_t phys_map_node_alloc(void)

{

    unsigned i;

    uint16_t ret;

    ret = phys_map_nodes_nb++;

    assert(ret != PHYS_MAP_NODE_NIL);

    assert(ret != phys_map_nodes_nb_alloc);

    for (i = 0; i < L2_SIZE; ++i) {

        phys_map_nodes[ret][i].is_leaf = 0;

        phys_map_nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;

    }

    return ret;

}

static void phys_map_nodes_reset(void)

{

    phys_map_nodes_nb = 0;

}

static void phys_page_set_level(PhysPageEntry *lp, hwaddr *index,

                                hwaddr *nb, uint16_t leaf,

                                int level)

{

    PhysPageEntry *p;

    int i;

    hwaddr step = (hwaddr)1 << (level * L2_BITS);

    if (!lp->is_leaf && lp->ptr == PHYS_MAP_NODE_NIL) {

        lp->ptr = phys_map_node_alloc();

        p = phys_map_nodes[lp->ptr];

        if (level == 0) {

            for (i = 0; i < L2_SIZE; i++) {

                p[i].is_leaf = 1;

                p[i].ptr = phys_section_unassigned;

            }

        }

    } else {

        p = phys_map_nodes[lp->ptr];

    }

    lp = &p[(*index >> (level * L2_BITS)) & (L2_SIZE - 1)];

    while (*nb && lp < &p[L2_SIZE]) {

        if ((*index & (step - 1)) == 0 && *nb >= step) {

            lp->is_leaf = true;

            lp->ptr = leaf;

            *index += step;

            *nb -= step;

        } else {

            phys_page_set_level(lp, index, nb, leaf, level - 1);

        }

        ++lp;

    }

}

static void phys_page_set(AddressSpaceDispatch *d,

                          hwaddr index, hwaddr nb,

                          uint16_t leaf)

{

    /* Wildly overreserve - it doesn't matter much. */

    phys_map_node_reserve(3 * P_L2_LEVELS);

    phys_page_set_level(&d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);

}

MemoryRegionSection *phys_page_find(AddressSpaceDispatch *d, hwaddr index)

{

    PhysPageEntry lp = d->phys_map;

    PhysPageEntry *p;

    int i;

    uint16_t s_index = phys_section_unassigned;

    for (i = P_L2_LEVELS - 1; i >= 0 && !lp.is_leaf; i--) {

        if (lp.ptr == PHYS_MAP_NODE_NIL) {

            goto not_found;

        }

        p = phys_map_nodes[lp.ptr];

        lp = p[(index >> (i * L2_BITS)) & (L2_SIZE - 1)];

    }

    s_index = lp.ptr;

not_found:

    return &phys_sections[s_index];

}

bool memory_region_is_unassigned(MemoryRegion *mr)

{

    return mr != &io_mem_ram && mr != &io_mem_rom

        && mr != &io_mem_notdirty && !mr->rom_device

        && mr != &io_mem_watch;

}

#endif

void cpu_exec_init_all(void)

{

#if !defined(CONFIG_USER_ONLY)

    qemu_mutex_init(&ram_list.mutex);

    memory_map_init();

    io_mem_init();

#endif

}

#if !defined(CONFIG_USER_ONLY)

static int cpu_common_post_load(void *opaque, int version_id)

{

    CPUState *cpu = opaque;

    /* 0x01 was CPU_INTERRUPT_EXIT. This line can be removed when the

       version_id is increased. */

    cpu->interrupt_request &= ~0x01;

    tlb_flush(cpu->env_ptr, 1);

    return 0;

}

static const VMStateDescription vmstate_cpu_common = {

    .name = "cpu_common",

    .version_id = 1,

    .minimum_version_id = 1,

    .minimum_version_id_old = 1,

    .post_load = cpu_common_post_load,

    .fields      = (VMStateField []) {

        VMSTATE_UINT32(halted, CPUState),

        VMSTATE_UINT32(interrupt_request, CPUState),

        VMSTATE_END_OF_LIST()

    }

};

#else

#define vmstate_cpu_common vmstate_dummy

#endif

CPUState *qemu_get_cpu(int index)

{

    CPUArchState *env = first_cpu;

    CPUState *cpu = NULL;

    while (env) {

        cpu = ENV_GET_CPU(env);

        if (cpu->cpu_index == index) {

            break;

        }

        env = env->next_cpu;

    }

    return env ? cpu : NULL;

}

void cpu_exec_init(CPUArchState *env)

{

    CPUState *cpu = ENV_GET_CPU(env);

    CPUClass *cc = CPU_GET_CLASS(cpu);

    CPUArchState **penv;

    int cpu_index;

#if defined(CONFIG_USER_ONLY)

    cpu_list_lock();

#endif

    env->next_cpu = NULL;

    penv = &first_cpu;

    cpu_index = 0;

    while (*penv != NULL) {

        penv = &(*penv)->next_cpu;

        cpu_index++;

    }

    cpu->cpu_index = cpu_index;

    cpu->numa_node = 0;

    QTAILQ_INIT(&env->breakpoints);

    QTAILQ_INIT(&env->watchpoints);

#ifndef CONFIG_USER_ONLY

    cpu->thread_id = qemu_get_thread_id();

#endif

    *penv = env;

#if defined(CONFIG_USER_ONLY)

    cpu_list_unlock();

#endif

    vmstate_register(NULL, cpu_index, &vmstate_cpu_common, cpu);

#if defined(CPU_SAVE_VERSION) && !defined(CONFIG_USER_ONLY)

    register_savevm(NULL, "cpu", cpu_index, CPU_SAVE_VERSION,

                    cpu_save, cpu_load, env);

    assert(cc->vmsd == NULL);

#endif

    if (cc->vmsd != NULL) {

        vmstate_register(NULL, cpu_index, cc->vmsd, cpu);

    }

}

#if defined(TARGET_HAS_ICE)

#if defined(CONFIG_USER_ONLY)

static void breakpoint_invalidate(CPUArchState *env, target_ulong pc)

{

    tb_invalidate_phys_page_range(pc, pc + 1, 0);

}

#else

static void breakpoint_invalidate(CPUArchState *env, target_ulong pc)

{

    tb_invalidate_phys_addr(cpu_get_phys_page_debug(env, pc) |

            (pc & ~TARGET_PAGE_MASK));

}

#endif

#endif /* TARGET_HAS_ICE */

#if defined(CONFIG_USER_ONLY)

void cpu_watchpoint_remove_all(CPUArchState *env, int mask)

{

}

int cpu_watchpoint_insert(CPUArchState *env, target_ulong addr, target_ulong len,

                          int flags, CPUWatchpoint **watchpoint)

{

    return -ENOSYS;

}

#else

/* Add a watchpoint.  */

int cpu_watchpoint_insert(CPUArchState *env, target_ulong addr, target_ulong len,

                          int flags, CPUWatchpoint **watchpoint)

{

    target_ulong len_mask = ~(len - 1);

    CPUWatchpoint *wp;

    /* sanity checks: allow power-of-2 lengths, deny unaligned watchpoints */

    if ((len & (len - 1)) || (addr & ~len_mask) ||

            len == 0 || len > TARGET_PAGE_SIZE) {

        fprintf(stderr, "qemu: tried to set invalid watchpoint at "

                TARGET_FMT_lx ", len=" TARGET_FMT_lu "\n", addr, len);

        return -EINVAL;

    }

    wp = g_malloc(sizeof(*wp));

    wp->vaddr = addr;

    wp->len_mask = len_mask;

    wp->flags = flags;

    /* keep all GDB-injected watchpoints in front */

    if (flags & BP_GDB)

        QTAILQ_INSERT_HEAD(&env->watchpoints, wp, entry);

    else

        QTAILQ_INSERT_TAIL(&env->watchpoints, wp, entry);

    tlb_flush_page(env, addr);

    if (watchpoint)

        *watchpoint = wp;

    return 0;

}

/* Remove a specific watchpoint.  */

int cpu_watchpoint_remove(CPUArchState *env, target_ulong addr, target_ulong len,

                          int flags)

{

    target_ulong len_mask = ~(len - 1);

    CPUWatchpoint *wp;

    QTAILQ_FOREACH(wp, &env->watchpoints, entry) {

        if (addr == wp->vaddr && len_mask == wp->len_mask

                && flags == (wp->flags & ~BP_WATCHPOINT_HIT)) {

            cpu_watchpoint_remove_by_ref(env, wp);

            return 0;

        }

    }

    return -ENOENT;

}

/* Remove a specific watchpoint by reference.  */

void cpu_watchpoint_remove_by_ref(CPUArchState *env, CPUWatchpoint *watchpoint)

{

    QTAILQ_REMOVE(&env->watchpoints, watchpoint, entry);

    tlb_flush_page(env, watchpoint->vaddr);

    g_free(watchpoint);

}

/* Remove all matching watchpoints.  */

void cpu_watchpoint_remove_all(CPUArchState *env, int mask)

{

    CPUWatchpoint *wp, *next;

    QTAILQ_FOREACH_SAFE(wp, &env->watchpoints, entry, next) {

        if (wp->flags & mask)

            cpu_watchpoint_remove_by_ref(env, wp);

    }

}

#endif

/* Add a breakpoint.  */

int cpu_breakpoint_insert(CPUArchState *env, target_ulong pc, int flags,

                          CPUBreakpoint **breakpoint)

{

#if defined(TARGET_HAS_ICE)

    CPUBreakpoint *bp;

    bp = g_malloc(sizeof(*bp));

    bp->pc = pc;

    bp->flags = flags;

    /* keep all GDB-injected breakpoints in front */

    if (flags & BP_GDB)

        QTAILQ_INSERT_HEAD(&env->breakpoints, bp, entry);

    else

        QTAILQ_INSERT_TAIL(&env->breakpoints, bp, entry);

    breakpoint_invalidate(env, pc);

    if (breakpoint)

        *breakpoint = bp;

    return 0;

#else

    return -ENOSYS;

#endif

}

/* Remove a specific breakpoint.  */

int cpu_breakpoint_remove(CPUArchState *env, target_ulong pc, int flags)

{

#if defined(TARGET_HAS_ICE)

    CPUBreakpoint *bp;

    QTAILQ_FOREACH(bp, &env->breakpoints, entry) {

        if (bp->pc == pc && bp->flags == flags) {

            cpu_breakpoint_remove_by_ref(env, bp);

            return 0;

        }

    }

    return -ENOENT;

#else

    return -ENOSYS;

#endif

}

/* Remove a specific breakpoint by reference.  */

void cpu_breakpoint_remove_by_ref(CPUArchState *env, CPUBreakpoint *breakpoint)

{

#if defined(TARGET_HAS_ICE)

    QTAILQ_REMOVE(&env->breakpoints, breakpoint, entry);

    breakpoint_invalidate(env, breakpoint->pc);

    g_free(breakpoint);

#endif

}

/* Remove all matching breakpoints. */

void cpu_breakpoint_remove_all(CPUArchState *env, int mask)

{

#if defined(TARGET_HAS_ICE)

    CPUBreakpoint *bp, *next;

    QTAILQ_FOREACH_SAFE(bp, &env->breakpoints, entry, next) {

        if (bp->flags & mask)

            cpu_breakpoint_remove_by_ref(env, bp);

    }

#endif

}

/* enable or disable single step mode. EXCP_DEBUG is returned by the

   CPU loop after each instruction */

void cpu_single_step(CPUArchState *env, int enabled)

{

#if defined(TARGET_HAS_ICE)

    if (env->singlestep_enabled != enabled) {

        env->singlestep_enabled = enabled;

        if (kvm_enabled())

            kvm_update_guest_debug(env, 0);

        else {

            /* must flush all the translated code to avoid inconsistencies */

            /* XXX: only flush what is necessary */

            tb_flush(env);

        }

    }

#endif

}

void cpu_exit(CPUArchState *env)

{

    CPUState *cpu = ENV_GET_CPU(env);

    cpu->exit_request = 1;

    cpu->tcg_exit_req = 1;

}

void cpu_abort(CPUArchState *env, const char *fmt, ...)

{

    va_list ap;

    va_list ap2;

    va_start(ap, fmt);

    va_copy(ap2, ap);

    fprintf(stderr, "qemu: fatal: ");

    vfprintf(stderr, fmt, ap);

    fprintf(stderr, "\n");

    cpu_dump_state(env, stderr, fprintf, CPU_DUMP_FPU | CPU_DUMP_CCOP);

    if (qemu_log_enabled()) {

        qemu_log("qemu: fatal: ");

        qemu_log_vprintf(fmt, ap2);

        qemu_log("\n");

        log_cpu_state(env, CPU_DUMP_FPU | CPU_DUMP_CCOP);

        qemu_log_flush();

        qemu_log_close();

    }

    va_end(ap2);

    va_end(ap);

#if defined(CONFIG_USER_ONLY)

    {

        struct sigaction act;

        sigfillset(&act.sa_mask);

        act.sa_handler = SIG_DFL;

        sigaction(SIGABRT, &act, NULL);

    }

#endif

    abort();

}

CPUArchState *cpu_copy(CPUArchState *env)

{

    CPUArchState *new_env = cpu_init(env->cpu_model_str);

    CPUArchState *next_cpu = new_env->next_cpu;

#if defined(TARGET_HAS_ICE)

    CPUBreakpoint *bp;

    CPUWatchpoint *wp;

#endif

    memcpy(new_env, env, sizeof(CPUArchState));

    /* Preserve chaining. */

    new_env->next_cpu = next_cpu;

    /* Clone all break/watchpoints.

       Note: Once we support ptrace with hw-debug register access, make sure

       BP_CPU break/watchpoints are handled correctly on clone. */

    QTAILQ_INIT(&env->breakpoints);

    QTAILQ_INIT(&env->watchpoints);

#if defined(TARGET_HAS_ICE)

    QTAILQ_FOREACH(bp, &env->breakpoints, entry) {

        cpu_breakpoint_insert(new_env, bp->pc, bp->flags, NULL);

    }

    QTAILQ_FOREACH(wp, &env->watchpoints, entry) {

        cpu_watchpoint_insert(new_env, wp->vaddr, (~wp->len_mask) + 1,

                              wp->flags, NULL);

    }

#endif

    return new_env;

}

#if !defined(CONFIG_USER_ONLY)

static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t end,

                                      uintptr_t length)

{

    uintptr_t start1;

    /* we modify the TLB cache so that the dirty bit will be set again

       when accessing the range */

    start1 = (uintptr_t)qemu_safe_ram_ptr(start);

    /* Check that we don't span multiple blocks - this breaks the

       address comparisons below.  */

    if ((uintptr_t)qemu_safe_ram_ptr(end - 1) - start1

            != (end - 1) - start) {

        abort();

    }

    cpu_tlb_reset_dirty_all(start1, length);

}

/* Note: start and end must be within the same ram block.  */

void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,

                                     int dirty_flags)

{

    uintptr_t length;

    start &= TARGET_PAGE_MASK;

    end = TARGET_PAGE_ALIGN(end);

    length = end - start;

    if (length == 0)

        return;

    cpu_physical_memory_mask_dirty_range(start, length, dirty_flags);

    if (tcg_enabled()) {

        tlb_reset_dirty_range_all(start, end, length);

    }

}

static int cpu_physical_memory_set_dirty_tracking(int enable)

{

    int ret = 0;

    in_migration = enable;

    return ret;

}

hwaddr memory_region_section_get_iotlb(CPUArchState *env,

                                                   MemoryRegionSection *section,

                                                   target_ulong vaddr,

                                                   hwaddr paddr,

                                                   int prot,

                                                   target_ulong *address)

{

    hwaddr iotlb;

    CPUWatchpoint *wp;

    if (memory_region_is_ram(section->mr)) {

        /* Normal RAM.  */

        iotlb = (memory_region_get_ram_addr(section->mr) & TARGET_PAGE_MASK)

            + memory_region_section_addr(section, paddr);

        if (!section->readonly) {

            iotlb |= phys_section_notdirty;

        } else {

            iotlb |= phys_section_rom;

        }

    } else {

        /* IO handlers are currently passed a physical address.

           It would be nice to pass an offset from the base address

           of that region.  This would avoid having to special case RAM,

           and avoid full address decoding in every device.

           We can't use the high bits of pd for this because

           IO_MEM_ROMD uses these as a ram address.  */

        iotlb = section - phys_sections;

        iotlb += memory_region_section_addr(section, paddr);

    }

    /* Make accesses to pages with watchpoints go via the

       watchpoint trap routines.  */

    QTAILQ_FOREACH(wp, &env->watchpoints, entry) {

        if (vaddr == (wp->vaddr & TARGET_PAGE_MASK)) {

            /* Avoid trapping reads of pages with a write breakpoint. */

            if ((prot & PAGE_WRITE) || (wp->flags & BP_MEM_READ)) {

                iotlb = phys_section_watch + paddr;

                *address |= TLB_MMIO;

                break;

            }

        }

    }

    return iotlb;

}

#endif /* defined(CONFIG_USER_ONLY) */

#if !defined(CONFIG_USER_ONLY)

#define SUBPAGE_IDX(addr) ((addr) & ~TARGET_PAGE_MASK)

typedef struct subpage_t {

    MemoryRegion iomem;

    hwaddr base;

    uint16_t sub_section[TARGET_PAGE_SIZE];

} subpage_t;

static int subpage_register (subpage_t *mmio, uint32_t start, uint32_t end,

                             uint16_t section);

static subpage_t *subpage_init(hwaddr base);

static void destroy_page_desc(uint16_t section_index)

{

    MemoryRegionSection *section = &phys_sections[section_index];

    MemoryRegion *mr = section->mr;

    if (mr->subpage) {

        subpage_t *subpage = container_of(mr, subpage_t, iomem);

        memory_region_destroy(&subpage->iomem);

        g_free(subpage);

    }

}

static void destroy_l2_mapping(PhysPageEntry *lp, unsigned level)

{

    unsigned i;

    PhysPageEntry *p;

    if (lp->ptr == PHYS_MAP_NODE_NIL) {

        return;

    }

    p = phys_map_nodes[lp->ptr];

    for (i = 0; i < L2_SIZE; ++i) {

        if (!p[i].is_leaf) {

            destroy_l2_mapping(&p[i], level - 1);

        } else {

            destroy_page_desc(p[i].ptr);

        }

    }

    lp->is_leaf = 0;

    lp->ptr = PHYS_MAP_NODE_NIL;

}

static void destroy_all_mappings(AddressSpaceDispatch *d)

{

    destroy_l2_mapping(&d->phys_map, P_L2_LEVELS - 1);

    phys_map_nodes_reset();

}

static uint16_t phys_section_add(MemoryRegionSection *section)

{

    if (phys_sections_nb == phys_sections_nb_alloc) {

        phys_sections_nb_alloc = MAX(phys_sections_nb_alloc * 2, 16);

        phys_sections = g_renew(MemoryRegionSection, phys_sections,

                                phys_sections_nb_alloc);

    }

    phys_sections[phys_sections_nb] = *section;

    return phys_sections_nb++;

}

static void phys_sections_clear(void)

{

    phys_sections_nb = 0;

}

static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *section)

{

    subpage_t *subpage;

    hwaddr base = section->offset_within_address_space

        & TARGET_PAGE_MASK;

    MemoryRegionSection *existing = phys_page_find(d, base >> TARGET_PAGE_BITS);

    MemoryRegionSection subsection = {

        .offset_within_address_space = base,

        .size = TARGET_PAGE_SIZE,

    };

    hwaddr start, end;

    assert(existing->mr->subpage || existing->mr == &io_mem_unassigned);

    if (!(existing->mr->subpage)) {

        subpage = subpage_init(base);

        subsection.mr = &subpage->iomem;

        phys_page_set(d, base >> TARGET_PAGE_BITS, 1,

                      phys_section_add(&subsection));

    } else {

        subpage = container_of(existing->mr, subpage_t, iomem);

    }

    start = section->offset_within_address_space & ~TARGET_PAGE_MASK;

    end = start + section->size - 1;

    subpage_register(subpage, start, end, phys_section_add(section));

}

static void register_multipage(AddressSpaceDispatch *d, MemoryRegionSection *section)

{

    hwaddr start_addr = section->offset_within_address_space;

    ram_addr_t size = section->size;

    hwaddr addr;

    uint16_t section_index = phys_section_add(section);

    assert(size);

    addr = start_addr;

    phys_page_set(d, addr >> TARGET_PAGE_BITS, size >> TARGET_PAGE_BITS,

                  section_index);

}

static void mem_add(MemoryListener *listener, MemoryRegionSection *section)

{

    AddressSpaceDispatch *d = container_of(listener, AddressSpaceDispatch, listener);

    MemoryRegionSection now = *section, remain = *section;

    if ((now.offset_within_address_space & ~TARGET_PAGE_MASK)

        || (now.size < TARGET_PAGE_SIZE)) {

        now.size = MIN(TARGET_PAGE_ALIGN(now.offset_within_address_space)

                       - now.offset_within_address_space,

                       now.size);

        register_subpage(d, &now);

        remain.size -= now.size;

        remain.offset_within_address_space += now.size;

        remain.offset_within_region += now.size;

    }

    while (remain.size >= TARGET_PAGE_SIZE) {

        now = remain;

        if (remain.offset_within_region & ~TARGET_PAGE_MASK) {

            now.size = TARGET_PAGE_SIZE;

            register_subpage(d, &now);

        } else {

            now.size &= TARGET_PAGE_MASK;

            register_multipage(d, &now);

        }

        remain.size -= now.size;

        remain.offset_within_address_space += now.size;

        remain.offset_within_region += now.size;

    }

    now = remain;

    if (now.size) {

        register_subpage(d, &now);

    }

}

void qemu_flush_coalesced_mmio_buffer(void)

{

    if (kvm_enabled())

        kvm_flush_coalesced_mmio_buffer();

}

void qemu_mutex_lock_ramlist(void)

{

    qemu_mutex_lock(&ram_list.mutex);

}

void qemu_mutex_unlock_ramlist(void)

{

    qemu_mutex_unlock(&ram_list.mutex);

}

#if defined(__linux__) && !defined(TARGET_S390X)

#include <sys/vfs.h>

#define HUGETLBFS_MAGIC       0x958458f6

static long gethugepagesize(const char *path)

{

    struct statfs fs;

    int ret;

    do {

        ret = statfs(path, &fs);

    } while (ret != 0 && errno == EINTR);

    if (ret != 0) {

        perror(path);

        return 0;

    }

    if (fs.f_type != HUGETLBFS_MAGIC)

        fprintf(stderr, "Warning: path not on HugeTLBFS: %s\n", path);

    return fs.f_bsize;

}

static void *file_ram_alloc(RAMBlock *block,

                            ram_addr_t memory,

                            const char *path)

{

    char *filename;

    char *sanitized_name;

    char *c;

    void *area;

    int fd;

#ifdef MAP_POPULATE

    int flags;

#endif

    unsigned long hpagesize;

    hpagesize = gethugepagesize(path);

    if (!hpagesize) {

        return NULL;

    }

    if (memory < hpagesize) {

        return NULL;

    }

    if (kvm_enabled() && !kvm_has_sync_mmu()) {

        fprintf(stderr, "host lacks kvm mmu notifiers, -mem-path unsupported\n");

        return NULL;

    }

    /* Make name safe to use with mkstemp by replacing '/' with '_'. */

    sanitized_name = g_strdup(block->mr->name);

    for (c = sanitized_name; *c != '\0'; c++) {

        if (*c == '/')

            *c = '_';

    }

    filename = g_strdup_printf("%s/qemu_back_mem.%s.XXXXXX", path,

                               sanitized_name);

    g_free(sanitized_name);

    fd = mkstemp(filename);

    if (fd < 0) {

        perror("unable to create backing store for hugepages");

        g_free(filename);

        return NULL;

    }

    unlink(filename);

    g_free(filename);

    memory = (memory+hpagesize-1) & ~(hpagesize-1);

    /*

     * ftruncate is not supported by hugetlbfs in older

     * hosts, so don't bother bailing out on errors.

     * If anything goes wrong with it under other filesystems,

     * mmap will fail.

     */

    if (ftruncate(fd, memory))

        perror("ftruncate");

#ifdef MAP_POPULATE

    /* NB: MAP_POPULATE won't exhaustively alloc all phys pages in the case

     * MAP_PRIVATE is requested.  For mem_prealloc we mmap as MAP_SHARED

     * to sidestep this quirk.

     */

    flags = mem_prealloc ? MAP_POPULATE | MAP_SHARED : MAP_PRIVATE;

    area = mmap(0, memory, PROT_READ | PROT_WRITE, flags, fd, 0);

#else

    area = mmap(0, memory, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);

#endif

    if (area == MAP_FAILED) {

        perror("file_ram_alloc: can't mmap RAM pages");

        close(fd);

        return (NULL);

    }

    block->fd = fd;