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/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_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;

MemoryRegion io_mem_rom, io_mem_notdirty;

static MemoryRegion io_mem_unassigned;

#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)

typedef struct PhysPageEntry PhysPageEntry;

struct PhysPageEntry {

    uint16_t is_leaf : 1;

     /* index into phys_sections (is_leaf) or phys_map_nodes (!is_leaf) */

    uint16_t ptr : 15;

};

struct AddressSpaceDispatch {

    /* This is a multi-level map on the physical address space.

     * The bottom level has pointers to MemoryRegionSections.

     */

    PhysPageEntry phys_map;

    MemoryListener listener;

    AddressSpace *as;

};

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

typedef struct subpage_t {

    MemoryRegion iomem;

    AddressSpace *as;

    hwaddr base;

    uint16_t sub_section[TARGET_PAGE_SIZE];

} subpage_t;

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_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);

}

static MemoryRegionSection *phys_page_find(AddressSpaceDispatch *d, hwaddr index)

{

    PhysPageEntry lp = d->phys_map;

    PhysPageEntry *p;

    int i;

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

        if (lp.ptr == PHYS_MAP_NODE_NIL) {

            return &phys_sections[phys_section_unassigned];

        }

        p = phys_map_nodes[lp.ptr];

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

    }

    return &phys_sections[lp.ptr];

}

bool memory_region_is_unassigned(MemoryRegion *mr)

{

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

        && mr != &io_mem_watch;

}

static MemoryRegionSection *address_space_lookup_region(AddressSpace *as,

                                                        hwaddr addr,

                                                        bool resolve_subpage)

{

    MemoryRegionSection *section;

    subpage_t *subpage;

    section = phys_page_find(as->dispatch, addr >> TARGET_PAGE_BITS);

    if (resolve_subpage && section->mr->subpage) {

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

        section = &phys_sections[subpage->sub_section[SUBPAGE_IDX(addr)]];

    }

    return section;

}

static MemoryRegionSection *

address_space_translate_internal(AddressSpace *as, hwaddr addr, hwaddr *xlat,

                                 hwaddr *plen, bool resolve_subpage)

{

    MemoryRegionSection *section;

    Int128 diff;

    section = address_space_lookup_region(as, addr, resolve_subpage);

    /* Compute offset within MemoryRegionSection */

    addr -= section->offset_within_address_space;

    /* Compute offset within MemoryRegion */

    *xlat = addr + section->offset_within_region;

    diff = int128_sub(section->mr->size, int128_make64(addr));

    *plen = int128_get64(int128_min(diff, int128_make64(*plen)));

    return section;

}

MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,

                                      hwaddr *xlat, hwaddr *plen,

                                      bool is_write)

{

    IOMMUTLBEntry iotlb;

    MemoryRegionSection *section;

    MemoryRegion *mr;

    hwaddr len = *plen;

    for (;;) {

        section = address_space_translate_internal(as, addr, &addr, plen, true);

        mr = section->mr;

        if (!mr->iommu_ops) {

            break;

        }

        iotlb = mr->iommu_ops->translate(mr, addr);

        addr = ((iotlb.translated_addr & ~iotlb.addr_mask)

                | (addr & iotlb.addr_mask));

        len = MIN(len, (addr | iotlb.addr_mask) - addr + 1);

        if (!(iotlb.perm & (1 << is_write))) {

            mr = &io_mem_unassigned;

            break;

        }

        as = iotlb.target_as;

    }

    *plen = len;

    *xlat = addr;

    return mr;

}

MemoryRegionSection *

address_space_translate_for_iotlb(AddressSpace *as, hwaddr addr, hwaddr *xlat,

                                  hwaddr *plen)

{

    MemoryRegionSection *section;

    section = address_space_translate_internal(as, addr, xlat, plen, false);

    assert(!section->mr->iommu_ops);

    return section;

}

#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;

}

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()

    }

};

#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 qemu_for_each_cpu(void (*func)(CPUState *cpu, void *data), void *data)

{

    CPUArchState *env = first_cpu;

    while (env) {

        func(ENV_GET_CPU(env), data);

        env = env->next_cpu;

    }

}

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_abort(CPUArchState *env, const char *fmt, ...)

{

    CPUState *cpu = ENV_GET_CPU(env);

    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(cpu, 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, hwaddr xlat,

                                       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)

            + xlat;

        if (!section->readonly) {

            iotlb |= phys_section_notdirty;

        } else {

            iotlb |= phys_section_rom;

        }

    } else {

        iotlb = section - phys_sections;

        iotlb += xlat;

    }

    /* 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)

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

                             uint16_t section);

static subpage_t *subpage_init(AddressSpace *as, hwaddr base);

static uint16_t phys_section_add(MemoryRegionSection *section)

{

    /* The physical section number is ORed with a page-aligned

     * pointer to produce the iotlb entries.  Thus it should

     * never overflow into the page-aligned value.

     */

    assert(phys_sections_nb < TARGET_PAGE_SIZE);

    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;

    memory_region_ref(section->mr);

    return phys_sections_nb++;

}

static void phys_section_destroy(MemoryRegion *mr)

{

    memory_region_unref(mr);

    if (mr->subpage) {

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

        memory_region_destroy(&subpage->iomem);

        g_free(subpage);

    }

}

static void phys_sections_clear(void)

{

    while (phys_sections_nb > 0) {

        MemoryRegionSection *section = &phys_sections[--phys_sections_nb];

        phys_section_destroy(section->mr);

    }

    phys_map_nodes_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 = int128_make64(TARGET_PAGE_SIZE),

    };

    hwaddr start, end;

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

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

        subpage = subpage_init(d->as, 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 + int128_get64(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;

    uint16_t section_index = phys_section_add(section);

    uint64_t num_pages = int128_get64(int128_rshift(section->size,

                                                    TARGET_PAGE_BITS));

    assert(num_pages);

    phys_page_set(d, start_addr >> TARGET_PAGE_BITS, num_pages, section_index);

}

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

{

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

    MemoryRegionSection now = *section, remain = *section;

    Int128 page_size = int128_make64(TARGET_PAGE_SIZE);

    if (now.offset_within_address_space & ~TARGET_PAGE_MASK) {

        uint64_t left = TARGET_PAGE_ALIGN(now.offset_within_address_space)

                       - now.offset_within_address_space;

        now.size = int128_min(int128_make64(left), now.size);

        register_subpage(d, &now);

    } else {

        now.size = int128_zero();

    }

    while (int128_ne(remain.size, now.size)) {

        remain.size = int128_sub(remain.size, now.size);

        remain.offset_within_address_space += int128_get64(now.size);

        remain.offset_within_region += int128_get64(now.size);

        now = remain;

        if (int128_lt(remain.size, page_size)) {

            register_subpage(d, &now);

        } else if (remain.offset_within_region & ~TARGET_PAGE_MASK) {

            now.size = page_size;

            register_subpage(d, &now);

        } else {

            now.size = int128_and(now.size, int128_neg(page_size));

            register_multipage(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;

    return area;

}

#endif

static ram_addr_t find_ram_offset(ram_addr_t size)

{

    RAMBlock *block, *next_block;

    ram_addr_t offset = RAM_ADDR_MAX, mingap = RAM_ADDR_MAX;

    assert(size != 0); /* it would hand out same offset multiple times */

    if (QTAILQ_EMPTY(&ram_list.blocks))

        return 0;

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        ram_addr_t end, next = RAM_ADDR_MAX;

        end = block->offset + block->length;

        QTAILQ_FOREACH(next_block, &ram_list.blocks, next) {

            if (next_block->offset >= end) {

                next = MIN(next, next_block->offset);

            }

        }

        if (next - end >= size && next - end < mingap) {

            offset = end;

            mingap = next - end;

        }

    }

    if (offset == RAM_ADDR_MAX) {

        fprintf(stderr, "Failed to find gap of requested size: %" PRIu64 "\n",

                (uint64_t)size);

        abort();

    }

    return offset;

}

ram_addr_t last_ram_offset(void)

{

    RAMBlock *block;

    ram_addr_t last = 0;

    QTAILQ_FOREACH(block, &ram_list.blocks, next)

        last = MAX(last, block->offset + block->length);

    return last;

}

static void qemu_ram_setup_dump(void *addr, ram_addr_t size)

{

    int ret;

    QemuOpts *machine_opts;

    /* Use MADV_DONTDUMP, if user doesn't want the guest memory in the core */

    machine_opts = qemu_opts_find(qemu_find_opts("machine"), 0);

    if (machine_opts &&

        !qemu_opt_get_bool(machine_opts, "dump-guest-core", true)) {

        ret = qemu_madvise(addr, size, QEMU_MADV_DONTDUMP);

        if (ret) {

            perror("qemu_madvise");

            fprintf(stderr, "madvise doesn't support MADV_DONTDUMP, "

                            "but dump_guest_core=off specified\n");

        }

    }

}

void qemu_ram_set_idstr(ram_addr_t addr, const char *name, DeviceState *dev)

{

    RAMBlock *new_block, *block;

    new_block = NULL;

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (block->offset == addr) {

            new_block = block;

            break;

        }

    }

    assert(new_block);

    assert(!new_block->idstr[0]);

    if (dev) {

        char *id = qdev_get_dev_path(dev);

        if (id) {

            snprintf(new_block->idstr, sizeof(new_block->idstr), "%s/", id);

            g_free(id);

        }

    }

    pstrcat(new_block->idstr, sizeof(new_block->idstr), name);

    /* This assumes the iothread lock is taken here too.  */

    qemu_mutex_lock_ramlist();

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (block != new_block && !strcmp(block->idstr, new_block->idstr)) {

            fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",

                    new_block->idstr);

            abort();

        }

    }

    qemu_mutex_unlock_ramlist();

}

static int memory_try_enable_merging(void *addr, size_t len)

{

    QemuOpts *opts;

    opts = qemu_opts_find(qemu_find_opts("machine"), 0);

    if (opts && !qemu_opt_get_bool(opts, "mem-merge", true)) {

        /* disabled by the user */

        return 0;

    }

    return qemu_madvise(addr, len, QEMU_MADV_MERGEABLE);

}

ram_addr_t qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,

                                   MemoryRegion *mr)

{

    RAMBlock *block, *new_block;

    size = TARGET_PAGE_ALIGN(size);

    new_block = g_malloc0(sizeof(*new_block));

    /* This assumes the iothread lock is taken here too.  */

    qemu_mutex_lock_ramlist();

    new_block->mr = mr;

    new_block->offset = find_ram_offset(size);

    if (host) {

        new_block->host = host;

        new_block->flags |= RAM_PREALLOC_MASK;

    } else {

        if (mem_path) {

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

            new_block->host = file_ram_alloc(new_block, size, mem_path);

            if (!new_block->host) {

                new_block->host = qemu_anon_ram_alloc(size);

                memory_try_enable_merging(new_block->host, size);

            }

#else

            fprintf(stderr, "-mem-path option unsupported\n");

            exit(1);

#endif

        } else {

            if (xen_enabled()) {

                xen_ram_alloc(new_block->offset, size, mr);

            } else if (kvm_enabled()) {

                /* some s390/kvm configurations have special constraints */

                new_block->host = kvm_ram_alloc(size);

            } else {

                new_block->host = qemu_anon_ram_alloc(size);

            }

            memory_try_enable_merging(new_block->host, size);

        }

    }

    new_block->length = size;

    /* Keep the list sorted from biggest to smallest block.  */

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (block->length < new_block->length) {

            break;

        }

    }

    if (block) {

        QTAILQ_INSERT_BEFORE(block, new_block, next);

    } else {

        QTAILQ_INSERT_TAIL(&ram_list.blocks, new_block, next);

    }

    ram_list.mru_block = NULL;

    ram_list.version++;

    qemu_mutex_unlock_ramlist();

    ram_list.phys_dirty = g_realloc(ram_list.phys_dirty,

                                       last_ram_offset() >> TARGET_PAGE_BITS);

    memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),

           0, size >> TARGET_PAGE_BITS);

    cpu_physical_memory_set_dirty_range(new_block->offset, size, 0xff);

    qemu_ram_setup_dump(new_block->host, size);

    qemu_madvise(new_block->host, size, QEMU_MADV_HUGEPAGE);

    if (kvm_enabled())

        kvm_setup_guest_memory(new_block->host, size);

    return new_block->offset;

}

ram_addr_t qemu_ram_alloc(ram_addr_t size, MemoryRegion *mr)

{

    return qemu_ram_alloc_from_ptr(size, NULL, mr);

}

void qemu_ram_free_from_ptr(ram_addr_t addr)

{

    RAMBlock *block;

    /* This assumes the iothread lock is taken here too.  */

    qemu_mutex_lock_ramlist();

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (addr == block->offset) {

            QTAILQ_REMOVE(&ram_list.blocks, block, next);

            ram_list.mru_block = NULL;

            ram_list.version++;

            g_free(block);

            break;

        }

    }

    qemu_mutex_unlock_ramlist();

}

void qemu_ram_free(ram_addr_t addr)

{

    RAMBlock *block;

    /* This assumes the iothread lock is taken here too.  */

    qemu_mutex_lock_ramlist();

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (addr == block->offset) {

            QTAILQ_REMOVE(&ram_list.blocks, block, next);

            ram_list.mru_block = NULL;

            ram_list.version++;

            if (block->flags & RAM_PREALLOC_MASK) {

                ;

            } else if (mem_path) {

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

                if (block->fd) {

                    munmap(block->host, block->length);

                    close(block->fd);

                } else {

                    qemu_anon_ram_free(block->host, block->length);

                }

#else

                abort();

#endif

            } else {

                if (xen_enabled()) {

                    xen_invalidate_map_cache_entry(block->host);

                } else {

                    qemu_anon_ram_free(block->host, block->length);

                }

            }

            g_free(block);

            break;

        }

    }

    qemu_mutex_unlock_ramlist();

}

#ifndef _WIN32

void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)

{

    RAMBlock *block;

    ram_addr_t offset;

    int flags;

    void *area, *vaddr;

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        offset = addr - block->offset;

        if (offset < block->length) {

            vaddr = block->host + offset;

            if (block->flags & RAM_PREALLOC_MASK) {

                ;

            } else {

                flags = MAP_FIXED;

                munmap(vaddr, length);

                if (mem_path) {

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

                    if (block->fd) {

#ifdef MAP_POPULATE

                        flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :

                            MAP_PRIVATE;

#else

                        flags |= MAP_PRIVATE;

#endif

                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,

                                    flags, block->fd, offset);

                    } else {

                        flags |= MAP_PRIVATE | MAP_ANONYMOUS;

                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,

                                    flags, -1, 0);

                    }

#else

                    abort();

#endif

                } else {

#if defined(TARGET_S390X) && defined(CONFIG_KVM)

                    flags |= MAP_SHARED | MAP_ANONYMOUS;

                    area = mmap(vaddr, length, PROT_EXEC|PROT_READ|PROT_WRITE,

                                flags, -1, 0);

#else

                    flags |= MAP_PRIVATE | MAP_ANONYMOUS;

                    area = mmap(vaddr, length, PROT_READ | PROT_WRITE,

                                flags, -1, 0);

#endif

                }

                if (area != vaddr) {

                    fprintf(stderr, "Could not remap addr: "

                            RAM_ADDR_FMT "@" RAM_ADDR_FMT "\n",

                            length, addr);

                    exit(1);

                }

                memory_try_enable_merging(vaddr, length);

                qemu_ram_setup_dump(vaddr, length);

            }

            return;

        }

    }

}

#endif /* !_WIN32 */

static RAMBlock *qemu_get_ram_block(ram_addr_t addr)

{

    RAMBlock *block;

    /* The list is protected by the iothread lock here.  */

    block = ram_list.mru_block;

    if (block && addr - block->offset < block->length) {

        goto found;

    }

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (addr - block->offset < block->length) {

            goto found;

        }

    }

    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);

    abort();

found:

    ram_list.mru_block = block;

    return block;

}

/* Return a host pointer to ram allocated with qemu_ram_alloc.

   With the exception of the softmmu code in this file, this should

   only be used for local memory (e.g. video ram) that the device owns,

   and knows it isn't going to access beyond the end of the block.

   It should not be used for general purpose DMA.

   Use cpu_physical_memory_map/cpu_physical_memory_rw instead.

 */

void *qemu_get_ram_ptr(ram_addr_t addr)

{

    RAMBlock *block = qemu_get_ram_block(addr);

    if (xen_enabled()) {

        /* We need to check if the requested address is in the RAM

         * because we don't want to map the entire memory in QEMU.

         * In that case just map until the end of the page.

         */

        if (block->offset == 0) {

            return xen_map_cache(addr, 0, 0);

        } else if (block->host == NULL) {

            block->host =

                xen_map_cache(block->offset, block->length, 1);

        }

    }

    return block->host + (addr - block->offset);

}

/* Return a host pointer to ram allocated with qemu_ram_alloc.  Same as

 * qemu_get_ram_ptr but do not touch ram_list.mru_block.

 *

 * ??? Is this still necessary?

 */

static void *qemu_safe_ram_ptr(ram_addr_t addr)

{

    RAMBlock *block;

    /* The list is protected by the iothread lock here.  */

    QTAILQ_FOREACH(block, &ram_list.blocks, next) {

        if (addr - block->offset < block->length) {

            if (xen_enabled()) {

                /* We need to check if the requested address is in the RAM

                 * because we don't want to map the entire memory in QEMU.

                 * In that case just map until the end of the page.

                 */

                if (block->offset == 0) {

                    return xen_map_cache(addr, 0, 0);

                } else if (block->host == NULL) {

                    block->host =

                        xen_map_cache(block->offset, block->length, 1);

                }

            }

            return block->host + (addr - block->offset);

        }

    }

    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);

    abort();

    return NULL;

}

/* Return a host pointer to guest's ram. Similar to qemu_get_ram_ptr

 * but takes a size argument */

static void *qemu_ram_ptr_length(ram_addr_t addr, ram_addr_t *size)

{

    if (*size == 0) {

        return NULL;

    }

    if (xen_enabled()) {

        return xen_map_cache(addr, *size, 1);

    } else {

        RAMBlock *block;

        QTAILQ_FOREACH(block, &ram_list.blocks, next) {

            if (addr - block->offset < block->length) {

                if (addr - block->offset + *size > block->length)

                    *size = block->length - addr + block->offset;

                return block->host + (addr - block->offset);

            }

        }

        fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);

        abort();

    }

}

/* Some of the softmmu routines need to translate from a host pointer

   (typically a TLB entry) back to a ram offset.  */

MemoryRegion *qemu_ram_addr_from_host(void *ptr, ram_addr_t *ram_addr)

{

    RAMBlock *block;

    uint8_t *host = ptr;

    if (xen_enabled()) {

        *ram_addr = xen_ram_addr_from_mapcache(ptr);