Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging

* qtest documentation improvements (Eduardo, myself)
* libqtest event buffering (Maxim)
* use RCU for list of children of a bus (Maxim)
* move more files to softmmu/ (myself)
* meson.build cleanups, qemu-storage-daemon fix (Philippe)

# gpg: Signature made Mon 12 Oct 2020 16:55:19 BST
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini-gitlab/tags/for-upstream: (38 commits)
  meson: identify more sections of meson.build
  scsi/scsi_bus: fix races in REPORT LUNS
  virtio-scsi: use scsi_device_get
  scsi/scsi_bus: Add scsi_device_get
  scsi/scsi-bus: scsi_device_find: don't return unrealized devices
  device-core: use atomic_set on .realized property
  scsi: switch to bus->check_address
  device-core: use RCU for list of children of a bus
  device_core: use drain_call_rcu in in qmp_device_add
  scsi/scsi_bus: switch search direction in scsi_device_find
  qdev: add "check if address free" callback for buses
  qemu-iotests, qtest: rewrite test 067 as a qtest
  qtest: check that drives are really appearing and disappearing
  qtest: switch users back to qtest_qmp_receive
  device-plug-test: use qtest_qmp to send the device_del command
  qtest: remove qtest_qmp_receive_success
  qtest: Reintroduce qtest_qmp_receive with QMP event buffering
  qtest: rename qtest_qmp_receive to qtest_qmp_receive_dict
  meson.build: Re-enable KVM support for MIPS
  build-sys: fix git version from -version
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

9 files changed, 6725 insertions, 8 deletions

diff --git a/softmmu/bootdevice.c b/softmmu/bootdevice.c
new file mode 100644
index 0000000..add4e3d
--- /dev/null
+++ b/softmmu/bootdevice.c
@@ -0,0 +1,429 @@
+/*
+ * QEMU Boot Device Implement
+ *
+ * Copyright (c) 2014 HUAWEI TECHNOLOGIES CO., LTD.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "sysemu/sysemu.h"
+#include "qapi/visitor.h"
+#include "qemu/error-report.h"
+#include "sysemu/reset.h"
+#include "hw/qdev-core.h"
+#include "hw/boards.h"
+
+typedef struct FWBootEntry FWBootEntry;
+
+struct FWBootEntry {
+    QTAILQ_ENTRY(FWBootEntry) link;
+    int32_t bootindex;
+    DeviceState *dev;
+    char *suffix;
+};
+
+static QTAILQ_HEAD(, FWBootEntry) fw_boot_order =
+    QTAILQ_HEAD_INITIALIZER(fw_boot_order);
+static QEMUBootSetHandler *boot_set_handler;
+static void *boot_set_opaque;
+
+void qemu_register_boot_set(QEMUBootSetHandler *func, void *opaque)
+{
+    boot_set_handler = func;
+    boot_set_opaque = opaque;
+}
+
+void qemu_boot_set(const char *boot_order, Error **errp)
+{
+    Error *local_err = NULL;
+
+    if (!boot_set_handler) {
+        error_setg(errp, "no function defined to set boot device list for"
+                         " this architecture");
+        return;
+    }
+
+    validate_bootdevices(boot_order, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    boot_set_handler(boot_set_opaque, boot_order, errp);
+}
+
+void validate_bootdevices(const char *devices, Error **errp)
+{
+    /* We just do some generic consistency checks */
+    const char *p;
+    int bitmap = 0;
+
+    for (p = devices; *p != '\0'; p++) {
+        /* Allowed boot devices are:
+         * a-b: floppy disk drives
+         * c-f: IDE disk drives
+         * g-m: machine implementation dependent drives
+         * n-p: network devices
+         * It's up to each machine implementation to check if the given boot
+         * devices match the actual hardware implementation and firmware
+         * features.
+         */
+        if (*p < 'a' || *p > 'p') {
+            error_setg(errp, "Invalid boot device '%c'", *p);
+            return;
+        }
+        if (bitmap & (1 << (*p - 'a'))) {
+            error_setg(errp, "Boot device '%c' was given twice", *p);
+            return;
+        }
+        bitmap |= 1 << (*p - 'a');
+    }
+}
+
+void restore_boot_order(void *opaque)
+{
+    char *normal_boot_order = opaque;
+    static int first = 1;
+
+    /* Restore boot order and remove ourselves after the first boot */
+    if (first) {
+        first = 0;
+        return;
+    }
+
+    if (boot_set_handler) {
+        qemu_boot_set(normal_boot_order, &error_abort);
+    }
+
+    qemu_unregister_reset(restore_boot_order, normal_boot_order);
+    g_free(normal_boot_order);
+}
+
+void check_boot_index(int32_t bootindex, Error **errp)
+{
+    FWBootEntry *i;
+
+    if (bootindex >= 0) {
+        QTAILQ_FOREACH(i, &fw_boot_order, link) {
+            if (i->bootindex == bootindex) {
+                error_setg(errp, "The bootindex %d has already been used",
+                           bootindex);
+                return;
+            }
+        }
+    }
+}
+
+void del_boot_device_path(DeviceState *dev, const char *suffix)
+{
+    FWBootEntry *i;
+
+    if (dev == NULL) {
+        return;
+    }
+
+    QTAILQ_FOREACH(i, &fw_boot_order, link) {
+        if ((!suffix || !g_strcmp0(i->suffix, suffix)) &&
+             i->dev == dev) {
+            QTAILQ_REMOVE(&fw_boot_order, i, link);
+            g_free(i->suffix);
+            g_free(i);
+
+            break;
+        }
+    }
+}
+
+void add_boot_device_path(int32_t bootindex, DeviceState *dev,
+                          const char *suffix)
+{
+    FWBootEntry *node, *i;
+
+    if (bootindex < 0) {
+        del_boot_device_path(dev, suffix);
+        return;
+    }
+
+    assert(dev != NULL || suffix != NULL);
+
+    del_boot_device_path(dev, suffix);
+
+    node = g_malloc0(sizeof(FWBootEntry));
+    node->bootindex = bootindex;
+    node->suffix = g_strdup(suffix);
+    node->dev = dev;
+
+    QTAILQ_FOREACH(i, &fw_boot_order, link) {
+        if (i->bootindex == bootindex) {
+            error_report("Two devices with same boot index %d", bootindex);
+            exit(1);
+        } else if (i->bootindex < bootindex) {
+            continue;
+        }
+        QTAILQ_INSERT_BEFORE(i, node, link);
+        return;
+    }
+    QTAILQ_INSERT_TAIL(&fw_boot_order, node, link);
+}
+
+DeviceState *get_boot_device(uint32_t position)
+{
+    uint32_t counter = 0;
+    FWBootEntry *i = NULL;
+    DeviceState *res = NULL;
+
+    if (!QTAILQ_EMPTY(&fw_boot_order)) {
+        QTAILQ_FOREACH(i, &fw_boot_order, link) {
+            if (counter == position) {
+                res = i->dev;
+                break;
+            }
+            counter++;
+        }
+    }
+    return res;
+}
+
+static char *get_boot_device_path(DeviceState *dev, bool ignore_suffixes,
+                                  const char *suffix)
+{
+    char *devpath = NULL, *s = NULL, *d, *bootpath;
+
+    if (dev) {
+        devpath = qdev_get_fw_dev_path(dev);
+        assert(devpath);
+    }
+
+    if (!ignore_suffixes) {
+        if (dev) {
+            d = qdev_get_own_fw_dev_path_from_handler(dev->parent_bus, dev);
+            if (d) {
+                assert(!suffix);
+                s = d;
+            } else {
+                s = g_strdup(suffix);
+            }
+        } else {
+            s = g_strdup(suffix);
+        }
+    }
+
+    bootpath = g_strdup_printf("%s%s",
+                               devpath ? devpath : "",
+                               s ? s : "");
+    g_free(devpath);
+    g_free(s);
+
+    return bootpath;
+}
+
+/*
+ * This function returns null terminated string that consist of new line
+ * separated device paths.
+ *
+ * memory pointed by "size" is assigned total length of the array in bytes
+ *
+ */
+char *get_boot_devices_list(size_t *size)
+{
+    FWBootEntry *i;
+    size_t total = 0;
+    char *list = NULL;
+    MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
+    bool ignore_suffixes = mc->ignore_boot_device_suffixes;
+
+    QTAILQ_FOREACH(i, &fw_boot_order, link) {
+        char *bootpath;
+        size_t len;
+
+        bootpath = get_boot_device_path(i->dev, ignore_suffixes, i->suffix);
+
+        if (total) {
+            list[total-1] = '\n';
+        }
+        len = strlen(bootpath) + 1;
+        list = g_realloc(list, total + len);
+        memcpy(&list[total], bootpath, len);
+        total += len;
+        g_free(bootpath);
+    }
+
+    *size = total;
+
+    if (boot_strict && *size > 0) {
+        list[total-1] = '\n';
+        list = g_realloc(list, total + 5);
+        memcpy(&list[total], "HALT", 5);
+        *size = total + 5;
+    }
+    return list;
+}
+
+typedef struct {
+    int32_t *bootindex;
+    const char *suffix;
+    DeviceState *dev;
+} BootIndexProperty;
+
+static void device_get_bootindex(Object *obj, Visitor *v, const char *name,
+                                 void *opaque, Error **errp)
+{
+    BootIndexProperty *prop = opaque;
+    visit_type_int32(v, name, prop->bootindex, errp);
+}
+
+static void device_set_bootindex(Object *obj, Visitor *v, const char *name,
+                                 void *opaque, Error **errp)
+{
+    BootIndexProperty *prop = opaque;
+    int32_t boot_index;
+    Error *local_err = NULL;
+
+    if (!visit_type_int32(v, name, &boot_index, errp)) {
+        return;
+    }
+    /* check whether bootindex is present in fw_boot_order list  */
+    check_boot_index(boot_index, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+    /* change bootindex to a new one */
+    *prop->bootindex = boot_index;
+
+    add_boot_device_path(*prop->bootindex, prop->dev, prop->suffix);
+}
+
+static void property_release_bootindex(Object *obj, const char *name,
+                                       void *opaque)
+
+{
+    BootIndexProperty *prop = opaque;
+
+    del_boot_device_path(prop->dev, prop->suffix);
+    g_free(prop);
+}
+
+void device_add_bootindex_property(Object *obj, int32_t *bootindex,
+                                   const char *name, const char *suffix,
+                                   DeviceState *dev)
+{
+    BootIndexProperty *prop = g_malloc0(sizeof(*prop));
+
+    prop->bootindex = bootindex;
+    prop->suffix = suffix;
+    prop->dev = dev;
+
+    object_property_add(obj, name, "int32",
+                        device_get_bootindex,
+                        device_set_bootindex,
+                        property_release_bootindex,
+                        prop);
+
+    /* initialize devices' bootindex property to -1 */
+    object_property_set_int(obj, name, -1, NULL);
+}
+
+typedef struct FWLCHSEntry FWLCHSEntry;
+
+struct FWLCHSEntry {
+    QTAILQ_ENTRY(FWLCHSEntry) link;
+    DeviceState *dev;
+    char *suffix;
+    uint32_t lcyls;
+    uint32_t lheads;
+    uint32_t lsecs;
+};
+
+static QTAILQ_HEAD(, FWLCHSEntry) fw_lchs =
+    QTAILQ_HEAD_INITIALIZER(fw_lchs);
+
+void add_boot_device_lchs(DeviceState *dev, const char *suffix,
+                          uint32_t lcyls, uint32_t lheads, uint32_t lsecs)
+{
+    FWLCHSEntry *node;
+
+    if (!lcyls && !lheads && !lsecs) {
+        return;
+    }
+
+    assert(dev != NULL || suffix != NULL);
+
+    node = g_malloc0(sizeof(FWLCHSEntry));
+    node->suffix = g_strdup(suffix);
+    node->dev = dev;
+    node->lcyls = lcyls;
+    node->lheads = lheads;
+    node->lsecs = lsecs;
+
+    QTAILQ_INSERT_TAIL(&fw_lchs, node, link);
+}
+
+void del_boot_device_lchs(DeviceState *dev, const char *suffix)
+{
+    FWLCHSEntry *i;
+
+    if (dev == NULL) {
+        return;
+    }
+
+    QTAILQ_FOREACH(i, &fw_lchs, link) {
+        if ((!suffix || !g_strcmp0(i->suffix, suffix)) &&
+             i->dev == dev) {
+            QTAILQ_REMOVE(&fw_lchs, i, link);
+            g_free(i->suffix);
+            g_free(i);
+
+            break;
+        }
+    }
+}
+
+char *get_boot_devices_lchs_list(size_t *size)
+{
+    FWLCHSEntry *i;
+    size_t total = 0;
+    char *list = NULL;
+
+    QTAILQ_FOREACH(i, &fw_lchs, link) {
+        char *bootpath;
+        char *chs_string;
+        size_t len;
+
+        bootpath = get_boot_device_path(i->dev, false, i->suffix);
+        chs_string = g_strdup_printf("%s %" PRIu32 " %" PRIu32 " %" PRIu32,
+                                     bootpath, i->lcyls, i->lheads, i->lsecs);
+
+        if (total) {
+            list[total - 1] = '\n';
+        }
+        len = strlen(chs_string) + 1;
+        list = g_realloc(list, total + len);
+        memcpy(&list[total], chs_string, len);
+        total += len;
+        g_free(chs_string);
+        g_free(bootpath);
+    }
+
+    *size = total;
+
+    return list;
+}
diff --git a/softmmu/device_tree.c b/softmmu/device_tree.c
new file mode 100644
index 0000000..b335dae
--- /dev/null
+++ b/softmmu/device_tree.c
@@ -0,0 +1,579 @@
+/*
+ * Functions to help device tree manipulation using libfdt.
+ * It also provides functions to read entries from device tree proc
+ * interface.
+ *
+ * Copyright 2008 IBM Corporation.
+ * Authors: Jerone Young <jyoung5@us.ibm.com>
+ *          Hollis Blanchard <hollisb@us.ibm.com>
+ *
+ * This work is licensed under the GNU GPL license version 2 or later.
+ *
+ */
+
+#include "qemu/osdep.h"
+
+#ifdef CONFIG_LINUX
+#include <dirent.h>
+#endif
+
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/option.h"
+#include "qemu/bswap.h"
+#include "sysemu/device_tree.h"
+#include "sysemu/sysemu.h"
+#include "hw/loader.h"
+#include "hw/boards.h"
+#include "qemu/config-file.h"
+
+#include <libfdt.h>
+
+#define FDT_MAX_SIZE  0x100000
+
+void *create_device_tree(int *sizep)
+{
+    void *fdt;
+    int ret;
+
+    *sizep = FDT_MAX_SIZE;
+    fdt = g_malloc0(FDT_MAX_SIZE);
+    ret = fdt_create(fdt, FDT_MAX_SIZE);
+    if (ret < 0) {
+        goto fail;
+    }
+    ret = fdt_finish_reservemap(fdt);
+    if (ret < 0) {
+        goto fail;
+    }
+    ret = fdt_begin_node(fdt, "");
+    if (ret < 0) {
+        goto fail;
+    }
+    ret = fdt_end_node(fdt);
+    if (ret < 0) {
+        goto fail;
+    }
+    ret = fdt_finish(fdt);
+    if (ret < 0) {
+        goto fail;
+    }
+    ret = fdt_open_into(fdt, fdt, *sizep);
+    if (ret) {
+        error_report("Unable to copy device tree in memory");
+        exit(1);
+    }
+
+    return fdt;
+fail:
+    error_report("%s Couldn't create dt: %s", __func__, fdt_strerror(ret));
+    exit(1);
+}
+
+void *load_device_tree(const char *filename_path, int *sizep)
+{
+    int dt_size;
+    int dt_file_load_size;
+    int ret;
+    void *fdt = NULL;
+
+    *sizep = 0;
+    dt_size = get_image_size(filename_path);
+    if (dt_size < 0) {
+        error_report("Unable to get size of device tree file '%s'",
+                     filename_path);
+        goto fail;
+    }
+    if (dt_size > INT_MAX / 2 - 10000) {
+        error_report("Device tree file '%s' is too large", filename_path);
+        goto fail;
+    }
+
+    /* Expand to 2x size to give enough room for manipulation.  */
+    dt_size += 10000;
+    dt_size *= 2;
+    /* First allocate space in qemu for device tree */
+    fdt = g_malloc0(dt_size);
+
+    dt_file_load_size = load_image_size(filename_path, fdt, dt_size);
+    if (dt_file_load_size < 0) {
+        error_report("Unable to open device tree file '%s'",
+                     filename_path);
+        goto fail;
+    }
+
+    ret = fdt_open_into(fdt, fdt, dt_size);
+    if (ret) {
+        error_report("Unable to copy device tree in memory");
+        goto fail;
+    }
+
+    /* Check sanity of device tree */
+    if (fdt_check_header(fdt)) {
+        error_report("Device tree file loaded into memory is invalid: %s",
+                     filename_path);
+        goto fail;
+    }
+    *sizep = dt_size;
+    return fdt;
+
+fail:
+    g_free(fdt);
+    return NULL;
+}
+
+#ifdef CONFIG_LINUX
+
+#define SYSFS_DT_BASEDIR "/proc/device-tree"
+
+/**
+ * read_fstree: this function is inspired from dtc read_fstree
+ * @fdt: preallocated fdt blob buffer, to be populated
+ * @dirname: directory to scan under SYSFS_DT_BASEDIR
+ * the search is recursive and the tree is searched down to the
+ * leaves (property files).
+ *
+ * the function asserts in case of error
+ */
+static void read_fstree(void *fdt, const char *dirname)
+{
+    DIR *d;
+    struct dirent *de;
+    struct stat st;
+    const char *root_dir = SYSFS_DT_BASEDIR;
+    const char *parent_node;
+
+    if (strstr(dirname, root_dir) != dirname) {
+        error_report("%s: %s must be searched within %s",
+                     __func__, dirname, root_dir);
+        exit(1);
+    }
+    parent_node = &dirname[strlen(SYSFS_DT_BASEDIR)];
+
+    d = opendir(dirname);
+    if (!d) {
+        error_report("%s cannot open %s", __func__, dirname);
+        exit(1);
+    }
+
+    while ((de = readdir(d)) != NULL) {
+        char *tmpnam;
+
+        if (!g_strcmp0(de->d_name, ".")
+            || !g_strcmp0(de->d_name, "..")) {
+            continue;
+        }
+
+        tmpnam = g_strdup_printf("%s/%s", dirname, de->d_name);
+
+        if (lstat(tmpnam, &st) < 0) {
+            error_report("%s cannot lstat %s", __func__, tmpnam);
+            exit(1);
+        }
+
+        if (S_ISREG(st.st_mode)) {
+            gchar *val;
+            gsize len;
+
+            if (!g_file_get_contents(tmpnam, &val, &len, NULL)) {
+                error_report("%s not able to extract info from %s",
+                             __func__, tmpnam);
+                exit(1);
+            }
+
+            if (strlen(parent_node) > 0) {
+                qemu_fdt_setprop(fdt, parent_node,
+                                 de->d_name, val, len);
+            } else {
+                qemu_fdt_setprop(fdt, "/", de->d_name, val, len);
+            }
+            g_free(val);
+        } else if (S_ISDIR(st.st_mode)) {
+            char *node_name;
+
+            node_name = g_strdup_printf("%s/%s",
+                                        parent_node, de->d_name);
+            qemu_fdt_add_subnode(fdt, node_name);
+            g_free(node_name);
+            read_fstree(fdt, tmpnam);
+        }
+
+        g_free(tmpnam);
+    }
+
+    closedir(d);
+}
+
+/* load_device_tree_from_sysfs: extract the dt blob from host sysfs */
+void *load_device_tree_from_sysfs(void)
+{
+    void *host_fdt;
+    int host_fdt_size;
+
+    host_fdt = create_device_tree(&host_fdt_size);
+    read_fstree(host_fdt, SYSFS_DT_BASEDIR);
+    if (fdt_check_header(host_fdt)) {
+        error_report("%s host device tree extracted into memory is invalid",
+                     __func__);
+        exit(1);
+    }
+    return host_fdt;
+}
+
+#endif /* CONFIG_LINUX */
+
+static int findnode_nofail(void *fdt, const char *node_path)
+{
+    int offset;
+
+    offset = fdt_path_offset(fdt, node_path);
+    if (offset < 0) {
+        error_report("%s Couldn't find node %s: %s", __func__, node_path,
+                     fdt_strerror(offset));
+        exit(1);
+    }
+
+    return offset;
+}
+
+char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp)
+{
+    char *prefix =  g_strdup_printf("%s@", name);
+    unsigned int path_len = 16, n = 0;
+    GSList *path_list = NULL, *iter;
+    const char *iter_name;
+    int offset, len, ret;
+    char **path_array;
+
+    offset = fdt_next_node(fdt, -1, NULL);
+
+    while (offset >= 0) {
+        iter_name = fdt_get_name(fdt, offset, &len);
+        if (!iter_name) {
+            offset = len;
+            break;
+        }
+        if (!strcmp(iter_name, name) || g_str_has_prefix(iter_name, prefix)) {
+            char *path;
+
+            path = g_malloc(path_len);
+            while ((ret = fdt_get_path(fdt, offset, path, path_len))
+                  == -FDT_ERR_NOSPACE) {
+                path_len += 16;
+                path = g_realloc(path, path_len);
+            }
+            path_list = g_slist_prepend(path_list, path);
+            n++;
+        }
+        offset = fdt_next_node(fdt, offset, NULL);
+    }
+    g_free(prefix);
+
+    if (offset < 0 && offset != -FDT_ERR_NOTFOUND) {
+        error_setg(errp, "%s: abort parsing dt for %s node units: %s",
+                   __func__, name, fdt_strerror(offset));
+        for (iter = path_list; iter; iter = iter->next) {
+            g_free(iter->data);
+        }
+        g_slist_free(path_list);
+        return NULL;
+    }
+
+    path_array = g_new(char *, n + 1);
+    path_array[n--] = NULL;
+
+    for (iter = path_list; iter; iter = iter->next) {
+        path_array[n--] = iter->data;
+    }
+
+    g_slist_free(path_list);
+
+    return path_array;
+}
+
+char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat,
+                          Error **errp)
+{
+    int offset, len, ret;
+    const char *iter_name;
+    unsigned int path_len = 16, n = 0;
+    GSList *path_list = NULL, *iter;
+    char **path_array;
+
+    offset = fdt_node_offset_by_compatible(fdt, -1, compat);
+
+    while (offset >= 0) {
+        iter_name = fdt_get_name(fdt, offset, &len);
+        if (!iter_name) {
+            offset = len;
+            break;
+        }
+        if (!name || !strcmp(iter_name, name)) {
+            char *path;
+
+            path = g_malloc(path_len);
+            while ((ret = fdt_get_path(fdt, offset, path, path_len))
+                  == -FDT_ERR_NOSPACE) {
+                path_len += 16;
+                path = g_realloc(path, path_len);
+            }
+            path_list = g_slist_prepend(path_list, path);
+            n++;
+        }
+        offset = fdt_node_offset_by_compatible(fdt, offset, compat);
+    }
+
+    if (offset < 0 && offset != -FDT_ERR_NOTFOUND) {
+        error_setg(errp, "%s: abort parsing dt for %s/%s: %s",
+                   __func__, name, compat, fdt_strerror(offset));
+        for (iter = path_list; iter; iter = iter->next) {
+            g_free(iter->data);
+        }
+        g_slist_free(path_list);
+        return NULL;
+    }
+
+    path_array = g_new(char *, n + 1);
+    path_array[n--] = NULL;
+
+    for (iter = path_list; iter; iter = iter->next) {
+        path_array[n--] = iter->data;
+    }
+
+    g_slist_free(path_list);
+
+    return path_array;
+}
+
+int qemu_fdt_setprop(void *fdt, const char *node_path,
+                     const char *property, const void *val, int size)
+{
+    int r;
+
+    r = fdt_setprop(fdt, findnode_nofail(fdt, node_path), property, val, size);
+    if (r < 0) {
+        error_report("%s: Couldn't set %s/%s: %s", __func__, node_path,
+                     property, fdt_strerror(r));
+        exit(1);
+    }
+
+    return r;
+}
+
+int qemu_fdt_setprop_cell(void *fdt, const char *node_path,
+                          const char *property, uint32_t val)
+{
+    int r;
+
+    r = fdt_setprop_cell(fdt, findnode_nofail(fdt, node_path), property, val);
+    if (r < 0) {
+        error_report("%s: Couldn't set %s/%s = %#08x: %s", __func__,
+                     node_path, property, val, fdt_strerror(r));
+        exit(1);
+    }
+
+    return r;
+}
+
+int qemu_fdt_setprop_u64(void *fdt, const char *node_path,
+                         const char *property, uint64_t val)
+{
+    val = cpu_to_be64(val);
+    return qemu_fdt_setprop(fdt, node_path, property, &val, sizeof(val));
+}
+
+int qemu_fdt_setprop_string(void *fdt, const char *node_path,
+                            const char *property, const char *string)
+{
+    int r;
+
+    r = fdt_setprop_string(fdt, findnode_nofail(fdt, node_path), property, string);
+    if (r < 0) {
+        error_report("%s: Couldn't set %s/%s = %s: %s", __func__,
+                     node_path, property, string, fdt_strerror(r));
+        exit(1);
+    }
+
+    return r;
+}
+
+const void *qemu_fdt_getprop(void *fdt, const char *node_path,
+                             const char *property, int *lenp, Error **errp)
+{
+    int len;
+    const void *r;
+
+    if (!lenp) {
+        lenp = &len;
+    }
+    r = fdt_getprop(fdt, findnode_nofail(fdt, node_path), property, lenp);
+    if (!r) {
+        error_setg(errp, "%s: Couldn't get %s/%s: %s", __func__,
+                  node_path, property, fdt_strerror(*lenp));
+    }
+    return r;
+}
+
+uint32_t qemu_fdt_getprop_cell(void *fdt, const char *node_path,
+                               const char *property, int *lenp, Error **errp)
+{
+    int len;
+    const uint32_t *p;
+
+    if (!lenp) {
+        lenp = &len;
+    }
+    p = qemu_fdt_getprop(fdt, node_path, property, lenp, errp);
+    if (!p) {
+        return 0;
+    } else if (*lenp != 4) {
+        error_setg(errp, "%s: %s/%s not 4 bytes long (not a cell?)",
+                   __func__, node_path, property);
+        *lenp = -EINVAL;
+        return 0;
+    }
+    return be32_to_cpu(*p);
+}
+
+uint32_t qemu_fdt_get_phandle(void *fdt, const char *path)
+{
+    uint32_t r;
+
+    r = fdt_get_phandle(fdt, findnode_nofail(fdt, path));
+    if (r == 0) {
+        error_report("%s: Couldn't get phandle for %s: %s", __func__,
+                     path, fdt_strerror(r));
+        exit(1);
+    }
+
+    return r;
+}
+
+int qemu_fdt_setprop_phandle(void *fdt, const char *node_path,
+                             const char *property,
+                             const char *target_node_path)
+{
+    uint32_t phandle = qemu_fdt_get_phandle(fdt, target_node_path);
+    return qemu_fdt_setprop_cell(fdt, node_path, property, phandle);
+}
+
+uint32_t qemu_fdt_alloc_phandle(void *fdt)
+{
+    static int phandle = 0x0;
+
+    /*
+     * We need to find out if the user gave us special instruction at
+     * which phandle id to start allocating phandles.
+     */
+    if (!phandle) {
+        phandle = machine_phandle_start(current_machine);
+    }
+
+    if (!phandle) {
+        /*
+         * None or invalid phandle given on the command line, so fall back to
+         * default starting point.
+         */
+        phandle = 0x8000;
+    }
+
+    return phandle++;
+}
+
+int qemu_fdt_nop_node(void *fdt, const char *node_path)
+{
+    int r;
+
+    r = fdt_nop_node(fdt, findnode_nofail(fdt, node_path));
+    if (r < 0) {
+        error_report("%s: Couldn't nop node %s: %s", __func__, node_path,
+                     fdt_strerror(r));
+        exit(1);
+    }
+
+    return r;
+}
+
+int qemu_fdt_add_subnode(void *fdt, const char *name)
+{
+    char *dupname = g_strdup(name);
+    char *basename = strrchr(dupname, '/');
+    int retval;
+    int parent = 0;
+
+    if (!basename) {
+        g_free(dupname);
+        return -1;
+    }
+
+    basename[0] = '\0';
+    basename++;
+
+    if (dupname[0]) {
+        parent = findnode_nofail(fdt, dupname);
+    }
+
+    retval = fdt_add_subnode(fdt, parent, basename);
+    if (retval < 0) {
+        error_report("FDT: Failed to create subnode %s: %s", name,
+                     fdt_strerror(retval));
+        exit(1);
+    }
+
+    g_free(dupname);
+    return retval;
+}
+
+void qemu_fdt_dumpdtb(void *fdt, int size)
+{
+    const char *dumpdtb = qemu_opt_get(qemu_get_machine_opts(), "dumpdtb");
+
+    if (dumpdtb) {
+        /* Dump the dtb to a file and quit */
+        if (g_file_set_contents(dumpdtb, fdt, size, NULL)) {
+            info_report("dtb dumped to %s. Exiting.", dumpdtb);
+            exit(0);
+        }
+        error_report("%s: Failed dumping dtb to %s", __func__, dumpdtb);
+        exit(1);
+    }
+}
+
+int qemu_fdt_setprop_sized_cells_from_array(void *fdt,
+                                            const char *node_path,
+                                            const char *property,
+                                            int numvalues,
+                                            uint64_t *values)
+{
+    uint32_t *propcells;
+    uint64_t value;
+    int cellnum, vnum, ncells;
+    uint32_t hival;
+    int ret;
+
+    propcells = g_new0(uint32_t, numvalues * 2);
+
+    cellnum = 0;
+    for (vnum = 0; vnum < numvalues; vnum++) {
+        ncells = values[vnum * 2];
+        if (ncells != 1 && ncells != 2) {
+            ret = -1;
+            goto out;
+        }
+        value = values[vnum * 2 + 1];
+        hival = cpu_to_be32(value >> 32);
+        if (ncells > 1) {
+            propcells[cellnum++] = hival;
+        } else if (hival != 0) {
+            ret = -1;
+            goto out;
+        }
+        propcells[cellnum++] = cpu_to_be32(value);
+    }
+
+    ret = qemu_fdt_setprop(fdt, node_path, property, propcells,
+                           cellnum * sizeof(uint32_t));
+out:
+    g_free(propcells);
+    return ret;
+}
diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c
new file mode 100644
index 0000000..03c92e0
--- /dev/null
+++ b/softmmu/dma-helpers.c
@@ -0,0 +1,331 @@
+/*
+ * DMA helper functions
+ *
+ * Copyright (c) 2009 Red Hat
+ *
+ * This work is licensed under the terms of the GNU General Public License
+ * (GNU GPL), version 2 or later.
+ */
+
+#include "qemu/osdep.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/dma.h"
+#include "trace/trace-root.h"
+#include "qemu/thread.h"
+#include "qemu/main-loop.h"
+#include "sysemu/cpu-timers.h"
+#include "qemu/range.h"
+
+/* #define DEBUG_IOMMU */
+
+int dma_memory_set(AddressSpace *as, dma_addr_t addr, uint8_t c, dma_addr_t len)
+{
+    dma_barrier(as, DMA_DIRECTION_FROM_DEVICE);
+
+#define FILLBUF_SIZE 512
+    uint8_t fillbuf[FILLBUF_SIZE];
+    int l;
+    bool error = false;
+
+    memset(fillbuf, c, FILLBUF_SIZE);
+    while (len > 0) {
+        l = len < FILLBUF_SIZE ? len : FILLBUF_SIZE;
+        error |= address_space_write(as, addr, MEMTXATTRS_UNSPECIFIED,
+                                     fillbuf, l);
+        len -= l;
+        addr += l;
+    }
+
+    return error;
+}
+
+void qemu_sglist_init(QEMUSGList *qsg, DeviceState *dev, int alloc_hint,
+                      AddressSpace *as)
+{
+    qsg->sg = g_malloc(alloc_hint * sizeof(ScatterGatherEntry));
+    qsg->nsg = 0;
+    qsg->nalloc = alloc_hint;
+    qsg->size = 0;
+    qsg->as = as;
+    qsg->dev = dev;
+    object_ref(OBJECT(dev));
+}
+
+void qemu_sglist_add(QEMUSGList *qsg, dma_addr_t base, dma_addr_t len)
+{
+    if (qsg->nsg == qsg->nalloc) {
+        qsg->nalloc = 2 * qsg->nalloc + 1;
+        qsg->sg = g_realloc(qsg->sg, qsg->nalloc * sizeof(ScatterGatherEntry));
+    }
+    qsg->sg[qsg->nsg].base = base;
+    qsg->sg[qsg->nsg].len = len;
+    qsg->size += len;
+    ++qsg->nsg;
+}
+
+void qemu_sglist_destroy(QEMUSGList *qsg)
+{
+    object_unref(OBJECT(qsg->dev));
+    g_free(qsg->sg);
+    memset(qsg, 0, sizeof(*qsg));
+}
+
+typedef struct {
+    BlockAIOCB common;
+    AioContext *ctx;
+    BlockAIOCB *acb;
+    QEMUSGList *sg;
+    uint32_t align;
+    uint64_t offset;
+    DMADirection dir;
+    int sg_cur_index;
+    dma_addr_t sg_cur_byte;
+    QEMUIOVector iov;
+    QEMUBH *bh;
+    DMAIOFunc *io_func;
+    void *io_func_opaque;
+} DMAAIOCB;
+
+static void dma_blk_cb(void *opaque, int ret);
+
+static void reschedule_dma(void *opaque)
+{
+    DMAAIOCB *dbs = (DMAAIOCB *)opaque;
+
+    assert(!dbs->acb && dbs->bh);
+    qemu_bh_delete(dbs->bh);
+    dbs->bh = NULL;
+    dma_blk_cb(dbs, 0);
+}
+
+static void dma_blk_unmap(DMAAIOCB *dbs)
+{
+    int i;
+
+    for (i = 0; i < dbs->iov.niov; ++i) {
+        dma_memory_unmap(dbs->sg->as, dbs->iov.iov[i].iov_base,
+                         dbs->iov.iov[i].iov_len, dbs->dir,
+                         dbs->iov.iov[i].iov_len);
+    }
+    qemu_iovec_reset(&dbs->iov);
+}
+
+static void dma_complete(DMAAIOCB *dbs, int ret)
+{
+    trace_dma_complete(dbs, ret, dbs->common.cb);
+
+    assert(!dbs->acb && !dbs->bh);
+    dma_blk_unmap(dbs);
+    if (dbs->common.cb) {
+        dbs->common.cb(dbs->common.opaque, ret);
+    }
+    qemu_iovec_destroy(&dbs->iov);
+    qemu_aio_unref(dbs);
+}
+
+static void dma_blk_cb(void *opaque, int ret)
+{
+    DMAAIOCB *dbs = (DMAAIOCB *)opaque;
+    dma_addr_t cur_addr, cur_len;
+    void *mem;
+
+    trace_dma_blk_cb(dbs, ret);
+
+    dbs->acb = NULL;
+    dbs->offset += dbs->iov.size;
+
+    if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) {
+        dma_complete(dbs, ret);
+        return;
+    }
+    dma_blk_unmap(dbs);
+
+    while (dbs->sg_cur_index < dbs->sg->nsg) {
+        cur_addr = dbs->sg->sg[dbs->sg_cur_index].base + dbs->sg_cur_byte;
+        cur_len = dbs->sg->sg[dbs->sg_cur_index].len - dbs->sg_cur_byte;
+        mem = dma_memory_map(dbs->sg->as, cur_addr, &cur_len, dbs->dir);
+        /*
+         * Make reads deterministic in icount mode. Windows sometimes issues
+         * disk read requests with overlapping SGs. It leads
+         * to non-determinism, because resulting buffer contents may be mixed
+         * from several sectors. This code splits all SGs into several
+         * groups. SGs in every group do not overlap.
+         */
+        if (mem && icount_enabled() && dbs->dir == DMA_DIRECTION_FROM_DEVICE) {
+            int i;
+            for (i = 0 ; i < dbs->iov.niov ; ++i) {
+                if (ranges_overlap((intptr_t)dbs->iov.iov[i].iov_base,
+                                   dbs->iov.iov[i].iov_len, (intptr_t)mem,
+                                   cur_len)) {
+                    dma_memory_unmap(dbs->sg->as, mem, cur_len,
+                                     dbs->dir, cur_len);
+                    mem = NULL;
+                    break;
+                }
+            }
+        }
+        if (!mem)
+            break;
+        qemu_iovec_add(&dbs->iov, mem, cur_len);
+        dbs->sg_cur_byte += cur_len;
+        if (dbs->sg_cur_byte == dbs->sg->sg[dbs->sg_cur_index].len) {
+            dbs->sg_cur_byte = 0;
+            ++dbs->sg_cur_index;
+        }
+    }
+
+    if (dbs->iov.size == 0) {
+        trace_dma_map_wait(dbs);
+        dbs->bh = aio_bh_new(dbs->ctx, reschedule_dma, dbs);
+        cpu_register_map_client(dbs->bh);
+        return;
+    }
+
+    if (!QEMU_IS_ALIGNED(dbs->iov.size, dbs->align)) {
+        qemu_iovec_discard_back(&dbs->iov,
+                                QEMU_ALIGN_DOWN(dbs->iov.size, dbs->align));
+    }
+
+    aio_context_acquire(dbs->ctx);
+    dbs->acb = dbs->io_func(dbs->offset, &dbs->iov,
+                            dma_blk_cb, dbs, dbs->io_func_opaque);
+    aio_context_release(dbs->ctx);
+    assert(dbs->acb);
+}
+
+static void dma_aio_cancel(BlockAIOCB *acb)
+{
+    DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);
+
+    trace_dma_aio_cancel(dbs);
+
+    assert(!(dbs->acb && dbs->bh));
+    if (dbs->acb) {
+        /* This will invoke dma_blk_cb.  */
+        blk_aio_cancel_async(dbs->acb);
+        return;
+    }
+
+    if (dbs->bh) {
+        cpu_unregister_map_client(dbs->bh);
+        qemu_bh_delete(dbs->bh);
+        dbs->bh = NULL;
+    }
+    if (dbs->common.cb) {
+        dbs->common.cb(dbs->common.opaque, -ECANCELED);
+    }
+}
+
+static AioContext *dma_get_aio_context(BlockAIOCB *acb)
+{
+    DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common);
+
+    return dbs->ctx;
+}
+
+static const AIOCBInfo dma_aiocb_info = {
+    .aiocb_size         = sizeof(DMAAIOCB),
+    .cancel_async       = dma_aio_cancel,
+    .get_aio_context    = dma_get_aio_context,
+};
+
+BlockAIOCB *dma_blk_io(AioContext *ctx,
+    QEMUSGList *sg, uint64_t offset, uint32_t align,
+    DMAIOFunc *io_func, void *io_func_opaque,
+    BlockCompletionFunc *cb,
+    void *opaque, DMADirection dir)
+{
+    DMAAIOCB *dbs = qemu_aio_get(&dma_aiocb_info, NULL, cb, opaque);
+
+    trace_dma_blk_io(dbs, io_func_opaque, offset, (dir == DMA_DIRECTION_TO_DEVICE));
+
+    dbs->acb = NULL;
+    dbs->sg = sg;
+    dbs->ctx = ctx;
+    dbs->offset = offset;
+    dbs->align = align;
+    dbs->sg_cur_index = 0;
+    dbs->sg_cur_byte = 0;
+    dbs->dir = dir;
+    dbs->io_func = io_func;
+    dbs->io_func_opaque = io_func_opaque;
+    dbs->bh = NULL;
+    qemu_iovec_init(&dbs->iov, sg->nsg);
+    dma_blk_cb(dbs, 0);
+    return &dbs->common;
+}
+
+
+static
+BlockAIOCB *dma_blk_read_io_func(int64_t offset, QEMUIOVector *iov,
+                                 BlockCompletionFunc *cb, void *cb_opaque,
+                                 void *opaque)
+{
+    BlockBackend *blk = opaque;
+    return blk_aio_preadv(blk, offset, iov, 0, cb, cb_opaque);
+}
+
+BlockAIOCB *dma_blk_read(BlockBackend *blk,
+                         QEMUSGList *sg, uint64_t offset, uint32_t align,
+                         void (*cb)(void *opaque, int ret), void *opaque)
+{
+    return dma_blk_io(blk_get_aio_context(blk), sg, offset, align,
+                      dma_blk_read_io_func, blk, cb, opaque,
+                      DMA_DIRECTION_FROM_DEVICE);
+}
+
+static
+BlockAIOCB *dma_blk_write_io_func(int64_t offset, QEMUIOVector *iov,
+                                  BlockCompletionFunc *cb, void *cb_opaque,
+                                  void *opaque)
+{
+    BlockBackend *blk = opaque;
+    return blk_aio_pwritev(blk, offset, iov, 0, cb, cb_opaque);
+}
+
+BlockAIOCB *dma_blk_write(BlockBackend *blk,
+                          QEMUSGList *sg, uint64_t offset, uint32_t align,
+                          void (*cb)(void *opaque, int ret), void *opaque)
+{
+    return dma_blk_io(blk_get_aio_context(blk), sg, offset, align,
+                      dma_blk_write_io_func, blk, cb, opaque,
+                      DMA_DIRECTION_TO_DEVICE);
+}
+
+
+static uint64_t dma_buf_rw(uint8_t *ptr, int32_t len, QEMUSGList *sg,
+                           DMADirection dir)
+{
+    uint64_t resid;
+    int sg_cur_index;
+
+    resid = sg->size;
+    sg_cur_index = 0;
+    len = MIN(len, resid);
+    while (len > 0) {
+        ScatterGatherEntry entry = sg->sg[sg_cur_index++];
+        int32_t xfer = MIN(len, entry.len);
+        dma_memory_rw(sg->as, entry.base, ptr, xfer, dir);
+        ptr += xfer;
+        len -= xfer;
+        resid -= xfer;
+    }
+
+    return resid;
+}
+
+uint64_t dma_buf_read(uint8_t *ptr, int32_t len, QEMUSGList *sg)
+{
+    return dma_buf_rw(ptr, len, sg, DMA_DIRECTION_FROM_DEVICE);
+}
+
+uint64_t dma_buf_write(uint8_t *ptr, int32_t len, QEMUSGList *sg)
+{
+    return dma_buf_rw(ptr, len, sg, DMA_DIRECTION_TO_DEVICE);
+}
+
+void dma_acct_start(BlockBackend *blk, BlockAcctCookie *cookie,
+                    QEMUSGList *sg, enum BlockAcctType type)
+{
+    block_acct_start(blk_get_stats(blk), cookie, sg->size, type);
+}
diff --git a/softmmu/meson.build b/softmmu/meson.build
index 36c96e7..8f7210b 100644
--- a/softmmu/meson.build
+++ b/softmmu/meson.build
@@ -3,6 +3,7 @@ specific_ss.add(when: 'CONFIG_SOFTMMU', if_true: [files(
   'balloon.c',
   'cpus.c',
   'cpu-throttle.c',
+  'physmem.c',
   'ioport.c',
   'memory.c',
   'memory_mapping.c',
@@ -14,3 +15,13 @@ specific_ss.add(when: 'CONFIG_SOFTMMU', if_true: [files(
 specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: [files(
   'icount.c'
 )])
+
+softmmu_ss.add(files(
+  'bootdevice.c',
+  'dma-helpers.c',
+  'qdev-monitor.c',
+), sdl, libpmem, libdaxctl)
+
+softmmu_ss.add(when: 'CONFIG_TPM', if_true: files('tpm.c'))
+softmmu_ss.add(when: 'CONFIG_SECCOMP', if_true: [files('qemu-seccomp.c'), seccomp])
+softmmu_ss.add(when: fdt, if_true: files('device_tree.c'))
diff --git a/softmmu/physmem.c b/softmmu/physmem.c
new file mode 100644
index 0000000..e319fb2
--- /dev/null
+++ b/softmmu/physmem.c
@@ -0,0 +1,3711 @@
+/*
+ * RAM allocation and memory access
+ *
+ *  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 "qemu/osdep.h"
+#include "qemu-common.h"
+#include "qapi/error.h"
+
+#include "qemu/cutils.h"
+#include "cpu.h"
+#include "exec/exec-all.h"
+#include "exec/target_page.h"
+#include "tcg/tcg.h"
+#include "hw/qdev-core.h"
+#include "hw/qdev-properties.h"
+#include "hw/boards.h"
+#include "hw/xen/xen.h"
+#include "sysemu/kvm.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/tcg.h"
+#include "sysemu/qtest.h"
+#include "qemu/timer.h"
+#include "qemu/config-file.h"
+#include "qemu/error-report.h"
+#include "qemu/qemu-print.h"
+#include "exec/memory.h"
+#include "exec/ioport.h"
+#include "sysemu/dma.h"
+#include "sysemu/hostmem.h"
+#include "sysemu/hw_accel.h"
+#include "exec/address-spaces.h"
+#include "sysemu/xen-mapcache.h"
+#include "trace/trace-root.h"
+
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+#include <linux/falloc.h>
+#endif
+
+#include "qemu/rcu_queue.h"
+#include "qemu/main-loop.h"
+#include "translate-all.h"
+#include "sysemu/replay.h"
+
+#include "exec/memory-internal.h"
+#include "exec/ram_addr.h"
+#include "exec/log.h"
+
+#include "qemu/pmem.h"
+
+#include "migration/vmstate.h"
+
+#include "qemu/range.h"
+#ifndef _WIN32
+#include "qemu/mmap-alloc.h"
+#endif
+
+#include "monitor/monitor.h"
+
+#ifdef CONFIG_LIBDAXCTL
+#include <daxctl/libdaxctl.h>
+#endif
+
+//#define DEBUG_SUBPAGE
+
+/* ram_list is read under rcu_read_lock()/rcu_read_unlock().  Writes
+ * are protected by the ramlist lock.
+ */
+RAMList ram_list = { .blocks = QLIST_HEAD_INITIALIZER(ram_list.blocks) };
+
+static MemoryRegion *system_memory;
+static MemoryRegion *system_io;
+
+AddressSpace address_space_io;
+AddressSpace address_space_memory;
+
+static MemoryRegion io_mem_unassigned;
+
+typedef struct PhysPageEntry PhysPageEntry;
+
+struct PhysPageEntry {
+    /* How many bits skip to next level (in units of L2_SIZE). 0 for a leaf. */
+    uint32_t skip : 6;
+     /* index into phys_sections (!skip) or phys_map_nodes (skip) */
+    uint32_t ptr : 26;
+};
+
+#define PHYS_MAP_NODE_NIL (((uint32_t)~0) >> 6)
+
+/* Size of the L2 (and L3, etc) page tables.  */
+#define ADDR_SPACE_BITS 64
+
+#define P_L2_BITS 9
+#define P_L2_SIZE (1 << P_L2_BITS)
+
+#define P_L2_LEVELS (((ADDR_SPACE_BITS - TARGET_PAGE_BITS - 1) / P_L2_BITS) + 1)
+
+typedef PhysPageEntry Node[P_L2_SIZE];
+
+typedef struct PhysPageMap {
+    struct rcu_head rcu;
+
+    unsigned sections_nb;
+    unsigned sections_nb_alloc;
+    unsigned nodes_nb;
+    unsigned nodes_nb_alloc;
+    Node *nodes;
+    MemoryRegionSection *sections;
+} PhysPageMap;
+
+struct AddressSpaceDispatch {
+    MemoryRegionSection *mru_section;
+    /* This is a multi-level map on the physical address space.
+     * The bottom level has pointers to MemoryRegionSections.
+     */
+    PhysPageEntry phys_map;
+    PhysPageMap map;
+};
+
+#define SUBPAGE_IDX(addr) ((addr) & ~TARGET_PAGE_MASK)
+typedef struct subpage_t {
+    MemoryRegion iomem;
+    FlatView *fv;
+    hwaddr base;
+    uint16_t sub_section[];
+} subpage_t;
+
+#define PHYS_SECTION_UNASSIGNED 0
+
+static void io_mem_init(void);
+static void memory_map_init(void);
+static void tcg_log_global_after_sync(MemoryListener *listener);
+static void tcg_commit(MemoryListener *listener);
+
+/**
+ * CPUAddressSpace: all the information a CPU needs about an AddressSpace
+ * @cpu: the CPU whose AddressSpace this is
+ * @as: the AddressSpace itself
+ * @memory_dispatch: its dispatch pointer (cached, RCU protected)
+ * @tcg_as_listener: listener for tracking changes to the AddressSpace
+ */
+struct CPUAddressSpace {
+    CPUState *cpu;
+    AddressSpace *as;
+    struct AddressSpaceDispatch *memory_dispatch;
+    MemoryListener tcg_as_listener;
+};
+
+struct DirtyBitmapSnapshot {
+    ram_addr_t start;
+    ram_addr_t end;
+    unsigned long dirty[];
+};
+
+static void phys_map_node_reserve(PhysPageMap *map, unsigned nodes)
+{
+    static unsigned alloc_hint = 16;
+    if (map->nodes_nb + nodes > map->nodes_nb_alloc) {
+        map->nodes_nb_alloc = MAX(alloc_hint, map->nodes_nb + nodes);
+        map->nodes = g_renew(Node, map->nodes, map->nodes_nb_alloc);
+        alloc_hint = map->nodes_nb_alloc;
+    }
+}
+
+static uint32_t phys_map_node_alloc(PhysPageMap *map, bool leaf)
+{
+    unsigned i;
+    uint32_t ret;
+    PhysPageEntry e;
+    PhysPageEntry *p;
+
+    ret = map->nodes_nb++;
+    p = map->nodes[ret];
+    assert(ret != PHYS_MAP_NODE_NIL);
+    assert(ret != map->nodes_nb_alloc);
+
+    e.skip = leaf ? 0 : 1;
+    e.ptr = leaf ? PHYS_SECTION_UNASSIGNED : PHYS_MAP_NODE_NIL;
+    for (i = 0; i < P_L2_SIZE; ++i) {
+        memcpy(&p[i], &e, sizeof(e));
+    }
+    return ret;
+}
+
+static void phys_page_set_level(PhysPageMap *map, PhysPageEntry *lp,
+                                hwaddr *index, uint64_t *nb, uint16_t leaf,
+                                int level)
+{
+    PhysPageEntry *p;
+    hwaddr step = (hwaddr)1 << (level * P_L2_BITS);
+
+    if (lp->skip && lp->ptr == PHYS_MAP_NODE_NIL) {
+        lp->ptr = phys_map_node_alloc(map, level == 0);
+    }
+    p = map->nodes[lp->ptr];
+    lp = &p[(*index >> (level * P_L2_BITS)) & (P_L2_SIZE - 1)];
+
+    while (*nb && lp < &p[P_L2_SIZE]) {
+        if ((*index & (step - 1)) == 0 && *nb >= step) {
+            lp->skip = 0;
+            lp->ptr = leaf;
+            *index += step;
+            *nb -= step;
+        } else {
+            phys_page_set_level(map, lp, index, nb, leaf, level - 1);
+        }
+        ++lp;
+    }
+}
+
+static void phys_page_set(AddressSpaceDispatch *d,
+                          hwaddr index, uint64_t nb,
+                          uint16_t leaf)
+{
+    /* Wildly overreserve - it doesn't matter much. */
+    phys_map_node_reserve(&d->map, 3 * P_L2_LEVELS);
+
+    phys_page_set_level(&d->map, &d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
+}
+
+/* Compact a non leaf page entry. Simply detect that the entry has a single child,
+ * and update our entry so we can skip it and go directly to the destination.
+ */
+static void phys_page_compact(PhysPageEntry *lp, Node *nodes)
+{
+    unsigned valid_ptr = P_L2_SIZE;
+    int valid = 0;
+    PhysPageEntry *p;
+    int i;
+
+    if (lp->ptr == PHYS_MAP_NODE_NIL) {
+        return;
+    }
+
+    p = nodes[lp->ptr];
+    for (i = 0; i < P_L2_SIZE; i++) {
+        if (p[i].ptr == PHYS_MAP_NODE_NIL) {
+            continue;
+        }
+
+        valid_ptr = i;
+        valid++;
+        if (p[i].skip) {
+            phys_page_compact(&p[i], nodes);
+        }
+    }
+
+    /* We can only compress if there's only one child. */
+    if (valid != 1) {
+        return;
+    }
+
+    assert(valid_ptr < P_L2_SIZE);
+
+    /* Don't compress if it won't fit in the # of bits we have. */
+    if (P_L2_LEVELS >= (1 << 6) &&
+        lp->skip + p[valid_ptr].skip >= (1 << 6)) {
+        return;
+    }
+
+    lp->ptr = p[valid_ptr].ptr;
+    if (!p[valid_ptr].skip) {
+        /* If our only child is a leaf, make this a leaf. */
+        /* By design, we should have made this node a leaf to begin with so we
+         * should never reach here.
+         * But since it's so simple to handle this, let's do it just in case we
+         * change this rule.
+         */
+        lp->skip = 0;
+    } else {
+        lp->skip += p[valid_ptr].skip;
+    }
+}
+
+void address_space_dispatch_compact(AddressSpaceDispatch *d)
+{
+    if (d->phys_map.skip) {
+        phys_page_compact(&d->phys_map, d->map.nodes);
+    }
+}
+
+static inline bool section_covers_addr(const MemoryRegionSection *section,
+                                       hwaddr addr)
+{
+    /* Memory topology clips a memory region to [0, 2^64); size.hi > 0 means
+     * the section must cover the entire address space.
+     */
+    return int128_gethi(section->size) ||
+           range_covers_byte(section->offset_within_address_space,
+                             int128_getlo(section->size), addr);
+}
+
+static MemoryRegionSection *phys_page_find(AddressSpaceDispatch *d, hwaddr addr)
+{
+    PhysPageEntry lp = d->phys_map, *p;
+    Node *nodes = d->map.nodes;
+    MemoryRegionSection *sections = d->map.sections;
+    hwaddr index = addr >> TARGET_PAGE_BITS;
+    int i;
+
+    for (i = P_L2_LEVELS; lp.skip && (i -= lp.skip) >= 0;) {
+        if (lp.ptr == PHYS_MAP_NODE_NIL) {
+            return &sections[PHYS_SECTION_UNASSIGNED];
+        }
+        p = nodes[lp.ptr];
+        lp = p[(index >> (i * P_L2_BITS)) & (P_L2_SIZE - 1)];
+    }
+
+    if (section_covers_addr(&sections[lp.ptr], addr)) {
+        return &sections[lp.ptr];
+    } else {
+        return &sections[PHYS_SECTION_UNASSIGNED];
+    }
+}
+
+/* Called from RCU critical section */
+static MemoryRegionSection *address_space_lookup_region(AddressSpaceDispatch *d,
+                                                        hwaddr addr,
+                                                        bool resolve_subpage)
+{
+    MemoryRegionSection *section = qatomic_read(&d->mru_section);
+    subpage_t *subpage;
+
+    if (!section || section == &d->map.sections[PHYS_SECTION_UNASSIGNED] ||
+        !section_covers_addr(section, addr)) {
+        section = phys_page_find(d, addr);
+        qatomic_set(&d->mru_section, section);
+    }
+    if (resolve_subpage && section->mr->subpage) {
+        subpage = container_of(section->mr, subpage_t, iomem);
+        section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
+    }
+    return section;
+}
+
+/* Called from RCU critical section */
+static MemoryRegionSection *
+address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *xlat,
+                                 hwaddr *plen, bool resolve_subpage)
+{
+    MemoryRegionSection *section;
+    MemoryRegion *mr;
+    Int128 diff;
+
+    section = address_space_lookup_region(d, addr, resolve_subpage);
+    /* Compute offset within MemoryRegionSection */
+    addr -= section->offset_within_address_space;
+
+    /* Compute offset within MemoryRegion */
+    *xlat = addr + section->offset_within_region;
+
+    mr = section->mr;
+
+    /* MMIO registers can be expected to perform full-width accesses based only
+     * on their address, without considering adjacent registers that could
+     * decode to completely different MemoryRegions.  When such registers
+     * exist (e.g. I/O ports 0xcf8 and 0xcf9 on most PC chipsets), MMIO
+     * regions overlap wildly.  For this reason we cannot clamp the accesses
+     * here.
+     *
+     * If the length is small (as is the case for address_space_ldl/stl),
+     * everything works fine.  If the incoming length is large, however,
+     * the caller really has to do the clamping through memory_access_size.
+     */
+    if (memory_region_is_ram(mr)) {
+        diff = int128_sub(section->size, int128_make64(addr));
+        *plen = int128_get64(int128_min(diff, int128_make64(*plen)));
+    }
+    return section;
+}
+
+/**
+ * address_space_translate_iommu - translate an address through an IOMMU
+ * memory region and then through the target address space.
+ *
+ * @iommu_mr: the IOMMU memory region that we start the translation from
+ * @addr: the address to be translated through the MMU
+ * @xlat: the translated address offset within the destination memory region.
+ *        It cannot be %NULL.
+ * @plen_out: valid read/write length of the translated address. It
+ *            cannot be %NULL.
+ * @page_mask_out: page mask for the translated address. This
+ *            should only be meaningful for IOMMU translated
+ *            addresses, since there may be huge pages that this bit
+ *            would tell. It can be %NULL if we don't care about it.
+ * @is_write: whether the translation operation is for write
+ * @is_mmio: whether this can be MMIO, set true if it can
+ * @target_as: the address space targeted by the IOMMU
+ * @attrs: transaction attributes
+ *
+ * This function is called from RCU critical section.  It is the common
+ * part of flatview_do_translate and address_space_translate_cached.
+ */
+static MemoryRegionSection address_space_translate_iommu(IOMMUMemoryRegion *iommu_mr,
+                                                         hwaddr *xlat,
+                                                         hwaddr *plen_out,
+                                                         hwaddr *page_mask_out,
+                                                         bool is_write,
+                                                         bool is_mmio,
+                                                         AddressSpace **target_as,
+                                                         MemTxAttrs attrs)
+{
+    MemoryRegionSection *section;
+    hwaddr page_mask = (hwaddr)-1;
+
+    do {
+        hwaddr addr = *xlat;
+        IOMMUMemoryRegionClass *imrc = memory_region_get_iommu_class_nocheck(iommu_mr);
+        int iommu_idx = 0;
+        IOMMUTLBEntry iotlb;
+
+        if (imrc->attrs_to_index) {
+            iommu_idx = imrc->attrs_to_index(iommu_mr, attrs);
+        }
+
+        iotlb = imrc->translate(iommu_mr, addr, is_write ?
+                                IOMMU_WO : IOMMU_RO, iommu_idx);
+
+        if (!(iotlb.perm & (1 << is_write))) {
+            goto unassigned;
+        }
+
+        addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
+                | (addr & iotlb.addr_mask));
+        page_mask &= iotlb.addr_mask;
+        *plen_out = MIN(*plen_out, (addr | iotlb.addr_mask) - addr + 1);
+        *target_as = iotlb.target_as;
+
+        section = address_space_translate_internal(
+                address_space_to_dispatch(iotlb.target_as), addr, xlat,
+                plen_out, is_mmio);
+
+        iommu_mr = memory_region_get_iommu(section->mr);
+    } while (unlikely(iommu_mr));
+
+    if (page_mask_out) {
+        *page_mask_out = page_mask;
+    }
+    return *section;
+
+unassigned:
+    return (MemoryRegionSection) { .mr = &io_mem_unassigned };
+}
+
+/**
+ * flatview_do_translate - translate an address in FlatView
+ *
+ * @fv: the flat view that we want to translate on
+ * @addr: the address to be translated in above address space
+ * @xlat: the translated address offset within memory region. It
+ *        cannot be @NULL.
+ * @plen_out: valid read/write length of the translated address. It
+ *            can be @NULL when we don't care about it.
+ * @page_mask_out: page mask for the translated address. This
+ *            should only be meaningful for IOMMU translated
+ *            addresses, since there may be huge pages that this bit
+ *            would tell. It can be @NULL if we don't care about it.
+ * @is_write: whether the translation operation is for write
+ * @is_mmio: whether this can be MMIO, set true if it can
+ * @target_as: the address space targeted by the IOMMU
+ * @attrs: memory transaction attributes
+ *
+ * This function is called from RCU critical section
+ */
+static MemoryRegionSection flatview_do_translate(FlatView *fv,
+                                                 hwaddr addr,
+                                                 hwaddr *xlat,
+                                                 hwaddr *plen_out,
+                                                 hwaddr *page_mask_out,
+                                                 bool is_write,
+                                                 bool is_mmio,
+                                                 AddressSpace **target_as,
+                                                 MemTxAttrs attrs)
+{
+    MemoryRegionSection *section;
+    IOMMUMemoryRegion *iommu_mr;
+    hwaddr plen = (hwaddr)(-1);
+
+    if (!plen_out) {
+        plen_out = &plen;
+    }
+
+    section = address_space_translate_internal(
+            flatview_to_dispatch(fv), addr, xlat,
+            plen_out, is_mmio);
+
+    iommu_mr = memory_region_get_iommu(section->mr);
+    if (unlikely(iommu_mr)) {
+        return address_space_translate_iommu(iommu_mr, xlat,
+                                             plen_out, page_mask_out,
+                                             is_write, is_mmio,
+                                             target_as, attrs);
+    }
+    if (page_mask_out) {
+        /* Not behind an IOMMU, use default page size. */
+        *page_mask_out = ~TARGET_PAGE_MASK;
+    }
+
+    return *section;
+}
+
+/* Called from RCU critical section */
+IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr,
+                                            bool is_write, MemTxAttrs attrs)
+{
+    MemoryRegionSection section;
+    hwaddr xlat, page_mask;
+
+    /*
+     * This can never be MMIO, and we don't really care about plen,
+     * but page mask.
+     */
+    section = flatview_do_translate(address_space_to_flatview(as), addr, &xlat,
+                                    NULL, &page_mask, is_write, false, &as,
+                                    attrs);
+
+    /* Illegal translation */
+    if (section.mr == &io_mem_unassigned) {
+        goto iotlb_fail;
+    }
+
+    /* Convert memory region offset into address space offset */
+    xlat += section.offset_within_address_space -
+        section.offset_within_region;
+
+    return (IOMMUTLBEntry) {
+        .target_as = as,
+        .iova = addr & ~page_mask,
+        .translated_addr = xlat & ~page_mask,
+        .addr_mask = page_mask,
+        /* IOTLBs are for DMAs, and DMA only allows on RAMs. */
+        .perm = IOMMU_RW,
+    };
+
+iotlb_fail:
+    return (IOMMUTLBEntry) {0};
+}
+
+/* Called from RCU critical section */
+MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat,
+                                 hwaddr *plen, bool is_write,
+                                 MemTxAttrs attrs)
+{
+    MemoryRegion *mr;
+    MemoryRegionSection section;
+    AddressSpace *as = NULL;
+
+    /* This can be MMIO, so setup MMIO bit. */
+    section = flatview_do_translate(fv, addr, xlat, plen, NULL,
+                                    is_write, true, &as, attrs);
+    mr = section.mr;
+
+    if (xen_enabled() && memory_access_is_direct(mr, is_write)) {
+        hwaddr page = ((addr & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE) - addr;
+        *plen = MIN(page, *plen);
+    }
+
+    return mr;
+}
+
+typedef struct TCGIOMMUNotifier {
+    IOMMUNotifier n;
+    MemoryRegion *mr;
+    CPUState *cpu;
+    int iommu_idx;
+    bool active;
+} TCGIOMMUNotifier;
+
+static void tcg_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+    TCGIOMMUNotifier *notifier = container_of(n, TCGIOMMUNotifier, n);
+
+    if (!notifier->active) {
+        return;
+    }
+    tlb_flush(notifier->cpu);
+    notifier->active = false;
+    /* We leave the notifier struct on the list to avoid reallocating it later.
+     * Generally the number of IOMMUs a CPU deals with will be small.
+     * In any case we can't unregister the iommu notifier from a notify
+     * callback.
+     */
+}
+
+static void tcg_register_iommu_notifier(CPUState *cpu,
+                                        IOMMUMemoryRegion *iommu_mr,
+                                        int iommu_idx)
+{
+    /* Make sure this CPU has an IOMMU notifier registered for this
+     * IOMMU/IOMMU index combination, so that we can flush its TLB
+     * when the IOMMU tells us the mappings we've cached have changed.
+     */
+    MemoryRegion *mr = MEMORY_REGION(iommu_mr);
+    TCGIOMMUNotifier *notifier;
+    int i;
+
+    for (i = 0; i < cpu->iommu_notifiers->len; i++) {
+        notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i);
+        if (notifier->mr == mr && notifier->iommu_idx == iommu_idx) {
+            break;
+        }
+    }
+    if (i == cpu->iommu_notifiers->len) {
+        /* Not found, add a new entry at the end of the array */
+        cpu->iommu_notifiers = g_array_set_size(cpu->iommu_notifiers, i + 1);
+        notifier = g_new0(TCGIOMMUNotifier, 1);
+        g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i) = notifier;
+
+        notifier->mr = mr;
+        notifier->iommu_idx = iommu_idx;
+        notifier->cpu = cpu;
+        /* Rather than trying to register interest in the specific part
+         * of the iommu's address space that we've accessed and then
+         * expand it later as subsequent accesses touch more of it, we
+         * just register interest in the whole thing, on the assumption
+         * that iommu reconfiguration will be rare.
+         */
+        iommu_notifier_init(&notifier->n,
+                            tcg_iommu_unmap_notify,
+                            IOMMU_NOTIFIER_UNMAP,
+                            0,
+                            HWADDR_MAX,
+                            iommu_idx);
+        memory_region_register_iommu_notifier(notifier->mr, &notifier->n,
+                                              &error_fatal);
+    }
+
+    if (!notifier->active) {
+        notifier->active = true;
+    }
+}
+
+void tcg_iommu_free_notifier_list(CPUState *cpu)
+{
+    /* Destroy the CPU's notifier list */
+    int i;
+    TCGIOMMUNotifier *notifier;
+
+    for (i = 0; i < cpu->iommu_notifiers->len; i++) {
+        notifier = g_array_index(cpu->iommu_notifiers, TCGIOMMUNotifier *, i);
+        memory_region_unregister_iommu_notifier(notifier->mr, &notifier->n);
+        g_free(notifier);
+    }
+    g_array_free(cpu->iommu_notifiers, true);
+}
+
+void tcg_iommu_init_notifier_list(CPUState *cpu)
+{
+    cpu->iommu_notifiers = g_array_new(false, true, sizeof(TCGIOMMUNotifier *));
+}
+
+/* Called from RCU critical section */
+MemoryRegionSection *
+address_space_translate_for_iotlb(CPUState *cpu, int asidx, hwaddr addr,
+                                  hwaddr *xlat, hwaddr *plen,
+                                  MemTxAttrs attrs, int *prot)
+{
+    MemoryRegionSection *section;
+    IOMMUMemoryRegion *iommu_mr;
+    IOMMUMemoryRegionClass *imrc;
+    IOMMUTLBEntry iotlb;
+    int iommu_idx;
+    AddressSpaceDispatch *d =
+        qatomic_rcu_read(&cpu->cpu_ases[asidx].memory_dispatch);
+
+    for (;;) {
+        section = address_space_translate_internal(d, addr, &addr, plen, false);
+
+        iommu_mr = memory_region_get_iommu(section->mr);
+        if (!iommu_mr) {
+            break;
+        }
+
+        imrc = memory_region_get_iommu_class_nocheck(iommu_mr);
+
+        iommu_idx = imrc->attrs_to_index(iommu_mr, attrs);
+        tcg_register_iommu_notifier(cpu, iommu_mr, iommu_idx);
+        /* We need all the permissions, so pass IOMMU_NONE so the IOMMU
+         * doesn't short-cut its translation table walk.
+         */
+        iotlb = imrc->translate(iommu_mr, addr, IOMMU_NONE, iommu_idx);
+        addr = ((iotlb.translated_addr & ~iotlb.addr_mask)
+                | (addr & iotlb.addr_mask));
+        /* Update the caller's prot bits to remove permissions the IOMMU
+         * is giving us a failure response for. If we get down to no
+         * permissions left at all we can give up now.
+         */
+        if (!(iotlb.perm & IOMMU_RO)) {
+            *prot &= ~(PAGE_READ | PAGE_EXEC);
+        }
+        if (!(iotlb.perm & IOMMU_WO)) {
+            *prot &= ~PAGE_WRITE;
+        }
+
+        if (!*prot) {
+            goto translate_fail;
+        }
+
+        d = flatview_to_dispatch(address_space_to_flatview(iotlb.target_as));
+    }
+
+    assert(!memory_region_is_iommu(section->mr));
+    *xlat = addr;
+    return section;
+
+translate_fail:
+    return &d->map.sections[PHYS_SECTION_UNASSIGNED];
+}
+
+void cpu_address_space_init(CPUState *cpu, int asidx,
+                            const char *prefix, MemoryRegion *mr)
+{
+    CPUAddressSpace *newas;
+    AddressSpace *as = g_new0(AddressSpace, 1);
+    char *as_name;
+
+    assert(mr);
+    as_name = g_strdup_printf("%s-%d", prefix, cpu->cpu_index);
+    address_space_init(as, mr, as_name);
+    g_free(as_name);
+
+    /* Target code should have set num_ases before calling us */
+    assert(asidx < cpu->num_ases);
+
+    if (asidx == 0) {
+        /* address space 0 gets the convenience alias */
+        cpu->as = as;
+    }
+
+    /* KVM cannot currently support multiple address spaces. */
+    assert(asidx == 0 || !kvm_enabled());
+
+    if (!cpu->cpu_ases) {
+        cpu->cpu_ases = g_new0(CPUAddressSpace, cpu->num_ases);
+    }
+
+    newas = &cpu->cpu_ases[asidx];
+    newas->cpu = cpu;
+    newas->as = as;
+    if (tcg_enabled()) {
+        newas->tcg_as_listener.log_global_after_sync = tcg_log_global_after_sync;
+        newas->tcg_as_listener.commit = tcg_commit;
+        memory_listener_register(&newas->tcg_as_listener, as);
+    }
+}
+
+AddressSpace *cpu_get_address_space(CPUState *cpu, int asidx)
+{
+    /* Return the AddressSpace corresponding to the specified index */
+    return cpu->cpu_ases[asidx].as;
+}
+
+/* Add a watchpoint.  */
+int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
+                          int flags, CPUWatchpoint **watchpoint)
+{
+    CPUWatchpoint *wp;
+    vaddr in_page;
+
+    /* forbid ranges which are empty or run off the end of the address space */
+    if (len == 0 || (addr + len - 1) < addr) {
+        error_report("tried to set invalid watchpoint at %"
+                     VADDR_PRIx ", len=%" VADDR_PRIu, addr, len);
+        return -EINVAL;
+    }
+    wp = g_malloc(sizeof(*wp));
+
+    wp->vaddr = addr;
+    wp->len = len;
+    wp->flags = flags;
+
+    /* keep all GDB-injected watchpoints in front */
+    if (flags & BP_GDB) {
+        QTAILQ_INSERT_HEAD(&cpu->watchpoints, wp, entry);
+    } else {
+        QTAILQ_INSERT_TAIL(&cpu->watchpoints, wp, entry);
+    }
+
+    in_page = -(addr | TARGET_PAGE_MASK);
+    if (len <= in_page) {
+        tlb_flush_page(cpu, addr);
+    } else {
+        tlb_flush(cpu);
+    }
+
+    if (watchpoint)
+        *watchpoint = wp;
+    return 0;
+}
+
+/* Remove a specific watchpoint.  */
+int cpu_watchpoint_remove(CPUState *cpu, vaddr addr, vaddr len,
+                          int flags)
+{
+    CPUWatchpoint *wp;
+
+    QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
+        if (addr == wp->vaddr && len == wp->len
+                && flags == (wp->flags & ~BP_WATCHPOINT_HIT)) {
+            cpu_watchpoint_remove_by_ref(cpu, wp);
+            return 0;
+        }
+    }
+    return -ENOENT;
+}
+
+/* Remove a specific watchpoint by reference.  */
+void cpu_watchpoint_remove_by_ref(CPUState *cpu, CPUWatchpoint *watchpoint)
+{
+    QTAILQ_REMOVE(&cpu->watchpoints, watchpoint, entry);
+
+    tlb_flush_page(cpu, watchpoint->vaddr);
+
+    g_free(watchpoint);
+}
+
+/* Remove all matching watchpoints.  */
+void cpu_watchpoint_remove_all(CPUState *cpu, int mask)
+{
+    CPUWatchpoint *wp, *next;
+
+    QTAILQ_FOREACH_SAFE(wp, &cpu->watchpoints, entry, next) {
+        if (wp->flags & mask) {
+            cpu_watchpoint_remove_by_ref(cpu, wp);
+        }
+    }
+}
+
+/* Return true if this watchpoint address matches the specified
+ * access (ie the address range covered by the watchpoint overlaps
+ * partially or completely with the address range covered by the
+ * access).
+ */
+static inline bool watchpoint_address_matches(CPUWatchpoint *wp,
+                                              vaddr addr, vaddr len)
+{
+    /* We know the lengths are non-zero, but a little caution is
+     * required to avoid errors in the case where the range ends
+     * exactly at the top of the address space and so addr + len
+     * wraps round to zero.
+     */
+    vaddr wpend = wp->vaddr + wp->len - 1;
+    vaddr addrend = addr + len - 1;
+
+    return !(addr > wpend || wp->vaddr > addrend);
+}
+
+/* Return flags for watchpoints that match addr + prot.  */
+int cpu_watchpoint_address_matches(CPUState *cpu, vaddr addr, vaddr len)
+{
+    CPUWatchpoint *wp;
+    int ret = 0;
+
+    QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
+        if (watchpoint_address_matches(wp, addr, len)) {
+            ret |= wp->flags;
+        }
+    }
+    return ret;
+}
+
+/* Called from RCU critical section */
+static RAMBlock *qemu_get_ram_block(ram_addr_t addr)
+{
+    RAMBlock *block;
+
+    block = qatomic_rcu_read(&ram_list.mru_block);
+    if (block && addr - block->offset < block->max_length) {
+        return block;
+    }
+    RAMBLOCK_FOREACH(block) {
+        if (addr - block->offset < block->max_length) {
+            goto found;
+        }
+    }
+
+    fprintf(stderr, "Bad ram offset %" PRIx64 "\n", (uint64_t)addr);
+    abort();
+
+found:
+    /* It is safe to write mru_block outside the iothread lock.  This
+     * is what happens:
+     *
+     *     mru_block = xxx
+     *     rcu_read_unlock()
+     *                                        xxx removed from list
+     *                  rcu_read_lock()
+     *                  read mru_block
+     *                                        mru_block = NULL;
+     *                                        call_rcu(reclaim_ramblock, xxx);
+     *                  rcu_read_unlock()
+     *
+     * qatomic_rcu_set is not needed here.  The block was already published
+     * when it was placed into the list.  Here we're just making an extra
+     * copy of the pointer.
+     */
+    ram_list.mru_block = block;
+    return block;
+}
+
+static void tlb_reset_dirty_range_all(ram_addr_t start, ram_addr_t length)
+{
+    CPUState *cpu;
+    ram_addr_t start1;
+    RAMBlock *block;
+    ram_addr_t end;
+
+    assert(tcg_enabled());
+    end = TARGET_PAGE_ALIGN(start + length);
+    start &= TARGET_PAGE_MASK;
+
+    RCU_READ_LOCK_GUARD();
+    block = qemu_get_ram_block(start);
+    assert(block == qemu_get_ram_block(end - 1));
+    start1 = (uintptr_t)ramblock_ptr(block, start - block->offset);
+    CPU_FOREACH(cpu) {
+        tlb_reset_dirty(cpu, start1, length);
+    }
+}
+
+/* Note: start and end must be within the same ram block.  */
+bool cpu_physical_memory_test_and_clear_dirty(ram_addr_t start,
+                                              ram_addr_t length,
+                                              unsigned client)
+{
+    DirtyMemoryBlocks *blocks;
+    unsigned long end, page, start_page;
+    bool dirty = false;
+    RAMBlock *ramblock;
+    uint64_t mr_offset, mr_size;
+
+    if (length == 0) {
+        return false;
+    }
+
+    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
+    start_page = start >> TARGET_PAGE_BITS;
+    page = start_page;
+
+    WITH_RCU_READ_LOCK_GUARD() {
+        blocks = qatomic_rcu_read(&ram_list.dirty_memory[client]);
+        ramblock = qemu_get_ram_block(start);
+        /* Range sanity check on the ramblock */
+        assert(start >= ramblock->offset &&
+               start + length <= ramblock->offset + ramblock->used_length);
+
+        while (page < end) {
+            unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+            unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+            unsigned long num = MIN(end - page,
+                                    DIRTY_MEMORY_BLOCK_SIZE - offset);
+
+            dirty |= bitmap_test_and_clear_atomic(blocks->blocks[idx],
+                                                  offset, num);
+            page += num;
+        }
+
+        mr_offset = (ram_addr_t)(start_page << TARGET_PAGE_BITS) - ramblock->offset;
+        mr_size = (end - start_page) << TARGET_PAGE_BITS;
+        memory_region_clear_dirty_bitmap(ramblock->mr, mr_offset, mr_size);
+    }
+
+    if (dirty && tcg_enabled()) {
+        tlb_reset_dirty_range_all(start, length);
+    }
+
+    return dirty;
+}
+
+DirtyBitmapSnapshot *cpu_physical_memory_snapshot_and_clear_dirty
+    (MemoryRegion *mr, hwaddr offset, hwaddr length, unsigned client)
+{
+    DirtyMemoryBlocks *blocks;
+    ram_addr_t start = memory_region_get_ram_addr(mr) + offset;
+    unsigned long align = 1UL << (TARGET_PAGE_BITS + BITS_PER_LEVEL);
+    ram_addr_t first = QEMU_ALIGN_DOWN(start, align);
+    ram_addr_t last  = QEMU_ALIGN_UP(start + length, align);
+    DirtyBitmapSnapshot *snap;
+    unsigned long page, end, dest;
+
+    snap = g_malloc0(sizeof(*snap) +
+                     ((last - first) >> (TARGET_PAGE_BITS + 3)));
+    snap->start = first;
+    snap->end   = last;
+
+    page = first >> TARGET_PAGE_BITS;
+    end  = last  >> TARGET_PAGE_BITS;
+    dest = 0;
+
+    WITH_RCU_READ_LOCK_GUARD() {
+        blocks = qatomic_rcu_read(&ram_list.dirty_memory[client]);
+
+        while (page < end) {
+            unsigned long idx = page / DIRTY_MEMORY_BLOCK_SIZE;
+            unsigned long offset = page % DIRTY_MEMORY_BLOCK_SIZE;
+            unsigned long num = MIN(end - page,
+                                    DIRTY_MEMORY_BLOCK_SIZE - offset);
+
+            assert(QEMU_IS_ALIGNED(offset, (1 << BITS_PER_LEVEL)));
+            assert(QEMU_IS_ALIGNED(num,    (1 << BITS_PER_LEVEL)));
+            offset >>= BITS_PER_LEVEL;
+
+            bitmap_copy_and_clear_atomic(snap->dirty + dest,
+                                         blocks->blocks[idx] + offset,
+                                         num);
+            page += num;
+            dest += num >> BITS_PER_LEVEL;
+        }
+    }
+
+    if (tcg_enabled()) {
+        tlb_reset_dirty_range_all(start, length);
+    }
+
+    memory_region_clear_dirty_bitmap(mr, offset, length);
+
+    return snap;
+}
+
+bool cpu_physical_memory_snapshot_get_dirty(DirtyBitmapSnapshot *snap,
+                                            ram_addr_t start,
+                                            ram_addr_t length)
+{
+    unsigned long page, end;
+
+    assert(start >= snap->start);
+    assert(start + length <= snap->end);
+
+    end = TARGET_PAGE_ALIGN(start + length - snap->start) >> TARGET_PAGE_BITS;
+    page = (start - snap->start) >> TARGET_PAGE_BITS;
+
+    while (page < end) {
+        if (test_bit(page, snap->dirty)) {
+            return true;
+        }
+        page++;
+    }
+    return false;
+}
+
+/* Called from RCU critical section */
+hwaddr memory_region_section_get_iotlb(CPUState *cpu,
+                                       MemoryRegionSection *section)
+{
+    AddressSpaceDispatch *d = flatview_to_dispatch(section->fv);
+    return section - d->map.sections;
+}
+
+static int subpage_register(subpage_t *mmio, uint32_t start, uint32_t end,
+                            uint16_t section);
+static subpage_t *subpage_init(FlatView *fv, hwaddr base);
+
+static void *(*phys_mem_alloc)(size_t size, uint64_t *align, bool shared) =
+                               qemu_anon_ram_alloc;
+
+/*
+ * Set a custom physical guest memory alloator.
+ * Accelerators with unusual needs may need this.  Hopefully, we can
+ * get rid of it eventually.
+ */
+void phys_mem_set_alloc(void *(*alloc)(size_t, uint64_t *align, bool shared))
+{
+    phys_mem_alloc = alloc;
+}
+
+static uint16_t phys_section_add(PhysPageMap *map,
+                                 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(map->sections_nb < TARGET_PAGE_SIZE);
+
+    if (map->sections_nb == map->sections_nb_alloc) {
+        map->sections_nb_alloc = MAX(map->sections_nb_alloc * 2, 16);
+        map->sections = g_renew(MemoryRegionSection, map->sections,
+                                map->sections_nb_alloc);
+    }
+    map->sections[map->sections_nb] = *section;
+    memory_region_ref(section->mr);
+    return map->sections_nb++;
+}
+
+static void phys_section_destroy(MemoryRegion *mr)
+{
+    bool have_sub_page = mr->subpage;
+
+    memory_region_unref(mr);
+
+    if (have_sub_page) {
+        subpage_t *subpage = container_of(mr, subpage_t, iomem);
+        object_unref(OBJECT(&subpage->iomem));
+        g_free(subpage);
+    }
+}
+
+static void phys_sections_free(PhysPageMap *map)
+{
+    while (map->sections_nb > 0) {
+        MemoryRegionSection *section = &map->sections[--map->sections_nb];
+        phys_section_destroy(section->mr);
+    }
+    g_free(map->sections);
+    g_free(map->nodes);
+}
+
+static void register_subpage(FlatView *fv, MemoryRegionSection *section)
+{
+    AddressSpaceDispatch *d = flatview_to_dispatch(fv);
+    subpage_t *subpage;
+    hwaddr base = section->offset_within_address_space
+        & TARGET_PAGE_MASK;
+    MemoryRegionSection *existing = phys_page_find(d, base);
+    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(fv, base);
+        subsection.fv = fv;
+        subsection.mr = &subpage->iomem;
+        phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
+                      phys_section_add(&d->map, &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(&d->map, section));
+}
+
+
+static void register_multipage(FlatView *fv,
+                               MemoryRegionSection *section)
+{
+    AddressSpaceDispatch *d = flatview_to_dispatch(fv);
+    hwaddr start_addr = section->offset_within_address_space;
+    uint16_t section_index = phys_section_add(&d->map, 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);
+}
+
+/*
+ * The range in *section* may look like this:
+ *
+ *      |s|PPPPPPP|s|
+ *
+ * where s stands for subpage and P for page.
+ */
+void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section)
+{
+    MemoryRegionSection remain = *section;
+    Int128 page_size = int128_make64(TARGET_PAGE_SIZE);
+
+    /* register first subpage */
+    if (remain.offset_within_address_space & ~TARGET_PAGE_MASK) {
+        uint64_t left = TARGET_PAGE_ALIGN(remain.offset_within_address_space)
+                        - remain.offset_within_address_space;
+
+        MemoryRegionSection now = remain;
+        now.size = int128_min(int128_make64(left), now.size);
+        register_subpage(fv, &now);
+        if (int128_eq(remain.size, now.size)) {
+            return;
+        }
+        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);
+    }
+
+    /* register whole pages */
+    if (int128_ge(remain.size, page_size)) {
+        MemoryRegionSection now = remain;
+        now.size = int128_and(now.size, int128_neg(page_size));
+        register_multipage(fv, &now);
+        if (int128_eq(remain.size, now.size)) {
+            return;
+        }
+        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);
+    }
+
+    /* register last subpage */
+    register_subpage(fv, &remain);
+}
+
+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);
+}
+
+void ram_block_dump(Monitor *mon)
+{
+    RAMBlock *block;
+    char *psize;
+
+    RCU_READ_LOCK_GUARD();
+    monitor_printf(mon, "%24s %8s  %18s %18s %18s\n",
+                   "Block Name", "PSize", "Offset", "Used", "Total");
+    RAMBLOCK_FOREACH(block) {
+        psize = size_to_str(block->page_size);
+        monitor_printf(mon, "%24s %8s  0x%016" PRIx64 " 0x%016" PRIx64
+                       " 0x%016" PRIx64 "\n", block->idstr, psize,
+                       (uint64_t)block->offset,
+                       (uint64_t)block->used_length,
+                       (uint64_t)block->max_length);
+        g_free(psize);
+    }
+}
+
+#ifdef __linux__
+/*
+ * FIXME TOCTTOU: this iterates over memory backends' mem-path, which
+ * may or may not name the same files / on the same filesystem now as
+ * when we actually open and map them.  Iterate over the file
+ * descriptors instead, and use qemu_fd_getpagesize().
+ */
+static int find_min_backend_pagesize(Object *obj, void *opaque)
+{
+    long *hpsize_min = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
+        HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+        long hpsize = host_memory_backend_pagesize(backend);
+
+        if (host_memory_backend_is_mapped(backend) && (hpsize < *hpsize_min)) {
+            *hpsize_min = hpsize;
+        }
+    }
+
+    return 0;
+}
+
+static int find_max_backend_pagesize(Object *obj, void *opaque)
+{
+    long *hpsize_max = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) {
+        HostMemoryBackend *backend = MEMORY_BACKEND(obj);
+        long hpsize = host_memory_backend_pagesize(backend);
+
+        if (host_memory_backend_is_mapped(backend) && (hpsize > *hpsize_max)) {
+            *hpsize_max = hpsize;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * TODO: We assume right now that all mapped host memory backends are
+ * used as RAM, however some might be used for different purposes.
+ */
+long qemu_minrampagesize(void)
+{
+    long hpsize = LONG_MAX;
+    Object *memdev_root = object_resolve_path("/objects", NULL);
+
+    object_child_foreach(memdev_root, find_min_backend_pagesize, &hpsize);
+    return hpsize;
+}
+
+long qemu_maxrampagesize(void)
+{
+    long pagesize = 0;
+    Object *memdev_root = object_resolve_path("/objects", NULL);
+
+    object_child_foreach(memdev_root, find_max_backend_pagesize, &pagesize);
+    return pagesize;
+}
+#else
+long qemu_minrampagesize(void)
+{
+    return qemu_real_host_page_size;
+}
+long qemu_maxrampagesize(void)
+{
+    return qemu_real_host_page_size;
+}
+#endif
+
+#ifdef CONFIG_POSIX
+static int64_t get_file_size(int fd)
+{
+    int64_t size;
+#if defined(__linux__)
+    struct stat st;
+
+    if (fstat(fd, &st) < 0) {
+        return -errno;
+    }
+
+    /* Special handling for devdax character devices */
+    if (S_ISCHR(st.st_mode)) {
+        g_autofree char *subsystem_path = NULL;
+        g_autofree char *subsystem = NULL;
+
+        subsystem_path = g_strdup_printf("/sys/dev/char/%d:%d/subsystem",
+                                         major(st.st_rdev), minor(st.st_rdev));
+        subsystem = g_file_read_link(subsystem_path, NULL);
+
+        if (subsystem && g_str_has_suffix(subsystem, "/dax")) {
+            g_autofree char *size_path = NULL;
+            g_autofree char *size_str = NULL;
+
+            size_path = g_strdup_printf("/sys/dev/char/%d:%d/size",
+                                    major(st.st_rdev), minor(st.st_rdev));
+
+            if (g_file_get_contents(size_path, &size_str, NULL, NULL)) {
+                return g_ascii_strtoll(size_str, NULL, 0);
+            }
+        }
+    }
+#endif /* defined(__linux__) */
+
+    /* st.st_size may be zero for special files yet lseek(2) works */
+    size = lseek(fd, 0, SEEK_END);
+    if (size < 0) {
+        return -errno;
+    }
+    return size;
+}
+
+static int64_t get_file_align(int fd)
+{
+    int64_t align = -1;
+#if defined(__linux__) && defined(CONFIG_LIBDAXCTL)
+    struct stat st;
+
+    if (fstat(fd, &st) < 0) {
+        return -errno;
+    }
+
+    /* Special handling for devdax character devices */
+    if (S_ISCHR(st.st_mode)) {
+        g_autofree char *path = NULL;
+        g_autofree char *rpath = NULL;
+        struct daxctl_ctx *ctx;
+        struct daxctl_region *region;
+        int rc = 0;
+
+        path = g_strdup_printf("/sys/dev/char/%d:%d",
+                    major(st.st_rdev), minor(st.st_rdev));
+        rpath = realpath(path, NULL);
+
+        rc = daxctl_new(&ctx);
+        if (rc) {
+            return -1;
+        }
+
+        daxctl_region_foreach(ctx, region) {
+            if (strstr(rpath, daxctl_region_get_path(region))) {
+                align = daxctl_region_get_align(region);
+                break;
+            }
+        }
+        daxctl_unref(ctx);
+    }
+#endif /* defined(__linux__) && defined(CONFIG_LIBDAXCTL) */
+
+    return align;
+}
+
+static int file_ram_open(const char *path,
+                         const char *region_name,
+                         bool *created,
+                         Error **errp)
+{
+    char *filename;
+    char *sanitized_name;
+    char *c;
+    int fd = -1;
+
+    *created = false;
+    for (;;) {
+        fd = open(path, O_RDWR);
+        if (fd >= 0) {
+            /* @path names an existing file, use it */
+            break;
+        }
+        if (errno == ENOENT) {
+            /* @path names a file that doesn't exist, create it */
+            fd = open(path, O_RDWR | O_CREAT | O_EXCL, 0644);
+            if (fd >= 0) {
+                *created = true;
+                break;
+            }
+        } else if (errno == EISDIR) {
+            /* @path names a directory, create a file there */
+            /* Make name safe to use with mkstemp by replacing '/' with '_'. */
+            sanitized_name = g_strdup(region_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) {
+                unlink(filename);
+                g_free(filename);
+                break;
+            }
+            g_free(filename);
+        }
+        if (errno != EEXIST && errno != EINTR) {
+            error_setg_errno(errp, errno,
+                             "can't open backing store %s for guest RAM",
+                             path);
+            return -1;
+        }
+        /*
+         * Try again on EINTR and EEXIST.  The latter happens when
+         * something else creates the file between our two open().
+         */
+    }
+
+    return fd;
+}
+
+static void *file_ram_alloc(RAMBlock *block,
+                            ram_addr_t memory,
+                            int fd,
+                            bool truncate,
+                            Error **errp)
+{
+    void *area;
+
+    block->page_size = qemu_fd_getpagesize(fd);
+    if (block->mr->align % block->page_size) {
+        error_setg(errp, "alignment 0x%" PRIx64
+                   " must be multiples of page size 0x%zx",
+                   block->mr->align, block->page_size);
+        return NULL;
+    } else if (block->mr->align && !is_power_of_2(block->mr->align)) {
+        error_setg(errp, "alignment 0x%" PRIx64
+                   " must be a power of two", block->mr->align);
+        return NULL;
+    }
+    block->mr->align = MAX(block->page_size, block->mr->align);
+#if defined(__s390x__)
+    if (kvm_enabled()) {
+        block->mr->align = MAX(block->mr->align, QEMU_VMALLOC_ALIGN);
+    }
+#endif
+
+    if (memory < block->page_size) {
+        error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
+                   "or larger than page size 0x%zx",
+                   memory, block->page_size);
+        return NULL;
+    }
+
+    memory = ROUND_UP(memory, block->page_size);
+
+    /*
+     * 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.
+     *
+     * Do not truncate the non-empty backend file to avoid corrupting
+     * the existing data in the file. Disabling shrinking is not
+     * enough. For example, the current vNVDIMM implementation stores
+     * the guest NVDIMM labels at the end of the backend file. If the
+     * backend file is later extended, QEMU will not be able to find
+     * those labels. Therefore, extending the non-empty backend file
+     * is disabled as well.
+     */
+    if (truncate && ftruncate(fd, memory)) {
+        perror("ftruncate");
+    }
+
+    area = qemu_ram_mmap(fd, memory, block->mr->align,
+                         block->flags & RAM_SHARED, block->flags & RAM_PMEM);
+    if (area == MAP_FAILED) {
+        error_setg_errno(errp, errno,
+                         "unable to map backing store for guest RAM");
+        return NULL;
+    }
+
+    block->fd = fd;
+    return area;
+}
+#endif
+
+/* Allocate space within the ram_addr_t space that governs the
+ * dirty bitmaps.
+ * Called with the ramlist lock held.
+ */
+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 (QLIST_EMPTY_RCU(&ram_list.blocks)) {
+        return 0;
+    }
+
+    RAMBLOCK_FOREACH(block) {
+        ram_addr_t candidate, next = RAM_ADDR_MAX;
+
+        /* Align blocks to start on a 'long' in the bitmap
+         * which makes the bitmap sync'ing take the fast path.
+         */
+        candidate = block->offset + block->max_length;
+        candidate = ROUND_UP(candidate, BITS_PER_LONG << TARGET_PAGE_BITS);
+
+        /* Search for the closest following block
+         * and find the gap.
+         */
+        RAMBLOCK_FOREACH(next_block) {
+            if (next_block->offset >= candidate) {
+                next = MIN(next, next_block->offset);
+            }
+        }
+
+        /* If it fits remember our place and remember the size
+         * of gap, but keep going so that we might find a smaller
+         * gap to fill so avoiding fragmentation.
+         */
+        if (next - candidate >= size && next - candidate < mingap) {
+            offset = candidate;
+            mingap = next - candidate;
+        }
+
+        trace_find_ram_offset_loop(size, candidate, offset, next, mingap);
+    }
+
+    if (offset == RAM_ADDR_MAX) {
+        fprintf(stderr, "Failed to find gap of requested size: %" PRIu64 "\n",
+                (uint64_t)size);
+        abort();
+    }
+
+    trace_find_ram_offset(size, offset);
+
+    return offset;
+}
+
+static unsigned long last_ram_page(void)
+{
+    RAMBlock *block;
+    ram_addr_t last = 0;
+
+    RCU_READ_LOCK_GUARD();
+    RAMBLOCK_FOREACH(block) {
+        last = MAX(last, block->offset + block->max_length);
+    }
+    return last >> TARGET_PAGE_BITS;
+}
+
+static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
+{
+    int ret;
+
+    /* Use MADV_DONTDUMP, if user doesn't want the guest memory in the core */
+    if (!machine_dump_guest_core(current_machine)) {
+        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");
+        }
+    }
+}
+
+const char *qemu_ram_get_idstr(RAMBlock *rb)
+{
+    return rb->idstr;
+}
+
+void *qemu_ram_get_host_addr(RAMBlock *rb)
+{
+    return rb->host;
+}
+
+ram_addr_t qemu_ram_get_offset(RAMBlock *rb)
+{
+    return rb->offset;
+}
+
+ram_addr_t qemu_ram_get_used_length(RAMBlock *rb)
+{
+    return rb->used_length;
+}
+
+bool qemu_ram_is_shared(RAMBlock *rb)
+{
+    return rb->flags & RAM_SHARED;
+}
+
+/* Note: Only set at the start of postcopy */
+bool qemu_ram_is_uf_zeroable(RAMBlock *rb)
+{
+    return rb->flags & RAM_UF_ZEROPAGE;
+}
+
+void qemu_ram_set_uf_zeroable(RAMBlock *rb)
+{
+    rb->flags |= RAM_UF_ZEROPAGE;
+}
+
+bool qemu_ram_is_migratable(RAMBlock *rb)
+{
+    return rb->flags & RAM_MIGRATABLE;
+}
+
+void qemu_ram_set_migratable(RAMBlock *rb)
+{
+    rb->flags |= RAM_MIGRATABLE;
+}
+
+void qemu_ram_unset_migratable(RAMBlock *rb)
+{
+    rb->flags &= ~RAM_MIGRATABLE;
+}
+
+/* Called with iothread lock held.  */
+void qemu_ram_set_idstr(RAMBlock *new_block, const char *name, DeviceState *dev)
+{
+    RAMBlock *block;
+
+    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);
+
+    RCU_READ_LOCK_GUARD();
+    RAMBLOCK_FOREACH(block) {
+        if (block != new_block &&
+            !strcmp(block->idstr, new_block->idstr)) {
+            fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
+                    new_block->idstr);
+            abort();
+        }
+    }
+}
+
+/* Called with iothread lock held.  */
+void qemu_ram_unset_idstr(RAMBlock *block)
+{
+    /* FIXME: arch_init.c assumes that this is not called throughout
+     * migration.  Ignore the problem since hot-unplug during migration
+     * does not work anyway.
+     */
+    if (block) {
+        memset(block->idstr, 0, sizeof(block->idstr));
+    }
+}
+
+size_t qemu_ram_pagesize(RAMBlock *rb)
+{
+    return rb->page_size;
+}
+
+/* Returns the largest size of page in use */
+size_t qemu_ram_pagesize_largest(void)
+{
+    RAMBlock *block;
+    size_t largest = 0;
+
+    RAMBLOCK_FOREACH(block) {
+        largest = MAX(largest, qemu_ram_pagesize(block));
+    }
+
+    return largest;
+}
+
+static int memory_try_enable_merging(void *addr, size_t len)
+{
+    if (!machine_mem_merge(current_machine)) {
+        /* disabled by the user */
+        return 0;
+    }
+
+    return qemu_madvise(addr, len, QEMU_MADV_MERGEABLE);
+}
+
+/* Only legal before guest might have detected the memory size: e.g. on
+ * incoming migration, or right after reset.
+ *
+ * As memory core doesn't know how is memory accessed, it is up to
+ * resize callback to update device state and/or add assertions to detect
+ * misuse, if necessary.
+ */
+int qemu_ram_resize(RAMBlock *block, ram_addr_t newsize, Error **errp)
+{
+    const ram_addr_t unaligned_size = newsize;
+
+    assert(block);
+
+    newsize = HOST_PAGE_ALIGN(newsize);
+
+    if (block->used_length == newsize) {
+        /*
+         * We don't have to resize the ram block (which only knows aligned
+         * sizes), however, we have to notify if the unaligned size changed.
+         */
+        if (unaligned_size != memory_region_size(block->mr)) {
+            memory_region_set_size(block->mr, unaligned_size);
+            if (block->resized) {
+                block->resized(block->idstr, unaligned_size, block->host);
+            }
+        }
+        return 0;
+    }
+
+    if (!(block->flags & RAM_RESIZEABLE)) {
+        error_setg_errno(errp, EINVAL,
+                         "Length mismatch: %s: 0x" RAM_ADDR_FMT
+                         " in != 0x" RAM_ADDR_FMT, block->idstr,
+                         newsize, block->used_length);
+        return -EINVAL;
+    }
+
+    if (block->max_length < newsize) {
+        error_setg_errno(errp, EINVAL,
+                         "Length too large: %s: 0x" RAM_ADDR_FMT
+                         " > 0x" RAM_ADDR_FMT, block->idstr,
+                         newsize, block->max_length);
+        return -EINVAL;
+    }
+
+    cpu_physical_memory_clear_dirty_range(block->offset, block->used_length);
+    block->used_length = newsize;
+    cpu_physical_memory_set_dirty_range(block->offset, block->used_length,
+                                        DIRTY_CLIENTS_ALL);
+    memory_region_set_size(block->mr, unaligned_size);
+    if (block->resized) {
+        block->resized(block->idstr, unaligned_size, block->host);
+    }
+    return 0;
+}
+
+/*
+ * Trigger sync on the given ram block for range [start, start + length]
+ * with the backing store if one is available.
+ * Otherwise no-op.
+ * @Note: this is supposed to be a synchronous op.
+ */
+void qemu_ram_msync(RAMBlock *block, ram_addr_t start, ram_addr_t length)
+{
+    /* The requested range should fit in within the block range */
+    g_assert((start + length) <= block->used_length);
+
+#ifdef CONFIG_LIBPMEM
+    /* The lack of support for pmem should not block the sync */
+    if (ramblock_is_pmem(block)) {
+        void *addr = ramblock_ptr(block, start);
+        pmem_persist(addr, length);
+        return;
+    }
+#endif
+    if (block->fd >= 0) {
+        /**
+         * Case there is no support for PMEM or the memory has not been
+         * specified as persistent (or is not one) - use the msync.
+         * Less optimal but still achieves the same goal
+         */
+        void *addr = ramblock_ptr(block, start);
+        if (qemu_msync(addr, length, block->fd)) {
+            warn_report("%s: failed to sync memory range: start: "
+                    RAM_ADDR_FMT " length: " RAM_ADDR_FMT,
+                    __func__, start, length);
+        }
+    }
+}
+
+/* Called with ram_list.mutex held */
+static void dirty_memory_extend(ram_addr_t old_ram_size,
+                                ram_addr_t new_ram_size)
+{
+    ram_addr_t old_num_blocks = DIV_ROUND_UP(old_ram_size,
+                                             DIRTY_MEMORY_BLOCK_SIZE);
+    ram_addr_t new_num_blocks = DIV_ROUND_UP(new_ram_size,
+                                             DIRTY_MEMORY_BLOCK_SIZE);
+    int i;
+
+    /* Only need to extend if block count increased */
+    if (new_num_blocks <= old_num_blocks) {
+        return;
+    }
+
+    for (i = 0; i < DIRTY_MEMORY_NUM; i++) {
+        DirtyMemoryBlocks *old_blocks;
+        DirtyMemoryBlocks *new_blocks;
+        int j;
+
+        old_blocks = qatomic_rcu_read(&ram_list.dirty_memory[i]);
+        new_blocks = g_malloc(sizeof(*new_blocks) +
+                              sizeof(new_blocks->blocks[0]) * new_num_blocks);
+
+        if (old_num_blocks) {
+            memcpy(new_blocks->blocks, old_blocks->blocks,
+                   old_num_blocks * sizeof(old_blocks->blocks[0]));
+        }
+
+        for (j = old_num_blocks; j < new_num_blocks; j++) {
+            new_blocks->blocks[j] = bitmap_new(DIRTY_MEMORY_BLOCK_SIZE);
+        }
+
+        qatomic_rcu_set(&ram_list.dirty_memory[i], new_blocks);
+
+        if (old_blocks) {
+            g_free_rcu(old_blocks, rcu);
+        }
+    }
+}
+
+static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared)
+{
+    RAMBlock *block;
+    RAMBlock *last_block = NULL;
+    ram_addr_t old_ram_size, new_ram_size;
+    Error *err = NULL;
+
+    old_ram_size = last_ram_page();
+
+    qemu_mutex_lock_ramlist();
+    new_block->offset = find_ram_offset(new_block->max_length);
+
+    if (!new_block->host) {
+        if (xen_enabled()) {
+            xen_ram_alloc(new_block->offset, new_block->max_length,
+                          new_block->mr, &err);
+            if (err) {
+                error_propagate(errp, err);
+                qemu_mutex_unlock_ramlist();
+                return;
+            }
+        } else {
+            new_block->host = phys_mem_alloc(new_block->max_length,
+                                             &new_block->mr->align, shared);
+            if (!new_block->host) {
+                error_setg_errno(errp, errno,
+                                 "cannot set up guest memory '%s'",
+                                 memory_region_name(new_block->mr));
+                qemu_mutex_unlock_ramlist();
+                return;
+            }
+            memory_try_enable_merging(new_block->host, new_block->max_length);
+        }
+    }
+
+    new_ram_size = MAX(old_ram_size,
+              (new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS);
+    if (new_ram_size > old_ram_size) {
+        dirty_memory_extend(old_ram_size, new_ram_size);
+    }
+    /* Keep the list sorted from biggest to smallest block.  Unlike QTAILQ,
+     * QLIST (which has an RCU-friendly variant) does not have insertion at
+     * tail, so save the last element in last_block.
+     */
+    RAMBLOCK_FOREACH(block) {
+        last_block = block;
+        if (block->max_length < new_block->max_length) {
+            break;
+        }
+    }
+    if (block) {
+        QLIST_INSERT_BEFORE_RCU(block, new_block, next);
+    } else if (last_block) {
+        QLIST_INSERT_AFTER_RCU(last_block, new_block, next);
+    } else { /* list is empty */
+        QLIST_INSERT_HEAD_RCU(&ram_list.blocks, new_block, next);
+    }
+    ram_list.mru_block = NULL;
+
+    /* Write list before version */
+    smp_wmb();
+    ram_list.version++;
+    qemu_mutex_unlock_ramlist();
+
+    cpu_physical_memory_set_dirty_range(new_block->offset,
+                                        new_block->used_length,
+                                        DIRTY_CLIENTS_ALL);
+
+    if (new_block->host) {
+        qemu_ram_setup_dump(new_block->host, new_block->max_length);
+        qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE);
+        /*
+         * MADV_DONTFORK is also needed by KVM in absence of synchronous MMU
+         * Configure it unless the machine is a qtest server, in which case
+         * KVM is not used and it may be forked (eg for fuzzing purposes).
+         */
+        if (!qtest_enabled()) {
+            qemu_madvise(new_block->host, new_block->max_length,
+                         QEMU_MADV_DONTFORK);
+        }
+        ram_block_notify_add(new_block->host, new_block->max_length);
+    }
+}
+
+#ifdef CONFIG_POSIX
+RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr,
+                                 uint32_t ram_flags, int fd,
+                                 Error **errp)
+{
+    RAMBlock *new_block;
+    Error *local_err = NULL;
+    int64_t file_size, file_align;
+
+    /* Just support these ram flags by now. */
+    assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);
+
+    if (xen_enabled()) {
+        error_setg(errp, "-mem-path not supported with Xen");
+        return NULL;
+    }
+
+    if (kvm_enabled() && !kvm_has_sync_mmu()) {
+        error_setg(errp,
+                   "host lacks kvm mmu notifiers, -mem-path unsupported");
+        return NULL;
+    }
+
+    if (phys_mem_alloc != qemu_anon_ram_alloc) {
+        /*
+         * file_ram_alloc() needs to allocate just like
+         * phys_mem_alloc, but we haven't bothered to provide
+         * a hook there.
+         */
+        error_setg(errp,
+                   "-mem-path not supported with this accelerator");
+        return NULL;
+    }
+
+    size = HOST_PAGE_ALIGN(size);
+    file_size = get_file_size(fd);
+    if (file_size > 0 && file_size < size) {
+        error_setg(errp, "backing store size 0x%" PRIx64
+                   " does not match 'size' option 0x" RAM_ADDR_FMT,
+                   file_size, size);
+        return NULL;
+    }
+
+    file_align = get_file_align(fd);
+    if (file_align > 0 && mr && file_align > mr->align) {
+        error_setg(errp, "backing store align 0x%" PRIx64
+                   " is larger than 'align' option 0x%" PRIx64,
+                   file_align, mr->align);
+        return NULL;
+    }
+
+    new_block = g_malloc0(sizeof(*new_block));
+    new_block->mr = mr;
+    new_block->used_length = size;
+    new_block->max_length = size;
+    new_block->flags = ram_flags;
+    new_block->host = file_ram_alloc(new_block, size, fd, !file_size, errp);
+    if (!new_block->host) {
+        g_free(new_block);
+        return NULL;
+    }
+
+    ram_block_add(new_block, &local_err, ram_flags & RAM_SHARED);
+    if (local_err) {
+        g_free(new_block);
+        error_propagate(errp, local_err);
+        return NULL;
+    }
+    return new_block;
+
+}
+
+
+RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
+                                   uint32_t ram_flags, const char *mem_path,
+                                   Error **errp)
+{
+    int fd;
+    bool created;
+    RAMBlock *block;
+
+    fd = file_ram_open(mem_path, memory_region_name(mr), &created, errp);
+    if (fd < 0) {
+        return NULL;
+    }
+
+    block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, errp);
+    if (!block) {
+        if (created) {
+            unlink(mem_path);
+        }
+        close(fd);
+        return NULL;
+    }
+
+    return block;
+}
+#endif
+
+static
+RAMBlock *qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
+                                  void (*resized)(const char*,
+                                                  uint64_t length,
+                                                  void *host),
+                                  void *host, bool resizeable, bool share,
+                                  MemoryRegion *mr, Error **errp)
+{
+    RAMBlock *new_block;
+    Error *local_err = NULL;
+
+    size = HOST_PAGE_ALIGN(size);
+    max_size = HOST_PAGE_ALIGN(max_size);
+    new_block = g_malloc0(sizeof(*new_block));
+    new_block->mr = mr;
+    new_block->resized = resized;
+    new_block->used_length = size;
+    new_block->max_length = max_size;
+    assert(max_size >= size);
+    new_block->fd = -1;
+    new_block->page_size = qemu_real_host_page_size;
+    new_block->host = host;
+    if (host) {
+        new_block->flags |= RAM_PREALLOC;
+    }
+    if (resizeable) {
+        new_block->flags |= RAM_RESIZEABLE;
+    }
+    ram_block_add(new_block, &local_err, share);
+    if (local_err) {
+        g_free(new_block);
+        error_propagate(errp, local_err);
+        return NULL;
+    }
+    return new_block;
+}
+
+RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host,
+                                   MemoryRegion *mr, Error **errp)
+{
+    return qemu_ram_alloc_internal(size, size, NULL, host, false,
+                                   false, mr, errp);
+}
+
+RAMBlock *qemu_ram_alloc(ram_addr_t size, bool share,
+                         MemoryRegion *mr, Error **errp)
+{
+    return qemu_ram_alloc_internal(size, size, NULL, NULL, false,
+                                   share, mr, errp);
+}
+
+RAMBlock *qemu_ram_alloc_resizeable(ram_addr_t size, ram_addr_t maxsz,
+                                     void (*resized)(const char*,
+                                                     uint64_t length,
+                                                     void *host),
+                                     MemoryRegion *mr, Error **errp)
+{
+    return qemu_ram_alloc_internal(size, maxsz, resized, NULL, true,
+                                   false, mr, errp);
+}
+
+static void reclaim_ramblock(RAMBlock *block)
+{
+    if (block->flags & RAM_PREALLOC) {
+        ;
+    } else if (xen_enabled()) {
+        xen_invalidate_map_cache_entry(block->host);
+#ifndef _WIN32
+    } else if (block->fd >= 0) {
+        qemu_ram_munmap(block->fd, block->host, block->max_length);
+        close(block->fd);
+#endif
+    } else {
+        qemu_anon_ram_free(block->host, block->max_length);
+    }
+    g_free(block);
+}
+
+void qemu_ram_free(RAMBlock *block)
+{
+    if (!block) {
+        return;
+    }
+
+    if (block->host) {
+        ram_block_notify_remove(block->host, block->max_length);
+    }
+
+    qemu_mutex_lock_ramlist();
+    QLIST_REMOVE_RCU(block, next);
+    ram_list.mru_block = NULL;
+    /* Write list before version */
+    smp_wmb();
+    ram_list.version++;
+    call_rcu(block, reclaim_ramblock, rcu);
+    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;
+
+    RAMBLOCK_FOREACH(block) {
+        offset = addr - block->offset;
+        if (offset < block->max_length) {
+            vaddr = ramblock_ptr(block, offset);
+            if (block->flags & RAM_PREALLOC) {
+                ;
+            } else if (xen_enabled()) {
+                abort();
+            } else {
+                flags = MAP_FIXED;
+                if (block->fd >= 0) {
+                    flags |= (block->flags & RAM_SHARED ?
+                              MAP_SHARED : MAP_PRIVATE);
+                    area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                flags, block->fd, offset);
+                } else {
+                    /*
+                     * Remap needs to match alloc.  Accelerators that
+                     * set phys_mem_alloc never remap.  If they did,
+                     * we'd need a remap hook here.
+                     */
+                    assert(phys_mem_alloc == qemu_anon_ram_alloc);
+
+                    flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+                    area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                flags, -1, 0);
+                }
+                if (area != vaddr) {
+                    error_report("Could not remap addr: "
+                                 RAM_ADDR_FMT "@" RAM_ADDR_FMT "",
+                                 length, addr);
+                    exit(1);
+                }
+                memory_try_enable_merging(vaddr, length);
+                qemu_ram_setup_dump(vaddr, length);
+            }
+        }
+    }
+}
+#endif /* !_WIN32 */
+
+/* Return a host pointer to ram allocated with qemu_ram_alloc.
+ * This should not be used for general purpose DMA.  Use address_space_map
+ * or address_space_rw instead. For local memory (e.g. video ram) that the
+ * device owns, use memory_region_get_ram_ptr.
+ *
+ * Called within RCU critical section.
+ */
+void *qemu_map_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
+{
+    RAMBlock *block = ram_block;
+
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+        addr -= block->offset;
+    }
+
+    if (xen_enabled() && block->host == NULL) {
+        /* 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, false);
+        }
+
+        block->host = xen_map_cache(block->offset, block->max_length, 1, false);
+    }
+    return ramblock_ptr(block, addr);
+}
+
+/* Return a host pointer to guest's ram. Similar to qemu_map_ram_ptr
+ * but takes a size argument.
+ *
+ * Called within RCU critical section.
+ */
+static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
+                                 hwaddr *size, bool lock)
+{
+    RAMBlock *block = ram_block;
+    if (*size == 0) {
+        return NULL;
+    }
+
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+        addr -= block->offset;
+    }
+    *size = MIN(*size, block->max_length - addr);
+
+    if (xen_enabled() && block->host == NULL) {
+        /* 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 the requested area.
+         */
+        if (block->offset == 0) {
+            return xen_map_cache(addr, *size, lock, lock);
+        }
+
+        block->host = xen_map_cache(block->offset, block->max_length, 1, lock);
+    }
+
+    return ramblock_ptr(block, addr);
+}
+
+/* Return the offset of a hostpointer within a ramblock */
+ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host)
+{
+    ram_addr_t res = (uint8_t *)host - (uint8_t *)rb->host;
+    assert((uintptr_t)host >= (uintptr_t)rb->host);
+    assert(res < rb->max_length);
+
+    return res;
+}
+
+/*
+ * Translates a host ptr back to a RAMBlock, a ram_addr and an offset
+ * in that RAMBlock.
+ *
+ * ptr: Host pointer to look up
+ * round_offset: If true round the result offset down to a page boundary
+ * *ram_addr: set to result ram_addr
+ * *offset: set to result offset within the RAMBlock
+ *
+ * Returns: RAMBlock (or NULL if not found)
+ *
+ * By the time this function returns, the returned pointer is not protected
+ * by RCU anymore.  If the caller is not within an RCU critical section and
+ * does not hold the iothread lock, it must have other means of protecting the
+ * pointer, such as a reference to the region that includes the incoming
+ * ram_addr_t.
+ */
+RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset,
+                                   ram_addr_t *offset)
+{
+    RAMBlock *block;
+    uint8_t *host = ptr;
+
+    if (xen_enabled()) {
+        ram_addr_t ram_addr;
+        RCU_READ_LOCK_GUARD();
+        ram_addr = xen_ram_addr_from_mapcache(ptr);
+        block = qemu_get_ram_block(ram_addr);
+        if (block) {
+            *offset = ram_addr - block->offset;
+        }
+        return block;
+    }
+
+    RCU_READ_LOCK_GUARD();
+    block = qatomic_rcu_read(&ram_list.mru_block);
+    if (block && block->host && host - block->host < block->max_length) {
+        goto found;
+    }
+
+    RAMBLOCK_FOREACH(block) {
+        /* This case append when the block is not mapped. */
+        if (block->host == NULL) {
+            continue;
+        }
+        if (host - block->host < block->max_length) {
+            goto found;
+        }
+    }
+
+    return NULL;
+
+found:
+    *offset = (host - block->host);
+    if (round_offset) {
+        *offset &= TARGET_PAGE_MASK;
+    }
+    return block;
+}
+
+/*
+ * Finds the named RAMBlock
+ *
+ * name: The name of RAMBlock to find
+ *
+ * Returns: RAMBlock (or NULL if not found)
+ */
+RAMBlock *qemu_ram_block_by_name(const char *name)
+{
+    RAMBlock *block;
+
+    RAMBLOCK_FOREACH(block) {
+        if (!strcmp(name, block->idstr)) {
+            return block;
+        }
+    }
+
+    return NULL;
+}
+
+/* Some of the softmmu routines need to translate from a host pointer
+   (typically a TLB entry) back to a ram offset.  */
+ram_addr_t qemu_ram_addr_from_host(void *ptr)
+{
+    RAMBlock *block;
+    ram_addr_t offset;
+
+    block = qemu_ram_block_from_host(ptr, false, &offset);
+    if (!block) {
+        return RAM_ADDR_INVALID;
+    }
+
+    return block->offset + offset;
+}
+
+/* Generate a debug exception if a watchpoint has been hit.  */
+void cpu_check_watchpoint(CPUState *cpu, vaddr addr, vaddr len,
+                          MemTxAttrs attrs, int flags, uintptr_t ra)
+{
+    CPUClass *cc = CPU_GET_CLASS(cpu);
+    CPUWatchpoint *wp;
+
+    assert(tcg_enabled());
+    if (cpu->watchpoint_hit) {
+        /*
+         * We re-entered the check after replacing the TB.
+         * Now raise the debug interrupt so that it will
+         * trigger after the current instruction.
+         */
+        qemu_mutex_lock_iothread();
+        cpu_interrupt(cpu, CPU_INTERRUPT_DEBUG);
+        qemu_mutex_unlock_iothread();
+        return;
+    }
+
+    addr = cc->adjust_watchpoint_address(cpu, addr, len);
+    QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) {
+        if (watchpoint_address_matches(wp, addr, len)
+            && (wp->flags & flags)) {
+            if (replay_running_debug()) {
+                /*
+                 * Don't process the watchpoints when we are
+                 * in a reverse debugging operation.
+                 */
+                replay_breakpoint();
+                return;
+            }
+            if (flags == BP_MEM_READ) {
+                wp->flags |= BP_WATCHPOINT_HIT_READ;
+            } else {
+                wp->flags |= BP_WATCHPOINT_HIT_WRITE;
+            }
+            wp->hitaddr = MAX(addr, wp->vaddr);
+            wp->hitattrs = attrs;
+            if (!cpu->watchpoint_hit) {
+                if (wp->flags & BP_CPU &&
+                    !cc->debug_check_watchpoint(cpu, wp)) {
+                    wp->flags &= ~BP_WATCHPOINT_HIT;
+                    continue;
+                }
+                cpu->watchpoint_hit = wp;
+
+                mmap_lock();
+                tb_check_watchpoint(cpu, ra);
+                if (wp->flags & BP_STOP_BEFORE_ACCESS) {
+                    cpu->exception_index = EXCP_DEBUG;
+                    mmap_unlock();
+                    cpu_loop_exit_restore(cpu, ra);
+                } else {
+                    /* Force execution of one insn next time.  */
+                    cpu->cflags_next_tb = 1 | curr_cflags();
+                    mmap_unlock();
+                    if (ra) {
+                        cpu_restore_state(cpu, ra, true);
+                    }
+                    cpu_loop_exit_noexc(cpu);
+                }
+            }
+        } else {
+            wp->flags &= ~BP_WATCHPOINT_HIT;
+        }
+    }
+}
+
+static MemTxResult flatview_read(FlatView *fv, hwaddr addr,
+                                 MemTxAttrs attrs, void *buf, hwaddr len);
+static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs,
+                                  const void *buf, hwaddr len);
+static bool flatview_access_valid(FlatView *fv, hwaddr addr, hwaddr len,
+                                  bool is_write, MemTxAttrs attrs);
+
+static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data,
+                                unsigned len, MemTxAttrs attrs)
+{
+    subpage_t *subpage = opaque;
+    uint8_t buf[8];
+    MemTxResult res;
+
+#if defined(DEBUG_SUBPAGE)
+    printf("%s: subpage %p len %u addr " TARGET_FMT_plx "\n", __func__,
+           subpage, len, addr);
+#endif
+    res = flatview_read(subpage->fv, addr + subpage->base, attrs, buf, len);
+    if (res) {
+        return res;
+    }
+    *data = ldn_p(buf, len);
+    return MEMTX_OK;
+}
+
+static MemTxResult subpage_write(void *opaque, hwaddr addr,
+                                 uint64_t value, unsigned len, MemTxAttrs attrs)
+{
+    subpage_t *subpage = opaque;
+    uint8_t buf[8];
+
+#if defined(DEBUG_SUBPAGE)
+    printf("%s: subpage %p len %u addr " TARGET_FMT_plx
+           " value %"PRIx64"\n",
+           __func__, subpage, len, addr, value);
+#endif
+    stn_p(buf, len, value);
+    return flatview_write(subpage->fv, addr + subpage->base, attrs, buf, len);
+}
+
+static bool subpage_accepts(void *opaque, hwaddr addr,
+                            unsigned len, bool is_write,
+                            MemTxAttrs attrs)
+{
+    subpage_t *subpage = opaque;
+#if defined(DEBUG_SUBPAGE)
+    printf("%s: subpage %p %c len %u addr " TARGET_FMT_plx "\n",
+           __func__, subpage, is_write ? 'w' : 'r', len, addr);
+#endif
+
+    return flatview_access_valid(subpage->fv, addr + subpage->base,
+                                 len, is_write, attrs);
+}
+
+static const MemoryRegionOps subpage_ops = {
+    .read_with_attrs = subpage_read,
+    .write_with_attrs = subpage_write,
+    .impl.min_access_size = 1,
+    .impl.max_access_size = 8,
+    .valid.min_access_size = 1,
+    .valid.max_access_size = 8,
+    .valid.accepts = subpage_accepts,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static int subpage_register(subpage_t *mmio, uint32_t start, uint32_t end,
+                            uint16_t section)
+{
+    int idx, eidx;
+
+    if (start >= TARGET_PAGE_SIZE || end >= TARGET_PAGE_SIZE)
+        return -1;
+    idx = SUBPAGE_IDX(start);
+    eidx = SUBPAGE_IDX(end);
+#if defined(DEBUG_SUBPAGE)
+    printf("%s: %p start %08x end %08x idx %08x eidx %08x section %d\n",
+           __func__, mmio, start, end, idx, eidx, section);
+#endif
+    for (; idx <= eidx; idx++) {
+        mmio->sub_section[idx] = section;
+    }
+
+    return 0;
+}
+
+static subpage_t *subpage_init(FlatView *fv, hwaddr base)
+{
+    subpage_t *mmio;
+
+    /* mmio->sub_section is set to PHYS_SECTION_UNASSIGNED with g_malloc0 */
+    mmio = g_malloc0(sizeof(subpage_t) + TARGET_PAGE_SIZE * sizeof(uint16_t));
+    mmio->fv = fv;
+    mmio->base = base;
+    memory_region_init_io(&mmio->iomem, NULL, &subpage_ops, mmio,
+                          NULL, TARGET_PAGE_SIZE);
+    mmio->iomem.subpage = true;
+#if defined(DEBUG_SUBPAGE)
+    printf("%s: %p base " TARGET_FMT_plx " len %08x\n", __func__,
+           mmio, base, TARGET_PAGE_SIZE);
+#endif
+
+    return mmio;
+}
+
+static uint16_t dummy_section(PhysPageMap *map, FlatView *fv, MemoryRegion *mr)
+{
+    assert(fv);
+    MemoryRegionSection section = {
+        .fv = fv,
+        .mr = mr,
+        .offset_within_address_space = 0,
+        .offset_within_region = 0,
+        .size = int128_2_64(),
+    };
+
+    return phys_section_add(map, &section);
+}
+
+MemoryRegionSection *iotlb_to_section(CPUState *cpu,
+                                      hwaddr index, MemTxAttrs attrs)
+{
+    int asidx = cpu_asidx_from_attrs(cpu, attrs);
+    CPUAddressSpace *cpuas = &cpu->cpu_ases[asidx];
+    AddressSpaceDispatch *d = qatomic_rcu_read(&cpuas->memory_dispatch);
+    MemoryRegionSection *sections = d->map.sections;
+
+    return &sections[index & ~TARGET_PAGE_MASK];
+}
+
+static void io_mem_init(void)
+{
+    memory_region_init_io(&io_mem_unassigned, NULL, &unassigned_mem_ops, NULL,
+                          NULL, UINT64_MAX);
+}
+
+AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv)
+{
+    AddressSpaceDispatch *d = g_new0(AddressSpaceDispatch, 1);
+    uint16_t n;
+
+    n = dummy_section(&d->map, fv, &io_mem_unassigned);
+    assert(n == PHYS_SECTION_UNASSIGNED);
+
+    d->phys_map  = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .skip = 1 };
+
+    return d;
+}
+
+void address_space_dispatch_free(AddressSpaceDispatch *d)
+{
+    phys_sections_free(&d->map);
+    g_free(d);
+}
+
+static void do_nothing(CPUState *cpu, run_on_cpu_data d)
+{
+}
+
+static void tcg_log_global_after_sync(MemoryListener *listener)
+{
+    CPUAddressSpace *cpuas;
+
+    /* Wait for the CPU to end the current TB.  This avoids the following
+     * incorrect race:
+     *
+     *      vCPU                         migration
+     *      ----------------------       -------------------------
+     *      TLB check -> slow path
+     *        notdirty_mem_write
+     *          write to RAM
+     *          mark dirty
+     *                                   clear dirty flag
+     *      TLB check -> fast path
+     *                                   read memory
+     *        write to RAM
+     *
+     * by pushing the migration thread's memory read after the vCPU thread has
+     * written the memory.
+     */
+    if (replay_mode == REPLAY_MODE_NONE) {
+        /*
+         * VGA can make calls to this function while updating the screen.
+         * In record/replay mode this causes a deadlock, because
+         * run_on_cpu waits for rr mutex. Therefore no races are possible
+         * in this case and no need for making run_on_cpu when
+         * record/replay is not enabled.
+         */
+        cpuas = container_of(listener, CPUAddressSpace, tcg_as_listener);
+        run_on_cpu(cpuas->cpu, do_nothing, RUN_ON_CPU_NULL);
+    }
+}
+
+static void tcg_commit(MemoryListener *listener)
+{
+    CPUAddressSpace *cpuas;
+    AddressSpaceDispatch *d;
+
+    assert(tcg_enabled());
+    /* since each CPU stores ram addresses in its TLB cache, we must
+       reset the modified entries */
+    cpuas = container_of(listener, CPUAddressSpace, tcg_as_listener);
+    cpu_reloading_memory_map();
+    /* The CPU and TLB are protected by the iothread lock.
+     * We reload the dispatch pointer now because cpu_reloading_memory_map()
+     * may have split the RCU critical section.
+     */
+    d = address_space_to_dispatch(cpuas->as);
+    qatomic_rcu_set(&cpuas->memory_dispatch, d);
+    tlb_flush(cpuas->cpu);
+}
+
+static void memory_map_init(void)
+{
+    system_memory = g_malloc(sizeof(*system_memory));
+
+    memory_region_init(system_memory, NULL, "system", UINT64_MAX);
+    address_space_init(&address_space_memory, system_memory, "memory");
+
+    system_io = g_malloc(sizeof(*system_io));
+    memory_region_init_io(system_io, NULL, &unassigned_io_ops, NULL, "io",
+                          65536);
+    address_space_init(&address_space_io, system_io, "I/O");
+}
+
+MemoryRegion *get_system_memory(void)
+{
+    return system_memory;
+}
+
+MemoryRegion *get_system_io(void)
+{
+    return system_io;
+}
+
+static void invalidate_and_set_dirty(MemoryRegion *mr, hwaddr addr,
+                                     hwaddr length)
+{
+    uint8_t dirty_log_mask = memory_region_get_dirty_log_mask(mr);
+    addr += memory_region_get_ram_addr(mr);
+
+    /* No early return if dirty_log_mask is or becomes 0, because
+     * cpu_physical_memory_set_dirty_range will still call
+     * xen_modified_memory.
+     */
+    if (dirty_log_mask) {
+        dirty_log_mask =
+            cpu_physical_memory_range_includes_clean(addr, length, dirty_log_mask);
+    }
+    if (dirty_log_mask & (1 << DIRTY_MEMORY_CODE)) {
+        assert(tcg_enabled());
+        tb_invalidate_phys_range(addr, addr + length);
+        dirty_log_mask &= ~(1 << DIRTY_MEMORY_CODE);
+    }
+    cpu_physical_memory_set_dirty_range(addr, length, dirty_log_mask);
+}
+
+void memory_region_flush_rom_device(MemoryRegion *mr, hwaddr addr, hwaddr size)
+{
+    /*
+     * In principle this function would work on other memory region types too,
+     * but the ROM device use case is the only one where this operation is
+     * necessary.  Other memory regions should use the
+     * address_space_read/write() APIs.
+     */
+    assert(memory_region_is_romd(mr));
+
+    invalidate_and_set_dirty(mr, addr, size);
+}
+
+static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
+{
+    unsigned access_size_max = mr->ops->valid.max_access_size;
+
+    /* Regions are assumed to support 1-4 byte accesses unless
+       otherwise specified.  */
+    if (access_size_max == 0) {
+        access_size_max = 4;
+    }
+
+    /* Bound the maximum access by the alignment of the address.  */
+    if (!mr->ops->impl.unaligned) {
+        unsigned align_size_max = addr & -addr;
+        if (align_size_max != 0 && align_size_max < access_size_max) {
+            access_size_max = align_size_max;
+        }
+    }
+
+    /* Don't attempt accesses larger than the maximum.  */
+    if (l > access_size_max) {
+        l = access_size_max;
+    }
+    l = pow2floor(l);
+
+    return l;
+}
+
+static bool prepare_mmio_access(MemoryRegion *mr)
+{
+    bool unlocked = !qemu_mutex_iothread_locked();
+    bool release_lock = false;
+
+    if (unlocked) {
+        qemu_mutex_lock_iothread();
+        unlocked = false;
+        release_lock = true;
+    }
+    if (mr->flush_coalesced_mmio) {
+        if (unlocked) {
+            qemu_mutex_lock_iothread();
+        }
+        qemu_flush_coalesced_mmio_buffer();
+        if (unlocked) {
+            qemu_mutex_unlock_iothread();
+        }
+    }
+
+    return release_lock;
+}
+
+/* Called within RCU critical section.  */
+static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr,
+                                           MemTxAttrs attrs,
+                                           const void *ptr,
+                                           hwaddr len, hwaddr addr1,
+                                           hwaddr l, MemoryRegion *mr)
+{
+    uint8_t *ram_ptr;
+    uint64_t val;
+    MemTxResult result = MEMTX_OK;
+    bool release_lock = false;
+    const uint8_t *buf = ptr;
+
+    for (;;) {
+        if (!memory_access_is_direct(mr, true)) {
+            release_lock |= prepare_mmio_access(mr);
+            l = memory_access_size(mr, l, addr1);
+            /* XXX: could force current_cpu to NULL to avoid
+               potential bugs */
+            val = ldn_he_p(buf, l);
+            result |= memory_region_dispatch_write(mr, addr1, val,
+                                                   size_memop(l), attrs);
+        } else {
+            /* RAM case */
+            ram_ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
+            memcpy(ram_ptr, buf, l);
+            invalidate_and_set_dirty(mr, addr1, l);
+        }
+
+        if (release_lock) {
+            qemu_mutex_unlock_iothread();
+            release_lock = false;
+        }
+
+        len -= l;
+        buf += l;
+        addr += l;
+
+        if (!len) {
+            break;
+        }
+
+        l = len;
+        mr = flatview_translate(fv, addr, &addr1, &l, true, attrs);
+    }
+
+    return result;
+}
+
+/* Called from RCU critical section.  */
+static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs,
+                                  const void *buf, hwaddr len)
+{
+    hwaddr l;
+    hwaddr addr1;
+    MemoryRegion *mr;
+    MemTxResult result = MEMTX_OK;
+
+    l = len;
+    mr = flatview_translate(fv, addr, &addr1, &l, true, attrs);
+    result = flatview_write_continue(fv, addr, attrs, buf, len,
+                                     addr1, l, mr);
+
+    return result;
+}
+
+/* Called within RCU critical section.  */
+MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr,
+                                   MemTxAttrs attrs, void *ptr,
+                                   hwaddr len, hwaddr addr1, hwaddr l,
+                                   MemoryRegion *mr)
+{
+    uint8_t *ram_ptr;
+    uint64_t val;
+    MemTxResult result = MEMTX_OK;
+    bool release_lock = false;
+    uint8_t *buf = ptr;
+
+    for (;;) {
+        if (!memory_access_is_direct(mr, false)) {
+            /* I/O case */
+            release_lock |= prepare_mmio_access(mr);
+            l = memory_access_size(mr, l, addr1);
+            result |= memory_region_dispatch_read(mr, addr1, &val,
+                                                  size_memop(l), attrs);
+            stn_he_p(buf, l, val);
+        } else {
+            /* RAM case */
+            ram_ptr = qemu_ram_ptr_length(mr->ram_block, addr1, &l, false);
+            memcpy(buf, ram_ptr, l);
+        }
+
+        if (release_lock) {
+            qemu_mutex_unlock_iothread();
+            release_lock = false;
+        }
+
+        len -= l;
+        buf += l;
+        addr += l;
+
+        if (!len) {
+            break;
+        }
+
+        l = len;
+        mr = flatview_translate(fv, addr, &addr1, &l, false, attrs);
+    }
+
+    return result;
+}
+
+/* Called from RCU critical section.  */
+static MemTxResult flatview_read(FlatView *fv, hwaddr addr,
+                                 MemTxAttrs attrs, void *buf, hwaddr len)
+{
+    hwaddr l;
+    hwaddr addr1;
+    MemoryRegion *mr;
+
+    l = len;
+    mr = flatview_translate(fv, addr, &addr1, &l, false, attrs);
+    return flatview_read_continue(fv, addr, attrs, buf, len,
+                                  addr1, l, mr);
+}
+
+MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
+                                    MemTxAttrs attrs, void *buf, hwaddr len)
+{
+    MemTxResult result = MEMTX_OK;
+    FlatView *fv;
+
+    if (len > 0) {
+        RCU_READ_LOCK_GUARD();
+        fv = address_space_to_flatview(as);
+        result = flatview_read(fv, addr, attrs, buf, len);
+    }
+
+    return result;
+}
+
+MemTxResult address_space_write(AddressSpace *as, hwaddr addr,
+                                MemTxAttrs attrs,
+                                const void *buf, hwaddr len)
+{
+    MemTxResult result = MEMTX_OK;
+    FlatView *fv;
+
+    if (len > 0) {
+        RCU_READ_LOCK_GUARD();
+        fv = address_space_to_flatview(as);
+        result = flatview_write(fv, addr, attrs, buf, len);
+    }
+
+    return result;
+}
+
+MemTxResult address_space_rw(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
+                             void *buf, hwaddr len, bool is_write)
+{
+    if (is_write) {
+        return address_space_write(as, addr, attrs, buf, len);
+    } else {
+        return address_space_read_full(as, addr, attrs, buf, len);
+    }
+}
+
+void cpu_physical_memory_rw(hwaddr addr, void *buf,
+                            hwaddr len, bool is_write)
+{
+    address_space_rw(&address_space_memory, addr, MEMTXATTRS_UNSPECIFIED,
+                     buf, len, is_write);
+}
+
+enum write_rom_type {
+    WRITE_DATA,
+    FLUSH_CACHE,
+};
+
+static inline MemTxResult address_space_write_rom_internal(AddressSpace *as,
+                                                           hwaddr addr,
+                                                           MemTxAttrs attrs,
+                                                           const void *ptr,
+                                                           hwaddr len,
+                                                           enum write_rom_type type)
+{
+    hwaddr l;
+    uint8_t *ram_ptr;
+    hwaddr addr1;
+    MemoryRegion *mr;
+    const uint8_t *buf = ptr;
+
+    RCU_READ_LOCK_GUARD();
+    while (len > 0) {
+        l = len;
+        mr = address_space_translate(as, addr, &addr1, &l, true, attrs);
+
+        if (!(memory_region_is_ram(mr) ||
+              memory_region_is_romd(mr))) {
+            l = memory_access_size(mr, l, addr1);
+        } else {
+            /* ROM/RAM case */
+            ram_ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
+            switch (type) {
+            case WRITE_DATA:
+                memcpy(ram_ptr, buf, l);
+                invalidate_and_set_dirty(mr, addr1, l);
+                break;
+            case FLUSH_CACHE:
+                flush_icache_range((uintptr_t)ram_ptr, (uintptr_t)ram_ptr + l);
+                break;
+            }
+        }
+        len -= l;
+        buf += l;
+        addr += l;
+    }
+    return MEMTX_OK;
+}
+
+/* used for ROM loading : can write in RAM and ROM */
+MemTxResult address_space_write_rom(AddressSpace *as, hwaddr addr,
+                                    MemTxAttrs attrs,
+                                    const void *buf, hwaddr len)
+{
+    return address_space_write_rom_internal(as, addr, attrs,
+                                            buf, len, WRITE_DATA);
+}
+
+void cpu_flush_icache_range(hwaddr start, hwaddr len)
+{
+    /*
+     * This function should do the same thing as an icache flush that was
+     * triggered from within the guest. For TCG we are always cache coherent,
+     * so there is no need to flush anything. For KVM / Xen we need to flush
+     * the host's instruction cache at least.
+     */
+    if (tcg_enabled()) {
+        return;
+    }
+
+    address_space_write_rom_internal(&address_space_memory,
+                                     start, MEMTXATTRS_UNSPECIFIED,
+                                     NULL, len, FLUSH_CACHE);
+}
+
+typedef struct {
+    MemoryRegion *mr;
+    void *buffer;
+    hwaddr addr;
+    hwaddr len;
+    bool in_use;
+} BounceBuffer;
+
+static BounceBuffer bounce;
+
+typedef struct MapClient {
+    QEMUBH *bh;
+    QLIST_ENTRY(MapClient) link;
+} MapClient;
+
+QemuMutex map_client_list_lock;
+static QLIST_HEAD(, MapClient) map_client_list
+    = QLIST_HEAD_INITIALIZER(map_client_list);
+
+static void cpu_unregister_map_client_do(MapClient *client)
+{
+    QLIST_REMOVE(client, link);
+    g_free(client);
+}
+
+static void cpu_notify_map_clients_locked(void)
+{
+    MapClient *client;
+
+    while (!QLIST_EMPTY(&map_client_list)) {
+        client = QLIST_FIRST(&map_client_list);
+        qemu_bh_schedule(client->bh);
+        cpu_unregister_map_client_do(client);
+    }
+}
+
+void cpu_register_map_client(QEMUBH *bh)
+{
+    MapClient *client = g_malloc(sizeof(*client));
+
+    qemu_mutex_lock(&map_client_list_lock);
+    client->bh = bh;
+    QLIST_INSERT_HEAD(&map_client_list, client, link);
+    if (!qatomic_read(&bounce.in_use)) {
+        cpu_notify_map_clients_locked();
+    }
+    qemu_mutex_unlock(&map_client_list_lock);
+}
+
+void cpu_exec_init_all(void)
+{
+    qemu_mutex_init(&ram_list.mutex);
+    /* The data structures we set up here depend on knowing the page size,
+     * so no more changes can be made after this point.
+     * In an ideal world, nothing we did before we had finished the
+     * machine setup would care about the target page size, and we could
+     * do this much later, rather than requiring board models to state
+     * up front what their requirements are.
+     */
+    finalize_target_page_bits();
+    io_mem_init();
+    memory_map_init();
+    qemu_mutex_init(&map_client_list_lock);
+}
+
+void cpu_unregister_map_client(QEMUBH *bh)
+{
+    MapClient *client;
+
+    qemu_mutex_lock(&map_client_list_lock);
+    QLIST_FOREACH(client, &map_client_list, link) {
+        if (client->bh == bh) {
+            cpu_unregister_map_client_do(client);
+            break;
+        }
+    }
+    qemu_mutex_unlock(&map_client_list_lock);
+}
+
+static void cpu_notify_map_clients(void)
+{
+    qemu_mutex_lock(&map_client_list_lock);
+    cpu_notify_map_clients_locked();
+    qemu_mutex_unlock(&map_client_list_lock);
+}
+
+static bool flatview_access_valid(FlatView *fv, hwaddr addr, hwaddr len,
+                                  bool is_write, MemTxAttrs attrs)
+{
+    MemoryRegion *mr;
+    hwaddr l, xlat;
+
+    while (len > 0) {
+        l = len;
+        mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs);
+        if (!memory_access_is_direct(mr, is_write)) {
+            l = memory_access_size(mr, l, addr);
+            if (!memory_region_access_valid(mr, xlat, l, is_write, attrs)) {
+                return false;
+            }
+        }
+
+        len -= l;
+        addr += l;
+    }
+    return true;
+}
+
+bool address_space_access_valid(AddressSpace *as, hwaddr addr,
+                                hwaddr len, bool is_write,
+                                MemTxAttrs attrs)
+{
+    FlatView *fv;
+    bool result;
+
+    RCU_READ_LOCK_GUARD();
+    fv = address_space_to_flatview(as);
+    result = flatview_access_valid(fv, addr, len, is_write, attrs);
+    return result;
+}
+
+static hwaddr
+flatview_extend_translation(FlatView *fv, hwaddr addr,
+                            hwaddr target_len,
+                            MemoryRegion *mr, hwaddr base, hwaddr len,
+                            bool is_write, MemTxAttrs attrs)
+{
+    hwaddr done = 0;
+    hwaddr xlat;
+    MemoryRegion *this_mr;
+
+    for (;;) {
+        target_len -= len;
+        addr += len;
+        done += len;
+        if (target_len == 0) {
+            return done;
+        }
+
+        len = target_len;
+        this_mr = flatview_translate(fv, addr, &xlat,
+                                     &len, is_write, attrs);
+        if (this_mr != mr || xlat != base + done) {
+            return done;
+        }
+    }
+}
+
+/* Map a physical memory region into a host virtual address.
+ * May map a subset of the requested range, given by and returned in *plen.
+ * May return NULL if resources needed to perform the mapping are exhausted.
+ * Use only for reads OR writes - not for read-modify-write operations.
+ * Use cpu_register_map_client() to know when retrying the map operation is
+ * likely to succeed.
+ */
+void *address_space_map(AddressSpace *as,
+                        hwaddr addr,
+                        hwaddr *plen,
+                        bool is_write,
+                        MemTxAttrs attrs)
+{
+    hwaddr len = *plen;
+    hwaddr l, xlat;
+    MemoryRegion *mr;
+    void *ptr;
+    FlatView *fv;
+
+    if (len == 0) {
+        return NULL;
+    }
+
+    l = len;
+    RCU_READ_LOCK_GUARD();
+    fv = address_space_to_flatview(as);
+    mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs);
+
+    if (!memory_access_is_direct(mr, is_write)) {
+        if (qatomic_xchg(&bounce.in_use, true)) {
+            *plen = 0;
+            return NULL;
+        }
+        /* Avoid unbounded allocations */
+        l = MIN(l, TARGET_PAGE_SIZE);
+        bounce.buffer = qemu_memalign(TARGET_PAGE_SIZE, l);
+        bounce.addr = addr;
+        bounce.len = l;
+
+        memory_region_ref(mr);
+        bounce.mr = mr;
+        if (!is_write) {
+            flatview_read(fv, addr, MEMTXATTRS_UNSPECIFIED,
+                               bounce.buffer, l);
+        }
+
+        *plen = l;
+        return bounce.buffer;
+    }
+
+
+    memory_region_ref(mr);
+    *plen = flatview_extend_translation(fv, addr, len, mr, xlat,
+                                        l, is_write, attrs);
+    ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen, true);
+
+    return ptr;
+}
+
+/* Unmaps a memory region previously mapped by address_space_map().
+ * Will also mark the memory as dirty if is_write is true.  access_len gives
+ * the amount of memory that was actually read or written by the caller.
+ */
+void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
+                         bool is_write, hwaddr access_len)
+{
+    if (buffer != bounce.buffer) {
+        MemoryRegion *mr;
+        ram_addr_t addr1;
+
+        mr = memory_region_from_host(buffer, &addr1);
+        assert(mr != NULL);
+        if (is_write) {
+            invalidate_and_set_dirty(mr, addr1, access_len);
+        }
+        if (xen_enabled()) {
+            xen_invalidate_map_cache_entry(buffer);
+        }
+        memory_region_unref(mr);
+        return;
+    }
+    if (is_write) {
+        address_space_write(as, bounce.addr, MEMTXATTRS_UNSPECIFIED,
+                            bounce.buffer, access_len);
+    }
+    qemu_vfree(bounce.buffer);
+    bounce.buffer = NULL;
+    memory_region_unref(bounce.mr);
+    qatomic_mb_set(&bounce.in_use, false);
+    cpu_notify_map_clients();
+}
+
+void *cpu_physical_memory_map(hwaddr addr,
+                              hwaddr *plen,
+                              bool is_write)
+{
+    return address_space_map(&address_space_memory, addr, plen, is_write,
+                             MEMTXATTRS_UNSPECIFIED);
+}
+
+void cpu_physical_memory_unmap(void *buffer, hwaddr len,
+                               bool is_write, hwaddr access_len)
+{
+    return address_space_unmap(&address_space_memory, buffer, len, is_write, access_len);
+}
+
+#define ARG1_DECL                AddressSpace *as
+#define ARG1                     as
+#define SUFFIX
+#define TRANSLATE(...)           address_space_translate(as, __VA_ARGS__)
+#define RCU_READ_LOCK(...)       rcu_read_lock()
+#define RCU_READ_UNLOCK(...)     rcu_read_unlock()
+#include "memory_ldst.c.inc"
+
+int64_t address_space_cache_init(MemoryRegionCache *cache,
+                                 AddressSpace *as,
+                                 hwaddr addr,
+                                 hwaddr len,
+                                 bool is_write)
+{
+    AddressSpaceDispatch *d;
+    hwaddr l;
+    MemoryRegion *mr;
+
+    assert(len > 0);
+
+    l = len;
+    cache->fv = address_space_get_flatview(as);
+    d = flatview_to_dispatch(cache->fv);
+    cache->mrs = *address_space_translate_internal(d, addr, &cache->xlat, &l, true);
+
+    mr = cache->mrs.mr;
+    memory_region_ref(mr);
+    if (memory_access_is_direct(mr, is_write)) {
+        /* We don't care about the memory attributes here as we're only
+         * doing this if we found actual RAM, which behaves the same
+         * regardless of attributes; so UNSPECIFIED is fine.
+         */
+        l = flatview_extend_translation(cache->fv, addr, len, mr,
+                                        cache->xlat, l, is_write,
+                                        MEMTXATTRS_UNSPECIFIED);
+        cache->ptr = qemu_ram_ptr_length(mr->ram_block, cache->xlat, &l, true);
+    } else {
+        cache->ptr = NULL;
+    }
+
+    cache->len = l;
+    cache->is_write = is_write;
+    return l;
+}
+
+void address_space_cache_invalidate(MemoryRegionCache *cache,
+                                    hwaddr addr,
+                                    hwaddr access_len)
+{
+    assert(cache->is_write);
+    if (likely(cache->ptr)) {
+        invalidate_and_set_dirty(cache->mrs.mr, addr + cache->xlat, access_len);
+    }
+}
+
+void address_space_cache_destroy(MemoryRegionCache *cache)
+{
+    if (!cache->mrs.mr) {
+        return;
+    }
+
+    if (xen_enabled()) {
+        xen_invalidate_map_cache_entry(cache->ptr);
+    }
+    memory_region_unref(cache->mrs.mr);
+    flatview_unref(cache->fv);
+    cache->mrs.mr = NULL;
+    cache->fv = NULL;
+}
+
+/* Called from RCU critical section.  This function has the same
+ * semantics as address_space_translate, but it only works on a
+ * predefined range of a MemoryRegion that was mapped with
+ * address_space_cache_init.
+ */
+static inline MemoryRegion *address_space_translate_cached(
+    MemoryRegionCache *cache, hwaddr addr, hwaddr *xlat,
+    hwaddr *plen, bool is_write, MemTxAttrs attrs)
+{
+    MemoryRegionSection section;
+    MemoryRegion *mr;
+    IOMMUMemoryRegion *iommu_mr;
+    AddressSpace *target_as;
+
+    assert(!cache->ptr);
+    *xlat = addr + cache->xlat;
+
+    mr = cache->mrs.mr;
+    iommu_mr = memory_region_get_iommu(mr);
+    if (!iommu_mr) {
+        /* MMIO region.  */
+        return mr;
+    }
+
+    section = address_space_translate_iommu(iommu_mr, xlat, plen,
+                                            NULL, is_write, true,
+                                            &target_as, attrs);
+    return section.mr;
+}
+
+/* Called from RCU critical section. address_space_read_cached uses this
+ * out of line function when the target is an MMIO or IOMMU region.
+ */
+MemTxResult
+address_space_read_cached_slow(MemoryRegionCache *cache, hwaddr addr,
+                                   void *buf, hwaddr len)
+{
+    hwaddr addr1, l;
+    MemoryRegion *mr;
+
+    l = len;
+    mr = address_space_translate_cached(cache, addr, &addr1, &l, false,
+                                        MEMTXATTRS_UNSPECIFIED);
+    return flatview_read_continue(cache->fv,
+                                  addr, MEMTXATTRS_UNSPECIFIED, buf, len,
+                                  addr1, l, mr);
+}
+
+/* Called from RCU critical section. address_space_write_cached uses this
+ * out of line function when the target is an MMIO or IOMMU region.
+ */
+MemTxResult
+address_space_write_cached_slow(MemoryRegionCache *cache, hwaddr addr,
+                                    const void *buf, hwaddr len)
+{
+    hwaddr addr1, l;
+    MemoryRegion *mr;
+
+    l = len;
+    mr = address_space_translate_cached(cache, addr, &addr1, &l, true,
+                                        MEMTXATTRS_UNSPECIFIED);
+    return flatview_write_continue(cache->fv,
+                                   addr, MEMTXATTRS_UNSPECIFIED, buf, len,
+                                   addr1, l, mr);
+}
+
+#define ARG1_DECL                MemoryRegionCache *cache
+#define ARG1                     cache
+#define SUFFIX                   _cached_slow
+#define TRANSLATE(...)           address_space_translate_cached(cache, __VA_ARGS__)
+#define RCU_READ_LOCK()          ((void)0)
+#define RCU_READ_UNLOCK()        ((void)0)
+#include "memory_ldst.c.inc"
+
+/* virtual memory access for debug (includes writing to ROM) */
+int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
+                        void *ptr, target_ulong len, bool is_write)
+{
+    hwaddr phys_addr;
+    target_ulong l, page;
+    uint8_t *buf = ptr;
+
+    cpu_synchronize_state(cpu);
+    while (len > 0) {
+        int asidx;
+        MemTxAttrs attrs;
+        MemTxResult res;
+
+        page = addr & TARGET_PAGE_MASK;
+        phys_addr = cpu_get_phys_page_attrs_debug(cpu, page, &attrs);
+        asidx = cpu_asidx_from_attrs(cpu, attrs);
+        /* if no physical page mapped, return an error */
+        if (phys_addr == -1)
+            return -1;
+        l = (page + TARGET_PAGE_SIZE) - addr;
+        if (l > len)
+            l = len;
+        phys_addr += (addr & ~TARGET_PAGE_MASK);
+        if (is_write) {
+            res = address_space_write_rom(cpu->cpu_ases[asidx].as, phys_addr,
+                                          attrs, buf, l);
+        } else {
+            res = address_space_read(cpu->cpu_ases[asidx].as, phys_addr,
+                                     attrs, buf, l);
+        }
+        if (res != MEMTX_OK) {
+            return -1;
+        }
+        len -= l;
+        buf += l;
+        addr += l;
+    }
+    return 0;
+}
+
+/*
+ * Allows code that needs to deal with migration bitmaps etc to still be built
+ * target independent.
+ */
+size_t qemu_target_page_size(void)
+{
+    return TARGET_PAGE_SIZE;
+}
+
+int qemu_target_page_bits(void)
+{
+    return TARGET_PAGE_BITS;
+}
+
+int qemu_target_page_bits_min(void)
+{
+    return TARGET_PAGE_BITS_MIN;
+}
+
+bool cpu_physical_memory_is_io(hwaddr phys_addr)
+{
+    MemoryRegion*mr;
+    hwaddr l = 1;
+    bool res;
+
+    RCU_READ_LOCK_GUARD();
+    mr = address_space_translate(&address_space_memory,
+                                 phys_addr, &phys_addr, &l, false,
+                                 MEMTXATTRS_UNSPECIFIED);
+
+    res = !(memory_region_is_ram(mr) || memory_region_is_romd(mr));
+    return res;
+}
+
+int qemu_ram_foreach_block(RAMBlockIterFunc func, void *opaque)
+{
+    RAMBlock *block;
+    int ret = 0;
+
+    RCU_READ_LOCK_GUARD();
+    RAMBLOCK_FOREACH(block) {
+        ret = func(block, opaque);
+        if (ret) {
+            break;
+        }
+    }
+    return ret;
+}
+
+/*
+ * Unmap pages of memory from start to start+length such that
+ * they a) read as 0, b) Trigger whatever fault mechanism
+ * the OS provides for postcopy.
+ * The pages must be unmapped by the end of the function.
+ * Returns: 0 on success, none-0 on failure
+ *
+ */
+int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
+{
+    int ret = -1;
+
+    uint8_t *host_startaddr = rb->host + start;
+
+    if (!QEMU_PTR_IS_ALIGNED(host_startaddr, rb->page_size)) {
+        error_report("ram_block_discard_range: Unaligned start address: %p",
+                     host_startaddr);
+        goto err;
+    }
+
+    if ((start + length) <= rb->used_length) {
+        bool need_madvise, need_fallocate;
+        if (!QEMU_IS_ALIGNED(length, rb->page_size)) {
+            error_report("ram_block_discard_range: Unaligned length: %zx",
+                         length);
+            goto err;
+        }
+
+        errno = ENOTSUP; /* If we are missing MADVISE etc */
+
+        /* The logic here is messy;
+         *    madvise DONTNEED fails for hugepages
+         *    fallocate works on hugepages and shmem
+         */
+        need_madvise = (rb->page_size == qemu_host_page_size);
+        need_fallocate = rb->fd != -1;
+        if (need_fallocate) {
+            /* For a file, this causes the area of the file to be zero'd
+             * if read, and for hugetlbfs also causes it to be unmapped
+             * so a userfault will trigger.
+             */
+#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
+            ret = fallocate(rb->fd, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+                            start, length);
+            if (ret) {
+                ret = -errno;
+                error_report("ram_block_discard_range: Failed to fallocate "
+                             "%s:%" PRIx64 " +%zx (%d)",
+                             rb->idstr, start, length, ret);
+                goto err;
+            }
+#else
+            ret = -ENOSYS;
+            error_report("ram_block_discard_range: fallocate not available/file"
+                         "%s:%" PRIx64 " +%zx (%d)",
+                         rb->idstr, start, length, ret);
+            goto err;
+#endif
+        }
+        if (need_madvise) {
+            /* For normal RAM this causes it to be unmapped,
+             * for shared memory it causes the local mapping to disappear
+             * and to fall back on the file contents (which we just
+             * fallocate'd away).
+             */
+#if defined(CONFIG_MADVISE)
+            ret =  madvise(host_startaddr, length, MADV_DONTNEED);
+            if (ret) {
+                ret = -errno;
+                error_report("ram_block_discard_range: Failed to discard range "
+                             "%s:%" PRIx64 " +%zx (%d)",
+                             rb->idstr, start, length, ret);
+                goto err;
+            }
+#else
+            ret = -ENOSYS;
+            error_report("ram_block_discard_range: MADVISE not available"
+                         "%s:%" PRIx64 " +%zx (%d)",
+                         rb->idstr, start, length, ret);
+            goto err;
+#endif
+        }
+        trace_ram_block_discard_range(rb->idstr, host_startaddr, length,
+                                      need_madvise, need_fallocate, ret);
+    } else {
+        error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
+                     "/%zx/" RAM_ADDR_FMT")",
+                     rb->idstr, start, length, rb->used_length);
+    }
+
+err:
+    return ret;
+}
+
+bool ramblock_is_pmem(RAMBlock *rb)
+{
+    return rb->flags & RAM_PMEM;
+}
+
+static void mtree_print_phys_entries(int start, int end, int skip, int ptr)
+{
+    if (start == end - 1) {
+        qemu_printf("\t%3d      ", start);
+    } else {
+        qemu_printf("\t%3d..%-3d ", start, end - 1);
+    }
+    qemu_printf(" skip=%d ", skip);
+    if (ptr == PHYS_MAP_NODE_NIL) {
+        qemu_printf(" ptr=NIL");
+    } else if (!skip) {
+        qemu_printf(" ptr=#%d", ptr);
+    } else {
+        qemu_printf(" ptr=[%d]", ptr);
+    }
+    qemu_printf("\n");
+}
+
+#define MR_SIZE(size) (int128_nz(size) ? (hwaddr)int128_get64( \
+                           int128_sub((size), int128_one())) : 0)
+
+void mtree_print_dispatch(AddressSpaceDispatch *d, MemoryRegion *root)
+{
+    int i;
+
+    qemu_printf("  Dispatch\n");
+    qemu_printf("    Physical sections\n");
+
+    for (i = 0; i < d->map.sections_nb; ++i) {
+        MemoryRegionSection *s = d->map.sections + i;
+        const char *names[] = { " [unassigned]", " [not dirty]",
+                                " [ROM]", " [watch]" };
+
+        qemu_printf("      #%d @" TARGET_FMT_plx ".." TARGET_FMT_plx
+                    " %s%s%s%s%s",
+            i,
+            s->offset_within_address_space,
+            s->offset_within_address_space + MR_SIZE(s->mr->size),
+            s->mr->name ? s->mr->name : "(noname)",
+            i < ARRAY_SIZE(names) ? names[i] : "",
+            s->mr == root ? " [ROOT]" : "",
+            s == d->mru_section ? " [MRU]" : "",
+            s->mr->is_iommu ? " [iommu]" : "");
+
+        if (s->mr->alias) {
+            qemu_printf(" alias=%s", s->mr->alias->name ?
+                    s->mr->alias->name : "noname");
+        }
+        qemu_printf("\n");
+    }
+
+    qemu_printf("    Nodes (%d bits per level, %d levels) ptr=[%d] skip=%d\n",
+               P_L2_BITS, P_L2_LEVELS, d->phys_map.ptr, d->phys_map.skip);
+    for (i = 0; i < d->map.nodes_nb; ++i) {
+        int j, jprev;
+        PhysPageEntry prev;
+        Node *n = d->map.nodes + i;
+
+        qemu_printf("      [%d]\n", i);
+
+        for (j = 0, jprev = 0, prev = *n[0]; j < ARRAY_SIZE(*n); ++j) {
+            PhysPageEntry *pe = *n + j;
+
+            if (pe->ptr == prev.ptr && pe->skip == prev.skip) {
+                continue;
+            }
+
+            mtree_print_phys_entries(jprev, j, prev.skip, prev.ptr);
+
+            jprev = j;
+            prev = *pe;
+        }
+
+        if (jprev != ARRAY_SIZE(*n)) {
+            mtree_print_phys_entries(jprev, j, prev.skip, prev.ptr);
+        }
+    }
+}
+
+/*
+ * If positive, discarding RAM is disabled. If negative, discarding RAM is
+ * required to work and cannot be disabled.
+ */
+static int ram_block_discard_disabled;
+
+int ram_block_discard_disable(bool state)
+{
+    int old;
+
+    if (!state) {
+        qatomic_dec(&ram_block_discard_disabled);
+        return 0;
+    }
+
+    do {
+        old = qatomic_read(&ram_block_discard_disabled);
+        if (old < 0) {
+            return -EBUSY;
+        }
+    } while (qatomic_cmpxchg(&ram_block_discard_disabled,
+                             old, old + 1) != old);
+    return 0;
+}
+
+int ram_block_discard_require(bool state)
+{
+    int old;
+
+    if (!state) {
+        qatomic_inc(&ram_block_discard_disabled);
+        return 0;
+    }
+
+    do {
+        old = qatomic_read(&ram_block_discard_disabled);
+        if (old > 0) {
+            return -EBUSY;
+        }
+    } while (qatomic_cmpxchg(&ram_block_discard_disabled,
+                             old, old - 1) != old);
+    return 0;
+}
+
+bool ram_block_discard_is_disabled(void)
+{
+    return qatomic_read(&ram_block_discard_disabled) > 0;
+}
+
+bool ram_block_discard_is_required(void)
+{
+    return qatomic_read(&ram_block_discard_disabled) < 0;
+}
diff --git a/softmmu/qdev-monitor.c b/softmmu/qdev-monitor.c
new file mode 100644
index 0000000..bcfb90a
--- /dev/null
+++ b/softmmu/qdev-monitor.c
@@ -0,0 +1,1005 @@
+/*
+ *  Dynamic device configuration and creation.
+ *
+ *  Copyright (c) 2009 CodeSourcery
+ *
+ * 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 "qemu/osdep.h"
+#include "hw/sysbus.h"
+#include "monitor/hmp.h"
+#include "monitor/monitor.h"
+#include "monitor/qdev.h"
+#include "sysemu/arch_init.h"
+#include "qapi/error.h"
+#include "qapi/qapi-commands-qdev.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qerror.h"
+#include "qemu/config-file.h"
+#include "qemu/error-report.h"
+#include "qemu/help_option.h"
+#include "qemu/option.h"
+#include "qemu/qemu-print.h"
+#include "qemu/option_int.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/sysemu.h"
+#include "migration/misc.h"
+#include "migration/migration.h"
+#include "qemu/cutils.h"
+#include "hw/clock.h"
+
+/*
+ * Aliases were a bad idea from the start.  Let's keep them
+ * from spreading further.
+ */
+typedef struct QDevAlias
+{
+    const char *typename;
+    const char *alias;
+    uint32_t arch_mask;
+} QDevAlias;
+
+/* Please keep this table sorted by typename. */
+static const QDevAlias qdev_alias_table[] = {
+    { "AC97", "ac97" }, /* -soundhw name */
+    { "e1000", "e1000-82540em" },
+    { "ES1370", "es1370" }, /* -soundhw name */
+    { "ich9-ahci", "ahci" },
+    { "lsi53c895a", "lsi" },
+    { "virtio-9p-ccw", "virtio-9p", QEMU_ARCH_S390X },
+    { "virtio-9p-pci", "virtio-9p", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-balloon-ccw", "virtio-balloon", QEMU_ARCH_S390X },
+    { "virtio-balloon-pci", "virtio-balloon",
+            QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-blk-ccw", "virtio-blk", QEMU_ARCH_S390X },
+    { "virtio-blk-pci", "virtio-blk", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-gpu-ccw", "virtio-gpu", QEMU_ARCH_S390X },
+    { "virtio-gpu-pci", "virtio-gpu", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-input-host-ccw", "virtio-input-host", QEMU_ARCH_S390X },
+    { "virtio-input-host-pci", "virtio-input-host",
+            QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-iommu-pci", "virtio-iommu", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-keyboard-ccw", "virtio-keyboard", QEMU_ARCH_S390X },
+    { "virtio-keyboard-pci", "virtio-keyboard",
+            QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-mouse-ccw", "virtio-mouse", QEMU_ARCH_S390X },
+    { "virtio-mouse-pci", "virtio-mouse", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-net-ccw", "virtio-net", QEMU_ARCH_S390X },
+    { "virtio-net-pci", "virtio-net", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-rng-ccw", "virtio-rng", QEMU_ARCH_S390X },
+    { "virtio-rng-pci", "virtio-rng", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-scsi-ccw", "virtio-scsi", QEMU_ARCH_S390X },
+    { "virtio-scsi-pci", "virtio-scsi", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-serial-ccw", "virtio-serial", QEMU_ARCH_S390X },
+    { "virtio-serial-pci", "virtio-serial", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { "virtio-tablet-ccw", "virtio-tablet", QEMU_ARCH_S390X },
+    { "virtio-tablet-pci", "virtio-tablet", QEMU_ARCH_ALL & ~QEMU_ARCH_S390X },
+    { }
+};
+
+static const char *qdev_class_get_alias(DeviceClass *dc)
+{
+    const char *typename = object_class_get_name(OBJECT_CLASS(dc));
+    int i;
+
+    for (i = 0; qdev_alias_table[i].typename; i++) {
+        if (qdev_alias_table[i].arch_mask &&
+            !(qdev_alias_table[i].arch_mask & arch_type)) {
+            continue;
+        }
+
+        if (strcmp(qdev_alias_table[i].typename, typename) == 0) {
+            return qdev_alias_table[i].alias;
+        }
+    }
+
+    return NULL;
+}
+
+static bool qdev_class_has_alias(DeviceClass *dc)
+{
+    return (qdev_class_get_alias(dc) != NULL);
+}
+
+static void qdev_print_devinfo(DeviceClass *dc)
+{
+    qemu_printf("name \"%s\"", object_class_get_name(OBJECT_CLASS(dc)));
+    if (dc->bus_type) {
+        qemu_printf(", bus %s", dc->bus_type);
+    }
+    if (qdev_class_has_alias(dc)) {
+        qemu_printf(", alias \"%s\"", qdev_class_get_alias(dc));
+    }
+    if (dc->desc) {
+        qemu_printf(", desc \"%s\"", dc->desc);
+    }
+    if (!dc->user_creatable) {
+        qemu_printf(", no-user");
+    }
+    qemu_printf("\n");
+}
+
+static void qdev_print_devinfos(bool show_no_user)
+{
+    static const char *cat_name[DEVICE_CATEGORY_MAX + 1] = {
+        [DEVICE_CATEGORY_BRIDGE]  = "Controller/Bridge/Hub",
+        [DEVICE_CATEGORY_USB]     = "USB",
+        [DEVICE_CATEGORY_STORAGE] = "Storage",
+        [DEVICE_CATEGORY_NETWORK] = "Network",
+        [DEVICE_CATEGORY_INPUT]   = "Input",
+        [DEVICE_CATEGORY_DISPLAY] = "Display",
+        [DEVICE_CATEGORY_SOUND]   = "Sound",
+        [DEVICE_CATEGORY_MISC]    = "Misc",
+        [DEVICE_CATEGORY_CPU]     = "CPU",
+        [DEVICE_CATEGORY_MAX]     = "Uncategorized",
+    };
+    GSList *list, *elt;
+    int i;
+    bool cat_printed;
+
+    module_load_qom_all();
+    list = object_class_get_list_sorted(TYPE_DEVICE, false);
+
+    for (i = 0; i <= DEVICE_CATEGORY_MAX; i++) {
+        cat_printed = false;
+        for (elt = list; elt; elt = elt->next) {
+            DeviceClass *dc = OBJECT_CLASS_CHECK(DeviceClass, elt->data,
+                                                 TYPE_DEVICE);
+            if ((i < DEVICE_CATEGORY_MAX
+                 ? !test_bit(i, dc->categories)
+                 : !bitmap_empty(dc->categories, DEVICE_CATEGORY_MAX))
+                || (!show_no_user
+                    && !dc->user_creatable)) {
+                continue;
+            }
+            if (!cat_printed) {
+                qemu_printf("%s%s devices:\n", i ? "\n" : "", cat_name[i]);
+                cat_printed = true;
+            }
+            qdev_print_devinfo(dc);
+        }
+    }
+
+    g_slist_free(list);
+}
+
+static int set_property(void *opaque, const char *name, const char *value,
+                        Error **errp)
+{
+    Object *obj = opaque;
+
+    if (strcmp(name, "driver") == 0)
+        return 0;
+    if (strcmp(name, "bus") == 0)
+        return 0;
+
+    if (!object_property_parse(obj, name, value, errp)) {
+        return -1;
+    }
+    return 0;
+}
+
+static const char *find_typename_by_alias(const char *alias)
+{
+    int i;
+
+    for (i = 0; qdev_alias_table[i].alias; i++) {
+        if (qdev_alias_table[i].arch_mask &&
+            !(qdev_alias_table[i].arch_mask & arch_type)) {
+            continue;
+        }
+
+        if (strcmp(qdev_alias_table[i].alias, alias) == 0) {
+            return qdev_alias_table[i].typename;
+        }
+    }
+
+    return NULL;
+}
+
+static DeviceClass *qdev_get_device_class(const char **driver, Error **errp)
+{
+    ObjectClass *oc;
+    DeviceClass *dc;
+    const char *original_name = *driver;
+
+    oc = module_object_class_by_name(*driver);
+    if (!oc) {
+        const char *typename = find_typename_by_alias(*driver);
+
+        if (typename) {
+            *driver = typename;
+            oc = module_object_class_by_name(*driver);
+        }
+    }
+
+    if (!object_class_dynamic_cast(oc, TYPE_DEVICE)) {
+        if (*driver != original_name) {
+            error_setg(errp, "'%s' (alias '%s') is not a valid device model"
+                       " name", original_name, *driver);
+        } else {
+            error_setg(errp, "'%s' is not a valid device model name", *driver);
+        }
+        return NULL;
+    }
+
+    if (object_class_is_abstract(oc)) {
+        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "driver",
+                   "non-abstract device type");
+        return NULL;
+    }
+
+    dc = DEVICE_CLASS(oc);
+    if (!dc->user_creatable ||
+        (qdev_hotplug && !dc->hotpluggable)) {
+        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "driver",
+                   "pluggable device type");
+        return NULL;
+    }
+
+    return dc;
+}
+
+
+int qdev_device_help(QemuOpts *opts)
+{
+    Error *local_err = NULL;
+    const char *driver;
+    ObjectPropertyInfoList *prop_list;
+    ObjectPropertyInfoList *prop;
+    GPtrArray *array;
+    int i;
+
+    driver = qemu_opt_get(opts, "driver");
+    if (driver && is_help_option(driver)) {
+        qdev_print_devinfos(false);
+        return 1;
+    }
+
+    if (!driver || !qemu_opt_has_help_opt(opts)) {
+        return 0;
+    }
+
+    if (!object_class_by_name(driver)) {
+        const char *typename = find_typename_by_alias(driver);
+
+        if (typename) {
+            driver = typename;
+        }
+    }
+
+    prop_list = qmp_device_list_properties(driver, &local_err);
+    if (local_err) {
+        goto error;
+    }
+
+    if (prop_list) {
+        qemu_printf("%s options:\n", driver);
+    } else {
+        qemu_printf("There are no options for %s.\n", driver);
+    }
+    array = g_ptr_array_new();
+    for (prop = prop_list; prop; prop = prop->next) {
+        g_ptr_array_add(array,
+                        object_property_help(prop->value->name,
+                                             prop->value->type,
+                                             prop->value->default_value,
+                                             prop->value->description));
+    }
+    g_ptr_array_sort(array, (GCompareFunc)qemu_pstrcmp0);
+    for (i = 0; i < array->len; i++) {
+        qemu_printf("%s\n", (char *)array->pdata[i]);
+    }
+    g_ptr_array_set_free_func(array, g_free);
+    g_ptr_array_free(array, true);
+    qapi_free_ObjectPropertyInfoList(prop_list);
+    return 1;
+
+error:
+    error_report_err(local_err);
+    return 1;
+}
+
+static Object *qdev_get_peripheral(void)
+{
+    static Object *dev;
+
+    if (dev == NULL) {
+        dev = container_get(qdev_get_machine(), "/peripheral");
+    }
+
+    return dev;
+}
+
+static Object *qdev_get_peripheral_anon(void)
+{
+    static Object *dev;
+
+    if (dev == NULL) {
+        dev = container_get(qdev_get_machine(), "/peripheral-anon");
+    }
+
+    return dev;
+}
+
+static void qbus_error_append_bus_list_hint(DeviceState *dev,
+                                            Error *const *errp)
+{
+    BusState *child;
+    const char *sep = " ";
+
+    error_append_hint(errp, "child buses at \"%s\":",
+                      dev->id ? dev->id : object_get_typename(OBJECT(dev)));
+    QLIST_FOREACH(child, &dev->child_bus, sibling) {
+        error_append_hint(errp, "%s\"%s\"", sep, child->name);
+        sep = ", ";
+    }
+    error_append_hint(errp, "\n");
+}
+
+static void qbus_error_append_dev_list_hint(BusState *bus,
+                                            Error *const *errp)
+{
+    BusChild *kid;
+    const char *sep = " ";
+
+    error_append_hint(errp, "devices at \"%s\":", bus->name);
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        error_append_hint(errp, "%s\"%s\"", sep,
+                          object_get_typename(OBJECT(dev)));
+        if (dev->id) {
+            error_append_hint(errp, "/\"%s\"", dev->id);
+        }
+        sep = ", ";
+    }
+    error_append_hint(errp, "\n");
+}
+
+static BusState *qbus_find_bus(DeviceState *dev, char *elem)
+{
+    BusState *child;
+
+    QLIST_FOREACH(child, &dev->child_bus, sibling) {
+        if (strcmp(child->name, elem) == 0) {
+            return child;
+        }
+    }
+    return NULL;
+}
+
+static DeviceState *qbus_find_dev(BusState *bus, char *elem)
+{
+    BusChild *kid;
+
+    /*
+     * try to match in order:
+     *   (1) instance id, if present
+     *   (2) driver name
+     *   (3) driver alias, if present
+     */
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        if (dev->id  &&  strcmp(dev->id, elem) == 0) {
+            return dev;
+        }
+    }
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        if (strcmp(object_get_typename(OBJECT(dev)), elem) == 0) {
+            return dev;
+        }
+    }
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        DeviceClass *dc = DEVICE_GET_CLASS(dev);
+
+        if (qdev_class_has_alias(dc) &&
+            strcmp(qdev_class_get_alias(dc), elem) == 0) {
+            return dev;
+        }
+    }
+    return NULL;
+}
+
+static inline bool qbus_is_full(BusState *bus)
+{
+    BusClass *bus_class = BUS_GET_CLASS(bus);
+    return bus_class->max_dev && bus->num_children >= bus_class->max_dev;
+}
+
+/*
+ * Search the tree rooted at @bus for a bus.
+ * If @name, search for a bus with that name.  Note that bus names
+ * need not be unique.  Yes, that's screwed up.
+ * Else search for a bus that is a subtype of @bus_typename.
+ * If more than one exists, prefer one that can take another device.
+ * Return the bus if found, else %NULL.
+ */
+static BusState *qbus_find_recursive(BusState *bus, const char *name,
+                                     const char *bus_typename)
+{
+    BusChild *kid;
+    BusState *pick, *child, *ret;
+    bool match;
+
+    assert(name || bus_typename);
+    if (name) {
+        match = !strcmp(bus->name, name);
+    } else {
+        match = !!object_dynamic_cast(OBJECT(bus), bus_typename);
+    }
+
+    if (match && !qbus_is_full(bus)) {
+        return bus;             /* root matches and isn't full */
+    }
+
+    pick = match ? bus : NULL;
+
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        QLIST_FOREACH(child, &dev->child_bus, sibling) {
+            ret = qbus_find_recursive(child, name, bus_typename);
+            if (ret && !qbus_is_full(ret)) {
+                return ret;     /* a descendant matches and isn't full */
+            }
+            if (ret && !pick) {
+                pick = ret;
+            }
+        }
+    }
+
+    /* root or a descendant matches, but is full */
+    return pick;
+}
+
+static BusState *qbus_find(const char *path, Error **errp)
+{
+    DeviceState *dev;
+    BusState *bus;
+    char elem[128];
+    int pos, len;
+
+    /* find start element */
+    if (path[0] == '/') {
+        bus = sysbus_get_default();
+        pos = 0;
+    } else {
+        if (sscanf(path, "%127[^/]%n", elem, &len) != 1) {
+            assert(!path[0]);
+            elem[0] = len = 0;
+        }
+        bus = qbus_find_recursive(sysbus_get_default(), elem, NULL);
+        if (!bus) {
+            error_setg(errp, "Bus '%s' not found", elem);
+            return NULL;
+        }
+        pos = len;
+    }
+
+    for (;;) {
+        assert(path[pos] == '/' || !path[pos]);
+        while (path[pos] == '/') {
+            pos++;
+        }
+        if (path[pos] == '\0') {
+            break;
+        }
+
+        /* find device */
+        if (sscanf(path+pos, "%127[^/]%n", elem, &len) != 1) {
+            g_assert_not_reached();
+            elem[0] = len = 0;
+        }
+        pos += len;
+        dev = qbus_find_dev(bus, elem);
+        if (!dev) {
+            error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+                      "Device '%s' not found", elem);
+            qbus_error_append_dev_list_hint(bus, errp);
+            return NULL;
+        }
+
+        assert(path[pos] == '/' || !path[pos]);
+        while (path[pos] == '/') {
+            pos++;
+        }
+        if (path[pos] == '\0') {
+            /* last specified element is a device.  If it has exactly
+             * one child bus accept it nevertheless */
+            if (dev->num_child_bus == 1) {
+                bus = QLIST_FIRST(&dev->child_bus);
+                break;
+            }
+            if (dev->num_child_bus) {
+                error_setg(errp, "Device '%s' has multiple child buses",
+                           elem);
+                qbus_error_append_bus_list_hint(dev, errp);
+            } else {
+                error_setg(errp, "Device '%s' has no child bus", elem);
+            }
+            return NULL;
+        }
+
+        /* find bus */
+        if (sscanf(path+pos, "%127[^/]%n", elem, &len) != 1) {
+            g_assert_not_reached();
+            elem[0] = len = 0;
+        }
+        pos += len;
+        bus = qbus_find_bus(dev, elem);
+        if (!bus) {
+            error_setg(errp, "Bus '%s' not found", elem);
+            qbus_error_append_bus_list_hint(dev, errp);
+            return NULL;
+        }
+    }
+
+    if (qbus_is_full(bus)) {
+        error_setg(errp, "Bus '%s' is full", path);
+        return NULL;
+    }
+    return bus;
+}
+
+void qdev_set_id(DeviceState *dev, const char *id)
+{
+    if (id) {
+        dev->id = id;
+    }
+
+    if (dev->id) {
+        object_property_add_child(qdev_get_peripheral(), dev->id,
+                                  OBJECT(dev));
+    } else {
+        static int anon_count;
+        gchar *name = g_strdup_printf("device[%d]", anon_count++);
+        object_property_add_child(qdev_get_peripheral_anon(), name,
+                                  OBJECT(dev));
+        g_free(name);
+    }
+}
+
+static int is_failover_device(void *opaque, const char *name, const char *value,
+                        Error **errp)
+{
+    if (strcmp(name, "failover_pair_id") == 0) {
+        QemuOpts *opts = (QemuOpts *)opaque;
+
+        if (qdev_should_hide_device(opts)) {
+            return 1;
+        }
+    }
+
+    return 0;
+}
+
+static bool should_hide_device(QemuOpts *opts)
+{
+    if (qemu_opt_foreach(opts, is_failover_device, opts, NULL) == 0) {
+        return false;
+    }
+    return true;
+}
+
+DeviceState *qdev_device_add(QemuOpts *opts, Error **errp)
+{
+    DeviceClass *dc;
+    const char *driver, *path;
+    DeviceState *dev = NULL;
+    BusState *bus = NULL;
+    bool hide;
+
+    driver = qemu_opt_get(opts, "driver");
+    if (!driver) {
+        error_setg(errp, QERR_MISSING_PARAMETER, "driver");
+        return NULL;
+    }
+
+    /* find driver */
+    dc = qdev_get_device_class(&driver, errp);
+    if (!dc) {
+        return NULL;
+    }
+
+    /* find bus */
+    path = qemu_opt_get(opts, "bus");
+    if (path != NULL) {
+        bus = qbus_find(path, errp);
+        if (!bus) {
+            return NULL;
+        }
+        if (!object_dynamic_cast(OBJECT(bus), dc->bus_type)) {
+            error_setg(errp, "Device '%s' can't go on %s bus",
+                       driver, object_get_typename(OBJECT(bus)));
+            return NULL;
+        }
+    } else if (dc->bus_type != NULL) {
+        bus = qbus_find_recursive(sysbus_get_default(), NULL, dc->bus_type);
+        if (!bus || qbus_is_full(bus)) {
+            error_setg(errp, "No '%s' bus found for device '%s'",
+                       dc->bus_type, driver);
+            return NULL;
+        }
+    }
+    hide = should_hide_device(opts);
+
+    if ((hide || qdev_hotplug) && bus && !qbus_is_hotpluggable(bus)) {
+        error_setg(errp, QERR_BUS_NO_HOTPLUG, bus->name);
+        return NULL;
+    }
+
+    if (hide) {
+        return NULL;
+    }
+
+    if (!migration_is_idle()) {
+        error_setg(errp, "device_add not allowed while migrating");
+        return NULL;
+    }
+
+    /* create device */
+    dev = qdev_new(driver);
+
+    /* Check whether the hotplug is allowed by the machine */
+    if (qdev_hotplug && !qdev_hotplug_allowed(dev, errp)) {
+        goto err_del_dev;
+    }
+
+    if (!bus && qdev_hotplug && !qdev_get_machine_hotplug_handler(dev)) {
+        /* No bus, no machine hotplug handler --> device is not hotpluggable */
+        error_setg(errp, "Device '%s' can not be hotplugged on this machine",
+                   driver);
+        goto err_del_dev;
+    }
+
+    qdev_set_id(dev, qemu_opts_id(opts));
+
+    /* set properties */
+    if (qemu_opt_foreach(opts, set_property, dev, errp)) {
+        goto err_del_dev;
+    }
+
+    dev->opts = opts;
+    if (!qdev_realize(DEVICE(dev), bus, errp)) {
+        dev->opts = NULL;
+        goto err_del_dev;
+    }
+    return dev;
+
+err_del_dev:
+    if (dev) {
+        object_unparent(OBJECT(dev));
+        object_unref(OBJECT(dev));
+    }
+    return NULL;
+}
+
+
+#define qdev_printf(fmt, ...) monitor_printf(mon, "%*s" fmt, indent, "", ## __VA_ARGS__)
+static void qbus_print(Monitor *mon, BusState *bus, int indent);
+
+static void qdev_print_props(Monitor *mon, DeviceState *dev, Property *props,
+                             int indent)
+{
+    if (!props)
+        return;
+    for (; props->name; props++) {
+        char *value;
+        char *legacy_name = g_strdup_printf("legacy-%s", props->name);
+
+        if (object_property_get_type(OBJECT(dev), legacy_name, NULL)) {
+            value = object_property_get_str(OBJECT(dev), legacy_name, NULL);
+        } else {
+            value = object_property_print(OBJECT(dev), props->name, true,
+                                          NULL);
+        }
+        g_free(legacy_name);
+
+        if (!value) {
+            continue;
+        }
+        qdev_printf("%s = %s\n", props->name,
+                    *value ? value : "<null>");
+        g_free(value);
+    }
+}
+
+static void bus_print_dev(BusState *bus, Monitor *mon, DeviceState *dev, int indent)
+{
+    BusClass *bc = BUS_GET_CLASS(bus);
+
+    if (bc->print_dev) {
+        bc->print_dev(mon, dev, indent);
+    }
+}
+
+static void qdev_print(Monitor *mon, DeviceState *dev, int indent)
+{
+    ObjectClass *class;
+    BusState *child;
+    NamedGPIOList *ngl;
+    NamedClockList *ncl;
+
+    qdev_printf("dev: %s, id \"%s\"\n", object_get_typename(OBJECT(dev)),
+                dev->id ? dev->id : "");
+    indent += 2;
+    QLIST_FOREACH(ngl, &dev->gpios, node) {
+        if (ngl->num_in) {
+            qdev_printf("gpio-in \"%s\" %d\n", ngl->name ? ngl->name : "",
+                        ngl->num_in);
+        }
+        if (ngl->num_out) {
+            qdev_printf("gpio-out \"%s\" %d\n", ngl->name ? ngl->name : "",
+                        ngl->num_out);
+        }
+    }
+    QLIST_FOREACH(ncl, &dev->clocks, node) {
+        qdev_printf("clock-%s%s \"%s\" freq_hz=%e\n",
+                    ncl->output ? "out" : "in",
+                    ncl->alias ? " (alias)" : "",
+                    ncl->name,
+                    CLOCK_PERIOD_TO_HZ(1.0 * clock_get(ncl->clock)));
+    }
+    class = object_get_class(OBJECT(dev));
+    do {
+        qdev_print_props(mon, dev, DEVICE_CLASS(class)->props_, indent);
+        class = object_class_get_parent(class);
+    } while (class != object_class_by_name(TYPE_DEVICE));
+    bus_print_dev(dev->parent_bus, mon, dev, indent);
+    QLIST_FOREACH(child, &dev->child_bus, sibling) {
+        qbus_print(mon, child, indent);
+    }
+}
+
+static void qbus_print(Monitor *mon, BusState *bus, int indent)
+{
+    BusChild *kid;
+
+    qdev_printf("bus: %s\n", bus->name);
+    indent += 2;
+    qdev_printf("type %s\n", object_get_typename(OBJECT(bus)));
+    QTAILQ_FOREACH(kid, &bus->children, sibling) {
+        DeviceState *dev = kid->child;
+        qdev_print(mon, dev, indent);
+    }
+}
+#undef qdev_printf
+
+void hmp_info_qtree(Monitor *mon, const QDict *qdict)
+{
+    if (sysbus_get_default())
+        qbus_print(mon, sysbus_get_default(), 0);
+}
+
+void hmp_info_qdm(Monitor *mon, const QDict *qdict)
+{
+    qdev_print_devinfos(true);
+}
+
+void qmp_device_add(QDict *qdict, QObject **ret_data, Error **errp)
+{
+    QemuOpts *opts;
+    DeviceState *dev;
+
+    opts = qemu_opts_from_qdict(qemu_find_opts("device"), qdict, errp);
+    if (!opts) {
+        return;
+    }
+    if (!monitor_cur_is_qmp() && qdev_device_help(opts)) {
+        qemu_opts_del(opts);
+        return;
+    }
+    dev = qdev_device_add(opts, errp);
+
+    /*
+     * Drain all pending RCU callbacks. This is done because
+     * some bus related operations can delay a device removal
+     * (in this case this can happen if device is added and then
+     * removed due to a configuration error)
+     * to a RCU callback, but user might expect that this interface
+     * will finish its job completely once qmp command returns result
+     * to the user
+     */
+    drain_call_rcu();
+
+    if (!dev) {
+        qemu_opts_del(opts);
+        return;
+    }
+    object_unref(OBJECT(dev));
+}
+
+static DeviceState *find_device_state(const char *id, Error **errp)
+{
+    Object *obj;
+
+    if (id[0] == '/') {
+        obj = object_resolve_path(id, NULL);
+    } else {
+        char *root_path = object_get_canonical_path(qdev_get_peripheral());
+        char *path = g_strdup_printf("%s/%s", root_path, id);
+
+        g_free(root_path);
+        obj = object_resolve_path_type(path, TYPE_DEVICE, NULL);
+        g_free(path);
+    }
+
+    if (!obj) {
+        error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+                  "Device '%s' not found", id);
+        return NULL;
+    }
+
+    if (!object_dynamic_cast(obj, TYPE_DEVICE)) {
+        error_setg(errp, "%s is not a hotpluggable device", id);
+        return NULL;
+    }
+
+    return DEVICE(obj);
+}
+
+void qdev_unplug(DeviceState *dev, Error **errp)
+{
+    DeviceClass *dc = DEVICE_GET_CLASS(dev);
+    HotplugHandler *hotplug_ctrl;
+    HotplugHandlerClass *hdc;
+    Error *local_err = NULL;
+
+    if (dev->parent_bus && !qbus_is_hotpluggable(dev->parent_bus)) {
+        error_setg(errp, QERR_BUS_NO_HOTPLUG, dev->parent_bus->name);
+        return;
+    }
+
+    if (!dc->hotpluggable) {
+        error_setg(errp, QERR_DEVICE_NO_HOTPLUG,
+                   object_get_typename(OBJECT(dev)));
+        return;
+    }
+
+    if (!migration_is_idle() && !dev->allow_unplug_during_migration) {
+        error_setg(errp, "device_del not allowed while migrating");
+        return;
+    }
+
+    qdev_hot_removed = true;
+
+    hotplug_ctrl = qdev_get_hotplug_handler(dev);
+    /* hotpluggable device MUST have HotplugHandler, if it doesn't
+     * then something is very wrong with it */
+    g_assert(hotplug_ctrl);
+
+    /* If device supports async unplug just request it to be done,
+     * otherwise just remove it synchronously */
+    hdc = HOTPLUG_HANDLER_GET_CLASS(hotplug_ctrl);
+    if (hdc->unplug_request) {
+        hotplug_handler_unplug_request(hotplug_ctrl, dev, &local_err);
+    } else {
+        hotplug_handler_unplug(hotplug_ctrl, dev, &local_err);
+        if (!local_err) {
+            object_unparent(OBJECT(dev));
+        }
+    }
+    error_propagate(errp, local_err);
+}
+
+void qmp_device_del(const char *id, Error **errp)
+{
+    DeviceState *dev = find_device_state(id, errp);
+    if (dev != NULL) {
+        if (dev->pending_deleted_event) {
+            error_setg(errp, "Device %s is already in the "
+                             "process of unplug", id);
+            return;
+        }
+
+        qdev_unplug(dev, errp);
+    }
+}
+
+void hmp_device_add(Monitor *mon, const QDict *qdict)
+{
+    Error *err = NULL;
+
+    qmp_device_add((QDict *)qdict, NULL, &err);
+    hmp_handle_error(mon, err);
+}
+
+void hmp_device_del(Monitor *mon, const QDict *qdict)
+{
+    const char *id = qdict_get_str(qdict, "id");
+    Error *err = NULL;
+
+    qmp_device_del(id, &err);
+    hmp_handle_error(mon, err);
+}
+
+BlockBackend *blk_by_qdev_id(const char *id, Error **errp)
+{
+    DeviceState *dev;
+    BlockBackend *blk;
+
+    dev = find_device_state(id, errp);
+    if (dev == NULL) {
+        return NULL;
+    }
+
+    blk = blk_by_dev(dev);
+    if (!blk) {
+        error_setg(errp, "Device does not have a block device backend");
+    }
+    return blk;
+}
+
+void qdev_machine_init(void)
+{
+    qdev_get_peripheral_anon();
+    qdev_get_peripheral();
+}
+
+QemuOptsList qemu_device_opts = {
+    .name = "device",
+    .implied_opt_name = "driver",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_device_opts.head),
+    .desc = {
+        /*
+         * no elements => accept any
+         * sanity checking will happen later
+         * when setting device properties
+         */
+        { /* end of list */ }
+    },
+};
+
+QemuOptsList qemu_global_opts = {
+    .name = "global",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_global_opts.head),
+    .desc = {
+        {
+            .name = "driver",
+            .type = QEMU_OPT_STRING,
+        },{
+            .name = "property",
+            .type = QEMU_OPT_STRING,
+        },{
+            .name = "value",
+            .type = QEMU_OPT_STRING,
+        },
+        { /* end of list */ }
+    },
+};
+
+int qemu_global_option(const char *str)
+{
+    char driver[64], property[64];
+    QemuOpts *opts;
+    int rc, offset;
+
+    rc = sscanf(str, "%63[^.=].%63[^=]%n", driver, property, &offset);
+    if (rc == 2 && str[offset] == '=') {
+        opts = qemu_opts_create(&qemu_global_opts, NULL, 0, &error_abort);
+        qemu_opt_set(opts, "driver", driver, &error_abort);
+        qemu_opt_set(opts, "property", property, &error_abort);
+        qemu_opt_set(opts, "value", str + offset + 1, &error_abort);
+        return 0;
+    }
+
+    opts = qemu_opts_parse_noisily(&qemu_global_opts, str, false);
+    if (!opts) {
+        return -1;
+    }
+
+    return 0;
+}
diff --git a/softmmu/qemu-seccomp.c b/softmmu/qemu-seccomp.c
new file mode 100644
index 0000000..8325ecb
--- /dev/null
+++ b/softmmu/qemu-seccomp.c
@@ -0,0 +1,331 @@
+/*
+ * QEMU seccomp mode 2 support with libseccomp
+ *
+ * Copyright IBM, Corp. 2012
+ *
+ * Authors:
+ *  Eduardo Otubo    <eotubo@br.ibm.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 "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/config-file.h"
+#include "qemu/option.h"
+#include "qemu/module.h"
+#include <sys/prctl.h>
+#include <seccomp.h>
+#include "sysemu/seccomp.h"
+#include <linux/seccomp.h>
+
+/* For some architectures (notably ARM) cacheflush is not supported until
+ * libseccomp 2.2.3, but configure enforces that we are using a more recent
+ * version on those hosts, so it is OK for this check to be less strict.
+ */
+#if SCMP_VER_MAJOR >= 3
+  #define HAVE_CACHEFLUSH
+#elif SCMP_VER_MAJOR == 2 && SCMP_VER_MINOR >= 2
+  #define HAVE_CACHEFLUSH
+#endif
+
+struct QemuSeccompSyscall {
+    int32_t num;
+    uint8_t set;
+    uint8_t narg;
+    const struct scmp_arg_cmp *arg_cmp;
+};
+
+const struct scmp_arg_cmp sched_setscheduler_arg[] = {
+    /* was SCMP_A1(SCMP_CMP_NE, SCHED_IDLE), but expanded due to GCC 4.x bug */
+    { .arg = 1, .op = SCMP_CMP_NE, .datum_a = SCHED_IDLE }
+};
+
+static const struct QemuSeccompSyscall blacklist[] = {
+    /* default set of syscalls to blacklist */
+    { SCMP_SYS(reboot),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(swapon),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(swapoff),                QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(syslog),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(mount),                  QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(umount),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(kexec_load),             QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(afs_syscall),            QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(break),                  QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(ftime),                  QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(getpmsg),                QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(gtty),                   QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(lock),                   QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(mpx),                    QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(prof),                   QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(profil),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(putpmsg),                QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(security),               QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(stty),                   QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(tuxcall),                QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(ulimit),                 QEMU_SECCOMP_SET_DEFAULT },
+    { SCMP_SYS(vserver),                QEMU_SECCOMP_SET_DEFAULT },
+    /* obsolete */
+    { SCMP_SYS(readdir),                QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(_sysctl),                QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(bdflush),                QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(create_module),          QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(get_kernel_syms),        QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(query_module),           QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(sgetmask),               QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(ssetmask),               QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(sysfs),                  QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(uselib),                 QEMU_SECCOMP_SET_OBSOLETE },
+    { SCMP_SYS(ustat),                  QEMU_SECCOMP_SET_OBSOLETE },
+    /* privileged */
+    { SCMP_SYS(setuid),                 QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setgid),                 QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setpgid),                QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setsid),                 QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setreuid),               QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setregid),               QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setresuid),              QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setresgid),              QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setfsuid),               QEMU_SECCOMP_SET_PRIVILEGED },
+    { SCMP_SYS(setfsgid),               QEMU_SECCOMP_SET_PRIVILEGED },
+    /* spawn */
+    { SCMP_SYS(fork),                   QEMU_SECCOMP_SET_SPAWN },
+    { SCMP_SYS(vfork),                  QEMU_SECCOMP_SET_SPAWN },
+    { SCMP_SYS(execve),                 QEMU_SECCOMP_SET_SPAWN },
+    /* resource control */
+    { SCMP_SYS(getpriority),            QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(setpriority),            QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setparam),         QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_getparam),         QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setscheduler),     QEMU_SECCOMP_SET_RESOURCECTL,
+      ARRAY_SIZE(sched_setscheduler_arg), sched_setscheduler_arg },
+    { SCMP_SYS(sched_getscheduler),     QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_setaffinity),      QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_getaffinity),      QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_get_priority_max), QEMU_SECCOMP_SET_RESOURCECTL },
+    { SCMP_SYS(sched_get_priority_min), QEMU_SECCOMP_SET_RESOURCECTL },
+};
+
+static inline __attribute__((unused)) int
+qemu_seccomp(unsigned int operation, unsigned int flags, void *args)
+{
+#ifdef __NR_seccomp
+    return syscall(__NR_seccomp, operation, flags, args);
+#else
+    errno = ENOSYS;
+    return -1;
+#endif
+}
+
+static uint32_t qemu_seccomp_get_action(int set)
+{
+    switch (set) {
+    case QEMU_SECCOMP_SET_DEFAULT:
+    case QEMU_SECCOMP_SET_OBSOLETE:
+    case QEMU_SECCOMP_SET_PRIVILEGED:
+    case QEMU_SECCOMP_SET_SPAWN: {
+#if defined(SECCOMP_GET_ACTION_AVAIL) && defined(SCMP_ACT_KILL_PROCESS) && \
+    defined(SECCOMP_RET_KILL_PROCESS)
+        static int kill_process = -1;
+        if (kill_process == -1) {
+            uint32_t action = SECCOMP_RET_KILL_PROCESS;
+
+            if (qemu_seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &action) == 0) {
+                kill_process = 1;
+            } else {
+                kill_process = 0;
+            }
+        }
+        if (kill_process == 1) {
+            return SCMP_ACT_KILL_PROCESS;
+        }
+#endif
+        return SCMP_ACT_TRAP;
+    }
+
+    case QEMU_SECCOMP_SET_RESOURCECTL:
+        return SCMP_ACT_ERRNO(EPERM);
+
+    default:
+        g_assert_not_reached();
+    }
+}
+
+
+static int seccomp_start(uint32_t seccomp_opts, Error **errp)
+{
+    int rc = -1;
+    unsigned int i = 0;
+    scmp_filter_ctx ctx;
+
+    ctx = seccomp_init(SCMP_ACT_ALLOW);
+    if (ctx == NULL) {
+        error_setg(errp, "failed to initialize seccomp context");
+        goto seccomp_return;
+    }
+
+    rc = seccomp_attr_set(ctx, SCMP_FLTATR_CTL_TSYNC, 1);
+    if (rc != 0) {
+        error_setg_errno(errp, -rc,
+                         "failed to set seccomp thread synchronization");
+        goto seccomp_return;
+    }
+
+    for (i = 0; i < ARRAY_SIZE(blacklist); i++) {
+        uint32_t action;
+        if (!(seccomp_opts & blacklist[i].set)) {
+            continue;
+        }
+
+        action = qemu_seccomp_get_action(blacklist[i].set);
+        rc = seccomp_rule_add_array(ctx, action, blacklist[i].num,
+                                    blacklist[i].narg, blacklist[i].arg_cmp);
+        if (rc < 0) {
+            error_setg_errno(errp, -rc,
+                             "failed to add seccomp blacklist rules");
+            goto seccomp_return;
+        }
+    }
+
+    rc = seccomp_load(ctx);
+    if (rc < 0) {
+        error_setg_errno(errp, -rc,
+                         "failed to load seccomp syscall filter in kernel");
+    }
+
+  seccomp_return:
+    seccomp_release(ctx);
+    return rc < 0 ? -1 : 0;
+}
+
+#ifdef CONFIG_SECCOMP
+int parse_sandbox(void *opaque, QemuOpts *opts, Error **errp)
+{
+    if (qemu_opt_get_bool(opts, "enable", false)) {
+        uint32_t seccomp_opts = QEMU_SECCOMP_SET_DEFAULT
+                | QEMU_SECCOMP_SET_OBSOLETE;
+        const char *value = NULL;
+
+        value = qemu_opt_get(opts, "obsolete");
+        if (value) {
+            if (g_str_equal(value, "allow")) {
+                seccomp_opts &= ~QEMU_SECCOMP_SET_OBSOLETE;
+            } else if (g_str_equal(value, "deny")) {
+                /* this is the default option, this if is here
+                 * to provide a little bit of consistency for
+                 * the command line */
+            } else {
+                error_setg(errp, "invalid argument for obsolete");
+                return -1;
+            }
+        }
+
+        value = qemu_opt_get(opts, "elevateprivileges");
+        if (value) {
+            if (g_str_equal(value, "deny")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_PRIVILEGED;
+            } else if (g_str_equal(value, "children")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_PRIVILEGED;
+
+                /* calling prctl directly because we're
+                 * not sure if host has CAP_SYS_ADMIN set*/
+                if (prctl(PR_SET_NO_NEW_PRIVS, 1)) {
+                    error_setg(errp, "failed to set no_new_privs aborting");
+                    return -1;
+                }
+            } else if (g_str_equal(value, "allow")) {
+                /* default value */
+            } else {
+                error_setg(errp, "invalid argument for elevateprivileges");
+                return -1;
+            }
+        }
+
+        value = qemu_opt_get(opts, "spawn");
+        if (value) {
+            if (g_str_equal(value, "deny")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_SPAWN;
+            } else if (g_str_equal(value, "allow")) {
+                /* default value */
+            } else {
+                error_setg(errp, "invalid argument for spawn");
+                return -1;
+            }
+        }
+
+        value = qemu_opt_get(opts, "resourcecontrol");
+        if (value) {
+            if (g_str_equal(value, "deny")) {
+                seccomp_opts |= QEMU_SECCOMP_SET_RESOURCECTL;
+            } else if (g_str_equal(value, "allow")) {
+                /* default value */
+            } else {
+                error_setg(errp, "invalid argument for resourcecontrol");
+                return -1;
+            }
+        }
+
+        if (seccomp_start(seccomp_opts, errp) < 0) {
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
+static QemuOptsList qemu_sandbox_opts = {
+    .name = "sandbox",
+    .implied_opt_name = "enable",
+    .head = QTAILQ_HEAD_INITIALIZER(qemu_sandbox_opts.head),
+    .desc = {
+        {
+            .name = "enable",
+            .type = QEMU_OPT_BOOL,
+        },
+        {
+            .name = "obsolete",
+            .type = QEMU_OPT_STRING,
+        },
+        {
+            .name = "elevateprivileges",
+            .type = QEMU_OPT_STRING,
+        },
+        {
+            .name = "spawn",
+            .type = QEMU_OPT_STRING,
+        },
+        {
+            .name = "resourcecontrol",
+            .type = QEMU_OPT_STRING,
+        },
+        { /* end of list */ }
+    },
+};
+
+static void seccomp_register(void)
+{
+    bool add = false;
+
+    /* FIXME: use seccomp_api_get() >= 2 check when released */
+
+#if defined(SECCOMP_FILTER_FLAG_TSYNC)
+    int check;
+
+    /* check host TSYNC capability, it returns errno == ENOSYS if unavailable */
+    check = qemu_seccomp(SECCOMP_SET_MODE_FILTER,
+                         SECCOMP_FILTER_FLAG_TSYNC, NULL);
+    if (check < 0 && errno == EFAULT) {
+        add = true;
+    }
+#endif
+
+    if (add) {
+        qemu_add_opts(&qemu_sandbox_opts);
+    }
+}
+opts_init(seccomp_register);
+#endif
diff --git a/softmmu/qtest.c b/softmmu/qtest.c
index 0d43cf8..2c6e8dc 100644
--- a/softmmu/qtest.c
+++ b/softmmu/qtest.c
@@ -49,92 +49,139 @@ static void *qtest_server_send_opaque;
 #define FMT_timeval "%ld.%06ld"
 
 /**
- * QTest Protocol
+ * DOC: QTest Protocol
  *
  * Line based protocol, request/response based.  Server can send async messages
  * so clients should always handle many async messages before the response
  * comes in.
  *
  * Valid requests
+ * ^^^^^^^^^^^^^^
  *
  * Clock management:
+ * """""""""""""""""
  *
  * The qtest client is completely in charge of the QEMU_CLOCK_VIRTUAL.  qtest commands
  * let you adjust the value of the clock (monotonically).  All the commands
  * return the current value of the clock in nanoseconds.
  *
+ * .. code-block:: none
+ *
  *  > clock_step
  *  < OK VALUE
  *
- *     Advance the clock to the next deadline.  Useful when waiting for
- *     asynchronous events.
+ * Advance the clock to the next deadline.  Useful when waiting for
+ * asynchronous events.
+ *
+ * .. code-block:: none
  *
  *  > clock_step NS
  *  < OK VALUE
  *
- *     Advance the clock by NS nanoseconds.
+ * Advance the clock by NS nanoseconds.
+ *
+ * .. code-block:: none
  *
  *  > clock_set NS
  *  < OK VALUE
  *
- *     Advance the clock to NS nanoseconds (do nothing if it's already past).
+ * Advance the clock to NS nanoseconds (do nothing if it's already past).
  *
  * PIO and memory access:
+ * """"""""""""""""""""""
+ *
+ * .. code-block:: none
  *
  *  > outb ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > outw ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > outl ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > inb ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > inw ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > inl ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > writeb ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > writew ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > writel ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > writeq ADDR VALUE
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > readb ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > readw ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > readl ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > readq ADDR
  *  < OK VALUE
  *
+ * .. code-block:: none
+ *
  *  > read ADDR SIZE
  *  < OK DATA
  *
+ * .. code-block:: none
+ *
  *  > write ADDR SIZE DATA
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > b64read ADDR SIZE
  *  < OK B64_DATA
  *
+ * .. code-block:: none
+ *
  *  > b64write ADDR SIZE B64_DATA
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > memset ADDR SIZE VALUE
  *  < OK
  *
@@ -149,16 +196,21 @@ static void *qtest_server_send_opaque;
  * If the sizes do not match, the data will be truncated.
  *
  * IRQ management:
+ * """""""""""""""
+ *
+ * .. code-block:: none
  *
  *  > irq_intercept_in QOM-PATH
  *  < OK
  *
+ * .. code-block:: none
+ *
  *  > irq_intercept_out QOM-PATH
  *  < OK
  *
  * Attach to the gpio-in (resp. gpio-out) pins exported by the device at
  * QOM-PATH.  When the pin is triggered, one of the following async messages
- * will be printed to the qtest stream:
+ * will be printed to the qtest stream::
  *
  *  IRQ raise NUM
  *  IRQ lower NUM
@@ -168,12 +220,15 @@ static void *qtest_server_send_opaque;
  * NUM=0 even though it is remapped to GSI 2).
  *
  * Setting interrupt level:
+ * """"""""""""""""""""""""
+ *
+ * .. code-block:: none
  *
  *  > set_irq_in QOM-PATH NAME NUM LEVEL
  *  < OK
  *
- *  where NAME is the name of the irq/gpio list, NUM is an IRQ number and
- *  LEVEL is an signed integer IRQ level.
+ * where NAME is the name of the irq/gpio list, NUM is an IRQ number and
+ * LEVEL is an signed integer IRQ level.
  *
  * Forcibly set the given interrupt pin to the given level.
  *
diff --git a/softmmu/tpm.c b/softmmu/tpm.c
new file mode 100644
index 0000000..cab2063
--- /dev/null
+++ b/softmmu/tpm.c
@@ -0,0 +1,265 @@
+/*
+ * TPM configuration
+ *
+ * Copyright (C) 2011-2013 IBM Corporation
+ *
+ * Authors:
+ *  Stefan Berger    <stefanb@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ * Based on net.c
+ */
+
+#include "qemu/osdep.h"
+
+#include "qapi/error.h"
+#include "qapi/qapi-commands-tpm.h"
+#include "qapi/qmp/qerror.h"
+#include "sysemu/tpm_backend.h"
+#include "sysemu/tpm.h"
+#include "qemu/config-file.h"
+#include "qemu/error-report.h"
+
+static QLIST_HEAD(, TPMBackend) tpm_backends =
+    QLIST_HEAD_INITIALIZER(tpm_backends);
+
+static const TPMBackendClass *
+tpm_be_find_by_type(enum TpmType type)
+{
+    ObjectClass *oc;
+    char *typename = g_strdup_printf("tpm-%s", TpmType_str(type));
+
+    oc = object_class_by_name(typename);
+    g_free(typename);
+
+    if (!object_class_dynamic_cast(oc, TYPE_TPM_BACKEND)) {
+        return NULL;
+    }
+
+    return TPM_BACKEND_CLASS(oc);
+}
+
+/*
+ * Walk the list of available TPM backend drivers and display them on the
+ * screen.
+ */
+static void tpm_display_backend_drivers(void)
+{
+    bool got_one = false;
+    int i;
+
+    for (i = 0; i < TPM_TYPE__MAX; i++) {
+        const TPMBackendClass *bc = tpm_be_find_by_type(i);
+        if (!bc) {
+            continue;
+        }
+        if (!got_one) {
+            error_printf("Supported TPM types (choose only one):\n");
+            got_one = true;
+        }
+        error_printf("%12s   %s\n", TpmType_str(i), bc->desc);
+    }
+    if (!got_one) {
+        error_printf("No TPM backend types are available\n");
+    }
+}
+
+/*
+ * Find the TPM with the given Id
+ */
+TPMBackend *qemu_find_tpm_be(const char *id)
+{
+    TPMBackend *drv;
+
+    if (id) {
+        QLIST_FOREACH(drv, &tpm_backends, list) {
+            if (!strcmp(drv->id, id)) {
+                return drv;
+            }
+        }
+    }
+
+    return NULL;
+}
+
+static int tpm_init_tpmdev(void *dummy, QemuOpts *opts, Error **errp)
+{
+    /*
+     * Use of error_report() in a function with an Error ** parameter
+     * is suspicious.  It is okay here.  The parameter only exists to
+     * make the function usable with qemu_opts_foreach().  It is not
+     * actually used.
+     */
+    const char *value;
+    const char *id;
+    const TPMBackendClass *be;
+    TPMBackend *drv;
+    Error *local_err = NULL;
+    int i;
+
+    if (!QLIST_EMPTY(&tpm_backends)) {
+        error_report("Only one TPM is allowed.");
+        return 1;
+    }
+
+    id = qemu_opts_id(opts);
+    if (id == NULL) {
+        error_report(QERR_MISSING_PARAMETER, "id");
+        return 1;
+    }
+
+    value = qemu_opt_get(opts, "type");
+    if (!value) {
+        error_report(QERR_MISSING_PARAMETER, "type");
+        tpm_display_backend_drivers();
+        return 1;
+    }
+
+    i = qapi_enum_parse(&TpmType_lookup, value, -1, NULL);
+    be = i >= 0 ? tpm_be_find_by_type(i) : NULL;
+    if (be == NULL) {
+        error_report(QERR_INVALID_PARAMETER_VALUE,
+                     "type", "a TPM backend type");
+        tpm_display_backend_drivers();
+        return 1;
+    }
+
+    /* validate backend specific opts */
+    if (!qemu_opts_validate(opts, be->opts, &local_err)) {
+        error_report_err(local_err);
+        return 1;
+    }
+
+    drv = be->create(opts);
+    if (!drv) {
+        return 1;
+    }
+
+    drv->id = g_strdup(id);
+    QLIST_INSERT_HEAD(&tpm_backends, drv, list);
+
+    return 0;
+}
+
+/*
+ * Walk the list of TPM backend drivers that are in use and call their
+ * destroy function to have them cleaned up.
+ */
+void tpm_cleanup(void)
+{
+    TPMBackend *drv, *next;
+
+    QLIST_FOREACH_SAFE(drv, &tpm_backends, list, next) {
+        QLIST_REMOVE(drv, list);
+        object_unref(OBJECT(drv));
+    }
+}
+
+/*
+ * Initialize the TPM. Process the tpmdev command line options describing the
+ * TPM backend.
+ */
+int tpm_init(void)
+{
+    if (qemu_opts_foreach(qemu_find_opts("tpmdev"),
+                          tpm_init_tpmdev, NULL, NULL)) {
+        return -1;
+    }
+
+    return 0;
+}
+
+/*
+ * Parse the TPM configuration options.
+ * To display all available TPM backends the user may use '-tpmdev help'
+ */
+int tpm_config_parse(QemuOptsList *opts_list, const char *optarg)
+{
+    QemuOpts *opts;
+
+    if (!strcmp(optarg, "help")) {
+        tpm_display_backend_drivers();
+        return -1;
+    }
+    opts = qemu_opts_parse_noisily(opts_list, optarg, true);
+    if (!opts) {
+        return -1;
+    }
+    return 0;
+}
+
+/*
+ * Walk the list of active TPM backends and collect information about them.
+ */
+TPMInfoList *qmp_query_tpm(Error **errp)
+{
+    TPMBackend *drv;
+    TPMInfoList *info, *head = NULL, *cur_item = NULL;
+
+    QLIST_FOREACH(drv, &tpm_backends, list) {
+        if (!drv->tpmif) {
+            continue;
+        }
+
+        info = g_new0(TPMInfoList, 1);
+        info->value = tpm_backend_query_tpm(drv);
+
+        if (!cur_item) {
+            head = cur_item = info;
+        } else {
+            cur_item->next = info;
+            cur_item = info;
+        }
+    }
+
+    return head;
+}
+
+TpmTypeList *qmp_query_tpm_types(Error **errp)
+{
+    unsigned int i = 0;
+    TpmTypeList *head = NULL, *prev = NULL, *cur_item;
+
+    for (i = 0; i < TPM_TYPE__MAX; i++) {
+        if (!tpm_be_find_by_type(i)) {
+            continue;
+        }
+        cur_item = g_new0(TpmTypeList, 1);
+        cur_item->value = i;
+
+        if (prev) {
+            prev->next = cur_item;
+        }
+        if (!head) {
+            head = cur_item;
+        }
+        prev = cur_item;
+    }
+
+    return head;
+}
+TpmModelList *qmp_query_tpm_models(Error **errp)
+{
+    TpmModelList *head = NULL, *prev = NULL, *cur_item;
+    GSList *e, *l = object_class_get_list(TYPE_TPM_IF, false);
+
+    for (e = l; e; e = e->next) {
+        TPMIfClass *c = TPM_IF_CLASS(e->data);
+
+        cur_item = g_new0(TpmModelList, 1);
+        cur_item->value = c->model;
+
+        if (prev) {
+            prev->next = cur_item;
+        }
+        if (!head) {
+            head = cur_item;
+        }
+        prev = cur_item;
+    }
+    g_slist_free(l);
+
+    return head;
+}