void libxl_report_child_exitstatus(libxl_ctx *ctx,
xentoollog_level level,
const char *what, pid_t pid, int status)
{
if (WIFEXITED(status)) {
int st = WEXITSTATUS(status);
if (st)
LIBXL__LOG(ctx, level, "%s [%ld] exited"
" with error status %d", what, (unsigned long)pid, st);
else
LIBXL__LOG(ctx, level, "%s [%ld] unexpectedly"
" exited status zero", what, (unsigned long)pid);
} else if (WIFSIGNALED(status)) {
int sig = WTERMSIG(status);
const char *str = strsignal(sig);
const char *coredump = WCOREDUMP(status) ? " (core dumped)" : "";
if (str)
LIBXL__LOG(ctx, level, "%s [%ld] died due to"
" fatal signal %s%s", what, (unsigned long)pid,
str, coredump);
else
LIBXL__LOG(ctx, level, "%s [%ld] died due to unknown"
" fatal signal number %d%s", what, (unsigned long)pid,
sig, coredump);
} else {
LIBXL__LOG(ctx, level, "%s [%ld] gave unknown"
" wait status 0x%x", what, (unsigned long)pid, status);
}
}
static char *dm_spice_options(libxl__gc *gc,
const libxl_spice_info *spice)
{
char *opt;
if (!spice->port && !spice->tls_port) {
LIBXL__LOG(CTX, LIBXL__LOG_ERROR,
"at least one of the spiceport or tls_port must be provided");
return NULL;
}
if (!libxl_defbool_val(spice->disable_ticketing)) {
if (!spice->passwd) {
LIBXL__LOG(CTX, LIBXL__LOG_ERROR,
"spice ticketing is enabled but missing password");
return NULL;
}
else if (!spice->passwd[0]) {
LIBXL__LOG(CTX, LIBXL__LOG_ERROR,
"spice password can't be empty");
return NULL;
}
}
opt = libxl__sprintf(gc, "port=%d,tls-port=%d",
spice->port, spice->tls_port);
if (spice->host)
opt = libxl__sprintf(gc, "%s,addr=%s", opt, spice->host);
if (libxl_defbool_val(spice->disable_ticketing))
opt = libxl__sprintf(gc, "%s,disable-ticketing", opt);
else
opt = libxl__sprintf(gc, "%s,password=%s", opt, spice->passwd);
opt = libxl__sprintf(gc, "%s,agent-mouse=%s", opt,
libxl_defbool_val(spice->agent_mouse) ? "on" : "off");
return opt;
}
const char *libxl__domain_device_model(libxl__gc *gc,
const libxl_domain_build_info *info)
{
libxl_ctx *ctx = libxl__gc_owner(gc);
const char *dm;
if (libxl_defbool_val(info->device_model_stubdomain))
return NULL;
if (info->device_model) {
dm = libxl__strdup(gc, info->device_model);
} else {
switch (info->device_model_version) {
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL:
dm = libxl__abs_path(gc, "qemu-dm", libxl__libexec_path());
break;
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN:
dm = qemu_xen_path(gc);
break;
default:
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"invalid device model version %d\n",
info->device_model_version);
dm = NULL;
break;
}
}
return dm;
}
static void domcreate_rebuild_done(libxl__egc *egc,
libxl__domain_create_state *dcs,
int ret)
{
STATE_AO_GC(dcs->ao);
/* convenience aliases */
const uint32_t domid = dcs->guest_domid;
libxl_domain_config *const d_config = dcs->guest_config;
libxl_ctx *const ctx = CTX;
if (ret) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR, "cannot (re-)build domain: %d", ret);
ret = ERROR_FAIL;
goto error_out;
}
store_libxl_entry(gc, domid, &d_config->b_info);
libxl__multidev_begin(ao, &dcs->multidev);
dcs->multidev.callback = domcreate_launch_dm;
libxl__add_disks(egc, ao, domid, d_config, &dcs->multidev);
libxl__multidev_prepared(egc, &dcs->multidev, 0);
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
static void domcreate_attach_pci(libxl__egc *egc, libxl__multidev *multidev,
int ret)
{
libxl__domain_create_state *dcs = CONTAINER_OF(multidev, *dcs, multidev);
STATE_AO_GC(dcs->ao);
int i;
libxl_ctx *ctx = CTX;
int domid = dcs->guest_domid;
/* convenience aliases */
libxl_domain_config *const d_config = dcs->guest_config;
if (ret) {
LOG(ERROR, "unable to add vtpm devices");
goto error_out;
}
for (i = 0; i < d_config->num_pcidevs; i++) {
ret = libxl__device_pci_add(gc, domid, &d_config->pcidevs[i], 1);
if (ret < 0) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"libxl_device_pci_add failed: %d", ret);
goto error_out;
}
}
if (d_config->num_pcidevs > 0) {
ret = libxl__create_pci_backend(gc, domid, d_config->pcidevs,
d_config->num_pcidevs);
if (ret < 0) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"libxl_create_pci_backend failed: %d", ret);
goto error_out;
}
}
domcreate_console_available(egc, dcs);
domcreate_complete(egc, dcs, 0);
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
int libxl__destroy_device_model(libxl_ctx *ctx, uint32_t domid)
{
libxl__gc gc = LIBXL_INIT_GC(ctx);
char *pid;
int ret;
pid = libxl__xs_read(&gc, XBT_NULL, libxl__sprintf(&gc, "/local/domain/%d/image/device-model-pid", domid));
if (!pid) {
int stubdomid = libxl_get_stubdom_id(ctx, domid);
if (!stubdomid) {
LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "Couldn't find device model's pid");
ret = ERROR_INVAL;
goto out;
}
LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Device model is a stubdom, domid=%d\n", stubdomid);
ret = libxl_domain_destroy(ctx, stubdomid, 0);
if (ret)
goto out;
} else {
ret = kill(atoi(pid), SIGHUP);
if (ret < 0 && errno == ESRCH) {
LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Device Model already exited");
ret = 0;
} else if (ret == 0) {
LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "Device Model signaled");
ret = 0;
} else {
LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "failed to kill Device Model [%d]",
atoi(pid));
ret = ERROR_FAIL;
goto out;
}
}
xs_rm(ctx->xsh, XBT_NULL, libxl__sprintf(&gc, "/local/domain/0/device-model/%d", domid));
out:
libxl__free_all(&gc);
return ret;
}
static void domcreate_attach_pci(libxl__egc *egc, libxl__multidev *multidev,
int ret)
{
libxl__domain_create_state *dcs = CONTAINER_OF(multidev, *dcs, multidev);
STATE_AO_GC(dcs->ao);
int i;
libxl_ctx *ctx = CTX;
int domid = dcs->guest_domid;
/* convenience aliases */
libxl_domain_config *const d_config = dcs->guest_config;
if (ret) {
LOG(ERROR, "unable to add nic devices");
goto error_out;
}
for (i = 0; i < d_config->num_pcidevs; i++) {
// TODO(Yusuke Suzuki): we should check target device is nvc0
libxl__device_pci_add_with_nvc0(gc, domid, &d_config->pcidevs[i], 1, d_config->b_info.u.hvm.nvc0 >= 0);
}
if (d_config->num_pcidevs > 0) {
ret = libxl__create_pci_backend(gc, domid, d_config->pcidevs,
d_config->num_pcidevs);
if (ret < 0) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"libxl_create_pci_backend failed: %d", ret);
goto error_out;
}
}
libxl__arch_domain_create(gc, d_config, domid);
domcreate_console_available(egc, dcs);
domcreate_complete(egc, dcs, 0);
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
static void domcreate_devmodel_started(libxl__egc *egc,
libxl__dm_spawn_state *dmss,
int ret)
{
libxl__domain_create_state *dcs = CONTAINER_OF(dmss, *dcs, dmss.dm);
STATE_AO_GC(dmss->spawn.ao);
libxl_ctx *ctx = CTX;
int domid = dcs->guest_domid;
/* convenience aliases */
libxl_domain_config *const d_config = dcs->guest_config;
if (ret) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"device model did not start: %d", ret);
goto error_out;
}
if (dcs->dmss.dm.guest_domid) {
if (d_config->b_info.device_model_version
== LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN) {
libxl__qmp_initializations(gc, domid, d_config);
}
}
/* Plug nic interfaces */
if (d_config->num_nics > 0) {
/* Attach nics */
libxl__multidev_begin(ao, &dcs->multidev);
dcs->multidev.callback = domcreate_attach_pci;
libxl__add_nics(egc, ao, domid, d_config, &dcs->multidev);
libxl__multidev_prepared(egc, &dcs->multidev, 0);
return;
}
domcreate_attach_pci(egc, &dcs->multidev, 0);
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
int libxl__device_model_version_running(libxl__gc *gc, uint32_t domid)
{
char *path = NULL;
char *dm_version = NULL;
libxl_device_model_version value;
path = libxl__xs_libxl_path(gc, domid);
path = libxl__sprintf(gc, "%s/dm-version", path);
dm_version = libxl__xs_read(gc, XBT_NULL, path);
if (!dm_version) {
return LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
}
if (libxl_device_model_version_from_string(dm_version, &value) < 0) {
libxl_ctx *ctx = libxl__gc_owner(gc);
LIBXL__LOG(ctx, LIBXL__LOG_ERROR,
"fatal: %s contain a wrong value (%s)", path, dm_version);
return -1;
}
return value;
}
void libxl__spawn_local_dm(libxl__egc *egc, libxl__dm_spawn_state *dmss)
{
/* convenience aliases */
const int domid = dmss->guest_domid;
libxl__domain_build_state *const state = dmss->build_state;
libxl__spawn_state *const spawn = &dmss->spawn;
STATE_AO_GC(dmss->spawn.ao);
libxl_ctx *ctx = CTX;
libxl_domain_config *guest_config = dmss->guest_config;
const libxl_domain_create_info *c_info = &guest_config->c_info;
const libxl_domain_build_info *b_info = &guest_config->b_info;
const libxl_vnc_info *vnc = libxl__dm_vnc(guest_config);
char *path, *logfile;
int logfile_w, null;
int rc;
char **args, **arg;
xs_transaction_t t;
char *vm_path;
char **pass_stuff;
const char *dm;
if (libxl_defbool_val(b_info->device_model_stubdomain)) {
abort();
}
dm = libxl__domain_device_model(gc, b_info);
if (!dm) {
rc = ERROR_FAIL;
goto out;
}
if (access(dm, X_OK) < 0) {
LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR,
"device model %s is not executable", dm);
rc = ERROR_FAIL;
goto out;
}
args = libxl__build_device_model_args(gc, dm, domid, guest_config, state);
if (!args) {
rc = ERROR_FAIL;
goto out;
}
if (b_info->type == LIBXL_DOMAIN_TYPE_HVM) {
path = xs_get_domain_path(ctx->xsh, domid);
libxl__xs_write(gc, XBT_NULL,
libxl__sprintf(gc, "%s/hvmloader/bios", path),
"%s", libxl_bios_type_to_string(b_info->u.hvm.bios));
/* Disable relocating memory to make the MMIO hole larger
* unless we're running qemu-traditional */
libxl__xs_write(gc, XBT_NULL,
libxl__sprintf(gc,
"%s/hvmloader/allow-memory-relocate",
path),
"%d",
b_info->device_model_version==LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL);
free(path);
}
path = libxl__sprintf(gc, "/local/domain/0/device-model/%d", domid);
xs_mkdir(ctx->xsh, XBT_NULL, path);
if (b_info->type == LIBXL_DOMAIN_TYPE_HVM &&
b_info->device_model_version
== LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL)
libxl__xs_write(gc, XBT_NULL, libxl__sprintf(gc, "%s/disable_pf", path),
"%d", !libxl_defbool_val(b_info->u.hvm.xen_platform_pci));
libxl_create_logfile(ctx,
libxl__sprintf(gc, "qemu-dm-%s", c_info->name),
&logfile);
logfile_w = open(logfile, O_WRONLY|O_CREAT|O_APPEND, 0644);
free(logfile);
null = open("/dev/null", O_RDONLY);
const char *dom_path = libxl__xs_get_dompath(gc, domid);
spawn->pidpath = GCSPRINTF("%s/%s", dom_path, "image/device-model-pid");
if (vnc && vnc->passwd) {
/* This xenstore key will only be used by qemu-xen-traditionnal.
* The code to supply vncpasswd to qemu-xen is later. */
retry_transaction:
/* Find uuid and the write the vnc password to xenstore for qemu. */
t = xs_transaction_start(ctx->xsh);
vm_path = libxl__xs_read(gc,t,libxl__sprintf(gc, "%s/vm", dom_path));
if (vm_path) {
/* Now write the vncpassword into it. */
pass_stuff = libxl__calloc(gc, 3, sizeof(char *));
pass_stuff[0] = "vncpasswd";
pass_stuff[1] = vnc->passwd;
libxl__xs_writev(gc,t,vm_path,pass_stuff);
if (!xs_transaction_end(ctx->xsh, t, 0))
if (errno == EAGAIN)
goto retry_transaction;
}
}
LIBXL__LOG(CTX, XTL_DEBUG, "Spawning device-model %s with arguments:", dm);
for (arg = args; *arg; arg++)
LIBXL__LOG(CTX, XTL_DEBUG, " %s", *arg);
spawn->what = GCSPRINTF("domain %d device model", domid);
spawn->xspath = GCSPRINTF("/local/domain/0/device-model/%d/state", domid);
spawn->timeout_ms = LIBXL_DEVICE_MODEL_START_TIMEOUT * 1000;
spawn->pidpath = GCSPRINTF("%s/image/device-model-pid", dom_path);
spawn->midproc_cb = libxl__spawn_record_pid;
spawn->confirm_cb = device_model_confirm;
spawn->failure_cb = device_model_startup_failed;
spawn->detached_cb = device_model_detached;
rc = libxl__spawn_spawn(egc, spawn);
if (rc < 0)
goto out_close;
if (!rc) { /* inner child */
setsid();
libxl__exec(gc, null, logfile_w, logfile_w, dm, args, NULL);
}
rc = 0;
out_close:
close(null);
close(logfile_w);
out:
if (rc)
device_model_spawn_outcome(egc, dmss, rc);
}
static void initiate_domain_create(libxl__egc *egc,
libxl__domain_create_state *dcs)
{
STATE_AO_GC(dcs->ao);
libxl_ctx *ctx = libxl__gc_owner(gc);
uint32_t domid;
int i, ret;
/* convenience aliases */
libxl_domain_config *const d_config = dcs->guest_config;
const int restore_fd = dcs->restore_fd;
memset(&dcs->build_state, 0, sizeof(dcs->build_state));
domid = 0;
ret = libxl__domain_create_info_setdefault(gc, &d_config->c_info);
if (ret) goto error_out;
ret = libxl__domain_make(gc, &d_config->c_info, &domid);
if (ret) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR, "cannot make domain: %d", ret);
dcs->guest_domid = domid;
ret = ERROR_FAIL;
goto error_out;
}
dcs->guest_domid = domid;
dcs->dmss.dm.guest_domid = 0; /* means we haven't spawned */
ret = libxl__domain_build_info_setdefault(gc, &d_config->b_info);
if (ret) goto error_out;
if (!sched_params_valid(gc, domid, &d_config->b_info.sched_params)) {
LOG(ERROR, "Invalid scheduling parameters\n");
ret = ERROR_INVAL;
goto error_out;
}
for (i = 0; i < d_config->num_disks; i++) {
ret = libxl__device_disk_setdefault(gc, &d_config->disks[i]);
if (ret) goto error_out;
}
dcs->bl.ao = ao;
libxl_device_disk *bootdisk =
d_config->num_disks > 0 ? &d_config->disks[0] : NULL;
if (restore_fd >= 0) {
LOG(DEBUG, "restoring, not running bootloader\n");
domcreate_bootloader_done(egc, &dcs->bl, 0);
} else {
LOG(DEBUG, "running bootloader");
dcs->bl.callback = domcreate_bootloader_done;
dcs->bl.console_available = domcreate_bootloader_console_available;
dcs->bl.info = &d_config->b_info;
dcs->bl.disk = bootdisk;
dcs->bl.domid = dcs->guest_domid;
dcs->bl.kernel = &dcs->build_state.pv_kernel;
dcs->bl.ramdisk = &dcs->build_state.pv_ramdisk;
libxl__bootloader_run(egc, &dcs->bl);
}
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
int libxl__domain_make(libxl__gc *gc, libxl_domain_create_info *info,
uint32_t *domid)
{
libxl_ctx *ctx = libxl__gc_owner(gc);
int flags, ret, rc, nb_vm;
char *uuid_string;
char *dom_path, *vm_path, *libxl_path;
struct xs_permissions roperm[2];
struct xs_permissions rwperm[1];
struct xs_permissions noperm[1];
xs_transaction_t t = 0;
xen_domain_handle_t handle;
libxl_vminfo *vm_list;
assert(!libxl_domid_valid_guest(*domid));
uuid_string = libxl__uuid2string(gc, info->uuid);
if (!uuid_string) {
rc = ERROR_NOMEM;
goto out;
}
flags = 0;
if (info->type == LIBXL_DOMAIN_TYPE_HVM) {
flags |= XEN_DOMCTL_CDF_hvm_guest;
flags |= libxl_defbool_val(info->hap) ? XEN_DOMCTL_CDF_hap : 0;
flags |= libxl_defbool_val(info->oos) ? 0 : XEN_DOMCTL_CDF_oos_off;
}
*domid = -1;
/* Ultimately, handle is an array of 16 uint8_t, same as uuid */
libxl_uuid_copy((libxl_uuid *)handle, &info->uuid);
ret = xc_domain_create(ctx->xch, info->ssidref, handle, flags, domid);
if (ret < 0) {
LIBXL__LOG_ERRNOVAL(ctx, LIBXL__LOG_ERROR, ret, "domain creation fail");
rc = ERROR_FAIL;
goto out;
}
ret = xc_cpupool_movedomain(ctx->xch, info->poolid, *domid);
if (ret < 0) {
LIBXL__LOG_ERRNOVAL(ctx, LIBXL__LOG_ERROR, ret, "domain move fail");
rc = ERROR_FAIL;
goto out;
}
dom_path = libxl__xs_get_dompath(gc, *domid);
if (!dom_path) {
rc = ERROR_FAIL;
goto out;
}
vm_path = libxl__sprintf(gc, "/vm/%s", uuid_string);
if (!vm_path) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR, "cannot allocate create paths");
rc = ERROR_FAIL;
goto out;
}
libxl_path = libxl__xs_libxl_path(gc, *domid);
if (!libxl_path) {
rc = ERROR_FAIL;
goto out;
}
noperm[0].id = 0;
noperm[0].perms = XS_PERM_NONE;
roperm[0].id = 0;
roperm[0].perms = XS_PERM_NONE;
roperm[1].id = *domid;
roperm[1].perms = XS_PERM_READ;
rwperm[0].id = *domid;
rwperm[0].perms = XS_PERM_NONE;
retry_transaction:
t = xs_transaction_start(ctx->xsh);
xs_rm(ctx->xsh, t, dom_path);
libxl__xs_mkdir(gc, t, dom_path, roperm, ARRAY_SIZE(roperm));
xs_rm(ctx->xsh, t, vm_path);
libxl__xs_mkdir(gc, t, vm_path, roperm, ARRAY_SIZE(roperm));
xs_rm(ctx->xsh, t, libxl_path);
libxl__xs_mkdir(gc, t, libxl_path, noperm, ARRAY_SIZE(noperm));
xs_write(ctx->xsh, t, libxl__sprintf(gc, "%s/vm", dom_path), vm_path, strlen(vm_path));
rc = libxl__domain_rename(gc, *domid, 0, info->name, t);
if (rc)
goto out;
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/cpu", dom_path),
roperm, ARRAY_SIZE(roperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/memory", dom_path),
roperm, ARRAY_SIZE(roperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/device", dom_path),
roperm, ARRAY_SIZE(roperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/control", dom_path),
roperm, ARRAY_SIZE(roperm));
if (info->type == LIBXL_DOMAIN_TYPE_HVM)
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/hvmloader", dom_path),
roperm, ARRAY_SIZE(roperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/control/shutdown", dom_path),
rwperm, ARRAY_SIZE(rwperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/device/suspend/event-channel", dom_path),
rwperm, ARRAY_SIZE(rwperm));
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/data", dom_path),
rwperm, ARRAY_SIZE(rwperm));
if (info->type == LIBXL_DOMAIN_TYPE_HVM)
libxl__xs_mkdir(gc, t,
libxl__sprintf(gc, "%s/hvmloader/generation-id-address", dom_path),
rwperm, ARRAY_SIZE(rwperm));
vm_list = libxl_list_vm(ctx, &nb_vm);
if (!vm_list) {
LOG(ERROR, "cannot get number of running guests");
rc = ERROR_FAIL;
goto out;
}
libxl_vminfo_list_free(vm_list, nb_vm);
int hotplug_setting = libxl__hotplug_settings(gc, t);
if (hotplug_setting < 0) {
LOG(ERROR, "unable to get current hotplug scripts execution setting");
rc = ERROR_FAIL;
goto out;
}
if (libxl_defbool_val(info->run_hotplug_scripts) != hotplug_setting &&
(nb_vm - 1)) {
LOG(ERROR, "cannot change hotplug execution option once set, "
"please shutdown all guests before changing it");
rc = ERROR_FAIL;
goto out;
}
if (libxl_defbool_val(info->run_hotplug_scripts)) {
rc = libxl__xs_write_checked(gc, t, DISABLE_UDEV_PATH, "1");
if (rc) {
LOGE(ERROR, "unable to write %s = 1", DISABLE_UDEV_PATH);
goto out;
}
} else {
rc = libxl__xs_rm_checked(gc, t, DISABLE_UDEV_PATH);
if (rc) {
LOGE(ERROR, "unable to delete %s", DISABLE_UDEV_PATH);
goto out;
}
}
xs_write(ctx->xsh, t, libxl__sprintf(gc, "%s/uuid", vm_path), uuid_string, strlen(uuid_string));
xs_write(ctx->xsh, t, libxl__sprintf(gc, "%s/name", vm_path), info->name, strlen(info->name));
libxl__xs_writev(gc, t, dom_path, info->xsdata);
libxl__xs_writev(gc, t, libxl__sprintf(gc, "%s/platform", dom_path), info->platformdata);
xs_write(ctx->xsh, t, libxl__sprintf(gc, "%s/control/platform-feature-multiprocessor-suspend", dom_path), "1", 1);
xs_write(ctx->xsh, t, libxl__sprintf(gc, "%s/control/platform-feature-xs_reset_watches", dom_path), "1", 1);
if (!xs_transaction_end(ctx->xsh, t, 0)) {
if (errno == EAGAIN) {
t = 0;
goto retry_transaction;
}
LIBXL__LOG_ERRNO(ctx, LIBXL__LOG_ERROR, "domain creation "
"xenstore transaction commit failed");
rc = ERROR_FAIL;
goto out;
}
t = 0;
rc = 0;
out:
if (t) xs_transaction_end(ctx->xsh, t, 1);
return rc;
}
int libxl__domain_build_info_setdefault(libxl__gc *gc,
libxl_domain_build_info *b_info)
{
if (b_info->type != LIBXL_DOMAIN_TYPE_HVM &&
b_info->type != LIBXL_DOMAIN_TYPE_PV)
return ERROR_INVAL;
libxl_defbool_setdefault(&b_info->device_model_stubdomain, false);
if (!b_info->device_model_version) {
if (b_info->type == LIBXL_DOMAIN_TYPE_HVM)
b_info->device_model_version =
LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
else {
const char *dm;
int rc;
b_info->device_model_version =
LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN;
dm = libxl__domain_device_model(gc, b_info);
rc = access(dm, X_OK);
if (rc < 0) {
/* qemu-xen unavailable, use qemu-xen-traditional */
if (errno == ENOENT) {
LIBXL__LOG_ERRNO(CTX, XTL_VERBOSE, "qemu-xen is unavailable"
", use qemu-xen-traditional instead");
b_info->device_model_version =
LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
} else {
LIBXL__LOG_ERRNO(CTX, XTL_ERROR, "qemu-xen access error");
return ERROR_FAIL;
}
}
}
}
if (b_info->blkdev_start == NULL)
b_info->blkdev_start = libxl__strdup(NOGC, "xvda");
if (b_info->type == LIBXL_DOMAIN_TYPE_HVM) {
if (!b_info->u.hvm.bios)
switch (b_info->device_model_version) {
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL:
b_info->u.hvm.bios = LIBXL_BIOS_TYPE_ROMBIOS; break;
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN:
b_info->u.hvm.bios = LIBXL_BIOS_TYPE_SEABIOS; break;
default:return ERROR_INVAL;
}
/* Enforce BIOS<->Device Model version relationship */
switch (b_info->device_model_version) {
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL:
if (b_info->u.hvm.bios != LIBXL_BIOS_TYPE_ROMBIOS)
return ERROR_INVAL;
break;
case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN:
if (b_info->u.hvm.bios == LIBXL_BIOS_TYPE_ROMBIOS)
return ERROR_INVAL;
break;
default:abort();
}
}
if (b_info->type == LIBXL_DOMAIN_TYPE_HVM &&
b_info->device_model_version !=
LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL &&
libxl_defbool_val(b_info->device_model_stubdomain)) {
LIBXL__LOG(CTX, XTL_ERROR,
"device model stubdomains require \"qemu-xen-traditional\"");
return ERROR_INVAL;
}
if (!b_info->max_vcpus)
b_info->max_vcpus = 1;
if (!b_info->avail_vcpus.size) {
if (libxl_cpu_bitmap_alloc(CTX, &b_info->avail_vcpus, 1))
return ERROR_FAIL;
libxl_bitmap_set(&b_info->avail_vcpus, 0);
} else if (b_info->avail_vcpus.size > HVM_MAX_VCPUS)
return ERROR_FAIL;
if (!b_info->cpumap.size) {
if (libxl_cpu_bitmap_alloc(CTX, &b_info->cpumap, 0))
return ERROR_FAIL;
libxl_bitmap_set_any(&b_info->cpumap);
}
libxl_defbool_setdefault(&b_info->numa_placement, true);
if (b_info->max_memkb == LIBXL_MEMKB_DEFAULT)
b_info->max_memkb = 32 * 1024;
if (b_info->target_memkb == LIBXL_MEMKB_DEFAULT)
b_info->target_memkb = b_info->max_memkb;
libxl_defbool_setdefault(&b_info->localtime, false);
libxl_defbool_setdefault(&b_info->disable_migrate, false);
switch (b_info->type) {
case LIBXL_DOMAIN_TYPE_HVM:
if (b_info->shadow_memkb == LIBXL_MEMKB_DEFAULT)
b_info->shadow_memkb = 0;
if (b_info->video_memkb == LIBXL_MEMKB_DEFAULT)
b_info->video_memkb = 8 * 1024;
if (b_info->u.hvm.timer_mode == LIBXL_TIMER_MODE_DEFAULT)
b_info->u.hvm.timer_mode =
LIBXL_TIMER_MODE_NO_DELAY_FOR_MISSED_TICKS;
libxl_defbool_setdefault(&b_info->u.hvm.pae, true);
libxl_defbool_setdefault(&b_info->u.hvm.apic, true);
libxl_defbool_setdefault(&b_info->u.hvm.acpi, true);
libxl_defbool_setdefault(&b_info->u.hvm.acpi_s3, true);
libxl_defbool_setdefault(&b_info->u.hvm.acpi_s4, true);
libxl_defbool_setdefault(&b_info->u.hvm.nx, true);
libxl_defbool_setdefault(&b_info->u.hvm.viridian, false);
libxl_defbool_setdefault(&b_info->u.hvm.hpet, true);
libxl_defbool_setdefault(&b_info->u.hvm.vpt_align, true);
libxl_defbool_setdefault(&b_info->u.hvm.nested_hvm, false);
libxl_defbool_setdefault(&b_info->u.hvm.usb, false);
libxl_defbool_setdefault(&b_info->u.hvm.xen_platform_pci, true);
if (!b_info->u.hvm.boot) {
b_info->u.hvm.boot = strdup("cda");
if (!b_info->u.hvm.boot) return ERROR_NOMEM;
}
if (!b_info->u.hvm.vga.kind)
b_info->u.hvm.vga.kind = LIBXL_VGA_INTERFACE_TYPE_CIRRUS;
libxl_defbool_setdefault(&b_info->u.hvm.vnc.enable, true);
if (libxl_defbool_val(b_info->u.hvm.vnc.enable)) {
libxl_defbool_setdefault(&b_info->u.hvm.vnc.findunused, true);
if (!b_info->u.hvm.vnc.listen) {
b_info->u.hvm.vnc.listen = strdup("127.0.0.1");
if (!b_info->u.hvm.vnc.listen) return ERROR_NOMEM;
}
}
libxl_defbool_setdefault(&b_info->u.hvm.sdl.enable, false);
if (libxl_defbool_val(b_info->u.hvm.sdl.enable)) {
libxl_defbool_setdefault(&b_info->u.hvm.sdl.opengl, false);
}
libxl_defbool_setdefault(&b_info->u.hvm.spice.enable, false);
if (libxl_defbool_val(b_info->u.hvm.spice.enable)) {
libxl_defbool_setdefault(&b_info->u.hvm.spice.disable_ticketing,
false);
libxl_defbool_setdefault(&b_info->u.hvm.spice.agent_mouse, true);
}
libxl_defbool_setdefault(&b_info->u.hvm.nographic, false);
libxl_defbool_setdefault(&b_info->u.hvm.gfx_passthru, false);
break;
case LIBXL_DOMAIN_TYPE_PV:
libxl_defbool_setdefault(&b_info->u.pv.e820_host, false);
if (b_info->shadow_memkb == LIBXL_MEMKB_DEFAULT)
b_info->shadow_memkb = 0;
if (b_info->u.pv.slack_memkb == LIBXL_MEMKB_DEFAULT)
b_info->u.pv.slack_memkb = 0;
break;
default:
LIBXL__LOG(CTX, LIBXL__LOG_ERROR,
"invalid domain type %s in create info",
libxl_domain_type_to_string(b_info->type));
return ERROR_INVAL;
}
return 0;
}
static void initiate_domain_create(libxl__egc *egc,
libxl__domain_create_state *dcs)
{
STATE_AO_GC(dcs->ao);
libxl_ctx *ctx = libxl__gc_owner(gc);
uint32_t domid;
int i, ret;
size_t last_devid = -1;
bool pod_enabled = false;
/* convenience aliases */
libxl_domain_config *const d_config = dcs->guest_config;
const int restore_fd = dcs->restore_fd;
memset(&dcs->build_state, 0, sizeof(dcs->build_state));
domid = 0;
/* If target_memkb is smaller than max_memkb, the subsequent call
* to libxc when building HVM domain will enable PoD mode.
*/
pod_enabled = (d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM) &&
(d_config->b_info.target_memkb < d_config->b_info.max_memkb);
/* We cannot have PoD and PCI device assignment at the same time
* for HVM guest. It was reported that IOMMU cannot work with PoD
* enabled because it needs to populated entire page table for
* guest. To stay on the safe side, we disable PCI device
* assignment when PoD is enabled.
*/
if (d_config->c_info.type == LIBXL_DOMAIN_TYPE_HVM &&
d_config->num_pcidevs && pod_enabled) {
ret = ERROR_INVAL;
LOG(ERROR, "PCI device assignment for HVM guest failed due to PoD enabled");
goto error_out;
}
ret = libxl__domain_create_info_setdefault(gc, &d_config->c_info);
if (ret) goto error_out;
ret = libxl__domain_make(gc, &d_config->c_info, &domid);
if (ret) {
LIBXL__LOG(ctx, LIBXL__LOG_ERROR, "cannot make domain: %d", ret);
dcs->guest_domid = domid;
ret = ERROR_FAIL;
goto error_out;
}
dcs->guest_domid = domid;
dcs->dmss.dm.guest_domid = 0; /* means we haven't spawned */
ret = libxl__domain_build_info_setdefault(gc, &d_config->b_info);
if (ret) goto error_out;
if (!sched_params_valid(gc, domid, &d_config->b_info.sched_params)) {
LOG(ERROR, "Invalid scheduling parameters\n");
ret = ERROR_INVAL;
goto error_out;
}
for (i = 0; i < d_config->num_disks; i++) {
ret = libxl__device_disk_setdefault(gc, &d_config->disks[i]);
if (ret) goto error_out;
}
dcs->bl.ao = ao;
libxl_device_disk *bootdisk =
d_config->num_disks > 0 ? &d_config->disks[0] : NULL;
/*
* The devid has to be set before launching the device model. For the
* hotplug case this is done in libxl_device_nic_add but on domain
* creation this is called too late.
* Make two runs over configured NICs in order to avoid duplicate IDs
* in case the caller partially assigned IDs.
*/
for (i = 0; i < d_config->num_nics; i++) {
/* We have to init the nic here, because we still haven't
* called libxl_device_nic_add when domcreate_launch_dm gets called,
* but qemu needs the nic information to be complete.
*/
ret = libxl__device_nic_setdefault(gc, &d_config->nics[i], domid);
if (ret) goto error_out;
if (d_config->nics[i].devid > last_devid)
last_devid = d_config->nics[i].devid;
}
for (i = 0; i < d_config->num_nics; i++) {
if (d_config->nics[i].devid < 0)
d_config->nics[i].devid = ++last_devid;
}
if (restore_fd >= 0) {
LOG(DEBUG, "restoring, not running bootloader\n");
domcreate_bootloader_done(egc, &dcs->bl, 0);
} else {
LOG(DEBUG, "running bootloader");
dcs->bl.callback = domcreate_bootloader_done;
dcs->bl.console_available = domcreate_bootloader_console_available;
dcs->bl.info = &d_config->b_info;
dcs->bl.disk = bootdisk;
dcs->bl.domid = dcs->guest_domid;
dcs->bl.kernel = &dcs->build_state.pv_kernel;
dcs->bl.ramdisk = &dcs->build_state.pv_ramdisk;
libxl__bootloader_run(egc, &dcs->bl);
}
return;
error_out:
assert(ret);
domcreate_complete(egc, dcs, ret);
}
