qemu-e2k/migration/savevm.c

3325 lines
96 KiB
C
Raw Normal View History

/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2009-2015 Red Hat Inc
*
* Authors:
* Juan Quintela <quintela@redhat.com>
*
* 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 "hw/boards.h"
#include "net/net.h"
#include "migration.h"
#include "migration/snapshot.h"
#include "migration/vmstate.h"
#include "migration/misc.h"
#include "migration/register.h"
#include "migration/global_state.h"
#include "ram.h"
#include "qemu-file-channel.h"
#include "qemu-file.h"
#include "savevm.h"
#include "postcopy-ram.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-migration.h"
#include "qapi/qmp/json-writer.h"
#include "qapi/clone-visitor.h"
#include "qapi/qapi-builtin-visit.h"
#include "qapi/qmp/qerror.h"
#include "qemu/error-report.h"
#include "sysemu/cpus.h"
#include "exec/memory.h"
#include "exec/target_page.h"
#include "trace.h"
#include "qemu/iov.h"
#include "qemu/main-loop.h"
#include "block/snapshot.h"
#include "qemu/cutils.h"
#include "io/channel-buffer.h"
#include "io/channel-file.h"
#include "sysemu/replay.h"
#include "sysemu/runstate.h"
#include "sysemu/sysemu.h"
#include "sysemu/xen.h"
#include "migration/colo.h"
#include "qemu/bitmap.h"
#include "net/announce.h"
#include "qemu/yank.h"
#include "yank_functions.h"
const unsigned int postcopy_ram_discard_version;
/* Subcommands for QEMU_VM_COMMAND */
enum qemu_vm_cmd {
MIG_CMD_INVALID = 0, /* Must be 0 */
MIG_CMD_OPEN_RETURN_PATH, /* Tell the dest to open the Return path */
MIG_CMD_PING, /* Request a PONG on the RP */
MIG_CMD_POSTCOPY_ADVISE, /* Prior to any page transfers, just
warn we might want to do PC */
MIG_CMD_POSTCOPY_LISTEN, /* Start listening for incoming
pages as it's running. */
MIG_CMD_POSTCOPY_RUN, /* Start execution */
MIG_CMD_POSTCOPY_RAM_DISCARD, /* A list of pages to discard that
were previously sent during
precopy but are dirty. */
MIG_CMD_PACKAGED, /* Send a wrapped stream within this stream */
MIG_CMD_ENABLE_COLO, /* Enable COLO */
MIG_CMD_POSTCOPY_RESUME, /* resume postcopy on dest */
MIG_CMD_RECV_BITMAP, /* Request for recved bitmap on dst */
MIG_CMD_MAX
};
migration/savevm.c: set MAX_VM_CMD_PACKAGED_SIZE to 1ul << 32 MAX_VM_CMD_PACKAGED_SIZE is a constant used in qemu_savevm_send_packaged and loadvm_handle_cmd_packaged to determine whether a package is too big to be sent or received. qemu_savevm_send_packaged is called inside postcopy_start (migration/migration.c) to send the MigrationState in a single blob to the destination, using the MIG_CMD_PACKAGED subcommand, which will read it up using loadvm_handle_cmd_packaged. If the blob is larger than MAX_VM_CMD_PACKAGED_SIZE, an error is thrown and the postcopy migration is aborted. Both MAX_VM_CMD_PACKAGED_SIZE and MIG_CMD_PACKAGED were introduced by commit 11cf1d984b ("MIG_CMD_PACKAGED: Send a packaged chunk ..."). The constant has its original value of 1ul << 24 (16MB). The current MAX_VM_CMD_PACKAGED_SIZE value is not enough to support postcopy migration of bigger pseries guests. The blob size for a postcopy migration of a pseries guest with the following setup: qemu-system-ppc64 --nographic -vga none -machine pseries,accel=kvm -m 64G \ -smp 1,maxcpus=32 -device virtio-blk-pci,drive=rootdisk \ -drive file=f27.qcow2,if=none,cache=none,format=qcow2,id=rootdisk \ -netdev user,id=u1 -net nic,netdev=u1 Goes around 12MB. Bumping the RAM to 128G makes the blob sizes goes to 20MB. With 256G the blob goes to 37MB - more than twice the current maximum size. At this moment the pseries machine can handle guests with up to 1TB of RAM, making this postcopy blob goes to 128MB of size approximately. Following the discussions made in [1], there is a need to understand what devices are aggressively consuming the blob in that manner and see if that can be mitigated. Until then, we can set MAX_VM_CMD_PACKAGED_SIZE to the maximum value allowed. Since the size is a 32 bit int variable, we can set it as 1ul << 32, giving a maximum blob size of 4G that is enough to support postcopy migration of 32TB RAM guests given the above constraints. [1] https://lists.nongnu.org/archive/html/qemu-devel/2018-01/msg06313.html Signed-off-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Signed-off-by: Juan Quintela <quintela@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2018-01-26 16:59:40 +01:00
#define MAX_VM_CMD_PACKAGED_SIZE UINT32_MAX
static struct mig_cmd_args {
ssize_t len; /* -1 = variable */
const char *name;
} mig_cmd_args[] = {
[MIG_CMD_INVALID] = { .len = -1, .name = "INVALID" },
[MIG_CMD_OPEN_RETURN_PATH] = { .len = 0, .name = "OPEN_RETURN_PATH" },
[MIG_CMD_PING] = { .len = sizeof(uint32_t), .name = "PING" },
[MIG_CMD_POSTCOPY_ADVISE] = { .len = -1, .name = "POSTCOPY_ADVISE" },
[MIG_CMD_POSTCOPY_LISTEN] = { .len = 0, .name = "POSTCOPY_LISTEN" },
[MIG_CMD_POSTCOPY_RUN] = { .len = 0, .name = "POSTCOPY_RUN" },
[MIG_CMD_POSTCOPY_RAM_DISCARD] = {
.len = -1, .name = "POSTCOPY_RAM_DISCARD" },
[MIG_CMD_POSTCOPY_RESUME] = { .len = 0, .name = "POSTCOPY_RESUME" },
[MIG_CMD_PACKAGED] = { .len = 4, .name = "PACKAGED" },
[MIG_CMD_RECV_BITMAP] = { .len = -1, .name = "RECV_BITMAP" },
[MIG_CMD_MAX] = { .len = -1, .name = "MAX" },
};
/* Note for MIG_CMD_POSTCOPY_ADVISE:
* The format of arguments is depending on postcopy mode:
* - postcopy RAM only
* uint64_t host page size
* uint64_t taget page size
*
* - postcopy RAM and postcopy dirty bitmaps
* format is the same as for postcopy RAM only
*
* - postcopy dirty bitmaps only
* Nothing. Command length field is 0.
*
* Be careful: adding a new postcopy entity with some other parameters should
* not break format self-description ability. Good way is to introduce some
* generic extendable format with an exception for two old entities.
*/
/***********************************************************/
/* savevm/loadvm support */
static ssize_t block_writev_buffer(void *opaque, struct iovec *iov, int iovcnt,
int64_t pos, Error **errp)
{
int ret;
QEMUIOVector qiov;
qemu_iovec_init_external(&qiov, iov, iovcnt);
ret = bdrv_writev_vmstate(opaque, &qiov, pos);
if (ret < 0) {
return ret;
}
return qiov.size;
}
static ssize_t block_get_buffer(void *opaque, uint8_t *buf, int64_t pos,
size_t size, Error **errp)
{
return bdrv_load_vmstate(opaque, buf, pos, size);
}
static int bdrv_fclose(void *opaque, Error **errp)
{
return bdrv_flush(opaque);
}
static const QEMUFileOps bdrv_read_ops = {
.get_buffer = block_get_buffer,
.close = bdrv_fclose
};
static const QEMUFileOps bdrv_write_ops = {
.writev_buffer = block_writev_buffer,
.close = bdrv_fclose
};
static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable)
{
if (is_writable) {
return qemu_fopen_ops(bs, &bdrv_write_ops, false);
}
return qemu_fopen_ops(bs, &bdrv_read_ops, false);
}
/* QEMUFile timer support.
* Not in qemu-file.c to not add qemu-timer.c as dependency to qemu-file.c
*/
void timer_put(QEMUFile *f, QEMUTimer *ts)
{
uint64_t expire_time;
expire_time = timer_expire_time_ns(ts);
qemu_put_be64(f, expire_time);
}
void timer_get(QEMUFile *f, QEMUTimer *ts)
{
uint64_t expire_time;
expire_time = qemu_get_be64(f);
if (expire_time != -1) {
timer_mod_ns(ts, expire_time);
} else {
timer_del(ts);
}
}
/* VMState timer support.
* Not in vmstate.c to not add qemu-timer.c as dependency to vmstate.c
*/
static int get_timer(QEMUFile *f, void *pv, size_t size,
const VMStateField *field)
{
QEMUTimer *v = pv;
timer_get(f, v);
return 0;
}
static int put_timer(QEMUFile *f, void *pv, size_t size,
const VMStateField *field, JSONWriter *vmdesc)
{
QEMUTimer *v = pv;
timer_put(f, v);
return 0;
}
const VMStateInfo vmstate_info_timer = {
.name = "timer",
.get = get_timer,
.put = put_timer,
};
typedef struct CompatEntry {
char idstr[256];
int instance_id;
} CompatEntry;
typedef struct SaveStateEntry {
QTAILQ_ENTRY(SaveStateEntry) entry;
char idstr[256];
uint32_t instance_id;
int alias_id;
int version_id;
/* version id read from the stream */
int load_version_id;
int section_id;
/* section id read from the stream */
int load_section_id;
const SaveVMHandlers *ops;
const VMStateDescription *vmsd;
void *opaque;
CompatEntry *compat;
int is_ram;
} SaveStateEntry;
typedef struct SaveState {
QTAILQ_HEAD(, SaveStateEntry) handlers;
SaveStateEntry *handler_pri_head[MIG_PRI_MAX + 1];
int global_section_id;
uint32_t len;
const char *name;
uint32_t target_page_bits;
uint32_t caps_count;
MigrationCapability *capabilities;
QemuUUID uuid;
} SaveState;
static SaveState savevm_state = {
.handlers = QTAILQ_HEAD_INITIALIZER(savevm_state.handlers),
.handler_pri_head = { [MIG_PRI_DEFAULT ... MIG_PRI_MAX] = NULL },
.global_section_id = 0,
};
static bool should_validate_capability(int capability)
{
assert(capability >= 0 && capability < MIGRATION_CAPABILITY__MAX);
/* Validate only new capabilities to keep compatibility. */
switch (capability) {
case MIGRATION_CAPABILITY_X_IGNORE_SHARED:
return true;
default:
return false;
}
}
static uint32_t get_validatable_capabilities_count(void)
{
MigrationState *s = migrate_get_current();
uint32_t result = 0;
int i;
for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
if (should_validate_capability(i) && s->enabled_capabilities[i]) {
result++;
}
}
return result;
}
static int configuration_pre_save(void *opaque)
{
SaveState *state = opaque;
const char *current_name = MACHINE_GET_CLASS(current_machine)->name;
MigrationState *s = migrate_get_current();
int i, j;
state->len = strlen(current_name);
state->name = current_name;
state->target_page_bits = qemu_target_page_bits();
state->caps_count = get_validatable_capabilities_count();
state->capabilities = g_renew(MigrationCapability, state->capabilities,
state->caps_count);
for (i = j = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
if (should_validate_capability(i) && s->enabled_capabilities[i]) {
state->capabilities[j++] = i;
}
}
state->uuid = qemu_uuid;
return 0;
}
static int configuration_post_save(void *opaque)
{
SaveState *state = opaque;
g_free(state->capabilities);
state->capabilities = NULL;
state->caps_count = 0;
return 0;
}
static int configuration_pre_load(void *opaque)
{
SaveState *state = opaque;
/* If there is no target-page-bits subsection it means the source
* predates the variable-target-page-bits support and is using the
* minimum possible value for this CPU.
*/
state->target_page_bits = qemu_target_page_bits_min();
return 0;
}
static bool configuration_validate_capabilities(SaveState *state)
{
bool ret = true;
MigrationState *s = migrate_get_current();
unsigned long *source_caps_bm;
int i;
source_caps_bm = bitmap_new(MIGRATION_CAPABILITY__MAX);
for (i = 0; i < state->caps_count; i++) {
MigrationCapability capability = state->capabilities[i];
set_bit(capability, source_caps_bm);
}
for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
bool source_state, target_state;
if (!should_validate_capability(i)) {
continue;
}
source_state = test_bit(i, source_caps_bm);
target_state = s->enabled_capabilities[i];
if (source_state != target_state) {
error_report("Capability %s is %s, but received capability is %s",
MigrationCapability_str(i),
target_state ? "on" : "off",
source_state ? "on" : "off");
ret = false;
/* Don't break here to report all failed capabilities */
}
}
g_free(source_caps_bm);
return ret;
}
static int configuration_post_load(void *opaque, int version_id)
{
SaveState *state = opaque;
const char *current_name = MACHINE_GET_CLASS(current_machine)->name;
int ret = 0;
if (strncmp(state->name, current_name, state->len) != 0) {
error_report("Machine type received is '%.*s' and local is '%s'",
(int) state->len, state->name, current_name);
ret = -EINVAL;
goto out;
}
if (state->target_page_bits != qemu_target_page_bits()) {
error_report("Received TARGET_PAGE_BITS is %d but local is %d",
state->target_page_bits, qemu_target_page_bits());
ret = -EINVAL;
goto out;
}
if (!configuration_validate_capabilities(state)) {
ret = -EINVAL;
goto out;
}
out:
g_free((void *)state->name);
state->name = NULL;
state->len = 0;
g_free(state->capabilities);
state->capabilities = NULL;
state->caps_count = 0;
return ret;
}
static int get_capability(QEMUFile *f, void *pv, size_t size,
const VMStateField *field)
{
MigrationCapability *capability = pv;
char capability_str[UINT8_MAX + 1];
uint8_t len;
int i;
len = qemu_get_byte(f);
qemu_get_buffer(f, (uint8_t *)capability_str, len);
capability_str[len] = '\0';
for (i = 0; i < MIGRATION_CAPABILITY__MAX; i++) {
if (!strcmp(MigrationCapability_str(i), capability_str)) {
*capability = i;
return 0;
}
}
error_report("Received unknown capability %s", capability_str);
return -EINVAL;
}
static int put_capability(QEMUFile *f, void *pv, size_t size,
const VMStateField *field, JSONWriter *vmdesc)
{
MigrationCapability *capability = pv;
const char *capability_str = MigrationCapability_str(*capability);
size_t len = strlen(capability_str);
assert(len <= UINT8_MAX);
qemu_put_byte(f, len);
qemu_put_buffer(f, (uint8_t *)capability_str, len);
return 0;
}
static const VMStateInfo vmstate_info_capability = {
.name = "capability",
.get = get_capability,
.put = put_capability,
};
/* The target-page-bits subsection is present only if the
* target page size is not the same as the default (ie the
* minimum page size for a variable-page-size guest CPU).
* If it is present then it contains the actual target page
* bits for the machine, and migration will fail if the
* two ends don't agree about it.
*/
static bool vmstate_target_page_bits_needed(void *opaque)
{
return qemu_target_page_bits()
> qemu_target_page_bits_min();
}
static const VMStateDescription vmstate_target_page_bits = {
.name = "configuration/target-page-bits",
.version_id = 1,
.minimum_version_id = 1,
.needed = vmstate_target_page_bits_needed,
.fields = (VMStateField[]) {
VMSTATE_UINT32(target_page_bits, SaveState),
VMSTATE_END_OF_LIST()
}
};
static bool vmstate_capabilites_needed(void *opaque)
{
return get_validatable_capabilities_count() > 0;
}
static const VMStateDescription vmstate_capabilites = {
.name = "configuration/capabilities",
.version_id = 1,
.minimum_version_id = 1,
.needed = vmstate_capabilites_needed,
.fields = (VMStateField[]) {
VMSTATE_UINT32_V(caps_count, SaveState, 1),
VMSTATE_VARRAY_UINT32_ALLOC(capabilities, SaveState, caps_count, 1,
vmstate_info_capability,
MigrationCapability),
VMSTATE_END_OF_LIST()
}
};
static bool vmstate_uuid_needed(void *opaque)
{
return qemu_uuid_set && migrate_validate_uuid();
}
static int vmstate_uuid_post_load(void *opaque, int version_id)
{
SaveState *state = opaque;
char uuid_src[UUID_FMT_LEN + 1];
char uuid_dst[UUID_FMT_LEN + 1];
if (!qemu_uuid_set) {
/*
* It's warning because user might not know UUID in some cases,
* e.g. load an old snapshot
*/
qemu_uuid_unparse(&state->uuid, uuid_src);
warn_report("UUID is received %s, but local uuid isn't set",
uuid_src);
return 0;
}
if (!qemu_uuid_is_equal(&state->uuid, &qemu_uuid)) {
qemu_uuid_unparse(&state->uuid, uuid_src);
qemu_uuid_unparse(&qemu_uuid, uuid_dst);
error_report("UUID received is %s and local is %s", uuid_src, uuid_dst);
return -EINVAL;
}
return 0;
}
static const VMStateDescription vmstate_uuid = {
.name = "configuration/uuid",
.version_id = 1,
.minimum_version_id = 1,
.needed = vmstate_uuid_needed,
.post_load = vmstate_uuid_post_load,
.fields = (VMStateField[]) {
VMSTATE_UINT8_ARRAY_V(uuid.data, SaveState, sizeof(QemuUUID), 1),
VMSTATE_END_OF_LIST()
}
};
static const VMStateDescription vmstate_configuration = {
.name = "configuration",
.version_id = 1,
.pre_load = configuration_pre_load,
.post_load = configuration_post_load,
.pre_save = configuration_pre_save,
.post_save = configuration_post_save,
.fields = (VMStateField[]) {
VMSTATE_UINT32(len, SaveState),
VMSTATE_VBUFFER_ALLOC_UINT32(name, SaveState, 0, NULL, len),
VMSTATE_END_OF_LIST()
},
.subsections = (const VMStateDescription *[]) {
&vmstate_target_page_bits,
&vmstate_capabilites,
&vmstate_uuid,
NULL
}
};
static void dump_vmstate_vmsd(FILE *out_file,
const VMStateDescription *vmsd, int indent,
bool is_subsection);
static void dump_vmstate_vmsf(FILE *out_file, const VMStateField *field,
int indent)
{
fprintf(out_file, "%*s{\n", indent, "");
indent += 2;
fprintf(out_file, "%*s\"field\": \"%s\",\n", indent, "", field->name);
fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "",
field->version_id);
fprintf(out_file, "%*s\"field_exists\": %s,\n", indent, "",
field->field_exists ? "true" : "false");
fprintf(out_file, "%*s\"size\": %zu", indent, "", field->size);
if (field->vmsd != NULL) {
fprintf(out_file, ",\n");
dump_vmstate_vmsd(out_file, field->vmsd, indent, false);
}
fprintf(out_file, "\n%*s}", indent - 2, "");
}
static void dump_vmstate_vmss(FILE *out_file,
const VMStateDescription **subsection,
int indent)
{
if (*subsection != NULL) {
dump_vmstate_vmsd(out_file, *subsection, indent, true);
}
}
static void dump_vmstate_vmsd(FILE *out_file,
const VMStateDescription *vmsd, int indent,
bool is_subsection)
{
if (is_subsection) {
fprintf(out_file, "%*s{\n", indent, "");
} else {
fprintf(out_file, "%*s\"%s\": {\n", indent, "", "Description");
}
indent += 2;
fprintf(out_file, "%*s\"name\": \"%s\",\n", indent, "", vmsd->name);
fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "",
vmsd->version_id);
fprintf(out_file, "%*s\"minimum_version_id\": %d", indent, "",
vmsd->minimum_version_id);
if (vmsd->fields != NULL) {
const VMStateField *field = vmsd->fields;
bool first;
fprintf(out_file, ",\n%*s\"Fields\": [\n", indent, "");
first = true;
while (field->name != NULL) {
if (field->flags & VMS_MUST_EXIST) {
/* Ignore VMSTATE_VALIDATE bits; these don't get migrated */
field++;
continue;
}
if (!first) {
fprintf(out_file, ",\n");
}
dump_vmstate_vmsf(out_file, field, indent + 2);
field++;
first = false;
}
fprintf(out_file, "\n%*s]", indent, "");
}
if (vmsd->subsections != NULL) {
const VMStateDescription **subsection = vmsd->subsections;
bool first;
fprintf(out_file, ",\n%*s\"Subsections\": [\n", indent, "");
first = true;
while (*subsection != NULL) {
if (!first) {
fprintf(out_file, ",\n");
}
dump_vmstate_vmss(out_file, subsection, indent + 2);
subsection++;
first = false;
}
fprintf(out_file, "\n%*s]", indent, "");
}
fprintf(out_file, "\n%*s}", indent - 2, "");
}
static void dump_machine_type(FILE *out_file)
{
MachineClass *mc;
mc = MACHINE_GET_CLASS(current_machine);
fprintf(out_file, " \"vmschkmachine\": {\n");
fprintf(out_file, " \"Name\": \"%s\"\n", mc->name);
fprintf(out_file, " },\n");
}
void dump_vmstate_json_to_file(FILE *out_file)
{
GSList *list, *elt;
bool first;
fprintf(out_file, "{\n");
dump_machine_type(out_file);
first = true;
list = object_class_get_list(TYPE_DEVICE, true);
for (elt = list; elt; elt = elt->next) {
DeviceClass *dc = OBJECT_CLASS_CHECK(DeviceClass, elt->data,
TYPE_DEVICE);
const char *name;
int indent = 2;
if (!dc->vmsd) {
continue;
}
if (!first) {
fprintf(out_file, ",\n");
}
name = object_class_get_name(OBJECT_CLASS(dc));
fprintf(out_file, "%*s\"%s\": {\n", indent, "", name);
indent += 2;
fprintf(out_file, "%*s\"Name\": \"%s\",\n", indent, "", name);
fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "",
dc->vmsd->version_id);
fprintf(out_file, "%*s\"minimum_version_id\": %d,\n", indent, "",
dc->vmsd->minimum_version_id);
dump_vmstate_vmsd(out_file, dc->vmsd, indent, false);
fprintf(out_file, "\n%*s}", indent - 2, "");
first = false;
}
fprintf(out_file, "\n}\n");
fclose(out_file);
migration/savevm: release gslist after dump_vmstate_json 'list' forgot to free at the end of dump_vmstate_json_to_file(), although it's called only once, but seems like a clean code. Fix the leak as follow: Direct leak of 16 byte(s) in 1 object(s) allocated from: #0 0x7fb946abd768 in __interceptor_malloc (/lib64/libasan.so.5+0xef768) #1 0x7fb945eca445 in g_malloc (/lib64/libglib-2.0.so.0+0x52445) #2 0x7fb945ee2066 in g_slice_alloc (/lib64/libglib-2.0.so.0+0x6a066) #3 0x7fb945ee3139 in g_slist_prepend (/lib64/libglib-2.0.so.0+0x6b139) #4 0x5585db591581 in object_class_get_list_tramp /mnt/sdb/qemu-new/qemu/qom/object.c:1084 #5 0x5585db590f66 in object_class_foreach_tramp /mnt/sdb/qemu-new/qemu/qom/object.c:1028 #6 0x7fb945eb35f7 in g_hash_table_foreach (/lib64/libglib-2.0.so.0+0x3b5f7) #7 0x5585db59110c in object_class_foreach /mnt/sdb/qemu-new/qemu/qom/object.c:1038 #8 0x5585db5916b6 in object_class_get_list /mnt/sdb/qemu-new/qemu/qom/object.c:1092 #9 0x5585db335ca0 in dump_vmstate_json_to_file /mnt/sdb/qemu-new/qemu/migration/savevm.c:638 #10 0x5585daa5bcbf in main /mnt/sdb/qemu-new/qemu/vl.c:4420 #11 0x7fb941204812 in __libc_start_main ../csu/libc-start.c:308 #12 0x5585da29420d in _start (/mnt/sdb/qemu-new/qemu/build/x86_64-softmmu/qemu-system-x86_64+0x27f020d) Indirect leak of 7472 byte(s) in 467 object(s) allocated from: #0 0x7fb946abd768 in __interceptor_malloc (/lib64/libasan.so.5+0xef768) #1 0x7fb945eca445 in g_malloc (/lib64/libglib-2.0.so.0+0x52445) #2 0x7fb945ee2066 in g_slice_alloc (/lib64/libglib-2.0.so.0+0x6a066) #3 0x7fb945ee3139 in g_slist_prepend (/lib64/libglib-2.0.so.0+0x6b139) #4 0x5585db591581 in object_class_get_list_tramp /mnt/sdb/qemu-new/qemu/qom/object.c:1084 #5 0x5585db590f66 in object_class_foreach_tramp /mnt/sdb/qemu-new/qemu/qom/object.c:1028 #6 0x7fb945eb35f7 in g_hash_table_foreach (/lib64/libglib-2.0.so.0+0x3b5f7) #7 0x5585db59110c in object_class_foreach /mnt/sdb/qemu-new/qemu/qom/object.c:1038 #8 0x5585db5916b6 in object_class_get_list /mnt/sdb/qemu-new/qemu/qom/object.c:1092 #9 0x5585db335ca0 in dump_vmstate_json_to_file /mnt/sdb/qemu-new/qemu/migration/savevm.c:638 #10 0x5585daa5bcbf in main /mnt/sdb/qemu-new/qemu/vl.c:4420 #11 0x7fb941204812 in __libc_start_main ../csu/libc-start.c:308 #12 0x5585da29420d in _start (/mnt/sdb/qemu-new/qemu/build/x86_64-softmmu/qemu-system-x86_64+0x27f020d) Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Pan Nengyuan <pannengyuan@huawei.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Juan Quintela <quintela@redhat.com>
2020-02-19 10:47:05 +01:00
g_slist_free(list);
}
static uint32_t calculate_new_instance_id(const char *idstr)
{
SaveStateEntry *se;
uint32_t instance_id = 0;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (strcmp(idstr, se->idstr) == 0
&& instance_id <= se->instance_id) {
instance_id = se->instance_id + 1;
}
}
/* Make sure we never loop over without being noticed */
assert(instance_id != VMSTATE_INSTANCE_ID_ANY);
return instance_id;
}
static int calculate_compat_instance_id(const char *idstr)
{
SaveStateEntry *se;
int instance_id = 0;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->compat) {
continue;
}
if (strcmp(idstr, se->compat->idstr) == 0
&& instance_id <= se->compat->instance_id) {
instance_id = se->compat->instance_id + 1;
}
}
return instance_id;
}
static inline MigrationPriority save_state_priority(SaveStateEntry *se)
{
if (se->vmsd) {
return se->vmsd->priority;
}
return MIG_PRI_DEFAULT;
}
static void savevm_state_handler_insert(SaveStateEntry *nse)
{
MigrationPriority priority = save_state_priority(nse);
SaveStateEntry *se;
int i;
assert(priority <= MIG_PRI_MAX);
for (i = priority - 1; i >= 0; i--) {
se = savevm_state.handler_pri_head[i];
if (se != NULL) {
assert(save_state_priority(se) < priority);
break;
}
}
if (i >= 0) {
QTAILQ_INSERT_BEFORE(se, nse, entry);
} else {
QTAILQ_INSERT_TAIL(&savevm_state.handlers, nse, entry);
}
if (savevm_state.handler_pri_head[priority] == NULL) {
savevm_state.handler_pri_head[priority] = nse;
}
}
static void savevm_state_handler_remove(SaveStateEntry *se)
{
SaveStateEntry *next;
MigrationPriority priority = save_state_priority(se);
if (se == savevm_state.handler_pri_head[priority]) {
next = QTAILQ_NEXT(se, entry);
if (next != NULL && save_state_priority(next) == priority) {
savevm_state.handler_pri_head[priority] = next;
} else {
savevm_state.handler_pri_head[priority] = NULL;
}
}
QTAILQ_REMOVE(&savevm_state.handlers, se, entry);
}
/* TODO: Individual devices generally have very little idea about the rest
of the system, so instance_id should be removed/replaced.
Meanwhile pass -1 as instance_id if you do not already have a clearly
distinguishing id for all instances of your device class. */
int register_savevm_live(const char *idstr,
uint32_t instance_id,
int version_id,
const SaveVMHandlers *ops,
void *opaque)
{
SaveStateEntry *se;
se = g_new0(SaveStateEntry, 1);
se->version_id = version_id;
se->section_id = savevm_state.global_section_id++;
se->ops = ops;
se->opaque = opaque;
se->vmsd = NULL;
/* if this is a live_savem then set is_ram */
if (ops->save_setup != NULL) {
se->is_ram = 1;
}
pstrcat(se->idstr, sizeof(se->idstr), idstr);
if (instance_id == VMSTATE_INSTANCE_ID_ANY) {
se->instance_id = calculate_new_instance_id(se->idstr);
} else {
se->instance_id = instance_id;
}
assert(!se->compat || se->instance_id == 0);
savevm_state_handler_insert(se);
return 0;
}
void unregister_savevm(VMStateIf *obj, const char *idstr, void *opaque)
{
SaveStateEntry *se, *new_se;
char id[256] = "";
if (obj) {
char *oid = vmstate_if_get_id(obj);
if (oid) {
pstrcpy(id, sizeof(id), oid);
pstrcat(id, sizeof(id), "/");
g_free(oid);
}
}
pstrcat(id, sizeof(id), idstr);
QTAILQ_FOREACH_SAFE(se, &savevm_state.handlers, entry, new_se) {
if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) {
savevm_state_handler_remove(se);
g_free(se->compat);
g_free(se);
}
}
}
int vmstate_register_with_alias_id(VMStateIf *obj, uint32_t instance_id,
const VMStateDescription *vmsd,
void *opaque, int alias_id,
int required_for_version,
Error **errp)
{
SaveStateEntry *se;
/* If this triggers, alias support can be dropped for the vmsd. */
assert(alias_id == -1 || required_for_version >= vmsd->minimum_version_id);
se = g_new0(SaveStateEntry, 1);
se->version_id = vmsd->version_id;
se->section_id = savevm_state.global_section_id++;
se->opaque = opaque;
se->vmsd = vmsd;
se->alias_id = alias_id;
if (obj) {
char *id = vmstate_if_get_id(obj);
if (id) {
if (snprintf(se->idstr, sizeof(se->idstr), "%s/", id) >=
sizeof(se->idstr)) {
error_setg(errp, "Path too long for VMState (%s)", id);
g_free(id);
g_free(se);
return -1;
}
g_free(id);
se->compat = g_new0(CompatEntry, 1);
pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), vmsd->name);
se->compat->instance_id = instance_id == VMSTATE_INSTANCE_ID_ANY ?
calculate_compat_instance_id(vmsd->name) : instance_id;
instance_id = VMSTATE_INSTANCE_ID_ANY;
}
}
pstrcat(se->idstr, sizeof(se->idstr), vmsd->name);
if (instance_id == VMSTATE_INSTANCE_ID_ANY) {
se->instance_id = calculate_new_instance_id(se->idstr);
} else {
se->instance_id = instance_id;
}
assert(!se->compat || se->instance_id == 0);
savevm_state_handler_insert(se);
return 0;
}
void vmstate_unregister(VMStateIf *obj, const VMStateDescription *vmsd,
void *opaque)
{
SaveStateEntry *se, *new_se;
QTAILQ_FOREACH_SAFE(se, &savevm_state.handlers, entry, new_se) {
if (se->vmsd == vmsd && se->opaque == opaque) {
savevm_state_handler_remove(se);
g_free(se->compat);
g_free(se);
}
}
}
static int vmstate_load(QEMUFile *f, SaveStateEntry *se)
{
trace_vmstate_load(se->idstr, se->vmsd ? se->vmsd->name : "(old)");
if (!se->vmsd) { /* Old style */
return se->ops->load_state(f, se->opaque, se->load_version_id);
}
return vmstate_load_state(f, se->vmsd, se->opaque, se->load_version_id);
}
static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se,
JSONWriter *vmdesc)
{
int64_t old_offset, size;
old_offset = qemu_ftell_fast(f);
se->ops->save_state(f, se->opaque);
size = qemu_ftell_fast(f) - old_offset;
if (vmdesc) {
json_writer_int64(vmdesc, "size", size);
json_writer_start_array(vmdesc, "fields");
json_writer_start_object(vmdesc, NULL);
json_writer_str(vmdesc, "name", "data");
json_writer_int64(vmdesc, "size", size);
json_writer_str(vmdesc, "type", "buffer");
json_writer_end_object(vmdesc);
json_writer_end_array(vmdesc);
}
}
static int vmstate_save(QEMUFile *f, SaveStateEntry *se,
JSONWriter *vmdesc)
{
trace_vmstate_save(se->idstr, se->vmsd ? se->vmsd->name : "(old)");
if (!se->vmsd) {
vmstate_save_old_style(f, se, vmdesc);
return 0;
}
return vmstate_save_state(f, se->vmsd, se->opaque, vmdesc);
}
/*
* Write the header for device section (QEMU_VM_SECTION START/END/PART/FULL)
*/
static void save_section_header(QEMUFile *f, SaveStateEntry *se,
uint8_t section_type)
{
qemu_put_byte(f, section_type);
qemu_put_be32(f, se->section_id);
if (section_type == QEMU_VM_SECTION_FULL ||
section_type == QEMU_VM_SECTION_START) {
/* ID string */
size_t len = strlen(se->idstr);
qemu_put_byte(f, len);
qemu_put_buffer(f, (uint8_t *)se->idstr, len);
qemu_put_be32(f, se->instance_id);
qemu_put_be32(f, se->version_id);
}
}
/*
* Write a footer onto device sections that catches cases misformatted device
* sections.
*/
static void save_section_footer(QEMUFile *f, SaveStateEntry *se)
{
if (migrate_get_current()->send_section_footer) {
qemu_put_byte(f, QEMU_VM_SECTION_FOOTER);
qemu_put_be32(f, se->section_id);
}
}
/**
* qemu_savevm_command_send: Send a 'QEMU_VM_COMMAND' type element with the
* command and associated data.
*
* @f: File to send command on
* @command: Command type to send
* @len: Length of associated data
* @data: Data associated with command.
*/
static void qemu_savevm_command_send(QEMUFile *f,
enum qemu_vm_cmd command,
uint16_t len,
uint8_t *data)
{
trace_savevm_command_send(command, len);
qemu_put_byte(f, QEMU_VM_COMMAND);
qemu_put_be16(f, (uint16_t)command);
qemu_put_be16(f, len);
qemu_put_buffer(f, data, len);
qemu_fflush(f);
}
void qemu_savevm_send_colo_enable(QEMUFile *f)
{
trace_savevm_send_colo_enable();
qemu_savevm_command_send(f, MIG_CMD_ENABLE_COLO, 0, NULL);
}
void qemu_savevm_send_ping(QEMUFile *f, uint32_t value)
{
uint32_t buf;
trace_savevm_send_ping(value);
buf = cpu_to_be32(value);
qemu_savevm_command_send(f, MIG_CMD_PING, sizeof(value), (uint8_t *)&buf);
}
void qemu_savevm_send_open_return_path(QEMUFile *f)
{
trace_savevm_send_open_return_path();
qemu_savevm_command_send(f, MIG_CMD_OPEN_RETURN_PATH, 0, NULL);
}
/* We have a buffer of data to send; we don't want that all to be loaded
* by the command itself, so the command contains just the length of the
* extra buffer that we then send straight after it.
* TODO: Must be a better way to organise that
*
* Returns:
* 0 on success
* -ve on error
*/
int qemu_savevm_send_packaged(QEMUFile *f, const uint8_t *buf, size_t len)
{
uint32_t tmp;
if (len > MAX_VM_CMD_PACKAGED_SIZE) {
error_report("%s: Unreasonably large packaged state: %zu",
__func__, len);
return -1;
}
tmp = cpu_to_be32(len);
trace_qemu_savevm_send_packaged();
qemu_savevm_command_send(f, MIG_CMD_PACKAGED, 4, (uint8_t *)&tmp);
qemu_put_buffer(f, buf, len);
return 0;
}
/* Send prior to any postcopy transfer */
void qemu_savevm_send_postcopy_advise(QEMUFile *f)
{
if (migrate_postcopy_ram()) {
uint64_t tmp[2];
tmp[0] = cpu_to_be64(ram_pagesize_summary());
tmp[1] = cpu_to_be64(qemu_target_page_size());
trace_qemu_savevm_send_postcopy_advise();
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_ADVISE,
16, (uint8_t *)tmp);
} else {
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_ADVISE, 0, NULL);
}
}
/* Sent prior to starting the destination running in postcopy, discard pages
* that have already been sent but redirtied on the source.
* CMD_POSTCOPY_RAM_DISCARD consist of:
* byte version (0)
* byte Length of name field (not including 0)
* n x byte RAM block name
* byte 0 terminator (just for safety)
* n x Byte ranges within the named RAMBlock
* be64 Start of the range
* be64 Length
*
* name: RAMBlock name that these entries are part of
* len: Number of page entries
* start_list: 'len' addresses
* length_list: 'len' addresses
*
*/
void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name,
uint16_t len,
uint64_t *start_list,
uint64_t *length_list)
{
uint8_t *buf;
uint16_t tmplen;
uint16_t t;
size_t name_len = strlen(name);
trace_qemu_savevm_send_postcopy_ram_discard(name, len);
assert(name_len < 256);
buf = g_malloc0(1 + 1 + name_len + 1 + (8 + 8) * len);
buf[0] = postcopy_ram_discard_version;
buf[1] = name_len;
memcpy(buf + 2, name, name_len);
tmplen = 2 + name_len;
buf[tmplen++] = '\0';
for (t = 0; t < len; t++) {
stq_be_p(buf + tmplen, start_list[t]);
tmplen += 8;
stq_be_p(buf + tmplen, length_list[t]);
tmplen += 8;
}
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RAM_DISCARD, tmplen, buf);
g_free(buf);
}
/* Get the destination into a state where it can receive postcopy data. */
void qemu_savevm_send_postcopy_listen(QEMUFile *f)
{
trace_savevm_send_postcopy_listen();
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_LISTEN, 0, NULL);
}
/* Kick the destination into running */
void qemu_savevm_send_postcopy_run(QEMUFile *f)
{
trace_savevm_send_postcopy_run();
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RUN, 0, NULL);
}
void qemu_savevm_send_postcopy_resume(QEMUFile *f)
{
trace_savevm_send_postcopy_resume();
qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RESUME, 0, NULL);
}
void qemu_savevm_send_recv_bitmap(QEMUFile *f, char *block_name)
{
size_t len;
char buf[256];
trace_savevm_send_recv_bitmap(block_name);
buf[0] = len = strlen(block_name);
memcpy(buf + 1, block_name, len);
qemu_savevm_command_send(f, MIG_CMD_RECV_BITMAP, len + 1, (uint8_t *)buf);
}
bool qemu_savevm_state_blocked(Error **errp)
{
SaveStateEntry *se;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->vmsd && se->vmsd->unmigratable) {
error_setg(errp, "State blocked by non-migratable device '%s'",
se->idstr);
return true;
}
}
return false;
}
void qemu_savevm_non_migratable_list(strList **reasons)
{
SaveStateEntry *se;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->vmsd && se->vmsd->unmigratable) {
QAPI_LIST_PREPEND(*reasons,
g_strdup_printf("non-migratable device: %s",
se->idstr));
}
}
}
void qemu_savevm_state_header(QEMUFile *f)
{
trace_savevm_state_header();
qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
qemu_put_be32(f, QEMU_VM_FILE_VERSION);
if (migrate_get_current()->send_configuration) {
qemu_put_byte(f, QEMU_VM_CONFIGURATION);
vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0);
}
}
bool qemu_savevm_state_guest_unplug_pending(void)
{
SaveStateEntry *se;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->vmsd && se->vmsd->dev_unplug_pending &&
se->vmsd->dev_unplug_pending(se->opaque)) {
return true;
}
}
return false;
}
void qemu_savevm_state_setup(QEMUFile *f)
{
SaveStateEntry *se;
Error *local_err = NULL;
int ret;
trace_savevm_state_setup();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->save_setup) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
save_section_header(f, se, QEMU_VM_SECTION_START);
ret = se->ops->save_setup(f, se->opaque);
save_section_footer(f, se);
if (ret < 0) {
qemu_file_set_error(f, ret);
break;
}
}
if (precopy_notify(PRECOPY_NOTIFY_SETUP, &local_err)) {
error_report_err(local_err);
}
}
int qemu_savevm_state_resume_prepare(MigrationState *s)
{
SaveStateEntry *se;
int ret;
trace_savevm_state_resume_prepare();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->resume_prepare) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
ret = se->ops->resume_prepare(s, se->opaque);
if (ret < 0) {
return ret;
}
}
return 0;
}
/*
* this function has three return values:
* negative: there was one error, and we have -errno.
* 0 : We haven't finished, caller have to go again
* 1 : We have finished, we can go to complete phase
*/
int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy)
{
SaveStateEntry *se;
int ret = 1;
trace_savevm_state_iterate();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->save_live_iterate) {
continue;
}
if (se->ops->is_active &&
!se->ops->is_active(se->opaque)) {
continue;
}
if (se->ops->is_active_iterate &&
!se->ops->is_active_iterate(se->opaque)) {
continue;
}
/*
* In the postcopy phase, any device that doesn't know how to
* do postcopy should have saved it's state in the _complete
* call that's already run, it might get confused if we call
* iterate afterwards.
*/
if (postcopy &&
!(se->ops->has_postcopy && se->ops->has_postcopy(se->opaque))) {
continue;
}
if (qemu_file_rate_limit(f)) {
return 0;
}
trace_savevm_section_start(se->idstr, se->section_id);
save_section_header(f, se, QEMU_VM_SECTION_PART);
ret = se->ops->save_live_iterate(f, se->opaque);
trace_savevm_section_end(se->idstr, se->section_id, ret);
save_section_footer(f, se);
if (ret < 0) {
error_report("failed to save SaveStateEntry with id(name): "
"%d(%s): %d",
se->section_id, se->idstr, ret);
qemu_file_set_error(f, ret);
}
if (ret <= 0) {
/* Do not proceed to the next vmstate before this one reported
completion of the current stage. This serializes the migration
and reduces the probability that a faster changing state is
synchronized over and over again. */
break;
}
}
return ret;
}
static bool should_send_vmdesc(void)
{
MachineState *machine = MACHINE(qdev_get_machine());
bool in_postcopy = migration_in_postcopy();
return !machine->suppress_vmdesc && !in_postcopy;
}
/*
* Calls the save_live_complete_postcopy methods
* causing the last few pages to be sent immediately and doing any associated
* cleanup.
* Note postcopy also calls qemu_savevm_state_complete_precopy to complete
* all the other devices, but that happens at the point we switch to postcopy.
*/
void qemu_savevm_state_complete_postcopy(QEMUFile *f)
{
SaveStateEntry *se;
int ret;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->save_live_complete_postcopy) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
trace_savevm_section_start(se->idstr, se->section_id);
/* Section type */
qemu_put_byte(f, QEMU_VM_SECTION_END);
qemu_put_be32(f, se->section_id);
ret = se->ops->save_live_complete_postcopy(f, se->opaque);
trace_savevm_section_end(se->idstr, se->section_id, ret);
save_section_footer(f, se);
if (ret < 0) {
qemu_file_set_error(f, ret);
return;
}
}
qemu_put_byte(f, QEMU_VM_EOF);
qemu_fflush(f);
}
static
int qemu_savevm_state_complete_precopy_iterable(QEMUFile *f, bool in_postcopy)
{
SaveStateEntry *se;
int ret;
KVM: Rework VCPU state writeback API This grand cleanup drops all reset and vmsave/load related synchronization points in favor of four(!) generic hooks: - cpu_synchronize_all_states in qemu_savevm_state_complete (initial sync from kernel before vmsave) - cpu_synchronize_all_post_init in qemu_loadvm_state (writeback after vmload) - cpu_synchronize_all_post_init in main after machine init - cpu_synchronize_all_post_reset in qemu_system_reset (writeback after system reset) These writeback points + the existing one of VCPU exec after cpu_synchronize_state map on three levels of writeback: - KVM_PUT_RUNTIME_STATE (during runtime, other VCPUs continue to run) - KVM_PUT_RESET_STATE (on synchronous system reset, all VCPUs stopped) - KVM_PUT_FULL_STATE (on init or vmload, all VCPUs stopped as well) This level is passed to the arch-specific VCPU state writing function that will decide which concrete substates need to be written. That way, no writer of load, save or reset functions that interact with in-kernel KVM states will ever have to worry about synchronization again. That also means that a lot of reasons for races, segfaults and deadlocks are eliminated. cpu_synchronize_state remains untouched, just as Anthony suggested. We continue to need it before reading or writing of VCPU states that are also tracked by in-kernel KVM subsystems. Consequently, this patch removes many cpu_synchronize_state calls that are now redundant, just like remaining explicit register syncs. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-03-01 19:10:30 +01:00
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops ||
(in_postcopy && se->ops->has_postcopy &&
se->ops->has_postcopy(se->opaque)) ||
!se->ops->save_live_complete_precopy) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
trace_savevm_section_start(se->idstr, se->section_id);
save_section_header(f, se, QEMU_VM_SECTION_END);
ret = se->ops->save_live_complete_precopy(f, se->opaque);
trace_savevm_section_end(se->idstr, se->section_id, ret);
save_section_footer(f, se);
if (ret < 0) {
qemu_file_set_error(f, ret);
return -1;
}
}
return 0;
}
int qemu_savevm_state_complete_precopy_non_iterable(QEMUFile *f,
bool in_postcopy,
bool inactivate_disks)
{
g_autoptr(JSONWriter) vmdesc = NULL;
int vmdesc_len;
SaveStateEntry *se;
int ret;
vmdesc = json_writer_new(false);
json_writer_start_object(vmdesc, NULL);
json_writer_int64(vmdesc, "page_size", qemu_target_page_size());
json_writer_start_array(vmdesc, "devices");
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
continue;
}
if (se->vmsd && !vmstate_save_needed(se->vmsd, se->opaque)) {
trace_savevm_section_skip(se->idstr, se->section_id);
continue;
}
trace_savevm_section_start(se->idstr, se->section_id);
json_writer_start_object(vmdesc, NULL);
json_writer_str(vmdesc, "name", se->idstr);
json_writer_int64(vmdesc, "instance_id", se->instance_id);
save_section_header(f, se, QEMU_VM_SECTION_FULL);
ret = vmstate_save(f, se, vmdesc);
if (ret) {
qemu_file_set_error(f, ret);
return ret;
}
trace_savevm_section_end(se->idstr, se->section_id, 0);
save_section_footer(f, se);
json_writer_end_object(vmdesc);
}
if (inactivate_disks) {
/* Inactivate before sending QEMU_VM_EOF so that the
* bdrv_activate_all() on the other end won't fail. */
ret = bdrv_inactivate_all();
if (ret) {
error_report("%s: bdrv_inactivate_all() failed (%d)",
__func__, ret);
qemu_file_set_error(f, ret);
return ret;
}
}
if (!in_postcopy) {
/* Postcopy stream will still be going */
qemu_put_byte(f, QEMU_VM_EOF);
}
json_writer_end_array(vmdesc);
json_writer_end_object(vmdesc);
vmdesc_len = strlen(json_writer_get(vmdesc));
if (should_send_vmdesc()) {
qemu_put_byte(f, QEMU_VM_VMDESCRIPTION);
qemu_put_be32(f, vmdesc_len);
qemu_put_buffer(f, (uint8_t *)json_writer_get(vmdesc), vmdesc_len);
}
return 0;
}
int qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only,
bool inactivate_disks)
{
int ret;
Error *local_err = NULL;
bool in_postcopy = migration_in_postcopy();
if (precopy_notify(PRECOPY_NOTIFY_COMPLETE, &local_err)) {
error_report_err(local_err);
}
trace_savevm_state_complete_precopy();
cpu_synchronize_all_states();
if (!in_postcopy || iterable_only) {
ret = qemu_savevm_state_complete_precopy_iterable(f, in_postcopy);
if (ret) {
return ret;
}
}
if (iterable_only) {
goto flush;
}
ret = qemu_savevm_state_complete_precopy_non_iterable(f, in_postcopy,
inactivate_disks);
if (ret) {
return ret;
}
flush:
qemu_fflush(f);
return 0;
}
/* Give an estimate of the amount left to be transferred,
* the result is split into the amount for units that can and
* for units that can't do postcopy.
*/
void qemu_savevm_state_pending(QEMUFile *f, uint64_t threshold_size,
uint64_t *res_precopy_only,
uint64_t *res_compatible,
uint64_t *res_postcopy_only)
{
SaveStateEntry *se;
*res_precopy_only = 0;
*res_compatible = 0;
*res_postcopy_only = 0;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->save_live_pending) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
se->ops->save_live_pending(f, se->opaque, threshold_size,
res_precopy_only, res_compatible,
res_postcopy_only);
}
}
void qemu_savevm_state_cleanup(void)
{
SaveStateEntry *se;
Error *local_err = NULL;
if (precopy_notify(PRECOPY_NOTIFY_CLEANUP, &local_err)) {
error_report_err(local_err);
}
trace_savevm_state_cleanup();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->ops && se->ops->save_cleanup) {
se->ops->save_cleanup(se->opaque);
}
}
}
static int qemu_savevm_state(QEMUFile *f, Error **errp)
{
int ret;
MigrationState *ms = migrate_get_current();
MigrationStatus status;
if (migration_is_running(ms->state)) {
error_setg(errp, QERR_MIGRATION_ACTIVE);
return -EINVAL;
}
if (migrate_use_block()) {
error_setg(errp, "Block migration and snapshots are incompatible");
return -EINVAL;
}
migrate_init(ms);
migration: always initialise ram_counters for a new migration This patch fix a multifd migration bug in migration speed calculation, this problem can be reproduced as follows: 1. start a vm and give a heavy memory write stress to prevent the vm be successfully migrated to destination 2. begin a migration with multifd 3. migrate for a long time [actually, this can be measured by transferred bytes] 4. migrate cancel 5. begin a new migration with multifd, the migration will directly run into migration_completion phase Reason as follows: Migration update bandwidth and s->threshold_size in function migration_update_counters after BUFFER_DELAY time: current_bytes = migration_total_bytes(s); transferred = current_bytes - s->iteration_initial_bytes; time_spent = current_time - s->iteration_start_time; bandwidth = (double)transferred / time_spent; s->threshold_size = bandwidth * s->parameters.downtime_limit; In multifd migration, migration_total_bytes function return qemu_ftell(s->to_dst_file) + ram_counters.multifd_bytes. s->iteration_initial_bytes will be initialized to 0 at every new migration, but ram_counters is a global variable, and history migration data will be accumulated. So if the ram_counters.multifd_bytes is big enough, it may lead pending_size >= s->threshold_size become false in migration_iteration_run after the first migration_update_counters. Signed-off-by: Ivan Ren <ivanren@tencent.com> Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Wei Yang <richardw.yang@linux.intel.com> Suggested-by: Wei Yang <richardw.yang@linux.intel.com> Message-Id: <1564741121-1840-1-git-send-email-ivanren@tencent.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2019-08-02 12:18:41 +02:00
memset(&ram_counters, 0, sizeof(ram_counters));
memset(&compression_counters, 0, sizeof(compression_counters));
ms->to_dst_file = f;
qemu_mutex_unlock_iothread();
qemu_savevm_state_header(f);
qemu_savevm_state_setup(f);
qemu_mutex_lock_iothread();
while (qemu_file_get_error(f) == 0) {
if (qemu_savevm_state_iterate(f, false) > 0) {
break;
}
}
ret = qemu_file_get_error(f);
if (ret == 0) {
qemu_savevm_state_complete_precopy(f, false, false);
ret = qemu_file_get_error(f);
}
qemu_savevm_state_cleanup();
if (ret != 0) {
error_setg_errno(errp, -ret, "Error while writing VM state");
}
if (ret != 0) {
status = MIGRATION_STATUS_FAILED;
} else {
status = MIGRATION_STATUS_COMPLETED;
}
migrate_set_state(&ms->state, MIGRATION_STATUS_SETUP, status);
/* f is outer parameter, it should not stay in global migration state after
* this function finished */
ms->to_dst_file = NULL;
return ret;
}
void qemu_savevm_live_state(QEMUFile *f)
{
/* save QEMU_VM_SECTION_END section */
qemu_savevm_state_complete_precopy(f, true, false);
qemu_put_byte(f, QEMU_VM_EOF);
}
int qemu_save_device_state(QEMUFile *f)
{
SaveStateEntry *se;
if (!migration_in_colo_state()) {
qemu_put_be32(f, QEMU_VM_FILE_MAGIC);
qemu_put_be32(f, QEMU_VM_FILE_VERSION);
}
cpu_synchronize_all_states();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
int ret;
if (se->is_ram) {
continue;
}
if ((!se->ops || !se->ops->save_state) && !se->vmsd) {
continue;
}
if (se->vmsd && !vmstate_save_needed(se->vmsd, se->opaque)) {
continue;
}
save_section_header(f, se, QEMU_VM_SECTION_FULL);
ret = vmstate_save(f, se, NULL);
if (ret) {
return ret;
}
save_section_footer(f, se);
}
qemu_put_byte(f, QEMU_VM_EOF);
return qemu_file_get_error(f);
}
static SaveStateEntry *find_se(const char *idstr, uint32_t instance_id)
{
SaveStateEntry *se;
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!strcmp(se->idstr, idstr) &&
(instance_id == se->instance_id ||
instance_id == se->alias_id))
return se;
/* Migrating from an older version? */
if (strstr(se->idstr, idstr) && se->compat) {
if (!strcmp(se->compat->idstr, idstr) &&
(instance_id == se->compat->instance_id ||
instance_id == se->alias_id))
return se;
}
}
return NULL;
}
enum LoadVMExitCodes {
/* Allow a command to quit all layers of nested loadvm loops */
LOADVM_QUIT = 1,
};
/* ------ incoming postcopy messages ------ */
/* 'advise' arrives before any transfers just to tell us that a postcopy
* *might* happen - it might be skipped if precopy transferred everything
* quickly.
*/
migration: incoming postcopy advise sanity checks If postcopy-ram was set on the source but not on the destination, migration doesn't occur, the destination prints an error and boots the guest: qemu-system-ppc64: Expected vmdescription section, but got 0 We end up with two running instances. This behaviour was introduced in 2.11 by commit 58110f0acb1a "migration: split common postcopy out of ram postcopy" to prepare ground for the upcoming dirty bitmap postcopy support. It adds a new case where the source may send an empty postcopy advise because dirty bitmap doesn't need to check page sizes like RAM postcopy does. If the source has enabled postcopy-ram, then it sends an advise with the page size values. If the destination hasn't enabled postcopy-ram, then loadvm_postcopy_handle_advise() leaves the page size values on the stream and returns. This confuses qemu_loadvm_state() later on and causes the destination to start execution. As discussed several times, postcopy-ram should be enabled both sides to be functional. This patch changes the destination to perform some extra checks on the advise length to ensure this is the case. Otherwise an error is returned and migration is aborted. Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com> Signed-off-by: Greg Kurz <groug@kaod.org> Reviewed-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-Id: <151791621042.19120.3103118434734245776.stgit@bahia> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2018-02-06 12:23:30 +01:00
static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis,
uint16_t len)
{
PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE);
uint64_t remote_pagesize_summary, local_pagesize_summary, remote_tps;
size_t page_size = qemu_target_page_size();
Error *local_err = NULL;
trace_loadvm_postcopy_handle_advise();
if (ps != POSTCOPY_INCOMING_NONE) {
error_report("CMD_POSTCOPY_ADVISE in wrong postcopy state (%d)", ps);
return -1;
}
migration: incoming postcopy advise sanity checks If postcopy-ram was set on the source but not on the destination, migration doesn't occur, the destination prints an error and boots the guest: qemu-system-ppc64: Expected vmdescription section, but got 0 We end up with two running instances. This behaviour was introduced in 2.11 by commit 58110f0acb1a "migration: split common postcopy out of ram postcopy" to prepare ground for the upcoming dirty bitmap postcopy support. It adds a new case where the source may send an empty postcopy advise because dirty bitmap doesn't need to check page sizes like RAM postcopy does. If the source has enabled postcopy-ram, then it sends an advise with the page size values. If the destination hasn't enabled postcopy-ram, then loadvm_postcopy_handle_advise() leaves the page size values on the stream and returns. This confuses qemu_loadvm_state() later on and causes the destination to start execution. As discussed several times, postcopy-ram should be enabled both sides to be functional. This patch changes the destination to perform some extra checks on the advise length to ensure this is the case. Otherwise an error is returned and migration is aborted. Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com> Signed-off-by: Greg Kurz <groug@kaod.org> Reviewed-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-Id: <151791621042.19120.3103118434734245776.stgit@bahia> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2018-02-06 12:23:30 +01:00
switch (len) {
case 0:
if (migrate_postcopy_ram()) {
error_report("RAM postcopy is enabled but have 0 byte advise");
return -EINVAL;
}
return 0;
migration: incoming postcopy advise sanity checks If postcopy-ram was set on the source but not on the destination, migration doesn't occur, the destination prints an error and boots the guest: qemu-system-ppc64: Expected vmdescription section, but got 0 We end up with two running instances. This behaviour was introduced in 2.11 by commit 58110f0acb1a "migration: split common postcopy out of ram postcopy" to prepare ground for the upcoming dirty bitmap postcopy support. It adds a new case where the source may send an empty postcopy advise because dirty bitmap doesn't need to check page sizes like RAM postcopy does. If the source has enabled postcopy-ram, then it sends an advise with the page size values. If the destination hasn't enabled postcopy-ram, then loadvm_postcopy_handle_advise() leaves the page size values on the stream and returns. This confuses qemu_loadvm_state() later on and causes the destination to start execution. As discussed several times, postcopy-ram should be enabled both sides to be functional. This patch changes the destination to perform some extra checks on the advise length to ensure this is the case. Otherwise an error is returned and migration is aborted. Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com> Signed-off-by: Greg Kurz <groug@kaod.org> Reviewed-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-Id: <151791621042.19120.3103118434734245776.stgit@bahia> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2018-02-06 12:23:30 +01:00
case 8 + 8:
if (!migrate_postcopy_ram()) {
error_report("RAM postcopy is disabled but have 16 byte advise");
return -EINVAL;
}
break;
default:
error_report("CMD_POSTCOPY_ADVISE invalid length (%d)", len);
return -EINVAL;
}
if (!postcopy_ram_supported_by_host(mis)) {
postcopy_state_set(POSTCOPY_INCOMING_NONE);
return -1;
}
remote_pagesize_summary = qemu_get_be64(mis->from_src_file);
local_pagesize_summary = ram_pagesize_summary();
if (remote_pagesize_summary != local_pagesize_summary) {
/*
* This detects two potential causes of mismatch:
* a) A mismatch in host page sizes
* Some combinations of mismatch are probably possible but it gets
* a bit more complicated. In particular we need to place whole
* host pages on the dest at once, and we need to ensure that we
* handle dirtying to make sure we never end up sending part of
* a hostpage on it's own.
* b) The use of different huge page sizes on source/destination
* a more fine grain test is performed during RAM block migration
* but this test here causes a nice early clear failure, and
* also fails when passed to an older qemu that doesn't
* do huge pages.
*/
error_report("Postcopy needs matching RAM page sizes (s=%" PRIx64
" d=%" PRIx64 ")",
remote_pagesize_summary, local_pagesize_summary);
return -1;
}
remote_tps = qemu_get_be64(mis->from_src_file);
if (remote_tps != page_size) {
/*
* Again, some differences could be dealt with, but for now keep it
* simple.
*/
error_report("Postcopy needs matching target page sizes (s=%d d=%zd)",
(int)remote_tps, page_size);
return -1;
}
if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_ADVISE, &local_err)) {
error_report_err(local_err);
return -1;
}
if (ram_postcopy_incoming_init(mis)) {
return -1;
}
return 0;
}
/* After postcopy we will be told to throw some pages away since they're
* dirty and will have to be demand fetched. Must happen before CPU is
* started.
* There can be 0..many of these messages, each encoding multiple pages.
*/
static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis,
uint16_t len)
{
int tmp;
char ramid[256];
PostcopyState ps = postcopy_state_get();
trace_loadvm_postcopy_ram_handle_discard();
switch (ps) {
case POSTCOPY_INCOMING_ADVISE:
/* 1st discard */
tmp = postcopy_ram_prepare_discard(mis);
if (tmp) {
return tmp;
}
break;
case POSTCOPY_INCOMING_DISCARD:
/* Expected state */
break;
default:
error_report("CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)",
ps);
return -1;
}
/* We're expecting a
* Version (0)
* a RAM ID string (length byte, name, 0 term)
* then at least 1 16 byte chunk
*/
if (len < (1 + 1 + 1 + 1 + 2 * 8)) {
error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len);
return -1;
}
tmp = qemu_get_byte(mis->from_src_file);
if (tmp != postcopy_ram_discard_version) {
error_report("CMD_POSTCOPY_RAM_DISCARD invalid version (%d)", tmp);
return -1;
}
if (!qemu_get_counted_string(mis->from_src_file, ramid)) {
error_report("CMD_POSTCOPY_RAM_DISCARD Failed to read RAMBlock ID");
return -1;
}
tmp = qemu_get_byte(mis->from_src_file);
if (tmp != 0) {
error_report("CMD_POSTCOPY_RAM_DISCARD missing nil (%d)", tmp);
return -1;
}
len -= 3 + strlen(ramid);
if (len % 16) {
error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len);
return -1;
}
trace_loadvm_postcopy_ram_handle_discard_header(ramid, len);
while (len) {
uint64_t start_addr, block_length;
start_addr = qemu_get_be64(mis->from_src_file);
block_length = qemu_get_be64(mis->from_src_file);
len -= 16;
int ret = ram_discard_range(ramid, start_addr, block_length);
if (ret) {
return ret;
}
}
trace_loadvm_postcopy_ram_handle_discard_end();
return 0;
}
/*
* Triggered by a postcopy_listen command; this thread takes over reading
* the input stream, leaving the main thread free to carry on loading the rest
* of the device state (from RAM).
* (TODO:This could do with being in a postcopy file - but there again it's
* just another input loop, not that postcopy specific)
*/
static void *postcopy_ram_listen_thread(void *opaque)
{
MigrationIncomingState *mis = migration_incoming_get_current();
QEMUFile *f = mis->from_src_file;
int load_res;
MigrationState *migr = migrate_get_current();
object_ref(OBJECT(migr));
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_POSTCOPY_ACTIVE);
qemu_sem_post(&mis->thread_sync_sem);
trace_postcopy_ram_listen_thread_start();
rcu_register_thread();
/*
* Because we're a thread and not a coroutine we can't yield
* in qemu_file, and thus we must be blocking now.
*/
qemu_file_set_blocking(f, true);
load_res = qemu_loadvm_state_main(f, mis);
/*
* This is tricky, but, mis->from_src_file can change after it
* returns, when postcopy recovery happened. In the future, we may
* want a wrapper for the QEMUFile handle.
*/
f = mis->from_src_file;
/* And non-blocking again so we don't block in any cleanup */
qemu_file_set_blocking(f, false);
trace_postcopy_ram_listen_thread_exit();
if (load_res < 0) {
qemu_file_set_error(f, load_res);
dirty_bitmap_mig_cancel_incoming();
if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING &&
!migrate_postcopy_ram() && migrate_dirty_bitmaps())
{
error_report("%s: loadvm failed during postcopy: %d. All states "
"are migrated except dirty bitmaps. Some dirty "
"bitmaps may be lost, and present migrated dirty "
"bitmaps are correctly migrated and valid.",
__func__, load_res);
load_res = 0; /* prevent further exit() */
} else {
error_report("%s: loadvm failed: %d", __func__, load_res);
migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
MIGRATION_STATUS_FAILED);
}
}
if (load_res >= 0) {
/*
* This looks good, but it's possible that the device loading in the
* main thread hasn't finished yet, and so we might not be in 'RUN'
* state yet; wait for the end of the main thread.
*/
qemu_event_wait(&mis->main_thread_load_event);
}
postcopy_ram_incoming_cleanup(mis);
if (load_res < 0) {
/*
* If something went wrong then we have a bad state so exit;
* depending how far we got it might be possible at this point
* to leave the guest running and fire MCEs for pages that never
* arrived as a desperate recovery step.
*/
rcu_unregister_thread();
exit(EXIT_FAILURE);
}
migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
MIGRATION_STATUS_COMPLETED);
/*
* If everything has worked fine, then the main thread has waited
* for us to start, and we're the last use of the mis.
* (If something broke then qemu will have to exit anyway since it's
* got a bad migration state).
*/
migration_incoming_state_destroy();
qemu_loadvm_state_cleanup();
rcu_unregister_thread();
mis->have_listen_thread = false;
postcopy_state_set(POSTCOPY_INCOMING_END);
object_unref(OBJECT(migr));
return NULL;
}
/* After this message we must be able to immediately receive postcopy data */
static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis)
{
PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_LISTENING);
Error *local_err = NULL;
trace_loadvm_postcopy_handle_listen("enter");
if (ps != POSTCOPY_INCOMING_ADVISE && ps != POSTCOPY_INCOMING_DISCARD) {
error_report("CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps);
return -1;
}
if (ps == POSTCOPY_INCOMING_ADVISE) {
/*
* A rare case, we entered listen without having to do any discards,
* so do the setup that's normally done at the time of the 1st discard.
*/
if (migrate_postcopy_ram()) {
postcopy_ram_prepare_discard(mis);
}
}
trace_loadvm_postcopy_handle_listen("after discard");
/*
* Sensitise RAM - can now generate requests for blocks that don't exist
* However, at this point the CPU shouldn't be running, and the IO
* shouldn't be doing anything yet so don't actually expect requests
*/
if (migrate_postcopy_ram()) {
if (postcopy_ram_incoming_setup(mis)) {
postcopy_ram_incoming_cleanup(mis);
return -1;
}
}
trace_loadvm_postcopy_handle_listen("after uffd");
if (postcopy_notify(POSTCOPY_NOTIFY_INBOUND_LISTEN, &local_err)) {
error_report_err(local_err);
return -1;
}
mis->have_listen_thread = true;
postcopy_thread_create(mis, &mis->listen_thread, "postcopy/listen",
postcopy_ram_listen_thread, QEMU_THREAD_DETACHED);
trace_loadvm_postcopy_handle_listen("return");
return 0;
}
static void loadvm_postcopy_handle_run_bh(void *opaque)
{
Error *local_err = NULL;
MigrationIncomingState *mis = opaque;
trace_loadvm_postcopy_handle_run_bh("enter");
/* TODO we should move all of this lot into postcopy_ram.c or a shared code
* in migration.c
*/
cpu_synchronize_all_post_init();
trace_loadvm_postcopy_handle_run_bh("after cpu sync");
qemu_announce_self(&mis->announce_timer, migrate_announce_params());
trace_loadvm_postcopy_handle_run_bh("after announce");
/* Make sure all file formats throw away their mutable metadata.
* If we get an error here, just don't restart the VM yet. */
bdrv_activate_all(&local_err);
if (local_err) {
error_report_err(local_err);
local_err = NULL;
autostart = false;
}
trace_loadvm_postcopy_handle_run_bh("after invalidate cache");
dirty_bitmap_mig_before_vm_start();
if (autostart) {
/* Hold onto your hats, starting the CPU */
vm_start();
} else {
/* leave it paused and let management decide when to start the CPU */
runstate_set(RUN_STATE_PAUSED);
}
qemu_bh_delete(mis->bh);
trace_loadvm_postcopy_handle_run_bh("return");
}
/* After all discards we can start running and asking for pages */
static int loadvm_postcopy_handle_run(MigrationIncomingState *mis)
{
PostcopyState ps = postcopy_state_get();
trace_loadvm_postcopy_handle_run();
if (ps != POSTCOPY_INCOMING_LISTENING) {
error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps);
return -1;
}
postcopy_state_set(POSTCOPY_INCOMING_RUNNING);
mis->bh = qemu_bh_new(loadvm_postcopy_handle_run_bh, mis);
qemu_bh_schedule(mis->bh);
/* We need to finish reading the stream from the package
* and also stop reading anything more from the stream that loaded the
* package (since it's now being read by the listener thread).
* LOADVM_QUIT will quit all the layers of nested loadvm loops.
*/
return LOADVM_QUIT;
}
/* We must be with page_request_mutex held */
static gboolean postcopy_sync_page_req(gpointer key, gpointer value,
gpointer data)
{
MigrationIncomingState *mis = data;
void *host_addr = (void *) key;
ram_addr_t rb_offset;
RAMBlock *rb;
int ret;
rb = qemu_ram_block_from_host(host_addr, true, &rb_offset);
if (!rb) {
/*
* This should _never_ happen. However be nice for a migrating VM to
* not crash/assert. Post an error (note: intended to not use *_once
* because we do want to see all the illegal addresses; and this can
* never be triggered by the guest so we're safe) and move on next.
*/
error_report("%s: illegal host addr %p", __func__, host_addr);
/* Try the next entry */
return FALSE;
}
ret = migrate_send_rp_message_req_pages(mis, rb, rb_offset);
if (ret) {
/* Please refer to above comment. */
error_report("%s: send rp message failed for addr %p",
__func__, host_addr);
return FALSE;
}
trace_postcopy_page_req_sync(host_addr);
return FALSE;
}
static void migrate_send_rp_req_pages_pending(MigrationIncomingState *mis)
{
WITH_QEMU_LOCK_GUARD(&mis->page_request_mutex) {
g_tree_foreach(mis->page_requested, postcopy_sync_page_req, mis);
}
}
static int loadvm_postcopy_handle_resume(MigrationIncomingState *mis)
{
if (mis->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
error_report("%s: illegal resume received", __func__);
/* Don't fail the load, only for this. */
return 0;
}
/*
* Reset the last_rb before we resend any page req to source again, since
* the source should have it reset already.
*/
mis->last_rb = NULL;
/*
* This means source VM is ready to resume the postcopy migration.
*/
migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_RECOVER,
MIGRATION_STATUS_POSTCOPY_ACTIVE);
trace_loadvm_postcopy_handle_resume();
/* Tell source that "we are ready" */
migrate_send_rp_resume_ack(mis, MIGRATION_RESUME_ACK_VALUE);
/*
* After a postcopy recovery, the source should have lost the postcopy
* queue, or potentially the requested pages could have been lost during
* the network down phase. Let's re-sync with the source VM by re-sending
* all the pending pages that we eagerly need, so these threads won't get
* blocked too long due to the recovery.
*
* Without this procedure, the faulted destination VM threads (waiting for
* page requests right before the postcopy is interrupted) can keep hanging
* until the pages are sent by the source during the background copying of
* pages, or another thread faulted on the same address accidentally.
*/
migrate_send_rp_req_pages_pending(mis);
/*
* It's time to switch state and release the fault thread to continue
* service page faults. Note that this should be explicitly after the
* above call to migrate_send_rp_req_pages_pending(). In short:
* migrate_send_rp_message_req_pages() is not thread safe, yet.
*/
qemu_sem_post(&mis->postcopy_pause_sem_fault);
return 0;
}
/**
* Immediately following this command is a blob of data containing an embedded
* chunk of migration stream; read it and load it.
*
* @mis: Incoming state
* @length: Length of packaged data to read
*
* Returns: Negative values on error
*
*/
static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis)
{
int ret;
size_t length;
QIOChannelBuffer *bioc;
length = qemu_get_be32(mis->from_src_file);
trace_loadvm_handle_cmd_packaged(length);
if (length > MAX_VM_CMD_PACKAGED_SIZE) {
error_report("Unreasonably large packaged state: %zu", length);
return -1;
}
bioc = qio_channel_buffer_new(length);
qio_channel_set_name(QIO_CHANNEL(bioc), "migration-loadvm-buffer");
ret = qemu_get_buffer(mis->from_src_file,
bioc->data,
length);
if (ret != length) {
object_unref(OBJECT(bioc));
error_report("CMD_PACKAGED: Buffer receive fail ret=%d length=%zu",
ret, length);
return (ret < 0) ? ret : -EAGAIN;
}
bioc->usage += length;
trace_loadvm_handle_cmd_packaged_received(ret);
QEMUFile *packf = qemu_fopen_channel_input(QIO_CHANNEL(bioc));
ret = qemu_loadvm_state_main(packf, mis);
trace_loadvm_handle_cmd_packaged_main(ret);
qemu_fclose(packf);
object_unref(OBJECT(bioc));
return ret;
}
/*
* Handle request that source requests for recved_bitmap on
* destination. Payload format:
*
* len (1 byte) + ramblock_name (<255 bytes)
*/
static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis,
uint16_t len)
{
QEMUFile *file = mis->from_src_file;
RAMBlock *rb;
char block_name[256];
size_t cnt;
cnt = qemu_get_counted_string(file, block_name);
if (!cnt) {
error_report("%s: failed to read block name", __func__);
return -EINVAL;
}
/* Validate before using the data */
if (qemu_file_get_error(file)) {
return qemu_file_get_error(file);
}
if (len != cnt + 1) {
error_report("%s: invalid payload length (%d)", __func__, len);
return -EINVAL;
}
rb = qemu_ram_block_by_name(block_name);
if (!rb) {
error_report("%s: block '%s' not found", __func__, block_name);
return -EINVAL;
}
migrate_send_rp_recv_bitmap(mis, block_name);
trace_loadvm_handle_recv_bitmap(block_name);
return 0;
}
static int loadvm_process_enable_colo(MigrationIncomingState *mis)
{
int ret = migration_incoming_enable_colo();
if (!ret) {
ret = colo_init_ram_cache();
if (ret) {
migration_incoming_disable_colo();
}
}
return ret;
}
/*
* Process an incoming 'QEMU_VM_COMMAND'
* 0 just a normal return
* LOADVM_QUIT All good, but exit the loop
* <0 Error
*/
static int loadvm_process_command(QEMUFile *f)
{
MigrationIncomingState *mis = migration_incoming_get_current();
uint16_t cmd;
uint16_t len;
uint32_t tmp32;
cmd = qemu_get_be16(f);
len = qemu_get_be16(f);
/* Check validity before continue processing of cmds */
if (qemu_file_get_error(f)) {
return qemu_file_get_error(f);
}
if (cmd >= MIG_CMD_MAX || cmd == MIG_CMD_INVALID) {
error_report("MIG_CMD 0x%x unknown (len 0x%x)", cmd, len);
return -EINVAL;
}
trace_loadvm_process_command(mig_cmd_args[cmd].name, len);
if (mig_cmd_args[cmd].len != -1 && mig_cmd_args[cmd].len != len) {
error_report("%s received with bad length - expecting %zu, got %d",
mig_cmd_args[cmd].name,
(size_t)mig_cmd_args[cmd].len, len);
return -ERANGE;
}
switch (cmd) {
case MIG_CMD_OPEN_RETURN_PATH:
if (mis->to_src_file) {
error_report("CMD_OPEN_RETURN_PATH called when RP already open");
/* Not really a problem, so don't give up */
return 0;
}
mis->to_src_file = qemu_file_get_return_path(f);
if (!mis->to_src_file) {
error_report("CMD_OPEN_RETURN_PATH failed");
return -1;
}
break;
case MIG_CMD_PING:
tmp32 = qemu_get_be32(f);
trace_loadvm_process_command_ping(tmp32);
if (!mis->to_src_file) {
error_report("CMD_PING (0x%x) received with no return path",
tmp32);
return -1;
}
migrate_send_rp_pong(mis, tmp32);
break;
case MIG_CMD_PACKAGED:
return loadvm_handle_cmd_packaged(mis);
case MIG_CMD_POSTCOPY_ADVISE:
migration: incoming postcopy advise sanity checks If postcopy-ram was set on the source but not on the destination, migration doesn't occur, the destination prints an error and boots the guest: qemu-system-ppc64: Expected vmdescription section, but got 0 We end up with two running instances. This behaviour was introduced in 2.11 by commit 58110f0acb1a "migration: split common postcopy out of ram postcopy" to prepare ground for the upcoming dirty bitmap postcopy support. It adds a new case where the source may send an empty postcopy advise because dirty bitmap doesn't need to check page sizes like RAM postcopy does. If the source has enabled postcopy-ram, then it sends an advise with the page size values. If the destination hasn't enabled postcopy-ram, then loadvm_postcopy_handle_advise() leaves the page size values on the stream and returns. This confuses qemu_loadvm_state() later on and causes the destination to start execution. As discussed several times, postcopy-ram should be enabled both sides to be functional. This patch changes the destination to perform some extra checks on the advise length to ensure this is the case. Otherwise an error is returned and migration is aborted. Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com> Signed-off-by: Greg Kurz <groug@kaod.org> Reviewed-by: Daniel Henrique Barboza <danielhb@linux.vnet.ibm.com> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-Id: <151791621042.19120.3103118434734245776.stgit@bahia> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
2018-02-06 12:23:30 +01:00
return loadvm_postcopy_handle_advise(mis, len);
case MIG_CMD_POSTCOPY_LISTEN:
return loadvm_postcopy_handle_listen(mis);
case MIG_CMD_POSTCOPY_RUN:
return loadvm_postcopy_handle_run(mis);
case MIG_CMD_POSTCOPY_RAM_DISCARD:
return loadvm_postcopy_ram_handle_discard(mis, len);
case MIG_CMD_POSTCOPY_RESUME:
return loadvm_postcopy_handle_resume(mis);
case MIG_CMD_RECV_BITMAP:
return loadvm_handle_recv_bitmap(mis, len);
case MIG_CMD_ENABLE_COLO:
return loadvm_process_enable_colo(mis);
}
return 0;
}
/*
* Read a footer off the wire and check that it matches the expected section
*
* Returns: true if the footer was good
* false if there is a problem (and calls error_report to say why)
*/
static bool check_section_footer(QEMUFile *f, SaveStateEntry *se)
{
int ret;
uint8_t read_mark;
uint32_t read_section_id;
if (!migrate_get_current()->send_section_footer) {
/* No footer to check */
return true;
}
read_mark = qemu_get_byte(f);
ret = qemu_file_get_error(f);
if (ret) {
error_report("%s: Read section footer failed: %d",
__func__, ret);
return false;
}
if (read_mark != QEMU_VM_SECTION_FOOTER) {
error_report("Missing section footer for %s", se->idstr);
return false;
}
read_section_id = qemu_get_be32(f);
if (read_section_id != se->load_section_id) {
error_report("Mismatched section id in footer for %s -"
" read 0x%x expected 0x%x",
se->idstr, read_section_id, se->load_section_id);
return false;
}
/* All good */
return true;
}
static int
qemu_loadvm_section_start_full(QEMUFile *f, MigrationIncomingState *mis)
{
uint32_t instance_id, version_id, section_id;
SaveStateEntry *se;
char idstr[256];
int ret;
/* Read section start */
section_id = qemu_get_be32(f);
if (!qemu_get_counted_string(f, idstr)) {
error_report("Unable to read ID string for section %u",
section_id);
return -EINVAL;
}
instance_id = qemu_get_be32(f);
version_id = qemu_get_be32(f);
ret = qemu_file_get_error(f);
if (ret) {
error_report("%s: Failed to read instance/version ID: %d",
__func__, ret);
return ret;
}
trace_qemu_loadvm_state_section_startfull(section_id, idstr,
instance_id, version_id);
/* Find savevm section */
se = find_se(idstr, instance_id);
if (se == NULL) {
error_report("Unknown savevm section or instance '%s' %"PRIu32". "
"Make sure that your current VM setup matches your "
"saved VM setup, including any hotplugged devices",
idstr, instance_id);
return -EINVAL;
}
/* Validate version */
if (version_id > se->version_id) {
error_report("savevm: unsupported version %d for '%s' v%d",
version_id, idstr, se->version_id);
return -EINVAL;
}
se->load_version_id = version_id;
se->load_section_id = section_id;
/* Validate if it is a device's state */
if (xen_enabled() && se->is_ram) {
error_report("loadvm: %s RAM loading not allowed on Xen", idstr);
return -EINVAL;
}
ret = vmstate_load(f, se);
if (ret < 0) {
error_report("error while loading state for instance 0x%"PRIx32" of"
" device '%s'", instance_id, idstr);
return ret;
}
if (!check_section_footer(f, se)) {
return -EINVAL;
}
return 0;
}
static int
qemu_loadvm_section_part_end(QEMUFile *f, MigrationIncomingState *mis)
{
uint32_t section_id;
SaveStateEntry *se;
int ret;
section_id = qemu_get_be32(f);
ret = qemu_file_get_error(f);
if (ret) {
error_report("%s: Failed to read section ID: %d",
__func__, ret);
return ret;
}
trace_qemu_loadvm_state_section_partend(section_id);
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->load_section_id == section_id) {
break;
}
}
if (se == NULL) {
error_report("Unknown savevm section %d", section_id);
return -EINVAL;
}
ret = vmstate_load(f, se);
if (ret < 0) {
error_report("error while loading state section id %d(%s)",
section_id, se->idstr);
return ret;
}
if (!check_section_footer(f, se)) {
return -EINVAL;
}
return 0;
}
static int qemu_loadvm_state_header(QEMUFile *f)
{
unsigned int v;
int ret;
v = qemu_get_be32(f);
if (v != QEMU_VM_FILE_MAGIC) {
error_report("Not a migration stream");
return -EINVAL;
}
v = qemu_get_be32(f);
if (v == QEMU_VM_FILE_VERSION_COMPAT) {
error_report("SaveVM v2 format is obsolete and don't work anymore");
return -ENOTSUP;
}
if (v != QEMU_VM_FILE_VERSION) {
error_report("Unsupported migration stream version");
return -ENOTSUP;
}
if (migrate_get_current()->send_configuration) {
if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) {
error_report("Configuration section missing");
qemu_loadvm_state_cleanup();
return -EINVAL;
}
ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0);
if (ret) {
qemu_loadvm_state_cleanup();
return ret;
}
}
return 0;
}
static int qemu_loadvm_state_setup(QEMUFile *f)
{
SaveStateEntry *se;
int ret;
trace_loadvm_state_setup();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (!se->ops || !se->ops->load_setup) {
continue;
}
if (se->ops->is_active) {
if (!se->ops->is_active(se->opaque)) {
continue;
}
}
ret = se->ops->load_setup(f, se->opaque);
if (ret < 0) {
qemu_file_set_error(f, ret);
error_report("Load state of device %s failed", se->idstr);
return ret;
}
}
return 0;
}
void qemu_loadvm_state_cleanup(void)
{
SaveStateEntry *se;
trace_loadvm_state_cleanup();
QTAILQ_FOREACH(se, &savevm_state.handlers, entry) {
if (se->ops && se->ops->load_cleanup) {
se->ops->load_cleanup(se->opaque);
}
}
}
/* Return true if we should continue the migration, or false. */
static bool postcopy_pause_incoming(MigrationIncomingState *mis)
{
migration: Introduce postcopy channels on dest node Postcopy handles huge pages in a special way that currently we can only have one "channel" to transfer the page. It's because when we install pages using UFFDIO_COPY, we need to have the whole huge page ready, it also means we need to have a temp huge page when trying to receive the whole content of the page. Currently all maintainance around this tmp page is global: firstly we'll allocate a temp huge page, then we maintain its status mostly within ram_load_postcopy(). To enable multiple channels for postcopy, the first thing we need to do is to prepare N temp huge pages as caching, one for each channel. Meanwhile we need to maintain the tmp huge page status per-channel too. To give some example, some local variables maintained in ram_load_postcopy() are listed; they are responsible for maintaining temp huge page status: - all_zero: this keeps whether this huge page contains all zeros - target_pages: this counts how many target pages have been copied - host_page: this keeps the host ptr for the page to install Move all these fields to be together with the temp huge pages to form a new structure called PostcopyTmpPage. Then for each (future) postcopy channel, we need one structure to keep the state around. For vanilla postcopy, obviously there's only one channel. It contains both precopy and postcopy pages. This patch teaches the dest migration node to start realize the possible number of postcopy channels by introducing the "postcopy_channels" variable. Its value is calculated when setup postcopy on dest node (during POSTCOPY_LISTEN phase). Vanilla postcopy will have channels=1, but when postcopy-preempt capability is enabled (in the future), we will boost it to 2 because even during partial sending of a precopy huge page we still want to preempt it and start sending the postcopy requested page right away (so we start to keep two temp huge pages; more if we want to enable multifd). In this patch there's a TODO marked for that; so far the channels is always set to 1. We need to send one "host huge page" on one channel only and we cannot split them, because otherwise the data upon the same huge page can locate on more than one channel so we need more complicated logic to manage. One temp host huge page for each channel will be enough for us for now. Postcopy will still always use the index=0 huge page even after this patch. However it prepares for the latter patches where it can start to use multiple channels (which needs src intervention, because only src knows which channel we should use). Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Peter Xu <peterx@redhat.com> Message-Id: <20220301083925.33483-5-peterx@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com> dgilbert: Fixed up long line
2022-03-01 09:39:04 +01:00
int i;
/*
* If network is interrupted, any temp page we received will be useless
* because we didn't mark them as "received" in receivedmap. After a
* proper recovery later (which will sync src dirty bitmap with receivedmap
* on dest) these cached small pages will be resent again.
*/
for (i = 0; i < mis->postcopy_channels; i++) {
postcopy_temp_page_reset(&mis->postcopy_tmp_pages[i]);
}
trace_postcopy_pause_incoming();
assert(migrate_postcopy_ram());
/*
* Unregister yank with either from/to src would work, since ioc behind it
* is the same
*/
migration_ioc_unregister_yank_from_file(mis->from_src_file);
assert(mis->from_src_file);
qemu_file_shutdown(mis->from_src_file);
qemu_fclose(mis->from_src_file);
mis->from_src_file = NULL;
assert(mis->to_src_file);
qemu_file_shutdown(mis->to_src_file);
qemu_mutex_lock(&mis->rp_mutex);
qemu_fclose(mis->to_src_file);
mis->to_src_file = NULL;
qemu_mutex_unlock(&mis->rp_mutex);
migrate_set_state(&mis->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
MIGRATION_STATUS_POSTCOPY_PAUSED);
/* Notify the fault thread for the invalidated file handle */
postcopy_fault_thread_notify(mis);
error_report("Detected IO failure for postcopy. "
"Migration paused.");
while (mis->state == MIGRATION_STATUS_POSTCOPY_PAUSED) {
qemu_sem_wait(&mis->postcopy_pause_sem_dst);
}
trace_postcopy_pause_incoming_continued();
return true;
}
int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis)
{
uint8_t section_type;
int ret = 0;
retry:
while (true) {
section_type = qemu_get_byte(f);
if (qemu_file_get_error(f)) {
ret = qemu_file_get_error(f);
break;
}
trace_qemu_loadvm_state_section(section_type);
switch (section_type) {
case QEMU_VM_SECTION_START:
case QEMU_VM_SECTION_FULL:
ret = qemu_loadvm_section_start_full(f, mis);
if (ret < 0) {
goto out;
}
break;
case QEMU_VM_SECTION_PART:
case QEMU_VM_SECTION_END:
ret = qemu_loadvm_section_part_end(f, mis);
if (ret < 0) {
goto out;
}
break;
case QEMU_VM_COMMAND:
ret = loadvm_process_command(f);
trace_qemu_loadvm_state_section_command(ret);
if ((ret < 0) || (ret == LOADVM_QUIT)) {
goto out;
}
break;
case QEMU_VM_EOF:
/* This is the end of migration */
goto out;
default:
error_report("Unknown savevm section type %d", section_type);
ret = -EINVAL;
goto out;
}
}
out:
if (ret < 0) {
qemu_file_set_error(f, ret);
/* Cancel bitmaps incoming regardless of recovery */
dirty_bitmap_mig_cancel_incoming();
/*
* If we are during an active postcopy, then we pause instead
* of bail out to at least keep the VM's dirty data. Note
* that POSTCOPY_INCOMING_LISTENING stage is still not enough,
* during which we're still receiving device states and we
* still haven't yet started the VM on destination.
*
* Only RAM postcopy supports recovery. Still, if RAM postcopy is
* enabled, canceled bitmaps postcopy will not affect RAM postcopy
* recovering.
*/
if (postcopy_state_get() == POSTCOPY_INCOMING_RUNNING &&
migrate_postcopy_ram() && postcopy_pause_incoming(mis)) {
/* Reset f to point to the newly created channel */
f = mis->from_src_file;
goto retry;
}
}
return ret;
}
int qemu_loadvm_state(QEMUFile *f)
{
MigrationIncomingState *mis = migration_incoming_get_current();
Error *local_err = NULL;
int ret;
if (qemu_savevm_state_blocked(&local_err)) {
error_report_err(local_err);
return -EINVAL;
}
ret = qemu_loadvm_state_header(f);
if (ret) {
return ret;
}
if (qemu_loadvm_state_setup(f) != 0) {
return -EINVAL;
}
2017-05-26 06:46:28 +02:00
cpu_synchronize_all_pre_loadvm();
ret = qemu_loadvm_state_main(f, mis);
qemu_event_set(&mis->main_thread_load_event);
trace_qemu_loadvm_state_post_main(ret);
if (mis->have_listen_thread) {
/* Listen thread still going, can't clean up yet */
return ret;
}
if (ret == 0) {
ret = qemu_file_get_error(f);
}
/*
* Try to read in the VMDESC section as well, so that dumping tools that
* intercept our migration stream have the chance to see it.
*/
/* We've got to be careful; if we don't read the data and just shut the fd
* then the sender can error if we close while it's still sending.
* We also mustn't read data that isn't there; some transports (RDMA)
* will stall waiting for that data when the source has already closed.
*/
if (ret == 0 && should_send_vmdesc()) {
uint8_t *buf;
uint32_t size;
uint8_t section_type = qemu_get_byte(f);
if (section_type != QEMU_VM_VMDESCRIPTION) {
error_report("Expected vmdescription section, but got %d",
section_type);
/*
* It doesn't seem worth failing at this point since
* we apparently have an otherwise valid VM state
*/
} else {
buf = g_malloc(0x1000);
size = qemu_get_be32(f);
while (size > 0) {
uint32_t read_chunk = MIN(size, 0x1000);
qemu_get_buffer(f, buf, read_chunk);
size -= read_chunk;
}
g_free(buf);
}
}
qemu_loadvm_state_cleanup();
KVM: Rework VCPU state writeback API This grand cleanup drops all reset and vmsave/load related synchronization points in favor of four(!) generic hooks: - cpu_synchronize_all_states in qemu_savevm_state_complete (initial sync from kernel before vmsave) - cpu_synchronize_all_post_init in qemu_loadvm_state (writeback after vmload) - cpu_synchronize_all_post_init in main after machine init - cpu_synchronize_all_post_reset in qemu_system_reset (writeback after system reset) These writeback points + the existing one of VCPU exec after cpu_synchronize_state map on three levels of writeback: - KVM_PUT_RUNTIME_STATE (during runtime, other VCPUs continue to run) - KVM_PUT_RESET_STATE (on synchronous system reset, all VCPUs stopped) - KVM_PUT_FULL_STATE (on init or vmload, all VCPUs stopped as well) This level is passed to the arch-specific VCPU state writing function that will decide which concrete substates need to be written. That way, no writer of load, save or reset functions that interact with in-kernel KVM states will ever have to worry about synchronization again. That also means that a lot of reasons for races, segfaults and deadlocks are eliminated. cpu_synchronize_state remains untouched, just as Anthony suggested. We continue to need it before reading or writing of VCPU states that are also tracked by in-kernel KVM subsystems. Consequently, this patch removes many cpu_synchronize_state calls that are now redundant, just like remaining explicit register syncs. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
2010-03-01 19:10:30 +01:00
cpu_synchronize_all_post_init();
return ret;
}
int qemu_load_device_state(QEMUFile *f)
{
MigrationIncomingState *mis = migration_incoming_get_current();
int ret;
/* Load QEMU_VM_SECTION_FULL section */
ret = qemu_loadvm_state_main(f, mis);
if (ret < 0) {
error_report("Failed to load device state: %d", ret);
return ret;
}
cpu_synchronize_all_post_init();
return 0;
}
bool save_snapshot(const char *name, bool overwrite, const char *vmstate,
bool has_devices, strList *devices, Error **errp)
{
BlockDriverState *bs;
QEMUSnapshotInfo sn1, *sn = &sn1;
int ret = -1, ret2;
QEMUFile *f;
int saved_vm_running;
uint64_t vm_state_size;
g_autoptr(GDateTime) now = g_date_time_new_now_local();
AioContext *aio_context;
GLOBAL_STATE_CODE();
if (migration_is_blocked(errp)) {
return false;
}
if (!replay_can_snapshot()) {
error_setg(errp, "Record/replay does not allow making snapshot "
"right now. Try once more later.");
return false;
}
if (!bdrv_all_can_snapshot(has_devices, devices, errp)) {
return false;
savevm: Really verify if a drive supports snapshots Both bdrv_can_snapshot() and bdrv_has_snapshot() does not work as advertized. First issue: Their names implies different porpouses, but they do the same thing and have exactly the same code. Maybe copied and pasted and forgotten? bdrv_has_snapshot() is called in various places for actually checking if there is snapshots or not. Second issue: the way bdrv_can_snapshot() verifies if a block driver supports or not snapshots does not catch all cases. E.g.: a raw image. So when do_savevm() is called, first thing it does is to set a global BlockDriverState to save the VM memory state calling get_bs_snapshots(). static BlockDriverState *get_bs_snapshots(void) { BlockDriverState *bs; DriveInfo *dinfo; if (bs_snapshots) return bs_snapshots; QTAILQ_FOREACH(dinfo, &drives, next) { bs = dinfo->bdrv; if (bdrv_can_snapshot(bs)) goto ok; } return NULL; ok: bs_snapshots = bs; return bs; } bdrv_can_snapshot() may return a BlockDriverState that does not support snapshots and do_savevm() goes on. Later on in do_savevm(), we find: QTAILQ_FOREACH(dinfo, &drives, next) { bs1 = dinfo->bdrv; if (bdrv_has_snapshot(bs1)) { /* Write VM state size only to the image that contains the state */ sn->vm_state_size = (bs == bs1 ? vm_state_size : 0); ret = bdrv_snapshot_create(bs1, sn); if (ret < 0) { monitor_printf(mon, "Error while creating snapshot on '%s'\n", bdrv_get_device_name(bs1)); } } } bdrv_has_snapshot(bs1) is not checking if the device does support or has snapshots as explained above. Only in bdrv_snapshot_create() the device is actually checked for snapshot support. So, in cases where the first device supports snapshots, and the second does not, the snapshot on the first will happen anyways. I believe this is not a good behavior. It should be an all or nothing process. This patch addresses these issues by making bdrv_can_snapshot() actually do what it must do and enforces better tests to avoid errors in the middle of do_savevm(). bdrv_has_snapshot() is removed and replaced by bdrv_can_snapshot() where appropriate. bdrv_can_snapshot() was moved from savevm.c to block.c. It makes more sense to me. The loadvm_state() function was updated too to enforce that when loading a VM at least all writable devices must support snapshots too. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-06-08 15:40:55 +02:00
}
/* Delete old snapshots of the same name */
if (name) {
if (overwrite) {
if (bdrv_all_delete_snapshot(name, has_devices,
devices, errp) < 0) {
return false;
}
} else {
ret2 = bdrv_all_has_snapshot(name, has_devices, devices, errp);
if (ret2 < 0) {
return false;
}
if (ret2 == 1) {
error_setg(errp,
"Snapshot '%s' already exists in one or more devices",
name);
return false;
}
}
}
bs = bdrv_all_find_vmstate_bs(vmstate, has_devices, devices, errp);
if (bs == NULL) {
return false;
}
aio_context = bdrv_get_aio_context(bs);
saved_vm_running = runstate_is_running();
ret = global_state_store();
if (ret) {
error_setg(errp, "Error saving global state");
return false;
}
vm_stop(RUN_STATE_SAVE_VM);
bdrv_drain_all_begin();
aio_context_acquire(aio_context);
memset(sn, 0, sizeof(*sn));
/* fill auxiliary fields */
sn->date_sec = g_date_time_to_unix(now);
sn->date_nsec = g_date_time_get_microsecond(now) * 1000;
sn->vm_clock_nsec = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
if (replay_mode != REPLAY_MODE_NONE) {
sn->icount = replay_get_current_icount();
} else {
sn->icount = -1ULL;
}
if (name) {
pstrcpy(sn->name, sizeof(sn->name), name);
} else {
g_autofree char *autoname = g_date_time_format(now, "vm-%Y%m%d%H%M%S");
pstrcpy(sn->name, sizeof(sn->name), autoname);
}
/* save the VM state */
f = qemu_fopen_bdrv(bs, 1);
if (!f) {
error_setg(errp, "Could not open VM state file");
goto the_end;
}
ret = qemu_savevm_state(f, errp);
vm_state_size = qemu_ftell(f);
ret2 = qemu_fclose(f);
if (ret < 0) {
goto the_end;
}
if (ret2 < 0) {
ret = ret2;
goto the_end;
}
/* The bdrv_all_create_snapshot() call that follows acquires the AioContext
* for itself. BDRV_POLL_WHILE() does not support nested locking because
* it only releases the lock once. Therefore synchronous I/O will deadlock
* unless we release the AioContext before bdrv_all_create_snapshot().
*/
aio_context_release(aio_context);
aio_context = NULL;
ret = bdrv_all_create_snapshot(sn, bs, vm_state_size,
has_devices, devices, errp);
if (ret < 0) {
bdrv_all_delete_snapshot(sn->name, has_devices, devices, NULL);
goto the_end;
}
ret = 0;
the_end:
if (aio_context) {
aio_context_release(aio_context);
}
bdrv_drain_all_end();
if (saved_vm_running) {
vm_start();
}
return ret == 0;
}
void qmp_xen_save_devices_state(const char *filename, bool has_live, bool live,
Error **errp)
{
QEMUFile *f;
QIOChannelFile *ioc;
int saved_vm_running;
int ret;
if (!has_live) {
/* live default to true so old version of Xen tool stack can have a
* successful live migration */
live = true;
}
saved_vm_running = runstate_is_running();
vm_stop(RUN_STATE_SAVE_VM);
global_state_store_running();
ioc = qio_channel_file_new_path(filename, O_WRONLY | O_CREAT | O_TRUNC,
0660, errp);
if (!ioc) {
goto the_end;
}
qio_channel_set_name(QIO_CHANNEL(ioc), "migration-xen-save-state");
f = qemu_fopen_channel_output(QIO_CHANNEL(ioc));
object_unref(OBJECT(ioc));
ret = qemu_save_device_state(f);
if (ret < 0 || qemu_fclose(f) < 0) {
error_setg(errp, QERR_IO_ERROR);
} else {
/* libxl calls the QMP command "stop" before calling
* "xen-save-devices-state" and in case of migration failure, libxl
* would call "cont".
* So call bdrv_inactivate_all (release locks) here to let the other
* side of the migration take control of the images.
*/
if (live && !saved_vm_running) {
ret = bdrv_inactivate_all();
if (ret) {
error_setg(errp, "%s: bdrv_inactivate_all() failed (%d)",
__func__, ret);
}
}
}
the_end:
if (saved_vm_running) {
vm_start();
}
}
void qmp_xen_load_devices_state(const char *filename, Error **errp)
{
QEMUFile *f;
QIOChannelFile *ioc;
int ret;
/* Guest must be paused before loading the device state; the RAM state
* will already have been loaded by xc
*/
if (runstate_is_running()) {
error_setg(errp, "Cannot update device state while vm is running");
return;
}
vm_stop(RUN_STATE_RESTORE_VM);
ioc = qio_channel_file_new_path(filename, O_RDONLY | O_BINARY, 0, errp);
if (!ioc) {
return;
}
qio_channel_set_name(QIO_CHANNEL(ioc), "migration-xen-load-state");
f = qemu_fopen_channel_input(QIO_CHANNEL(ioc));
object_unref(OBJECT(ioc));
ret = qemu_loadvm_state(f);
qemu_fclose(f);
if (ret < 0) {
error_setg(errp, QERR_IO_ERROR);
}
migration_incoming_state_destroy();
}
bool load_snapshot(const char *name, const char *vmstate,
bool has_devices, strList *devices, Error **errp)
{
BlockDriverState *bs_vm_state;
QEMUSnapshotInfo sn;
QEMUFile *f;
int ret;
AioContext *aio_context;
MigrationIncomingState *mis = migration_incoming_get_current();
if (!bdrv_all_can_snapshot(has_devices, devices, errp)) {
return false;
}
ret = bdrv_all_has_snapshot(name, has_devices, devices, errp);
if (ret < 0) {
return false;
}
if (ret == 0) {
error_setg(errp, "Snapshot '%s' does not exist in one or more devices",
name);
return false;
}
bs_vm_state = bdrv_all_find_vmstate_bs(vmstate, has_devices, devices, errp);
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
if (!bs_vm_state) {
return false;
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
}
aio_context = bdrv_get_aio_context(bs_vm_state);
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
/* Don't even try to load empty VM states */
aio_context_acquire(aio_context);
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
ret = bdrv_snapshot_find(bs_vm_state, &sn, name);
aio_context_release(aio_context);
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
if (ret < 0) {
return false;
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
} else if (sn.vm_state_size == 0) {
error_setg(errp, "This is a disk-only snapshot. Revert to it "
" offline using qemu-img");
return false;
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
}
/*
* Flush the record/replay queue. Now the VM state is going
* to change. Therefore we don't need to preserve its consistency
*/
replay_flush_events();
/* Flush all IO requests so they don't interfere with the new state. */
bdrv_drain_all_begin();
ret = bdrv_all_goto_snapshot(name, has_devices, devices, errp);
if (ret < 0) {
goto err_drain;
}
/* restore the VM state */
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
f = qemu_fopen_bdrv(bs_vm_state, 0);
if (!f) {
error_setg(errp, "Could not open VM state file");
goto err_drain;
}
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
shutdown: Prepare for use of an enum in reset/shutdown_request We want to track why a guest was shutdown; in particular, being able to tell the difference between a guest request (such as ACPI request) and host request (such as SIGINT) will prove useful to libvirt. Since all requests eventually end up changing shutdown_requested in vl.c, the logical change is to make that value track the reason, rather than its current 0/1 contents. Since command-line options control whether a reset request is turned into a shutdown request instead, the same treatment is given to reset_requested. This patch adds an internal enum ShutdownCause that describes reasons that a shutdown can be requested, and changes qemu_system_reset() to pass the reason through, although for now nothing is actually changed with regards to what gets reported. The enum could be exported via QAPI at a later date, if deemed necessary, but for now, there has not been a request to expose that much detail to end clients. For the most part, we turn 0 into SHUTDOWN_CAUSE_NONE, and 1 into SHUTDOWN_CAUSE_HOST_ERROR; the only specific case where we have enough information right now to use a different value is when we are reacting to a host signal. It will take a further patch to edit all call-sites that can trigger a reset or shutdown request to properly pass in any other reasons; this patch includes TODOs to point such places out. qemu_system_reset() trades its 'bool report' parameter for a 'ShutdownCause reason', with all non-zero values having the same effect; this lets us get rid of the weird #defines for VMRESET_* as synonyms for bools. Signed-off-by: Eric Blake <eblake@redhat.com> Message-Id: <20170515214114.15442-3-eblake@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Markus Armbruster <armbru@redhat.com>
2017-05-15 23:41:11 +02:00
qemu_system_reset(SHUTDOWN_CAUSE_NONE);
mis->from_src_file = f;
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
if (!yank_register_instance(MIGRATION_YANK_INSTANCE, errp)) {
ret = -EINVAL;
goto err_drain;
}
aio_context_acquire(aio_context);
ret = qemu_loadvm_state(f);
migration_incoming_state_destroy();
aio_context_release(aio_context);
bdrv_drain_all_end();
if (ret < 0) {
error_setg(errp, "Error %d while loading VM state", ret);
return false;
}
loadvm: improve tests before bdrv_snapshot_goto() This patch improves the resilience of the load_vmstate() function, doing further and better ordered tests. In load_vmstate(), if there is any error on bdrv_snapshot_goto(), except if the error is on VM state device, load_vmstate() will return zero and the VM will be started with major corruption chances. The current process: - test if there is any writable device without snapshot support - if exists return -error - get the device that saves the VM state, possible return -error but unlikely because it was tested earlier - flush I/O - run bdrv_snapshot_goto() on devices - if fails, give an warning and goes to the next (not good!) - if fails on the VM state device, return zero (not good!) - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero New behavior: - get the device that saves the VM state - if fails return -error - check if the requested snapshot exists on the device that saves the VM state and the state is not zero - if fails return -error - test if there is any writable device without snapshot support - if exists return -error - test if the devices with snapshot support have the requested snapshot - if anyone fails, return -error - flush I/O - run snapshot_goto() on devices - if anyone fails, return -error - open the file with the VM state - if fails return -error - load the VM state - if fails return -error - return zero do_loadvm must not call vm_start if any error has occurred in load_vmstate. Signed-off-by: Miguel Di Ciurcio Filho <miguel.filho@gmail.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-19 20:25:01 +02:00
return true;
err_drain:
bdrv_drain_all_end();
return false;
}
bool delete_snapshot(const char *name, bool has_devices,
strList *devices, Error **errp)
{
if (!bdrv_all_can_snapshot(has_devices, devices, errp)) {
return false;
}
if (bdrv_all_delete_snapshot(name, has_devices, devices, errp) < 0) {
return false;
}
return true;
}
void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev)
{
qemu_ram_set_idstr(mr->ram_block,
memory_region_name(mr), dev);
qemu_ram_set_migratable(mr->ram_block);
}
void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev)
{
qemu_ram_unset_idstr(mr->ram_block);
qemu_ram_unset_migratable(mr->ram_block);
}
void vmstate_register_ram_global(MemoryRegion *mr)
{
vmstate_register_ram(mr, NULL);
}
bool vmstate_check_only_migratable(const VMStateDescription *vmsd)
{
/* check needed if --only-migratable is specified */
Revert "migration: move only_migratable to MigrationState" This reverts commit 3df663e575f1876d7f3bc684f80e72fca0703d39. This reverts commit b605c47b57b58e61a901a50a0762dccf43d94783. Command line option --only-migratable is for disallowing any configuration that can block migration. Initially, --only-migratable set global variable @only_migratable. Commit 3df663e575 "migration: move only_migratable to MigrationState" replaced it by MigrationState member @only_migratable. That was a mistake. First, it doesn't make sense on the design level. MigrationState captures the state of an individual migration, but --only-migratable isn't a property of an individual migration, it's a restriction on QEMU configuration. With fault tolerance, we could have several migrations at once. --only-migratable would certainly protect all of them. Storing it in MigrationState feels inappropriate. Second, it contributes to a dependency cycle that manifests itself as a bug now. Putting @only_migratable into MigrationState means its available only after migration_object_init(). We can't set it before migration_object_init(), so we delay setting it with a global property (this is fixup commit b605c47b57 "migration: fix handling for --only-migratable"). We can't get it before migration_object_init(), so anything that uses it can only run afterwards. Since migrate_add_blocker() needs to obey --only-migratable, any code adding migration blockers can run only afterwards. This contributes to the following dependency cycle: * configure_blockdev() must run before machine_set_property() so machine properties can refer to block backends * machine_set_property() before configure_accelerator() so machine properties like kvm-irqchip get applied * configure_accelerator() before migration_object_init() so that Xen's accelerator compat properties get applied. * migration_object_init() before configure_blockdev() so configure_blockdev() can add migration blockers The cycle was closed when recent commit cda4aa9a5a0 "Create block backends before setting machine properties" added the first dependency, and satisfied it by violating the last one. Broke block backends that add migration blockers. Moving @only_migratable into MigrationState was a mistake. Revert it. This doesn't quite break the "migration_object_init() before configure_blockdev() dependency, since migrate_add_blocker() still has another dependency on migration_object_init(). To be addressed the next commit. Note that the reverted commit made -only-migratable sugar for -global migration.only-migratable=on below the hood. Documentation has only ever mentioned -only-migratable. This commit removes the arcane & undocumented alternative to -only-migratable again. Nobody should be using it. Conflicts: include/migration/misc.h migration/migration.c migration/migration.h vl.c Signed-off-by: Markus Armbruster <armbru@redhat.com> Message-Id: <20190401090827.20793-3-armbru@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com>
2019-04-01 11:08:24 +02:00
if (!only_migratable) {
return true;
}
return !(vmsd && vmsd->unmigratable);
}
migration: introduce snapshot-{save, load, delete} QMP commands savevm, loadvm and delvm are some of the few HMP commands that have never been converted to use QMP. The reasons for the lack of conversion are that they blocked execution of the event thread, and the semantics around choice of disks were ill-defined. Despite this downside, however, libvirt and applications using libvirt have used these commands for as long as QMP has existed, via the "human-monitor-command" passthrough command. IOW, while it is clearly desirable to be able to fix the problems, they are not a blocker to all real world usage. Meanwhile there is a need for other features which involve adding new parameters to the commands. This is possible with HMP passthrough, but it provides no reliable way for apps to introspect features, so using QAPI modelling is highly desirable. This patch thus introduces new snapshot-{load,save,delete} commands to QMP that are intended to replace the old HMP counterparts. The new commands are given different names, because they will be using the new QEMU job framework and thus will have diverging behaviour from the HMP originals. It would thus be misleading to keep the same name. While this design uses the generic job framework, the current impl is still blocking. The intention that the blocking problem is fixed later. None the less applications using these new commands should assume that they are asynchronous and thus wait for the job status change event to indicate completion. In addition to using the job framework, the new commands require the caller to be explicit about all the block device nodes used in the snapshot operations, with no built-in default heuristics in use. Note that the existing "query-named-block-nodes" can be used to query what snapshots currently exist for block nodes. Acked-by: Markus Armbruster <armbru@redhat.com> Signed-off-by: Daniel P. Berrangé <berrange@redhat.com> Message-Id: <20210204124834.774401-13-berrange@redhat.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com> dgilbert: removed tests for now, the output ordering isn't deterministic
2021-02-04 13:48:34 +01:00
typedef struct SnapshotJob {
Job common;
char *tag;
char *vmstate;
strList *devices;
Coroutine *co;
Error **errp;
bool ret;
} SnapshotJob;
static void qmp_snapshot_job_free(SnapshotJob *s)
{
g_free(s->tag);
g_free(s->vmstate);
qapi_free_strList(s->devices);
}
static void snapshot_load_job_bh(void *opaque)
{
Job *job = opaque;
SnapshotJob *s = container_of(job, SnapshotJob, common);
int orig_vm_running;
job_progress_set_remaining(&s->common, 1);
orig_vm_running = runstate_is_running();
vm_stop(RUN_STATE_RESTORE_VM);
s->ret = load_snapshot(s->tag, s->vmstate, true, s->devices, s->errp);
if (s->ret && orig_vm_running) {
vm_start();
}
job_progress_update(&s->common, 1);
qmp_snapshot_job_free(s);
aio_co_wake(s->co);
}
static void snapshot_save_job_bh(void *opaque)
{
Job *job = opaque;
SnapshotJob *s = container_of(job, SnapshotJob, common);
job_progress_set_remaining(&s->common, 1);
s->ret = save_snapshot(s->tag, false, s->vmstate,
true, s->devices, s->errp);
job_progress_update(&s->common, 1);
qmp_snapshot_job_free(s);
aio_co_wake(s->co);
}
static void snapshot_delete_job_bh(void *opaque)
{
Job *job = opaque;
SnapshotJob *s = container_of(job, SnapshotJob, common);
job_progress_set_remaining(&s->common, 1);
s->ret = delete_snapshot(s->tag, true, s->devices, s->errp);
job_progress_update(&s->common, 1);
qmp_snapshot_job_free(s);
aio_co_wake(s->co);
}
static int coroutine_fn snapshot_save_job_run(Job *job, Error **errp)
{
SnapshotJob *s = container_of(job, SnapshotJob, common);
s->errp = errp;
s->co = qemu_coroutine_self();
aio_bh_schedule_oneshot(qemu_get_aio_context(),
snapshot_save_job_bh, job);
qemu_coroutine_yield();
return s->ret ? 0 : -1;
}
static int coroutine_fn snapshot_load_job_run(Job *job, Error **errp)
{
SnapshotJob *s = container_of(job, SnapshotJob, common);
s->errp = errp;
s->co = qemu_coroutine_self();
aio_bh_schedule_oneshot(qemu_get_aio_context(),
snapshot_load_job_bh, job);
qemu_coroutine_yield();
return s->ret ? 0 : -1;
}
static int coroutine_fn snapshot_delete_job_run(Job *job, Error **errp)
{
SnapshotJob *s = container_of(job, SnapshotJob, common);
s->errp = errp;
s->co = qemu_coroutine_self();
aio_bh_schedule_oneshot(qemu_get_aio_context(),
snapshot_delete_job_bh, job);
qemu_coroutine_yield();
return s->ret ? 0 : -1;
}
static const JobDriver snapshot_load_job_driver = {
.instance_size = sizeof(SnapshotJob),
.job_type = JOB_TYPE_SNAPSHOT_LOAD,
.run = snapshot_load_job_run,
};
static const JobDriver snapshot_save_job_driver = {
.instance_size = sizeof(SnapshotJob),
.job_type = JOB_TYPE_SNAPSHOT_SAVE,
.run = snapshot_save_job_run,
};
static const JobDriver snapshot_delete_job_driver = {
.instance_size = sizeof(SnapshotJob),
.job_type = JOB_TYPE_SNAPSHOT_DELETE,
.run = snapshot_delete_job_run,
};
void qmp_snapshot_save(const char *job_id,
const char *tag,
const char *vmstate,
strList *devices,
Error **errp)
{
SnapshotJob *s;
s = job_create(job_id, &snapshot_save_job_driver, NULL,
qemu_get_aio_context(), JOB_MANUAL_DISMISS,
NULL, NULL, errp);
if (!s) {
return;
}
s->tag = g_strdup(tag);
s->vmstate = g_strdup(vmstate);
s->devices = QAPI_CLONE(strList, devices);
job_start(&s->common);
}
void qmp_snapshot_load(const char *job_id,
const char *tag,
const char *vmstate,
strList *devices,
Error **errp)
{
SnapshotJob *s;
s = job_create(job_id, &snapshot_load_job_driver, NULL,
qemu_get_aio_context(), JOB_MANUAL_DISMISS,
NULL, NULL, errp);
if (!s) {
return;
}
s->tag = g_strdup(tag);
s->vmstate = g_strdup(vmstate);
s->devices = QAPI_CLONE(strList, devices);
job_start(&s->common);
}
void qmp_snapshot_delete(const char *job_id,
const char *tag,
strList *devices,
Error **errp)
{
SnapshotJob *s;
s = job_create(job_id, &snapshot_delete_job_driver, NULL,
qemu_get_aio_context(), JOB_MANUAL_DISMISS,
NULL, NULL, errp);
if (!s) {
return;
}
s->tag = g_strdup(tag);
s->devices = QAPI_CLONE(strList, devices);
job_start(&s->common);
}