aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPeter Maydell <peter.maydell@linaro.org>2017-04-21 15:59:27 +0100
committerPeter Maydell <peter.maydell@linaro.org>2017-04-21 15:59:27 +0100
commit32c7e0ab755745e961f1772e95cac381cc68769d (patch)
treefa40ac2dd8de6e9d4dfa6607c41cc7ee03c3daf7
parentaf7ec403b213544667cbc275926fa23b54e0cb02 (diff)
parent2c02468c9b1750aaa5fbeee49cdb55f101608c6a (diff)
downloadqemu-32c7e0ab755745e961f1772e95cac381cc68769d.zip
qemu-32c7e0ab755745e961f1772e95cac381cc68769d.tar.gz
qemu-32c7e0ab755745e961f1772e95cac381cc68769d.tar.bz2
Merge remote-tracking branch 'remotes/juanquintela/tags/migration/20170421' into staging
migration/next for 20170421 # gpg: Signature made Fri 21 Apr 2017 11:28:13 BST # gpg: using RSA key 0xF487EF185872D723 # gpg: Good signature from "Juan Quintela <quintela@redhat.com>" # gpg: aka "Juan Quintela <quintela@trasno.org>" # Primary key fingerprint: 1899 FF8E DEBF 58CC EE03 4B82 F487 EF18 5872 D723 * remotes/juanquintela/tags/migration/20170421: (65 commits) hmp: info migrate_parameters format tunes hmp: info migrate_capability format tunes migration: rename max_size to threshold_size migration: set current_active_state once virtio-rng: stop virtqueue while the CPU is stopped migration: don't close a file descriptor while it can be in use ram: Remove migration_bitmap_extend() migration: Disable hotplug/unplug during migration qdev: Move qdev_unplug() to qdev-monitor.c qdev: Export qdev_hot_removed qdev: qdev_hotplug is really a bool migration: Remove MigrationState parameter from migration_is_idle() ram: Use RAMBitmap type for coherence ram: rename last_ram_offset() last_ram_pages() ram: Use ramblock and page offset instead of absolute offset ram: Change offset field in PageSearchStatus to page ram: Remember last_page instead of last_offset ram: Use page number instead of an address for the bitmap operations ram: reorganize last_sent_block ram: ram_discard_range() don't use the mis parameter ... Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat
-rw-r--r--exec.c11
-rw-r--r--hmp.c29
-rw-r--r--hw/core/qdev.c40
-rw-r--r--hw/virtio/trace-events3
-rw-r--r--hw/virtio/virtio-rng.c29
-rw-r--r--include/exec/ram_addr.h8
-rw-r--r--include/hw/qdev-core.h3
-rw-r--r--include/hw/virtio/virtio-rng.h2
-rw-r--r--include/migration/migration.h41
-rw-r--r--include/migration/vmstate.h3
-rw-r--r--include/sysemu/sysemu.h2
-rw-r--r--migration/migration.c72
-rw-r--r--migration/postcopy-ram.c14
-rw-r--r--migration/ram.c1192
-rw-r--r--migration/savevm.c19
-rw-r--r--migration/trace-events4
-rw-r--r--qapi-schema.json5
-rw-r--r--qdev-monitor.c45
18 files changed, 791 insertions, 731 deletions
diff --git a/exec.c b/exec.c
index c97ef4a..c2def9e 100644
--- a/exec.c
+++ b/exec.c
@@ -1528,7 +1528,7 @@ static ram_addr_t find_ram_offset(ram_addr_t size)
return offset;
}
-ram_addr_t last_ram_offset(void)
+unsigned long last_ram_page(void)
{
RAMBlock *block;
ram_addr_t last = 0;
@@ -1538,7 +1538,7 @@ ram_addr_t last_ram_offset(void)
last = MAX(last, block->offset + block->max_length);
}
rcu_read_unlock();
- return last;
+ return last >> TARGET_PAGE_BITS;
}
static void qemu_ram_setup_dump(void *addr, ram_addr_t size)
@@ -1727,7 +1727,7 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
ram_addr_t old_ram_size, new_ram_size;
Error *err = NULL;
- old_ram_size = last_ram_offset() >> TARGET_PAGE_BITS;
+ old_ram_size = last_ram_page();
qemu_mutex_lock_ramlist();
new_block->offset = find_ram_offset(new_block->max_length);
@@ -1758,7 +1758,6 @@ static void ram_block_add(RAMBlock *new_block, Error **errp)
new_ram_size = MAX(old_ram_size,
(new_block->offset + new_block->max_length) >> TARGET_PAGE_BITS);
if (new_ram_size > old_ram_size) {
- migration_bitmap_extend(old_ram_size, new_ram_size);
dirty_memory_extend(old_ram_size, new_ram_size);
}
/* Keep the list sorted from biggest to smallest block. Unlike QTAILQ,
@@ -3307,9 +3306,9 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
* Allows code that needs to deal with migration bitmaps etc to still be built
* target independent.
*/
-size_t qemu_target_page_bits(void)
+size_t qemu_target_page_size(void)
{
- return TARGET_PAGE_BITS;
+ return TARGET_PAGE_SIZE;
}
#endif
diff --git a/hmp.c b/hmp.c
index edb8970..ab407d6 100644
--- a/hmp.c
+++ b/hmp.c
@@ -215,6 +215,9 @@ void hmp_info_migrate(Monitor *mon, const QDict *qdict)
info->ram->normal_bytes >> 10);
monitor_printf(mon, "dirty sync count: %" PRIu64 "\n",
info->ram->dirty_sync_count);
+ monitor_printf(mon, "page size: %" PRIu64 " kbytes\n",
+ info->ram->page_size >> 10);
+
if (info->ram->dirty_pages_rate) {
monitor_printf(mon, "dirty pages rate: %" PRIu64 " pages\n",
info->ram->dirty_pages_rate);
@@ -265,13 +268,11 @@ void hmp_info_migrate_capabilities(Monitor *mon, const QDict *qdict)
caps = qmp_query_migrate_capabilities(NULL);
if (caps) {
- monitor_printf(mon, "capabilities: ");
for (cap = caps; cap; cap = cap->next) {
- monitor_printf(mon, "%s: %s ",
+ monitor_printf(mon, "%s: %s\n",
MigrationCapability_lookup[cap->value->capability],
cap->value->state ? "on" : "off");
}
- monitor_printf(mon, "\n");
}
qapi_free_MigrationCapabilityStatusList(caps);
@@ -284,46 +285,44 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict)
params = qmp_query_migrate_parameters(NULL);
if (params) {
- monitor_printf(mon, "parameters:");
assert(params->has_compress_level);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_COMPRESS_LEVEL],
params->compress_level);
assert(params->has_compress_threads);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_COMPRESS_THREADS],
params->compress_threads);
assert(params->has_decompress_threads);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_DECOMPRESS_THREADS],
params->decompress_threads);
assert(params->has_cpu_throttle_initial);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_CPU_THROTTLE_INITIAL],
params->cpu_throttle_initial);
assert(params->has_cpu_throttle_increment);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_CPU_THROTTLE_INCREMENT],
params->cpu_throttle_increment);
- monitor_printf(mon, " %s: '%s'",
+ monitor_printf(mon, "%s: '%s'\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_TLS_CREDS],
params->has_tls_creds ? params->tls_creds : "");
- monitor_printf(mon, " %s: '%s'",
+ monitor_printf(mon, "%s: '%s'\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_TLS_HOSTNAME],
params->has_tls_hostname ? params->tls_hostname : "");
assert(params->has_max_bandwidth);
- monitor_printf(mon, " %s: %" PRId64 " bytes/second",
+ monitor_printf(mon, "%s: %" PRId64 " bytes/second\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_MAX_BANDWIDTH],
params->max_bandwidth);
assert(params->has_downtime_limit);
- monitor_printf(mon, " %s: %" PRId64 " milliseconds",
+ monitor_printf(mon, "%s: %" PRId64 " milliseconds\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_DOWNTIME_LIMIT],
params->downtime_limit);
assert(params->has_x_checkpoint_delay);
- monitor_printf(mon, " %s: %" PRId64,
+ monitor_printf(mon, "%s: %" PRId64 "\n",
MigrationParameter_lookup[MIGRATION_PARAMETER_X_CHECKPOINT_DELAY],
params->x_checkpoint_delay);
- monitor_printf(mon, "\n");
}
qapi_free_MigrationParameters(params);
diff --git a/hw/core/qdev.c b/hw/core/qdev.c
index 695d7c4..02b632f 100644
--- a/hw/core/qdev.c
+++ b/hw/core/qdev.c
@@ -39,9 +39,9 @@
#include "qapi-event.h"
#include "migration/migration.h"
-int qdev_hotplug = 0;
+bool qdev_hotplug = false;
static bool qdev_hot_added = false;
-static bool qdev_hot_removed = false;
+bool qdev_hot_removed = false;
const VMStateDescription *qdev_get_vmsd(DeviceState *dev)
{
@@ -271,40 +271,6 @@ HotplugHandler *qdev_get_hotplug_handler(DeviceState *dev)
return hotplug_ctrl;
}
-void qdev_unplug(DeviceState *dev, Error **errp)
-{
- DeviceClass *dc = DEVICE_GET_CLASS(dev);
- HotplugHandler *hotplug_ctrl;
- HotplugHandlerClass *hdc;
-
- if (dev->parent_bus && !qbus_is_hotpluggable(dev->parent_bus)) {
- error_setg(errp, QERR_BUS_NO_HOTPLUG, dev->parent_bus->name);
- return;
- }
-
- if (!dc->hotpluggable) {
- error_setg(errp, QERR_DEVICE_NO_HOTPLUG,
- object_get_typename(OBJECT(dev)));
- return;
- }
-
- qdev_hot_removed = true;
-
- hotplug_ctrl = qdev_get_hotplug_handler(dev);
- /* hotpluggable device MUST have HotplugHandler, if it doesn't
- * then something is very wrong with it */
- g_assert(hotplug_ctrl);
-
- /* If device supports async unplug just request it to be done,
- * otherwise just remove it synchronously */
- hdc = HOTPLUG_HANDLER_GET_CLASS(hotplug_ctrl);
- if (hdc->unplug_request) {
- hotplug_handler_unplug_request(hotplug_ctrl, dev, errp);
- } else {
- hotplug_handler_unplug(hotplug_ctrl, dev, errp);
- }
-}
-
static int qdev_reset_one(DeviceState *dev, void *opaque)
{
device_reset(dev);
@@ -385,7 +351,7 @@ void qdev_machine_creation_done(void)
* ok, initial machine setup is done, starting from now we can
* only create hotpluggable devices
*/
- qdev_hotplug = 1;
+ qdev_hotplug = true;
}
bool qdev_machine_modified(void)
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 6926eed..1f7a7c1 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -11,8 +11,11 @@ virtio_set_status(void *vdev, uint8_t val) "vdev %p val %u"
# hw/virtio/virtio-rng.c
virtio_rng_guest_not_ready(void *rng) "rng %p: guest not ready"
+virtio_rng_cpu_is_stopped(void *rng, int size) "rng %p: cpu is stopped, dropping %d bytes"
+virtio_rng_popped(void *rng) "rng %p: elem popped"
virtio_rng_pushed(void *rng, size_t len) "rng %p: %zd bytes pushed"
virtio_rng_request(void *rng, size_t size, unsigned quota) "rng %p: %zd bytes requested, %u bytes quota left"
+virtio_rng_vm_state_change(void *rng, int running, int state) "rng %p: state change to running %d state %d"
# hw/virtio/virtio-balloon.c
#
diff --git a/hw/virtio/virtio-rng.c b/hw/virtio/virtio-rng.c
index 9639f4e..a6ee501 100644
--- a/hw/virtio/virtio-rng.c
+++ b/hw/virtio/virtio-rng.c
@@ -53,6 +53,15 @@ static void chr_read(void *opaque, const void *buf, size_t size)
return;
}
+ /* we can't modify the virtqueue until
+ * our state is fully synced
+ */
+
+ if (!runstate_check(RUN_STATE_RUNNING)) {
+ trace_virtio_rng_cpu_is_stopped(vrng, size);
+ return;
+ }
+
vrng->quota_remaining -= size;
offset = 0;
@@ -61,6 +70,7 @@ static void chr_read(void *opaque, const void *buf, size_t size)
if (!elem) {
break;
}
+ trace_virtio_rng_popped(vrng);
len = iov_from_buf(elem->in_sg, elem->in_num,
0, buf + offset, size - offset);
offset += len;
@@ -120,17 +130,21 @@ static uint64_t get_features(VirtIODevice *vdev, uint64_t f, Error **errp)
return f;
}
-static int virtio_rng_post_load(void *opaque, int version_id)
+static void virtio_rng_vm_state_change(void *opaque, int running,
+ RunState state)
{
VirtIORNG *vrng = opaque;
+ trace_virtio_rng_vm_state_change(vrng, running, state);
+
/* We may have an element ready but couldn't process it due to a quota
- * limit. Make sure to try again after live migration when the quota may
- * have been reset.
+ * limit or because CPU was stopped. Make sure to try again when the
+ * CPU restart.
*/
- virtio_rng_process(vrng);
- return 0;
+ if (running && is_guest_ready(vrng)) {
+ virtio_rng_process(vrng);
+ }
}
static void check_rate_limit(void *opaque)
@@ -198,6 +212,9 @@ static void virtio_rng_device_realize(DeviceState *dev, Error **errp)
vrng->rate_limit_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
check_rate_limit, vrng);
vrng->activate_timer = true;
+
+ vrng->vmstate = qemu_add_vm_change_state_handler(virtio_rng_vm_state_change,
+ vrng);
}
static void virtio_rng_device_unrealize(DeviceState *dev, Error **errp)
@@ -205,6 +222,7 @@ static void virtio_rng_device_unrealize(DeviceState *dev, Error **errp)
VirtIODevice *vdev = VIRTIO_DEVICE(dev);
VirtIORNG *vrng = VIRTIO_RNG(dev);
+ qemu_del_vm_change_state_handler(vrng->vmstate);
timer_del(vrng->rate_limit_timer);
timer_free(vrng->rate_limit_timer);
virtio_cleanup(vdev);
@@ -218,7 +236,6 @@ static const VMStateDescription vmstate_virtio_rng = {
VMSTATE_VIRTIO_DEVICE,
VMSTATE_END_OF_LIST()
},
- .post_load = virtio_rng_post_load,
};
static Property virtio_rng_properties[] = {
diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h
index b05dc84..c9ddcd0 100644
--- a/include/exec/ram_addr.h
+++ b/include/exec/ram_addr.h
@@ -53,7 +53,7 @@ static inline void *ramblock_ptr(RAMBlock *block, ram_addr_t offset)
}
long qemu_getrampagesize(void);
-ram_addr_t last_ram_offset(void);
+unsigned long last_ram_page(void);
RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr,
bool share, const char *mem_path,
Error **errp);
@@ -354,11 +354,13 @@ static inline void cpu_physical_memory_clear_dirty_range(ram_addr_t start,
static inline
uint64_t cpu_physical_memory_sync_dirty_bitmap(unsigned long *dest,
+ RAMBlock *rb,
ram_addr_t start,
ram_addr_t length,
- int64_t *real_dirty_pages)
+ uint64_t *real_dirty_pages)
{
ram_addr_t addr;
+ start = rb->offset + start;
unsigned long page = BIT_WORD(start >> TARGET_PAGE_BITS);
uint64_t num_dirty = 0;
@@ -411,7 +413,5 @@ uint64_t cpu_physical_memory_sync_dirty_bitmap(unsigned long *dest,
return num_dirty;
}
-
-void migration_bitmap_extend(ram_addr_t old, ram_addr_t new);
#endif
#endif
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index ac682a6..4bf86b0 100644
--- a/include/hw/qdev-core.h
+++ b/include/hw/qdev-core.h
@@ -373,7 +373,8 @@ Object *qdev_get_machine(void);
/* FIXME: make this a link<> */
void qdev_set_parent_bus(DeviceState *dev, BusState *bus);
-extern int qdev_hotplug;
+extern bool qdev_hotplug;
+extern bool qdev_hot_removed;
char *qdev_get_dev_path(DeviceState *dev);
diff --git a/include/hw/virtio/virtio-rng.h b/include/hw/virtio/virtio-rng.h
index 2d40abd..922dce7 100644
--- a/include/hw/virtio/virtio-rng.h
+++ b/include/hw/virtio/virtio-rng.h
@@ -45,6 +45,8 @@ typedef struct VirtIORNG {
QEMUTimer *rate_limit_timer;
int64_t quota_remaining;
bool activate_timer;
+
+ VMChangeStateEntry *vmstate;
} VirtIORNG;
#endif
diff --git a/include/migration/migration.h b/include/migration/migration.h
index 5720c88..ba1a16c 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -128,18 +128,6 @@ struct MigrationIncomingState {
MigrationIncomingState *migration_incoming_get_current(void);
void migration_incoming_state_destroy(void);
-/*
- * An outstanding page request, on the source, having been received
- * and queued
- */
-struct MigrationSrcPageRequest {
- RAMBlock *rb;
- hwaddr offset;
- hwaddr len;
-
- QSIMPLEQ_ENTRY(MigrationSrcPageRequest) next_req;
-};
-
struct MigrationState
{
size_t bytes_xfer;
@@ -166,14 +154,9 @@ struct MigrationState
int64_t total_time;
int64_t downtime;
int64_t expected_downtime;
- int64_t dirty_pages_rate;
- int64_t dirty_bytes_rate;
bool enabled_capabilities[MIGRATION_CAPABILITY__MAX];
int64_t xbzrle_cache_size;
int64_t setup_time;
- int64_t dirty_sync_count;
- /* Count of requests incoming from destination */
- int64_t postcopy_requests;
/* Flag set once the migration has been asked to enter postcopy */
bool start_postcopy;
@@ -186,11 +169,6 @@ struct MigrationState
/* Flag set once the migration thread called bdrv_inactivate_all */
bool block_inactive;
- /* Queue of outstanding page requests from the destination */
- QemuMutex src_page_req_mutex;
- QSIMPLEQ_HEAD(src_page_requests, MigrationSrcPageRequest) src_page_requests;
- /* The RAMBlock used in the last src_page_request */
- RAMBlock *last_req_rb;
/* The semaphore is used to notify COLO thread that failover is finished */
QemuSemaphore colo_exit_sem;
@@ -256,11 +234,11 @@ void remove_migration_state_change_notifier(Notifier *notify);
MigrationState *migrate_init(const MigrationParams *params);
bool migration_is_blocked(Error **errp);
bool migration_in_setup(MigrationState *);
-bool migration_is_idle(MigrationState *s);
+bool migration_is_idle(void);
bool migration_has_finished(MigrationState *);
bool migration_has_failed(MigrationState *);
/* True if outgoing migration has entered postcopy phase */
-bool migration_in_postcopy(MigrationState *);
+bool migration_in_postcopy(void);
/* ...and after the device transmission */
bool migration_in_postcopy_after_devices(MigrationState *);
MigrationState *migrate_get_current(void);
@@ -272,15 +250,14 @@ void migrate_decompress_threads_join(void);
uint64_t ram_bytes_remaining(void);
uint64_t ram_bytes_transferred(void);
uint64_t ram_bytes_total(void);
+uint64_t ram_dirty_sync_count(void);
+uint64_t ram_dirty_pages_rate(void);
+uint64_t ram_postcopy_requests(void);
void free_xbzrle_decoded_buf(void);
void acct_update_position(QEMUFile *f, size_t size, bool zero);
-uint64_t dup_mig_bytes_transferred(void);
uint64_t dup_mig_pages_transferred(void);
-uint64_t skipped_mig_bytes_transferred(void);
-uint64_t skipped_mig_pages_transferred(void);
-uint64_t norm_mig_bytes_transferred(void);
uint64_t norm_mig_pages_transferred(void);
uint64_t xbzrle_mig_bytes_transferred(void);
uint64_t xbzrle_mig_pages_transferred(void);
@@ -293,8 +270,7 @@ void ram_debug_dump_bitmap(unsigned long *todump, bool expected);
/* For outgoing discard bitmap */
int ram_postcopy_send_discard_bitmap(MigrationState *ms);
/* For incoming postcopy discard */
-int ram_discard_range(MigrationIncomingState *mis, const char *block_name,
- uint64_t start, size_t length);
+int ram_discard_range(const char *block_name, uint64_t start, size_t length);
int ram_postcopy_incoming_init(MigrationIncomingState *mis);
void ram_postcopy_migrated_memory_release(MigrationState *ms);
@@ -377,9 +353,8 @@ void savevm_skip_configuration(void);
int global_state_store(void);
void global_state_store_running(void);
-void flush_page_queue(MigrationState *ms);
-int ram_save_queue_pages(MigrationState *ms, const char *rbname,
- ram_addr_t start, ram_addr_t len);
+void migration_page_queue_free(void);
+int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len);
uint64_t ram_pagesize_summary(void);
PostcopyState postcopy_state_get(void);
diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h
index f2dbf84..dad3984 100644
--- a/include/migration/vmstate.h
+++ b/include/migration/vmstate.h
@@ -56,7 +56,8 @@ typedef struct SaveVMHandlers {
/* This runs outside the iothread lock! */
int (*save_live_setup)(QEMUFile *f, void *opaque);
- void (*save_live_pending)(QEMUFile *f, void *opaque, uint64_t max_size,
+ void (*save_live_pending)(QEMUFile *f, void *opaque,
+ uint64_t threshold_size,
uint64_t *non_postcopiable_pending,
uint64_t *postcopiable_pending);
LoadStateHandler *load_state;
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 576c7ce..16175f7 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -67,7 +67,7 @@ int qemu_reset_requested_get(void);
void qemu_system_killed(int signal, pid_t pid);
void qemu_system_reset(bool report);
void qemu_system_guest_panicked(GuestPanicInformation *info);
-size_t qemu_target_page_bits(void);
+size_t qemu_target_page_size(void);
void qemu_add_exit_notifier(Notifier *notify);
void qemu_remove_exit_notifier(Notifier *notify);
diff --git a/migration/migration.c b/migration/migration.c
index ad4036f..353f272 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -109,7 +109,6 @@ MigrationState *migrate_get_current(void)
};
if (!once) {
- qemu_mutex_init(&current_migration.src_page_req_mutex);
current_migration.parameters.tls_creds = g_strdup("");
current_migration.parameters.tls_hostname = g_strdup("");
once = true;
@@ -436,9 +435,6 @@ static void process_incoming_migration_co(void *opaque)
qemu_thread_join(&mis->colo_incoming_thread);
}
- qemu_fclose(f);
- free_xbzrle_decoded_buf();
-
if (ret < 0) {
migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE,
MIGRATION_STATUS_FAILED);
@@ -447,6 +443,9 @@ static void process_incoming_migration_co(void *opaque)
exit(EXIT_FAILURE);
}
+ qemu_fclose(f);
+ free_xbzrle_decoded_buf();
+
mis->bh = qemu_bh_new(process_incoming_migration_bh, mis);
qemu_bh_schedule(mis->bh);
}
@@ -651,16 +650,19 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s)
info->ram->transferred = ram_bytes_transferred();
info->ram->total = ram_bytes_total();
info->ram->duplicate = dup_mig_pages_transferred();
- info->ram->skipped = skipped_mig_pages_transferred();
+ /* legacy value. It is not used anymore */
+ info->ram->skipped = 0;
info->ram->normal = norm_mig_pages_transferred();
- info->ram->normal_bytes = norm_mig_bytes_transferred();
+ info->ram->normal_bytes = norm_mig_pages_transferred() *
+ qemu_target_page_size();
info->ram->mbps = s->mbps;
- info->ram->dirty_sync_count = s->dirty_sync_count;
- info->ram->postcopy_requests = s->postcopy_requests;
+ info->ram->dirty_sync_count = ram_dirty_sync_count();
+ info->ram->postcopy_requests = ram_postcopy_requests();
+ info->ram->page_size = qemu_target_page_size();
if (s->state != MIGRATION_STATUS_COMPLETED) {
info->ram->remaining = ram_bytes_remaining();
- info->ram->dirty_pages_rate = s->dirty_pages_rate;
+ info->ram->dirty_pages_rate = ram_dirty_pages_rate();
}
}
@@ -955,7 +957,7 @@ static void migrate_fd_cleanup(void *opaque)
qemu_bh_delete(s->cleanup_bh);
s->cleanup_bh = NULL;
- flush_page_queue(s);
+ migration_page_queue_free();
if (s->to_dst_file) {
trace_migrate_fd_cleanup();
@@ -1061,21 +1063,21 @@ bool migration_has_failed(MigrationState *s)
s->state == MIGRATION_STATUS_FAILED);
}
-bool migration_in_postcopy(MigrationState *s)
+bool migration_in_postcopy(void)
{
+ MigrationState *s = migrate_get_current();
+
return (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE);
}
bool migration_in_postcopy_after_devices(MigrationState *s)
{
- return migration_in_postcopy(s) && s->postcopy_after_devices;
+ return migration_in_postcopy() && s->postcopy_after_devices;
}
-bool migration_is_idle(MigrationState *s)
+bool migration_is_idle(void)
{
- if (!s) {
- s = migrate_get_current();
- }
+ MigrationState *s = migrate_get_current();
switch (s->state) {
case MIGRATION_STATUS_NONE:
@@ -1116,22 +1118,15 @@ MigrationState *migrate_init(const MigrationParams *params)
s->mbps = 0.0;
s->downtime = 0;
s->expected_downtime = 0;
- s->dirty_pages_rate = 0;
- s->dirty_bytes_rate = 0;
s->setup_time = 0;
- s->dirty_sync_count = 0;
s->start_postcopy = false;
s->postcopy_after_devices = false;
- s->postcopy_requests = 0;
s->migration_thread_running = false;
- s->last_req_rb = NULL;
error_free(s->error);
s->error = NULL;
migrate_set_state(&s->state, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP);
- QSIMPLEQ_INIT(&s->src_page_requests);
-
s->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
return s;
}
@@ -1147,7 +1142,7 @@ int migrate_add_blocker(Error *reason, Error **errp)
return -EACCES;
}
- if (migration_is_idle(NULL)) {
+ if (migration_is_idle()) {
migration_blockers = g_slist_prepend(migration_blockers, reason);
return 0;
}
@@ -1485,7 +1480,7 @@ static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname,
return;
}
- if (ram_save_queue_pages(ms, rbname, start, len)) {
+ if (ram_save_queue_pages(rbname, start, len)) {
mark_source_rp_bad(ms);
}
}
@@ -1915,7 +1910,12 @@ static void *migration_thread(void *opaque)
int64_t initial_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
int64_t setup_start = qemu_clock_get_ms(QEMU_CLOCK_HOST);
int64_t initial_bytes = 0;
- int64_t max_size = 0;
+ /*
+ * The final stage happens when the remaining data is smaller than
+ * this threshold; it's calculated from the requested downtime and
+ * measured bandwidth
+ */
+ int64_t threshold_size = 0;
int64_t start_time = initial_time;
int64_t end_time;
bool old_vm_running = false;
@@ -1946,7 +1946,6 @@ static void *migration_thread(void *opaque)
qemu_savevm_state_begin(s->to_dst_file, &s->params);
s->setup_time = qemu_clock_get_ms(QEMU_CLOCK_HOST) - setup_start;
- current_active_state = MIGRATION_STATUS_ACTIVE;
migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
MIGRATION_STATUS_ACTIVE);
@@ -1960,17 +1959,17 @@ static void *migration_thread(void *opaque)
if (!qemu_file_rate_limit(s->to_dst_file)) {
uint64_t pend_post, pend_nonpost;
- qemu_savevm_state_pending(s->to_dst_file, max_size, &pend_nonpost,
- &pend_post);
+ qemu_savevm_state_pending(s->to_dst_file, threshold_size,
+ &pend_nonpost, &pend_post);
pending_size = pend_nonpost + pend_post;
- trace_migrate_pending(pending_size, max_size,
+ trace_migrate_pending(pending_size, threshold_size,
pend_post, pend_nonpost);
- if (pending_size && pending_size >= max_size) {
+ if (pending_size && pending_size >= threshold_size) {
/* Still a significant amount to transfer */
if (migrate_postcopy_ram() &&
s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE &&
- pend_nonpost <= max_size &&
+ pend_nonpost <= threshold_size &&
atomic_read(&s->start_postcopy)) {
if (!postcopy_start(s, &old_vm_running)) {
@@ -2002,17 +2001,18 @@ static void *migration_thread(void *opaque)
initial_bytes;
uint64_t time_spent = current_time - initial_time;
double bandwidth = (double)transferred_bytes / time_spent;
- max_size = bandwidth * s->parameters.downtime_limit;
+ threshold_size = bandwidth * s->parameters.downtime_limit;
s->mbps = (((double) transferred_bytes * 8.0) /
((double) time_spent / 1000.0)) / 1000.0 / 1000.0;
trace_migrate_transferred(transferred_bytes, time_spent,
- bandwidth, max_size);
+ bandwidth, threshold_size);
/* if we haven't sent anything, we don't want to recalculate
10000 is a small enough number for our purposes */
- if (s->dirty_bytes_rate && transferred_bytes > 10000) {
- s->expected_downtime = s->dirty_bytes_rate / bandwidth;
+ if (ram_dirty_pages_rate() && transferred_bytes > 10000) {
+ s->expected_downtime = ram_dirty_pages_rate() *
+ qemu_target_page_size() / bandwidth;
}
qemu_file_reset_rate_limit(s->to_dst_file);
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index dc80dbb..85fd8d7 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -123,7 +123,7 @@ bool postcopy_ram_supported_by_host(void)
struct uffdio_range range_struct;
uint64_t feature_mask;
- if ((1ul << qemu_target_page_bits()) > pagesize) {
+ if (qemu_target_page_size() > pagesize) {
error_report("Target page size bigger than host page size");
goto out;
}
@@ -213,8 +213,6 @@ out:
static int init_range(const char *block_name, void *host_addr,
ram_addr_t offset, ram_addr_t length, void *opaque)
{
- MigrationIncomingState *mis = opaque;
-
trace_postcopy_init_range(block_name, host_addr, offset, length);
/*
@@ -223,7 +221,7 @@ static int init_range(const char *block_name, void *host_addr,
* - we're going to get the copy from the source anyway.
* (Precopy will just overwrite this data, so doesn't need the discard)
*/
- if (ram_discard_range(mis, block_name, 0, length)) {
+ if (ram_discard_range(block_name, 0, length)) {
return -1;
}
@@ -271,7 +269,7 @@ static int cleanup_range(const char *block_name, void *host_addr,
*/
int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages)
{
- if (qemu_ram_foreach_block(init_range, mis)) {
+ if (qemu_ram_foreach_block(init_range, NULL)) {
return -1;
}
@@ -745,10 +743,10 @@ PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms,
void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds,
unsigned long start, unsigned long length)
{
- size_t tp_bits = qemu_target_page_bits();
+ size_t tp_size = qemu_target_page_size();
/* Convert to byte offsets within the RAM block */
- pds->start_list[pds->cur_entry] = (start - pds->offset) << tp_bits;
- pds->length_list[pds->cur_entry] = length << tp_bits;
+ pds->start_list[pds->cur_entry] = (start - pds->offset) * tp_size;
+ pds->length_list[pds->cur_entry] = length * tp_size;
trace_postcopy_discard_send_range(pds->ramblock_name, start, length);
pds->cur_entry++;
pds->nsentwords++;
diff --git a/migration/ram.c b/migration/ram.c
index de1e0a3..f48664e 100644
--- a/migration/ram.c
+++ b/migration/ram.c
@@ -45,10 +45,6 @@
#include "qemu/rcu_queue.h"
#include "migration/colo.h"
-static int dirty_rate_high_cnt;
-
-static uint64_t bitmap_sync_count;
-
/***********************************************************/
/* ram save/restore */
@@ -96,11 +92,17 @@ static void XBZRLE_cache_unlock(void)
qemu_mutex_unlock(&XBZRLE.lock);
}
-/*
- * called from qmp_migrate_set_cache_size in main thread, possibly while
- * a migration is in progress.
- * A running migration maybe using the cache and might finish during this
- * call, hence changes to the cache are protected by XBZRLE.lock().
+/**
+ * xbzrle_cache_resize: resize the xbzrle cache
+ *
+ * This function is called from qmp_migrate_set_cache_size in main
+ * thread, possibly while a migration is in progress. A running
+ * migration may be using the cache and might finish during this call,
+ * hence changes to the cache are protected by XBZRLE.lock().
+ *
+ * Returns the new_size or negative in case of error.
+ *
+ * @new_size: new cache size
*/
int64_t xbzrle_cache_resize(int64_t new_size)
{
@@ -136,115 +138,171 @@ out:
return ret;
}
-/* accounting for migration statistics */
-typedef struct AccountingInfo {
- uint64_t dup_pages;
- uint64_t skipped_pages;
+struct RAMBitmap {
+ struct rcu_head rcu;
+ /* Main migration bitmap */
+ unsigned long *bmap;
+ /* bitmap of pages that haven't been sent even once
+ * only maintained and used in postcopy at the moment
+ * where it's used to send the dirtymap at the start
+ * of the postcopy phase
+ */
+ unsigned long *unsentmap;
+};
+typedef struct RAMBitmap RAMBitmap;
+
+/*
+ * An outstanding page request, on the source, having been received
+ * and queued
+ */
+struct RAMSrcPageRequest {
+ RAMBlock *rb;
+ hwaddr offset;
+ hwaddr len;
+
+ QSIMPLEQ_ENTRY(RAMSrcPageRequest) next_req;
+};
+
+/* State of RAM for migration */
+struct RAMState {
+ /* QEMUFile used for this migration */
+ QEMUFile *f;
+ /* Last block that we have visited searching for dirty pages */
+ RAMBlock *last_seen_block;
+ /* Last block from where we have sent data */
+ RAMBlock *last_sent_block;
+ /* Last dirty target page we have sent */
+ ram_addr_t last_page;
+ /* last ram version we have seen */
+ uint32_t last_version;
+ /* We are in the first round */
+ bool ram_bulk_stage;
+ /* How many times we have dirty too many pages */
+ int dirty_rate_high_cnt;
+ /* How many times we have synchronized the bitmap */
+ uint64_t bitmap_sync_count;
+ /* these variables are used for bitmap sync */
+ /* last time we did a full bitmap_sync */
+ int64_t time_last_bitmap_sync;
+ /* bytes transferred at start_time */
+ uint64_t bytes_xfer_prev;
+ /* number of dirty pages since start_time */
+ uint64_t num_dirty_pages_period;
+ /* xbzrle misses since the beginning of the period */
+ uint64_t xbzrle_cache_miss_prev;
+ /* number of iterations at the beginning of period */
+ uint64_t iterations_prev;
+ /* Accounting fields */
+ /* number of zero pages. It used to be pages filled by the same char. */
+ uint64_t zero_pages;
+ /* number of normal transferred pages */
uint64_t norm_pages;
+ /* Iterations since start */
uint64_t iterations;
+ /* xbzrle transmitted bytes. Notice that this is with
+ * compression, they can't be calculated from the pages */
uint64_t xbzrle_bytes;
+ /* xbzrle transmmited pages */
uint64_t xbzrle_pages;
+ /* xbzrle number of cache miss */
uint64_t xbzrle_cache_miss;
+ /* xbzrle miss rate */
double xbzrle_cache_miss_rate;
+ /* xbzrle number of overflows */
uint64_t xbzrle_overflows;
-} AccountingInfo;
+ /* number of dirty bits in the bitmap */
+ uint64_t migration_dirty_pages;
+ /* total number of bytes transferred */
+ uint64_t bytes_transferred;
+ /* number of dirtied pages in the last second */
+ uint64_t dirty_pages_rate;
+ /* Count of requests incoming from destination */
+ uint64_t postcopy_requests;
+ /* protects modification of the bitmap */
+ QemuMutex bitmap_mutex;
+ /* Ram Bitmap protected by RCU */
+ RAMBitmap *ram_bitmap;
+ /* The RAMBlock used in the last src_page_requests */
+ RAMBlock *last_req_rb;
+ /* Queue of outstanding page requests from the destination */
+ QemuMutex src_page_req_mutex;
+ QSIMPLEQ_HEAD(src_page_requests, RAMSrcPageRequest) src_page_requests;
+};
+typedef struct RAMState RAMState;
-static AccountingInfo acct_info;
+static RAMState ram_state;
-static void acct_clear(void)
+uint64_t dup_mig_pages_transferred(void)
{
- memset(&acct_info, 0, sizeof(acct_info));
+ return ram_state.zero_pages;
}
-uint64_t dup_mig_bytes_transferred(void)
+uint64_t norm_mig_pages_transferred(void)
{
- return acct_info.dup_pages * TARGET_PAGE_SIZE;
+ return ram_state.norm_pages;
}
-uint64_t dup_mig_pages_transferred(void)
+uint64_t xbzrle_mig_bytes_transferred(void)
{
- return acct_info.dup_pages;
+ return ram_state.xbzrle_bytes;
}
-uint64_t skipped_mig_bytes_transferred(void)
+uint64_t xbzrle_mig_pages_transferred(void)
{
- return acct_info.skipped_pages * TARGET_PAGE_SIZE;
+ return ram_state.xbzrle_pages;
}
-uint64_t skipped_mig_pages_transferred(void)
+uint64_t xbzrle_mig_pages_cache_miss(void)
{
- return acct_info.skipped_pages;
+ return ram_state.xbzrle_cache_miss;
}
-uint64_t norm_mig_bytes_transferred(void)
+double xbzrle_mig_cache_miss_rate(void)
{
- return acct_info.norm_pages * TARGET_PAGE_SIZE;
+ return ram_state.xbzrle_cache_miss_rate;
}
-uint64_t norm_mig_pages_transferred(void)
+uint64_t xbzrle_mig_pages_overflow(void)
{
- return acct_info.norm_pages;
+ return ram_state.xbzrle_overflows;
}
-uint64_t xbzrle_mig_bytes_transferred(void)
+uint64_t ram_bytes_transferred(void)
{
- return acct_info.xbzrle_bytes;
+ return ram_state.bytes_transferred;
}
-uint64_t xbzrle_mig_pages_transferred(void)
+uint64_t ram_bytes_remaining(void)
{
- return acct_info.xbzrle_pages;
+ return ram_state.migration_dirty_pages * TARGET_PAGE_SIZE;
}
-uint64_t xbzrle_mig_pages_cache_miss(void)
+uint64_t ram_dirty_sync_count(void)
{
- return acct_info.xbzrle_cache_miss;
+ return ram_state.bitmap_sync_count;
}
-double xbzrle_mig_cache_miss_rate(void)
+uint64_t ram_dirty_pages_rate(void)
{
- return acct_info.xbzrle_cache_miss_rate;
+ return ram_state.dirty_pages_rate;
}
-uint64_t xbzrle_mig_pages_overflow(void)
+uint64_t ram_postcopy_requests(void)
{
- return acct_info.xbzrle_overflows;
+ return ram_state.postcopy_requests;
}
-/* This is the last block that we have visited serching for dirty pages
- */
-static RAMBlock *last_seen_block;
-/* This is the last block from where we have sent data */
-static RAMBlock *last_sent_block;
-static ram_addr_t last_offset;
-static QemuMutex migration_bitmap_mutex;
-static uint64_t migration_dirty_pages;
-static uint32_t last_version;
-static bool ram_bulk_stage;
-
/* used by the search for pages to send */
struct PageSearchStatus {
/* Current block being searched */
RAMBlock *block;
- /* Current offset to search from */
- ram_addr_t offset;
+ /* Current page to search from */
+ unsigned long page;
/* Set once we wrap around */
bool complete_round;
};
typedef struct PageSearchStatus PageSearchStatus;
-static struct BitmapRcu {
- struct rcu_head rcu;
- /* Main migration bitmap */
- unsigned long *bmap;
- /* bitmap of pages that haven't been sent even once
- * only maintained and used in postcopy at the moment
- * where it's used to send the dirtymap at the start
- * of the postcopy phase
- */
- unsigned long *unsentmap;
-} *migration_bitmap_rcu;
-
struct CompressParam {
bool done;
bool quit;
@@ -278,7 +336,6 @@ static QemuCond comp_done_cond;
/* The empty QEMUFileOps will be used by file in CompressParam */
static const QEMUFileOps empty_ops = { };
-static bool compression_switch;
static DecompressParam *decomp_param;
static QemuThread *decompress_threads;
static QemuMutex decomp_done_lock;
@@ -323,6 +380,7 @@ static inline void terminate_compression_threads(void)
int idx, thread_count;
thread_count = migrate_compress_threads();
+
for (idx = 0; idx < thread_count; idx++) {
qemu_mutex_lock(&comp_param[idx].mutex);
comp_param[idx].quit = true;
@@ -361,7 +419,6 @@ void migrate_compress_threads_create(void)
if (!migrate_use_compression()) {
return;
}
- compression_switch = true;
thread_count = migrate_compress_threads();
compress_threads = g_new0(QemuThread, thread_count);
comp_param = g_new0(CompressParam, thread_count);
@@ -383,38 +440,45 @@ void migrate_compress_threads_create(void)
}
/**
- * save_page_header: Write page header to wire
+ * save_page_header: write page header to wire
*
* If this is the 1st block, it also writes the block identification
*
- * Returns: Number of bytes written
+ * Returns the number of bytes written
*
* @f: QEMUFile where to send the data
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* in the lower bits, it contains flags
*/
-static size_t save_page_header(QEMUFile *f, RAMBlock *block, ram_addr_t offset)
+static size_t save_page_header(RAMState *rs, RAMBlock *block, ram_addr_t offset)
{
size_t size, len;
- qemu_put_be64(f, offset);
+ if (block == rs->last_sent_block) {
+ offset |= RAM_SAVE_FLAG_CONTINUE;
+ }
+ qemu_put_be64(rs->f, offset);
size = 8;
if (!(offset & RAM_SAVE_FLAG_CONTINUE)) {
len = strlen(block->idstr);
- qemu_put_byte(f, len);
- qemu_put_buffer(f, (uint8_t *)block->idstr, len);
+ qemu_put_byte(rs->f, len);
+ qemu_put_buffer(rs->f, (uint8_t *)block->idstr, len);
size += 1 + len;
+ rs->last_sent_block = block;
}
return size;
}
-/* Reduce amount of guest cpu execution to hopefully slow down memory writes.
- * If guest dirty memory rate is reduced below the rate at which we can
- * transfer pages to the destination then we should be able to complete
- * migration. Some workloads dirty memory way too fast and will not effectively
- * converge, even with auto-converge.
+/**
+ * mig_throttle_guest_down: throotle down the guest
+ *
+ * Reduce amount of guest cpu execution to hopefully slow down memory
+ * writes. If guest dirty memory rate is reduced below the rate at
+ * which we can transfer pages to the destination then we should be
+ * able to complete migration. Some workloads dirty memory way too
+ * fast and will not effectively converge, even with auto-converge.
*/
static void mig_throttle_guest_down(void)
{
@@ -431,22 +495,28 @@ static void mig_throttle_guest_down(void)
}
}
-/* Update the xbzrle cache to reflect a page that's been sent as all 0.
+/**
+ * xbzrle_cache_zero_page: insert a zero page in the XBZRLE cache
+ *
+ * @rs: current RAM state
+ * @current_addr: address for the zero page
+ *
+ * Update the xbzrle cache to reflect a page that's been sent as all 0.
* The important thing is that a stale (not-yet-0'd) page be replaced
* by the new data.
* As a bonus, if the page wasn't in the cache it gets added so that
- * when a small write is made into the 0'd page it gets XBZRLE sent
+ * when a small write is made into the 0'd page it gets XBZRLE sent.
*/
-static void xbzrle_cache_zero_page(ram_addr_t current_addr)
+static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr)
{
- if (ram_bulk_stage || !migrate_use_xbzrle()) {
+ if (rs->ram_bulk_stage || !migrate_use_xbzrle()) {
return;
}
/* We don't care if this fails to allocate a new cache page
* as long as it updated an old one */
cache_insert(XBZRLE.cache, current_addr, ZERO_TARGET_PAGE,
- bitmap_sync_count);
+ rs->bitmap_sync_count);
}
#define ENCODING_FLAG_XBZRLE 0x1
@@ -458,27 +528,25 @@ static void xbzrle_cache_zero_page(ram_addr_t current_addr)
* 0 means that page is identical to the one already sent
* -1 means that xbzrle would be longer than normal
*
- * @f: QEMUFile where to send the data
- * @current_data:
- * @current_addr:
+ * @rs: current RAM state
+ * @current_data: pointer to the address of the page contents
+ * @current_addr: addr of the page
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
*/
-static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
+static int save_xbzrle_page(RAMState *rs, uint8_t **current_data,
ram_addr_t current_addr, RAMBlock *block,
- ram_addr_t offset, bool last_stage,
- uint64_t *bytes_transferred)
+ ram_addr_t offset, bool last_stage)
{
int encoded_len = 0, bytes_xbzrle;
uint8_t *prev_cached_page;
- if (!cache_is_cached(XBZRLE.cache, current_addr, bitmap_sync_count)) {
- acct_info.xbzrle_cache_miss++;
+ if (!cache_is_cached(XBZRLE.cache, current_addr, rs->bitmap_sync_count)) {
+ rs->xbzrle_cache_miss++;
if (!last_stage) {
if (cache_insert(XBZRLE.cache, current_addr, *current_data,
- bitmap_sync_count) == -1) {
+ rs->bitmap_sync_count) == -1) {
return -1;
} else {
/* update *current_data when the page has been
@@ -503,7 +571,7 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
return 0;
} else if (encoded_len == -1) {
trace_save_xbzrle_page_overflow();
- acct_info.xbzrle_overflows++;
+ rs->xbzrle_overflows++;
/* update data in the cache */
if (!last_stage) {
memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE);
@@ -518,92 +586,86 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
}
/* Send XBZRLE based compressed page */
- bytes_xbzrle = save_page_header(f, block, offset | RAM_SAVE_FLAG_XBZRLE);
- qemu_put_byte(f, ENCODING_FLAG_XBZRLE);
- qemu_put_be16(f, encoded_len);
- qemu_put_buffer(f, XBZRLE.encoded_buf, encoded_len);
+ bytes_xbzrle = save_page_header(rs, block,
+ offset | RAM_SAVE_FLAG_XBZRLE);
+ qemu_put_byte(rs->f, ENCODING_FLAG_XBZRLE);
+ qemu_put_be16(rs->f, encoded_len);
+ qemu_put_buffer(rs->f, XBZRLE.encoded_buf, encoded_len);
bytes_xbzrle += encoded_len + 1 + 2;
- acct_info.xbzrle_pages++;
- acct_info.xbzrle_bytes += bytes_xbzrle;
- *bytes_transferred += bytes_xbzrle;
+ rs->xbzrle_pages++;
+ rs->xbzrle_bytes += bytes_xbzrle;
+ rs->bytes_transferred += bytes_xbzrle;
return 1;
}
-/* Called with rcu_read_lock() to protect migration_bitmap
- * rb: The RAMBlock to search for dirty pages in
- * start: Start address (typically so we can continue from previous page)
- * ram_addr_abs: Pointer into which to store the address of the dirty page
- * within the global ram_addr space
+/**
+ * migration_bitmap_find_dirty: find the next dirty page from start
+ *
+ * Called with rcu_read_lock() to protect migration_bitmap
*
- * Returns: byte offset within memory region of the start of a dirty page
+ * Returns the byte offset within memory region of the start of a dirty page
+ *
+ * @rs: current RAM state
+ * @rb: RAMBlock where to search for dirty pages
+ * @start: page where we start the search
*/
static inline
-ram_addr_t migration_bitmap_find_dirty(RAMBlock *rb,
- ram_addr_t start,
- ram_addr_t *ram_addr_abs)
+unsigned long migration_bitmap_find_dirty(RAMState *rs, RAMBlock *rb,
+ unsigned long start)
{
unsigned long base = rb->offset >> TARGET_PAGE_BITS;
- unsigned long nr = base + (start >> TARGET_PAGE_BITS);
+ unsigned long nr = base + start;
uint64_t rb_size = rb->used_length;
unsigned long size = base + (rb_size >> TARGET_PAGE_BITS);
unsigned long *bitmap;
unsigned long next;
- bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
- if (ram_bulk_stage && nr > base) {
+ bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ if (rs->ram_bulk_stage && nr > base) {
next = nr + 1;
} else {
next = find_next_bit(bitmap, size, nr);
}
- *ram_addr_abs = next << TARGET_PAGE_BITS;
- return (next - base) << TARGET_PAGE_BITS;
+ return next - base;
}
-static inline bool migration_bitmap_clear_dirty(ram_addr_t addr)
+static inline bool migration_bitmap_clear_dirty(RAMState *rs,
+ RAMBlock *rb,
+ unsigned long page)
{
bool ret;
- int nr = addr >> TARGET_PAGE_BITS;
- unsigned long *bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+ unsigned long *bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ unsigned long nr = (rb->offset >> TARGET_PAGE_BITS) + page;
ret = test_and_clear_bit(nr, bitmap);
if (ret) {
- migration_dirty_pages--;
+ rs->migration_dirty_pages--;
}
return ret;
}
-static int64_t num_dirty_pages_period;
-static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
+static void migration_bitmap_sync_range(RAMState *rs, RAMBlock *rb,
+ ram_addr_t start, ram_addr_t length)
{
unsigned long *bitmap;
- bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
- migration_dirty_pages += cpu_physical_memory_sync_dirty_bitmap(bitmap,
- start, length, &num_dirty_pages_period);
-}
-
-/* Fix me: there are too many global variables used in migration process. */
-static int64_t start_time;
-static int64_t bytes_xfer_prev;
-static uint64_t xbzrle_cache_miss_prev;
-static uint64_t iterations_prev;
-
-static void migration_bitmap_sync_init(void)
-{
- start_time = 0;
- bytes_xfer_prev = 0;
- num_dirty_pages_period = 0;
- xbzrle_cache_miss_prev = 0;
- iterations_prev = 0;
+ bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ rs->migration_dirty_pages +=
+ cpu_physical_memory_sync_dirty_bitmap(bitmap, rb, start, length,
+ &rs->num_dirty_pages_period);
}
-/* Returns a summary bitmap of the page sizes of all RAMBlocks;
- * for VMs with just normal pages this is equivalent to the
- * host page size. If it's got some huge pages then it's the OR
- * of all the different page sizes.
+/**
+ * ram_pagesize_summary: calculate all the pagesizes of a VM
+ *
+ * Returns a summary bitmap of the page sizes of all RAMBlocks
+ *
+ * For VMs with just normal pages this is equivalent to the host page
+ * size. If it's got some huge pages then it's the OR of all the
+ * different page sizes.
*/
uint64_t ram_pagesize_summary(void)
{
@@ -617,40 +679,39 @@ uint64_t ram_pagesize_summary(void)
return summary;
}
-static void migration_bitmap_sync(void)
+static void migration_bitmap_sync(RAMState *rs)
{
RAMBlock *block;
- MigrationState *s = migrate_get_current();
int64_t end_time;
- int64_t bytes_xfer_now;
+ uint64_t bytes_xfer_now;
- bitmap_sync_count++;
+ rs->bitmap_sync_count++;
- if (!bytes_xfer_prev) {
- bytes_xfer_prev = ram_bytes_transferred();
+ if (!rs->bytes_xfer_prev) {
+ rs->bytes_xfer_prev = ram_bytes_transferred();
}
- if (!start_time) {
- start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
+ if (!rs->time_last_bitmap_sync) {
+ rs->time_last_bitmap_sync = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
}
trace_migration_bitmap_sync_start();
memory_global_dirty_log_sync();
- qemu_mutex_lock(&migration_bitmap_mutex);
+ qemu_mutex_lock(&rs->bitmap_mutex);
rcu_read_lock();
QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
- migration_bitmap_sync_range(block->offset, block->used_length);
+ migration_bitmap_sync_range(rs, block, 0, block->used_length);
}
rcu_read_unlock();
- qemu_mutex_unlock(&migration_bitmap_mutex);
+ qemu_mutex_unlock(&rs->bitmap_mutex);
- trace_migration_bitmap_sync_end(num_dirty_pages_period);
+ trace_migration_bitmap_sync_end(rs->num_dirty_pages_period);
end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
/* more than 1 second = 1000 millisecons */
- if (end_time > start_time + 1000) {
+ if (end_time > rs->time_last_bitmap_sync + 1000) {
if (migrate_auto_converge()) {
/* The following detection logic can be refined later. For now:
Check to see if the dirtied bytes is 50% more than the approx.
@@ -659,94 +720,87 @@ static void migration_bitmap_sync(void)
throttling */
bytes_xfer_now = ram_bytes_transferred();
- if (s->dirty_pages_rate &&
- (num_dirty_pages_period * TARGET_PAGE_SIZE >
- (bytes_xfer_now - bytes_xfer_prev)/2) &&
- (dirty_rate_high_cnt++ >= 2)) {
+ if (rs->dirty_pages_rate &&
+ (rs->num_dirty_pages_period * TARGET_PAGE_SIZE >
+ (bytes_xfer_now - rs->bytes_xfer_prev) / 2) &&
+ (rs->dirty_rate_high_cnt++ >= 2)) {
trace_migration_throttle();
- dirty_rate_high_cnt = 0;
+ rs->dirty_rate_high_cnt = 0;
mig_throttle_guest_down();
}
- bytes_xfer_prev = bytes_xfer_now;
+ rs->bytes_xfer_prev = bytes_xfer_now;
}
if (migrate_use_xbzrle()) {
- if (iterations_prev != acct_info.iterations) {
- acct_info.xbzrle_cache_miss_rate =
- (double)(acct_info.xbzrle_cache_miss -
- xbzrle_cache_miss_prev) /
- (acct_info.iterations - iterations_prev);
+ if (rs->iterations_prev != rs->iterations) {
+ rs->xbzrle_cache_miss_rate =
+ (double)(rs->xbzrle_cache_miss -
+ rs->xbzrle_cache_miss_prev) /
+ (rs->iterations - rs->iterations_prev);
}
- iterations_prev = acct_info.iterations;
- xbzrle_cache_miss_prev = acct_info.xbzrle_cache_miss;
+ rs->iterations_prev = rs->iterations;
+ rs->xbzrle_cache_miss_prev = rs->xbzrle_cache_miss;
}
- s->dirty_pages_rate = num_dirty_pages_period * 1000
- / (end_time - start_time);
- s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
- start_time = end_time;
- num_dirty_pages_period = 0;
+ rs->dirty_pages_rate = rs->num_dirty_pages_period * 1000
+ / (end_time - rs->time_last_bitmap_sync);
+ rs->time_last_bitmap_sync = end_time;
+ rs->num_dirty_pages_period = 0;
}
- s->dirty_sync_count = bitmap_sync_count;
if (migrate_use_events()) {
- qapi_event_send_migration_pass(bitmap_sync_count, NULL);
+ qapi_event_send_migration_pass(rs->bitmap_sync_count, NULL);
}
}
/**
- * save_zero_page: Send the zero page to the stream
+ * save_zero_page: send the zero page to the stream
*
- * Returns: Number of pages written.
+ * Returns the number of pages written.
*
- * @f: QEMUFile where to send the data
+ * @rs: current RAM state
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* @p: pointer to the page
- * @bytes_transferred: increase it with the number of transferred bytes
*/
-static int save_zero_page(QEMUFile *f, RAMBlock *block, ram_addr_t offset,
- uint8_t *p, uint64_t *bytes_transferred)
+static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset,
+ uint8_t *p)
{
int pages = -1;
if (is_zero_range(p, TARGET_PAGE_SIZE)) {
- acct_info.dup_pages++;
- *bytes_transferred += save_page_header(f, block,
- offset | RAM_SAVE_FLAG_COMPRESS);
- qemu_put_byte(f, 0);
- *bytes_transferred += 1;
+ rs->zero_pages++;
+ rs->bytes_transferred +=
+ save_page_header(rs, block, offset | RAM_SAVE_FLAG_COMPRESS);
+ qemu_put_byte(rs->f, 0);
+ rs->bytes_transferred += 1;
pages = 1;
}
return pages;
}
-static void ram_release_pages(MigrationState *ms, const char *block_name,
- uint64_t offset, int pages)
+static void ram_release_pages(const char *rbname, uint64_t offset, int pages)
{
- if (!migrate_release_ram() || !migration_in_postcopy(ms)) {
+ if (!migrate_release_ram() || !migration_in_postcopy()) {
return;
}
- ram_discard_range(NULL, block_name, offset, pages << TARGET_PAGE_BITS);
+ ram_discard_range(rbname, offset, pages << TARGET_PAGE_BITS);
}
/**
- * ram_save_page: Send the given page to the stream
+ * ram_save_page: send the given page to the stream
*
- * Returns: Number of pages written.
+ * Returns the number of pages written.
* < 0 - error
* >=0 - Number of pages written - this might legally be 0
* if xbzrle noticed the page was the same.
*
- * @ms: The current migration state.
- * @f: QEMUFile where to send the data
+ * @rs: current RAM state
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
*/
-static int ram_save_page(MigrationState *ms, QEMUFile *f, PageSearchStatus *pss,
- bool last_stage, uint64_t *bytes_transferred)
+static int ram_save_page(RAMState *rs, PageSearchStatus *pss, bool last_stage)
{
int pages = -1;
uint64_t bytes_xmit;
@@ -755,16 +809,16 @@ static int ram_save_page(MigrationState *ms, QEMUFile *f, PageSearchStatus *pss,
int ret;
bool send_async = true;
RAMBlock *block = pss->block;
- ram_addr_t offset = pss->offset;
+ ram_addr_t offset = pss->page << TARGET_PAGE_BITS;
p = block->host + offset;
/* In doubt sent page as normal */
bytes_xmit = 0;
- ret = ram_control_save_page(f, block->offset,
+ ret = ram_control_save_page(rs->f, block->offset,
offset, TARGET_PAGE_SIZE, &bytes_xmit);
if (bytes_xmit) {
- *bytes_transferred += bytes_xmit;
+ rs->bytes_transferred += bytes_xmit;
pages = 1;
}
@@ -772,29 +826,26 @@ static int ram_save_page(MigrationState *ms, QEMUFile *f, PageSearchStatus *pss,
current_addr = block->offset + offset;
- if (block == last_sent_block) {
- offset |= RAM_SAVE_FLAG_CONTINUE;
- }
if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret != RAM_SAVE_CONTROL_DELAYED) {
if (bytes_xmit > 0) {
- acct_info.norm_pages++;
+ rs->norm_pages++;
} else if (bytes_xmit == 0) {
- acct_info.dup_pages++;
+ rs->zero_pages++;
}
}
} else {
- pages = save_zero_page(f, block, offset, p, bytes_transferred);
+ pages = save_zero_page(rs, block, offset, p);
if (pages > 0) {
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
*/
- xbzrle_cache_zero_page(current_addr);
- ram_release_pages(ms, block->idstr, pss->offset, pages);
- } else if (!ram_bulk_stage &&
- !migration_in_postcopy(ms) && migrate_use_xbzrle()) {
- pages = save_xbzrle_page(f, &p, current_addr, block,
- offset, last_stage, bytes_transferred);
+ xbzrle_cache_zero_page(rs, current_addr);
+ ram_release_pages(block->idstr, offset, pages);
+ } else if (!rs->ram_bulk_stage &&
+ !migration_in_postcopy() && migrate_use_xbzrle()) {
+ pages = save_xbzrle_page(rs, &p, current_addr, block,
+ offset, last_stage);
if (!last_stage) {
/* Can't send this cached data async, since the cache page
* might get updated before it gets to the wire
@@ -806,18 +857,18 @@ static int ram_save_page(MigrationState *ms, QEMUFile *f, PageSearchStatus *pss,
/* XBZRLE overflow or normal page */
if (pages == -1) {
- *bytes_transferred += save_page_header(f, block,
- offset | RAM_SAVE_FLAG_PAGE);
+ rs->bytes_transferred += save_page_header(rs, block,
+ offset | RAM_SAVE_FLAG_PAGE);
if (send_async) {
- qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE,
+ qemu_put_buffer_async(rs->f, p, TARGET_PAGE_SIZE,
migrate_release_ram() &
- migration_in_postcopy(ms));
+ migration_in_postcopy());
} else {
- qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
+ qemu_put_buffer(rs->f, p, TARGET_PAGE_SIZE);
}
- *bytes_transferred += TARGET_PAGE_SIZE;
+ rs->bytes_transferred += TARGET_PAGE_SIZE;
pages = 1;
- acct_info.norm_pages++;
+ rs->norm_pages++;
}
XBZRLE_cache_unlock();
@@ -828,10 +879,11 @@ static int ram_save_page(MigrationState *ms, QEMUFile *f, PageSearchStatus *pss,
static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
ram_addr_t offset)
{
+ RAMState *rs = &ram_state;
int bytes_sent, blen;
uint8_t *p = block->host + (offset & TARGET_PAGE_MASK);
- bytes_sent = save_page_header(f, block, offset |
+ bytes_sent = save_page_header(rs, block, offset |
RAM_SAVE_FLAG_COMPRESS_PAGE);
blen = qemu_put_compression_data(f, p, TARGET_PAGE_SIZE,
migrate_compress_level());
@@ -841,16 +893,13 @@ static int do_compress_ram_page(QEMUFile *f, RAMBlock *block,
error_report("compressed data failed!");
} else {
bytes_sent += blen;
- ram_release_pages(migrate_get_current(), block->idstr,
- offset & TARGET_PAGE_MASK, 1);
+ ram_release_pages(block->idstr, offset & TARGET_PAGE_MASK, 1);
}
return bytes_sent;
}
-static uint64_t bytes_transferred;
-
-static void flush_compressed_data(QEMUFile *f)
+static void flush_compressed_data(RAMState *rs)
{
int idx, len, thread_count;
@@ -870,8 +919,8 @@ static void flush_compressed_data(QEMUFile *f)
for (idx = 0; idx < thread_count; idx++) {
qemu_mutex_lock(&comp_param[idx].mutex);
if (!comp_param[idx].quit) {
- len = qemu_put_qemu_file(f, comp_param[idx].file);
- bytes_transferred += len;
+ len = qemu_put_qemu_file(rs->f, comp_param[idx].file);
+ rs->bytes_transferred += len;
}
qemu_mutex_unlock(&comp_param[idx].mutex);
}
@@ -884,9 +933,8 @@ static inline void set_compress_params(CompressParam *param, RAMBlock *block,
param->offset = offset;
}
-static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block,
- ram_addr_t offset,
- uint64_t *bytes_transferred)
+static int compress_page_with_multi_thread(RAMState *rs, RAMBlock *block,
+ ram_addr_t offset)
{
int idx, thread_count, bytes_xmit = -1, pages = -1;
@@ -896,14 +944,14 @@ static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block,
for (idx = 0; idx < thread_count; idx++) {
if (comp_param[idx].done) {
comp_param[idx].done = false;
- bytes_xmit = qemu_put_qemu_file(f, comp_param[idx].file);
+ bytes_xmit = qemu_put_qemu_file(rs->f, comp_param[idx].file);
qemu_mutex_lock(&comp_param[idx].mutex);
set_compress_params(&comp_param[idx], block, offset);
qemu_cond_signal(&comp_param[idx].cond);
qemu_mutex_unlock(&comp_param[idx].mutex);
pages = 1;
- acct_info.norm_pages++;
- *bytes_transferred += bytes_xmit;
+ rs->norm_pages++;
+ rs->bytes_transferred += bytes_xmit;
break;
}
}
@@ -921,40 +969,37 @@ static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block,
/**
* ram_save_compressed_page: compress the given page and send it to the stream
*
- * Returns: Number of pages written.
+ * Returns the number of pages written.
*
- * @ms: The current migration state.
- * @f: QEMUFile where to send the data
+ * @rs: current RAM state
* @block: block that contains the page we want to send
* @offset: offset inside the block for the page
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
*/
-static int ram_save_compressed_page(MigrationState *ms, QEMUFile *f,
- PageSearchStatus *pss, bool last_stage,
- uint64_t *bytes_transferred)
+static int ram_save_compressed_page(RAMState *rs, PageSearchStatus *pss,
+ bool last_stage)
{
int pages = -1;
uint64_t bytes_xmit = 0;
uint8_t *p;
int ret, blen;
RAMBlock *block = pss->block;
- ram_addr_t offset = pss->offset;
+ ram_addr_t offset = pss->page << TARGET_PAGE_BITS;
p = block->host + offset;
- ret = ram_control_save_page(f, block->offset,
+ ret = ram_control_save_page(rs->f, block->offset,
offset, TARGET_PAGE_SIZE, &bytes_xmit);
if (bytes_xmit) {
- *bytes_transferred += bytes_xmit;
+ rs->bytes_transferred += bytes_xmit;
pages = 1;
}
if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret != RAM_SAVE_CONTROL_DELAYED) {
if (bytes_xmit > 0) {
- acct_info.norm_pages++;
+ rs->norm_pages++;
} else if (bytes_xmit == 0) {
- acct_info.dup_pages++;
+ rs->zero_pages++;
}
}
} else {
@@ -964,35 +1009,33 @@ static int ram_save_compressed_page(MigrationState *ms, QEMUFile *f,
* out, keeping this order is important, because the 'cont' flag
* is used to avoid resending the block name.
*/
- if (block != last_sent_block) {
- flush_compressed_data(f);
- pages = save_zero_page(f, block, offset, p, bytes_transferred);
+ if (block != rs->last_sent_block) {
+ flush_compressed_data(rs);
+ pages = save_zero_page(rs, block, offset, p);
if (pages == -1) {
/* Make sure the first page is sent out before other pages */
- bytes_xmit = save_page_header(f, block, offset |
+ bytes_xmit = save_page_header(rs, block, offset |
RAM_SAVE_FLAG_COMPRESS_PAGE);
- blen = qemu_put_compression_data(f, p, TARGET_PAGE_SIZE,
+ blen = qemu_put_compression_data(rs->f, p, TARGET_PAGE_SIZE,
migrate_compress_level());
if (blen > 0) {
- *bytes_transferred += bytes_xmit + blen;
- acct_info.norm_pages++;
+ rs->bytes_transferred += bytes_xmit + blen;
+ rs->norm_pages++;
pages = 1;
} else {
- qemu_file_set_error(f, blen);
+ qemu_file_set_error(rs->f, blen);
error_report("compressed data failed!");
}
}
if (pages > 0) {
- ram_release_pages(ms, block->idstr, pss->offset, pages);
+ ram_release_pages(block->idstr, offset, pages);
}
} else {
- offset |= RAM_SAVE_FLAG_CONTINUE;
- pages = save_zero_page(f, block, offset, p, bytes_transferred);
+ pages = save_zero_page(rs, block, offset, p);
if (pages == -1) {
- pages = compress_page_with_multi_thread(f, block, offset,
- bytes_transferred);
+ pages = compress_page_with_multi_thread(rs, block, offset);
} else {
- ram_release_pages(ms, block->idstr, pss->offset, pages);
+ ram_release_pages(block->idstr, offset, pages);
}
}
}
@@ -1000,25 +1043,21 @@ static int ram_save_compressed_page(MigrationState *ms, QEMUFile *f,
return pages;
}
-/*
- * Find the next dirty page and update any state associated with
- * the search process.
+/**
+ * find_dirty_block: find the next dirty page and update any state
+ * associated with the search process.
*
- * Returns: True if a page is found
+ * Returns if a page is found
*
- * @f: Current migration stream.
- * @pss: Data about the state of the current dirty page scan.
- * @*again: Set to false if the search has scanned the whole of RAM
- * *ram_addr_abs: Pointer into which to store the address of the dirty page
- * within the global ram_addr space
+ * @rs: current RAM state
+ * @pss: data about the state of the current dirty page scan
+ * @again: set to false if the search has scanned the whole of RAM
*/
-static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss,
- bool *again, ram_addr_t *ram_addr_abs)
+static bool find_dirty_block(RAMState *rs, PageSearchStatus *pss, bool *again)
{
- pss->offset = migration_bitmap_find_dirty(pss->block, pss->offset,
- ram_addr_abs);
- if (pss->complete_round && pss->block == last_seen_block &&
- pss->offset >= last_offset) {
+ pss->page = migration_bitmap_find_dirty(rs, pss->block, pss->page);
+ if (pss->complete_round && pss->block == rs->last_seen_block &&
+ pss->page >= rs->last_page) {
/*
* We've been once around the RAM and haven't found anything.
* Give up.
@@ -1026,22 +1065,21 @@ static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss,
*again = false;
return false;
}
- if (pss->offset >= pss->block->used_length) {
+ if ((pss->page << TARGET_PAGE_BITS) >= pss->block->used_length) {
/* Didn't find anything in this RAM Block */
- pss->offset = 0;
+ pss->page = 0;
pss->block = QLIST_NEXT_RCU(pss->block, next);
if (!pss->block) {
/* Hit the end of the list */
pss->block = QLIST_FIRST_RCU(&ram_list.blocks);
/* Flag that we've looped */
pss->complete_round = true;
- ram_bulk_stage = false;
+ rs->ram_bulk_stage = false;
if (migrate_use_xbzrle()) {
/* If xbzrle is on, stop using the data compression at this
* point. In theory, xbzrle can do better than compression.
*/
- flush_compressed_data(f);
- compression_switch = false;
+ flush_compressed_data(rs);
}
}
/* Didn't find anything this time, but try again on the new block */
@@ -1055,61 +1093,59 @@ static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss,
}
}
-/*
+/**
+ * unqueue_page: gets a page of the queue
+ *
* Helper for 'get_queued_page' - gets a page off the queue
- * ms: MigrationState in
- * *offset: Used to return the offset within the RAMBlock
- * ram_addr_abs: global offset in the dirty/sent bitmaps
*
- * Returns: block (or NULL if none available)
+ * Returns the block of the page (or NULL if none available)
+ *
+ * @rs: current RAM state
+ * @offset: used to return the offset within the RAMBlock
*/
-static RAMBlock *unqueue_page(MigrationState *ms, ram_addr_t *offset,
- ram_addr_t *ram_addr_abs)
+static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
{
RAMBlock *block = NULL;
- qemu_mutex_lock(&ms->src_page_req_mutex);
- if (!QSIMPLEQ_EMPTY(&ms->src_page_requests)) {
- struct MigrationSrcPageRequest *entry =
- QSIMPLEQ_FIRST(&ms->src_page_requests);
+ qemu_mutex_lock(&rs->src_page_req_mutex);
+ if (!QSIMPLEQ_EMPTY(&rs->src_page_requests)) {
+ struct RAMSrcPageRequest *entry =
+ QSIMPLEQ_FIRST(&rs->src_page_requests);
block = entry->rb;
*offset = entry->offset;
- *ram_addr_abs = (entry->offset + entry->rb->offset) &
- TARGET_PAGE_MASK;
if (entry->len > TARGET_PAGE_SIZE) {
entry->len -= TARGET_PAGE_SIZE;
entry->offset += TARGET_PAGE_SIZE;
} else {
memory_region_unref(block->mr);
- QSIMPLEQ_REMOVE_HEAD(&ms->src_page_requests, next_req);
+ QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
g_free(entry);
}
}
- qemu_mutex_unlock(&ms->src_page_req_mutex);
+ qemu_mutex_unlock(&rs->src_page_req_mutex);
return block;
}
-/*
- * Unqueue a page from the queue fed by postcopy page requests; skips pages
- * that are already sent (!dirty)
+/**
+ * get_queued_page: unqueue a page from the postocpy requests
+ *
+ * Skips pages that are already sent (!dirty)
*
- * ms: MigrationState in
- * pss: PageSearchStatus structure updated with found block/offset
- * ram_addr_abs: global offset in the dirty/sent bitmaps
+ * Returns if a queued page is found
*
- * Returns: true if a queued page is found
+ * @rs: current RAM state
+ * @pss: data about the state of the current dirty page scan
*/
-static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss,
- ram_addr_t *ram_addr_abs)
+static bool get_queued_page(RAMState *rs, PageSearchStatus *pss)
{
RAMBlock *block;
ram_addr_t offset;
bool dirty;
do {
- block = unqueue_page(ms, &offset, ram_addr_abs);
+ block = unqueue_page(rs, &offset);
/*
* We're sending this page, and since it's postcopy nothing else
* will dirty it, and we must make sure it doesn't get sent again
@@ -1118,18 +1154,18 @@ static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss,
*/
if (block) {
unsigned long *bitmap;
- bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
- dirty = test_bit(*ram_addr_abs >> TARGET_PAGE_BITS, bitmap);
+ unsigned long page;
+
+ bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ page = (block->offset + offset) >> TARGET_PAGE_BITS;
+ dirty = test_bit(page, bitmap);
if (!dirty) {
- trace_get_queued_page_not_dirty(
- block->idstr, (uint64_t)offset,
- (uint64_t)*ram_addr_abs,
- test_bit(*ram_addr_abs >> TARGET_PAGE_BITS,
- atomic_rcu_read(&migration_bitmap_rcu)->unsentmap));
+ trace_get_queued_page_not_dirty(block->idstr, (uint64_t)offset,
+ page,
+ test_bit(page,
+ atomic_rcu_read(&rs->ram_bitmap)->unsentmap));
} else {
- trace_get_queued_page(block->idstr,
- (uint64_t)offset,
- (uint64_t)*ram_addr_abs);
+ trace_get_queued_page(block->idstr, (uint64_t)offset, page);
}
}
@@ -1142,7 +1178,7 @@ static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss,
* in (migration_bitmap_find_and_reset_dirty) that every page is
* dirty, that's no longer true.
*/
- ram_bulk_stage = false;
+ rs->ram_bulk_stage = false;
/*
* We want the background search to continue from the queued page
@@ -1150,52 +1186,58 @@ static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss,
* it just requested.
*/
pss->block = block;
- pss->offset = offset;
+ pss->page = offset >> TARGET_PAGE_BITS;
}
return !!block;
}
/**
- * flush_page_queue: Flush any remaining pages in the ram request queue
- * it should be empty at the end anyway, but in error cases there may be
- * some left.
+ * migration_page_queue_free: drop any remaining pages in the ram
+ * request queue
+ *
+ * It should be empty at the end anyway, but in error cases there may
+ * be some left. in case that there is any page left, we drop it.
*
- * ms: MigrationState
*/
-void flush_page_queue(MigrationState *ms)
+void migration_page_queue_free(void)
{
- struct MigrationSrcPageRequest *mspr, *next_mspr;
+ struct RAMSrcPageRequest *mspr, *next_mspr;
+ RAMState *rs = &ram_state;
/* This queue generally should be empty - but in the case of a failed
* migration might have some droppings in.
*/
rcu_read_lock();
- QSIMPLEQ_FOREACH_SAFE(mspr, &ms->src_page_requests, next_req, next_mspr) {
+ QSIMPLEQ_FOREACH_SAFE(mspr, &rs->src_page_requests, next_req, next_mspr) {
memory_region_unref(mspr->rb->mr);
- QSIMPLEQ_REMOVE_HEAD(&ms->src_page_requests, next_req);
+ QSIMPLEQ_REMOVE_HEAD(&rs->src_page_requests, next_req);
g_free(mspr);
}
rcu_read_unlock();
}
/**
- * Queue the pages for transmission, e.g. a request from postcopy destination
- * ms: MigrationStatus in which the queue is held
- * rbname: The RAMBlock the request is for - may be NULL (to mean reuse last)
- * start: Offset from the start of the RAMBlock
- * len: Length (in bytes) to send
- * Return: 0 on success
+ * ram_save_queue_pages: queue the page for transmission
+ *
+ * A request from postcopy destination for example.
+ *
+ * Returns zero on success or negative on error
+ *
+ * @rbname: Name of the RAMBLock of the request. NULL means the
+ * same that last one.
+ * @start: starting address from the start of the RAMBlock
+ * @len: length (in bytes) to send
*/
-int ram_save_queue_pages(MigrationState *ms, const char *rbname,
- ram_addr_t start, ram_addr_t len)
+int ram_save_queue_pages(const char *rbname, ram_addr_t start, ram_addr_t len)
{
RAMBlock *ramblock;
+ RAMState *rs = &ram_state;
- ms->postcopy_requests++;
+ rs->postcopy_requests++;
rcu_read_lock();
if (!rbname) {
/* Reuse last RAMBlock */
- ramblock = ms->last_req_rb;
+ ramblock = rs->last_req_rb;
if (!ramblock) {
/*
@@ -1213,7 +1255,7 @@ int ram_save_queue_pages(MigrationState *ms, const char *rbname,
error_report("ram_save_queue_pages no block '%s'", rbname);
goto err;
}
- ms->last_req_rb = ramblock;
+ rs->last_req_rb = ramblock;
}
trace_ram_save_queue_pages(ramblock->idstr, start, len);
if (start+len > ramblock->used_length) {
@@ -1223,16 +1265,16 @@ int ram_save_queue_pages(MigrationState *ms, const char *rbname,
goto err;
}
- struct MigrationSrcPageRequest *new_entry =
- g_malloc0(sizeof(struct MigrationSrcPageRequest));
+ struct RAMSrcPageRequest *new_entry =
+ g_malloc0(sizeof(struct RAMSrcPageRequest));
new_entry->rb = ramblock;
new_entry->offset = start;
new_entry->len = len;
memory_region_ref(ramblock->mr);
- qemu_mutex_lock(&ms->src_page_req_mutex);
- QSIMPLEQ_INSERT_TAIL(&ms->src_page_requests, new_entry, next_req);
- qemu_mutex_unlock(&ms->src_page_req_mutex);
+ qemu_mutex_lock(&rs->src_page_req_mutex);
+ QSIMPLEQ_INSERT_TAIL(&rs->src_page_requests, new_entry, next_req);
+ qemu_mutex_unlock(&rs->src_page_req_mutex);
rcu_read_unlock();
return 0;
@@ -1243,51 +1285,43 @@ err:
}
/**
- * ram_save_target_page: Save one target page
+ * ram_save_target_page: save one target page
*
+ * Returns the number of pages written
*
- * @f: QEMUFile where to send the data
- * @block: pointer to block that contains the page we want to send
- * @offset: offset inside the block for the page;
+ * @rs: current RAM state
+ * @ms: current migration state
+ * @pss: data about the page we want to send
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
- * @dirty_ram_abs: Address of the start of the dirty page in ram_addr_t space
- *
- * Returns: Number of pages written.
*/
-static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
- PageSearchStatus *pss,
- bool last_stage,
- uint64_t *bytes_transferred,
- ram_addr_t dirty_ram_abs)
+static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss,
+ bool last_stage)
{
int res = 0;
/* Check the pages is dirty and if it is send it */
- if (migration_bitmap_clear_dirty(dirty_ram_abs)) {
+ if (migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
unsigned long *unsentmap;
- if (compression_switch && migrate_use_compression()) {
- res = ram_save_compressed_page(ms, f, pss,
- last_stage,
- bytes_transferred);
+ /*
+ * If xbzrle is on, stop using the data compression after first
+ * round of migration even if compression is enabled. In theory,
+ * xbzrle can do better than compression.
+ */
+ unsigned long page =
+ (pss->block->offset >> TARGET_PAGE_BITS) + pss->page;
+ if (migrate_use_compression()
+ && (rs->ram_bulk_stage || !migrate_use_xbzrle())) {
+ res = ram_save_compressed_page(rs, pss, last_stage);
} else {
- res = ram_save_page(ms, f, pss, last_stage,
- bytes_transferred);
+ res = ram_save_page(rs, pss, last_stage);
}
if (res < 0) {
return res;
}
- unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+ unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap;
if (unsentmap) {
- clear_bit(dirty_ram_abs >> TARGET_PAGE_BITS, unsentmap);
- }
- /* Only update last_sent_block if a block was actually sent; xbzrle
- * might have decided the page was identical so didn't bother writing
- * to the stream.
- */
- if (res > 0) {
- last_sent_block = pss->block;
+ clear_bit(page, unsentmap);
}
}
@@ -1295,83 +1329,70 @@ static int ram_save_target_page(MigrationState *ms, QEMUFile *f,
}
/**
- * ram_save_host_page: Starting at *offset send pages up to the end
- * of the current host page. It's valid for the initial
- * offset to point into the middle of a host page
- * in which case the remainder of the hostpage is sent.
- * Only dirty target pages are sent.
- * Note that the host page size may be a huge page for this
- * block.
+ * ram_save_host_page: save a whole host page
*
- * Returns: Number of pages written.
+ * Starting at *offset send pages up to the end of the current host
+ * page. It's valid for the initial offset to point into the middle of
+ * a host page in which case the remainder of the hostpage is sent.
+ * Only dirty target pages are sent. Note that the host page size may
+ * be a huge page for this block.
*
- * @f: QEMUFile where to send the data
- * @block: pointer to block that contains the page we want to send
- * @offset: offset inside the block for the page; updated to last target page
- * sent
+ * Returns the number of pages written or negative on error
+ *
+ * @rs: current RAM state
+ * @ms: current migration state
+ * @pss: data about the page we want to send
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
- * @dirty_ram_abs: Address of the start of the dirty page in ram_addr_t space
*/
-static int ram_save_host_page(MigrationState *ms, QEMUFile *f,
- PageSearchStatus *pss,
- bool last_stage,
- uint64_t *bytes_transferred,
- ram_addr_t dirty_ram_abs)
+static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
+ bool last_stage)
{
int tmppages, pages = 0;
- size_t pagesize = qemu_ram_pagesize(pss->block);
+ size_t pagesize_bits =
+ qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
do {
- tmppages = ram_save_target_page(ms, f, pss, last_stage,
- bytes_transferred, dirty_ram_abs);
+ tmppages = ram_save_target_page(rs, pss, last_stage);
if (tmppages < 0) {
return tmppages;
}
pages += tmppages;
- pss->offset += TARGET_PAGE_SIZE;
- dirty_ram_abs += TARGET_PAGE_SIZE;
- } while (pss->offset & (pagesize - 1));
+ pss->page++;
+ } while (pss->page & (pagesize_bits - 1));
/* The offset we leave with is the last one we looked at */
- pss->offset -= TARGET_PAGE_SIZE;
+ pss->page--;
return pages;
}
/**
- * ram_find_and_save_block: Finds a dirty page and sends it to f
+ * ram_find_and_save_block: finds a dirty page and sends it to f
*
* Called within an RCU critical section.
*
- * Returns: The number of pages written
- * 0 means no dirty pages
+ * Returns the number of pages written where zero means no dirty pages
*
- * @f: QEMUFile where to send the data
+ * @rs: current RAM state
* @last_stage: if we are at the completion stage
- * @bytes_transferred: increase it with the number of transferred bytes
*
* On systems where host-page-size > target-page-size it will send all the
* pages in a host page that are dirty.
*/
-static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
- uint64_t *bytes_transferred)
+static int ram_find_and_save_block(RAMState *rs, bool last_stage)
{
PageSearchStatus pss;
- MigrationState *ms = migrate_get_current();
int pages = 0;
bool again, found;
- ram_addr_t dirty_ram_abs; /* Address of the start of the dirty page in
- ram_addr_t space */
/* No dirty page as there is zero RAM */
if (!ram_bytes_total()) {
return pages;
}
- pss.block = last_seen_block;
- pss.offset = last_offset;
+ pss.block = rs->last_seen_block;
+ pss.page = rs->last_page;
pss.complete_round = false;
if (!pss.block) {
@@ -1380,22 +1401,20 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
do {
again = true;
- found = get_queued_page(ms, &pss, &dirty_ram_abs);
+ found = get_queued_page(rs, &pss);
if (!found) {
/* priority queue empty, so just search for something dirty */
- found = find_dirty_block(f, &pss, &again, &dirty_ram_abs);
+ found = find_dirty_block(rs, &pss, &again);
}
if (found) {
- pages = ram_save_host_page(ms, f, &pss,
- last_stage, bytes_transferred,
- dirty_ram_abs);
+ pages = ram_save_host_page(rs, &pss, last_stage);
}
} while (!pages && again);
- last_seen_block = pss.block;
- last_offset = pss.offset;
+ rs->last_seen_block = pss.block;
+ rs->last_page = pss.page;
return pages;
}
@@ -1403,30 +1422,17 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage,
void acct_update_position(QEMUFile *f, size_t size, bool zero)
{
uint64_t pages = size / TARGET_PAGE_SIZE;
+ RAMState *rs = &ram_state;
+
if (zero) {
- acct_info.dup_pages += pages;
+ rs->zero_pages += pages;
} else {
- acct_info.norm_pages += pages;
- bytes_transferred += size;
+ rs->norm_pages += pages;
+ rs->bytes_transferred += size;
qemu_update_position(f, size);
}
}
-static ram_addr_t ram_save_remaining(void)
-{
- return migration_dirty_pages;
-}
-
-uint64_t ram_bytes_remaining(void)
-{
- return ram_save_remaining() * TARGET_PAGE_SIZE;
-}
-
-uint64_t ram_bytes_transferred(void)
-{
- return bytes_transferred;
-}
-
uint64_t ram_bytes_total(void)
{
RAMBlock *block;
@@ -1445,7 +1451,7 @@ void free_xbzrle_decoded_buf(void)
xbzrle_decoded_buf = NULL;
}
-static void migration_bitmap_free(struct BitmapRcu *bmap)
+static void migration_bitmap_free(RAMBitmap *bmap)
{
g_free(bmap->bmap);
g_free(bmap->unsentmap);
@@ -1454,11 +1460,13 @@ static void migration_bitmap_free(struct BitmapRcu *bmap)
static void ram_migration_cleanup(void *opaque)
{
+ RAMState *rs = opaque;
+
/* caller have hold iothread lock or is in a bh, so there is
* no writing race against this migration_bitmap
*/
- struct BitmapRcu *bitmap = migration_bitmap_rcu;
- atomic_rcu_set(&migration_bitmap_rcu, NULL);
+ RAMBitmap *bitmap = rs->ram_bitmap;
+ atomic_rcu_set(&rs->ram_bitmap, NULL);
if (bitmap) {
memory_global_dirty_log_stop();
call_rcu(bitmap, migration_bitmap_free, rcu);
@@ -1477,49 +1485,17 @@ static void ram_migration_cleanup(void *opaque)
XBZRLE_cache_unlock();
}
-static void reset_ram_globals(void)
+static void ram_state_reset(RAMState *rs)
{
- last_seen_block = NULL;
- last_sent_block = NULL;
- last_offset = 0;
- last_version = ram_list.version;
- ram_bulk_stage = true;
+ rs->last_seen_block = NULL;
+ rs->last_sent_block = NULL;
+ rs->last_page = 0;
+ rs->last_version = ram_list.version;
+ rs->ram_bulk_stage = true;
}
#define MAX_WAIT 50 /* ms, half buffered_file limit */
-void migration_bitmap_extend(ram_addr_t old, ram_addr_t new)
-{
- /* called in qemu main thread, so there is
- * no writing race against this migration_bitmap
- */
- if (migration_bitmap_rcu) {
- struct BitmapRcu *old_bitmap = migration_bitmap_rcu, *bitmap;
- bitmap = g_new(struct BitmapRcu, 1);
- bitmap->bmap = bitmap_new(new);
-
- /* prevent migration_bitmap content from being set bit
- * by migration_bitmap_sync_range() at the same time.
- * it is safe to migration if migration_bitmap is cleared bit
- * at the same time.
- */
- qemu_mutex_lock(&migration_bitmap_mutex);
- bitmap_copy(bitmap->bmap, old_bitmap->bmap, old);
- bitmap_set(bitmap->bmap, old, new - old);
-
- /* We don't have a way to safely extend the sentmap
- * with RCU; so mark it as missing, entry to postcopy
- * will fail.
- */
- bitmap->unsentmap = NULL;
-
- atomic_rcu_set(&migration_bitmap_rcu, bitmap);
- qemu_mutex_unlock(&migration_bitmap_mutex);
- migration_dirty_pages += new - old;
- call_rcu(old_bitmap, migration_bitmap_free, rcu);
- }
-}
-
/*
* 'expected' is the value you expect the bitmap mostly to be full
* of; it won't bother printing lines that are all this value.
@@ -1527,14 +1503,14 @@ void migration_bitmap_extend(ram_addr_t old, ram_addr_t new)
*/
void ram_debug_dump_bitmap(unsigned long *todump, bool expected)
{
- int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
-
+ unsigned long ram_pages = last_ram_page();
+ RAMState *rs = &ram_state;
int64_t cur;
int64_t linelen = 128;
char linebuf[129];
if (!todump) {
- todump = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+ todump = atomic_rcu_read(&rs->ram_bitmap)->bmap;
}
for (cur = 0; cur < ram_pages; cur += linelen) {
@@ -1563,8 +1539,9 @@ void ram_debug_dump_bitmap(unsigned long *todump, bool expected)
void ram_postcopy_migrated_memory_release(MigrationState *ms)
{
+ RAMState *rs = &ram_state;
struct RAMBlock *block;
- unsigned long *bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
+ unsigned long *bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
unsigned long first = block->offset >> TARGET_PAGE_BITS;
@@ -1573,30 +1550,38 @@ void ram_postcopy_migrated_memory_release(MigrationState *ms)
while (run_start < range) {
unsigned long run_end = find_next_bit(bitmap, range, run_start + 1);
- ram_discard_range(NULL, block->idstr, run_start << TARGET_PAGE_BITS,
+ ram_discard_range(block->idstr, run_start << TARGET_PAGE_BITS,
(run_end - run_start) << TARGET_PAGE_BITS);
run_start = find_next_zero_bit(bitmap, range, run_end + 1);
}
}
}
-/*
+/**
+ * postcopy_send_discard_bm_ram: discard a RAMBlock
+ *
+ * Returns zero on success
+ *
* Callback from postcopy_each_ram_send_discard for each RAMBlock
* Note: At this point the 'unsentmap' is the processed bitmap combined
* with the dirtymap; so a '1' means it's either dirty or unsent.
- * start,length: Indexes into the bitmap for the first bit
- * representing the named block and length in target-pages
+ *
+ * @ms: current migration state
+ * @pds: state for postcopy
+ * @start: RAMBlock starting page
+ * @length: RAMBlock size
*/
static int postcopy_send_discard_bm_ram(MigrationState *ms,
PostcopyDiscardState *pds,
unsigned long start,
unsigned long length)
{
+ RAMState *rs = &ram_state;
unsigned long end = start + length; /* one after the end */
unsigned long current;
unsigned long *unsentmap;
- unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+ unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap;
for (current = start; current < end; ) {
unsigned long one = find_next_bit(unsentmap, end, current);
@@ -1621,13 +1606,18 @@ static int postcopy_send_discard_bm_ram(MigrationState *ms,
return 0;
}
-/*
+/**
+ * postcopy_each_ram_send_discard: discard all RAMBlocks
+ *
+ * Returns 0 for success or negative for error
+ *
* Utility for the outgoing postcopy code.
* Calls postcopy_send_discard_bm_ram for each RAMBlock
* passing it bitmap indexes and name.
- * Returns: 0 on success
* (qemu_ram_foreach_block ends up passing unscaled lengths
* which would mean postcopy code would have to deal with target page)
+ *
+ * @ms: current migration state
*/
static int postcopy_each_ram_send_discard(MigrationState *ms)
{
@@ -1656,22 +1646,27 @@ static int postcopy_each_ram_send_discard(MigrationState *ms)
return 0;
}
-/*
- * Helper for postcopy_chunk_hostpages; it's called twice to cleanup
- * the two bitmaps, that are similar, but one is inverted.
+/**
+ * postcopy_chunk_hostpages_pass: canocalize bitmap in hostpages
+ *
+ * Helper for postcopy_chunk_hostpages; it's called twice to
+ * canonicalize the two bitmaps, that are similar, but one is
+ * inverted.
*
- * We search for runs of target-pages that don't start or end on a
- * host page boundary;
- * unsent_pass=true: Cleans up partially unsent host pages by searching
- * the unsentmap
- * unsent_pass=false: Cleans up partially dirty host pages by searching
- * the main migration bitmap
+ * Postcopy requires that all target pages in a hostpage are dirty or
+ * clean, not a mix. This function canonicalizes the bitmaps.
*
+ * @ms: current migration state
+ * @unsent_pass: if true we need to canonicalize partially unsent host pages
+ * otherwise we need to canonicalize partially dirty host pages
+ * @block: block that contains the page we want to canonicalize
+ * @pds: state for postcopy
*/
static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass,
RAMBlock *block,
PostcopyDiscardState *pds)
{
+ RAMState *rs = &ram_state;
unsigned long *bitmap;
unsigned long *unsentmap;
unsigned int host_ratio = block->page_size / TARGET_PAGE_SIZE;
@@ -1685,8 +1680,8 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass,
return;
}
- bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
- unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+ bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap;
if (unsent_pass) {
/* Find a sent page */
@@ -1769,7 +1764,7 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass,
* Remark them as dirty, updating the count for any pages
* that weren't previously dirty.
*/
- migration_dirty_pages += !test_and_set_bit(page, bitmap);
+ rs->migration_dirty_pages += !test_and_set_bit(page, bitmap);
}
}
@@ -1784,23 +1779,28 @@ static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass,
}
}
-/*
+/**
+ * postcopy_chuck_hostpages: discrad any partially sent host page
+ *
* Utility for the outgoing postcopy code.
*
* Discard any partially sent host-page size chunks, mark any partially
* dirty host-page size chunks as all dirty. In this case the host-page
* is the host-page for the particular RAMBlock, i.e. it might be a huge page
*
- * Returns: 0 on success
+ * Returns zero on success
+ *
+ * @ms: current migration state
*/
static int postcopy_chunk_hostpages(MigrationState *ms)
{
+ RAMState *rs = &ram_state;
struct RAMBlock *block;
/* Easiest way to make sure we don't resume in the middle of a host-page */
- last_seen_block = NULL;
- last_sent_block = NULL;
- last_offset = 0;
+ rs->last_seen_block = NULL;
+ rs->last_sent_block = NULL;
+ rs->last_page = 0;
QLIST_FOREACH_RCU(block, &ram_list.blocks, next) {
unsigned long first = block->offset >> TARGET_PAGE_BITS;
@@ -1822,7 +1822,11 @@ static int postcopy_chunk_hostpages(MigrationState *ms)
return 0;
}
-/*
+/**
+ * ram_postcopy_send_discard_bitmap: transmit the discard bitmap
+ *
+ * Returns zero on success
+ *
* Transmit the set of pages to be discarded after precopy to the target
* these are pages that:
* a) Have been previously transmitted but are now dirty again
@@ -1830,18 +1834,21 @@ static int postcopy_chunk_hostpages(MigrationState *ms)
* any pages on the destination that have been mapped by background
* tasks get discarded (transparent huge pages is the specific concern)
* Hopefully this is pretty sparse
+ *
+ * @ms: current migration state
*/
int ram_postcopy_send_discard_bitmap(MigrationState *ms)
{
+ RAMState *rs = &ram_state;
int ret;
unsigned long *bitmap, *unsentmap;
rcu_read_lock();
/* This should be our last sync, the src is now paused */
- migration_bitmap_sync();
+ migration_bitmap_sync(rs);
- unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap;
+ unsentmap = atomic_rcu_read(&rs->ram_bitmap)->unsentmap;
if (!unsentmap) {
/* We don't have a safe way to resize the sentmap, so
* if the bitmap was resized it will be NULL at this
@@ -1862,9 +1869,8 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms)
/*
* Update the unsentmap to be unsentmap = unsentmap | dirty
*/
- bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap;
- bitmap_or(unsentmap, unsentmap, bitmap,
- last_ram_offset() >> TARGET_PAGE_BITS);
+ bitmap = atomic_rcu_read(&rs->ram_bitmap)->bmap;
+ bitmap_or(unsentmap, unsentmap, bitmap, last_ram_page());
trace_ram_postcopy_send_discard_bitmap();
@@ -1878,28 +1884,27 @@ int ram_postcopy_send_discard_bitmap(MigrationState *ms)
return ret;
}
-/*
- * At the start of the postcopy phase of migration, any now-dirty
- * precopied pages are discarded.
+/**
+ * ram_discard_range: discard dirtied pages at the beginning of postcopy
*
- * start, length describe a byte address range within the RAMBlock
+ * Returns zero on success
*
- * Returns 0 on success.
+ * @rbname: name of the RAMBlock of the request. NULL means the
+ * same that last one.
+ * @start: RAMBlock starting page
+ * @length: RAMBlock size
*/
-int ram_discard_range(MigrationIncomingState *mis,
- const char *block_name,
- uint64_t start, size_t length)
+int ram_discard_range(const char *rbname, uint64_t start, size_t length)
{
int ret = -1;
- trace_ram_discard_range(block_name, start, length);
+ trace_ram_discard_range(rbname, start, length);
rcu_read_lock();
- RAMBlock *rb = qemu_ram_block_by_name(block_name);
+ RAMBlock *rb = qemu_ram_block_by_name(rbname);
if (!rb) {
- error_report("ram_discard_range: Failed to find block '%s'",
- block_name);
+ error_report("ram_discard_range: Failed to find block '%s'", rbname);
goto err;
}
@@ -1911,14 +1916,14 @@ err:
return ret;
}
-static int ram_save_init_globals(void)
+static int ram_state_init(RAMState *rs)
{
- int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
+ unsigned long ram_bitmap_pages;
- dirty_rate_high_cnt = 0;
- bitmap_sync_count = 0;
- migration_bitmap_sync_init();
- qemu_mutex_init(&migration_bitmap_mutex);
+ memset(rs, 0, sizeof(*rs));
+ qemu_mutex_init(&rs->bitmap_mutex);
+ qemu_mutex_init(&rs->src_page_req_mutex);
+ QSIMPLEQ_INIT(&rs->src_page_requests);
if (migrate_use_xbzrle()) {
XBZRLE_cache_lock();
@@ -1947,8 +1952,6 @@ static int ram_save_init_globals(void)
XBZRLE.encoded_buf = NULL;
return -1;
}
-
- acct_clear();
}
/* For memory_global_dirty_log_start below. */
@@ -1956,19 +1959,18 @@ static int ram_save_init_globals(void)
qemu_mutex_lock_ramlist();
rcu_read_lock();
- bytes_transferred = 0;
- reset_ram_globals();
+ ram_state_reset(rs);
- migration_bitmap_rcu = g_new0(struct BitmapRcu, 1);
+ rs->ram_bitmap = g_new0(RAMBitmap, 1);
/* Skip setting bitmap if there is no RAM */
if (ram_bytes_total()) {
- ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
- migration_bitmap_rcu->bmap = bitmap_new(ram_bitmap_pages);
- bitmap_set(migration_bitmap_rcu->bmap, 0, ram_bitmap_pages);
+ ram_bitmap_pages = last_ram_page();
+ rs->ram_bitmap->bmap = bitmap_new(ram_bitmap_pages);
+ bitmap_set(rs->ram_bitmap->bmap, 0, ram_bitmap_pages);
if (migrate_postcopy_ram()) {
- migration_bitmap_rcu->unsentmap = bitmap_new(ram_bitmap_pages);
- bitmap_set(migration_bitmap_rcu->unsentmap, 0, ram_bitmap_pages);
+ rs->ram_bitmap->unsentmap = bitmap_new(ram_bitmap_pages);
+ bitmap_set(rs->ram_bitmap->unsentmap, 0, ram_bitmap_pages);
}
}
@@ -1976,10 +1978,10 @@ static int ram_save_init_globals(void)
* Count the total number of pages used by ram blocks not including any
* gaps due to alignment or unplugs.
*/
- migration_dirty_pages = ram_bytes_total() >> TARGET_PAGE_BITS;
+ rs->migration_dirty_pages = ram_bytes_total() >> TARGET_PAGE_BITS;
memory_global_dirty_log_start();
- migration_bitmap_sync();
+ migration_bitmap_sync(rs);
qemu_mutex_unlock_ramlist();
qemu_mutex_unlock_iothread();
rcu_read_unlock();
@@ -1987,22 +1989,33 @@ static int ram_save_init_globals(void)
return 0;
}
-/* Each of ram_save_setup, ram_save_iterate and ram_save_complete has
+/*
+ * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
* long-running RCU critical section. When rcu-reclaims in the code
* start to become numerous it will be necessary to reduce the
* granularity of these critical sections.
*/
+/**
+ * ram_save_setup: Setup RAM for migration
+ *
+ * Returns zero to indicate success and negative for error
+ *
+ * @f: QEMUFile where to send the data
+ * @opaque: RAMState pointer
+ */
static int ram_save_setup(QEMUFile *f, void *opaque)
{
+ RAMState *rs = opaque;
RAMBlock *block;
/* migration has already setup the bitmap, reuse it. */
if (!migration_in_colo_state()) {
- if (ram_save_init_globals() < 0) {
+ if (ram_state_init(rs) < 0) {
return -1;
}
}
+ rs->f = f;
rcu_read_lock();
@@ -2027,16 +2040,25 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
return 0;
}
+/**
+ * ram_save_iterate: iterative stage for migration
+ *
+ * Returns zero to indicate success and negative for error
+ *
+ * @f: QEMUFile where to send the data
+ * @opaque: RAMState pointer
+ */
static int ram_save_iterate(QEMUFile *f, void *opaque)
{
+ RAMState *rs = opaque;
int ret;
int i;
int64_t t0;
int done = 0;
rcu_read_lock();
- if (ram_list.version != last_version) {
- reset_ram_globals();
+ if (ram_list.version != rs->last_version) {
+ ram_state_reset(rs);
}
/* Read version before ram_list.blocks */
@@ -2049,13 +2071,13 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
while ((ret = qemu_file_rate_limit(f)) == 0) {
int pages;
- pages = ram_find_and_save_block(f, false, &bytes_transferred);
+ pages = ram_find_and_save_block(rs, false);
/* no more pages to sent */
if (pages == 0) {
done = 1;
break;
}
- acct_info.iterations++;
+ rs->iterations++;
/* we want to check in the 1st loop, just in case it was the 1st time
and we had to sync the dirty bitmap.
@@ -2071,7 +2093,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
}
i++;
}
- flush_compressed_data(f);
+ flush_compressed_data(rs);
rcu_read_unlock();
/*
@@ -2081,7 +2103,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
ram_control_after_iterate(f, RAM_CONTROL_ROUND);
qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
- bytes_transferred += 8;
+ rs->bytes_transferred += 8;
ret = qemu_file_get_error(f);
if (ret < 0) {
@@ -2091,13 +2113,24 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
return done;
}
-/* Called with iothread lock */
+/**
+ * ram_save_complete: function called to send the remaining amount of ram
+ *
+ * Returns zero to indicate success
+ *
+ * Called with iothread lock
+ *
+ * @f: QEMUFile where to send the data
+ * @opaque: RAMState pointer
+ */
static int ram_save_complete(QEMUFile *f, void *opaque)
{
+ RAMState *rs = opaque;
+
rcu_read_lock();
- if (!migration_in_postcopy(migrate_get_current())) {
- migration_bitmap_sync();
+ if (!migration_in_postcopy()) {
+ migration_bitmap_sync(rs);
}
ram_control_before_iterate(f, RAM_CONTROL_FINISH);
@@ -2108,15 +2141,14 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
while (true) {
int pages;
- pages = ram_find_and_save_block(f, !migration_in_colo_state(),
- &bytes_transferred);
+ pages = ram_find_and_save_block(rs, !migration_in_colo_state());
/* no more blocks to sent */
if (pages == 0) {
break;
}
}
- flush_compressed_data(f);
+ flush_compressed_data(rs);
ram_control_after_iterate(f, RAM_CONTROL_FINISH);
rcu_read_unlock();
@@ -2130,18 +2162,19 @@ static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
uint64_t *non_postcopiable_pending,
uint64_t *postcopiable_pending)
{
+ RAMState *rs = opaque;
uint64_t remaining_size;
- remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
+ remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
- if (!migration_in_postcopy(migrate_get_current()) &&
+ if (!migration_in_postcopy() &&
remaining_size < max_size) {
qemu_mutex_lock_iothread();
rcu_read_lock();
- migration_bitmap_sync();
+ migration_bitmap_sync(rs);
rcu_read_unlock();
qemu_mutex_unlock_iothread();
- remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE;
+ remaining_size = rs->migration_dirty_pages * TARGET_PAGE_SIZE;
}
/* We can do postcopy, and all the data is postcopiable */
@@ -2185,17 +2218,17 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
return 0;
}
-/* Must be called from within a rcu critical section.
+/**
+ * ram_block_from_stream: read a RAMBlock id from the migration stream
+ *
+ * Must be called from within a rcu critical section.
+ *
* Returns a pointer from within the RCU-protected ram_list.
- */
-/*
- * Read a RAMBlock ID from the stream f.
*
- * f: Stream to read from
- * flags: Page flags (mostly to see if it's a continuation of previous block)
+ * @f: QEMUFile where to read the data from
+ * @flags: Page flags (mostly to see if it's a continuation of previous block)
*/
-static inline RAMBlock *ram_block_from_stream(QEMUFile *f,
- int flags)
+static inline RAMBlock *ram_block_from_stream(QEMUFile *f, int flags)
{
static RAMBlock *block = NULL;
char id[256];
@@ -2232,9 +2265,15 @@ static inline void *host_from_ram_block_offset(RAMBlock *block,
return block->host + offset;
}
-/*
+/**
+ * ram_handle_compressed: handle the zero page case
+ *
* If a page (or a whole RDMA chunk) has been
* determined to be zero, then zap it.
+ *
+ * @host: host address for the zero page
+ * @ch: what the page is filled from. We only support zero
+ * @size: size of the zero page
*/
void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
{
@@ -2373,20 +2412,33 @@ static void decompress_data_with_multi_threads(QEMUFile *f,
qemu_mutex_unlock(&decomp_done_lock);
}
-/*
- * Allocate data structures etc needed by incoming migration with postcopy-ram
- * postcopy-ram's similarly names postcopy_ram_incoming_init does the work
+/**
+ * ram_postcopy_incoming_init: allocate postcopy data structures
+ *
+ * Returns 0 for success and negative if there was one error
+ *
+ * @mis: current migration incoming state
+ *
+ * Allocate data structures etc needed by incoming migration with
+ * postcopy-ram. postcopy-ram's similarly names
+ * postcopy_ram_incoming_init does the work.
*/
int ram_postcopy_incoming_init(MigrationIncomingState *mis)
{
- size_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
+ unsigned long ram_pages = last_ram_page();
return postcopy_ram_incoming_init(mis, ram_pages);
}
-/*
+/**
+ * ram_load_postcopy: load a page in postcopy case
+ *
+ * Returns 0 for success or -errno in case of error
+ *
* Called in postcopy mode by ram_load().
* rcu_read_lock is taken prior to this being called.
+ *
+ * @f: QEMUFile where to send the data
*/
static int ram_load_postcopy(QEMUFile *f)
{
@@ -2673,5 +2725,5 @@ static SaveVMHandlers savevm_ram_handlers = {
void ram_mig_init(void)
{
qemu_mutex_init(&XBZRLE.lock);
- register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
+ register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, &ram_state);
}
diff --git a/migration/savevm.c b/migration/savevm.c
index 3b19a4a..03ae1bd 100644
--- a/migration/savevm.c
+++ b/migration/savevm.c
@@ -871,7 +871,7 @@ void qemu_savevm_send_postcopy_advise(QEMUFile *f)
{
uint64_t tmp[2];
tmp[0] = cpu_to_be64(ram_pagesize_summary());
- tmp[1] = cpu_to_be64(1ul << qemu_target_page_bits());
+ 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);
@@ -1062,7 +1062,7 @@ int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy)
static bool should_send_vmdesc(void)
{
MachineState *machine = MACHINE(qdev_get_machine());
- bool in_postcopy = migration_in_postcopy(migrate_get_current());
+ bool in_postcopy = migration_in_postcopy();
return !machine->suppress_vmdesc && !in_postcopy;
}
@@ -1111,7 +1111,7 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only)
int vmdesc_len;
SaveStateEntry *se;
int ret;
- bool in_postcopy = migration_in_postcopy(migrate_get_current());
+ bool in_postcopy = migration_in_postcopy();
trace_savevm_state_complete_precopy();
@@ -1197,7 +1197,7 @@ void qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only)
* 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 max_size,
+void qemu_savevm_state_pending(QEMUFile *f, uint64_t threshold_size,
uint64_t *res_non_postcopiable,
uint64_t *res_postcopiable)
{
@@ -1216,7 +1216,7 @@ void qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size,
continue;
}
}
- se->ops->save_live_pending(f, se->opaque, max_size,
+ se->ops->save_live_pending(f, se->opaque, threshold_size,
res_non_postcopiable, res_postcopiable);
}
}
@@ -1390,13 +1390,13 @@ static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis)
}
remote_tps = qemu_get_be64(mis->from_src_file);
- if (remote_tps != (1ul << qemu_target_page_bits())) {
+ if (remote_tps != qemu_target_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=%d)",
- (int)remote_tps, 1 << qemu_target_page_bits());
+ error_report("Postcopy needs matching target page sizes (s=%d d=%zd)",
+ (int)remote_tps, qemu_target_page_size());
return -1;
}
@@ -1479,8 +1479,7 @@ static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis,
block_length = qemu_get_be64(mis->from_src_file);
len -= 16;
- int ret = ram_discard_range(mis, ramid, start_addr,
- block_length);
+ int ret = ram_discard_range(ramid, start_addr, block_length);
if (ret) {
return ret;
}
diff --git a/migration/trace-events b/migration/trace-events
index 7372ce2..b8f01a2 100644
--- a/migration/trace-events
+++ b/migration/trace-events
@@ -63,8 +63,8 @@ put_qtailq_end(const char *name, const char *reason) "%s %s"
qemu_file_fclose(void) ""
# migration/ram.c
-get_queued_page(const char *block_name, uint64_t tmp_offset, uint64_t ram_addr) "%s/%" PRIx64 " ram_addr=%" PRIx64
-get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, uint64_t ram_addr, int sent) "%s/%" PRIx64 " ram_addr=%" PRIx64 " (sent=%d)"
+get_queued_page(const char *block_name, uint64_t tmp_offset, unsigned long page_abs) "%s/%" PRIx64 " page_abs=%lx"
+get_queued_page_not_dirty(const char *block_name, uint64_t tmp_offset, unsigned long page_abs, int sent) "%s/%" PRIx64 " page_abs=%lx (sent=%d)"
migration_bitmap_sync_start(void) ""
migration_bitmap_sync_end(uint64_t dirty_pages) "dirty_pages %" PRIu64
migration_throttle(void) ""
diff --git a/qapi-schema.json b/qapi-schema.json
index 250e4dc..01b087f 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -598,6 +598,9 @@
# @postcopy-requests: The number of page requests received from the destination
# (since 2.7)
#
+# @page-size: The number of bytes per page for the various page-based
+# statistics (since 2.10)
+#
# Since: 0.14.0
##
{ 'struct': 'MigrationStats',
@@ -605,7 +608,7 @@
'duplicate': 'int', 'skipped': 'int', 'normal': 'int',
'normal-bytes': 'int', 'dirty-pages-rate' : 'int',
'mbps' : 'number', 'dirty-sync-count' : 'int',
- 'postcopy-requests' : 'int' } }
+ 'postcopy-requests' : 'int', 'page-size' : 'int' } }
##
# @XBZRLECacheStats:
diff --git a/qdev-monitor.c b/qdev-monitor.c
index 5f2fcdf..e61d596 100644
--- a/qdev-monitor.c
+++ b/qdev-monitor.c
@@ -29,6 +29,7 @@
#include "qemu/error-report.h"
#include "qemu/help_option.h"
#include "sysemu/block-backend.h"
+#include "migration/migration.h"
/*
* Aliases were a bad idea from the start. Let's keep them
@@ -603,6 +604,11 @@ DeviceState *qdev_device_add(QemuOpts *opts, Error **errp)
return NULL;
}
+ if (!migration_is_idle()) {
+ error_setg(errp, "device_add not allowed while migrating");
+ return NULL;
+ }
+
/* create device */
dev = DEVICE(object_new(driver));
@@ -836,6 +842,45 @@ static DeviceState *find_device_state(const char *id, Error **errp)
return DEVICE(obj);
}
+void qdev_unplug(DeviceState *dev, Error **errp)
+{
+ DeviceClass *dc = DEVICE_GET_CLASS(dev);
+ HotplugHandler *hotplug_ctrl;
+ HotplugHandlerClass *hdc;
+
+ if (dev->parent_bus && !qbus_is_hotpluggable(dev->parent_bus)) {
+ error_setg(errp, QERR_BUS_NO_HOTPLUG, dev->parent_bus->name);
+ return;
+ }
+
+ if (!dc->hotpluggable) {
+ error_setg(errp, QERR_DEVICE_NO_HOTPLUG,
+ object_get_typename(OBJECT(dev)));
+ return;
+ }
+
+ if (!migration_is_idle()) {
+ error_setg(errp, "device_del not allowed while migrating");
+ return;
+ }
+
+ qdev_hot_removed = true;
+
+ hotplug_ctrl = qdev_get_hotplug_handler(dev);
+ /* hotpluggable device MUST have HotplugHandler, if it doesn't
+ * then something is very wrong with it */
+ g_assert(hotplug_ctrl);
+
+ /* If device supports async unplug just request it to be done,
+ * otherwise just remove it synchronously */
+ hdc = HOTPLUG_HANDLER_GET_CLASS(hotplug_ctrl);
+ if (hdc->unplug_request) {
+ hotplug_handler_unplug_request(hotplug_ctrl, dev, errp);
+ } else {
+ hotplug_handler_unplug(hotplug_ctrl, dev, errp);
+ }
+}
+
void qmp_device_del(const char *id, Error **errp)
{
DeviceState *dev = find_device_state(id, errp);
generated by cgit v1.1 at 2024-08-16 02:39:23 +0000