* GNU GPL, version 2 or (at your option) any later version.
*/
+#include "qemu/osdep.h"
+#include "qapi/error.h"
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "hw/hw.h"
+#include "qemu/cutils.h"
#include "qemu/queue.h"
#include "qemu/timer.h"
#include "migration/block.h"
#include "migration/migration.h"
#include "sysemu/blockdev.h"
#include "sysemu/block-backend.h"
-#include <assert.h>
#define BLOCK_SIZE (1 << 20)
#define BDRV_SECTORS_PER_DIRTY_CHUNK (BLOCK_SIZE >> BDRV_SECTOR_BITS)
#define MAX_IS_ALLOCATED_SEARCH 65536
+#define MAX_INFLIGHT_IO 512
+
//#define DEBUG_BLK_MIGRATION
#ifdef DEBUG_BLK_MIGRATION
int shared_base;
int64_t total_sectors;
QSIMPLEQ_ENTRY(BlkMigDevState) entry;
+ Error *blocker;
/* Only used by migration thread. Does not need a lock. */
int bulk_completed;
int64_t cur_sector;
int64_t cur_dirty;
- /* Protected by block migration lock. */
+ /* Data in the aio_bitmap is protected by block migration lock.
+ * Allocation and free happen during setup and cleanup respectively.
+ */
unsigned long *aio_bitmap;
+
+ /* Protected by block migration lock. */
int64_t completed_sectors;
+
+ /* During migration this is protected by iothread lock / AioContext.
+ * Allocation and free happen during setup and cleanup respectively.
+ */
BdrvDirtyBitmap *dirty_bitmap;
- Error *blocker;
} BlkMigDevState;
typedef struct BlkMigBlock {
int prev_progress;
int bulk_completed;
- /* Lock must be taken _inside_ the iothread lock. */
+ /* Lock must be taken _inside_ the iothread lock and any AioContexts. */
QemuMutex lock;
} BlkMigState;
if (bmds->shared_base) {
qemu_mutex_lock_iothread();
+ aio_context_acquire(bdrv_get_aio_context(bs));
while (cur_sector < total_sectors &&
!bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH,
&nr_sectors)) {
cur_sector += nr_sectors;
}
+ aio_context_release(bdrv_get_aio_context(bs));
qemu_mutex_unlock_iothread();
}
block_mig_state.submitted++;
blk_mig_unlock();
+ /* We do not know if bs is under the main thread (and thus does
+ * not acquire the AioContext when doing AIO) or rather under
+ * dataplane. Thus acquire both the iothread mutex and the
+ * AioContext.
+ *
+ * This is ugly and will disappear when we make bdrv_* thread-safe,
+ * without the need to acquire the AioContext.
+ */
qemu_mutex_lock_iothread();
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
blk->aiocb = bdrv_aio_readv(bs, cur_sector, &blk->qiov,
nr_sectors, blk_mig_read_cb, blk);
bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, cur_sector, nr_sectors);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
qemu_mutex_unlock_iothread();
bmds->cur_sector = cur_sector + nr_sectors;
int ret;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
NULL, NULL);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
if (!bmds->dirty_bitmap) {
ret = -errno;
goto fail;
fail:
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
if (bmds->dirty_bitmap) {
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
}
}
return ret;
}
+/* Called with iothread lock taken. */
+
static void unset_dirty_tracking(void)
{
BlkMigDevState *bmds;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
}
}
}
}
-/* Called with iothread lock taken. */
+/* Called with iothread lock and AioContext taken. */
static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
int is_async)
int ret = 1;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
ret = mig_save_device_dirty(f, bmds, is_async);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
if (ret <= 0) {
break;
}
int64_t dirty = 0;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
+ aio_context_acquire(bdrv_get_aio_context(bmds->bs));
dirty += bdrv_get_dirty_count(bmds->dirty_bitmap);
+ aio_context_release(bdrv_get_aio_context(bmds->bs));
}
return dirty << BDRV_SECTOR_BITS;
/* Called with iothread lock taken. */
-static void blk_mig_cleanup(void)
+static void block_migration_cleanup(void *opaque)
{
BlkMigDevState *bmds;
BlkMigBlock *blk;
+ AioContext *ctx;
bdrv_drain_all();
unset_dirty_tracking();
- blk_mig_lock();
while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
bdrv_op_unblock_all(bmds->bs, bmds->blocker);
error_free(bmds->blocker);
+
+ /* Save ctx, because bmds->bs can disappear during bdrv_unref. */
+ ctx = bdrv_get_aio_context(bmds->bs);
+ aio_context_acquire(ctx);
bdrv_unref(bmds->bs);
+ aio_context_release(ctx);
+
g_free(bmds->aio_bitmap);
g_free(bmds);
}
+ blk_mig_lock();
while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) {
QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry);
g_free(blk->buf);
blk_mig_unlock();
}
-static void block_migration_cancel(void *opaque)
-{
- blk_mig_cleanup();
-}
-
static int block_save_setup(QEMUFile *f, void *opaque)
{
int ret;
/* start track dirty blocks */
ret = set_dirty_tracking();
+ qemu_mutex_unlock_iothread();
+
if (ret) {
- qemu_mutex_unlock_iothread();
return ret;
}
- qemu_mutex_unlock_iothread();
-
ret = flush_blks(f);
blk_mig_reset_dirty_cursor();
qemu_put_be64(f, BLK_MIG_FLAG_EOS);
blk_mig_lock();
while ((block_mig_state.submitted +
block_mig_state.read_done) * BLOCK_SIZE <
- qemu_file_get_rate_limit(f)) {
+ qemu_file_get_rate_limit(f) &&
+ (block_mig_state.submitted +
+ block_mig_state.read_done) <
+ MAX_INFLIGHT_IO) {
blk_mig_unlock();
if (block_mig_state.bulk_completed == 0) {
/* first finish the bulk phase */
qemu_put_be64(f, BLK_MIG_FLAG_EOS);
- blk_mig_cleanup();
return 0;
}
-static uint64_t block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
+static void block_save_pending(QEMUFile *f, void *opaque, uint64_t max_size,
+ uint64_t *non_postcopiable_pending,
+ uint64_t *postcopiable_pending)
{
/* Estimate pending number of bytes to send */
uint64_t pending;
qemu_mutex_lock_iothread();
+ pending = get_remaining_dirty();
+ qemu_mutex_unlock_iothread();
+
blk_mig_lock();
- pending = get_remaining_dirty() +
- block_mig_state.submitted * BLOCK_SIZE +
- block_mig_state.read_done * BLOCK_SIZE;
+ pending += block_mig_state.submitted * BLOCK_SIZE +
+ block_mig_state.read_done * BLOCK_SIZE;
+ blk_mig_unlock();
/* Report at least one block pending during bulk phase */
if (pending <= max_size && !block_mig_state.bulk_completed) {
pending = max_size + BLOCK_SIZE;
}
- blk_mig_unlock();
- qemu_mutex_unlock_iothread();
DPRINTF("Enter save live pending %" PRIu64 "\n", pending);
- return pending;
+ /* We don't do postcopy */
+ *non_postcopiable_pending += pending;
}
static int block_load(QEMUFile *f, void *opaque, int version_id)
int64_t addr;
BlockDriverState *bs, *bs_prev = NULL;
BlockBackend *blk;
+ Error *local_err = NULL;
uint8_t *buf;
int64_t total_sectors = 0;
int nr_sectors;
return -EINVAL;
}
bs = blk_bs(blk);
+ if (!bs) {
+ fprintf(stderr, "Block device %s has no medium\n",
+ device_name);
+ return -EINVAL;
+ }
if (bs != bs_prev) {
bs_prev = bs;
device_name);
return -EINVAL;
}
+
+ bdrv_invalidate_cache(bs, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ return -EINVAL;
+ }
}
if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) {
.set_params = block_set_params,
.save_live_setup = block_save_setup,
.save_live_iterate = block_save_iterate,
- .save_live_complete = block_save_complete,
+ .save_live_complete_precopy = block_save_complete,
.save_live_pending = block_save_pending,
.load_state = block_load,
- .cancel = block_migration_cancel,
+ .cleanup = block_migration_cleanup,
.is_active = block_is_active,
};