diff options
Diffstat (limited to 'src/migration')
-rw-r--r-- | src/migration/Makefile.objs | 10 | ||||
-rw-r--r-- | src/migration/block.c | 902 | ||||
-rw-r--r-- | src/migration/exec.c | 69 | ||||
-rw-r--r-- | src/migration/fd.c | 88 | ||||
-rw-r--r-- | src/migration/migration.c | 1773 | ||||
-rw-r--r-- | src/migration/postcopy-ram.c | 761 | ||||
-rw-r--r-- | src/migration/qemu-file-buf.c | 463 | ||||
-rw-r--r-- | src/migration/qemu-file-internal.h | 53 | ||||
-rw-r--r-- | src/migration/qemu-file-stdio.c | 195 | ||||
-rw-r--r-- | src/migration/qemu-file-unix.c | 324 | ||||
-rw-r--r-- | src/migration/qemu-file.c | 677 | ||||
-rw-r--r-- | src/migration/ram.c | 2544 | ||||
-rw-r--r-- | src/migration/rdma.c | 3516 | ||||
-rw-r--r-- | src/migration/savevm.c | 2195 | ||||
-rw-r--r-- | src/migration/tcp.c | 103 | ||||
-rw-r--r-- | src/migration/unix.c | 103 | ||||
-rw-r--r-- | src/migration/vmstate.c | 890 | ||||
-rw-r--r-- | src/migration/xbzrle.c | 175 |
18 files changed, 14841 insertions, 0 deletions
diff --git a/src/migration/Makefile.objs b/src/migration/Makefile.objs new file mode 100644 index 0000000..0cac6d7 --- /dev/null +++ b/src/migration/Makefile.objs @@ -0,0 +1,10 @@ +common-obj-y += migration.o tcp.o +common-obj-y += vmstate.o +common-obj-y += qemu-file.o qemu-file-buf.o qemu-file-unix.o qemu-file-stdio.o +common-obj-y += xbzrle.o postcopy-ram.o + +common-obj-$(CONFIG_RDMA) += rdma.o +common-obj-$(CONFIG_POSIX) += exec.o unix.o fd.o + +common-obj-y += block.o + diff --git a/src/migration/block.c b/src/migration/block.c new file mode 100644 index 0000000..656f38f --- /dev/null +++ b/src/migration/block.c @@ -0,0 +1,902 @@ +/* + * QEMU live block migration + * + * Copyright IBM, Corp. 2009 + * + * Authors: + * Liran Schour <lirans@il.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu-common.h" +#include "block/block.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "hw/hw.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 BLK_MIG_FLAG_DEVICE_BLOCK 0x01 +#define BLK_MIG_FLAG_EOS 0x02 +#define BLK_MIG_FLAG_PROGRESS 0x04 +#define BLK_MIG_FLAG_ZERO_BLOCK 0x08 + +#define MAX_IS_ALLOCATED_SEARCH 65536 + +#define MAX_INFLIGHT_IO 512 + +//#define DEBUG_BLK_MIGRATION + +#ifdef DEBUG_BLK_MIGRATION +#define DPRINTF(fmt, ...) \ + do { printf("blk_migration: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +typedef struct BlkMigDevState { + /* Written during setup phase. Can be read without a lock. */ + BlockDriverState *bs; + int shared_base; + int64_t total_sectors; + QSIMPLEQ_ENTRY(BlkMigDevState) entry; + + /* 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. */ + unsigned long *aio_bitmap; + int64_t completed_sectors; + BdrvDirtyBitmap *dirty_bitmap; + Error *blocker; +} BlkMigDevState; + +typedef struct BlkMigBlock { + /* Only used by migration thread. */ + uint8_t *buf; + BlkMigDevState *bmds; + int64_t sector; + int nr_sectors; + struct iovec iov; + QEMUIOVector qiov; + BlockAIOCB *aiocb; + + /* Protected by block migration lock. */ + int ret; + QSIMPLEQ_ENTRY(BlkMigBlock) entry; +} BlkMigBlock; + +typedef struct BlkMigState { + /* Written during setup phase. Can be read without a lock. */ + int blk_enable; + int shared_base; + QSIMPLEQ_HEAD(bmds_list, BlkMigDevState) bmds_list; + int64_t total_sector_sum; + bool zero_blocks; + + /* Protected by lock. */ + QSIMPLEQ_HEAD(blk_list, BlkMigBlock) blk_list; + int submitted; + int read_done; + + /* Only used by migration thread. Does not need a lock. */ + int transferred; + int prev_progress; + int bulk_completed; + + /* Lock must be taken _inside_ the iothread lock. */ + QemuMutex lock; +} BlkMigState; + +static BlkMigState block_mig_state; + +static void blk_mig_lock(void) +{ + qemu_mutex_lock(&block_mig_state.lock); +} + +static void blk_mig_unlock(void) +{ + qemu_mutex_unlock(&block_mig_state.lock); +} + +/* Must run outside of the iothread lock during the bulk phase, + * or the VM will stall. + */ + +static void blk_send(QEMUFile *f, BlkMigBlock * blk) +{ + int len; + uint64_t flags = BLK_MIG_FLAG_DEVICE_BLOCK; + + if (block_mig_state.zero_blocks && + buffer_is_zero(blk->buf, BLOCK_SIZE)) { + flags |= BLK_MIG_FLAG_ZERO_BLOCK; + } + + /* sector number and flags */ + qemu_put_be64(f, (blk->sector << BDRV_SECTOR_BITS) + | flags); + + /* device name */ + len = strlen(bdrv_get_device_name(blk->bmds->bs)); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)bdrv_get_device_name(blk->bmds->bs), len); + + /* if a block is zero we need to flush here since the network + * bandwidth is now a lot higher than the storage device bandwidth. + * thus if we queue zero blocks we slow down the migration */ + if (flags & BLK_MIG_FLAG_ZERO_BLOCK) { + qemu_fflush(f); + return; + } + + qemu_put_buffer(f, blk->buf, BLOCK_SIZE); +} + +int blk_mig_active(void) +{ + return !QSIMPLEQ_EMPTY(&block_mig_state.bmds_list); +} + +uint64_t blk_mig_bytes_transferred(void) +{ + BlkMigDevState *bmds; + uint64_t sum = 0; + + blk_mig_lock(); + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + sum += bmds->completed_sectors; + } + blk_mig_unlock(); + return sum << BDRV_SECTOR_BITS; +} + +uint64_t blk_mig_bytes_remaining(void) +{ + return blk_mig_bytes_total() - blk_mig_bytes_transferred(); +} + +uint64_t blk_mig_bytes_total(void) +{ + BlkMigDevState *bmds; + uint64_t sum = 0; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + sum += bmds->total_sectors; + } + return sum << BDRV_SECTOR_BITS; +} + + +/* Called with migration lock held. */ + +static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector) +{ + int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK; + + if (sector < bdrv_nb_sectors(bmds->bs)) { + return !!(bmds->aio_bitmap[chunk / (sizeof(unsigned long) * 8)] & + (1UL << (chunk % (sizeof(unsigned long) * 8)))); + } else { + return 0; + } +} + +/* Called with migration lock held. */ + +static void bmds_set_aio_inflight(BlkMigDevState *bmds, int64_t sector_num, + int nb_sectors, int set) +{ + int64_t start, end; + unsigned long val, idx, bit; + + start = sector_num / BDRV_SECTORS_PER_DIRTY_CHUNK; + end = (sector_num + nb_sectors - 1) / BDRV_SECTORS_PER_DIRTY_CHUNK; + + for (; start <= end; start++) { + idx = start / (sizeof(unsigned long) * 8); + bit = start % (sizeof(unsigned long) * 8); + val = bmds->aio_bitmap[idx]; + if (set) { + val |= 1UL << bit; + } else { + val &= ~(1UL << bit); + } + bmds->aio_bitmap[idx] = val; + } +} + +static void alloc_aio_bitmap(BlkMigDevState *bmds) +{ + BlockDriverState *bs = bmds->bs; + int64_t bitmap_size; + + bitmap_size = bdrv_nb_sectors(bs) + BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1; + bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8; + + bmds->aio_bitmap = g_malloc0(bitmap_size); +} + +/* Never hold migration lock when yielding to the main loop! */ + +static void blk_mig_read_cb(void *opaque, int ret) +{ + BlkMigBlock *blk = opaque; + + blk_mig_lock(); + blk->ret = ret; + + QSIMPLEQ_INSERT_TAIL(&block_mig_state.blk_list, blk, entry); + bmds_set_aio_inflight(blk->bmds, blk->sector, blk->nr_sectors, 0); + + block_mig_state.submitted--; + block_mig_state.read_done++; + assert(block_mig_state.submitted >= 0); + blk_mig_unlock(); +} + +/* Called with no lock taken. */ + +static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds) +{ + int64_t total_sectors = bmds->total_sectors; + int64_t cur_sector = bmds->cur_sector; + BlockDriverState *bs = bmds->bs; + BlkMigBlock *blk; + int nr_sectors; + + if (bmds->shared_base) { + qemu_mutex_lock_iothread(); + while (cur_sector < total_sectors && + !bdrv_is_allocated(bs, cur_sector, MAX_IS_ALLOCATED_SEARCH, + &nr_sectors)) { + cur_sector += nr_sectors; + } + qemu_mutex_unlock_iothread(); + } + + if (cur_sector >= total_sectors) { + bmds->cur_sector = bmds->completed_sectors = total_sectors; + return 1; + } + + bmds->completed_sectors = cur_sector; + + cur_sector &= ~((int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK - 1); + + /* we are going to transfer a full block even if it is not allocated */ + nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK; + + if (total_sectors - cur_sector < BDRV_SECTORS_PER_DIRTY_CHUNK) { + nr_sectors = total_sectors - cur_sector; + } + + blk = g_new(BlkMigBlock, 1); + blk->buf = g_malloc(BLOCK_SIZE); + blk->bmds = bmds; + blk->sector = cur_sector; + blk->nr_sectors = nr_sectors; + + blk->iov.iov_base = blk->buf; + blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE; + qemu_iovec_init_external(&blk->qiov, &blk->iov, 1); + + blk_mig_lock(); + block_mig_state.submitted++; + blk_mig_unlock(); + + qemu_mutex_lock_iothread(); + 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); + qemu_mutex_unlock_iothread(); + + bmds->cur_sector = cur_sector + nr_sectors; + return (bmds->cur_sector >= total_sectors); +} + +/* Called with iothread lock taken. */ + +static int set_dirty_tracking(void) +{ + BlkMigDevState *bmds; + int ret; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE, + NULL, NULL); + if (!bmds->dirty_bitmap) { + ret = -errno; + goto fail; + } + } + return 0; + +fail: + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + if (bmds->dirty_bitmap) { + bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap); + } + } + return ret; +} + +static void unset_dirty_tracking(void) +{ + BlkMigDevState *bmds; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap); + } +} + +static void init_blk_migration(QEMUFile *f) +{ + BlockDriverState *bs; + BlkMigDevState *bmds; + int64_t sectors; + + block_mig_state.submitted = 0; + block_mig_state.read_done = 0; + block_mig_state.transferred = 0; + block_mig_state.total_sector_sum = 0; + block_mig_state.prev_progress = -1; + block_mig_state.bulk_completed = 0; + block_mig_state.zero_blocks = migrate_zero_blocks(); + + for (bs = bdrv_next(NULL); bs; bs = bdrv_next(bs)) { + if (bdrv_is_read_only(bs)) { + continue; + } + + sectors = bdrv_nb_sectors(bs); + if (sectors <= 0) { + return; + } + + bmds = g_new0(BlkMigDevState, 1); + bmds->bs = bs; + bmds->bulk_completed = 0; + bmds->total_sectors = sectors; + bmds->completed_sectors = 0; + bmds->shared_base = block_mig_state.shared_base; + alloc_aio_bitmap(bmds); + error_setg(&bmds->blocker, "block device is in use by migration"); + bdrv_op_block_all(bs, bmds->blocker); + bdrv_ref(bs); + + block_mig_state.total_sector_sum += sectors; + + if (bmds->shared_base) { + DPRINTF("Start migration for %s with shared base image\n", + bdrv_get_device_name(bs)); + } else { + DPRINTF("Start full migration for %s\n", bdrv_get_device_name(bs)); + } + + QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry); + } +} + +/* Called with no lock taken. */ + +static int blk_mig_save_bulked_block(QEMUFile *f) +{ + int64_t completed_sector_sum = 0; + BlkMigDevState *bmds; + int progress; + int ret = 0; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + if (bmds->bulk_completed == 0) { + if (mig_save_device_bulk(f, bmds) == 1) { + /* completed bulk section for this device */ + bmds->bulk_completed = 1; + } + completed_sector_sum += bmds->completed_sectors; + ret = 1; + break; + } else { + completed_sector_sum += bmds->completed_sectors; + } + } + + if (block_mig_state.total_sector_sum != 0) { + progress = completed_sector_sum * 100 / + block_mig_state.total_sector_sum; + } else { + progress = 100; + } + if (progress != block_mig_state.prev_progress) { + block_mig_state.prev_progress = progress; + qemu_put_be64(f, (progress << BDRV_SECTOR_BITS) + | BLK_MIG_FLAG_PROGRESS); + DPRINTF("Completed %d %%\r", progress); + } + + return ret; +} + +static void blk_mig_reset_dirty_cursor(void) +{ + BlkMigDevState *bmds; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + bmds->cur_dirty = 0; + } +} + +/* Called with iothread lock taken. */ + +static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds, + int is_async) +{ + BlkMigBlock *blk; + int64_t total_sectors = bmds->total_sectors; + int64_t sector; + int nr_sectors; + int ret = -EIO; + + for (sector = bmds->cur_dirty; sector < bmds->total_sectors;) { + blk_mig_lock(); + if (bmds_aio_inflight(bmds, sector)) { + blk_mig_unlock(); + bdrv_drain(bmds->bs); + } else { + blk_mig_unlock(); + } + if (bdrv_get_dirty(bmds->bs, bmds->dirty_bitmap, sector)) { + + if (total_sectors - sector < BDRV_SECTORS_PER_DIRTY_CHUNK) { + nr_sectors = total_sectors - sector; + } else { + nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK; + } + blk = g_new(BlkMigBlock, 1); + blk->buf = g_malloc(BLOCK_SIZE); + blk->bmds = bmds; + blk->sector = sector; + blk->nr_sectors = nr_sectors; + + if (is_async) { + blk->iov.iov_base = blk->buf; + blk->iov.iov_len = nr_sectors * BDRV_SECTOR_SIZE; + qemu_iovec_init_external(&blk->qiov, &blk->iov, 1); + + blk->aiocb = bdrv_aio_readv(bmds->bs, sector, &blk->qiov, + nr_sectors, blk_mig_read_cb, blk); + + blk_mig_lock(); + block_mig_state.submitted++; + bmds_set_aio_inflight(bmds, sector, nr_sectors, 1); + blk_mig_unlock(); + } else { + ret = bdrv_read(bmds->bs, sector, blk->buf, nr_sectors); + if (ret < 0) { + goto error; + } + blk_send(f, blk); + + g_free(blk->buf); + g_free(blk); + } + + bdrv_reset_dirty_bitmap(bmds->dirty_bitmap, sector, nr_sectors); + break; + } + sector += BDRV_SECTORS_PER_DIRTY_CHUNK; + bmds->cur_dirty = sector; + } + + return (bmds->cur_dirty >= bmds->total_sectors); + +error: + DPRINTF("Error reading sector %" PRId64 "\n", sector); + g_free(blk->buf); + g_free(blk); + return ret; +} + +/* Called with iothread lock taken. + * + * return value: + * 0: too much data for max_downtime + * 1: few enough data for max_downtime +*/ +static int blk_mig_save_dirty_block(QEMUFile *f, int is_async) +{ + BlkMigDevState *bmds; + int ret = 1; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + ret = mig_save_device_dirty(f, bmds, is_async); + if (ret <= 0) { + break; + } + } + + return ret; +} + +/* Called with no locks taken. */ + +static int flush_blks(QEMUFile *f) +{ + BlkMigBlock *blk; + int ret = 0; + + DPRINTF("%s Enter submitted %d read_done %d transferred %d\n", + __FUNCTION__, block_mig_state.submitted, block_mig_state.read_done, + block_mig_state.transferred); + + blk_mig_lock(); + while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) { + if (qemu_file_rate_limit(f)) { + break; + } + if (blk->ret < 0) { + ret = blk->ret; + break; + } + + QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry); + blk_mig_unlock(); + blk_send(f, blk); + blk_mig_lock(); + + g_free(blk->buf); + g_free(blk); + + block_mig_state.read_done--; + block_mig_state.transferred++; + assert(block_mig_state.read_done >= 0); + } + blk_mig_unlock(); + + DPRINTF("%s Exit submitted %d read_done %d transferred %d\n", __FUNCTION__, + block_mig_state.submitted, block_mig_state.read_done, + block_mig_state.transferred); + return ret; +} + +/* Called with iothread lock taken. */ + +static int64_t get_remaining_dirty(void) +{ + BlkMigDevState *bmds; + int64_t dirty = 0; + + QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) { + dirty += bdrv_get_dirty_count(bmds->dirty_bitmap); + } + + return dirty << BDRV_SECTOR_BITS; +} + +/* Called with iothread lock taken. */ + +static void block_migration_cleanup(void *opaque) +{ + BlkMigDevState *bmds; + BlkMigBlock *blk; + + 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); + bdrv_unref(bmds->bs); + g_free(bmds->aio_bitmap); + g_free(bmds); + } + + while ((blk = QSIMPLEQ_FIRST(&block_mig_state.blk_list)) != NULL) { + QSIMPLEQ_REMOVE_HEAD(&block_mig_state.blk_list, entry); + g_free(blk->buf); + g_free(blk); + } + blk_mig_unlock(); +} + +static int block_save_setup(QEMUFile *f, void *opaque) +{ + int ret; + + DPRINTF("Enter save live setup submitted %d transferred %d\n", + block_mig_state.submitted, block_mig_state.transferred); + + qemu_mutex_lock_iothread(); + init_blk_migration(f); + + /* start track dirty blocks */ + ret = set_dirty_tracking(); + + 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); + + return ret; +} + +static int block_save_iterate(QEMUFile *f, void *opaque) +{ + int ret; + int64_t last_ftell = qemu_ftell(f); + int64_t delta_ftell; + + DPRINTF("Enter save live iterate submitted %d transferred %d\n", + block_mig_state.submitted, block_mig_state.transferred); + + ret = flush_blks(f); + if (ret) { + return ret; + } + + blk_mig_reset_dirty_cursor(); + + /* control the rate of transfer */ + blk_mig_lock(); + while ((block_mig_state.submitted + + block_mig_state.read_done) * BLOCK_SIZE < + 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 */ + if (blk_mig_save_bulked_block(f) == 0) { + /* finished saving bulk on all devices */ + block_mig_state.bulk_completed = 1; + } + ret = 0; + } else { + /* Always called with iothread lock taken for + * simplicity, block_save_complete also calls it. + */ + qemu_mutex_lock_iothread(); + ret = blk_mig_save_dirty_block(f, 1); + qemu_mutex_unlock_iothread(); + } + if (ret < 0) { + return ret; + } + blk_mig_lock(); + if (ret != 0) { + /* no more dirty blocks */ + break; + } + } + blk_mig_unlock(); + + ret = flush_blks(f); + if (ret) { + return ret; + } + + qemu_put_be64(f, BLK_MIG_FLAG_EOS); + delta_ftell = qemu_ftell(f) - last_ftell; + if (delta_ftell > 0) { + return 1; + } else if (delta_ftell < 0) { + return -1; + } else { + return 0; + } +} + +/* Called with iothread lock taken. */ + +static int block_save_complete(QEMUFile *f, void *opaque) +{ + int ret; + + DPRINTF("Enter save live complete submitted %d transferred %d\n", + block_mig_state.submitted, block_mig_state.transferred); + + ret = flush_blks(f); + if (ret) { + return ret; + } + + blk_mig_reset_dirty_cursor(); + + /* we know for sure that save bulk is completed and + all async read completed */ + blk_mig_lock(); + assert(block_mig_state.submitted == 0); + blk_mig_unlock(); + + do { + ret = blk_mig_save_dirty_block(f, 0); + if (ret < 0) { + return ret; + } + } while (ret == 0); + + /* report completion */ + qemu_put_be64(f, (100 << BDRV_SECTOR_BITS) | BLK_MIG_FLAG_PROGRESS); + + DPRINTF("Block migration completed\n"); + + qemu_put_be64(f, BLK_MIG_FLAG_EOS); + + return 0; +} + +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(); + blk_mig_lock(); + pending = get_remaining_dirty() + + block_mig_state.submitted * BLOCK_SIZE + + block_mig_state.read_done * BLOCK_SIZE; + + /* 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); + /* We don't do postcopy */ + *non_postcopiable_pending += pending; +} + +static int block_load(QEMUFile *f, void *opaque, int version_id) +{ + static int banner_printed; + int len, flags; + char device_name[256]; + int64_t addr; + BlockDriverState *bs, *bs_prev = NULL; + BlockBackend *blk; + uint8_t *buf; + int64_t total_sectors = 0; + int nr_sectors; + int ret; + + do { + addr = qemu_get_be64(f); + + flags = addr & ~BDRV_SECTOR_MASK; + addr >>= BDRV_SECTOR_BITS; + + if (flags & BLK_MIG_FLAG_DEVICE_BLOCK) { + /* get device name */ + len = qemu_get_byte(f); + qemu_get_buffer(f, (uint8_t *)device_name, len); + device_name[len] = '\0'; + + blk = blk_by_name(device_name); + if (!blk) { + fprintf(stderr, "Error unknown block device %s\n", + device_name); + 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; + total_sectors = bdrv_nb_sectors(bs); + if (total_sectors <= 0) { + error_report("Error getting length of block device %s", + device_name); + return -EINVAL; + } + } + + if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) { + nr_sectors = total_sectors - addr; + } else { + nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK; + } + + if (flags & BLK_MIG_FLAG_ZERO_BLOCK) { + ret = bdrv_write_zeroes(bs, addr, nr_sectors, + BDRV_REQ_MAY_UNMAP); + } else { + buf = g_malloc(BLOCK_SIZE); + qemu_get_buffer(f, buf, BLOCK_SIZE); + ret = bdrv_write(bs, addr, buf, nr_sectors); + g_free(buf); + } + + if (ret < 0) { + return ret; + } + } else if (flags & BLK_MIG_FLAG_PROGRESS) { + if (!banner_printed) { + printf("Receiving block device images\n"); + banner_printed = 1; + } + printf("Completed %d %%%c", (int)addr, + (addr == 100) ? '\n' : '\r'); + fflush(stdout); + } else if (!(flags & BLK_MIG_FLAG_EOS)) { + fprintf(stderr, "Unknown block migration flags: %#x\n", flags); + return -EINVAL; + } + ret = qemu_file_get_error(f); + if (ret != 0) { + return ret; + } + } while (!(flags & BLK_MIG_FLAG_EOS)); + + return 0; +} + +static void block_set_params(const MigrationParams *params, void *opaque) +{ + block_mig_state.blk_enable = params->blk; + block_mig_state.shared_base = params->shared; + + /* shared base means that blk_enable = 1 */ + block_mig_state.blk_enable |= params->shared; +} + +static bool block_is_active(void *opaque) +{ + return block_mig_state.blk_enable == 1; +} + +static SaveVMHandlers savevm_block_handlers = { + .set_params = block_set_params, + .save_live_setup = block_save_setup, + .save_live_iterate = block_save_iterate, + .save_live_complete_precopy = block_save_complete, + .save_live_pending = block_save_pending, + .load_state = block_load, + .cleanup = block_migration_cleanup, + .is_active = block_is_active, +}; + +void blk_mig_init(void) +{ + QSIMPLEQ_INIT(&block_mig_state.bmds_list); + QSIMPLEQ_INIT(&block_mig_state.blk_list); + qemu_mutex_init(&block_mig_state.lock); + + register_savevm_live(NULL, "block", 0, 1, &savevm_block_handlers, + &block_mig_state); +} diff --git a/src/migration/exec.c b/src/migration/exec.c new file mode 100644 index 0000000..8406d2b --- /dev/null +++ b/src/migration/exec.c @@ -0,0 +1,69 @@ +/* + * QEMU live migration + * + * Copyright IBM, Corp. 2008 + * Copyright Dell MessageOne 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * Charles Duffy <charles_duffy@messageone.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu-common.h" +#include "qemu/sockets.h" +#include "qemu/main-loop.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "block/block.h" +#include <sys/types.h> +#include <sys/wait.h> + +//#define DEBUG_MIGRATION_EXEC + +#ifdef DEBUG_MIGRATION_EXEC +#define DPRINTF(fmt, ...) \ + do { printf("migration-exec: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +void exec_start_outgoing_migration(MigrationState *s, const char *command, Error **errp) +{ + s->file = qemu_popen_cmd(command, "w"); + if (s->file == NULL) { + error_setg_errno(errp, errno, "failed to popen the migration target"); + return; + } + + migrate_fd_connect(s); +} + +static void exec_accept_incoming_migration(void *opaque) +{ + QEMUFile *f = opaque; + + qemu_set_fd_handler(qemu_get_fd(f), NULL, NULL, NULL); + process_incoming_migration(f); +} + +void exec_start_incoming_migration(const char *command, Error **errp) +{ + QEMUFile *f; + + DPRINTF("Attempting to start an incoming migration\n"); + f = qemu_popen_cmd(command, "r"); + if(f == NULL) { + error_setg_errno(errp, errno, "failed to popen the migration source"); + return; + } + + qemu_set_fd_handler(qemu_get_fd(f), exec_accept_incoming_migration, NULL, + f); +} diff --git a/src/migration/fd.c b/src/migration/fd.c new file mode 100644 index 0000000..3e4bed0 --- /dev/null +++ b/src/migration/fd.c @@ -0,0 +1,88 @@ +/* + * QEMU live migration via generic fd + * + * Copyright Red Hat, Inc. 2009 + * + * Authors: + * Chris Lalancette <clalance@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu-common.h" +#include "qemu/main-loop.h" +#include "qemu/sockets.h" +#include "migration/migration.h" +#include "monitor/monitor.h" +#include "migration/qemu-file.h" +#include "block/block.h" + +//#define DEBUG_MIGRATION_FD + +#ifdef DEBUG_MIGRATION_FD +#define DPRINTF(fmt, ...) \ + do { printf("migration-fd: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static bool fd_is_socket(int fd) +{ + struct stat stat; + int ret = fstat(fd, &stat); + if (ret == -1) { + /* When in doubt say no */ + return false; + } + return S_ISSOCK(stat.st_mode); +} + +void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **errp) +{ + int fd = monitor_get_fd(cur_mon, fdname, errp); + if (fd == -1) { + return; + } + + if (fd_is_socket(fd)) { + s->file = qemu_fopen_socket(fd, "wb"); + } else { + s->file = qemu_fdopen(fd, "wb"); + } + + migrate_fd_connect(s); +} + +static void fd_accept_incoming_migration(void *opaque) +{ + QEMUFile *f = opaque; + + qemu_set_fd_handler(qemu_get_fd(f), NULL, NULL, NULL); + process_incoming_migration(f); +} + +void fd_start_incoming_migration(const char *infd, Error **errp) +{ + int fd; + QEMUFile *f; + + DPRINTF("Attempting to start an incoming migration via fd\n"); + + fd = strtol(infd, NULL, 0); + if (fd_is_socket(fd)) { + f = qemu_fopen_socket(fd, "rb"); + } else { + f = qemu_fdopen(fd, "rb"); + } + if(f == NULL) { + error_setg_errno(errp, errno, "failed to open the source descriptor"); + return; + } + + qemu_set_fd_handler(fd, fd_accept_incoming_migration, NULL, f); +} diff --git a/src/migration/migration.c b/src/migration/migration.c new file mode 100644 index 0000000..adc6b6f --- /dev/null +++ b/src/migration/migration.c @@ -0,0 +1,1773 @@ +/* + * QEMU live migration + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "sysemu/sysemu.h" +#include "block/block.h" +#include "qapi/qmp/qerror.h" +#include "qapi/util.h" +#include "qemu/sockets.h" +#include "qemu/rcu.h" +#include "migration/block.h" +#include "migration/postcopy-ram.h" +#include "qemu/thread.h" +#include "qmp-commands.h" +#include "trace.h" +#include "qapi-event.h" +#include "qom/cpu.h" +#include "exec/memory.h" +#include "exec/address-spaces.h" + +#define MAX_THROTTLE (32 << 20) /* Migration transfer speed throttling */ + +/* Amount of time to allocate to each "chunk" of bandwidth-throttled + * data. */ +#define BUFFER_DELAY 100 +#define XFER_LIMIT_RATIO (1000 / BUFFER_DELAY) + +/* Default compression thread count */ +#define DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT 8 +/* Default decompression thread count, usually decompression is at + * least 4 times as fast as compression.*/ +#define DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT 2 +/*0: means nocompress, 1: best speed, ... 9: best compress ratio */ +#define DEFAULT_MIGRATE_COMPRESS_LEVEL 1 +/* Define default autoconverge cpu throttle migration parameters */ +#define DEFAULT_MIGRATE_X_CPU_THROTTLE_INITIAL 20 +#define DEFAULT_MIGRATE_X_CPU_THROTTLE_INCREMENT 10 + +/* Migration XBZRLE default cache size */ +#define DEFAULT_MIGRATE_CACHE_SIZE (64 * 1024 * 1024) + +static NotifierList migration_state_notifiers = + NOTIFIER_LIST_INITIALIZER(migration_state_notifiers); + +static bool deferred_incoming; + +/* + * Current state of incoming postcopy; note this is not part of + * MigrationIncomingState since it's state is used during cleanup + * at the end as MIS is being freed. + */ +static PostcopyState incoming_postcopy_state; + +/* When we add fault tolerance, we could have several + migrations at once. For now we don't need to add + dynamic creation of migration */ + +/* For outgoing */ +MigrationState *migrate_get_current(void) +{ + static bool once; + static MigrationState current_migration = { + .state = MIGRATION_STATUS_NONE, + .bandwidth_limit = MAX_THROTTLE, + .xbzrle_cache_size = DEFAULT_MIGRATE_CACHE_SIZE, + .mbps = -1, + .parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL] = + DEFAULT_MIGRATE_COMPRESS_LEVEL, + .parameters[MIGRATION_PARAMETER_COMPRESS_THREADS] = + DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT, + .parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] = + DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT, + .parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] = + DEFAULT_MIGRATE_X_CPU_THROTTLE_INITIAL, + .parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] = + DEFAULT_MIGRATE_X_CPU_THROTTLE_INCREMENT, + }; + + if (!once) { + qemu_mutex_init(¤t_migration.src_page_req_mutex); + once = true; + } + return ¤t_migration; +} + +/* For incoming */ +static MigrationIncomingState *mis_current; + +MigrationIncomingState *migration_incoming_get_current(void) +{ + return mis_current; +} + +MigrationIncomingState *migration_incoming_state_new(QEMUFile* f) +{ + mis_current = g_new0(MigrationIncomingState, 1); + mis_current->from_src_file = f; + QLIST_INIT(&mis_current->loadvm_handlers); + qemu_mutex_init(&mis_current->rp_mutex); + qemu_event_init(&mis_current->main_thread_load_event, false); + + return mis_current; +} + +void migration_incoming_state_destroy(void) +{ + qemu_event_destroy(&mis_current->main_thread_load_event); + loadvm_free_handlers(mis_current); + g_free(mis_current); + mis_current = NULL; +} + + +typedef struct { + bool optional; + uint32_t size; + uint8_t runstate[100]; + RunState state; + bool received; +} GlobalState; + +static GlobalState global_state; + +int global_state_store(void) +{ + if (!runstate_store((char *)global_state.runstate, + sizeof(global_state.runstate))) { + error_report("runstate name too big: %s", global_state.runstate); + trace_migrate_state_too_big(); + return -EINVAL; + } + return 0; +} + +void global_state_store_running(void) +{ + const char *state = RunState_lookup[RUN_STATE_RUNNING]; + strncpy((char *)global_state.runstate, + state, sizeof(global_state.runstate)); +} + +static bool global_state_received(void) +{ + return global_state.received; +} + +static RunState global_state_get_runstate(void) +{ + return global_state.state; +} + +void global_state_set_optional(void) +{ + global_state.optional = true; +} + +static bool global_state_needed(void *opaque) +{ + GlobalState *s = opaque; + char *runstate = (char *)s->runstate; + + /* If it is not optional, it is mandatory */ + + if (s->optional == false) { + return true; + } + + /* If state is running or paused, it is not needed */ + + if (strcmp(runstate, "running") == 0 || + strcmp(runstate, "paused") == 0) { + return false; + } + + /* for any other state it is needed */ + return true; +} + +static int global_state_post_load(void *opaque, int version_id) +{ + GlobalState *s = opaque; + Error *local_err = NULL; + int r; + char *runstate = (char *)s->runstate; + + s->received = true; + trace_migrate_global_state_post_load(runstate); + + r = qapi_enum_parse(RunState_lookup, runstate, RUN_STATE_MAX, + -1, &local_err); + + if (r == -1) { + if (local_err) { + error_report_err(local_err); + } + return -EINVAL; + } + s->state = r; + + return 0; +} + +static void global_state_pre_save(void *opaque) +{ + GlobalState *s = opaque; + + trace_migrate_global_state_pre_save((char *)s->runstate); + s->size = strlen((char *)s->runstate) + 1; +} + +static const VMStateDescription vmstate_globalstate = { + .name = "globalstate", + .version_id = 1, + .minimum_version_id = 1, + .post_load = global_state_post_load, + .pre_save = global_state_pre_save, + .needed = global_state_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(size, GlobalState), + VMSTATE_BUFFER(runstate, GlobalState), + VMSTATE_END_OF_LIST() + }, +}; + +void register_global_state(void) +{ + /* We would use it independently that we receive it */ + strcpy((char *)&global_state.runstate, ""); + global_state.received = false; + vmstate_register(NULL, 0, &vmstate_globalstate, &global_state); +} + +static void migrate_generate_event(int new_state) +{ + if (migrate_use_events()) { + qapi_event_send_migration(new_state, &error_abort); + } +} + +/* + * Called on -incoming with a defer: uri. + * The migration can be started later after any parameters have been + * changed. + */ +static void deferred_incoming_migration(Error **errp) +{ + if (deferred_incoming) { + error_setg(errp, "Incoming migration already deferred"); + } + deferred_incoming = true; +} + +/* Request a range of pages from the source VM at the given + * start address. + * rbname: Name of the RAMBlock to request the page in, if NULL it's the same + * as the last request (a name must have been given previously) + * Start: Address offset within the RB + * Len: Length in bytes required - must be a multiple of pagesize + */ +void migrate_send_rp_req_pages(MigrationIncomingState *mis, const char *rbname, + ram_addr_t start, size_t len) +{ + uint8_t bufc[12 + 1 + 255]; /* start (8), len (4), rbname upto 256 */ + size_t msglen = 12; /* start + len */ + + *(uint64_t *)bufc = cpu_to_be64((uint64_t)start); + *(uint32_t *)(bufc + 8) = cpu_to_be32((uint32_t)len); + + if (rbname) { + int rbname_len = strlen(rbname); + assert(rbname_len < 256); + + bufc[msglen++] = rbname_len; + memcpy(bufc + msglen, rbname, rbname_len); + msglen += rbname_len; + migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES_ID, msglen, bufc); + } else { + migrate_send_rp_message(mis, MIG_RP_MSG_REQ_PAGES, msglen, bufc); + } +} + +void qemu_start_incoming_migration(const char *uri, Error **errp) +{ + const char *p; + + qapi_event_send_migration(MIGRATION_STATUS_SETUP, &error_abort); + if (!strcmp(uri, "defer")) { + deferred_incoming_migration(errp); + } else if (strstart(uri, "tcp:", &p)) { + tcp_start_incoming_migration(p, errp); +#ifdef CONFIG_RDMA + } else if (strstart(uri, "rdma:", &p)) { + rdma_start_incoming_migration(p, errp); +#endif +#if !defined(WIN32) + } else if (strstart(uri, "exec:", &p)) { + exec_start_incoming_migration(p, errp); + } else if (strstart(uri, "unix:", &p)) { + unix_start_incoming_migration(p, errp); + } else if (strstart(uri, "fd:", &p)) { + fd_start_incoming_migration(p, errp); +#endif + } else { + error_setg(errp, "unknown migration protocol: %s", uri); + } +} + +static void process_incoming_migration_co(void *opaque) +{ + QEMUFile *f = opaque; + Error *local_err = NULL; + MigrationIncomingState *mis; + PostcopyState ps; + int ret; + + mis = migration_incoming_state_new(f); + postcopy_state_set(POSTCOPY_INCOMING_NONE); + migrate_generate_event(MIGRATION_STATUS_ACTIVE); + + ret = qemu_loadvm_state(f); + + ps = postcopy_state_get(); + trace_process_incoming_migration_co_end(ret, ps); + if (ps != POSTCOPY_INCOMING_NONE) { + if (ps == POSTCOPY_INCOMING_ADVISE) { + /* + * Where a migration had postcopy enabled (and thus went to advise) + * but managed to complete within the precopy period, we can use + * the normal exit. + */ + postcopy_ram_incoming_cleanup(mis); + } else if (ret >= 0) { + /* + * Postcopy was started, cleanup should happen at the end of the + * postcopy thread. + */ + trace_process_incoming_migration_co_postcopy_end_main(); + return; + } + /* Else if something went wrong then just fall out of the normal exit */ + } + + qemu_fclose(f); + free_xbzrle_decoded_buf(); + migration_incoming_state_destroy(); + + if (ret < 0) { + migrate_generate_event(MIGRATION_STATUS_FAILED); + error_report("load of migration failed: %s", strerror(-ret)); + migrate_decompress_threads_join(); + exit(EXIT_FAILURE); + } + + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + migrate_generate_event(MIGRATION_STATUS_FAILED); + error_report_err(local_err); + migrate_decompress_threads_join(); + exit(EXIT_FAILURE); + } + + /* + * This must happen after all error conditions are dealt with and + * we're sure the VM is going to be running on this host. + */ + qemu_announce_self(); + + /* If global state section was not received or we are in running + state, we need to obey autostart. Any other state is set with + runstate_set. */ + + if (!global_state_received() || + global_state_get_runstate() == RUN_STATE_RUNNING) { + if (autostart) { + vm_start(); + } else { + runstate_set(RUN_STATE_PAUSED); + } + } else { + runstate_set(global_state_get_runstate()); + } + migrate_decompress_threads_join(); + /* + * This must happen after any state changes since as soon as an external + * observer sees this event they might start to prod at the VM assuming + * it's ready to use. + */ + migrate_generate_event(MIGRATION_STATUS_COMPLETED); +} + +void process_incoming_migration(QEMUFile *f) +{ + Coroutine *co = qemu_coroutine_create(process_incoming_migration_co); + int fd = qemu_get_fd(f); + + assert(fd != -1); + migrate_decompress_threads_create(); + qemu_set_nonblock(fd); + qemu_coroutine_enter(co, f); +} + +/* + * Send a message on the return channel back to the source + * of the migration. + */ +void migrate_send_rp_message(MigrationIncomingState *mis, + enum mig_rp_message_type message_type, + uint16_t len, void *data) +{ + trace_migrate_send_rp_message((int)message_type, len); + qemu_mutex_lock(&mis->rp_mutex); + qemu_put_be16(mis->to_src_file, (unsigned int)message_type); + qemu_put_be16(mis->to_src_file, len); + qemu_put_buffer(mis->to_src_file, data, len); + qemu_fflush(mis->to_src_file); + qemu_mutex_unlock(&mis->rp_mutex); +} + +/* + * Send a 'SHUT' message on the return channel with the given value + * to indicate that we've finished with the RP. Non-0 value indicates + * error. + */ +void migrate_send_rp_shut(MigrationIncomingState *mis, + uint32_t value) +{ + uint32_t buf; + + buf = cpu_to_be32(value); + migrate_send_rp_message(mis, MIG_RP_MSG_SHUT, sizeof(buf), &buf); +} + +/* + * Send a 'PONG' message on the return channel with the given value + * (normally in response to a 'PING') + */ +void migrate_send_rp_pong(MigrationIncomingState *mis, + uint32_t value) +{ + uint32_t buf; + + buf = cpu_to_be32(value); + migrate_send_rp_message(mis, MIG_RP_MSG_PONG, sizeof(buf), &buf); +} + +/* amount of nanoseconds we are willing to wait for migration to be down. + * the choice of nanoseconds is because it is the maximum resolution that + * get_clock() can achieve. It is an internal measure. All user-visible + * units must be in seconds */ +static uint64_t max_downtime = 300000000; + +uint64_t migrate_max_downtime(void) +{ + return max_downtime; +} + +MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp) +{ + MigrationCapabilityStatusList *head = NULL; + MigrationCapabilityStatusList *caps; + MigrationState *s = migrate_get_current(); + int i; + + caps = NULL; /* silence compiler warning */ + for (i = 0; i < MIGRATION_CAPABILITY_MAX; i++) { + if (head == NULL) { + head = g_malloc0(sizeof(*caps)); + caps = head; + } else { + caps->next = g_malloc0(sizeof(*caps)); + caps = caps->next; + } + caps->value = + g_malloc(sizeof(*caps->value)); + caps->value->capability = i; + caps->value->state = s->enabled_capabilities[i]; + } + + return head; +} + +MigrationParameters *qmp_query_migrate_parameters(Error **errp) +{ + MigrationParameters *params; + MigrationState *s = migrate_get_current(); + + params = g_malloc0(sizeof(*params)); + params->compress_level = s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL]; + params->compress_threads = + s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS]; + params->decompress_threads = + s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS]; + params->x_cpu_throttle_initial = + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL]; + params->x_cpu_throttle_increment = + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT]; + + return params; +} + +/* + * Return true if we're already in the middle of a migration + * (i.e. any of the active or setup states) + */ +static bool migration_is_setup_or_active(int state) +{ + switch (state) { + case MIGRATION_STATUS_ACTIVE: + case MIGRATION_STATUS_POSTCOPY_ACTIVE: + case MIGRATION_STATUS_SETUP: + return true; + + default: + return false; + + } +} + +static void get_xbzrle_cache_stats(MigrationInfo *info) +{ + if (migrate_use_xbzrle()) { + info->has_xbzrle_cache = true; + info->xbzrle_cache = g_malloc0(sizeof(*info->xbzrle_cache)); + info->xbzrle_cache->cache_size = migrate_xbzrle_cache_size(); + info->xbzrle_cache->bytes = xbzrle_mig_bytes_transferred(); + info->xbzrle_cache->pages = xbzrle_mig_pages_transferred(); + info->xbzrle_cache->cache_miss = xbzrle_mig_pages_cache_miss(); + info->xbzrle_cache->cache_miss_rate = xbzrle_mig_cache_miss_rate(); + info->xbzrle_cache->overflow = xbzrle_mig_pages_overflow(); + } +} + +MigrationInfo *qmp_query_migrate(Error **errp) +{ + MigrationInfo *info = g_malloc0(sizeof(*info)); + MigrationState *s = migrate_get_current(); + + switch (s->state) { + case MIGRATION_STATUS_NONE: + /* no migration has happened ever */ + break; + case MIGRATION_STATUS_SETUP: + info->has_status = true; + info->has_total_time = false; + break; + case MIGRATION_STATUS_ACTIVE: + case MIGRATION_STATUS_CANCELLING: + info->has_status = true; + info->has_total_time = true; + info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + - s->total_time; + info->has_expected_downtime = true; + info->expected_downtime = s->expected_downtime; + info->has_setup_time = true; + info->setup_time = s->setup_time; + + info->has_ram = true; + info->ram = g_malloc0(sizeof(*info->ram)); + info->ram->transferred = ram_bytes_transferred(); + info->ram->remaining = ram_bytes_remaining(); + info->ram->total = ram_bytes_total(); + info->ram->duplicate = dup_mig_pages_transferred(); + info->ram->skipped = skipped_mig_pages_transferred(); + info->ram->normal = norm_mig_pages_transferred(); + info->ram->normal_bytes = norm_mig_bytes_transferred(); + info->ram->dirty_pages_rate = s->dirty_pages_rate; + info->ram->mbps = s->mbps; + info->ram->dirty_sync_count = s->dirty_sync_count; + + if (blk_mig_active()) { + info->has_disk = true; + info->disk = g_malloc0(sizeof(*info->disk)); + info->disk->transferred = blk_mig_bytes_transferred(); + info->disk->remaining = blk_mig_bytes_remaining(); + info->disk->total = blk_mig_bytes_total(); + } + + if (cpu_throttle_active()) { + info->has_x_cpu_throttle_percentage = true; + info->x_cpu_throttle_percentage = cpu_throttle_get_percentage(); + } + + get_xbzrle_cache_stats(info); + break; + case MIGRATION_STATUS_POSTCOPY_ACTIVE: + /* Mostly the same as active; TODO add some postcopy stats */ + info->has_status = true; + info->has_total_time = true; + info->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + - s->total_time; + info->has_expected_downtime = true; + info->expected_downtime = s->expected_downtime; + info->has_setup_time = true; + info->setup_time = s->setup_time; + + info->has_ram = true; + info->ram = g_malloc0(sizeof(*info->ram)); + info->ram->transferred = ram_bytes_transferred(); + info->ram->remaining = ram_bytes_remaining(); + info->ram->total = ram_bytes_total(); + info->ram->duplicate = dup_mig_pages_transferred(); + info->ram->skipped = skipped_mig_pages_transferred(); + info->ram->normal = norm_mig_pages_transferred(); + info->ram->normal_bytes = norm_mig_bytes_transferred(); + info->ram->dirty_pages_rate = s->dirty_pages_rate; + info->ram->mbps = s->mbps; + + if (blk_mig_active()) { + info->has_disk = true; + info->disk = g_malloc0(sizeof(*info->disk)); + info->disk->transferred = blk_mig_bytes_transferred(); + info->disk->remaining = blk_mig_bytes_remaining(); + info->disk->total = blk_mig_bytes_total(); + } + + get_xbzrle_cache_stats(info); + break; + case MIGRATION_STATUS_COMPLETED: + get_xbzrle_cache_stats(info); + + info->has_status = true; + info->has_total_time = true; + info->total_time = s->total_time; + info->has_downtime = true; + info->downtime = s->downtime; + info->has_setup_time = true; + info->setup_time = s->setup_time; + + info->has_ram = true; + info->ram = g_malloc0(sizeof(*info->ram)); + info->ram->transferred = ram_bytes_transferred(); + info->ram->remaining = 0; + info->ram->total = ram_bytes_total(); + info->ram->duplicate = dup_mig_pages_transferred(); + info->ram->skipped = skipped_mig_pages_transferred(); + info->ram->normal = norm_mig_pages_transferred(); + info->ram->normal_bytes = norm_mig_bytes_transferred(); + info->ram->mbps = s->mbps; + info->ram->dirty_sync_count = s->dirty_sync_count; + break; + case MIGRATION_STATUS_FAILED: + info->has_status = true; + break; + case MIGRATION_STATUS_CANCELLED: + info->has_status = true; + break; + } + info->status = s->state; + + return info; +} + +void qmp_migrate_set_capabilities(MigrationCapabilityStatusList *params, + Error **errp) +{ + MigrationState *s = migrate_get_current(); + MigrationCapabilityStatusList *cap; + + if (migration_is_setup_or_active(s->state)) { + error_setg(errp, QERR_MIGRATION_ACTIVE); + return; + } + + for (cap = params; cap; cap = cap->next) { + s->enabled_capabilities[cap->value->capability] = cap->value->state; + } + + if (migrate_postcopy_ram()) { + if (migrate_use_compression()) { + /* The decompression threads asynchronously write into RAM + * rather than use the atomic copies needed to avoid + * userfaulting. It should be possible to fix the decompression + * threads for compatibility in future. + */ + error_report("Postcopy is not currently compatible with " + "compression"); + s->enabled_capabilities[MIGRATION_CAPABILITY_X_POSTCOPY_RAM] = + false; + } + } +} + +void qmp_migrate_set_parameters(bool has_compress_level, + int64_t compress_level, + bool has_compress_threads, + int64_t compress_threads, + bool has_decompress_threads, + int64_t decompress_threads, + bool has_x_cpu_throttle_initial, + int64_t x_cpu_throttle_initial, + bool has_x_cpu_throttle_increment, + int64_t x_cpu_throttle_increment, Error **errp) +{ + MigrationState *s = migrate_get_current(); + + if (has_compress_level && (compress_level < 0 || compress_level > 9)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "compress_level", + "is invalid, it should be in the range of 0 to 9"); + return; + } + if (has_compress_threads && + (compress_threads < 1 || compress_threads > 255)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "compress_threads", + "is invalid, it should be in the range of 1 to 255"); + return; + } + if (has_decompress_threads && + (decompress_threads < 1 || decompress_threads > 255)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "decompress_threads", + "is invalid, it should be in the range of 1 to 255"); + return; + } + if (has_x_cpu_throttle_initial && + (x_cpu_throttle_initial < 1 || x_cpu_throttle_initial > 99)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "x_cpu_throttle_initial", + "an integer in the range of 1 to 99"); + } + if (has_x_cpu_throttle_increment && + (x_cpu_throttle_increment < 1 || x_cpu_throttle_increment > 99)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "x_cpu_throttle_increment", + "an integer in the range of 1 to 99"); + } + + if (has_compress_level) { + s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL] = compress_level; + } + if (has_compress_threads) { + s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS] = compress_threads; + } + if (has_decompress_threads) { + s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS] = + decompress_threads; + } + if (has_x_cpu_throttle_initial) { + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL] = + x_cpu_throttle_initial; + } + + if (has_x_cpu_throttle_increment) { + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT] = + x_cpu_throttle_increment; + } +} + +void qmp_migrate_start_postcopy(Error **errp) +{ + MigrationState *s = migrate_get_current(); + + if (!migrate_postcopy_ram()) { + error_setg(errp, "Enable postcopy with migrate_set_capability before" + " the start of migration"); + return; + } + + if (s->state == MIGRATION_STATUS_NONE) { + error_setg(errp, "Postcopy must be started after migration has been" + " started"); + return; + } + /* + * we don't error if migration has finished since that would be racy + * with issuing this command. + */ + atomic_set(&s->start_postcopy, true); +} + +/* shared migration helpers */ + +static void migrate_set_state(MigrationState *s, int old_state, int new_state) +{ + if (atomic_cmpxchg(&s->state, old_state, new_state) == old_state) { + trace_migrate_set_state(new_state); + migrate_generate_event(new_state); + } +} + +static void migrate_fd_cleanup(void *opaque) +{ + MigrationState *s = opaque; + + qemu_bh_delete(s->cleanup_bh); + s->cleanup_bh = NULL; + + flush_page_queue(s); + + if (s->file) { + trace_migrate_fd_cleanup(); + qemu_mutex_unlock_iothread(); + if (s->migration_thread_running) { + qemu_thread_join(&s->thread); + s->migration_thread_running = false; + } + qemu_mutex_lock_iothread(); + + migrate_compress_threads_join(); + qemu_fclose(s->file); + s->file = NULL; + } + + assert((s->state != MIGRATION_STATUS_ACTIVE) && + (s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE)); + + if (s->state == MIGRATION_STATUS_CANCELLING) { + migrate_set_state(s, MIGRATION_STATUS_CANCELLING, + MIGRATION_STATUS_CANCELLED); + } + + notifier_list_notify(&migration_state_notifiers, s); +} + +void migrate_fd_error(MigrationState *s) +{ + trace_migrate_fd_error(); + assert(s->file == NULL); + migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_FAILED); + notifier_list_notify(&migration_state_notifiers, s); +} + +static void migrate_fd_cancel(MigrationState *s) +{ + int old_state ; + QEMUFile *f = migrate_get_current()->file; + trace_migrate_fd_cancel(); + + if (s->rp_state.from_dst_file) { + /* shutdown the rp socket, so causing the rp thread to shutdown */ + qemu_file_shutdown(s->rp_state.from_dst_file); + } + + do { + old_state = s->state; + if (!migration_is_setup_or_active(old_state)) { + break; + } + migrate_set_state(s, old_state, MIGRATION_STATUS_CANCELLING); + } while (s->state != MIGRATION_STATUS_CANCELLING); + + /* + * If we're unlucky the migration code might be stuck somewhere in a + * send/write while the network has failed and is waiting to timeout; + * if we've got shutdown(2) available then we can force it to quit. + * The outgoing qemu file gets closed in migrate_fd_cleanup that is + * called in a bh, so there is no race against this cancel. + */ + if (s->state == MIGRATION_STATUS_CANCELLING && f) { + qemu_file_shutdown(f); + } +} + +void add_migration_state_change_notifier(Notifier *notify) +{ + notifier_list_add(&migration_state_notifiers, notify); +} + +void remove_migration_state_change_notifier(Notifier *notify) +{ + notifier_remove(notify); +} + +bool migration_in_setup(MigrationState *s) +{ + return s->state == MIGRATION_STATUS_SETUP; +} + +bool migration_has_finished(MigrationState *s) +{ + return s->state == MIGRATION_STATUS_COMPLETED; +} + +bool migration_has_failed(MigrationState *s) +{ + return (s->state == MIGRATION_STATUS_CANCELLED || + s->state == MIGRATION_STATUS_FAILED); +} + +bool migration_in_postcopy(MigrationState *s) +{ + return (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE); +} + +MigrationState *migrate_init(const MigrationParams *params) +{ + MigrationState *s = migrate_get_current(); + + /* + * Reinitialise all migration state, except + * parameters/capabilities that the user set, and + * locks. + */ + s->bytes_xfer = 0; + s->xfer_limit = 0; + s->cleanup_bh = 0; + s->file = NULL; + s->state = MIGRATION_STATUS_NONE; + s->params = *params; + s->rp_state.from_dst_file = NULL; + s->rp_state.error = false; + 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->migration_thread_running = false; + s->last_req_rb = NULL; + + migrate_set_state(s, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP); + + QSIMPLEQ_INIT(&s->src_page_requests); + + s->total_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + return s; +} + +static GSList *migration_blockers; + +void migrate_add_blocker(Error *reason) +{ + migration_blockers = g_slist_prepend(migration_blockers, reason); +} + +void migrate_del_blocker(Error *reason) +{ + migration_blockers = g_slist_remove(migration_blockers, reason); +} + +void qmp_migrate_incoming(const char *uri, Error **errp) +{ + Error *local_err = NULL; + static bool once = true; + + if (!deferred_incoming) { + error_setg(errp, "For use with '-incoming defer'"); + return; + } + if (!once) { + error_setg(errp, "The incoming migration has already been started"); + } + + qemu_start_incoming_migration(uri, &local_err); + + if (local_err) { + error_propagate(errp, local_err); + return; + } + + once = false; +} + +void qmp_migrate(const char *uri, bool has_blk, bool blk, + bool has_inc, bool inc, bool has_detach, bool detach, + Error **errp) +{ + Error *local_err = NULL; + MigrationState *s = migrate_get_current(); + MigrationParams params; + const char *p; + + params.blk = has_blk && blk; + params.shared = has_inc && inc; + + if (migration_is_setup_or_active(s->state) || + s->state == MIGRATION_STATUS_CANCELLING) { + error_setg(errp, QERR_MIGRATION_ACTIVE); + return; + } + if (runstate_check(RUN_STATE_INMIGRATE)) { + error_setg(errp, "Guest is waiting for an incoming migration"); + return; + } + + if (qemu_savevm_state_blocked(errp)) { + return; + } + + if (migration_blockers) { + *errp = error_copy(migration_blockers->data); + return; + } + + /* We are starting a new migration, so we want to start in a clean + state. This change is only needed if previous migration + failed/was cancelled. We don't use migrate_set_state() because + we are setting the initial state, not changing it. */ + s->state = MIGRATION_STATUS_NONE; + + s = migrate_init(¶ms); + + if (strstart(uri, "tcp:", &p)) { + tcp_start_outgoing_migration(s, p, &local_err); +#ifdef CONFIG_RDMA + } else if (strstart(uri, "rdma:", &p)) { + rdma_start_outgoing_migration(s, p, &local_err); +#endif +#if !defined(WIN32) + } else if (strstart(uri, "exec:", &p)) { + exec_start_outgoing_migration(s, p, &local_err); + } else if (strstart(uri, "unix:", &p)) { + unix_start_outgoing_migration(s, p, &local_err); + } else if (strstart(uri, "fd:", &p)) { + fd_start_outgoing_migration(s, p, &local_err); +#endif + } else { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri", + "a valid migration protocol"); + migrate_set_state(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_FAILED); + return; + } + + if (local_err) { + migrate_fd_error(s); + error_propagate(errp, local_err); + return; + } +} + +void qmp_migrate_cancel(Error **errp) +{ + migrate_fd_cancel(migrate_get_current()); +} + +void qmp_migrate_set_cache_size(int64_t value, Error **errp) +{ + MigrationState *s = migrate_get_current(); + int64_t new_size; + + /* Check for truncation */ + if (value != (size_t)value) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cache size", + "exceeding address space"); + return; + } + + /* Cache should not be larger than guest ram size */ + if (value > ram_bytes_total()) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cache size", + "exceeds guest ram size "); + return; + } + + new_size = xbzrle_cache_resize(value); + if (new_size < 0) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "cache size", + "is smaller than page size"); + return; + } + + s->xbzrle_cache_size = new_size; +} + +int64_t qmp_query_migrate_cache_size(Error **errp) +{ + return migrate_xbzrle_cache_size(); +} + +void qmp_migrate_set_speed(int64_t value, Error **errp) +{ + MigrationState *s; + + if (value < 0) { + value = 0; + } + if (value > SIZE_MAX) { + value = SIZE_MAX; + } + + s = migrate_get_current(); + s->bandwidth_limit = value; + if (s->file) { + qemu_file_set_rate_limit(s->file, s->bandwidth_limit / XFER_LIMIT_RATIO); + } +} + +void qmp_migrate_set_downtime(double value, Error **errp) +{ + value *= 1e9; + value = MAX(0, MIN(UINT64_MAX, value)); + max_downtime = (uint64_t)value; +} + +bool migrate_postcopy_ram(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_X_POSTCOPY_RAM]; +} + +bool migrate_auto_converge(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_AUTO_CONVERGE]; +} + +bool migrate_zero_blocks(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_ZERO_BLOCKS]; +} + +bool migrate_use_compression(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_COMPRESS]; +} + +int migrate_compress_level(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->parameters[MIGRATION_PARAMETER_COMPRESS_LEVEL]; +} + +int migrate_compress_threads(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->parameters[MIGRATION_PARAMETER_COMPRESS_THREADS]; +} + +int migrate_decompress_threads(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->parameters[MIGRATION_PARAMETER_DECOMPRESS_THREADS]; +} + +bool migrate_use_events(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_EVENTS]; +} + +int migrate_use_xbzrle(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->enabled_capabilities[MIGRATION_CAPABILITY_XBZRLE]; +} + +int64_t migrate_xbzrle_cache_size(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->xbzrle_cache_size; +} + +/* migration thread support */ +/* + * Something bad happened to the RP stream, mark an error + * The caller shall print or trace something to indicate why + */ +static void mark_source_rp_bad(MigrationState *s) +{ + s->rp_state.error = true; +} + +static struct rp_cmd_args { + ssize_t len; /* -1 = variable */ + const char *name; +} rp_cmd_args[] = { + [MIG_RP_MSG_INVALID] = { .len = -1, .name = "INVALID" }, + [MIG_RP_MSG_SHUT] = { .len = 4, .name = "SHUT" }, + [MIG_RP_MSG_PONG] = { .len = 4, .name = "PONG" }, + [MIG_RP_MSG_REQ_PAGES] = { .len = 12, .name = "REQ_PAGES" }, + [MIG_RP_MSG_REQ_PAGES_ID] = { .len = -1, .name = "REQ_PAGES_ID" }, + [MIG_RP_MSG_MAX] = { .len = -1, .name = "MAX" }, +}; + +/* + * Process a request for pages received on the return path, + * We're allowed to send more than requested (e.g. to round to our page size) + * and we don't need to send pages that have already been sent. + */ +static void migrate_handle_rp_req_pages(MigrationState *ms, const char* rbname, + ram_addr_t start, size_t len) +{ + long our_host_ps = getpagesize(); + + trace_migrate_handle_rp_req_pages(rbname, start, len); + + /* + * Since we currently insist on matching page sizes, just sanity check + * we're being asked for whole host pages. + */ + if (start & (our_host_ps-1) || + (len & (our_host_ps-1))) { + error_report("%s: Misaligned page request, start: " RAM_ADDR_FMT + " len: %zd", __func__, start, len); + mark_source_rp_bad(ms); + return; + } + + if (ram_save_queue_pages(ms, rbname, start, len)) { + mark_source_rp_bad(ms); + } +} + +/* + * Handles messages sent on the return path towards the source VM + * + */ +static void *source_return_path_thread(void *opaque) +{ + MigrationState *ms = opaque; + QEMUFile *rp = ms->rp_state.from_dst_file; + uint16_t header_len, header_type; + const int max_len = 512; + uint8_t buf[max_len]; + uint32_t tmp32, sibling_error; + ram_addr_t start = 0; /* =0 to silence warning */ + size_t len = 0, expected_len; + int res; + + trace_source_return_path_thread_entry(); + while (!ms->rp_state.error && !qemu_file_get_error(rp) && + migration_is_setup_or_active(ms->state)) { + trace_source_return_path_thread_loop_top(); + header_type = qemu_get_be16(rp); + header_len = qemu_get_be16(rp); + + if (header_type >= MIG_RP_MSG_MAX || + header_type == MIG_RP_MSG_INVALID) { + error_report("RP: Received invalid message 0x%04x length 0x%04x", + header_type, header_len); + mark_source_rp_bad(ms); + goto out; + } + + if ((rp_cmd_args[header_type].len != -1 && + header_len != rp_cmd_args[header_type].len) || + header_len > max_len) { + error_report("RP: Received '%s' message (0x%04x) with" + "incorrect length %d expecting %zu", + rp_cmd_args[header_type].name, header_type, header_len, + (size_t)rp_cmd_args[header_type].len); + mark_source_rp_bad(ms); + goto out; + } + + /* We know we've got a valid header by this point */ + res = qemu_get_buffer(rp, buf, header_len); + if (res != header_len) { + error_report("RP: Failed reading data for message 0x%04x" + " read %d expected %d", + header_type, res, header_len); + mark_source_rp_bad(ms); + goto out; + } + + /* OK, we have the message and the data */ + switch (header_type) { + case MIG_RP_MSG_SHUT: + sibling_error = be32_to_cpup((uint32_t *)buf); + trace_source_return_path_thread_shut(sibling_error); + if (sibling_error) { + error_report("RP: Sibling indicated error %d", sibling_error); + mark_source_rp_bad(ms); + } + /* + * We'll let the main thread deal with closing the RP + * we could do a shutdown(2) on it, but we're the only user + * anyway, so there's nothing gained. + */ + goto out; + + case MIG_RP_MSG_PONG: + tmp32 = be32_to_cpup((uint32_t *)buf); + trace_source_return_path_thread_pong(tmp32); + break; + + case MIG_RP_MSG_REQ_PAGES: + start = be64_to_cpup((uint64_t *)buf); + len = be32_to_cpup((uint32_t *)(buf + 8)); + migrate_handle_rp_req_pages(ms, NULL, start, len); + break; + + case MIG_RP_MSG_REQ_PAGES_ID: + expected_len = 12 + 1; /* header + termination */ + + if (header_len >= expected_len) { + start = be64_to_cpup((uint64_t *)buf); + len = be32_to_cpup((uint32_t *)(buf + 8)); + /* Now we expect an idstr */ + tmp32 = buf[12]; /* Length of the following idstr */ + buf[13 + tmp32] = '\0'; + expected_len += tmp32; + } + if (header_len != expected_len) { + error_report("RP: Req_Page_id with length %d expecting %zd", + header_len, expected_len); + mark_source_rp_bad(ms); + goto out; + } + migrate_handle_rp_req_pages(ms, (char *)&buf[13], start, len); + break; + + default: + break; + } + } + if (qemu_file_get_error(rp)) { + trace_source_return_path_thread_bad_end(); + mark_source_rp_bad(ms); + } + + trace_source_return_path_thread_end(); +out: + ms->rp_state.from_dst_file = NULL; + qemu_fclose(rp); + return NULL; +} + +static int open_return_path_on_source(MigrationState *ms) +{ + + ms->rp_state.from_dst_file = qemu_file_get_return_path(ms->file); + if (!ms->rp_state.from_dst_file) { + return -1; + } + + trace_open_return_path_on_source(); + qemu_thread_create(&ms->rp_state.rp_thread, "return path", + source_return_path_thread, ms, QEMU_THREAD_JOINABLE); + + trace_open_return_path_on_source_continue(); + + return 0; +} + +/* Returns 0 if the RP was ok, otherwise there was an error on the RP */ +static int await_return_path_close_on_source(MigrationState *ms) +{ + /* + * If this is a normal exit then the destination will send a SHUT and the + * rp_thread will exit, however if there's an error we need to cause + * it to exit. + */ + if (qemu_file_get_error(ms->file) && ms->rp_state.from_dst_file) { + /* + * shutdown(2), if we have it, will cause it to unblock if it's stuck + * waiting for the destination. + */ + qemu_file_shutdown(ms->rp_state.from_dst_file); + mark_source_rp_bad(ms); + } + trace_await_return_path_close_on_source_joining(); + qemu_thread_join(&ms->rp_state.rp_thread); + trace_await_return_path_close_on_source_close(); + return ms->rp_state.error; +} + +/* + * Switch from normal iteration to postcopy + * Returns non-0 on error + */ +static int postcopy_start(MigrationState *ms, bool *old_vm_running) +{ + int ret; + const QEMUSizedBuffer *qsb; + int64_t time_at_stop = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + migrate_set_state(ms, MIGRATION_STATUS_ACTIVE, + MIGRATION_STATUS_POSTCOPY_ACTIVE); + + trace_postcopy_start(); + qemu_mutex_lock_iothread(); + trace_postcopy_start_set_run(); + + qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER); + *old_vm_running = runstate_is_running(); + global_state_store(); + ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); + + if (ret < 0) { + goto fail; + } + + /* + * Cause any non-postcopiable, but iterative devices to + * send out their final data. + */ + qemu_savevm_state_complete_precopy(ms->file, true); + + /* + * in Finish migrate and with the io-lock held everything should + * be quiet, but we've potentially still got dirty pages and we + * need to tell the destination to throw any pages it's already received + * that are dirty + */ + if (ram_postcopy_send_discard_bitmap(ms)) { + error_report("postcopy send discard bitmap failed"); + goto fail; + } + + /* + * send rest of state - note things that are doing postcopy + * will notice we're in POSTCOPY_ACTIVE and not actually + * wrap their state up here + */ + qemu_file_set_rate_limit(ms->file, INT64_MAX); + /* Ping just for debugging, helps line traces up */ + qemu_savevm_send_ping(ms->file, 2); + + /* + * While loading the device state we may trigger page transfer + * requests and the fd must be free to process those, and thus + * the destination must read the whole device state off the fd before + * it starts processing it. Unfortunately the ad-hoc migration format + * doesn't allow the destination to know the size to read without fully + * parsing it through each devices load-state code (especially the open + * coded devices that use get/put). + * So we wrap the device state up in a package with a length at the start; + * to do this we use a qemu_buf to hold the whole of the device state. + */ + QEMUFile *fb = qemu_bufopen("w", NULL); + if (!fb) { + error_report("Failed to create buffered file"); + goto fail; + } + + /* + * Make sure the receiver can get incoming pages before we send the rest + * of the state + */ + qemu_savevm_send_postcopy_listen(fb); + + qemu_savevm_state_complete_precopy(fb, false); + qemu_savevm_send_ping(fb, 3); + + qemu_savevm_send_postcopy_run(fb); + + /* <><> end of stuff going into the package */ + qsb = qemu_buf_get(fb); + + /* Now send that blob */ + if (qemu_savevm_send_packaged(ms->file, qsb)) { + goto fail_closefb; + } + qemu_fclose(fb); + ms->downtime = qemu_clock_get_ms(QEMU_CLOCK_REALTIME) - time_at_stop; + + qemu_mutex_unlock_iothread(); + + /* + * Although this ping is just for debug, it could potentially be + * used for getting a better measurement of downtime at the source. + */ + qemu_savevm_send_ping(ms->file, 4); + + ret = qemu_file_get_error(ms->file); + if (ret) { + error_report("postcopy_start: Migration stream errored"); + migrate_set_state(ms, MIGRATION_STATUS_POSTCOPY_ACTIVE, + MIGRATION_STATUS_FAILED); + } + + return ret; + +fail_closefb: + qemu_fclose(fb); +fail: + migrate_set_state(ms, MIGRATION_STATUS_POSTCOPY_ACTIVE, + MIGRATION_STATUS_FAILED); + qemu_mutex_unlock_iothread(); + return -1; +} + +/** + * migration_completion: Used by migration_thread when there's not much left. + * The caller 'breaks' the loop when this returns. + * + * @s: Current migration state + * @current_active_state: The migration state we expect to be in + * @*old_vm_running: Pointer to old_vm_running flag + * @*start_time: Pointer to time to update + */ +static void migration_completion(MigrationState *s, int current_active_state, + bool *old_vm_running, + int64_t *start_time) +{ + int ret; + + if (s->state == MIGRATION_STATUS_ACTIVE) { + qemu_mutex_lock_iothread(); + *start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER); + *old_vm_running = runstate_is_running(); + ret = global_state_store(); + + if (!ret) { + ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); + if (ret >= 0) { + qemu_file_set_rate_limit(s->file, INT64_MAX); + qemu_savevm_state_complete_precopy(s->file, false); + } + } + qemu_mutex_unlock_iothread(); + + if (ret < 0) { + goto fail; + } + } else if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + trace_migration_completion_postcopy_end(); + + qemu_savevm_state_complete_postcopy(s->file); + trace_migration_completion_postcopy_end_after_complete(); + } + + /* + * If rp was opened we must clean up the thread before + * cleaning everything else up (since if there are no failures + * it will wait for the destination to send it's status in + * a SHUT command). + * Postcopy opens rp if enabled (even if it's not avtivated) + */ + if (migrate_postcopy_ram()) { + int rp_error; + trace_migration_completion_postcopy_end_before_rp(); + rp_error = await_return_path_close_on_source(s); + trace_migration_completion_postcopy_end_after_rp(rp_error); + if (rp_error) { + goto fail; + } + } + + if (qemu_file_get_error(s->file)) { + trace_migration_completion_file_err(); + goto fail; + } + + migrate_set_state(s, current_active_state, MIGRATION_STATUS_COMPLETED); + return; + +fail: + migrate_set_state(s, current_active_state, MIGRATION_STATUS_FAILED); +} + +/* + * Master migration thread on the source VM. + * It drives the migration and pumps the data down the outgoing channel. + */ +static void *migration_thread(void *opaque) +{ + MigrationState *s = opaque; + /* Used by the bandwidth calcs, updated later */ + 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; + int64_t start_time = initial_time; + int64_t end_time; + bool old_vm_running = false; + bool entered_postcopy = false; + /* The active state we expect to be in; ACTIVE or POSTCOPY_ACTIVE */ + enum MigrationStatus current_active_state = MIGRATION_STATUS_ACTIVE; + + rcu_register_thread(); + + qemu_savevm_state_header(s->file); + + if (migrate_postcopy_ram()) { + /* Now tell the dest that it should open its end so it can reply */ + qemu_savevm_send_open_return_path(s->file); + + /* And do a ping that will make stuff easier to debug */ + qemu_savevm_send_ping(s->file, 1); + + /* + * Tell the destination that we *might* want to do postcopy later; + * if the other end can't do postcopy it should fail now, nice and + * early. + */ + qemu_savevm_send_postcopy_advise(s->file); + } + + qemu_savevm_state_begin(s->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, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE); + + trace_migration_thread_setup_complete(); + + while (s->state == MIGRATION_STATUS_ACTIVE || + s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + int64_t current_time; + uint64_t pending_size; + + if (!qemu_file_rate_limit(s->file)) { + uint64_t pend_post, pend_nonpost; + + qemu_savevm_state_pending(s->file, max_size, &pend_nonpost, + &pend_post); + pending_size = pend_nonpost + pend_post; + trace_migrate_pending(pending_size, max_size, + pend_post, pend_nonpost); + if (pending_size && pending_size >= max_size) { + /* Still a significant amount to transfer */ + + if (migrate_postcopy_ram() && + s->state != MIGRATION_STATUS_POSTCOPY_ACTIVE && + pend_nonpost <= max_size && + atomic_read(&s->start_postcopy)) { + + if (!postcopy_start(s, &old_vm_running)) { + current_active_state = MIGRATION_STATUS_POSTCOPY_ACTIVE; + entered_postcopy = true; + } + + continue; + } + /* Just another iteration step */ + qemu_savevm_state_iterate(s->file, entered_postcopy); + } else { + trace_migration_thread_low_pending(pending_size); + migration_completion(s, current_active_state, + &old_vm_running, &start_time); + break; + } + } + + if (qemu_file_get_error(s->file)) { + migrate_set_state(s, current_active_state, MIGRATION_STATUS_FAILED); + trace_migration_thread_file_err(); + break; + } + current_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + if (current_time >= initial_time + BUFFER_DELAY) { + uint64_t transferred_bytes = qemu_ftell(s->file) - initial_bytes; + uint64_t time_spent = current_time - initial_time; + double bandwidth = (double)transferred_bytes / time_spent; + max_size = bandwidth * migrate_max_downtime() / 1000000; + + s->mbps = time_spent ? (((double) transferred_bytes * 8.0) / + ((double) time_spent / 1000.0)) / 1000.0 / 1000.0 : -1; + + trace_migrate_transferred(transferred_bytes, time_spent, + bandwidth, max_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; + } + + qemu_file_reset_rate_limit(s->file); + initial_time = current_time; + initial_bytes = qemu_ftell(s->file); + } + if (qemu_file_rate_limit(s->file)) { + /* usleep expects microseconds */ + g_usleep((initial_time + BUFFER_DELAY - current_time)*1000); + } + } + + trace_migration_thread_after_loop(); + /* If we enabled cpu throttling for auto-converge, turn it off. */ + cpu_throttle_stop(); + end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + + qemu_mutex_lock_iothread(); + qemu_savevm_state_cleanup(); + if (s->state == MIGRATION_STATUS_COMPLETED) { + uint64_t transferred_bytes = qemu_ftell(s->file); + s->total_time = end_time - s->total_time; + if (!entered_postcopy) { + s->downtime = end_time - start_time; + } + if (s->total_time) { + s->mbps = (((double) transferred_bytes * 8.0) / + ((double) s->total_time)) / 1000; + } + runstate_set(RUN_STATE_POSTMIGRATE); + } else { + if (old_vm_running && !entered_postcopy) { + vm_start(); + } + } + qemu_bh_schedule(s->cleanup_bh); + qemu_mutex_unlock_iothread(); + + rcu_unregister_thread(); + return NULL; +} + +void migrate_fd_connect(MigrationState *s) +{ + /* This is a best 1st approximation. ns to ms */ + s->expected_downtime = max_downtime/1000000; + s->cleanup_bh = qemu_bh_new(migrate_fd_cleanup, s); + + qemu_file_set_rate_limit(s->file, + s->bandwidth_limit / XFER_LIMIT_RATIO); + + /* Notify before starting migration thread */ + notifier_list_notify(&migration_state_notifiers, s); + + /* + * Open the return path; currently for postcopy but other things might + * also want it. + */ + if (migrate_postcopy_ram()) { + if (open_return_path_on_source(s)) { + error_report("Unable to open return-path for postcopy"); + migrate_set_state(s, MIGRATION_STATUS_SETUP, + MIGRATION_STATUS_FAILED); + migrate_fd_cleanup(s); + return; + } + } + + migrate_compress_threads_create(); + qemu_thread_create(&s->thread, "migration", migration_thread, s, + QEMU_THREAD_JOINABLE); + s->migration_thread_running = true; +} + +PostcopyState postcopy_state_get(void) +{ + return atomic_mb_read(&incoming_postcopy_state); +} + +/* Set the state and return the old state */ +PostcopyState postcopy_state_set(PostcopyState new_state) +{ + return atomic_xchg(&incoming_postcopy_state, new_state); +} + diff --git a/src/migration/postcopy-ram.c b/src/migration/postcopy-ram.c new file mode 100644 index 0000000..3946aa9 --- /dev/null +++ b/src/migration/postcopy-ram.c @@ -0,0 +1,761 @@ +/* + * Postcopy migration for RAM + * + * Copyright 2013-2015 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Dave Gilbert <dgilbert@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +/* + * Postcopy is a migration technique where the execution flips from the + * source to the destination before all the data has been copied. + */ + +#include <glib.h> +#include <stdio.h> +#include <unistd.h> + +#include "qemu-common.h" +#include "migration/migration.h" +#include "migration/postcopy-ram.h" +#include "sysemu/sysemu.h" +#include "sysemu/balloon.h" +#include "qemu/error-report.h" +#include "trace.h" + +/* Arbitrary limit on size of each discard command, + * keeps them around ~200 bytes + */ +#define MAX_DISCARDS_PER_COMMAND 12 + +struct PostcopyDiscardState { + const char *ramblock_name; + uint64_t offset; /* Bitmap entry for the 1st bit of this RAMBlock */ + uint16_t cur_entry; + /* + * Start and length of a discard range (bytes) + */ + uint64_t start_list[MAX_DISCARDS_PER_COMMAND]; + uint64_t length_list[MAX_DISCARDS_PER_COMMAND]; + unsigned int nsentwords; + unsigned int nsentcmds; +}; + +/* Postcopy needs to detect accesses to pages that haven't yet been copied + * across, and efficiently map new pages in, the techniques for doing this + * are target OS specific. + */ +#if defined(__linux__) + +#include <poll.h> +#include <sys/eventfd.h> +#include <sys/mman.h> +#include <sys/ioctl.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <asm/types.h> /* for __u64 */ +#endif + +#if defined(__linux__) && defined(__NR_userfaultfd) +#include <linux/userfaultfd.h> + +static bool ufd_version_check(int ufd) +{ + struct uffdio_api api_struct; + uint64_t ioctl_mask; + + api_struct.api = UFFD_API; + api_struct.features = 0; + if (ioctl(ufd, UFFDIO_API, &api_struct)) { + error_report("postcopy_ram_supported_by_host: UFFDIO_API failed: %s", + strerror(errno)); + return false; + } + + ioctl_mask = (__u64)1 << _UFFDIO_REGISTER | + (__u64)1 << _UFFDIO_UNREGISTER; + if ((api_struct.ioctls & ioctl_mask) != ioctl_mask) { + error_report("Missing userfault features: %" PRIx64, + (uint64_t)(~api_struct.ioctls & ioctl_mask)); + return false; + } + + return true; +} + +/* + * Note: This has the side effect of munlock'ing all of RAM, that's + * normally fine since if the postcopy succeeds it gets turned back on at the + * end. + */ +bool postcopy_ram_supported_by_host(void) +{ + long pagesize = getpagesize(); + int ufd = -1; + bool ret = false; /* Error unless we change it */ + void *testarea = NULL; + struct uffdio_register reg_struct; + struct uffdio_range range_struct; + uint64_t feature_mask; + + if ((1ul << qemu_target_page_bits()) > pagesize) { + error_report("Target page size bigger than host page size"); + goto out; + } + + ufd = syscall(__NR_userfaultfd, O_CLOEXEC); + if (ufd == -1) { + error_report("%s: userfaultfd not available: %s", __func__, + strerror(errno)); + goto out; + } + + /* Version and features check */ + if (!ufd_version_check(ufd)) { + goto out; + } + + /* + * userfault and mlock don't go together; we'll put it back later if + * it was enabled. + */ + if (munlockall()) { + error_report("%s: munlockall: %s", __func__, strerror(errno)); + return -1; + } + + /* + * We need to check that the ops we need are supported on anon memory + * To do that we need to register a chunk and see the flags that + * are returned. + */ + testarea = mmap(NULL, pagesize, PROT_READ | PROT_WRITE, MAP_PRIVATE | + MAP_ANONYMOUS, -1, 0); + if (testarea == MAP_FAILED) { + error_report("%s: Failed to map test area: %s", __func__, + strerror(errno)); + goto out; + } + g_assert(((size_t)testarea & (pagesize-1)) == 0); + + reg_struct.range.start = (uintptr_t)testarea; + reg_struct.range.len = pagesize; + reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING; + + if (ioctl(ufd, UFFDIO_REGISTER, ®_struct)) { + error_report("%s userfault register: %s", __func__, strerror(errno)); + goto out; + } + + range_struct.start = (uintptr_t)testarea; + range_struct.len = pagesize; + if (ioctl(ufd, UFFDIO_UNREGISTER, &range_struct)) { + error_report("%s userfault unregister: %s", __func__, strerror(errno)); + goto out; + } + + feature_mask = (__u64)1 << _UFFDIO_WAKE | + (__u64)1 << _UFFDIO_COPY | + (__u64)1 << _UFFDIO_ZEROPAGE; + if ((reg_struct.ioctls & feature_mask) != feature_mask) { + error_report("Missing userfault map features: %" PRIx64, + (uint64_t)(~reg_struct.ioctls & feature_mask)); + goto out; + } + + /* Success! */ + ret = true; +out: + if (testarea) { + munmap(testarea, pagesize); + } + if (ufd != -1) { + close(ufd); + } + return ret; +} + +/** + * postcopy_ram_discard_range: Discard a range of memory. + * We can assume that if we've been called postcopy_ram_hosttest returned true. + * + * @mis: Current incoming migration state. + * @start, @length: range of memory to discard. + * + * returns: 0 on success. + */ +int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, + size_t length) +{ + trace_postcopy_ram_discard_range(start, length); + if (madvise(start, length, MADV_DONTNEED)) { + error_report("%s MADV_DONTNEED: %s", __func__, strerror(errno)); + return -1; + } + + return 0; +} + +/* + * Setup an area of RAM so that it *can* be used for postcopy later; this + * must be done right at the start prior to pre-copy. + * opaque should be the MIS. + */ +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); + + /* + * We need the whole of RAM to be truly empty for postcopy, so things + * like ROMs and any data tables built during init must be zero'd + * - we're going to get the copy from the source anyway. + * (Precopy will just overwrite this data, so doesn't need the discard) + */ + if (postcopy_ram_discard_range(mis, host_addr, length)) { + return -1; + } + + return 0; +} + +/* + * At the end of migration, undo the effects of init_range + * opaque should be the MIS. + */ +static int cleanup_range(const char *block_name, void *host_addr, + ram_addr_t offset, ram_addr_t length, void *opaque) +{ + MigrationIncomingState *mis = opaque; + struct uffdio_range range_struct; + trace_postcopy_cleanup_range(block_name, host_addr, offset, length); + + /* + * We turned off hugepage for the precopy stage with postcopy enabled + * we can turn it back on now. + */ + qemu_madvise(host_addr, length, QEMU_MADV_HUGEPAGE); + + /* + * We can also turn off userfault now since we should have all the + * pages. It can be useful to leave it on to debug postcopy + * if you're not sure it's always getting every page. + */ + range_struct.start = (uintptr_t)host_addr; + range_struct.len = length; + + if (ioctl(mis->userfault_fd, UFFDIO_UNREGISTER, &range_struct)) { + error_report("%s: userfault unregister %s", __func__, strerror(errno)); + + return -1; + } + + return 0; +} + +/* + * Initialise postcopy-ram, setting the RAM to a state where we can go into + * postcopy later; must be called prior to any precopy. + * called from arch_init's similarly named ram_postcopy_incoming_init + */ +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages) +{ + if (qemu_ram_foreach_block(init_range, mis)) { + return -1; + } + + return 0; +} + +/* + * At the end of a migration where postcopy_ram_incoming_init was called. + */ +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) +{ + trace_postcopy_ram_incoming_cleanup_entry(); + + if (mis->have_fault_thread) { + uint64_t tmp64; + + if (qemu_ram_foreach_block(cleanup_range, mis)) { + return -1; + } + /* + * Tell the fault_thread to exit, it's an eventfd that should + * currently be at 0, we're going to increment it to 1 + */ + tmp64 = 1; + if (write(mis->userfault_quit_fd, &tmp64, 8) == 8) { + trace_postcopy_ram_incoming_cleanup_join(); + qemu_thread_join(&mis->fault_thread); + } else { + /* Not much we can do here, but may as well report it */ + error_report("%s: incrementing userfault_quit_fd: %s", __func__, + strerror(errno)); + } + trace_postcopy_ram_incoming_cleanup_closeuf(); + close(mis->userfault_fd); + close(mis->userfault_quit_fd); + mis->have_fault_thread = false; + } + + qemu_balloon_inhibit(false); + + if (enable_mlock) { + if (os_mlock() < 0) { + error_report("mlock: %s", strerror(errno)); + /* + * It doesn't feel right to fail at this point, we have a valid + * VM state. + */ + } + } + + postcopy_state_set(POSTCOPY_INCOMING_END); + migrate_send_rp_shut(mis, qemu_file_get_error(mis->from_src_file) != 0); + + if (mis->postcopy_tmp_page) { + munmap(mis->postcopy_tmp_page, getpagesize()); + mis->postcopy_tmp_page = NULL; + } + trace_postcopy_ram_incoming_cleanup_exit(); + return 0; +} + +/* + * Disable huge pages on an area + */ +static int nhp_range(const char *block_name, void *host_addr, + ram_addr_t offset, ram_addr_t length, void *opaque) +{ + trace_postcopy_nhp_range(block_name, host_addr, offset, length); + + /* + * Before we do discards we need to ensure those discards really + * do delete areas of the page, even if THP thinks a hugepage would + * be a good idea, so force hugepages off. + */ + qemu_madvise(host_addr, length, QEMU_MADV_NOHUGEPAGE); + + return 0; +} + +/* + * Userfault requires us to mark RAM as NOHUGEPAGE prior to discard + * however leaving it until after precopy means that most of the precopy + * data is still THPd + */ +int postcopy_ram_prepare_discard(MigrationIncomingState *mis) +{ + if (qemu_ram_foreach_block(nhp_range, mis)) { + return -1; + } + + postcopy_state_set(POSTCOPY_INCOMING_DISCARD); + + return 0; +} + +/* + * Mark the given area of RAM as requiring notification to unwritten areas + * Used as a callback on qemu_ram_foreach_block. + * host_addr: Base of area to mark + * offset: Offset in the whole ram arena + * length: Length of the section + * opaque: MigrationIncomingState pointer + * Returns 0 on success + */ +static int ram_block_enable_notify(const char *block_name, void *host_addr, + ram_addr_t offset, ram_addr_t length, + void *opaque) +{ + MigrationIncomingState *mis = opaque; + struct uffdio_register reg_struct; + + reg_struct.range.start = (uintptr_t)host_addr; + reg_struct.range.len = length; + reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING; + + /* Now tell our userfault_fd that it's responsible for this area */ + if (ioctl(mis->userfault_fd, UFFDIO_REGISTER, ®_struct)) { + error_report("%s userfault register: %s", __func__, strerror(errno)); + return -1; + } + + return 0; +} + +/* + * Handle faults detected by the USERFAULT markings + */ +static void *postcopy_ram_fault_thread(void *opaque) +{ + MigrationIncomingState *mis = opaque; + struct uffd_msg msg; + int ret; + size_t hostpagesize = getpagesize(); + RAMBlock *rb = NULL; + RAMBlock *last_rb = NULL; /* last RAMBlock we sent part of */ + + trace_postcopy_ram_fault_thread_entry(); + qemu_sem_post(&mis->fault_thread_sem); + + while (true) { + ram_addr_t rb_offset; + ram_addr_t in_raspace; + struct pollfd pfd[2]; + + /* + * We're mainly waiting for the kernel to give us a faulting HVA, + * however we can be told to quit via userfault_quit_fd which is + * an eventfd + */ + pfd[0].fd = mis->userfault_fd; + pfd[0].events = POLLIN; + pfd[0].revents = 0; + pfd[1].fd = mis->userfault_quit_fd; + pfd[1].events = POLLIN; /* Waiting for eventfd to go positive */ + pfd[1].revents = 0; + + if (poll(pfd, 2, -1 /* Wait forever */) == -1) { + error_report("%s: userfault poll: %s", __func__, strerror(errno)); + break; + } + + if (pfd[1].revents) { + trace_postcopy_ram_fault_thread_quit(); + break; + } + + ret = read(mis->userfault_fd, &msg, sizeof(msg)); + if (ret != sizeof(msg)) { + if (errno == EAGAIN) { + /* + * if a wake up happens on the other thread just after + * the poll, there is nothing to read. + */ + continue; + } + if (ret < 0) { + error_report("%s: Failed to read full userfault message: %s", + __func__, strerror(errno)); + break; + } else { + error_report("%s: Read %d bytes from userfaultfd expected %zd", + __func__, ret, sizeof(msg)); + break; /* Lost alignment, don't know what we'd read next */ + } + } + if (msg.event != UFFD_EVENT_PAGEFAULT) { + error_report("%s: Read unexpected event %ud from userfaultfd", + __func__, msg.event); + continue; /* It's not a page fault, shouldn't happen */ + } + + rb = qemu_ram_block_from_host( + (void *)(uintptr_t)msg.arg.pagefault.address, + true, &in_raspace, &rb_offset); + if (!rb) { + error_report("postcopy_ram_fault_thread: Fault outside guest: %" + PRIx64, (uint64_t)msg.arg.pagefault.address); + break; + } + + rb_offset &= ~(hostpagesize - 1); + trace_postcopy_ram_fault_thread_request(msg.arg.pagefault.address, + qemu_ram_get_idstr(rb), + rb_offset); + + /* + * Send the request to the source - we want to request one + * of our host page sizes (which is >= TPS) + */ + if (rb != last_rb) { + last_rb = rb; + migrate_send_rp_req_pages(mis, qemu_ram_get_idstr(rb), + rb_offset, hostpagesize); + } else { + /* Save some space */ + migrate_send_rp_req_pages(mis, NULL, + rb_offset, hostpagesize); + } + } + trace_postcopy_ram_fault_thread_exit(); + return NULL; +} + +int postcopy_ram_enable_notify(MigrationIncomingState *mis) +{ + /* Open the fd for the kernel to give us userfaults */ + mis->userfault_fd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (mis->userfault_fd == -1) { + error_report("%s: Failed to open userfault fd: %s", __func__, + strerror(errno)); + return -1; + } + + /* + * Although the host check already tested the API, we need to + * do the check again as an ABI handshake on the new fd. + */ + if (!ufd_version_check(mis->userfault_fd)) { + return -1; + } + + /* Now an eventfd we use to tell the fault-thread to quit */ + mis->userfault_quit_fd = eventfd(0, EFD_CLOEXEC); + if (mis->userfault_quit_fd == -1) { + error_report("%s: Opening userfault_quit_fd: %s", __func__, + strerror(errno)); + close(mis->userfault_fd); + return -1; + } + + qemu_sem_init(&mis->fault_thread_sem, 0); + qemu_thread_create(&mis->fault_thread, "postcopy/fault", + postcopy_ram_fault_thread, mis, QEMU_THREAD_JOINABLE); + qemu_sem_wait(&mis->fault_thread_sem); + qemu_sem_destroy(&mis->fault_thread_sem); + mis->have_fault_thread = true; + + /* Mark so that we get notified of accesses to unwritten areas */ + if (qemu_ram_foreach_block(ram_block_enable_notify, mis)) { + return -1; + } + + /* + * Ballooning can mark pages as absent while we're postcopying + * that would cause false userfaults. + */ + qemu_balloon_inhibit(true); + + trace_postcopy_ram_enable_notify(); + + return 0; +} + +/* + * Place a host page (from) at (host) atomically + * returns 0 on success + */ +int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from) +{ + struct uffdio_copy copy_struct; + + copy_struct.dst = (uint64_t)(uintptr_t)host; + copy_struct.src = (uint64_t)(uintptr_t)from; + copy_struct.len = getpagesize(); + copy_struct.mode = 0; + + /* copy also acks to the kernel waking the stalled thread up + * TODO: We can inhibit that ack and only do it if it was requested + * which would be slightly cheaper, but we'd have to be careful + * of the order of updating our page state. + */ + if (ioctl(mis->userfault_fd, UFFDIO_COPY, ©_struct)) { + int e = errno; + error_report("%s: %s copy host: %p from: %p", + __func__, strerror(e), host, from); + + return -e; + } + + trace_postcopy_place_page(host); + return 0; +} + +/* + * Place a zero page at (host) atomically + * returns 0 on success + */ +int postcopy_place_page_zero(MigrationIncomingState *mis, void *host) +{ + struct uffdio_zeropage zero_struct; + + zero_struct.range.start = (uint64_t)(uintptr_t)host; + zero_struct.range.len = getpagesize(); + zero_struct.mode = 0; + + if (ioctl(mis->userfault_fd, UFFDIO_ZEROPAGE, &zero_struct)) { + int e = errno; + error_report("%s: %s zero host: %p", + __func__, strerror(e), host); + + return -e; + } + + trace_postcopy_place_page_zero(host); + return 0; +} + +/* + * Returns a target page of memory that can be mapped at a later point in time + * using postcopy_place_page + * The same address is used repeatedly, postcopy_place_page just takes the + * backing page away. + * Returns: Pointer to allocated page + * + */ +void *postcopy_get_tmp_page(MigrationIncomingState *mis) +{ + if (!mis->postcopy_tmp_page) { + mis->postcopy_tmp_page = mmap(NULL, getpagesize(), + PROT_READ | PROT_WRITE, MAP_PRIVATE | + MAP_ANONYMOUS, -1, 0); + if (!mis->postcopy_tmp_page) { + error_report("%s: %s", __func__, strerror(errno)); + return NULL; + } + } + + return mis->postcopy_tmp_page; +} + +#else +/* No target OS support, stubs just fail */ +bool postcopy_ram_supported_by_host(void) +{ + error_report("%s: No OS support", __func__); + return false; +} + +int postcopy_ram_incoming_init(MigrationIncomingState *mis, size_t ram_pages) +{ + error_report("postcopy_ram_incoming_init: No OS support"); + return -1; +} + +int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) +{ + assert(0); + return -1; +} + +int postcopy_ram_discard_range(MigrationIncomingState *mis, uint8_t *start, + size_t length) +{ + assert(0); + return -1; +} + +int postcopy_ram_prepare_discard(MigrationIncomingState *mis) +{ + assert(0); + return -1; +} + +int postcopy_ram_enable_notify(MigrationIncomingState *mis) +{ + assert(0); + return -1; +} + +int postcopy_place_page(MigrationIncomingState *mis, void *host, void *from) +{ + assert(0); + return -1; +} + +int postcopy_place_page_zero(MigrationIncomingState *mis, void *host) +{ + assert(0); + return -1; +} + +void *postcopy_get_tmp_page(MigrationIncomingState *mis) +{ + assert(0); + return NULL; +} + +#endif + +/* ------------------------------------------------------------------------- */ + +/** + * postcopy_discard_send_init: Called at the start of each RAMBlock before + * asking to discard individual ranges. + * + * @ms: The current migration state. + * @offset: the bitmap offset of the named RAMBlock in the migration + * bitmap. + * @name: RAMBlock that discards will operate on. + * + * returns: a new PDS. + */ +PostcopyDiscardState *postcopy_discard_send_init(MigrationState *ms, + unsigned long offset, + const char *name) +{ + PostcopyDiscardState *res = g_malloc0(sizeof(PostcopyDiscardState)); + + if (res) { + res->ramblock_name = name; + res->offset = offset; + } + + return res; +} + +/** + * postcopy_discard_send_range: Called by the bitmap code for each chunk to + * discard. May send a discard message, may just leave it queued to + * be sent later. + * + * @ms: Current migration state. + * @pds: Structure initialised by postcopy_discard_send_init(). + * @start,@length: a range of pages in the migration bitmap in the + * RAM block passed to postcopy_discard_send_init() (length=1 is one page) + */ +void postcopy_discard_send_range(MigrationState *ms, PostcopyDiscardState *pds, + unsigned long start, unsigned long length) +{ + size_t tp_bits = qemu_target_page_bits(); + /* 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; + trace_postcopy_discard_send_range(pds->ramblock_name, start, length); + pds->cur_entry++; + pds->nsentwords++; + + if (pds->cur_entry == MAX_DISCARDS_PER_COMMAND) { + /* Full set, ship it! */ + qemu_savevm_send_postcopy_ram_discard(ms->file, pds->ramblock_name, + pds->cur_entry, + pds->start_list, + pds->length_list); + pds->nsentcmds++; + pds->cur_entry = 0; + } +} + +/** + * postcopy_discard_send_finish: Called at the end of each RAMBlock by the + * bitmap code. Sends any outstanding discard messages, frees the PDS + * + * @ms: Current migration state. + * @pds: Structure initialised by postcopy_discard_send_init(). + */ +void postcopy_discard_send_finish(MigrationState *ms, PostcopyDiscardState *pds) +{ + /* Anything unsent? */ + if (pds->cur_entry) { + qemu_savevm_send_postcopy_ram_discard(ms->file, pds->ramblock_name, + pds->cur_entry, + pds->start_list, + pds->length_list); + pds->nsentcmds++; + } + + trace_postcopy_discard_send_finish(pds->ramblock_name, pds->nsentwords, + pds->nsentcmds); + + g_free(pds); +} diff --git a/src/migration/qemu-file-buf.c b/src/migration/qemu-file-buf.c new file mode 100644 index 0000000..49516b8 --- /dev/null +++ b/src/migration/qemu-file-buf.c @@ -0,0 +1,463 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2014 IBM Corp. + * + * Authors: + * Stefan Berger <stefanb@linux.vnet.ibm.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/iov.h" +#include "qemu/sockets.h" +#include "qemu/coroutine.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "migration/qemu-file-internal.h" +#include "trace.h" + +#define QSB_CHUNK_SIZE (1 << 10) +#define QSB_MAX_CHUNK_SIZE (16 * QSB_CHUNK_SIZE) + +/** + * Create a QEMUSizedBuffer + * This type of buffer uses scatter-gather lists internally and + * can grow to any size. Any data array in the scatter-gather list + * can hold different amount of bytes. + * + * @buffer: Optional buffer to copy into the QSB + * @len: size of initial buffer; if @buffer is given, buffer must + * hold at least len bytes + * + * Returns a pointer to a QEMUSizedBuffer or NULL on allocation failure + */ +QEMUSizedBuffer *qsb_create(const uint8_t *buffer, size_t len) +{ + QEMUSizedBuffer *qsb; + size_t alloc_len, num_chunks, i, to_copy; + size_t chunk_size = (len > QSB_MAX_CHUNK_SIZE) + ? QSB_MAX_CHUNK_SIZE + : QSB_CHUNK_SIZE; + + num_chunks = DIV_ROUND_UP(len ? len : QSB_CHUNK_SIZE, chunk_size); + alloc_len = num_chunks * chunk_size; + + qsb = g_try_new0(QEMUSizedBuffer, 1); + if (!qsb) { + return NULL; + } + + qsb->iov = g_try_new0(struct iovec, num_chunks); + if (!qsb->iov) { + g_free(qsb); + return NULL; + } + + qsb->n_iov = num_chunks; + + for (i = 0; i < num_chunks; i++) { + qsb->iov[i].iov_base = g_try_malloc0(chunk_size); + if (!qsb->iov[i].iov_base) { + /* qsb_free is safe since g_free can cope with NULL */ + qsb_free(qsb); + return NULL; + } + + qsb->iov[i].iov_len = chunk_size; + if (buffer) { + to_copy = (len - qsb->used) > chunk_size + ? chunk_size : (len - qsb->used); + memcpy(qsb->iov[i].iov_base, &buffer[qsb->used], to_copy); + qsb->used += to_copy; + } + } + + qsb->size = alloc_len; + + return qsb; +} + +/** + * Free the QEMUSizedBuffer + * + * @qsb: The QEMUSizedBuffer to free + */ +void qsb_free(QEMUSizedBuffer *qsb) +{ + size_t i; + + if (!qsb) { + return; + } + + for (i = 0; i < qsb->n_iov; i++) { + g_free(qsb->iov[i].iov_base); + } + g_free(qsb->iov); + g_free(qsb); +} + +/** + * Get the number of used bytes in the QEMUSizedBuffer + * + * @qsb: A QEMUSizedBuffer + * + * Returns the number of bytes currently used in this buffer + */ +size_t qsb_get_length(const QEMUSizedBuffer *qsb) +{ + return qsb->used; +} + +/** + * Set the length of the buffer; the primary usage of this + * function is to truncate the number of used bytes in the buffer. + * The size will not be extended beyond the current number of + * allocated bytes in the QEMUSizedBuffer. + * + * @qsb: A QEMUSizedBuffer + * @new_len: The new length of bytes in the buffer + * + * Returns the number of bytes the buffer was truncated or extended + * to. + */ +size_t qsb_set_length(QEMUSizedBuffer *qsb, size_t new_len) +{ + if (new_len <= qsb->size) { + qsb->used = new_len; + } else { + qsb->used = qsb->size; + } + return qsb->used; +} + +/** + * Get the iovec that holds the data for a given position @pos. + * + * @qsb: A QEMUSizedBuffer + * @pos: The index of a byte in the buffer + * @d_off: Pointer to an offset that this function will indicate + * at what position within the returned iovec the byte + * is to be found + * + * Returns the index of the iovec that holds the byte at the given + * index @pos in the byte stream; a negative number if the iovec + * for the given position @pos does not exist. + */ +static ssize_t qsb_get_iovec(const QEMUSizedBuffer *qsb, + off_t pos, off_t *d_off) +{ + ssize_t i; + off_t curr = 0; + + if (pos > qsb->used) { + return -1; + } + + for (i = 0; i < qsb->n_iov; i++) { + if (curr + qsb->iov[i].iov_len > pos) { + *d_off = pos - curr; + return i; + } + curr += qsb->iov[i].iov_len; + } + return -1; +} + +/* + * Convert the QEMUSizedBuffer into a flat buffer. + * + * Note: If at all possible, try to avoid this function since it + * may unnecessarily copy memory around. + * + * @qsb: pointer to QEMUSizedBuffer + * @start: offset to start at + * @count: number of bytes to copy + * @buf: a pointer to a buffer to write into (at least @count bytes) + * + * Returns the number of bytes copied into the output buffer + */ +ssize_t qsb_get_buffer(const QEMUSizedBuffer *qsb, off_t start, + size_t count, uint8_t *buffer) +{ + const struct iovec *iov; + size_t to_copy, all_copy; + ssize_t index; + off_t s_off; + off_t d_off = 0; + char *s; + + if (start > qsb->used) { + return 0; + } + + all_copy = qsb->used - start; + if (all_copy > count) { + all_copy = count; + } else { + count = all_copy; + } + + index = qsb_get_iovec(qsb, start, &s_off); + if (index < 0) { + return 0; + } + + while (all_copy > 0) { + iov = &qsb->iov[index]; + + s = iov->iov_base; + + to_copy = iov->iov_len - s_off; + if (to_copy > all_copy) { + to_copy = all_copy; + } + memcpy(&buffer[d_off], &s[s_off], to_copy); + + d_off += to_copy; + all_copy -= to_copy; + + s_off = 0; + index++; + } + + return count; +} + +/** + * Grow the QEMUSizedBuffer to the given size and allocate + * memory for it. + * + * @qsb: A QEMUSizedBuffer + * @new_size: The new size of the buffer + * + * Return: + * a negative error code in case of memory allocation failure + * or + * the new size of the buffer. The returned size may be greater or equal + * to @new_size. + */ +static ssize_t qsb_grow(QEMUSizedBuffer *qsb, size_t new_size) +{ + size_t needed_chunks, i; + + if (qsb->size < new_size) { + struct iovec *new_iov; + size_t size_diff = new_size - qsb->size; + size_t chunk_size = (size_diff > QSB_MAX_CHUNK_SIZE) + ? QSB_MAX_CHUNK_SIZE : QSB_CHUNK_SIZE; + + needed_chunks = DIV_ROUND_UP(size_diff, chunk_size); + + new_iov = g_try_new(struct iovec, qsb->n_iov + needed_chunks); + if (new_iov == NULL) { + return -ENOMEM; + } + + /* Allocate new chunks as needed into new_iov */ + for (i = qsb->n_iov; i < qsb->n_iov + needed_chunks; i++) { + new_iov[i].iov_base = g_try_malloc0(chunk_size); + new_iov[i].iov_len = chunk_size; + if (!new_iov[i].iov_base) { + size_t j; + + /* Free previously allocated new chunks */ + for (j = qsb->n_iov; j < i; j++) { + g_free(new_iov[j].iov_base); + } + g_free(new_iov); + + return -ENOMEM; + } + } + + /* + * Now we can't get any allocation errors, copy over to new iov + * and switch. + */ + for (i = 0; i < qsb->n_iov; i++) { + new_iov[i] = qsb->iov[i]; + } + + qsb->n_iov += needed_chunks; + g_free(qsb->iov); + qsb->iov = new_iov; + qsb->size += (needed_chunks * chunk_size); + } + + return qsb->size; +} + +/** + * Write into the QEMUSizedBuffer at a given position and a given + * number of bytes. This function will automatically grow the + * QEMUSizedBuffer. + * + * @qsb: A QEMUSizedBuffer + * @source: A byte array to copy data from + * @pos: The position within the @qsb to write data to + * @size: The number of bytes to copy into the @qsb + * + * Returns @size or a negative error code in case of memory allocation failure, + * or with an invalid 'pos' + */ +ssize_t qsb_write_at(QEMUSizedBuffer *qsb, const uint8_t *source, + off_t pos, size_t count) +{ + ssize_t rc = qsb_grow(qsb, pos + count); + size_t to_copy; + size_t all_copy = count; + const struct iovec *iov; + ssize_t index; + char *dest; + off_t d_off, s_off = 0; + + if (rc < 0) { + return rc; + } + + if (pos + count > qsb->used) { + qsb->used = pos + count; + } + + index = qsb_get_iovec(qsb, pos, &d_off); + if (index < 0) { + return -EINVAL; + } + + while (all_copy > 0) { + iov = &qsb->iov[index]; + + dest = iov->iov_base; + + to_copy = iov->iov_len - d_off; + if (to_copy > all_copy) { + to_copy = all_copy; + } + + memcpy(&dest[d_off], &source[s_off], to_copy); + + s_off += to_copy; + all_copy -= to_copy; + + d_off = 0; + index++; + } + + return count; +} + +typedef struct QEMUBuffer { + QEMUSizedBuffer *qsb; + QEMUFile *file; + bool qsb_allocated; +} QEMUBuffer; + +static ssize_t buf_get_buffer(void *opaque, uint8_t *buf, int64_t pos, + size_t size) +{ + QEMUBuffer *s = opaque; + ssize_t len = qsb_get_length(s->qsb) - pos; + + if (len <= 0) { + return 0; + } + + if (len > size) { + len = size; + } + return qsb_get_buffer(s->qsb, pos, len, buf); +} + +static ssize_t buf_put_buffer(void *opaque, const uint8_t *buf, + int64_t pos, size_t size) +{ + QEMUBuffer *s = opaque; + + return qsb_write_at(s->qsb, buf, pos, size); +} + +static int buf_close(void *opaque) +{ + QEMUBuffer *s = opaque; + + if (s->qsb_allocated) { + qsb_free(s->qsb); + } + + g_free(s); + + return 0; +} + +const QEMUSizedBuffer *qemu_buf_get(QEMUFile *f) +{ + QEMUBuffer *p; + + qemu_fflush(f); + + p = f->opaque; + + return p->qsb; +} + +static const QEMUFileOps buf_read_ops = { + .get_buffer = buf_get_buffer, + .close = buf_close, +}; + +static const QEMUFileOps buf_write_ops = { + .put_buffer = buf_put_buffer, + .close = buf_close, +}; + +QEMUFile *qemu_bufopen(const char *mode, QEMUSizedBuffer *input) +{ + QEMUBuffer *s; + + if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || + mode[1] != '\0') { + error_report("qemu_bufopen: Argument validity check failed"); + return NULL; + } + + s = g_new0(QEMUBuffer, 1); + s->qsb = input; + + if (s->qsb == NULL) { + s->qsb = qsb_create(NULL, 0); + s->qsb_allocated = true; + } + if (!s->qsb) { + g_free(s); + error_report("qemu_bufopen: qsb_create failed"); + return NULL; + } + + + if (mode[0] == 'r') { + s->file = qemu_fopen_ops(s, &buf_read_ops); + } else { + s->file = qemu_fopen_ops(s, &buf_write_ops); + } + return s->file; +} diff --git a/src/migration/qemu-file-internal.h b/src/migration/qemu-file-internal.h new file mode 100644 index 0000000..d95e853 --- /dev/null +++ b/src/migration/qemu-file-internal.h @@ -0,0 +1,53 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef QEMU_FILE_INTERNAL_H +#define QEMU_FILE_INTERNAL_H 1 + +#include "qemu-common.h" +#include "qemu/iov.h" + +#define IO_BUF_SIZE 32768 +#define MAX_IOV_SIZE MIN(IOV_MAX, 64) + +struct QEMUFile { + const QEMUFileOps *ops; + void *opaque; + + int64_t bytes_xfer; + int64_t xfer_limit; + + int64_t pos; /* start of buffer when writing, end of buffer + when reading */ + int buf_index; + int buf_size; /* 0 when writing */ + uint8_t buf[IO_BUF_SIZE]; + + struct iovec iov[MAX_IOV_SIZE]; + unsigned int iovcnt; + + int last_error; +}; + +#endif diff --git a/src/migration/qemu-file-stdio.c b/src/migration/qemu-file-stdio.c new file mode 100644 index 0000000..9bde9db --- /dev/null +++ b/src/migration/qemu-file-stdio.c @@ -0,0 +1,195 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu-common.h" +#include "qemu/coroutine.h" +#include "migration/qemu-file.h" + +typedef struct QEMUFileStdio { + FILE *stdio_file; + QEMUFile *file; +} QEMUFileStdio; + +static int stdio_get_fd(void *opaque) +{ + QEMUFileStdio *s = opaque; + + return fileno(s->stdio_file); +} + +static ssize_t stdio_put_buffer(void *opaque, const uint8_t *buf, int64_t pos, + size_t size) +{ + QEMUFileStdio *s = opaque; + size_t res; + + res = fwrite(buf, 1, size, s->stdio_file); + + if (res != size) { + return -errno; + } + return res; +} + +static ssize_t stdio_get_buffer(void *opaque, uint8_t *buf, int64_t pos, + size_t size) +{ + QEMUFileStdio *s = opaque; + FILE *fp = s->stdio_file; + ssize_t bytes; + + for (;;) { + clearerr(fp); + bytes = fread(buf, 1, size, fp); + if (bytes != 0 || !ferror(fp)) { + break; + } + if (errno == EAGAIN) { + yield_until_fd_readable(fileno(fp)); + } else if (errno != EINTR) { + break; + } + } + return bytes; +} + +static int stdio_pclose(void *opaque) +{ + QEMUFileStdio *s = opaque; + int ret; + ret = pclose(s->stdio_file); + if (ret == -1) { + ret = -errno; + } else if (!WIFEXITED(ret) || WEXITSTATUS(ret) != 0) { + /* close succeeded, but non-zero exit code: */ + ret = -EIO; /* fake errno value */ + } + g_free(s); + return ret; +} + +static int stdio_fclose(void *opaque) +{ + QEMUFileStdio *s = opaque; + int ret = 0; + + if (qemu_file_is_writable(s->file)) { + int fd = fileno(s->stdio_file); + struct stat st; + + ret = fstat(fd, &st); + if (ret == 0 && S_ISREG(st.st_mode)) { + /* + * If the file handle is a regular file make sure the + * data is flushed to disk before signaling success. + */ + ret = fsync(fd); + if (ret != 0) { + ret = -errno; + return ret; + } + } + } + if (fclose(s->stdio_file) == EOF) { + ret = -errno; + } + g_free(s); + return ret; +} + +static const QEMUFileOps stdio_pipe_read_ops = { + .get_fd = stdio_get_fd, + .get_buffer = stdio_get_buffer, + .close = stdio_pclose +}; + +static const QEMUFileOps stdio_pipe_write_ops = { + .get_fd = stdio_get_fd, + .put_buffer = stdio_put_buffer, + .close = stdio_pclose +}; + +QEMUFile *qemu_popen_cmd(const char *command, const char *mode) +{ + FILE *stdio_file; + QEMUFileStdio *s; + + if (mode == NULL || (mode[0] != 'r' && mode[0] != 'w') || mode[1] != 0) { + fprintf(stderr, "qemu_popen: Argument validity check failed\n"); + return NULL; + } + + stdio_file = popen(command, mode); + if (stdio_file == NULL) { + return NULL; + } + + s = g_new0(QEMUFileStdio, 1); + + s->stdio_file = stdio_file; + + if (mode[0] == 'r') { + s->file = qemu_fopen_ops(s, &stdio_pipe_read_ops); + } else { + s->file = qemu_fopen_ops(s, &stdio_pipe_write_ops); + } + return s->file; +} + +static const QEMUFileOps stdio_file_read_ops = { + .get_fd = stdio_get_fd, + .get_buffer = stdio_get_buffer, + .close = stdio_fclose +}; + +static const QEMUFileOps stdio_file_write_ops = { + .get_fd = stdio_get_fd, + .put_buffer = stdio_put_buffer, + .close = stdio_fclose +}; + +QEMUFile *qemu_fopen(const char *filename, const char *mode) +{ + QEMUFileStdio *s; + + if (qemu_file_mode_is_not_valid(mode)) { + return NULL; + } + + s = g_new0(QEMUFileStdio, 1); + + s->stdio_file = fopen(filename, mode); + if (!s->stdio_file) { + goto fail; + } + + if (mode[0] == 'w') { + s->file = qemu_fopen_ops(s, &stdio_file_write_ops); + } else { + s->file = qemu_fopen_ops(s, &stdio_file_read_ops); + } + return s->file; +fail: + g_free(s); + return NULL; +} diff --git a/src/migration/qemu-file-unix.c b/src/migration/qemu-file-unix.c new file mode 100644 index 0000000..6ca53e7 --- /dev/null +++ b/src/migration/qemu-file-unix.c @@ -0,0 +1,324 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/iov.h" +#include "qemu/sockets.h" +#include "qemu/coroutine.h" +#include "migration/qemu-file.h" +#include "migration/qemu-file-internal.h" + +typedef struct QEMUFileSocket { + int fd; + QEMUFile *file; +} QEMUFileSocket; + +static ssize_t socket_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + QEMUFileSocket *s = opaque; + ssize_t len; + ssize_t size = iov_size(iov, iovcnt); + ssize_t offset = 0; + int err; + + while (size > 0) { + len = iov_send(s->fd, iov, iovcnt, offset, size); + + if (len > 0) { + size -= len; + offset += len; + } + + if (size > 0) { + err = socket_error(); + + if (err != EAGAIN && err != EWOULDBLOCK) { + error_report("socket_writev_buffer: Got err=%d for (%zu/%zu)", + err, (size_t)size, (size_t)len); + /* + * If I've already sent some but only just got the error, I + * could return the amount validly sent so far and wait for the + * next call to report the error, but I'd rather flag the error + * immediately. + */ + return -err; + } + + /* Emulate blocking */ + GPollFD pfd; + + pfd.fd = s->fd; + pfd.events = G_IO_OUT | G_IO_ERR; + pfd.revents = 0; + TFR(err = g_poll(&pfd, 1, -1 /* no timeout */)); + /* Errors other than EINTR intentionally ignored */ + } + } + + return offset; +} + +static int socket_get_fd(void *opaque) +{ + QEMUFileSocket *s = opaque; + + return s->fd; +} + +static ssize_t socket_get_buffer(void *opaque, uint8_t *buf, int64_t pos, + size_t size) +{ + QEMUFileSocket *s = opaque; + ssize_t len; + + for (;;) { + len = qemu_recv(s->fd, buf, size, 0); + if (len != -1) { + break; + } + if (socket_error() == EAGAIN) { + yield_until_fd_readable(s->fd); + } else if (socket_error() != EINTR) { + break; + } + } + + if (len == -1) { + len = -socket_error(); + } + return len; +} + +static int socket_close(void *opaque) +{ + QEMUFileSocket *s = opaque; + closesocket(s->fd); + g_free(s); + return 0; +} + +static int socket_shutdown(void *opaque, bool rd, bool wr) +{ + QEMUFileSocket *s = opaque; + + if (shutdown(s->fd, rd ? (wr ? SHUT_RDWR : SHUT_RD) : SHUT_WR)) { + return -errno; + } else { + return 0; + } +} + +static int socket_return_close(void *opaque) +{ + QEMUFileSocket *s = opaque; + /* + * Note: We don't close the socket, that should be done by the forward + * path. + */ + g_free(s); + return 0; +} + +static const QEMUFileOps socket_return_read_ops = { + .get_fd = socket_get_fd, + .get_buffer = socket_get_buffer, + .close = socket_return_close, + .shut_down = socket_shutdown, +}; + +static const QEMUFileOps socket_return_write_ops = { + .get_fd = socket_get_fd, + .writev_buffer = socket_writev_buffer, + .close = socket_return_close, + .shut_down = socket_shutdown, +}; + +/* + * Give a QEMUFile* off the same socket but data in the opposite + * direction. + */ +static QEMUFile *socket_get_return_path(void *opaque) +{ + QEMUFileSocket *forward = opaque; + QEMUFileSocket *reverse; + + if (qemu_file_get_error(forward->file)) { + /* If the forward file is in error, don't try and open a return */ + return NULL; + } + + reverse = g_malloc0(sizeof(QEMUFileSocket)); + reverse->fd = forward->fd; + /* I don't think there's a better way to tell which direction 'this' is */ + if (forward->file->ops->get_buffer != NULL) { + /* being called from the read side, so we need to be able to write */ + return qemu_fopen_ops(reverse, &socket_return_write_ops); + } else { + return qemu_fopen_ops(reverse, &socket_return_read_ops); + } +} + +static ssize_t unix_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + QEMUFileSocket *s = opaque; + ssize_t len, offset; + ssize_t size = iov_size(iov, iovcnt); + ssize_t total = 0; + + assert(iovcnt > 0); + offset = 0; + while (size > 0) { + /* Find the next start position; skip all full-sized vector elements */ + while (offset >= iov[0].iov_len) { + offset -= iov[0].iov_len; + iov++, iovcnt--; + } + + /* skip `offset' bytes from the (now) first element, undo it on exit */ + assert(iovcnt > 0); + iov[0].iov_base += offset; + iov[0].iov_len -= offset; + + do { + len = writev(s->fd, iov, iovcnt); + } while (len == -1 && errno == EINTR); + if (len == -1) { + return -errno; + } + + /* Undo the changes above */ + iov[0].iov_base -= offset; + iov[0].iov_len += offset; + + /* Prepare for the next iteration */ + offset += len; + total += len; + size -= len; + } + + return total; +} + +static ssize_t unix_get_buffer(void *opaque, uint8_t *buf, int64_t pos, + size_t size) +{ + QEMUFileSocket *s = opaque; + ssize_t len; + + for (;;) { + len = read(s->fd, buf, size); + if (len != -1) { + break; + } + if (errno == EAGAIN) { + yield_until_fd_readable(s->fd); + } else if (errno != EINTR) { + break; + } + } + + if (len == -1) { + len = -errno; + } + return len; +} + +static int unix_close(void *opaque) +{ + QEMUFileSocket *s = opaque; + close(s->fd); + g_free(s); + return 0; +} + +static const QEMUFileOps unix_read_ops = { + .get_fd = socket_get_fd, + .get_buffer = unix_get_buffer, + .close = unix_close +}; + +static const QEMUFileOps unix_write_ops = { + .get_fd = socket_get_fd, + .writev_buffer = unix_writev_buffer, + .close = unix_close +}; + +QEMUFile *qemu_fdopen(int fd, const char *mode) +{ + QEMUFileSocket *s; + + if (mode == NULL || + (mode[0] != 'r' && mode[0] != 'w') || + mode[1] != 'b' || mode[2] != 0) { + fprintf(stderr, "qemu_fdopen: Argument validity check failed\n"); + return NULL; + } + + s = g_new0(QEMUFileSocket, 1); + s->fd = fd; + + if (mode[0] == 'r') { + s->file = qemu_fopen_ops(s, &unix_read_ops); + } else { + s->file = qemu_fopen_ops(s, &unix_write_ops); + } + return s->file; +} + +static const QEMUFileOps socket_read_ops = { + .get_fd = socket_get_fd, + .get_buffer = socket_get_buffer, + .close = socket_close, + .shut_down = socket_shutdown, + .get_return_path = socket_get_return_path +}; + +static const QEMUFileOps socket_write_ops = { + .get_fd = socket_get_fd, + .writev_buffer = socket_writev_buffer, + .close = socket_close, + .shut_down = socket_shutdown, + .get_return_path = socket_get_return_path +}; + +QEMUFile *qemu_fopen_socket(int fd, const char *mode) +{ + QEMUFileSocket *s; + + if (qemu_file_mode_is_not_valid(mode)) { + return NULL; + } + + s = g_new0(QEMUFileSocket, 1); + s->fd = fd; + if (mode[0] == 'w') { + qemu_set_block(s->fd); + s->file = qemu_fopen_ops(s, &socket_write_ops); + } else { + s->file = qemu_fopen_ops(s, &socket_read_ops); + } + return s->file; +} diff --git a/src/migration/qemu-file.c b/src/migration/qemu-file.c new file mode 100644 index 0000000..0bbd257 --- /dev/null +++ b/src/migration/qemu-file.c @@ -0,0 +1,677 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include <zlib.h> +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/iov.h" +#include "qemu/sockets.h" +#include "qemu/coroutine.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "migration/qemu-file-internal.h" +#include "trace.h" + +/* + * Stop a file from being read/written - not all backing files can do this + * typically only sockets can. + */ +int qemu_file_shutdown(QEMUFile *f) +{ + if (!f->ops->shut_down) { + return -ENOSYS; + } + return f->ops->shut_down(f->opaque, true, true); +} + +/* + * Result: QEMUFile* for a 'return path' for comms in the opposite direction + * NULL if not available + */ +QEMUFile *qemu_file_get_return_path(QEMUFile *f) +{ + if (!f->ops->get_return_path) { + return NULL; + } + return f->ops->get_return_path(f->opaque); +} + +bool qemu_file_mode_is_not_valid(const char *mode) +{ + if (mode == NULL || + (mode[0] != 'r' && mode[0] != 'w') || + mode[1] != 'b' || mode[2] != 0) { + fprintf(stderr, "qemu_fopen: Argument validity check failed\n"); + return true; + } + + return false; +} + +QEMUFile *qemu_fopen_ops(void *opaque, const QEMUFileOps *ops) +{ + QEMUFile *f; + + f = g_new0(QEMUFile, 1); + + f->opaque = opaque; + f->ops = ops; + return f; +} + +/* + * Get last error for stream f + * + * Return negative error value if there has been an error on previous + * operations, return 0 if no error happened. + * + */ +int qemu_file_get_error(QEMUFile *f) +{ + return f->last_error; +} + +void qemu_file_set_error(QEMUFile *f, int ret) +{ + if (f->last_error == 0) { + f->last_error = ret; + } +} + +bool qemu_file_is_writable(QEMUFile *f) +{ + return f->ops->writev_buffer || f->ops->put_buffer; +} + +/** + * Flushes QEMUFile buffer + * + * If there is writev_buffer QEMUFileOps it uses it otherwise uses + * put_buffer ops. + */ +void qemu_fflush(QEMUFile *f) +{ + ssize_t ret = 0; + + if (!qemu_file_is_writable(f)) { + return; + } + + if (f->ops->writev_buffer) { + if (f->iovcnt > 0) { + ret = f->ops->writev_buffer(f->opaque, f->iov, f->iovcnt, f->pos); + } + } else { + if (f->buf_index > 0) { + ret = f->ops->put_buffer(f->opaque, f->buf, f->pos, f->buf_index); + } + } + if (ret >= 0) { + f->pos += ret; + } + f->buf_index = 0; + f->iovcnt = 0; + if (ret < 0) { + qemu_file_set_error(f, ret); + } +} + +void ram_control_before_iterate(QEMUFile *f, uint64_t flags) +{ + int ret = 0; + + if (f->ops->before_ram_iterate) { + ret = f->ops->before_ram_iterate(f, f->opaque, flags, NULL); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } +} + +void ram_control_after_iterate(QEMUFile *f, uint64_t flags) +{ + int ret = 0; + + if (f->ops->after_ram_iterate) { + ret = f->ops->after_ram_iterate(f, f->opaque, flags, NULL); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } +} + +void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data) +{ + int ret = -EINVAL; + + if (f->ops->hook_ram_load) { + ret = f->ops->hook_ram_load(f, f->opaque, flags, data); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } else { + /* + * Hook is a hook specifically requested by the source sending a flag + * that expects there to be a hook on the destination. + */ + if (flags == RAM_CONTROL_HOOK) { + qemu_file_set_error(f, ret); + } + } +} + +size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, + ram_addr_t offset, size_t size, + uint64_t *bytes_sent) +{ + if (f->ops->save_page) { + int ret = f->ops->save_page(f, f->opaque, block_offset, + offset, size, bytes_sent); + + if (ret != RAM_SAVE_CONTROL_DELAYED) { + if (bytes_sent && *bytes_sent > 0) { + qemu_update_position(f, *bytes_sent); + } else if (ret < 0) { + qemu_file_set_error(f, ret); + } + } + + return ret; + } + + return RAM_SAVE_CONTROL_NOT_SUPP; +} + +/* + * Attempt to fill the buffer from the underlying file + * Returns the number of bytes read, or negative value for an error. + * + * Note that it can return a partially full buffer even in a not error/not EOF + * case if the underlying file descriptor gives a short read, and that can + * happen even on a blocking fd. + */ +static ssize_t qemu_fill_buffer(QEMUFile *f) +{ + int len; + int pending; + + assert(!qemu_file_is_writable(f)); + + pending = f->buf_size - f->buf_index; + if (pending > 0) { + memmove(f->buf, f->buf + f->buf_index, pending); + } + f->buf_index = 0; + f->buf_size = pending; + + len = f->ops->get_buffer(f->opaque, f->buf + pending, f->pos, + IO_BUF_SIZE - pending); + if (len > 0) { + f->buf_size += len; + f->pos += len; + } else if (len == 0) { + qemu_file_set_error(f, -EIO); + } else if (len != -EAGAIN) { + qemu_file_set_error(f, len); + } + + return len; +} + +int qemu_get_fd(QEMUFile *f) +{ + if (f->ops->get_fd) { + return f->ops->get_fd(f->opaque); + } + return -1; +} + +void qemu_update_position(QEMUFile *f, size_t size) +{ + f->pos += size; +} + +/** Closes the file + * + * Returns negative error value if any error happened on previous operations or + * while closing the file. Returns 0 or positive number on success. + * + * The meaning of return value on success depends on the specific backend + * being used. + */ +int qemu_fclose(QEMUFile *f) +{ + int ret; + qemu_fflush(f); + ret = qemu_file_get_error(f); + + if (f->ops->close) { + int ret2 = f->ops->close(f->opaque); + if (ret >= 0) { + ret = ret2; + } + } + /* If any error was spotted before closing, we should report it + * instead of the close() return value. + */ + if (f->last_error) { + ret = f->last_error; + } + g_free(f); + trace_qemu_file_fclose(); + return ret; +} + +static void add_to_iovec(QEMUFile *f, const uint8_t *buf, size_t size) +{ + /* check for adjacent buffer and coalesce them */ + if (f->iovcnt > 0 && buf == f->iov[f->iovcnt - 1].iov_base + + f->iov[f->iovcnt - 1].iov_len) { + f->iov[f->iovcnt - 1].iov_len += size; + } else { + f->iov[f->iovcnt].iov_base = (uint8_t *)buf; + f->iov[f->iovcnt++].iov_len = size; + } + + if (f->iovcnt >= MAX_IOV_SIZE) { + qemu_fflush(f); + } +} + +void qemu_put_buffer_async(QEMUFile *f, const uint8_t *buf, size_t size) +{ + if (!f->ops->writev_buffer) { + qemu_put_buffer(f, buf, size); + return; + } + + if (f->last_error) { + return; + } + + f->bytes_xfer += size; + add_to_iovec(f, buf, size); +} + +void qemu_put_buffer(QEMUFile *f, const uint8_t *buf, size_t size) +{ + size_t l; + + if (f->last_error) { + return; + } + + while (size > 0) { + l = IO_BUF_SIZE - f->buf_index; + if (l > size) { + l = size; + } + memcpy(f->buf + f->buf_index, buf, l); + f->bytes_xfer += l; + if (f->ops->writev_buffer) { + add_to_iovec(f, f->buf + f->buf_index, l); + } + f->buf_index += l; + if (f->buf_index == IO_BUF_SIZE) { + qemu_fflush(f); + } + if (qemu_file_get_error(f)) { + break; + } + buf += l; + size -= l; + } +} + +void qemu_put_byte(QEMUFile *f, int v) +{ + if (f->last_error) { + return; + } + + f->buf[f->buf_index] = v; + f->bytes_xfer++; + if (f->ops->writev_buffer) { + add_to_iovec(f, f->buf + f->buf_index, 1); + } + f->buf_index++; + if (f->buf_index == IO_BUF_SIZE) { + qemu_fflush(f); + } +} + +void qemu_file_skip(QEMUFile *f, int size) +{ + if (f->buf_index + size <= f->buf_size) { + f->buf_index += size; + } +} + +/* + * Read 'size' bytes from file (at 'offset') without moving the + * pointer and set 'buf' to point to that data. + * + * It will return size bytes unless there was an error, in which case it will + * return as many as it managed to read (assuming blocking fd's which + * all current QEMUFile are) + */ +size_t qemu_peek_buffer(QEMUFile *f, uint8_t **buf, size_t size, size_t offset) +{ + ssize_t pending; + size_t index; + + assert(!qemu_file_is_writable(f)); + assert(offset < IO_BUF_SIZE); + assert(size <= IO_BUF_SIZE - offset); + + /* The 1st byte to read from */ + index = f->buf_index + offset; + /* The number of available bytes starting at index */ + pending = f->buf_size - index; + + /* + * qemu_fill_buffer might return just a few bytes, even when there isn't + * an error, so loop collecting them until we get enough. + */ + while (pending < size) { + int received = qemu_fill_buffer(f); + + if (received <= 0) { + break; + } + + index = f->buf_index + offset; + pending = f->buf_size - index; + } + + if (pending <= 0) { + return 0; + } + if (size > pending) { + size = pending; + } + + *buf = f->buf + index; + return size; +} + +/* + * Read 'size' bytes of data from the file into buf. + * 'size' can be larger than the internal buffer. + * + * It will return size bytes unless there was an error, in which case it will + * return as many as it managed to read (assuming blocking fd's which + * all current QEMUFile are) + */ +size_t qemu_get_buffer(QEMUFile *f, uint8_t *buf, size_t size) +{ + size_t pending = size; + size_t done = 0; + + while (pending > 0) { + size_t res; + uint8_t *src; + + res = qemu_peek_buffer(f, &src, MIN(pending, IO_BUF_SIZE), 0); + if (res == 0) { + return done; + } + memcpy(buf, src, res); + qemu_file_skip(f, res); + buf += res; + pending -= res; + done += res; + } + return done; +} + +/* + * Read 'size' bytes of data from the file. + * 'size' can be larger than the internal buffer. + * + * The data: + * may be held on an internal buffer (in which case *buf is updated + * to point to it) that is valid until the next qemu_file operation. + * OR + * will be copied to the *buf that was passed in. + * + * The code tries to avoid the copy if possible. + * + * It will return size bytes unless there was an error, in which case it will + * return as many as it managed to read (assuming blocking fd's which + * all current QEMUFile are) + * + * Note: Since **buf may get changed, the caller should take care to + * keep a pointer to the original buffer if it needs to deallocate it. + */ +size_t qemu_get_buffer_in_place(QEMUFile *f, uint8_t **buf, size_t size) +{ + if (size < IO_BUF_SIZE) { + size_t res; + uint8_t *src; + + res = qemu_peek_buffer(f, &src, size, 0); + + if (res == size) { + qemu_file_skip(f, res); + *buf = src; + return res; + } + } + + return qemu_get_buffer(f, *buf, size); +} + +/* + * Peeks a single byte from the buffer; this isn't guaranteed to work if + * offset leaves a gap after the previous read/peeked data. + */ +int qemu_peek_byte(QEMUFile *f, int offset) +{ + int index = f->buf_index + offset; + + assert(!qemu_file_is_writable(f)); + assert(offset < IO_BUF_SIZE); + + if (index >= f->buf_size) { + qemu_fill_buffer(f); + index = f->buf_index + offset; + if (index >= f->buf_size) { + return 0; + } + } + return f->buf[index]; +} + +int qemu_get_byte(QEMUFile *f) +{ + int result; + + result = qemu_peek_byte(f, 0); + qemu_file_skip(f, 1); + return result; +} + +int64_t qemu_ftell_fast(QEMUFile *f) +{ + int64_t ret = f->pos; + int i; + + if (f->ops->writev_buffer) { + for (i = 0; i < f->iovcnt; i++) { + ret += f->iov[i].iov_len; + } + } else { + ret += f->buf_index; + } + + return ret; +} + +int64_t qemu_ftell(QEMUFile *f) +{ + qemu_fflush(f); + return f->pos; +} + +int qemu_file_rate_limit(QEMUFile *f) +{ + if (qemu_file_get_error(f)) { + return 1; + } + if (f->xfer_limit > 0 && f->bytes_xfer > f->xfer_limit) { + return 1; + } + return 0; +} + +int64_t qemu_file_get_rate_limit(QEMUFile *f) +{ + return f->xfer_limit; +} + +void qemu_file_set_rate_limit(QEMUFile *f, int64_t limit) +{ + f->xfer_limit = limit; +} + +void qemu_file_reset_rate_limit(QEMUFile *f) +{ + f->bytes_xfer = 0; +} + +void qemu_put_be16(QEMUFile *f, unsigned int v) +{ + qemu_put_byte(f, v >> 8); + qemu_put_byte(f, v); +} + +void qemu_put_be32(QEMUFile *f, unsigned int v) +{ + qemu_put_byte(f, v >> 24); + qemu_put_byte(f, v >> 16); + qemu_put_byte(f, v >> 8); + qemu_put_byte(f, v); +} + +void qemu_put_be64(QEMUFile *f, uint64_t v) +{ + qemu_put_be32(f, v >> 32); + qemu_put_be32(f, v); +} + +unsigned int qemu_get_be16(QEMUFile *f) +{ + unsigned int v; + v = qemu_get_byte(f) << 8; + v |= qemu_get_byte(f); + return v; +} + +unsigned int qemu_get_be32(QEMUFile *f) +{ + unsigned int v; + v = (unsigned int)qemu_get_byte(f) << 24; + v |= qemu_get_byte(f) << 16; + v |= qemu_get_byte(f) << 8; + v |= qemu_get_byte(f); + return v; +} + +uint64_t qemu_get_be64(QEMUFile *f) +{ + uint64_t v; + v = (uint64_t)qemu_get_be32(f) << 32; + v |= qemu_get_be32(f); + return v; +} + +/* compress size bytes of data start at p with specific compression + * level and store the compressed data to the buffer of f. + */ + +ssize_t qemu_put_compression_data(QEMUFile *f, const uint8_t *p, size_t size, + int level) +{ + ssize_t blen = IO_BUF_SIZE - f->buf_index - sizeof(int32_t); + + if (blen < compressBound(size)) { + return 0; + } + if (compress2(f->buf + f->buf_index + sizeof(int32_t), (uLongf *)&blen, + (Bytef *)p, size, level) != Z_OK) { + error_report("Compress Failed!"); + return 0; + } + qemu_put_be32(f, blen); + f->buf_index += blen; + return blen + sizeof(int32_t); +} + +/* Put the data in the buffer of f_src to the buffer of f_des, and + * then reset the buf_index of f_src to 0. + */ + +int qemu_put_qemu_file(QEMUFile *f_des, QEMUFile *f_src) +{ + int len = 0; + + if (f_src->buf_index > 0) { + len = f_src->buf_index; + qemu_put_buffer(f_des, f_src->buf, f_src->buf_index); + f_src->buf_index = 0; + } + return len; +} + +/* + * Get a string whose length is determined by a single preceding byte + * A preallocated 256 byte buffer must be passed in. + * Returns: len on success and a 0 terminated string in the buffer + * else 0 + * (Note a 0 length string will return 0 either way) + */ +size_t qemu_get_counted_string(QEMUFile *f, char buf[256]) +{ + size_t len = qemu_get_byte(f); + size_t res = qemu_get_buffer(f, (uint8_t *)buf, len); + + buf[res] = 0; + + return res == len ? res : 0; +} + +/* + * Set the blocking state of the QEMUFile. + * Note: On some transports the OS only keeps a single blocking state for + * both directions, and thus changing the blocking on the main + * QEMUFile can also affect the return path. + */ +void qemu_file_set_blocking(QEMUFile *f, bool block) +{ + if (block) { + qemu_set_block(qemu_get_fd(f)); + } else { + qemu_set_nonblock(qemu_get_fd(f)); + } +} diff --git a/src/migration/ram.c b/src/migration/ram.c new file mode 100644 index 0000000..0490f00 --- /dev/null +++ b/src/migration/ram.c @@ -0,0 +1,2544 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2011-2015 Red Hat Inc + * + * Authors: + * Juan Quintela <quintela@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include <stdint.h> +#include <zlib.h> +#include "qemu/bitops.h" +#include "qemu/bitmap.h" +#include "qemu/timer.h" +#include "qemu/main-loop.h" +#include "migration/migration.h" +#include "migration/postcopy-ram.h" +#include "exec/address-spaces.h" +#include "migration/page_cache.h" +#include "qemu/error-report.h" +#include "trace.h" +#include "exec/ram_addr.h" +#include "qemu/rcu_queue.h" + +#ifdef DEBUG_MIGRATION_RAM +#define DPRINTF(fmt, ...) \ + do { fprintf(stdout, "migration_ram: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static int dirty_rate_high_cnt; + +static uint64_t bitmap_sync_count; + +/***********************************************************/ +/* ram save/restore */ + +#define RAM_SAVE_FLAG_FULL 0x01 /* Obsolete, not used anymore */ +#define RAM_SAVE_FLAG_COMPRESS 0x02 +#define RAM_SAVE_FLAG_MEM_SIZE 0x04 +#define RAM_SAVE_FLAG_PAGE 0x08 +#define RAM_SAVE_FLAG_EOS 0x10 +#define RAM_SAVE_FLAG_CONTINUE 0x20 +#define RAM_SAVE_FLAG_XBZRLE 0x40 +/* 0x80 is reserved in migration.h start with 0x100 next */ +#define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 + +static const uint8_t ZERO_TARGET_PAGE[TARGET_PAGE_SIZE]; + +static inline bool is_zero_range(uint8_t *p, uint64_t size) +{ + return buffer_find_nonzero_offset(p, size) == size; +} + +/* struct contains XBZRLE cache and a static page + used by the compression */ +static struct { + /* buffer used for XBZRLE encoding */ + uint8_t *encoded_buf; + /* buffer for storing page content */ + uint8_t *current_buf; + /* Cache for XBZRLE, Protected by lock. */ + PageCache *cache; + QemuMutex lock; +} XBZRLE; + +/* buffer used for XBZRLE decoding */ +static uint8_t *xbzrle_decoded_buf; + +static void XBZRLE_cache_lock(void) +{ + if (migrate_use_xbzrle()) + qemu_mutex_lock(&XBZRLE.lock); +} + +static void XBZRLE_cache_unlock(void) +{ + if (migrate_use_xbzrle()) + 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(). + */ +int64_t xbzrle_cache_resize(int64_t new_size) +{ + PageCache *new_cache; + int64_t ret; + + if (new_size < TARGET_PAGE_SIZE) { + return -1; + } + + XBZRLE_cache_lock(); + + if (XBZRLE.cache != NULL) { + if (pow2floor(new_size) == migrate_xbzrle_cache_size()) { + goto out_new_size; + } + new_cache = cache_init(new_size / TARGET_PAGE_SIZE, + TARGET_PAGE_SIZE); + if (!new_cache) { + error_report("Error creating cache"); + ret = -1; + goto out; + } + + cache_fini(XBZRLE.cache); + XBZRLE.cache = new_cache; + } + +out_new_size: + ret = pow2floor(new_size); +out: + XBZRLE_cache_unlock(); + return ret; +} + +/* accounting for migration statistics */ +typedef struct AccountingInfo { + uint64_t dup_pages; + uint64_t skipped_pages; + uint64_t norm_pages; + uint64_t iterations; + uint64_t xbzrle_bytes; + uint64_t xbzrle_pages; + uint64_t xbzrle_cache_miss; + double xbzrle_cache_miss_rate; + uint64_t xbzrle_overflows; +} AccountingInfo; + +static AccountingInfo acct_info; + +static void acct_clear(void) +{ + memset(&acct_info, 0, sizeof(acct_info)); +} + +uint64_t dup_mig_bytes_transferred(void) +{ + return acct_info.dup_pages * TARGET_PAGE_SIZE; +} + +uint64_t dup_mig_pages_transferred(void) +{ + return acct_info.dup_pages; +} + +uint64_t skipped_mig_bytes_transferred(void) +{ + return acct_info.skipped_pages * TARGET_PAGE_SIZE; +} + +uint64_t skipped_mig_pages_transferred(void) +{ + return acct_info.skipped_pages; +} + +uint64_t norm_mig_bytes_transferred(void) +{ + return acct_info.norm_pages * TARGET_PAGE_SIZE; +} + +uint64_t norm_mig_pages_transferred(void) +{ + return acct_info.norm_pages; +} + +uint64_t xbzrle_mig_bytes_transferred(void) +{ + return acct_info.xbzrle_bytes; +} + +uint64_t xbzrle_mig_pages_transferred(void) +{ + return acct_info.xbzrle_pages; +} + +uint64_t xbzrle_mig_pages_cache_miss(void) +{ + return acct_info.xbzrle_cache_miss; +} + +double xbzrle_mig_cache_miss_rate(void) +{ + return acct_info.xbzrle_cache_miss_rate; +} + +uint64_t xbzrle_mig_pages_overflow(void) +{ + return acct_info.xbzrle_overflows; +} + +/* 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; + /* 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 start; + bool done; + QEMUFile *file; + QemuMutex mutex; + QemuCond cond; + RAMBlock *block; + ram_addr_t offset; +}; +typedef struct CompressParam CompressParam; + +struct DecompressParam { + bool start; + QemuMutex mutex; + QemuCond cond; + void *des; + uint8 *compbuf; + int len; +}; +typedef struct DecompressParam DecompressParam; + +static CompressParam *comp_param; +static QemuThread *compress_threads; +/* comp_done_cond is used to wake up the migration thread when + * one of the compression threads has finished the compression. + * comp_done_lock is used to co-work with comp_done_cond. + */ +static QemuMutex *comp_done_lock; +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 bool quit_comp_thread; +static bool quit_decomp_thread; +static DecompressParam *decomp_param; +static QemuThread *decompress_threads; +static uint8_t *compressed_data_buf; + +static int do_compress_ram_page(CompressParam *param); + +static void *do_data_compress(void *opaque) +{ + CompressParam *param = opaque; + + while (!quit_comp_thread) { + qemu_mutex_lock(¶m->mutex); + /* Re-check the quit_comp_thread in case of + * terminate_compression_threads is called just before + * qemu_mutex_lock(¶m->mutex) and after + * while(!quit_comp_thread), re-check it here can make + * sure the compression thread terminate as expected. + */ + while (!param->start && !quit_comp_thread) { + qemu_cond_wait(¶m->cond, ¶m->mutex); + } + if (!quit_comp_thread) { + do_compress_ram_page(param); + } + param->start = false; + qemu_mutex_unlock(¶m->mutex); + + qemu_mutex_lock(comp_done_lock); + param->done = true; + qemu_cond_signal(comp_done_cond); + qemu_mutex_unlock(comp_done_lock); + } + + return NULL; +} + +static inline void terminate_compression_threads(void) +{ + int idx, thread_count; + + thread_count = migrate_compress_threads(); + quit_comp_thread = true; + for (idx = 0; idx < thread_count; idx++) { + qemu_mutex_lock(&comp_param[idx].mutex); + qemu_cond_signal(&comp_param[idx].cond); + qemu_mutex_unlock(&comp_param[idx].mutex); + } +} + +void migrate_compress_threads_join(void) +{ + int i, thread_count; + + if (!migrate_use_compression()) { + return; + } + terminate_compression_threads(); + thread_count = migrate_compress_threads(); + for (i = 0; i < thread_count; i++) { + qemu_thread_join(compress_threads + i); + qemu_fclose(comp_param[i].file); + qemu_mutex_destroy(&comp_param[i].mutex); + qemu_cond_destroy(&comp_param[i].cond); + } + qemu_mutex_destroy(comp_done_lock); + qemu_cond_destroy(comp_done_cond); + g_free(compress_threads); + g_free(comp_param); + g_free(comp_done_cond); + g_free(comp_done_lock); + compress_threads = NULL; + comp_param = NULL; + comp_done_cond = NULL; + comp_done_lock = NULL; +} + +void migrate_compress_threads_create(void) +{ + int i, thread_count; + + if (!migrate_use_compression()) { + return; + } + quit_comp_thread = false; + compression_switch = true; + thread_count = migrate_compress_threads(); + compress_threads = g_new0(QemuThread, thread_count); + comp_param = g_new0(CompressParam, thread_count); + comp_done_cond = g_new0(QemuCond, 1); + comp_done_lock = g_new0(QemuMutex, 1); + qemu_cond_init(comp_done_cond); + qemu_mutex_init(comp_done_lock); + for (i = 0; i < thread_count; i++) { + /* com_param[i].file is just used as a dummy buffer to save data, set + * it's ops to empty. + */ + comp_param[i].file = qemu_fopen_ops(NULL, &empty_ops); + comp_param[i].done = true; + qemu_mutex_init(&comp_param[i].mutex); + qemu_cond_init(&comp_param[i].cond); + qemu_thread_create(compress_threads + i, "compress", + do_data_compress, comp_param + i, + QEMU_THREAD_JOINABLE); + } +} + +/** + * 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 + * + * @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) +{ + size_t size, len; + + qemu_put_be64(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); + size += 1 + len; + } + 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. + */ +static void mig_throttle_guest_down(void) +{ + MigrationState *s = migrate_get_current(); + uint64_t pct_initial = + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INITIAL]; + uint64_t pct_icrement = + s->parameters[MIGRATION_PARAMETER_X_CPU_THROTTLE_INCREMENT]; + + /* We have not started throttling yet. Let's start it. */ + if (!cpu_throttle_active()) { + cpu_throttle_set(pct_initial); + } else { + /* Throttling already on, just increase the rate */ + cpu_throttle_set(cpu_throttle_get_percentage() + pct_icrement); + } +} + +/* 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 + */ +static void xbzrle_cache_zero_page(ram_addr_t current_addr) +{ + if (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); +} + +#define ENCODING_FLAG_XBZRLE 0x1 + +/** + * save_xbzrle_page: compress and send current page + * + * Returns: 1 means that we wrote the page + * 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: + * @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, + ram_addr_t current_addr, RAMBlock *block, + ram_addr_t offset, bool last_stage, + uint64_t *bytes_transferred) +{ + 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 (!last_stage) { + if (cache_insert(XBZRLE.cache, current_addr, *current_data, + bitmap_sync_count) == -1) { + return -1; + } else { + /* update *current_data when the page has been + inserted into cache */ + *current_data = get_cached_data(XBZRLE.cache, current_addr); + } + } + return -1; + } + + prev_cached_page = get_cached_data(XBZRLE.cache, current_addr); + + /* save current buffer into memory */ + memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE); + + /* XBZRLE encoding (if there is no overflow) */ + encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf, + TARGET_PAGE_SIZE, XBZRLE.encoded_buf, + TARGET_PAGE_SIZE); + if (encoded_len == 0) { + DPRINTF("Skipping unmodified page\n"); + return 0; + } else if (encoded_len == -1) { + DPRINTF("Overflow\n"); + acct_info.xbzrle_overflows++; + /* update data in the cache */ + if (!last_stage) { + memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE); + *current_data = prev_cached_page; + } + return -1; + } + + /* we need to update the data in the cache, in order to get the same data */ + if (!last_stage) { + memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE); + } + + /* 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 += encoded_len + 1 + 2; + acct_info.xbzrle_pages++; + acct_info.xbzrle_bytes += bytes_xbzrle; + *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 + * + * Returns: byte offset within memory region of the start of a dirty page + */ +static inline +ram_addr_t migration_bitmap_find_dirty(RAMBlock *rb, + ram_addr_t start, + ram_addr_t *ram_addr_abs) +{ + unsigned long base = rb->offset >> TARGET_PAGE_BITS; + unsigned long nr = base + (start >> TARGET_PAGE_BITS); + 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) { + next = nr + 1; + } else { + next = find_next_bit(bitmap, size, nr); + } + + *ram_addr_abs = next << TARGET_PAGE_BITS; + return (next - base) << TARGET_PAGE_BITS; +} + +static inline bool migration_bitmap_clear_dirty(ram_addr_t addr) +{ + bool ret; + int nr = addr >> TARGET_PAGE_BITS; + unsigned long *bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + + ret = test_and_clear_bit(nr, bitmap); + + if (ret) { + migration_dirty_pages--; + } + return ret; +} + +static void migration_bitmap_sync_range(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); +} + +/* Fix me: there are too many global variables used in migration process. */ +static int64_t start_time; +static int64_t bytes_xfer_prev; +static int64_t num_dirty_pages_period; +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; +} + +/* Called with iothread lock held, to protect ram_list.dirty_memory[] */ +static void migration_bitmap_sync(void) +{ + RAMBlock *block; + uint64_t num_dirty_pages_init = migration_dirty_pages; + MigrationState *s = migrate_get_current(); + int64_t end_time; + int64_t bytes_xfer_now; + + bitmap_sync_count++; + + if (!bytes_xfer_prev) { + bytes_xfer_prev = ram_bytes_transferred(); + } + + if (!start_time) { + start_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + } + + trace_migration_bitmap_sync_start(); + address_space_sync_dirty_bitmap(&address_space_memory); + + qemu_mutex_lock(&migration_bitmap_mutex); + rcu_read_lock(); + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + migration_bitmap_sync_range(block->offset, block->used_length); + } + rcu_read_unlock(); + qemu_mutex_unlock(&migration_bitmap_mutex); + + trace_migration_bitmap_sync_end(migration_dirty_pages + - num_dirty_pages_init); + num_dirty_pages_period += migration_dirty_pages - num_dirty_pages_init; + end_time = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + + /* more than 1 second = 1000 millisecons */ + if (end_time > start_time + 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. + amount of bytes that just got transferred since the last time we + were in this routine. If that happens twice, start or increase + 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)) { + trace_migration_throttle(); + dirty_rate_high_cnt = 0; + mig_throttle_guest_down(); + } + 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); + } + iterations_prev = acct_info.iterations; + xbzrle_cache_miss_prev = acct_info.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; + } + s->dirty_sync_count = bitmap_sync_count; +} + +/** + * save_zero_page: Send the zero page to the stream + * + * Returns: Number of pages 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 + * @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) +{ + 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; + pages = 1; + } + + return pages; +} + +/** + * ram_save_page: Send the given page to the stream + * + * Returns: Number of pages written. + * < 0 - error + * >=0 - Number of pages written - this might legally be 0 + * if xbzrle noticed the page was the same. + * + * @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 + * @last_stage: if we are at the completion stage + * @bytes_transferred: increase it with the number of transferred bytes + */ +static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset, + bool last_stage, uint64_t *bytes_transferred) +{ + int pages = -1; + uint64_t bytes_xmit; + ram_addr_t current_addr; + uint8_t *p; + int ret; + bool send_async = true; + + p = block->host + offset; + + /* In doubt sent page as normal */ + bytes_xmit = 0; + ret = ram_control_save_page(f, block->offset, + offset, TARGET_PAGE_SIZE, &bytes_xmit); + if (bytes_xmit) { + *bytes_transferred += bytes_xmit; + pages = 1; + } + + XBZRLE_cache_lock(); + + 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++; + } else if (bytes_xmit == 0) { + acct_info.dup_pages++; + } + } + } else { + pages = save_zero_page(f, block, offset, p, bytes_transferred); + if (pages > 0) { + /* Must let xbzrle know, otherwise a previous (now 0'd) cached + * page would be stale + */ + xbzrle_cache_zero_page(current_addr); + } else if (!ram_bulk_stage && migrate_use_xbzrle()) { + pages = save_xbzrle_page(f, &p, current_addr, block, + offset, last_stage, bytes_transferred); + if (!last_stage) { + /* Can't send this cached data async, since the cache page + * might get updated before it gets to the wire + */ + send_async = false; + } + } + } + + /* XBZRLE overflow or normal page */ + if (pages == -1) { + *bytes_transferred += save_page_header(f, block, + offset | RAM_SAVE_FLAG_PAGE); + if (send_async) { + qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE); + } else { + qemu_put_buffer(f, p, TARGET_PAGE_SIZE); + } + *bytes_transferred += TARGET_PAGE_SIZE; + pages = 1; + acct_info.norm_pages++; + } + + XBZRLE_cache_unlock(); + + return pages; +} + +static int do_compress_ram_page(CompressParam *param) +{ + int bytes_sent, blen; + uint8_t *p; + RAMBlock *block = param->block; + ram_addr_t offset = param->offset; + + p = block->host + (offset & TARGET_PAGE_MASK); + + bytes_sent = save_page_header(param->file, block, offset | + RAM_SAVE_FLAG_COMPRESS_PAGE); + blen = qemu_put_compression_data(param->file, p, TARGET_PAGE_SIZE, + migrate_compress_level()); + bytes_sent += blen; + + return bytes_sent; +} + +static inline void start_compression(CompressParam *param) +{ + param->done = false; + qemu_mutex_lock(¶m->mutex); + param->start = true; + qemu_cond_signal(¶m->cond); + qemu_mutex_unlock(¶m->mutex); +} + +static inline void start_decompression(DecompressParam *param) +{ + qemu_mutex_lock(¶m->mutex); + param->start = true; + qemu_cond_signal(¶m->cond); + qemu_mutex_unlock(¶m->mutex); +} + +static uint64_t bytes_transferred; + +static void flush_compressed_data(QEMUFile *f) +{ + int idx, len, thread_count; + + if (!migrate_use_compression()) { + return; + } + thread_count = migrate_compress_threads(); + for (idx = 0; idx < thread_count; idx++) { + if (!comp_param[idx].done) { + qemu_mutex_lock(comp_done_lock); + while (!comp_param[idx].done && !quit_comp_thread) { + qemu_cond_wait(comp_done_cond, comp_done_lock); + } + qemu_mutex_unlock(comp_done_lock); + } + if (!quit_comp_thread) { + len = qemu_put_qemu_file(f, comp_param[idx].file); + bytes_transferred += len; + } + } +} + +static inline void set_compress_params(CompressParam *param, RAMBlock *block, + ram_addr_t offset) +{ + param->block = block; + param->offset = offset; +} + +static int compress_page_with_multi_thread(QEMUFile *f, RAMBlock *block, + ram_addr_t offset, + uint64_t *bytes_transferred) +{ + int idx, thread_count, bytes_xmit = -1, pages = -1; + + thread_count = migrate_compress_threads(); + qemu_mutex_lock(comp_done_lock); + while (true) { + for (idx = 0; idx < thread_count; idx++) { + if (comp_param[idx].done) { + bytes_xmit = qemu_put_qemu_file(f, comp_param[idx].file); + set_compress_params(&comp_param[idx], block, offset); + start_compression(&comp_param[idx]); + pages = 1; + acct_info.norm_pages++; + *bytes_transferred += bytes_xmit; + break; + } + } + if (pages > 0) { + break; + } else { + qemu_cond_wait(comp_done_cond, comp_done_lock); + } + } + qemu_mutex_unlock(comp_done_lock); + + return pages; +} + +/** + * ram_save_compressed_page: compress the given page and send it to the stream + * + * Returns: Number of pages 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 + * @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(QEMUFile *f, RAMBlock *block, + ram_addr_t offset, bool last_stage, + uint64_t *bytes_transferred) +{ + int pages = -1; + uint64_t bytes_xmit; + uint8_t *p; + int ret; + + p = block->host + offset; + + bytes_xmit = 0; + ret = ram_control_save_page(f, block->offset, + offset, TARGET_PAGE_SIZE, &bytes_xmit); + if (bytes_xmit) { + *bytes_transferred += bytes_xmit; + pages = 1; + } + 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++; + } else if (bytes_xmit == 0) { + acct_info.dup_pages++; + } + } + } else { + /* When starting the process of a new block, the first page of + * the block should be sent out before other pages in the same + * block, and all the pages in last block should have been sent + * 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 (pages == -1) { + set_compress_params(&comp_param[0], block, offset); + /* Use the qemu thread to compress the data to make sure the + * first page is sent out before other pages + */ + bytes_xmit = do_compress_ram_page(&comp_param[0]); + acct_info.norm_pages++; + qemu_put_qemu_file(f, comp_param[0].file); + *bytes_transferred += bytes_xmit; + pages = 1; + } + } else { + pages = save_zero_page(f, block, offset, p, bytes_transferred); + if (pages == -1) { + pages = compress_page_with_multi_thread(f, block, offset, + bytes_transferred); + } + } + } + + return pages; +} + +/* + * Find the next dirty page and update any state associated with + * the search process. + * + * Returns: True 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 + */ +static bool find_dirty_block(QEMUFile *f, PageSearchStatus *pss, + bool *again, ram_addr_t *ram_addr_abs) +{ + 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) { + /* + * We've been once around the RAM and haven't found anything. + * Give up. + */ + *again = false; + return false; + } + if (pss->offset >= pss->block->used_length) { + /* Didn't find anything in this RAM Block */ + pss->offset = 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; + 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; + } + } + /* Didn't find anything this time, but try again on the new block */ + *again = true; + return false; + } else { + /* Can go around again, but... */ + *again = true; + /* We've found something so probably don't need to */ + return true; + } +} + +/* + * 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) + */ +static RAMBlock *unqueue_page(MigrationState *ms, ram_addr_t *offset, + ram_addr_t *ram_addr_abs) +{ + 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); + 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); + g_free(entry); + } + } + qemu_mutex_unlock(&ms->src_page_req_mutex); + + return block; +} + +/* + * Unqueue a page from the queue fed by postcopy page 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: true if a queued page is found + */ +static bool get_queued_page(MigrationState *ms, PageSearchStatus *pss, + ram_addr_t *ram_addr_abs) +{ + RAMBlock *block; + ram_addr_t offset; + bool dirty; + + do { + block = unqueue_page(ms, &offset, ram_addr_abs); + /* + * 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 + * even if this queue request was received after the background + * search already sent it. + */ + if (block) { + unsigned long *bitmap; + bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + dirty = test_bit(*ram_addr_abs >> TARGET_PAGE_BITS, 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)); + } else { + trace_get_queued_page(block->idstr, + (uint64_t)offset, + (uint64_t)*ram_addr_abs); + } + } + + } while (block && !dirty); + + if (block) { + /* + * As soon as we start servicing pages out of order, then we have + * to kill the bulk stage, since the bulk stage assumes + * in (migration_bitmap_find_and_reset_dirty) that every page is + * dirty, that's no longer true. + */ + ram_bulk_stage = false; + + /* + * We want the background search to continue from the queued page + * since the guest is likely to want other pages near to the page + * it just requested. + */ + pss->block = block; + pss->offset = offset; + } + + 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. + * + * ms: MigrationState + */ +void flush_page_queue(MigrationState *ms) +{ + struct MigrationSrcPageRequest *mspr, *next_mspr; + /* 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) { + memory_region_unref(mspr->rb->mr); + QSIMPLEQ_REMOVE_HEAD(&ms->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 + */ +int ram_save_queue_pages(MigrationState *ms, const char *rbname, + ram_addr_t start, ram_addr_t len) +{ + RAMBlock *ramblock; + + rcu_read_lock(); + if (!rbname) { + /* Reuse last RAMBlock */ + ramblock = ms->last_req_rb; + + if (!ramblock) { + /* + * Shouldn't happen, we can't reuse the last RAMBlock if + * it's the 1st request. + */ + error_report("ram_save_queue_pages no previous block"); + goto err; + } + } else { + ramblock = qemu_ram_block_by_name(rbname); + + if (!ramblock) { + /* We shouldn't be asked for a non-existent RAMBlock */ + error_report("ram_save_queue_pages no block '%s'", rbname); + goto err; + } + ms->last_req_rb = ramblock; + } + trace_ram_save_queue_pages(ramblock->idstr, start, len); + if (start+len > ramblock->used_length) { + error_report("%s request overrun start=" RAM_ADDR_FMT " len=" + RAM_ADDR_FMT " blocklen=" RAM_ADDR_FMT, + __func__, start, len, ramblock->used_length); + goto err; + } + + struct MigrationSrcPageRequest *new_entry = + g_malloc0(sizeof(struct MigrationSrcPageRequest)); + 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); + rcu_read_unlock(); + + return 0; + +err: + rcu_read_unlock(); + return -1; +} + +/** + * ram_save_target_page: Save one target page + * + * + * @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; + * @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, + RAMBlock *block, ram_addr_t offset, + bool last_stage, + uint64_t *bytes_transferred, + ram_addr_t dirty_ram_abs) +{ + int res = 0; + + /* Check the pages is dirty and if it is send it */ + if (migration_bitmap_clear_dirty(dirty_ram_abs)) { + unsigned long *unsentmap; + if (compression_switch && migrate_use_compression()) { + res = ram_save_compressed_page(f, block, offset, + last_stage, + bytes_transferred); + } else { + res = ram_save_page(f, block, offset, last_stage, + bytes_transferred); + } + + if (res < 0) { + return res; + } + unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->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 = block; + } + } + + return res; +} + +/** + * ram_save_host_page: Starting at *offset send pages upto 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. + * + * Returns: 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; updated to last target page + * sent + * @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, RAMBlock *block, + ram_addr_t *offset, bool last_stage, + uint64_t *bytes_transferred, + ram_addr_t dirty_ram_abs) +{ + int tmppages, pages = 0; + do { + tmppages = ram_save_target_page(ms, f, block, *offset, last_stage, + bytes_transferred, dirty_ram_abs); + if (tmppages < 0) { + return tmppages; + } + + pages += tmppages; + *offset += TARGET_PAGE_SIZE; + dirty_ram_abs += TARGET_PAGE_SIZE; + } while (*offset & (qemu_host_page_size - 1)); + + /* The offset we leave with is the last one we looked at */ + *offset -= TARGET_PAGE_SIZE; + return pages; +} + +/** + * 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 + * + * @f: QEMUFile where to send the data + * @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) +{ + 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 */ + + pss.block = last_seen_block; + pss.offset = last_offset; + pss.complete_round = false; + + if (!pss.block) { + pss.block = QLIST_FIRST_RCU(&ram_list.blocks); + } + + do { + again = true; + found = get_queued_page(ms, &pss, &dirty_ram_abs); + + if (!found) { + /* priority queue empty, so just search for something dirty */ + found = find_dirty_block(f, &pss, &again, &dirty_ram_abs); + } + + if (found) { + pages = ram_save_host_page(ms, f, pss.block, &pss.offset, + last_stage, bytes_transferred, + dirty_ram_abs); + } + } while (!pages && again); + + last_seen_block = pss.block; + last_offset = pss.offset; + + return pages; +} + +void acct_update_position(QEMUFile *f, size_t size, bool zero) +{ + uint64_t pages = size / TARGET_PAGE_SIZE; + if (zero) { + acct_info.dup_pages += pages; + } else { + acct_info.norm_pages += pages; + 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; + uint64_t total = 0; + + rcu_read_lock(); + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) + total += block->used_length; + rcu_read_unlock(); + return total; +} + +void free_xbzrle_decoded_buf(void) +{ + g_free(xbzrle_decoded_buf); + xbzrle_decoded_buf = NULL; +} + +static void migration_bitmap_free(struct BitmapRcu *bmap) +{ + g_free(bmap->bmap); + g_free(bmap->unsentmap); + g_free(bmap); +} + +static void ram_migration_cleanup(void *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); + if (bitmap) { + memory_global_dirty_log_stop(); + call_rcu(bitmap, migration_bitmap_free, rcu); + } + + XBZRLE_cache_lock(); + if (XBZRLE.cache) { + cache_fini(XBZRLE.cache); + g_free(XBZRLE.encoded_buf); + g_free(XBZRLE.current_buf); + XBZRLE.cache = NULL; + XBZRLE.encoded_buf = NULL; + XBZRLE.current_buf = NULL; + } + XBZRLE_cache_unlock(); +} + +static void reset_ram_globals(void) +{ + last_seen_block = NULL; + last_sent_block = NULL; + last_offset = 0; + last_version = ram_list.version; + 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. + * If 'todump' is null the migration bitmap is dumped. + */ +void ram_debug_dump_bitmap(unsigned long *todump, bool expected) +{ + int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS; + + int64_t cur; + int64_t linelen = 128; + char linebuf[129]; + + if (!todump) { + todump = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + } + + for (cur = 0; cur < ram_pages; cur += linelen) { + int64_t curb; + bool found = false; + /* + * Last line; catch the case where the line length + * is longer than remaining ram + */ + if (cur + linelen > ram_pages) { + linelen = ram_pages - cur; + } + for (curb = 0; curb < linelen; curb++) { + bool thisbit = test_bit(cur + curb, todump); + linebuf[curb] = thisbit ? '1' : '.'; + found = found || (thisbit != expected); + } + if (found) { + linebuf[curb] = '\0'; + fprintf(stderr, "0x%08" PRIx64 " : %s\n", cur, linebuf); + } + } +} + +/* **** functions for postcopy ***** */ + +/* + * 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 + */ +static int postcopy_send_discard_bm_ram(MigrationState *ms, + PostcopyDiscardState *pds, + unsigned long start, + unsigned long length) +{ + unsigned long end = start + length; /* one after the end */ + unsigned long current; + unsigned long *unsentmap; + + unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap; + for (current = start; current < end; ) { + unsigned long one = find_next_bit(unsentmap, end, current); + + if (one <= end) { + unsigned long zero = find_next_zero_bit(unsentmap, end, one + 1); + unsigned long discard_length; + + if (zero >= end) { + discard_length = end - one; + } else { + discard_length = zero - one; + } + postcopy_discard_send_range(ms, pds, one, discard_length); + current = one + discard_length; + } else { + current = one; + } + } + + return 0; +} + +/* + * 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) + */ +static int postcopy_each_ram_send_discard(MigrationState *ms) +{ + struct RAMBlock *block; + int ret; + + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + unsigned long first = block->offset >> TARGET_PAGE_BITS; + PostcopyDiscardState *pds = postcopy_discard_send_init(ms, + first, + block->idstr); + + /* + * Postcopy sends chunks of bitmap over the wire, but it + * just needs indexes at this point, avoids it having + * target page specific code. + */ + ret = postcopy_send_discard_bm_ram(ms, pds, first, + block->used_length >> TARGET_PAGE_BITS); + postcopy_discard_send_finish(ms, pds); + if (ret) { + return ret; + } + } + + return 0; +} + +/* + * Helper for postcopy_chunk_hostpages; it's called twice to cleanup + * 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 + * + */ +static void postcopy_chunk_hostpages_pass(MigrationState *ms, bool unsent_pass, + RAMBlock *block, + PostcopyDiscardState *pds) +{ + unsigned long *bitmap; + unsigned long *unsentmap; + unsigned int host_ratio = qemu_host_page_size / TARGET_PAGE_SIZE; + unsigned long first = block->offset >> TARGET_PAGE_BITS; + unsigned long len = block->used_length >> TARGET_PAGE_BITS; + unsigned long last = first + (len - 1); + unsigned long run_start; + + bitmap = atomic_rcu_read(&migration_bitmap_rcu)->bmap; + unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->unsentmap; + + if (unsent_pass) { + /* Find a sent page */ + run_start = find_next_zero_bit(unsentmap, last + 1, first); + } else { + /* Find a dirty page */ + run_start = find_next_bit(bitmap, last + 1, first); + } + + while (run_start <= last) { + bool do_fixup = false; + unsigned long fixup_start_addr; + unsigned long host_offset; + + /* + * If the start of this run of pages is in the middle of a host + * page, then we need to fixup this host page. + */ + host_offset = run_start % host_ratio; + if (host_offset) { + do_fixup = true; + run_start -= host_offset; + fixup_start_addr = run_start; + /* For the next pass */ + run_start = run_start + host_ratio; + } else { + /* Find the end of this run */ + unsigned long run_end; + if (unsent_pass) { + run_end = find_next_bit(unsentmap, last + 1, run_start + 1); + } else { + run_end = find_next_zero_bit(bitmap, last + 1, run_start + 1); + } + /* + * If the end isn't at the start of a host page, then the + * run doesn't finish at the end of a host page + * and we need to discard. + */ + host_offset = run_end % host_ratio; + if (host_offset) { + do_fixup = true; + fixup_start_addr = run_end - host_offset; + /* + * This host page has gone, the next loop iteration starts + * from after the fixup + */ + run_start = fixup_start_addr + host_ratio; + } else { + /* + * No discards on this iteration, next loop starts from + * next sent/dirty page + */ + run_start = run_end + 1; + } + } + + if (do_fixup) { + unsigned long page; + + /* Tell the destination to discard this page */ + if (unsent_pass || !test_bit(fixup_start_addr, unsentmap)) { + /* For the unsent_pass we: + * discard partially sent pages + * For the !unsent_pass (dirty) we: + * discard partially dirty pages that were sent + * (any partially sent pages were already discarded + * by the previous unsent_pass) + */ + postcopy_discard_send_range(ms, pds, fixup_start_addr, + host_ratio); + } + + /* Clean up the bitmap */ + for (page = fixup_start_addr; + page < fixup_start_addr + host_ratio; page++) { + /* All pages in this host page are now not sent */ + set_bit(page, unsentmap); + + /* + * Remark them as dirty, updating the count for any pages + * that weren't previously dirty. + */ + migration_dirty_pages += !test_and_set_bit(page, bitmap); + } + } + + if (unsent_pass) { + /* Find the next sent page for the next iteration */ + run_start = find_next_zero_bit(unsentmap, last + 1, + run_start); + } else { + /* Find the next dirty page for the next iteration */ + run_start = find_next_bit(bitmap, last + 1, run_start); + } + } +} + +/* + * 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. + * + * Returns: 0 on success + */ +static int postcopy_chunk_hostpages(MigrationState *ms) +{ + struct RAMBlock *block; + + if (qemu_host_page_size == TARGET_PAGE_SIZE) { + /* Easy case - TPS==HPS - nothing to be done */ + return 0; + } + + /* 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; + + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + unsigned long first = block->offset >> TARGET_PAGE_BITS; + + PostcopyDiscardState *pds = + postcopy_discard_send_init(ms, first, block->idstr); + + /* First pass: Discard all partially sent host pages */ + postcopy_chunk_hostpages_pass(ms, true, block, pds); + /* + * Second pass: Ensure that all partially dirty host pages are made + * fully dirty. + */ + postcopy_chunk_hostpages_pass(ms, false, block, pds); + + postcopy_discard_send_finish(ms, pds); + } /* ram_list loop */ + + return 0; +} + +/* + * 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 + * b) Pages that have never been transmitted, this ensures that + * 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 + */ +int ram_postcopy_send_discard_bitmap(MigrationState *ms) +{ + int ret; + unsigned long *bitmap, *unsentmap; + + rcu_read_lock(); + + /* This should be our last sync, the src is now paused */ + migration_bitmap_sync(); + + unsentmap = atomic_rcu_read(&migration_bitmap_rcu)->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 + * point. + */ + error_report("migration ram resized during precopy phase"); + rcu_read_unlock(); + return -EINVAL; + } + + /* Deal with TPS != HPS */ + ret = postcopy_chunk_hostpages(ms); + if (ret) { + rcu_read_unlock(); + return ret; + } + + /* + * 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); + + + trace_ram_postcopy_send_discard_bitmap(); +#ifdef DEBUG_POSTCOPY + ram_debug_dump_bitmap(unsentmap, true); +#endif + + ret = postcopy_each_ram_send_discard(ms); + rcu_read_unlock(); + + return ret; +} + +/* + * At the start of the postcopy phase of migration, any now-dirty + * precopied pages are discarded. + * + * start, length describe a byte address range within the RAMBlock + * + * Returns 0 on success. + */ +int ram_discard_range(MigrationIncomingState *mis, + const char *block_name, + uint64_t start, size_t length) +{ + int ret = -1; + + rcu_read_lock(); + RAMBlock *rb = qemu_ram_block_by_name(block_name); + + if (!rb) { + error_report("ram_discard_range: Failed to find block '%s'", + block_name); + goto err; + } + + uint8_t *host_startaddr = rb->host + start; + + if ((uintptr_t)host_startaddr & (qemu_host_page_size - 1)) { + error_report("ram_discard_range: Unaligned start address: %p", + host_startaddr); + goto err; + } + + if ((start + length) <= rb->used_length) { + uint8_t *host_endaddr = host_startaddr + length; + if ((uintptr_t)host_endaddr & (qemu_host_page_size - 1)) { + error_report("ram_discard_range: Unaligned end address: %p", + host_endaddr); + goto err; + } + ret = postcopy_ram_discard_range(mis, host_startaddr, length); + } else { + error_report("ram_discard_range: Overrun block '%s' (%" PRIu64 + "/%zx/" RAM_ADDR_FMT")", + block_name, start, length, rb->used_length); + } + +err: + rcu_read_unlock(); + + return ret; +} + + +/* 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. + */ + +static int ram_save_setup(QEMUFile *f, void *opaque) +{ + RAMBlock *block; + int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */ + + dirty_rate_high_cnt = 0; + bitmap_sync_count = 0; + migration_bitmap_sync_init(); + qemu_mutex_init(&migration_bitmap_mutex); + + if (migrate_use_xbzrle()) { + XBZRLE_cache_lock(); + XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() / + TARGET_PAGE_SIZE, + TARGET_PAGE_SIZE); + if (!XBZRLE.cache) { + XBZRLE_cache_unlock(); + error_report("Error creating cache"); + return -1; + } + XBZRLE_cache_unlock(); + + /* We prefer not to abort if there is no memory */ + XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE); + if (!XBZRLE.encoded_buf) { + error_report("Error allocating encoded_buf"); + return -1; + } + + XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE); + if (!XBZRLE.current_buf) { + error_report("Error allocating current_buf"); + g_free(XBZRLE.encoded_buf); + XBZRLE.encoded_buf = NULL; + return -1; + } + + acct_clear(); + } + + /* iothread lock needed for ram_list.dirty_memory[] */ + qemu_mutex_lock_iothread(); + qemu_mutex_lock_ramlist(); + rcu_read_lock(); + bytes_transferred = 0; + reset_ram_globals(); + + ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS; + migration_bitmap_rcu = g_new0(struct BitmapRcu, 1); + migration_bitmap_rcu->bmap = bitmap_new(ram_bitmap_pages); + bitmap_set(migration_bitmap_rcu->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); + } + + /* + * 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; + + memory_global_dirty_log_start(); + migration_bitmap_sync(); + qemu_mutex_unlock_ramlist(); + qemu_mutex_unlock_iothread(); + + qemu_put_be64(f, ram_bytes_total() | RAM_SAVE_FLAG_MEM_SIZE); + + QLIST_FOREACH_RCU(block, &ram_list.blocks, next) { + qemu_put_byte(f, strlen(block->idstr)); + qemu_put_buffer(f, (uint8_t *)block->idstr, strlen(block->idstr)); + qemu_put_be64(f, block->used_length); + } + + rcu_read_unlock(); + + ram_control_before_iterate(f, RAM_CONTROL_SETUP); + ram_control_after_iterate(f, RAM_CONTROL_SETUP); + + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + + return 0; +} + +static int ram_save_iterate(QEMUFile *f, void *opaque) +{ + int ret; + int i; + int64_t t0; + int pages_sent = 0; + + rcu_read_lock(); + if (ram_list.version != last_version) { + reset_ram_globals(); + } + + /* Read version before ram_list.blocks */ + smp_rmb(); + + ram_control_before_iterate(f, RAM_CONTROL_ROUND); + + t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); + i = 0; + while ((ret = qemu_file_rate_limit(f)) == 0) { + int pages; + + pages = ram_find_and_save_block(f, false, &bytes_transferred); + /* no more pages to sent */ + if (pages == 0) { + break; + } + pages_sent += pages; + acct_info.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. + qemu_get_clock_ns() is a bit expensive, so we only check each some + iterations + */ + if ((i & 63) == 0) { + uint64_t t1 = (qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - t0) / 1000000; + if (t1 > MAX_WAIT) { + DPRINTF("big wait: %" PRIu64 " milliseconds, %d iterations\n", + t1, i); + break; + } + } + i++; + } + flush_compressed_data(f); + rcu_read_unlock(); + + /* + * Must occur before EOS (or any QEMUFile operation) + * because of RDMA protocol. + */ + ram_control_after_iterate(f, RAM_CONTROL_ROUND); + + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + bytes_transferred += 8; + + ret = qemu_file_get_error(f); + if (ret < 0) { + return ret; + } + + return pages_sent; +} + +/* Called with iothread lock */ +static int ram_save_complete(QEMUFile *f, void *opaque) +{ + rcu_read_lock(); + + if (!migration_in_postcopy(migrate_get_current())) { + migration_bitmap_sync(); + } + + ram_control_before_iterate(f, RAM_CONTROL_FINISH); + + /* try transferring iterative blocks of memory */ + + /* flush all remaining blocks regardless of rate limiting */ + while (true) { + int pages; + + pages = ram_find_and_save_block(f, true, &bytes_transferred); + /* no more blocks to sent */ + if (pages == 0) { + break; + } + } + + flush_compressed_data(f); + ram_control_after_iterate(f, RAM_CONTROL_FINISH); + + rcu_read_unlock(); + + qemu_put_be64(f, RAM_SAVE_FLAG_EOS); + + return 0; +} + +static void ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size, + uint64_t *non_postcopiable_pending, + uint64_t *postcopiable_pending) +{ + uint64_t remaining_size; + + remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE; + + if (!migration_in_postcopy(migrate_get_current()) && + remaining_size < max_size) { + qemu_mutex_lock_iothread(); + rcu_read_lock(); + migration_bitmap_sync(); + rcu_read_unlock(); + qemu_mutex_unlock_iothread(); + remaining_size = ram_save_remaining() * TARGET_PAGE_SIZE; + } + + /* We can do postcopy, and all the data is postcopiable */ + *postcopiable_pending += remaining_size; +} + +static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host) +{ + unsigned int xh_len; + int xh_flags; + + if (!xbzrle_decoded_buf) { + xbzrle_decoded_buf = g_malloc(TARGET_PAGE_SIZE); + } + + /* extract RLE header */ + xh_flags = qemu_get_byte(f); + xh_len = qemu_get_be16(f); + + if (xh_flags != ENCODING_FLAG_XBZRLE) { + error_report("Failed to load XBZRLE page - wrong compression!"); + return -1; + } + + if (xh_len > TARGET_PAGE_SIZE) { + error_report("Failed to load XBZRLE page - len overflow!"); + return -1; + } + /* load data and decode */ + qemu_get_buffer(f, xbzrle_decoded_buf, xh_len); + + /* decode RLE */ + if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host, + TARGET_PAGE_SIZE) == -1) { + error_report("Failed to load XBZRLE page - decode error!"); + return -1; + } + + return 0; +} + +/* 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, find the host address of the + * start of that block and add on 'offset' + * + * f: Stream to read from + * offset: Offset within the block + * flags: Page flags (mostly to see if it's a continuation of previous block) + */ +static inline void *host_from_stream_offset(QEMUFile *f, + ram_addr_t offset, + int flags) +{ + static RAMBlock *block = NULL; + char id[256]; + uint8_t len; + + if (flags & RAM_SAVE_FLAG_CONTINUE) { + if (!block || block->max_length <= offset) { + error_report("Ack, bad migration stream!"); + return NULL; + } + + return block->host + offset; + } + + len = qemu_get_byte(f); + qemu_get_buffer(f, (uint8_t *)id, len); + id[len] = 0; + + block = qemu_ram_block_by_name(id); + if (block && block->max_length > offset) { + return block->host + offset; + } + + error_report("Can't find block %s", id); + return NULL; +} + +/* + * If a page (or a whole RDMA chunk) has been + * determined to be zero, then zap it. + */ +void ram_handle_compressed(void *host, uint8_t ch, uint64_t size) +{ + if (ch != 0 || !is_zero_range(host, size)) { + memset(host, ch, size); + } +} + +static void *do_data_decompress(void *opaque) +{ + DecompressParam *param = opaque; + unsigned long pagesize; + + while (!quit_decomp_thread) { + qemu_mutex_lock(¶m->mutex); + while (!param->start && !quit_decomp_thread) { + qemu_cond_wait(¶m->cond, ¶m->mutex); + pagesize = TARGET_PAGE_SIZE; + if (!quit_decomp_thread) { + /* uncompress() will return failed in some case, especially + * when the page is dirted when doing the compression, it's + * not a problem because the dirty page will be retransferred + * and uncompress() won't break the data in other pages. + */ + uncompress((Bytef *)param->des, &pagesize, + (const Bytef *)param->compbuf, param->len); + } + param->start = false; + } + qemu_mutex_unlock(¶m->mutex); + } + + return NULL; +} + +void migrate_decompress_threads_create(void) +{ + int i, thread_count; + + thread_count = migrate_decompress_threads(); + decompress_threads = g_new0(QemuThread, thread_count); + decomp_param = g_new0(DecompressParam, thread_count); + compressed_data_buf = g_malloc0(compressBound(TARGET_PAGE_SIZE)); + quit_decomp_thread = false; + for (i = 0; i < thread_count; i++) { + qemu_mutex_init(&decomp_param[i].mutex); + qemu_cond_init(&decomp_param[i].cond); + decomp_param[i].compbuf = g_malloc0(compressBound(TARGET_PAGE_SIZE)); + qemu_thread_create(decompress_threads + i, "decompress", + do_data_decompress, decomp_param + i, + QEMU_THREAD_JOINABLE); + } +} + +void migrate_decompress_threads_join(void) +{ + int i, thread_count; + + quit_decomp_thread = true; + thread_count = migrate_decompress_threads(); + for (i = 0; i < thread_count; i++) { + qemu_mutex_lock(&decomp_param[i].mutex); + qemu_cond_signal(&decomp_param[i].cond); + qemu_mutex_unlock(&decomp_param[i].mutex); + } + for (i = 0; i < thread_count; i++) { + qemu_thread_join(decompress_threads + i); + qemu_mutex_destroy(&decomp_param[i].mutex); + qemu_cond_destroy(&decomp_param[i].cond); + g_free(decomp_param[i].compbuf); + } + g_free(decompress_threads); + g_free(decomp_param); + g_free(compressed_data_buf); + decompress_threads = NULL; + decomp_param = NULL; + compressed_data_buf = NULL; +} + +static void decompress_data_with_multi_threads(uint8_t *compbuf, + void *host, int len) +{ + int idx, thread_count; + + thread_count = migrate_decompress_threads(); + while (true) { + for (idx = 0; idx < thread_count; idx++) { + if (!decomp_param[idx].start) { + memcpy(decomp_param[idx].compbuf, compbuf, len); + decomp_param[idx].des = host; + decomp_param[idx].len = len; + start_decompression(&decomp_param[idx]); + break; + } + } + if (idx < thread_count) { + break; + } + } +} + +/* + * 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; + + return postcopy_ram_incoming_init(mis, ram_pages); +} + +/* + * Called in postcopy mode by ram_load(). + * rcu_read_lock is taken prior to this being called. + */ +static int ram_load_postcopy(QEMUFile *f) +{ + int flags = 0, ret = 0; + bool place_needed = false; + bool matching_page_sizes = qemu_host_page_size == TARGET_PAGE_SIZE; + MigrationIncomingState *mis = migration_incoming_get_current(); + /* Temporary page that is later 'placed' */ + void *postcopy_host_page = postcopy_get_tmp_page(mis); + void *last_host = NULL; + bool all_zero = false; + + while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) { + ram_addr_t addr; + void *host = NULL; + void *page_buffer = NULL; + void *place_source = NULL; + uint8_t ch; + + addr = qemu_get_be64(f); + flags = addr & ~TARGET_PAGE_MASK; + addr &= TARGET_PAGE_MASK; + + trace_ram_load_postcopy_loop((uint64_t)addr, flags); + place_needed = false; + if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE)) { + host = host_from_stream_offset(f, addr, flags); + if (!host) { + error_report("Illegal RAM offset " RAM_ADDR_FMT, addr); + ret = -EINVAL; + break; + } + page_buffer = host; + /* + * Postcopy requires that we place whole host pages atomically. + * To make it atomic, the data is read into a temporary page + * that's moved into place later. + * The migration protocol uses, possibly smaller, target-pages + * however the source ensures it always sends all the components + * of a host page in order. + */ + page_buffer = postcopy_host_page + + ((uintptr_t)host & ~qemu_host_page_mask); + /* If all TP are zero then we can optimise the place */ + if (!((uintptr_t)host & ~qemu_host_page_mask)) { + all_zero = true; + } else { + /* not the 1st TP within the HP */ + if (host != (last_host + TARGET_PAGE_SIZE)) { + error_report("Non-sequential target page %p/%p\n", + host, last_host); + ret = -EINVAL; + break; + } + } + + + /* + * If it's the last part of a host page then we place the host + * page + */ + place_needed = (((uintptr_t)host + TARGET_PAGE_SIZE) & + ~qemu_host_page_mask) == 0; + place_source = postcopy_host_page; + } + last_host = host; + + switch (flags & ~RAM_SAVE_FLAG_CONTINUE) { + case RAM_SAVE_FLAG_COMPRESS: + ch = qemu_get_byte(f); + memset(page_buffer, ch, TARGET_PAGE_SIZE); + if (ch) { + all_zero = false; + } + break; + + case RAM_SAVE_FLAG_PAGE: + all_zero = false; + if (!place_needed || !matching_page_sizes) { + qemu_get_buffer(f, page_buffer, TARGET_PAGE_SIZE); + } else { + /* Avoids the qemu_file copy during postcopy, which is + * going to do a copy later; can only do it when we + * do this read in one go (matching page sizes) + */ + qemu_get_buffer_in_place(f, (uint8_t **)&place_source, + TARGET_PAGE_SIZE); + } + break; + case RAM_SAVE_FLAG_EOS: + /* normal exit */ + break; + default: + error_report("Unknown combination of migration flags: %#x" + " (postcopy mode)", flags); + ret = -EINVAL; + } + + if (place_needed) { + /* This gets called at the last target page in the host page */ + if (all_zero) { + ret = postcopy_place_page_zero(mis, + host + TARGET_PAGE_SIZE - + qemu_host_page_size); + } else { + ret = postcopy_place_page(mis, host + TARGET_PAGE_SIZE - + qemu_host_page_size, + place_source); + } + } + if (!ret) { + ret = qemu_file_get_error(f); + } + } + + return ret; +} + +static int ram_load(QEMUFile *f, void *opaque, int version_id) +{ + int flags = 0, ret = 0; + static uint64_t seq_iter; + int len = 0; + /* + * If system is running in postcopy mode, page inserts to host memory must + * be atomic + */ + bool postcopy_running = postcopy_state_get() >= POSTCOPY_INCOMING_LISTENING; + + seq_iter++; + + if (version_id != 4) { + ret = -EINVAL; + } + + /* This RCU critical section can be very long running. + * When RCU reclaims in the code start to become numerous, + * it will be necessary to reduce the granularity of this + * critical section. + */ + rcu_read_lock(); + + if (postcopy_running) { + ret = ram_load_postcopy(f); + } + + while (!postcopy_running && !ret && !(flags & RAM_SAVE_FLAG_EOS)) { + ram_addr_t addr, total_ram_bytes; + void *host = NULL; + uint8_t ch; + + addr = qemu_get_be64(f); + flags = addr & ~TARGET_PAGE_MASK; + addr &= TARGET_PAGE_MASK; + + if (flags & (RAM_SAVE_FLAG_COMPRESS | RAM_SAVE_FLAG_PAGE | + RAM_SAVE_FLAG_COMPRESS_PAGE | RAM_SAVE_FLAG_XBZRLE)) { + host = host_from_stream_offset(f, addr, flags); + if (!host) { + error_report("Illegal RAM offset " RAM_ADDR_FMT, addr); + ret = -EINVAL; + break; + } + } + + switch (flags & ~RAM_SAVE_FLAG_CONTINUE) { + case RAM_SAVE_FLAG_MEM_SIZE: + /* Synchronize RAM block list */ + total_ram_bytes = addr; + while (!ret && total_ram_bytes) { + RAMBlock *block; + char id[256]; + ram_addr_t length; + + len = qemu_get_byte(f); + qemu_get_buffer(f, (uint8_t *)id, len); + id[len] = 0; + length = qemu_get_be64(f); + + block = qemu_ram_block_by_name(id); + if (block) { + if (length != block->used_length) { + Error *local_err = NULL; + + ret = qemu_ram_resize(block->offset, length, + &local_err); + if (local_err) { + error_report_err(local_err); + } + } + ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG, + block->idstr); + } else { + error_report("Unknown ramblock \"%s\", cannot " + "accept migration", id); + ret = -EINVAL; + } + + total_ram_bytes -= length; + } + break; + + case RAM_SAVE_FLAG_COMPRESS: + ch = qemu_get_byte(f); + ram_handle_compressed(host, ch, TARGET_PAGE_SIZE); + break; + + case RAM_SAVE_FLAG_PAGE: + qemu_get_buffer(f, host, TARGET_PAGE_SIZE); + break; + + case RAM_SAVE_FLAG_COMPRESS_PAGE: + len = qemu_get_be32(f); + if (len < 0 || len > compressBound(TARGET_PAGE_SIZE)) { + error_report("Invalid compressed data length: %d", len); + ret = -EINVAL; + break; + } + qemu_get_buffer(f, compressed_data_buf, len); + decompress_data_with_multi_threads(compressed_data_buf, host, len); + break; + + case RAM_SAVE_FLAG_XBZRLE: + if (load_xbzrle(f, addr, host) < 0) { + error_report("Failed to decompress XBZRLE page at " + RAM_ADDR_FMT, addr); + ret = -EINVAL; + break; + } + break; + case RAM_SAVE_FLAG_EOS: + /* normal exit */ + break; + default: + if (flags & RAM_SAVE_FLAG_HOOK) { + ram_control_load_hook(f, RAM_CONTROL_HOOK, NULL); + } else { + error_report("Unknown combination of migration flags: %#x", + flags); + ret = -EINVAL; + } + } + if (!ret) { + ret = qemu_file_get_error(f); + } + } + + rcu_read_unlock(); + DPRINTF("Completed load of VM with exit code %d seq iteration " + "%" PRIu64 "\n", ret, seq_iter); + return ret; +} + +static SaveVMHandlers savevm_ram_handlers = { + .save_live_setup = ram_save_setup, + .save_live_iterate = ram_save_iterate, + .save_live_complete_postcopy = ram_save_complete, + .save_live_complete_precopy = ram_save_complete, + .save_live_pending = ram_save_pending, + .load_state = ram_load, + .cleanup = ram_migration_cleanup, +}; + +void ram_mig_init(void) +{ + qemu_mutex_init(&XBZRLE.lock); + register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL); +} diff --git a/src/migration/rdma.c b/src/migration/rdma.c new file mode 100644 index 0000000..dcabb91 --- /dev/null +++ b/src/migration/rdma.c @@ -0,0 +1,3516 @@ +/* + * RDMA protocol and interfaces + * + * Copyright IBM, Corp. 2010-2013 + * + * Authors: + * Michael R. Hines <mrhines@us.ibm.com> + * Jiuxing Liu <jl@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or + * later. See the COPYING file in the top-level directory. + * + */ +#include "qemu-common.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "exec/cpu-common.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "qemu/sockets.h" +#include "qemu/bitmap.h" +#include "qemu/coroutine.h" +#include <stdio.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netdb.h> +#include <arpa/inet.h> +#include <string.h> +#include <rdma/rdma_cma.h> +#include "trace.h" + +/* + * Print and error on both the Monitor and the Log file. + */ +#define ERROR(errp, fmt, ...) \ + do { \ + fprintf(stderr, "RDMA ERROR: " fmt "\n", ## __VA_ARGS__); \ + if (errp && (*(errp) == NULL)) { \ + error_setg(errp, "RDMA ERROR: " fmt, ## __VA_ARGS__); \ + } \ + } while (0) + +#define RDMA_RESOLVE_TIMEOUT_MS 10000 + +/* Do not merge data if larger than this. */ +#define RDMA_MERGE_MAX (2 * 1024 * 1024) +#define RDMA_SIGNALED_SEND_MAX (RDMA_MERGE_MAX / 4096) + +#define RDMA_REG_CHUNK_SHIFT 20 /* 1 MB */ + +/* + * This is only for non-live state being migrated. + * Instead of RDMA_WRITE messages, we use RDMA_SEND + * messages for that state, which requires a different + * delivery design than main memory. + */ +#define RDMA_SEND_INCREMENT 32768 + +/* + * Maximum size infiniband SEND message + */ +#define RDMA_CONTROL_MAX_BUFFER (512 * 1024) +#define RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE 4096 + +#define RDMA_CONTROL_VERSION_CURRENT 1 +/* + * Capabilities for negotiation. + */ +#define RDMA_CAPABILITY_PIN_ALL 0x01 + +/* + * Add the other flags above to this list of known capabilities + * as they are introduced. + */ +static uint32_t known_capabilities = RDMA_CAPABILITY_PIN_ALL; + +#define CHECK_ERROR_STATE() \ + do { \ + if (rdma->error_state) { \ + if (!rdma->error_reported) { \ + error_report("RDMA is in an error state waiting migration" \ + " to abort!"); \ + rdma->error_reported = 1; \ + } \ + return rdma->error_state; \ + } \ + } while (0); + +/* + * A work request ID is 64-bits and we split up these bits + * into 3 parts: + * + * bits 0-15 : type of control message, 2^16 + * bits 16-29: ram block index, 2^14 + * bits 30-63: ram block chunk number, 2^34 + * + * The last two bit ranges are only used for RDMA writes, + * in order to track their completion and potentially + * also track unregistration status of the message. + */ +#define RDMA_WRID_TYPE_SHIFT 0UL +#define RDMA_WRID_BLOCK_SHIFT 16UL +#define RDMA_WRID_CHUNK_SHIFT 30UL + +#define RDMA_WRID_TYPE_MASK \ + ((1UL << RDMA_WRID_BLOCK_SHIFT) - 1UL) + +#define RDMA_WRID_BLOCK_MASK \ + (~RDMA_WRID_TYPE_MASK & ((1UL << RDMA_WRID_CHUNK_SHIFT) - 1UL)) + +#define RDMA_WRID_CHUNK_MASK (~RDMA_WRID_BLOCK_MASK & ~RDMA_WRID_TYPE_MASK) + +/* + * RDMA migration protocol: + * 1. RDMA Writes (data messages, i.e. RAM) + * 2. IB Send/Recv (control channel messages) + */ +enum { + RDMA_WRID_NONE = 0, + RDMA_WRID_RDMA_WRITE = 1, + RDMA_WRID_SEND_CONTROL = 2000, + RDMA_WRID_RECV_CONTROL = 4000, +}; + +static const char *wrid_desc[] = { + [RDMA_WRID_NONE] = "NONE", + [RDMA_WRID_RDMA_WRITE] = "WRITE RDMA", + [RDMA_WRID_SEND_CONTROL] = "CONTROL SEND", + [RDMA_WRID_RECV_CONTROL] = "CONTROL RECV", +}; + +/* + * Work request IDs for IB SEND messages only (not RDMA writes). + * This is used by the migration protocol to transmit + * control messages (such as device state and registration commands) + * + * We could use more WRs, but we have enough for now. + */ +enum { + RDMA_WRID_READY = 0, + RDMA_WRID_DATA, + RDMA_WRID_CONTROL, + RDMA_WRID_MAX, +}; + +/* + * SEND/RECV IB Control Messages. + */ +enum { + RDMA_CONTROL_NONE = 0, + RDMA_CONTROL_ERROR, + RDMA_CONTROL_READY, /* ready to receive */ + RDMA_CONTROL_QEMU_FILE, /* QEMUFile-transmitted bytes */ + RDMA_CONTROL_RAM_BLOCKS_REQUEST, /* RAMBlock synchronization */ + RDMA_CONTROL_RAM_BLOCKS_RESULT, /* RAMBlock synchronization */ + RDMA_CONTROL_COMPRESS, /* page contains repeat values */ + RDMA_CONTROL_REGISTER_REQUEST, /* dynamic page registration */ + RDMA_CONTROL_REGISTER_RESULT, /* key to use after registration */ + RDMA_CONTROL_REGISTER_FINISHED, /* current iteration finished */ + RDMA_CONTROL_UNREGISTER_REQUEST, /* dynamic UN-registration */ + RDMA_CONTROL_UNREGISTER_FINISHED, /* unpinning finished */ +}; + +static const char *control_desc[] = { + [RDMA_CONTROL_NONE] = "NONE", + [RDMA_CONTROL_ERROR] = "ERROR", + [RDMA_CONTROL_READY] = "READY", + [RDMA_CONTROL_QEMU_FILE] = "QEMU FILE", + [RDMA_CONTROL_RAM_BLOCKS_REQUEST] = "RAM BLOCKS REQUEST", + [RDMA_CONTROL_RAM_BLOCKS_RESULT] = "RAM BLOCKS RESULT", + [RDMA_CONTROL_COMPRESS] = "COMPRESS", + [RDMA_CONTROL_REGISTER_REQUEST] = "REGISTER REQUEST", + [RDMA_CONTROL_REGISTER_RESULT] = "REGISTER RESULT", + [RDMA_CONTROL_REGISTER_FINISHED] = "REGISTER FINISHED", + [RDMA_CONTROL_UNREGISTER_REQUEST] = "UNREGISTER REQUEST", + [RDMA_CONTROL_UNREGISTER_FINISHED] = "UNREGISTER FINISHED", +}; + +/* + * Memory and MR structures used to represent an IB Send/Recv work request. + * This is *not* used for RDMA writes, only IB Send/Recv. + */ +typedef struct { + uint8_t control[RDMA_CONTROL_MAX_BUFFER]; /* actual buffer to register */ + struct ibv_mr *control_mr; /* registration metadata */ + size_t control_len; /* length of the message */ + uint8_t *control_curr; /* start of unconsumed bytes */ +} RDMAWorkRequestData; + +/* + * Negotiate RDMA capabilities during connection-setup time. + */ +typedef struct { + uint32_t version; + uint32_t flags; +} RDMACapabilities; + +static void caps_to_network(RDMACapabilities *cap) +{ + cap->version = htonl(cap->version); + cap->flags = htonl(cap->flags); +} + +static void network_to_caps(RDMACapabilities *cap) +{ + cap->version = ntohl(cap->version); + cap->flags = ntohl(cap->flags); +} + +/* + * Representation of a RAMBlock from an RDMA perspective. + * This is not transmitted, only local. + * This and subsequent structures cannot be linked lists + * because we're using a single IB message to transmit + * the information. It's small anyway, so a list is overkill. + */ +typedef struct RDMALocalBlock { + char *block_name; + uint8_t *local_host_addr; /* local virtual address */ + uint64_t remote_host_addr; /* remote virtual address */ + uint64_t offset; + uint64_t length; + struct ibv_mr **pmr; /* MRs for chunk-level registration */ + struct ibv_mr *mr; /* MR for non-chunk-level registration */ + uint32_t *remote_keys; /* rkeys for chunk-level registration */ + uint32_t remote_rkey; /* rkeys for non-chunk-level registration */ + int index; /* which block are we */ + unsigned int src_index; /* (Only used on dest) */ + bool is_ram_block; + int nb_chunks; + unsigned long *transit_bitmap; + unsigned long *unregister_bitmap; +} RDMALocalBlock; + +/* + * Also represents a RAMblock, but only on the dest. + * This gets transmitted by the dest during connection-time + * to the source VM and then is used to populate the + * corresponding RDMALocalBlock with + * the information needed to perform the actual RDMA. + */ +typedef struct QEMU_PACKED RDMADestBlock { + uint64_t remote_host_addr; + uint64_t offset; + uint64_t length; + uint32_t remote_rkey; + uint32_t padding; +} RDMADestBlock; + +static uint64_t htonll(uint64_t v) +{ + union { uint32_t lv[2]; uint64_t llv; } u; + u.lv[0] = htonl(v >> 32); + u.lv[1] = htonl(v & 0xFFFFFFFFULL); + return u.llv; +} + +static uint64_t ntohll(uint64_t v) { + union { uint32_t lv[2]; uint64_t llv; } u; + u.llv = v; + return ((uint64_t)ntohl(u.lv[0]) << 32) | (uint64_t) ntohl(u.lv[1]); +} + +static void dest_block_to_network(RDMADestBlock *db) +{ + db->remote_host_addr = htonll(db->remote_host_addr); + db->offset = htonll(db->offset); + db->length = htonll(db->length); + db->remote_rkey = htonl(db->remote_rkey); +} + +static void network_to_dest_block(RDMADestBlock *db) +{ + db->remote_host_addr = ntohll(db->remote_host_addr); + db->offset = ntohll(db->offset); + db->length = ntohll(db->length); + db->remote_rkey = ntohl(db->remote_rkey); +} + +/* + * Virtual address of the above structures used for transmitting + * the RAMBlock descriptions at connection-time. + * This structure is *not* transmitted. + */ +typedef struct RDMALocalBlocks { + int nb_blocks; + bool init; /* main memory init complete */ + RDMALocalBlock *block; +} RDMALocalBlocks; + +/* + * Main data structure for RDMA state. + * While there is only one copy of this structure being allocated right now, + * this is the place where one would start if you wanted to consider + * having more than one RDMA connection open at the same time. + */ +typedef struct RDMAContext { + char *host; + int port; + + RDMAWorkRequestData wr_data[RDMA_WRID_MAX]; + + /* + * This is used by *_exchange_send() to figure out whether or not + * the initial "READY" message has already been received or not. + * This is because other functions may potentially poll() and detect + * the READY message before send() does, in which case we need to + * know if it completed. + */ + int control_ready_expected; + + /* number of outstanding writes */ + int nb_sent; + + /* store info about current buffer so that we can + merge it with future sends */ + uint64_t current_addr; + uint64_t current_length; + /* index of ram block the current buffer belongs to */ + int current_index; + /* index of the chunk in the current ram block */ + int current_chunk; + + bool pin_all; + + /* + * infiniband-specific variables for opening the device + * and maintaining connection state and so forth. + * + * cm_id also has ibv_context, rdma_event_channel, and ibv_qp in + * cm_id->verbs, cm_id->channel, and cm_id->qp. + */ + struct rdma_cm_id *cm_id; /* connection manager ID */ + struct rdma_cm_id *listen_id; + bool connected; + + struct ibv_context *verbs; + struct rdma_event_channel *channel; + struct ibv_qp *qp; /* queue pair */ + struct ibv_comp_channel *comp_channel; /* completion channel */ + struct ibv_pd *pd; /* protection domain */ + struct ibv_cq *cq; /* completion queue */ + + /* + * If a previous write failed (perhaps because of a failed + * memory registration, then do not attempt any future work + * and remember the error state. + */ + int error_state; + int error_reported; + + /* + * Description of ram blocks used throughout the code. + */ + RDMALocalBlocks local_ram_blocks; + RDMADestBlock *dest_blocks; + + /* Index of the next RAMBlock received during block registration */ + unsigned int next_src_index; + + /* + * Migration on *destination* started. + * Then use coroutine yield function. + * Source runs in a thread, so we don't care. + */ + int migration_started_on_destination; + + int total_registrations; + int total_writes; + + int unregister_current, unregister_next; + uint64_t unregistrations[RDMA_SIGNALED_SEND_MAX]; + + GHashTable *blockmap; +} RDMAContext; + +/* + * Interface to the rest of the migration call stack. + */ +typedef struct QEMUFileRDMA { + RDMAContext *rdma; + size_t len; + void *file; +} QEMUFileRDMA; + +/* + * Main structure for IB Send/Recv control messages. + * This gets prepended at the beginning of every Send/Recv. + */ +typedef struct QEMU_PACKED { + uint32_t len; /* Total length of data portion */ + uint32_t type; /* which control command to perform */ + uint32_t repeat; /* number of commands in data portion of same type */ + uint32_t padding; +} RDMAControlHeader; + +static void control_to_network(RDMAControlHeader *control) +{ + control->type = htonl(control->type); + control->len = htonl(control->len); + control->repeat = htonl(control->repeat); +} + +static void network_to_control(RDMAControlHeader *control) +{ + control->type = ntohl(control->type); + control->len = ntohl(control->len); + control->repeat = ntohl(control->repeat); +} + +/* + * Register a single Chunk. + * Information sent by the source VM to inform the dest + * to register an single chunk of memory before we can perform + * the actual RDMA operation. + */ +typedef struct QEMU_PACKED { + union QEMU_PACKED { + uint64_t current_addr; /* offset into the ram_addr_t space */ + uint64_t chunk; /* chunk to lookup if unregistering */ + } key; + uint32_t current_index; /* which ramblock the chunk belongs to */ + uint32_t padding; + uint64_t chunks; /* how many sequential chunks to register */ +} RDMARegister; + +static void register_to_network(RDMAContext *rdma, RDMARegister *reg) +{ + RDMALocalBlock *local_block; + local_block = &rdma->local_ram_blocks.block[reg->current_index]; + + if (local_block->is_ram_block) { + /* + * current_addr as passed in is an address in the local ram_addr_t + * space, we need to translate this for the destination + */ + reg->key.current_addr -= local_block->offset; + reg->key.current_addr += rdma->dest_blocks[reg->current_index].offset; + } + reg->key.current_addr = htonll(reg->key.current_addr); + reg->current_index = htonl(reg->current_index); + reg->chunks = htonll(reg->chunks); +} + +static void network_to_register(RDMARegister *reg) +{ + reg->key.current_addr = ntohll(reg->key.current_addr); + reg->current_index = ntohl(reg->current_index); + reg->chunks = ntohll(reg->chunks); +} + +typedef struct QEMU_PACKED { + uint32_t value; /* if zero, we will madvise() */ + uint32_t block_idx; /* which ram block index */ + uint64_t offset; /* Address in remote ram_addr_t space */ + uint64_t length; /* length of the chunk */ +} RDMACompress; + +static void compress_to_network(RDMAContext *rdma, RDMACompress *comp) +{ + comp->value = htonl(comp->value); + /* + * comp->offset as passed in is an address in the local ram_addr_t + * space, we need to translate this for the destination + */ + comp->offset -= rdma->local_ram_blocks.block[comp->block_idx].offset; + comp->offset += rdma->dest_blocks[comp->block_idx].offset; + comp->block_idx = htonl(comp->block_idx); + comp->offset = htonll(comp->offset); + comp->length = htonll(comp->length); +} + +static void network_to_compress(RDMACompress *comp) +{ + comp->value = ntohl(comp->value); + comp->block_idx = ntohl(comp->block_idx); + comp->offset = ntohll(comp->offset); + comp->length = ntohll(comp->length); +} + +/* + * The result of the dest's memory registration produces an "rkey" + * which the source VM must reference in order to perform + * the RDMA operation. + */ +typedef struct QEMU_PACKED { + uint32_t rkey; + uint32_t padding; + uint64_t host_addr; +} RDMARegisterResult; + +static void result_to_network(RDMARegisterResult *result) +{ + result->rkey = htonl(result->rkey); + result->host_addr = htonll(result->host_addr); +}; + +static void network_to_result(RDMARegisterResult *result) +{ + result->rkey = ntohl(result->rkey); + result->host_addr = ntohll(result->host_addr); +}; + +const char *print_wrid(int wrid); +static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head, + uint8_t *data, RDMAControlHeader *resp, + int *resp_idx, + int (*callback)(RDMAContext *rdma)); + +static inline uint64_t ram_chunk_index(const uint8_t *start, + const uint8_t *host) +{ + return ((uintptr_t) host - (uintptr_t) start) >> RDMA_REG_CHUNK_SHIFT; +} + +static inline uint8_t *ram_chunk_start(const RDMALocalBlock *rdma_ram_block, + uint64_t i) +{ + return (uint8_t *)(uintptr_t)(rdma_ram_block->local_host_addr + + (i << RDMA_REG_CHUNK_SHIFT)); +} + +static inline uint8_t *ram_chunk_end(const RDMALocalBlock *rdma_ram_block, + uint64_t i) +{ + uint8_t *result = ram_chunk_start(rdma_ram_block, i) + + (1UL << RDMA_REG_CHUNK_SHIFT); + + if (result > (rdma_ram_block->local_host_addr + rdma_ram_block->length)) { + result = rdma_ram_block->local_host_addr + rdma_ram_block->length; + } + + return result; +} + +static int rdma_add_block(RDMAContext *rdma, const char *block_name, + void *host_addr, + ram_addr_t block_offset, uint64_t length) +{ + RDMALocalBlocks *local = &rdma->local_ram_blocks; + RDMALocalBlock *block; + RDMALocalBlock *old = local->block; + + local->block = g_new0(RDMALocalBlock, local->nb_blocks + 1); + + if (local->nb_blocks) { + int x; + + if (rdma->blockmap) { + for (x = 0; x < local->nb_blocks; x++) { + g_hash_table_remove(rdma->blockmap, + (void *)(uintptr_t)old[x].offset); + g_hash_table_insert(rdma->blockmap, + (void *)(uintptr_t)old[x].offset, + &local->block[x]); + } + } + memcpy(local->block, old, sizeof(RDMALocalBlock) * local->nb_blocks); + g_free(old); + } + + block = &local->block[local->nb_blocks]; + + block->block_name = g_strdup(block_name); + block->local_host_addr = host_addr; + block->offset = block_offset; + block->length = length; + block->index = local->nb_blocks; + block->src_index = ~0U; /* Filled in by the receipt of the block list */ + block->nb_chunks = ram_chunk_index(host_addr, host_addr + length) + 1UL; + block->transit_bitmap = bitmap_new(block->nb_chunks); + bitmap_clear(block->transit_bitmap, 0, block->nb_chunks); + block->unregister_bitmap = bitmap_new(block->nb_chunks); + bitmap_clear(block->unregister_bitmap, 0, block->nb_chunks); + block->remote_keys = g_new0(uint32_t, block->nb_chunks); + + block->is_ram_block = local->init ? false : true; + + if (rdma->blockmap) { + g_hash_table_insert(rdma->blockmap, (void *)(uintptr_t)block_offset, block); + } + + trace_rdma_add_block(block_name, local->nb_blocks, + (uintptr_t) block->local_host_addr, + block->offset, block->length, + (uintptr_t) (block->local_host_addr + block->length), + BITS_TO_LONGS(block->nb_chunks) * + sizeof(unsigned long) * 8, + block->nb_chunks); + + local->nb_blocks++; + + return 0; +} + +/* + * Memory regions need to be registered with the device and queue pairs setup + * in advanced before the migration starts. This tells us where the RAM blocks + * are so that we can register them individually. + */ +static int qemu_rdma_init_one_block(const char *block_name, void *host_addr, + ram_addr_t block_offset, ram_addr_t length, void *opaque) +{ + return rdma_add_block(opaque, block_name, host_addr, block_offset, length); +} + +/* + * Identify the RAMBlocks and their quantity. They will be references to + * identify chunk boundaries inside each RAMBlock and also be referenced + * during dynamic page registration. + */ +static int qemu_rdma_init_ram_blocks(RDMAContext *rdma) +{ + RDMALocalBlocks *local = &rdma->local_ram_blocks; + + assert(rdma->blockmap == NULL); + memset(local, 0, sizeof *local); + qemu_ram_foreach_block(qemu_rdma_init_one_block, rdma); + trace_qemu_rdma_init_ram_blocks(local->nb_blocks); + rdma->dest_blocks = g_new0(RDMADestBlock, + rdma->local_ram_blocks.nb_blocks); + local->init = true; + return 0; +} + +/* + * Note: If used outside of cleanup, the caller must ensure that the destination + * block structures are also updated + */ +static int rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) +{ + RDMALocalBlocks *local = &rdma->local_ram_blocks; + RDMALocalBlock *old = local->block; + int x; + + if (rdma->blockmap) { + g_hash_table_remove(rdma->blockmap, (void *)(uintptr_t)block->offset); + } + if (block->pmr) { + int j; + + for (j = 0; j < block->nb_chunks; j++) { + if (!block->pmr[j]) { + continue; + } + ibv_dereg_mr(block->pmr[j]); + rdma->total_registrations--; + } + g_free(block->pmr); + block->pmr = NULL; + } + + if (block->mr) { + ibv_dereg_mr(block->mr); + rdma->total_registrations--; + block->mr = NULL; + } + + g_free(block->transit_bitmap); + block->transit_bitmap = NULL; + + g_free(block->unregister_bitmap); + block->unregister_bitmap = NULL; + + g_free(block->remote_keys); + block->remote_keys = NULL; + + g_free(block->block_name); + block->block_name = NULL; + + if (rdma->blockmap) { + for (x = 0; x < local->nb_blocks; x++) { + g_hash_table_remove(rdma->blockmap, + (void *)(uintptr_t)old[x].offset); + } + } + + if (local->nb_blocks > 1) { + + local->block = g_new0(RDMALocalBlock, local->nb_blocks - 1); + + if (block->index) { + memcpy(local->block, old, sizeof(RDMALocalBlock) * block->index); + } + + if (block->index < (local->nb_blocks - 1)) { + memcpy(local->block + block->index, old + (block->index + 1), + sizeof(RDMALocalBlock) * + (local->nb_blocks - (block->index + 1))); + } + } else { + assert(block == local->block); + local->block = NULL; + } + + trace_rdma_delete_block(block, (uintptr_t)block->local_host_addr, + block->offset, block->length, + (uintptr_t)(block->local_host_addr + block->length), + BITS_TO_LONGS(block->nb_chunks) * + sizeof(unsigned long) * 8, block->nb_chunks); + + g_free(old); + + local->nb_blocks--; + + if (local->nb_blocks && rdma->blockmap) { + for (x = 0; x < local->nb_blocks; x++) { + g_hash_table_insert(rdma->blockmap, + (void *)(uintptr_t)local->block[x].offset, + &local->block[x]); + } + } + + return 0; +} + +/* + * Put in the log file which RDMA device was opened and the details + * associated with that device. + */ +static void qemu_rdma_dump_id(const char *who, struct ibv_context *verbs) +{ + struct ibv_port_attr port; + + if (ibv_query_port(verbs, 1, &port)) { + error_report("Failed to query port information"); + return; + } + + printf("%s RDMA Device opened: kernel name %s " + "uverbs device name %s, " + "infiniband_verbs class device path %s, " + "infiniband class device path %s, " + "transport: (%d) %s\n", + who, + verbs->device->name, + verbs->device->dev_name, + verbs->device->dev_path, + verbs->device->ibdev_path, + port.link_layer, + (port.link_layer == IBV_LINK_LAYER_INFINIBAND) ? "Infiniband" : + ((port.link_layer == IBV_LINK_LAYER_ETHERNET) + ? "Ethernet" : "Unknown")); +} + +/* + * Put in the log file the RDMA gid addressing information, + * useful for folks who have trouble understanding the + * RDMA device hierarchy in the kernel. + */ +static void qemu_rdma_dump_gid(const char *who, struct rdma_cm_id *id) +{ + char sgid[33]; + char dgid[33]; + inet_ntop(AF_INET6, &id->route.addr.addr.ibaddr.sgid, sgid, sizeof sgid); + inet_ntop(AF_INET6, &id->route.addr.addr.ibaddr.dgid, dgid, sizeof dgid); + trace_qemu_rdma_dump_gid(who, sgid, dgid); +} + +/* + * As of now, IPv6 over RoCE / iWARP is not supported by linux. + * We will try the next addrinfo struct, and fail if there are + * no other valid addresses to bind against. + * + * If user is listening on '[::]', then we will not have a opened a device + * yet and have no way of verifying if the device is RoCE or not. + * + * In this case, the source VM will throw an error for ALL types of + * connections (both IPv4 and IPv6) if the destination machine does not have + * a regular infiniband network available for use. + * + * The only way to guarantee that an error is thrown for broken kernels is + * for the management software to choose a *specific* interface at bind time + * and validate what time of hardware it is. + * + * Unfortunately, this puts the user in a fix: + * + * If the source VM connects with an IPv4 address without knowing that the + * destination has bound to '[::]' the migration will unconditionally fail + * unless the management software is explicitly listening on the IPv4 + * address while using a RoCE-based device. + * + * If the source VM connects with an IPv6 address, then we're OK because we can + * throw an error on the source (and similarly on the destination). + * + * But in mixed environments, this will be broken for a while until it is fixed + * inside linux. + * + * We do provide a *tiny* bit of help in this function: We can list all of the + * devices in the system and check to see if all the devices are RoCE or + * Infiniband. + * + * If we detect that we have a *pure* RoCE environment, then we can safely + * thrown an error even if the management software has specified '[::]' as the + * bind address. + * + * However, if there is are multiple hetergeneous devices, then we cannot make + * this assumption and the user just has to be sure they know what they are + * doing. + * + * Patches are being reviewed on linux-rdma. + */ +static int qemu_rdma_broken_ipv6_kernel(Error **errp, struct ibv_context *verbs) +{ + struct ibv_port_attr port_attr; + + /* This bug only exists in linux, to our knowledge. */ +#ifdef CONFIG_LINUX + + /* + * Verbs are only NULL if management has bound to '[::]'. + * + * Let's iterate through all the devices and see if there any pure IB + * devices (non-ethernet). + * + * If not, then we can safely proceed with the migration. + * Otherwise, there are no guarantees until the bug is fixed in linux. + */ + if (!verbs) { + int num_devices, x; + struct ibv_device ** dev_list = ibv_get_device_list(&num_devices); + bool roce_found = false; + bool ib_found = false; + + for (x = 0; x < num_devices; x++) { + verbs = ibv_open_device(dev_list[x]); + if (!verbs) { + if (errno == EPERM) { + continue; + } else { + return -EINVAL; + } + } + + if (ibv_query_port(verbs, 1, &port_attr)) { + ibv_close_device(verbs); + ERROR(errp, "Could not query initial IB port"); + return -EINVAL; + } + + if (port_attr.link_layer == IBV_LINK_LAYER_INFINIBAND) { + ib_found = true; + } else if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { + roce_found = true; + } + + ibv_close_device(verbs); + + } + + if (roce_found) { + if (ib_found) { + fprintf(stderr, "WARN: migrations may fail:" + " IPv6 over RoCE / iWARP in linux" + " is broken. But since you appear to have a" + " mixed RoCE / IB environment, be sure to only" + " migrate over the IB fabric until the kernel " + " fixes the bug.\n"); + } else { + ERROR(errp, "You only have RoCE / iWARP devices in your systems" + " and your management software has specified '[::]'" + ", but IPv6 over RoCE / iWARP is not supported in Linux."); + return -ENONET; + } + } + + return 0; + } + + /* + * If we have a verbs context, that means that some other than '[::]' was + * used by the management software for binding. In which case we can + * actually warn the user about a potentially broken kernel. + */ + + /* IB ports start with 1, not 0 */ + if (ibv_query_port(verbs, 1, &port_attr)) { + ERROR(errp, "Could not query initial IB port"); + return -EINVAL; + } + + if (port_attr.link_layer == IBV_LINK_LAYER_ETHERNET) { + ERROR(errp, "Linux kernel's RoCE / iWARP does not support IPv6 " + "(but patches on linux-rdma in progress)"); + return -ENONET; + } + +#endif + + return 0; +} + +/* + * Figure out which RDMA device corresponds to the requested IP hostname + * Also create the initial connection manager identifiers for opening + * the connection. + */ +static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) +{ + int ret; + struct rdma_addrinfo *res; + char port_str[16]; + struct rdma_cm_event *cm_event; + char ip[40] = "unknown"; + struct rdma_addrinfo *e; + + if (rdma->host == NULL || !strcmp(rdma->host, "")) { + ERROR(errp, "RDMA hostname has not been set"); + return -EINVAL; + } + + /* create CM channel */ + rdma->channel = rdma_create_event_channel(); + if (!rdma->channel) { + ERROR(errp, "could not create CM channel"); + return -EINVAL; + } + + /* create CM id */ + ret = rdma_create_id(rdma->channel, &rdma->cm_id, NULL, RDMA_PS_TCP); + if (ret) { + ERROR(errp, "could not create channel id"); + goto err_resolve_create_id; + } + + snprintf(port_str, 16, "%d", rdma->port); + port_str[15] = '\0'; + + ret = rdma_getaddrinfo(rdma->host, port_str, NULL, &res); + if (ret < 0) { + ERROR(errp, "could not rdma_getaddrinfo address %s", rdma->host); + goto err_resolve_get_addr; + } + + for (e = res; e != NULL; e = e->ai_next) { + inet_ntop(e->ai_family, + &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); + trace_qemu_rdma_resolve_host_trying(rdma->host, ip); + + ret = rdma_resolve_addr(rdma->cm_id, NULL, e->ai_dst_addr, + RDMA_RESOLVE_TIMEOUT_MS); + if (!ret) { + if (e->ai_family == AF_INET6) { + ret = qemu_rdma_broken_ipv6_kernel(errp, rdma->cm_id->verbs); + if (ret) { + continue; + } + } + goto route; + } + } + + ERROR(errp, "could not resolve address %s", rdma->host); + goto err_resolve_get_addr; + +route: + qemu_rdma_dump_gid("source_resolve_addr", rdma->cm_id); + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + ERROR(errp, "could not perform event_addr_resolved"); + goto err_resolve_get_addr; + } + + if (cm_event->event != RDMA_CM_EVENT_ADDR_RESOLVED) { + ERROR(errp, "result not equal to event_addr_resolved %s", + rdma_event_str(cm_event->event)); + perror("rdma_resolve_addr"); + rdma_ack_cm_event(cm_event); + ret = -EINVAL; + goto err_resolve_get_addr; + } + rdma_ack_cm_event(cm_event); + + /* resolve route */ + ret = rdma_resolve_route(rdma->cm_id, RDMA_RESOLVE_TIMEOUT_MS); + if (ret) { + ERROR(errp, "could not resolve rdma route"); + goto err_resolve_get_addr; + } + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + ERROR(errp, "could not perform event_route_resolved"); + goto err_resolve_get_addr; + } + if (cm_event->event != RDMA_CM_EVENT_ROUTE_RESOLVED) { + ERROR(errp, "result not equal to event_route_resolved: %s", + rdma_event_str(cm_event->event)); + rdma_ack_cm_event(cm_event); + ret = -EINVAL; + goto err_resolve_get_addr; + } + rdma_ack_cm_event(cm_event); + rdma->verbs = rdma->cm_id->verbs; + qemu_rdma_dump_id("source_resolve_host", rdma->cm_id->verbs); + qemu_rdma_dump_gid("source_resolve_host", rdma->cm_id); + return 0; + +err_resolve_get_addr: + rdma_destroy_id(rdma->cm_id); + rdma->cm_id = NULL; +err_resolve_create_id: + rdma_destroy_event_channel(rdma->channel); + rdma->channel = NULL; + return ret; +} + +/* + * Create protection domain and completion queues + */ +static int qemu_rdma_alloc_pd_cq(RDMAContext *rdma) +{ + /* allocate pd */ + rdma->pd = ibv_alloc_pd(rdma->verbs); + if (!rdma->pd) { + error_report("failed to allocate protection domain"); + return -1; + } + + /* create completion channel */ + rdma->comp_channel = ibv_create_comp_channel(rdma->verbs); + if (!rdma->comp_channel) { + error_report("failed to allocate completion channel"); + goto err_alloc_pd_cq; + } + + /* + * Completion queue can be filled by both read and write work requests, + * so must reflect the sum of both possible queue sizes. + */ + rdma->cq = ibv_create_cq(rdma->verbs, (RDMA_SIGNALED_SEND_MAX * 3), + NULL, rdma->comp_channel, 0); + if (!rdma->cq) { + error_report("failed to allocate completion queue"); + goto err_alloc_pd_cq; + } + + return 0; + +err_alloc_pd_cq: + if (rdma->pd) { + ibv_dealloc_pd(rdma->pd); + } + if (rdma->comp_channel) { + ibv_destroy_comp_channel(rdma->comp_channel); + } + rdma->pd = NULL; + rdma->comp_channel = NULL; + return -1; + +} + +/* + * Create queue pairs. + */ +static int qemu_rdma_alloc_qp(RDMAContext *rdma) +{ + struct ibv_qp_init_attr attr = { 0 }; + int ret; + + attr.cap.max_send_wr = RDMA_SIGNALED_SEND_MAX; + attr.cap.max_recv_wr = 3; + attr.cap.max_send_sge = 1; + attr.cap.max_recv_sge = 1; + attr.send_cq = rdma->cq; + attr.recv_cq = rdma->cq; + attr.qp_type = IBV_QPT_RC; + + ret = rdma_create_qp(rdma->cm_id, rdma->pd, &attr); + if (ret) { + return -1; + } + + rdma->qp = rdma->cm_id->qp; + return 0; +} + +static int qemu_rdma_reg_whole_ram_blocks(RDMAContext *rdma) +{ + int i; + RDMALocalBlocks *local = &rdma->local_ram_blocks; + + for (i = 0; i < local->nb_blocks; i++) { + local->block[i].mr = + ibv_reg_mr(rdma->pd, + local->block[i].local_host_addr, + local->block[i].length, + IBV_ACCESS_LOCAL_WRITE | + IBV_ACCESS_REMOTE_WRITE + ); + if (!local->block[i].mr) { + perror("Failed to register local dest ram block!\n"); + break; + } + rdma->total_registrations++; + } + + if (i >= local->nb_blocks) { + return 0; + } + + for (i--; i >= 0; i--) { + ibv_dereg_mr(local->block[i].mr); + rdma->total_registrations--; + } + + return -1; + +} + +/* + * Find the ram block that corresponds to the page requested to be + * transmitted by QEMU. + * + * Once the block is found, also identify which 'chunk' within that + * block that the page belongs to. + * + * This search cannot fail or the migration will fail. + */ +static int qemu_rdma_search_ram_block(RDMAContext *rdma, + uintptr_t block_offset, + uint64_t offset, + uint64_t length, + uint64_t *block_index, + uint64_t *chunk_index) +{ + uint64_t current_addr = block_offset + offset; + RDMALocalBlock *block = g_hash_table_lookup(rdma->blockmap, + (void *) block_offset); + assert(block); + assert(current_addr >= block->offset); + assert((current_addr + length) <= (block->offset + block->length)); + + *block_index = block->index; + *chunk_index = ram_chunk_index(block->local_host_addr, + block->local_host_addr + (current_addr - block->offset)); + + return 0; +} + +/* + * Register a chunk with IB. If the chunk was already registered + * previously, then skip. + * + * Also return the keys associated with the registration needed + * to perform the actual RDMA operation. + */ +static int qemu_rdma_register_and_get_keys(RDMAContext *rdma, + RDMALocalBlock *block, uintptr_t host_addr, + uint32_t *lkey, uint32_t *rkey, int chunk, + uint8_t *chunk_start, uint8_t *chunk_end) +{ + if (block->mr) { + if (lkey) { + *lkey = block->mr->lkey; + } + if (rkey) { + *rkey = block->mr->rkey; + } + return 0; + } + + /* allocate memory to store chunk MRs */ + if (!block->pmr) { + block->pmr = g_new0(struct ibv_mr *, block->nb_chunks); + } + + /* + * If 'rkey', then we're the destination, so grant access to the source. + * + * If 'lkey', then we're the source VM, so grant access only to ourselves. + */ + if (!block->pmr[chunk]) { + uint64_t len = chunk_end - chunk_start; + + trace_qemu_rdma_register_and_get_keys(len, chunk_start); + + block->pmr[chunk] = ibv_reg_mr(rdma->pd, + chunk_start, len, + (rkey ? (IBV_ACCESS_LOCAL_WRITE | + IBV_ACCESS_REMOTE_WRITE) : 0)); + + if (!block->pmr[chunk]) { + perror("Failed to register chunk!"); + fprintf(stderr, "Chunk details: block: %d chunk index %d" + " start %" PRIuPTR " end %" PRIuPTR + " host %" PRIuPTR + " local %" PRIuPTR " registrations: %d\n", + block->index, chunk, (uintptr_t)chunk_start, + (uintptr_t)chunk_end, host_addr, + (uintptr_t)block->local_host_addr, + rdma->total_registrations); + return -1; + } + rdma->total_registrations++; + } + + if (lkey) { + *lkey = block->pmr[chunk]->lkey; + } + if (rkey) { + *rkey = block->pmr[chunk]->rkey; + } + return 0; +} + +/* + * Register (at connection time) the memory used for control + * channel messages. + */ +static int qemu_rdma_reg_control(RDMAContext *rdma, int idx) +{ + rdma->wr_data[idx].control_mr = ibv_reg_mr(rdma->pd, + rdma->wr_data[idx].control, RDMA_CONTROL_MAX_BUFFER, + IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE); + if (rdma->wr_data[idx].control_mr) { + rdma->total_registrations++; + return 0; + } + error_report("qemu_rdma_reg_control failed"); + return -1; +} + +const char *print_wrid(int wrid) +{ + if (wrid >= RDMA_WRID_RECV_CONTROL) { + return wrid_desc[RDMA_WRID_RECV_CONTROL]; + } + return wrid_desc[wrid]; +} + +/* + * RDMA requires memory registration (mlock/pinning), but this is not good for + * overcommitment. + * + * In preparation for the future where LRU information or workload-specific + * writable writable working set memory access behavior is available to QEMU + * it would be nice to have in place the ability to UN-register/UN-pin + * particular memory regions from the RDMA hardware when it is determine that + * those regions of memory will likely not be accessed again in the near future. + * + * While we do not yet have such information right now, the following + * compile-time option allows us to perform a non-optimized version of this + * behavior. + * + * By uncommenting this option, you will cause *all* RDMA transfers to be + * unregistered immediately after the transfer completes on both sides of the + * connection. This has no effect in 'rdma-pin-all' mode, only regular mode. + * + * This will have a terrible impact on migration performance, so until future + * workload information or LRU information is available, do not attempt to use + * this feature except for basic testing. + */ +//#define RDMA_UNREGISTRATION_EXAMPLE + +/* + * Perform a non-optimized memory unregistration after every transfer + * for demonstration purposes, only if pin-all is not requested. + * + * Potential optimizations: + * 1. Start a new thread to run this function continuously + - for bit clearing + - and for receipt of unregister messages + * 2. Use an LRU. + * 3. Use workload hints. + */ +static int qemu_rdma_unregister_waiting(RDMAContext *rdma) +{ + while (rdma->unregistrations[rdma->unregister_current]) { + int ret; + uint64_t wr_id = rdma->unregistrations[rdma->unregister_current]; + uint64_t chunk = + (wr_id & RDMA_WRID_CHUNK_MASK) >> RDMA_WRID_CHUNK_SHIFT; + uint64_t index = + (wr_id & RDMA_WRID_BLOCK_MASK) >> RDMA_WRID_BLOCK_SHIFT; + RDMALocalBlock *block = + &(rdma->local_ram_blocks.block[index]); + RDMARegister reg = { .current_index = index }; + RDMAControlHeader resp = { .type = RDMA_CONTROL_UNREGISTER_FINISHED, + }; + RDMAControlHeader head = { .len = sizeof(RDMARegister), + .type = RDMA_CONTROL_UNREGISTER_REQUEST, + .repeat = 1, + }; + + trace_qemu_rdma_unregister_waiting_proc(chunk, + rdma->unregister_current); + + rdma->unregistrations[rdma->unregister_current] = 0; + rdma->unregister_current++; + + if (rdma->unregister_current == RDMA_SIGNALED_SEND_MAX) { + rdma->unregister_current = 0; + } + + + /* + * Unregistration is speculative (because migration is single-threaded + * and we cannot break the protocol's inifinband message ordering). + * Thus, if the memory is currently being used for transmission, + * then abort the attempt to unregister and try again + * later the next time a completion is received for this memory. + */ + clear_bit(chunk, block->unregister_bitmap); + + if (test_bit(chunk, block->transit_bitmap)) { + trace_qemu_rdma_unregister_waiting_inflight(chunk); + continue; + } + + trace_qemu_rdma_unregister_waiting_send(chunk); + + ret = ibv_dereg_mr(block->pmr[chunk]); + block->pmr[chunk] = NULL; + block->remote_keys[chunk] = 0; + + if (ret != 0) { + perror("unregistration chunk failed"); + return -ret; + } + rdma->total_registrations--; + + reg.key.chunk = chunk; + register_to_network(rdma, ®); + ret = qemu_rdma_exchange_send(rdma, &head, (uint8_t *) ®, + &resp, NULL, NULL); + if (ret < 0) { + return ret; + } + + trace_qemu_rdma_unregister_waiting_complete(chunk); + } + + return 0; +} + +static uint64_t qemu_rdma_make_wrid(uint64_t wr_id, uint64_t index, + uint64_t chunk) +{ + uint64_t result = wr_id & RDMA_WRID_TYPE_MASK; + + result |= (index << RDMA_WRID_BLOCK_SHIFT); + result |= (chunk << RDMA_WRID_CHUNK_SHIFT); + + return result; +} + +/* + * Set bit for unregistration in the next iteration. + * We cannot transmit right here, but will unpin later. + */ +static void qemu_rdma_signal_unregister(RDMAContext *rdma, uint64_t index, + uint64_t chunk, uint64_t wr_id) +{ + if (rdma->unregistrations[rdma->unregister_next] != 0) { + error_report("rdma migration: queue is full"); + } else { + RDMALocalBlock *block = &(rdma->local_ram_blocks.block[index]); + + if (!test_and_set_bit(chunk, block->unregister_bitmap)) { + trace_qemu_rdma_signal_unregister_append(chunk, + rdma->unregister_next); + + rdma->unregistrations[rdma->unregister_next++] = + qemu_rdma_make_wrid(wr_id, index, chunk); + + if (rdma->unregister_next == RDMA_SIGNALED_SEND_MAX) { + rdma->unregister_next = 0; + } + } else { + trace_qemu_rdma_signal_unregister_already(chunk); + } + } +} + +/* + * Consult the connection manager to see a work request + * (of any kind) has completed. + * Return the work request ID that completed. + */ +static uint64_t qemu_rdma_poll(RDMAContext *rdma, uint64_t *wr_id_out, + uint32_t *byte_len) +{ + int ret; + struct ibv_wc wc; + uint64_t wr_id; + + ret = ibv_poll_cq(rdma->cq, 1, &wc); + + if (!ret) { + *wr_id_out = RDMA_WRID_NONE; + return 0; + } + + if (ret < 0) { + error_report("ibv_poll_cq return %d", ret); + return ret; + } + + wr_id = wc.wr_id & RDMA_WRID_TYPE_MASK; + + if (wc.status != IBV_WC_SUCCESS) { + fprintf(stderr, "ibv_poll_cq wc.status=%d %s!\n", + wc.status, ibv_wc_status_str(wc.status)); + fprintf(stderr, "ibv_poll_cq wrid=%s!\n", wrid_desc[wr_id]); + + return -1; + } + + if (rdma->control_ready_expected && + (wr_id >= RDMA_WRID_RECV_CONTROL)) { + trace_qemu_rdma_poll_recv(wrid_desc[RDMA_WRID_RECV_CONTROL], + wr_id - RDMA_WRID_RECV_CONTROL, wr_id, rdma->nb_sent); + rdma->control_ready_expected = 0; + } + + if (wr_id == RDMA_WRID_RDMA_WRITE) { + uint64_t chunk = + (wc.wr_id & RDMA_WRID_CHUNK_MASK) >> RDMA_WRID_CHUNK_SHIFT; + uint64_t index = + (wc.wr_id & RDMA_WRID_BLOCK_MASK) >> RDMA_WRID_BLOCK_SHIFT; + RDMALocalBlock *block = &(rdma->local_ram_blocks.block[index]); + + trace_qemu_rdma_poll_write(print_wrid(wr_id), wr_id, rdma->nb_sent, + index, chunk, block->local_host_addr, + (void *)(uintptr_t)block->remote_host_addr); + + clear_bit(chunk, block->transit_bitmap); + + if (rdma->nb_sent > 0) { + rdma->nb_sent--; + } + + if (!rdma->pin_all) { + /* + * FYI: If one wanted to signal a specific chunk to be unregistered + * using LRU or workload-specific information, this is the function + * you would call to do so. That chunk would then get asynchronously + * unregistered later. + */ +#ifdef RDMA_UNREGISTRATION_EXAMPLE + qemu_rdma_signal_unregister(rdma, index, chunk, wc.wr_id); +#endif + } + } else { + trace_qemu_rdma_poll_other(print_wrid(wr_id), wr_id, rdma->nb_sent); + } + + *wr_id_out = wc.wr_id; + if (byte_len) { + *byte_len = wc.byte_len; + } + + return 0; +} + +/* + * Block until the next work request has completed. + * + * First poll to see if a work request has already completed, + * otherwise block. + * + * If we encounter completed work requests for IDs other than + * the one we're interested in, then that's generally an error. + * + * The only exception is actual RDMA Write completions. These + * completions only need to be recorded, but do not actually + * need further processing. + */ +static int qemu_rdma_block_for_wrid(RDMAContext *rdma, int wrid_requested, + uint32_t *byte_len) +{ + int num_cq_events = 0, ret = 0; + struct ibv_cq *cq; + void *cq_ctx; + uint64_t wr_id = RDMA_WRID_NONE, wr_id_in; + + if (ibv_req_notify_cq(rdma->cq, 0)) { + return -1; + } + /* poll cq first */ + while (wr_id != wrid_requested) { + ret = qemu_rdma_poll(rdma, &wr_id_in, byte_len); + if (ret < 0) { + return ret; + } + + wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; + + if (wr_id == RDMA_WRID_NONE) { + break; + } + if (wr_id != wrid_requested) { + trace_qemu_rdma_block_for_wrid_miss(print_wrid(wrid_requested), + wrid_requested, print_wrid(wr_id), wr_id); + } + } + + if (wr_id == wrid_requested) { + return 0; + } + + while (1) { + /* + * Coroutine doesn't start until process_incoming_migration() + * so don't yield unless we know we're running inside of a coroutine. + */ + if (rdma->migration_started_on_destination) { + yield_until_fd_readable(rdma->comp_channel->fd); + } + + if (ibv_get_cq_event(rdma->comp_channel, &cq, &cq_ctx)) { + perror("ibv_get_cq_event"); + goto err_block_for_wrid; + } + + num_cq_events++; + + if (ibv_req_notify_cq(cq, 0)) { + goto err_block_for_wrid; + } + + while (wr_id != wrid_requested) { + ret = qemu_rdma_poll(rdma, &wr_id_in, byte_len); + if (ret < 0) { + goto err_block_for_wrid; + } + + wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; + + if (wr_id == RDMA_WRID_NONE) { + break; + } + if (wr_id != wrid_requested) { + trace_qemu_rdma_block_for_wrid_miss(print_wrid(wrid_requested), + wrid_requested, print_wrid(wr_id), wr_id); + } + } + + if (wr_id == wrid_requested) { + goto success_block_for_wrid; + } + } + +success_block_for_wrid: + if (num_cq_events) { + ibv_ack_cq_events(cq, num_cq_events); + } + return 0; + +err_block_for_wrid: + if (num_cq_events) { + ibv_ack_cq_events(cq, num_cq_events); + } + return ret; +} + +/* + * Post a SEND message work request for the control channel + * containing some data and block until the post completes. + */ +static int qemu_rdma_post_send_control(RDMAContext *rdma, uint8_t *buf, + RDMAControlHeader *head) +{ + int ret = 0; + RDMAWorkRequestData *wr = &rdma->wr_data[RDMA_WRID_CONTROL]; + struct ibv_send_wr *bad_wr; + struct ibv_sge sge = { + .addr = (uintptr_t)(wr->control), + .length = head->len + sizeof(RDMAControlHeader), + .lkey = wr->control_mr->lkey, + }; + struct ibv_send_wr send_wr = { + .wr_id = RDMA_WRID_SEND_CONTROL, + .opcode = IBV_WR_SEND, + .send_flags = IBV_SEND_SIGNALED, + .sg_list = &sge, + .num_sge = 1, + }; + + trace_qemu_rdma_post_send_control(control_desc[head->type]); + + /* + * We don't actually need to do a memcpy() in here if we used + * the "sge" properly, but since we're only sending control messages + * (not RAM in a performance-critical path), then its OK for now. + * + * The copy makes the RDMAControlHeader simpler to manipulate + * for the time being. + */ + assert(head->len <= RDMA_CONTROL_MAX_BUFFER - sizeof(*head)); + memcpy(wr->control, head, sizeof(RDMAControlHeader)); + control_to_network((void *) wr->control); + + if (buf) { + memcpy(wr->control + sizeof(RDMAControlHeader), buf, head->len); + } + + + ret = ibv_post_send(rdma->qp, &send_wr, &bad_wr); + + if (ret > 0) { + error_report("Failed to use post IB SEND for control"); + return -ret; + } + + ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_SEND_CONTROL, NULL); + if (ret < 0) { + error_report("rdma migration: send polling control error"); + } + + return ret; +} + +/* + * Post a RECV work request in anticipation of some future receipt + * of data on the control channel. + */ +static int qemu_rdma_post_recv_control(RDMAContext *rdma, int idx) +{ + struct ibv_recv_wr *bad_wr; + struct ibv_sge sge = { + .addr = (uintptr_t)(rdma->wr_data[idx].control), + .length = RDMA_CONTROL_MAX_BUFFER, + .lkey = rdma->wr_data[idx].control_mr->lkey, + }; + + struct ibv_recv_wr recv_wr = { + .wr_id = RDMA_WRID_RECV_CONTROL + idx, + .sg_list = &sge, + .num_sge = 1, + }; + + + if (ibv_post_recv(rdma->qp, &recv_wr, &bad_wr)) { + return -1; + } + + return 0; +} + +/* + * Block and wait for a RECV control channel message to arrive. + */ +static int qemu_rdma_exchange_get_response(RDMAContext *rdma, + RDMAControlHeader *head, int expecting, int idx) +{ + uint32_t byte_len; + int ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RECV_CONTROL + idx, + &byte_len); + + if (ret < 0) { + error_report("rdma migration: recv polling control error!"); + return ret; + } + + network_to_control((void *) rdma->wr_data[idx].control); + memcpy(head, rdma->wr_data[idx].control, sizeof(RDMAControlHeader)); + + trace_qemu_rdma_exchange_get_response_start(control_desc[expecting]); + + if (expecting == RDMA_CONTROL_NONE) { + trace_qemu_rdma_exchange_get_response_none(control_desc[head->type], + head->type); + } else if (head->type != expecting || head->type == RDMA_CONTROL_ERROR) { + error_report("Was expecting a %s (%d) control message" + ", but got: %s (%d), length: %d", + control_desc[expecting], expecting, + control_desc[head->type], head->type, head->len); + return -EIO; + } + if (head->len > RDMA_CONTROL_MAX_BUFFER - sizeof(*head)) { + error_report("too long length: %d", head->len); + return -EINVAL; + } + if (sizeof(*head) + head->len != byte_len) { + error_report("Malformed length: %d byte_len %d", head->len, byte_len); + return -EINVAL; + } + + return 0; +} + +/* + * When a RECV work request has completed, the work request's + * buffer is pointed at the header. + * + * This will advance the pointer to the data portion + * of the control message of the work request's buffer that + * was populated after the work request finished. + */ +static void qemu_rdma_move_header(RDMAContext *rdma, int idx, + RDMAControlHeader *head) +{ + rdma->wr_data[idx].control_len = head->len; + rdma->wr_data[idx].control_curr = + rdma->wr_data[idx].control + sizeof(RDMAControlHeader); +} + +/* + * This is an 'atomic' high-level operation to deliver a single, unified + * control-channel message. + * + * Additionally, if the user is expecting some kind of reply to this message, + * they can request a 'resp' response message be filled in by posting an + * additional work request on behalf of the user and waiting for an additional + * completion. + * + * The extra (optional) response is used during registration to us from having + * to perform an *additional* exchange of message just to provide a response by + * instead piggy-backing on the acknowledgement. + */ +static int qemu_rdma_exchange_send(RDMAContext *rdma, RDMAControlHeader *head, + uint8_t *data, RDMAControlHeader *resp, + int *resp_idx, + int (*callback)(RDMAContext *rdma)) +{ + int ret = 0; + + /* + * Wait until the dest is ready before attempting to deliver the message + * by waiting for a READY message. + */ + if (rdma->control_ready_expected) { + RDMAControlHeader resp; + ret = qemu_rdma_exchange_get_response(rdma, + &resp, RDMA_CONTROL_READY, RDMA_WRID_READY); + if (ret < 0) { + return ret; + } + } + + /* + * If the user is expecting a response, post a WR in anticipation of it. + */ + if (resp) { + ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_DATA); + if (ret) { + error_report("rdma migration: error posting" + " extra control recv for anticipated result!"); + return ret; + } + } + + /* + * Post a WR to replace the one we just consumed for the READY message. + */ + ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY); + if (ret) { + error_report("rdma migration: error posting first control recv!"); + return ret; + } + + /* + * Deliver the control message that was requested. + */ + ret = qemu_rdma_post_send_control(rdma, data, head); + + if (ret < 0) { + error_report("Failed to send control buffer!"); + return ret; + } + + /* + * If we're expecting a response, block and wait for it. + */ + if (resp) { + if (callback) { + trace_qemu_rdma_exchange_send_issue_callback(); + ret = callback(rdma); + if (ret < 0) { + return ret; + } + } + + trace_qemu_rdma_exchange_send_waiting(control_desc[resp->type]); + ret = qemu_rdma_exchange_get_response(rdma, resp, + resp->type, RDMA_WRID_DATA); + + if (ret < 0) { + return ret; + } + + qemu_rdma_move_header(rdma, RDMA_WRID_DATA, resp); + if (resp_idx) { + *resp_idx = RDMA_WRID_DATA; + } + trace_qemu_rdma_exchange_send_received(control_desc[resp->type]); + } + + rdma->control_ready_expected = 1; + + return 0; +} + +/* + * This is an 'atomic' high-level operation to receive a single, unified + * control-channel message. + */ +static int qemu_rdma_exchange_recv(RDMAContext *rdma, RDMAControlHeader *head, + int expecting) +{ + RDMAControlHeader ready = { + .len = 0, + .type = RDMA_CONTROL_READY, + .repeat = 1, + }; + int ret; + + /* + * Inform the source that we're ready to receive a message. + */ + ret = qemu_rdma_post_send_control(rdma, NULL, &ready); + + if (ret < 0) { + error_report("Failed to send control buffer!"); + return ret; + } + + /* + * Block and wait for the message. + */ + ret = qemu_rdma_exchange_get_response(rdma, head, + expecting, RDMA_WRID_READY); + + if (ret < 0) { + return ret; + } + + qemu_rdma_move_header(rdma, RDMA_WRID_READY, head); + + /* + * Post a new RECV work request to replace the one we just consumed. + */ + ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY); + if (ret) { + error_report("rdma migration: error posting second control recv!"); + return ret; + } + + return 0; +} + +/* + * Write an actual chunk of memory using RDMA. + * + * If we're using dynamic registration on the dest-side, we have to + * send a registration command first. + */ +static int qemu_rdma_write_one(QEMUFile *f, RDMAContext *rdma, + int current_index, uint64_t current_addr, + uint64_t length) +{ + struct ibv_sge sge; + struct ibv_send_wr send_wr = { 0 }; + struct ibv_send_wr *bad_wr; + int reg_result_idx, ret, count = 0; + uint64_t chunk, chunks; + uint8_t *chunk_start, *chunk_end; + RDMALocalBlock *block = &(rdma->local_ram_blocks.block[current_index]); + RDMARegister reg; + RDMARegisterResult *reg_result; + RDMAControlHeader resp = { .type = RDMA_CONTROL_REGISTER_RESULT }; + RDMAControlHeader head = { .len = sizeof(RDMARegister), + .type = RDMA_CONTROL_REGISTER_REQUEST, + .repeat = 1, + }; + +retry: + sge.addr = (uintptr_t)(block->local_host_addr + + (current_addr - block->offset)); + sge.length = length; + + chunk = ram_chunk_index(block->local_host_addr, + (uint8_t *)(uintptr_t)sge.addr); + chunk_start = ram_chunk_start(block, chunk); + + if (block->is_ram_block) { + chunks = length / (1UL << RDMA_REG_CHUNK_SHIFT); + + if (chunks && ((length % (1UL << RDMA_REG_CHUNK_SHIFT)) == 0)) { + chunks--; + } + } else { + chunks = block->length / (1UL << RDMA_REG_CHUNK_SHIFT); + + if (chunks && ((block->length % (1UL << RDMA_REG_CHUNK_SHIFT)) == 0)) { + chunks--; + } + } + + trace_qemu_rdma_write_one_top(chunks + 1, + (chunks + 1) * + (1UL << RDMA_REG_CHUNK_SHIFT) / 1024 / 1024); + + chunk_end = ram_chunk_end(block, chunk + chunks); + + if (!rdma->pin_all) { +#ifdef RDMA_UNREGISTRATION_EXAMPLE + qemu_rdma_unregister_waiting(rdma); +#endif + } + + while (test_bit(chunk, block->transit_bitmap)) { + (void)count; + trace_qemu_rdma_write_one_block(count++, current_index, chunk, + sge.addr, length, rdma->nb_sent, block->nb_chunks); + + ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); + + if (ret < 0) { + error_report("Failed to Wait for previous write to complete " + "block %d chunk %" PRIu64 + " current %" PRIu64 " len %" PRIu64 " %d", + current_index, chunk, sge.addr, length, rdma->nb_sent); + return ret; + } + } + + if (!rdma->pin_all || !block->is_ram_block) { + if (!block->remote_keys[chunk]) { + /* + * This chunk has not yet been registered, so first check to see + * if the entire chunk is zero. If so, tell the other size to + * memset() + madvise() the entire chunk without RDMA. + */ + + if (can_use_buffer_find_nonzero_offset((void *)(uintptr_t)sge.addr, + length) + && buffer_find_nonzero_offset((void *)(uintptr_t)sge.addr, + length) == length) { + RDMACompress comp = { + .offset = current_addr, + .value = 0, + .block_idx = current_index, + .length = length, + }; + + head.len = sizeof(comp); + head.type = RDMA_CONTROL_COMPRESS; + + trace_qemu_rdma_write_one_zero(chunk, sge.length, + current_index, current_addr); + + compress_to_network(rdma, &comp); + ret = qemu_rdma_exchange_send(rdma, &head, + (uint8_t *) &comp, NULL, NULL, NULL); + + if (ret < 0) { + return -EIO; + } + + acct_update_position(f, sge.length, true); + + return 1; + } + + /* + * Otherwise, tell other side to register. + */ + reg.current_index = current_index; + if (block->is_ram_block) { + reg.key.current_addr = current_addr; + } else { + reg.key.chunk = chunk; + } + reg.chunks = chunks; + + trace_qemu_rdma_write_one_sendreg(chunk, sge.length, current_index, + current_addr); + + register_to_network(rdma, ®); + ret = qemu_rdma_exchange_send(rdma, &head, (uint8_t *) ®, + &resp, ®_result_idx, NULL); + if (ret < 0) { + return ret; + } + + /* try to overlap this single registration with the one we sent. */ + if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, + &sge.lkey, NULL, chunk, + chunk_start, chunk_end)) { + error_report("cannot get lkey"); + return -EINVAL; + } + + reg_result = (RDMARegisterResult *) + rdma->wr_data[reg_result_idx].control_curr; + + network_to_result(reg_result); + + trace_qemu_rdma_write_one_recvregres(block->remote_keys[chunk], + reg_result->rkey, chunk); + + block->remote_keys[chunk] = reg_result->rkey; + block->remote_host_addr = reg_result->host_addr; + } else { + /* already registered before */ + if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, + &sge.lkey, NULL, chunk, + chunk_start, chunk_end)) { + error_report("cannot get lkey!"); + return -EINVAL; + } + } + + send_wr.wr.rdma.rkey = block->remote_keys[chunk]; + } else { + send_wr.wr.rdma.rkey = block->remote_rkey; + + if (qemu_rdma_register_and_get_keys(rdma, block, sge.addr, + &sge.lkey, NULL, chunk, + chunk_start, chunk_end)) { + error_report("cannot get lkey!"); + return -EINVAL; + } + } + + /* + * Encode the ram block index and chunk within this wrid. + * We will use this information at the time of completion + * to figure out which bitmap to check against and then which + * chunk in the bitmap to look for. + */ + send_wr.wr_id = qemu_rdma_make_wrid(RDMA_WRID_RDMA_WRITE, + current_index, chunk); + + send_wr.opcode = IBV_WR_RDMA_WRITE; + send_wr.send_flags = IBV_SEND_SIGNALED; + send_wr.sg_list = &sge; + send_wr.num_sge = 1; + send_wr.wr.rdma.remote_addr = block->remote_host_addr + + (current_addr - block->offset); + + trace_qemu_rdma_write_one_post(chunk, sge.addr, send_wr.wr.rdma.remote_addr, + sge.length); + + /* + * ibv_post_send() does not return negative error numbers, + * per the specification they are positive - no idea why. + */ + ret = ibv_post_send(rdma->qp, &send_wr, &bad_wr); + + if (ret == ENOMEM) { + trace_qemu_rdma_write_one_queue_full(); + ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); + if (ret < 0) { + error_report("rdma migration: failed to make " + "room in full send queue! %d", ret); + return ret; + } + + goto retry; + + } else if (ret > 0) { + perror("rdma migration: post rdma write failed"); + return -ret; + } + + set_bit(chunk, block->transit_bitmap); + acct_update_position(f, sge.length, false); + rdma->total_writes++; + + return 0; +} + +/* + * Push out any unwritten RDMA operations. + * + * We support sending out multiple chunks at the same time. + * Not all of them need to get signaled in the completion queue. + */ +static int qemu_rdma_write_flush(QEMUFile *f, RDMAContext *rdma) +{ + int ret; + + if (!rdma->current_length) { + return 0; + } + + ret = qemu_rdma_write_one(f, rdma, + rdma->current_index, rdma->current_addr, rdma->current_length); + + if (ret < 0) { + return ret; + } + + if (ret == 0) { + rdma->nb_sent++; + trace_qemu_rdma_write_flush(rdma->nb_sent); + } + + rdma->current_length = 0; + rdma->current_addr = 0; + + return 0; +} + +static inline int qemu_rdma_buffer_mergable(RDMAContext *rdma, + uint64_t offset, uint64_t len) +{ + RDMALocalBlock *block; + uint8_t *host_addr; + uint8_t *chunk_end; + + if (rdma->current_index < 0) { + return 0; + } + + if (rdma->current_chunk < 0) { + return 0; + } + + block = &(rdma->local_ram_blocks.block[rdma->current_index]); + host_addr = block->local_host_addr + (offset - block->offset); + chunk_end = ram_chunk_end(block, rdma->current_chunk); + + if (rdma->current_length == 0) { + return 0; + } + + /* + * Only merge into chunk sequentially. + */ + if (offset != (rdma->current_addr + rdma->current_length)) { + return 0; + } + + if (offset < block->offset) { + return 0; + } + + if ((offset + len) > (block->offset + block->length)) { + return 0; + } + + if ((host_addr + len) > chunk_end) { + return 0; + } + + return 1; +} + +/* + * We're not actually writing here, but doing three things: + * + * 1. Identify the chunk the buffer belongs to. + * 2. If the chunk is full or the buffer doesn't belong to the current + * chunk, then start a new chunk and flush() the old chunk. + * 3. To keep the hardware busy, we also group chunks into batches + * and only require that a batch gets acknowledged in the completion + * qeueue instead of each individual chunk. + */ +static int qemu_rdma_write(QEMUFile *f, RDMAContext *rdma, + uint64_t block_offset, uint64_t offset, + uint64_t len) +{ + uint64_t current_addr = block_offset + offset; + uint64_t index = rdma->current_index; + uint64_t chunk = rdma->current_chunk; + int ret; + + /* If we cannot merge it, we flush the current buffer first. */ + if (!qemu_rdma_buffer_mergable(rdma, current_addr, len)) { + ret = qemu_rdma_write_flush(f, rdma); + if (ret) { + return ret; + } + rdma->current_length = 0; + rdma->current_addr = current_addr; + + ret = qemu_rdma_search_ram_block(rdma, block_offset, + offset, len, &index, &chunk); + if (ret) { + error_report("ram block search failed"); + return ret; + } + rdma->current_index = index; + rdma->current_chunk = chunk; + } + + /* merge it */ + rdma->current_length += len; + + /* flush it if buffer is too large */ + if (rdma->current_length >= RDMA_MERGE_MAX) { + return qemu_rdma_write_flush(f, rdma); + } + + return 0; +} + +static void qemu_rdma_cleanup(RDMAContext *rdma) +{ + struct rdma_cm_event *cm_event; + int ret, idx; + + if (rdma->cm_id && rdma->connected) { + if (rdma->error_state) { + RDMAControlHeader head = { .len = 0, + .type = RDMA_CONTROL_ERROR, + .repeat = 1, + }; + error_report("Early error. Sending error."); + qemu_rdma_post_send_control(rdma, NULL, &head); + } + + ret = rdma_disconnect(rdma->cm_id); + if (!ret) { + trace_qemu_rdma_cleanup_waiting_for_disconnect(); + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (!ret) { + rdma_ack_cm_event(cm_event); + } + } + trace_qemu_rdma_cleanup_disconnect(); + rdma->connected = false; + } + + g_free(rdma->dest_blocks); + rdma->dest_blocks = NULL; + + for (idx = 0; idx < RDMA_WRID_MAX; idx++) { + if (rdma->wr_data[idx].control_mr) { + rdma->total_registrations--; + ibv_dereg_mr(rdma->wr_data[idx].control_mr); + } + rdma->wr_data[idx].control_mr = NULL; + } + + if (rdma->local_ram_blocks.block) { + while (rdma->local_ram_blocks.nb_blocks) { + rdma_delete_block(rdma, &rdma->local_ram_blocks.block[0]); + } + } + + if (rdma->qp) { + rdma_destroy_qp(rdma->cm_id); + rdma->qp = NULL; + } + if (rdma->cq) { + ibv_destroy_cq(rdma->cq); + rdma->cq = NULL; + } + if (rdma->comp_channel) { + ibv_destroy_comp_channel(rdma->comp_channel); + rdma->comp_channel = NULL; + } + if (rdma->pd) { + ibv_dealloc_pd(rdma->pd); + rdma->pd = NULL; + } + if (rdma->cm_id) { + rdma_destroy_id(rdma->cm_id); + rdma->cm_id = NULL; + } + if (rdma->listen_id) { + rdma_destroy_id(rdma->listen_id); + rdma->listen_id = NULL; + } + if (rdma->channel) { + rdma_destroy_event_channel(rdma->channel); + rdma->channel = NULL; + } + g_free(rdma->host); + rdma->host = NULL; +} + + +static int qemu_rdma_source_init(RDMAContext *rdma, Error **errp, bool pin_all) +{ + int ret, idx; + Error *local_err = NULL, **temp = &local_err; + + /* + * Will be validated against destination's actual capabilities + * after the connect() completes. + */ + rdma->pin_all = pin_all; + + ret = qemu_rdma_resolve_host(rdma, temp); + if (ret) { + goto err_rdma_source_init; + } + + ret = qemu_rdma_alloc_pd_cq(rdma); + if (ret) { + ERROR(temp, "rdma migration: error allocating pd and cq! Your mlock()" + " limits may be too low. Please check $ ulimit -a # and " + "search for 'ulimit -l' in the output"); + goto err_rdma_source_init; + } + + ret = qemu_rdma_alloc_qp(rdma); + if (ret) { + ERROR(temp, "rdma migration: error allocating qp!"); + goto err_rdma_source_init; + } + + ret = qemu_rdma_init_ram_blocks(rdma); + if (ret) { + ERROR(temp, "rdma migration: error initializing ram blocks!"); + goto err_rdma_source_init; + } + + /* Build the hash that maps from offset to RAMBlock */ + rdma->blockmap = g_hash_table_new(g_direct_hash, g_direct_equal); + for (idx = 0; idx < rdma->local_ram_blocks.nb_blocks; idx++) { + g_hash_table_insert(rdma->blockmap, + (void *)(uintptr_t)rdma->local_ram_blocks.block[idx].offset, + &rdma->local_ram_blocks.block[idx]); + } + + for (idx = 0; idx < RDMA_WRID_MAX; idx++) { + ret = qemu_rdma_reg_control(rdma, idx); + if (ret) { + ERROR(temp, "rdma migration: error registering %d control!", + idx); + goto err_rdma_source_init; + } + } + + return 0; + +err_rdma_source_init: + error_propagate(errp, local_err); + qemu_rdma_cleanup(rdma); + return -1; +} + +static int qemu_rdma_connect(RDMAContext *rdma, Error **errp) +{ + RDMACapabilities cap = { + .version = RDMA_CONTROL_VERSION_CURRENT, + .flags = 0, + }; + struct rdma_conn_param conn_param = { .initiator_depth = 2, + .retry_count = 5, + .private_data = &cap, + .private_data_len = sizeof(cap), + }; + struct rdma_cm_event *cm_event; + int ret; + + /* + * Only negotiate the capability with destination if the user + * on the source first requested the capability. + */ + if (rdma->pin_all) { + trace_qemu_rdma_connect_pin_all_requested(); + cap.flags |= RDMA_CAPABILITY_PIN_ALL; + } + + caps_to_network(&cap); + + ret = rdma_connect(rdma->cm_id, &conn_param); + if (ret) { + perror("rdma_connect"); + ERROR(errp, "connecting to destination!"); + goto err_rdma_source_connect; + } + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + perror("rdma_get_cm_event after rdma_connect"); + ERROR(errp, "connecting to destination!"); + rdma_ack_cm_event(cm_event); + goto err_rdma_source_connect; + } + + if (cm_event->event != RDMA_CM_EVENT_ESTABLISHED) { + perror("rdma_get_cm_event != EVENT_ESTABLISHED after rdma_connect"); + ERROR(errp, "connecting to destination!"); + rdma_ack_cm_event(cm_event); + goto err_rdma_source_connect; + } + rdma->connected = true; + + memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap)); + network_to_caps(&cap); + + /* + * Verify that the *requested* capabilities are supported by the destination + * and disable them otherwise. + */ + if (rdma->pin_all && !(cap.flags & RDMA_CAPABILITY_PIN_ALL)) { + ERROR(errp, "Server cannot support pinning all memory. " + "Will register memory dynamically."); + rdma->pin_all = false; + } + + trace_qemu_rdma_connect_pin_all_outcome(rdma->pin_all); + + rdma_ack_cm_event(cm_event); + + ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY); + if (ret) { + ERROR(errp, "posting second control recv!"); + goto err_rdma_source_connect; + } + + rdma->control_ready_expected = 1; + rdma->nb_sent = 0; + return 0; + +err_rdma_source_connect: + qemu_rdma_cleanup(rdma); + return -1; +} + +static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) +{ + int ret, idx; + struct rdma_cm_id *listen_id; + char ip[40] = "unknown"; + struct rdma_addrinfo *res, *e; + char port_str[16]; + + for (idx = 0; idx < RDMA_WRID_MAX; idx++) { + rdma->wr_data[idx].control_len = 0; + rdma->wr_data[idx].control_curr = NULL; + } + + if (!rdma->host || !rdma->host[0]) { + ERROR(errp, "RDMA host is not set!"); + rdma->error_state = -EINVAL; + return -1; + } + /* create CM channel */ + rdma->channel = rdma_create_event_channel(); + if (!rdma->channel) { + ERROR(errp, "could not create rdma event channel"); + rdma->error_state = -EINVAL; + return -1; + } + + /* create CM id */ + ret = rdma_create_id(rdma->channel, &listen_id, NULL, RDMA_PS_TCP); + if (ret) { + ERROR(errp, "could not create cm_id!"); + goto err_dest_init_create_listen_id; + } + + snprintf(port_str, 16, "%d", rdma->port); + port_str[15] = '\0'; + + ret = rdma_getaddrinfo(rdma->host, port_str, NULL, &res); + if (ret < 0) { + ERROR(errp, "could not rdma_getaddrinfo address %s", rdma->host); + goto err_dest_init_bind_addr; + } + + for (e = res; e != NULL; e = e->ai_next) { + inet_ntop(e->ai_family, + &((struct sockaddr_in *) e->ai_dst_addr)->sin_addr, ip, sizeof ip); + trace_qemu_rdma_dest_init_trying(rdma->host, ip); + ret = rdma_bind_addr(listen_id, e->ai_dst_addr); + if (ret) { + continue; + } + if (e->ai_family == AF_INET6) { + ret = qemu_rdma_broken_ipv6_kernel(errp, listen_id->verbs); + if (ret) { + continue; + } + } + break; + } + + if (!e) { + ERROR(errp, "Error: could not rdma_bind_addr!"); + goto err_dest_init_bind_addr; + } + + rdma->listen_id = listen_id; + qemu_rdma_dump_gid("dest_init", listen_id); + return 0; + +err_dest_init_bind_addr: + rdma_destroy_id(listen_id); +err_dest_init_create_listen_id: + rdma_destroy_event_channel(rdma->channel); + rdma->channel = NULL; + rdma->error_state = ret; + return ret; + +} + +static void *qemu_rdma_data_init(const char *host_port, Error **errp) +{ + RDMAContext *rdma = NULL; + InetSocketAddress *addr; + + if (host_port) { + rdma = g_new0(RDMAContext, 1); + rdma->current_index = -1; + rdma->current_chunk = -1; + + addr = inet_parse(host_port, NULL); + if (addr != NULL) { + rdma->port = atoi(addr->port); + rdma->host = g_strdup(addr->host); + } else { + ERROR(errp, "bad RDMA migration address '%s'", host_port); + g_free(rdma); + rdma = NULL; + } + + qapi_free_InetSocketAddress(addr); + } + + return rdma; +} + +/* + * QEMUFile interface to the control channel. + * SEND messages for control only. + * VM's ram is handled with regular RDMA messages. + */ +static ssize_t qemu_rdma_put_buffer(void *opaque, const uint8_t *buf, + int64_t pos, size_t size) +{ + QEMUFileRDMA *r = opaque; + QEMUFile *f = r->file; + RDMAContext *rdma = r->rdma; + size_t remaining = size; + uint8_t * data = (void *) buf; + int ret; + + CHECK_ERROR_STATE(); + + /* + * Push out any writes that + * we're queued up for VM's ram. + */ + ret = qemu_rdma_write_flush(f, rdma); + if (ret < 0) { + rdma->error_state = ret; + return ret; + } + + while (remaining) { + RDMAControlHeader head; + + r->len = MIN(remaining, RDMA_SEND_INCREMENT); + remaining -= r->len; + + /* Guaranteed to fit due to RDMA_SEND_INCREMENT MIN above */ + head.len = (uint32_t)r->len; + head.type = RDMA_CONTROL_QEMU_FILE; + + ret = qemu_rdma_exchange_send(rdma, &head, data, NULL, NULL, NULL); + + if (ret < 0) { + rdma->error_state = ret; + return ret; + } + + data += r->len; + } + + return size; +} + +static size_t qemu_rdma_fill(RDMAContext *rdma, uint8_t *buf, + size_t size, int idx) +{ + size_t len = 0; + + if (rdma->wr_data[idx].control_len) { + trace_qemu_rdma_fill(rdma->wr_data[idx].control_len, size); + + len = MIN(size, rdma->wr_data[idx].control_len); + memcpy(buf, rdma->wr_data[idx].control_curr, len); + rdma->wr_data[idx].control_curr += len; + rdma->wr_data[idx].control_len -= len; + } + + return len; +} + +/* + * QEMUFile interface to the control channel. + * RDMA links don't use bytestreams, so we have to + * return bytes to QEMUFile opportunistically. + */ +static ssize_t qemu_rdma_get_buffer(void *opaque, uint8_t *buf, + int64_t pos, size_t size) +{ + QEMUFileRDMA *r = opaque; + RDMAContext *rdma = r->rdma; + RDMAControlHeader head; + int ret = 0; + + CHECK_ERROR_STATE(); + + /* + * First, we hold on to the last SEND message we + * were given and dish out the bytes until we run + * out of bytes. + */ + r->len = qemu_rdma_fill(r->rdma, buf, size, 0); + if (r->len) { + return r->len; + } + + /* + * Once we run out, we block and wait for another + * SEND message to arrive. + */ + ret = qemu_rdma_exchange_recv(rdma, &head, RDMA_CONTROL_QEMU_FILE); + + if (ret < 0) { + rdma->error_state = ret; + return ret; + } + + /* + * SEND was received with new bytes, now try again. + */ + return qemu_rdma_fill(r->rdma, buf, size, 0); +} + +/* + * Block until all the outstanding chunks have been delivered by the hardware. + */ +static int qemu_rdma_drain_cq(QEMUFile *f, RDMAContext *rdma) +{ + int ret; + + if (qemu_rdma_write_flush(f, rdma) < 0) { + return -EIO; + } + + while (rdma->nb_sent) { + ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); + if (ret < 0) { + error_report("rdma migration: complete polling error!"); + return -EIO; + } + } + + qemu_rdma_unregister_waiting(rdma); + + return 0; +} + +static int qemu_rdma_close(void *opaque) +{ + trace_qemu_rdma_close(); + QEMUFileRDMA *r = opaque; + if (r->rdma) { + qemu_rdma_cleanup(r->rdma); + g_free(r->rdma); + } + g_free(r); + return 0; +} + +/* + * Parameters: + * @offset == 0 : + * This means that 'block_offset' is a full virtual address that does not + * belong to a RAMBlock of the virtual machine and instead + * represents a private malloc'd memory area that the caller wishes to + * transfer. + * + * @offset != 0 : + * Offset is an offset to be added to block_offset and used + * to also lookup the corresponding RAMBlock. + * + * @size > 0 : + * Initiate an transfer this size. + * + * @size == 0 : + * A 'hint' or 'advice' that means that we wish to speculatively + * and asynchronously unregister this memory. In this case, there is no + * guarantee that the unregister will actually happen, for example, + * if the memory is being actively transmitted. Additionally, the memory + * may be re-registered at any future time if a write within the same + * chunk was requested again, even if you attempted to unregister it + * here. + * + * @size < 0 : TODO, not yet supported + * Unregister the memory NOW. This means that the caller does not + * expect there to be any future RDMA transfers and we just want to clean + * things up. This is used in case the upper layer owns the memory and + * cannot wait for qemu_fclose() to occur. + * + * @bytes_sent : User-specificed pointer to indicate how many bytes were + * sent. Usually, this will not be more than a few bytes of + * the protocol because most transfers are sent asynchronously. + */ +static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque, + ram_addr_t block_offset, ram_addr_t offset, + size_t size, uint64_t *bytes_sent) +{ + QEMUFileRDMA *rfile = opaque; + RDMAContext *rdma = rfile->rdma; + int ret; + + CHECK_ERROR_STATE(); + + qemu_fflush(f); + + if (size > 0) { + /* + * Add this page to the current 'chunk'. If the chunk + * is full, or the page doen't belong to the current chunk, + * an actual RDMA write will occur and a new chunk will be formed. + */ + ret = qemu_rdma_write(f, rdma, block_offset, offset, size); + if (ret < 0) { + error_report("rdma migration: write error! %d", ret); + goto err; + } + + /* + * We always return 1 bytes because the RDMA + * protocol is completely asynchronous. We do not yet know + * whether an identified chunk is zero or not because we're + * waiting for other pages to potentially be merged with + * the current chunk. So, we have to call qemu_update_position() + * later on when the actual write occurs. + */ + if (bytes_sent) { + *bytes_sent = 1; + } + } else { + uint64_t index, chunk; + + /* TODO: Change QEMUFileOps prototype to be signed: size_t => long + if (size < 0) { + ret = qemu_rdma_drain_cq(f, rdma); + if (ret < 0) { + fprintf(stderr, "rdma: failed to synchronously drain" + " completion queue before unregistration.\n"); + goto err; + } + } + */ + + ret = qemu_rdma_search_ram_block(rdma, block_offset, + offset, size, &index, &chunk); + + if (ret) { + error_report("ram block search failed"); + goto err; + } + + qemu_rdma_signal_unregister(rdma, index, chunk, 0); + + /* + * TODO: Synchronous, guaranteed unregistration (should not occur during + * fast-path). Otherwise, unregisters will process on the next call to + * qemu_rdma_drain_cq() + if (size < 0) { + qemu_rdma_unregister_waiting(rdma); + } + */ + } + + /* + * Drain the Completion Queue if possible, but do not block, + * just poll. + * + * If nothing to poll, the end of the iteration will do this + * again to make sure we don't overflow the request queue. + */ + while (1) { + uint64_t wr_id, wr_id_in; + int ret = qemu_rdma_poll(rdma, &wr_id_in, NULL); + if (ret < 0) { + error_report("rdma migration: polling error! %d", ret); + goto err; + } + + wr_id = wr_id_in & RDMA_WRID_TYPE_MASK; + + if (wr_id == RDMA_WRID_NONE) { + break; + } + } + + return RAM_SAVE_CONTROL_DELAYED; +err: + rdma->error_state = ret; + return ret; +} + +static int qemu_rdma_accept(RDMAContext *rdma) +{ + RDMACapabilities cap; + struct rdma_conn_param conn_param = { + .responder_resources = 2, + .private_data = &cap, + .private_data_len = sizeof(cap), + }; + struct rdma_cm_event *cm_event; + struct ibv_context *verbs; + int ret = -EINVAL; + int idx; + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + goto err_rdma_dest_wait; + } + + if (cm_event->event != RDMA_CM_EVENT_CONNECT_REQUEST) { + rdma_ack_cm_event(cm_event); + goto err_rdma_dest_wait; + } + + memcpy(&cap, cm_event->param.conn.private_data, sizeof(cap)); + + network_to_caps(&cap); + + if (cap.version < 1 || cap.version > RDMA_CONTROL_VERSION_CURRENT) { + error_report("Unknown source RDMA version: %d, bailing...", + cap.version); + rdma_ack_cm_event(cm_event); + goto err_rdma_dest_wait; + } + + /* + * Respond with only the capabilities this version of QEMU knows about. + */ + cap.flags &= known_capabilities; + + /* + * Enable the ones that we do know about. + * Add other checks here as new ones are introduced. + */ + if (cap.flags & RDMA_CAPABILITY_PIN_ALL) { + rdma->pin_all = true; + } + + rdma->cm_id = cm_event->id; + verbs = cm_event->id->verbs; + + rdma_ack_cm_event(cm_event); + + trace_qemu_rdma_accept_pin_state(rdma->pin_all); + + caps_to_network(&cap); + + trace_qemu_rdma_accept_pin_verbsc(verbs); + + if (!rdma->verbs) { + rdma->verbs = verbs; + } else if (rdma->verbs != verbs) { + error_report("ibv context not matching %p, %p!", rdma->verbs, + verbs); + goto err_rdma_dest_wait; + } + + qemu_rdma_dump_id("dest_init", verbs); + + ret = qemu_rdma_alloc_pd_cq(rdma); + if (ret) { + error_report("rdma migration: error allocating pd and cq!"); + goto err_rdma_dest_wait; + } + + ret = qemu_rdma_alloc_qp(rdma); + if (ret) { + error_report("rdma migration: error allocating qp!"); + goto err_rdma_dest_wait; + } + + ret = qemu_rdma_init_ram_blocks(rdma); + if (ret) { + error_report("rdma migration: error initializing ram blocks!"); + goto err_rdma_dest_wait; + } + + for (idx = 0; idx < RDMA_WRID_MAX; idx++) { + ret = qemu_rdma_reg_control(rdma, idx); + if (ret) { + error_report("rdma: error registering %d control", idx); + goto err_rdma_dest_wait; + } + } + + qemu_set_fd_handler(rdma->channel->fd, NULL, NULL, NULL); + + ret = rdma_accept(rdma->cm_id, &conn_param); + if (ret) { + error_report("rdma_accept returns %d", ret); + goto err_rdma_dest_wait; + } + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + error_report("rdma_accept get_cm_event failed %d", ret); + goto err_rdma_dest_wait; + } + + if (cm_event->event != RDMA_CM_EVENT_ESTABLISHED) { + error_report("rdma_accept not event established"); + rdma_ack_cm_event(cm_event); + goto err_rdma_dest_wait; + } + + rdma_ack_cm_event(cm_event); + rdma->connected = true; + + ret = qemu_rdma_post_recv_control(rdma, RDMA_WRID_READY); + if (ret) { + error_report("rdma migration: error posting second control recv"); + goto err_rdma_dest_wait; + } + + qemu_rdma_dump_gid("dest_connect", rdma->cm_id); + + return 0; + +err_rdma_dest_wait: + rdma->error_state = ret; + qemu_rdma_cleanup(rdma); + return ret; +} + +static int dest_ram_sort_func(const void *a, const void *b) +{ + unsigned int a_index = ((const RDMALocalBlock *)a)->src_index; + unsigned int b_index = ((const RDMALocalBlock *)b)->src_index; + + return (a_index < b_index) ? -1 : (a_index != b_index); +} + +/* + * During each iteration of the migration, we listen for instructions + * by the source VM to perform dynamic page registrations before they + * can perform RDMA operations. + * + * We respond with the 'rkey'. + * + * Keep doing this until the source tells us to stop. + */ +static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque) +{ + RDMAControlHeader reg_resp = { .len = sizeof(RDMARegisterResult), + .type = RDMA_CONTROL_REGISTER_RESULT, + .repeat = 0, + }; + RDMAControlHeader unreg_resp = { .len = 0, + .type = RDMA_CONTROL_UNREGISTER_FINISHED, + .repeat = 0, + }; + RDMAControlHeader blocks = { .type = RDMA_CONTROL_RAM_BLOCKS_RESULT, + .repeat = 1 }; + QEMUFileRDMA *rfile = opaque; + RDMAContext *rdma = rfile->rdma; + RDMALocalBlocks *local = &rdma->local_ram_blocks; + RDMAControlHeader head; + RDMARegister *reg, *registers; + RDMACompress *comp; + RDMARegisterResult *reg_result; + static RDMARegisterResult results[RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE]; + RDMALocalBlock *block; + void *host_addr; + int ret = 0; + int idx = 0; + int count = 0; + int i = 0; + + CHECK_ERROR_STATE(); + + do { + trace_qemu_rdma_registration_handle_wait(); + + ret = qemu_rdma_exchange_recv(rdma, &head, RDMA_CONTROL_NONE); + + if (ret < 0) { + break; + } + + if (head.repeat > RDMA_CONTROL_MAX_COMMANDS_PER_MESSAGE) { + error_report("rdma: Too many requests in this message (%d)." + "Bailing.", head.repeat); + ret = -EIO; + break; + } + + switch (head.type) { + case RDMA_CONTROL_COMPRESS: + comp = (RDMACompress *) rdma->wr_data[idx].control_curr; + network_to_compress(comp); + + trace_qemu_rdma_registration_handle_compress(comp->length, + comp->block_idx, + comp->offset); + if (comp->block_idx >= rdma->local_ram_blocks.nb_blocks) { + error_report("rdma: 'compress' bad block index %u (vs %d)", + (unsigned int)comp->block_idx, + rdma->local_ram_blocks.nb_blocks); + ret = -EIO; + goto out; + } + block = &(rdma->local_ram_blocks.block[comp->block_idx]); + + host_addr = block->local_host_addr + + (comp->offset - block->offset); + + ram_handle_compressed(host_addr, comp->value, comp->length); + break; + + case RDMA_CONTROL_REGISTER_FINISHED: + trace_qemu_rdma_registration_handle_finished(); + goto out; + + case RDMA_CONTROL_RAM_BLOCKS_REQUEST: + trace_qemu_rdma_registration_handle_ram_blocks(); + + /* Sort our local RAM Block list so it's the same as the source, + * we can do this since we've filled in a src_index in the list + * as we received the RAMBlock list earlier. + */ + qsort(rdma->local_ram_blocks.block, + rdma->local_ram_blocks.nb_blocks, + sizeof(RDMALocalBlock), dest_ram_sort_func); + if (rdma->pin_all) { + ret = qemu_rdma_reg_whole_ram_blocks(rdma); + if (ret) { + error_report("rdma migration: error dest " + "registering ram blocks"); + goto out; + } + } + + /* + * Dest uses this to prepare to transmit the RAMBlock descriptions + * to the source VM after connection setup. + * Both sides use the "remote" structure to communicate and update + * their "local" descriptions with what was sent. + */ + for (i = 0; i < local->nb_blocks; i++) { + rdma->dest_blocks[i].remote_host_addr = + (uintptr_t)(local->block[i].local_host_addr); + + if (rdma->pin_all) { + rdma->dest_blocks[i].remote_rkey = local->block[i].mr->rkey; + } + + rdma->dest_blocks[i].offset = local->block[i].offset; + rdma->dest_blocks[i].length = local->block[i].length; + + dest_block_to_network(&rdma->dest_blocks[i]); + trace_qemu_rdma_registration_handle_ram_blocks_loop( + local->block[i].block_name, + local->block[i].offset, + local->block[i].length, + local->block[i].local_host_addr, + local->block[i].src_index); + } + + blocks.len = rdma->local_ram_blocks.nb_blocks + * sizeof(RDMADestBlock); + + + ret = qemu_rdma_post_send_control(rdma, + (uint8_t *) rdma->dest_blocks, &blocks); + + if (ret < 0) { + error_report("rdma migration: error sending remote info"); + goto out; + } + + break; + case RDMA_CONTROL_REGISTER_REQUEST: + trace_qemu_rdma_registration_handle_register(head.repeat); + + reg_resp.repeat = head.repeat; + registers = (RDMARegister *) rdma->wr_data[idx].control_curr; + + for (count = 0; count < head.repeat; count++) { + uint64_t chunk; + uint8_t *chunk_start, *chunk_end; + + reg = ®isters[count]; + network_to_register(reg); + + reg_result = &results[count]; + + trace_qemu_rdma_registration_handle_register_loop(count, + reg->current_index, reg->key.current_addr, reg->chunks); + + if (reg->current_index >= rdma->local_ram_blocks.nb_blocks) { + error_report("rdma: 'register' bad block index %u (vs %d)", + (unsigned int)reg->current_index, + rdma->local_ram_blocks.nb_blocks); + ret = -ENOENT; + goto out; + } + block = &(rdma->local_ram_blocks.block[reg->current_index]); + if (block->is_ram_block) { + if (block->offset > reg->key.current_addr) { + error_report("rdma: bad register address for block %s" + " offset: %" PRIx64 " current_addr: %" PRIx64, + block->block_name, block->offset, + reg->key.current_addr); + ret = -ERANGE; + goto out; + } + host_addr = (block->local_host_addr + + (reg->key.current_addr - block->offset)); + chunk = ram_chunk_index(block->local_host_addr, + (uint8_t *) host_addr); + } else { + chunk = reg->key.chunk; + host_addr = block->local_host_addr + + (reg->key.chunk * (1UL << RDMA_REG_CHUNK_SHIFT)); + /* Check for particularly bad chunk value */ + if (host_addr < (void *)block->local_host_addr) { + error_report("rdma: bad chunk for block %s" + " chunk: %" PRIx64, + block->block_name, reg->key.chunk); + ret = -ERANGE; + goto out; + } + } + chunk_start = ram_chunk_start(block, chunk); + chunk_end = ram_chunk_end(block, chunk + reg->chunks); + if (qemu_rdma_register_and_get_keys(rdma, block, + (uintptr_t)host_addr, NULL, ®_result->rkey, + chunk, chunk_start, chunk_end)) { + error_report("cannot get rkey"); + ret = -EINVAL; + goto out; + } + + reg_result->host_addr = (uintptr_t)block->local_host_addr; + + trace_qemu_rdma_registration_handle_register_rkey( + reg_result->rkey); + + result_to_network(reg_result); + } + + ret = qemu_rdma_post_send_control(rdma, + (uint8_t *) results, ®_resp); + + if (ret < 0) { + error_report("Failed to send control buffer"); + goto out; + } + break; + case RDMA_CONTROL_UNREGISTER_REQUEST: + trace_qemu_rdma_registration_handle_unregister(head.repeat); + unreg_resp.repeat = head.repeat; + registers = (RDMARegister *) rdma->wr_data[idx].control_curr; + + for (count = 0; count < head.repeat; count++) { + reg = ®isters[count]; + network_to_register(reg); + + trace_qemu_rdma_registration_handle_unregister_loop(count, + reg->current_index, reg->key.chunk); + + block = &(rdma->local_ram_blocks.block[reg->current_index]); + + ret = ibv_dereg_mr(block->pmr[reg->key.chunk]); + block->pmr[reg->key.chunk] = NULL; + + if (ret != 0) { + perror("rdma unregistration chunk failed"); + ret = -ret; + goto out; + } + + rdma->total_registrations--; + + trace_qemu_rdma_registration_handle_unregister_success( + reg->key.chunk); + } + + ret = qemu_rdma_post_send_control(rdma, NULL, &unreg_resp); + + if (ret < 0) { + error_report("Failed to send control buffer"); + goto out; + } + break; + case RDMA_CONTROL_REGISTER_RESULT: + error_report("Invalid RESULT message at dest."); + ret = -EIO; + goto out; + default: + error_report("Unknown control message %s", control_desc[head.type]); + ret = -EIO; + goto out; + } + } while (1); +out: + if (ret < 0) { + rdma->error_state = ret; + } + return ret; +} + +/* Destination: + * Called via a ram_control_load_hook during the initial RAM load section which + * lists the RAMBlocks by name. This lets us know the order of the RAMBlocks + * on the source. + * We've already built our local RAMBlock list, but not yet sent the list to + * the source. + */ +static int rdma_block_notification_handle(QEMUFileRDMA *rfile, const char *name) +{ + RDMAContext *rdma = rfile->rdma; + int curr; + int found = -1; + + /* Find the matching RAMBlock in our local list */ + for (curr = 0; curr < rdma->local_ram_blocks.nb_blocks; curr++) { + if (!strcmp(rdma->local_ram_blocks.block[curr].block_name, name)) { + found = curr; + break; + } + } + + if (found == -1) { + error_report("RAMBlock '%s' not found on destination", name); + return -ENOENT; + } + + rdma->local_ram_blocks.block[curr].src_index = rdma->next_src_index; + trace_rdma_block_notification_handle(name, rdma->next_src_index); + rdma->next_src_index++; + + return 0; +} + +static int rdma_load_hook(QEMUFile *f, void *opaque, uint64_t flags, void *data) +{ + switch (flags) { + case RAM_CONTROL_BLOCK_REG: + return rdma_block_notification_handle(opaque, data); + + case RAM_CONTROL_HOOK: + return qemu_rdma_registration_handle(f, opaque); + + default: + /* Shouldn't be called with any other values */ + abort(); + } +} + +static int qemu_rdma_registration_start(QEMUFile *f, void *opaque, + uint64_t flags, void *data) +{ + QEMUFileRDMA *rfile = opaque; + RDMAContext *rdma = rfile->rdma; + + CHECK_ERROR_STATE(); + + trace_qemu_rdma_registration_start(flags); + qemu_put_be64(f, RAM_SAVE_FLAG_HOOK); + qemu_fflush(f); + + return 0; +} + +/* + * Inform dest that dynamic registrations are done for now. + * First, flush writes, if any. + */ +static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, + uint64_t flags, void *data) +{ + Error *local_err = NULL, **errp = &local_err; + QEMUFileRDMA *rfile = opaque; + RDMAContext *rdma = rfile->rdma; + RDMAControlHeader head = { .len = 0, .repeat = 1 }; + int ret = 0; + + CHECK_ERROR_STATE(); + + qemu_fflush(f); + ret = qemu_rdma_drain_cq(f, rdma); + + if (ret < 0) { + goto err; + } + + if (flags == RAM_CONTROL_SETUP) { + RDMAControlHeader resp = {.type = RDMA_CONTROL_RAM_BLOCKS_RESULT }; + RDMALocalBlocks *local = &rdma->local_ram_blocks; + int reg_result_idx, i, nb_dest_blocks; + + head.type = RDMA_CONTROL_RAM_BLOCKS_REQUEST; + trace_qemu_rdma_registration_stop_ram(); + + /* + * Make sure that we parallelize the pinning on both sides. + * For very large guests, doing this serially takes a really + * long time, so we have to 'interleave' the pinning locally + * with the control messages by performing the pinning on this + * side before we receive the control response from the other + * side that the pinning has completed. + */ + ret = qemu_rdma_exchange_send(rdma, &head, NULL, &resp, + ®_result_idx, rdma->pin_all ? + qemu_rdma_reg_whole_ram_blocks : NULL); + if (ret < 0) { + ERROR(errp, "receiving remote info!"); + return ret; + } + + nb_dest_blocks = resp.len / sizeof(RDMADestBlock); + + /* + * The protocol uses two different sets of rkeys (mutually exclusive): + * 1. One key to represent the virtual address of the entire ram block. + * (dynamic chunk registration disabled - pin everything with one rkey.) + * 2. One to represent individual chunks within a ram block. + * (dynamic chunk registration enabled - pin individual chunks.) + * + * Once the capability is successfully negotiated, the destination transmits + * the keys to use (or sends them later) including the virtual addresses + * and then propagates the remote ram block descriptions to his local copy. + */ + + if (local->nb_blocks != nb_dest_blocks) { + ERROR(errp, "ram blocks mismatch (Number of blocks %d vs %d) " + "Your QEMU command line parameters are probably " + "not identical on both the source and destination.", + local->nb_blocks, nb_dest_blocks); + rdma->error_state = -EINVAL; + return -EINVAL; + } + + qemu_rdma_move_header(rdma, reg_result_idx, &resp); + memcpy(rdma->dest_blocks, + rdma->wr_data[reg_result_idx].control_curr, resp.len); + for (i = 0; i < nb_dest_blocks; i++) { + network_to_dest_block(&rdma->dest_blocks[i]); + + /* We require that the blocks are in the same order */ + if (rdma->dest_blocks[i].length != local->block[i].length) { + ERROR(errp, "Block %s/%d has a different length %" PRIu64 + "vs %" PRIu64, local->block[i].block_name, i, + local->block[i].length, + rdma->dest_blocks[i].length); + rdma->error_state = -EINVAL; + return -EINVAL; + } + local->block[i].remote_host_addr = + rdma->dest_blocks[i].remote_host_addr; + local->block[i].remote_rkey = rdma->dest_blocks[i].remote_rkey; + } + } + + trace_qemu_rdma_registration_stop(flags); + + head.type = RDMA_CONTROL_REGISTER_FINISHED; + ret = qemu_rdma_exchange_send(rdma, &head, NULL, NULL, NULL, NULL); + + if (ret < 0) { + goto err; + } + + return 0; +err: + rdma->error_state = ret; + return ret; +} + +static int qemu_rdma_get_fd(void *opaque) +{ + QEMUFileRDMA *rfile = opaque; + RDMAContext *rdma = rfile->rdma; + + return rdma->comp_channel->fd; +} + +static const QEMUFileOps rdma_read_ops = { + .get_buffer = qemu_rdma_get_buffer, + .get_fd = qemu_rdma_get_fd, + .close = qemu_rdma_close, + .hook_ram_load = rdma_load_hook, +}; + +static const QEMUFileOps rdma_write_ops = { + .put_buffer = qemu_rdma_put_buffer, + .close = qemu_rdma_close, + .before_ram_iterate = qemu_rdma_registration_start, + .after_ram_iterate = qemu_rdma_registration_stop, + .save_page = qemu_rdma_save_page, +}; + +static void *qemu_fopen_rdma(RDMAContext *rdma, const char *mode) +{ + QEMUFileRDMA *r; + + if (qemu_file_mode_is_not_valid(mode)) { + return NULL; + } + + r = g_new0(QEMUFileRDMA, 1); + r->rdma = rdma; + + if (mode[0] == 'w') { + r->file = qemu_fopen_ops(r, &rdma_write_ops); + } else { + r->file = qemu_fopen_ops(r, &rdma_read_ops); + } + + return r->file; +} + +static void rdma_accept_incoming_migration(void *opaque) +{ + RDMAContext *rdma = opaque; + int ret; + QEMUFile *f; + Error *local_err = NULL, **errp = &local_err; + + trace_qemu_rdma_accept_incoming_migration(); + ret = qemu_rdma_accept(rdma); + + if (ret) { + ERROR(errp, "RDMA Migration initialization failed!"); + return; + } + + trace_qemu_rdma_accept_incoming_migration_accepted(); + + f = qemu_fopen_rdma(rdma, "rb"); + if (f == NULL) { + ERROR(errp, "could not qemu_fopen_rdma!"); + qemu_rdma_cleanup(rdma); + return; + } + + rdma->migration_started_on_destination = 1; + process_incoming_migration(f); +} + +void rdma_start_incoming_migration(const char *host_port, Error **errp) +{ + int ret; + RDMAContext *rdma; + Error *local_err = NULL; + + trace_rdma_start_incoming_migration(); + rdma = qemu_rdma_data_init(host_port, &local_err); + + if (rdma == NULL) { + goto err; + } + + ret = qemu_rdma_dest_init(rdma, &local_err); + + if (ret) { + goto err; + } + + trace_rdma_start_incoming_migration_after_dest_init(); + + ret = rdma_listen(rdma->listen_id, 5); + + if (ret) { + ERROR(errp, "listening on socket!"); + goto err; + } + + trace_rdma_start_incoming_migration_after_rdma_listen(); + + qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, + NULL, (void *)(intptr_t)rdma); + return; +err: + error_propagate(errp, local_err); + g_free(rdma); +} + +void rdma_start_outgoing_migration(void *opaque, + const char *host_port, Error **errp) +{ + MigrationState *s = opaque; + Error *local_err = NULL, **temp = &local_err; + RDMAContext *rdma = qemu_rdma_data_init(host_port, &local_err); + int ret = 0; + + if (rdma == NULL) { + ERROR(temp, "Failed to initialize RDMA data structures! %d", ret); + goto err; + } + + ret = qemu_rdma_source_init(rdma, &local_err, + s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL]); + + if (ret) { + goto err; + } + + trace_rdma_start_outgoing_migration_after_rdma_source_init(); + ret = qemu_rdma_connect(rdma, &local_err); + + if (ret) { + goto err; + } + + trace_rdma_start_outgoing_migration_after_rdma_connect(); + + s->file = qemu_fopen_rdma(rdma, "wb"); + migrate_fd_connect(s); + return; +err: + error_propagate(errp, local_err); + g_free(rdma); + migrate_fd_error(s); +} diff --git a/src/migration/savevm.c b/src/migration/savevm.c new file mode 100644 index 0000000..41be296 --- /dev/null +++ b/src/migration/savevm.c @@ -0,0 +1,2195 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2008 Fabrice Bellard + * Copyright (c) 2009-2015 Red Hat Inc + * + * Authors: + * Juan Quintela <quintela@redhat.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "config-host.h" +#include "qemu-common.h" +#include "hw/boards.h" +#include "hw/hw.h" +#include "hw/qdev.h" +#include "net/net.h" +#include "monitor/monitor.h" +#include "sysemu/sysemu.h" +#include "qemu/timer.h" +#include "audio/audio.h" +#include "migration/migration.h" +#include "migration/postcopy-ram.h" +#include "qapi/qmp/qerror.h" +#include "qemu/error-report.h" +#include "qemu/sockets.h" +#include "qemu/queue.h" +#include "sysemu/cpus.h" +#include "exec/memory.h" +#include "qmp-commands.h" +#include "trace.h" +#include "qemu/bitops.h" +#include "qemu/iov.h" +#include "block/snapshot.h" +#include "block/qapi.h" + + +#ifndef ETH_P_RARP +#define ETH_P_RARP 0x8035 +#endif +#define ARP_HTYPE_ETH 0x0001 +#define ARP_PTYPE_IP 0x0800 +#define ARP_OP_REQUEST_REV 0x3 + +const unsigned int postcopy_ram_discard_version = 0; + +static bool skip_section_footers; + +static struct mig_cmd_args { + ssize_t len; /* -1 = variable */ + const char *name; +} mig_cmd_args[] = { + [MIG_CMD_INVALID] = { .len = -1, .name = "INVALID" }, + [MIG_CMD_OPEN_RETURN_PATH] = { .len = 0, .name = "OPEN_RETURN_PATH" }, + [MIG_CMD_PING] = { .len = sizeof(uint32_t), .name = "PING" }, + [MIG_CMD_POSTCOPY_ADVISE] = { .len = 16, .name = "POSTCOPY_ADVISE" }, + [MIG_CMD_POSTCOPY_LISTEN] = { .len = 0, .name = "POSTCOPY_LISTEN" }, + [MIG_CMD_POSTCOPY_RUN] = { .len = 0, .name = "POSTCOPY_RUN" }, + [MIG_CMD_POSTCOPY_RAM_DISCARD] = { + .len = -1, .name = "POSTCOPY_RAM_DISCARD" }, + [MIG_CMD_PACKAGED] = { .len = 4, .name = "PACKAGED" }, + [MIG_CMD_MAX] = { .len = -1, .name = "MAX" }, +}; + +static int announce_self_create(uint8_t *buf, + uint8_t *mac_addr) +{ + /* Ethernet header. */ + memset(buf, 0xff, 6); /* destination MAC addr */ + memcpy(buf + 6, mac_addr, 6); /* source MAC addr */ + *(uint16_t *)(buf + 12) = htons(ETH_P_RARP); /* ethertype */ + + /* RARP header. */ + *(uint16_t *)(buf + 14) = htons(ARP_HTYPE_ETH); /* hardware addr space */ + *(uint16_t *)(buf + 16) = htons(ARP_PTYPE_IP); /* protocol addr space */ + *(buf + 18) = 6; /* hardware addr length (ethernet) */ + *(buf + 19) = 4; /* protocol addr length (IPv4) */ + *(uint16_t *)(buf + 20) = htons(ARP_OP_REQUEST_REV); /* opcode */ + memcpy(buf + 22, mac_addr, 6); /* source hw addr */ + memset(buf + 28, 0x00, 4); /* source protocol addr */ + memcpy(buf + 32, mac_addr, 6); /* target hw addr */ + memset(buf + 38, 0x00, 4); /* target protocol addr */ + + /* Padding to get up to 60 bytes (ethernet min packet size, minus FCS). */ + memset(buf + 42, 0x00, 18); + + return 60; /* len (FCS will be added by hardware) */ +} + +static void qemu_announce_self_iter(NICState *nic, void *opaque) +{ + uint8_t buf[60]; + int len; + + trace_qemu_announce_self_iter(qemu_ether_ntoa(&nic->conf->macaddr)); + len = announce_self_create(buf, nic->conf->macaddr.a); + + qemu_send_packet_raw(qemu_get_queue(nic), buf, len); +} + + +static void qemu_announce_self_once(void *opaque) +{ + static int count = SELF_ANNOUNCE_ROUNDS; + QEMUTimer *timer = *(QEMUTimer **)opaque; + + qemu_foreach_nic(qemu_announce_self_iter, NULL); + + if (--count) { + /* delay 50ms, 150ms, 250ms, ... */ + timer_mod(timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + + self_announce_delay(count)); + } else { + timer_del(timer); + timer_free(timer); + } +} + +void qemu_announce_self(void) +{ + static QEMUTimer *timer; + timer = timer_new_ms(QEMU_CLOCK_REALTIME, qemu_announce_self_once, &timer); + qemu_announce_self_once(&timer); +} + +/***********************************************************/ +/* savevm/loadvm support */ + +static ssize_t block_writev_buffer(void *opaque, struct iovec *iov, int iovcnt, + int64_t pos) +{ + int ret; + QEMUIOVector qiov; + + qemu_iovec_init_external(&qiov, iov, iovcnt); + ret = bdrv_writev_vmstate(opaque, &qiov, pos); + if (ret < 0) { + return ret; + } + + return qiov.size; +} + +static ssize_t block_put_buffer(void *opaque, const uint8_t *buf, + int64_t pos, size_t size) +{ + bdrv_save_vmstate(opaque, buf, pos, size); + return size; +} + +static ssize_t block_get_buffer(void *opaque, uint8_t *buf, int64_t pos, + size_t size) +{ + return bdrv_load_vmstate(opaque, buf, pos, size); +} + +static int bdrv_fclose(void *opaque) +{ + return bdrv_flush(opaque); +} + +static const QEMUFileOps bdrv_read_ops = { + .get_buffer = block_get_buffer, + .close = bdrv_fclose +}; + +static const QEMUFileOps bdrv_write_ops = { + .put_buffer = block_put_buffer, + .writev_buffer = block_writev_buffer, + .close = bdrv_fclose +}; + +static QEMUFile *qemu_fopen_bdrv(BlockDriverState *bs, int is_writable) +{ + if (is_writable) { + return qemu_fopen_ops(bs, &bdrv_write_ops); + } + return qemu_fopen_ops(bs, &bdrv_read_ops); +} + + +/* QEMUFile timer support. + * Not in qemu-file.c to not add qemu-timer.c as dependency to qemu-file.c + */ + +void timer_put(QEMUFile *f, QEMUTimer *ts) +{ + uint64_t expire_time; + + expire_time = timer_expire_time_ns(ts); + qemu_put_be64(f, expire_time); +} + +void timer_get(QEMUFile *f, QEMUTimer *ts) +{ + uint64_t expire_time; + + expire_time = qemu_get_be64(f); + if (expire_time != -1) { + timer_mod_ns(ts, expire_time); + } else { + timer_del(ts); + } +} + + +/* VMState timer support. + * Not in vmstate.c to not add qemu-timer.c as dependency to vmstate.c + */ + +static int get_timer(QEMUFile *f, void *pv, size_t size) +{ + QEMUTimer *v = pv; + timer_get(f, v); + return 0; +} + +static void put_timer(QEMUFile *f, void *pv, size_t size) +{ + QEMUTimer *v = pv; + timer_put(f, v); +} + +const VMStateInfo vmstate_info_timer = { + .name = "timer", + .get = get_timer, + .put = put_timer, +}; + + +typedef struct CompatEntry { + char idstr[256]; + int instance_id; +} CompatEntry; + +typedef struct SaveStateEntry { + QTAILQ_ENTRY(SaveStateEntry) entry; + char idstr[256]; + int instance_id; + int alias_id; + int version_id; + int section_id; + SaveVMHandlers *ops; + const VMStateDescription *vmsd; + void *opaque; + CompatEntry *compat; + int is_ram; +} SaveStateEntry; + +typedef struct SaveState { + QTAILQ_HEAD(, SaveStateEntry) handlers; + int global_section_id; + bool skip_configuration; + uint32_t len; + const char *name; +} SaveState; + +static SaveState savevm_state = { + .handlers = QTAILQ_HEAD_INITIALIZER(savevm_state.handlers), + .global_section_id = 0, + .skip_configuration = false, +}; + +void savevm_skip_configuration(void) +{ + savevm_state.skip_configuration = true; +} + + +static void configuration_pre_save(void *opaque) +{ + SaveState *state = opaque; + const char *current_name = MACHINE_GET_CLASS(current_machine)->name; + + state->len = strlen(current_name); + state->name = current_name; +} + +static int configuration_post_load(void *opaque, int version_id) +{ + SaveState *state = opaque; + const char *current_name = MACHINE_GET_CLASS(current_machine)->name; + + if (strncmp(state->name, current_name, state->len) != 0) { + error_report("Machine type received is '%s' and local is '%s'", + state->name, current_name); + return -EINVAL; + } + return 0; +} + +static const VMStateDescription vmstate_configuration = { + .name = "configuration", + .version_id = 1, + .post_load = configuration_post_load, + .pre_save = configuration_pre_save, + .fields = (VMStateField[]) { + VMSTATE_UINT32(len, SaveState), + VMSTATE_VBUFFER_ALLOC_UINT32(name, SaveState, 0, NULL, 0, len), + VMSTATE_END_OF_LIST() + }, +}; + +static void dump_vmstate_vmsd(FILE *out_file, + const VMStateDescription *vmsd, int indent, + bool is_subsection); + +static void dump_vmstate_vmsf(FILE *out_file, const VMStateField *field, + int indent) +{ + fprintf(out_file, "%*s{\n", indent, ""); + indent += 2; + fprintf(out_file, "%*s\"field\": \"%s\",\n", indent, "", field->name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + field->version_id); + fprintf(out_file, "%*s\"field_exists\": %s,\n", indent, "", + field->field_exists ? "true" : "false"); + fprintf(out_file, "%*s\"size\": %zu", indent, "", field->size); + if (field->vmsd != NULL) { + fprintf(out_file, ",\n"); + dump_vmstate_vmsd(out_file, field->vmsd, indent, false); + } + fprintf(out_file, "\n%*s}", indent - 2, ""); +} + +static void dump_vmstate_vmss(FILE *out_file, + const VMStateDescription **subsection, + int indent) +{ + if (*subsection != NULL) { + dump_vmstate_vmsd(out_file, *subsection, indent, true); + } +} + +static void dump_vmstate_vmsd(FILE *out_file, + const VMStateDescription *vmsd, int indent, + bool is_subsection) +{ + if (is_subsection) { + fprintf(out_file, "%*s{\n", indent, ""); + } else { + fprintf(out_file, "%*s\"%s\": {\n", indent, "", "Description"); + } + indent += 2; + fprintf(out_file, "%*s\"name\": \"%s\",\n", indent, "", vmsd->name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + vmsd->version_id); + fprintf(out_file, "%*s\"minimum_version_id\": %d", indent, "", + vmsd->minimum_version_id); + if (vmsd->fields != NULL) { + const VMStateField *field = vmsd->fields; + bool first; + + fprintf(out_file, ",\n%*s\"Fields\": [\n", indent, ""); + first = true; + while (field->name != NULL) { + if (field->flags & VMS_MUST_EXIST) { + /* Ignore VMSTATE_VALIDATE bits; these don't get migrated */ + field++; + continue; + } + if (!first) { + fprintf(out_file, ",\n"); + } + dump_vmstate_vmsf(out_file, field, indent + 2); + field++; + first = false; + } + fprintf(out_file, "\n%*s]", indent, ""); + } + if (vmsd->subsections != NULL) { + const VMStateDescription **subsection = vmsd->subsections; + bool first; + + fprintf(out_file, ",\n%*s\"Subsections\": [\n", indent, ""); + first = true; + while (*subsection != NULL) { + if (!first) { + fprintf(out_file, ",\n"); + } + dump_vmstate_vmss(out_file, subsection, indent + 2); + subsection++; + first = false; + } + fprintf(out_file, "\n%*s]", indent, ""); + } + fprintf(out_file, "\n%*s}", indent - 2, ""); +} + +static void dump_machine_type(FILE *out_file) +{ + MachineClass *mc; + + mc = MACHINE_GET_CLASS(current_machine); + + fprintf(out_file, " \"vmschkmachine\": {\n"); + fprintf(out_file, " \"Name\": \"%s\"\n", mc->name); + fprintf(out_file, " },\n"); +} + +void dump_vmstate_json_to_file(FILE *out_file) +{ + GSList *list, *elt; + bool first; + + fprintf(out_file, "{\n"); + dump_machine_type(out_file); + + first = true; + list = object_class_get_list(TYPE_DEVICE, true); + for (elt = list; elt; elt = elt->next) { + DeviceClass *dc = OBJECT_CLASS_CHECK(DeviceClass, elt->data, + TYPE_DEVICE); + const char *name; + int indent = 2; + + if (!dc->vmsd) { + continue; + } + + if (!first) { + fprintf(out_file, ",\n"); + } + name = object_class_get_name(OBJECT_CLASS(dc)); + fprintf(out_file, "%*s\"%s\": {\n", indent, "", name); + indent += 2; + fprintf(out_file, "%*s\"Name\": \"%s\",\n", indent, "", name); + fprintf(out_file, "%*s\"version_id\": %d,\n", indent, "", + dc->vmsd->version_id); + fprintf(out_file, "%*s\"minimum_version_id\": %d,\n", indent, "", + dc->vmsd->minimum_version_id); + + dump_vmstate_vmsd(out_file, dc->vmsd, indent, false); + + fprintf(out_file, "\n%*s}", indent - 2, ""); + first = false; + } + fprintf(out_file, "\n}\n"); + fclose(out_file); +} + +static int calculate_new_instance_id(const char *idstr) +{ + SaveStateEntry *se; + int instance_id = 0; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (strcmp(idstr, se->idstr) == 0 + && instance_id <= se->instance_id) { + instance_id = se->instance_id + 1; + } + } + return instance_id; +} + +static int calculate_compat_instance_id(const char *idstr) +{ + SaveStateEntry *se; + int instance_id = 0; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->compat) { + continue; + } + + if (strcmp(idstr, se->compat->idstr) == 0 + && instance_id <= se->compat->instance_id) { + instance_id = se->compat->instance_id + 1; + } + } + return instance_id; +} + +/* TODO: Individual devices generally have very little idea about the rest + of the system, so instance_id should be removed/replaced. + Meanwhile pass -1 as instance_id if you do not already have a clearly + distinguishing id for all instances of your device class. */ +int register_savevm_live(DeviceState *dev, + const char *idstr, + int instance_id, + int version_id, + SaveVMHandlers *ops, + void *opaque) +{ + SaveStateEntry *se; + + se = g_new0(SaveStateEntry, 1); + se->version_id = version_id; + se->section_id = savevm_state.global_section_id++; + se->ops = ops; + se->opaque = opaque; + se->vmsd = NULL; + /* if this is a live_savem then set is_ram */ + if (ops->save_live_setup != NULL) { + se->is_ram = 1; + } + + if (dev) { + char *id = qdev_get_dev_path(dev); + if (id) { + pstrcpy(se->idstr, sizeof(se->idstr), id); + pstrcat(se->idstr, sizeof(se->idstr), "/"); + g_free(id); + + se->compat = g_new0(CompatEntry, 1); + pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), idstr); + se->compat->instance_id = instance_id == -1 ? + calculate_compat_instance_id(idstr) : instance_id; + instance_id = -1; + } + } + pstrcat(se->idstr, sizeof(se->idstr), idstr); + + if (instance_id == -1) { + se->instance_id = calculate_new_instance_id(se->idstr); + } else { + se->instance_id = instance_id; + } + assert(!se->compat || se->instance_id == 0); + /* add at the end of list */ + QTAILQ_INSERT_TAIL(&savevm_state.handlers, se, entry); + return 0; +} + +int register_savevm(DeviceState *dev, + const char *idstr, + int instance_id, + int version_id, + SaveStateHandler *save_state, + LoadStateHandler *load_state, + void *opaque) +{ + SaveVMHandlers *ops = g_new0(SaveVMHandlers, 1); + ops->save_state = save_state; + ops->load_state = load_state; + return register_savevm_live(dev, idstr, instance_id, version_id, + ops, opaque); +} + +void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque) +{ + SaveStateEntry *se, *new_se; + char id[256] = ""; + + if (dev) { + char *path = qdev_get_dev_path(dev); + if (path) { + pstrcpy(id, sizeof(id), path); + pstrcat(id, sizeof(id), "/"); + g_free(path); + } + } + pstrcat(id, sizeof(id), idstr); + + QTAILQ_FOREACH_SAFE(se, &savevm_state.handlers, entry, new_se) { + if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) { + QTAILQ_REMOVE(&savevm_state.handlers, se, entry); + g_free(se->compat); + g_free(se->ops); + g_free(se); + } + } +} + +int vmstate_register_with_alias_id(DeviceState *dev, int instance_id, + const VMStateDescription *vmsd, + void *opaque, int alias_id, + int required_for_version) +{ + SaveStateEntry *se; + + /* If this triggers, alias support can be dropped for the vmsd. */ + assert(alias_id == -1 || required_for_version >= vmsd->minimum_version_id); + + se = g_new0(SaveStateEntry, 1); + se->version_id = vmsd->version_id; + se->section_id = savevm_state.global_section_id++; + se->opaque = opaque; + se->vmsd = vmsd; + se->alias_id = alias_id; + + if (dev) { + char *id = qdev_get_dev_path(dev); + if (id) { + pstrcpy(se->idstr, sizeof(se->idstr), id); + pstrcat(se->idstr, sizeof(se->idstr), "/"); + g_free(id); + + se->compat = g_new0(CompatEntry, 1); + pstrcpy(se->compat->idstr, sizeof(se->compat->idstr), vmsd->name); + se->compat->instance_id = instance_id == -1 ? + calculate_compat_instance_id(vmsd->name) : instance_id; + instance_id = -1; + } + } + pstrcat(se->idstr, sizeof(se->idstr), vmsd->name); + + if (instance_id == -1) { + se->instance_id = calculate_new_instance_id(se->idstr); + } else { + se->instance_id = instance_id; + } + assert(!se->compat || se->instance_id == 0); + /* add at the end of list */ + QTAILQ_INSERT_TAIL(&savevm_state.handlers, se, entry); + return 0; +} + +void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd, + void *opaque) +{ + SaveStateEntry *se, *new_se; + + QTAILQ_FOREACH_SAFE(se, &savevm_state.handlers, entry, new_se) { + if (se->vmsd == vmsd && se->opaque == opaque) { + QTAILQ_REMOVE(&savevm_state.handlers, se, entry); + g_free(se->compat); + g_free(se); + } + } +} + +static int vmstate_load(QEMUFile *f, SaveStateEntry *se, int version_id) +{ + trace_vmstate_load(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); + if (!se->vmsd) { /* Old style */ + return se->ops->load_state(f, se->opaque, version_id); + } + return vmstate_load_state(f, se->vmsd, se->opaque, version_id); +} + +static void vmstate_save_old_style(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) +{ + int64_t old_offset, size; + + old_offset = qemu_ftell_fast(f); + se->ops->save_state(f, se->opaque); + size = qemu_ftell_fast(f) - old_offset; + + if (vmdesc) { + json_prop_int(vmdesc, "size", size); + json_start_array(vmdesc, "fields"); + json_start_object(vmdesc, NULL); + json_prop_str(vmdesc, "name", "data"); + json_prop_int(vmdesc, "size", size); + json_prop_str(vmdesc, "type", "buffer"); + json_end_object(vmdesc); + json_end_array(vmdesc); + } +} + +static void vmstate_save(QEMUFile *f, SaveStateEntry *se, QJSON *vmdesc) +{ + trace_vmstate_save(se->idstr, se->vmsd ? se->vmsd->name : "(old)"); + if (!se->vmsd) { + vmstate_save_old_style(f, se, vmdesc); + return; + } + vmstate_save_state(f, se->vmsd, se->opaque, vmdesc); +} + +void savevm_skip_section_footers(void) +{ + skip_section_footers = true; +} + +/* + * Write the header for device section (QEMU_VM_SECTION START/END/PART/FULL) + */ +static void save_section_header(QEMUFile *f, SaveStateEntry *se, + uint8_t section_type) +{ + qemu_put_byte(f, section_type); + qemu_put_be32(f, se->section_id); + + if (section_type == QEMU_VM_SECTION_FULL || + section_type == QEMU_VM_SECTION_START) { + /* ID string */ + size_t len = strlen(se->idstr); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)se->idstr, len); + + qemu_put_be32(f, se->instance_id); + qemu_put_be32(f, se->version_id); + } +} + +/* + * Write a footer onto device sections that catches cases misformatted device + * sections. + */ +static void save_section_footer(QEMUFile *f, SaveStateEntry *se) +{ + if (!skip_section_footers) { + qemu_put_byte(f, QEMU_VM_SECTION_FOOTER); + qemu_put_be32(f, se->section_id); + } +} + +/** + * qemu_savevm_command_send: Send a 'QEMU_VM_COMMAND' type element with the + * command and associated data. + * + * @f: File to send command on + * @command: Command type to send + * @len: Length of associated data + * @data: Data associated with command. + */ +void qemu_savevm_command_send(QEMUFile *f, + enum qemu_vm_cmd command, + uint16_t len, + uint8_t *data) +{ + trace_savevm_command_send(command, len); + qemu_put_byte(f, QEMU_VM_COMMAND); + qemu_put_be16(f, (uint16_t)command); + qemu_put_be16(f, len); + qemu_put_buffer(f, data, len); + qemu_fflush(f); +} + +void qemu_savevm_send_ping(QEMUFile *f, uint32_t value) +{ + uint32_t buf; + + trace_savevm_send_ping(value); + buf = cpu_to_be32(value); + qemu_savevm_command_send(f, MIG_CMD_PING, sizeof(value), (uint8_t *)&buf); +} + +void qemu_savevm_send_open_return_path(QEMUFile *f) +{ + trace_savevm_send_open_return_path(); + qemu_savevm_command_send(f, MIG_CMD_OPEN_RETURN_PATH, 0, NULL); +} + +/* We have a buffer of data to send; we don't want that all to be loaded + * by the command itself, so the command contains just the length of the + * extra buffer that we then send straight after it. + * TODO: Must be a better way to organise that + * + * Returns: + * 0 on success + * -ve on error + */ +int qemu_savevm_send_packaged(QEMUFile *f, const QEMUSizedBuffer *qsb) +{ + size_t cur_iov; + size_t len = qsb_get_length(qsb); + uint32_t tmp; + + if (len > MAX_VM_CMD_PACKAGED_SIZE) { + error_report("%s: Unreasonably large packaged state: %zu", + __func__, len); + return -1; + } + + tmp = cpu_to_be32(len); + + trace_qemu_savevm_send_packaged(); + qemu_savevm_command_send(f, MIG_CMD_PACKAGED, 4, (uint8_t *)&tmp); + + /* all the data follows (concatinating the iov's) */ + for (cur_iov = 0; cur_iov < qsb->n_iov; cur_iov++) { + /* The iov entries are partially filled */ + size_t towrite = MIN(qsb->iov[cur_iov].iov_len, len); + len -= towrite; + + if (!towrite) { + break; + } + + qemu_put_buffer(f, qsb->iov[cur_iov].iov_base, towrite); + } + + return 0; +} + +/* Send prior to any postcopy transfer */ +void qemu_savevm_send_postcopy_advise(QEMUFile *f) +{ + uint64_t tmp[2]; + tmp[0] = cpu_to_be64(getpagesize()); + tmp[1] = cpu_to_be64(1ul << qemu_target_page_bits()); + + trace_qemu_savevm_send_postcopy_advise(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_ADVISE, 16, (uint8_t *)tmp); +} + +/* Sent prior to starting the destination running in postcopy, discard pages + * that have already been sent but redirtied on the source. + * CMD_POSTCOPY_RAM_DISCARD consist of: + * byte version (0) + * byte Length of name field (not including 0) + * n x byte RAM block name + * byte 0 terminator (just for safety) + * n x Byte ranges within the named RAMBlock + * be64 Start of the range + * be64 Length + * + * name: RAMBlock name that these entries are part of + * len: Number of page entries + * start_list: 'len' addresses + * length_list: 'len' addresses + * + */ +void qemu_savevm_send_postcopy_ram_discard(QEMUFile *f, const char *name, + uint16_t len, + uint64_t *start_list, + uint64_t *length_list) +{ + uint8_t *buf; + uint16_t tmplen; + uint16_t t; + size_t name_len = strlen(name); + + trace_qemu_savevm_send_postcopy_ram_discard(name, len); + assert(name_len < 256); + buf = g_malloc0(1 + 1 + name_len + 1 + (8 + 8) * len); + buf[0] = postcopy_ram_discard_version; + buf[1] = name_len; + memcpy(buf + 2, name, name_len); + tmplen = 2 + name_len; + buf[tmplen++] = '\0'; + + for (t = 0; t < len; t++) { + cpu_to_be64w((uint64_t *)(buf + tmplen), start_list[t]); + tmplen += 8; + cpu_to_be64w((uint64_t *)(buf + tmplen), length_list[t]); + tmplen += 8; + } + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RAM_DISCARD, tmplen, buf); + g_free(buf); +} + +/* Get the destination into a state where it can receive postcopy data. */ +void qemu_savevm_send_postcopy_listen(QEMUFile *f) +{ + trace_savevm_send_postcopy_listen(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_LISTEN, 0, NULL); +} + +/* Kick the destination into running */ +void qemu_savevm_send_postcopy_run(QEMUFile *f) +{ + trace_savevm_send_postcopy_run(); + qemu_savevm_command_send(f, MIG_CMD_POSTCOPY_RUN, 0, NULL); +} + +bool qemu_savevm_state_blocked(Error **errp) +{ + SaveStateEntry *se; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (se->vmsd && se->vmsd->unmigratable) { + error_setg(errp, "State blocked by non-migratable device '%s'", + se->idstr); + return true; + } + } + return false; +} + +static bool enforce_config_section(void) +{ + MachineState *machine = MACHINE(qdev_get_machine()); + return machine->enforce_config_section; +} + +void qemu_savevm_state_header(QEMUFile *f) +{ + trace_savevm_state_header(); + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + + if (!savevm_state.skip_configuration || enforce_config_section()) { + qemu_put_byte(f, QEMU_VM_CONFIGURATION); + vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0); + } + +} + +void qemu_savevm_state_begin(QEMUFile *f, + const MigrationParams *params) +{ + SaveStateEntry *se; + int ret; + + trace_savevm_state_begin(); + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->set_params) { + continue; + } + se->ops->set_params(params, se->opaque); + } + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_live_setup) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + save_section_header(f, se, QEMU_VM_SECTION_START); + + ret = se->ops->save_live_setup(f, se->opaque); + save_section_footer(f, se); + if (ret < 0) { + qemu_file_set_error(f, ret); + break; + } + } +} + +/* + * this function has three return values: + * negative: there was one error, and we have -errno. + * 0 : We haven't finished, caller have to go again + * 1 : We have finished, we can go to complete phase + */ +int qemu_savevm_state_iterate(QEMUFile *f, bool postcopy) +{ + SaveStateEntry *se; + int ret = 1; + + trace_savevm_state_iterate(); + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_live_iterate) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + /* + * In the postcopy phase, any device that doesn't know how to + * do postcopy should have saved it's state in the _complete + * call that's already run, it might get confused if we call + * iterate afterwards. + */ + if (postcopy && !se->ops->save_live_complete_postcopy) { + continue; + } + if (qemu_file_rate_limit(f)) { + return 0; + } + trace_savevm_section_start(se->idstr, se->section_id); + + save_section_header(f, se, QEMU_VM_SECTION_PART); + + ret = se->ops->save_live_iterate(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + + if (ret < 0) { + qemu_file_set_error(f, ret); + } + if (ret <= 0) { + /* Do not proceed to the next vmstate before this one reported + completion of the current stage. This serializes the migration + and reduces the probability that a faster changing state is + synchronized over and over again. */ + break; + } + } + return ret; +} + +static bool should_send_vmdesc(void) +{ + MachineState *machine = MACHINE(qdev_get_machine()); + bool in_postcopy = migration_in_postcopy(migrate_get_current()); + return !machine->suppress_vmdesc && !in_postcopy; +} + +/* + * Calls the save_live_complete_postcopy methods + * causing the last few pages to be sent immediately and doing any associated + * cleanup. + * Note postcopy also calls qemu_savevm_state_complete_precopy to complete + * all the other devices, but that happens at the point we switch to postcopy. + */ +void qemu_savevm_state_complete_postcopy(QEMUFile *f) +{ + SaveStateEntry *se; + int ret; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_live_complete_postcopy) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + trace_savevm_section_start(se->idstr, se->section_id); + /* Section type */ + qemu_put_byte(f, QEMU_VM_SECTION_END); + qemu_put_be32(f, se->section_id); + + ret = se->ops->save_live_complete_postcopy(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { + qemu_file_set_error(f, ret); + return; + } + } + + qemu_put_byte(f, QEMU_VM_EOF); + qemu_fflush(f); +} + +void qemu_savevm_state_complete_precopy(QEMUFile *f, bool iterable_only) +{ + QJSON *vmdesc; + int vmdesc_len; + SaveStateEntry *se; + int ret; + bool in_postcopy = migration_in_postcopy(migrate_get_current()); + + trace_savevm_state_complete_precopy(); + + cpu_synchronize_all_states(); + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || + (in_postcopy && se->ops->save_live_complete_postcopy) || + (in_postcopy && !iterable_only) || + !se->ops->save_live_complete_precopy) { + continue; + } + + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + trace_savevm_section_start(se->idstr, se->section_id); + + save_section_header(f, se, QEMU_VM_SECTION_END); + + ret = se->ops->save_live_complete_precopy(f, se->opaque); + trace_savevm_section_end(se->idstr, se->section_id, ret); + save_section_footer(f, se); + if (ret < 0) { + qemu_file_set_error(f, ret); + return; + } + } + + if (iterable_only) { + return; + } + + vmdesc = qjson_new(); + json_prop_int(vmdesc, "page_size", TARGET_PAGE_SIZE); + json_start_array(vmdesc, "devices"); + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + + if ((!se->ops || !se->ops->save_state) && !se->vmsd) { + continue; + } + if (se->vmsd && !vmstate_save_needed(se->vmsd, se->opaque)) { + trace_savevm_section_skip(se->idstr, se->section_id); + continue; + } + + trace_savevm_section_start(se->idstr, se->section_id); + + json_start_object(vmdesc, NULL); + json_prop_str(vmdesc, "name", se->idstr); + json_prop_int(vmdesc, "instance_id", se->instance_id); + + save_section_header(f, se, QEMU_VM_SECTION_FULL); + + vmstate_save(f, se, vmdesc); + + json_end_object(vmdesc); + trace_savevm_section_end(se->idstr, se->section_id, 0); + save_section_footer(f, se); + } + + if (!in_postcopy) { + /* Postcopy stream will still be going */ + qemu_put_byte(f, QEMU_VM_EOF); + } + + json_end_array(vmdesc); + qjson_finish(vmdesc); + vmdesc_len = strlen(qjson_get_str(vmdesc)); + + if (should_send_vmdesc()) { + qemu_put_byte(f, QEMU_VM_VMDESCRIPTION); + qemu_put_be32(f, vmdesc_len); + qemu_put_buffer(f, (uint8_t *)qjson_get_str(vmdesc), vmdesc_len); + } + object_unref(OBJECT(vmdesc)); + + qemu_fflush(f); +} + +/* Give an estimate of the amount left to be transferred, + * the result is split into the amount for units that can and + * for units that can't do postcopy. + */ +void qemu_savevm_state_pending(QEMUFile *f, uint64_t max_size, + uint64_t *res_non_postcopiable, + uint64_t *res_postcopiable) +{ + SaveStateEntry *se; + + *res_non_postcopiable = 0; + *res_postcopiable = 0; + + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!se->ops || !se->ops->save_live_pending) { + continue; + } + if (se->ops && se->ops->is_active) { + if (!se->ops->is_active(se->opaque)) { + continue; + } + } + se->ops->save_live_pending(f, se->opaque, max_size, + res_non_postcopiable, res_postcopiable); + } +} + +void qemu_savevm_state_cleanup(void) +{ + SaveStateEntry *se; + + trace_savevm_state_cleanup(); + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (se->ops && se->ops->cleanup) { + se->ops->cleanup(se->opaque); + } + } +} + +static int qemu_savevm_state(QEMUFile *f, Error **errp) +{ + int ret; + MigrationParams params = { + .blk = 0, + .shared = 0 + }; + MigrationState *ms = migrate_init(¶ms); + ms->file = f; + + if (qemu_savevm_state_blocked(errp)) { + return -EINVAL; + } + + qemu_mutex_unlock_iothread(); + qemu_savevm_state_header(f); + qemu_savevm_state_begin(f, ¶ms); + qemu_mutex_lock_iothread(); + + while (qemu_file_get_error(f) == 0) { + if (qemu_savevm_state_iterate(f, false) > 0) { + break; + } + } + + ret = qemu_file_get_error(f); + if (ret == 0) { + qemu_savevm_state_complete_precopy(f, false); + ret = qemu_file_get_error(f); + } + qemu_savevm_state_cleanup(); + if (ret != 0) { + error_setg_errno(errp, -ret, "Error while writing VM state"); + } + return ret; +} + +static int qemu_save_device_state(QEMUFile *f) +{ + SaveStateEntry *se; + + qemu_put_be32(f, QEMU_VM_FILE_MAGIC); + qemu_put_be32(f, QEMU_VM_FILE_VERSION); + + cpu_synchronize_all_states(); + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (se->is_ram) { + continue; + } + if ((!se->ops || !se->ops->save_state) && !se->vmsd) { + continue; + } + if (se->vmsd && !vmstate_save_needed(se->vmsd, se->opaque)) { + continue; + } + + save_section_header(f, se, QEMU_VM_SECTION_FULL); + + vmstate_save(f, se, NULL); + + save_section_footer(f, se); + } + + qemu_put_byte(f, QEMU_VM_EOF); + + return qemu_file_get_error(f); +} + +static SaveStateEntry *find_se(const char *idstr, int instance_id) +{ + SaveStateEntry *se; + + QTAILQ_FOREACH(se, &savevm_state.handlers, entry) { + if (!strcmp(se->idstr, idstr) && + (instance_id == se->instance_id || + instance_id == se->alias_id)) + return se; + /* Migrating from an older version? */ + if (strstr(se->idstr, idstr) && se->compat) { + if (!strcmp(se->compat->idstr, idstr) && + (instance_id == se->compat->instance_id || + instance_id == se->alias_id)) + return se; + } + } + return NULL; +} + +enum LoadVMExitCodes { + /* Allow a command to quit all layers of nested loadvm loops */ + LOADVM_QUIT = 1, +}; + +static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis); + +/* ------ incoming postcopy messages ------ */ +/* 'advise' arrives before any transfers just to tell us that a postcopy + * *might* happen - it might be skipped if precopy transferred everything + * quickly. + */ +static int loadvm_postcopy_handle_advise(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_ADVISE); + uint64_t remote_hps, remote_tps; + + trace_loadvm_postcopy_handle_advise(); + if (ps != POSTCOPY_INCOMING_NONE) { + error_report("CMD_POSTCOPY_ADVISE in wrong postcopy state (%d)", ps); + return -1; + } + + if (!postcopy_ram_supported_by_host()) { + return -1; + } + + remote_hps = qemu_get_be64(mis->from_src_file); + if (remote_hps != getpagesize()) { + /* + * Some combinations of mismatch are probably possible but it gets + * a bit more complicated. In particular we need to place whole + * host pages on the dest at once, and we need to ensure that we + * handle dirtying to make sure we never end up sending part of + * a hostpage on it's own. + */ + error_report("Postcopy needs matching host page sizes (s=%d d=%d)", + (int)remote_hps, getpagesize()); + return -1; + } + + remote_tps = qemu_get_be64(mis->from_src_file); + if (remote_tps != (1ul << qemu_target_page_bits())) { + /* + * 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()); + return -1; + } + + if (ram_postcopy_incoming_init(mis)) { + return -1; + } + + postcopy_state_set(POSTCOPY_INCOMING_ADVISE); + + return 0; +} + +/* After postcopy we will be told to throw some pages away since they're + * dirty and will have to be demand fetched. Must happen before CPU is + * started. + * There can be 0..many of these messages, each encoding multiple pages. + */ +static int loadvm_postcopy_ram_handle_discard(MigrationIncomingState *mis, + uint16_t len) +{ + int tmp; + char ramid[256]; + PostcopyState ps = postcopy_state_get(); + + trace_loadvm_postcopy_ram_handle_discard(); + + switch (ps) { + case POSTCOPY_INCOMING_ADVISE: + /* 1st discard */ + tmp = postcopy_ram_prepare_discard(mis); + if (tmp) { + return tmp; + } + break; + + case POSTCOPY_INCOMING_DISCARD: + /* Expected state */ + break; + + default: + error_report("CMD_POSTCOPY_RAM_DISCARD in wrong postcopy state (%d)", + ps); + return -1; + } + /* We're expecting a + * Version (0) + * a RAM ID string (length byte, name, 0 term) + * then at least 1 16 byte chunk + */ + if (len < (1 + 1 + 1 + 1 + 2 * 8)) { + error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); + return -1; + } + + tmp = qemu_get_byte(mis->from_src_file); + if (tmp != postcopy_ram_discard_version) { + error_report("CMD_POSTCOPY_RAM_DISCARD invalid version (%d)", tmp); + return -1; + } + + if (!qemu_get_counted_string(mis->from_src_file, ramid)) { + error_report("CMD_POSTCOPY_RAM_DISCARD Failed to read RAMBlock ID"); + return -1; + } + tmp = qemu_get_byte(mis->from_src_file); + if (tmp != 0) { + error_report("CMD_POSTCOPY_RAM_DISCARD missing nil (%d)", tmp); + return -1; + } + + len -= 3 + strlen(ramid); + if (len % 16) { + error_report("CMD_POSTCOPY_RAM_DISCARD invalid length (%d)", len); + return -1; + } + trace_loadvm_postcopy_ram_handle_discard_header(ramid, len); + while (len) { + uint64_t start_addr, block_length; + start_addr = qemu_get_be64(mis->from_src_file); + block_length = qemu_get_be64(mis->from_src_file); + + len -= 16; + int ret = ram_discard_range(mis, ramid, start_addr, + block_length); + if (ret) { + return ret; + } + } + trace_loadvm_postcopy_ram_handle_discard_end(); + + return 0; +} + +/* + * Triggered by a postcopy_listen command; this thread takes over reading + * the input stream, leaving the main thread free to carry on loading the rest + * of the device state (from RAM). + * (TODO:This could do with being in a postcopy file - but there again it's + * just another input loop, not that postcopy specific) + */ +static void *postcopy_ram_listen_thread(void *opaque) +{ + QEMUFile *f = opaque; + MigrationIncomingState *mis = migration_incoming_get_current(); + int load_res; + + qemu_sem_post(&mis->listen_thread_sem); + trace_postcopy_ram_listen_thread_start(); + + /* + * Because we're a thread and not a coroutine we can't yield + * in qemu_file, and thus we must be blocking now. + */ + qemu_file_set_blocking(f, true); + load_res = qemu_loadvm_state_main(f, mis); + /* And non-blocking again so we don't block in any cleanup */ + qemu_file_set_blocking(f, false); + + trace_postcopy_ram_listen_thread_exit(); + if (load_res < 0) { + error_report("%s: loadvm failed: %d", __func__, load_res); + qemu_file_set_error(f, load_res); + } else { + /* + * This looks good, but it's possible that the device loading in the + * main thread hasn't finished yet, and so we might not be in 'RUN' + * state yet; wait for the end of the main thread. + */ + qemu_event_wait(&mis->main_thread_load_event); + } + postcopy_ram_incoming_cleanup(mis); + /* + * If everything has worked fine, then the main thread has waited + * for us to start, and we're the last use of the mis. + * (If something broke then qemu will have to exit anyway since it's + * got a bad migration state). + */ + migration_incoming_state_destroy(); + + if (load_res < 0) { + /* + * If something went wrong then we have a bad state so exit; + * depending how far we got it might be possible at this point + * to leave the guest running and fire MCEs for pages that never + * arrived as a desperate recovery step. + */ + exit(EXIT_FAILURE); + } + + return NULL; +} + +/* After this message we must be able to immediately receive postcopy data */ +static int loadvm_postcopy_handle_listen(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_LISTENING); + trace_loadvm_postcopy_handle_listen(); + if (ps != POSTCOPY_INCOMING_ADVISE && ps != POSTCOPY_INCOMING_DISCARD) { + error_report("CMD_POSTCOPY_LISTEN in wrong postcopy state (%d)", ps); + return -1; + } + if (ps == POSTCOPY_INCOMING_ADVISE) { + /* + * A rare case, we entered listen without having to do any discards, + * so do the setup that's normally done at the time of the 1st discard. + */ + postcopy_ram_prepare_discard(mis); + } + + /* + * Sensitise RAM - can now generate requests for blocks that don't exist + * However, at this point the CPU shouldn't be running, and the IO + * shouldn't be doing anything yet so don't actually expect requests + */ + if (postcopy_ram_enable_notify(mis)) { + return -1; + } + + if (mis->have_listen_thread) { + error_report("CMD_POSTCOPY_RAM_LISTEN already has a listen thread"); + return -1; + } + + mis->have_listen_thread = true; + /* Start up the listening thread and wait for it to signal ready */ + qemu_sem_init(&mis->listen_thread_sem, 0); + qemu_thread_create(&mis->listen_thread, "postcopy/listen", + postcopy_ram_listen_thread, mis->from_src_file, + QEMU_THREAD_JOINABLE); + qemu_sem_wait(&mis->listen_thread_sem); + qemu_sem_destroy(&mis->listen_thread_sem); + + return 0; +} + +/* After all discards we can start running and asking for pages */ +static int loadvm_postcopy_handle_run(MigrationIncomingState *mis) +{ + PostcopyState ps = postcopy_state_set(POSTCOPY_INCOMING_RUNNING); + Error *local_err = NULL; + + trace_loadvm_postcopy_handle_run(); + if (ps != POSTCOPY_INCOMING_LISTENING) { + error_report("CMD_POSTCOPY_RUN in wrong postcopy state (%d)", ps); + return -1; + } + + /* TODO we should move all of this lot into postcopy_ram.c or a shared code + * in migration.c + */ + cpu_synchronize_all_post_init(); + + qemu_announce_self(); + + /* Make sure all file formats flush their mutable metadata */ + bdrv_invalidate_cache_all(&local_err); + if (local_err) { + error_report_err(local_err); + return -1; + } + + trace_loadvm_postcopy_handle_run_cpu_sync(); + cpu_synchronize_all_post_init(); + + trace_loadvm_postcopy_handle_run_vmstart(); + + if (autostart) { + /* Hold onto your hats, starting the CPU */ + vm_start(); + } else { + /* leave it paused and let management decide when to start the CPU */ + runstate_set(RUN_STATE_PAUSED); + } + + /* We need to finish reading the stream from the package + * and also stop reading anything more from the stream that loaded the + * package (since it's now being read by the listener thread). + * LOADVM_QUIT will quit all the layers of nested loadvm loops. + */ + return LOADVM_QUIT; +} + +/** + * Immediately following this command is a blob of data containing an embedded + * chunk of migration stream; read it and load it. + * + * @mis: Incoming state + * @length: Length of packaged data to read + * + * Returns: Negative values on error + * + */ +static int loadvm_handle_cmd_packaged(MigrationIncomingState *mis) +{ + int ret; + uint8_t *buffer; + uint32_t length; + QEMUSizedBuffer *qsb; + + length = qemu_get_be32(mis->from_src_file); + trace_loadvm_handle_cmd_packaged(length); + + if (length > MAX_VM_CMD_PACKAGED_SIZE) { + error_report("Unreasonably large packaged state: %u", length); + return -1; + } + buffer = g_malloc0(length); + ret = qemu_get_buffer(mis->from_src_file, buffer, (int)length); + if (ret != length) { + g_free(buffer); + error_report("CMD_PACKAGED: Buffer receive fail ret=%d length=%d\n", + ret, length); + return (ret < 0) ? ret : -EAGAIN; + } + trace_loadvm_handle_cmd_packaged_received(ret); + + /* Setup a dummy QEMUFile that actually reads from the buffer */ + qsb = qsb_create(buffer, length); + g_free(buffer); /* Because qsb_create copies */ + if (!qsb) { + error_report("Unable to create qsb"); + } + QEMUFile *packf = qemu_bufopen("r", qsb); + + ret = qemu_loadvm_state_main(packf, mis); + trace_loadvm_handle_cmd_packaged_main(ret); + qemu_fclose(packf); + qsb_free(qsb); + + return ret; +} + +/* + * Process an incoming 'QEMU_VM_COMMAND' + * 0 just a normal return + * LOADVM_QUIT All good, but exit the loop + * <0 Error + */ +static int loadvm_process_command(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + uint16_t cmd; + uint16_t len; + uint32_t tmp32; + + cmd = qemu_get_be16(f); + len = qemu_get_be16(f); + + trace_loadvm_process_command(cmd, len); + if (cmd >= MIG_CMD_MAX || cmd == MIG_CMD_INVALID) { + error_report("MIG_CMD 0x%x unknown (len 0x%x)", cmd, len); + return -EINVAL; + } + + if (mig_cmd_args[cmd].len != -1 && mig_cmd_args[cmd].len != len) { + error_report("%s received with bad length - expecting %zu, got %d", + mig_cmd_args[cmd].name, + (size_t)mig_cmd_args[cmd].len, len); + return -ERANGE; + } + + switch (cmd) { + case MIG_CMD_OPEN_RETURN_PATH: + if (mis->to_src_file) { + error_report("CMD_OPEN_RETURN_PATH called when RP already open"); + /* Not really a problem, so don't give up */ + return 0; + } + mis->to_src_file = qemu_file_get_return_path(f); + if (!mis->to_src_file) { + error_report("CMD_OPEN_RETURN_PATH failed"); + return -1; + } + break; + + case MIG_CMD_PING: + tmp32 = qemu_get_be32(f); + trace_loadvm_process_command_ping(tmp32); + if (!mis->to_src_file) { + error_report("CMD_PING (0x%x) received with no return path", + tmp32); + return -1; + } + migrate_send_rp_pong(mis, tmp32); + break; + + case MIG_CMD_PACKAGED: + return loadvm_handle_cmd_packaged(mis); + + case MIG_CMD_POSTCOPY_ADVISE: + return loadvm_postcopy_handle_advise(mis); + + case MIG_CMD_POSTCOPY_LISTEN: + return loadvm_postcopy_handle_listen(mis); + + case MIG_CMD_POSTCOPY_RUN: + return loadvm_postcopy_handle_run(mis); + + case MIG_CMD_POSTCOPY_RAM_DISCARD: + return loadvm_postcopy_ram_handle_discard(mis, len); + } + + return 0; +} + +struct LoadStateEntry { + QLIST_ENTRY(LoadStateEntry) entry; + SaveStateEntry *se; + int section_id; + int version_id; +}; + +/* + * Read a footer off the wire and check that it matches the expected section + * + * Returns: true if the footer was good + * false if there is a problem (and calls error_report to say why) + */ +static bool check_section_footer(QEMUFile *f, LoadStateEntry *le) +{ + uint8_t read_mark; + uint32_t read_section_id; + + if (skip_section_footers) { + /* No footer to check */ + return true; + } + + read_mark = qemu_get_byte(f); + + if (read_mark != QEMU_VM_SECTION_FOOTER) { + error_report("Missing section footer for %s", le->se->idstr); + return false; + } + + read_section_id = qemu_get_be32(f); + if (read_section_id != le->section_id) { + error_report("Mismatched section id in footer for %s -" + " read 0x%x expected 0x%x", + le->se->idstr, read_section_id, le->section_id); + return false; + } + + /* All good */ + return true; +} + +void loadvm_free_handlers(MigrationIncomingState *mis) +{ + LoadStateEntry *le, *new_le; + + QLIST_FOREACH_SAFE(le, &mis->loadvm_handlers, entry, new_le) { + QLIST_REMOVE(le, entry); + g_free(le); + } +} + +static int qemu_loadvm_state_main(QEMUFile *f, MigrationIncomingState *mis) +{ + uint8_t section_type; + int ret; + + while ((section_type = qemu_get_byte(f)) != QEMU_VM_EOF) { + uint32_t instance_id, version_id, section_id; + SaveStateEntry *se; + LoadStateEntry *le; + char idstr[256]; + + trace_qemu_loadvm_state_section(section_type); + switch (section_type) { + case QEMU_VM_SECTION_START: + case QEMU_VM_SECTION_FULL: + /* Read section start */ + section_id = qemu_get_be32(f); + if (!qemu_get_counted_string(f, idstr)) { + error_report("Unable to read ID string for section %u", + section_id); + return -EINVAL; + } + instance_id = qemu_get_be32(f); + version_id = qemu_get_be32(f); + + trace_qemu_loadvm_state_section_startfull(section_id, idstr, + instance_id, version_id); + /* Find savevm section */ + se = find_se(idstr, instance_id); + if (se == NULL) { + error_report("Unknown savevm section or instance '%s' %d", + idstr, instance_id); + return -EINVAL; + } + + /* Validate version */ + if (version_id > se->version_id) { + error_report("savevm: unsupported version %d for '%s' v%d", + version_id, idstr, se->version_id); + return -EINVAL; + } + + /* Add entry */ + le = g_malloc0(sizeof(*le)); + + le->se = se; + le->section_id = section_id; + le->version_id = version_id; + QLIST_INSERT_HEAD(&mis->loadvm_handlers, le, entry); + + ret = vmstate_load(f, le->se, le->version_id); + if (ret < 0) { + error_report("error while loading state for instance 0x%x of" + " device '%s'", instance_id, idstr); + return ret; + } + if (!check_section_footer(f, le)) { + return -EINVAL; + } + break; + case QEMU_VM_SECTION_PART: + case QEMU_VM_SECTION_END: + section_id = qemu_get_be32(f); + + trace_qemu_loadvm_state_section_partend(section_id); + QLIST_FOREACH(le, &mis->loadvm_handlers, entry) { + if (le->section_id == section_id) { + break; + } + } + if (le == NULL) { + error_report("Unknown savevm section %d", section_id); + return -EINVAL; + } + + ret = vmstate_load(f, le->se, le->version_id); + if (ret < 0) { + error_report("error while loading state section id %d(%s)", + section_id, le->se->idstr); + return ret; + } + if (!check_section_footer(f, le)) { + return -EINVAL; + } + break; + case QEMU_VM_COMMAND: + ret = loadvm_process_command(f); + trace_qemu_loadvm_state_section_command(ret); + if ((ret < 0) || (ret & LOADVM_QUIT)) { + return ret; + } + break; + default: + error_report("Unknown savevm section type %d", section_type); + return -EINVAL; + } + } + + return 0; +} + +int qemu_loadvm_state(QEMUFile *f) +{ + MigrationIncomingState *mis = migration_incoming_get_current(); + Error *local_err = NULL; + unsigned int v; + int ret; + + if (qemu_savevm_state_blocked(&local_err)) { + error_report_err(local_err); + return -EINVAL; + } + + v = qemu_get_be32(f); + if (v != QEMU_VM_FILE_MAGIC) { + error_report("Not a migration stream"); + return -EINVAL; + } + + v = qemu_get_be32(f); + if (v == QEMU_VM_FILE_VERSION_COMPAT) { + error_report("SaveVM v2 format is obsolete and don't work anymore"); + return -ENOTSUP; + } + if (v != QEMU_VM_FILE_VERSION) { + error_report("Unsupported migration stream version"); + return -ENOTSUP; + } + + if (!savevm_state.skip_configuration || enforce_config_section()) { + if (qemu_get_byte(f) != QEMU_VM_CONFIGURATION) { + error_report("Configuration section missing"); + return -EINVAL; + } + ret = vmstate_load_state(f, &vmstate_configuration, &savevm_state, 0); + + if (ret) { + return ret; + } + } + + ret = qemu_loadvm_state_main(f, mis); + qemu_event_set(&mis->main_thread_load_event); + + trace_qemu_loadvm_state_post_main(ret); + + if (mis->have_listen_thread) { + /* Listen thread still going, can't clean up yet */ + return ret; + } + + if (ret == 0) { + ret = qemu_file_get_error(f); + } + + /* + * Try to read in the VMDESC section as well, so that dumping tools that + * intercept our migration stream have the chance to see it. + */ + + /* We've got to be careful; if we don't read the data and just shut the fd + * then the sender can error if we close while it's still sending. + * We also mustn't read data that isn't there; some transports (RDMA) + * will stall waiting for that data when the source has already closed. + */ + if (ret == 0 && should_send_vmdesc()) { + uint8_t *buf; + uint32_t size; + uint8_t section_type = qemu_get_byte(f); + + if (section_type != QEMU_VM_VMDESCRIPTION) { + error_report("Expected vmdescription section, but got %d", + section_type); + /* + * It doesn't seem worth failing at this point since + * we apparently have an otherwise valid VM state + */ + } else { + buf = g_malloc(0x1000); + size = qemu_get_be32(f); + + while (size > 0) { + uint32_t read_chunk = MIN(size, 0x1000); + qemu_get_buffer(f, buf, read_chunk); + size -= read_chunk; + } + g_free(buf); + } + } + + cpu_synchronize_all_post_init(); + + return ret; +} + +void hmp_savevm(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs, *bs1; + QEMUSnapshotInfo sn1, *sn = &sn1, old_sn1, *old_sn = &old_sn1; + int ret; + QEMUFile *f; + int saved_vm_running; + uint64_t vm_state_size; + qemu_timeval tv; + struct tm tm; + const char *name = qdict_get_try_str(qdict, "name"); + Error *local_err = NULL; + AioContext *aio_context; + + if (!bdrv_all_can_snapshot(&bs)) { + monitor_printf(mon, "Device '%s' is writable but does not " + "support snapshots.\n", bdrv_get_device_name(bs)); + return; + } + + /* Delete old snapshots of the same name */ + if (name && bdrv_all_delete_snapshot(name, &bs1, &local_err) < 0) { + monitor_printf(mon, + "Error while deleting snapshot on device '%s': %s\n", + bdrv_get_device_name(bs1), error_get_pretty(local_err)); + error_free(local_err); + return; + } + + bs = bdrv_all_find_vmstate_bs(); + if (bs == NULL) { + monitor_printf(mon, "No block device can accept snapshots\n"); + return; + } + aio_context = bdrv_get_aio_context(bs); + + saved_vm_running = runstate_is_running(); + + ret = global_state_store(); + if (ret) { + monitor_printf(mon, "Error saving global state\n"); + return; + } + vm_stop(RUN_STATE_SAVE_VM); + + aio_context_acquire(aio_context); + + memset(sn, 0, sizeof(*sn)); + + /* fill auxiliary fields */ + qemu_gettimeofday(&tv); + sn->date_sec = tv.tv_sec; + sn->date_nsec = tv.tv_usec * 1000; + sn->vm_clock_nsec = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + if (name) { + ret = bdrv_snapshot_find(bs, old_sn, name); + if (ret >= 0) { + pstrcpy(sn->name, sizeof(sn->name), old_sn->name); + pstrcpy(sn->id_str, sizeof(sn->id_str), old_sn->id_str); + } else { + pstrcpy(sn->name, sizeof(sn->name), name); + } + } else { + /* cast below needed for OpenBSD where tv_sec is still 'long' */ + localtime_r((const time_t *)&tv.tv_sec, &tm); + strftime(sn->name, sizeof(sn->name), "vm-%Y%m%d%H%M%S", &tm); + } + + /* save the VM state */ + f = qemu_fopen_bdrv(bs, 1); + if (!f) { + monitor_printf(mon, "Could not open VM state file\n"); + goto the_end; + } + ret = qemu_savevm_state(f, &local_err); + vm_state_size = qemu_ftell(f); + qemu_fclose(f); + if (ret < 0) { + monitor_printf(mon, "%s\n", error_get_pretty(local_err)); + error_free(local_err); + goto the_end; + } + + ret = bdrv_all_create_snapshot(sn, bs, vm_state_size, &bs); + if (ret < 0) { + monitor_printf(mon, "Error while creating snapshot on '%s'\n", + bdrv_get_device_name(bs)); + } + + the_end: + aio_context_release(aio_context); + if (saved_vm_running) { + vm_start(); + } +} + +void qmp_xen_save_devices_state(const char *filename, Error **errp) +{ + QEMUFile *f; + int saved_vm_running; + int ret; + + saved_vm_running = runstate_is_running(); + vm_stop(RUN_STATE_SAVE_VM); + global_state_store_running(); + + f = qemu_fopen(filename, "wb"); + if (!f) { + error_setg_file_open(errp, errno, filename); + goto the_end; + } + ret = qemu_save_device_state(f); + qemu_fclose(f); + if (ret < 0) { + error_setg(errp, QERR_IO_ERROR); + } + + the_end: + if (saved_vm_running) { + vm_start(); + } +} + +int load_vmstate(const char *name) +{ + BlockDriverState *bs, *bs_vm_state; + QEMUSnapshotInfo sn; + QEMUFile *f; + int ret; + AioContext *aio_context; + + if (!bdrv_all_can_snapshot(&bs)) { + error_report("Device '%s' is writable but does not support snapshots.", + bdrv_get_device_name(bs)); + return -ENOTSUP; + } + ret = bdrv_all_find_snapshot(name, &bs); + if (ret < 0) { + error_report("Device '%s' does not have the requested snapshot '%s'", + bdrv_get_device_name(bs), name); + return ret; + } + + bs_vm_state = bdrv_all_find_vmstate_bs(); + if (!bs_vm_state) { + error_report("No block device supports snapshots"); + return -ENOTSUP; + } + aio_context = bdrv_get_aio_context(bs_vm_state); + + /* Don't even try to load empty VM states */ + aio_context_acquire(aio_context); + ret = bdrv_snapshot_find(bs_vm_state, &sn, name); + aio_context_release(aio_context); + if (ret < 0) { + return ret; + } else if (sn.vm_state_size == 0) { + error_report("This is a disk-only snapshot. Revert to it offline " + "using qemu-img."); + return -EINVAL; + } + + /* Flush all IO requests so they don't interfere with the new state. */ + bdrv_drain_all(); + + ret = bdrv_all_goto_snapshot(name, &bs); + if (ret < 0) { + error_report("Error %d while activating snapshot '%s' on '%s'", + ret, name, bdrv_get_device_name(bs)); + return ret; + } + + /* restore the VM state */ + f = qemu_fopen_bdrv(bs_vm_state, 0); + if (!f) { + error_report("Could not open VM state file"); + return -EINVAL; + } + + qemu_system_reset(VMRESET_SILENT); + migration_incoming_state_new(f); + + aio_context_acquire(aio_context); + ret = qemu_loadvm_state(f); + qemu_fclose(f); + aio_context_release(aio_context); + + migration_incoming_state_destroy(); + if (ret < 0) { + error_report("Error %d while loading VM state", ret); + return ret; + } + + return 0; +} + +void hmp_delvm(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs; + Error *err; + const char *name = qdict_get_str(qdict, "name"); + + if (bdrv_all_delete_snapshot(name, &bs, &err) < 0) { + monitor_printf(mon, + "Error while deleting snapshot on device '%s': %s\n", + bdrv_get_device_name(bs), error_get_pretty(err)); + error_free(err); + } +} + +void hmp_info_snapshots(Monitor *mon, const QDict *qdict) +{ + BlockDriverState *bs, *bs1; + QEMUSnapshotInfo *sn_tab, *sn; + int nb_sns, i; + int total; + int *available_snapshots; + AioContext *aio_context; + + bs = bdrv_all_find_vmstate_bs(); + if (!bs) { + monitor_printf(mon, "No available block device supports snapshots\n"); + return; + } + aio_context = bdrv_get_aio_context(bs); + + aio_context_acquire(aio_context); + nb_sns = bdrv_snapshot_list(bs, &sn_tab); + aio_context_release(aio_context); + + if (nb_sns < 0) { + monitor_printf(mon, "bdrv_snapshot_list: error %d\n", nb_sns); + return; + } + + if (nb_sns == 0) { + monitor_printf(mon, "There is no snapshot available.\n"); + return; + } + + available_snapshots = g_new0(int, nb_sns); + total = 0; + for (i = 0; i < nb_sns; i++) { + if (bdrv_all_find_snapshot(sn_tab[i].id_str, &bs1) == 0) { + available_snapshots[total] = i; + total++; + } + } + + if (total > 0) { + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, NULL); + monitor_printf(mon, "\n"); + for (i = 0; i < total; i++) { + sn = &sn_tab[available_snapshots[i]]; + bdrv_snapshot_dump((fprintf_function)monitor_printf, mon, sn); + monitor_printf(mon, "\n"); + } + } else { + monitor_printf(mon, "There is no suitable snapshot available\n"); + } + + g_free(sn_tab); + g_free(available_snapshots); + +} + +void vmstate_register_ram(MemoryRegion *mr, DeviceState *dev) +{ + qemu_ram_set_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK, + memory_region_name(mr), dev); +} + +void vmstate_unregister_ram(MemoryRegion *mr, DeviceState *dev) +{ + qemu_ram_unset_idstr(memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK); +} + +void vmstate_register_ram_global(MemoryRegion *mr) +{ + vmstate_register_ram(mr, NULL); +} diff --git a/src/migration/tcp.c b/src/migration/tcp.c new file mode 100644 index 0000000..ae89172 --- /dev/null +++ b/src/migration/tcp.c @@ -0,0 +1,103 @@ +/* + * QEMU live migration + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include <string.h> + +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/sockets.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "block/block.h" +#include "qemu/main-loop.h" + +//#define DEBUG_MIGRATION_TCP + +#ifdef DEBUG_MIGRATION_TCP +#define DPRINTF(fmt, ...) \ + do { printf("migration-tcp: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static void tcp_wait_for_connect(int fd, Error *err, void *opaque) +{ + MigrationState *s = opaque; + + if (fd < 0) { + DPRINTF("migrate connect error: %s\n", error_get_pretty(err)); + s->file = NULL; + migrate_fd_error(s); + } else { + DPRINTF("migrate connect success\n"); + s->file = qemu_fopen_socket(fd, "wb"); + migrate_fd_connect(s); + } +} + +void tcp_start_outgoing_migration(MigrationState *s, const char *host_port, Error **errp) +{ + inet_nonblocking_connect(host_port, tcp_wait_for_connect, s, errp); +} + +static void tcp_accept_incoming_migration(void *opaque) +{ + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + int s = (intptr_t)opaque; + QEMUFile *f; + int c, err; + + do { + c = qemu_accept(s, (struct sockaddr *)&addr, &addrlen); + err = socket_error(); + } while (c < 0 && err == EINTR); + qemu_set_fd_handler(s, NULL, NULL, NULL); + closesocket(s); + + DPRINTF("accepted migration\n"); + + if (c < 0) { + error_report("could not accept migration connection (%s)", + strerror(err)); + return; + } + + f = qemu_fopen_socket(c, "rb"); + if (f == NULL) { + error_report("could not qemu_fopen socket"); + goto out; + } + + process_incoming_migration(f); + return; + +out: + closesocket(c); +} + +void tcp_start_incoming_migration(const char *host_port, Error **errp) +{ + int s; + + s = inet_listen(host_port, NULL, 256, SOCK_STREAM, 0, errp); + if (s < 0) { + return; + } + + qemu_set_fd_handler(s, tcp_accept_incoming_migration, NULL, + (void *)(intptr_t)s); +} diff --git a/src/migration/unix.c b/src/migration/unix.c new file mode 100644 index 0000000..b591813 --- /dev/null +++ b/src/migration/unix.c @@ -0,0 +1,103 @@ +/* + * QEMU live migration via Unix Domain Sockets + * + * Copyright Red Hat, Inc. 2009 + * + * Authors: + * Chris Lalancette <clalance@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include <string.h> + +#include "qemu-common.h" +#include "qemu/error-report.h" +#include "qemu/sockets.h" +#include "qemu/main-loop.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "block/block.h" + +//#define DEBUG_MIGRATION_UNIX + +#ifdef DEBUG_MIGRATION_UNIX +#define DPRINTF(fmt, ...) \ + do { printf("migration-unix: " fmt, ## __VA_ARGS__); } while (0) +#else +#define DPRINTF(fmt, ...) \ + do { } while (0) +#endif + +static void unix_wait_for_connect(int fd, Error *err, void *opaque) +{ + MigrationState *s = opaque; + + if (fd < 0) { + DPRINTF("migrate connect error: %s\n", error_get_pretty(err)); + s->file = NULL; + migrate_fd_error(s); + } else { + DPRINTF("migrate connect success\n"); + s->file = qemu_fopen_socket(fd, "wb"); + migrate_fd_connect(s); + } +} + +void unix_start_outgoing_migration(MigrationState *s, const char *path, Error **errp) +{ + unix_nonblocking_connect(path, unix_wait_for_connect, s, errp); +} + +static void unix_accept_incoming_migration(void *opaque) +{ + struct sockaddr_un addr; + socklen_t addrlen = sizeof(addr); + int s = (intptr_t)opaque; + QEMUFile *f; + int c, err; + + do { + c = qemu_accept(s, (struct sockaddr *)&addr, &addrlen); + err = errno; + } while (c < 0 && err == EINTR); + qemu_set_fd_handler(s, NULL, NULL, NULL); + close(s); + + DPRINTF("accepted migration\n"); + + if (c < 0) { + error_report("could not accept migration connection (%s)", + strerror(err)); + return; + } + + f = qemu_fopen_socket(c, "rb"); + if (f == NULL) { + error_report("could not qemu_fopen socket"); + goto out; + } + + process_incoming_migration(f); + return; + +out: + close(c); +} + +void unix_start_incoming_migration(const char *path, Error **errp) +{ + int s; + + s = unix_listen(path, NULL, 0, errp); + if (s < 0) { + return; + } + + qemu_set_fd_handler(s, unix_accept_incoming_migration, NULL, + (void *)(intptr_t)s); +} diff --git a/src/migration/vmstate.c b/src/migration/vmstate.c new file mode 100644 index 0000000..e8ccf22 --- /dev/null +++ b/src/migration/vmstate.c @@ -0,0 +1,890 @@ +#include "qemu-common.h" +#include "migration/migration.h" +#include "migration/qemu-file.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "trace.h" +#include "qjson.h" + +static void vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque, QJSON *vmdesc); +static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque); + +static int vmstate_n_elems(void *opaque, VMStateField *field) +{ + int n_elems = 1; + + if (field->flags & VMS_ARRAY) { + n_elems = field->num; + } else if (field->flags & VMS_VARRAY_INT32) { + n_elems = *(int32_t *)(opaque+field->num_offset); + } else if (field->flags & VMS_VARRAY_UINT32) { + n_elems = *(uint32_t *)(opaque+field->num_offset); + } else if (field->flags & VMS_VARRAY_UINT16) { + n_elems = *(uint16_t *)(opaque+field->num_offset); + } else if (field->flags & VMS_VARRAY_UINT8) { + n_elems = *(uint8_t *)(opaque+field->num_offset); + } + + return n_elems; +} + +static int vmstate_size(void *opaque, VMStateField *field) +{ + int size = field->size; + + if (field->flags & VMS_VBUFFER) { + size = *(int32_t *)(opaque+field->size_offset); + if (field->flags & VMS_MULTIPLY) { + size *= field->size; + } + } + + return size; +} + +static void *vmstate_base_addr(void *opaque, VMStateField *field, bool alloc) +{ + void *base_addr = opaque + field->offset; + + if (field->flags & VMS_POINTER) { + if (alloc && (field->flags & VMS_ALLOC)) { + gsize size = 0; + if (field->flags & VMS_VBUFFER) { + size = vmstate_size(opaque, field); + } else { + int n_elems = vmstate_n_elems(opaque, field); + if (n_elems) { + size = n_elems * field->size; + } + } + if (size) { + *((void **)base_addr + field->start) = g_malloc(size); + } + } + base_addr = *(void **)base_addr + field->start; + } + + return base_addr; +} + +int vmstate_load_state(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque, int version_id) +{ + VMStateField *field = vmsd->fields; + int ret = 0; + + trace_vmstate_load_state(vmsd->name, version_id); + if (version_id > vmsd->version_id) { + trace_vmstate_load_state_end(vmsd->name, "too new", -EINVAL); + return -EINVAL; + } + if (version_id < vmsd->minimum_version_id) { + if (vmsd->load_state_old && + version_id >= vmsd->minimum_version_id_old) { + ret = vmsd->load_state_old(f, opaque, version_id); + trace_vmstate_load_state_end(vmsd->name, "old path", ret); + return ret; + } + trace_vmstate_load_state_end(vmsd->name, "too old", -EINVAL); + return -EINVAL; + } + if (vmsd->pre_load) { + int ret = vmsd->pre_load(opaque); + if (ret) { + return ret; + } + } + while (field->name) { + trace_vmstate_load_state_field(vmsd->name, field->name); + if ((field->field_exists && + field->field_exists(opaque, version_id)) || + (!field->field_exists && + field->version_id <= version_id)) { + void *base_addr = vmstate_base_addr(opaque, field, true); + int i, n_elems = vmstate_n_elems(opaque, field); + int size = vmstate_size(opaque, field); + + for (i = 0; i < n_elems; i++) { + void *addr = base_addr + size * i; + + if (field->flags & VMS_ARRAY_OF_POINTER) { + addr = *(void **)addr; + } + if (field->flags & VMS_STRUCT) { + ret = vmstate_load_state(f, field->vmsd, addr, + field->vmsd->version_id); + } else { + ret = field->info->get(f, addr, size); + + } + if (ret >= 0) { + ret = qemu_file_get_error(f); + } + if (ret < 0) { + qemu_file_set_error(f, ret); + trace_vmstate_load_field_error(field->name, ret); + return ret; + } + } + } else if (field->flags & VMS_MUST_EXIST) { + error_report("Input validation failed: %s/%s", + vmsd->name, field->name); + return -1; + } + field++; + } + ret = vmstate_subsection_load(f, vmsd, opaque); + if (ret != 0) { + return ret; + } + if (vmsd->post_load) { + ret = vmsd->post_load(opaque, version_id); + } + trace_vmstate_load_state_end(vmsd->name, "end", ret); + return ret; +} + +static int vmfield_name_num(VMStateField *start, VMStateField *search) +{ + VMStateField *field; + int found = 0; + + for (field = start; field->name; field++) { + if (!strcmp(field->name, search->name)) { + if (field == search) { + return found; + } + found++; + } + } + + return -1; +} + +static bool vmfield_name_is_unique(VMStateField *start, VMStateField *search) +{ + VMStateField *field; + int found = 0; + + for (field = start; field->name; field++) { + if (!strcmp(field->name, search->name)) { + found++; + /* name found more than once, so it's not unique */ + if (found > 1) { + return false; + } + } + } + + return true; +} + +static const char *vmfield_get_type_name(VMStateField *field) +{ + const char *type = "unknown"; + + if (field->flags & VMS_STRUCT) { + type = "struct"; + } else if (field->info->name) { + type = field->info->name; + } + + return type; +} + +static bool vmsd_can_compress(VMStateField *field) +{ + if (field->field_exists) { + /* Dynamically existing fields mess up compression */ + return false; + } + + if (field->flags & VMS_STRUCT) { + VMStateField *sfield = field->vmsd->fields; + while (sfield->name) { + if (!vmsd_can_compress(sfield)) { + /* Child elements can't compress, so can't we */ + return false; + } + sfield++; + } + + if (field->vmsd->subsections) { + /* Subsections may come and go, better don't compress */ + return false; + } + } + + return true; +} + +static void vmsd_desc_field_start(const VMStateDescription *vmsd, QJSON *vmdesc, + VMStateField *field, int i, int max) +{ + char *name, *old_name; + bool is_array = max > 1; + bool can_compress = vmsd_can_compress(field); + + if (!vmdesc) { + return; + } + + name = g_strdup(field->name); + + /* Field name is not unique, need to make it unique */ + if (!vmfield_name_is_unique(vmsd->fields, field)) { + int num = vmfield_name_num(vmsd->fields, field); + old_name = name; + name = g_strdup_printf("%s[%d]", name, num); + g_free(old_name); + } + + json_start_object(vmdesc, NULL); + json_prop_str(vmdesc, "name", name); + if (is_array) { + if (can_compress) { + json_prop_int(vmdesc, "array_len", max); + } else { + json_prop_int(vmdesc, "index", i); + } + } + json_prop_str(vmdesc, "type", vmfield_get_type_name(field)); + + if (field->flags & VMS_STRUCT) { + json_start_object(vmdesc, "struct"); + } + + g_free(name); +} + +static void vmsd_desc_field_end(const VMStateDescription *vmsd, QJSON *vmdesc, + VMStateField *field, size_t size, int i) +{ + if (!vmdesc) { + return; + } + + if (field->flags & VMS_STRUCT) { + /* We printed a struct in between, close its child object */ + json_end_object(vmdesc); + } + + json_prop_int(vmdesc, "size", size); + json_end_object(vmdesc); +} + + +bool vmstate_save_needed(const VMStateDescription *vmsd, void *opaque) +{ + if (vmsd->needed && !vmsd->needed(opaque)) { + /* optional section not needed */ + return false; + } + return true; +} + + +void vmstate_save_state(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque, QJSON *vmdesc) +{ + VMStateField *field = vmsd->fields; + + if (vmsd->pre_save) { + vmsd->pre_save(opaque); + } + + if (vmdesc) { + json_prop_str(vmdesc, "vmsd_name", vmsd->name); + json_prop_int(vmdesc, "version", vmsd->version_id); + json_start_array(vmdesc, "fields"); + } + + while (field->name) { + if (!field->field_exists || + field->field_exists(opaque, vmsd->version_id)) { + void *base_addr = vmstate_base_addr(opaque, field, false); + int i, n_elems = vmstate_n_elems(opaque, field); + int size = vmstate_size(opaque, field); + int64_t old_offset, written_bytes; + QJSON *vmdesc_loop = vmdesc; + + for (i = 0; i < n_elems; i++) { + void *addr = base_addr + size * i; + + vmsd_desc_field_start(vmsd, vmdesc_loop, field, i, n_elems); + old_offset = qemu_ftell_fast(f); + + if (field->flags & VMS_ARRAY_OF_POINTER) { + addr = *(void **)addr; + } + if (field->flags & VMS_STRUCT) { + vmstate_save_state(f, field->vmsd, addr, vmdesc_loop); + } else { + field->info->put(f, addr, size); + } + + written_bytes = qemu_ftell_fast(f) - old_offset; + vmsd_desc_field_end(vmsd, vmdesc_loop, field, written_bytes, i); + + /* Compressed arrays only care about the first element */ + if (vmdesc_loop && vmsd_can_compress(field)) { + vmdesc_loop = NULL; + } + } + } else { + if (field->flags & VMS_MUST_EXIST) { + error_report("Output state validation failed: %s/%s", + vmsd->name, field->name); + assert(!(field->flags & VMS_MUST_EXIST)); + } + } + field++; + } + + if (vmdesc) { + json_end_array(vmdesc); + } + + vmstate_subsection_save(f, vmsd, opaque, vmdesc); +} + +static const VMStateDescription * +vmstate_get_subsection(const VMStateDescription **sub, char *idstr) +{ + while (sub && *sub && (*sub)->needed) { + if (strcmp(idstr, (*sub)->name) == 0) { + return *sub; + } + sub++; + } + return NULL; +} + +static int vmstate_subsection_load(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque) +{ + trace_vmstate_subsection_load(vmsd->name); + + while (qemu_peek_byte(f, 0) == QEMU_VM_SUBSECTION) { + char idstr[256], *idstr_ret; + int ret; + uint8_t version_id, len, size; + const VMStateDescription *sub_vmsd; + + len = qemu_peek_byte(f, 1); + if (len < strlen(vmsd->name) + 1) { + /* subsection name has be be "section_name/a" */ + trace_vmstate_subsection_load_bad(vmsd->name, "(short)"); + return 0; + } + size = qemu_peek_buffer(f, (uint8_t **)&idstr_ret, len, 2); + if (size != len) { + trace_vmstate_subsection_load_bad(vmsd->name, "(peek fail)"); + return 0; + } + memcpy(idstr, idstr_ret, size); + idstr[size] = 0; + + if (strncmp(vmsd->name, idstr, strlen(vmsd->name)) != 0) { + trace_vmstate_subsection_load_bad(vmsd->name, idstr); + /* it don't have a valid subsection name */ + return 0; + } + sub_vmsd = vmstate_get_subsection(vmsd->subsections, idstr); + if (sub_vmsd == NULL) { + trace_vmstate_subsection_load_bad(vmsd->name, "(lookup)"); + return -ENOENT; + } + qemu_file_skip(f, 1); /* subsection */ + qemu_file_skip(f, 1); /* len */ + qemu_file_skip(f, len); /* idstr */ + version_id = qemu_get_be32(f); + + ret = vmstate_load_state(f, sub_vmsd, opaque, version_id); + if (ret) { + trace_vmstate_subsection_load_bad(vmsd->name, "(child)"); + return ret; + } + } + + trace_vmstate_subsection_load_good(vmsd->name); + return 0; +} + +static void vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, + void *opaque, QJSON *vmdesc) +{ + const VMStateDescription **sub = vmsd->subsections; + bool subsection_found = false; + + while (sub && *sub && (*sub)->needed) { + if ((*sub)->needed(opaque)) { + const VMStateDescription *vmsd = *sub; + uint8_t len; + + if (vmdesc) { + /* Only create subsection array when we have any */ + if (!subsection_found) { + json_start_array(vmdesc, "subsections"); + subsection_found = true; + } + + json_start_object(vmdesc, NULL); + } + + qemu_put_byte(f, QEMU_VM_SUBSECTION); + len = strlen(vmsd->name); + qemu_put_byte(f, len); + qemu_put_buffer(f, (uint8_t *)vmsd->name, len); + qemu_put_be32(f, vmsd->version_id); + vmstate_save_state(f, vmsd, opaque, vmdesc); + + if (vmdesc) { + json_end_object(vmdesc); + } + } + sub++; + } + + if (vmdesc && subsection_found) { + json_end_array(vmdesc); + } +} + +/* bool */ + +static int get_bool(QEMUFile *f, void *pv, size_t size) +{ + bool *v = pv; + *v = qemu_get_byte(f); + return 0; +} + +static void put_bool(QEMUFile *f, void *pv, size_t size) +{ + bool *v = pv; + qemu_put_byte(f, *v); +} + +const VMStateInfo vmstate_info_bool = { + .name = "bool", + .get = get_bool, + .put = put_bool, +}; + +/* 8 bit int */ + +static int get_int8(QEMUFile *f, void *pv, size_t size) +{ + int8_t *v = pv; + qemu_get_s8s(f, v); + return 0; +} + +static void put_int8(QEMUFile *f, void *pv, size_t size) +{ + int8_t *v = pv; + qemu_put_s8s(f, v); +} + +const VMStateInfo vmstate_info_int8 = { + .name = "int8", + .get = get_int8, + .put = put_int8, +}; + +/* 16 bit int */ + +static int get_int16(QEMUFile *f, void *pv, size_t size) +{ + int16_t *v = pv; + qemu_get_sbe16s(f, v); + return 0; +} + +static void put_int16(QEMUFile *f, void *pv, size_t size) +{ + int16_t *v = pv; + qemu_put_sbe16s(f, v); +} + +const VMStateInfo vmstate_info_int16 = { + .name = "int16", + .get = get_int16, + .put = put_int16, +}; + +/* 32 bit int */ + +static int get_int32(QEMUFile *f, void *pv, size_t size) +{ + int32_t *v = pv; + qemu_get_sbe32s(f, v); + return 0; +} + +static void put_int32(QEMUFile *f, void *pv, size_t size) +{ + int32_t *v = pv; + qemu_put_sbe32s(f, v); +} + +const VMStateInfo vmstate_info_int32 = { + .name = "int32", + .get = get_int32, + .put = put_int32, +}; + +/* 32 bit int. See that the received value is the same than the one + in the field */ + +static int get_int32_equal(QEMUFile *f, void *pv, size_t size) +{ + int32_t *v = pv; + int32_t v2; + qemu_get_sbe32s(f, &v2); + + if (*v == v2) { + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_int32_equal = { + .name = "int32 equal", + .get = get_int32_equal, + .put = put_int32, +}; + +/* 32 bit int. Check that the received value is non-negative + * and less than or equal to the one in the field. + */ + +static int get_int32_le(QEMUFile *f, void *pv, size_t size) +{ + int32_t *cur = pv; + int32_t loaded; + qemu_get_sbe32s(f, &loaded); + + if (loaded >= 0 && loaded <= *cur) { + *cur = loaded; + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_int32_le = { + .name = "int32 le", + .get = get_int32_le, + .put = put_int32, +}; + +/* 64 bit int */ + +static int get_int64(QEMUFile *f, void *pv, size_t size) +{ + int64_t *v = pv; + qemu_get_sbe64s(f, v); + return 0; +} + +static void put_int64(QEMUFile *f, void *pv, size_t size) +{ + int64_t *v = pv; + qemu_put_sbe64s(f, v); +} + +const VMStateInfo vmstate_info_int64 = { + .name = "int64", + .get = get_int64, + .put = put_int64, +}; + +/* 8 bit unsigned int */ + +static int get_uint8(QEMUFile *f, void *pv, size_t size) +{ + uint8_t *v = pv; + qemu_get_8s(f, v); + return 0; +} + +static void put_uint8(QEMUFile *f, void *pv, size_t size) +{ + uint8_t *v = pv; + qemu_put_8s(f, v); +} + +const VMStateInfo vmstate_info_uint8 = { + .name = "uint8", + .get = get_uint8, + .put = put_uint8, +}; + +/* 16 bit unsigned int */ + +static int get_uint16(QEMUFile *f, void *pv, size_t size) +{ + uint16_t *v = pv; + qemu_get_be16s(f, v); + return 0; +} + +static void put_uint16(QEMUFile *f, void *pv, size_t size) +{ + uint16_t *v = pv; + qemu_put_be16s(f, v); +} + +const VMStateInfo vmstate_info_uint16 = { + .name = "uint16", + .get = get_uint16, + .put = put_uint16, +}; + +/* 32 bit unsigned int */ + +static int get_uint32(QEMUFile *f, void *pv, size_t size) +{ + uint32_t *v = pv; + qemu_get_be32s(f, v); + return 0; +} + +static void put_uint32(QEMUFile *f, void *pv, size_t size) +{ + uint32_t *v = pv; + qemu_put_be32s(f, v); +} + +const VMStateInfo vmstate_info_uint32 = { + .name = "uint32", + .get = get_uint32, + .put = put_uint32, +}; + +/* 32 bit uint. See that the received value is the same than the one + in the field */ + +static int get_uint32_equal(QEMUFile *f, void *pv, size_t size) +{ + uint32_t *v = pv; + uint32_t v2; + qemu_get_be32s(f, &v2); + + if (*v == v2) { + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_uint32_equal = { + .name = "uint32 equal", + .get = get_uint32_equal, + .put = put_uint32, +}; + +/* 64 bit unsigned int */ + +static int get_uint64(QEMUFile *f, void *pv, size_t size) +{ + uint64_t *v = pv; + qemu_get_be64s(f, v); + return 0; +} + +static void put_uint64(QEMUFile *f, void *pv, size_t size) +{ + uint64_t *v = pv; + qemu_put_be64s(f, v); +} + +const VMStateInfo vmstate_info_uint64 = { + .name = "uint64", + .get = get_uint64, + .put = put_uint64, +}; + +/* 64 bit unsigned int. See that the received value is the same than the one + in the field */ + +static int get_uint64_equal(QEMUFile *f, void *pv, size_t size) +{ + uint64_t *v = pv; + uint64_t v2; + qemu_get_be64s(f, &v2); + + if (*v == v2) { + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_uint64_equal = { + .name = "int64 equal", + .get = get_uint64_equal, + .put = put_uint64, +}; + +/* 8 bit int. See that the received value is the same than the one + in the field */ + +static int get_uint8_equal(QEMUFile *f, void *pv, size_t size) +{ + uint8_t *v = pv; + uint8_t v2; + qemu_get_8s(f, &v2); + + if (*v == v2) { + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_uint8_equal = { + .name = "uint8 equal", + .get = get_uint8_equal, + .put = put_uint8, +}; + +/* 16 bit unsigned int int. See that the received value is the same than the one + in the field */ + +static int get_uint16_equal(QEMUFile *f, void *pv, size_t size) +{ + uint16_t *v = pv; + uint16_t v2; + qemu_get_be16s(f, &v2); + + if (*v == v2) { + return 0; + } + return -EINVAL; +} + +const VMStateInfo vmstate_info_uint16_equal = { + .name = "uint16 equal", + .get = get_uint16_equal, + .put = put_uint16, +}; + +/* floating point */ + +static int get_float64(QEMUFile *f, void *pv, size_t size) +{ + float64 *v = pv; + + *v = make_float64(qemu_get_be64(f)); + return 0; +} + +static void put_float64(QEMUFile *f, void *pv, size_t size) +{ + uint64_t *v = pv; + + qemu_put_be64(f, float64_val(*v)); +} + +const VMStateInfo vmstate_info_float64 = { + .name = "float64", + .get = get_float64, + .put = put_float64, +}; + +/* uint8_t buffers */ + +static int get_buffer(QEMUFile *f, void *pv, size_t size) +{ + uint8_t *v = pv; + qemu_get_buffer(f, v, size); + return 0; +} + +static void put_buffer(QEMUFile *f, void *pv, size_t size) +{ + uint8_t *v = pv; + qemu_put_buffer(f, v, size); +} + +const VMStateInfo vmstate_info_buffer = { + .name = "buffer", + .get = get_buffer, + .put = put_buffer, +}; + +/* unused buffers: space that was used for some fields that are + not useful anymore */ + +static int get_unused_buffer(QEMUFile *f, void *pv, size_t size) +{ + uint8_t buf[1024]; + int block_len; + + while (size > 0) { + block_len = MIN(sizeof(buf), size); + size -= block_len; + qemu_get_buffer(f, buf, block_len); + } + return 0; +} + +static void put_unused_buffer(QEMUFile *f, void *pv, size_t size) +{ + static const uint8_t buf[1024]; + int block_len; + + while (size > 0) { + block_len = MIN(sizeof(buf), size); + size -= block_len; + qemu_put_buffer(f, buf, block_len); + } +} + +const VMStateInfo vmstate_info_unused_buffer = { + .name = "unused_buffer", + .get = get_unused_buffer, + .put = put_unused_buffer, +}; + +/* bitmaps (as defined by bitmap.h). Note that size here is the size + * of the bitmap in bits. The on-the-wire format of a bitmap is 64 + * bit words with the bits in big endian order. The in-memory format + * is an array of 'unsigned long', which may be either 32 or 64 bits. + */ +/* This is the number of 64 bit words sent over the wire */ +#define BITS_TO_U64S(nr) DIV_ROUND_UP(nr, 64) +static int get_bitmap(QEMUFile *f, void *pv, size_t size) +{ + unsigned long *bmp = pv; + int i, idx = 0; + for (i = 0; i < BITS_TO_U64S(size); i++) { + uint64_t w = qemu_get_be64(f); + bmp[idx++] = w; + if (sizeof(unsigned long) == 4 && idx < BITS_TO_LONGS(size)) { + bmp[idx++] = w >> 32; + } + } + return 0; +} + +static void put_bitmap(QEMUFile *f, void *pv, size_t size) +{ + unsigned long *bmp = pv; + int i, idx = 0; + for (i = 0; i < BITS_TO_U64S(size); i++) { + uint64_t w = bmp[idx++]; + if (sizeof(unsigned long) == 4 && idx < BITS_TO_LONGS(size)) { + w |= ((uint64_t)bmp[idx++]) << 32; + } + qemu_put_be64(f, w); + } +} + +const VMStateInfo vmstate_info_bitmap = { + .name = "bitmap", + .get = get_bitmap, + .put = put_bitmap, +}; diff --git a/src/migration/xbzrle.c b/src/migration/xbzrle.c new file mode 100644 index 0000000..8e220bf --- /dev/null +++ b/src/migration/xbzrle.c @@ -0,0 +1,175 @@ +/* + * Xor Based Zero Run Length Encoding + * + * Copyright 2013 Red Hat, Inc. and/or its affiliates + * + * Authors: + * Orit Wasserman <owasserm@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ +#include "qemu-common.h" +#include "include/migration/migration.h" + +/* + page = zrun nzrun + | zrun nzrun page + + zrun = length + + nzrun = length byte... + + length = uleb128 encoded integer + */ +int xbzrle_encode_buffer(uint8_t *old_buf, uint8_t *new_buf, int slen, + uint8_t *dst, int dlen) +{ + uint32_t zrun_len = 0, nzrun_len = 0; + int d = 0, i = 0; + long res; + uint8_t *nzrun_start = NULL; + + g_assert(!(((uintptr_t)old_buf | (uintptr_t)new_buf | slen) % + sizeof(long))); + + while (i < slen) { + /* overflow */ + if (d + 2 > dlen) { + return -1; + } + + /* not aligned to sizeof(long) */ + res = (slen - i) % sizeof(long); + while (res && old_buf[i] == new_buf[i]) { + zrun_len++; + i++; + res--; + } + + /* word at a time for speed */ + if (!res) { + while (i < slen && + (*(long *)(old_buf + i)) == (*(long *)(new_buf + i))) { + i += sizeof(long); + zrun_len += sizeof(long); + } + + /* go over the rest */ + while (i < slen && old_buf[i] == new_buf[i]) { + zrun_len++; + i++; + } + } + + /* buffer unchanged */ + if (zrun_len == slen) { + return 0; + } + + /* skip last zero run */ + if (i == slen) { + return d; + } + + d += uleb128_encode_small(dst + d, zrun_len); + + zrun_len = 0; + nzrun_start = new_buf + i; + + /* overflow */ + if (d + 2 > dlen) { + return -1; + } + /* not aligned to sizeof(long) */ + res = (slen - i) % sizeof(long); + while (res && old_buf[i] != new_buf[i]) { + i++; + nzrun_len++; + res--; + } + + /* word at a time for speed, use of 32-bit long okay */ + if (!res) { + /* truncation to 32-bit long okay */ + unsigned long mask = (unsigned long)0x0101010101010101ULL; + while (i < slen) { + unsigned long xor; + xor = *(unsigned long *)(old_buf + i) + ^ *(unsigned long *)(new_buf + i); + if ((xor - mask) & ~xor & (mask << 7)) { + /* found the end of an nzrun within the current long */ + while (old_buf[i] != new_buf[i]) { + nzrun_len++; + i++; + } + break; + } else { + i += sizeof(long); + nzrun_len += sizeof(long); + } + } + } + + d += uleb128_encode_small(dst + d, nzrun_len); + /* overflow */ + if (d + nzrun_len > dlen) { + return -1; + } + memcpy(dst + d, nzrun_start, nzrun_len); + d += nzrun_len; + nzrun_len = 0; + } + + return d; +} + +int xbzrle_decode_buffer(uint8_t *src, int slen, uint8_t *dst, int dlen) +{ + int i = 0, d = 0; + int ret; + uint32_t count = 0; + + while (i < slen) { + + /* zrun */ + if ((slen - i) < 2) { + return -1; + } + + ret = uleb128_decode_small(src + i, &count); + if (ret < 0 || (i && !count)) { + return -1; + } + i += ret; + d += count; + + /* overflow */ + if (d > dlen) { + return -1; + } + + /* nzrun */ + if ((slen - i) < 2) { + return -1; + } + + ret = uleb128_decode_small(src + i, &count); + if (ret < 0 || !count) { + return -1; + } + i += ret; + + /* overflow */ + if (d + count > dlen || i + count > slen) { + return -1; + } + + memcpy(dst + d, src + i, count); + d += count; + i += count; + } + + return d; +} |