* Peter Xu (pet...@redhat.com) wrote:
> Introducing new return path message MIG_RP_MSG_RECV_BITMAP to send
> received bitmap of ramblock back to source.
>
> This is the reply message of MIG_CMD_RECV_BITMAP, it contains not only
> the header (including the ramblock name), and it was appended with the
> whole ramblock received bitmap on the destination side.
>
> When the source receives such a reply message (MIG_RP_MSG_RECV_BITMAP),
> it parses it, convert it to the dirty bitmap by inverting the bits.
>
> One thing to mention is that, when we send the recv bitmap, we are doing
> these things in extra:
>
> - converting the bitmap to little endian, to support when hosts are
> using different endianess on src/dst.
>
> - do proper alignment for 8 bytes, to support when hosts are using
> different word size (32/64 bits) on src/dst.
>
> Signed-off-by: Peter Xu <pet...@redhat.com>
(The comment on the receive side 'Add addings' is a bit odd!
The send side is much better); other than that:
Reviewed-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
> ---
> migration/migration.c | 68 +++++++++++++++++++++++
> migration/migration.h | 2 +
> migration/ram.c | 144
> +++++++++++++++++++++++++++++++++++++++++++++++++
> migration/ram.h | 3 ++
> migration/savevm.c | 2 +-
> migration/trace-events | 3 ++
> 6 files changed, 221 insertions(+), 1 deletion(-)
>
> diff --git a/migration/migration.c b/migration/migration.c
> index 32c036fa82..5592975d33 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -93,6 +93,7 @@ enum mig_rp_message_type {
>
> MIG_RP_MSG_REQ_PAGES_ID, /* data (start: be64, len: be32, id: string) */
> MIG_RP_MSG_REQ_PAGES, /* data (start: be64, len: be32) */
> + MIG_RP_MSG_RECV_BITMAP, /* send recved_bitmap back to source */
>
> MIG_RP_MSG_MAX
> };
> @@ -502,6 +503,45 @@ void migrate_send_rp_pong(MigrationIncomingState *mis,
> migrate_send_rp_message(mis, MIG_RP_MSG_PONG, sizeof(buf), &buf);
> }
>
> +void migrate_send_rp_recv_bitmap(MigrationIncomingState *mis,
> + char *block_name)
> +{
> + char buf[512];
> + int len;
> + int64_t res;
> +
> + /*
> + * First, we send the header part. It contains only the len of
> + * idstr, and the idstr itself.
> + */
> + len = strlen(block_name);
> + buf[0] = len;
> + memcpy(buf + 1, block_name, len);
> +
> + if (mis->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
> + error_report("%s: MSG_RP_RECV_BITMAP only used for recovery",
> + __func__);
> + return;
> + }
> +
> + migrate_send_rp_message(mis, MIG_RP_MSG_RECV_BITMAP, len + 1, buf);
> +
> + /*
> + * Next, we dump the received bitmap to the stream.
> + *
> + * TODO: currently we are safe since we are the only one that is
> + * using the to_src_file handle (fault thread is still paused),
> + * and it's ok even not taking the mutex. However the best way is
> + * to take the lock before sending the message header, and release
> + * the lock after sending the bitmap.
> + */
> + qemu_mutex_lock(&mis->rp_mutex);
> + res = ramblock_recv_bitmap_send(mis->to_src_file, block_name);
> + qemu_mutex_unlock(&mis->rp_mutex);
> +
> + trace_migrate_send_rp_recv_bitmap(block_name, res);
> +}
> +
> MigrationCapabilityStatusList *qmp_query_migrate_capabilities(Error **errp)
> {
> MigrationCapabilityStatusList *head = NULL;
> @@ -1736,6 +1776,7 @@ static struct rp_cmd_args {
> [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_RECV_BITMAP] = { .len = -1, .name = "RECV_BITMAP" },
> [MIG_RP_MSG_MAX] = { .len = -1, .name = "MAX" },
> };
>
> @@ -1780,6 +1821,19 @@ static bool
> postcopy_pause_return_path_thread(MigrationState *s)
> return true;
> }
>
> +static int migrate_handle_rp_recv_bitmap(MigrationState *s, char *block_name)
> +{
> + RAMBlock *block = qemu_ram_block_by_name(block_name);
> +
> + if (!block) {
> + error_report("%s: invalid block name '%s'", __func__, block_name);
> + return -EINVAL;
> + }
> +
> + /* Fetch the received bitmap and refresh the dirty bitmap */
> + return ram_dirty_bitmap_reload(s, block);
> +}
> +
> /*
> * Handles messages sent on the return path towards the source VM
> *
> @@ -1885,6 +1939,20 @@ retry:
> migrate_handle_rp_req_pages(ms, (char *)&buf[13], start, len);
> break;
>
> + case MIG_RP_MSG_RECV_BITMAP:
> + if (header_len < 1) {
> + error_report("%s: missing block name", __func__);
> + mark_source_rp_bad(ms);
> + goto out;
> + }
> + /* Format: len (1B) + idstr (<255B). This ends the idstr. */
> + buf[buf[0] + 1] = '\0';
> + if (migrate_handle_rp_recv_bitmap(ms, (char *)(buf + 1))) {
> + mark_source_rp_bad(ms);
> + goto out;
> + }
> + break;
> +
> default:
> break;
> }
> diff --git a/migration/migration.h b/migration/migration.h
> index d052669e1c..f879c93542 100644
> --- a/migration/migration.h
> +++ b/migration/migration.h
> @@ -219,5 +219,7 @@ void migrate_send_rp_pong(MigrationIncomingState *mis,
> uint32_t value);
> int migrate_send_rp_req_pages(MigrationIncomingState *mis, const char*
> rbname,
> ram_addr_t start, size_t len);
> +void migrate_send_rp_recv_bitmap(MigrationIncomingState *mis,
> + char *block_name);
>
> #endif
> diff --git a/migration/ram.c b/migration/ram.c
> index 960c726ff2..b30c669476 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -180,6 +180,70 @@ void ramblock_recv_bitmap_set_range(RAMBlock *rb, void
> *host_addr,
> nr);
> }
>
> +#define RAMBLOCK_RECV_BITMAP_ENDING (0x0123456789abcdefULL)
> +
> +/*
> + * Format: bitmap_size (8 bytes) + whole_bitmap (N bytes).
> + *
> + * Returns >0 if success with sent bytes, or <0 if error.
> + */
> +int64_t ramblock_recv_bitmap_send(QEMUFile *file,
> + const char *block_name)
> +{
> + RAMBlock *block = qemu_ram_block_by_name(block_name);
> + unsigned long *le_bitmap, nbits;
> + uint64_t size;
> +
> + if (!block) {
> + error_report("%s: invalid block name: %s", __func__, block_name);
> + return -1;
> + }
> +
> + nbits = block->used_length >> TARGET_PAGE_BITS;
> +
> + /*
> + * Make sure the tmp bitmap buffer is big enough, e.g., on 32bit
> + * machines we may need 4 more bytes for padding (see below
> + * comment). So extend it a bit before hand.
> + */
> + le_bitmap = bitmap_new(nbits + BITS_PER_LONG);
> +
> + /*
> + * Always use little endian when sending the bitmap. This is
> + * required that when source and destination VMs are not using the
> + * same endianess. (Note: big endian won't work.)
> + */
> + bitmap_to_le(le_bitmap, block->receivedmap, nbits);
> +
> + /* Size of the bitmap, in bytes */
> + size = nbits / 8;
> +
> + /*
> + * size is always aligned to 8 bytes for 64bit machines, but it
> + * may not be true for 32bit machines. We need this padding to
> + * make sure the migration can survive even between 32bit and
> + * 64bit machines.
> + */
> + size = ROUND_UP(size, 8);
> +
> + qemu_put_be64(file, size);
> + qemu_put_buffer(file, (const uint8_t *)le_bitmap, size);
> + /*
> + * Mark as an end, in case the middle part is screwed up due to
> + * some "misterious" reason.
> + */
> + qemu_put_be64(file, RAMBLOCK_RECV_BITMAP_ENDING);
> + qemu_fflush(file);
> +
> + free(le_bitmap);
> +
> + if (qemu_file_get_error(file)) {
> + return qemu_file_get_error(file);
> + }
> +
> + return size + sizeof(size);
> +}
> +
> /*
> * An outstanding page request, on the source, having been received
> * and queued
> @@ -2985,6 +3049,86 @@ static bool ram_has_postcopy(void *opaque)
> return migrate_postcopy_ram();
> }
>
> +/*
> + * Read the received bitmap, revert it as the initial dirty bitmap.
> + * This is only used when the postcopy migration is paused but wants
> + * to resume from a middle point.
> + */
> +int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block)
> +{
> + int ret = -EINVAL;
> + QEMUFile *file = s->rp_state.from_dst_file;
> + unsigned long *le_bitmap, nbits = block->used_length >> TARGET_PAGE_BITS;
> + uint64_t local_size = nbits / 8;
> + uint64_t size, end_mark;
> +
> + trace_ram_dirty_bitmap_reload_begin(block->idstr);
> +
> + if (s->state != MIGRATION_STATUS_POSTCOPY_RECOVER) {
> + error_report("%s: incorrect state %s", __func__,
> + MigrationStatus_str(s->state));
> + return -EINVAL;
> + }
> +
> + /*
> + * Note: see comments in ramblock_recv_bitmap_send() on why we
> + * need the endianess convertion, and the paddings.
> + */
> + local_size = ROUND_UP(local_size, 8);
> +
> + /* Add addings */
> + le_bitmap = bitmap_new(nbits + BITS_PER_LONG);
> +
> + size = qemu_get_be64(file);
> +
> + /* The size of the bitmap should match with our ramblock */
> + if (size != local_size) {
> + error_report("%s: ramblock '%s' bitmap size mismatch "
> + "(0x%"PRIx64" != 0x%"PRIx64")", __func__,
> + block->idstr, size, local_size);
> + ret = -EINVAL;
> + goto out;
> + }
> +
> + size = qemu_get_buffer(file, (uint8_t *)le_bitmap, local_size);
> + end_mark = qemu_get_be64(file);
> +
> + ret = qemu_file_get_error(file);
> + if (ret || size != local_size) {
> + error_report("%s: read bitmap failed for ramblock '%s': %d"
> + " (size 0x%"PRIx64", got: 0x%"PRIx64")",
> + __func__, block->idstr, ret, local_size, size);
> + ret = -EIO;
> + goto out;
> + }
> +
> + if (end_mark != RAMBLOCK_RECV_BITMAP_ENDING) {
> + error_report("%s: ramblock '%s' end mark incorrect: 0x%"PRIu64,
> + __func__, block->idstr, end_mark);
> + ret = -EINVAL;
> + goto out;
> + }
> +
> + /*
> + * Endianess convertion. We are during postcopy (though paused).
> + * The dirty bitmap won't change. We can directly modify it.
> + */
> + bitmap_from_le(block->bmap, le_bitmap, nbits);
> +
> + /*
> + * What we received is "received bitmap". Revert it as the initial
> + * dirty bitmap for this ramblock.
> + */
> + bitmap_complement(block->bmap, block->bmap, nbits);
> +
> + trace_ram_dirty_bitmap_reload_complete(block->idstr);
> +
> + ret = 0;
> +out:
> + free(le_bitmap);
> + return ret;
> +}
> +
> static SaveVMHandlers savevm_ram_handlers = {
> .save_setup = ram_save_setup,
> .save_live_iterate = ram_save_iterate,
> diff --git a/migration/ram.h b/migration/ram.h
> index 64d81e9f1d..10a459cc89 100644
> --- a/migration/ram.h
> +++ b/migration/ram.h
> @@ -61,5 +61,8 @@ void ram_handle_compressed(void *host, uint8_t ch, uint64_t
> size);
> int ramblock_recv_bitmap_test(RAMBlock *rb, void *host_addr);
> void ramblock_recv_bitmap_set(RAMBlock *rb, void *host_addr);
> void ramblock_recv_bitmap_set_range(RAMBlock *rb, void *host_addr, size_t
> nr);
> +int64_t ramblock_recv_bitmap_send(QEMUFile *file,
> + const char *block_name);
> +int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *rb);
>
> #endif
> diff --git a/migration/savevm.c b/migration/savevm.c
> index 0f61da3ebb..2148b198c7 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -1811,7 +1811,7 @@ static int
> loadvm_handle_recv_bitmap(MigrationIncomingState *mis,
> return -EINVAL;
> }
>
> - /* TODO: send the bitmap back to source */
> + migrate_send_rp_recv_bitmap(mis, block_name);
>
> trace_loadvm_handle_recv_bitmap(block_name);
>
> diff --git a/migration/trace-events b/migration/trace-events
> index 55c0412aaa..3dcf8a93d9 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -79,6 +79,8 @@ ram_load_postcopy_loop(uint64_t addr, int flags) "@%"
> PRIx64 " %x"
> ram_postcopy_send_discard_bitmap(void) ""
> ram_save_page(const char *rbname, uint64_t offset, void *host) "%s: offset:
> 0x%" PRIx64 " host: %p"
> ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s:
> start: 0x%zx len: 0x%zx"
> +ram_dirty_bitmap_reload_begin(char *str) "%s"
> +ram_dirty_bitmap_reload_complete(char *str) "%s"
>
> # migration/migration.c
> await_return_path_close_on_source_close(void) ""
> @@ -90,6 +92,7 @@ migrate_fd_cancel(void) ""
> migrate_handle_rp_req_pages(const char *rbname, size_t start, size_t len)
> "in %s at 0x%zx len 0x%zx"
> migrate_pending(uint64_t size, uint64_t max, uint64_t post, uint64_t
> nonpost) "pending size %" PRIu64 " max %" PRIu64 " (post=%" PRIu64 "
> nonpost=%" PRIu64 ")"
> migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
> +migrate_send_rp_recv_bitmap(char *name, int64_t size) "block '%s' size
> 0x%"PRIi64
> migration_completion_file_err(void) ""
> migration_completion_postcopy_end(void) ""
> migration_completion_postcopy_end_after_complete(void) ""
> --
> 2.13.6
>
--
Dr. David Alan Gilbert / dgilb...@redhat.com / Manchester, UK
