#define BLOCK_COPY_MAX_BUFFER (1 * MiB)
#define BLOCK_COPY_MAX_MEM (128 * MiB)
+typedef struct BlockCopyInFlightReq {
+ int64_t offset;
+ int64_t bytes;
+ QLIST_ENTRY(BlockCopyInFlightReq) list;
+ CoQueue wait_queue; /* coroutines blocked on this request */
+} BlockCopyInFlightReq;
+
+typedef struct BlockCopyState {
+ /*
+ * BdrvChild objects are not owned or managed by block-copy. They are
+ * provided by block-copy user and user is responsible for appropriate
+ * permissions on these children.
+ */
+ BdrvChild *source;
+ BdrvChild *target;
+ BdrvDirtyBitmap *copy_bitmap;
+ int64_t in_flight_bytes;
+ int64_t cluster_size;
+ bool use_copy_range;
+ int64_t copy_size;
+ uint64_t len;
+ QLIST_HEAD(, BlockCopyInFlightReq) inflight_reqs;
+
+ BdrvRequestFlags write_flags;
+
+ /*
+ * skip_unallocated:
+ *
+ * Used by sync=top jobs, which first scan the source node for unallocated
+ * areas and clear them in the copy_bitmap. During this process, the bitmap
+ * is thus not fully initialized: It may still have bits set for areas that
+ * are unallocated and should actually not be copied.
+ *
+ * This is indicated by skip_unallocated.
+ *
+ * In this case, block_copy() will query the source’s allocation status,
+ * skip unallocated regions, clear them in the copy_bitmap, and invoke
+ * block_copy_reset_unallocated() every time it does.
+ */
+ bool skip_unallocated;
+
+ ProgressMeter *progress;
+ /* progress_bytes_callback: called when some copying progress is done. */
+ ProgressBytesCallbackFunc progress_bytes_callback;
+ void *progress_opaque;
+
+ SharedResource *mem;
+} BlockCopyState;
+
static BlockCopyInFlightReq *find_conflicting_inflight_req(BlockCopyState *s,
- int64_t start,
- int64_t end)
+ int64_t offset,
+ int64_t bytes)
{
BlockCopyInFlightReq *req;
QLIST_FOREACH(req, &s->inflight_reqs, list) {
- if (end > req->start_byte && start < req->end_byte) {
+ if (offset + bytes > req->offset && offset < req->offset + req->bytes) {
return req;
}
}
return NULL;
}
-static void coroutine_fn block_copy_wait_inflight_reqs(BlockCopyState *s,
- int64_t start,
- int64_t end)
+/*
+ * If there are no intersecting requests return false. Otherwise, wait for the
+ * first found intersecting request to finish and return true.
+ */
+static bool coroutine_fn block_copy_wait_one(BlockCopyState *s, int64_t offset,
+ int64_t bytes)
{
- BlockCopyInFlightReq *req;
+ BlockCopyInFlightReq *req = find_conflicting_inflight_req(s, offset, bytes);
- while ((req = find_conflicting_inflight_req(s, start, end))) {
- qemu_co_queue_wait(&req->wait_queue, NULL);
+ if (!req) {
+ return false;
}
+
+ qemu_co_queue_wait(&req->wait_queue, NULL);
+
+ return true;
}
+/* Called only on full-dirty region */
static void block_copy_inflight_req_begin(BlockCopyState *s,
BlockCopyInFlightReq *req,
- int64_t start, int64_t end)
+ int64_t offset, int64_t bytes)
{
- req->start_byte = start;
- req->end_byte = end;
+ assert(!find_conflicting_inflight_req(s, offset, bytes));
+
+ bdrv_reset_dirty_bitmap(s->copy_bitmap, offset, bytes);
+ s->in_flight_bytes += bytes;
+
+ req->offset = offset;
+ req->bytes = bytes;
qemu_co_queue_init(&req->wait_queue);
QLIST_INSERT_HEAD(&s->inflight_reqs, req, list);
}
-static void coroutine_fn block_copy_inflight_req_end(BlockCopyInFlightReq *req)
+/*
+ * block_copy_inflight_req_shrink
+ *
+ * Drop the tail of the request to be handled later. Set dirty bits back and
+ * wake up all requests waiting for us (may be some of them are not intersecting
+ * with shrunk request)
+ */
+static void coroutine_fn block_copy_inflight_req_shrink(BlockCopyState *s,
+ BlockCopyInFlightReq *req, int64_t new_bytes)
{
+ if (new_bytes == req->bytes) {
+ return;
+ }
+
+ assert(new_bytes > 0 && new_bytes < req->bytes);
+
+ s->in_flight_bytes -= req->bytes - new_bytes;
+ bdrv_set_dirty_bitmap(s->copy_bitmap,
+ req->offset + new_bytes, req->bytes - new_bytes);
+
+ req->bytes = new_bytes;
+ qemu_co_queue_restart_all(&req->wait_queue);
+}
+
+static void coroutine_fn block_copy_inflight_req_end(BlockCopyState *s,
+ BlockCopyInFlightReq *req,
+ int ret)
+{
+ s->in_flight_bytes -= req->bytes;
+ if (ret < 0) {
+ bdrv_set_dirty_bitmap(s->copy_bitmap, req->offset, req->bytes);
+ }
QLIST_REMOVE(req, list);
qemu_co_queue_restart_all(&req->wait_queue);
}
/*
* block_copy_do_copy
*
- * Do copy of cluser-aligned chunk. @end is allowed to exceed s->len only to
- * cover last cluster when s->len is not aligned to clusters.
+ * Do copy of cluster-aligned chunk. Requested region is allowed to exceed
+ * s->len only to cover last cluster when s->len is not aligned to clusters.
*
* No sync here: nor bitmap neighter intersecting requests handling, only copy.
*
* Returns 0 on success.
*/
static int coroutine_fn block_copy_do_copy(BlockCopyState *s,
- int64_t start, int64_t end,
+ int64_t offset, int64_t bytes,
bool zeroes, bool *error_is_read)
{
int ret;
- int nbytes = MIN(end, s->len) - start;
+ int64_t nbytes = MIN(offset + bytes, s->len) - offset;
void *bounce_buffer = NULL;
- assert(QEMU_IS_ALIGNED(start, s->cluster_size));
- assert(QEMU_IS_ALIGNED(end, s->cluster_size));
- assert(end < s->len || end == QEMU_ALIGN_UP(s->len, s->cluster_size));
+ assert(offset >= 0 && bytes > 0 && INT64_MAX - offset >= bytes);
+ assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+ assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
+ assert(offset < s->len);
+ assert(offset + bytes <= s->len ||
+ offset + bytes == QEMU_ALIGN_UP(s->len, s->cluster_size));
+ assert(nbytes < INT_MAX);
if (zeroes) {
- ret = bdrv_co_pwrite_zeroes(s->target, start, nbytes, s->write_flags &
+ ret = bdrv_co_pwrite_zeroes(s->target, offset, nbytes, s->write_flags &
~BDRV_REQ_WRITE_COMPRESSED);
if (ret < 0) {
- trace_block_copy_write_zeroes_fail(s, start, ret);
+ trace_block_copy_write_zeroes_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = false;
}
}
if (s->use_copy_range) {
- ret = bdrv_co_copy_range(s->source, start, s->target, start, nbytes,
+ ret = bdrv_co_copy_range(s->source, offset, s->target, offset, nbytes,
0, s->write_flags);
if (ret < 0) {
- trace_block_copy_copy_range_fail(s, start, ret);
+ trace_block_copy_copy_range_fail(s, offset, ret);
s->use_copy_range = false;
s->copy_size = MAX(s->cluster_size, BLOCK_COPY_MAX_BUFFER);
/* Fallback to read+write with allocated buffer */
bounce_buffer = qemu_blockalign(s->source->bs, nbytes);
- ret = bdrv_co_pread(s->source, start, nbytes, bounce_buffer, 0);
+ ret = bdrv_co_pread(s->source, offset, nbytes, bounce_buffer, 0);
if (ret < 0) {
- trace_block_copy_read_fail(s, start, ret);
+ trace_block_copy_read_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = true;
}
goto out;
}
- ret = bdrv_co_pwrite(s->target, start, nbytes, bounce_buffer,
+ ret = bdrv_co_pwrite(s->target, offset, nbytes, bounce_buffer,
s->write_flags);
if (ret < 0) {
- trace_block_copy_write_fail(s, start, ret);
+ trace_block_copy_write_fail(s, offset, ret);
if (error_is_read) {
*error_is_read = false;
}
return ret;
}
-int coroutine_fn block_copy(BlockCopyState *s,
- int64_t start, uint64_t bytes,
- bool *error_is_read)
+/*
+ * block_copy_dirty_clusters
+ *
+ * Copy dirty clusters in @offset/@bytes range.
+ * Returns 1 if dirty clusters found and successfully copied, 0 if no dirty
+ * clusters found and -errno on failure.
+ */
+static int coroutine_fn block_copy_dirty_clusters(BlockCopyState *s,
+ int64_t offset, int64_t bytes,
+ bool *error_is_read)
{
int ret = 0;
- int64_t end = bytes + start; /* bytes */
- BlockCopyInFlightReq req;
+ bool found_dirty = false;
/*
* block_copy() user is responsible for keeping source and target in same
assert(bdrv_get_aio_context(s->source->bs) ==
bdrv_get_aio_context(s->target->bs));
- assert(QEMU_IS_ALIGNED(start, s->cluster_size));
- assert(QEMU_IS_ALIGNED(end, s->cluster_size));
-
- block_copy_wait_inflight_reqs(s, start, bytes);
- block_copy_inflight_req_begin(s, &req, start, end);
+ assert(QEMU_IS_ALIGNED(offset, s->cluster_size));
+ assert(QEMU_IS_ALIGNED(bytes, s->cluster_size));
- while (start < end) {
- int64_t next_zero, chunk_end, status_bytes;
+ while (bytes) {
+ BlockCopyInFlightReq req;
+ int64_t next_zero, cur_bytes, status_bytes;
- if (!bdrv_dirty_bitmap_get(s->copy_bitmap, start)) {
- trace_block_copy_skip(s, start);
- start += s->cluster_size;
+ if (!bdrv_dirty_bitmap_get(s->copy_bitmap, offset)) {
+ trace_block_copy_skip(s, offset);
+ offset += s->cluster_size;
+ bytes -= s->cluster_size;
continue; /* already copied */
}
- chunk_end = MIN(end, start + s->copy_size);
+ found_dirty = true;
+
+ cur_bytes = MIN(bytes, s->copy_size);
- next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, start,
- chunk_end - start);
+ next_zero = bdrv_dirty_bitmap_next_zero(s->copy_bitmap, offset,
+ cur_bytes);
if (next_zero >= 0) {
- assert(next_zero > start); /* start is dirty */
- assert(next_zero < chunk_end); /* no need to do MIN() */
- chunk_end = next_zero;
+ assert(next_zero > offset); /* offset is dirty */
+ assert(next_zero < offset + cur_bytes); /* no need to do MIN() */
+ cur_bytes = next_zero - offset;
}
+ block_copy_inflight_req_begin(s, &req, offset, cur_bytes);
- ret = block_copy_block_status(s, start, chunk_end - start,
- &status_bytes);
+ ret = block_copy_block_status(s, offset, cur_bytes, &status_bytes);
+ assert(ret >= 0); /* never fail */
+ cur_bytes = MIN(cur_bytes, status_bytes);
+ block_copy_inflight_req_shrink(s, &req, cur_bytes);
if (s->skip_unallocated && !(ret & BDRV_BLOCK_ALLOCATED)) {
- bdrv_reset_dirty_bitmap(s->copy_bitmap, start, status_bytes);
+ block_copy_inflight_req_end(s, &req, 0);
progress_set_remaining(s->progress,
bdrv_get_dirty_count(s->copy_bitmap) +
s->in_flight_bytes);
- trace_block_copy_skip_range(s, start, status_bytes);
- start += status_bytes;
+ trace_block_copy_skip_range(s, offset, status_bytes);
+ offset += status_bytes;
+ bytes -= status_bytes;
continue;
}
- chunk_end = MIN(chunk_end, start + status_bytes);
+ trace_block_copy_process(s, offset);
- trace_block_copy_process(s, start);
-
- bdrv_reset_dirty_bitmap(s->copy_bitmap, start, chunk_end - start);
- s->in_flight_bytes += chunk_end - start;
-
- co_get_from_shres(s->mem, chunk_end - start);
- ret = block_copy_do_copy(s, start, chunk_end, ret & BDRV_BLOCK_ZERO,
+ co_get_from_shres(s->mem, cur_bytes);
+ ret = block_copy_do_copy(s, offset, cur_bytes, ret & BDRV_BLOCK_ZERO,
error_is_read);
- co_put_to_shres(s->mem, chunk_end - start);
- s->in_flight_bytes -= chunk_end - start;
+ co_put_to_shres(s->mem, cur_bytes);
+ block_copy_inflight_req_end(s, &req, ret);
if (ret < 0) {
- bdrv_set_dirty_bitmap(s->copy_bitmap, start, chunk_end - start);
- break;
+ return ret;
}
- progress_work_done(s->progress, chunk_end - start);
- s->progress_bytes_callback(chunk_end - start, s->progress_opaque);
- start = chunk_end;
- ret = 0;
+ progress_work_done(s->progress, cur_bytes);
+ s->progress_bytes_callback(cur_bytes, s->progress_opaque);
+ offset += cur_bytes;
+ bytes -= cur_bytes;
}
- block_copy_inflight_req_end(&req);
+ return found_dirty;
+}
+
+/*
+ * block_copy
+ *
+ * Copy requested region, accordingly to dirty bitmap.
+ * Collaborate with parallel block_copy requests: if they succeed it will help
+ * us. If they fail, we will retry not-copied regions. So, if we return error,
+ * it means that some I/O operation failed in context of _this_ block_copy call,
+ * not some parallel operation.
+ */
+int coroutine_fn block_copy(BlockCopyState *s, int64_t offset, int64_t bytes,
+ bool *error_is_read)
+{
+ int ret;
+
+ do {
+ ret = block_copy_dirty_clusters(s, offset, bytes, error_is_read);
+
+ if (ret == 0) {
+ ret = block_copy_wait_one(s, offset, bytes);
+ }
+
+ /*
+ * We retry in two cases:
+ * 1. Some progress done
+ * Something was copied, which means that there were yield points
+ * and some new dirty bits may have appeared (due to failed parallel
+ * block-copy requests).
+ * 2. We have waited for some intersecting block-copy request
+ * It may have failed and produced new dirty bits.
+ */
+ } while (ret > 0);
return ret;
}
+
+BdrvDirtyBitmap *block_copy_dirty_bitmap(BlockCopyState *s)
+{
+ return s->copy_bitmap;
+}
+
+void block_copy_set_skip_unallocated(BlockCopyState *s, bool skip)
+{
+ s->skip_unallocated = skip;
+}