block: Introduce API for copy offloading

Introduce the bdrv_co_copy_range() API for copy offloading.  Block
drivers implementing this API support efficient copy operations that
avoid reading each block from the source device and writing it to the
destination devices.  Examples of copy offload primitives are SCSI
EXTENDED COPY and Linux copy_file_range(2).

Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20180601092648.24614-2-famz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 97 insertions, 0 deletions

diff --git a/block/io.c b/block/io.c
index ca96b487eb..b7beaeeb9f 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2835,3 +2835,100 @@ void bdrv_unregister_buf(BlockDriverState *bs, void *host)
         bdrv_unregister_buf(child->bs, host);
     }
 }
+
+static int coroutine_fn bdrv_co_copy_range_internal(BdrvChild *src,
+                                                    uint64_t src_offset,
+                                                    BdrvChild *dst,
+                                                    uint64_t dst_offset,
+                                                    uint64_t bytes,
+                                                    BdrvRequestFlags flags,
+                                                    bool recurse_src)
+{
+    int ret;
+
+    if (!src || !dst || !src->bs || !dst->bs) {
+        return -ENOMEDIUM;
+    }
+    ret = bdrv_check_byte_request(src->bs, src_offset, bytes);
+    if (ret) {
+        return ret;
+    }
+
+    ret = bdrv_check_byte_request(dst->bs, dst_offset, bytes);
+    if (ret) {
+        return ret;
+    }
+    if (flags & BDRV_REQ_ZERO_WRITE) {
+        return bdrv_co_pwrite_zeroes(dst, dst_offset, bytes, flags);
+    }
+
+    if (!src->bs->drv->bdrv_co_copy_range_from
+        || !dst->bs->drv->bdrv_co_copy_range_to
+        || src->bs->encrypted || dst->bs->encrypted) {
+        return -ENOTSUP;
+    }
+    if (recurse_src) {
+        return src->bs->drv->bdrv_co_copy_range_from(src->bs,
+                                                     src, src_offset,
+                                                     dst, dst_offset,
+                                                     bytes, flags);
+    } else {
+        return dst->bs->drv->bdrv_co_copy_range_to(dst->bs,
+                                                   src, src_offset,
+                                                   dst, dst_offset,
+                                                   bytes, flags);
+    }
+}
+
+/* Copy range from @src to @dst.
+ *
+ * See the comment of bdrv_co_copy_range for the parameter and return value
+ * semantics. */
+int coroutine_fn bdrv_co_copy_range_from(BdrvChild *src, uint64_t src_offset,
+                                         BdrvChild *dst, uint64_t dst_offset,
+                                         uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
+                                       bytes, flags, true);
+}
+
+/* Copy range from @src to @dst.
+ *
+ * See the comment of bdrv_co_copy_range for the parameter and return value
+ * semantics. */
+int coroutine_fn bdrv_co_copy_range_to(BdrvChild *src, uint64_t src_offset,
+                                       BdrvChild *dst, uint64_t dst_offset,
+                                       uint64_t bytes, BdrvRequestFlags flags)
+{
+    return bdrv_co_copy_range_internal(src, src_offset, dst, dst_offset,
+                                       bytes, flags, false);
+}
+
+int coroutine_fn bdrv_co_copy_range(BdrvChild *src, uint64_t src_offset,
+                                    BdrvChild *dst, uint64_t dst_offset,
+                                    uint64_t bytes, BdrvRequestFlags flags)
+{
+    BdrvTrackedRequest src_req, dst_req;
+    BlockDriverState *src_bs = src->bs;
+    BlockDriverState *dst_bs = dst->bs;
+    int ret;
+
+    bdrv_inc_in_flight(src_bs);
+    bdrv_inc_in_flight(dst_bs);
+    tracked_request_begin(&src_req, src_bs, src_offset,
+                          bytes, BDRV_TRACKED_READ);
+    tracked_request_begin(&dst_req, dst_bs, dst_offset,
+                          bytes, BDRV_TRACKED_WRITE);
+
+    wait_serialising_requests(&src_req);
+    wait_serialising_requests(&dst_req);
+    ret = bdrv_co_copy_range_from(src, src_offset,
+                                  dst, dst_offset,
+                                  bytes, flags);
+
+    tracked_request_end(&src_req);
+    tracked_request_end(&dst_req);
+    bdrv_dec_in_flight(src_bs);
+    bdrv_dec_in_flight(dst_bs);
+    return ret;
+}