qemu-img: Convert with copy offloading

The new blk_co_copy_range interface offers a more efficient way in the
case of network based storage. Make use of it to allow faster convert
operation.

Since copy offloading cannot do zero detection ('-S') and compression
(-c), only try it when these options are not used.

Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20180601092648.24614-11-famz@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

qemu-img.c

@@ -1547,6 +1547,7 @@ typedef struct ImgConvertState {
     bool compressed;
     bool target_has_backing;
     bool wr_in_order;
+    bool copy_range;
     int min_sparse;
     size_t cluster_sectors;
     size_t buf_sectors;
@@ -1740,6 +1741,37 @@ static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num,
     return 0;
 }
 
+static int coroutine_fn convert_co_copy_range(ImgConvertState *s, int64_t sector_num,
+                                              int nb_sectors)
+{
+    int n, ret;
+
+    while (nb_sectors > 0) {
+        BlockBackend *blk;
+        int src_cur;
+        int64_t bs_sectors, src_cur_offset;
+        int64_t offset;
+
+        convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
+        offset = (sector_num - src_cur_offset) << BDRV_SECTOR_BITS;
+        blk = s->src[src_cur];
+        bs_sectors = s->src_sectors[src_cur];
+
+        n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
+
+        ret = blk_co_copy_range(blk, offset, s->target,
+                                sector_num << BDRV_SECTOR_BITS,
+                                n << BDRV_SECTOR_BITS, 0);
+        if (ret < 0) {
+            return ret;
+        }
+
+        sector_num += n;
+        nb_sectors -= n;
+    }
+    return 0;
+}
+
 static void coroutine_fn convert_co_do_copy(void *opaque)
 {
     ImgConvertState *s = opaque;
@@ -1762,6 +1794,7 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
         int n;
         int64_t sector_num;
         enum ImgConvertBlockStatus status;
+        bool copy_range;
 
         qemu_co_mutex_lock(&s->lock);
         if (s->ret != -EINPROGRESS || s->sector_num >= s->total_sectors) {
@@ -1791,7 +1824,9 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
                                         s->allocated_sectors, 0);
         }
 
-        if (status == BLK_DATA) {
+retry:
+        copy_range = s->copy_range && s->status == BLK_DATA;
+        if (status == BLK_DATA && !copy_range) {
             ret = convert_co_read(s, sector_num, n, buf);
             if (ret < 0) {
                 error_report("error while reading sector %" PRId64
@@ -1813,7 +1848,15 @@ static void coroutine_fn convert_co_do_copy(void *opaque)
         }
 
         if (s->ret == -EINPROGRESS) {
-            ret = convert_co_write(s, sector_num, n, buf, status);
+            if (copy_range) {
+                ret = convert_co_copy_range(s, sector_num, n);
+                if (ret) {
+                    s->copy_range = false;
+                    goto retry;
+                }
+            } else {
+                ret = convert_co_write(s, sector_num, n, buf, status);
+            }
             if (ret < 0) {
                 error_report("error while writing sector %" PRId64
                              ": %s", sector_num, strerror(-ret));
@@ -1936,6 +1979,7 @@ static int img_convert(int argc, char **argv)
     ImgConvertState s = (ImgConvertState) {
         /* Need at least 4k of zeros for sparse detection */
         .min_sparse         = 8,
+        .copy_range         = true,
         .buf_sectors        = IO_BUF_SIZE / BDRV_SECTOR_SIZE,
         .wr_in_order        = true,
         .num_coroutines     = 8,
@@ -1976,6 +2020,7 @@ static int img_convert(int argc, char **argv)
             break;
         case 'c':
             s.compressed = true;
+            s.copy_range = false;
             break;
         case 'o':
             if (!is_valid_option_list(optarg)) {
@@ -2017,6 +2062,7 @@ static int img_convert(int argc, char **argv)
             }
 
             s.min_sparse = sval / BDRV_SECTOR_SIZE;
+            s.copy_range = false;
             break;
         }
         case 'p':