qcow2: Add subcluster support to qcow2_co_pwrite_zeroes()

This works now at the subcluster level and pwrite_zeroes_alignment is
updated accordingly.

qcow2_cluster_zeroize() is turned into qcow2_subcluster_zeroize() with
the following changes:

   - The request can now be subcluster-aligned.

   - The cluster-aligned body of the request is still zeroized using
     zero_in_l2_slice() as before.

   - The subcluster-aligned head and tail of the request are zeroized
     with the new zero_l2_subclusters() function.

There is just one thing to take into account for a possible future
improvement: compressed clusters cannot be partially zeroized so
zero_l2_subclusters() on the head or the tail can return -ENOTSUP.
This makes the caller repeat the *complete* request and write actual
zeroes to disk. This is sub-optimal because

   1) if the head area was compressed we would still be able to use
      the fast path for the body and possibly the tail.

   2) if the tail area was compressed we are writing zeroes to the
      head and the body areas, which are already zeroized.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-Id: <17e05e2ee7e12f10dcf012da81e83ebe27eb3bef.1594396418.git.berto@igalia.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>

1 files changed, 17 insertions, 16 deletions

diff --git a/block/qcow2.c b/block/qcow2.c
index 9990535c46..0cf0b0a9fb 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1913,7 +1913,7 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
         /* Encryption works on a sector granularity */
         bs->bl.request_alignment = qcrypto_block_get_sector_size(s->crypto);
     }
-    bs->bl.pwrite_zeroes_alignment = s->cluster_size;
+    bs->bl.pwrite_zeroes_alignment = s->subcluster_size;
     bs->bl.pdiscard_alignment = s->cluster_size;
 }
 
@@ -3833,8 +3833,9 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
     int ret;
     BDRVQcow2State *s = bs->opaque;
 
-    uint32_t head = offset % s->cluster_size;
-    uint32_t tail = (offset + bytes) % s->cluster_size;
+    uint32_t head = offset_into_subcluster(s, offset);
+    uint32_t tail = ROUND_UP(offset + bytes, s->subcluster_size) -
+        (offset + bytes);
 
     trace_qcow2_pwrite_zeroes_start_req(qemu_coroutine_self(), offset, bytes);
     if (offset + bytes == bs->total_sectors * BDRV_SECTOR_SIZE) {
@@ -3846,20 +3847,19 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
         unsigned int nr;
         QCow2SubclusterType type;
 
-        assert(head + bytes <= s->cluster_size);
+        assert(head + bytes + tail <= s->subcluster_size);
 
         /* check whether remainder of cluster already reads as zero */
         if (!(is_zero(bs, offset - head, head) &&
-              is_zero(bs, offset + bytes,
-                      tail ? s->cluster_size - tail : 0))) {
+              is_zero(bs, offset + bytes, tail))) {
             return -ENOTSUP;
         }
 
         qemu_co_mutex_lock(&s->lock);
         /* We can have new write after previous check */
-        offset = QEMU_ALIGN_DOWN(offset, s->cluster_size);
-        bytes = s->cluster_size;
-        nr = s->cluster_size;
+        offset -= head;
+        bytes = s->subcluster_size;
+        nr = s->subcluster_size;
         ret = qcow2_get_host_offset(bs, offset, &nr, &off, &type);
         if (ret < 0 ||
             (type != QCOW2_SUBCLUSTER_UNALLOCATED_PLAIN &&
@@ -3875,8 +3875,8 @@ static coroutine_fn int qcow2_co_pwrite_zeroes(BlockDriverState *bs,
 
     trace_qcow2_pwrite_zeroes(qemu_coroutine_self(), offset, bytes);
 
-    /* Whatever is left can use real zero clusters */
-    ret = qcow2_cluster_zeroize(bs, offset, bytes, flags);
+    /* Whatever is left can use real zero subclusters */
+    ret = qcow2_subcluster_zeroize(bs, offset, bytes, flags);
     qemu_co_mutex_unlock(&s->lock);
 
     return ret;
@@ -4357,15 +4357,16 @@ static int coroutine_fn qcow2_co_truncate(BlockDriverState *bs, int64_t offset,
     }
 
     if ((flags & BDRV_REQ_ZERO_WRITE) && offset > old_length) {
-        uint64_t zero_start = QEMU_ALIGN_UP(old_length, s->cluster_size);
+        uint64_t zero_start = QEMU_ALIGN_UP(old_length, s->subcluster_size);
 
         /*
-         * Use zero clusters as much as we can. qcow2_cluster_zeroize()
-         * requires a cluster-aligned start. The end may be unaligned if it is
-         * at the end of the image (which it is here).
+         * Use zero clusters as much as we can. qcow2_subcluster_zeroize()
+         * requires a subcluster-aligned start. The end may be unaligned if
+         * it is at the end of the image (which it is here).
          */
         if (offset > zero_start) {
-            ret = qcow2_cluster_zeroize(bs, zero_start, offset - zero_start, 0);
+            ret = qcow2_subcluster_zeroize(bs, zero_start, offset - zero_start,
+                                           0);
             if (ret < 0) {
                 error_setg_errno(errp, -ret, "Failed to zero out new clusters");
                 goto fail;