qed: Add support for zero clusters

Zero clusters are similar to unallocated clusters except instead of reading
their value from a backing file when one is available, the cluster is always
read as zero.

This implements read support only.  At this stage, QED will never write a
zero cluster.

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

4 files changed, 66 insertions, 17 deletions

diff --git a/block/qed-check.c b/block/qed-check.c
index 4600932..ea4ebc8 100644
--- a/block/qed-check.c
+++ b/block/qed-check.c
@@ -72,7 +72,8 @@ static unsigned int qed_check_l2_table(QEDCheck *check, QEDTable *table)
     for (i = 0; i < s->table_nelems; i++) {
         uint64_t offset = table->offsets[i];
 
-        if (!offset) {
+        if (qed_offset_is_unalloc_cluster(offset) ||
+            qed_offset_is_zero_cluster(offset)) {
             continue;
         }
 
@@ -111,7 +112,7 @@ static int qed_check_l1_table(QEDCheck *check, QEDTable *table)
         unsigned int num_invalid_l2;
         uint64_t offset = table->offsets[i];
 
-        if (!offset) {
+        if (qed_offset_is_unalloc_cluster(offset)) {
             continue;
         }
 
diff --git a/block/qed-cluster.c b/block/qed-cluster.c
index 0ec864b..3e19ad1 100644
--- a/block/qed-cluster.c
+++ b/block/qed-cluster.c
@@ -23,7 +23,8 @@
  * @n:              Maximum number of clusters
  * @offset:         Set to first cluster offset
  *
- * This function scans tables for contiguous allocated or free clusters.
+ * This function scans tables for contiguous clusters.  A contiguous run of
+ * clusters may be allocated, unallocated, or zero.
  */
 static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s,
                                                   QEDTable *table,
@@ -38,9 +39,14 @@ static unsigned int qed_count_contiguous_clusters(BDRVQEDState *s,
     *offset = last;
 
     for (i = index + 1; i < end; i++) {
-        if (last == 0) {
-            /* Counting free clusters */
-            if (table->offsets[i] != 0) {
+        if (qed_offset_is_unalloc_cluster(last)) {
+            /* Counting unallocated clusters */
+            if (!qed_offset_is_unalloc_cluster(table->offsets[i])) {
+                break;
+            }
+        } else if (qed_offset_is_zero_cluster(last)) {
+            /* Counting zero clusters */
+            if (!qed_offset_is_zero_cluster(table->offsets[i])) {
                 break;
             }
         } else {
@@ -87,14 +93,19 @@ static void qed_find_cluster_cb(void *opaque, int ret)
     n = qed_count_contiguous_clusters(s, request->l2_table->table,
                                       index, n, &offset);
 
-    ret = offset ? QED_CLUSTER_FOUND : QED_CLUSTER_L2;
-    len = MIN(find_cluster_cb->len, n * s->header.cluster_size -
-              qed_offset_into_cluster(s, find_cluster_cb->pos));
-
-    if (offset && !qed_check_cluster_offset(s, offset)) {
+    if (qed_offset_is_unalloc_cluster(offset)) {
+        ret = QED_CLUSTER_L2;
+    } else if (qed_offset_is_zero_cluster(offset)) {
+        ret = QED_CLUSTER_ZERO;
+    } else if (qed_check_cluster_offset(s, offset)) {
+        ret = QED_CLUSTER_FOUND;
+    } else {
         ret = -EINVAL;
     }
 
+    len = MIN(find_cluster_cb->len, n * s->header.cluster_size -
+              qed_offset_into_cluster(s, find_cluster_cb->pos));
+
 out:
     find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
     qemu_free(find_cluster_cb);
@@ -132,7 +143,7 @@ void qed_find_cluster(BDRVQEDState *s, QEDRequest *request, uint64_t pos,
     len = MIN(len, (((pos >> s->l1_shift) + 1) << s->l1_shift) - pos);
 
     l2_offset = s->l1_table->offsets[qed_l1_index(s, pos)];
-    if (!l2_offset) {
+    if (qed_offset_is_unalloc_cluster(l2_offset)) {
         cb(opaque, QED_CLUSTER_L1, 0, len);
         return;
     }
diff --git a/block/qed.c b/block/qed.c
index 75ae244..c8c5930 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -573,7 +573,7 @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l
 {
     QEDIsAllocatedCB *cb = opaque;
     *cb->pnum = len / BDRV_SECTOR_SIZE;
-    cb->is_allocated = ret == QED_CLUSTER_FOUND;
+    cb->is_allocated = (ret == QED_CLUSTER_FOUND || ret == QED_CLUSTER_ZERO);
 }
 
 static int bdrv_qed_is_allocated(BlockDriverState *bs, int64_t sector_num,
@@ -745,7 +745,10 @@ static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
  * @table:          L2 table
  * @index:          First cluster index
  * @n:              Number of contiguous clusters
- * @cluster:        First cluster byte offset in image file
+ * @cluster:        First cluster offset
+ *
+ * The cluster offset may be an allocated byte offset in the image file, the
+ * zero cluster marker, or the unallocated cluster marker.
  */
 static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
                                 unsigned int n, uint64_t cluster)
@@ -753,7 +756,10 @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
     int i;
     for (i = index; i < index + n; i++) {
         table->offsets[i] = cluster;
-        cluster += s->header.cluster_size;
+        if (!qed_offset_is_unalloc_cluster(cluster) &&
+            !qed_offset_is_zero_cluster(cluster)) {
+            cluster += s->header.cluster_size;
+        }
     }
 }
 
@@ -1075,6 +1081,7 @@ static void qed_aio_write_data(void *opaque, int ret,
 
     case QED_CLUSTER_L2:
     case QED_CLUSTER_L1:
+    case QED_CLUSTER_ZERO:
         qed_aio_write_alloc(acb, len);
         break;
 
@@ -1114,8 +1121,12 @@ static void qed_aio_read_data(void *opaque, int ret,
 
     qemu_iovec_copy(&acb->cur_qiov, acb->qiov, acb->qiov_offset, len);
 
-    /* Handle backing file and unallocated sparse hole reads */
-    if (ret != QED_CLUSTER_FOUND) {
+    /* Handle zero cluster and backing file reads */
+    if (ret == QED_CLUSTER_ZERO) {
+        qemu_iovec_memset(&acb->cur_qiov, 0, acb->cur_qiov.size);
+        qed_aio_next_io(acb, 0);
+        return;
+    } else if (ret != QED_CLUSTER_FOUND) {
         qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
                               qed_aio_next_io, acb);
         return;
diff --git a/block/qed.h b/block/qed.h
index 2925e37..3e1ab84 100644
--- a/block/qed.h
+++ b/block/qed.h
@@ -161,6 +161,7 @@ typedef struct {
 
 enum {
     QED_CLUSTER_FOUND,         /* cluster found */
+    QED_CLUSTER_ZERO,          /* zero cluster found */
     QED_CLUSTER_L2,            /* cluster missing in L2 */
     QED_CLUSTER_L1,            /* cluster missing in L1 */
 };
@@ -298,4 +299,29 @@ static inline bool qed_check_table_offset(BDRVQEDState *s, uint64_t offset)
            qed_check_cluster_offset(s, end_offset);
 }
 
+static inline bool qed_offset_is_cluster_aligned(BDRVQEDState *s,
+                                                 uint64_t offset)
+{
+    if (qed_offset_into_cluster(s, offset)) {
+        return false;
+    }
+    return true;
+}
+
+static inline bool qed_offset_is_unalloc_cluster(uint64_t offset)
+{
+    if (offset == 0) {
+        return true;
+    }
+    return false;
+}
+
+static inline bool qed_offset_is_zero_cluster(uint64_t offset)
+{
+    if (offset == 1) {
+        return true;
+    }
+    return false;
+}
+
 #endif /* BLOCK_QED_H */