[Qemu-devel] [RFC PATCH 15/16] qcow2: Zero write support

[Kevin Wolf <kwolf@redhat.com>]

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block.c               |   14 +++++++--
 block/qcow2-cluster.c |   72 +++++++++++++++++++++++++++++++++++++++++++++++++
 block/qcow2.c         |   21 ++++++++++++++
 block/qcow2.h         |    1 +
 4 files changed, 105 insertions(+), 3 deletions(-)

diff --git a/block.c b/block.c
index 8858be0..0b99ebc 100644
--- a/block.c
+++ b/block.c
@@ -80,6 +80,8 @@ static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
                                                void *opaque,
                                                bool is_write);
 static void coroutine_fn bdrv_co_do_rw(void *opaque);
+static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors);
 
 static bool bdrv_exceed_bps_limits(BlockDriverState *bs, int nb_sectors,
         bool is_write, double elapsed_time, uint64_t *wait);
@@ -1680,8 +1682,8 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
 
     if (drv->bdrv_co_write_zeroes &&
         buffer_is_zero(bounce_buffer, iov.iov_len)) {
-        ret = drv->bdrv_co_write_zeroes(bs, cluster_sector_num,
-                                        cluster_nb_sectors);
+        ret = bdrv_co_do_write_zeroes(bs, cluster_sector_num,
+                                      cluster_nb_sectors);
     } else {
         ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
                                   &bounce_qiov);
@@ -1791,9 +1793,15 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
     struct iovec iov;
     int ret;
 
+    /* TODO Emulate only part of misaligned requests instead of letting block
+     * drivers return -ENOTSUP and emulate everything */
+
     /* First try the efficient write zeroes operation */
     if (drv->bdrv_co_write_zeroes) {
-        return drv->bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+        ret = drv->bdrv_co_write_zeroes(bs, sector_num, nb_sectors);
+        if (ret != -ENOTSUP) {
+            return ret;
+        }
     }
 
     /* Fall back to bounce buffer if write zeroes is unsupported */
diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c
index 4853f1f..f820ac3 100644
--- a/block/qcow2-cluster.c
+++ b/block/qcow2-cluster.c
@@ -1102,3 +1102,75 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
 
     return 0;
 }
+
+/*
+ * This zeroes as many clusters of nb_clusters as possible at once (i.e.
+ * all clusters in the same L2 table) and returns the number of zeroed
+ * clusters.
+ */
+static int zero_single_l2(BlockDriverState *bs, uint64_t offset,
+    unsigned int nb_clusters)
+{
+    BDRVQcowState *s = bs->opaque;
+    uint64_t *l2_table;
+    int l2_index;
+    int ret;
+    int i;
+
+    ret = get_cluster_table(bs, offset, &l2_table, &l2_index);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* Limit nb_clusters to one L2 table */
+    nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
+
+    for (i = 0; i < nb_clusters; i++) {
+        uint64_t old_offset;
+
+        old_offset = be64_to_cpu(l2_table[l2_index + i]);
+
+        /* Update L2 entries */
+        qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
+        if (old_offset & QCOW_OFLAG_COMPRESSED) {
+            l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
+            qcow2_free_any_clusters(bs, old_offset, 1);
+        } else {
+            l2_table[l2_index + i] |= cpu_to_be64(QCOW_OFLAG_ZERO);
+        }
+    }
+
+    ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
+    if (ret < 0) {
+        return ret;
+    }
+
+    return nb_clusters;
+}
+
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors)
+{
+    BDRVQcowState *s = bs->opaque;
+    unsigned int nb_clusters;
+    int ret;
+
+    /* The zero flag is only supported by version 3 and newer */
+    if (s->qcow_version < 3) {
+        return -ENOTSUP;
+    }
+
+    /* Each L2 table is handled by its own loop iteration */
+    nb_clusters = size_to_clusters(s, nb_sectors << BDRV_SECTOR_BITS);
+
+    while (nb_clusters > 0) {
+        ret = zero_single_l2(bs, offset, nb_clusters);
+        if (ret < 0) {
+            return ret;
+        }
+
+        nb_clusters -= ret;
+        offset += (ret * s->cluster_size);
+    }
+
+    return 0;
+}
diff --git a/block/qcow2.c b/block/qcow2.c
index 002e138..6f8228f 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -1289,6 +1289,26 @@ static int qcow2_make_empty(BlockDriverState *bs)
     return 0;
 }
 
+static coroutine_fn int qcow2_co_write_zeroes(BlockDriverState *bs,
+    int64_t sector_num, int nb_sectors)
+{
+    int ret;
+    BDRVQcowState *s = bs->opaque;
+
+    /* Emulate misaligned zero writes */
+    if (sector_num % s->cluster_sectors || nb_sectors % s->cluster_sectors) {
+        return -ENOTSUP;
+    }
+
+    /* Whatever is left can use real zero clusters */
+    qemu_co_mutex_lock(&s->lock);
+    ret = qcow2_zero_clusters(bs, sector_num << BDRV_SECTOR_BITS,
+        nb_sectors);
+    qemu_co_mutex_unlock(&s->lock);
+
+    return ret;
+}
+
 static coroutine_fn int qcow2_co_discard(BlockDriverState *bs,
     int64_t sector_num, int nb_sectors)
 {
@@ -1566,6 +1586,7 @@ static BlockDriver bdrv_qcow2 = {
     .bdrv_co_writev         = qcow2_co_writev,
     .bdrv_co_flush_to_os    = qcow2_co_flush_to_os,
 
+    .bdrv_co_write_zeroes   = qcow2_co_write_zeroes,
     .bdrv_co_discard        = qcow2_co_discard,
     .bdrv_truncate          = qcow2_truncate,
     .bdrv_write_compressed  = qcow2_write_compressed,
diff --git a/block/qcow2.h b/block/qcow2.h
index 1adf01d..1143245 100644
--- a/block/qcow2.h
+++ b/block/qcow2.h
@@ -282,6 +282,7 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
 int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
 int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
     int nb_sectors);
+int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
 
 /* qcow2-snapshot.c functions */
 int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);
-- 
1.7.6.5