@@ -940,7 +940,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags)
}
}
- /* TODO: differencing files, write */
+ /* TODO: differencing files */
return 0;
fail:
@@ -1069,7 +1069,43 @@ exit:
return ret;
}
+/*
+ * Allocate a new payload block at the end of the file.
+ *
+ * Allocation will happen at 1MB alignment inside the file
+ *
+ * Returns the file offset start of the new payload block
+ */
+static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
+ uint64_t *new_offset)
+{
+ *new_offset = bdrv_getlength(bs->file);
+
+ /* per the spec, the address for a block is in units of 1MB */
+ *new_offset = ROUND_UP(*new_offset, 1024*1024);
+
+ return bdrv_truncate(bs->file, *new_offset + s->block_size);
+}
+
+/*
+ * Update the BAT tablet entry with the new file offset, and the new entry
+ * state */
+static void vhdx_update_bat_table_entry(BlockDriverState *bs, BDRVVHDXState *s,
+ VHDXSectorInfo *sinfo,
+ uint64_t *bat_entry,
+ uint64_t *bat_offset, int state)
+{
+ /* The BAT entry is a uint64, with 44 bits for the file offset in units of
+ * 1MB, and 3 bits for the block state. */
+ s->bat[sinfo->bat_idx] = ((sinfo->file_offset>>20) <<
+ VHDX_BAT_FILE_OFF_BITS);
+ s->bat[sinfo->bat_idx] |= state & VHDX_BAT_STATE_BIT_MASK;
+
+ *bat_entry = cpu_to_le64(s->bat[sinfo->bat_idx]);
+ *bat_offset = s->bat_offset + sinfo->bat_idx * sizeof(VHDXBatEntry);
+
+}
/* Per the spec, on the first write of guest-visible data to the file the
* data write guid must be updated in the header */
@@ -1086,7 +1122,117 @@ int vhdx_user_visible_write(BlockDriverState *bs, BDRVVHDXState *s)
static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov)
{
- return -ENOTSUP;
+ int ret = -ENOTSUP;
+ BDRVVHDXState *s = bs->opaque;
+ VHDXSectorInfo sinfo;
+ uint64_t bytes_done = 0;
+ uint64_t bat_entry = 0;
+ uint64_t bat_entry_offset = 0;
+ bool bat_update;
+ QEMUIOVector hd_qiov;
+
+ qemu_iovec_init(&hd_qiov, qiov->niov);
+
+ qemu_co_mutex_lock(&s->lock);
+
+ ret = vhdx_user_visible_write(bs, s);
+ if (ret < 0) {
+ goto exit;
+ }
+
+ while (nb_sectors > 0) {
+ if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
+ /* not supported yet */
+ ret = -ENOTSUP;
+ goto exit;
+ } else {
+ bat_update = false;
+ vhdx_block_translate(s, sector_num, nb_sectors, &sinfo);
+
+ qemu_iovec_reset(&hd_qiov);
+ qemu_iovec_concat(&hd_qiov, qiov, bytes_done, sinfo.bytes_avail);
+ /* check the payload block state */
+ switch (s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK) {
+ case PAYLOAD_BLOCK_ZERO:
+ /* in this case, we need to preserve zero writes for
+ * data that is not part of this write, so we must pad
+ * the rest of the buffer to zeroes */
+
+ /* if we are on a posix system with ftruncate() that extends
+ * a file, then it is zero-filled for us. On Win32, the raw
+ * layer uses SetFilePointer and SetFileEnd, which does not
+ * zero fill AFAIK */
+
+ /* TODO: queue another write of zero buffers if the host OS does
+ * not zero-fill on file extension */
+
+ /* fall through */
+ case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
+ case PAYLOAD_BLOCK_UNMAPPED: /* fall through */
+ case PAYLOAD_BLOCK_UNDEFINED: /* fall through */
+ ret = vhdx_allocate_block(bs, s, &sinfo.file_offset);
+ if (ret < 0) {
+ goto exit;
+ }
+ /* once we support differencing files, this may also be
+ * partially present */
+ /* update block state to the newly specified state */
+ vhdx_update_bat_table_entry(bs, s, &sinfo, &bat_entry,
+ &bat_entry_offset,
+ PAYLOAD_BLOCK_FULL_PRESENT);
+ bat_update = true;
+ /* since we just allocated a block, file_offset is the
+ * beginning of the payload block. It needs to be the
+ * write address, which includes the offset into the block */
+ sinfo.file_offset += sinfo.block_offset;
+ /* fall through */
+ case PAYLOAD_BLOCK_FULL_PRESENT:
+ /* if the file offset address is in the header zone,
+ * there is a problem */
+ if (sinfo.file_offset < (1024*1024)) {
+ ret = -EFAULT;
+ goto exit;
+ }
+ /* block exists, so we can just overwrite it */
+ qemu_co_mutex_unlock(&s->lock);
+ ret = bdrv_co_writev(bs->file,
+ sinfo.file_offset>>BDRV_SECTOR_BITS,
+ sinfo.sectors_avail, &hd_qiov);
+ qemu_co_mutex_lock(&s->lock);
+ if (ret < 0) {
+ goto exit;
+ }
+ break;
+ case PAYLOAD_BLOCK_PARTIALLY_PRESENT:
+ /* we don't yet support difference files, fall through
+ * to error */
+ default:
+ ret = -EIO;
+ goto exit;
+ break;
+ }
+
+ if (bat_update) {
+ /* this will update the BAT entry into the log journal, and
+ * then flush the log journal out to disk */
+ ret = vhdx_log_write_and_flush(bs, s, &bat_entry,
+ sizeof(VHDXBatEntry),
+ bat_entry_offset);
+ if (ret < 0) {
+ goto exit;
+ }
+ }
+
+ nb_sectors -= sinfo.sectors_avail;
+ sector_num += sinfo.sectors_avail;
+ bytes_done += sinfo.bytes_avail;
+
+ }
+ }
+
+exit:
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
}
This adds support for writing to VHDX image files, using coroutines. Writes into the BAT table goes through the VHDX log. Currently, BAT table writes occur when expanding a dynamic VHDX file, and allocating a new BAT entry. Signed-off-by: Jeff Cody <jcody@redhat.com> --- block/vhdx.c | 150 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 148 insertions(+), 2 deletions(-)