#define VMDK3_MAGIC (('C' << 24) | ('O' << 16) | ('W' << 8) | 'D')
#define VMDK4_MAGIC (('K' << 24) | ('D' << 16) | ('M' << 8) | 'V')
#define VMDK4_COMPRESSION_DEFLATE 1
+#define VMDK4_FLAG_NL_DETECT (1 << 0)
#define VMDK4_FLAG_RGD (1 << 1)
+/* Zeroed-grain enable bit */
+#define VMDK4_FLAG_ZERO_GRAIN (1 << 2)
#define VMDK4_FLAG_COMPRESS (1 << 16)
#define VMDK4_FLAG_MARKER (1 << 17)
#define VMDK4_GD_AT_END 0xffffffffffffffffULL
+#define VMDK_GTE_ZEROED 0x1
+
+/* VMDK internal error codes */
+#define VMDK_OK 0
+#define VMDK_ERROR (-1)
+/* Cluster not allocated */
+#define VMDK_UNALLOC (-2)
+#define VMDK_ZEROED (-3)
+
+#define BLOCK_OPT_ZEROED_GRAIN "zeroed_grain"
+
typedef struct {
uint32_t version;
uint32_t flags;
bool flat;
bool compressed;
bool has_marker;
+ bool has_zero_grain;
+ int version;
int64_t sectors;
int64_t end_sector;
int64_t flat_start_offset;
extent->compressed =
le16_to_cpu(header.compressAlgorithm) == VMDK4_COMPRESSION_DEFLATE;
extent->has_marker = le32_to_cpu(header.flags) & VMDK4_FLAG_MARKER;
+ extent->version = le32_to_cpu(header.version);
+ extent->has_zero_grain = le32_to_cpu(header.flags) & VMDK4_FLAG_ZERO_GRAIN;
ret = vmdk_init_tables(bs, extent);
if (ret) {
/* free extent allocated by vmdk_add_extent */
opt_pos = strstr(desc, opt_name);
if (!opt_pos) {
- return -1;
+ return VMDK_ERROR;
}
/* Skip "=\"" following opt_name */
opt_pos += strlen(opt_name) + 2;
if (opt_pos >= end) {
- return -1;
+ return VMDK_ERROR;
}
opt_end = opt_pos;
while (opt_end < end && *opt_end != '"') {
opt_end++;
}
if (opt_end == end || buf_size < opt_end - opt_pos + 1) {
- return -1;
+ return VMDK_ERROR;
}
pstrcpy(buf, opt_end - opt_pos + 1, opt_pos);
- return 0;
+ return VMDK_OK;
}
/* Open an extent file and append to bs array */
int ret;
if (!vmdk_is_cid_valid(bs)) {
- return -1;
+ return VMDK_ERROR;
}
/* floor offset to cluster */
ret = bdrv_read(bs->backing_hd, offset >> 9, whole_grain,
extent->cluster_sectors);
if (ret < 0) {
- return -1;
+ return VMDK_ERROR;
}
/* Write grain only into the active image */
ret = bdrv_write(extent->file, cluster_offset, whole_grain,
extent->cluster_sectors);
if (ret < 0) {
- return -1;
+ return VMDK_ERROR;
}
}
- return 0;
+ return VMDK_OK;
}
static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data)
{
+ uint32_t offset;
+ QEMU_BUILD_BUG_ON(sizeof(offset) != sizeof(m_data->offset));
+ offset = cpu_to_le32(m_data->offset);
/* update L2 table */
if (bdrv_pwrite_sync(
extent->file,
((int64_t)m_data->l2_offset * 512)
+ (m_data->l2_index * sizeof(m_data->offset)),
- &(m_data->offset),
- sizeof(m_data->offset)
- ) < 0) {
- return -1;
+ &offset, sizeof(offset)) < 0) {
+ return VMDK_ERROR;
}
/* update backup L2 table */
if (extent->l1_backup_table_offset != 0) {
extent->file,
((int64_t)m_data->l2_offset * 512)
+ (m_data->l2_index * sizeof(m_data->offset)),
- &(m_data->offset), sizeof(m_data->offset)
- ) < 0) {
- return -1;
+ &offset, sizeof(offset)) < 0) {
+ return VMDK_ERROR;
}
}
- return 0;
+ return VMDK_OK;
}
static int get_cluster_offset(BlockDriverState *bs,
{
unsigned int l1_index, l2_offset, l2_index;
int min_index, i, j;
- uint32_t min_count, *l2_table, tmp = 0;
+ uint32_t min_count, *l2_table;
+ bool zeroed = false;
if (m_data) {
m_data->valid = 0;
}
if (extent->flat) {
*cluster_offset = extent->flat_start_offset;
- return 0;
+ return VMDK_OK;
}
offset -= (extent->end_sector - extent->sectors) * SECTOR_SIZE;
l1_index = (offset >> 9) / extent->l1_entry_sectors;
if (l1_index >= extent->l1_size) {
- return -1;
+ return VMDK_ERROR;
}
l2_offset = extent->l1_table[l1_index];
if (!l2_offset) {
- return -1;
+ return VMDK_UNALLOC;
}
for (i = 0; i < L2_CACHE_SIZE; i++) {
if (l2_offset == extent->l2_cache_offsets[i]) {
l2_table,
extent->l2_size * sizeof(uint32_t)
) != extent->l2_size * sizeof(uint32_t)) {
- return -1;
+ return VMDK_ERROR;
}
extent->l2_cache_offsets[min_index] = l2_offset;
l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
*cluster_offset = le32_to_cpu(l2_table[l2_index]);
- if (!*cluster_offset) {
+ if (extent->has_zero_grain && *cluster_offset == VMDK_GTE_ZEROED) {
+ zeroed = true;
+ }
+
+ if (!*cluster_offset || zeroed) {
if (!allocate) {
- return -1;
+ return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
}
/* Avoid the L2 tables update for the images that have snapshots. */
}
*cluster_offset >>= 9;
- tmp = cpu_to_le32(*cluster_offset);
- l2_table[l2_index] = tmp;
+ l2_table[l2_index] = cpu_to_le32(*cluster_offset);
/* First of all we write grain itself, to avoid race condition
* that may to corrupt the image.
*/
if (get_whole_cluster(
bs, extent, *cluster_offset, offset, allocate) == -1) {
- return -1;
+ return VMDK_ERROR;
}
if (m_data) {
- m_data->offset = tmp;
+ m_data->offset = *cluster_offset;
m_data->l1_index = l1_index;
m_data->l2_index = l2_index;
m_data->l2_offset = l2_offset;
}
}
*cluster_offset <<= 9;
- return 0;
+ return VMDK_OK;
}
static VmdkExtent *find_extent(BDRVVmdkState *s,
ret = get_cluster_offset(bs, extent, NULL,
sector_num * 512, 0, &offset);
qemu_co_mutex_unlock(&s->lock);
- /* get_cluster_offset returning 0 means success */
- ret = !ret;
+
+ ret = (ret == VMDK_OK || ret == VMDK_ZEROED);
index_in_cluster = sector_num % extent->cluster_sectors;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
}
- if (ret) {
+ if (ret != VMDK_OK) {
/* if not allocated, try to read from parent image, if exist */
- if (bs->backing_hd) {
+ if (bs->backing_hd && ret != VMDK_ZEROED) {
if (!vmdk_is_cid_valid(bs)) {
return -EINVAL;
}
sector_num << 9, !extent->compressed,
&cluster_offset);
if (extent->compressed) {
- if (ret == 0) {
+ if (ret == VMDK_OK) {
/* Refuse write to allocated cluster for streamOptimized */
fprintf(stderr,
"VMDK: can't write to allocated cluster"
static int vmdk_create_extent(const char *filename, int64_t filesize,
- bool flat, bool compress)
+ bool flat, bool compress, bool zeroed_grain)
{
int ret, i;
int fd = 0;
}
magic = cpu_to_be32(VMDK4_MAGIC);
memset(&header, 0, sizeof(header));
- header.version = 1;
- header.flags =
- 3 | (compress ? VMDK4_FLAG_COMPRESS | VMDK4_FLAG_MARKER : 0);
+ header.version = zeroed_grain ? 2 : 1;
+ header.flags = VMDK4_FLAG_RGD | VMDK4_FLAG_NL_DETECT
+ | (compress ? VMDK4_FLAG_COMPRESS | VMDK4_FLAG_MARKER : 0)
+ | (zeroed_grain ? VMDK4_FLAG_ZERO_GRAIN : 0);
header.compressAlgorithm = compress ? VMDK4_COMPRESSION_DEFLATE : 0;
header.capacity = filesize / 512;
header.granularity = 128;
if (filename == NULL || !strlen(filename)) {
fprintf(stderr, "Vmdk: no filename provided.\n");
- return -1;
+ return VMDK_ERROR;
}
p = strrchr(filename, '/');
if (p == NULL) {
if (p != NULL) {
p++;
if (p - filename >= buf_len) {
- return -1;
+ return VMDK_ERROR;
}
pstrcpy(path, p - filename + 1, filename);
} else {
postfix[0] = '\0';
} else {
if (q - p >= buf_len) {
- return -1;
+ return VMDK_ERROR;
}
pstrcpy(prefix, q - p + 1, p);
pstrcpy(postfix, buf_len, q);
}
- return 0;
+ return VMDK_OK;
}
static int relative_path(char *dest, int dest_size,
#endif
if (!(dest && base && target)) {
- return -1;
+ return VMDK_ERROR;
}
if (path_is_absolute(target)) {
pstrcpy(dest, dest_size, target);
- return 0;
+ return VMDK_OK;
}
while (base[i] == target[i]) {
i++;
pstrcat(dest, dest_size, sep);
}
pstrcat(dest, dest_size, q);
- return 0;
+ return VMDK_OK;
}
static int vmdk_create(const char *filename, QEMUOptionParameter *options)
char parent_desc_line[BUF_SIZE] = "";
uint32_t parent_cid = 0xffffffff;
uint32_t number_heads = 16;
+ bool zeroed_grain = false;
const char desc_template[] =
"# Disk DescriptorFile\n"
"version=1\n"
flags |= options->value.n ? BLOCK_FLAG_COMPAT6 : 0;
} else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
fmt = options->value.s;
+ } else if (!strcmp(options->name, BLOCK_OPT_ZEROED_GRAIN)) {
+ zeroed_grain |= options->value.n;
}
options++;
}
snprintf(ext_filename, sizeof(ext_filename), "%s%s",
path, desc_filename);
- if (vmdk_create_extent(ext_filename, size, flat, compress)) {
+ if (vmdk_create_extent(ext_filename, size,
+ flat, compress, zeroed_grain)) {
return -EINVAL;
}
filesize -= size;
"VMDK flat extent format, can be one of "
"{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
},
+ {
+ .name = BLOCK_OPT_ZEROED_GRAIN,
+ .type = OPT_FLAG,
+ .help = "Enable efficient zero writes using the zeroed-grain GTE feature"
+ },
{ NULL }
};
projects / qemu.git / blobdiff