*/
#include "qemu-common.h"
-#include "block_int.h"
-#include "module.h"
-#include "migration.h"
+#include "block/block_int.h"
+#include "qemu/module.h"
+#include "migration/migration.h"
#include <zlib.h>
#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;
int64_t desc_offset;
int64_t desc_size;
int32_t num_gtes_per_gte;
- int64_t gd_offset;
int64_t rgd_offset;
+ int64_t gd_offset;
int64_t grain_offset;
char filler[1];
char check_bytes[4];
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;
uint8_t data[0];
} VmdkGrainMarker;
+enum {
+ MARKER_END_OF_STREAM = 0,
+ MARKER_GRAIN_TABLE = 1,
+ MARKER_GRAIN_DIRECTORY = 2,
+ MARKER_FOOTER = 3,
+};
+
static int vmdk_probe(const uint8_t *buf, int buf_size, const char *filename)
{
uint32_t magic;
return 1;
}
+/* Queue extents, if any, for reopen() */
+static int vmdk_reopen_prepare(BDRVReopenState *state,
+ BlockReopenQueue *queue, Error **errp)
+{
+ BDRVVmdkState *s;
+ int ret = -1;
+ int i;
+ VmdkExtent *e;
+
+ assert(state != NULL);
+ assert(state->bs != NULL);
+
+ if (queue == NULL) {
+ error_set(errp, ERROR_CLASS_GENERIC_ERROR,
+ "No reopen queue for VMDK extents");
+ goto exit;
+ }
+
+ s = state->bs->opaque;
+
+ assert(s != NULL);
+
+ for (i = 0; i < s->num_extents; i++) {
+ e = &s->extents[i];
+ if (e->file != state->bs->file) {
+ bdrv_reopen_queue(queue, e->file, state->flags);
+ }
+ }
+ ret = 0;
+
+exit:
+ return ret;
+}
+
static int vmdk_parent_open(BlockDriverState *bs)
{
char *p_name;
if (header.capacity == 0 && header.desc_offset) {
return vmdk_open_desc_file(bs, flags, header.desc_offset << 9);
}
+
+ if (le64_to_cpu(header.gd_offset) == VMDK4_GD_AT_END) {
+ /*
+ * The footer takes precedence over the header, so read it in. The
+ * footer starts at offset -1024 from the end: One sector for the
+ * footer, and another one for the end-of-stream marker.
+ */
+ struct {
+ struct {
+ uint64_t val;
+ uint32_t size;
+ uint32_t type;
+ uint8_t pad[512 - 16];
+ } QEMU_PACKED footer_marker;
+
+ uint32_t magic;
+ VMDK4Header header;
+ uint8_t pad[512 - 4 - sizeof(VMDK4Header)];
+
+ struct {
+ uint64_t val;
+ uint32_t size;
+ uint32_t type;
+ uint8_t pad[512 - 16];
+ } QEMU_PACKED eos_marker;
+ } QEMU_PACKED footer;
+
+ ret = bdrv_pread(file,
+ bs->file->total_sectors * 512 - 1536,
+ &footer, sizeof(footer));
+ if (ret < 0) {
+ return ret;
+ }
+
+ /* Some sanity checks for the footer */
+ if (be32_to_cpu(footer.magic) != VMDK4_MAGIC ||
+ le32_to_cpu(footer.footer_marker.size) != 0 ||
+ le32_to_cpu(footer.footer_marker.type) != MARKER_FOOTER ||
+ le64_to_cpu(footer.eos_marker.val) != 0 ||
+ le32_to_cpu(footer.eos_marker.size) != 0 ||
+ le32_to_cpu(footer.eos_marker.type) != MARKER_END_OF_STREAM)
+ {
+ return -EINVAL;
+ }
+
+ header = footer.header;
+ }
+
l1_entry_sectors = le32_to_cpu(header.num_gtes_per_gte)
* le64_to_cpu(header.granularity);
if (l1_entry_sectors == 0) {
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 */
return vmdk_open_vmdk4(bs, file, flags);
break;
default:
- return -EINVAL;
+ return -EMEDIUMTYPE;
break;
}
}
* RW [size in sectors] SPARSE "file-name.vmdk"
*/
flat_offset = -1;
- ret = sscanf(p, "%10s %" SCNd64 " %10s %511s %" SCNd64,
+ ret = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
access, §ors, type, fname, &flat_offset);
if (ret < 4 || strcmp(access, "RW")) {
goto next_line;
return -EINVAL;
}
- /* trim the quotation marks around */
- if (fname[0] == '"') {
- memmove(fname, fname + 1, strlen(fname));
- if (strlen(fname) <= 1 || fname[strlen(fname) - 1] != '"') {
- return -EINVAL;
- }
- fname[strlen(fname) - 1] = '\0';
- }
if (sectors <= 0 ||
(strcmp(type, "FLAT") && strcmp(type, "SPARSE")) ||
(strcmp(access, "RW"))) {
path_combine(extent_path, sizeof(extent_path),
desc_file_path, fname);
- ret = bdrv_file_open(&extent_file, extent_path, bs->open_flags);
+ ret = bdrv_file_open(&extent_file, extent_path, NULL, bs->open_flags);
if (ret) {
return ret;
}
}
buf[2047] = '\0';
if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {
- return -EINVAL;
+ return -EMEDIUMTYPE;
}
if (strcmp(ct, "monolithicFlat") &&
strcmp(ct, "twoGbMaxExtentSparse") &&
return vmdk_parse_extents(buf, bs, bs->file->filename);
}
-static int vmdk_open(BlockDriverState *bs, int flags)
+static int vmdk_open(BlockDriverState *bs, QDict *options, int flags)
{
int ret;
BDRVVmdkState *s = bs->opaque;
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;
BDRVVmdkState *s = bs->opaque;
int ret;
uint64_t n, index_in_cluster;
+ uint64_t extent_begin_sector, extent_relative_sector_num;
VmdkExtent *extent = NULL;
uint64_t cluster_offset;
ret = get_cluster_offset(
bs, extent, NULL,
sector_num << 9, 0, &cluster_offset);
- index_in_cluster = sector_num % extent->cluster_sectors;
+ extent_begin_sector = extent->end_sector - extent->sectors;
+ extent_relative_sector_num = sector_num - extent_begin_sector;
+ index_in_cluster = extent_relative_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;
}
VmdkExtent *extent = NULL;
int n, ret;
int64_t index_in_cluster;
+ uint64_t extent_begin_sector, extent_relative_sector_num;
uint64_t cluster_offset;
VmdkMetaData m_data;
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"
if (ret) {
return -EINVAL;
}
- index_in_cluster = sector_num % extent->cluster_sectors;
+ extent_begin_sector = extent->end_sector - extent->sectors;
+ extent_relative_sector_num = sector_num - extent_begin_sector;
+ index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
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)) {
- dest[dest_size - 1] = '\0';
- strncpy(dest, target, dest_size - 1);
- return 0;
+ pstrcpy(dest, dest_size, target);
+ 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)
int fd, idx = 0;
char desc[BUF_SIZE];
int64_t total_size = 0, filesize;
+ const char *adapter_type = NULL;
const char *backing_file = NULL;
const char *fmt = NULL;
int flags = 0;
const char *desc_extent_line;
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"
"\n"
"ddb.virtualHWVersion = \"%d\"\n"
"ddb.geometry.cylinders = \"%" PRId64 "\"\n"
- "ddb.geometry.heads = \"16\"\n"
+ "ddb.geometry.heads = \"%d\"\n"
"ddb.geometry.sectors = \"63\"\n"
- "ddb.adapterType = \"ide\"\n";
+ "ddb.adapterType = \"%s\"\n";
if (filename_decompose(filename, path, prefix, postfix, PATH_MAX)) {
return -EINVAL;
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n;
+ } else if (!strcmp(options->name, BLOCK_OPT_ADAPTER_TYPE)) {
+ adapter_type = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
backing_file = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_COMPAT6)) {
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++;
}
+ if (!adapter_type) {
+ adapter_type = "ide";
+ } else if (strcmp(adapter_type, "ide") &&
+ strcmp(adapter_type, "buslogic") &&
+ strcmp(adapter_type, "lsilogic") &&
+ strcmp(adapter_type, "legacyESX")) {
+ fprintf(stderr, "VMDK: Unknown adapter type: '%s'.\n", adapter_type);
+ return -EINVAL;
+ }
+ if (strcmp(adapter_type, "ide") != 0) {
+ /* that's the number of heads with which vmware operates when
+ creating, exporting, etc. vmdk files with a non-ide adapter type */
+ number_heads = 255;
+ }
if (!fmt) {
/* Default format to monolithicSparse */
fmt = "monolithicSparse";
if (backing_file) {
char parent_filename[PATH_MAX];
BlockDriverState *bs = bdrv_new("");
- ret = bdrv_open(bs, backing_file, 0, NULL);
+ ret = bdrv_open(bs, backing_file, NULL, 0, NULL);
if (ret != 0) {
bdrv_delete(bs);
return ret;
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;
parent_desc_line,
ext_desc_lines,
(flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
- total_size / (int64_t)(63 * 16 * 512));
+ total_size / (int64_t)(63 * number_heads * 512), number_heads,
+ adapter_type);
if (split || flat) {
fd = qemu_open(filename,
O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
+ {
+ .name = BLOCK_OPT_ADAPTER_TYPE,
+ .type = OPT_STRING,
+ .help = "Virtual adapter type, can be one of "
+ "ide (default), lsilogic, buslogic or legacyESX"
+ },
{
.name = BLOCK_OPT_BACKING_FILE,
.type = OPT_STRING,
"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 }
};
.instance_size = sizeof(BDRVVmdkState),
.bdrv_probe = vmdk_probe,
.bdrv_open = vmdk_open,
+ .bdrv_reopen_prepare = vmdk_reopen_prepare,
.bdrv_read = vmdk_co_read,
.bdrv_write = vmdk_co_write,
.bdrv_close = vmdk_close,
projects / qemu.git / blobdiff