#include "qemu-common.h"
#include "block_int.h"
#include "module.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_RGD (1 << 1)
+#define VMDK4_FLAG_COMPRESS (1 << 16)
+#define VMDK4_FLAG_MARKER (1 << 17)
typedef struct {
uint32_t version;
int64_t desc_offset;
int64_t desc_size;
int32_t num_gtes_per_gte;
- int64_t rgd_offset;
int64_t gd_offset;
+ int64_t rgd_offset;
int64_t grain_offset;
char filler[1];
char check_bytes[4];
-} __attribute__((packed)) VMDK4Header;
+ uint16_t compressAlgorithm;
+} QEMU_PACKED VMDK4Header;
#define L2_CACHE_SIZE 16
-typedef struct BDRVVmdkState {
- BlockDriverState *hd;
+typedef struct VmdkExtent {
+ BlockDriverState *file;
+ bool flat;
+ bool compressed;
+ bool has_marker;
+ int64_t sectors;
+ int64_t end_sector;
+ int64_t flat_start_offset;
int64_t l1_table_offset;
int64_t l1_backup_table_offset;
uint32_t *l1_table;
uint32_t l2_cache_counts[L2_CACHE_SIZE];
unsigned int cluster_sectors;
+} VmdkExtent;
+
+typedef struct BDRVVmdkState {
+ CoMutex lock;
+ int desc_offset;
+ bool cid_updated;
uint32_t parent_cid;
- int is_parent;
+ int num_extents;
+ /* Extent array with num_extents entries, ascend ordered by address */
+ VmdkExtent *extents;
} BDRVVmdkState;
typedef struct VmdkMetaData {
int valid;
} VmdkMetaData;
-typedef struct ActiveBDRVState{
- BlockDriverState *hd; // active image handler
- uint64_t cluster_offset; // current write offset
-}ActiveBDRVState;
-
-static ActiveBDRVState activeBDRV;
-
+typedef struct VmdkGrainMarker {
+ uint64_t lba;
+ uint32_t size;
+ uint8_t data[0];
+} VmdkGrainMarker;
static int vmdk_probe(const uint8_t *buf, int buf_size, const char *filename)
{
uint32_t magic;
- if (buf_size < 4)
+ if (buf_size < 4) {
return 0;
+ }
magic = be32_to_cpu(*(uint32_t *)buf);
if (magic == VMDK3_MAGIC ||
- magic == VMDK4_MAGIC)
+ magic == VMDK4_MAGIC) {
return 100;
- else
+ } else {
+ const char *p = (const char *)buf;
+ const char *end = p + buf_size;
+ while (p < end) {
+ if (*p == '#') {
+ /* skip comment line */
+ while (p < end && *p != '\n') {
+ p++;
+ }
+ p++;
+ continue;
+ }
+ if (*p == ' ') {
+ while (p < end && *p == ' ') {
+ p++;
+ }
+ /* skip '\r' if windows line endings used. */
+ if (p < end && *p == '\r') {
+ p++;
+ }
+ /* only accept blank lines before 'version=' line */
+ if (p == end || *p != '\n') {
+ return 0;
+ }
+ p++;
+ continue;
+ }
+ if (end - p >= strlen("version=X\n")) {
+ if (strncmp("version=1\n", p, strlen("version=1\n")) == 0 ||
+ strncmp("version=2\n", p, strlen("version=2\n")) == 0) {
+ return 100;
+ }
+ }
+ if (end - p >= strlen("version=X\r\n")) {
+ if (strncmp("version=1\r\n", p, strlen("version=1\r\n")) == 0 ||
+ strncmp("version=2\r\n", p, strlen("version=2\r\n")) == 0) {
+ return 100;
+ }
+ }
+ return 0;
+ }
return 0;
+ }
}
#define CHECK_CID 1
#define SECTOR_SIZE 512
-#define DESC_SIZE 20*SECTOR_SIZE // 20 sectors of 512 bytes each
-#define HEADER_SIZE 512 // first sector of 512 bytes
+#define DESC_SIZE (20 * SECTOR_SIZE) /* 20 sectors of 512 bytes each */
+#define BUF_SIZE 4096
+#define HEADER_SIZE 512 /* first sector of 512 bytes */
-static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
+static void vmdk_free_extents(BlockDriverState *bs)
+{
+ int i;
+ BDRVVmdkState *s = bs->opaque;
+ VmdkExtent *e;
+
+ for (i = 0; i < s->num_extents; i++) {
+ e = &s->extents[i];
+ g_free(e->l1_table);
+ g_free(e->l2_cache);
+ g_free(e->l1_backup_table);
+ if (e->file != bs->file) {
+ bdrv_delete(e->file);
+ }
+ }
+ g_free(s->extents);
+}
+
+static void vmdk_free_last_extent(BlockDriverState *bs)
{
BDRVVmdkState *s = bs->opaque;
+
+ if (s->num_extents == 0) {
+ return;
+ }
+ s->num_extents--;
+ s->extents = g_realloc(s->extents, s->num_extents * sizeof(VmdkExtent));
+}
+
+static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
+{
char desc[DESC_SIZE];
uint32_t cid;
const char *p_name, *cid_str;
size_t cid_str_size;
+ BDRVVmdkState *s = bs->opaque;
- /* the descriptor offset = 0x200 */
- if (bdrv_pread(s->hd, 0x200, desc, DESC_SIZE) != DESC_SIZE)
+ if (bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE) != DESC_SIZE) {
return 0;
+ }
if (parent) {
cid_str = "parentCID";
cid_str_size = sizeof("CID");
}
- if ((p_name = strstr(desc,cid_str)) != NULL) {
+ p_name = strstr(desc, cid_str);
+ if (p_name != NULL) {
p_name += cid_str_size;
- sscanf(p_name,"%x",&cid);
+ sscanf(p_name, "%x", &cid);
}
return cid;
static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
{
- BDRVVmdkState *s = bs->opaque;
char desc[DESC_SIZE], tmp_desc[DESC_SIZE];
char *p_name, *tmp_str;
+ BDRVVmdkState *s = bs->opaque;
- /* the descriptor offset = 0x200 */
- if (bdrv_pread(s->hd, 0x200, desc, DESC_SIZE) != DESC_SIZE)
- return -1;
+ memset(desc, 0, sizeof(desc));
+ if (bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE) != DESC_SIZE) {
+ return -EIO;
+ }
- tmp_str = strstr(desc,"parentCID");
+ tmp_str = strstr(desc, "parentCID");
pstrcpy(tmp_desc, sizeof(tmp_desc), tmp_str);
- if ((p_name = strstr(desc,"CID")) != NULL) {
+ p_name = strstr(desc, "CID");
+ if (p_name != NULL) {
p_name += sizeof("CID");
snprintf(p_name, sizeof(desc) - (p_name - desc), "%x\n", cid);
pstrcat(desc, sizeof(desc), tmp_desc);
}
- if (bdrv_pwrite(s->hd, 0x200, desc, DESC_SIZE) != DESC_SIZE)
- return -1;
+ if (bdrv_pwrite_sync(bs->file, s->desc_offset, desc, DESC_SIZE) < 0) {
+ return -EIO;
+ }
return 0;
}
uint32_t cur_pcid;
if (p_bs) {
- cur_pcid = vmdk_read_cid(p_bs,0);
- if (s->parent_cid != cur_pcid)
- // CID not valid
+ cur_pcid = vmdk_read_cid(p_bs, 0);
+ if (s->parent_cid != cur_pcid) {
+ /* CID not valid */
return 0;
+ }
}
#endif
- // CID valid
+ /* CID valid */
return 1;
}
-static int vmdk_snapshot_create(const char *filename, const char *backing_file)
+static int vmdk_parent_open(BlockDriverState *bs)
{
- int snp_fd, p_fd;
+ char *p_name;
+ char desc[DESC_SIZE + 1];
+ BDRVVmdkState *s = bs->opaque;
int ret;
- uint32_t p_cid;
- char *p_name, *gd_buf, *rgd_buf;
- const char *real_filename, *temp_str;
- VMDK4Header header;
- uint32_t gde_entries, gd_size;
- int64_t gd_offset, rgd_offset, capacity, gt_size;
- char p_desc[DESC_SIZE], s_desc[DESC_SIZE], hdr[HEADER_SIZE];
- static const char desc_template[] =
- "# Disk DescriptorFile\n"
- "version=1\n"
- "CID=%x\n"
- "parentCID=%x\n"
- "createType=\"monolithicSparse\"\n"
- "parentFileNameHint=\"%s\"\n"
- "\n"
- "# Extent description\n"
- "RW %u SPARSE \"%s\"\n"
- "\n"
- "# The Disk Data Base \n"
- "#DDB\n"
- "\n";
-
- snp_fd = open(filename, O_RDWR | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE, 0644);
- if (snp_fd < 0)
- return -errno;
- p_fd = open(backing_file, O_RDONLY | O_BINARY | O_LARGEFILE);
- if (p_fd < 0) {
- close(snp_fd);
- return -errno;
- }
- /* read the header */
- if (lseek(p_fd, 0x0, SEEK_SET) == -1) {
- ret = -errno;
- goto fail;
- }
- if (read(p_fd, hdr, HEADER_SIZE) != HEADER_SIZE) {
- ret = -errno;
- goto fail;
+ desc[DESC_SIZE] = '\0';
+ ret = bdrv_pread(bs->file, s->desc_offset, desc, DESC_SIZE);
+ if (ret < 0) {
+ return ret;
}
- /* write the header */
- if (lseek(snp_fd, 0x0, SEEK_SET) == -1) {
- ret = -errno;
- goto fail;
- }
- if (write(snp_fd, hdr, HEADER_SIZE) == -1) {
- ret = -errno;
- goto fail;
+ p_name = strstr(desc, "parentFileNameHint");
+ if (p_name != NULL) {
+ char *end_name;
+
+ p_name += sizeof("parentFileNameHint") + 1;
+ end_name = strchr(p_name, '\"');
+ if (end_name == NULL) {
+ return -EINVAL;
+ }
+ if ((end_name - p_name) > sizeof(bs->backing_file) - 1) {
+ return -EINVAL;
+ }
+
+ pstrcpy(bs->backing_file, end_name - p_name + 1, p_name);
}
- memset(&header, 0, sizeof(header));
- memcpy(&header,&hdr[4], sizeof(header)); // skip the VMDK4_MAGIC
+ return 0;
+}
- if (ftruncate(snp_fd, header.grain_offset << 9)) {
- ret = -errno;
- goto fail;
+/* Create and append extent to the extent array. Return the added VmdkExtent
+ * address. return NULL if allocation failed. */
+static VmdkExtent *vmdk_add_extent(BlockDriverState *bs,
+ BlockDriverState *file, bool flat, int64_t sectors,
+ int64_t l1_offset, int64_t l1_backup_offset,
+ uint32_t l1_size,
+ int l2_size, unsigned int cluster_sectors)
+{
+ VmdkExtent *extent;
+ BDRVVmdkState *s = bs->opaque;
+
+ s->extents = g_realloc(s->extents,
+ (s->num_extents + 1) * sizeof(VmdkExtent));
+ extent = &s->extents[s->num_extents];
+ s->num_extents++;
+
+ memset(extent, 0, sizeof(VmdkExtent));
+ extent->file = file;
+ extent->flat = flat;
+ extent->sectors = sectors;
+ extent->l1_table_offset = l1_offset;
+ extent->l1_backup_table_offset = l1_backup_offset;
+ extent->l1_size = l1_size;
+ extent->l1_entry_sectors = l2_size * cluster_sectors;
+ extent->l2_size = l2_size;
+ extent->cluster_sectors = cluster_sectors;
+
+ if (s->num_extents > 1) {
+ extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
+ } else {
+ extent->end_sector = extent->sectors;
}
- /* the descriptor offset = 0x200 */
- if (lseek(p_fd, 0x200, SEEK_SET) == -1) {
- ret = -errno;
- goto fail;
+ bs->total_sectors = extent->end_sector;
+ return extent;
+}
+
+static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent)
+{
+ int ret;
+ int l1_size, i;
+
+ /* read the L1 table */
+ l1_size = extent->l1_size * sizeof(uint32_t);
+ extent->l1_table = g_malloc(l1_size);
+ ret = bdrv_pread(extent->file,
+ extent->l1_table_offset,
+ extent->l1_table,
+ l1_size);
+ if (ret < 0) {
+ goto fail_l1;
}
- if (read(p_fd, p_desc, DESC_SIZE) != DESC_SIZE) {
- ret = -errno;
- goto fail;
+ for (i = 0; i < extent->l1_size; i++) {
+ le32_to_cpus(&extent->l1_table[i]);
}
- if ((p_name = strstr(p_desc,"CID")) != NULL) {
- p_name += sizeof("CID");
- sscanf(p_name,"%x",&p_cid);
+ if (extent->l1_backup_table_offset) {
+ extent->l1_backup_table = g_malloc(l1_size);
+ ret = bdrv_pread(extent->file,
+ extent->l1_backup_table_offset,
+ extent->l1_backup_table,
+ l1_size);
+ if (ret < 0) {
+ goto fail_l1b;
+ }
+ for (i = 0; i < extent->l1_size; i++) {
+ le32_to_cpus(&extent->l1_backup_table[i]);
+ }
}
- real_filename = filename;
- if ((temp_str = strrchr(real_filename, '\\')) != NULL)
- real_filename = temp_str + 1;
- if ((temp_str = strrchr(real_filename, '/')) != NULL)
- real_filename = temp_str + 1;
- if ((temp_str = strrchr(real_filename, ':')) != NULL)
- real_filename = temp_str + 1;
+ extent->l2_cache =
+ g_malloc(extent->l2_size * L2_CACHE_SIZE * sizeof(uint32_t));
+ return 0;
+ fail_l1b:
+ g_free(extent->l1_backup_table);
+ fail_l1:
+ g_free(extent->l1_table);
+ return ret;
+}
- snprintf(s_desc, sizeof(s_desc), desc_template, p_cid, p_cid, backing_file,
- (uint32_t)header.capacity, real_filename);
+static int vmdk_open_vmdk3(BlockDriverState *bs,
+ BlockDriverState *file,
+ int flags)
+{
+ int ret;
+ uint32_t magic;
+ VMDK3Header header;
+ VmdkExtent *extent;
- /* write the descriptor */
- if (lseek(snp_fd, 0x200, SEEK_SET) == -1) {
- ret = -errno;
- goto fail;
+ ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));
+ if (ret < 0) {
+ return ret;
}
- if (write(snp_fd, s_desc, strlen(s_desc)) == -1) {
- ret = -errno;
- goto fail;
+ extent = vmdk_add_extent(bs,
+ bs->file, false,
+ le32_to_cpu(header.disk_sectors),
+ le32_to_cpu(header.l1dir_offset) << 9,
+ 0, 1 << 6, 1 << 9,
+ le32_to_cpu(header.granularity));
+ ret = vmdk_init_tables(bs, extent);
+ if (ret) {
+ /* free extent allocated by vmdk_add_extent */
+ vmdk_free_last_extent(bs);
}
+ return ret;
+}
- gd_offset = header.gd_offset * SECTOR_SIZE; // offset of GD table
- rgd_offset = header.rgd_offset * SECTOR_SIZE; // offset of RGD table
- capacity = header.capacity * SECTOR_SIZE; // Extent size
- /*
- * Each GDE span 32M disk, means:
- * 512 GTE per GT, each GTE points to grain
- */
- gt_size = (int64_t)header.num_gtes_per_gte * header.granularity * SECTOR_SIZE;
- if (!gt_size) {
- ret = -EINVAL;
- goto fail;
- }
- gde_entries = (uint32_t)(capacity / gt_size); // number of gde/rgde
- gd_size = gde_entries * sizeof(uint32_t);
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+ int64_t desc_offset);
- /* write RGD */
- rgd_buf = qemu_malloc(gd_size);
- if (lseek(p_fd, rgd_offset, SEEK_SET) == -1) {
- ret = -errno;
- goto fail_rgd;
+static int vmdk_open_vmdk4(BlockDriverState *bs,
+ BlockDriverState *file,
+ int flags)
+{
+ int ret;
+ uint32_t magic;
+ uint32_t l1_size, l1_entry_sectors;
+ VMDK4Header header;
+ VmdkExtent *extent;
+ int64_t l1_backup_offset = 0;
+
+ ret = bdrv_pread(file, sizeof(magic), &header, sizeof(header));
+ if (ret < 0) {
+ return ret;
}
- if (read(p_fd, rgd_buf, gd_size) != gd_size) {
- ret = -errno;
- goto fail_rgd;
+ if (header.capacity == 0 && header.desc_offset) {
+ return vmdk_open_desc_file(bs, flags, header.desc_offset << 9);
}
- if (lseek(snp_fd, rgd_offset, SEEK_SET) == -1) {
- ret = -errno;
- goto fail_rgd;
+ l1_entry_sectors = le32_to_cpu(header.num_gtes_per_gte)
+ * le64_to_cpu(header.granularity);
+ if (l1_entry_sectors <= 0) {
+ return -EINVAL;
}
- if (write(snp_fd, rgd_buf, gd_size) == -1) {
- ret = -errno;
- goto fail_rgd;
+ l1_size = (le64_to_cpu(header.capacity) + l1_entry_sectors - 1)
+ / l1_entry_sectors;
+ if (le32_to_cpu(header.flags) & VMDK4_FLAG_RGD) {
+ l1_backup_offset = le64_to_cpu(header.rgd_offset) << 9;
}
+ extent = vmdk_add_extent(bs, file, false,
+ le64_to_cpu(header.capacity),
+ le64_to_cpu(header.gd_offset) << 9,
+ l1_backup_offset,
+ l1_size,
+ le32_to_cpu(header.num_gtes_per_gte),
+ le64_to_cpu(header.granularity));
+ extent->compressed =
+ le16_to_cpu(header.compressAlgorithm) == VMDK4_COMPRESSION_DEFLATE;
+ extent->has_marker = le32_to_cpu(header.flags) & VMDK4_FLAG_MARKER;
+ ret = vmdk_init_tables(bs, extent);
+ if (ret) {
+ /* free extent allocated by vmdk_add_extent */
+ vmdk_free_last_extent(bs);
+ }
+ return ret;
+}
- /* write GD */
- gd_buf = qemu_malloc(gd_size);
- if (lseek(p_fd, gd_offset, SEEK_SET) == -1) {
- ret = -errno;
- goto fail_gd;
+/* find an option value out of descriptor file */
+static int vmdk_parse_description(const char *desc, const char *opt_name,
+ char *buf, int buf_size)
+{
+ char *opt_pos, *opt_end;
+ const char *end = desc + strlen(desc);
+
+ opt_pos = strstr(desc, opt_name);
+ if (!opt_pos) {
+ return -1;
}
- if (read(p_fd, gd_buf, gd_size) != gd_size) {
- ret = -errno;
- goto fail_gd;
+ /* Skip "=\"" following opt_name */
+ opt_pos += strlen(opt_name) + 2;
+ if (opt_pos >= end) {
+ return -1;
}
- if (lseek(snp_fd, gd_offset, SEEK_SET) == -1) {
- ret = -errno;
- goto fail_gd;
+ opt_end = opt_pos;
+ while (opt_end < end && *opt_end != '"') {
+ opt_end++;
}
- if (write(snp_fd, gd_buf, gd_size) == -1) {
- ret = -errno;
- goto fail_gd;
+ if (opt_end == end || buf_size < opt_end - opt_pos + 1) {
+ return -1;
}
- ret = 0;
-
-fail_gd:
- qemu_free(gd_buf);
-fail_rgd:
- qemu_free(rgd_buf);
-fail:
- close(p_fd);
- close(snp_fd);
- return ret;
+ pstrcpy(buf, opt_end - opt_pos + 1, opt_pos);
+ return 0;
}
-static void vmdk_parent_close(BlockDriverState *bs)
+/* Open an extent file and append to bs array */
+static int vmdk_open_sparse(BlockDriverState *bs,
+ BlockDriverState *file,
+ int flags)
{
- if (bs->backing_hd)
- bdrv_close(bs->backing_hd);
+ uint32_t magic;
+
+ if (bdrv_pread(file, 0, &magic, sizeof(magic)) != sizeof(magic)) {
+ return -EIO;
+ }
+
+ magic = be32_to_cpu(magic);
+ switch (magic) {
+ case VMDK3_MAGIC:
+ return vmdk_open_vmdk3(bs, file, flags);
+ break;
+ case VMDK4_MAGIC:
+ return vmdk_open_vmdk4(bs, file, flags);
+ break;
+ default:
+ return -EINVAL;
+ break;
+ }
}
-static int parent_open = 0;
-static int vmdk_parent_open(BlockDriverState *bs, const char * filename)
+static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
+ const char *desc_file_path)
{
- BDRVVmdkState *s = bs->opaque;
- char *p_name;
- char desc[DESC_SIZE];
- char parent_img_name[1024];
-
- /* the descriptor offset = 0x200 */
- if (bdrv_pread(s->hd, 0x200, desc, DESC_SIZE) != DESC_SIZE)
- return -1;
+ int ret;
+ char access[11];
+ char type[11];
+ char fname[512];
+ const char *p = desc;
+ int64_t sectors = 0;
+ int64_t flat_offset;
+ char extent_path[PATH_MAX];
+ BlockDriverState *extent_file;
+
+ while (*p) {
+ /* parse extent line:
+ * RW [size in sectors] FLAT "file-name.vmdk" OFFSET
+ * or
+ * RW [size in sectors] SPARSE "file-name.vmdk"
+ */
+ flat_offset = -1;
+ ret = sscanf(p, "%10s %" SCNd64 " %10s %511s %" SCNd64,
+ access, §ors, type, fname, &flat_offset);
+ if (ret < 4 || strcmp(access, "RW")) {
+ goto next_line;
+ } else if (!strcmp(type, "FLAT")) {
+ if (ret != 5 || flat_offset < 0) {
+ return -EINVAL;
+ }
+ } else if (ret != 4) {
+ return -EINVAL;
+ }
- if ((p_name = strstr(desc,"parentFileNameHint")) != NULL) {
- char *end_name;
- struct stat file_buf;
+ /* 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"))) {
+ goto next_line;
+ }
- p_name += sizeof("parentFileNameHint") + 1;
- if ((end_name = strchr(p_name,'\"')) == NULL)
- return -1;
- if ((end_name - p_name) > sizeof (bs->backing_file) - 1)
- return -1;
+ path_combine(extent_path, sizeof(extent_path),
+ desc_file_path, fname);
+ ret = bdrv_file_open(&extent_file, extent_path, bs->open_flags);
+ if (ret) {
+ return ret;
+ }
- pstrcpy(bs->backing_file, end_name - p_name + 1, p_name);
- if (stat(bs->backing_file, &file_buf) != 0) {
- path_combine(parent_img_name, sizeof(parent_img_name),
- filename, bs->backing_file);
+ /* save to extents array */
+ if (!strcmp(type, "FLAT")) {
+ /* FLAT extent */
+ VmdkExtent *extent;
+
+ extent = vmdk_add_extent(bs, extent_file, true, sectors,
+ 0, 0, 0, 0, sectors);
+ extent->flat_start_offset = flat_offset << 9;
+ } else if (!strcmp(type, "SPARSE")) {
+ /* SPARSE extent */
+ ret = vmdk_open_sparse(bs, extent_file, bs->open_flags);
+ if (ret) {
+ bdrv_delete(extent_file);
+ return ret;
+ }
} else {
- pstrcpy(parent_img_name, sizeof(parent_img_name),
- bs->backing_file);
+ fprintf(stderr,
+ "VMDK: Not supported extent type \"%s\""".\n", type);
+ return -ENOTSUP;
}
-
- bs->backing_hd = bdrv_new("");
- if (!bs->backing_hd) {
- failure:
- bdrv_close(s->hd);
- return -1;
+next_line:
+ /* move to next line */
+ while (*p && *p != '\n') {
+ p++;
}
- parent_open = 1;
- if (bdrv_open(bs->backing_hd, parent_img_name, 0, NULL) < 0)
- goto failure;
- parent_open = 0;
+ p++;
}
-
return 0;
}
-static int vmdk_open(BlockDriverState *bs, const char *filename, int flags)
+static int vmdk_open_desc_file(BlockDriverState *bs, int flags,
+ int64_t desc_offset)
{
+ int ret;
+ char buf[2048];
+ char ct[128];
BDRVVmdkState *s = bs->opaque;
- uint32_t magic;
- int l1_size, i, ret;
- if (parent_open) {
- /* Parent must be opened as RO, no RDWR. */
- flags = 0;
- }
-
- ret = bdrv_file_open(&s->hd, filename, flags);
- if (ret < 0)
+ ret = bdrv_pread(bs->file, desc_offset, buf, sizeof(buf));
+ if (ret < 0) {
return ret;
- if (bdrv_pread(s->hd, 0, &magic, sizeof(magic)) != sizeof(magic))
- goto fail;
-
- magic = be32_to_cpu(magic);
- if (magic == VMDK3_MAGIC) {
- VMDK3Header header;
-
- if (bdrv_pread(s->hd, sizeof(magic), &header, sizeof(header)) != sizeof(header))
- goto fail;
- s->cluster_sectors = le32_to_cpu(header.granularity);
- s->l2_size = 1 << 9;
- s->l1_size = 1 << 6;
- bs->total_sectors = le32_to_cpu(header.disk_sectors);
- s->l1_table_offset = le32_to_cpu(header.l1dir_offset) << 9;
- s->l1_backup_table_offset = 0;
- s->l1_entry_sectors = s->l2_size * s->cluster_sectors;
- } else if (magic == VMDK4_MAGIC) {
- VMDK4Header header;
-
- if (bdrv_pread(s->hd, sizeof(magic), &header, sizeof(header)) != sizeof(header))
- goto fail;
- bs->total_sectors = le64_to_cpu(header.capacity);
- s->cluster_sectors = le64_to_cpu(header.granularity);
- s->l2_size = le32_to_cpu(header.num_gtes_per_gte);
- s->l1_entry_sectors = s->l2_size * s->cluster_sectors;
- if (s->l1_entry_sectors <= 0)
- goto fail;
- s->l1_size = (bs->total_sectors + s->l1_entry_sectors - 1)
- / s->l1_entry_sectors;
- s->l1_table_offset = le64_to_cpu(header.rgd_offset) << 9;
- s->l1_backup_table_offset = le64_to_cpu(header.gd_offset) << 9;
-
- if (parent_open)
- s->is_parent = 1;
- else
- s->is_parent = 0;
-
- // try to open parent images, if exist
- if (vmdk_parent_open(bs, filename) != 0)
- goto fail;
- // write the CID once after the image creation
- s->parent_cid = vmdk_read_cid(bs,1);
- } else {
- goto fail;
}
-
- /* read the L1 table */
- l1_size = s->l1_size * sizeof(uint32_t);
- s->l1_table = qemu_malloc(l1_size);
- if (bdrv_pread(s->hd, s->l1_table_offset, s->l1_table, l1_size) != l1_size)
- goto fail;
- for(i = 0; i < s->l1_size; i++) {
- le32_to_cpus(&s->l1_table[i]);
+ buf[2047] = '\0';
+ if (vmdk_parse_description(buf, "createType", ct, sizeof(ct))) {
+ return -EINVAL;
+ }
+ if (strcmp(ct, "monolithicFlat") &&
+ strcmp(ct, "twoGbMaxExtentSparse") &&
+ strcmp(ct, "twoGbMaxExtentFlat")) {
+ fprintf(stderr,
+ "VMDK: Not supported image type \"%s\""".\n", ct);
+ return -ENOTSUP;
}
+ s->desc_offset = 0;
+ return vmdk_parse_extents(buf, bs, bs->file->filename);
+}
- if (s->l1_backup_table_offset) {
- s->l1_backup_table = qemu_malloc(l1_size);
- if (bdrv_pread(s->hd, s->l1_backup_table_offset, s->l1_backup_table, l1_size) != l1_size)
+static int vmdk_open(BlockDriverState *bs, int flags)
+{
+ int ret;
+ BDRVVmdkState *s = bs->opaque;
+
+ if (vmdk_open_sparse(bs, bs->file, flags) == 0) {
+ s->desc_offset = 0x200;
+ } else {
+ ret = vmdk_open_desc_file(bs, flags, 0);
+ if (ret) {
goto fail;
- for(i = 0; i < s->l1_size; i++) {
- le32_to_cpus(&s->l1_backup_table[i]);
}
}
+ /* try to open parent images, if exist */
+ ret = vmdk_parent_open(bs);
+ if (ret) {
+ goto fail;
+ }
+ s->parent_cid = vmdk_read_cid(bs, 1);
+ qemu_co_mutex_init(&s->lock);
+ return ret;
- s->l2_cache = qemu_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint32_t));
- return 0;
- fail:
- qemu_free(s->l1_backup_table);
- qemu_free(s->l1_table);
- qemu_free(s->l2_cache);
- bdrv_delete(s->hd);
- return -1;
+fail:
+ vmdk_free_extents(bs);
+ return ret;
}
-static uint64_t get_cluster_offset(BlockDriverState *bs, VmdkMetaData *m_data,
- uint64_t offset, int allocate);
-
-static int get_whole_cluster(BlockDriverState *bs, uint64_t cluster_offset,
- uint64_t offset, int allocate)
+static int get_whole_cluster(BlockDriverState *bs,
+ VmdkExtent *extent,
+ uint64_t cluster_offset,
+ uint64_t offset,
+ bool allocate)
{
- uint64_t parent_cluster_offset;
- BDRVVmdkState *s = bs->opaque;
- uint8_t whole_grain[s->cluster_sectors*512]; // 128 sectors * 512 bytes each = grain size 64KB
+ /* 128 sectors * 512 bytes each = grain size 64KB */
+ uint8_t whole_grain[extent->cluster_sectors * 512];
- // we will be here if it's first write on non-exist grain(cluster).
- // try to read from parent image, if exist
+ /* we will be here if it's first write on non-exist grain(cluster).
+ * try to read from parent image, if exist */
if (bs->backing_hd) {
- BDRVVmdkState *ps = bs->backing_hd->opaque;
+ int ret;
- if (!vmdk_is_cid_valid(bs))
+ if (!vmdk_is_cid_valid(bs)) {
return -1;
+ }
- parent_cluster_offset = get_cluster_offset(bs->backing_hd, NULL,
- offset, allocate);
-
- if (parent_cluster_offset) {
- BDRVVmdkState *act_s = activeBDRV.hd->opaque;
-
- if (bdrv_pread(ps->hd, parent_cluster_offset, whole_grain, ps->cluster_sectors*512) != ps->cluster_sectors*512)
- return -1;
+ /* floor offset to cluster */
+ offset -= offset % (extent->cluster_sectors * 512);
+ ret = bdrv_read(bs->backing_hd, offset >> 9, whole_grain,
+ extent->cluster_sectors);
+ if (ret < 0) {
+ return -1;
+ }
- //Write grain only into the active image
- if (bdrv_pwrite(act_s->hd, activeBDRV.cluster_offset << 9, whole_grain, sizeof(whole_grain)) != sizeof(whole_grain))
- return -1;
+ /* 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 0;
}
-static int vmdk_L2update(BlockDriverState *bs, VmdkMetaData *m_data)
+static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data)
{
- BDRVVmdkState *s = bs->opaque;
-
/* update L2 table */
- if (bdrv_pwrite(s->hd, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(m_data->offset)),
- &(m_data->offset), sizeof(m_data->offset)) != sizeof(m_data->offset))
+ 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;
+ }
/* update backup L2 table */
- if (s->l1_backup_table_offset != 0) {
- m_data->l2_offset = s->l1_backup_table[m_data->l1_index];
- if (bdrv_pwrite(s->hd, ((int64_t)m_data->l2_offset * 512) + (m_data->l2_index * sizeof(m_data->offset)),
- &(m_data->offset), sizeof(m_data->offset)) != sizeof(m_data->offset))
+ if (extent->l1_backup_table_offset != 0) {
+ m_data->l2_offset = extent->l1_backup_table[m_data->l1_index];
+ 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;
+ }
}
return 0;
}
-static uint64_t get_cluster_offset(BlockDriverState *bs, VmdkMetaData *m_data,
- uint64_t offset, int allocate)
+static int get_cluster_offset(BlockDriverState *bs,
+ VmdkExtent *extent,
+ VmdkMetaData *m_data,
+ uint64_t offset,
+ int allocate,
+ uint64_t *cluster_offset)
{
- BDRVVmdkState *s = bs->opaque;
unsigned int l1_index, l2_offset, l2_index;
int min_index, i, j;
uint32_t min_count, *l2_table, tmp = 0;
- uint64_t cluster_offset;
- if (m_data)
+ if (m_data) {
m_data->valid = 0;
-
- l1_index = (offset >> 9) / s->l1_entry_sectors;
- if (l1_index >= s->l1_size)
- return 0;
- l2_offset = s->l1_table[l1_index];
- if (!l2_offset)
+ }
+ if (extent->flat) {
+ *cluster_offset = extent->flat_start_offset;
return 0;
- for(i = 0; i < L2_CACHE_SIZE; i++) {
- if (l2_offset == s->l2_cache_offsets[i]) {
+ }
+
+ offset -= (extent->end_sector - extent->sectors) * SECTOR_SIZE;
+ l1_index = (offset >> 9) / extent->l1_entry_sectors;
+ if (l1_index >= extent->l1_size) {
+ return -1;
+ }
+ l2_offset = extent->l1_table[l1_index];
+ if (!l2_offset) {
+ return -1;
+ }
+ for (i = 0; i < L2_CACHE_SIZE; i++) {
+ if (l2_offset == extent->l2_cache_offsets[i]) {
/* increment the hit count */
- if (++s->l2_cache_counts[i] == 0xffffffff) {
- for(j = 0; j < L2_CACHE_SIZE; j++) {
- s->l2_cache_counts[j] >>= 1;
+ if (++extent->l2_cache_counts[i] == 0xffffffff) {
+ for (j = 0; j < L2_CACHE_SIZE; j++) {
+ extent->l2_cache_counts[j] >>= 1;
}
}
- l2_table = s->l2_cache + (i * s->l2_size);
+ l2_table = extent->l2_cache + (i * extent->l2_size);
goto found;
}
}
/* not found: load a new entry in the least used one */
min_index = 0;
min_count = 0xffffffff;
- for(i = 0; i < L2_CACHE_SIZE; i++) {
- if (s->l2_cache_counts[i] < min_count) {
- min_count = s->l2_cache_counts[i];
+ for (i = 0; i < L2_CACHE_SIZE; i++) {
+ if (extent->l2_cache_counts[i] < min_count) {
+ min_count = extent->l2_cache_counts[i];
min_index = i;
}
}
- l2_table = s->l2_cache + (min_index * s->l2_size);
- if (bdrv_pread(s->hd, (int64_t)l2_offset * 512, l2_table, s->l2_size * sizeof(uint32_t)) !=
- s->l2_size * sizeof(uint32_t))
- return 0;
+ l2_table = extent->l2_cache + (min_index * extent->l2_size);
+ if (bdrv_pread(
+ extent->file,
+ (int64_t)l2_offset * 512,
+ l2_table,
+ extent->l2_size * sizeof(uint32_t)
+ ) != extent->l2_size * sizeof(uint32_t)) {
+ return -1;
+ }
- s->l2_cache_offsets[min_index] = l2_offset;
- s->l2_cache_counts[min_index] = 1;
+ extent->l2_cache_offsets[min_index] = l2_offset;
+ extent->l2_cache_counts[min_index] = 1;
found:
- l2_index = ((offset >> 9) / s->cluster_sectors) % s->l2_size;
- cluster_offset = le32_to_cpu(l2_table[l2_index]);
+ l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
+ *cluster_offset = le32_to_cpu(l2_table[l2_index]);
- if (!cluster_offset) {
- if (!allocate)
- return 0;
- // Avoid the L2 tables update for the images that have snapshots.
- if (!s->is_parent) {
- cluster_offset = bdrv_getlength(s->hd);
- bdrv_truncate(s->hd, cluster_offset + (s->cluster_sectors << 9));
-
- cluster_offset >>= 9;
- tmp = cpu_to_le32(cluster_offset);
- l2_table[l2_index] = tmp;
- // Save the active image state
- activeBDRV.cluster_offset = cluster_offset;
- activeBDRV.hd = bs;
+ if (!*cluster_offset) {
+ if (!allocate) {
+ return -1;
+ }
+
+ /* Avoid the L2 tables update for the images that have snapshots. */
+ *cluster_offset = bdrv_getlength(extent->file);
+ if (!extent->compressed) {
+ bdrv_truncate(
+ extent->file,
+ *cluster_offset + (extent->cluster_sectors << 9)
+ );
}
+
+ *cluster_offset >>= 9;
+ tmp = cpu_to_le32(*cluster_offset);
+ l2_table[l2_index] = tmp;
+
/* First of all we write grain itself, to avoid race condition
* that may to corrupt the image.
* This problem may occur because of insufficient space on host disk
* or inappropriate VM shutdown.
*/
- if (get_whole_cluster(bs, cluster_offset, offset, allocate) == -1)
- return 0;
+ if (get_whole_cluster(
+ bs, extent, *cluster_offset, offset, allocate) == -1) {
+ return -1;
+ }
if (m_data) {
m_data->offset = tmp;
m_data->valid = 1;
}
}
- cluster_offset <<= 9;
- return cluster_offset;
+ *cluster_offset <<= 9;
+ return 0;
+}
+
+static VmdkExtent *find_extent(BDRVVmdkState *s,
+ int64_t sector_num, VmdkExtent *start_hint)
+{
+ VmdkExtent *extent = start_hint;
+
+ if (!extent) {
+ extent = &s->extents[0];
+ }
+ while (extent < &s->extents[s->num_extents]) {
+ if (sector_num < extent->end_sector) {
+ return extent;
+ }
+ extent++;
+ }
+ return NULL;
}
static int vmdk_is_allocated(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum)
{
BDRVVmdkState *s = bs->opaque;
- int index_in_cluster, n;
- uint64_t cluster_offset;
+ int64_t index_in_cluster, n, ret;
+ uint64_t offset;
+ VmdkExtent *extent;
- cluster_offset = get_cluster_offset(bs, NULL, sector_num << 9, 0);
- index_in_cluster = sector_num % s->cluster_sectors;
- n = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
+ extent = find_extent(s, sector_num, NULL);
+ if (!extent) {
+ return 0;
+ }
+ ret = get_cluster_offset(bs, extent, NULL,
+ sector_num * 512, 0, &offset);
+ /* get_cluster_offset returning 0 means success */
+ ret = !ret;
+
+ index_in_cluster = sector_num % extent->cluster_sectors;
+ n = extent->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors) {
n = nb_sectors;
+ }
*pnum = n;
- return (cluster_offset != 0);
+ return ret;
+}
+
+static int vmdk_write_extent(VmdkExtent *extent, int64_t cluster_offset,
+ int64_t offset_in_cluster, const uint8_t *buf,
+ int nb_sectors, int64_t sector_num)
+{
+ int ret;
+ VmdkGrainMarker *data = NULL;
+ uLongf buf_len;
+ const uint8_t *write_buf = buf;
+ int write_len = nb_sectors * 512;
+
+ if (extent->compressed) {
+ if (!extent->has_marker) {
+ ret = -EINVAL;
+ goto out;
+ }
+ buf_len = (extent->cluster_sectors << 9) * 2;
+ data = g_malloc(buf_len + sizeof(VmdkGrainMarker));
+ if (compress(data->data, &buf_len, buf, nb_sectors << 9) != Z_OK ||
+ buf_len == 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+ data->lba = sector_num;
+ data->size = buf_len;
+ write_buf = (uint8_t *)data;
+ write_len = buf_len + sizeof(VmdkGrainMarker);
+ }
+ ret = bdrv_pwrite(extent->file,
+ cluster_offset + offset_in_cluster,
+ write_buf,
+ write_len);
+ if (ret != write_len) {
+ ret = ret < 0 ? ret : -EIO;
+ goto out;
+ }
+ ret = 0;
+ out:
+ g_free(data);
+ return ret;
+}
+
+static int vmdk_read_extent(VmdkExtent *extent, int64_t cluster_offset,
+ int64_t offset_in_cluster, uint8_t *buf,
+ int nb_sectors)
+{
+ int ret;
+ int cluster_bytes, buf_bytes;
+ uint8_t *cluster_buf, *compressed_data;
+ uint8_t *uncomp_buf;
+ uint32_t data_len;
+ VmdkGrainMarker *marker;
+ uLongf buf_len;
+
+
+ if (!extent->compressed) {
+ ret = bdrv_pread(extent->file,
+ cluster_offset + offset_in_cluster,
+ buf, nb_sectors * 512);
+ if (ret == nb_sectors * 512) {
+ return 0;
+ } else {
+ return -EIO;
+ }
+ }
+ cluster_bytes = extent->cluster_sectors * 512;
+ /* Read two clusters in case GrainMarker + compressed data > one cluster */
+ buf_bytes = cluster_bytes * 2;
+ cluster_buf = g_malloc(buf_bytes);
+ uncomp_buf = g_malloc(cluster_bytes);
+ ret = bdrv_pread(extent->file,
+ cluster_offset,
+ cluster_buf, buf_bytes);
+ if (ret < 0) {
+ goto out;
+ }
+ compressed_data = cluster_buf;
+ buf_len = cluster_bytes;
+ data_len = cluster_bytes;
+ if (extent->has_marker) {
+ marker = (VmdkGrainMarker *)cluster_buf;
+ compressed_data = marker->data;
+ data_len = le32_to_cpu(marker->size);
+ }
+ if (!data_len || data_len > buf_bytes) {
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = uncompress(uncomp_buf, &buf_len, compressed_data, data_len);
+ if (ret != Z_OK) {
+ ret = -EINVAL;
+ goto out;
+
+ }
+ if (offset_in_cluster < 0 ||
+ offset_in_cluster + nb_sectors * 512 > buf_len) {
+ ret = -EINVAL;
+ goto out;
+ }
+ memcpy(buf, uncomp_buf + offset_in_cluster, nb_sectors * 512);
+ ret = 0;
+
+ out:
+ g_free(uncomp_buf);
+ g_free(cluster_buf);
+ return ret;
}
static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVVmdkState *s = bs->opaque;
- int index_in_cluster, n, ret;
+ int ret;
+ uint64_t n, index_in_cluster;
+ VmdkExtent *extent = NULL;
uint64_t cluster_offset;
while (nb_sectors > 0) {
- cluster_offset = get_cluster_offset(bs, NULL, sector_num << 9, 0);
- index_in_cluster = sector_num % s->cluster_sectors;
- n = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
+ extent = find_extent(s, sector_num, extent);
+ if (!extent) {
+ return -EIO;
+ }
+ ret = get_cluster_offset(
+ bs, extent, NULL,
+ sector_num << 9, 0, &cluster_offset);
+ index_in_cluster = sector_num % extent->cluster_sectors;
+ n = extent->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors) {
n = nb_sectors;
- if (!cluster_offset) {
- // try to read from parent image, if exist
+ }
+ if (ret) {
+ /* if not allocated, try to read from parent image, if exist */
if (bs->backing_hd) {
- if (!vmdk_is_cid_valid(bs))
- return -1;
+ if (!vmdk_is_cid_valid(bs)) {
+ return -EINVAL;
+ }
ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
- if (ret < 0)
- return -1;
+ if (ret < 0) {
+ return ret;
+ }
} else {
memset(buf, 0, 512 * n);
}
} else {
- if(bdrv_pread(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512) != n * 512)
- return -1;
+ ret = vmdk_read_extent(extent,
+ cluster_offset, index_in_cluster * 512,
+ buf, n);
+ if (ret) {
+ return ret;
+ }
}
nb_sectors -= n;
sector_num += n;
return 0;
}
+static coroutine_fn int vmdk_co_read(BlockDriverState *bs, int64_t sector_num,
+ uint8_t *buf, int nb_sectors)
+{
+ int ret;
+ BDRVVmdkState *s = bs->opaque;
+ qemu_co_mutex_lock(&s->lock);
+ ret = vmdk_read(bs, sector_num, buf, nb_sectors);
+ qemu_co_mutex_unlock(&s->lock);
+ return ret;
+}
+
static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVVmdkState *s = bs->opaque;
- VmdkMetaData m_data;
- int index_in_cluster, n;
+ VmdkExtent *extent = NULL;
+ int n, ret;
+ int64_t index_in_cluster;
uint64_t cluster_offset;
- static int cid_update = 0;
+ VmdkMetaData m_data;
if (sector_num > bs->total_sectors) {
fprintf(stderr,
"(VMDK) Wrong offset: sector_num=0x%" PRIx64
" total_sectors=0x%" PRIx64 "\n",
sector_num, bs->total_sectors);
- return -1;
+ return -EIO;
}
while (nb_sectors > 0) {
- index_in_cluster = sector_num & (s->cluster_sectors - 1);
- n = s->cluster_sectors - index_in_cluster;
- if (n > nb_sectors)
+ extent = find_extent(s, sector_num, extent);
+ if (!extent) {
+ return -EIO;
+ }
+ ret = get_cluster_offset(
+ bs,
+ extent,
+ &m_data,
+ sector_num << 9, !extent->compressed,
+ &cluster_offset);
+ if (extent->compressed) {
+ if (ret == 0) {
+ /* Refuse write to allocated cluster for streamOptimized */
+ fprintf(stderr,
+ "VMDK: can't write to allocated cluster"
+ " for streamOptimized\n");
+ return -EIO;
+ } else {
+ /* allocate */
+ ret = get_cluster_offset(
+ bs,
+ extent,
+ &m_data,
+ sector_num << 9, 1,
+ &cluster_offset);
+ }
+ }
+ if (ret) {
+ return -EINVAL;
+ }
+ index_in_cluster = sector_num % extent->cluster_sectors;
+ n = extent->cluster_sectors - index_in_cluster;
+ if (n > nb_sectors) {
n = nb_sectors;
- cluster_offset = get_cluster_offset(bs, &m_data, sector_num << 9, 1);
- if (!cluster_offset)
- return -1;
+ }
- if (bdrv_pwrite(s->hd, cluster_offset + index_in_cluster * 512, buf, n * 512) != n * 512)
- return -1;
+ ret = vmdk_write_extent(extent,
+ cluster_offset, index_in_cluster * 512,
+ buf, n, sector_num);
+ if (ret) {
+ return ret;
+ }
if (m_data.valid) {
/* update L2 tables */
- if (vmdk_L2update(bs, &m_data) == -1)
- return -1;
+ if (vmdk_L2update(extent, &m_data) == -1) {
+ return -EIO;
+ }
}
nb_sectors -= n;
sector_num += n;
buf += n * 512;
- // update CID on the first write every time the virtual disk is opened
- if (!cid_update) {
+ /* update CID on the first write every time the virtual disk is
+ * opened */
+ if (!s->cid_updated) {
vmdk_write_cid(bs, time(NULL));
- cid_update++;
+ s->cid_updated = true;
}
}
return 0;
}
-static int vmdk_create(const char *filename, QEMUOptionParameter *options)
+
+static int vmdk_create_extent(const char *filename, int64_t filesize,
+ bool flat, bool compress)
{
- int fd, i;
+ int ret, i;
+ int fd = 0;
VMDK4Header header;
uint32_t tmp, magic, grains, gd_size, gt_size, gt_count;
- static const char desc_template[] =
- "# Disk DescriptorFile\n"
- "version=1\n"
- "CID=%x\n"
- "parentCID=ffffffff\n"
- "createType=\"monolithicSparse\"\n"
- "\n"
- "# Extent description\n"
- "RW %" PRId64 " SPARSE \"%s\"\n"
- "\n"
- "# The Disk Data Base \n"
- "#DDB\n"
- "\n"
- "ddb.virtualHWVersion = \"%d\"\n"
- "ddb.geometry.cylinders = \"%" PRId64 "\"\n"
- "ddb.geometry.heads = \"16\"\n"
- "ddb.geometry.sectors = \"63\"\n"
- "ddb.adapterType = \"ide\"\n";
- char desc[1024];
- const char *real_filename, *temp_str;
- int64_t total_size = 0;
- const char *backing_file = NULL;
- int flags = 0;
- int ret;
- // Read out options
- while (options && options->name) {
- if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
- total_size = options->value.n / 512;
- } 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;
- }
- options++;
+ fd = open(
+ filename,
+ O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+ 0644);
+ if (fd < 0) {
+ return -errno;
}
-
- /* XXX: add support for backing file */
- if (backing_file) {
- return vmdk_snapshot_create(filename, backing_file);
+ if (flat) {
+ ret = ftruncate(fd, filesize);
+ if (ret < 0) {
+ ret = -errno;
+ }
+ goto exit;
}
-
- fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
- 0644);
- if (fd < 0)
- return -errno;
magic = cpu_to_be32(VMDK4_MAGIC);
memset(&header, 0, sizeof(header));
- header.version = cpu_to_le32(1);
- header.flags = cpu_to_le32(3); /* ?? */
- header.capacity = cpu_to_le64(total_size);
- header.granularity = cpu_to_le64(128);
- header.num_gtes_per_gte = cpu_to_le32(512);
-
- grains = (total_size + header.granularity - 1) / header.granularity;
+ header.version = 1;
+ header.flags =
+ 3 | (compress ? VMDK4_FLAG_COMPRESS | VMDK4_FLAG_MARKER : 0);
+ header.compressAlgorithm = compress ? VMDK4_COMPRESSION_DEFLATE : 0;
+ header.capacity = filesize / 512;
+ header.granularity = 128;
+ header.num_gtes_per_gte = 512;
+
+ grains = (filesize / 512 + header.granularity - 1) / header.granularity;
gt_size = ((header.num_gtes_per_gte * sizeof(uint32_t)) + 511) >> 9;
- gt_count = (grains + header.num_gtes_per_gte - 1) / header.num_gtes_per_gte;
+ gt_count =
+ (grains + header.num_gtes_per_gte - 1) / header.num_gtes_per_gte;
gd_size = (gt_count * sizeof(uint32_t) + 511) >> 9;
header.desc_offset = 1;
((header.gd_offset + gd_size + (gt_size * gt_count) +
header.granularity - 1) / header.granularity) *
header.granularity;
-
+ /* swap endianness for all header fields */
+ header.version = cpu_to_le32(header.version);
+ header.flags = cpu_to_le32(header.flags);
+ header.capacity = cpu_to_le64(header.capacity);
+ header.granularity = cpu_to_le64(header.granularity);
+ header.num_gtes_per_gte = cpu_to_le32(header.num_gtes_per_gte);
header.desc_offset = cpu_to_le64(header.desc_offset);
header.desc_size = cpu_to_le64(header.desc_size);
header.rgd_offset = cpu_to_le64(header.rgd_offset);
header.gd_offset = cpu_to_le64(header.gd_offset);
header.grain_offset = cpu_to_le64(header.grain_offset);
+ header.compressAlgorithm = cpu_to_le16(header.compressAlgorithm);
header.check_bytes[0] = 0xa;
header.check_bytes[1] = 0x20;
goto exit;
}
- ret = ftruncate(fd, header.grain_offset << 9);
+ ret = ftruncate(fd, le64_to_cpu(header.grain_offset) << 9);
if (ret < 0) {
ret = -errno;
goto exit;
/* write grain directory */
lseek(fd, le64_to_cpu(header.rgd_offset) << 9, SEEK_SET);
- for (i = 0, tmp = header.rgd_offset + gd_size;
+ for (i = 0, tmp = le64_to_cpu(header.rgd_offset) + gd_size;
i < gt_count; i++, tmp += gt_size) {
ret = qemu_write_full(fd, &tmp, sizeof(tmp));
if (ret != sizeof(tmp)) {
/* write backup grain directory */
lseek(fd, le64_to_cpu(header.gd_offset) << 9, SEEK_SET);
- for (i = 0, tmp = header.gd_offset + gd_size;
+ for (i = 0, tmp = le64_to_cpu(header.gd_offset) + gd_size;
i < gt_count; i++, tmp += gt_size) {
ret = qemu_write_full(fd, &tmp, sizeof(tmp));
if (ret != sizeof(tmp)) {
}
}
- /* compose the descriptor */
- real_filename = filename;
- if ((temp_str = strrchr(real_filename, '\\')) != NULL)
- real_filename = temp_str + 1;
- if ((temp_str = strrchr(real_filename, '/')) != NULL)
- real_filename = temp_str + 1;
- if ((temp_str = strrchr(real_filename, ':')) != NULL)
- real_filename = temp_str + 1;
- snprintf(desc, sizeof(desc), desc_template, (unsigned int)time(NULL),
- total_size, real_filename,
- (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
- total_size / (int64_t)(63 * 16));
+ ret = 0;
+ exit:
+ close(fd);
+ return ret;
+}
+
+static int filename_decompose(const char *filename, char *path, char *prefix,
+ char *postfix, size_t buf_len)
+{
+ const char *p, *q;
+
+ if (filename == NULL || !strlen(filename)) {
+ fprintf(stderr, "Vmdk: no filename provided.\n");
+ return -1;
+ }
+ p = strrchr(filename, '/');
+ if (p == NULL) {
+ p = strrchr(filename, '\\');
+ }
+ if (p == NULL) {
+ p = strrchr(filename, ':');
+ }
+ if (p != NULL) {
+ p++;
+ if (p - filename >= buf_len) {
+ return -1;
+ }
+ pstrcpy(path, p - filename + 1, filename);
+ } else {
+ p = filename;
+ path[0] = '\0';
+ }
+ q = strrchr(p, '.');
+ if (q == NULL) {
+ pstrcpy(prefix, buf_len, p);
+ postfix[0] = '\0';
+ } else {
+ if (q - p >= buf_len) {
+ return -1;
+ }
+ pstrcpy(prefix, q - p + 1, p);
+ pstrcpy(postfix, buf_len, q);
+ }
+ return 0;
+}
+
+static int relative_path(char *dest, int dest_size,
+ const char *base, const char *target)
+{
+ int i = 0;
+ int n = 0;
+ const char *p, *q;
+#ifdef _WIN32
+ const char *sep = "\\";
+#else
+ const char *sep = "/";
+#endif
+
+ if (!(dest && base && target)) {
+ return -1;
+ }
+ if (path_is_absolute(target)) {
+ dest[dest_size - 1] = '\0';
+ strncpy(dest, target, dest_size - 1);
+ return 0;
+ }
+ while (base[i] == target[i]) {
+ i++;
+ }
+ p = &base[i];
+ q = &target[i];
+ while (*p) {
+ if (*p == *sep) {
+ n++;
+ }
+ p++;
+ }
+ dest[0] = '\0';
+ for (; n; n--) {
+ pstrcat(dest, dest_size, "..");
+ pstrcat(dest, dest_size, sep);
+ }
+ pstrcat(dest, dest_size, q);
+ return 0;
+}
- /* write the descriptor */
- lseek(fd, le64_to_cpu(header.desc_offset) << 9, SEEK_SET);
+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 *backing_file = NULL;
+ const char *fmt = NULL;
+ int flags = 0;
+ int ret = 0;
+ bool flat, split, compress;
+ char ext_desc_lines[BUF_SIZE] = "";
+ char path[PATH_MAX], prefix[PATH_MAX], postfix[PATH_MAX];
+ const int64_t split_size = 0x80000000; /* VMDK has constant split size */
+ const char *desc_extent_line;
+ char parent_desc_line[BUF_SIZE] = "";
+ uint32_t parent_cid = 0xffffffff;
+ const char desc_template[] =
+ "# Disk DescriptorFile\n"
+ "version=1\n"
+ "CID=%x\n"
+ "parentCID=%x\n"
+ "createType=\"%s\"\n"
+ "%s"
+ "\n"
+ "# Extent description\n"
+ "%s"
+ "\n"
+ "# The Disk Data Base\n"
+ "#DDB\n"
+ "\n"
+ "ddb.virtualHWVersion = \"%d\"\n"
+ "ddb.geometry.cylinders = \"%" PRId64 "\"\n"
+ "ddb.geometry.heads = \"16\"\n"
+ "ddb.geometry.sectors = \"63\"\n"
+ "ddb.adapterType = \"ide\"\n";
+
+ if (filename_decompose(filename, path, prefix, postfix, PATH_MAX)) {
+ return -EINVAL;
+ }
+ /* Read out options */
+ while (options && options->name) {
+ if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+ total_size = options->value.n;
+ } 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;
+ }
+ options++;
+ }
+ if (!fmt) {
+ /* Default format to monolithicSparse */
+ fmt = "monolithicSparse";
+ } else if (strcmp(fmt, "monolithicFlat") &&
+ strcmp(fmt, "monolithicSparse") &&
+ strcmp(fmt, "twoGbMaxExtentSparse") &&
+ strcmp(fmt, "twoGbMaxExtentFlat") &&
+ strcmp(fmt, "streamOptimized")) {
+ fprintf(stderr, "VMDK: Unknown subformat: %s\n", fmt);
+ return -EINVAL;
+ }
+ split = !(strcmp(fmt, "twoGbMaxExtentFlat") &&
+ strcmp(fmt, "twoGbMaxExtentSparse"));
+ flat = !(strcmp(fmt, "monolithicFlat") &&
+ strcmp(fmt, "twoGbMaxExtentFlat"));
+ compress = !strcmp(fmt, "streamOptimized");
+ if (flat) {
+ desc_extent_line = "RW %lld FLAT \"%s\" 0\n";
+ } else {
+ desc_extent_line = "RW %lld SPARSE \"%s\"\n";
+ }
+ if (flat && backing_file) {
+ /* not supporting backing file for flat image */
+ return -ENOTSUP;
+ }
+ if (backing_file) {
+ char parent_filename[PATH_MAX];
+ BlockDriverState *bs = bdrv_new("");
+ ret = bdrv_open(bs, backing_file, 0, NULL);
+ if (ret != 0) {
+ bdrv_delete(bs);
+ return ret;
+ }
+ if (strcmp(bs->drv->format_name, "vmdk")) {
+ bdrv_delete(bs);
+ return -EINVAL;
+ }
+ filesize = bdrv_getlength(bs);
+ parent_cid = vmdk_read_cid(bs, 0);
+ bdrv_delete(bs);
+ relative_path(parent_filename, sizeof(parent_filename),
+ filename, backing_file);
+ snprintf(parent_desc_line, sizeof(parent_desc_line),
+ "parentFileNameHint=\"%s\"", parent_filename);
+ }
+
+ /* Create extents */
+ filesize = total_size;
+ while (filesize > 0) {
+ char desc_line[BUF_SIZE];
+ char ext_filename[PATH_MAX];
+ char desc_filename[PATH_MAX];
+ int64_t size = filesize;
+
+ if (split && size > split_size) {
+ size = split_size;
+ }
+ if (split) {
+ snprintf(desc_filename, sizeof(desc_filename), "%s-%c%03d%s",
+ prefix, flat ? 'f' : 's', ++idx, postfix);
+ } else if (flat) {
+ snprintf(desc_filename, sizeof(desc_filename), "%s-flat%s",
+ prefix, postfix);
+ } else {
+ snprintf(desc_filename, sizeof(desc_filename), "%s%s",
+ prefix, postfix);
+ }
+ snprintf(ext_filename, sizeof(ext_filename), "%s%s",
+ path, desc_filename);
+
+ if (vmdk_create_extent(ext_filename, size, flat, compress)) {
+ return -EINVAL;
+ }
+ filesize -= size;
+
+ /* Format description line */
+ snprintf(desc_line, sizeof(desc_line),
+ desc_extent_line, size / 512, desc_filename);
+ pstrcat(ext_desc_lines, sizeof(ext_desc_lines), desc_line);
+ }
+ /* generate descriptor file */
+ snprintf(desc, sizeof(desc), desc_template,
+ (unsigned int)time(NULL),
+ parent_cid,
+ fmt,
+ parent_desc_line,
+ ext_desc_lines,
+ (flags & BLOCK_FLAG_COMPAT6 ? 6 : 4),
+ total_size / (int64_t)(63 * 16 * 512));
+ if (split || flat) {
+ fd = open(
+ filename,
+ O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
+ 0644);
+ } else {
+ fd = open(
+ filename,
+ O_WRONLY | O_BINARY | O_LARGEFILE,
+ 0644);
+ }
+ if (fd < 0) {
+ return -errno;
+ }
+ /* the descriptor offset = 0x200 */
+ if (!split && !flat && 0x200 != lseek(fd, 0x200, SEEK_SET)) {
+ ret = -errno;
+ goto exit;
+ }
ret = qemu_write_full(fd, desc, strlen(desc));
if (ret != strlen(desc)) {
ret = -errno;
goto exit;
}
-
ret = 0;
exit:
close(fd);
static void vmdk_close(BlockDriverState *bs)
{
+ vmdk_free_extents(bs);
+}
+
+static int vmdk_flush(BlockDriverState *bs)
+{
+ int i, ret, err;
BDRVVmdkState *s = bs->opaque;
- qemu_free(s->l1_table);
- qemu_free(s->l2_cache);
- // try to close parent image, if exist
- vmdk_parent_close(s->hd);
- bdrv_delete(s->hd);
+ ret = bdrv_flush(bs->file);
+ for (i = 0; i < s->num_extents; i++) {
+ err = bdrv_flush(s->extents[i].file);
+ if (err < 0) {
+ ret = err;
+ }
+ }
+ return ret;
}
-static void vmdk_flush(BlockDriverState *bs)
+static int64_t vmdk_get_allocated_file_size(BlockDriverState *bs)
{
+ int i;
+ int64_t ret = 0;
+ int64_t r;
BDRVVmdkState *s = bs->opaque;
- bdrv_flush(s->hd);
-}
+ ret = bdrv_get_allocated_file_size(bs->file);
+ if (ret < 0) {
+ return ret;
+ }
+ for (i = 0; i < s->num_extents; i++) {
+ if (s->extents[i].file == bs->file) {
+ continue;
+ }
+ r = bdrv_get_allocated_file_size(s->extents[i].file);
+ if (r < 0) {
+ return r;
+ }
+ ret += r;
+ }
+ return ret;
+}
static QEMUOptionParameter vmdk_create_options[] = {
{
.type = OPT_FLAG,
.help = "VMDK version 6 image"
},
+ {
+ .name = BLOCK_OPT_SUBFMT,
+ .type = OPT_STRING,
+ .help =
+ "VMDK flat extent format, can be one of "
+ "{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
+ },
{ NULL }
};
static BlockDriver bdrv_vmdk = {
- .format_name = "vmdk",
- .instance_size = sizeof(BDRVVmdkState),
- .bdrv_probe = vmdk_probe,
- .bdrv_file_open = vmdk_open,
- .bdrv_read = vmdk_read,
- .bdrv_write = vmdk_write,
- .bdrv_close = vmdk_close,
- .bdrv_create = vmdk_create,
- .bdrv_flush = vmdk_flush,
- .bdrv_is_allocated = vmdk_is_allocated,
+ .format_name = "vmdk",
+ .instance_size = sizeof(BDRVVmdkState),
+ .bdrv_probe = vmdk_probe,
+ .bdrv_open = vmdk_open,
+ .bdrv_read = vmdk_co_read,
+ .bdrv_write = vmdk_write,
+ .bdrv_close = vmdk_close,
+ .bdrv_create = vmdk_create,
+ .bdrv_flush = vmdk_flush,
+ .bdrv_is_allocated = vmdk_is_allocated,
+ .bdrv_get_allocated_file_size = vmdk_get_allocated_file_size,
.create_options = vmdk_create_options,
};
projects / qemu.git / blobdiff