VMDK: create different subformats

Add create option 'format', with enums:
    monolithicSparse
    monolithicFlat
    twoGbMaxExtentSparse
    twoGbMaxExtentFlat
Each creates a subformat image file. The default is monolithicSparse.

Signed-off-by: Fam Zheng <famcool@gmail.com>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2 files changed, 275 insertions, 229 deletions

diff --git a/block/vmdk.c b/block/vmdk.c
index e1fb962b53..b53c5f5eb3 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -156,8 +156,9 @@ static int vmdk_probe(const uint8_t *buf, int buf_size, const char *filename)
 #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 void vmdk_free_extents(BlockDriverState *bs)
 {
@@ -243,168 +244,6 @@ static int vmdk_is_cid_valid(BlockDriverState *bs)
     return 1;
 }
 
-static int vmdk_snapshot_create(const char *filename, const char *backing_file)
-{
-    int snp_fd, p_fd;
-    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;
-    }
-
-    /* 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;
-    }
-
-    memset(&header, 0, sizeof(header));
-    memcpy(&header,&hdr[4], sizeof(header)); // skip the VMDK4_MAGIC
-
-    if (ftruncate(snp_fd, header.grain_offset << 9)) {
-        ret = -errno;
-        goto fail;
-    }
-    /* the descriptor offset = 0x200 */
-    if (lseek(p_fd, 0x200, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail;
-    }
-    if (read(p_fd, p_desc, DESC_SIZE) != DESC_SIZE) {
-        ret = -errno;
-        goto fail;
-    }
-
-    if ((p_name = strstr(p_desc,"CID")) != NULL) {
-        p_name += sizeof("CID");
-        sscanf(p_name,"%x",&p_cid);
-    }
-
-    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(s_desc, sizeof(s_desc), desc_template, p_cid, p_cid, backing_file,
-             (uint32_t)header.capacity, real_filename);
-
-    /* write the descriptor */
-    if (lseek(snp_fd, 0x200, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail;
-    }
-    if (write(snp_fd, s_desc, strlen(s_desc)) == -1) {
-        ret = -errno;
-        goto fail;
-    }
-
-    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);
-
-    /* write RGD */
-    rgd_buf = qemu_malloc(gd_size);
-    if (lseek(p_fd, rgd_offset, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail_rgd;
-    }
-    if (read(p_fd, rgd_buf, gd_size) != gd_size) {
-        ret = -errno;
-        goto fail_rgd;
-    }
-    if (lseek(snp_fd, rgd_offset, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail_rgd;
-    }
-    if (write(snp_fd, rgd_buf, gd_size) == -1) {
-        ret = -errno;
-        goto fail_rgd;
-    }
-
-    /* write GD */
-    gd_buf = qemu_malloc(gd_size);
-    if (lseek(p_fd, gd_offset, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail_gd;
-    }
-    if (read(p_fd, gd_buf, gd_size) != gd_size) {
-        ret = -errno;
-        goto fail_gd;
-    }
-    if (lseek(snp_fd, gd_offset, SEEK_SET) == -1) {
-        ret = -errno;
-        goto fail_gd;
-    }
-    if (write(snp_fd, gd_buf, gd_size) == -1) {
-        ret = -errno;
-        goto fail_gd;
-    }
-    ret = 0;
-
-fail_gd:
-    qemu_free(gd_buf);
-fail_rgd:
-    qemu_free(rgd_buf);
-fail:
-    close(p_fd);
-    close(snp_fd);
-    return ret;
-}
-
 static int vmdk_parent_open(BlockDriverState *bs)
 {
     char *p_name;
@@ -1058,68 +897,40 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
     return 0;
 }
 
-static int vmdk_create(const char *filename, QEMUOptionParameter *options)
+
+static int vmdk_create_extent(const char *filename, int64_t filesize, bool flat)
 {
-    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 = 1;
     header.flags = 3; /* ?? */
-    header.capacity = total_size;
+    header.capacity = filesize / 512;
     header.granularity = 128;
     header.num_gtes_per_gte = 512;
 
-    grains = (total_size + header.granularity - 1) / header.granularity;
+    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;
@@ -1130,7 +941,6 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
        ((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);
@@ -1188,27 +998,255 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options)
         }
     }
 
-    /* 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));
-
-    /* write the descriptor */
-    lseek(fd, le64_to_cpu(header.desc_offset) << 9, SEEK_SET);
+    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;
+}
+
+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;
+    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")) {
+        fprintf(stderr, "VMDK: Unknown subformat: %s\n", fmt);
+        return -EINVAL;
+    }
+    split = !(strcmp(fmt, "twoGbMaxExtentFlat") &&
+              strcmp(fmt, "twoGbMaxExtentSparse"));
+    flat = !(strcmp(fmt, "monolithicFlat") &&
+             strcmp(fmt, "twoGbMaxExtentFlat"));
+    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)) {
+            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);
@@ -1252,6 +1290,13 @@ 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} "
+    },
     { NULL }
 };
 
diff --git a/block_int.h b/block_int.h
index 1e265d274d..8a7b6cbb42 100644
--- a/block_int.h
+++ b/block_int.h
@@ -39,6 +39,7 @@
 #define BLOCK_OPT_CLUSTER_SIZE  "cluster_size"
 #define BLOCK_OPT_TABLE_SIZE    "table_size"
 #define BLOCK_OPT_PREALLOC      "preallocation"
+#define BLOCK_OPT_SUBFMT        "subformat"
 
 typedef struct AIOPool {
     void (*cancel)(BlockDriverAIOCB *acb);