[Qemu-devel] [PATCH 1/2 v7] block: add-cow file format

[Dong Xu Wang]

From: Dong Xu Wang <address@hidden>

Provide a new file format: add-cow. The usage can be found in add-cow.txt of
this patch.

CC: Marcelo Tosatti <address@hidden>
CC: Kevin Wolf <address@hidden>
CC: Stefan Hajnoczi <address@hidden>
Signed-off-by: Dong Xu Wang <address@hidden>
---
 Makefile.objs          |    1 +
 block.c                |    2 +-
 block.h                |    1 +
 block/add-cow.c        |  402 ++++++++++++++++++++++++++++++++++++++++++++++++
 block_int.h            |    1 +
 docs/specs/add-cow.txt |   68 ++++++++
 6 files changed, 474 insertions(+), 1 deletions(-)
 create mode 100644 block/add-cow.c
 create mode 100644 docs/specs/add-cow.txt

diff --git a/Makefile.objs b/Makefile.objs
index 808de6a..fa9dde0 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -34,6 +34,7 @@ block-nested-y += raw.o cow.o qcow.o vdi.o vmdk.o cloop.o 
dmg.o bochs.o vpc.o vv
 block-nested-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o 
qcow2-cache.o
 block-nested-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
 block-nested-y += qed-check.o
+block-nested-y += add-cow.o add-cow-cache.o
 block-nested-y += parallels.o nbd.o blkdebug.o sheepdog.o blkverify.o
 block-nested-y += stream.o
 block-nested-$(CONFIG_WIN32) += raw-win32.o
diff --git a/block.c b/block.c
index 52ffe14..581c092 100644
--- a/block.c
+++ b/block.c
@@ -194,7 +194,7 @@ static void bdrv_io_limits_intercept(BlockDriverState *bs,
 }
 
 /* check if the path starts with "<protocol>:" */
-static int path_has_protocol(const char *path)
+int path_has_protocol(const char *path)
 {
 #ifdef _WIN32
     if (is_windows_drive(path) ||
diff --git a/block.h b/block.h
index 48d0bf3..3d96444 100644
--- a/block.h
+++ b/block.h
@@ -310,6 +310,7 @@ char *bdrv_snapshot_dump(char *buf, int buf_size, 
QEMUSnapshotInfo *sn);
 
 char *get_human_readable_size(char *buf, int buf_size, int64_t size);
 int path_is_absolute(const char *path);
+int path_has_protocol(const char *path);
 void path_combine(char *dest, int dest_size,
                   const char *base_path,
                   const char *filename);
diff --git a/block/add-cow.c b/block/add-cow.c
new file mode 100644
index 0000000..6897a52
--- /dev/null
+++ b/block/add-cow.c
@@ -0,0 +1,402 @@
+/*
+ * QEMU ADD-COW Disk Format
+ *
+ * Copyright IBM, Corp. 2012
+ *
+ * Authors:
+ *  Dong Xu Wang <address@hidden>
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "block_int.h"
+#include "module.h"
+#include "add-cow.h"
+
+static int add_cow_probe(const uint8_t *buf, int buf_size, const char 
*filename)
+{
+    const AddCowHeader *header = (const void *)buf;
+
+    if (be64_to_cpu(header->magic) == ADD_COW_MAGIC &&
+        be32_to_cpu(header->version) == ADD_COW_VERSION) {
+        return 100;
+    } else {
+        return 0;
+    }
+}
+
+static int add_cow_open(BlockDriverState *bs, int flags)
+{
+    AddCowHeader        header;
+    char                image_filename[ADD_COW_FILE_LEN];
+    BlockDriver         *image_drv = NULL;
+    int                 ret;
+    BDRVAddCowState     *s = bs->opaque;
+
+    ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
+    if (ret != sizeof(header)) {
+        goto fail;
+    }
+
+    if (be64_to_cpu(header.magic) != ADD_COW_MAGIC) {
+        ret = -EINVAL;
+        goto fail;
+    }
+    if (be32_to_cpu(header.version) != ADD_COW_VERSION) {
+        char version[64];
+        snprintf(version, sizeof(version), "ADD-COW version %d", 
header.version);
+        qerror_report(QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
+            bs->device_name, "add-cow", version);
+        ret = -ENOTSUP;
+        goto fail;
+    }
+
+    QEMU_BUILD_BUG_ON(sizeof(bs->backing_file) != sizeof(header.backing_file));
+    strncpy(bs->backing_file, header.backing_file,
+            sizeof(bs->backing_file));
+
+    if (header.image_file[0] == '\0') {
+        ret = -ENOENT;
+        goto fail;
+    }
+    s->image_hd = bdrv_new("");
+    if (path_has_protocol(header.image_file)) {
+        strncpy(image_filename, header.image_file, sizeof(image_filename));
+    } else {
+        path_combine(image_filename, sizeof(image_filename),
+                     bs->filename, header.image_file);
+    }
+
+    image_drv = bdrv_find_format("raw");
+    ret = bdrv_open(s->image_hd, image_filename, flags, image_drv);
+    if (ret < 0) {
+        bdrv_delete(s->image_hd);
+        goto fail;
+    }
+    bs->total_sectors = s->image_hd->total_sectors;
+    s->cluster_size = ADD_COW_CLUSTER_SIZE;
+    s->bitmap_cache = add_cow_cache_create(bs, ADD_COW_CACHE_SIZE);
+    qemu_co_mutex_init(&s->lock);
+    return 0;
+ fail:
+    return ret;
+}
+
+static inline bool is_bit_set(BlockDriverState *bs, int64_t bitnum)
+{
+    BDRVAddCowState *s = bs->opaque;
+    uint64_t offset = bitnum >> 3;
+    uint8_t *bitmap;
+    int ret = add_cow_cache_get(bs, s->bitmap_cache,
+        offset & ~(ADD_COW_CLUSTER_SIZE - 1), (void **)&bitmap);
+    if (ret < 0) {
+        abort();
+    }
+
+    return *(bitmap + (offset & (ADD_COW_CLUSTER_SIZE - 1))) & (1 << (bitnum % 
8));
+}
+
+static coroutine_fn int add_cow_is_allocated(BlockDriverState *bs,
+        int64_t sector_num, int nb_sectors, int *num_same)
+{
+    int changed;
+
+    if (nb_sectors == 0) {
+        *num_same = nb_sectors;
+        return 0;
+    }
+
+    changed = is_bit_set(bs, sector_num);
+    for (*num_same = 1; *num_same < nb_sectors; (*num_same)++) {
+        if (is_bit_set(bs, sector_num + *num_same) != changed) {
+            break;
+        }
+    }
+
+    return changed;
+}
+
+static int add_cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
+        int nb_sectors)
+{
+    BDRVAddCowState *s = bs->opaque;
+    uint8_t *bitmap;
+
+    int i, ret = 0;
+    for (i = 0; i < nb_sectors; i++) {
+        int ret = add_cow_cache_get(bs, s->bitmap_cache,
+            (sector_num + i) / 8 & ~(ADD_COW_CLUSTER_SIZE - 1), (void 
**)&bitmap);
+        if (ret < 0) {
+            abort();
+        }
+        *(bitmap + ((sector_num + i) / 8 & (ADD_COW_CLUSTER_SIZE - 1))) |=
+                    (1 << ((sector_num + i) % 8));
+        add_cow_cache_entry_mark_dirty(s->bitmap_cache, bitmap);
+
+    }
+    ret = add_cow_cache_flush(bs, s->bitmap_cache);
+    if (ret < 0) {
+        abort();
+    }
+    return ret;
+}
+
+static void add_cow_close(BlockDriverState *bs)
+{
+    BDRVAddCowState *s = bs->opaque;
+    add_cow_cache_destroy(bs, s->bitmap_cache);
+    bdrv_delete(s->image_hd);
+}
+static int add_cow_create(const char *filename, QEMUOptionParameter *options)
+{
+    AddCowHeader header;
+    int64_t image_sectors = 0;
+    const char *backing_filename = NULL;
+    const char *image_filename = NULL;
+    int ret;
+    BlockDriverState *bs, *image_bs = NULL, *backing_bs = NULL;
+
+    while (options && options->name) {
+        if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
+            image_sectors = options->value.n / BDRV_SECTOR_SIZE;
+        } else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
+            backing_filename = options->value.s;
+        } else if (!strcmp(options->name, BLOCK_OPT_IMAGE_FILE)) {
+            image_filename = options->value.s;
+        }
+        options++;
+    }
+
+    if (!backing_filename || !image_filename) {
+        error_report("Both backing_file and image_file should be given.");
+        return -EINVAL;
+    }
+
+    ret = bdrv_file_open(&image_bs, image_filename, BDRV_O_RDWR
+            | BDRV_O_CACHE_WB);
+    if (ret < 0) {
+        return ret;
+    }
+    image_sectors = image_bs->total_sectors;
+    bdrv_delete(image_bs);
+
+    ret = bdrv_file_open(&backing_bs, backing_filename, BDRV_O_RDWR
+            | BDRV_O_CACHE_WB);
+    if (ret < 0) {
+        return ret;
+    }
+    bdrv_delete(backing_bs);
+
+    ret = bdrv_create_file(filename, NULL);
+    if (ret < 0) {
+        return ret;
+    }
+
+    ret = bdrv_file_open(&bs, filename, BDRV_O_RDWR);
+    if (ret < 0) {
+        return ret;
+    }
+
+    memset(&header, 0, sizeof(header));
+    header.magic = cpu_to_be64(ADD_COW_MAGIC);
+    header.version = cpu_to_be32(ADD_COW_VERSION);
+    strncpy(header.backing_file, backing_filename, 
sizeof(header.backing_file));
+    strncpy(header.image_file, image_filename, sizeof(header.image_file));
+
+    ret = bdrv_pwrite(bs, 0, &header, sizeof(header));
+    if (ret < 0) {
+        bdrv_delete(bs);
+        return ret;
+    }
+
+    BlockDriver *drv = bdrv_find_format("add-cow");
+    assert(drv != NULL);
+    ret = bdrv_open(bs, filename, BDRV_O_RDWR | BDRV_O_NO_FLUSH, drv);
+    if (ret < 0) {
+        bdrv_delete(bs);
+        return ret;
+    }
+
+    ret = bdrv_truncate(bs, image_sectors * BDRV_SECTOR_SIZE);
+    bdrv_delete(bs);
+    return ret;
+}
+
+static int add_cow_backing_read(BlockDriverState *bs, QEMUIOVector *qiov,
+                  int64_t sector_num, int nb_sectors)
+{
+    int n1;
+    if ((sector_num + nb_sectors) <= bs->total_sectors) {
+        return nb_sectors;
+    }
+    if (sector_num >= bs->total_sectors) {
+        n1 = 0;
+    } else {
+        n1 = bs->total_sectors - sector_num;
+    }
+
+    qemu_iovec_memset_skip(qiov, 0, BDRV_SECTOR_SIZE * (nb_sectors - n1),
+            BDRV_SECTOR_SIZE * n1);
+    return n1;
+}
+
+static coroutine_fn int add_cow_co_readv(BlockDriverState *bs, int64_t 
sector_num,
+                         int remaining_sectors, QEMUIOVector *qiov)
+{
+    BDRVAddCowState *s = bs->opaque;
+    int cur_nr_sectors;
+    uint64_t bytes_done = 0;
+    QEMUIOVector hd_qiov;
+    int n, n1, ret = 0;
+
+    qemu_iovec_init(&hd_qiov, qiov->niov);
+    qemu_co_mutex_lock(&s->lock);
+    while (remaining_sectors != 0) {
+        cur_nr_sectors = remaining_sectors;
+        if (add_cow_is_allocated(bs, sector_num, cur_nr_sectors, &n)) {
+            cur_nr_sectors = n;
+            qemu_iovec_reset(&hd_qiov);
+            qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
+                            cur_nr_sectors * BDRV_SECTOR_SIZE);
+            ret = bdrv_co_readv(s->image_hd, sector_num, n, &hd_qiov);
+            if (ret < 0) {
+                goto fail;
+            }
+        } else {
+            cur_nr_sectors = n;
+            if (bs->backing_hd) {
+                n1 = add_cow_backing_read(bs->backing_hd, &hd_qiov,
+                    sector_num, cur_nr_sectors);
+                if (n1 > 0) {
+                    qemu_iovec_reset(&hd_qiov);
+                    qemu_iovec_copy(&hd_qiov, qiov, bytes_done,
+                                cur_nr_sectors * BDRV_SECTOR_SIZE);
+                    ret = bdrv_co_readv(bs->backing_hd, sector_num,
+                                        n, &hd_qiov);
+                    if (ret < 0) {
+                        goto fail;
+                    }
+                }
+            } else {
+                qemu_iovec_reset(&hd_qiov);
+            }
+        }
+        remaining_sectors -= cur_nr_sectors;
+        sector_num += cur_nr_sectors;
+        bytes_done += cur_nr_sectors * BDRV_SECTOR_SIZE;
+    }
+fail:
+    qemu_co_mutex_unlock(&s->lock);
+    qemu_iovec_destroy(&hd_qiov);
+    return ret;
+}
+
+static coroutine_fn int add_cow_co_writev(BlockDriverState *bs, int64_t 
sector_num,
+                          int remaining_sectors, QEMUIOVector *qiov)
+{
+    BDRVAddCowState *s = bs->opaque;
+    int ret = 0;
+    QEMUIOVector hd_qiov;
+    qemu_iovec_init(&hd_qiov, qiov->niov);
+    qemu_co_mutex_lock(&s->lock);
+    qemu_iovec_reset(&hd_qiov);
+    qemu_iovec_copy(&hd_qiov, qiov, 0, remaining_sectors * BDRV_SECTOR_SIZE);
+    ret = bdrv_co_writev(s->image_hd,
+                     sector_num,
+                     remaining_sectors, &hd_qiov);
+    if (ret < 0) {
+        goto fail;
+    }
+
+    ret = add_cow_update_bitmap(bs, sector_num, remaining_sectors);
+    if (ret < 0) {
+        goto fail;
+    }
+fail:
+    qemu_co_mutex_unlock(&s->lock);
+    qemu_iovec_destroy(&hd_qiov);
+    return ret;
+}
+
+static int bdrv_add_cow_truncate(BlockDriverState *bs, int64_t offset)
+{
+    int ret = 0;
+    int64_t image_sectors = offset / BDRV_SECTOR_SIZE;
+    BDRVAddCowState *s = bs->opaque;
+    int64_t old_image_sector = s->image_hd->total_sectors;
+
+    ret = bdrv_truncate(bs->file, sizeof(AddCowHeader) + ((image_sectors + 7) 
>> 3));
+    if (ret < 0) {
+        bdrv_truncate(s->image_hd, old_image_sector * BDRV_SECTOR_SIZE);
+        return ret;
+    }
+    return ret;
+}
+
+static coroutine_fn int add_cow_co_flush(BlockDriverState *bs)
+{
+    BDRVAddCowState *s = bs->opaque;
+    int ret = bdrv_co_flush(s->image_hd);
+    if (ret < 0) {
+        return ret;
+    }
+
+    qemu_co_mutex_lock(&s->lock);
+    ret = add_cow_cache_flush(bs, s->bitmap_cache);
+    if (ret < 0) {
+        qemu_co_mutex_unlock(&s->lock);
+        return ret;
+    }
+    qemu_co_mutex_unlock(&s->lock);
+    return bdrv_co_flush(bs->file);
+}
+
+static QEMUOptionParameter add_cow_create_options[] = {
+    {
+        .name = BLOCK_OPT_SIZE,
+        .type = OPT_SIZE,
+        .help = "Virtual disk size"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a base image"
+    },
+    {
+        .name = BLOCK_OPT_IMAGE_FILE,
+        .type = OPT_STRING,
+        .help = "File name of a image file"
+    },
+    {
+        .name = BLOCK_OPT_BACKING_FMT,
+        .type = OPT_STRING,
+        .help = "Image format of the base image"
+    },
+    { NULL }
+};
+
+static BlockDriver bdrv_add_cow = {
+    .format_name                = "add-cow",
+    .instance_size              = sizeof(BDRVAddCowState),
+    .bdrv_probe                 = add_cow_probe,
+    .bdrv_open                  = add_cow_open,
+    .bdrv_close                 = add_cow_close,
+    .bdrv_create                = add_cow_create,
+    .bdrv_co_is_allocated       = add_cow_is_allocated,
+
+    .bdrv_co_readv              = add_cow_co_readv,
+    .bdrv_co_writev             = add_cow_co_writev,
+    .bdrv_truncate              = bdrv_add_cow_truncate,
+
+    .create_options             = add_cow_create_options,
+    .bdrv_co_flush_to_disk      = add_cow_co_flush,
+};
+
+static void bdrv_add_cow_init(void)
+{
+    bdrv_register(&bdrv_add_cow);
+}
+
+block_init(bdrv_add_cow_init);
diff --git a/block_int.h b/block_int.h
index b460c36..8126f27 100644
--- a/block_int.h
+++ b/block_int.h
@@ -50,6 +50,7 @@
 #define BLOCK_OPT_TABLE_SIZE    "table_size"
 #define BLOCK_OPT_PREALLOC      "preallocation"
 #define BLOCK_OPT_SUBFMT        "subformat"
+#define BLOCK_OPT_IMAGE_FILE    "image_file"
 
 typedef struct BdrvTrackedRequest BdrvTrackedRequest;
 
diff --git a/docs/specs/add-cow.txt b/docs/specs/add-cow.txt
new file mode 100644
index 0000000..db992a4
--- /dev/null
+++ b/docs/specs/add-cow.txt
@@ -0,0 +1,68 @@
+== General ==
+
+Raw file format does not support backing_file and copy on write feature.
+The add-cow image format makes it possible to use backing files with raw
+image by keeping a separate .add-cow metadata file.  Once all sectors
+have been written to in the raw image it is safe to discard the .add-cow
+and backing files and instead use the raw image directly.
+
+When using add-cow, procedures may like this:
+(ubuntu.img is a disk image which has been installed OS.)
+    1)  Create a raw image with the same size of ubuntu.img
+            qemu-img create -f raw test.raw 8G
+    2)  Create a add-cow image which will store dirty bitmap
+            qemu-img create -f add-cow test.add-cow -o 
backing_file=ubuntu.img,image_file=test.raw
+    3)  Run qemu with add-cow image
+            qemu -drive if=virtio,file=test.add-cow
+
+=Specification=
+
+The file format looks like this:
+
+ +---------------+--------------------------+
+ |     Header    |           Data           |
+ +---------------+--------------------------+
+
+All numbers in add-cow are stored in Big Endian byte order.
+
+== Header ==
+
+The Header is included in the first bytes:
+
+    Byte  0 -  7:       magic
+                        add-cow magic string ("ADD_COW\xff")
+
+          8 -  11:      version
+                        Version number (only valid value is 1 now)
+
+          12 - 1035:    backing_file
+                        backing_file file name related to add-cow file. All
+                        unused bytes are padded with zeros. Must not be longer
+                        than 1023 bytes.
+
+         1036 - 2059:   image_file
+                        image_file is a raw file. All unused bytes are padded
+                        with zeros. Must not be longer than 1023 bytes.
+
+         2060  - 2559:   The Reserved field is used to make sure Data field 
starts
+                        at the multiple of 512, not used currently. All bytes 
are
+                        filled with 0.
+
+== Data ==
+
+The Data field starts at the 2560th byte, stores a bitmap related to 
backing_file
+and image_file. The bitmap will track whether the sector in backing_file is 
dirty
+or not.
+
+
+Each bit in the bitmap indicates one sector's status. So the size of bitmap is
+calculated according to virtual size of backing_file. In each byte, bit 0 to 7
+will track the 1st to 7th sector in sequence, bit orders in one byte look like:
+ +----+----+----+----+----+----+----+----+
+ | b7 | b6 | b5 | b4 | b3 | b2 | b1 | b0 |
+ +----+----+----+----+----+----+----+----+
+
+If the bit is 0, indicates the sector has not been allocated in image_file, 
data
+should be loaded from backing_file while reading; if the bit is 1,  indicates 
the
+related sector has been dirty, should be loaded from image_file while reading.
+Writing to a sector causes the corresponding bit to be set to 1.
-- 
1.7.5.4