improve vma_spec.txt

[pve-qemu-kvm.git] / debian / patches / backup-add-vma-binary.patch

From 6289a43696ca6f713a5d3bb9f95a5adb608a5e13 Mon Sep 17 00:00:00 2001
From: Dietmar Maurer <dietmar@proxmox.com>
Date: Tue, 13 Nov 2012 11:11:38 +0100
Subject: [PATCH v5 4/6] introduce new vma archive format

This is a very simple archive format, see docs/specs/vma_spec.txt

Signed-off-by: Dietmar Maurer <dietmar@proxmox.com>
---
 Makefile                |    3 +-
 Makefile.objs           |    2 +-
 blockdev.c              |    6 +-
 docs/specs/vma_spec.txt |   24 ++
 vma-reader.c            |  799 ++++++++++++++++++++++++++++++++++++++++
 vma-writer.c            |  940 +++++++++++++++++++++++++++++++++++++++++++++++
 vma.c                   |  561 ++++++++++++++++++++++++++++
 vma.h                   |  145 ++++++++
 8 files changed, 2476 insertions(+), 4 deletions(-)
 create mode 100644 docs/specs/vma_spec.txt
 create mode 100644 vma-reader.c
 create mode 100644 vma-writer.c
 create mode 100644 vma.c
 create mode 100644 vma.h

Index: new/Makefile
===================================================================
--- new.orig/Makefile	2013-12-04 12:07:18.000000000 +0100
+++ new/Makefile	2013-12-04 12:07:25.000000000 +0100
@@ -128,7 +128,7 @@
 include $(SRC_PATH)/libcacard/Makefile
 endif
 
-all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all
+all: $(DOCS) $(TOOLS) vma$(EXESUF) $(HELPERS-y) recurse-all
 
 config-host.h: config-host.h-timestamp
 config-host.h-timestamp: config-host.mak
@@ -194,6 +194,7 @@
 qemu-img$(EXESUF): qemu-img.o $(block-obj-y) libqemuutil.a libqemustub.a
 qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) libqemuutil.a libqemustub.a
 qemu-io$(EXESUF): qemu-io.o $(block-obj-y) libqemuutil.a libqemustub.a
+vma$(EXESUF): vma.o vma-reader.o $(block-obj-y)  libqemuutil.a libqemustub.a
 
 qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
 
Index: new/docs/specs/vma_spec.txt
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ new/docs/specs/vma_spec.txt	2013-12-05 08:14:11.000000000 +0100
@@ -0,0 +1,132 @@
+= Virtual Machine Archive format (VMA) =
+
+This format contains a header which includes the VM configuration as
+binary blobs, and a list of devices (dev_id, name).
+
+The actual VM image data is stored inside extents. An extent contains
+up to 64 clusters, and start with a 512 byte header containing
+additional information for those clusters.
+
+We use a cluster size of 65536, and use 8 bytes for each
+cluster in the header to store the following information:
+
+* 1 byte dev_id (to identity the drive)
+* 1 byte not used (reserved)
+* 2 bytes zero indicator (mark zero regions (16x4096))
+* 4 bytes cluster number
+
+We only store non-zero blocks (such block is 4096 bytes).
+
+Each archive is marked with a uuid. The archive header and all
+extent headers includes that uuid and a MD5 checksum (over header
+data).
+
+All numbers in VMA archive are stored in Big Endian byte order.
+
+== VMA Header ==
+
+    Byte  0 -  3:   magic
+                    VMA magic string ("VMA\x00")
+
+	  4 -  7:   version
+                    Version number (valid value is 1)
+
+          8 - 23:   uuid
+		    Unique ID, Same uuid is used to mark extents.
+
+         24 - 31:   ctime
+	      	    Backup time stamp (seconds since epoch)
+
+         32 - 47:   md5sum
+	      	    Header checksum (from byte 0 to header_size). This field
+		    is filled with zero to generate the checksum.
+
+         48 - 51:   blob_buffer_offset
+	      	    Start of blob buffer (multiple of 512)
+
+         52 - 55:   blob_buffer_size
+	      	    Size of blob buffer (multiple of 512)
+
+         56 - 59:   header_size
+	      	    Overall size of this header (multiple of 512)
+
+	 60 - 2043: reserved
+
+       2044 - 3067: uint32_t config_names[256]
+       	      	    Offsets into blob_buffer table
+
+       3068 - 4091: uint32_t config_data[256]
+       	      	    Offsets into blob_buffer table
+
+       4092 - 4095: reserved
+
+      4096 - 12287: VmaDeviceInfoHeader dev_info[256]
+                    The offset in this table is used as 'dev_id' inside
+		    the data streams.
+
+      12288 - header_size: Blob buffer
+
+
+=== Devive Info Header (VmaDeviceInfoHeader) ===
+
+This is use to store details about the contained disk images.
+
+    Byte  0 -  3:   devive name (offsets into blob_buffer table)
+
+    	  4 -  7:   reserved
+
+	  8 - 15:   device size in bytes
+
+	 16 - 31:   reserved
+
+Note: Devive name 'vmstate' is reserved to store VM RAM state.
+
+=== Blob buffer ===
+
+The blob buffer is used to store both configuration file names and
+configuration data.
+
+This region contain a list of binary data blobs. Each blob starts with
+a 2 byte size field, followed by the actual data.
+
+== Image Data Streams ==
+
+The VMA header is followed by the image data stream. Image data is grouped
+with extents, which contains up to 59 clusters from different images.
+
+=== VMA Extent Header ===
+
+    Byte  0 -  3:   magic
+                    VMA extent magic string ("VMAE")
+
+   	  4 -  5:   reserved
+
+   	  6 -  7:   block_count
+	      	    Overall number of contained 4K block
+
+          8 - 23:   uuid
+		    Unique ID, Same uuid as used in the VMA header.
+
+         24 - 39:   md5sum
+	      	    Header checksum (from byte 0 to header_size). This field
+		    is filled with zero to generate the checksum.
+
+        40 - 511:   blockinfo[59]
+
+
+Each 'blockinfo' (8 bytes) give further details about contained clusters:
+
+    Byte  0 - 1:   mask
+   	      	   Bitmap used to indicate non-zero 4K blocks inside the
+		   cluster.
+
+              2:   reserved
+
+              3:   dev_id
+	           Device ID (offset into dev_info table)
+
+          4 - 7:   cluster_num
+
+The extend header if followed by the actual cluster data, where we only
+store non-zero 4K blocks.
+
Index: new/vma-reader.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ new/vma-reader.c	2013-12-04 12:07:25.000000000 +0100
@@ -0,0 +1,799 @@
+/*
+ * VMA: Virtual Machine Archive
+ *
+ * Copyright (C) 2012 Proxmox Server Solutions
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <glib.h>
+#include <uuid/uuid.h>
+
+#include "qemu-common.h"
+#include "qemu/timer.h"
+#include "qemu/ratelimit.h"
+#include "vma.h"
+#include "block/block.h"
+
+#define BITS_PER_LONG  (sizeof(unsigned long) * CHAR_BIT)
+
+static unsigned char zero_vma_block[VMA_BLOCK_SIZE];
+
+typedef struct VmaRestoreState {
+    BlockDriverState *bs;
+    bool write_zeroes;
+    unsigned long *bitmap;
+    int bitmap_size;
+}  VmaRestoreState;
+
+struct VmaReader {
+    int fd;
+    GChecksum *md5csum;
+    GHashTable *blob_hash;
+    unsigned char *head_data;
+    VmaDeviceInfo devinfo[256];
+    VmaRestoreState rstate[256];
+    GList *cdata_list;
+    guint8 vmstate_stream;
+    uint32_t vmstate_clusters;
+    /* to show restore percentage if run with -v */
+    time_t start_time;
+    int64_t cluster_count;
+    int64_t clusters_read;
+    int clusters_read_per;
+};
+
+static guint
+g_int32_hash(gconstpointer v)
+{
+    return *(const uint32_t *)v;
+}
+
+static gboolean
+g_int32_equal(gconstpointer v1, gconstpointer v2)
+{
+    return *((const uint32_t *)v1) == *((const uint32_t *)v2);
+}
+
+static int vma_reader_get_bitmap(VmaRestoreState *rstate, int64_t cluster_num)
+{
+    assert(rstate);
+    assert(rstate->bitmap);
+
+    unsigned long val, idx, bit;
+
+    idx = cluster_num / BITS_PER_LONG;
+
+    assert(rstate->bitmap_size > idx);
+
+    bit = cluster_num % BITS_PER_LONG;
+    val = rstate->bitmap[idx];
+
+    return !!(val & (1UL << bit));
+}
+
+static void vma_reader_set_bitmap(VmaRestoreState *rstate, int64_t cluster_num,
+                                  int dirty)
+{
+    assert(rstate);
+    assert(rstate->bitmap);
+
+    unsigned long val, idx, bit;
+
+    idx = cluster_num / BITS_PER_LONG;
+
+    assert(rstate->bitmap_size > idx);
+
+    bit = cluster_num % BITS_PER_LONG;
+    val = rstate->bitmap[idx];
+    if (dirty) {
+        if (!(val & (1UL << bit))) {
+            val |= 1UL << bit;
+        }
+    } else {
+        if (val & (1UL << bit)) {
+            val &= ~(1UL << bit);
+        }
+    }
+    rstate->bitmap[idx] = val;
+}
+
+typedef struct VmaBlob {
+    uint32_t start;
+    uint32_t len;
+    void *data;
+} VmaBlob;
+
+static const VmaBlob *get_header_blob(VmaReader *vmar, uint32_t pos)
+{
+    assert(vmar);
+    assert(vmar->blob_hash);
+
+    return g_hash_table_lookup(vmar->blob_hash, &pos);
+}
+
+static const char *get_header_str(VmaReader *vmar, uint32_t pos)
+{
+    const VmaBlob *blob = get_header_blob(vmar, pos);
+    if (!blob) {
+        return NULL;
+    }
+    const char *res = (char *)blob->data;
+    if (res[blob->len-1] != '\0') {
+        return NULL;
+    }
+    return res;
+}
+
+static ssize_t
+safe_read(int fd, unsigned char *buf, size_t count)
+{
+    ssize_t n;
+
+    do {
+        n = read(fd, buf, count);
+    } while (n < 0 && errno == EINTR);
+
+    return n;
+}
+
+static ssize_t
+full_read(int fd, unsigned char *buf, size_t len)
+{
+    ssize_t n;
+    size_t total;
+
+    total = 0;
+
+    while (len > 0) {
+        n = safe_read(fd, buf, len);
+
+        if (n == 0) {
+            return total;
+        }
+
+        if (n <= 0) {
+            break;
+        }
+
+        buf += n;
+        total += n;
+        len -= n;
+    }
+
+    if (len) {
+        return -1;
+    }
+
+    return total;
+}
+
+void vma_reader_destroy(VmaReader *vmar)
+{
+    assert(vmar);
+
+    if (vmar->fd >= 0) {
+        close(vmar->fd);
+    }
+
+    if (vmar->cdata_list) {
+        g_list_free(vmar->cdata_list);
+    }
+
+    int i;
+    for (i = 1; i < 256; i++) {
+        if (vmar->rstate[i].bitmap) {
+            g_free(vmar->rstate[i].bitmap);
+        }
+    }
+
+    if (vmar->md5csum) {
+        g_checksum_free(vmar->md5csum);
+    }
+
+    if (vmar->blob_hash) {
+        g_hash_table_destroy(vmar->blob_hash);
+    }
+
+    if (vmar->head_data) {
+        g_free(vmar->head_data);
+    }
+
+    g_free(vmar);
+
+};
+
+static int vma_reader_read_head(VmaReader *vmar, Error **errp)
+{
+    assert(vmar);
+    assert(errp);
+    assert(*errp == NULL);
+
+    unsigned char md5sum[16];
+    int i;
+    int ret = 0;
+
+    vmar->head_data = g_malloc(sizeof(VmaHeader));
+
+    if (full_read(vmar->fd, vmar->head_data, sizeof(VmaHeader)) !=
+        sizeof(VmaHeader)) {
+        error_setg(errp, "can't read vma header - %s",
+                   errno ? g_strerror(errno) : "got EOF");
+        return -1;
+    }
+
+    VmaHeader *h = (VmaHeader *)vmar->head_data;
+
+    if (h->magic != VMA_MAGIC) {
+        error_setg(errp, "not a vma file - wrong magic number");
+        return -1;
+    }
+
+    uint32_t header_size = GUINT32_FROM_BE(h->header_size);
+    int need = header_size - sizeof(VmaHeader);
+    if (need <= 0) {
+        error_setg(errp, "wrong vma header size %d", header_size);
+        return -1;
+    }
+
+    vmar->head_data = g_realloc(vmar->head_data, header_size);
+    h = (VmaHeader *)vmar->head_data;
+
+    if (full_read(vmar->fd, vmar->head_data + sizeof(VmaHeader), need) !=
+        need) {
+        error_setg(errp, "can't read vma header data - %s",
+                   errno ? g_strerror(errno) : "got EOF");
+        return -1;
+    }
+
+    memcpy(md5sum, h->md5sum, 16);
+    memset(h->md5sum, 0, 16);
+
+    g_checksum_reset(vmar->md5csum);
+    g_checksum_update(vmar->md5csum, vmar->head_data, header_size);
+    gsize csize = 16;
+    g_checksum_get_digest(vmar->md5csum, (guint8 *)(h->md5sum), &csize);
+
+    if (memcmp(md5sum, h->md5sum, 16) != 0) {
+        error_setg(errp, "wrong vma header chechsum");
+        return -1;
+    }
+
+    /* we can modify header data after checksum verify */
+    h->header_size = header_size;
+
+    h->version = GUINT32_FROM_BE(h->version);
+    if (h->version != 1) {
+        error_setg(errp, "wrong vma version %d", h->version);
+        return -1;
+    }
+
+    h->ctime = GUINT64_FROM_BE(h->ctime);
+    h->blob_buffer_offset = GUINT32_FROM_BE(h->blob_buffer_offset);
+    h->blob_buffer_size = GUINT32_FROM_BE(h->blob_buffer_size);
+
+    uint32_t bstart = h->blob_buffer_offset + 1;
+    uint32_t bend = h->blob_buffer_offset + h->blob_buffer_size;
+
+    if (bstart <= sizeof(VmaHeader)) {
+        error_setg(errp, "wrong vma blob buffer offset %d",
+                   h->blob_buffer_offset);
+        return -1;
+    }
+
+    if (bend > header_size) {
+        error_setg(errp, "wrong vma blob buffer size %d/%d",
+                   h->blob_buffer_offset, h->blob_buffer_size);
+        return -1;
+    }
+
+    while ((bstart + 2) <= bend) {
+        uint32_t size = vmar->head_data[bstart] +
+            (vmar->head_data[bstart+1] << 8);
+        if ((bstart + size + 2) <= bend) {
+            VmaBlob *blob = g_new0(VmaBlob, 1);
+            blob->start = bstart - h->blob_buffer_offset;
+            blob->len = size;
+            blob->data = vmar->head_data + bstart + 2;
+            g_hash_table_insert(vmar->blob_hash, &blob->start, blob);
+        }
+        bstart += size + 2;
+    }
+
+
+    int count = 0;
+    for (i = 1; i < 256; i++) {
+        VmaDeviceInfoHeader *dih = &h->dev_info[i];
+        uint32_t devname_ptr = GUINT32_FROM_BE(dih->devname_ptr);
+        uint64_t size = GUINT64_FROM_BE(dih->size);
+        const char *devname =  get_header_str(vmar, devname_ptr);
+
+        if (size && devname) {
+            count++;
+            vmar->devinfo[i].size = size;
+            vmar->devinfo[i].devname = devname;
+
+            if (strcmp(devname, "vmstate") == 0) {
+                vmar->vmstate_stream = i;
+            }
+        }
+    }
+
+    if (!count) {
+        error_setg(errp, "vma does not contain data");
+        return -1;
+    }
+
+    for (i = 0; i < VMA_MAX_CONFIGS; i++) {
+        uint32_t name_ptr = GUINT32_FROM_BE(h->config_names[i]);
+        uint32_t data_ptr = GUINT32_FROM_BE(h->config_data[i]);
+
+        if (!(name_ptr && data_ptr)) {
+            continue;
+        }
+        const char *name =  get_header_str(vmar, name_ptr);
+        const VmaBlob *blob = get_header_blob(vmar, data_ptr);
+
+        if (!(name && blob)) {
+            error_setg(errp, "vma contains invalid data pointers");
+            return -1;
+        }
+
+        VmaConfigData *cdata = g_new0(VmaConfigData, 1);
+        cdata->name = name;
+        cdata->data = blob->data;
+        cdata->len = blob->len;
+
+        vmar->cdata_list = g_list_append(vmar->cdata_list, cdata);
+    }
+
+    return ret;
+};
+
+VmaReader *vma_reader_create(const char *filename, Error **errp)
+{
+    assert(filename);
+    assert(errp);
+
+    VmaReader *vmar = g_new0(VmaReader, 1);
+
+    if (strcmp(filename, "-") == 0) {
+        vmar->fd = dup(0);
+    } else {
+        vmar->fd = open(filename, O_RDONLY);
+    }
+
+    if (vmar->fd < 0) {
+        error_setg(errp, "can't open file %s - %s\n", filename,
+                   g_strerror(errno));
+        goto err;
+    }
+
+    vmar->md5csum = g_checksum_new(G_CHECKSUM_MD5);
+    if (!vmar->md5csum) {
+        error_setg(errp, "can't allocate cmsum\n");
+        goto err;
+    }
+
+    vmar->blob_hash = g_hash_table_new_full(g_int32_hash, g_int32_equal,
+                                            NULL, g_free);
+
+    if (vma_reader_read_head(vmar, errp) < 0) {
+        goto err;
+    }
+
+    return vmar;
+
+err:
+    if (vmar) {
+        vma_reader_destroy(vmar);
+    }
+
+    return NULL;
+}
+
+VmaHeader *vma_reader_get_header(VmaReader *vmar)
+{
+    assert(vmar);
+    assert(vmar->head_data);
+
+    return (VmaHeader *)(vmar->head_data);
+}
+
+GList *vma_reader_get_config_data(VmaReader *vmar)
+{
+    assert(vmar);
+    assert(vmar->head_data);
+
+    return vmar->cdata_list;
+}
+
+VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id)
+{
+    assert(vmar);
+    assert(dev_id);
+
+    if (vmar->devinfo[dev_id].size && vmar->devinfo[dev_id].devname) {
+        return &vmar->devinfo[dev_id];
+    }
+
+    return NULL;
+}
+
+int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id, BlockDriverState *bs,
+                           bool write_zeroes, Error **errp)
+{
+    assert(vmar);
+    assert(bs != NULL);
+    assert(dev_id);
+    assert(vmar->rstate[dev_id].bs == NULL);
+
+    int64_t size = bdrv_getlength(bs);
+    if (size != vmar->devinfo[dev_id].size) {
+        error_setg(errp, "vma_reader_register_bs for stream %s failed - "
+                   "unexpected size %zd != %zd", vmar->devinfo[dev_id].devname,
+                   size, vmar->devinfo[dev_id].size);
+        return -1;
+    }
+
+    vmar->rstate[dev_id].bs = bs;
+    vmar->rstate[dev_id].write_zeroes = write_zeroes;
+
+    int64_t bitmap_size = (size/BDRV_SECTOR_SIZE) +
+        (VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE) * BITS_PER_LONG - 1;
+    bitmap_size /= (VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE) * BITS_PER_LONG;
+
+    vmar->rstate[dev_id].bitmap_size = bitmap_size;
+    vmar->rstate[dev_id].bitmap = g_new0(unsigned long, bitmap_size);
+
+    vmar->cluster_count += size/VMA_CLUSTER_SIZE;
+
+    return 0;
+}
+
+static ssize_t safe_write(int fd, void *buf, size_t count)
+{
+    ssize_t n;
+
+    do {
+        n = write(fd, buf, count);
+    } while (n < 0 && errno == EINTR);
+
+    return n;
+}
+
+static size_t full_write(int fd, void *buf, size_t len)
+{
+    ssize_t n;
+    size_t total;
+
+    total = 0;
+
+    while (len > 0) {
+        n = safe_write(fd, buf, len);
+        if (n < 0) {
+            return n;
+        }
+        buf += n;
+        total += n;
+        len -= n;
+    }
+
+    if (len) {
+        /* incomplete write ? */
+        return -1;
+    }
+
+    return total;
+}
+
+static int restore_write_data(VmaReader *vmar, guint8 dev_id,
+                              BlockDriverState *bs, int vmstate_fd,
+                              unsigned char *buf, int64_t sector_num,
+                              int nb_sectors, Error **errp)
+{
+    assert(vmar);
+
+    if (dev_id == vmar->vmstate_stream) {
+        if (vmstate_fd >= 0) {
+            int len = nb_sectors * BDRV_SECTOR_SIZE;
+            int res = full_write(vmstate_fd, buf, len);
+            if (res < 0) {
+                error_setg(errp, "write vmstate failed %d", res);
+                return -1;
+            }
+        }
+    } else {
+        int res = bdrv_write(bs, sector_num, buf, nb_sectors);
+        if (res < 0) {
+            error_setg(errp, "bdrv_write to %s failed (%d)",
+                       bdrv_get_device_name(bs), res);
+            return -1;
+        }
+    }
+    return 0;
+}
+static int restore_extent(VmaReader *vmar, unsigned char *buf,
+                          int extent_size, int vmstate_fd,
+                          bool verbose, Error **errp)
+{
+    assert(vmar);
+    assert(buf);
+
+    VmaExtentHeader *ehead = (VmaExtentHeader *)buf;
+    int start = VMA_EXTENT_HEADER_SIZE;
+    int i;
+
+    for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) {
+        uint64_t block_info = GUINT64_FROM_BE(ehead->blockinfo[i]);
+        uint64_t cluster_num = block_info & 0xffffffff;
+        uint8_t dev_id = (block_info >> 32) & 0xff;
+        uint16_t mask = block_info >> (32+16);
+        int64_t max_sector;
+
+        if (!dev_id) {
+            continue;
+        }
+
+        VmaRestoreState *rstate = &vmar->rstate[dev_id];
+        BlockDriverState *bs = NULL;
+
+        if (dev_id != vmar->vmstate_stream) {
+            bs = rstate->bs;
+            if (!bs) {
+                error_setg(errp, "got wrong dev id %d", dev_id);
+                return -1;
+            }
+
+            if (vma_reader_get_bitmap(rstate, cluster_num)) {
+                error_setg(errp, "found duplicated cluster %zd for stream %s",
+                          cluster_num, vmar->devinfo[dev_id].devname);
+                return -1;
+            }
+            vma_reader_set_bitmap(rstate, cluster_num, 1);
+
+            max_sector = vmar->devinfo[dev_id].size/BDRV_SECTOR_SIZE;
+        } else {
+            max_sector = G_MAXINT64;
+            if (cluster_num != vmar->vmstate_clusters) {
+                error_setg(errp, "found out of order vmstate data");
+                return -1;
+            }
+            vmar->vmstate_clusters++;
+        }
+
+        vmar->clusters_read++;
+
+        if (verbose) {
+            time_t duration = time(NULL) - vmar->start_time;
+            int percent = (vmar->clusters_read*100)/vmar->cluster_count;
+            if (percent != vmar->clusters_read_per) {
+                printf("progress %d%% (read %zd bytes, duration %zd sec)\n",
+                       percent, vmar->clusters_read*VMA_CLUSTER_SIZE,
+                       duration);
+                fflush(stdout);
+                vmar->clusters_read_per = percent;
+            }
+        }
+
+        /* try to write whole clusters to speedup restore */
+        if (mask == 0xffff) {
+            if ((start + VMA_CLUSTER_SIZE) > extent_size) {
+                error_setg(errp, "short vma extent - too many blocks");
+                return -1;
+            }
+            int64_t sector_num = (cluster_num * VMA_CLUSTER_SIZE) /
+                BDRV_SECTOR_SIZE;
+            int64_t end_sector = sector_num +
+                VMA_CLUSTER_SIZE/BDRV_SECTOR_SIZE;
+
+            if (end_sector > max_sector) {
+                end_sector = max_sector;
+            }
+
+            if (end_sector <= sector_num) {
+                error_setg(errp, "got wrong block address - write bejond end");
+                return -1;
+            }
+
+            int nb_sectors = end_sector - sector_num;
+            if (restore_write_data(vmar, dev_id, bs, vmstate_fd, buf + start,
+                                   sector_num, nb_sectors, errp) < 0) {
+                return -1;
+            }
+
+            start += VMA_CLUSTER_SIZE;
+        } else {
+            int j;
+            int bit = 1;
+
+            for (j = 0; j < 16; j++) {
+                int64_t sector_num = (cluster_num*VMA_CLUSTER_SIZE +
+                                      j*VMA_BLOCK_SIZE)/BDRV_SECTOR_SIZE;
+
+                int64_t end_sector = sector_num +
+                    VMA_BLOCK_SIZE/BDRV_SECTOR_SIZE;
+                if (end_sector > max_sector) {
+                    end_sector = max_sector;
+                }
+
+                if (mask & bit) {
+                    if ((start + VMA_BLOCK_SIZE) > extent_size) {
+                        error_setg(errp, "short vma extent - too many blocks");
+                        return -1;
+                    }
+
+                    if (end_sector <= sector_num) {
+                        error_setg(errp, "got wrong block address - "
+                                   "write bejond end");
+                        return -1;
+                    }
+
+                    int nb_sectors = end_sector - sector_num;
+                    if (restore_write_data(vmar, dev_id, bs, vmstate_fd,
+                                           buf + start, sector_num,
+                                           nb_sectors, errp) < 0) {
+                        return -1;
+                    }
+
+                    start += VMA_BLOCK_SIZE;
+
+                } else {
+
+                    if (rstate->write_zeroes && (end_sector > sector_num)) {
+                        /* Todo: use bdrv_co_write_zeroes (but that need to
+                         * be run inside coroutine?)
+                         */
+                        int nb_sectors = end_sector - sector_num;
+                        if (restore_write_data(vmar, dev_id, bs, vmstate_fd,
+                                              zero_vma_block, sector_num,
+                                               nb_sectors, errp) < 0) {
+                            return -1;
+                        }
+                    }
+                }
+
+                bit = bit << 1;
+            }
+        }
+    }
+
+    if (start != extent_size) {
+        error_setg(errp, "vma extent error - missing blocks");
+        return -1;
+    }
+
+    return 0;
+}
+
+int vma_reader_restore(VmaReader *vmar, int vmstate_fd, bool verbose,
+                       Error **errp)
+{
+    assert(vmar);
+    assert(vmar->head_data);
+
+    int ret = 0;
+    unsigned char buf[VMA_MAX_EXTENT_SIZE];
+    int buf_pos = 0;
+    unsigned char md5sum[16];
+    VmaHeader *h = (VmaHeader *)vmar->head_data;
+
+    vmar->start_time = time(NULL);
+
+    while (1) {
+        int bytes = full_read(vmar->fd, buf + buf_pos, sizeof(buf) - buf_pos);
+        if (bytes < 0) {
+            error_setg(errp, "read failed - %s", g_strerror(errno));
+            return -1;
+        }
+
+        buf_pos += bytes;
+
+        if (!buf_pos) {
+            break; /* EOF */
+        }
+
+        if (buf_pos < VMA_EXTENT_HEADER_SIZE) {
+            error_setg(errp, "read short extent (%d bytes)", buf_pos);
+            return -1;
+        }
+
+        VmaExtentHeader *ehead = (VmaExtentHeader *)buf;
+
+        /* extract md5sum */
+        memcpy(md5sum, ehead->md5sum, sizeof(ehead->md5sum));
+        memset(ehead->md5sum, 0, sizeof(ehead->md5sum));
+
+        g_checksum_reset(vmar->md5csum);
+        g_checksum_update(vmar->md5csum, buf, VMA_EXTENT_HEADER_SIZE);
+        gsize csize = 16;
+        g_checksum_get_digest(vmar->md5csum, ehead->md5sum, &csize);
+
+        if (memcmp(md5sum, ehead->md5sum, 16) != 0) {
+            error_setg(errp, "wrong vma extent header chechsum");
+            return -1;
+        }
+
+        if (memcmp(h->uuid, ehead->uuid, sizeof(ehead->uuid)) != 0) {
+            error_setg(errp, "wrong vma extent uuid");
+            return -1;
+        }
+
+        if (ehead->magic != VMA_EXTENT_MAGIC || ehead->reserved1 != 0) {
+            error_setg(errp, "wrong vma extent header magic");
+            return -1;
+        }
+
+        int block_count = GUINT16_FROM_BE(ehead->block_count);
+        int extent_size = VMA_EXTENT_HEADER_SIZE + block_count*VMA_BLOCK_SIZE;
+
+        if (buf_pos < extent_size) {
+            error_setg(errp, "short vma extent (%d < %d)", buf_pos,
+                       extent_size);
+            return -1;
+        }
+
+        if (restore_extent(vmar, buf, extent_size, vmstate_fd, verbose,
+                           errp) < 0) {
+            return -1;
+        }
+
+        if (buf_pos > extent_size) {
+            memmove(buf, buf + extent_size, buf_pos - extent_size);
+            buf_pos = buf_pos - extent_size;
+        } else {
+            buf_pos = 0;
+        }
+    }
+
+    bdrv_drain_all();
+
+    int i;
+    for (i = 1; i < 256; i++) {
+        VmaRestoreState *rstate = &vmar->rstate[i];
+        if (!rstate->bs) {
+            continue;
+        }
+
+        if (bdrv_flush(rstate->bs) < 0) {
+            error_setg(errp, "vma bdrv_flush %s failed",
+                       vmar->devinfo[i].devname);
+            return -1;
+        }
+
+        if (vmar->devinfo[i].size &&
+            (strcmp(vmar->devinfo[i].devname, "vmstate") != 0)) {
+            assert(rstate->bitmap);
+
+            int64_t cluster_num, end;
+
+            end = (vmar->devinfo[i].size + VMA_CLUSTER_SIZE - 1) /
+                VMA_CLUSTER_SIZE;
+
+            for (cluster_num = 0; cluster_num < end; cluster_num++) {
+                if (!vma_reader_get_bitmap(rstate, cluster_num)) {
+                    error_setg(errp, "detected missing cluster %zd "
+                               "for stream %s", cluster_num,
+                               vmar->devinfo[i].devname);
+                    return -1;
+                }
+            }
+        }
+    }
+
+    return ret;
+}
+
Index: new/vma-writer.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ new/vma-writer.c	2013-12-04 14:26:06.000000000 +0100
@@ -0,0 +1,875 @@
+/*
+ * VMA: Virtual Machine Archive
+ *
+ * Copyright (C) 2012 Proxmox Server Solutions
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <glib.h>
+#include <uuid/uuid.h>
+
+#include "qemu-common.h"
+#include "vma.h"
+#include "block/block.h"
+#include "monitor/monitor.h"
+
+#define DEBUG_VMA 0
+
+#define DPRINTF(fmt, ...)\
+    do { if (DEBUG_VMA) { printf("vma: " fmt, ## __VA_ARGS__); } } while (0)
+
+#define WRITE_BUFFERS 5
+
+typedef struct VmaAIOCB VmaAIOCB;
+struct VmaAIOCB {
+    unsigned char buffer[VMA_MAX_EXTENT_SIZE];
+    VmaWriter *vmaw;
+    size_t bytes;
+    Coroutine *co;
+};
+
+struct VmaWriter {
+    int fd;
+    FILE *cmd;
+    int status;
+    char errmsg[8192];
+    uuid_t uuid;
+    bool header_written;
+    bool closed;
+
+    /* we always write extents */
+    unsigned char outbuf[VMA_MAX_EXTENT_SIZE];
+    int outbuf_pos; /* in bytes */
+    int outbuf_count; /* in VMA_BLOCKS */
+    uint64_t outbuf_block_info[VMA_BLOCKS_PER_EXTENT];
+
+    VmaAIOCB *aiocbs[WRITE_BUFFERS];
+    CoQueue wqueue;
+
+    GChecksum *md5csum;
+    CoMutex writer_lock;
+    CoMutex flush_lock;
+    Coroutine *co_writer;
+
+    /* drive informations */
+    VmaStreamInfo stream_info[256];
+    guint stream_count;
+
+    guint8 vmstate_stream;
+    uint32_t vmstate_clusters;
+
+    /* header blob table */
+    char *header_blob_table;
+    uint32_t header_blob_table_size;
+    uint32_t header_blob_table_pos;
+
+    /* store for config blobs */
+    uint32_t config_names[VMA_MAX_CONFIGS]; /* offset into blob_buffer table */
+    uint32_t config_data[VMA_MAX_CONFIGS];  /* offset into blob_buffer table */
+    uint32_t config_count;
+};
+
+void vma_writer_set_error(VmaWriter *vmaw, const char *fmt, ...)
+{
+    va_list ap;
+
+    if (vmaw->status < 0) {
+        return;
+    }
+
+    vmaw->status = -1;
+
+    va_start(ap, fmt);
+    g_vsnprintf(vmaw->errmsg, sizeof(vmaw->errmsg), fmt, ap);
+    va_end(ap);
+
+    DPRINTF("vma_writer_set_error: %s\n", vmaw->errmsg);
+}
+
+static uint32_t allocate_header_blob(VmaWriter *vmaw, const char *data,
+                                     size_t len)
+{
+    if (len > 65535) {
+        return 0;
+    }
+
+    if (!vmaw->header_blob_table ||
+        (vmaw->header_blob_table_size <
+         (vmaw->header_blob_table_pos + len + 2))) {
+        int newsize = vmaw->header_blob_table_size + ((len + 2 + 511)/512)*512;
+
+        vmaw->header_blob_table = g_realloc(vmaw->header_blob_table, newsize);
+        memset(vmaw->header_blob_table + vmaw->header_blob_table_size,
+               0, newsize - vmaw->header_blob_table_size);
+        vmaw->header_blob_table_size = newsize;
+    }
+
+    uint32_t cpos = vmaw->header_blob_table_pos;
+    vmaw->header_blob_table[cpos] = len & 255;
+    vmaw->header_blob_table[cpos+1] = (len >> 8) & 255;
+    memcpy(vmaw->header_blob_table + cpos + 2, data, len);
+    vmaw->header_blob_table_pos += len + 2;
+    return cpos;
+}
+
+static uint32_t allocate_header_string(VmaWriter *vmaw, const char *str)
+{
+    assert(vmaw);
+
+    size_t len = strlen(str) + 1;
+
+    return allocate_header_blob(vmaw, str, len);
+}
+
+int vma_writer_add_config(VmaWriter *vmaw, const char *name, gpointer data,
+                          gsize len)
+{
+    assert(vmaw);
+    assert(!vmaw->header_written);
+    assert(vmaw->config_count < VMA_MAX_CONFIGS);
+    assert(name);
+    assert(data);
+    assert(len);
+
+    gchar *basename = g_path_get_basename(name);
+    uint32_t name_ptr = allocate_header_string(vmaw, basename);
+    g_free(basename);
+
+    if (!name_ptr) {
+        return -1;
+    }
+
+    uint32_t data_ptr = allocate_header_blob(vmaw, data, len);
+    if (!data_ptr) {
+        return -1;
+    }
+
+    vmaw->config_names[vmaw->config_count] = name_ptr;
+    vmaw->config_data[vmaw->config_count] = data_ptr;
+
+    vmaw->config_count++;
+
+    return 0;
+}
+
+int vma_writer_register_stream(VmaWriter *vmaw, const char *devname,
+                               size_t size)
+{
+    assert(vmaw);
+    assert(devname);
+    assert(!vmaw->status);
+
+    if (vmaw->header_written) {
+        vma_writer_set_error(vmaw, "vma_writer_register_stream: header "
+                             "already written");
+        return -1;
+    }
+
+    guint n = vmaw->stream_count + 1;
+
+    /* we can have dev_ids form 1 to 255 (0 reserved)
+     * 255(-1) reseverd for safety
+     */
+    if (n > 254) {
+        vma_writer_set_error(vmaw, "vma_writer_register_stream: "
+                             "too many drives");
+        return -1;
+    }
+
+    if (size <= 0) {
+        vma_writer_set_error(vmaw, "vma_writer_register_stream: "
+                             "got strange size %zd", size);
+        return -1;
+    }
+
+    DPRINTF("vma_writer_register_stream %s %zu %d\n", devname, size, n);
+
+    vmaw->stream_info[n].devname = g_strdup(devname);
+    vmaw->stream_info[n].size = size;
+
+    vmaw->stream_info[n].cluster_count = (size + VMA_CLUSTER_SIZE - 1) /
+        VMA_CLUSTER_SIZE;
+
+    vmaw->stream_count = n;
+
+    if (strcmp(devname, "vmstate") == 0) {
+        vmaw->vmstate_stream = n;
+    }
+
+    return n;
+}
+
+static void vma_co_continue_write(void *opaque)
+{
+    VmaWriter *vmaw = opaque;
+
+    DPRINTF("vma_co_continue_write\n");
+    qemu_coroutine_enter(vmaw->co_writer, NULL);
+}
+
+static ssize_t coroutine_fn
+vma_co_write(VmaWriter *vmaw, const void *buf, size_t bytes)
+{
+    size_t done = 0;
+    ssize_t ret;
+
+    /* atomic writes (we cannot interleave writes) */
+    qemu_co_mutex_lock(&vmaw->writer_lock);
+
+    DPRINTF("vma_co_write enter %zd\n", bytes);
+
+    assert(vmaw->co_writer == NULL);
+
+    vmaw->co_writer = qemu_coroutine_self();
+
+    qemu_aio_set_fd_handler(vmaw->fd, NULL, vma_co_continue_write, vmaw);
+
+    DPRINTF("vma_co_write wait until writable\n");
+    qemu_coroutine_yield();
+    DPRINTF("vma_co_write starting %zd\n", bytes);
+
+    while (done < bytes) {
+        ret = write(vmaw->fd, buf + done, bytes - done);
+        if (ret > 0) {
+            done += ret;
+            DPRINTF("vma_co_write written %zd %zd\n", done, ret);
+        } else if (ret < 0) {
+            if (errno == EAGAIN || errno == EWOULDBLOCK) {
+                DPRINTF("vma_co_write yield %zd\n", done);
+                qemu_coroutine_yield();
+                DPRINTF("vma_co_write restart %zd\n", done);
+            } else {
+                vma_writer_set_error(vmaw, "vma_co_write write error - %s",
+                                     g_strerror(errno));
+                done = -1; /* always return failure for partial writes */
+                break;
+            }
+        } else if (ret == 0) {
+            /* should not happen - simply try again */
+        }
+    }
+
+    qemu_aio_set_fd_handler(vmaw->fd, NULL, NULL, NULL);
+
+    vmaw->co_writer = NULL;
+
+    qemu_co_mutex_unlock(&vmaw->writer_lock);
+
+    DPRINTF("vma_co_write leave %zd\n", done);
+    return done;
+}
+
+static void coroutine_fn vma_co_writer_task(void *opaque)
+{
+    VmaAIOCB *cb = opaque;
+
+    DPRINTF("vma_co_writer_task start\n");
+
+    int64_t done = vma_co_write(cb->vmaw, cb->buffer, cb->bytes);
+    DPRINTF("vma_co_writer_task write done %zd\n", done);
+
+    if (done != cb->bytes) {
+        DPRINTF("vma_co_writer_task failed write %zd %zd", cb->bytes, done);
+        vma_writer_set_error(cb->vmaw, "vma_co_writer_task failed write %zd",
+                             done);
+    }
+
+    cb->bytes = 0;
+
+    qemu_co_queue_next(&cb->vmaw->wqueue);
+
+    DPRINTF("vma_co_writer_task end\n");
+}
+
+static void coroutine_fn vma_queue_flush(VmaWriter *vmaw)
+{
+    DPRINTF("vma_queue_flush enter\n");
+
+    assert(vmaw);
+
+    while (1) {
+        int i;
+        VmaAIOCB *cb = NULL;
+        for (i = 0; i < WRITE_BUFFERS; i++) {
+            if (vmaw->aiocbs[i]->bytes) {
+                cb = vmaw->aiocbs[i];
+                DPRINTF("FOUND USED AIO BUFFER %d %zd\n", i,
+                        vmaw->aiocbs[i]->bytes);
+                break;
+            }
+        }
+        if (!cb) {
+            break;
+        }
+        qemu_co_queue_wait(&vmaw->wqueue);
+    }
+
+    DPRINTF("vma_queue_flush leave\n");
+}
+
+/**
+ * NOTE: pipe buffer size in only 4096 bytes on linux (see 'ulimit -a')
+ * So we need to create a coroutione to allow 'parallel' execution.
+ */
+static ssize_t coroutine_fn
+vma_queue_write(VmaWriter *vmaw, const void *buf, size_t bytes)
+{
+    DPRINTF("vma_queue_write enter %zd\n", bytes);
+
+    assert(vmaw);
+    assert(buf);
+    assert(bytes <= VMA_MAX_EXTENT_SIZE);
+
+    VmaAIOCB *cb = NULL;
+    while (!cb) {
+        int i;
+        for (i = 0; i < WRITE_BUFFERS; i++) {
+            if (!vmaw->aiocbs[i]->bytes) {
+                cb = vmaw->aiocbs[i];
+                break;
+            }
+        }
+        if (!cb) {
+            qemu_co_queue_wait(&vmaw->wqueue);
+        }
+    }
+
+    memcpy(cb->buffer, buf, bytes);
+    cb->bytes = bytes;
+    cb->vmaw = vmaw;
+
+    DPRINTF("vma_queue_write start %zd\n", bytes);
+    cb->co = qemu_coroutine_create(vma_co_writer_task);
+    qemu_coroutine_enter(cb->co, cb);
+
+    DPRINTF("vma_queue_write leave\n");
+
+    return bytes;
+}
+
+VmaWriter *vma_writer_create(const char *filename, uuid_t uuid, Error **errp)
+{
+    const char *p;
+
+    assert(sizeof(VmaHeader) == (4096 + 8192));
+    assert(G_STRUCT_OFFSET(VmaHeader, config_names) == 2044);
+    assert(G_STRUCT_OFFSET(VmaHeader, config_data) == 3068);
+    assert(G_STRUCT_OFFSET(VmaHeader, dev_info) == 4096);
+    assert(sizeof(VmaExtentHeader) == 512);
+
+    VmaWriter *vmaw = g_new0(VmaWriter, 1);
+    vmaw->fd = -1;
+
+    vmaw->md5csum = g_checksum_new(G_CHECKSUM_MD5);
+    if (!vmaw->md5csum) {
+        error_setg(errp, "can't allocate cmsum\n");
+        goto err;
+    }
+
+    if (strstart(filename, "exec:", &p)) {
+        vmaw->cmd = popen(p, "w");
+        if (vmaw->cmd == NULL) {
+            error_setg(errp, "can't popen command '%s' - %s\n", p,
+                       g_strerror(errno));
+            goto err;
+        }
+        vmaw->fd = fileno(vmaw->cmd);
+
+        /* try to use O_NONBLOCK and O_DIRECT */
+        fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_NONBLOCK);
+        fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_DIRECT);
+
+    } else {
+        struct stat st;
+        int oflags;
+        const char *tmp_id_str;
+
+        if ((stat(filename, &st) == 0) && S_ISFIFO(st.st_mode)) {
+            oflags = O_NONBLOCK|O_DIRECT|O_WRONLY;
+            vmaw->fd = qemu_open(filename, oflags, 0644);
+        } else if (strstart(filename, "/dev/fdset/", &tmp_id_str)) {
+            oflags = O_NONBLOCK|O_DIRECT|O_WRONLY;
+            vmaw->fd = qemu_open(filename, oflags, 0644);
+        } else if (strstart(filename, "/dev/fdname/", &tmp_id_str)) {
+            vmaw->fd = monitor_get_fd(cur_mon, tmp_id_str, errp);
+            if (vmaw->fd < 0) {
+                goto err;
+            }
+            /* try to use O_NONBLOCK and O_DIRECT */
+            fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_NONBLOCK);
+            fcntl(vmaw->fd, F_SETFL, fcntl(vmaw->fd, F_GETFL)|O_DIRECT);
+        } else  {
+            oflags = O_NONBLOCK|O_DIRECT|O_WRONLY|O_CREAT|O_EXCL;
+            vmaw->fd = qemu_open(filename, oflags, 0644);
+        }
+
+        if (vmaw->fd < 0) {
+            error_setg(errp, "can't open file %s - %s\n", filename,
+                       g_strerror(errno));
+            goto err;
+        }
+    }
+
+    /* we use O_DIRECT, so we need to align IO buffers */
+    int i;
+    for (i = 0; i < WRITE_BUFFERS; i++) {
+        vmaw->aiocbs[i] = qemu_memalign(512, sizeof(VmaAIOCB));
+        memset(vmaw->aiocbs[i], 0, sizeof(VmaAIOCB));
+    }
+
+    vmaw->outbuf_count = 0;
+    vmaw->outbuf_pos = VMA_EXTENT_HEADER_SIZE;
+
+    vmaw->header_blob_table_pos = 1; /* start at pos 1 */
+
+    qemu_co_mutex_init(&vmaw->writer_lock);
+    qemu_co_mutex_init(&vmaw->flush_lock);
+    qemu_co_queue_init(&vmaw->wqueue);
+
+    uuid_copy(vmaw->uuid, uuid);
+
+    return vmaw;
+
+err:
+    if (vmaw) {
+        if (vmaw->cmd) {
+            pclose(vmaw->cmd);
+        } else if (vmaw->fd >= 0) {
+            close(vmaw->fd);
+        }
+
+        if (vmaw->md5csum) {
+            g_checksum_free(vmaw->md5csum);
+        }
+
+        g_free(vmaw);
+    }
+
+    return NULL;
+}
+
+static int coroutine_fn vma_write_header(VmaWriter *vmaw)
+{
+    assert(vmaw);
+    int header_clusters = 8;
+    char buf[65536*header_clusters];
+    VmaHeader *head = (VmaHeader *)buf;
+
+    int i;
+
+    DPRINTF("VMA WRITE HEADER\n");
+
+    if (vmaw->status < 0) {
+        return vmaw->status;
+    }
+
+    memset(buf, 0, sizeof(buf));
+
+    head->magic = VMA_MAGIC;
+    head->version = GUINT32_TO_BE(1); /* v1 */
+    memcpy(head->uuid, vmaw->uuid, 16);
+
+    time_t ctime = time(NULL);
+    head->ctime = GUINT64_TO_BE(ctime);
+
+    if (!vmaw->stream_count) {
+        return -1;
+    }
+
+    for (i = 0; i < VMA_MAX_CONFIGS; i++) {
+        head->config_names[i] = GUINT32_TO_BE(vmaw->config_names[i]);
+        head->config_data[i] = GUINT32_TO_BE(vmaw->config_data[i]);
+    }
+
+    /* 32 bytes per device (12 used currently) = 8192 bytes max */
+    for (i = 1; i <= 254; i++) {
+        VmaStreamInfo *si = &vmaw->stream_info[i];
+        if (si->size) {
+            assert(si->devname);
+            uint32_t devname_ptr = allocate_header_string(vmaw, si->devname);
+            if (!devname_ptr) {
+                return -1;
+            }
+            head->dev_info[i].devname_ptr = GUINT32_TO_BE(devname_ptr);
+            head->dev_info[i].size = GUINT64_TO_BE(si->size);
+        }
+    }
+
+    uint32_t header_size = sizeof(VmaHeader) + vmaw->header_blob_table_size;
+    head->header_size = GUINT32_TO_BE(header_size);
+
+    if (header_size > sizeof(buf)) {
+        return -1; /* just to be sure */
+    }
+
+    uint32_t blob_buffer_offset = sizeof(VmaHeader);
+    memcpy(buf + blob_buffer_offset, vmaw->header_blob_table,
+           vmaw->header_blob_table_size);
+    head->blob_buffer_offset = GUINT32_TO_BE(blob_buffer_offset);
+    head->blob_buffer_size = GUINT32_TO_BE(vmaw->header_blob_table_pos);
+
+    g_checksum_reset(vmaw->md5csum);
+    g_checksum_update(vmaw->md5csum, (const guchar *)buf, header_size);
+    gsize csize = 16;
+    g_checksum_get_digest(vmaw->md5csum, (guint8 *)(head->md5sum), &csize);
+
+    return vma_queue_write(vmaw, buf, header_size);
+}
+
+static int coroutine_fn vma_writer_flush(VmaWriter *vmaw)
+{
+    assert(vmaw);
+
+    int ret;
+    int i;
+
+    if (vmaw->status < 0) {
+        return vmaw->status;
+    }
+
+    if (!vmaw->header_written) {
+        vmaw->header_written = true;
+        ret = vma_write_header(vmaw);
+        if (ret < 0) {
+            vma_writer_set_error(vmaw, "vma_writer_flush: write header failed");
+            return ret;
+        }
+    }
+
+    DPRINTF("VMA WRITE FLUSH %d %d\n", vmaw->outbuf_count, vmaw->outbuf_pos);
+
+
+    VmaExtentHeader *ehead = (VmaExtentHeader *)vmaw->outbuf;
+
+    ehead->magic = VMA_EXTENT_MAGIC;
+    ehead->reserved1 = 0;
+
+    for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) {
+        ehead->blockinfo[i] = GUINT64_TO_BE(vmaw->outbuf_block_info[i]);
+    }
+
+    guint16 block_count = (vmaw->outbuf_pos - VMA_EXTENT_HEADER_SIZE) /
+        VMA_BLOCK_SIZE;
+
+    ehead->block_count = GUINT16_TO_BE(block_count);
+
+    memcpy(ehead->uuid, vmaw->uuid, sizeof(ehead->uuid));
+    memset(ehead->md5sum, 0, sizeof(ehead->md5sum));
+
+    g_checksum_reset(vmaw->md5csum);
+    g_checksum_update(vmaw->md5csum, vmaw->outbuf, VMA_EXTENT_HEADER_SIZE);
+    gsize csize = 16;
+    g_checksum_get_digest(vmaw->md5csum, ehead->md5sum, &csize);
+
+    int bytes = vmaw->outbuf_pos;
+    ret = vma_queue_write(vmaw, vmaw->outbuf, bytes);
+    if (ret != bytes) {
+        vma_writer_set_error(vmaw, "vma_writer_flush: failed write");
+    }
+
+    vmaw->outbuf_count = 0;
+    vmaw->outbuf_pos = VMA_EXTENT_HEADER_SIZE;
+
+    for (i = 0; i < VMA_BLOCKS_PER_EXTENT; i++) {
+        vmaw->outbuf_block_info[i] = 0;
+    }
+
+    return vmaw->status;
+}
+
+static int vma_count_open_streams(VmaWriter *vmaw)
+{
+    g_assert(vmaw != NULL);
+
+    int i;
+    int open_drives = 0;
+    for (i = 0; i <= 255; i++) {
+        if (vmaw->stream_info[i].size && !vmaw->stream_info[i].finished) {
+            open_drives++;
+        }
+    }
+
+    return open_drives;
+}
+
+/**
+ * all jobs should call this when there is no more data
+ * Returns: number of remaining stream (0 ==> finished)
+ */
+int coroutine_fn
+vma_writer_close_stream(VmaWriter *vmaw, uint8_t dev_id)
+{
+    g_assert(vmaw != NULL);
+
+    DPRINTF("vma_writer_set_status %d\n", dev_id);
+    if (!vmaw->stream_info[dev_id].size) {
+        vma_writer_set_error(vmaw, "vma_writer_close_stream: "
+                             "no such stream %d", dev_id);
+        return -1;
+    }
+    if (vmaw->stream_info[dev_id].finished) {
+        vma_writer_set_error(vmaw, "vma_writer_close_stream: "
+                             "stream already closed %d", dev_id);
+        return -1;
+    }
+
+    vmaw->stream_info[dev_id].finished = true;
+
+    int open_drives = vma_count_open_streams(vmaw);
+
+    if (open_drives <= 0) {
+        DPRINTF("vma_writer_set_status all drives completed\n");
+        qemu_co_mutex_lock(&vmaw->flush_lock);
+        int ret = vma_writer_flush(vmaw);
+        qemu_co_mutex_unlock(&vmaw->flush_lock);
+        if (ret < 0) {
+            vma_writer_set_error(vmaw, "vma_writer_close_stream: flush failed");
+        }
+    }
+
+    return open_drives;
+}
+
+int vma_writer_get_status(VmaWriter *vmaw, VmaStatus *status)
+{
+    int i;
+
+    g_assert(vmaw != NULL);
+
+    if (status) {
+        status->status = vmaw->status;
+        g_strlcpy(status->errmsg, vmaw->errmsg, sizeof(status->errmsg));
+        for (i = 0; i <= 255; i++) {
+            status->stream_info[i] = vmaw->stream_info[i];
+        }
+
+        uuid_unparse_lower(vmaw->uuid, status->uuid_str);
+    }
+
+    status->closed = vmaw->closed;
+
+    return vmaw->status;
+}
+
+static int vma_writer_get_buffer(VmaWriter *vmaw)
+{
+    int ret = 0;
+
+    qemu_co_mutex_lock(&vmaw->flush_lock);
+
+    /* wait until buffer is available */
+    while (vmaw->outbuf_count >= (VMA_BLOCKS_PER_EXTENT - 1)) {
+        ret = vma_writer_flush(vmaw);
+        if (ret < 0) {
+            vma_writer_set_error(vmaw, "vma_writer_get_buffer: flush failed");
+            break;
+        }
+    }
+
+    qemu_co_mutex_unlock(&vmaw->flush_lock);
+
+    return ret;
+}
+
+
+int64_t coroutine_fn
+vma_writer_write(VmaWriter *vmaw, uint8_t dev_id, int64_t cluster_num,
+                 unsigned char *buf, size_t *zero_bytes)
+{
+    g_assert(vmaw != NULL);
+    g_assert(zero_bytes != NULL);
+
+    *zero_bytes = 0;
+
+    if (vmaw->status < 0) {
+        return vmaw->status;
+    }
+
+    if (!dev_id || !vmaw->stream_info[dev_id].size) {
+        vma_writer_set_error(vmaw, "vma_writer_write: "
+                             "no such stream %d", dev_id);
+        return -1;
+    }
+
+    if (vmaw->stream_info[dev_id].finished) {
+        vma_writer_set_error(vmaw, "vma_writer_write: "
+                             "stream already closed %d", dev_id);
+        return -1;
+    }
+
+
+    if (cluster_num >= (((uint64_t)1)<<32)) {
+        vma_writer_set_error(vmaw, "vma_writer_write: "
+                             "cluster number out of range");
+        return -1;
+    }
+
+    if (dev_id == vmaw->vmstate_stream) {
+        if (cluster_num != vmaw->vmstate_clusters) {
+            vma_writer_set_error(vmaw, "vma_writer_write: "
+                                 "non sequential vmstate write");
+        }
+        vmaw->vmstate_clusters++;
+    } else if (cluster_num >= vmaw->stream_info[dev_id].cluster_count) {
+        vma_writer_set_error(vmaw, "vma_writer_write: cluster number too big");
+        return -1;
+    }
+
+    /* wait until buffer is available */
+    if (vma_writer_get_buffer(vmaw) < 0) {
+        vma_writer_set_error(vmaw, "vma_writer_write: "
+                             "vma_writer_get_buffer failed");
+        return -1;
+    }
+
+    DPRINTF("VMA WRITE %d %zd\n", dev_id, cluster_num);
+
+    uint16_t mask = 0;
+
+    if (buf) {
+        int i;
+        int bit = 1;
+        for (i = 0; i < 16; i++) {
+            unsigned char *vmablock = buf + (i*VMA_BLOCK_SIZE);
+            if (!buffer_is_zero(vmablock, VMA_BLOCK_SIZE)) {
+                mask |= bit;
+                memcpy(vmaw->outbuf + vmaw->outbuf_pos, vmablock,
+                       VMA_BLOCK_SIZE);
+                vmaw->outbuf_pos += VMA_BLOCK_SIZE;
+            } else {
+                DPRINTF("VMA WRITE %zd ZERO BLOCK %d\n", cluster_num, i);
+                vmaw->stream_info[dev_id].zero_bytes += VMA_BLOCK_SIZE;
+                *zero_bytes += VMA_BLOCK_SIZE;
+            }
+
+            bit = bit << 1;
+        }
+    } else {
+        DPRINTF("VMA WRITE %zd ZERO CLUSTER\n", cluster_num);
+        vmaw->stream_info[dev_id].zero_bytes += VMA_CLUSTER_SIZE;
+        *zero_bytes += VMA_CLUSTER_SIZE;
+    }
+
+    uint64_t block_info = ((uint64_t)mask) << (32+16);
+    block_info |= ((uint64_t)dev_id) << 32;
+    block_info |= (cluster_num & 0xffffffff);
+    vmaw->outbuf_block_info[vmaw->outbuf_count] = block_info;
+
+    DPRINTF("VMA WRITE MASK %zd %zx\n", cluster_num, block_info);
+
+    vmaw->outbuf_count++;
+
+    /** NOTE: We allways write whole clusters, but we correctly set
+     * transferred bytes. So transferred == size when when everything
+     * went OK.
+     */
+    size_t transferred = VMA_CLUSTER_SIZE;
+
+    if (dev_id != vmaw->vmstate_stream) {
+        uint64_t last = (cluster_num + 1) * VMA_CLUSTER_SIZE;
+        if (last > vmaw->stream_info[dev_id].size) {
+            uint64_t diff = last - vmaw->stream_info[dev_id].size;
+            if (diff >= VMA_CLUSTER_SIZE) {
+                vma_writer_set_error(vmaw, "vma_writer_write: "
+                                     "read after last cluster");
+                return -1;
+            }
+            transferred -= diff;
+        }
+    }
+
+    vmaw->stream_info[dev_id].transferred += transferred;
+
+    return transferred;
+}
+
+int vma_writer_close(VmaWriter *vmaw, Error **errp)
+{
+    g_assert(vmaw != NULL);
+
+    int i;
+
+    vma_queue_flush(vmaw);
+
+    /* this should not happen - just to be sure */
+    while (!qemu_co_queue_empty(&vmaw->wqueue)) {
+        DPRINTF("vma_writer_close wait\n");
+        co_sleep_ns(QEMU_CLOCK_REALTIME, 1000000);
+    }
+
+    if (vmaw->cmd) {
+        if (pclose(vmaw->cmd) < 0) {
+            vma_writer_set_error(vmaw, "vma_writer_close: "
+                                 "pclose failed - %s", g_strerror(errno));
+        }
+    } else {
+        if (close(vmaw->fd) < 0) {
+            vma_writer_set_error(vmaw, "vma_writer_close: "
+                                 "close failed - %s", g_strerror(errno));
+        }
+    }
+
+    for (i = 0; i <= 255; i++) {
+        VmaStreamInfo *si = &vmaw->stream_info[i];
+        if (si->size) {
+            if (!si->finished) {
+                vma_writer_set_error(vmaw, "vma_writer_close: "
+                                     "detected open stream '%s'", si->devname);
+            } else if ((si->transferred != si->size) &&
+                       (i != vmaw->vmstate_stream)) {
+                vma_writer_set_error(vmaw, "vma_writer_close: "
+                                     "incomplete stream '%s' (%zd != %zd)",
+                                     si->devname, si->transferred, si->size);
+            }
+        }
+    }
+
+    for (i = 0; i <= 255; i++) {
+        vmaw->stream_info[i].finished = 1; /* mark as closed */
+    }
+
+    vmaw->closed = 1;
+
+    if (vmaw->status < 0 && *errp == NULL) {
+        error_setg(errp, "%s", vmaw->errmsg);
+    }
+
+    return vmaw->status;
+}
+
+void vma_writer_destroy(VmaWriter *vmaw)
+{
+    assert(vmaw);
+
+    int i;
+
+    for (i = 0; i <= 255; i++) {
+        if (vmaw->stream_info[i].devname) {
+            g_free(vmaw->stream_info[i].devname);
+        }
+    }
+
+    if (vmaw->md5csum) {
+        g_checksum_free(vmaw->md5csum);
+    }
+
+    for (i = 0; i < WRITE_BUFFERS; i++) {
+        free(vmaw->aiocbs[i]);
+    }
+
+    g_free(vmaw);
+}
Index: new/vma.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ new/vma.c	2013-12-04 12:07:25.000000000 +0100
@@ -0,0 +1,579 @@
+/*
+ * VMA: Virtual Machine Archive
+ *
+ * Copyright (C) 2012-2013 Proxmox Server Solutions
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <glib.h>
+
+#include "vma.h"
+#include "qemu-common.h"
+#include "qemu/error-report.h"
+#include "qemu/main-loop.h"
+
+static void help(void)
+{
+    const char *help_msg =
+        "usage: vma command [command options]\n"
+        "\n"
+        "vma list <filename>\n"
+        "vma create <filename> [-c config] <archive> pathname ...\n"
+        "vma extract <filename> [-r <fifo>] <targetdir>\n"
+        ;
+
+    printf("%s", help_msg);
+    exit(1);
+}
+
+static const char *extract_devname(const char *path, char **devname, int index)
+{
+    assert(path);
+
+    const char *sep = strchr(path, '=');
+
+    if (sep) {
+        *devname = g_strndup(path, sep - path);
+        path = sep + 1;
+    } else {
+        if (index >= 0) {
+            *devname = g_strdup_printf("disk%d", index);
+        } else {
+            *devname = NULL;
+        }
+    }
+
+    return path;
+}
+
+static void print_content(VmaReader *vmar)
+{
+    assert(vmar);
+
+    VmaHeader *head = vma_reader_get_header(vmar);
+
+    GList *l = vma_reader_get_config_data(vmar);
+    while (l && l->data) {
+        VmaConfigData *cdata = (VmaConfigData *)l->data;
+        l = g_list_next(l);
+        printf("CFG: size: %d name: %s\n", cdata->len, cdata->name);
+    }
+
+    int i;
+    VmaDeviceInfo *di;
+    for (i = 1; i < 255; i++) {
+        di = vma_reader_get_device_info(vmar, i);
+        if (di) {
+            if (strcmp(di->devname, "vmstate") == 0) {
+                printf("VMSTATE: dev_id=%d memory: %zd\n", i, di->size);
+            } else {
+                printf("DEV: dev_id=%d size: %zd devname: %s\n",
+                       i, di->size, di->devname);
+            }
+        }
+    }
+    /* ctime is the last entry we print */
+    printf("CTIME: %s", ctime(&head->ctime));
+    fflush(stdout);
+}
+
+static int list_content(int argc, char **argv)
+{
+    int c, ret = 0;
+    const char *filename;
+
+    for (;;) {
+        c = getopt(argc, argv, "h");
+        if (c == -1) {
+            break;
+        }
+        switch (c) {
+        case '?':
+        case 'h':
+            help();
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    }
+
+    /* Get the filename */
+    if ((optind + 1) != argc) {
+        help();
+    }
+    filename = argv[optind++];
+
+    Error *errp = NULL;
+    VmaReader *vmar = vma_reader_create(filename, &errp);
+
+    if (!vmar) {
+        g_error("%s", error_get_pretty(errp));
+    }
+
+    print_content(vmar);
+
+    vma_reader_destroy(vmar);
+
+    return ret;
+}
+
+typedef struct RestoreMap {
+    char *devname;
+    char *path;
+    bool write_zero;
+} RestoreMap;
+
+static int extract_content(int argc, char **argv)
+{
+    int c, ret = 0;
+    int verbose = 0;
+    const char *filename;
+    const char *dirname;
+    const char *readmap = NULL;
+
+    for (;;) {
+        c = getopt(argc, argv, "hvr:");
+        if (c == -1) {
+            break;
+        }
+        switch (c) {
+        case '?':
+        case 'h':
+            help();
+            break;
+        case 'r':
+            readmap = optarg;
+            break;
+        case 'v':
+            verbose = 1;
+            break;
+        default:
+            help();
+        }
+    }
+
+    /* Get the filename */
+    if ((optind + 2) != argc) {
+        help();
+    }
+    filename = argv[optind++];
+    dirname = argv[optind++];
+
+    Error *errp = NULL;
+    VmaReader *vmar = vma_reader_create(filename, &errp);
+
+    if (!vmar) {
+        g_error("%s", error_get_pretty(errp));
+    }
+
+    if (mkdir(dirname, 0777) < 0) {
+        g_error("unable to create target directory %s - %s",
+                dirname, g_strerror(errno));
+    }
+
+    GList *l = vma_reader_get_config_data(vmar);
+    while (l && l->data) {
+        VmaConfigData *cdata = (VmaConfigData *)l->data;
+        l = g_list_next(l);
+        char *cfgfn = g_strdup_printf("%s/%s", dirname, cdata->name);
+        GError *err = NULL;
+        if (!g_file_set_contents(cfgfn, (gchar *)cdata->data, cdata->len,
+                                 &err)) {
+            g_error("unable to write file: %s", err->message);
+        }
+    }
+
+    GHashTable *devmap = g_hash_table_new(g_str_hash, g_str_equal);
+
+    if (readmap) {
+        print_content(vmar);
+
+        FILE *map = fopen(readmap, "r");
+        if (!map) {
+            g_error("unable to open fifo %s - %s", readmap, g_strerror(errno));
+        }
+
+        while (1) {
+            char inbuf[8192];
+            char *line = fgets(inbuf, sizeof(inbuf), map);
+            if (!line || line[0] == '\0' || !strcmp(line, "done\n")) {
+                break;
+            }
+            int len = strlen(line);
+            if (line[len - 1] == '\n') {
+                line[len - 1] = '\0';
+                if (len == 1) {
+                    break;
+                }
+            }
+
+            const char *path;
+            bool write_zero;
+            if (line[0] == '0' && line[1] == ':') {
+                path = inbuf + 2;
+                write_zero = false;
+            } else if (line[0] == '1' && line[1] == ':') {
+                path = inbuf + 2;
+                write_zero = true;
+            } else {
+                g_error("read map failed - parse error ('%s')", inbuf);
+            }
+
+            char *devname = NULL;
+            path = extract_devname(path, &devname, -1);
+            if (!devname) {
+                g_error("read map failed - no dev name specified ('%s')",
+                        inbuf);
+            }
+
+            RestoreMap *map = g_new0(RestoreMap, 1);
+            map->devname = g_strdup(devname);
+            map->path = g_strdup(path);
+            map->write_zero = write_zero;
+
+            g_hash_table_insert(devmap, map->devname, map);
+
+        };
+    }
+
+    int i;
+    int vmstate_fd = -1;
+    guint8 vmstate_stream = 0;
+
+    for (i = 1; i < 255; i++) {
+        VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i);
+        if (di && (strcmp(di->devname, "vmstate") == 0)) {
+            vmstate_stream = i;
+            char *statefn = g_strdup_printf("%s/vmstate.bin", dirname);
+            vmstate_fd = open(statefn, O_WRONLY|O_CREAT|O_EXCL, 0644);
+            if (vmstate_fd < 0) {
+                g_error("create vmstate file '%s' failed - %s", statefn,
+                        g_strerror(errno));
+            }
+            g_free(statefn);
+        } else if (di) {
+            char *devfn = NULL;
+            int flags = BDRV_O_RDWR|BDRV_O_CACHE_WB;
+            bool write_zero = true;
+
+            if (readmap) {
+                RestoreMap *map;
+                map = (RestoreMap *)g_hash_table_lookup(devmap, di->devname);
+                if (map == NULL) {
+                    g_error("no device name mapping for %s", di->devname);
+                }
+                devfn = map->path;
+                write_zero = map->write_zero;
+            } else {
+                devfn = g_strdup_printf("%s/tmp-disk-%s.raw",
+                                        dirname, di->devname);
+                printf("DEVINFO %s %zd\n", devfn, di->size);
+
+                bdrv_img_create(devfn, "raw", NULL, NULL, NULL, di->size,
+                                flags, &errp, 0);
+                if (error_is_set(&errp)) {
+                    g_error("can't create file %s: %s", devfn,
+                            error_get_pretty(errp));
+                }
+
+                /* Note: we created an empty file above, so there is no
+                 * need to write zeroes (so we generate a sparse file)
+                 */
+                write_zero = false;
+            }
+
+            BlockDriverState *bs = bdrv_new(di->devname);
+            if (bdrv_open(bs, devfn, NULL, flags, NULL, &errp)) {
+                g_error("can't open file %s - %s", devfn,
+                        error_get_pretty(errp));
+            }
+            if (vma_reader_register_bs(vmar, i, bs, write_zero, &errp) < 0) {
+                g_error("%s", error_get_pretty(errp));
+            }
+
+            if (!readmap) {
+                g_free(devfn);
+            }
+        }
+    }
+
+    if (vma_reader_restore(vmar, vmstate_fd, verbose, &errp) < 0) {
+        g_error("restore failed - %s", error_get_pretty(errp));
+    }
+
+    if (!readmap) {
+        for (i = 1; i < 255; i++) {
+            VmaDeviceInfo *di = vma_reader_get_device_info(vmar, i);
+            if (di && (i != vmstate_stream)) {
+                char *tmpfn = g_strdup_printf("%s/tmp-disk-%s.raw",
+                                              dirname, di->devname);
+                char *fn = g_strdup_printf("%s/disk-%s.raw",
+                                           dirname, di->devname);
+                if (rename(tmpfn, fn) != 0) {
+                    g_error("rename %s to %s failed - %s",
+                            tmpfn, fn, g_strerror(errno));
+                }
+            }
+        }
+    }
+
+    vma_reader_destroy(vmar);
+
+    bdrv_close_all();
+
+    return ret;
+}
+
+typedef struct BackupJob {
+    BlockDriverState *bs;
+    int64_t len;
+    VmaWriter *vmaw;
+    uint8_t dev_id;
+} BackupJob;
+
+#define BACKUP_SECTORS_PER_CLUSTER (VMA_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
+
+static void coroutine_fn backup_run(void *opaque)
+{
+    BackupJob *job = (BackupJob *)opaque;
+    struct iovec iov;
+    QEMUIOVector qiov;
+
+    int64_t start, end;
+    int ret = 0;
+
+    unsigned char *buf = qemu_blockalign(job->bs, VMA_CLUSTER_SIZE);
+
+    start = 0;
+    end = DIV_ROUND_UP(job->len / BDRV_SECTOR_SIZE,
+                       BACKUP_SECTORS_PER_CLUSTER);
+
+    for (; start < end; start++) {
+        iov.iov_base = buf;
+        iov.iov_len = VMA_CLUSTER_SIZE;
+        qemu_iovec_init_external(&qiov, &iov, 1);
+
+        ret = bdrv_co_readv(job->bs, start * BACKUP_SECTORS_PER_CLUSTER,
+                            BACKUP_SECTORS_PER_CLUSTER, &qiov);
+        if (ret < 0) {
+            vma_writer_set_error(job->vmaw, "read error", -1);
+            goto out;
+        }
+
+        size_t zb = 0;
+        if (vma_writer_write(job->vmaw, job->dev_id, start, buf, &zb) < 0) {
+            vma_writer_set_error(job->vmaw, "backup_dump_cb vma_writer_write failed", -1);
+            goto out;
+        }
+    }
+
+
+out:
+    if (vma_writer_close_stream(job->vmaw, job->dev_id) <= 0) {
+        Error *err = NULL;
+        if (vma_writer_close(job->vmaw, &err) != 0) {
+            g_warning("vma_writer_close failed %s", error_get_pretty(err));
+        }
+    }
+}
+
+static int create_archive(int argc, char **argv)
+{
+    int i, c, res;
+    int verbose = 0;
+    const char *archivename;
+    GList *config_files = NULL;
+
+    for (;;) {
+        c = getopt(argc, argv, "hvc:");
+        if (c == -1) {
+            break;
+        }
+        switch (c) {
+        case '?':
+        case 'h':
+            help();
+            break;
+        case 'c':
+            config_files = g_list_append(config_files, optarg);
+            break;
+        case 'v':
+            verbose = 1;
+            break;
+        default:
+            g_assert_not_reached();
+        }
+    }
+
+
+    /* make sure we have archive name and at least one path */
+    if ((optind + 2) > argc) {
+        help();
+    }
+
+    archivename = argv[optind++];
+
+    uuid_t uuid;
+    uuid_generate(uuid);
+
+    Error *local_err = NULL;
+    VmaWriter *vmaw = vma_writer_create(archivename, uuid, &local_err);
+
+    if (vmaw == NULL) {
+        g_error("%s", error_get_pretty(local_err));
+    }
+
+    GList *l = config_files;
+    while (l && l->data) {
+        char *name = l->data;
+        char *cdata = NULL;
+        gsize clen = 0;
+        GError *err = NULL;
+        if (!g_file_get_contents(name, &cdata, &clen, &err)) {
+            unlink(archivename);
+            g_error("Unable to read file: %s", err->message);
+        }
+
+        if (vma_writer_add_config(vmaw, name, cdata, clen) != 0) {
+            unlink(archivename);
+            g_error("Unable to append config data %s (len = %zd)",
+                    name, clen);
+        }
+        l = g_list_next(l);
+    }
+
+    int ind = 0;
+    while (optind < argc) {
+        const char *path = argv[optind++];
+        char *devname = NULL;
+        path = extract_devname(path, &devname, ind++);
+
+        BlockDriver *drv = NULL;
+        BlockDriverState *bs = bdrv_new(devname);
+        Error *errp = NULL;
+
+        res = bdrv_open(bs, path, NULL, BDRV_O_CACHE_WB , drv, &errp);
+        if (res < 0) {
+            unlink(archivename);
+            g_error("bdrv_open '%s' failed - %s", path, error_get_pretty(errp));
+        }
+        int64_t size = bdrv_getlength(bs);
+        int dev_id = vma_writer_register_stream(vmaw, devname, size);
+        if (dev_id <= 0) {
+            unlink(archivename);
+            g_error("vma_writer_register_stream '%s' failed", devname);
+        }
+
+        BackupJob *job = g_new0(BackupJob, 1);
+        job->len = size;
+        job->bs = bs;
+        job->vmaw = vmaw;
+        job->dev_id = dev_id;
+
+        Coroutine *co = qemu_coroutine_create(backup_run);
+        qemu_coroutine_enter(co, job);
+    }
+
+    VmaStatus vmastat;
+    int percent = 0;
+    int last_percent = -1;
+
+    while (1) {
+        main_loop_wait(false);
+        vma_writer_get_status(vmaw, &vmastat);
+
+        if (verbose) {
+
+            uint64_t total = 0;
+            uint64_t transferred = 0;
+            uint64_t zero_bytes = 0;
+
+            int i;
+            for (i = 0; i < 256; i++) {
+                if (vmastat.stream_info[i].size) {
+                    total += vmastat.stream_info[i].size;
+                    transferred += vmastat.stream_info[i].transferred;
+                    zero_bytes += vmastat.stream_info[i].zero_bytes;
+                }
+            }
+            percent = (transferred*100)/total;
+            if (percent != last_percent) {
+                fprintf(stderr, "progress %d%% %zd/%zd %zd\n", percent,
+                        transferred, total, zero_bytes);
+                fflush(stderr);
+
+                last_percent = percent;
+            }
+        }
+
+        if (vmastat.closed) {
+            break;
+        }
+    }
+
+    bdrv_drain_all();
+
+    vma_writer_get_status(vmaw, &vmastat);
+
+    if (verbose) {
+        for (i = 0; i < 256; i++) {
+            VmaStreamInfo *si = &vmastat.stream_info[i];
+            if (si->size) {
+                fprintf(stderr, "image %s: size=%zd zeros=%zd saved=%zd\n",
+                        si->devname, si->size, si->zero_bytes,
+                        si->size - si->zero_bytes);
+            }
+        }
+    }
+
+    if (vmastat.status < 0) {
+        unlink(archivename);
+        g_error("creating vma archive failed");
+    }
+
+    return 0;
+}
+
+int main(int argc, char **argv)
+{
+    const char *cmdname;
+
+    error_set_progname(argv[0]);
+
+    qemu_init_main_loop();
+
+    bdrv_init();
+
+    if (argc < 2) {
+        help();
+    }
+
+    cmdname = argv[1];
+    argc--; argv++;
+
+
+    if (!strcmp(cmdname, "list")) {
+        return list_content(argc, argv);
+    } else if (!strcmp(cmdname, "create")) {
+        return create_archive(argc, argv);
+    } else if (!strcmp(cmdname, "extract")) {
+        return extract_content(argc, argv);
+    }
+
+    help();
+    return 0;
+}
Index: new/vma.h
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ new/vma.h	2013-12-04 14:27:56.000000000 +0100
@@ -0,0 +1,146 @@
+/*
+ * VMA: Virtual Machine Archive
+ *
+ * Copyright (C) Proxmox Server Solutions
+ *
+ * Authors:
+ *  Dietmar Maurer (dietmar@proxmox.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef BACKUP_VMA_H
+#define BACKUP_VMA_H
+
+#include <uuid/uuid.h>
+#include "qapi/error.h"
+#include "block/block.h"
+
+#define VMA_BLOCK_BITS 12
+#define VMA_BLOCK_SIZE (1<<VMA_BLOCK_BITS)
+#define VMA_CLUSTER_BITS (VMA_BLOCK_BITS+4)
+#define VMA_CLUSTER_SIZE (1<<VMA_CLUSTER_BITS)
+
+#if VMA_CLUSTER_SIZE != 65536
+#error unexpected cluster size
+#endif
+
+#define VMA_EXTENT_HEADER_SIZE 512
+#define VMA_BLOCKS_PER_EXTENT 59
+#define VMA_MAX_CONFIGS 256
+
+#define VMA_MAX_EXTENT_SIZE \
+    (VMA_EXTENT_HEADER_SIZE+VMA_CLUSTER_SIZE*VMA_BLOCKS_PER_EXTENT)
+#if VMA_MAX_EXTENT_SIZE != 3867136
+#error unexpected VMA_EXTENT_SIZE
+#endif
+
+/* File Format Definitions */
+
+#define VMA_MAGIC (GUINT32_TO_BE(('V'<<24)|('M'<<16)|('A'<<8)|0x00))
+#define VMA_EXTENT_MAGIC (GUINT32_TO_BE(('V'<<24)|('M'<<16)|('A'<<8)|'E'))
+
+typedef struct VmaDeviceInfoHeader {
+    uint32_t devname_ptr; /* offset into blob_buffer table */
+    uint32_t reserved0;
+    uint64_t size; /* device size in bytes */
+    uint64_t reserved1;
+    uint64_t reserved2;
+} VmaDeviceInfoHeader;
+
+typedef struct VmaHeader {
+    uint32_t magic;
+    uint32_t version;
+    unsigned char uuid[16];
+    int64_t ctime;
+    unsigned char md5sum[16];
+
+    uint32_t blob_buffer_offset;
+    uint32_t blob_buffer_size;
+    uint32_t header_size;
+
+    unsigned char reserved[1984];
+
+    uint32_t config_names[VMA_MAX_CONFIGS]; /* offset into blob_buffer table */
+    uint32_t config_data[VMA_MAX_CONFIGS];  /* offset into blob_buffer table */
+
+    uint32_t reserved1;
+
+    VmaDeviceInfoHeader dev_info[256];
+} VmaHeader;
+
+typedef struct VmaExtentHeader {
+    uint32_t magic;
+    uint16_t reserved1;
+    uint16_t block_count;
+    unsigned char uuid[16];
+    unsigned char md5sum[16];
+    uint64_t blockinfo[VMA_BLOCKS_PER_EXTENT];
+} VmaExtentHeader;
+
+/* functions/definitions to read/write vma files */
+
+typedef struct VmaReader VmaReader;
+
+typedef struct VmaWriter VmaWriter;
+
+typedef struct VmaConfigData {
+    const char *name;
+    const void *data;
+    uint32_t len;
+} VmaConfigData;
+
+typedef struct VmaStreamInfo {
+    uint64_t size;
+    uint64_t cluster_count;
+    uint64_t transferred;
+    uint64_t zero_bytes;
+    int finished;
+    char *devname;
+} VmaStreamInfo;
+
+typedef struct VmaStatus {
+    int status;
+    bool closed;
+    char errmsg[8192];
+    char uuid_str[37];
+    VmaStreamInfo stream_info[256];
+} VmaStatus;
+
+typedef struct VmaDeviceInfo {
+    uint64_t size; /* device size in bytes */
+    const char *devname;
+} VmaDeviceInfo;
+
+VmaWriter *vma_writer_create(const char *filename, uuid_t uuid, Error **errp);
+int vma_writer_close(VmaWriter *vmaw, Error **errp);
+void vma_writer_destroy(VmaWriter *vmaw);
+int vma_writer_add_config(VmaWriter *vmaw, const char *name, gpointer data,
+                          size_t len);
+int vma_writer_register_stream(VmaWriter *vmaw, const char *devname,
+                               size_t size);
+
+int64_t coroutine_fn vma_writer_write(VmaWriter *vmaw, uint8_t dev_id,
+                                      int64_t cluster_num, unsigned char *buf,
+                                      size_t *zero_bytes);
+
+int coroutine_fn vma_writer_close_stream(VmaWriter *vmaw, uint8_t dev_id);
+
+int vma_writer_get_status(VmaWriter *vmaw, VmaStatus *status);
+void vma_writer_set_error(VmaWriter *vmaw, const char *fmt, ...);
+
+
+VmaReader *vma_reader_create(const char *filename, Error **errp);
+void vma_reader_destroy(VmaReader *vmar);
+VmaHeader *vma_reader_get_header(VmaReader *vmar);
+GList *vma_reader_get_config_data(VmaReader *vmar);
+VmaDeviceInfo *vma_reader_get_device_info(VmaReader *vmar, guint8 dev_id);
+int vma_reader_register_bs(VmaReader *vmar, guint8 dev_id,
+                           BlockDriverState *bs, bool write_zeroes,
+                           Error **errp);
+int vma_reader_restore(VmaReader *vmar, int vmstate_fd, bool verbose,
+                       Error **errp);
+
+#endif /* BACKUP_VMA_H */
Index: new/Makefile.objs
===================================================================
--- new.orig/Makefile.objs	2013-12-04 12:07:18.000000000 +0100
+++ new/Makefile.objs	2013-12-04 12:07:25.000000000 +0100
@@ -14,6 +14,7 @@
 block-obj-y += block/
 block-obj-y += qapi-types.o qapi-visit.o
 block-obj-y += qemu-io-cmds.o
+block-obj-y += vma-writer.o
 
 block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
 block-obj-y += qemu-coroutine-sleep.o