2013-04-29 20:48:18 +02:00
|
|
|
/*
|
|
|
|
* Block driver for Hyper-V VHDX Images
|
|
|
|
*
|
|
|
|
* Copyright (c) 2013 Red Hat, Inc.,
|
|
|
|
*
|
|
|
|
* Authors:
|
|
|
|
* Jeff Cody <jcody@redhat.com>
|
|
|
|
*
|
2013-10-30 15:44:38 +01:00
|
|
|
* This is based on the "VHDX Format Specification v1.00", published 8/25/2012
|
2013-04-29 20:48:18 +02:00
|
|
|
* by Microsoft:
|
2013-10-30 15:44:38 +01:00
|
|
|
* https://www.microsoft.com/en-us/download/details.aspx?id=34750
|
2013-04-29 20:48:18 +02:00
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2016-01-18 19:01:42 +01:00
|
|
|
#include "qemu/osdep.h"
|
include/qemu/osdep.h: Don't include qapi/error.h
Commit 57cb38b included qapi/error.h into qemu/osdep.h to get the
Error typedef. Since then, we've moved to include qemu/osdep.h
everywhere. Its file comment explains: "To avoid getting into
possible circular include dependencies, this file should not include
any other QEMU headers, with the exceptions of config-host.h,
compiler.h, os-posix.h and os-win32.h, all of which are doing a
similar job to this file and are under similar constraints."
qapi/error.h doesn't do a similar job, and it doesn't adhere to
similar constraints: it includes qapi-types.h. That's in excess of
100KiB of crap most .c files don't actually need.
Add the typedef to qemu/typedefs.h, and include that instead of
qapi/error.h. Include qapi/error.h in .c files that need it and don't
get it now. Include qapi-types.h in qom/object.h for uint16List.
Update scripts/clean-includes accordingly. Update it further to match
reality: replace config.h by config-target.h, add sysemu/os-posix.h,
sysemu/os-win32.h. Update the list of includes in the qemu/osdep.h
comment quoted above similarly.
This reduces the number of objects depending on qapi/error.h from "all
of them" to less than a third. Unfortunately, the number depending on
qapi-types.h shrinks only a little. More work is needed for that one.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
[Fix compilation without the spice devel packages. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2016-03-14 09:01:28 +01:00
|
|
|
#include "qapi/error.h"
|
2013-04-29 20:48:18 +02:00
|
|
|
#include "block/block_int.h"
|
2018-06-14 21:14:28 +02:00
|
|
|
#include "block/qdict.h"
|
2016-03-08 15:57:05 +01:00
|
|
|
#include "sysemu/block-backend.h"
|
2013-04-29 20:48:18 +02:00
|
|
|
#include "qemu/module.h"
|
2018-02-01 12:18:46 +01:00
|
|
|
#include "qemu/option.h"
|
2013-04-29 20:48:18 +02:00
|
|
|
#include "qemu/crc32c.h"
|
2016-03-15 17:22:36 +01:00
|
|
|
#include "qemu/bswap.h"
|
2019-09-10 17:26:22 +02:00
|
|
|
#include "qemu/error-report.h"
|
2018-05-03 21:50:20 +02:00
|
|
|
#include "vhdx.h"
|
2017-04-06 12:00:28 +02:00
|
|
|
#include "migration/blocker.h"
|
2016-09-21 06:27:16 +02:00
|
|
|
#include "qemu/uuid.h"
|
2018-03-09 19:53:19 +01:00
|
|
|
#include "qapi/qmp/qdict.h"
|
|
|
|
#include "qapi/qobject-input-visitor.h"
|
|
|
|
#include "qapi/qapi-visit-block-core.h"
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
/* Options for VHDX creation */
|
|
|
|
|
|
|
|
#define VHDX_BLOCK_OPT_LOG_SIZE "log_size"
|
|
|
|
#define VHDX_BLOCK_OPT_BLOCK_SIZE "block_size"
|
|
|
|
#define VHDX_BLOCK_OPT_ZERO "block_state_zero"
|
|
|
|
|
|
|
|
typedef enum VHDXImageType {
|
|
|
|
VHDX_TYPE_DYNAMIC = 0,
|
|
|
|
VHDX_TYPE_FIXED,
|
|
|
|
VHDX_TYPE_DIFFERENCING, /* Currently unsupported */
|
|
|
|
} VHDXImageType;
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
static QemuOptsList vhdx_create_opts;
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
/* Several metadata and region table data entries are identified by
|
|
|
|
* guids in a MS-specific GUID format. */
|
|
|
|
|
|
|
|
|
|
|
|
/* ------- Known Region Table GUIDs ---------------------- */
|
|
|
|
static const MSGUID bat_guid = { .data1 = 0x2dc27766,
|
|
|
|
.data2 = 0xf623,
|
|
|
|
.data3 = 0x4200,
|
|
|
|
.data4 = { 0x9d, 0x64, 0x11, 0x5e,
|
|
|
|
0x9b, 0xfd, 0x4a, 0x08} };
|
|
|
|
|
|
|
|
static const MSGUID metadata_guid = { .data1 = 0x8b7ca206,
|
|
|
|
.data2 = 0x4790,
|
|
|
|
.data3 = 0x4b9a,
|
|
|
|
.data4 = { 0xb8, 0xfe, 0x57, 0x5f,
|
|
|
|
0x05, 0x0f, 0x88, 0x6e} };
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* ------- Known Metadata Entry GUIDs ---------------------- */
|
|
|
|
static const MSGUID file_param_guid = { .data1 = 0xcaa16737,
|
|
|
|
.data2 = 0xfa36,
|
|
|
|
.data3 = 0x4d43,
|
|
|
|
.data4 = { 0xb3, 0xb6, 0x33, 0xf0,
|
|
|
|
0xaa, 0x44, 0xe7, 0x6b} };
|
|
|
|
|
|
|
|
static const MSGUID virtual_size_guid = { .data1 = 0x2FA54224,
|
|
|
|
.data2 = 0xcd1b,
|
|
|
|
.data3 = 0x4876,
|
|
|
|
.data4 = { 0xb2, 0x11, 0x5d, 0xbe,
|
|
|
|
0xd8, 0x3b, 0xf4, 0xb8} };
|
|
|
|
|
|
|
|
static const MSGUID page83_guid = { .data1 = 0xbeca12ab,
|
|
|
|
.data2 = 0xb2e6,
|
|
|
|
.data3 = 0x4523,
|
|
|
|
.data4 = { 0x93, 0xef, 0xc3, 0x09,
|
|
|
|
0xe0, 0x00, 0xc7, 0x46} };
|
|
|
|
|
|
|
|
|
|
|
|
static const MSGUID phys_sector_guid = { .data1 = 0xcda348c7,
|
|
|
|
.data2 = 0x445d,
|
|
|
|
.data3 = 0x4471,
|
|
|
|
.data4 = { 0x9c, 0xc9, 0xe9, 0x88,
|
|
|
|
0x52, 0x51, 0xc5, 0x56} };
|
|
|
|
|
|
|
|
static const MSGUID parent_locator_guid = { .data1 = 0xa8d35f2d,
|
|
|
|
.data2 = 0xb30b,
|
|
|
|
.data3 = 0x454d,
|
|
|
|
.data4 = { 0xab, 0xf7, 0xd3,
|
|
|
|
0xd8, 0x48, 0x34,
|
|
|
|
0xab, 0x0c} };
|
|
|
|
|
|
|
|
static const MSGUID logical_sector_guid = { .data1 = 0x8141bf1d,
|
|
|
|
.data2 = 0xa96f,
|
|
|
|
.data3 = 0x4709,
|
|
|
|
.data4 = { 0xba, 0x47, 0xf2,
|
|
|
|
0x33, 0xa8, 0xfa,
|
|
|
|
0xab, 0x5f} };
|
|
|
|
|
|
|
|
/* Each parent type must have a valid GUID; this is for parent images
|
|
|
|
* of type 'VHDX'. If we were to allow e.g. a QCOW2 parent, we would
|
|
|
|
* need to make up our own QCOW2 GUID type */
|
2014-09-14 21:29:59 +02:00
|
|
|
static const MSGUID parent_vhdx_guid __attribute__((unused))
|
|
|
|
= { .data1 = 0xb04aefb7,
|
2013-04-29 20:48:18 +02:00
|
|
|
.data2 = 0xd19e,
|
|
|
|
.data3 = 0x4a81,
|
|
|
|
.data4 = { 0xb7, 0x89, 0x25, 0xb8,
|
|
|
|
0xe9, 0x44, 0x59, 0x13} };
|
|
|
|
|
|
|
|
|
|
|
|
#define META_FILE_PARAMETER_PRESENT 0x01
|
|
|
|
#define META_VIRTUAL_DISK_SIZE_PRESENT 0x02
|
|
|
|
#define META_PAGE_83_PRESENT 0x04
|
|
|
|
#define META_LOGICAL_SECTOR_SIZE_PRESENT 0x08
|
|
|
|
#define META_PHYS_SECTOR_SIZE_PRESENT 0x10
|
|
|
|
#define META_PARENT_LOCATOR_PRESENT 0x20
|
|
|
|
|
|
|
|
#define META_ALL_PRESENT \
|
|
|
|
(META_FILE_PARAMETER_PRESENT | META_VIRTUAL_DISK_SIZE_PRESENT | \
|
|
|
|
META_PAGE_83_PRESENT | META_LOGICAL_SECTOR_SIZE_PRESENT | \
|
|
|
|
META_PHYS_SECTOR_SIZE_PRESENT)
|
|
|
|
|
|
|
|
|
2013-04-29 20:48:19 +02:00
|
|
|
typedef struct VHDXSectorInfo {
|
|
|
|
uint32_t bat_idx; /* BAT entry index */
|
|
|
|
uint32_t sectors_avail; /* sectors available in payload block */
|
|
|
|
uint32_t bytes_left; /* bytes left in the block after data to r/w */
|
|
|
|
uint32_t bytes_avail; /* bytes available in payload block */
|
|
|
|
uint64_t file_offset; /* absolute offset in bytes, in file */
|
|
|
|
uint64_t block_offset; /* block offset, in bytes */
|
|
|
|
} VHDXSectorInfo;
|
|
|
|
|
2013-10-30 15:44:39 +01:00
|
|
|
/* Calculates new checksum.
|
|
|
|
*
|
|
|
|
* Zero is substituted during crc calculation for the original crc field
|
|
|
|
* crc_offset: byte offset in buf of the buffer crc
|
|
|
|
* buf: buffer pointer
|
|
|
|
* size: size of buffer (must be > crc_offset+4)
|
|
|
|
*
|
2014-08-06 21:54:58 +02:00
|
|
|
* Note: The buffer should have all multi-byte data in little-endian format,
|
|
|
|
* and the resulting checksum is in little endian format.
|
2013-10-30 15:44:39 +01:00
|
|
|
*/
|
|
|
|
uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset)
|
|
|
|
{
|
|
|
|
uint32_t crc;
|
|
|
|
|
|
|
|
assert(buf != NULL);
|
|
|
|
assert(size > (crc_offset + sizeof(crc)));
|
|
|
|
|
|
|
|
memset(buf + crc_offset, 0, sizeof(crc));
|
|
|
|
crc = crc32c(0xffffffff, buf, size);
|
2018-10-16 19:09:38 +02:00
|
|
|
crc = cpu_to_le32(crc);
|
2013-10-30 15:44:39 +01:00
|
|
|
memcpy(buf + crc_offset, &crc, sizeof(crc));
|
|
|
|
|
|
|
|
return crc;
|
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size,
|
|
|
|
int crc_offset)
|
|
|
|
{
|
|
|
|
uint32_t crc_new;
|
|
|
|
uint32_t crc_orig;
|
|
|
|
assert(buf != NULL);
|
|
|
|
|
|
|
|
if (crc_offset > 0) {
|
|
|
|
memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
|
|
|
|
memset(buf + crc_offset, 0, sizeof(crc_orig));
|
|
|
|
}
|
|
|
|
|
|
|
|
crc_new = crc32c(crc, buf, size);
|
|
|
|
if (crc_offset > 0) {
|
|
|
|
memcpy(buf + crc_offset, &crc_orig, sizeof(crc_orig));
|
|
|
|
}
|
|
|
|
|
|
|
|
return crc_new;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Validates the checksum of the buffer, with an in-place CRC.
|
|
|
|
*
|
|
|
|
* Zero is substituted during crc calculation for the original crc field,
|
2018-07-12 21:51:20 +02:00
|
|
|
* and the crc field is restored afterwards. But the buffer will be modified
|
2013-04-29 20:48:18 +02:00
|
|
|
* during the calculation, so this may not be not suitable for multi-threaded
|
|
|
|
* use.
|
|
|
|
*
|
|
|
|
* crc_offset: byte offset in buf of the buffer crc
|
|
|
|
* buf: buffer pointer
|
|
|
|
* size: size of buffer (must be > crc_offset+4)
|
|
|
|
*
|
|
|
|
* returns true if checksum is valid, false otherwise
|
|
|
|
*/
|
|
|
|
bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset)
|
|
|
|
{
|
|
|
|
uint32_t crc_orig;
|
|
|
|
uint32_t crc;
|
|
|
|
|
|
|
|
assert(buf != NULL);
|
|
|
|
assert(size > (crc_offset + 4));
|
|
|
|
|
|
|
|
memcpy(&crc_orig, buf + crc_offset, sizeof(crc_orig));
|
|
|
|
crc_orig = le32_to_cpu(crc_orig);
|
|
|
|
|
|
|
|
crc = vhdx_checksum_calc(0xffffffff, buf, size, crc_offset);
|
|
|
|
|
|
|
|
return crc == crc_orig;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2013-10-30 15:44:39 +01:00
|
|
|
/*
|
|
|
|
* This generates a UUID that is compliant with the MS GUIDs used
|
|
|
|
* in the VHDX spec (and elsewhere).
|
|
|
|
*/
|
|
|
|
void vhdx_guid_generate(MSGUID *guid)
|
|
|
|
{
|
2016-09-21 06:27:16 +02:00
|
|
|
QemuUUID uuid;
|
2013-10-30 15:44:39 +01:00
|
|
|
assert(guid != NULL);
|
|
|
|
|
2016-09-21 06:27:16 +02:00
|
|
|
qemu_uuid_generate(&uuid);
|
|
|
|
memcpy(guid, &uuid, sizeof(MSGUID));
|
2013-10-30 15:44:39 +01:00
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:46 +01:00
|
|
|
/* Check for region overlaps inside the VHDX image */
|
|
|
|
static int vhdx_region_check(BDRVVHDXState *s, uint64_t start, uint64_t length)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint64_t end;
|
|
|
|
VHDXRegionEntry *r;
|
|
|
|
|
|
|
|
end = start + length;
|
|
|
|
QLIST_FOREACH(r, &s->regions, entries) {
|
|
|
|
if (!((start >= r->end) || (end <= r->start))) {
|
2019-09-10 17:26:22 +02:00
|
|
|
error_report("VHDX region %" PRIu64 "-%" PRIu64 " overlaps with "
|
|
|
|
"region %" PRIu64 "-%." PRIu64, start, end, r->start,
|
|
|
|
r->end);
|
2013-10-30 15:44:46 +01:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
exit:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Register a region for future checks */
|
|
|
|
static void vhdx_region_register(BDRVVHDXState *s,
|
|
|
|
uint64_t start, uint64_t length)
|
|
|
|
{
|
|
|
|
VHDXRegionEntry *r;
|
|
|
|
|
|
|
|
r = g_malloc0(sizeof(*r));
|
|
|
|
|
|
|
|
r->start = start;
|
|
|
|
r->end = start + length;
|
|
|
|
|
|
|
|
QLIST_INSERT_HEAD(&s->regions, r, entries);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Free all registered regions */
|
|
|
|
static void vhdx_region_unregister_all(BDRVVHDXState *s)
|
|
|
|
{
|
|
|
|
VHDXRegionEntry *r, *r_next;
|
|
|
|
|
|
|
|
QLIST_FOREACH_SAFE(r, &s->regions, entries, r_next) {
|
|
|
|
QLIST_REMOVE(r, entries);
|
|
|
|
g_free(r);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:51 +01:00
|
|
|
static void vhdx_set_shift_bits(BDRVVHDXState *s)
|
|
|
|
{
|
2015-12-18 16:04:26 +01:00
|
|
|
s->logical_sector_size_bits = ctz32(s->logical_sector_size);
|
|
|
|
s->sectors_per_block_bits = ctz32(s->sectors_per_block);
|
|
|
|
s->chunk_ratio_bits = ctz64(s->chunk_ratio);
|
|
|
|
s->block_size_bits = ctz32(s->block_size);
|
2013-10-30 15:44:51 +01:00
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
/*
|
|
|
|
* Per the MS VHDX Specification, for every VHDX file:
|
|
|
|
* - The header section is fixed size - 1 MB
|
|
|
|
* - The header section is always the first "object"
|
|
|
|
* - The first 64KB of the header is the File Identifier
|
|
|
|
* - The first uint64 (8 bytes) is the VHDX Signature ("vhdxfile")
|
|
|
|
* - The following 512 bytes constitute a UTF-16 string identifiying the
|
|
|
|
* software that created the file, and is optional and diagnostic only.
|
|
|
|
*
|
|
|
|
* Therefore, we probe by looking for the vhdxfile signature "vhdxfile"
|
|
|
|
*/
|
|
|
|
static int vhdx_probe(const uint8_t *buf, int buf_size, const char *filename)
|
|
|
|
{
|
|
|
|
if (buf_size >= 8 && !memcmp(buf, "vhdxfile", 8)) {
|
|
|
|
return 100;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:51 +01:00
|
|
|
/*
|
|
|
|
* Writes the header to the specified offset.
|
|
|
|
*
|
|
|
|
* This will optionally read in buffer data from disk (otherwise zero-fill),
|
|
|
|
* and then update the header checksum. Header is converted to proper
|
|
|
|
* endianness before being written to the specified file offset
|
|
|
|
*/
|
2016-06-20 18:24:02 +02:00
|
|
|
static int vhdx_write_header(BdrvChild *file, VHDXHeader *hdr,
|
2013-10-30 15:44:51 +01:00
|
|
|
uint64_t offset, bool read)
|
|
|
|
{
|
2016-06-20 18:24:02 +02:00
|
|
|
BlockDriverState *bs_file = file->bs;
|
2013-10-30 15:44:51 +01:00
|
|
|
uint8_t *buffer = NULL;
|
|
|
|
int ret;
|
2014-08-06 21:54:58 +02:00
|
|
|
VHDXHeader *header_le;
|
2013-10-30 15:44:51 +01:00
|
|
|
|
|
|
|
assert(bs_file != NULL);
|
|
|
|
assert(hdr != NULL);
|
|
|
|
|
|
|
|
/* the header checksum is not over just the packed size of VHDXHeader,
|
|
|
|
* but rather over the entire 'reserved' range for the header, which is
|
|
|
|
* 4KB (VHDX_HEADER_SIZE). */
|
|
|
|
|
|
|
|
buffer = qemu_blockalign(bs_file, VHDX_HEADER_SIZE);
|
|
|
|
if (read) {
|
|
|
|
/* if true, we can't assume the extra reserved bytes are 0 */
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(file, offset, buffer, VHDX_HEADER_SIZE);
|
2013-10-30 15:44:51 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
memset(buffer, 0, VHDX_HEADER_SIZE);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* overwrite the actual VHDXHeader portion */
|
2014-08-06 21:54:58 +02:00
|
|
|
header_le = (VHDXHeader *)buffer;
|
|
|
|
memcpy(header_le, hdr, sizeof(VHDXHeader));
|
|
|
|
vhdx_header_le_export(hdr, header_le);
|
|
|
|
vhdx_update_checksum(buffer, VHDX_HEADER_SIZE,
|
|
|
|
offsetof(VHDXHeader, checksum));
|
2016-06-20 20:09:15 +02:00
|
|
|
ret = bdrv_pwrite_sync(file, offset, header_le, sizeof(VHDXHeader));
|
2013-10-30 15:44:51 +01:00
|
|
|
|
|
|
|
exit:
|
|
|
|
qemu_vfree(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:39 +01:00
|
|
|
/* Update the VHDX headers
|
|
|
|
*
|
|
|
|
* This follows the VHDX spec procedures for header updates.
|
|
|
|
*
|
|
|
|
* - non-current header is updated with largest sequence number
|
|
|
|
*/
|
|
|
|
static int vhdx_update_header(BlockDriverState *bs, BDRVVHDXState *s,
|
2013-10-30 15:44:43 +01:00
|
|
|
bool generate_data_write_guid, MSGUID *log_guid)
|
2013-10-30 15:44:39 +01:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
int hdr_idx = 0;
|
|
|
|
uint64_t header_offset = VHDX_HEADER1_OFFSET;
|
|
|
|
|
|
|
|
VHDXHeader *active_header;
|
|
|
|
VHDXHeader *inactive_header;
|
|
|
|
|
|
|
|
/* operate on the non-current header */
|
|
|
|
if (s->curr_header == 0) {
|
|
|
|
hdr_idx = 1;
|
|
|
|
header_offset = VHDX_HEADER2_OFFSET;
|
|
|
|
}
|
|
|
|
|
|
|
|
active_header = s->headers[s->curr_header];
|
|
|
|
inactive_header = s->headers[hdr_idx];
|
|
|
|
|
|
|
|
inactive_header->sequence_number = active_header->sequence_number + 1;
|
|
|
|
|
|
|
|
/* a new file guid must be generated before any file write, including
|
|
|
|
* headers */
|
|
|
|
inactive_header->file_write_guid = s->session_guid;
|
|
|
|
|
|
|
|
/* a new data guid only needs to be generated before any guest-visible
|
|
|
|
* writes (i.e. something observable via virtual disk read) */
|
|
|
|
if (generate_data_write_guid) {
|
|
|
|
vhdx_guid_generate(&inactive_header->data_write_guid);
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:43 +01:00
|
|
|
/* update the log guid if present */
|
|
|
|
if (log_guid) {
|
|
|
|
inactive_header->log_guid = *log_guid;
|
|
|
|
}
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = vhdx_write_header(bs->file, inactive_header, header_offset, true);
|
2013-10-30 15:44:39 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->curr_header = hdr_idx;
|
|
|
|
|
|
|
|
exit:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The VHDX spec calls for header updates to be performed twice, so that both
|
|
|
|
* the current and non-current header have valid info
|
|
|
|
*/
|
2013-10-30 15:44:43 +01:00
|
|
|
int vhdx_update_headers(BlockDriverState *bs, BDRVVHDXState *s,
|
|
|
|
bool generate_data_write_guid, MSGUID *log_guid)
|
2013-10-30 15:44:39 +01:00
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
2013-10-30 15:44:43 +01:00
|
|
|
ret = vhdx_update_header(bs, s, generate_data_write_guid, log_guid);
|
2013-10-30 15:44:39 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
return ret;
|
|
|
|
}
|
2020-04-01 18:53:14 +02:00
|
|
|
return vhdx_update_header(bs, s, generate_data_write_guid, log_guid);
|
2013-10-30 15:44:39 +01:00
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
/* opens the specified header block from the VHDX file header section */
|
2014-02-17 14:44:00 +01:00
|
|
|
static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
|
|
|
|
Error **errp)
|
2013-04-29 20:48:18 +02:00
|
|
|
{
|
2014-02-17 14:44:00 +01:00
|
|
|
int ret;
|
2013-04-29 20:48:18 +02:00
|
|
|
VHDXHeader *header1;
|
|
|
|
VHDXHeader *header2;
|
|
|
|
bool h1_valid = false;
|
|
|
|
bool h2_valid = false;
|
|
|
|
uint64_t h1_seq = 0;
|
|
|
|
uint64_t h2_seq = 0;
|
|
|
|
uint8_t *buffer;
|
|
|
|
|
2013-10-30 15:44:38 +01:00
|
|
|
/* header1 & header2 are freed in vhdx_close() */
|
2013-04-29 20:48:18 +02:00
|
|
|
header1 = qemu_blockalign(bs, sizeof(VHDXHeader));
|
|
|
|
header2 = qemu_blockalign(bs, sizeof(VHDXHeader));
|
|
|
|
|
|
|
|
buffer = qemu_blockalign(bs, VHDX_HEADER_SIZE);
|
|
|
|
|
|
|
|
s->headers[0] = header1;
|
|
|
|
s->headers[1] = header2;
|
|
|
|
|
|
|
|
/* We have to read the whole VHDX_HEADER_SIZE instead of
|
|
|
|
* sizeof(VHDXHeader), because the checksum is over the whole
|
|
|
|
* region */
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, VHDX_HEADER1_OFFSET, buffer,
|
2015-06-16 14:19:22 +02:00
|
|
|
VHDX_HEADER_SIZE);
|
2013-04-29 20:48:18 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
/* copy over just the relevant portion that we need */
|
|
|
|
memcpy(header1, buffer, sizeof(VHDXHeader));
|
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4)) {
|
|
|
|
vhdx_header_le_import(header1);
|
|
|
|
if (header1->signature == VHDX_HEADER_SIGNATURE &&
|
|
|
|
header1->version == 1) {
|
|
|
|
h1_seq = header1->sequence_number;
|
|
|
|
h1_valid = true;
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer,
|
2015-06-16 14:19:22 +02:00
|
|
|
VHDX_HEADER_SIZE);
|
2013-04-29 20:48:18 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
/* copy over just the relevant portion that we need */
|
|
|
|
memcpy(header2, buffer, sizeof(VHDXHeader));
|
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4)) {
|
|
|
|
vhdx_header_le_import(header2);
|
|
|
|
if (header2->signature == VHDX_HEADER_SIGNATURE &&
|
|
|
|
header2->version == 1) {
|
|
|
|
h2_seq = header2->sequence_number;
|
|
|
|
h2_valid = true;
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
/* If there is only 1 valid header (or no valid headers), we
|
|
|
|
* don't care what the sequence numbers are */
|
|
|
|
if (h1_valid && !h2_valid) {
|
|
|
|
s->curr_header = 0;
|
|
|
|
} else if (!h1_valid && h2_valid) {
|
|
|
|
s->curr_header = 1;
|
|
|
|
} else if (!h1_valid && !h2_valid) {
|
|
|
|
goto fail;
|
|
|
|
} else {
|
|
|
|
/* If both headers are valid, then we choose the active one by the
|
|
|
|
* highest sequence number. If the sequence numbers are equal, that is
|
|
|
|
* invalid */
|
|
|
|
if (h1_seq > h2_seq) {
|
|
|
|
s->curr_header = 0;
|
|
|
|
} else if (h2_seq > h1_seq) {
|
|
|
|
s->curr_header = 1;
|
|
|
|
} else {
|
block: vhdx - account for identical header sections
The VHDX spec v1.00 declares that "a header is current if it is the only
valid header or if it is valid and its SequenceNumber field is greater
than the other header’s SequenceNumber field. The parser must only use
data from the current header. If there is no current header, then the
VHDX file is corrupt."
However, the Disk2VHD tool from Microsoft creates a VHDX image file that
has 2 identical headers, including matching checksums and matching
sequence numbers. Likely, as a shortcut the tool is just writing the
header twice, for the active and inactive headers, during the image
creation. Technically, this should be considered a corrupt VHDX file
(at least per the 1.00 spec, and that is how we currently treat it).
But in order to accomodate images created with Disk2VHD, we can safely
create an exception for this case. If we find identical sequence
numbers, then we check the VHDXHeader-sized chunks of each 64KB header
sections (we won't rely just on the crc32c to indicate the headers are
the same). If they are identical, then we go ahead and use the first
one.
Reported-by: Nerijus Baliūnas <nerijus@users.sourceforge.net>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2014-05-13 16:00:52 +02:00
|
|
|
/* The Microsoft Disk2VHD tool will create 2 identical
|
|
|
|
* headers, with identical sequence numbers. If the headers are
|
|
|
|
* identical, don't consider the file corrupt */
|
|
|
|
if (!memcmp(header1, header2, sizeof(VHDXHeader))) {
|
|
|
|
s->curr_header = 0;
|
|
|
|
} else {
|
|
|
|
goto fail;
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:46 +01:00
|
|
|
vhdx_region_register(s, s->headers[s->curr_header]->log_offset,
|
|
|
|
s->headers[s->curr_header]->log_length);
|
2013-04-29 20:48:18 +02:00
|
|
|
goto exit;
|
|
|
|
|
|
|
|
fail:
|
2014-02-17 14:44:00 +01:00
|
|
|
error_setg_errno(errp, -ret, "No valid VHDX header found");
|
2013-04-29 20:48:18 +02:00
|
|
|
qemu_vfree(header1);
|
|
|
|
qemu_vfree(header2);
|
|
|
|
s->headers[0] = NULL;
|
|
|
|
s->headers[1] = NULL;
|
|
|
|
exit:
|
|
|
|
qemu_vfree(buffer);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint8_t *buffer;
|
|
|
|
int offset = 0;
|
|
|
|
VHDXRegionTableEntry rt_entry;
|
|
|
|
uint32_t i;
|
|
|
|
bool bat_rt_found = false;
|
|
|
|
bool metadata_rt_found = false;
|
|
|
|
|
|
|
|
/* We have to read the whole 64KB block, because the crc32 is over the
|
|
|
|
* whole block */
|
|
|
|
buffer = qemu_blockalign(bs, VHDX_HEADER_BLOCK_SIZE);
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, VHDX_REGION_TABLE_OFFSET, buffer,
|
2013-04-29 20:48:18 +02:00
|
|
|
VHDX_HEADER_BLOCK_SIZE);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
memcpy(&s->rt, buffer, sizeof(s->rt));
|
|
|
|
offset += sizeof(s->rt);
|
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
vhdx_region_header_le_import(&s->rt);
|
|
|
|
|
|
|
|
if (s->rt.signature != VHDX_REGION_SIGNATURE) {
|
2013-04-29 20:48:18 +02:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
/* Per spec, maximum region table entry count is 2047 */
|
|
|
|
if (s->rt.entry_count > 2047) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < s->rt.entry_count; i++) {
|
|
|
|
memcpy(&rt_entry, buffer + offset, sizeof(rt_entry));
|
|
|
|
offset += sizeof(rt_entry);
|
|
|
|
|
2013-10-30 15:44:50 +01:00
|
|
|
vhdx_region_entry_le_import(&rt_entry);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2013-10-30 15:44:46 +01:00
|
|
|
/* check for region overlap between these entries, and any
|
|
|
|
* other memory regions in the file */
|
|
|
|
ret = vhdx_region_check(s, rt_entry.file_offset, rt_entry.length);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
vhdx_region_register(s, rt_entry.file_offset, rt_entry.length);
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
/* see if we recognize the entry */
|
|
|
|
if (guid_eq(rt_entry.guid, bat_guid)) {
|
|
|
|
/* must be unique; if we have already found it this is invalid */
|
|
|
|
if (bat_rt_found) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
bat_rt_found = true;
|
|
|
|
s->bat_rt = rt_entry;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(rt_entry.guid, metadata_guid)) {
|
|
|
|
/* must be unique; if we have already found it this is invalid */
|
|
|
|
if (metadata_rt_found) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
metadata_rt_found = true;
|
|
|
|
s->metadata_rt = rt_entry;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (rt_entry.data_bits & VHDX_REGION_ENTRY_REQUIRED) {
|
|
|
|
/* cannot read vhdx file - required region table entry that
|
|
|
|
* we do not understand. per spec, we must fail to open */
|
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
}
|
2013-10-30 15:44:46 +01:00
|
|
|
|
|
|
|
if (!bat_rt_found || !metadata_rt_found) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
fail:
|
|
|
|
qemu_vfree(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* Metadata initial parser
|
|
|
|
*
|
|
|
|
* This loads all the metadata entry fields. This may cause additional
|
|
|
|
* fields to be processed (e.g. parent locator, etc..).
|
|
|
|
*
|
|
|
|
* There are 5 Metadata items that are always required:
|
|
|
|
* - File Parameters (block size, has a parent)
|
|
|
|
* - Virtual Disk Size (size, in bytes, of the virtual drive)
|
|
|
|
* - Page 83 Data (scsi page 83 guid)
|
|
|
|
* - Logical Sector Size (logical sector size in bytes, either 512 or
|
|
|
|
* 4096. We only support 512 currently)
|
|
|
|
* - Physical Sector Size (512 or 4096)
|
|
|
|
*
|
|
|
|
* Also, if the File Parameters indicate this is a differencing file,
|
|
|
|
* we must also look for the Parent Locator metadata item.
|
|
|
|
*/
|
|
|
|
static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint8_t *buffer;
|
|
|
|
int offset = 0;
|
|
|
|
uint32_t i = 0;
|
|
|
|
VHDXMetadataTableEntry md_entry;
|
|
|
|
|
|
|
|
buffer = qemu_blockalign(bs, VHDX_METADATA_TABLE_MAX_SIZE);
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, s->metadata_rt.file_offset, buffer,
|
2013-04-29 20:48:18 +02:00
|
|
|
VHDX_METADATA_TABLE_MAX_SIZE);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
memcpy(&s->metadata_hdr, buffer, sizeof(s->metadata_hdr));
|
|
|
|
offset += sizeof(s->metadata_hdr);
|
|
|
|
|
2013-10-30 15:44:50 +01:00
|
|
|
vhdx_metadata_header_le_import(&s->metadata_hdr);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
if (s->metadata_hdr.signature != VHDX_METADATA_SIGNATURE) {
|
2013-04-29 20:48:18 +02:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
s->metadata_entries.present = 0;
|
|
|
|
|
|
|
|
if ((s->metadata_hdr.entry_count * sizeof(md_entry)) >
|
|
|
|
(VHDX_METADATA_TABLE_MAX_SIZE - offset)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < s->metadata_hdr.entry_count; i++) {
|
|
|
|
memcpy(&md_entry, buffer + offset, sizeof(md_entry));
|
|
|
|
offset += sizeof(md_entry);
|
|
|
|
|
2013-10-30 15:44:50 +01:00
|
|
|
vhdx_metadata_entry_le_import(&md_entry);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, file_param_guid)) {
|
|
|
|
if (s->metadata_entries.present & META_FILE_PARAMETER_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.file_parameters_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_FILE_PARAMETER_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, virtual_size_guid)) {
|
|
|
|
if (s->metadata_entries.present & META_VIRTUAL_DISK_SIZE_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.virtual_disk_size_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_VIRTUAL_DISK_SIZE_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, page83_guid)) {
|
|
|
|
if (s->metadata_entries.present & META_PAGE_83_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.page83_data_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_PAGE_83_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, logical_sector_guid)) {
|
|
|
|
if (s->metadata_entries.present &
|
|
|
|
META_LOGICAL_SECTOR_SIZE_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.logical_sector_size_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_LOGICAL_SECTOR_SIZE_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, phys_sector_guid)) {
|
|
|
|
if (s->metadata_entries.present & META_PHYS_SECTOR_SIZE_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.phys_sector_size_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_PHYS_SECTOR_SIZE_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (guid_eq(md_entry.item_id, parent_locator_guid)) {
|
|
|
|
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->metadata_entries.parent_locator_entry = md_entry;
|
|
|
|
s->metadata_entries.present |= META_PARENT_LOCATOR_PRESENT;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (md_entry.data_bits & VHDX_META_FLAGS_IS_REQUIRED) {
|
|
|
|
/* cannot read vhdx file - required region table entry that
|
|
|
|
* we do not understand. per spec, we must fail to open */
|
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s->metadata_entries.present != META_ALL_PRESENT) {
|
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file,
|
2013-04-29 20:48:18 +02:00
|
|
|
s->metadata_entries.file_parameters_entry.offset
|
|
|
|
+ s->metadata_rt.file_offset,
|
|
|
|
&s->params,
|
|
|
|
sizeof(s->params));
|
|
|
|
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2018-10-16 19:09:38 +02:00
|
|
|
s->params.block_size = le32_to_cpu(s->params.block_size);
|
|
|
|
s->params.data_bits = le32_to_cpu(s->params.data_bits);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
|
|
|
|
/* We now have the file parameters, so we can tell if this is a
|
|
|
|
* differencing file (i.e.. has_parent), is dynamic or fixed
|
|
|
|
* sized (leave_blocks_allocated), and the block size */
|
|
|
|
|
|
|
|
/* The parent locator required iff the file parameters has_parent set */
|
|
|
|
if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
|
|
|
|
if (s->metadata_entries.present & META_PARENT_LOCATOR_PRESENT) {
|
|
|
|
/* TODO: parse parent locator fields */
|
|
|
|
ret = -ENOTSUP; /* temp, until differencing files are supported */
|
|
|
|
goto exit;
|
|
|
|
} else {
|
|
|
|
/* if has_parent is set, but there is not parent locator present,
|
|
|
|
* then that is an invalid combination */
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* determine virtual disk size, logical sector size,
|
|
|
|
* and phys sector size */
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file,
|
2013-04-29 20:48:18 +02:00
|
|
|
s->metadata_entries.virtual_disk_size_entry.offset
|
|
|
|
+ s->metadata_rt.file_offset,
|
|
|
|
&s->virtual_disk_size,
|
|
|
|
sizeof(uint64_t));
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file,
|
2013-04-29 20:48:18 +02:00
|
|
|
s->metadata_entries.logical_sector_size_entry.offset
|
|
|
|
+ s->metadata_rt.file_offset,
|
|
|
|
&s->logical_sector_size,
|
|
|
|
sizeof(uint32_t));
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file,
|
2013-04-29 20:48:18 +02:00
|
|
|
s->metadata_entries.phys_sector_size_entry.offset
|
|
|
|
+ s->metadata_rt.file_offset,
|
|
|
|
&s->physical_sector_size,
|
|
|
|
sizeof(uint32_t));
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2018-10-16 19:09:38 +02:00
|
|
|
s->virtual_disk_size = le64_to_cpu(s->virtual_disk_size);
|
|
|
|
s->logical_sector_size = le32_to_cpu(s->logical_sector_size);
|
|
|
|
s->physical_sector_size = le32_to_cpu(s->physical_sector_size);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2014-03-26 13:05:39 +01:00
|
|
|
if (s->params.block_size < VHDX_BLOCK_SIZE_MIN ||
|
|
|
|
s->params.block_size > VHDX_BLOCK_SIZE_MAX) {
|
2013-04-29 20:48:18 +02:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2014-03-26 13:05:39 +01:00
|
|
|
/* only 2 supported sector sizes */
|
|
|
|
if (s->logical_sector_size != 512 && s->logical_sector_size != 4096) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Both block_size and sector_size are guaranteed powers of 2, below.
|
|
|
|
Due to range checks above, s->sectors_per_block can never be < 256 */
|
2013-04-29 20:48:18 +02:00
|
|
|
s->sectors_per_block = s->params.block_size / s->logical_sector_size;
|
|
|
|
s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
|
|
|
|
(uint64_t)s->logical_sector_size /
|
|
|
|
(uint64_t)s->params.block_size;
|
|
|
|
|
|
|
|
/* These values are ones we will want to use for division / multiplication
|
|
|
|
* later on, and they are all guaranteed (per the spec) to be powers of 2,
|
|
|
|
* so we can take advantage of that for shift operations during
|
|
|
|
* reads/writes */
|
|
|
|
if (s->logical_sector_size & (s->logical_sector_size - 1)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
if (s->sectors_per_block & (s->sectors_per_block - 1)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
if (s->chunk_ratio & (s->chunk_ratio - 1)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
s->block_size = s->params.block_size;
|
|
|
|
if (s->block_size & (s->block_size - 1)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:51 +01:00
|
|
|
vhdx_set_shift_bits(s);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
exit:
|
|
|
|
qemu_vfree(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:51 +01:00
|
|
|
/*
|
|
|
|
* Calculate the number of BAT entries, including sector
|
|
|
|
* bitmap entries.
|
|
|
|
*/
|
|
|
|
static void vhdx_calc_bat_entries(BDRVVHDXState *s)
|
|
|
|
{
|
|
|
|
uint32_t data_blocks_cnt, bitmap_blocks_cnt;
|
|
|
|
|
2015-12-18 16:04:25 +01:00
|
|
|
data_blocks_cnt = DIV_ROUND_UP(s->virtual_disk_size, s->block_size);
|
|
|
|
bitmap_blocks_cnt = DIV_ROUND_UP(data_blocks_cnt, s->chunk_ratio);
|
2013-10-30 15:44:51 +01:00
|
|
|
|
|
|
|
if (s->parent_entries) {
|
|
|
|
s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
|
|
|
|
} else {
|
|
|
|
s->bat_entries = data_blocks_cnt +
|
|
|
|
((data_blocks_cnt - 1) >> s->chunk_ratio_bits);
|
|
|
|
}
|
|
|
|
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2019-09-10 17:26:22 +02:00
|
|
|
static int vhdx_check_bat_entries(BlockDriverState *bs, int *errcnt)
|
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
int64_t image_file_size = bdrv_getlength(bs->file->bs);
|
|
|
|
uint64_t payblocks = s->chunk_ratio;
|
|
|
|
uint64_t i;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (image_file_size < 0) {
|
|
|
|
error_report("Could not determinate VHDX image file size.");
|
|
|
|
return image_file_size;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (i = 0; i < s->bat_entries; i++) {
|
|
|
|
if ((s->bat[i] & VHDX_BAT_STATE_BIT_MASK) ==
|
|
|
|
PAYLOAD_BLOCK_FULLY_PRESENT) {
|
|
|
|
uint64_t offset = s->bat[i] & VHDX_BAT_FILE_OFF_MASK;
|
|
|
|
/*
|
|
|
|
* Allow that the last block exists only partially. The VHDX spec
|
|
|
|
* states that the image file can only grow in blocksize increments,
|
|
|
|
* but QEMU created images with partial last blocks in the past.
|
|
|
|
*/
|
|
|
|
uint32_t block_length = MIN(s->block_size,
|
|
|
|
bs->total_sectors * BDRV_SECTOR_SIZE - i * s->block_size);
|
|
|
|
/*
|
|
|
|
* Check for BAT entry overflow.
|
|
|
|
*/
|
|
|
|
if (offset > INT64_MAX - s->block_size) {
|
|
|
|
error_report("VHDX BAT entry %" PRIu64 " offset overflow.", i);
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (!errcnt) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
(*errcnt)++;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* Check if fully allocated BAT entries do not reside after
|
|
|
|
* end of the image file.
|
|
|
|
*/
|
|
|
|
if (offset >= image_file_size) {
|
|
|
|
error_report("VHDX BAT entry %" PRIu64 " start offset %" PRIu64
|
|
|
|
" points after end of file (%" PRIi64 "). Image"
|
|
|
|
" has probably been truncated.",
|
|
|
|
i, offset, image_file_size);
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (!errcnt) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
(*errcnt)++;
|
|
|
|
} else if (offset + block_length > image_file_size) {
|
|
|
|
error_report("VHDX BAT entry %" PRIu64 " end offset %" PRIu64
|
|
|
|
" points after end of file (%" PRIi64 "). Image"
|
|
|
|
" has probably been truncated.",
|
|
|
|
i, offset + block_length - 1, image_file_size);
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (!errcnt) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
(*errcnt)++;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* verify populated BAT field file offsets against
|
|
|
|
* region table and log entries
|
|
|
|
*/
|
|
|
|
if (payblocks--) {
|
|
|
|
/* payload bat entries */
|
|
|
|
int ret2;
|
|
|
|
ret2 = vhdx_region_check(s, offset, s->block_size);
|
|
|
|
if (ret2 < 0) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (!errcnt) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
(*errcnt)++;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
payblocks = s->chunk_ratio;
|
|
|
|
/*
|
|
|
|
* Once differencing files are supported, verify sector bitmap
|
|
|
|
* blocks here
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:44 +01:00
|
|
|
static void vhdx_close(BlockDriverState *bs)
|
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
qemu_vfree(s->headers[0]);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
s->headers[0] = NULL;
|
2013-10-30 15:44:44 +01:00
|
|
|
qemu_vfree(s->headers[1]);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
s->headers[1] = NULL;
|
2013-10-30 15:44:44 +01:00
|
|
|
qemu_vfree(s->bat);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
s->bat = NULL;
|
2013-10-30 15:44:44 +01:00
|
|
|
qemu_vfree(s->parent_entries);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
s->parent_entries = NULL;
|
2013-10-30 15:44:44 +01:00
|
|
|
migrate_del_blocker(s->migration_blocker);
|
|
|
|
error_free(s->migration_blocker);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
qemu_vfree(s->log.hdr);
|
|
|
|
s->log.hdr = NULL;
|
2013-10-30 15:44:46 +01:00
|
|
|
vhdx_region_unregister_all(s);
|
2013-10-30 15:44:44 +01:00
|
|
|
}
|
|
|
|
|
2013-09-05 14:22:29 +02:00
|
|
|
static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
|
|
|
|
Error **errp)
|
2013-04-29 20:48:18 +02:00
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
int ret = 0;
|
|
|
|
uint32_t i;
|
|
|
|
uint64_t signature;
|
2014-02-17 14:44:00 +01:00
|
|
|
Error *local_err = NULL;
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2020-05-13 13:05:35 +02:00
|
|
|
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
|
|
|
|
BDRV_CHILD_IMAGE, false, errp);
|
2016-12-16 18:52:37 +01:00
|
|
|
if (!bs->file) {
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
s->bat = NULL;
|
2013-10-30 15:44:43 +01:00
|
|
|
s->first_visible_write = true;
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
qemu_co_mutex_init(&s->lock);
|
2013-10-30 15:44:46 +01:00
|
|
|
QLIST_INIT(&s->regions);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
/* validate the file signature */
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, 0, &signature, sizeof(uint64_t));
|
2013-04-29 20:48:18 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
if (memcmp(&signature, "vhdxfile", 8)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:39 +01:00
|
|
|
/* This is used for any header updates, for the file_write_guid.
|
|
|
|
* The spec dictates that a new value should be used for the first
|
|
|
|
* header update */
|
|
|
|
vhdx_guid_generate(&s->session_guid);
|
|
|
|
|
2014-02-17 14:44:00 +01:00
|
|
|
vhdx_parse_header(bs, s, &local_err);
|
|
|
|
if (local_err != NULL) {
|
|
|
|
error_propagate(errp, local_err);
|
|
|
|
ret = -EINVAL;
|
2013-04-29 20:48:18 +02:00
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2013-12-17 11:33:37 +01:00
|
|
|
ret = vhdx_parse_log(bs, s, &s->log_replayed_on_open, errp);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
if (ret < 0) {
|
2013-04-29 20:48:18 +02:00
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = vhdx_open_region_tables(bs, s);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
if (ret < 0) {
|
2013-04-29 20:48:18 +02:00
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
ret = vhdx_parse_metadata(bs, s);
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
if (ret < 0) {
|
2013-04-29 20:48:18 +02:00
|
|
|
goto fail;
|
|
|
|
}
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
s->block_size = s->params.block_size;
|
|
|
|
|
|
|
|
/* the VHDX spec dictates that virtual_disk_size is always a multiple of
|
|
|
|
* logical_sector_size */
|
|
|
|
bs->total_sectors = s->virtual_disk_size >> s->logical_sector_size_bits;
|
|
|
|
|
2013-10-30 15:44:51 +01:00
|
|
|
vhdx_calc_bat_entries(s);
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
s->bat_offset = s->bat_rt.file_offset;
|
|
|
|
|
|
|
|
if (s->bat_entries > s->bat_rt.length / sizeof(VHDXBatEntry)) {
|
|
|
|
/* BAT allocation is not large enough for all entries */
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:38 +01:00
|
|
|
/* s->bat is freed in vhdx_close() */
|
2015-06-16 14:19:22 +02:00
|
|
|
s->bat = qemu_try_blockalign(bs->file->bs, s->bat_rt.length);
|
2014-05-20 13:55:50 +02:00
|
|
|
if (s->bat == NULL) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
|
2013-04-29 20:48:18 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2019-09-10 17:26:22 +02:00
|
|
|
/* endian convert populated BAT field entires */
|
2013-04-29 20:48:18 +02:00
|
|
|
for (i = 0; i < s->bat_entries; i++) {
|
2018-10-16 19:09:38 +02:00
|
|
|
s->bat[i] = le64_to_cpu(s->bat[i]);
|
2019-09-10 17:26:22 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!(flags & BDRV_O_CHECK)) {
|
|
|
|
ret = vhdx_check_bat_entries(bs, NULL);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
2013-10-30 15:44:46 +01:00
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
|
2017-01-16 12:31:53 +01:00
|
|
|
/* Disable migration when VHDX images are used */
|
|
|
|
error_setg(&s->migration_blocker, "The vhdx format used by node '%s' "
|
|
|
|
"does not support live migration",
|
|
|
|
bdrv_get_device_or_node_name(bs));
|
error: Avoid error_propagate() after migrate_add_blocker()
When migrate_add_blocker(blocker, &errp) is followed by
error_propagate(errp, err), we can often just as well do
migrate_add_blocker(..., errp).
Do that with this Coccinelle script:
@@
expression blocker, err, errp;
expression ret;
@@
- ret = migrate_add_blocker(blocker, &err);
- if (err) {
+ ret = migrate_add_blocker(blocker, errp);
+ if (ret < 0) {
... when != err;
- error_propagate(errp, err);
...
}
@@
expression blocker, err, errp;
@@
- migrate_add_blocker(blocker, &err);
- if (err) {
+ if (migrate_add_blocker(blocker, errp) < 0) {
... when != err;
- error_propagate(errp, err);
...
}
Double-check @err is not used afterwards. Dereferencing it would be
use after free, but checking whether it's null would be legitimate.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20200707160613.848843-43-armbru@redhat.com>
2020-07-07 18:06:10 +02:00
|
|
|
ret = migrate_add_blocker(s->migration_blocker, errp);
|
|
|
|
if (ret < 0) {
|
2017-01-16 12:31:53 +01:00
|
|
|
error_free(s->migration_blocker);
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:48 +01:00
|
|
|
/* TODO: differencing files */
|
2013-04-29 20:48:18 +02:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
fail:
|
block: vhdx - log parsing, replay, and flush support
This adds support for VHDX v0 logs, as specified in Microsoft's
VHDX Specification Format v1.00:
https://www.microsoft.com/en-us/download/details.aspx?id=34750
The following support is added:
* Log parsing, and validation - validate that an existing log
is correct.
* Log search - search through an existing log, to find any valid
sequence of entries.
* Log replay and flush - replay an existing log, and flush/clear
the log when complete.
The VHDX log is a circular buffer, with elements (sectors) of 4KB.
A log entry is a variably-length number of sectors, that is
comprised of a header and 'descriptors', that describe each sector.
A log may contain multiple entries, know as a log sequence. In a log
sequence, each log entry immediately follows the previous entry, with an
incrementing sequence number. There can only ever be one active and
valid sequence in the log.
Each log entry must match the file log GUID in order to be valid (along
with other criteria). Once we have flushed all valid log entries, we
marked the file log GUID to be zero, which indicates a buffer with no
valid entries.
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-10-30 15:44:45 +01:00
|
|
|
vhdx_close(bs);
|
2013-04-29 20:48:18 +02:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int vhdx_reopen_prepare(BDRVReopenState *state,
|
|
|
|
BlockReopenQueue *queue, Error **errp)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2013-04-29 20:48:19 +02:00
|
|
|
/*
|
|
|
|
* Perform sector to block offset translations, to get various
|
|
|
|
* sector and file offsets into the image. See VHDXSectorInfo
|
|
|
|
*/
|
|
|
|
static void vhdx_block_translate(BDRVVHDXState *s, int64_t sector_num,
|
|
|
|
int nb_sectors, VHDXSectorInfo *sinfo)
|
|
|
|
{
|
|
|
|
uint32_t block_offset;
|
|
|
|
|
|
|
|
sinfo->bat_idx = sector_num >> s->sectors_per_block_bits;
|
|
|
|
/* effectively a modulo - this gives us the offset into the block
|
|
|
|
* (in sector sizes) for our sector number */
|
|
|
|
block_offset = sector_num - (sinfo->bat_idx << s->sectors_per_block_bits);
|
|
|
|
/* the chunk ratio gives us the interleaving of the sector
|
|
|
|
* bitmaps, so we need to advance our page block index by the
|
|
|
|
* sector bitmaps entry number */
|
|
|
|
sinfo->bat_idx += sinfo->bat_idx >> s->chunk_ratio_bits;
|
|
|
|
|
|
|
|
/* the number of sectors we can read/write in this cycle */
|
|
|
|
sinfo->sectors_avail = s->sectors_per_block - block_offset;
|
|
|
|
|
|
|
|
sinfo->bytes_left = sinfo->sectors_avail << s->logical_sector_size_bits;
|
|
|
|
|
|
|
|
if (sinfo->sectors_avail > nb_sectors) {
|
|
|
|
sinfo->sectors_avail = nb_sectors;
|
|
|
|
}
|
|
|
|
|
|
|
|
sinfo->bytes_avail = sinfo->sectors_avail << s->logical_sector_size_bits;
|
|
|
|
|
2013-10-30 15:44:49 +01:00
|
|
|
sinfo->file_offset = s->bat[sinfo->bat_idx] & VHDX_BAT_FILE_OFF_MASK;
|
2013-04-29 20:48:19 +02:00
|
|
|
|
|
|
|
sinfo->block_offset = block_offset << s->logical_sector_size_bits;
|
|
|
|
|
|
|
|
/* The file offset must be past the header section, so must be > 0 */
|
|
|
|
if (sinfo->file_offset == 0) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* block offset is the offset in vhdx logical sectors, in
|
|
|
|
* the payload data block. Convert that to a byte offset
|
|
|
|
* in the block, and add in the payload data block offset
|
|
|
|
* in the file, in bytes, to get the final read address */
|
|
|
|
|
|
|
|
sinfo->file_offset += sinfo->block_offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2013-11-22 13:39:49 +01:00
|
|
|
static int vhdx_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
|
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
|
|
|
|
bdi->cluster_size = s->block_size;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:19 +02:00
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
static coroutine_fn int vhdx_co_readv(BlockDriverState *bs, int64_t sector_num,
|
|
|
|
int nb_sectors, QEMUIOVector *qiov)
|
|
|
|
{
|
2013-04-29 20:48:19 +02:00
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
int ret = 0;
|
|
|
|
VHDXSectorInfo sinfo;
|
|
|
|
uint64_t bytes_done = 0;
|
|
|
|
QEMUIOVector hd_qiov;
|
|
|
|
|
|
|
|
qemu_iovec_init(&hd_qiov, qiov->niov);
|
|
|
|
|
|
|
|
qemu_co_mutex_lock(&s->lock);
|
|
|
|
|
|
|
|
while (nb_sectors > 0) {
|
|
|
|
/* We are a differencing file, so we need to inspect the sector bitmap
|
|
|
|
* to see if we have the data or not */
|
|
|
|
if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
|
|
|
|
/* not supported yet */
|
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto exit;
|
|
|
|
} else {
|
|
|
|
vhdx_block_translate(s, sector_num, nb_sectors, &sinfo);
|
|
|
|
|
|
|
|
qemu_iovec_reset(&hd_qiov);
|
|
|
|
qemu_iovec_concat(&hd_qiov, qiov, bytes_done, sinfo.bytes_avail);
|
|
|
|
|
|
|
|
/* check the payload block state */
|
|
|
|
switch (s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK) {
|
|
|
|
case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
|
2014-12-08 07:07:42 +01:00
|
|
|
case PAYLOAD_BLOCK_UNDEFINED:
|
|
|
|
case PAYLOAD_BLOCK_UNMAPPED:
|
2014-12-08 07:07:43 +01:00
|
|
|
case PAYLOAD_BLOCK_UNMAPPED_v095:
|
2013-04-29 20:48:19 +02:00
|
|
|
case PAYLOAD_BLOCK_ZERO:
|
|
|
|
/* return zero */
|
|
|
|
qemu_iovec_memset(&hd_qiov, 0, 0, sinfo.bytes_avail);
|
|
|
|
break;
|
2013-10-30 15:44:48 +01:00
|
|
|
case PAYLOAD_BLOCK_FULLY_PRESENT:
|
2013-04-29 20:48:19 +02:00
|
|
|
qemu_co_mutex_unlock(&s->lock);
|
2018-06-28 22:15:24 +02:00
|
|
|
ret = bdrv_co_preadv(bs->file, sinfo.file_offset,
|
|
|
|
sinfo.sectors_avail * BDRV_SECTOR_SIZE,
|
|
|
|
&hd_qiov, 0);
|
2013-04-29 20:48:19 +02:00
|
|
|
qemu_co_mutex_lock(&s->lock);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case PAYLOAD_BLOCK_PARTIALLY_PRESENT:
|
|
|
|
/* we don't yet support difference files, fall through
|
|
|
|
* to error */
|
|
|
|
default:
|
|
|
|
ret = -EIO;
|
|
|
|
goto exit;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
nb_sectors -= sinfo.sectors_avail;
|
|
|
|
sector_num += sinfo.sectors_avail;
|
|
|
|
bytes_done += sinfo.bytes_avail;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ret = 0;
|
|
|
|
exit:
|
|
|
|
qemu_co_mutex_unlock(&s->lock);
|
|
|
|
qemu_iovec_destroy(&hd_qiov);
|
|
|
|
return ret;
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
|
2013-10-30 15:44:48 +01:00
|
|
|
/*
|
|
|
|
* Allocate a new payload block at the end of the file.
|
|
|
|
*
|
2020-04-28 22:29:04 +02:00
|
|
|
* Allocation will happen at 1MB alignment inside the file.
|
|
|
|
*
|
|
|
|
* If @need_zero is set on entry but not cleared on return, then truncation
|
|
|
|
* could not guarantee that the new portion reads as zero, and the caller
|
|
|
|
* will take care of it instead.
|
2013-10-30 15:44:48 +01:00
|
|
|
*
|
|
|
|
* Returns the file offset start of the new payload block
|
|
|
|
*/
|
|
|
|
static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
|
2020-04-28 22:29:04 +02:00
|
|
|
uint64_t *new_offset, bool *need_zero)
|
2013-10-30 15:44:48 +01:00
|
|
|
{
|
2017-08-07 14:38:19 +02:00
|
|
|
int64_t current_len;
|
|
|
|
|
|
|
|
current_len = bdrv_getlength(bs->file->bs);
|
|
|
|
if (current_len < 0) {
|
|
|
|
return current_len;
|
|
|
|
}
|
|
|
|
|
|
|
|
*new_offset = current_len;
|
2013-10-30 15:44:48 +01:00
|
|
|
|
|
|
|
/* per the spec, the address for a block is in units of 1MB */
|
2019-03-27 10:56:34 +01:00
|
|
|
*new_offset = ROUND_UP(*new_offset, 1 * MiB);
|
2017-08-07 14:38:20 +02:00
|
|
|
if (*new_offset > INT64_MAX) {
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2013-10-30 15:44:48 +01:00
|
|
|
|
2020-04-28 22:29:04 +02:00
|
|
|
if (*need_zero) {
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = bdrv_truncate(bs->file, *new_offset + s->block_size, false,
|
|
|
|
PREALLOC_MODE_OFF, BDRV_REQ_ZERO_WRITE, NULL);
|
|
|
|
if (ret != -ENOTSUP) {
|
|
|
|
*need_zero = false;
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-09-18 11:51:40 +02:00
|
|
|
return bdrv_truncate(bs->file, *new_offset + s->block_size, false,
|
2020-04-24 14:54:40 +02:00
|
|
|
PREALLOC_MODE_OFF, 0, NULL);
|
2013-10-30 15:44:48 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Update the BAT table entry with the new file offset, and the new entry
|
|
|
|
* state */
|
|
|
|
static void vhdx_update_bat_table_entry(BlockDriverState *bs, BDRVVHDXState *s,
|
|
|
|
VHDXSectorInfo *sinfo,
|
|
|
|
uint64_t *bat_entry_le,
|
|
|
|
uint64_t *bat_offset, int state)
|
|
|
|
{
|
|
|
|
/* The BAT entry is a uint64, with 44 bits for the file offset in units of
|
|
|
|
* 1MB, and 3 bits for the block state. */
|
2015-01-20 22:01:43 +01:00
|
|
|
if ((state == PAYLOAD_BLOCK_ZERO) ||
|
|
|
|
(state == PAYLOAD_BLOCK_UNDEFINED) ||
|
|
|
|
(state == PAYLOAD_BLOCK_NOT_PRESENT) ||
|
|
|
|
(state == PAYLOAD_BLOCK_UNMAPPED)) {
|
|
|
|
s->bat[sinfo->bat_idx] = 0; /* For PAYLOAD_BLOCK_ZERO, the
|
|
|
|
FileOffsetMB field is denoted as
|
|
|
|
'reserved' in the v1.0 spec. If it is
|
|
|
|
non-zero, MS Hyper-V will fail to read
|
|
|
|
the disk image */
|
|
|
|
} else {
|
|
|
|
s->bat[sinfo->bat_idx] = sinfo->file_offset;
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2013-10-30 15:44:48 +01:00
|
|
|
s->bat[sinfo->bat_idx] |= state & VHDX_BAT_STATE_BIT_MASK;
|
|
|
|
|
|
|
|
*bat_entry_le = cpu_to_le64(s->bat[sinfo->bat_idx]);
|
|
|
|
*bat_offset = s->bat_offset + sinfo->bat_idx * sizeof(VHDXBatEntry);
|
|
|
|
|
|
|
|
}
|
2013-04-29 20:48:18 +02:00
|
|
|
|
2013-10-30 15:44:43 +01:00
|
|
|
/* Per the spec, on the first write of guest-visible data to the file the
|
|
|
|
* data write guid must be updated in the header */
|
|
|
|
int vhdx_user_visible_write(BlockDriverState *bs, BDRVVHDXState *s)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
if (s->first_visible_write) {
|
|
|
|
s->first_visible_write = false;
|
|
|
|
ret = vhdx_update_headers(bs, s, true, NULL);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
static coroutine_fn int vhdx_co_writev(BlockDriverState *bs, int64_t sector_num,
|
2018-04-25 00:01:57 +02:00
|
|
|
int nb_sectors, QEMUIOVector *qiov,
|
|
|
|
int flags)
|
2013-04-29 20:48:18 +02:00
|
|
|
{
|
2013-10-30 15:44:48 +01:00
|
|
|
int ret = -ENOTSUP;
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
VHDXSectorInfo sinfo;
|
|
|
|
uint64_t bytes_done = 0;
|
|
|
|
uint64_t bat_entry = 0;
|
|
|
|
uint64_t bat_entry_offset = 0;
|
|
|
|
QEMUIOVector hd_qiov;
|
|
|
|
struct iovec iov1 = { 0 };
|
|
|
|
struct iovec iov2 = { 0 };
|
|
|
|
int sectors_to_write;
|
|
|
|
int bat_state;
|
|
|
|
uint64_t bat_prior_offset = 0;
|
|
|
|
bool bat_update = false;
|
|
|
|
|
2018-04-25 00:01:57 +02:00
|
|
|
assert(!flags);
|
2013-10-30 15:44:48 +01:00
|
|
|
qemu_iovec_init(&hd_qiov, qiov->niov);
|
|
|
|
|
|
|
|
qemu_co_mutex_lock(&s->lock);
|
|
|
|
|
|
|
|
ret = vhdx_user_visible_write(bs, s);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (nb_sectors > 0) {
|
|
|
|
bool use_zero_buffers = false;
|
|
|
|
bat_update = false;
|
|
|
|
if (s->params.data_bits & VHDX_PARAMS_HAS_PARENT) {
|
|
|
|
/* not supported yet */
|
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto exit;
|
|
|
|
} else {
|
|
|
|
vhdx_block_translate(s, sector_num, nb_sectors, &sinfo);
|
|
|
|
sectors_to_write = sinfo.sectors_avail;
|
|
|
|
|
|
|
|
qemu_iovec_reset(&hd_qiov);
|
|
|
|
/* check the payload block state */
|
|
|
|
bat_state = s->bat[sinfo.bat_idx] & VHDX_BAT_STATE_BIT_MASK;
|
|
|
|
switch (bat_state) {
|
|
|
|
case PAYLOAD_BLOCK_ZERO:
|
|
|
|
/* in this case, we need to preserve zero writes for
|
|
|
|
* data that is not part of this write, so we must pad
|
|
|
|
* the rest of the buffer to zeroes */
|
2020-04-28 22:29:04 +02:00
|
|
|
use_zero_buffers = true;
|
|
|
|
/* fall through */
|
|
|
|
case PAYLOAD_BLOCK_NOT_PRESENT: /* fall through */
|
|
|
|
case PAYLOAD_BLOCK_UNMAPPED:
|
|
|
|
case PAYLOAD_BLOCK_UNMAPPED_v095:
|
|
|
|
case PAYLOAD_BLOCK_UNDEFINED:
|
|
|
|
bat_prior_offset = sinfo.file_offset;
|
|
|
|
ret = vhdx_allocate_block(bs, s, &sinfo.file_offset,
|
|
|
|
&use_zero_buffers);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* once we support differencing files, this may also be
|
|
|
|
* partially present
|
|
|
|
*/
|
|
|
|
/* update block state to the newly specified state */
|
|
|
|
vhdx_update_bat_table_entry(bs, s, &sinfo, &bat_entry,
|
|
|
|
&bat_entry_offset,
|
|
|
|
PAYLOAD_BLOCK_FULLY_PRESENT);
|
|
|
|
bat_update = true;
|
|
|
|
/*
|
|
|
|
* Since we just allocated a block, file_offset is the
|
|
|
|
* beginning of the payload block. It needs to be the
|
|
|
|
* write address, which includes the offset into the
|
|
|
|
* block, unless the entire block needs to read as
|
|
|
|
* zeroes but truncation was not able to provide them,
|
|
|
|
* in which case we need to fill in the rest.
|
|
|
|
*/
|
|
|
|
if (!use_zero_buffers) {
|
|
|
|
sinfo.file_offset += sinfo.block_offset;
|
|
|
|
} else {
|
2013-10-30 15:44:48 +01:00
|
|
|
/* zero fill the front, if any */
|
|
|
|
if (sinfo.block_offset) {
|
|
|
|
iov1.iov_len = sinfo.block_offset;
|
|
|
|
iov1.iov_base = qemu_blockalign(bs, iov1.iov_len);
|
|
|
|
memset(iov1.iov_base, 0, iov1.iov_len);
|
|
|
|
qemu_iovec_concat_iov(&hd_qiov, &iov1, 1, 0,
|
2015-04-14 16:36:16 +02:00
|
|
|
iov1.iov_len);
|
2013-10-30 15:44:48 +01:00
|
|
|
sectors_to_write += iov1.iov_len >> BDRV_SECTOR_BITS;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* our actual data */
|
2020-04-28 22:29:04 +02:00
|
|
|
qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
|
2013-10-30 15:44:48 +01:00
|
|
|
sinfo.bytes_avail);
|
|
|
|
|
|
|
|
/* zero fill the back, if any */
|
|
|
|
if ((sinfo.bytes_avail - sinfo.block_offset) <
|
|
|
|
s->block_size) {
|
|
|
|
iov2.iov_len = s->block_size -
|
|
|
|
(sinfo.bytes_avail + sinfo.block_offset);
|
|
|
|
iov2.iov_base = qemu_blockalign(bs, iov2.iov_len);
|
|
|
|
memset(iov2.iov_base, 0, iov2.iov_len);
|
|
|
|
qemu_iovec_concat_iov(&hd_qiov, &iov2, 1, 0,
|
2015-04-14 16:36:16 +02:00
|
|
|
iov2.iov_len);
|
2013-10-30 15:44:48 +01:00
|
|
|
sectors_to_write += iov2.iov_len >> BDRV_SECTOR_BITS;
|
|
|
|
}
|
|
|
|
}
|
2020-04-28 22:29:04 +02:00
|
|
|
|
2013-10-30 15:44:48 +01:00
|
|
|
/* fall through */
|
|
|
|
case PAYLOAD_BLOCK_FULLY_PRESENT:
|
|
|
|
/* if the file offset address is in the header zone,
|
|
|
|
* there is a problem */
|
2019-03-27 10:56:34 +01:00
|
|
|
if (sinfo.file_offset < (1 * MiB)) {
|
2013-10-30 15:44:48 +01:00
|
|
|
ret = -EFAULT;
|
|
|
|
goto error_bat_restore;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!use_zero_buffers) {
|
|
|
|
qemu_iovec_concat(&hd_qiov, qiov, bytes_done,
|
|
|
|
sinfo.bytes_avail);
|
|
|
|
}
|
|
|
|
/* block exists, so we can just overwrite it */
|
|
|
|
qemu_co_mutex_unlock(&s->lock);
|
2018-06-28 22:15:24 +02:00
|
|
|
ret = bdrv_co_pwritev(bs->file, sinfo.file_offset,
|
|
|
|
sectors_to_write * BDRV_SECTOR_SIZE,
|
|
|
|
&hd_qiov, 0);
|
2013-10-30 15:44:48 +01:00
|
|
|
qemu_co_mutex_lock(&s->lock);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto error_bat_restore;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
case PAYLOAD_BLOCK_PARTIALLY_PRESENT:
|
|
|
|
/* we don't yet support difference files, fall through
|
|
|
|
* to error */
|
|
|
|
default:
|
|
|
|
ret = -EIO;
|
|
|
|
goto exit;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bat_update) {
|
|
|
|
/* this will update the BAT entry into the log journal, and
|
|
|
|
* then flush the log journal out to disk */
|
|
|
|
ret = vhdx_log_write_and_flush(bs, s, &bat_entry,
|
|
|
|
sizeof(VHDXBatEntry),
|
|
|
|
bat_entry_offset);
|
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
nb_sectors -= sinfo.sectors_avail;
|
|
|
|
sector_num += sinfo.sectors_avail;
|
|
|
|
bytes_done += sinfo.bytes_avail;
|
|
|
|
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
goto exit;
|
|
|
|
|
|
|
|
error_bat_restore:
|
|
|
|
if (bat_update) {
|
|
|
|
/* keep metadata in sync, and restore the bat entry state
|
|
|
|
* if error. */
|
|
|
|
sinfo.file_offset = bat_prior_offset;
|
|
|
|
vhdx_update_bat_table_entry(bs, s, &sinfo, &bat_entry,
|
|
|
|
&bat_entry_offset, bat_state);
|
|
|
|
}
|
|
|
|
exit:
|
|
|
|
qemu_vfree(iov1.iov_base);
|
|
|
|
qemu_vfree(iov2.iov_base);
|
|
|
|
qemu_co_mutex_unlock(&s->lock);
|
|
|
|
qemu_iovec_destroy(&hd_qiov);
|
|
|
|
return ret;
|
2013-04-29 20:48:18 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Create VHDX Headers
|
|
|
|
*
|
|
|
|
* There are 2 headers, and the highest sequence number will represent
|
|
|
|
* the active header
|
|
|
|
*/
|
2016-06-20 22:05:39 +02:00
|
|
|
static int vhdx_create_new_headers(BlockBackend *blk, uint64_t image_size,
|
2013-10-30 15:44:53 +01:00
|
|
|
uint32_t log_size)
|
|
|
|
{
|
2016-06-20 22:05:39 +02:00
|
|
|
BlockDriverState *bs = blk_bs(blk);
|
2016-06-20 18:24:02 +02:00
|
|
|
BdrvChild *child;
|
2013-10-30 15:44:53 +01:00
|
|
|
int ret = 0;
|
|
|
|
VHDXHeader *hdr = NULL;
|
|
|
|
|
block: Use g_new() & friends where that makes obvious sense
g_new(T, n) is neater than g_malloc(sizeof(T) * n). It's also safer,
for two reasons. One, it catches multiplication overflowing size_t.
Two, it returns T * rather than void *, which lets the compiler catch
more type errors.
Patch created with Coccinelle, with two manual changes on top:
* Add const to bdrv_iterate_format() to keep the types straight
* Convert the allocation in bdrv_drop_intermediate(), which Coccinelle
inexplicably misses
Coccinelle semantic patch:
@@
type T;
@@
-g_malloc(sizeof(T))
+g_new(T, 1)
@@
type T;
@@
-g_try_malloc(sizeof(T))
+g_try_new(T, 1)
@@
type T;
@@
-g_malloc0(sizeof(T))
+g_new0(T, 1)
@@
type T;
@@
-g_try_malloc0(sizeof(T))
+g_try_new0(T, 1)
@@
type T;
expression n;
@@
-g_malloc(sizeof(T) * (n))
+g_new(T, n)
@@
type T;
expression n;
@@
-g_try_malloc(sizeof(T) * (n))
+g_try_new(T, n)
@@
type T;
expression n;
@@
-g_malloc0(sizeof(T) * (n))
+g_new0(T, n)
@@
type T;
expression n;
@@
-g_try_malloc0(sizeof(T) * (n))
+g_try_new0(T, n)
@@
type T;
expression p, n;
@@
-g_realloc(p, sizeof(T) * (n))
+g_renew(T, p, n)
@@
type T;
expression p, n;
@@
-g_try_realloc(p, sizeof(T) * (n))
+g_try_renew(T, p, n)
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2014-08-19 10:31:08 +02:00
|
|
|
hdr = g_new0(VHDXHeader, 1);
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
hdr->signature = VHDX_HEADER_SIGNATURE;
|
|
|
|
hdr->sequence_number = g_random_int();
|
|
|
|
hdr->log_version = 0;
|
|
|
|
hdr->version = 1;
|
|
|
|
hdr->log_length = log_size;
|
|
|
|
hdr->log_offset = VHDX_HEADER_SECTION_END;
|
|
|
|
vhdx_guid_generate(&hdr->file_write_guid);
|
|
|
|
vhdx_guid_generate(&hdr->data_write_guid);
|
|
|
|
|
2016-06-20 18:24:02 +02:00
|
|
|
/* XXX Ugly way to get blk->root, but that's a feature, not a bug. This
|
|
|
|
* hack makes it obvious that vhdx_write_header() bypasses the BlockBackend
|
|
|
|
* here, which it really shouldn't be doing. */
|
|
|
|
child = QLIST_FIRST(&bs->parents);
|
|
|
|
assert(!QLIST_NEXT(child, next_parent));
|
|
|
|
|
|
|
|
ret = vhdx_write_header(child, hdr, VHDX_HEADER1_OFFSET, false);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
hdr->sequence_number++;
|
2016-06-20 18:24:02 +02:00
|
|
|
ret = vhdx_write_header(child, hdr, VHDX_HEADER2_OFFSET, false);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
exit:
|
|
|
|
g_free(hdr);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2014-09-16 21:12:06 +02:00
|
|
|
#define VHDX_METADATA_ENTRY_BUFFER_SIZE \
|
|
|
|
(sizeof(VHDXFileParameters) +\
|
|
|
|
sizeof(VHDXVirtualDiskSize) +\
|
|
|
|
sizeof(VHDXPage83Data) +\
|
|
|
|
sizeof(VHDXVirtualDiskLogicalSectorSize) +\
|
|
|
|
sizeof(VHDXVirtualDiskPhysicalSectorSize))
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Create the Metadata entries.
|
|
|
|
*
|
|
|
|
* For more details on the entries, see section 3.5 (pg 29) in the
|
|
|
|
* VHDX 1.00 specification.
|
|
|
|
*
|
|
|
|
* We support 5 metadata entries (all required by spec):
|
|
|
|
* File Parameters,
|
|
|
|
* Virtual Disk Size,
|
|
|
|
* Page 83 Data,
|
|
|
|
* Logical Sector Size,
|
|
|
|
* Physical Sector Size
|
|
|
|
*
|
|
|
|
* The first 64KB of the Metadata section is reserved for the metadata
|
|
|
|
* header and entries; beyond that, the metadata items themselves reside.
|
|
|
|
*/
|
2016-06-20 22:05:39 +02:00
|
|
|
static int vhdx_create_new_metadata(BlockBackend *blk,
|
2013-10-30 15:44:53 +01:00
|
|
|
uint64_t image_size,
|
|
|
|
uint32_t block_size,
|
|
|
|
uint32_t sector_size,
|
|
|
|
uint64_t metadata_offset,
|
|
|
|
VHDXImageType type)
|
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint32_t offset = 0;
|
|
|
|
void *buffer = NULL;
|
|
|
|
void *entry_buffer;
|
2015-08-26 13:17:12 +02:00
|
|
|
VHDXMetadataTableHeader *md_table;
|
2013-10-30 15:44:53 +01:00
|
|
|
VHDXMetadataTableEntry *md_table_entry;
|
|
|
|
|
|
|
|
/* Metadata entries */
|
|
|
|
VHDXFileParameters *mt_file_params;
|
|
|
|
VHDXVirtualDiskSize *mt_virtual_size;
|
|
|
|
VHDXPage83Data *mt_page83;
|
|
|
|
VHDXVirtualDiskLogicalSectorSize *mt_log_sector_size;
|
|
|
|
VHDXVirtualDiskPhysicalSectorSize *mt_phys_sector_size;
|
|
|
|
|
2014-09-16 21:12:06 +02:00
|
|
|
entry_buffer = g_malloc0(VHDX_METADATA_ENTRY_BUFFER_SIZE);
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
mt_file_params = entry_buffer;
|
|
|
|
offset += sizeof(VHDXFileParameters);
|
|
|
|
mt_virtual_size = entry_buffer + offset;
|
|
|
|
offset += sizeof(VHDXVirtualDiskSize);
|
|
|
|
mt_page83 = entry_buffer + offset;
|
|
|
|
offset += sizeof(VHDXPage83Data);
|
|
|
|
mt_log_sector_size = entry_buffer + offset;
|
|
|
|
offset += sizeof(VHDXVirtualDiskLogicalSectorSize);
|
|
|
|
mt_phys_sector_size = entry_buffer + offset;
|
|
|
|
|
|
|
|
mt_file_params->block_size = cpu_to_le32(block_size);
|
|
|
|
if (type == VHDX_TYPE_FIXED) {
|
|
|
|
mt_file_params->data_bits |= VHDX_PARAMS_LEAVE_BLOCKS_ALLOCED;
|
2018-10-16 19:09:38 +02:00
|
|
|
mt_file_params->data_bits = cpu_to_le32(mt_file_params->data_bits);
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
vhdx_guid_generate(&mt_page83->page_83_data);
|
|
|
|
cpu_to_leguids(&mt_page83->page_83_data);
|
|
|
|
mt_virtual_size->virtual_disk_size = cpu_to_le64(image_size);
|
|
|
|
mt_log_sector_size->logical_sector_size = cpu_to_le32(sector_size);
|
|
|
|
mt_phys_sector_size->physical_sector_size = cpu_to_le32(sector_size);
|
|
|
|
|
|
|
|
buffer = g_malloc0(VHDX_HEADER_BLOCK_SIZE);
|
|
|
|
md_table = buffer;
|
|
|
|
|
|
|
|
md_table->signature = VHDX_METADATA_SIGNATURE;
|
|
|
|
md_table->entry_count = 5;
|
|
|
|
vhdx_metadata_header_le_export(md_table);
|
|
|
|
|
|
|
|
|
|
|
|
/* This will reference beyond the reserved table portion */
|
|
|
|
offset = 64 * KiB;
|
|
|
|
|
|
|
|
md_table_entry = buffer + sizeof(VHDXMetadataTableHeader);
|
|
|
|
|
|
|
|
md_table_entry[0].item_id = file_param_guid;
|
|
|
|
md_table_entry[0].offset = offset;
|
|
|
|
md_table_entry[0].length = sizeof(VHDXFileParameters);
|
|
|
|
md_table_entry[0].data_bits |= VHDX_META_FLAGS_IS_REQUIRED;
|
|
|
|
offset += md_table_entry[0].length;
|
|
|
|
vhdx_metadata_entry_le_export(&md_table_entry[0]);
|
|
|
|
|
|
|
|
md_table_entry[1].item_id = virtual_size_guid;
|
|
|
|
md_table_entry[1].offset = offset;
|
|
|
|
md_table_entry[1].length = sizeof(VHDXVirtualDiskSize);
|
|
|
|
md_table_entry[1].data_bits |= VHDX_META_FLAGS_IS_REQUIRED |
|
|
|
|
VHDX_META_FLAGS_IS_VIRTUAL_DISK;
|
|
|
|
offset += md_table_entry[1].length;
|
|
|
|
vhdx_metadata_entry_le_export(&md_table_entry[1]);
|
|
|
|
|
|
|
|
md_table_entry[2].item_id = page83_guid;
|
|
|
|
md_table_entry[2].offset = offset;
|
|
|
|
md_table_entry[2].length = sizeof(VHDXPage83Data);
|
|
|
|
md_table_entry[2].data_bits |= VHDX_META_FLAGS_IS_REQUIRED |
|
|
|
|
VHDX_META_FLAGS_IS_VIRTUAL_DISK;
|
|
|
|
offset += md_table_entry[2].length;
|
|
|
|
vhdx_metadata_entry_le_export(&md_table_entry[2]);
|
|
|
|
|
|
|
|
md_table_entry[3].item_id = logical_sector_guid;
|
|
|
|
md_table_entry[3].offset = offset;
|
|
|
|
md_table_entry[3].length = sizeof(VHDXVirtualDiskLogicalSectorSize);
|
|
|
|
md_table_entry[3].data_bits |= VHDX_META_FLAGS_IS_REQUIRED |
|
|
|
|
VHDX_META_FLAGS_IS_VIRTUAL_DISK;
|
|
|
|
offset += md_table_entry[3].length;
|
|
|
|
vhdx_metadata_entry_le_export(&md_table_entry[3]);
|
|
|
|
|
|
|
|
md_table_entry[4].item_id = phys_sector_guid;
|
|
|
|
md_table_entry[4].offset = offset;
|
|
|
|
md_table_entry[4].length = sizeof(VHDXVirtualDiskPhysicalSectorSize);
|
|
|
|
md_table_entry[4].data_bits |= VHDX_META_FLAGS_IS_REQUIRED |
|
|
|
|
VHDX_META_FLAGS_IS_VIRTUAL_DISK;
|
|
|
|
vhdx_metadata_entry_le_export(&md_table_entry[4]);
|
|
|
|
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = blk_pwrite(blk, metadata_offset, buffer, VHDX_HEADER_BLOCK_SIZE, 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = blk_pwrite(blk, metadata_offset + (64 * KiB), entry_buffer,
|
|
|
|
VHDX_METADATA_ENTRY_BUFFER_SIZE, 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
exit:
|
|
|
|
g_free(buffer);
|
|
|
|
g_free(entry_buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* This create the actual BAT itself. We currently only support
|
|
|
|
* 'Dynamic' and 'Fixed' image types.
|
|
|
|
*
|
|
|
|
* Dynamic images: default state of the BAT is all zeroes.
|
|
|
|
*
|
|
|
|
* Fixed images: default state of the BAT is fully populated, with
|
|
|
|
* file offsets and state PAYLOAD_BLOCK_FULLY_PRESENT.
|
|
|
|
*/
|
2016-06-20 22:05:39 +02:00
|
|
|
static int vhdx_create_bat(BlockBackend *blk, BDRVVHDXState *s,
|
2013-10-30 15:44:53 +01:00
|
|
|
uint64_t image_size, VHDXImageType type,
|
2014-08-06 21:54:58 +02:00
|
|
|
bool use_zero_blocks, uint64_t file_offset,
|
2017-03-28 22:51:26 +02:00
|
|
|
uint32_t length, Error **errp)
|
2013-10-30 15:44:53 +01:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint64_t data_file_offset;
|
|
|
|
uint64_t total_sectors = 0;
|
|
|
|
uint64_t sector_num = 0;
|
|
|
|
uint64_t unused;
|
|
|
|
int block_state;
|
|
|
|
VHDXSectorInfo sinfo;
|
|
|
|
|
|
|
|
assert(s->bat == NULL);
|
|
|
|
|
|
|
|
/* this gives a data start after BAT/bitmap entries, and well
|
|
|
|
* past any metadata entries (with a 4 MB buffer for future
|
|
|
|
* expansion */
|
2014-08-06 21:54:58 +02:00
|
|
|
data_file_offset = file_offset + length + 5 * MiB;
|
2013-10-30 15:44:53 +01:00
|
|
|
total_sectors = image_size >> s->logical_sector_size_bits;
|
|
|
|
|
|
|
|
if (type == VHDX_TYPE_DYNAMIC) {
|
|
|
|
/* All zeroes, so we can just extend the file - the end of the BAT
|
|
|
|
* is the furthest thing we have written yet */
|
2019-09-18 11:51:40 +02:00
|
|
|
ret = blk_truncate(blk, data_file_offset, false, PREALLOC_MODE_OFF,
|
2020-04-24 14:54:41 +02:00
|
|
|
0, errp);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
} else if (type == VHDX_TYPE_FIXED) {
|
2019-09-18 11:51:40 +02:00
|
|
|
ret = blk_truncate(blk, data_file_offset + image_size, false,
|
2020-04-24 14:54:41 +02:00
|
|
|
PREALLOC_MODE_OFF, 0, errp);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
} else {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg(errp, "Unsupported image type");
|
2013-10-30 15:44:53 +01:00
|
|
|
ret = -ENOTSUP;
|
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (type == VHDX_TYPE_FIXED ||
|
|
|
|
use_zero_blocks ||
|
2016-06-20 22:05:39 +02:00
|
|
|
bdrv_has_zero_init(blk_bs(blk)) == 0) {
|
2013-10-30 15:44:53 +01:00
|
|
|
/* for a fixed file, the default BAT entry is not zero */
|
2014-05-20 13:55:50 +02:00
|
|
|
s->bat = g_try_malloc0(length);
|
2014-09-18 17:17:44 +02:00
|
|
|
if (length && s->bat == NULL) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg(errp, "Failed to allocate memory for the BAT");
|
2014-05-20 13:55:50 +02:00
|
|
|
ret = -ENOMEM;
|
|
|
|
goto exit;
|
|
|
|
}
|
2013-10-30 15:44:53 +01:00
|
|
|
block_state = type == VHDX_TYPE_FIXED ? PAYLOAD_BLOCK_FULLY_PRESENT :
|
|
|
|
PAYLOAD_BLOCK_NOT_PRESENT;
|
|
|
|
block_state = use_zero_blocks ? PAYLOAD_BLOCK_ZERO : block_state;
|
|
|
|
/* fill the BAT by emulating sector writes of sectors_per_block size */
|
|
|
|
while (sector_num < total_sectors) {
|
|
|
|
vhdx_block_translate(s, sector_num, s->sectors_per_block, &sinfo);
|
|
|
|
sinfo.file_offset = data_file_offset +
|
|
|
|
(sector_num << s->logical_sector_size_bits);
|
|
|
|
sinfo.file_offset = ROUND_UP(sinfo.file_offset, MiB);
|
2016-06-20 22:05:39 +02:00
|
|
|
vhdx_update_bat_table_entry(blk_bs(blk), s, &sinfo, &unused, &unused,
|
2013-10-30 15:44:53 +01:00
|
|
|
block_state);
|
2018-10-16 19:09:38 +02:00
|
|
|
s->bat[sinfo.bat_idx] = cpu_to_le64(s->bat[sinfo.bat_idx]);
|
2013-10-30 15:44:53 +01:00
|
|
|
sector_num += s->sectors_per_block;
|
|
|
|
}
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = blk_pwrite(blk, file_offset, s->bat, length, 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write the BAT");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
exit:
|
|
|
|
g_free(s->bat);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Creates the region table header, and region table entries.
|
|
|
|
* There are 2 supported region table entries: BAT, and Metadata/
|
|
|
|
*
|
|
|
|
* As the calculations for the BAT region table are also needed
|
|
|
|
* to create the BAT itself, we will also cause the BAT to be
|
|
|
|
* created.
|
|
|
|
*/
|
2016-06-20 22:05:39 +02:00
|
|
|
static int vhdx_create_new_region_table(BlockBackend *blk,
|
2013-10-30 15:44:53 +01:00
|
|
|
uint64_t image_size,
|
|
|
|
uint32_t block_size,
|
|
|
|
uint32_t sector_size,
|
|
|
|
uint32_t log_size,
|
|
|
|
bool use_zero_blocks,
|
|
|
|
VHDXImageType type,
|
2017-03-28 22:51:26 +02:00
|
|
|
uint64_t *metadata_offset,
|
|
|
|
Error **errp)
|
2013-10-30 15:44:53 +01:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
uint32_t offset = 0;
|
|
|
|
void *buffer = NULL;
|
2014-08-06 21:54:58 +02:00
|
|
|
uint64_t bat_file_offset;
|
|
|
|
uint32_t bat_length;
|
2013-10-30 15:44:53 +01:00
|
|
|
BDRVVHDXState *s = NULL;
|
|
|
|
VHDXRegionTableHeader *region_table;
|
|
|
|
VHDXRegionTableEntry *rt_bat;
|
|
|
|
VHDXRegionTableEntry *rt_metadata;
|
|
|
|
|
|
|
|
assert(metadata_offset != NULL);
|
|
|
|
|
|
|
|
/* Populate enough of the BDRVVHDXState to be able to use the
|
|
|
|
* pre-existing BAT calculation, translation, and update functions */
|
block: Use g_new() & friends where that makes obvious sense
g_new(T, n) is neater than g_malloc(sizeof(T) * n). It's also safer,
for two reasons. One, it catches multiplication overflowing size_t.
Two, it returns T * rather than void *, which lets the compiler catch
more type errors.
Patch created with Coccinelle, with two manual changes on top:
* Add const to bdrv_iterate_format() to keep the types straight
* Convert the allocation in bdrv_drop_intermediate(), which Coccinelle
inexplicably misses
Coccinelle semantic patch:
@@
type T;
@@
-g_malloc(sizeof(T))
+g_new(T, 1)
@@
type T;
@@
-g_try_malloc(sizeof(T))
+g_try_new(T, 1)
@@
type T;
@@
-g_malloc0(sizeof(T))
+g_new0(T, 1)
@@
type T;
@@
-g_try_malloc0(sizeof(T))
+g_try_new0(T, 1)
@@
type T;
expression n;
@@
-g_malloc(sizeof(T) * (n))
+g_new(T, n)
@@
type T;
expression n;
@@
-g_try_malloc(sizeof(T) * (n))
+g_try_new(T, n)
@@
type T;
expression n;
@@
-g_malloc0(sizeof(T) * (n))
+g_new0(T, n)
@@
type T;
expression n;
@@
-g_try_malloc0(sizeof(T) * (n))
+g_try_new0(T, n)
@@
type T;
expression p, n;
@@
-g_realloc(p, sizeof(T) * (n))
+g_renew(T, p, n)
@@
type T;
expression p, n;
@@
-g_try_realloc(p, sizeof(T) * (n))
+g_try_renew(T, p, n)
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2014-08-19 10:31:08 +02:00
|
|
|
s = g_new0(BDRVVHDXState, 1);
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
|
|
|
|
(uint64_t) sector_size / (uint64_t) block_size;
|
|
|
|
|
|
|
|
s->sectors_per_block = block_size / sector_size;
|
|
|
|
s->virtual_disk_size = image_size;
|
|
|
|
s->block_size = block_size;
|
|
|
|
s->logical_sector_size = sector_size;
|
|
|
|
|
|
|
|
vhdx_set_shift_bits(s);
|
|
|
|
|
|
|
|
vhdx_calc_bat_entries(s);
|
|
|
|
|
|
|
|
/* At this point the VHDX state is populated enough for creation */
|
|
|
|
|
|
|
|
/* a single buffer is used so we can calculate the checksum over the
|
|
|
|
* entire 64KB block */
|
|
|
|
buffer = g_malloc0(VHDX_HEADER_BLOCK_SIZE);
|
|
|
|
region_table = buffer;
|
|
|
|
offset += sizeof(VHDXRegionTableHeader);
|
|
|
|
rt_bat = buffer + offset;
|
|
|
|
offset += sizeof(VHDXRegionTableEntry);
|
|
|
|
rt_metadata = buffer + offset;
|
|
|
|
|
|
|
|
region_table->signature = VHDX_REGION_SIGNATURE;
|
|
|
|
region_table->entry_count = 2; /* BAT and Metadata */
|
|
|
|
|
|
|
|
rt_bat->guid = bat_guid;
|
|
|
|
rt_bat->length = ROUND_UP(s->bat_entries * sizeof(VHDXBatEntry), MiB);
|
|
|
|
rt_bat->file_offset = ROUND_UP(VHDX_HEADER_SECTION_END + log_size, MiB);
|
|
|
|
s->bat_offset = rt_bat->file_offset;
|
|
|
|
|
|
|
|
rt_metadata->guid = metadata_guid;
|
|
|
|
rt_metadata->file_offset = ROUND_UP(rt_bat->file_offset + rt_bat->length,
|
|
|
|
MiB);
|
|
|
|
rt_metadata->length = 1 * MiB; /* min size, and more than enough */
|
|
|
|
*metadata_offset = rt_metadata->file_offset;
|
|
|
|
|
2014-08-06 21:54:58 +02:00
|
|
|
bat_file_offset = rt_bat->file_offset;
|
|
|
|
bat_length = rt_bat->length;
|
|
|
|
|
|
|
|
vhdx_region_header_le_export(region_table);
|
|
|
|
vhdx_region_entry_le_export(rt_bat);
|
|
|
|
vhdx_region_entry_le_export(rt_metadata);
|
|
|
|
|
2013-10-30 15:44:53 +01:00
|
|
|
vhdx_update_checksum(buffer, VHDX_HEADER_BLOCK_SIZE,
|
|
|
|
offsetof(VHDXRegionTableHeader, checksum));
|
|
|
|
|
|
|
|
|
|
|
|
/* The region table gives us the data we need to create the BAT,
|
|
|
|
* so do that now */
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = vhdx_create_bat(blk, s, image_size, type, use_zero_blocks,
|
2017-03-28 22:51:26 +02:00
|
|
|
bat_file_offset, bat_length, errp);
|
2014-08-06 21:54:58 +02:00
|
|
|
if (ret < 0) {
|
|
|
|
goto exit;
|
|
|
|
}
|
2013-10-30 15:44:53 +01:00
|
|
|
|
|
|
|
/* Now write out the region headers to disk */
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = blk_pwrite(blk, VHDX_REGION_TABLE_OFFSET, buffer,
|
|
|
|
VHDX_HEADER_BLOCK_SIZE, 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write first region table");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = blk_pwrite(blk, VHDX_REGION_TABLE2_OFFSET, buffer,
|
|
|
|
VHDX_HEADER_BLOCK_SIZE, 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write second region table");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
exit:
|
|
|
|
g_free(s);
|
|
|
|
g_free(buffer);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* We need to create the following elements:
|
|
|
|
*
|
|
|
|
* .-----------------------------------------------------------------.
|
|
|
|
* | (A) | (B) | (C) | (D) | (E) |
|
|
|
|
* | File ID | Header1 | Header 2 | Region Tbl 1 | Region Tbl 2 |
|
|
|
|
* | | | | | |
|
|
|
|
* .-----------------------------------------------------------------.
|
|
|
|
* 0 64KB 128KB 192KB 256KB 320KB
|
|
|
|
*
|
|
|
|
*
|
|
|
|
* .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
|
|
|
|
* | (F) | (G) | (H) | |
|
|
|
|
* | Journal Log | BAT / Bitmap | Metadata | .... data ...... |
|
|
|
|
* | | | | |
|
|
|
|
* .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
|
|
|
|
* 1MB
|
|
|
|
*/
|
2018-03-09 19:53:19 +01:00
|
|
|
static int coroutine_fn vhdx_co_create(BlockdevCreateOptions *opts,
|
|
|
|
Error **errp)
|
2013-10-30 15:44:53 +01:00
|
|
|
{
|
2018-03-09 19:53:19 +01:00
|
|
|
BlockdevCreateOptionsVhdx *vhdx_opts;
|
|
|
|
BlockBackend *blk = NULL;
|
|
|
|
BlockDriverState *bs = NULL;
|
|
|
|
|
2013-10-30 15:44:53 +01:00
|
|
|
int ret = 0;
|
2018-03-09 19:53:19 +01:00
|
|
|
uint64_t image_size;
|
|
|
|
uint32_t log_size;
|
|
|
|
uint32_t block_size;
|
2013-10-30 15:44:53 +01:00
|
|
|
uint64_t signature;
|
|
|
|
uint64_t metadata_offset;
|
|
|
|
bool use_zero_blocks = false;
|
|
|
|
|
|
|
|
gunichar2 *creator = NULL;
|
|
|
|
glong creator_items;
|
|
|
|
VHDXImageType image_type;
|
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
assert(opts->driver == BLOCKDEV_DRIVER_VHDX);
|
|
|
|
vhdx_opts = &opts->u.vhdx;
|
2013-10-30 15:44:53 +01:00
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
/* Validate options and set default values */
|
|
|
|
image_size = vhdx_opts->size;
|
2013-10-30 15:44:53 +01:00
|
|
|
if (image_size > VHDX_MAX_IMAGE_SIZE) {
|
2018-03-20 18:11:09 +01:00
|
|
|
error_setg(errp, "Image size too large; max of 64TB");
|
2018-03-09 19:53:19 +01:00
|
|
|
return -EINVAL;
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
if (!vhdx_opts->has_log_size) {
|
|
|
|
log_size = DEFAULT_LOG_SIZE;
|
|
|
|
} else {
|
2018-03-20 18:24:54 +01:00
|
|
|
if (vhdx_opts->log_size > UINT32_MAX) {
|
|
|
|
error_setg(errp, "Log size must be smaller than 4 GB");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2018-03-09 19:53:19 +01:00
|
|
|
log_size = vhdx_opts->log_size;
|
|
|
|
}
|
|
|
|
if (log_size < MiB || (log_size % MiB) != 0) {
|
2018-03-20 18:11:09 +01:00
|
|
|
error_setg(errp, "Log size must be a multiple of 1 MB");
|
2018-03-09 19:53:19 +01:00
|
|
|
return -EINVAL;
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
if (!vhdx_opts->has_block_state_zero) {
|
|
|
|
use_zero_blocks = true;
|
|
|
|
} else {
|
|
|
|
use_zero_blocks = vhdx_opts->block_state_zero;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!vhdx_opts->has_subformat) {
|
|
|
|
vhdx_opts->subformat = BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC;
|
|
|
|
}
|
|
|
|
|
|
|
|
switch (vhdx_opts->subformat) {
|
|
|
|
case BLOCKDEV_VHDX_SUBFORMAT_DYNAMIC:
|
2013-10-30 15:44:53 +01:00
|
|
|
image_type = VHDX_TYPE_DYNAMIC;
|
2018-03-09 19:53:19 +01:00
|
|
|
break;
|
|
|
|
case BLOCKDEV_VHDX_SUBFORMAT_FIXED:
|
2013-10-30 15:44:53 +01:00
|
|
|
image_type = VHDX_TYPE_FIXED;
|
2018-03-09 19:53:19 +01:00
|
|
|
break;
|
|
|
|
default:
|
|
|
|
g_assert_not_reached();
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
|
|
|
/* These are pretty arbitrary, and mainly designed to keep the BAT
|
|
|
|
* size reasonable to load into RAM */
|
2018-03-09 19:53:19 +01:00
|
|
|
if (vhdx_opts->has_block_size) {
|
|
|
|
block_size = vhdx_opts->block_size;
|
|
|
|
} else {
|
2013-10-30 15:44:53 +01:00
|
|
|
if (image_size > 32 * TiB) {
|
|
|
|
block_size = 64 * MiB;
|
|
|
|
} else if (image_size > (uint64_t) 100 * GiB) {
|
|
|
|
block_size = 32 * MiB;
|
|
|
|
} else if (image_size > 1 * GiB) {
|
|
|
|
block_size = 16 * MiB;
|
|
|
|
} else {
|
|
|
|
block_size = 8 * MiB;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
if (block_size < MiB || (block_size % MiB) != 0) {
|
2018-03-20 18:11:09 +01:00
|
|
|
error_setg(errp, "Block size must be a multiple of 1 MB");
|
2018-03-09 19:53:19 +01:00
|
|
|
return -EINVAL;
|
2018-03-20 18:09:15 +01:00
|
|
|
}
|
|
|
|
if (!is_power_of_2(block_size)) {
|
|
|
|
error_setg(errp, "Block size must be a power of two");
|
|
|
|
return -EINVAL;
|
2018-03-09 19:53:19 +01:00
|
|
|
}
|
|
|
|
if (block_size > VHDX_BLOCK_SIZE_MAX) {
|
2019-03-27 10:56:33 +01:00
|
|
|
error_setg(errp, "Block size must not exceed %" PRId64,
|
|
|
|
VHDX_BLOCK_SIZE_MAX);
|
2018-03-09 19:53:19 +01:00
|
|
|
return -EINVAL;
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
2018-03-09 19:53:19 +01:00
|
|
|
/* Create BlockBackend to write to the image */
|
|
|
|
bs = bdrv_open_blockdev_ref(vhdx_opts->file, errp);
|
|
|
|
if (bs == NULL) {
|
|
|
|
return -EIO;
|
2013-10-30 15:44:53 +01:00
|
|
|
}
|
|
|
|
|
2020-04-28 21:26:46 +02:00
|
|
|
blk = blk_new_with_bs(bs, BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL,
|
|
|
|
errp);
|
|
|
|
if (!blk) {
|
|
|
|
ret = -EPERM;
|
2018-03-09 19:53:19 +01:00
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
2016-03-08 15:57:05 +01:00
|
|
|
blk_set_allow_write_beyond_eof(blk, true);
|
|
|
|
|
2013-10-30 15:44:53 +01:00
|
|
|
/* Create (A) */
|
|
|
|
|
|
|
|
/* The creator field is optional, but may be useful for
|
|
|
|
* debugging / diagnostics */
|
|
|
|
creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL,
|
|
|
|
&creator_items, NULL);
|
|
|
|
signature = cpu_to_le64(VHDX_FILE_SIGNATURE);
|
2016-05-06 18:26:27 +02:00
|
|
|
ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature),
|
|
|
|
0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write file signature");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
|
|
|
if (creator) {
|
2016-03-08 15:57:05 +01:00
|
|
|
ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature),
|
2016-05-06 18:26:27 +02:00
|
|
|
creator, creator_items * sizeof(gunichar2), 0);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write creator field");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Creates (B),(C) */
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = vhdx_create_new_headers(blk, image_size, log_size);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to write image headers");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Creates (D),(E),(G) explicitly. (F) created as by-product */
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = vhdx_create_new_region_table(blk, image_size, block_size, 512,
|
2013-10-30 15:44:53 +01:00
|
|
|
log_size, use_zero_blocks, image_type,
|
2017-03-28 22:51:26 +02:00
|
|
|
&metadata_offset, errp);
|
2013-10-30 15:44:53 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Creates (H) */
|
2016-06-20 22:05:39 +02:00
|
|
|
ret = vhdx_create_new_metadata(blk, image_size, block_size, 512,
|
2013-10-30 15:44:53 +01:00
|
|
|
metadata_offset, image_type);
|
|
|
|
if (ret < 0) {
|
2017-03-28 22:51:26 +02:00
|
|
|
error_setg_errno(errp, -ret, "Failed to initialize metadata");
|
2013-10-30 15:44:53 +01:00
|
|
|
goto delete_and_exit;
|
|
|
|
}
|
|
|
|
|
2018-05-25 14:48:16 +02:00
|
|
|
ret = 0;
|
2013-10-30 15:44:53 +01:00
|
|
|
delete_and_exit:
|
2016-03-08 15:57:05 +01:00
|
|
|
blk_unref(blk);
|
2018-03-09 19:53:19 +01:00
|
|
|
bdrv_unref(bs);
|
2013-10-30 15:44:53 +01:00
|
|
|
g_free(creator);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-03-26 02:12:17 +01:00
|
|
|
static int coroutine_fn vhdx_co_create_opts(BlockDriver *drv,
|
|
|
|
const char *filename,
|
2018-03-09 19:53:19 +01:00
|
|
|
QemuOpts *opts,
|
|
|
|
Error **errp)
|
|
|
|
{
|
|
|
|
BlockdevCreateOptions *create_options = NULL;
|
2018-06-14 21:14:32 +02:00
|
|
|
QDict *qdict;
|
2018-03-09 19:53:19 +01:00
|
|
|
Visitor *v;
|
|
|
|
BlockDriverState *bs = NULL;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
static const QDictRenames opt_renames[] = {
|
|
|
|
{ VHDX_BLOCK_OPT_LOG_SIZE, "log-size" },
|
|
|
|
{ VHDX_BLOCK_OPT_BLOCK_SIZE, "block-size" },
|
|
|
|
{ VHDX_BLOCK_OPT_ZERO, "block-state-zero" },
|
|
|
|
{ NULL, NULL },
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Parse options and convert legacy syntax */
|
|
|
|
qdict = qemu_opts_to_qdict_filtered(opts, NULL, &vhdx_create_opts, true);
|
|
|
|
|
|
|
|
if (!qdict_rename_keys(qdict, opt_renames, errp)) {
|
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Create and open the file (protocol layer) */
|
error: Eliminate error_propagate() with Coccinelle, part 1
When all we do with an Error we receive into a local variable is
propagating to somewhere else, we can just as well receive it there
right away. Convert
if (!foo(..., &err)) {
...
error_propagate(errp, err);
...
return ...
}
to
if (!foo(..., errp)) {
...
...
return ...
}
where nothing else needs @err. Coccinelle script:
@rule1 forall@
identifier fun, err, errp, lbl;
expression list args, args2;
binary operator op;
constant c1, c2;
symbol false;
@@
if (
(
- fun(args, &err, args2)
+ fun(args, errp, args2)
|
- !fun(args, &err, args2)
+ !fun(args, errp, args2)
|
- fun(args, &err, args2) op c1
+ fun(args, errp, args2) op c1
)
)
{
... when != err
when != lbl:
when strict
- error_propagate(errp, err);
... when != err
(
return;
|
return c2;
|
return false;
)
}
@rule2 forall@
identifier fun, err, errp, lbl;
expression list args, args2;
expression var;
binary operator op;
constant c1, c2;
symbol false;
@@
- var = fun(args, &err, args2);
+ var = fun(args, errp, args2);
... when != err
if (
(
var
|
!var
|
var op c1
)
)
{
... when != err
when != lbl:
when strict
- error_propagate(errp, err);
... when != err
(
return;
|
return c2;
|
return false;
|
return var;
)
}
@depends on rule1 || rule2@
identifier err;
@@
- Error *err = NULL;
... when != err
Not exactly elegant, I'm afraid.
The "when != lbl:" is necessary to avoid transforming
if (fun(args, &err)) {
goto out
}
...
out:
error_propagate(errp, err);
even though other paths to label out still need the error_propagate().
For an actual example, see sclp_realize().
Without the "when strict", Coccinelle transforms vfio_msix_setup(),
incorrectly. I don't know what exactly "when strict" does, only that
it helps here.
The match of return is narrower than what I want, but I can't figure
out how to express "return where the operand doesn't use @err". For
an example where it's too narrow, see vfio_intx_enable().
Silently fails to convert hw/arm/armsse.c, because Coccinelle gets
confused by ARMSSE being used both as typedef and function-like macro
there. Converted manually.
Line breaks tidied up manually. One nested declaration of @local_err
deleted manually. Preexisting unwanted blank line dropped in
hw/riscv/sifive_e.c.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200707160613.848843-35-armbru@redhat.com>
2020-07-07 18:06:02 +02:00
|
|
|
ret = bdrv_create_file(filename, opts, errp);
|
2018-03-09 19:53:19 +01:00
|
|
|
if (ret < 0) {
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
bs = bdrv_open(filename, NULL, NULL,
|
|
|
|
BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
|
|
|
|
if (bs == NULL) {
|
|
|
|
ret = -EIO;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Now get the QAPI type BlockdevCreateOptions */
|
|
|
|
qdict_put_str(qdict, "driver", "vhdx");
|
|
|
|
qdict_put_str(qdict, "file", bs->node_name);
|
|
|
|
|
2018-06-14 21:14:33 +02:00
|
|
|
v = qobject_input_visitor_new_flat_confused(qdict, errp);
|
|
|
|
if (!v) {
|
2018-03-09 19:53:19 +01:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
2020-07-07 18:06:07 +02:00
|
|
|
visit_type_BlockdevCreateOptions(v, NULL, &create_options, errp);
|
2018-03-09 19:53:19 +01:00
|
|
|
visit_free(v);
|
2020-07-07 18:06:07 +02:00
|
|
|
if (!create_options) {
|
2018-03-09 19:53:19 +01:00
|
|
|
ret = -EINVAL;
|
|
|
|
goto fail;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Silently round up sizes:
|
|
|
|
* The image size is rounded to 512 bytes. Make the block and log size
|
|
|
|
* close to what was specified, but must be at least 1MB, and a multiple of
|
|
|
|
* 1 MB. Also respect VHDX_BLOCK_SIZE_MAX for block sizes. block_size = 0
|
|
|
|
* means auto, which is represented by a missing key in QAPI. */
|
|
|
|
assert(create_options->driver == BLOCKDEV_DRIVER_VHDX);
|
|
|
|
create_options->u.vhdx.size =
|
|
|
|
ROUND_UP(create_options->u.vhdx.size, BDRV_SECTOR_SIZE);
|
|
|
|
|
|
|
|
if (create_options->u.vhdx.has_log_size) {
|
|
|
|
create_options->u.vhdx.log_size =
|
|
|
|
ROUND_UP(create_options->u.vhdx.log_size, MiB);
|
|
|
|
}
|
|
|
|
if (create_options->u.vhdx.has_block_size) {
|
|
|
|
create_options->u.vhdx.block_size =
|
|
|
|
ROUND_UP(create_options->u.vhdx.block_size, MiB);
|
|
|
|
|
|
|
|
if (create_options->u.vhdx.block_size == 0) {
|
|
|
|
create_options->u.vhdx.has_block_size = false;
|
|
|
|
}
|
|
|
|
if (create_options->u.vhdx.block_size > VHDX_BLOCK_SIZE_MAX) {
|
|
|
|
create_options->u.vhdx.block_size = VHDX_BLOCK_SIZE_MAX;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Create the vhdx image (format layer) */
|
|
|
|
ret = vhdx_co_create(create_options, errp);
|
|
|
|
|
|
|
|
fail:
|
2018-04-19 17:01:43 +02:00
|
|
|
qobject_unref(qdict);
|
2018-03-09 19:53:19 +01:00
|
|
|
bdrv_unref(bs);
|
|
|
|
qapi_free_BlockdevCreateOptions(create_options);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-12-17 11:33:37 +01:00
|
|
|
/* If opened r/w, the VHDX driver will automatically replay the log,
|
|
|
|
* if one is present, inside the vhdx_open() call.
|
|
|
|
*
|
|
|
|
* If qemu-img check -r all is called, the image is automatically opened
|
|
|
|
* r/w and any log has already been replayed, so there is nothing (currently)
|
|
|
|
* for us to do here
|
|
|
|
*/
|
2018-03-01 17:36:19 +01:00
|
|
|
static int coroutine_fn vhdx_co_check(BlockDriverState *bs,
|
|
|
|
BdrvCheckResult *result,
|
|
|
|
BdrvCheckMode fix)
|
2013-12-17 11:33:37 +01:00
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
|
|
|
|
if (s->log_replayed_on_open) {
|
|
|
|
result->corruptions_fixed++;
|
|
|
|
}
|
2019-09-10 17:26:22 +02:00
|
|
|
|
|
|
|
vhdx_check_bat_entries(bs, &result->corruptions);
|
|
|
|
|
2013-12-17 11:33:37 +01:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-07-24 19:12:36 +02:00
|
|
|
static int vhdx_has_zero_init(BlockDriverState *bs)
|
|
|
|
{
|
|
|
|
BDRVVHDXState *s = bs->opaque;
|
|
|
|
int state;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check the subformat: Fixed images have all BAT entries present,
|
|
|
|
* dynamic images have none (right after creation). It is
|
|
|
|
* therefore enough to check the first BAT entry.
|
|
|
|
*/
|
|
|
|
if (!s->bat_entries) {
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
state = s->bat[0] & VHDX_BAT_STATE_BIT_MASK;
|
|
|
|
if (state == PAYLOAD_BLOCK_FULLY_PRESENT) {
|
|
|
|
/* Fixed subformat */
|
|
|
|
return bdrv_has_zero_init(bs->file->bs);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Dynamic subformat */
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2014-06-05 11:21:08 +02:00
|
|
|
static QemuOptsList vhdx_create_opts = {
|
|
|
|
.name = "vhdx-create-opts",
|
|
|
|
.head = QTAILQ_HEAD_INITIALIZER(vhdx_create_opts.head),
|
|
|
|
.desc = {
|
|
|
|
{
|
|
|
|
.name = BLOCK_OPT_SIZE,
|
|
|
|
.type = QEMU_OPT_SIZE,
|
|
|
|
.help = "Virtual disk size; max of 64TB."
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = VHDX_BLOCK_OPT_LOG_SIZE,
|
|
|
|
.type = QEMU_OPT_SIZE,
|
|
|
|
.def_value_str = stringify(DEFAULT_LOG_SIZE),
|
|
|
|
.help = "Log size; min 1MB."
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = VHDX_BLOCK_OPT_BLOCK_SIZE,
|
|
|
|
.type = QEMU_OPT_SIZE,
|
|
|
|
.def_value_str = stringify(0),
|
2020-04-13 00:35:56 +02:00
|
|
|
.help = "Block Size; min 1MB, max 256MB. "
|
2014-06-05 11:21:08 +02:00
|
|
|
"0 means auto-calculate based on image size."
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = BLOCK_OPT_SUBFMT,
|
|
|
|
.type = QEMU_OPT_STRING,
|
2020-04-13 00:35:56 +02:00
|
|
|
.help = "VHDX format type, can be either 'dynamic' or 'fixed'. "
|
2014-06-05 11:21:08 +02:00
|
|
|
"Default is 'dynamic'."
|
|
|
|
},
|
|
|
|
{
|
|
|
|
.name = VHDX_BLOCK_OPT_ZERO,
|
|
|
|
.type = QEMU_OPT_BOOL,
|
2020-04-13 00:35:56 +02:00
|
|
|
.help = "Force use of payload blocks of type 'ZERO'. "
|
|
|
|
"Non-standard, but default. Do not set to 'off' when "
|
2014-12-08 07:07:44 +01:00
|
|
|
"using 'qemu-img convert' with subformat=dynamic."
|
2014-06-05 11:21:08 +02:00
|
|
|
},
|
|
|
|
{ NULL }
|
|
|
|
}
|
2013-10-30 15:44:53 +01:00
|
|
|
};
|
|
|
|
|
2013-04-29 20:48:18 +02:00
|
|
|
static BlockDriver bdrv_vhdx = {
|
|
|
|
.format_name = "vhdx",
|
|
|
|
.instance_size = sizeof(BDRVVHDXState),
|
|
|
|
.bdrv_probe = vhdx_probe,
|
|
|
|
.bdrv_open = vhdx_open,
|
|
|
|
.bdrv_close = vhdx_close,
|
|
|
|
.bdrv_reopen_prepare = vhdx_reopen_prepare,
|
2020-05-13 13:05:39 +02:00
|
|
|
.bdrv_child_perm = bdrv_default_perms,
|
2013-04-29 20:48:18 +02:00
|
|
|
.bdrv_co_readv = vhdx_co_readv,
|
|
|
|
.bdrv_co_writev = vhdx_co_writev,
|
2018-03-09 19:53:19 +01:00
|
|
|
.bdrv_co_create = vhdx_co_create,
|
2018-01-18 13:43:45 +01:00
|
|
|
.bdrv_co_create_opts = vhdx_co_create_opts,
|
2013-11-22 13:39:49 +01:00
|
|
|
.bdrv_get_info = vhdx_get_info,
|
2018-03-01 17:36:19 +01:00
|
|
|
.bdrv_co_check = vhdx_co_check,
|
2019-07-24 19:12:36 +02:00
|
|
|
.bdrv_has_zero_init = vhdx_has_zero_init,
|
2013-10-30 15:44:53 +01:00
|
|
|
|
2020-05-13 13:05:12 +02:00
|
|
|
.is_format = true,
|
2014-06-05 11:21:08 +02:00
|
|
|
.create_opts = &vhdx_create_opts,
|
2013-04-29 20:48:18 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
static void bdrv_vhdx_init(void)
|
|
|
|
{
|
|
|
|
bdrv_register(&bdrv_vhdx);
|
|
|
|
}
|
|
|
|
|
|
|
|
block_init(bdrv_vhdx_init);
|