blob: ad04f5956547f7d2944a7ce56eb856e664ad8aaa [file] [log] [blame]
/*
* QEMU disk image utility
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <getopt.h>
#include "qemu-version.h"
#include "qapi/error.h"
#include "qapi/qapi-visit-block-core.h"
#include "qapi/qobject-output-visitor.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
#include "qemu/cutils.h"
#include "qemu/config-file.h"
#include "qemu/option.h"
#include "qemu/error-report.h"
#include "qemu/log.h"
#include "qom/object_interfaces.h"
#include "sysemu/sysemu.h"
#include "sysemu/block-backend.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/qapi.h"
#include "crypto/init.h"
#include "trace/control.h"
#define QEMU_IMG_VERSION "qemu-img version " QEMU_FULL_VERSION \
"\n" QEMU_COPYRIGHT "\n"
typedef struct img_cmd_t {
const char *name;
int (*handler)(int argc, char **argv);
} img_cmd_t;
enum {
OPTION_OUTPUT = 256,
OPTION_BACKING_CHAIN = 257,
OPTION_OBJECT = 258,
OPTION_IMAGE_OPTS = 259,
OPTION_PATTERN = 260,
OPTION_FLUSH_INTERVAL = 261,
OPTION_NO_DRAIN = 262,
OPTION_TARGET_IMAGE_OPTS = 263,
OPTION_SIZE = 264,
OPTION_PREALLOCATION = 265,
OPTION_SHRINK = 266,
};
typedef enum OutputFormat {
OFORMAT_JSON,
OFORMAT_HUMAN,
} OutputFormat;
/* Default to cache=writeback as data integrity is not important for qemu-img */
#define BDRV_DEFAULT_CACHE "writeback"
static void format_print(void *opaque, const char *name)
{
printf(" %s", name);
}
static void QEMU_NORETURN GCC_FMT_ATTR(1, 2) error_exit(const char *fmt, ...)
{
va_list ap;
error_printf("qemu-img: ");
va_start(ap, fmt);
error_vprintf(fmt, ap);
va_end(ap);
error_printf("\nTry 'qemu-img --help' for more information\n");
exit(EXIT_FAILURE);
}
static void QEMU_NORETURN missing_argument(const char *option)
{
error_exit("missing argument for option '%s'", option);
}
static void QEMU_NORETURN unrecognized_option(const char *option)
{
error_exit("unrecognized option '%s'", option);
}
/* Please keep in synch with qemu-img.texi */
static void QEMU_NORETURN help(void)
{
const char *help_msg =
QEMU_IMG_VERSION
"usage: qemu-img [standard options] command [command options]\n"
"QEMU disk image utility\n"
"\n"
" '-h', '--help' display this help and exit\n"
" '-V', '--version' output version information and exit\n"
" '-T', '--trace' [[enable=]<pattern>][,events=<file>][,file=<file>]\n"
" specify tracing options\n"
"\n"
"Command syntax:\n"
#define DEF(option, callback, arg_string) \
" " arg_string "\n"
#include "qemu-img-cmds.h"
#undef DEF
"\n"
"Command parameters:\n"
" 'filename' is a disk image filename\n"
" 'objectdef' is a QEMU user creatable object definition. See the qemu(1)\n"
" manual page for a description of the object properties. The most common\n"
" object type is a 'secret', which is used to supply passwords and/or\n"
" encryption keys.\n"
" 'fmt' is the disk image format. It is guessed automatically in most cases\n"
" 'cache' is the cache mode used to write the output disk image, the valid\n"
" options are: 'none', 'writeback' (default, except for convert), 'writethrough',\n"
" 'directsync' and 'unsafe' (default for convert)\n"
" 'src_cache' is the cache mode used to read input disk images, the valid\n"
" options are the same as for the 'cache' option\n"
" 'size' is the disk image size in bytes. Optional suffixes\n"
" 'k' or 'K' (kilobyte, 1024), 'M' (megabyte, 1024k), 'G' (gigabyte, 1024M),\n"
" 'T' (terabyte, 1024G), 'P' (petabyte, 1024T) and 'E' (exabyte, 1024P) are\n"
" supported. 'b' is ignored.\n"
" 'output_filename' is the destination disk image filename\n"
" 'output_fmt' is the destination format\n"
" 'options' is a comma separated list of format specific options in a\n"
" name=value format. Use -o ? for an overview of the options supported by the\n"
" used format\n"
" 'snapshot_param' is param used for internal snapshot, format\n"
" is 'snapshot.id=[ID],snapshot.name=[NAME]', or\n"
" '[ID_OR_NAME]'\n"
" '-c' indicates that target image must be compressed (qcow format only)\n"
" '-u' allows unsafe backing chains. For rebasing, it is assumed that old and\n"
" new backing file match exactly. The image doesn't need a working\n"
" backing file before rebasing in this case (useful for renaming the\n"
" backing file). For image creation, allow creating without attempting\n"
" to open the backing file.\n"
" '-h' with or without a command shows this help and lists the supported formats\n"
" '-p' show progress of command (only certain commands)\n"
" '-q' use Quiet mode - do not print any output (except errors)\n"
" '-S' indicates the consecutive number of bytes (defaults to 4k) that must\n"
" contain only zeros for qemu-img to create a sparse image during\n"
" conversion. If the number of bytes is 0, the source will not be scanned for\n"
" unallocated or zero sectors, and the destination image will always be\n"
" fully allocated\n"
" '--output' takes the format in which the output must be done (human or json)\n"
" '-n' skips the target volume creation (useful if the volume is created\n"
" prior to running qemu-img)\n"
"\n"
"Parameters to check subcommand:\n"
" '-r' tries to repair any inconsistencies that are found during the check.\n"
" '-r leaks' repairs only cluster leaks, whereas '-r all' fixes all\n"
" kinds of errors, with a higher risk of choosing the wrong fix or\n"
" hiding corruption that has already occurred.\n"
"\n"
"Parameters to convert subcommand:\n"
" '-m' specifies how many coroutines work in parallel during the convert\n"
" process (defaults to 8)\n"
" '-W' allow to write to the target out of order rather than sequential\n"
"\n"
"Parameters to snapshot subcommand:\n"
" 'snapshot' is the name of the snapshot to create, apply or delete\n"
" '-a' applies a snapshot (revert disk to saved state)\n"
" '-c' creates a snapshot\n"
" '-d' deletes a snapshot\n"
" '-l' lists all snapshots in the given image\n"
"\n"
"Parameters to compare subcommand:\n"
" '-f' first image format\n"
" '-F' second image format\n"
" '-s' run in Strict mode - fail on different image size or sector allocation\n"
"\n"
"Parameters to dd subcommand:\n"
" 'bs=BYTES' read and write up to BYTES bytes at a time "
"(default: 512)\n"
" 'count=N' copy only N input blocks\n"
" 'if=FILE' read from FILE\n"
" 'of=FILE' write to FILE\n"
" 'skip=N' skip N bs-sized blocks at the start of input\n";
printf("%s\nSupported formats:", help_msg);
bdrv_iterate_format(format_print, NULL);
printf("\n\n" QEMU_HELP_BOTTOM "\n");
exit(EXIT_SUCCESS);
}
static QemuOptsList qemu_object_opts = {
.name = "object",
.implied_opt_name = "qom-type",
.head = QTAILQ_HEAD_INITIALIZER(qemu_object_opts.head),
.desc = {
{ }
},
};
static QemuOptsList qemu_source_opts = {
.name = "source",
.implied_opt_name = "file",
.head = QTAILQ_HEAD_INITIALIZER(qemu_source_opts.head),
.desc = {
{ }
},
};
static int GCC_FMT_ATTR(2, 3) qprintf(bool quiet, const char *fmt, ...)
{
int ret = 0;
if (!quiet) {
va_list args;
va_start(args, fmt);
ret = vprintf(fmt, args);
va_end(args);
}
return ret;
}
static int print_block_option_help(const char *filename, const char *fmt)
{
BlockDriver *drv, *proto_drv;
QemuOptsList *create_opts = NULL;
Error *local_err = NULL;
/* Find driver and parse its options */
drv = bdrv_find_format(fmt);
if (!drv) {
error_report("Unknown file format '%s'", fmt);
return 1;
}
if (!drv->create_opts) {
error_report("Format driver '%s' does not support image creation", fmt);
return 1;
}
create_opts = qemu_opts_append(create_opts, drv->create_opts);
if (filename) {
proto_drv = bdrv_find_protocol(filename, true, &local_err);
if (!proto_drv) {
error_report_err(local_err);
qemu_opts_free(create_opts);
return 1;
}
if (!proto_drv->create_opts) {
error_report("Protocol driver '%s' does not support image creation",
proto_drv->format_name);
qemu_opts_free(create_opts);
return 1;
}
create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
}
printf("Supported options:\n");
qemu_opts_print_help(create_opts, false);
qemu_opts_free(create_opts);
return 0;
}
static BlockBackend *img_open_opts(const char *optstr,
QemuOpts *opts, int flags, bool writethrough,
bool quiet, bool force_share)
{
QDict *options;
Error *local_err = NULL;
BlockBackend *blk;
options = qemu_opts_to_qdict(opts, NULL);
if (force_share) {
if (qdict_haskey(options, BDRV_OPT_FORCE_SHARE)
&& strcmp(qdict_get_str(options, BDRV_OPT_FORCE_SHARE), "on")) {
error_report("--force-share/-U conflicts with image options");
qobject_unref(options);
return NULL;
}
qdict_put_str(options, BDRV_OPT_FORCE_SHARE, "on");
}
blk = blk_new_open(NULL, NULL, options, flags, &local_err);
if (!blk) {
error_reportf_err(local_err, "Could not open '%s': ", optstr);
return NULL;
}
blk_set_enable_write_cache(blk, !writethrough);
return blk;
}
static BlockBackend *img_open_file(const char *filename,
QDict *options,
const char *fmt, int flags,
bool writethrough, bool quiet,
bool force_share)
{
BlockBackend *blk;
Error *local_err = NULL;
if (!options) {
options = qdict_new();
}
if (fmt) {
qdict_put_str(options, "driver", fmt);
}
if (force_share) {
qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true);
}
blk = blk_new_open(filename, NULL, options, flags, &local_err);
if (!blk) {
error_reportf_err(local_err, "Could not open '%s': ", filename);
return NULL;
}
blk_set_enable_write_cache(blk, !writethrough);
return blk;
}
static int img_add_key_secrets(void *opaque,
const char *name, const char *value,
Error **errp)
{
QDict *options = opaque;
if (g_str_has_suffix(name, "key-secret")) {
qdict_put_str(options, name, value);
}
return 0;
}
static BlockBackend *img_open(bool image_opts,
const char *filename,
const char *fmt, int flags, bool writethrough,
bool quiet, bool force_share)
{
BlockBackend *blk;
if (image_opts) {
QemuOpts *opts;
if (fmt) {
error_report("--image-opts and --format are mutually exclusive");
return NULL;
}
opts = qemu_opts_parse_noisily(qemu_find_opts("source"),
filename, true);
if (!opts) {
return NULL;
}
blk = img_open_opts(filename, opts, flags, writethrough, quiet,
force_share);
} else {
blk = img_open_file(filename, NULL, fmt, flags, writethrough, quiet,
force_share);
}
return blk;
}
static int add_old_style_options(const char *fmt, QemuOpts *opts,
const char *base_filename,
const char *base_fmt)
{
Error *err = NULL;
if (base_filename) {
qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, base_filename, &err);
if (err) {
error_report("Backing file not supported for file format '%s'",
fmt);
error_free(err);
return -1;
}
}
if (base_fmt) {
qemu_opt_set(opts, BLOCK_OPT_BACKING_FMT, base_fmt, &err);
if (err) {
error_report("Backing file format not supported for file "
"format '%s'", fmt);
error_free(err);
return -1;
}
}
return 0;
}
static int64_t cvtnum(const char *s)
{
int err;
uint64_t value;
err = qemu_strtosz(s, NULL, &value);
if (err < 0) {
return err;
}
if (value > INT64_MAX) {
return -ERANGE;
}
return value;
}
static int img_create(int argc, char **argv)
{
int c;
uint64_t img_size = -1;
const char *fmt = "raw";
const char *base_fmt = NULL;
const char *filename;
const char *base_filename = NULL;
char *options = NULL;
Error *local_err = NULL;
bool quiet = false;
int flags = 0;
for(;;) {
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"object", required_argument, 0, OPTION_OBJECT},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":F:b:f:ho:qu",
long_options, NULL);
if (c == -1) {
break;
}
switch(c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'F':
base_fmt = optarg;
break;
case 'b':
base_filename = optarg;
break;
case 'f':
fmt = optarg;
break;
case 'o':
if (!is_valid_option_list(optarg)) {
error_report("Invalid option list: %s", optarg);
goto fail;
}
if (!options) {
options = g_strdup(optarg);
} else {
char *old_options = options;
options = g_strdup_printf("%s,%s", options, optarg);
g_free(old_options);
}
break;
case 'q':
quiet = true;
break;
case 'u':
flags |= BDRV_O_NO_BACKING;
break;
case OPTION_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
goto fail;
}
} break;
}
}
/* Get the filename */
filename = (optind < argc) ? argv[optind] : NULL;
if (options && has_help_option(options)) {
g_free(options);
return print_block_option_help(filename, fmt);
}
if (optind >= argc) {
error_exit("Expecting image file name");
}
optind++;
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
goto fail;
}
/* Get image size, if specified */
if (optind < argc) {
int64_t sval;
sval = cvtnum(argv[optind++]);
if (sval < 0) {
if (sval == -ERANGE) {
error_report("Image size must be less than 8 EiB!");
} else {
error_report("Invalid image size specified! You may use k, M, "
"G, T, P or E suffixes for ");
error_report("kilobytes, megabytes, gigabytes, terabytes, "
"petabytes and exabytes.");
}
goto fail;
}
img_size = (uint64_t)sval;
}
if (optind != argc) {
error_exit("Unexpected argument: %s", argv[optind]);
}
bdrv_img_create(filename, fmt, base_filename, base_fmt,
options, img_size, flags, quiet, &local_err);
if (local_err) {
error_reportf_err(local_err, "%s: ", filename);
goto fail;
}
g_free(options);
return 0;
fail:
g_free(options);
return 1;
}
static void dump_json_image_check(ImageCheck *check, bool quiet)
{
QString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
visit_type_ImageCheck(v, NULL, &check, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj);
assert(str != NULL);
qprintf(quiet, "%s\n", qstring_get_str(str));
qobject_unref(obj);
visit_free(v);
qobject_unref(str);
}
static void dump_human_image_check(ImageCheck *check, bool quiet)
{
if (!(check->corruptions || check->leaks || check->check_errors)) {
qprintf(quiet, "No errors were found on the image.\n");
} else {
if (check->corruptions) {
qprintf(quiet, "\n%" PRId64 " errors were found on the image.\n"
"Data may be corrupted, or further writes to the image "
"may corrupt it.\n",
check->corruptions);
}
if (check->leaks) {
qprintf(quiet,
"\n%" PRId64 " leaked clusters were found on the image.\n"
"This means waste of disk space, but no harm to data.\n",
check->leaks);
}
if (check->check_errors) {
qprintf(quiet,
"\n%" PRId64
" internal errors have occurred during the check.\n",
check->check_errors);
}
}
if (check->total_clusters != 0 && check->allocated_clusters != 0) {
qprintf(quiet, "%" PRId64 "/%" PRId64 " = %0.2f%% allocated, "
"%0.2f%% fragmented, %0.2f%% compressed clusters\n",
check->allocated_clusters, check->total_clusters,
check->allocated_clusters * 100.0 / check->total_clusters,
check->fragmented_clusters * 100.0 / check->allocated_clusters,
check->compressed_clusters * 100.0 /
check->allocated_clusters);
}
if (check->image_end_offset) {
qprintf(quiet,
"Image end offset: %" PRId64 "\n", check->image_end_offset);
}
}
static int collect_image_check(BlockDriverState *bs,
ImageCheck *check,
const char *filename,
const char *fmt,
int fix)
{
int ret;
BdrvCheckResult result;
ret = bdrv_check(bs, &result, fix);
if (ret < 0) {
return ret;
}
check->filename = g_strdup(filename);
check->format = g_strdup(bdrv_get_format_name(bs));
check->check_errors = result.check_errors;
check->corruptions = result.corruptions;
check->has_corruptions = result.corruptions != 0;
check->leaks = result.leaks;
check->has_leaks = result.leaks != 0;
check->corruptions_fixed = result.corruptions_fixed;
check->has_corruptions_fixed = result.corruptions != 0;
check->leaks_fixed = result.leaks_fixed;
check->has_leaks_fixed = result.leaks != 0;
check->image_end_offset = result.image_end_offset;
check->has_image_end_offset = result.image_end_offset != 0;
check->total_clusters = result.bfi.total_clusters;
check->has_total_clusters = result.bfi.total_clusters != 0;
check->allocated_clusters = result.bfi.allocated_clusters;
check->has_allocated_clusters = result.bfi.allocated_clusters != 0;
check->fragmented_clusters = result.bfi.fragmented_clusters;
check->has_fragmented_clusters = result.bfi.fragmented_clusters != 0;
check->compressed_clusters = result.bfi.compressed_clusters;
check->has_compressed_clusters = result.bfi.compressed_clusters != 0;
return 0;
}
/*
* Checks an image for consistency. Exit codes:
*
* 0 - Check completed, image is good
* 1 - Check not completed because of internal errors
* 2 - Check completed, image is corrupted
* 3 - Check completed, image has leaked clusters, but is good otherwise
* 63 - Checks are not supported by the image format
*/
static int img_check(int argc, char **argv)
{
int c, ret;
OutputFormat output_format = OFORMAT_HUMAN;
const char *filename, *fmt, *output, *cache;
BlockBackend *blk;
BlockDriverState *bs;
int fix = 0;
int flags = BDRV_O_CHECK;
bool writethrough;
ImageCheck *check;
bool quiet = false;
bool image_opts = false;
bool force_share = false;
fmt = NULL;
output = NULL;
cache = BDRV_DEFAULT_CACHE;
for(;;) {
int option_index = 0;
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"format", required_argument, 0, 'f'},
{"repair", required_argument, 0, 'r'},
{"output", required_argument, 0, OPTION_OUTPUT},
{"object", required_argument, 0, OPTION_OBJECT},
{"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
{"force-share", no_argument, 0, 'U'},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":hf:r:T:qU",
long_options, &option_index);
if (c == -1) {
break;
}
switch(c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'f':
fmt = optarg;
break;
case 'r':
flags |= BDRV_O_RDWR;
if (!strcmp(optarg, "leaks")) {
fix = BDRV_FIX_LEAKS;
} else if (!strcmp(optarg, "all")) {
fix = BDRV_FIX_LEAKS | BDRV_FIX_ERRORS;
} else {
error_exit("Unknown option value for -r "
"(expecting 'leaks' or 'all'): %s", optarg);
}
break;
case OPTION_OUTPUT:
output = optarg;
break;
case 'T':
cache = optarg;
break;
case 'q':
quiet = true;
break;
case 'U':
force_share = true;
break;
case OPTION_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
return 1;
}
} break;
case OPTION_IMAGE_OPTS:
image_opts = true;
break;
}
}
if (optind != argc - 1) {
error_exit("Expecting one image file name");
}
filename = argv[optind++];
if (output && !strcmp(output, "json")) {
output_format = OFORMAT_JSON;
} else if (output && !strcmp(output, "human")) {
output_format = OFORMAT_HUMAN;
} else if (output) {
error_report("--output must be used with human or json as argument.");
return 1;
}
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
return 1;
}
ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
if (ret < 0) {
error_report("Invalid source cache option: %s", cache);
return 1;
}
blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet,
force_share);
if (!blk) {
return 1;
}
bs = blk_bs(blk);
check = g_new0(ImageCheck, 1);
ret = collect_image_check(bs, check, filename, fmt, fix);
if (ret == -ENOTSUP) {
error_report("This image format does not support checks");
ret = 63;
goto fail;
}
if (check->corruptions_fixed || check->leaks_fixed) {
int corruptions_fixed, leaks_fixed;
leaks_fixed = check->leaks_fixed;
corruptions_fixed = check->corruptions_fixed;
if (output_format == OFORMAT_HUMAN) {
qprintf(quiet,
"The following inconsistencies were found and repaired:\n\n"
" %" PRId64 " leaked clusters\n"
" %" PRId64 " corruptions\n\n"
"Double checking the fixed image now...\n",
check->leaks_fixed,
check->corruptions_fixed);
}
ret = collect_image_check(bs, check, filename, fmt, 0);
check->leaks_fixed = leaks_fixed;
check->corruptions_fixed = corruptions_fixed;
}
if (!ret) {
switch (output_format) {
case OFORMAT_HUMAN:
dump_human_image_check(check, quiet);
break;
case OFORMAT_JSON:
dump_json_image_check(check, quiet);
break;
}
}
if (ret || check->check_errors) {
if (ret) {
error_report("Check failed: %s", strerror(-ret));
} else {
error_report("Check failed");
}
ret = 1;
goto fail;
}
if (check->corruptions) {
ret = 2;
} else if (check->leaks) {
ret = 3;
} else {
ret = 0;
}
fail:
qapi_free_ImageCheck(check);
blk_unref(blk);
return ret;
}
typedef struct CommonBlockJobCBInfo {
BlockDriverState *bs;
Error **errp;
} CommonBlockJobCBInfo;
static void common_block_job_cb(void *opaque, int ret)
{
CommonBlockJobCBInfo *cbi = opaque;
if (ret < 0) {
error_setg_errno(cbi->errp, -ret, "Block job failed");
}
}
static void run_block_job(BlockJob *job, Error **errp)
{
AioContext *aio_context = blk_get_aio_context(job->blk);
int ret = 0;
aio_context_acquire(aio_context);
job_ref(&job->job);
do {
float progress = 0.0f;
aio_poll(aio_context, true);
if (job->job.progress_total) {
progress = (float)job->job.progress_current /
job->job.progress_total * 100.f;
}
qemu_progress_print(progress, 0);
} while (!job_is_ready(&job->job) && !job_is_completed(&job->job));
if (!job_is_completed(&job->job)) {
ret = job_complete_sync(&job->job, errp);
} else {
ret = job->job.ret;
}
job_unref(&job->job);
aio_context_release(aio_context);
/* publish completion progress only when success */
if (!ret) {
qemu_progress_print(100.f, 0);
}
}
static int img_commit(int argc, char **argv)
{
int c, ret, flags;
const char *filename, *fmt, *cache, *base;
BlockBackend *blk;
BlockDriverState *bs, *base_bs;
BlockJob *job;
bool progress = false, quiet = false, drop = false;
bool writethrough;
Error *local_err = NULL;
CommonBlockJobCBInfo cbi;
bool image_opts = false;
AioContext *aio_context;
fmt = NULL;
cache = BDRV_DEFAULT_CACHE;
base = NULL;
for(;;) {
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"object", required_argument, 0, OPTION_OBJECT},
{"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":f:ht:b:dpq",
long_options, NULL);
if (c == -1) {
break;
}
switch(c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'f':
fmt = optarg;
break;
case 't':
cache = optarg;
break;
case 'b':
base = optarg;
/* -b implies -d */
drop = true;
break;
case 'd':
drop = true;
break;
case 'p':
progress = true;
break;
case 'q':
quiet = true;
break;
case OPTION_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
return 1;
}
} break;
case OPTION_IMAGE_OPTS:
image_opts = true;
break;
}
}
/* Progress is not shown in Quiet mode */
if (quiet) {
progress = false;
}
if (optind != argc - 1) {
error_exit("Expecting one image file name");
}
filename = argv[optind++];
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
return 1;
}
flags = BDRV_O_RDWR | BDRV_O_UNMAP;
ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
if (ret < 0) {
error_report("Invalid cache option: %s", cache);
return 1;
}
blk = img_open(image_opts, filename, fmt, flags, writethrough, quiet,
false);
if (!blk) {
return 1;
}
bs = blk_bs(blk);
qemu_progress_init(progress, 1.f);
qemu_progress_print(0.f, 100);
if (base) {
base_bs = bdrv_find_backing_image(bs, base);
if (!base_bs) {
error_setg(&local_err,
"Did not find '%s' in the backing chain of '%s'",
base, filename);
goto done;
}
} else {
/* This is different from QMP, which by default uses the deepest file in
* the backing chain (i.e., the very base); however, the traditional
* behavior of qemu-img commit is using the immediate backing file. */
base_bs = backing_bs(bs);
if (!base_bs) {
error_setg(&local_err, "Image does not have a backing file");
goto done;
}
}
cbi = (CommonBlockJobCBInfo){
.errp = &local_err,
.bs = bs,
};
aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
commit_active_start("commit", bs, base_bs, JOB_DEFAULT, 0,
BLOCKDEV_ON_ERROR_REPORT, NULL, common_block_job_cb,
&cbi, false, &local_err);
aio_context_release(aio_context);
if (local_err) {
goto done;
}
/* When the block job completes, the BlockBackend reference will point to
* the old backing file. In order to avoid that the top image is already
* deleted, so we can still empty it afterwards, increment the reference
* counter here preemptively. */
if (!drop) {
bdrv_ref(bs);
}
job = block_job_get("commit");
assert(job);
run_block_job(job, &local_err);
if (local_err) {
goto unref_backing;
}
if (!drop && bs->drv->bdrv_make_empty) {
ret = bs->drv->bdrv_make_empty(bs);
if (ret) {
error_setg_errno(&local_err, -ret, "Could not empty %s",
filename);
goto unref_backing;
}
}
unref_backing:
if (!drop) {
bdrv_unref(bs);
}
done:
qemu_progress_end();
blk_unref(blk);
if (local_err) {
error_report_err(local_err);
return 1;
}
qprintf(quiet, "Image committed.\n");
return 0;
}
/*
* Returns -1 if 'buf' contains only zeroes, otherwise the byte index
* of the first sector boundary within buf where the sector contains a
* non-zero byte. This function is robust to a buffer that is not
* sector-aligned.
*/
static int64_t find_nonzero(const uint8_t *buf, int64_t n)
{
int64_t i;
int64_t end = QEMU_ALIGN_DOWN(n, BDRV_SECTOR_SIZE);
for (i = 0; i < end; i += BDRV_SECTOR_SIZE) {
if (!buffer_is_zero(buf + i, BDRV_SECTOR_SIZE)) {
return i;
}
}
if (i < n && !buffer_is_zero(buf + i, n - end)) {
return i;
}
return -1;
}
/*
* Returns true iff the first sector pointed to by 'buf' contains at least
* a non-NUL byte.
*
* 'pnum' is set to the number of sectors (including and immediately following
* the first one) that are known to be in the same allocated/unallocated state.
* The function will try to align the end offset to alignment boundaries so
* that the request will at least end aligned and consequtive requests will
* also start at an aligned offset.
*/
static int is_allocated_sectors(const uint8_t *buf, int n, int *pnum,
int64_t sector_num, int alignment)
{
bool is_zero;
int i, tail;
if (n <= 0) {
*pnum = 0;
return 0;
}
is_zero = buffer_is_zero(buf, 512);
for(i = 1; i < n; i++) {
buf += 512;
if (is_zero != buffer_is_zero(buf, 512)) {
break;
}
}
tail = (sector_num + i) & (alignment - 1);
if (tail) {
if (is_zero && i <= tail) {
/* treat unallocated areas which only consist
* of a small tail as allocated. */
is_zero = false;
}
if (!is_zero) {
/* align up end offset of allocated areas. */
i += alignment - tail;
i = MIN(i, n);
} else {
/* align down end offset of zero areas. */
i -= tail;
}
}
*pnum = i;
return !is_zero;
}
/*
* Like is_allocated_sectors, but if the buffer starts with a used sector,
* up to 'min' consecutive sectors containing zeros are ignored. This avoids
* breaking up write requests for only small sparse areas.
*/
static int is_allocated_sectors_min(const uint8_t *buf, int n, int *pnum,
int min, int64_t sector_num, int alignment)
{
int ret;
int num_checked, num_used;
if (n < min) {
min = n;
}
ret = is_allocated_sectors(buf, n, pnum, sector_num, alignment);
if (!ret) {
return ret;
}
num_used = *pnum;
buf += BDRV_SECTOR_SIZE * *pnum;
n -= *pnum;
sector_num += *pnum;
num_checked = num_used;
while (n > 0) {
ret = is_allocated_sectors(buf, n, pnum, sector_num, alignment);
buf += BDRV_SECTOR_SIZE * *pnum;
n -= *pnum;
sector_num += *pnum;
num_checked += *pnum;
if (ret) {
num_used = num_checked;
} else if (*pnum >= min) {
break;
}
}
*pnum = num_used;
return 1;
}
/*
* Compares two buffers sector by sector. Returns 0 if the first
* sector of each buffer matches, non-zero otherwise.
*
* pnum is set to the sector-aligned size of the buffer prefix that
* has the same matching status as the first sector.
*/
static int compare_buffers(const uint8_t *buf1, const uint8_t *buf2,
int64_t bytes, int64_t *pnum)
{
bool res;
int64_t i = MIN(bytes, BDRV_SECTOR_SIZE);
assert(bytes > 0);
res = !!memcmp(buf1, buf2, i);
while (i < bytes) {
int64_t len = MIN(bytes - i, BDRV_SECTOR_SIZE);
if (!!memcmp(buf1 + i, buf2 + i, len) != res) {
break;
}
i += len;
}
*pnum = i;
return res;
}
#define IO_BUF_SIZE (2 * 1024 * 1024)
/*
* Check if passed sectors are empty (not allocated or contain only 0 bytes)
*
* Intended for use by 'qemu-img compare': Returns 0 in case sectors are
* filled with 0, 1 if sectors contain non-zero data (this is a comparison
* failure), and 4 on error (the exit status for read errors), after emitting
* an error message.
*
* @param blk: BlockBackend for the image
* @param offset: Starting offset to check
* @param bytes: Number of bytes to check
* @param filename: Name of disk file we are checking (logging purpose)
* @param buffer: Allocated buffer for storing read data
* @param quiet: Flag for quiet mode
*/
static int check_empty_sectors(BlockBackend *blk, int64_t offset,
int64_t bytes, const char *filename,
uint8_t *buffer, bool quiet)
{
int ret = 0;
int64_t idx;
ret = blk_pread(blk, offset, buffer, bytes);
if (ret < 0) {
error_report("Error while reading offset %" PRId64 " of %s: %s",
offset, filename, strerror(-ret));
return 4;
}
idx = find_nonzero(buffer, bytes);
if (idx >= 0) {
qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
offset + idx);
return 1;
}
return 0;
}
/*
* Compares two images. Exit codes:
*
* 0 - Images are identical
* 1 - Images differ
* >1 - Error occurred
*/
static int img_compare(int argc, char **argv)
{
const char *fmt1 = NULL, *fmt2 = NULL, *cache, *filename1, *filename2;
BlockBackend *blk1, *blk2;
BlockDriverState *bs1, *bs2;
int64_t total_size1, total_size2;
uint8_t *buf1 = NULL, *buf2 = NULL;
int64_t pnum1, pnum2;
int allocated1, allocated2;
int ret = 0; /* return value - 0 Ident, 1 Different, >1 Error */
bool progress = false, quiet = false, strict = false;
int flags;
bool writethrough;
int64_t total_size;
int64_t offset = 0;
int64_t chunk;
int c;
uint64_t progress_base;
bool image_opts = false;
bool force_share = false;
cache = BDRV_DEFAULT_CACHE;
for (;;) {
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"object", required_argument, 0, OPTION_OBJECT},
{"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
{"force-share", no_argument, 0, 'U'},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":hf:F:T:pqsU",
long_options, NULL);
if (c == -1) {
break;
}
switch (c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'f':
fmt1 = optarg;
break;
case 'F':
fmt2 = optarg;
break;
case 'T':
cache = optarg;
break;
case 'p':
progress = true;
break;
case 'q':
quiet = true;
break;
case 's':
strict = true;
break;
case 'U':
force_share = true;
break;
case OPTION_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
ret = 2;
goto out4;
}
} break;
case OPTION_IMAGE_OPTS:
image_opts = true;
break;
}
}
/* Progress is not shown in Quiet mode */
if (quiet) {
progress = false;
}
if (optind != argc - 2) {
error_exit("Expecting two image file names");
}
filename1 = argv[optind++];
filename2 = argv[optind++];
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
ret = 2;
goto out4;
}
/* Initialize before goto out */
qemu_progress_init(progress, 2.0);
flags = 0;
ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
if (ret < 0) {
error_report("Invalid source cache option: %s", cache);
ret = 2;
goto out3;
}
blk1 = img_open(image_opts, filename1, fmt1, flags, writethrough, quiet,
force_share);
if (!blk1) {
ret = 2;
goto out3;
}
blk2 = img_open(image_opts, filename2, fmt2, flags, writethrough, quiet,
force_share);
if (!blk2) {
ret = 2;
goto out2;
}
bs1 = blk_bs(blk1);
bs2 = blk_bs(blk2);
buf1 = blk_blockalign(blk1, IO_BUF_SIZE);
buf2 = blk_blockalign(blk2, IO_BUF_SIZE);
total_size1 = blk_getlength(blk1);
if (total_size1 < 0) {
error_report("Can't get size of %s: %s",
filename1, strerror(-total_size1));
ret = 4;
goto out;
}
total_size2 = blk_getlength(blk2);
if (total_size2 < 0) {
error_report("Can't get size of %s: %s",
filename2, strerror(-total_size2));
ret = 4;
goto out;
}
total_size = MIN(total_size1, total_size2);
progress_base = MAX(total_size1, total_size2);
qemu_progress_print(0, 100);
if (strict && total_size1 != total_size2) {
ret = 1;
qprintf(quiet, "Strict mode: Image size mismatch!\n");
goto out;
}
while (offset < total_size) {
int status1, status2;
status1 = bdrv_block_status_above(bs1, NULL, offset,
total_size1 - offset, &pnum1, NULL,
NULL);
if (status1 < 0) {
ret = 3;
error_report("Sector allocation test failed for %s", filename1);
goto out;
}
allocated1 = status1 & BDRV_BLOCK_ALLOCATED;
status2 = bdrv_block_status_above(bs2, NULL, offset,
total_size2 - offset, &pnum2, NULL,
NULL);
if (status2 < 0) {
ret = 3;
error_report("Sector allocation test failed for %s", filename2);
goto out;
}
allocated2 = status2 & BDRV_BLOCK_ALLOCATED;
assert(pnum1 && pnum2);
chunk = MIN(pnum1, pnum2);
if (strict) {
if (status1 != status2) {
ret = 1;
qprintf(quiet, "Strict mode: Offset %" PRId64
" block status mismatch!\n", offset);
goto out;
}
}
if ((status1 & BDRV_BLOCK_ZERO) && (status2 & BDRV_BLOCK_ZERO)) {
/* nothing to do */
} else if (allocated1 == allocated2) {
if (allocated1) {
int64_t pnum;
chunk = MIN(chunk, IO_BUF_SIZE);
ret = blk_pread(blk1, offset, buf1, chunk);
if (ret < 0) {
error_report("Error while reading offset %" PRId64
" of %s: %s",
offset, filename1, strerror(-ret));
ret = 4;
goto out;
}
ret = blk_pread(blk2, offset, buf2, chunk);
if (ret < 0) {
error_report("Error while reading offset %" PRId64
" of %s: %s",
offset, filename2, strerror(-ret));
ret = 4;
goto out;
}
ret = compare_buffers(buf1, buf2, chunk, &pnum);
if (ret || pnum != chunk) {
qprintf(quiet, "Content mismatch at offset %" PRId64 "!\n",
offset + (ret ? 0 : pnum));
ret = 1;
goto out;
}
}
} else {
chunk = MIN(chunk, IO_BUF_SIZE);
if (allocated1) {
ret = check_empty_sectors(blk1, offset, chunk,
filename1, buf1, quiet);
} else {
ret = check_empty_sectors(blk2, offset, chunk,
filename2, buf1, quiet);
}
if (ret) {
goto out;
}
}
offset += chunk;
qemu_progress_print(((float) chunk / progress_base) * 100, 100);
}
if (total_size1 != total_size2) {
BlockBackend *blk_over;
const char *filename_over;
qprintf(quiet, "Warning: Image size mismatch!\n");
if (total_size1 > total_size2) {
blk_over = blk1;
filename_over = filename1;
} else {
blk_over = blk2;
filename_over = filename2;
}
while (offset < progress_base) {
ret = bdrv_block_status_above(blk_bs(blk_over), NULL, offset,
progress_base - offset, &chunk,
NULL, NULL);
if (ret < 0) {
ret = 3;
error_report("Sector allocation test failed for %s",
filename_over);
goto out;
}
if (ret & BDRV_BLOCK_ALLOCATED && !(ret & BDRV_BLOCK_ZERO)) {
chunk = MIN(chunk, IO_BUF_SIZE);
ret = check_empty_sectors(blk_over, offset, chunk,
filename_over, buf1, quiet);
if (ret) {
goto out;
}
}
offset += chunk;
qemu_progress_print(((float) chunk / progress_base) * 100, 100);
}
}
qprintf(quiet, "Images are identical.\n");
ret = 0;
out:
qemu_vfree(buf1);
qemu_vfree(buf2);
blk_unref(blk2);
out2:
blk_unref(blk1);
out3:
qemu_progress_end();
out4:
return ret;
}
enum ImgConvertBlockStatus {
BLK_DATA,
BLK_ZERO,
BLK_BACKING_FILE,
};
#define MAX_COROUTINES 16
typedef struct ImgConvertState {
BlockBackend **src;
int64_t *src_sectors;
int src_num;
int64_t total_sectors;
int64_t allocated_sectors;
int64_t allocated_done;
int64_t sector_num;
int64_t wr_offs;
enum ImgConvertBlockStatus status;
int64_t sector_next_status;
BlockBackend *target;
bool has_zero_init;
bool compressed;
bool unallocated_blocks_are_zero;
bool target_has_backing;
int64_t target_backing_sectors; /* negative if unknown */
bool wr_in_order;
bool copy_range;
int min_sparse;
int alignment;
size_t cluster_sectors;
size_t buf_sectors;
long num_coroutines;
int running_coroutines;
Coroutine *co[MAX_COROUTINES];
int64_t wait_sector_num[MAX_COROUTINES];
CoMutex lock;
int ret;
} ImgConvertState;
static void convert_select_part(ImgConvertState *s, int64_t sector_num,
int *src_cur, int64_t *src_cur_offset)
{
*src_cur = 0;
*src_cur_offset = 0;
while (sector_num - *src_cur_offset >= s->src_sectors[*src_cur]) {
*src_cur_offset += s->src_sectors[*src_cur];
(*src_cur)++;
assert(*src_cur < s->src_num);
}
}
static int convert_iteration_sectors(ImgConvertState *s, int64_t sector_num)
{
int64_t src_cur_offset;
int ret, n, src_cur;
bool post_backing_zero = false;
convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
assert(s->total_sectors > sector_num);
n = MIN(s->total_sectors - sector_num, BDRV_REQUEST_MAX_SECTORS);
if (s->target_backing_sectors >= 0) {
if (sector_num >= s->target_backing_sectors) {
post_backing_zero = s->unallocated_blocks_are_zero;
} else if (sector_num + n > s->target_backing_sectors) {
/* Split requests around target_backing_sectors (because
* starting from there, zeros are handled differently) */
n = s->target_backing_sectors - sector_num;
}
}
if (s->sector_next_status <= sector_num) {
int64_t count = n * BDRV_SECTOR_SIZE;
if (s->target_has_backing) {
ret = bdrv_block_status(blk_bs(s->src[src_cur]),
(sector_num - src_cur_offset) *
BDRV_SECTOR_SIZE,
count, &count, NULL, NULL);
} else {
ret = bdrv_block_status_above(blk_bs(s->src[src_cur]), NULL,
(sector_num - src_cur_offset) *
BDRV_SECTOR_SIZE,
count, &count, NULL, NULL);
}
if (ret < 0) {
return ret;
}
n = DIV_ROUND_UP(count, BDRV_SECTOR_SIZE);
if (ret & BDRV_BLOCK_ZERO) {
s->status = post_backing_zero ? BLK_BACKING_FILE : BLK_ZERO;
} else if (ret & BDRV_BLOCK_DATA) {
s->status = BLK_DATA;
} else {
s->status = s->target_has_backing ? BLK_BACKING_FILE : BLK_DATA;
}
s->sector_next_status = sector_num + n;
}
n = MIN(n, s->sector_next_status - sector_num);
if (s->status == BLK_DATA) {
n = MIN(n, s->buf_sectors);
}
/* We need to write complete clusters for compressed images, so if an
* unallocated area is shorter than that, we must consider the whole
* cluster allocated. */
if (s->compressed) {
if (n < s->cluster_sectors) {
n = MIN(s->cluster_sectors, s->total_sectors - sector_num);
s->status = BLK_DATA;
} else {
n = QEMU_ALIGN_DOWN(n, s->cluster_sectors);
}
}
return n;
}
static int coroutine_fn convert_co_read(ImgConvertState *s, int64_t sector_num,
int nb_sectors, uint8_t *buf)
{
int n, ret;
QEMUIOVector qiov;
struct iovec iov;
assert(nb_sectors <= s->buf_sectors);
while (nb_sectors > 0) {
BlockBackend *blk;
int src_cur;
int64_t bs_sectors, src_cur_offset;
/* In the case of compression with multiple source files, we can get a
* nb_sectors that spreads into the next part. So we must be able to
* read across multiple BDSes for one convert_read() call. */
convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
blk = s->src[src_cur];
bs_sectors = s->src_sectors[src_cur];
n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
iov.iov_base = buf;
iov.iov_len = n << BDRV_SECTOR_BITS;
qemu_iovec_init_external(&qiov, &iov, 1);
ret = blk_co_preadv(
blk, (sector_num - src_cur_offset) << BDRV_SECTOR_BITS,
n << BDRV_SECTOR_BITS, &qiov, 0);
if (ret < 0) {
return ret;
}
sector_num += n;
nb_sectors -= n;
buf += n * BDRV_SECTOR_SIZE;
}
return 0;
}
static int coroutine_fn convert_co_write(ImgConvertState *s, int64_t sector_num,
int nb_sectors, uint8_t *buf,
enum ImgConvertBlockStatus status)
{
int ret;
QEMUIOVector qiov;
struct iovec iov;
while (nb_sectors > 0) {
int n = nb_sectors;
BdrvRequestFlags flags = s->compressed ? BDRV_REQ_WRITE_COMPRESSED : 0;
switch (status) {
case BLK_BACKING_FILE:
/* If we have a backing file, leave clusters unallocated that are
* unallocated in the source image, so that the backing file is
* visible at the respective offset. */
assert(s->target_has_backing);
break;
case BLK_DATA:
/* If we're told to keep the target fully allocated (-S 0) or there
* is real non-zero data, we must write it. Otherwise we can treat
* it as zero sectors.
* Compressed clusters need to be written as a whole, so in that
* case we can only save the write if the buffer is completely
* zeroed. */
if (!s->min_sparse ||
(!s->compressed &&
is_allocated_sectors_min(buf, n, &n, s->min_sparse,
sector_num, s->alignment)) ||
(s->compressed &&
!buffer_is_zero(buf, n * BDRV_SECTOR_SIZE)))
{
iov.iov_base = buf;
iov.iov_len = n << BDRV_SECTOR_BITS;
qemu_iovec_init_external(&qiov, &iov, 1);
ret = blk_co_pwritev(s->target, sector_num << BDRV_SECTOR_BITS,
n << BDRV_SECTOR_BITS, &qiov, flags);
if (ret < 0) {
return ret;
}
break;
}
/* fall-through */
case BLK_ZERO:
if (s->has_zero_init) {
assert(!s->target_has_backing);
break;
}
ret = blk_co_pwrite_zeroes(s->target,
sector_num << BDRV_SECTOR_BITS,
n << BDRV_SECTOR_BITS, 0);
if (ret < 0) {
return ret;
}
break;
}
sector_num += n;
nb_sectors -= n;
buf += n * BDRV_SECTOR_SIZE;
}
return 0;
}
static int coroutine_fn convert_co_copy_range(ImgConvertState *s, int64_t sector_num,
int nb_sectors)
{
int n, ret;
while (nb_sectors > 0) {
BlockBackend *blk;
int src_cur;
int64_t bs_sectors, src_cur_offset;
int64_t offset;
convert_select_part(s, sector_num, &src_cur, &src_cur_offset);
offset = (sector_num - src_cur_offset) << BDRV_SECTOR_BITS;
blk = s->src[src_cur];
bs_sectors = s->src_sectors[src_cur];
n = MIN(nb_sectors, bs_sectors - (sector_num - src_cur_offset));
ret = blk_co_copy_range(blk, offset, s->target,
sector_num << BDRV_SECTOR_BITS,
n << BDRV_SECTOR_BITS, 0, 0);
if (ret < 0) {
return ret;
}
sector_num += n;
nb_sectors -= n;
}
return 0;
}
static void coroutine_fn convert_co_do_copy(void *opaque)
{
ImgConvertState *s = opaque;
uint8_t *buf = NULL;
int ret, i;
int index = -1;
for (i = 0; i < s->num_coroutines; i++) {
if (s->co[i] == qemu_coroutine_self()) {
index = i;
break;
}
}
assert(index >= 0);
s->running_coroutines++;
buf = blk_blockalign(s->target, s->buf_sectors * BDRV_SECTOR_SIZE);
while (1) {
int n;
int64_t sector_num;
enum ImgConvertBlockStatus status;
bool copy_range;
qemu_co_mutex_lock(&s->lock);
if (s->ret != -EINPROGRESS || s->sector_num >= s->total_sectors) {
qemu_co_mutex_unlock(&s->lock);
break;
}
n = convert_iteration_sectors(s, s->sector_num);
if (n < 0) {
qemu_co_mutex_unlock(&s->lock);
s->ret = n;
break;
}
/* save current sector and allocation status to local variables */
sector_num = s->sector_num;
status = s->status;
if (!s->min_sparse && s->status == BLK_ZERO) {
n = MIN(n, s->buf_sectors);
}
/* increment global sector counter so that other coroutines can
* already continue reading beyond this request */
s->sector_num += n;
qemu_co_mutex_unlock(&s->lock);
if (status == BLK_DATA || (!s->min_sparse && status == BLK_ZERO)) {
s->allocated_done += n;
qemu_progress_print(100.0 * s->allocated_done /
s->allocated_sectors, 0);
}
retry:
copy_range = s->copy_range && s->status == BLK_DATA;
if (status == BLK_DATA && !copy_range) {
ret = convert_co_read(s, sector_num, n, buf);
if (ret < 0) {
error_report("error while reading sector %" PRId64
": %s", sector_num, strerror(-ret));
s->ret = ret;
}
} else if (!s->min_sparse && status == BLK_ZERO) {
status = BLK_DATA;
memset(buf, 0x00, n * BDRV_SECTOR_SIZE);
}
if (s->wr_in_order) {
/* keep writes in order */
while (s->wr_offs != sector_num && s->ret == -EINPROGRESS) {
s->wait_sector_num[index] = sector_num;
qemu_coroutine_yield();
}
s->wait_sector_num[index] = -1;
}
if (s->ret == -EINPROGRESS) {
if (copy_range) {
ret = convert_co_copy_range(s, sector_num, n);
if (ret) {
s->copy_range = false;
goto retry;
}
} else {
ret = convert_co_write(s, sector_num, n, buf, status);
}
if (ret < 0) {
error_report("error while writing sector %" PRId64
": %s", sector_num, strerror(-ret));
s->ret = ret;
}
}
if (s->wr_in_order) {
/* reenter the coroutine that might have waited
* for this write to complete */
s->wr_offs = sector_num + n;
for (i = 0; i < s->num_coroutines; i++) {
if (s->co[i] && s->wait_sector_num[i] == s->wr_offs) {
/*
* A -> B -> A cannot occur because A has
* s->wait_sector_num[i] == -1 during A -> B. Therefore
* B will never enter A during this time window.
*/
qemu_coroutine_enter(s->co[i]);
break;
}
}
}
}
qemu_vfree(buf);
s->co[index] = NULL;
s->running_coroutines--;
if (!s->running_coroutines && s->ret == -EINPROGRESS) {
/* the convert job finished successfully */
s->ret = 0;
}
}
static int convert_do_copy(ImgConvertState *s)
{
int ret, i, n;
int64_t sector_num = 0;
/* Check whether we have zero initialisation or can get it efficiently */
s->has_zero_init = s->min_sparse && !s->target_has_backing
? bdrv_has_zero_init(blk_bs(s->target))
: false;
if (!s->has_zero_init && !s->target_has_backing &&
bdrv_can_write_zeroes_with_unmap(blk_bs(s->target)))
{
ret = blk_make_zero(s->target, BDRV_REQ_MAY_UNMAP);
if (ret == 0) {
s->has_zero_init = true;
}
}
/* Allocate buffer for copied data. For compressed images, only one cluster
* can be copied at a time. */
if (s->compressed) {
if (s->cluster_sectors <= 0 || s->cluster_sectors > s->buf_sectors) {
error_report("invalid cluster size");
return -EINVAL;
}
s->buf_sectors = s->cluster_sectors;
}
while (sector_num < s->total_sectors) {
n = convert_iteration_sectors(s, sector_num);
if (n < 0) {
return n;
}
if (s->status == BLK_DATA || (!s->min_sparse && s->status == BLK_ZERO))
{
s->allocated_sectors += n;
}
sector_num += n;
}
/* Do the copy */
s->sector_next_status = 0;
s->ret = -EINPROGRESS;
qemu_co_mutex_init(&s->lock);
for (i = 0; i < s->num_coroutines; i++) {
s->co[i] = qemu_coroutine_create(convert_co_do_copy, s);
s->wait_sector_num[i] = -1;
qemu_coroutine_enter(s->co[i]);
}
while (s->running_coroutines) {
main_loop_wait(false);
}
if (s->compressed && !s->ret) {
/* signal EOF to align */
ret = blk_pwrite_compressed(s->target, 0, NULL, 0);
if (ret < 0) {
return ret;
}
}
return s->ret;
}
#define MAX_BUF_SECTORS 32768
static int img_convert(int argc, char **argv)
{
int c, bs_i, flags, src_flags = 0;
const char *fmt = NULL, *out_fmt = NULL, *cache = "unsafe",
*src_cache = BDRV_DEFAULT_CACHE, *out_baseimg = NULL,
*out_filename, *out_baseimg_param, *snapshot_name = NULL;
BlockDriver *drv = NULL, *proto_drv = NULL;
BlockDriverInfo bdi;
BlockDriverState *out_bs;
QemuOpts *opts = NULL, *sn_opts = NULL;
QemuOptsList *create_opts = NULL;
QDict *open_opts = NULL;
char *options = NULL;
Error *local_err = NULL;
bool writethrough, src_writethrough, quiet = false, image_opts = false,
skip_create = false, progress = false, tgt_image_opts = false;
int64_t ret = -EINVAL;
bool force_share = false;
bool explict_min_sparse = false;
ImgConvertState s = (ImgConvertState) {
/* Need at least 4k of zeros for sparse detection */
.min_sparse = 8,
.copy_range = false,
.buf_sectors = IO_BUF_SIZE / BDRV_SECTOR_SIZE,
.wr_in_order = true,
.num_coroutines = 8,
};
for(;;) {
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"object", required_argument, 0, OPTION_OBJECT},
{"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
{"force-share", no_argument, 0, 'U'},
{"target-image-opts", no_argument, 0, OPTION_TARGET_IMAGE_OPTS},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":hf:O:B:Cco:l:S:pt:T:qnm:WU",
long_options, NULL);
if (c == -1) {
break;
}
switch(c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'f':
fmt = optarg;
break;
case 'O':
out_fmt = optarg;
break;
case 'B':
out_baseimg = optarg;
break;
case 'C':
s.copy_range = true;
break;
case 'c':
s.compressed = true;
break;
case 'o':
if (!is_valid_option_list(optarg)) {
error_report("Invalid option list: %s", optarg);
goto fail_getopt;
}
if (!options) {
options = g_strdup(optarg);
} else {
char *old_options = options;
options = g_strdup_printf("%s,%s", options, optarg);
g_free(old_options);
}
break;
case 'l':
if (strstart(optarg, SNAPSHOT_OPT_BASE, NULL)) {
sn_opts = qemu_opts_parse_noisily(&internal_snapshot_opts,
optarg, false);
if (!sn_opts) {
error_report("Failed in parsing snapshot param '%s'",
optarg);
goto fail_getopt;
}
} else {
snapshot_name = optarg;
}
break;
case 'S':
{
int64_t sval;
sval = cvtnum(optarg);
if (sval < 0 || sval & (BDRV_SECTOR_SIZE - 1) ||
sval / BDRV_SECTOR_SIZE > MAX_BUF_SECTORS) {
error_report("Invalid buffer size for sparse output specified. "
"Valid sizes are multiples of %llu up to %llu. Select "
"0 to disable sparse detection (fully allocates output).",
BDRV_SECTOR_SIZE, MAX_BUF_SECTORS * BDRV_SECTOR_SIZE);
goto fail_getopt;
}
s.min_sparse = sval / BDRV_SECTOR_SIZE;
explict_min_sparse = true;
break;
}
case 'p':
progress = true;
break;
case 't':
cache = optarg;
break;
case 'T':
src_cache = optarg;
break;
case 'q':
quiet = true;
break;
case 'n':
skip_create = true;
break;
case 'm':
if (qemu_strtol(optarg, NULL, 0, &s.num_coroutines) ||
s.num_coroutines < 1 || s.num_coroutines > MAX_COROUTINES) {
error_report("Invalid number of coroutines. Allowed number of"
" coroutines is between 1 and %d", MAX_COROUTINES);
goto fail_getopt;
}
break;
case 'W':
s.wr_in_order = false;
break;
case 'U':
force_share = true;
break;
case OPTION_OBJECT: {
QemuOpts *object_opts;
object_opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!object_opts) {
goto fail_getopt;
}
break;
}
case OPTION_IMAGE_OPTS:
image_opts = true;
break;
case OPTION_TARGET_IMAGE_OPTS:
tgt_image_opts = true;
break;
}
}
if (!out_fmt && !tgt_image_opts) {
out_fmt = "raw";
}
if (qemu_opts_foreach(&qemu_object_opts,
user_creatable_add_opts_foreach,
NULL, NULL)) {
goto fail_getopt;
}
if (s.compressed && s.copy_range) {
error_report("Cannot enable copy offloading when -c is used");
goto fail_getopt;
}
if (explict_min_sparse && s.copy_range) {
error_report("Cannot enable copy offloading when -S is used");
goto fail_getopt;
}
if (tgt_image_opts && !skip_create) {
error_report("--target-image-opts requires use of -n flag");
goto fail_getopt;
}
s.src_num = argc - optind - 1;
out_filename = s.src_num >= 1 ? argv[argc - 1] : NULL;
if (options && has_help_option(options)) {
if (out_fmt) {
ret = print_block_option_help(out_filename, out_fmt);
goto fail_getopt;
} else {
error_report("Option help requires a format be specified");
goto fail_getopt;
}
}
if (s.src_num < 1) {
error_report("Must specify image file name");
goto fail_getopt;
}
/* ret is still -EINVAL until here */
ret = bdrv_parse_cache_mode(src_cache, &src_flags, &src_writethrough);
if (ret < 0) {
error_report("Invalid source cache option: %s", src_cache);
goto fail_getopt;
}
/* Initialize before goto out */
if (quiet) {
progress = false;
}
qemu_progress_init(progress, 1.0);
qemu_progress_print(0, 100);
s.src = g_new0(BlockBackend *, s.src_num);
s.src_sectors = g_new(int64_t, s.src_num);
for (bs_i = 0; bs_i < s.src_num; bs_i++) {
s.src[bs_i] = img_open(image_opts, argv[optind + bs_i],
fmt, src_flags, src_writethrough, quiet,
force_share);
if (!s.src[bs_i]) {
ret = -1;
goto out;
}
s.src_sectors[bs_i] = blk_nb_sectors(s.src[bs_i]);
if (s.src_sectors[bs_i] < 0) {
error_report("Could not get size of %s: %s",
argv[optind + bs_i], strerror(-s.src_sectors[bs_i]));
ret = -1;
goto out;
}
s.total_sectors += s.src_sectors[bs_i];
}
if (sn_opts) {
bdrv_snapshot_load_tmp(blk_bs(s.src[0]),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_ID),
qemu_opt_get(sn_opts, SNAPSHOT_OPT_NAME),
&local_err);
} else if (snapshot_name != NULL) {
if (s.src_num > 1) {
error_report("No support for concatenating multiple snapshot");
ret = -1;
goto out;
}
bdrv_snapshot_load_tmp_by_id_or_name(blk_bs(s.src[0]), snapshot_name,
&local_err);
}
if (local_err) {
error_reportf_err(local_err, "Failed to load snapshot: ");
ret = -1;
goto out;
}
if (!skip_create) {
/* Find driver and parse its options */
drv = bdrv_find_format(out_fmt);
if (!drv) {
error_report("Unknown file format '%s'", out_fmt);
ret = -1;
goto out;
}
proto_drv = bdrv_find_protocol(out_filename, true, &local_err);
if (!proto_drv) {
error_report_err(local_err);
ret = -1;
goto out;
}
if (!drv->create_opts) {
error_report("Format driver '%s' does not support image creation",
drv->format_name);
ret = -1;
goto out;
}
if (!proto_drv->create_opts) {
error_report("Protocol driver '%s' does not support image creation",
proto_drv->format_name);
ret = -1;
goto out;
}
create_opts = qemu_opts_append(create_opts, drv->create_opts);
create_opts = qemu_opts_append(create_opts, proto_drv->create_opts);
opts = qemu_opts_create(create_opts, NULL, 0, &error_abort);
if (options) {
qemu_opts_do_parse(opts, options, NULL, &local_err);
if (local_err) {
error_report_err(local_err);
ret = -1;
goto out;
}
}
qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s.total_sectors * 512,
&error_abort);
ret = add_old_style_options(out_fmt, opts, out_baseimg, NULL);
if (ret < 0) {
goto out;
}
}
/* Get backing file name if -o backing_file was used */
out_baseimg_param = qemu_opt_get(opts, BLOCK_OPT_BACKING_FILE);
if (out_baseimg_param) {
out_baseimg = out_baseimg_param;
}
s.target_has_backing = (bool) out_baseimg;
if (s.src_num > 1 && out_baseimg) {
error_report("Having a backing file for the target makes no sense when "
"concatenating multiple input images");
ret = -1;
goto out;
}
/* Check if compression is supported */
if (s.compressed) {
bool encryption =
qemu_opt_get_bool(opts, BLOCK_OPT_ENCRYPT, false);
const char *encryptfmt =
qemu_opt_get(opts, BLOCK_OPT_ENCRYPT_FORMAT);
const char *preallocation =
qemu_opt_get(opts, BLOCK_OPT_PREALLOC);
if (drv && !drv->bdrv_co_pwritev_compressed) {
error_report("Compression not supported for this file format");
ret = -1;
goto out;
}
if (encryption || encryptfmt) {
error_report("Compression and encryption not supported at "
"the same time");
ret = -1;
goto out;
}
if (preallocation
&& strcmp(preallocation, "off"))
{
error_report("Compression and preallocation not supported at "
"the same time");
ret = -1;
goto out;
}
}
/*
* The later open call will need any decryption secrets, and
* bdrv_create() will purge "opts", so extract them now before
* they are lost.
*/
if (!skip_create) {
open_opts = qdict_new();
qemu_opt_foreach(opts, img_add_key_secrets, open_opts, &error_abort);
}
if (!skip_create) {
/* Create the new image */
ret = bdrv_create(drv, out_filename, opts, &local_err);
if (ret < 0) {
error_reportf_err(local_err, "%s: error while converting %s: ",
out_filename, out_fmt);
goto out;
}
}
flags = s.min_sparse ? (BDRV_O_RDWR | BDRV_O_UNMAP) : BDRV_O_RDWR;
ret = bdrv_parse_cache_mode(cache, &flags, &writethrough);
if (ret < 0) {
error_report("Invalid cache option: %s", cache);
goto out;
}
if (skip_create) {
s.target = img_open(tgt_image_opts, out_filename, out_fmt,
flags, writethrough, quiet, false);
} else {
/* TODO ultimately we should allow --target-image-opts
* to be used even when -n is not given.
* That has to wait for bdrv_create to be improved
* to allow filenames in option syntax
*/
s.target = img_open_file(out_filename, open_opts, out_fmt,
flags, writethrough, quiet, false);
open_opts = NULL; /* blk_new_open will have freed it */
}
if (!s.target) {
ret = -1;
goto out;
}
out_bs = blk_bs(s.target);
if (s.compressed && !out_bs->drv->bdrv_co_pwritev_compressed) {
error_report("Compression not supported for this file format");
ret = -1;
goto out;
}
/* increase bufsectors from the default 4096 (2M) if opt_transfer
* or discard_alignment of the out_bs is greater. Limit to
* MAX_BUF_SECTORS as maximum which is currently 32768 (16MB). */
s.buf_sectors = MIN(MAX_BUF_SECTORS,
MAX(s.buf_sectors,
MAX(out_bs->bl.opt_transfer >> BDRV_SECTOR_BITS,
out_bs->bl.pdiscard_alignment >>
BDRV_SECTOR_BITS)));
/* try to align the write requests to the destination to avoid unnecessary
* RMW cycles. */
s.alignment = MAX(pow2floor(s.min_sparse),
DIV_ROUND_UP(out_bs->bl.request_alignment,
BDRV_SECTOR_SIZE));
assert(is_power_of_2(s.alignment));
if (skip_create) {
int64_t output_sectors = blk_nb_sectors(s.target);
if (output_sectors < 0) {
error_report("unable to get output image length: %s",
strerror(-output_sectors));
ret = -1;
goto out;
} else if (output_sectors < s.total_sectors) {
error_report("output file is smaller than input file");
ret = -1;
goto out;
}
}
if (s.target_has_backing) {
/* Errors are treated as "backing length unknown" (which means
* s.target_backing_sectors has to be negative, which it will
* be automatically). The backing file length is used only
* for optimizations, so such a case is not fatal. */
s.target_backing_sectors = bdrv_nb_sectors(out_bs->backing->bs);
} else {
s.target_backing_sectors = -1;
}
ret = bdrv_get_info(out_bs, &bdi);
if (ret < 0) {
if (s.compressed) {
error_report("could not get block driver info");
goto out;
}
} else {
s.compressed = s.compressed || bdi.needs_compressed_writes;
s.cluster_sectors = bdi.cluster_size / BDRV_SECTOR_SIZE;
s.unallocated_blocks_are_zero = bdi.unallocated_blocks_are_zero;
}
ret = convert_do_copy(&s);
out:
if (!ret) {
qemu_progress_print(100, 0);
}
qemu_progress_end();
qemu_opts_del(opts);
qemu_opts_free(create_opts);
qemu_opts_del(sn_opts);
qobject_unref(open_opts);
blk_unref(s.target);
if (s.src) {
for (bs_i = 0; bs_i < s.src_num; bs_i++) {
blk_unref(s.src[bs_i]);
}
g_free(s.src);
}
g_free(s.src_sectors);
fail_getopt:
g_free(options);
return !!ret;
}
static void dump_snapshots(BlockDriverState *bs)
{
QEMUSnapshotInfo *sn_tab, *sn;
int nb_sns, i;
nb_sns = bdrv_snapshot_list(bs, &sn_tab);
if (nb_sns <= 0)
return;
printf("Snapshot list:\n");
bdrv_snapshot_dump(fprintf, stdout, NULL);
printf("\n");
for(i = 0; i < nb_sns; i++) {
sn = &sn_tab[i];
bdrv_snapshot_dump(fprintf, stdout, sn);
printf("\n");
}
g_free(sn_tab);
}
static void dump_json_image_info_list(ImageInfoList *list)
{
QString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
visit_type_ImageInfoList(v, NULL, &list, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj);
assert(str != NULL);
printf("%s\n", qstring_get_str(str));
qobject_unref(obj);
visit_free(v);
qobject_unref(str);
}
static void dump_json_image_info(ImageInfo *info)
{
QString *str;
QObject *obj;
Visitor *v = qobject_output_visitor_new(&obj);
visit_type_ImageInfo(v, NULL, &info, &error_abort);
visit_complete(v, &obj);
str = qobject_to_json_pretty(obj);
assert(str != NULL);
printf("%s\n", qstring_get_str(str));
qobject_unref(obj);
visit_free(v);
qobject_unref(str);
}
static void dump_human_image_info_list(ImageInfoList *list)
{
ImageInfoList *elem;
bool delim = false;
for (elem = list; elem; elem = elem->next) {
if (delim) {
printf("\n");
}
delim = true;
bdrv_image_info_dump(fprintf, stdout, elem->value);
}
}
static gboolean str_equal_func(gconstpointer a, gconstpointer b)
{
return strcmp(a, b) == 0;
}
/**
* Open an image file chain and return an ImageInfoList
*
* @filename: topmost image filename
* @fmt: topmost image format (may be NULL to autodetect)
* @chain: true - enumerate entire backing file chain
* false - only topmost image file
*
* Returns a list of ImageInfo objects or NULL if there was an error opening an
* image file. If there was an error a message will have been printed to
* stderr.
*/
static ImageInfoList *collect_image_info_list(bool image_opts,
const char *filename,
const char *fmt,
bool chain, bool force_share)
{
ImageInfoList *head = NULL;
ImageInfoList **last = &head;
GHashTable *filenames;
Error *err = NULL;
filenames = g_hash_table_new_full(g_str_hash, str_equal_func, NULL, NULL);
while (filename) {
BlockBackend *blk;
BlockDriverState *bs;
ImageInfo *info;
ImageInfoList *elem;
if (g_hash_table_lookup_extended(filenames, filename, NULL, NULL)) {
error_report("Backing file '%s' creates an infinite loop.",
filename);
goto err;
}
g_hash_table_insert(filenames, (gpointer)filename, NULL);
blk = img_open(image_opts, filename, fmt,
BDRV_O_NO_BACKING | BDRV_O_NO_IO, false, false,
force_share);
if (!blk) {
goto err;
}
bs = blk_bs(blk);
bdrv_query_image_info(bs, &info, &err);
if (err) {
error_report_err(err);
blk_unref(blk);
goto err;
}
elem = g_new0(ImageInfoList, 1);
elem->value = info;
*last = elem;
last = &elem->next;
blk_unref(blk);
filename = fmt = NULL;
if (chain) {
if (info->has_full_backing_filename) {
filename = info->full_backing_filename;
} else if (info->has_backing_filename) {
error_report("Could not determine absolute backing filename,"
" but backing filename '%s' present",
info->backing_filename);
goto err;
}
if (info->has_backing_filename_format) {
fmt = info->backing_filename_format;
}
}
}
g_hash_table_destroy(filenames);
return head;
err:
qapi_free_ImageInfoList(head);
g_hash_table_destroy(filenames);
return NULL;
}
static int img_info(int argc, char **argv)
{
int c;
OutputFormat output_format = OFORMAT_HUMAN;
bool chain = false;
const char *filename, *fmt, *output;
ImageInfoList *list;
bool image_opts = false;
bool force_share = false;
fmt = NULL;
output = NULL;
for(;;) {
int option_index = 0;
static const struct option long_options[] = {
{"help", no_argument, 0, 'h'},
{"format", required_argument, 0, 'f'},
{"output", required_argument, 0, OPTION_OUTPUT},
{"backing-chain", no_argument, 0, OPTION_BACKING_CHAIN},
{"object", required_argument, 0, OPTION_OBJECT},
{"image-opts", no_argument, 0, OPTION_IMAGE_OPTS},
{"force-share", no_argument, 0, 'U'},
{0, 0, 0, 0}
};
c = getopt_long(argc, argv, ":f:hU",
long_options, &option_index);
if (c == -1) {
break;
}
switch(c) {
case ':':
missing_argument(argv[optind - 1]);
break;
case '?':
unrecognized_option(argv[optind - 1]);
break;
case 'h':
help();
break;
case 'f':
fmt = optarg;
break;
case 'U':
force_share = true;
break;
case OPTION_OUTPUT:
output = optarg;
break;
case OPTION_BACKING_CHAIN:
chain = true;
break;
case OPTION_OBJECT: {
QemuOpts *opts;
opts = qemu_opts_parse_noisily(&qemu_object_opts,
optarg, true);
if (!opts) {
return 1;