blob: bbb042800a6101f8da71041135dc305077061fd9 [file] [log] [blame]
/*
* QEMU System Emulator block driver
*
* Copyright (c) 2003 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 "block/trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/nbd.h"
#include "qemu/error-report.h"
#include "module_block.h"
#include "qemu/module.h"
#include "qapi/error.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qmp/qnull.h"
#include "qapi/qmp/qstring.h"
#include "qapi/qobject-output-visitor.h"
#include "qapi/qapi-visit-block-core.h"
#include "sysemu/block-backend.h"
#include "sysemu/sysemu.h"
#include "qemu/notify.h"
#include "qemu/option.h"
#include "qemu/coroutine.h"
#include "block/qapi.h"
#include "qemu/timer.h"
#include "qemu/cutils.h"
#include "qemu/id.h"
#ifdef CONFIG_BSD
#include <sys/ioctl.h>
#include <sys/queue.h>
#ifndef __DragonFly__
#include <sys/disk.h>
#endif
#endif
#ifdef _WIN32
#include <windows.h>
#endif
#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
static QTAILQ_HEAD(, BlockDriverState) graph_bdrv_states =
QTAILQ_HEAD_INITIALIZER(graph_bdrv_states);
static QTAILQ_HEAD(, BlockDriverState) all_bdrv_states =
QTAILQ_HEAD_INITIALIZER(all_bdrv_states);
static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
static BlockDriverState *bdrv_open_inherit(const char *filename,
const char *reference,
QDict *options, int flags,
BlockDriverState *parent,
const BdrvChildRole *child_role,
Error **errp);
/* If non-zero, use only whitelisted block drivers */
static int use_bdrv_whitelist;
#ifdef _WIN32
static int is_windows_drive_prefix(const char *filename)
{
return (((filename[0] >= 'a' && filename[0] <= 'z') ||
(filename[0] >= 'A' && filename[0] <= 'Z')) &&
filename[1] == ':');
}
int is_windows_drive(const char *filename)
{
if (is_windows_drive_prefix(filename) &&
filename[2] == '\0')
return 1;
if (strstart(filename, "\\\\.\\", NULL) ||
strstart(filename, "//./", NULL))
return 1;
return 0;
}
#endif
size_t bdrv_opt_mem_align(BlockDriverState *bs)
{
if (!bs || !bs->drv) {
/* page size or 4k (hdd sector size) should be on the safe side */
return MAX(4096, getpagesize());
}
return bs->bl.opt_mem_alignment;
}
size_t bdrv_min_mem_align(BlockDriverState *bs)
{
if (!bs || !bs->drv) {
/* page size or 4k (hdd sector size) should be on the safe side */
return MAX(4096, getpagesize());
}
return bs->bl.min_mem_alignment;
}
/* check if the path starts with "<protocol>:" */
int path_has_protocol(const char *path)
{
const char *p;
#ifdef _WIN32
if (is_windows_drive(path) ||
is_windows_drive_prefix(path)) {
return 0;
}
p = path + strcspn(path, ":/\\");
#else
p = path + strcspn(path, ":/");
#endif
return *p == ':';
}
int path_is_absolute(const char *path)
{
#ifdef _WIN32
/* specific case for names like: "\\.\d:" */
if (is_windows_drive(path) || is_windows_drive_prefix(path)) {
return 1;
}
return (*path == '/' || *path == '\\');
#else
return (*path == '/');
#endif
}
/* if filename is absolute, just copy it to dest. Otherwise, build a
path to it by considering it is relative to base_path. URL are
supported. */
void path_combine(char *dest, int dest_size,
const char *base_path,
const char *filename)
{
const char *p, *p1;
int len;
if (dest_size <= 0)
return;
if (path_is_absolute(filename)) {
pstrcpy(dest, dest_size, filename);
} else {
const char *protocol_stripped = NULL;
if (path_has_protocol(base_path)) {
protocol_stripped = strchr(base_path, ':');
if (protocol_stripped) {
protocol_stripped++;
}
}
p = protocol_stripped ?: base_path;
p1 = strrchr(base_path, '/');
#ifdef _WIN32
{
const char *p2;
p2 = strrchr(base_path, '\\');
if (!p1 || p2 > p1)
p1 = p2;
}
#endif
if (p1)
p1++;
else
p1 = base_path;
if (p1 > p)
p = p1;
len = p - base_path;
if (len > dest_size - 1)
len = dest_size - 1;
memcpy(dest, base_path, len);
dest[len] = '\0';
pstrcat(dest, dest_size, filename);
}
}
/*
* Helper function for bdrv_parse_filename() implementations to remove optional
* protocol prefixes (especially "file:") from a filename and for putting the
* stripped filename into the options QDict if there is such a prefix.
*/
void bdrv_parse_filename_strip_prefix(const char *filename, const char *prefix,
QDict *options)
{
if (strstart(filename, prefix, &filename)) {
/* Stripping the explicit protocol prefix may result in a protocol
* prefix being (wrongly) detected (if the filename contains a colon) */
if (path_has_protocol(filename)) {
QString *fat_filename;
/* This means there is some colon before the first slash; therefore,
* this cannot be an absolute path */
assert(!path_is_absolute(filename));
/* And we can thus fix the protocol detection issue by prefixing it
* by "./" */
fat_filename = qstring_from_str("./");
qstring_append(fat_filename, filename);
assert(!path_has_protocol(qstring_get_str(fat_filename)));
qdict_put(options, "filename", fat_filename);
} else {
/* If no protocol prefix was detected, we can use the shortened
* filename as-is */
qdict_put_str(options, "filename", filename);
}
}
}
/* Returns whether the image file is opened as read-only. Note that this can
* return false and writing to the image file is still not possible because the
* image is inactivated. */
bool bdrv_is_read_only(BlockDriverState *bs)
{
return bs->read_only;
}
int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only,
bool ignore_allow_rdw, Error **errp)
{
/* Do not set read_only if copy_on_read is enabled */
if (bs->copy_on_read && read_only) {
error_setg(errp, "Can't set node '%s' to r/o with copy-on-read enabled",
bdrv_get_device_or_node_name(bs));
return -EINVAL;
}
/* Do not clear read_only if it is prohibited */
if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR) &&
!ignore_allow_rdw)
{
error_setg(errp, "Node '%s' is read only",
bdrv_get_device_or_node_name(bs));
return -EPERM;
}
return 0;
}
/* TODO Remove (deprecated since 2.11)
* Block drivers are not supposed to automatically change bs->read_only.
* Instead, they should just check whether they can provide what the user
* explicitly requested and error out if read-write is requested, but they can
* only provide read-only access. */
int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
{
int ret = 0;
ret = bdrv_can_set_read_only(bs, read_only, false, errp);
if (ret < 0) {
return ret;
}
bs->read_only = read_only;
return 0;
}
void bdrv_get_full_backing_filename_from_filename(const char *backed,
const char *backing,
char *dest, size_t sz,
Error **errp)
{
if (backing[0] == '\0' || path_has_protocol(backing) ||
path_is_absolute(backing))
{
pstrcpy(dest, sz, backing);
} else if (backed[0] == '\0' || strstart(backed, "json:", NULL)) {
error_setg(errp, "Cannot use relative backing file names for '%s'",
backed);
} else {
path_combine(dest, sz, backed, backing);
}
}
void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz,
Error **errp)
{
char *backed = bs->exact_filename[0] ? bs->exact_filename : bs->filename;
bdrv_get_full_backing_filename_from_filename(backed, bs->backing_file,
dest, sz, errp);
}
void bdrv_register(BlockDriver *bdrv)
{
QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
}
BlockDriverState *bdrv_new(void)
{
BlockDriverState *bs;
int i;
bs = g_new0(BlockDriverState, 1);
QLIST_INIT(&bs->dirty_bitmaps);
for (i = 0; i < BLOCK_OP_TYPE_MAX; i++) {
QLIST_INIT(&bs->op_blockers[i]);
}
notifier_with_return_list_init(&bs->before_write_notifiers);
qemu_co_mutex_init(&bs->reqs_lock);
qemu_mutex_init(&bs->dirty_bitmap_mutex);
bs->refcnt = 1;
bs->aio_context = qemu_get_aio_context();
qemu_co_queue_init(&bs->flush_queue);
QTAILQ_INSERT_TAIL(&all_bdrv_states, bs, bs_list);
return bs;
}
static BlockDriver *bdrv_do_find_format(const char *format_name)
{
BlockDriver *drv1;
QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (!strcmp(drv1->format_name, format_name)) {
return drv1;
}
}
return NULL;
}
BlockDriver *bdrv_find_format(const char *format_name)
{
BlockDriver *drv1;
int i;
drv1 = bdrv_do_find_format(format_name);
if (drv1) {
return drv1;
}
/* The driver isn't registered, maybe we need to load a module */
for (i = 0; i < (int)ARRAY_SIZE(block_driver_modules); ++i) {
if (!strcmp(block_driver_modules[i].format_name, format_name)) {
block_module_load_one(block_driver_modules[i].library_name);
break;
}
}
return bdrv_do_find_format(format_name);
}
int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
{
static const char *whitelist_rw[] = {
CONFIG_BDRV_RW_WHITELIST
};
static const char *whitelist_ro[] = {
CONFIG_BDRV_RO_WHITELIST
};
const char **p;
if (!whitelist_rw[0] && !whitelist_ro[0]) {
return 1; /* no whitelist, anything goes */
}
for (p = whitelist_rw; *p; p++) {
if (!strcmp(drv->format_name, *p)) {
return 1;
}
}
if (read_only) {
for (p = whitelist_ro; *p; p++) {
if (!strcmp(drv->format_name, *p)) {
return 1;
}
}
}
return 0;
}
bool bdrv_uses_whitelist(void)
{
return use_bdrv_whitelist;
}
typedef struct CreateCo {
BlockDriver *drv;
char *filename;
QemuOpts *opts;
int ret;
Error *err;
} CreateCo;
static void coroutine_fn bdrv_create_co_entry(void *opaque)
{
Error *local_err = NULL;
int ret;
CreateCo *cco = opaque;
assert(cco->drv);
ret = cco->drv->bdrv_co_create_opts(cco->filename, cco->opts, &local_err);
error_propagate(&cco->err, local_err);
cco->ret = ret;
}
int bdrv_create(BlockDriver *drv, const char* filename,
QemuOpts *opts, Error **errp)
{
int ret;
Coroutine *co;
CreateCo cco = {
.drv = drv,
.filename = g_strdup(filename),
.opts = opts,
.ret = NOT_DONE,
.err = NULL,
};
if (!drv->bdrv_co_create_opts) {
error_setg(errp, "Driver '%s' does not support image creation", drv->format_name);
ret = -ENOTSUP;
goto out;
}
if (qemu_in_coroutine()) {
/* Fast-path if already in coroutine context */
bdrv_create_co_entry(&cco);
} else {
co = qemu_coroutine_create(bdrv_create_co_entry, &cco);
qemu_coroutine_enter(co);
while (cco.ret == NOT_DONE) {
aio_poll(qemu_get_aio_context(), true);
}
}
ret = cco.ret;
if (ret < 0) {
if (cco.err) {
error_propagate(errp, cco.err);
} else {
error_setg_errno(errp, -ret, "Could not create image");
}
}
out:
g_free(cco.filename);
return ret;
}
int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp)
{
BlockDriver *drv;
Error *local_err = NULL;
int ret;
drv = bdrv_find_protocol(filename, true, errp);
if (drv == NULL) {
return -ENOENT;
}
ret = bdrv_create(drv, filename, opts, &local_err);
error_propagate(errp, local_err);
return ret;
}
/**
* Try to get @bs's logical and physical block size.
* On success, store them in @bsz struct and return 0.
* On failure return -errno.
* @bs must not be empty.
*/
int bdrv_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
{
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_probe_blocksizes) {
return drv->bdrv_probe_blocksizes(bs, bsz);
} else if (drv && drv->is_filter && bs->file) {
return bdrv_probe_blocksizes(bs->file->bs, bsz);
}
return -ENOTSUP;
}
/**
* Try to get @bs's geometry (cyls, heads, sectors).
* On success, store them in @geo struct and return 0.
* On failure return -errno.
* @bs must not be empty.
*/
int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
{
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_probe_geometry) {
return drv->bdrv_probe_geometry(bs, geo);
} else if (drv && drv->is_filter && bs->file) {
return bdrv_probe_geometry(bs->file->bs, geo);
}
return -ENOTSUP;
}
/*
* Create a uniquely-named empty temporary file.
* Return 0 upon success, otherwise a negative errno value.
*/
int get_tmp_filename(char *filename, int size)
{
#ifdef _WIN32
char temp_dir[MAX_PATH];
/* GetTempFileName requires that its output buffer (4th param)
have length MAX_PATH or greater. */
assert(size >= MAX_PATH);
return (GetTempPath(MAX_PATH, temp_dir)
&& GetTempFileName(temp_dir, "qem", 0, filename)
? 0 : -GetLastError());
#else
int fd;
const char *tmpdir;
tmpdir = getenv("TMPDIR");
if (!tmpdir) {
tmpdir = "/var/tmp";
}
if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
return -EOVERFLOW;
}
fd = mkstemp(filename);
if (fd < 0) {
return -errno;
}
if (close(fd) != 0) {
unlink(filename);
return -errno;
}
return 0;
#endif
}
/*
* Detect host devices. By convention, /dev/cdrom[N] is always
* recognized as a host CDROM.
*/
static BlockDriver *find_hdev_driver(const char *filename)
{
int score_max = 0, score;
BlockDriver *drv = NULL, *d;
QLIST_FOREACH(d, &bdrv_drivers, list) {
if (d->bdrv_probe_device) {
score = d->bdrv_probe_device(filename);
if (score > score_max) {
score_max = score;
drv = d;
}
}
}
return drv;
}
static BlockDriver *bdrv_do_find_protocol(const char *protocol)
{
BlockDriver *drv1;
QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (drv1->protocol_name && !strcmp(drv1->protocol_name, protocol)) {
return drv1;
}
}
return NULL;
}
BlockDriver *bdrv_find_protocol(const char *filename,
bool allow_protocol_prefix,
Error **errp)
{
BlockDriver *drv1;
char protocol[128];
int len;
const char *p;
int i;
/* TODO Drivers without bdrv_file_open must be specified explicitly */
/*
* XXX(hch): we really should not let host device detection
* override an explicit protocol specification, but moving this
* later breaks access to device names with colons in them.
* Thanks to the brain-dead persistent naming schemes on udev-
* based Linux systems those actually are quite common.
*/
drv1 = find_hdev_driver(filename);
if (drv1) {
return drv1;
}
if (!path_has_protocol(filename) || !allow_protocol_prefix) {
return &bdrv_file;
}
p = strchr(filename, ':');
assert(p != NULL);
len = p - filename;
if (len > sizeof(protocol) - 1)
len = sizeof(protocol) - 1;
memcpy(protocol, filename, len);
protocol[len] = '\0';
drv1 = bdrv_do_find_protocol(protocol);
if (drv1) {
return drv1;
}
for (i = 0; i < (int)ARRAY_SIZE(block_driver_modules); ++i) {
if (block_driver_modules[i].protocol_name &&
!strcmp(block_driver_modules[i].protocol_name, protocol)) {
block_module_load_one(block_driver_modules[i].library_name);
break;
}
}
drv1 = bdrv_do_find_protocol(protocol);
if (!drv1) {
error_setg(errp, "Unknown protocol '%s'", protocol);
}
return drv1;
}
/*
* Guess image format by probing its contents.
* This is not a good idea when your image is raw (CVE-2008-2004), but
* we do it anyway for backward compatibility.
*
* @buf contains the image's first @buf_size bytes.
* @buf_size is the buffer size in bytes (generally BLOCK_PROBE_BUF_SIZE,
* but can be smaller if the image file is smaller)
* @filename is its filename.
*
* For all block drivers, call the bdrv_probe() method to get its
* probing score.
* Return the first block driver with the highest probing score.
*/
BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
const char *filename)
{
int score_max = 0, score;
BlockDriver *drv = NULL, *d;
QLIST_FOREACH(d, &bdrv_drivers, list) {
if (d->bdrv_probe) {
score = d->bdrv_probe(buf, buf_size, filename);
if (score > score_max) {
score_max = score;
drv = d;
}
}
}
return drv;
}
static int find_image_format(BlockBackend *file, const char *filename,
BlockDriver **pdrv, Error **errp)
{
BlockDriver *drv;
uint8_t buf[BLOCK_PROBE_BUF_SIZE];
int ret = 0;
/* Return the raw BlockDriver * to scsi-generic devices or empty drives */
if (blk_is_sg(file) || !blk_is_inserted(file) || blk_getlength(file) == 0) {
*pdrv = &bdrv_raw;
return ret;
}
ret = blk_pread(file, 0, buf, sizeof(buf));
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not read image for determining its "
"format");
*pdrv = NULL;
return ret;
}
drv = bdrv_probe_all(buf, ret, filename);
if (!drv) {
error_setg(errp, "Could not determine image format: No compatible "
"driver found");
ret = -ENOENT;
}
*pdrv = drv;
return ret;
}
/**
* Set the current 'total_sectors' value
* Return 0 on success, -errno on error.
*/
static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
{
BlockDriver *drv = bs->drv;
if (!drv) {
return -ENOMEDIUM;
}
/* Do not attempt drv->bdrv_getlength() on scsi-generic devices */
if (bdrv_is_sg(bs))
return 0;
/* query actual device if possible, otherwise just trust the hint */
if (drv->bdrv_getlength) {
int64_t length = drv->bdrv_getlength(bs);
if (length < 0) {
return length;
}
hint = DIV_ROUND_UP(length, BDRV_SECTOR_SIZE);
}
bs->total_sectors = hint;
return 0;
}
/**
* Combines a QDict of new block driver @options with any missing options taken
* from @old_options, so that leaving out an option defaults to its old value.
*/
static void bdrv_join_options(BlockDriverState *bs, QDict *options,
QDict *old_options)
{
if (bs->drv && bs->drv->bdrv_join_options) {
bs->drv->bdrv_join_options(options, old_options);
} else {
qdict_join(options, old_options, false);
}
}
/**
* Set open flags for a given discard mode
*
* Return 0 on success, -1 if the discard mode was invalid.
*/
int bdrv_parse_discard_flags(const char *mode, int *flags)
{
*flags &= ~BDRV_O_UNMAP;
if (!strcmp(mode, "off") || !strcmp(mode, "ignore")) {
/* do nothing */
} else if (!strcmp(mode, "on") || !strcmp(mode, "unmap")) {
*flags |= BDRV_O_UNMAP;
} else {
return -1;
}
return 0;
}
/**
* Set open flags for a given cache mode
*
* Return 0 on success, -1 if the cache mode was invalid.
*/
int bdrv_parse_cache_mode(const char *mode, int *flags, bool *writethrough)
{
*flags &= ~BDRV_O_CACHE_MASK;
if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
*writethrough = false;
*flags |= BDRV_O_NOCACHE;
} else if (!strcmp(mode, "directsync")) {
*writethrough = true;
*flags |= BDRV_O_NOCACHE;
} else if (!strcmp(mode, "writeback")) {
*writethrough = false;
} else if (!strcmp(mode, "unsafe")) {
*writethrough = false;
*flags |= BDRV_O_NO_FLUSH;
} else if (!strcmp(mode, "writethrough")) {
*writethrough = true;
} else {
return -1;
}
return 0;
}
static char *bdrv_child_get_parent_desc(BdrvChild *c)
{
BlockDriverState *parent = c->opaque;
return g_strdup(bdrv_get_device_or_node_name(parent));
}
static void bdrv_child_cb_drained_begin(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
bdrv_drained_begin(bs);
}
static void bdrv_child_cb_drained_end(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
bdrv_drained_end(bs);
}
static void bdrv_child_cb_attach(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
bdrv_apply_subtree_drain(child, bs);
}
static void bdrv_child_cb_detach(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
bdrv_unapply_subtree_drain(child, bs);
}
static int bdrv_child_cb_inactivate(BdrvChild *child)
{
BlockDriverState *bs = child->opaque;
assert(bs->open_flags & BDRV_O_INACTIVE);
return 0;
}
/*
* Returns the options and flags that a temporary snapshot should get, based on
* the originally requested flags (the originally requested image will have
* flags like a backing file)
*/
static void bdrv_temp_snapshot_options(int *child_flags, QDict *child_options,
int parent_flags, QDict *parent_options)
{
*child_flags = (parent_flags & ~BDRV_O_SNAPSHOT) | BDRV_O_TEMPORARY;
/* For temporary files, unconditional cache=unsafe is fine */
qdict_set_default_str(child_options, BDRV_OPT_CACHE_DIRECT, "off");
qdict_set_default_str(child_options, BDRV_OPT_CACHE_NO_FLUSH, "on");
/* Copy the read-only option from the parent */
qdict_copy_default(child_options, parent_options, BDRV_OPT_READ_ONLY);
/* aio=native doesn't work for cache.direct=off, so disable it for the
* temporary snapshot */
*child_flags &= ~BDRV_O_NATIVE_AIO;
}
/*
* Returns the options and flags that bs->file should get if a protocol driver
* is expected, based on the given options and flags for the parent BDS
*/
static void bdrv_inherited_options(int *child_flags, QDict *child_options,
int parent_flags, QDict *parent_options)
{
int flags = parent_flags;
/* Enable protocol handling, disable format probing for bs->file */
flags |= BDRV_O_PROTOCOL;
/* If the cache mode isn't explicitly set, inherit direct and no-flush from
* the parent. */
qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
qdict_copy_default(child_options, parent_options, BDRV_OPT_FORCE_SHARE);
/* Inherit the read-only option from the parent if it's not set */
qdict_copy_default(child_options, parent_options, BDRV_OPT_READ_ONLY);
/* Our block drivers take care to send flushes and respect unmap policy,
* so we can default to enable both on lower layers regardless of the
* corresponding parent options. */
qdict_set_default_str(child_options, BDRV_OPT_DISCARD, "unmap");
/* Clear flags that only apply to the top layer */
flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ |
BDRV_O_NO_IO);
*child_flags = flags;
}
const BdrvChildRole child_file = {
.get_parent_desc = bdrv_child_get_parent_desc,
.inherit_options = bdrv_inherited_options,
.drained_begin = bdrv_child_cb_drained_begin,
.drained_end = bdrv_child_cb_drained_end,
.attach = bdrv_child_cb_attach,
.detach = bdrv_child_cb_detach,
.inactivate = bdrv_child_cb_inactivate,
};
/*
* Returns the options and flags that bs->file should get if the use of formats
* (and not only protocols) is permitted for it, based on the given options and
* flags for the parent BDS
*/
static void bdrv_inherited_fmt_options(int *child_flags, QDict *child_options,
int parent_flags, QDict *parent_options)
{
child_file.inherit_options(child_flags, child_options,
parent_flags, parent_options);
*child_flags &= ~(BDRV_O_PROTOCOL | BDRV_O_NO_IO);
}
const BdrvChildRole child_format = {
.get_parent_desc = bdrv_child_get_parent_desc,
.inherit_options = bdrv_inherited_fmt_options,
.drained_begin = bdrv_child_cb_drained_begin,
.drained_end = bdrv_child_cb_drained_end,
.attach = bdrv_child_cb_attach,
.detach = bdrv_child_cb_detach,
.inactivate = bdrv_child_cb_inactivate,
};
static void bdrv_backing_attach(BdrvChild *c)
{
BlockDriverState *parent = c->opaque;
BlockDriverState *backing_hd = c->bs;
assert(!parent->backing_blocker);
error_setg(&parent->backing_blocker,
"node is used as backing hd of '%s'",
bdrv_get_device_or_node_name(parent));
parent->open_flags &= ~BDRV_O_NO_BACKING;
pstrcpy(parent->backing_file, sizeof(parent->backing_file),
backing_hd->filename);
pstrcpy(parent->backing_format, sizeof(parent->backing_format),
backing_hd->drv ? backing_hd->drv->format_name : "");
bdrv_op_block_all(backing_hd, parent->backing_blocker);
/* Otherwise we won't be able to commit or stream */
bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
parent->backing_blocker);
bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
parent->backing_blocker);
/*
* We do backup in 3 ways:
* 1. drive backup
* The target bs is new opened, and the source is top BDS
* 2. blockdev backup
* Both the source and the target are top BDSes.
* 3. internal backup(used for block replication)
* Both the source and the target are backing file
*
* In case 1 and 2, neither the source nor the target is the backing file.
* In case 3, we will block the top BDS, so there is only one block job
* for the top BDS and its backing chain.
*/
bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_SOURCE,
parent->backing_blocker);
bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
parent->backing_blocker);
bdrv_child_cb_attach(c);
}
static void bdrv_backing_detach(BdrvChild *c)
{
BlockDriverState *parent = c->opaque;
assert(parent->backing_blocker);
bdrv_op_unblock_all(c->bs, parent->backing_blocker);
error_free(parent->backing_blocker);
parent->backing_blocker = NULL;
bdrv_child_cb_detach(c);
}
/*
* Returns the options and flags that bs->backing should get, based on the
* given options and flags for the parent BDS
*/
static void bdrv_backing_options(int *child_flags, QDict *child_options,
int parent_flags, QDict *parent_options)
{
int flags = parent_flags;
/* The cache mode is inherited unmodified for backing files; except WCE,
* which is only applied on the top level (BlockBackend) */
qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_DIRECT);
qdict_copy_default(child_options, parent_options, BDRV_OPT_CACHE_NO_FLUSH);
qdict_copy_default(child_options, parent_options, BDRV_OPT_FORCE_SHARE);
/* backing files always opened read-only */
qdict_set_default_str(child_options, BDRV_OPT_READ_ONLY, "on");
flags &= ~BDRV_O_COPY_ON_READ;
/* snapshot=on is handled on the top layer */
flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_TEMPORARY);
*child_flags = flags;
}
static int bdrv_backing_update_filename(BdrvChild *c, BlockDriverState *base,
const char *filename, Error **errp)
{
BlockDriverState *parent = c->opaque;
int orig_flags = bdrv_get_flags(parent);
int ret;
if (!(orig_flags & BDRV_O_RDWR)) {
ret = bdrv_reopen(parent, orig_flags | BDRV_O_RDWR, errp);
if (ret < 0) {
return ret;
}
}
ret = bdrv_change_backing_file(parent, filename,
base->drv ? base->drv->format_name : "");
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not update backing file link");
}
if (!(orig_flags & BDRV_O_RDWR)) {
bdrv_reopen(parent, orig_flags, NULL);
}
return ret;
}
const BdrvChildRole child_backing = {
.get_parent_desc = bdrv_child_get_parent_desc,
.attach = bdrv_backing_attach,
.detach = bdrv_backing_detach,
.inherit_options = bdrv_backing_options,
.drained_begin = bdrv_child_cb_drained_begin,
.drained_end = bdrv_child_cb_drained_end,
.inactivate = bdrv_child_cb_inactivate,
.update_filename = bdrv_backing_update_filename,
};
static int bdrv_open_flags(BlockDriverState *bs, int flags)
{
int open_flags = flags;
/*
* Clear flags that are internal to the block layer before opening the
* image.
*/
open_flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_PROTOCOL);
/*
* Snapshots should be writable.
*/
if (flags & BDRV_O_TEMPORARY) {
open_flags |= BDRV_O_RDWR;
}
return open_flags;
}
static void update_flags_from_options(int *flags, QemuOpts *opts)
{
*flags &= ~BDRV_O_CACHE_MASK;
assert(qemu_opt_find(opts, BDRV_OPT_CACHE_NO_FLUSH));
if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
*flags |= BDRV_O_NO_FLUSH;
}
assert(qemu_opt_find(opts, BDRV_OPT_CACHE_DIRECT));
if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_DIRECT, false)) {
*flags |= BDRV_O_NOCACHE;
}
*flags &= ~BDRV_O_RDWR;
assert(qemu_opt_find(opts, BDRV_OPT_READ_ONLY));
if (!qemu_opt_get_bool(opts, BDRV_OPT_READ_ONLY, false)) {
*flags |= BDRV_O_RDWR;
}
}
static void update_options_from_flags(QDict *options, int flags)
{
if (!qdict_haskey(options, BDRV_OPT_CACHE_DIRECT)) {
qdict_put_bool(options, BDRV_OPT_CACHE_DIRECT, flags & BDRV_O_NOCACHE);
}
if (!qdict_haskey(options, BDRV_OPT_CACHE_NO_FLUSH)) {
qdict_put_bool(options, BDRV_OPT_CACHE_NO_FLUSH,
flags & BDRV_O_NO_FLUSH);
}
if (!qdict_haskey(options, BDRV_OPT_READ_ONLY)) {
qdict_put_bool(options, BDRV_OPT_READ_ONLY, !(flags & BDRV_O_RDWR));
}
}
static void bdrv_assign_node_name(BlockDriverState *bs,
const char *node_name,
Error **errp)
{
char *gen_node_name = NULL;
if (!node_name) {
node_name = gen_node_name = id_generate(ID_BLOCK);
} else if (!id_wellformed(node_name)) {
/*
* Check for empty string or invalid characters, but not if it is
* generated (generated names use characters not available to the user)
*/
error_setg(errp, "Invalid node name");
return;
}
/* takes care of avoiding namespaces collisions */
if (blk_by_name(node_name)) {
error_setg(errp, "node-name=%s is conflicting with a device id",
node_name);
goto out;
}
/* takes care of avoiding duplicates node names */
if (bdrv_find_node(node_name)) {
error_setg(errp, "Duplicate node name");
goto out;
}
/* copy node name into the bs and insert it into the graph list */
pstrcpy(bs->node_name, sizeof(bs->node_name), node_name);
QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs, node_list);
out:
g_free(gen_node_name);
}
static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
const char *node_name, QDict *options,
int open_flags, Error **errp)
{
Error *local_err = NULL;
int ret;
bdrv_assign_node_name(bs, node_name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
bs->drv = drv;
bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
bs->opaque = g_malloc0(drv->instance_size);
if (drv->bdrv_file_open) {
assert(!drv->bdrv_needs_filename || bs->filename[0]);
ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
} else if (drv->bdrv_open) {
ret = drv->bdrv_open(bs, options, open_flags, &local_err);
} else {
ret = 0;
}
if (ret < 0) {
if (local_err) {
error_propagate(errp, local_err);
} else if (bs->filename[0]) {
error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
} else {
error_setg_errno(errp, -ret, "Could not open image");
}
goto open_failed;
}
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
return ret;
}
bdrv_refresh_limits(bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
assert(bdrv_opt_mem_align(bs) != 0);
assert(bdrv_min_mem_align(bs) != 0);
assert(is_power_of_2(bs->bl.request_alignment));
return 0;
open_failed:
bs->drv = NULL;
if (bs->file != NULL) {
bdrv_unref_child(bs, bs->file);
bs->file = NULL;
}
g_free(bs->opaque);
bs->opaque = NULL;
return ret;
}
BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
int flags, Error **errp)
{
BlockDriverState *bs;
int ret;
bs = bdrv_new();
bs->open_flags = flags;
bs->explicit_options = qdict_new();
bs->options = qdict_new();
bs->opaque = NULL;
update_options_from_flags(bs->options, flags);
ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp);
if (ret < 0) {
QDECREF(bs->explicit_options);
bs->explicit_options = NULL;
QDECREF(bs->options);
bs->options = NULL;
bdrv_unref(bs);
return NULL;
}
return bs;
}
QemuOptsList bdrv_runtime_opts = {
.name = "bdrv_common",
.head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
.desc = {
{
.name = "node-name",
.type = QEMU_OPT_STRING,
.help = "Node name of the block device node",
},
{
.name = "driver",
.type = QEMU_OPT_STRING,
.help = "Block driver to use for the node",
},
{
.name = BDRV_OPT_CACHE_DIRECT,
.type = QEMU_OPT_BOOL,
.help = "Bypass software writeback cache on the host",
},
{
.name = BDRV_OPT_CACHE_NO_FLUSH,
.type = QEMU_OPT_BOOL,
.help = "Ignore flush requests",
},
{
.name = BDRV_OPT_READ_ONLY,
.type = QEMU_OPT_BOOL,
.help = "Node is opened in read-only mode",
},
{
.name = "detect-zeroes",
.type = QEMU_OPT_STRING,
.help = "try to optimize zero writes (off, on, unmap)",
},
{
.name = "discard",
.type = QEMU_OPT_STRING,
.help = "discard operation (ignore/off, unmap/on)",
},
{
.name = BDRV_OPT_FORCE_SHARE,
.type = QEMU_OPT_BOOL,
.help = "always accept other writers (default: off)",
},
{ /* end of list */ }
},
};
/*
* Common part for opening disk images and files
*
* Removes all processed options from *options.
*/
static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
QDict *options, Error **errp)
{
int ret, open_flags;
const char *filename;
const char *driver_name = NULL;
const char *node_name = NULL;
const char *discard;
const char *detect_zeroes;
QemuOpts *opts;
BlockDriver *drv;
Error *local_err = NULL;
assert(bs->file == NULL);
assert(options != NULL && bs->options != options);
opts = qemu_opts_create(&bdrv_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail_opts;
}
update_flags_from_options(&bs->open_flags, opts);
driver_name = qemu_opt_get(opts, "driver");
drv = bdrv_find_format(driver_name);
assert(drv != NULL);
bs->force_share = qemu_opt_get_bool(opts, BDRV_OPT_FORCE_SHARE, false);
if (bs->force_share && (bs->open_flags & BDRV_O_RDWR)) {
error_setg(errp,
BDRV_OPT_FORCE_SHARE
"=on can only be used with read-only images");
ret = -EINVAL;
goto fail_opts;
}
if (file != NULL) {
filename = blk_bs(file)->filename;
} else {
/*
* Caution: while qdict_get_try_str() is fine, getting
* non-string types would require more care. When @options
* come from -blockdev or blockdev_add, its members are typed
* according to the QAPI schema, but when they come from
* -drive, they're all QString.
*/
filename = qdict_get_try_str(options, "filename");
}
if (drv->bdrv_needs_filename && (!filename || !filename[0])) {
error_setg(errp, "The '%s' block driver requires a file name",
drv->format_name);
ret = -EINVAL;
goto fail_opts;
}
trace_bdrv_open_common(bs, filename ?: "", bs->open_flags,
drv->format_name);
bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
error_setg(errp,
!bs->read_only && bdrv_is_whitelisted(drv, true)
? "Driver '%s' can only be used for read-only devices"
: "Driver '%s' is not whitelisted",
drv->format_name);
ret = -ENOTSUP;
goto fail_opts;
}
/* bdrv_new() and bdrv_close() make it so */
assert(atomic_read(&bs->copy_on_read) == 0);
if (bs->open_flags & BDRV_O_COPY_ON_READ) {
if (!bs->read_only) {
bdrv_enable_copy_on_read(bs);
} else {
error_setg(errp, "Can't use copy-on-read on read-only device");
ret = -EINVAL;
goto fail_opts;
}
}
discard = qemu_opt_get(opts, "discard");
if (discard != NULL) {
if (bdrv_parse_discard_flags(discard, &bs->open_flags) != 0) {
error_setg(errp, "Invalid discard option");
ret = -EINVAL;
goto fail_opts;
}
}
detect_zeroes = qemu_opt_get(opts, "detect-zeroes");
if (detect_zeroes) {
BlockdevDetectZeroesOptions value =
qapi_enum_parse(&BlockdevDetectZeroesOptions_lookup,
detect_zeroes,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail_opts;
}
if (value == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP &&
!(bs->open_flags & BDRV_O_UNMAP))
{
error_setg(errp, "setting detect-zeroes to unmap is not allowed "
"without setting discard operation to unmap");
ret = -EINVAL;
goto fail_opts;
}
bs->detect_zeroes = value;
}
if (filename != NULL) {
pstrcpy(bs->filename, sizeof(bs->filename), filename);
} else {
bs->filename[0] = '\0';
}
pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->filename);
/* Open the image, either directly or using a protocol */
open_flags = bdrv_open_flags(bs, bs->open_flags);
node_name = qemu_opt_get(opts, "node-name");
assert(!drv->bdrv_file_open || file == NULL);
ret = bdrv_open_driver(bs, drv, node_name, options, open_flags, errp);
if (ret < 0) {
goto fail_opts;
}
qemu_opts_del(opts);
return 0;
fail_opts:
qemu_opts_del(opts);
return ret;
}
static QDict *parse_json_filename(const char *filename, Error **errp)
{
QObject *options_obj;
QDict *options;
int ret;
ret = strstart(filename, "json:", &filename);
assert(ret);
(void)ret;
options_obj = qobject_from_json(filename, errp);
if (!options_obj) {
/* Work around qobject_from_json() lossage TODO fix that */
if (errp && !*errp) {
error_setg(errp, "Could not parse the JSON options");
return NULL;
}
error_prepend(errp, "Could not parse the JSON options: ");
return NULL;
}
options = qobject_to(QDict, options_obj);
if (!options) {
qobject_decref(options_obj);
error_setg(errp, "Invalid JSON object given");
return NULL;
}
qdict_flatten(options);
return options;
}
static void parse_json_protocol(QDict *options, const char **pfilename,
Error **errp)
{
QDict *json_options;
Error *local_err = NULL;
/* Parse json: pseudo-protocol */
if (!*pfilename || !g_str_has_prefix(*pfilename, "json:")) {
return;
}
json_options = parse_json_filename(*pfilename, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
/* Options given in the filename have lower priority than options
* specified directly */
qdict_join(options, json_options, false);
QDECREF(json_options);
*pfilename = NULL;
}
/*
* Fills in default options for opening images and converts the legacy
* filename/flags pair to option QDict entries.
* The BDRV_O_PROTOCOL flag in *flags will be set or cleared accordingly if a
* block driver has been specified explicitly.
*/
static int bdrv_fill_options(QDict **options, const char *filename,
int *flags, Error **errp)
{
const char *drvname;
bool protocol = *flags & BDRV_O_PROTOCOL;
bool parse_filename = false;
BlockDriver *drv = NULL;
Error *local_err = NULL;
/*
* Caution: while qdict_get_try_str() is fine, getting non-string
* types would require more care. When @options come from
* -blockdev or blockdev_add, its members are typed according to
* the QAPI schema, but when they come from -drive, they're all
* QString.
*/
drvname = qdict_get_try_str(*options, "driver");
if (drvname) {
drv = bdrv_find_format(drvname);
if (!drv) {
error_setg(errp, "Unknown driver '%s'", drvname);
return -ENOENT;
}
/* If the user has explicitly specified the driver, this choice should
* override the BDRV_O_PROTOCOL flag */
protocol = drv->bdrv_file_open;
}
if (protocol) {
*flags |= BDRV_O_PROTOCOL;
} else {
*flags &= ~BDRV_O_PROTOCOL;
}
/* Translate cache options from flags into options */
update_options_from_flags(*options, *flags);
/* Fetch the file name from the options QDict if necessary */
if (protocol && filename) {
if (!qdict_haskey(*options, "filename")) {
qdict_put_str(*options, "filename", filename);
parse_filename = true;
} else {
error_setg(errp, "Can't specify 'file' and 'filename' options at "
"the same time");
return -EINVAL;
}
}
/* Find the right block driver */
/* See cautionary note on accessing @options above */
filename = qdict_get_try_str(*options, "filename");
if (!drvname && protocol) {
if (filename) {
drv = bdrv_find_protocol(filename, parse_filename, errp);
if (!drv) {
return -EINVAL;
}
drvname = drv->format_name;
qdict_put_str(*options, "driver", drvname);
} else {
error_setg(errp, "Must specify either driver or file");
return -EINVAL;
}
}
assert(drv || !protocol);
/* Driver-specific filename parsing */
if (drv && drv->bdrv_parse_filename && parse_filename) {
drv->bdrv_parse_filename(filename, *options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
if (!drv->bdrv_needs_filename) {
qdict_del(*options, "filename");
}
}
return 0;
}
static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
uint64_t perm, uint64_t shared,
GSList *ignore_children, Error **errp);
static void bdrv_child_abort_perm_update(BdrvChild *c);
static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared);
typedef struct BlockReopenQueueEntry {
bool prepared;
BDRVReopenState state;
QSIMPLEQ_ENTRY(BlockReopenQueueEntry) entry;
} BlockReopenQueueEntry;
/*
* Return the flags that @bs will have after the reopens in @q have
* successfully completed. If @q is NULL (or @bs is not contained in @q),
* return the current flags.
*/
static int bdrv_reopen_get_flags(BlockReopenQueue *q, BlockDriverState *bs)
{
BlockReopenQueueEntry *entry;
if (q != NULL) {
QSIMPLEQ_FOREACH(entry, q, entry) {
if (entry->state.bs == bs) {
return entry->state.flags;
}
}
}
return bs->open_flags;
}
/* Returns whether the image file can be written to after the reopen queue @q
* has been successfully applied, or right now if @q is NULL. */
static bool bdrv_is_writable(BlockDriverState *bs, BlockReopenQueue *q)
{
int flags = bdrv_reopen_get_flags(q, bs);
return (flags & (BDRV_O_RDWR | BDRV_O_INACTIVE)) == BDRV_O_RDWR;
}
static void bdrv_child_perm(BlockDriverState *bs, BlockDriverState *child_bs,
BdrvChild *c, const BdrvChildRole *role,
BlockReopenQueue *reopen_queue,
uint64_t parent_perm, uint64_t parent_shared,
uint64_t *nperm, uint64_t *nshared)
{
if (bs->drv && bs->drv->bdrv_child_perm) {
bs->drv->bdrv_child_perm(bs, c, role, reopen_queue,
parent_perm, parent_shared,
nperm, nshared);
}
/* TODO Take force_share from reopen_queue */
if (child_bs && child_bs->force_share) {
*nshared = BLK_PERM_ALL;
}
}
/*
* Check whether permissions on this node can be changed in a way that
* @cumulative_perms and @cumulative_shared_perms are the new cumulative
* permissions of all its parents. This involves checking whether all necessary
* permission changes to child nodes can be performed.
*
* A call to this function must always be followed by a call to bdrv_set_perm()
* or bdrv_abort_perm_update().
*/
static int bdrv_check_perm(BlockDriverState *bs, BlockReopenQueue *q,
uint64_t cumulative_perms,
uint64_t cumulative_shared_perms,
GSList *ignore_children, Error **errp)
{
BlockDriver *drv = bs->drv;
BdrvChild *c;
int ret;
/* Write permissions never work with read-only images */
if ((cumulative_perms & (BLK_PERM_WRITE | BLK_PERM_WRITE_UNCHANGED)) &&
!bdrv_is_writable(bs, q))
{
error_setg(errp, "Block node is read-only");
return -EPERM;
}
/* Check this node */
if (!drv) {
return 0;
}
if (drv->bdrv_check_perm) {
return drv->bdrv_check_perm(bs, cumulative_perms,
cumulative_shared_perms, errp);
}
/* Drivers that never have children can omit .bdrv_child_perm() */
if (!drv->bdrv_child_perm) {
assert(QLIST_EMPTY(&bs->children));
return 0;
}
/* Check all children */
QLIST_FOREACH(c, &bs->children, next) {
uint64_t cur_perm, cur_shared;
bdrv_child_perm(bs, c->bs, c, c->role, q,
cumulative_perms, cumulative_shared_perms,
&cur_perm, &cur_shared);
ret = bdrv_child_check_perm(c, q, cur_perm, cur_shared,
ignore_children, errp);
if (ret < 0) {
return ret;
}
}
return 0;
}
/*
* Notifies drivers that after a previous bdrv_check_perm() call, the
* permission update is not performed and any preparations made for it (e.g.
* taken file locks) need to be undone.
*
* This function recursively notifies all child nodes.
*/
static void bdrv_abort_perm_update(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
BdrvChild *c;
if (!drv) {
return;
}
if (drv->bdrv_abort_perm_update) {
drv->bdrv_abort_perm_update(bs);
}
QLIST_FOREACH(c, &bs->children, next) {
bdrv_child_abort_perm_update(c);
}
}
static void bdrv_set_perm(BlockDriverState *bs, uint64_t cumulative_perms,
uint64_t cumulative_shared_perms)
{
BlockDriver *drv = bs->drv;
BdrvChild *c;
if (!drv) {
return;
}
/* Update this node */
if (drv->bdrv_set_perm) {
drv->bdrv_set_perm(bs, cumulative_perms, cumulative_shared_perms);
}
/* Drivers that never have children can omit .bdrv_child_perm() */
if (!drv->bdrv_child_perm) {
assert(QLIST_EMPTY(&bs->children));
return;
}
/* Update all children */
QLIST_FOREACH(c, &bs->children, next) {
uint64_t cur_perm, cur_shared;
bdrv_child_perm(bs, c->bs, c, c->role, NULL,
cumulative_perms, cumulative_shared_perms,
&cur_perm, &cur_shared);
bdrv_child_set_perm(c, cur_perm, cur_shared);
}
}
static void bdrv_get_cumulative_perm(BlockDriverState *bs, uint64_t *perm,
uint64_t *shared_perm)
{
BdrvChild *c;
uint64_t cumulative_perms = 0;
uint64_t cumulative_shared_perms = BLK_PERM_ALL;
QLIST_FOREACH(c, &bs->parents, next_parent) {
cumulative_perms |= c->perm;
cumulative_shared_perms &= c->shared_perm;
}
*perm = cumulative_perms;
*shared_perm = cumulative_shared_perms;
}
static char *bdrv_child_user_desc(BdrvChild *c)
{
if (c->role->get_parent_desc) {
return c->role->get_parent_desc(c);
}
return g_strdup("another user");
}
char *bdrv_perm_names(uint64_t perm)
{
struct perm_name {
uint64_t perm;
const char *name;
} permissions[] = {
{ BLK_PERM_CONSISTENT_READ, "consistent read" },
{ BLK_PERM_WRITE, "write" },
{ BLK_PERM_WRITE_UNCHANGED, "write unchanged" },
{ BLK_PERM_RESIZE, "resize" },
{ BLK_PERM_GRAPH_MOD, "change children" },
{ 0, NULL }
};
char *result = g_strdup("");
struct perm_name *p;
for (p = permissions; p->name; p++) {
if (perm & p->perm) {
char *old = result;
result = g_strdup_printf("%s%s%s", old, *old ? ", " : "", p->name);
g_free(old);
}
}
return result;
}
/*
* Checks whether a new reference to @bs can be added if the new user requires
* @new_used_perm/@new_shared_perm as its permissions. If @ignore_children is
* set, the BdrvChild objects in this list are ignored in the calculations;
* this allows checking permission updates for an existing reference.
*
* Needs to be followed by a call to either bdrv_set_perm() or
* bdrv_abort_perm_update(). */
static int bdrv_check_update_perm(BlockDriverState *bs, BlockReopenQueue *q,
uint64_t new_used_perm,
uint64_t new_shared_perm,
GSList *ignore_children, Error **errp)
{
BdrvChild *c;
uint64_t cumulative_perms = new_used_perm;
uint64_t cumulative_shared_perms = new_shared_perm;
/* There is no reason why anyone couldn't tolerate write_unchanged */
assert(new_shared_perm & BLK_PERM_WRITE_UNCHANGED);
QLIST_FOREACH(c, &bs->parents, next_parent) {
if (g_slist_find(ignore_children, c)) {
continue;
}
if ((new_used_perm & c->shared_perm) != new_used_perm) {
char *user = bdrv_child_user_desc(c);
char *perm_names = bdrv_perm_names(new_used_perm & ~c->shared_perm);
error_setg(errp, "Conflicts with use by %s as '%s', which does not "
"allow '%s' on %s",
user, c->name, perm_names, bdrv_get_node_name(c->bs));
g_free(user);
g_free(perm_names);
return -EPERM;
}
if ((c->perm & new_shared_perm) != c->perm) {
char *user = bdrv_child_user_desc(c);
char *perm_names = bdrv_perm_names(c->perm & ~new_shared_perm);
error_setg(errp, "Conflicts with use by %s as '%s', which uses "
"'%s' on %s",
user, c->name, perm_names, bdrv_get_node_name(c->bs));
g_free(user);
g_free(perm_names);
return -EPERM;
}
cumulative_perms |= c->perm;
cumulative_shared_perms &= c->shared_perm;
}
return bdrv_check_perm(bs, q, cumulative_perms, cumulative_shared_perms,
ignore_children, errp);
}
/* Needs to be followed by a call to either bdrv_child_set_perm() or
* bdrv_child_abort_perm_update(). */
static int bdrv_child_check_perm(BdrvChild *c, BlockReopenQueue *q,
uint64_t perm, uint64_t shared,
GSList *ignore_children, Error **errp)
{
int ret;
ignore_children = g_slist_prepend(g_slist_copy(ignore_children), c);
ret = bdrv_check_update_perm(c->bs, q, perm, shared, ignore_children, errp);
g_slist_free(ignore_children);
return ret;
}
static void bdrv_child_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared)
{
uint64_t cumulative_perms, cumulative_shared_perms;
c->perm = perm;
c->shared_perm = shared;
bdrv_get_cumulative_perm(c->bs, &cumulative_perms,
&cumulative_shared_perms);
bdrv_set_perm(c->bs, cumulative_perms, cumulative_shared_perms);
}
static void bdrv_child_abort_perm_update(BdrvChild *c)
{
bdrv_abort_perm_update(c->bs);
}
int bdrv_child_try_set_perm(BdrvChild *c, uint64_t perm, uint64_t shared,
Error **errp)
{
int ret;
ret = bdrv_child_check_perm(c, NULL, perm, shared, NULL, errp);
if (ret < 0) {
bdrv_child_abort_perm_update(c);
return ret;
}
bdrv_child_set_perm(c, perm, shared);
return 0;
}
#define DEFAULT_PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
| BLK_PERM_WRITE \
| BLK_PERM_WRITE_UNCHANGED \
| BLK_PERM_RESIZE)
#define DEFAULT_PERM_UNCHANGED (BLK_PERM_ALL & ~DEFAULT_PERM_PASSTHROUGH)
void bdrv_filter_default_perms(BlockDriverState *bs, BdrvChild *c,
const BdrvChildRole *role,
BlockReopenQueue *reopen_queue,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
if (c == NULL) {
*nperm = perm & DEFAULT_PERM_PASSTHROUGH;
*nshared = (shared & DEFAULT_PERM_PASSTHROUGH) | DEFAULT_PERM_UNCHANGED;
return;
}
*nperm = (perm & DEFAULT_PERM_PASSTHROUGH) |
(c->perm & DEFAULT_PERM_UNCHANGED);
*nshared = (shared & DEFAULT_PERM_PASSTHROUGH) |
(c->shared_perm & DEFAULT_PERM_UNCHANGED);
}
void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
const BdrvChildRole *role,
BlockReopenQueue *reopen_queue,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
bool backing = (role == &child_backing);
assert(role == &child_backing || role == &child_file);
if (!backing) {
int flags = bdrv_reopen_get_flags(reopen_queue, bs);
/* Apart from the modifications below, the same permissions are
* forwarded and left alone as for filters */
bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
&perm, &shared);
/* Format drivers may touch metadata even if the guest doesn't write */
if (bdrv_is_writable(bs, reopen_queue)) {
perm |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
}
/* bs->file always needs to be consistent because of the metadata. We
* can never allow other users to resize or write to it. */
if (!(flags & BDRV_O_NO_IO)) {
perm |= BLK_PERM_CONSISTENT_READ;
}
shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
} else {
/* We want consistent read from backing files if the parent needs it.
* No other operations are performed on backing files. */
perm &= BLK_PERM_CONSISTENT_READ;
/* If the parent can deal with changing data, we're okay with a
* writable and resizable backing file. */
/* TODO Require !(perm & BLK_PERM_CONSISTENT_READ), too? */
if (shared & BLK_PERM_WRITE) {
shared = BLK_PERM_WRITE | BLK_PERM_RESIZE;
} else {
shared = 0;
}
shared |= BLK_PERM_CONSISTENT_READ | BLK_PERM_GRAPH_MOD |
BLK_PERM_WRITE_UNCHANGED;
}
if (bs->open_flags & BDRV_O_INACTIVE) {
shared |= BLK_PERM_WRITE | BLK_PERM_RESIZE;
}
*nperm = perm;
*nshared = shared;
}
static void bdrv_replace_child_noperm(BdrvChild *child,
BlockDriverState *new_bs)
{
BlockDriverState *old_bs = child->bs;
int i;
if (old_bs && new_bs) {
assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
}
if (old_bs) {
/* Detach first so that the recursive drain sections coming from @child
* are already gone and we only end the drain sections that came from
* elsewhere. */
if (child->role->detach) {
child->role->detach(child);
}
if (old_bs->quiesce_counter && child->role->drained_end) {
for (i = 0; i < old_bs->quiesce_counter; i++) {
child->role->drained_end(child);
}
}
QLIST_REMOVE(child, next_parent);
}
child->bs = new_bs;
if (new_bs) {
QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
if (new_bs->quiesce_counter && child->role->drained_begin) {
for (i = 0; i < new_bs->quiesce_counter; i++) {
child->role->drained_begin(child);
}
}
/* Attach only after starting new drained sections, so that recursive
* drain sections coming from @child don't get an extra .drained_begin
* callback. */
if (child->role->attach) {
child->role->attach(child);
}
}
}
/*
* Updates @child to change its reference to point to @new_bs, including
* checking and applying the necessary permisson updates both to the old node
* and to @new_bs.
*
* NULL is passed as @new_bs for removing the reference before freeing @child.
*
* If @new_bs is not NULL, bdrv_check_perm() must be called beforehand, as this
* function uses bdrv_set_perm() to update the permissions according to the new
* reference that @new_bs gets.
*/
static void bdrv_replace_child(BdrvChild *child, BlockDriverState *new_bs)
{
BlockDriverState *old_bs = child->bs;
uint64_t perm, shared_perm;
bdrv_replace_child_noperm(child, new_bs);
if (old_bs) {
/* Update permissions for old node. This is guaranteed to succeed
* because we're just taking a parent away, so we're loosening
* restrictions. */
bdrv_get_cumulative_perm(old_bs, &perm, &shared_perm);
bdrv_check_perm(old_bs, NULL, perm, shared_perm, NULL, &error_abort);
bdrv_set_perm(old_bs, perm, shared_perm);
}
if (new_bs) {
bdrv_get_cumulative_perm(new_bs, &perm, &shared_perm);
bdrv_set_perm(new_bs, perm, shared_perm);
}
}
BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs,
const char *child_name,
const BdrvChildRole *child_role,
uint64_t perm, uint64_t shared_perm,
void *opaque, Error **errp)
{
BdrvChild *child;
int ret;
ret = bdrv_check_update_perm(child_bs, NULL, perm, shared_perm, NULL, errp);
if (ret < 0) {
bdrv_abort_perm_update(child_bs);
return NULL;
}
child = g_new(BdrvChild, 1);
*child = (BdrvChild) {
.bs = NULL,
.name = g_strdup(child_name),
.role = child_role,
.perm = perm,
.shared_perm = shared_perm,
.opaque = opaque,
};
/* This performs the matching bdrv_set_perm() for the above check. */
bdrv_replace_child(child, child_bs);
return child;
}
BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs,
BlockDriverState *child_bs,
const char *child_name,
const BdrvChildRole *child_role,
Error **errp)
{
BdrvChild *child;
uint64_t perm, shared_perm;
bdrv_get_cumulative_perm(parent_bs, &perm, &shared_perm);
assert(parent_bs->drv);
assert(bdrv_get_aio_context(parent_bs) == bdrv_get_aio_context(child_bs));
bdrv_child_perm(parent_bs, child_bs, NULL, child_role, NULL,
perm, shared_perm, &perm, &shared_perm);
child = bdrv_root_attach_child(child_bs, child_name, child_role,
perm, shared_perm, parent_bs, errp);
if (child == NULL) {
return NULL;
}
QLIST_INSERT_HEAD(&parent_bs->children, child, next);
return child;
}
static void bdrv_detach_child(BdrvChild *child)
{
if (child->next.le_prev) {
QLIST_REMOVE(child, next);
child->next.le_prev = NULL;
}
bdrv_replace_child(child, NULL);
g_free(child->name);
g_free(child);
}
void bdrv_root_unref_child(BdrvChild *child)
{
BlockDriverState *child_bs;
child_bs = child->bs;
bdrv_detach_child(child);
bdrv_unref(child_bs);
}
void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
{
if (child == NULL) {
return;
}
if (child->bs->inherits_from == parent) {
BdrvChild *c;
/* Remove inherits_from only when the last reference between parent and
* child->bs goes away. */
QLIST_FOREACH(c, &parent->children, next) {
if (c != child && c->bs == child->bs) {
break;
}
}
if (c == NULL) {
child->bs->inherits_from = NULL;
}
}
bdrv_root_unref_child(child);
}
static void bdrv_parent_cb_change_media(BlockDriverState *bs, bool load)
{
BdrvChild *c;
QLIST_FOREACH(c, &bs->parents, next_parent) {
if (c->role->change_media) {
c->role->change_media(c, load);
}
}
}
static void bdrv_parent_cb_resize(BlockDriverState *bs)
{
BdrvChild *c;
QLIST_FOREACH(c, &bs->parents, next_parent) {
if (c->role->resize) {
c->role->resize(c);
}
}
}
/*
* Sets the backing file link of a BDS. A new reference is created; callers
* which don't need their own reference any more must call bdrv_unref().
*/
void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd,
Error **errp)
{
if (backing_hd) {
bdrv_ref(backing_hd);
}
if (bs->backing) {
bdrv_unref_child(bs, bs->backing);
}
if (!backing_hd) {
bs->backing = NULL;
goto out;
}
bs->backing = bdrv_attach_child(bs, backing_hd, "backing", &child_backing,
errp);
if (!bs->backing) {
bdrv_unref(backing_hd);
}
bdrv_refresh_filename(bs);
out:
bdrv_refresh_limits(bs, NULL);
}
/*
* Opens the backing file for a BlockDriverState if not yet open
*
* bdref_key specifies the key for the image's BlockdevRef in the options QDict.
* That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
* TODO Can this be unified with bdrv_open_image()?
*/
int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options,
const char *bdref_key, Error **errp)
{
char *backing_filename = g_malloc0(PATH_MAX);
char *bdref_key_dot;
const char *reference = NULL;
int ret = 0;
BlockDriverState *backing_hd;
QDict *options;
QDict *tmp_parent_options = NULL;
Error *local_err = NULL;
if (bs->backing != NULL) {
goto free_exit;
}
/* NULL means an empty set of options */
if (parent_options == NULL) {
tmp_parent_options = qdict_new();
parent_options = tmp_parent_options;
}
bs->open_flags &= ~BDRV_O_NO_BACKING;
bdref_key_dot = g_strdup_printf("%s.", bdref_key);
qdict_extract_subqdict(parent_options, &options, bdref_key_dot);
g_free(bdref_key_dot);
/*
* Caution: while qdict_get_try_str() is fine, getting non-string
* types would require more care. When @parent_options come from
* -blockdev or blockdev_add, its members are typed according to
* the QAPI schema, but when they come from -drive, they're all
* QString.
*/
reference = qdict_get_try_str(parent_options, bdref_key);
if (reference || qdict_haskey(options, "file.filename")) {
backing_filename[0] = '\0';
} else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
QDECREF(options);
goto free_exit;
} else {
bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX,
&local_err);
if (local_err) {
ret = -EINVAL;
error_propagate(errp, local_err);
QDECREF(options);
goto free_exit;
}
}
if (!bs->drv || !bs->drv->supports_backing) {
ret = -EINVAL;
error_setg(errp, "Driver doesn't support backing files");
QDECREF(options);
goto free_exit;
}
if (!reference &&
bs->backing_format[0] != '\0' && !qdict_haskey(options, "driver")) {
qdict_put_str(options, "driver", bs->backing_format);
}
backing_hd = bdrv_open_inherit(*backing_filename ? backing_filename : NULL,
reference, options, 0, bs, &child_backing,
errp);
if (!backing_hd) {
bs->open_flags |= BDRV_O_NO_BACKING;
error_prepend(errp, "Could not open backing file: ");
ret = -EINVAL;
goto free_exit;
}
bdrv_set_aio_context(backing_hd, bdrv_get_aio_context(bs));
/* Hook up the backing file link; drop our reference, bs owns the
* backing_hd reference now */
bdrv_set_backing_hd(bs, backing_hd, &local_err);
bdrv_unref(backing_hd);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto free_exit;
}
qdict_del(parent_options, bdref_key);
free_exit:
g_free(backing_filename);
QDECREF(tmp_parent_options);
return ret;
}
static BlockDriverState *
bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
BlockDriverState *parent, const BdrvChildRole *child_role,
bool allow_none, Error **errp)
{
BlockDriverState *bs = NULL;
QDict *image_options;
char *bdref_key_dot;
const char *reference;
assert(child_role != NULL);
bdref_key_dot = g_strdup_printf("%s.", bdref_key);
qdict_extract_subqdict(options, &image_options, bdref_key_dot);
g_free(bdref_key_dot);
/*
* Caution: while qdict_get_try_str() is fine, getting non-string
* types would require more care. When @options come from
* -blockdev or blockdev_add, its members are typed according to
* the QAPI schema, but when they come from -drive, they're all
* QString.
*/
reference = qdict_get_try_str(options, bdref_key);
if (!filename && !reference && !qdict_size(image_options)) {
if (!allow_none) {
error_setg(errp, "A block device must be specified for \"%s\"",
bdref_key);
}
QDECREF(image_options);
goto done;
}
bs = bdrv_open_inherit(filename, reference, image_options, 0,
parent, child_role, errp);
if (!bs) {
goto done;
}
done:
qdict_del(options, bdref_key);
return bs;
}
/*
* Opens a disk image whose options are given as BlockdevRef in another block
* device's options.
*
* If allow_none is true, no image will be opened if filename is false and no
* BlockdevRef is given. NULL will be returned, but errp remains unset.
*
* bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
* That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
* The BlockdevRef will be removed from the options QDict.
*/
BdrvChild *bdrv_open_child(const char *filename,
QDict *options, const char *bdref_key,
BlockDriverState *parent,
const BdrvChildRole *child_role,
bool allow_none, Error **errp)
{
BdrvChild *c;
BlockDriverState *bs;
bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role,
allow_none, errp);
if (bs == NULL) {
return NULL;
}
c = bdrv_attach_child(parent, bs, bdref_key, child_role, errp);
if (!c) {
bdrv_unref(bs);
return NULL;
}
return c;
}
/* TODO Future callers may need to specify parent/child_role in order for
* option inheritance to work. Existing callers use it for the root node. */
BlockDriverState *bdrv_open_blockdev_ref(BlockdevRef *ref, Error **errp)
{
BlockDriverState *bs = NULL;
Error *local_err = NULL;
QObject *obj = NULL;
QDict *qdict = NULL;
const char *reference = NULL;
Visitor *v = NULL;
if (ref->type == QTYPE_QSTRING) {
reference = ref->u.reference;
} else {
BlockdevOptions *options = &ref->u.definition;
assert(ref->type == QTYPE_QDICT);
v = qobject_output_visitor_new(&obj);
visit_type_BlockdevOptions(v, NULL, &options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto fail;
}
visit_complete(v, &obj);
qdict = qobject_to(QDict, obj);
qdict_flatten(qdict);
/* bdrv_open_inherit() defaults to the values in bdrv_flags (for
* compatibility with other callers) rather than what we want as the
* real defaults. Apply the defaults here instead. */
qdict_set_default_str(qdict, BDRV_OPT_CACHE_DIRECT, "off");
qdict_set_default_str(qdict, BDRV_OPT_CACHE_NO_FLUSH, "off");
qdict_set_default_str(qdict, BDRV_OPT_READ_ONLY, "off");
}
bs = bdrv_open_inherit(NULL, reference, qdict, 0, NULL, NULL, errp);
obj = NULL;
fail:
qobject_decref(obj);
visit_free(v);
return bs;
}
static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
int flags,
QDict *snapshot_options,
Error **errp)
{
/* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
char *tmp_filename = g_malloc0(PATH_MAX + 1);
int64_t total_size;
QemuOpts *opts = NULL;
BlockDriverState *bs_snapshot = NULL;
Error *local_err = NULL;
int ret;
/* if snapshot, we create a temporary backing file and open it
instead of opening 'filename' directly */
/* Get the required size from the image */
total_size = bdrv_getlength(bs);
if (total_size < 0) {
error_setg_errno(errp, -total_size, "Could not get image size");
goto out;
}
/* Create the temporary image */
ret = get_tmp_filename(tmp_filename, PATH_MAX + 1);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not get temporary filename");
goto out;
}
opts = qemu_opts_create(bdrv_qcow2.create_opts, NULL, 0,
&error_abort);
qemu_opt_set_number(opts, BLOCK_OPT_SIZE, total_size, &error_abort);
ret = bdrv_create(&bdrv_qcow2, tmp_filename, opts, errp);
qemu_opts_del(opts);
if (ret < 0) {
error_prepend(errp, "Could not create temporary overlay '%s': ",
tmp_filename);
goto out;
}
/* Prepare options QDict for the temporary file */
qdict_put_str(snapshot_options, "file.driver", "file");
qdict_put_str(snapshot_options, "file.filename", tmp_filename);
qdict_put_str(snapshot_options, "driver", "qcow2");
bs_snapshot = bdrv_open(NULL, NULL, snapshot_options, flags, errp);
snapshot_options = NULL;
if (!bs_snapshot) {
goto out;
}
/* bdrv_append() consumes a strong reference to bs_snapshot
* (i.e. it will call bdrv_unref() on it) even on error, so in
* order to be able to return one, we have to increase
* bs_snapshot's refcount here */
bdrv_ref(bs_snapshot);
bdrv_append(bs_snapshot, bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
bs_snapshot = NULL;
goto out;
}
out:
QDECREF(snapshot_options);
g_free(tmp_filename);
return bs_snapshot;
}
/*
* Opens a disk image (raw, qcow2, vmdk, ...)
*
* options is a QDict of options to pass to the block drivers, or NULL for an
* empty set of options. The reference to the QDict belongs to the block layer
* after the call (even on failure), so if the caller intends to reuse the
* dictionary, it needs to use QINCREF() before calling bdrv_open.
*
* If *pbs is NULL, a new BDS will be created with a pointer to it stored there.
* If it is not NULL, the referenced BDS will be reused.
*
* The reference parameter may be used to specify an existing block device which
* should be opened. If specified, neither options nor a filename may be given,
* nor can an existing BDS be reused (that is, *pbs has to be NULL).
*/
static BlockDriverState *bdrv_open_inherit(const char *filename,
const char *reference,
QDict *options, int flags,
BlockDriverState *parent,
const BdrvChildRole *child_role,
Error **errp)
{
int ret;
BlockBackend *file = NULL;
BlockDriverState *bs;
BlockDriver *drv = NULL;
const char *drvname;
const char *backing;
Error *local_err = NULL;
QDict *snapshot_options = NULL;
int snapshot_flags = 0;
assert(!child_role || !flags);
assert(!child_role == !parent);
if (reference) {
bool options_non_empty = options ? qdict_size(options) : false;
QDECREF(options);
if (filename || options_non_empty) {
error_setg(errp, "Cannot reference an existing block device with "
"additional options or a new filename");
return NULL;
}
bs = bdrv_lookup_bs(reference, reference, errp);
if (!bs) {
return NULL;
}
bdrv_ref(bs);
return bs;
}
bs = bdrv_new();
/* NULL means an empty set of options */
if (options == NULL) {
options = qdict_new();
}
/* json: syntax counts as explicit options, as if in the QDict */
parse_json_protocol(options, &filename, &local_err);
if (local_err) {
goto fail;
}
bs->explicit_options = qdict_clone_shallow(options);
if (child_role) {
bs->inherits_from = parent;
child_role->inherit_options(&flags, options,
parent->open_flags, parent->options);
}
ret = bdrv_fill_options(&options, filename, &flags, &local_err);
if (local_err) {
goto fail;
}
/*
* Set the BDRV_O_RDWR and BDRV_O_ALLOW_RDWR flags.
* Caution: getting a boolean member of @options requires care.
* When @options come from -blockdev or blockdev_add, members are
* typed according to the QAPI schema, but when they come from
* -drive, they're all QString.
*/
if (g_strcmp0(qdict_get_try_str(options, BDRV_OPT_READ_ONLY), "on") &&
!qdict_get_try_bool(options, BDRV_OPT_READ_ONLY, false)) {
flags |= (BDRV_O_RDWR | BDRV_O_ALLOW_RDWR);
} else {
flags &= ~BDRV_O_RDWR;
}
if (flags & BDRV_O_SNAPSHOT) {
snapshot_options = qdict_new();
bdrv_temp_snapshot_options(&snapshot_flags, snapshot_options,
flags, options);
/* Let bdrv_backing_options() override "read-only" */
qdict_del(options, BDRV_OPT_READ_ONLY);
bdrv_backing_options(&flags, options, flags, options);
}
bs->open_flags = flags;
bs->options = options;
options = qdict_clone_shallow(options);
/* Find the right image format driver */
/* See cautionary note on accessing @options above */
drvname = qdict_get_try_str(options, "driver");
if (drvname) {
drv = bdrv_find_format(drvname);
if (!drv) {
error_setg(errp, "Unknown driver: '%s'", drvname);
goto fail;
}
}
assert(drvname || !(flags & BDRV_O_PROTOCOL));
/* See cautionary note on accessing @options above */
backing = qdict_get_try_str(options, "backing");
if (qobject_to(QNull, qdict_get(options, "backing")) != NULL ||
(backing && *backing == '\0'))
{
if (backing) {
warn_report("Use of \"backing\": \"\" is deprecated; "
"use \"backing\": null instead");
}
flags |= BDRV_O_NO_BACKING;
qdict_del(options, "backing");
}
/* Open image file without format layer. This BlockBackend is only used for
* probing, the block drivers will do their own bdrv_open_child() for the
* same BDS, which is why we put the node name back into options. */
if ((flags & BDRV_O_PROTOCOL) == 0) {
BlockDriverState *file_bs;
file_bs = bdrv_open_child_bs(filename, options, "file", bs,
&child_file, true, &local_err);
if (local_err) {
goto fail;
}
if (file_bs != NULL) {
/* Not requesting BLK_PERM_CONSISTENT_READ because we're only
* looking at the header to guess the image format. This works even
* in cases where a guest would not see a consistent state. */
file = blk_new(0, BLK_PERM_ALL);
blk_insert_bs(file, file_bs, &local_err);
bdrv_unref(file_bs);
if (local_err) {
goto fail;
}
qdict_put_str(options, "file", bdrv_get_node_name(file_bs));
}
}
/* Image format probing */
bs->probed = !drv;
if (!drv && file) {
ret = find_image_format(file, filename, &drv, &local_err);
if (ret < 0) {
goto fail;
}
/*
* This option update would logically belong in bdrv_fill_options(),
* but we first need to open bs->file for the probing to work, while
* opening bs->file already requires the (mostly) final set of options
* so that cache mode etc. can be inherited.
*
* Adding the driver later is somewhat ugly, but it's not an option
* that would ever be inherited, so it's correct. We just need to make
* sure to update both bs->options (which has the full effective
* options for bs) and options (which has file.* already removed).
*/
qdict_put_str(bs->options, "driver", drv->format_name);
qdict_put_str(options, "driver", drv->format_name);
} else if (!drv) {
error_setg(errp, "Must specify either driver or file");
goto fail;
}
/* BDRV_O_PROTOCOL must be set iff a protocol BDS is about to be created */
assert(!!(flags & BDRV_O_PROTOCOL) == !!drv->bdrv_file_open);
/* file must be NULL if a protocol BDS is about to be created
* (the inverse results in an error message from bdrv_open_common()) */
assert(!(flags & BDRV_O_PROTOCOL) || !file);
/* Open the image */
ret = bdrv_open_common(bs, file, options, &local_err);
if (ret < 0) {
goto fail;
}
if (file) {
blk_unref(file);
file = NULL;
}
/* If there is a backing file, use it */
if ((flags & BDRV_O_NO_BACKING) == 0) {
ret = bdrv_open_backing_file(bs, options, "backing", &local_err);
if (ret < 0) {
goto close_and_fail;
}
}
bdrv_refresh_filename(bs);
/* Check if any unknown options were used */
if (qdict_size(options) != 0) {
const QDictEntry *entry = qdict_first(options);
if (flags & BDRV_O_PROTOCOL) {
error_setg(errp, "Block protocol '%s' doesn't support the option "
"'%s'", drv->format_name, entry->key);