blob: 65e81918de8ef6e464d46643621a9a57fb5574fb [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 "config-host.h"
#include "qemu-common.h"
#include "trace.h"
#include "monitor/monitor.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "qemu/module.h"
#include "qapi/qmp/qjson.h"
#include "sysemu/sysemu.h"
#include "qemu/notify.h"
#include "block/coroutine.h"
#include "block/qapi.h"
#include "qmp-commands.h"
#include "qemu/timer.h"
#ifdef CONFIG_BSD
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
#include <sys/queue.h>
#ifndef __DragonFly__
#include <sys/disk.h>
#endif
#endif
#ifdef _WIN32
#include <windows.h>
#endif
struct BdrvDirtyBitmap {
HBitmap *bitmap;
QLIST_ENTRY(BdrvDirtyBitmap) list;
};
#define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress */
static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load);
static BlockDriverAIOCB *bdrv_aio_readv_em(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
static BlockDriverAIOCB *bdrv_aio_writev_em(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
static int coroutine_fn bdrv_co_readv_em(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *iov);
static int coroutine_fn bdrv_co_writev_em(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *iov);
static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags);
static BlockDriverAIOCB *bdrv_co_aio_rw_vector(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BdrvRequestFlags flags,
BlockDriverCompletionFunc *cb,
void *opaque,
bool is_write);
static void coroutine_fn bdrv_co_do_rw(void *opaque);
static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, BdrvRequestFlags flags);
static QTAILQ_HEAD(, BlockDriverState) bdrv_states =
QTAILQ_HEAD_INITIALIZER(bdrv_states);
static QTAILQ_HEAD(, BlockDriverState) graph_bdrv_states =
QTAILQ_HEAD_INITIALIZER(graph_bdrv_states);
static QLIST_HEAD(, BlockDriver) bdrv_drivers =
QLIST_HEAD_INITIALIZER(bdrv_drivers);
/* 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
/* throttling disk I/O limits */
void bdrv_set_io_limits(BlockDriverState *bs,
ThrottleConfig *cfg)
{
int i;
throttle_config(&bs->throttle_state, cfg);
for (i = 0; i < 2; i++) {
qemu_co_enter_next(&bs->throttled_reqs[i]);
}
}
/* this function drain all the throttled IOs */
static bool bdrv_start_throttled_reqs(BlockDriverState *bs)
{
bool drained = false;
bool enabled = bs->io_limits_enabled;
int i;
bs->io_limits_enabled = false;
for (i = 0; i < 2; i++) {
while (qemu_co_enter_next(&bs->throttled_reqs[i])) {
drained = true;
}
}
bs->io_limits_enabled = enabled;
return drained;
}
void bdrv_io_limits_disable(BlockDriverState *bs)
{
bs->io_limits_enabled = false;
bdrv_start_throttled_reqs(bs);
throttle_destroy(&bs->throttle_state);
}
static void bdrv_throttle_read_timer_cb(void *opaque)
{
BlockDriverState *bs = opaque;
qemu_co_enter_next(&bs->throttled_reqs[0]);
}
static void bdrv_throttle_write_timer_cb(void *opaque)
{
BlockDriverState *bs = opaque;
qemu_co_enter_next(&bs->throttled_reqs[1]);
}
/* should be called before bdrv_set_io_limits if a limit is set */
void bdrv_io_limits_enable(BlockDriverState *bs)
{
assert(!bs->io_limits_enabled);
throttle_init(&bs->throttle_state,
QEMU_CLOCK_VIRTUAL,
bdrv_throttle_read_timer_cb,
bdrv_throttle_write_timer_cb,
bs);
bs->io_limits_enabled = true;
}
/* This function makes an IO wait if needed
*
* @nb_sectors: the number of sectors of the IO
* @is_write: is the IO a write
*/
static void bdrv_io_limits_intercept(BlockDriverState *bs,
unsigned int bytes,
bool is_write)
{
/* does this io must wait */
bool must_wait = throttle_schedule_timer(&bs->throttle_state, is_write);
/* if must wait or any request of this type throttled queue the IO */
if (must_wait ||
!qemu_co_queue_empty(&bs->throttled_reqs[is_write])) {
qemu_co_queue_wait(&bs->throttled_reqs[is_write]);
}
/* the IO will be executed, do the accounting */
throttle_account(&bs->throttle_state, is_write, bytes);
/* if the next request must wait -> do nothing */
if (throttle_schedule_timer(&bs->throttle_state, is_write)) {
return;
}
/* else queue next request for execution */
qemu_co_queue_next(&bs->throttled_reqs[is_write]);
}
size_t bdrv_opt_mem_align(BlockDriverState *bs)
{
if (!bs || !bs->drv) {
/* 4k should be on the safe side */
return 4096;
}
return bs->bl.opt_mem_alignment;
}
/* check if the path starts with "<protocol>:" */
static 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 {
p = strchr(base_path, ':');
if (p)
p++;
else
p = 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);
}
}
void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz)
{
if (bs->backing_file[0] == '\0' || path_has_protocol(bs->backing_file)) {
pstrcpy(dest, sz, bs->backing_file);
} else {
path_combine(dest, sz, bs->filename, bs->backing_file);
}
}
void bdrv_register(BlockDriver *bdrv)
{
/* Block drivers without coroutine functions need emulation */
if (!bdrv->bdrv_co_readv) {
bdrv->bdrv_co_readv = bdrv_co_readv_em;
bdrv->bdrv_co_writev = bdrv_co_writev_em;
/* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
* the block driver lacks aio we need to emulate that too.
*/
if (!bdrv->bdrv_aio_readv) {
/* add AIO emulation layer */
bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
}
}
QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
}
/* create a new block device (by default it is empty) */
BlockDriverState *bdrv_new(const char *device_name, Error **errp)
{
BlockDriverState *bs;
if (bdrv_find(device_name)) {
error_setg(errp, "Device with id '%s' already exists",
device_name);
return NULL;
}
if (bdrv_find_node(device_name)) {
error_setg(errp, "Device with node-name '%s' already exists",
device_name);
return NULL;
}
bs = g_malloc0(sizeof(BlockDriverState));
QLIST_INIT(&bs->dirty_bitmaps);
pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
if (device_name[0] != '\0') {
QTAILQ_INSERT_TAIL(&bdrv_states, bs, device_list);
}
bdrv_iostatus_disable(bs);
notifier_list_init(&bs->close_notifiers);
notifier_with_return_list_init(&bs->before_write_notifiers);
qemu_co_queue_init(&bs->throttled_reqs[0]);
qemu_co_queue_init(&bs->throttled_reqs[1]);
bs->refcnt = 1;
return bs;
}
void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify)
{
notifier_list_add(&bs->close_notifiers, notify);
}
BlockDriver *bdrv_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;
}
static 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;
}
BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
bool read_only)
{
BlockDriver *drv = bdrv_find_format(format_name);
return drv && bdrv_is_whitelisted(drv, read_only) ? drv : NULL;
}
typedef struct CreateCo {
BlockDriver *drv;
char *filename;
QEMUOptionParameter *options;
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_create(cco->filename, cco->options, &local_err);
if (local_err) {
error_propagate(&cco->err, local_err);
}
cco->ret = ret;
}
int bdrv_create(BlockDriver *drv, const char* filename,
QEMUOptionParameter *options, Error **errp)
{
int ret;
Coroutine *co;
CreateCo cco = {
.drv = drv,
.filename = g_strdup(filename),
.options = options,
.ret = NOT_DONE,
.err = NULL,
};
if (!drv->bdrv_create) {
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);
qemu_coroutine_enter(co, &cco);
while (cco.ret == NOT_DONE) {
qemu_aio_wait();
}
}
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, QEMUOptionParameter *options,
Error **errp)
{
BlockDriver *drv;
Error *local_err = NULL;
int ret;
drv = bdrv_find_protocol(filename, true);
if (drv == NULL) {
error_setg(errp, "Could not find protocol for file '%s'", filename);
return -ENOENT;
}
ret = bdrv_create(drv, filename, options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
}
return ret;
}
int bdrv_refresh_limits(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
memset(&bs->bl, 0, sizeof(bs->bl));
if (!drv) {
return 0;
}
/* Take some limits from the children as a default */
if (bs->file) {
bdrv_refresh_limits(bs->file);
bs->bl.opt_transfer_length = bs->file->bl.opt_transfer_length;
bs->bl.opt_mem_alignment = bs->file->bl.opt_mem_alignment;
} else {
bs->bl.opt_mem_alignment = 512;
}
if (bs->backing_hd) {
bdrv_refresh_limits(bs->backing_hd);
bs->bl.opt_transfer_length =
MAX(bs->bl.opt_transfer_length,
bs->backing_hd->bl.opt_transfer_length);
bs->bl.opt_mem_alignment =
MAX(bs->bl.opt_mem_alignment,
bs->backing_hd->bl.opt_mem_alignment);
}
/* Then let the driver override it */
if (drv->bdrv_refresh_limits) {
return drv->bdrv_refresh_limits(bs);
}
return 0;
}
/*
* 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;
}
BlockDriver *bdrv_find_protocol(const char *filename,
bool allow_protocol_prefix)
{
BlockDriver *drv1;
char protocol[128];
int len;
const char *p;
/* 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_find_format("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';
QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (drv1->protocol_name &&
!strcmp(drv1->protocol_name, protocol)) {
return drv1;
}
}
return NULL;
}
static int find_image_format(BlockDriverState *bs, const char *filename,
BlockDriver **pdrv, Error **errp)
{
int score, score_max;
BlockDriver *drv1, *drv;
uint8_t buf[2048];
int ret = 0;
/* Return the raw BlockDriver * to scsi-generic devices or empty drives */
if (bs->sg || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
drv = bdrv_find_format("raw");
if (!drv) {
error_setg(errp, "Could not find raw image format");
ret = -ENOENT;
}
*pdrv = drv;
return ret;
}
ret = bdrv_pread(bs, 0, buf, sizeof(buf));
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not read image for determining its "
"format");
*pdrv = NULL;
return ret;
}
score_max = 0;
drv = NULL;
QLIST_FOREACH(drv1, &bdrv_drivers, list) {
if (drv1->bdrv_probe) {
score = drv1->bdrv_probe(buf, ret, filename);
if (score > score_max) {
score_max = score;
drv = drv1;
}
}
}
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
*/
static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
{
BlockDriver *drv = bs->drv;
/* Do not attempt drv->bdrv_getlength() on scsi-generic devices */
if (bs->sg)
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;
}
/**
* 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_flags(const char *mode, int *flags)
{
*flags &= ~BDRV_O_CACHE_MASK;
if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
*flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
} else if (!strcmp(mode, "directsync")) {
*flags |= BDRV_O_NOCACHE;
} else if (!strcmp(mode, "writeback")) {
*flags |= BDRV_O_CACHE_WB;
} else if (!strcmp(mode, "unsafe")) {
*flags |= BDRV_O_CACHE_WB;
*flags |= BDRV_O_NO_FLUSH;
} else if (!strcmp(mode, "writethrough")) {
/* this is the default */
} else {
return -1;
}
return 0;
}
/**
* The copy-on-read flag is actually a reference count so multiple users may
* use the feature without worrying about clobbering its previous state.
* Copy-on-read stays enabled until all users have called to disable it.
*/
void bdrv_enable_copy_on_read(BlockDriverState *bs)
{
bs->copy_on_read++;
}
void bdrv_disable_copy_on_read(BlockDriverState *bs)
{
assert(bs->copy_on_read > 0);
bs->copy_on_read--;
}
/*
* Returns the 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 int bdrv_temp_snapshot_flags(int flags)
{
return (flags & ~BDRV_O_SNAPSHOT) | BDRV_O_TEMPORARY;
}
/*
* Returns the flags that bs->file should get, based on the given flags for
* the parent BDS
*/
static int bdrv_inherited_flags(int flags)
{
/* Enable protocol handling, disable format probing for bs->file */
flags |= BDRV_O_PROTOCOL;
/* Our block drivers take care to send flushes and respect unmap policy,
* so we can enable both unconditionally on lower layers. */
flags |= BDRV_O_CACHE_WB | BDRV_O_UNMAP;
/* Clear flags that only apply to the top layer */
flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING | BDRV_O_COPY_ON_READ);
return flags;
}
/*
* Returns the flags that bs->backing_hd should get, based on the given flags
* for the parent BDS
*/
static int bdrv_backing_flags(int flags)
{
/* backing files always opened read-only */
flags &= ~(BDRV_O_RDWR | BDRV_O_COPY_ON_READ);
/* snapshot=on is handled on the top layer */
flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_TEMPORARY);
return flags;
}
static int bdrv_open_flags(BlockDriverState *bs, int flags)
{
int open_flags = flags | BDRV_O_CACHE_WB;
/*
* Clear flags that are internal to the block layer before opening the
* image.
*/
open_flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
/*
* Snapshots should be writable.
*/
if (flags & BDRV_O_TEMPORARY) {
open_flags |= BDRV_O_RDWR;
}
return open_flags;
}
static void bdrv_assign_node_name(BlockDriverState *bs,
const char *node_name,
Error **errp)
{
if (!node_name) {
return;
}
/* empty string node name is invalid */
if (node_name[0] == '\0') {
error_setg(errp, "Empty node name");
return;
}
/* takes care of avoiding namespaces collisions */
if (bdrv_find(node_name)) {
error_setg(errp, "node-name=%s is conflicting with a device id",
node_name);
return;
}
/* takes care of avoiding duplicates node names */
if (bdrv_find_node(node_name)) {
error_setg(errp, "Duplicate node name");
return;
}
/* 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);
}
/*
* Common part for opening disk images and files
*
* Removes all processed options from *options.
*/
static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
QDict *options, int flags, BlockDriver *drv, Error **errp)
{
int ret, open_flags;
const char *filename;
const char *node_name = NULL;
Error *local_err = NULL;
assert(drv != NULL);
assert(bs->file == NULL);
assert(options != NULL && bs->options != options);
if (file != NULL) {
filename = file->filename;
} else {
filename = qdict_get_try_str(options, "filename");
}
if (drv->bdrv_needs_filename && !filename) {
error_setg(errp, "The '%s' block driver requires a file name",
drv->format_name);
return -EINVAL;
}
trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
node_name = qdict_get_try_str(options, "node-name");
bdrv_assign_node_name(bs, node_name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
qdict_del(options, "node-name");
/* bdrv_open() with directly using a protocol as drv. This layer is already
* opened, so assign it to bs (while file becomes a closed BlockDriverState)
* and return immediately. */
if (file != NULL && drv->bdrv_file_open) {
bdrv_swap(file, bs);
return 0;
}
bs->open_flags = flags;
bs->guest_block_size = 512;
bs->request_alignment = 512;
bs->zero_beyond_eof = true;
open_flags = bdrv_open_flags(bs, flags);
bs->read_only = !(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);
return -ENOTSUP;
}
assert(bs->copy_on_read == 0); /* bdrv_new() and bdrv_close() make it so */
if (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");
return -EINVAL;
}
}
if (filename != NULL) {
pstrcpy(bs->filename, sizeof(bs->filename), filename);
} else {
bs->filename[0] = '\0';
}
bs->drv = drv;
bs->opaque = g_malloc0(drv->instance_size);
bs->enable_write_cache = !!(flags & BDRV_O_CACHE_WB);
/* Open the image, either directly or using a protocol */
if (drv->bdrv_file_open) {
assert(file == NULL);
assert(!drv->bdrv_needs_filename || filename != NULL);
ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
} else {
if (file == NULL) {
error_setg(errp, "Can't use '%s' as a block driver for the "
"protocol level", drv->format_name);
ret = -EINVAL;
goto free_and_fail;
}
bs->file = file;
ret = drv->bdrv_open(bs, options, open_flags, &local_err);
}
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 free_and_fail;
}
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
goto free_and_fail;
}
bdrv_refresh_limits(bs);
assert(bdrv_opt_mem_align(bs) != 0);
assert((bs->request_alignment != 0) || bs->sg);
return 0;
free_and_fail:
bs->file = NULL;
g_free(bs->opaque);
bs->opaque = NULL;
bs->drv = NULL;
return ret;
}
/*
* Opens a file using a protocol (file, host_device, nbd, ...)
*
* options is an indirect pointer to a QDict of options to pass to the block
* drivers, or pointer to NULL for an empty set of options. If this function
* takes ownership of the QDict reference, it will set *options to NULL;
* otherwise, it will contain unused/unrecognized options after this function
* returns. Then, the caller is responsible for freeing it. If it intends to
* reuse the QDict, QINCREF() should be called beforehand.
*/
static int bdrv_file_open(BlockDriverState *bs, const char *filename,
QDict **options, int flags, Error **errp)
{
BlockDriver *drv;
const char *drvname;
bool parse_filename = false;
Error *local_err = NULL;
int ret;
/* Fetch the file name from the options QDict if necessary */
if (!filename) {
filename = qdict_get_try_str(*options, "filename");
} else if (filename && !qdict_haskey(*options, "filename")) {
qdict_put(*options, "filename", qstring_from_str(filename));
parse_filename = true;
} else {
error_setg(errp, "Can't specify 'file' and 'filename' options at the "
"same time");
ret = -EINVAL;
goto fail;
}
/* Find the right block driver */
drvname = qdict_get_try_str(*options, "driver");
if (drvname) {
drv = bdrv_find_format(drvname);
if (!drv) {
error_setg(errp, "Unknown driver '%s'", drvname);
}
qdict_del(*options, "driver");
} else if (filename) {
drv = bdrv_find_protocol(filename, parse_filename);
if (!drv) {
error_setg(errp, "Unknown protocol");
}
} else {
error_setg(errp, "Must specify either driver or file");
drv = NULL;
}
if (!drv) {
/* errp has been set already */
ret = -ENOENT;
goto fail;
}
/* Parse the filename and open it */
if (drv->bdrv_parse_filename && parse_filename) {
drv->bdrv_parse_filename(filename, *options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
if (!drv->bdrv_needs_filename) {
qdict_del(*options, "filename");
} else {
filename = qdict_get_str(*options, "filename");
}
}
if (!drv->bdrv_file_open) {
ret = bdrv_open(&bs, filename, NULL, *options, flags, drv, &local_err);
*options = NULL;
} else {
ret = bdrv_open_common(bs, NULL, *options, flags, drv, &local_err);
}
if (ret < 0) {
error_propagate(errp, local_err);
goto fail;
}
bs->growable = 1;
return 0;
fail:
return ret;
}
/*
* Opens the backing file for a BlockDriverState if not yet open
*
* 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 is transferred to this
* function (even on failure), so if the caller intends to reuse the dictionary,
* it needs to use QINCREF() before calling bdrv_file_open.
*/
int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
{
char *backing_filename = g_malloc0(PATH_MAX);
int ret = 0;
BlockDriver *back_drv = NULL;
Error *local_err = NULL;
if (bs->backing_hd != NULL) {
QDECREF(options);
goto free_exit;
}
/* NULL means an empty set of options */
if (options == NULL) {
options = qdict_new();
}
bs->open_flags &= ~BDRV_O_NO_BACKING;
if (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);
}
if (bs->backing_format[0] != '\0') {
back_drv = bdrv_find_format(bs->backing_format);
}
assert(bs->backing_hd == NULL);
ret = bdrv_open(&bs->backing_hd,
*backing_filename ? backing_filename : NULL, NULL, options,
bdrv_backing_flags(bs->open_flags), back_drv, &local_err);
if (ret < 0) {
bs->backing_hd = NULL;
bs->open_flags |= BDRV_O_NO_BACKING;
error_setg(errp, "Could not open backing file: %s",
error_get_pretty(local_err));
error_free(local_err);
goto free_exit;
}
if (bs->backing_hd->file) {
pstrcpy(bs->backing_file, sizeof(bs->backing_file),
bs->backing_hd->file->filename);
}
/* Recalculate the BlockLimits with the backing file */
bdrv_refresh_limits(bs);
free_exit:
g_free(backing_filename);
return ret;
}
/*
* 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. *pbs will remain unchanged and 0 will be returned.
*
* 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.
*
* To conform with the behavior of bdrv_open(), *pbs has to be NULL.
*/
int bdrv_open_image(BlockDriverState **pbs, const char *filename,
QDict *options, const char *bdref_key, int flags,
bool allow_none, Error **errp)
{
QDict *image_options;
int ret;
char *bdref_key_dot;
const char *reference;
assert(pbs);
assert(*pbs == NULL);
bdref_key_dot = g_strdup_printf("%s.", bdref_key);
qdict_extract_subqdict(options, &image_options, bdref_key_dot);
g_free(bdref_key_dot);
reference = qdict_get_try_str(options, bdref_key);
if (!filename && !reference && !qdict_size(image_options)) {
if (allow_none) {
ret = 0;
} else {
error_setg(errp, "A block device must be specified for \"%s\"",
bdref_key);
ret = -EINVAL;
}
goto done;
}
ret = bdrv_open(pbs, filename, reference, image_options, flags, NULL, errp);
done:
qdict_del(options, bdref_key);
return ret;
}
void bdrv_append_temp_snapshot(BlockDriverState *bs, int flags, 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;
BlockDriver *bdrv_qcow2;
QEMUOptionParameter *create_options;
QDict *snapshot_options;
BlockDriverState *bs_snapshot;
Error *local_err;
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;
}
total_size &= BDRV_SECTOR_MASK;
/* 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;
}
bdrv_qcow2 = bdrv_find_format("qcow2");
create_options = parse_option_parameters("", bdrv_qcow2->create_options,
NULL);
set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options, &local_err);
free_option_parameters(create_options);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not create temporary overlay "
"'%s': %s", tmp_filename,
error_get_pretty(local_err));
error_free(local_err);
goto out;
}
/* Prepare a new options QDict for the temporary file */
snapshot_options = qdict_new();
qdict_put(snapshot_options, "file.driver",
qstring_from_str("file"));
qdict_put(snapshot_options, "file.filename",
qstring_from_str(tmp_filename));
bs_snapshot = bdrv_new("", &error_abort);
ret = bdrv_open(&bs_snapshot, NULL, NULL, snapshot_options,
flags, bdrv_qcow2, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto out;
}
bdrv_append(bs_snapshot, bs);
out:
g_free(tmp_filename);
}
/*
* 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).
*/
int bdrv_open(BlockDriverState **pbs, const char *filename,
const char *reference, QDict *options, int flags,
BlockDriver *drv, Error **errp)
{
int ret;
BlockDriverState *file = NULL, *bs;
const char *drvname;
Error *local_err = NULL;
int snapshot_flags = 0;
assert(pbs);
if (reference) {
bool options_non_empty = options ? qdict_size(options) : false;
QDECREF(options);
if (*pbs) {
error_setg(errp, "Cannot reuse an existing BDS when referencing "
"another block device");
return -EINVAL;
}
if (filename || options_non_empty) {
error_setg(errp, "Cannot reference an existing block device with "
"additional options or a new filename");
return -EINVAL;
}
bs = bdrv_lookup_bs(reference, reference, errp);
if (!bs) {
return -ENODEV;
}
bdrv_ref(bs);
*pbs = bs;
return 0;
}
if (*pbs) {
bs = *pbs;
} else {
bs = bdrv_new("", &error_abort);
}
/* NULL means an empty set of options */
if (options == NULL) {
options = qdict_new();
}
bs->options = options;
options = qdict_clone_shallow(options);
if (flags & BDRV_O_PROTOCOL) {
assert(!drv);
ret = bdrv_file_open(bs, filename, &options, flags & ~BDRV_O_PROTOCOL,
&local_err);
if (!ret) {
drv = bs->drv;
goto done;
} else if (bs->drv) {
goto close_and_fail;
} else {
goto fail;
}
}
/* Open image file without format layer */
if (flags & BDRV_O_RDWR) {
flags |= BDRV_O_ALLOW_RDWR;
}
if (flags & BDRV_O_SNAPSHOT) {
snapshot_flags = bdrv_temp_snapshot_flags(flags);
flags = bdrv_backing_flags(flags);
}
assert(file == NULL);
ret = bdrv_open_image(&file, filename, options, "file",
bdrv_inherited_flags(flags),
true, &local_err);
if (ret < 0) {
goto fail;
}
/* Find the right image format driver */
drvname = qdict_get_try_str(options, "driver");
if (drvname) {
drv = bdrv_find_format(drvname);
qdict_del(options, "driver");
if (!drv) {
error_setg(errp, "Invalid driver: '%s'", drvname);
ret = -EINVAL;
goto fail;
}
}
if (!drv) {
if (file) {
ret = find_image_format(file, filename, &drv, &local_err);
} else {
error_setg(errp, "Must specify either driver or file");
ret = -EINVAL;
goto fail;
}
}
if (!drv) {
goto fail;
}
/* Open the image */
ret = bdrv_open_common(bs, file, options, flags, drv, &local_err);
if (ret < 0) {
goto fail;
}
if (file && (bs->file != file)) {
bdrv_unref(file);
file = NULL;
}
/* If there is a backing file, use it */
if ((flags & BDRV_O_NO_BACKING) == 0) {
QDict *backing_options;
qdict_extract_subqdict(options, &backing_options, "backing.");
ret = bdrv_open_backing_file(bs, backing_options, &local_err);
if (ret < 0) {
goto close_and_fail;
}
}
/* For snapshot=on, create a temporary qcow2 overlay. bs points to the
* temporary snapshot afterwards. */
if (snapshot_flags) {
bdrv_append_temp_snapshot(bs, snapshot_flags, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto close_and_fail;
}
}
done:
/* Check if any unknown options were used */
if (options && (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);
} else {
error_setg(errp, "Block format '%s' used by device '%s' doesn't "
"support the option '%s'", drv->format_name,
bs->device_name, entry->key);
}
ret = -EINVAL;
goto close_and_fail;
}
if (!bdrv_key_required(bs)) {
bdrv_dev_change_media_cb(bs, true);
} else if (!runstate_check(RUN_STATE_PRELAUNCH)
&& !runstate_check(RUN_STATE_INMIGRATE)
&& !runstate_check(RUN_STATE_PAUSED)) { /* HACK */
error_setg(errp,
"Guest must be stopped for opening of encrypted image");
ret = -EBUSY;
goto close_and_fail;
}
QDECREF(options);
*pbs = bs;
return 0;
fail:
if (file != NULL) {
bdrv_unref(file);
}
QDECREF(bs->options);
QDECREF(options);
bs->options = NULL;
if (!*pbs) {
/* If *pbs is NULL, a new BDS has been created in this function and
needs to be freed now. Otherwise, it does not need to be closed,
since it has not really been opened yet. */
bdrv_unref(bs);
}
if (local_err) {
error_propagate(errp, local_err);
}
return ret;
close_and_fail:
/* See fail path, but now the BDS has to be always closed */
if (*pbs) {
bdrv_close(bs);
} else {
bdrv_unref(bs);
}
QDECREF(options);
if (local_err) {
error_propagate(errp, local_err);
}
return ret;
}
typedef struct BlockReopenQueueEntry {
bool prepared;
BDRVReopenState state;
QSIMPLEQ_ENTRY(BlockReopenQueueEntry) entry;
} BlockReopenQueueEntry;
/*
* Adds a BlockDriverState to a simple queue for an atomic, transactional
* reopen of multiple devices.
*
* bs_queue can either be an existing BlockReopenQueue that has had QSIMPLE_INIT
* already performed, or alternatively may be NULL a new BlockReopenQueue will
* be created and initialized. This newly created BlockReopenQueue should be
* passed back in for subsequent calls that are intended to be of the same
* atomic 'set'.
*
* bs is the BlockDriverState to add to the reopen queue.
*
* flags contains the open flags for the associated bs
*
* returns a pointer to bs_queue, which is either the newly allocated
* bs_queue, or the existing bs_queue being used.
*
*/
BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
BlockDriverState *bs, int flags)
{
assert(bs != NULL);
BlockReopenQueueEntry *bs_entry;
if (bs_queue == NULL) {
bs_queue = g_new0(BlockReopenQueue, 1);
QSIMPLEQ_INIT(bs_queue);
}
/* bdrv_open() masks this flag out */
flags &= ~BDRV_O_PROTOCOL;
if (bs->file) {
bdrv_reopen_queue(bs_queue, bs->file, bdrv_inherited_flags(flags));
}
bs_entry = g_new0(BlockReopenQueueEntry, 1);
QSIMPLEQ_INSERT_TAIL(bs_queue, bs_entry, entry);
bs_entry->state.bs = bs;
bs_entry->state.flags = flags;
return bs_queue;
}
/*
* Reopen multiple BlockDriverStates atomically & transactionally.
*
* The queue passed in (bs_queue) must have been built up previous
* via bdrv_reopen_queue().
*
* Reopens all BDS specified in the queue, with the appropriate
* flags. All devices are prepared for reopen, and failure of any
* device will cause all device changes to be abandonded, and intermediate
* data cleaned up.
*
* If all devices prepare successfully, then the changes are committed
* to all devices.
*
*/
int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
{
int ret = -1;
BlockReopenQueueEntry *bs_entry, *next;
Error *local_err = NULL;
assert(bs_queue != NULL);
bdrv_drain_all();
QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) {
error_propagate(errp, local_err);
goto cleanup;
}
bs_entry->prepared = true;
}
/* If we reach this point, we have success and just need to apply the
* changes
*/
QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
bdrv_reopen_commit(&bs_entry->state);
}
ret = 0;
cleanup:
QSIMPLEQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
if (ret && bs_entry->prepared) {
bdrv_reopen_abort(&bs_entry->state);
}
g_free(bs_entry);
}
g_free(bs_queue);
return ret;
}
/* Reopen a single BlockDriverState with the specified flags. */
int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp)
{
int ret = -1;
Error *local_err = NULL;
BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, bdrv_flags);
ret = bdrv_reopen_multiple(queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
}
return ret;
}
/*
* Prepares a BlockDriverState for reopen. All changes are staged in the
* 'opaque' field of the BDRVReopenState, which is used and allocated by
* the block driver layer .bdrv_reopen_prepare()
*
* bs is the BlockDriverState to reopen
* flags are the new open flags
* queue is the reopen queue
*
* Returns 0 on success, non-zero on error. On error errp will be set
* as well.
*
* On failure, bdrv_reopen_abort() will be called to clean up any data.
* It is the responsibility of the caller to then call the abort() or
* commit() for any other BDS that have been left in a prepare() state
*
*/
int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
Error **errp)
{
int ret = -1;
Error *local_err = NULL;
BlockDriver *drv;
assert(reopen_state != NULL);
assert(reopen_state->bs->drv != NULL);
drv = reopen_state->bs->drv;
/* if we are to stay read-only, do not allow permission change
* to r/w */
if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
reopen_state->flags & BDRV_O_RDWR) {
error_set(errp, QERR_DEVICE_IS_READ_ONLY,
reopen_state->bs->device_name);
goto error;
}
ret = bdrv_flush(reopen_state->bs);
if (ret) {
error_set(errp, ERROR_CLASS_GENERIC_ERROR, "Error (%s) flushing drive",
strerror(-ret));
goto error;
}
if (drv->bdrv_reopen_prepare) {
ret = drv->bdrv_reopen_prepare(reopen_state, queue, &local_err);
if (ret) {
if (local_err != NULL) {
error_propagate(errp, local_err);
} else {
error_setg(errp, "failed while preparing to reopen image '%s'",
reopen_state->bs->filename);
}
goto error;
}
} else {
/* It is currently mandatory to have a bdrv_reopen_prepare()
* handler for each supported drv. */
error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
drv->format_name, reopen_state->bs->device_name,
"reopening of file");
ret = -1;
goto error;
}
ret = 0;
error:
return ret;
}
/*
* Takes the staged changes for the reopen from bdrv_reopen_prepare(), and
* makes them final by swapping the staging BlockDriverState contents into
* the active BlockDriverState contents.
*/
void bdrv_reopen_commit(BDRVReopenState *reopen_state)
{
BlockDriver *drv;
assert(reopen_state != NULL);
drv = reopen_state->bs->drv;
assert(drv != NULL);
/* If there are any driver level actions to take */
if (drv->bdrv_reopen_commit) {
drv->bdrv_reopen_commit(reopen_state);
}
/* set BDS specific flags now */
reopen_state->bs->open_flags = reopen_state->flags;
reopen_state->bs->enable_write_cache = !!(reopen_state->flags &
BDRV_O_CACHE_WB);
reopen_state->bs->read_only = !(reopen_state->flags & BDRV_O_RDWR);
bdrv_refresh_limits(reopen_state->bs);
}
/*
* Abort the reopen, and delete and free the staged changes in
* reopen_state
*/
void bdrv_reopen_abort(BDRVReopenState *reopen_state)
{
BlockDriver *drv;
assert(reopen_state != NULL);
drv = reopen_state->bs->drv;
assert(drv != NULL);
if (drv->bdrv_reopen_abort) {
drv->bdrv_reopen_abort(reopen_state);
}
}
void bdrv_close(BlockDriverState *bs)
{
if (bs->job) {
block_job_cancel_sync(bs->job);
}
bdrv_drain_all(); /* complete I/O */
bdrv_flush(bs);
bdrv_drain_all(); /* in case flush left pending I/O */
notifier_list_notify(&bs->close_notifiers, bs);
if (bs->drv) {
if (bs->backing_hd) {
bdrv_unref(bs->backing_hd);
bs->backing_hd = NULL;
}
bs->drv->bdrv_close(bs);
g_free(bs->opaque);
bs->opaque = NULL;
bs->drv = NULL;
bs->copy_on_read = 0;
bs->backing_file[0] = '\0';
bs->backing_format[0] = '\0';
bs->total_sectors = 0;
bs->encrypted = 0;
bs->valid_key = 0;
bs->sg = 0;
bs->growable = 0;
bs->zero_beyond_eof = false;
QDECREF(bs->options);
bs->options = NULL;
if (bs->file != NULL) {
bdrv_unref(bs->file);
bs->file = NULL;
}
}
bdrv_dev_change_media_cb(bs, false);
/*throttling disk I/O limits*/
if (bs->io_limits_enabled) {
bdrv_io_limits_disable(bs);
}
}
void bdrv_close_all(void)
{
BlockDriverState *bs;
QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
bdrv_close(bs);
}
}
/* Check if any requests are in-flight (including throttled requests) */
static bool bdrv_requests_pending(BlockDriverState *bs)
{
if (!QLIST_EMPTY(&bs->tracked_requests)) {
return true;
}
if (!qemu_co_queue_empty(&bs->throttled_reqs[0])) {
return true;
}
if (!qemu_co_queue_empty(&bs->throttled_reqs[1])) {
return true;
}
if (bs->file && bdrv_requests_pending(bs->file)) {
return true;
}
if (bs->backing_hd && bdrv_requests_pending(bs->backing_hd)) {
return true;
}
return false;
}
static bool bdrv_requests_pending_all(void)
{
BlockDriverState *bs;
QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
if (bdrv_requests_pending(bs)) {
return true;
}
}
return false;
}
/*
* Wait for pending requests to complete across all BlockDriverStates
*
* This function does not flush data to disk, use bdrv_flush_all() for that
* after calling this function.
*
* Note that completion of an asynchronous I/O operation can trigger any
* number of other I/O operations on other devices---for example a coroutine
* can be arbitrarily complex and a constant flow of I/O can come until the
* coroutine is complete. Because of this, it is not possible to have a
* function to drain a single device's I/O queue.
*/
void bdrv_drain_all(void)
{
/* Always run first iteration so any pending completion BHs run */
bool busy = true;
BlockDriverState *bs;
while (busy) {
QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
bdrv_start_throttled_reqs(bs);
}
busy = bdrv_requests_pending_all();
busy |= aio_poll(qemu_get_aio_context(), busy);
}
}
/* make a BlockDriverState anonymous by removing from bdrv_state and
* graph_bdrv_state list.
Also, NULL terminate the device_name to prevent double remove */
void bdrv_make_anon(BlockDriverState *bs)
{
if (bs->device_name[0] != '\0') {
QTAILQ_REMOVE(&bdrv_states, bs, device_list);
}
bs->device_name[0] = '\0';
if (bs->node_name[0] != '\0') {
QTAILQ_REMOVE(&graph_bdrv_states, bs, node_list);
}
bs->node_name[0] = '\0';
}
static void bdrv_rebind(BlockDriverState *bs)
{
if (bs->drv && bs->drv->bdrv_rebind) {
bs->drv->bdrv_rebind(bs);
}
}
static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
BlockDriverState *bs_src)
{
/* move some fields that need to stay attached to the device */
/* dev info */
bs_dest->dev_ops = bs_src->dev_ops;
bs_dest->dev_opaque = bs_src->dev_opaque;
bs_dest->dev = bs_src->dev;
bs_dest->guest_block_size = bs_src->guest_block_size;
bs_dest->copy_on_read = bs_src->copy_on_read;
bs_dest->enable_write_cache = bs_src->enable_write_cache;
/* i/o throttled req */
memcpy(&bs_dest->throttle_state,
&bs_src->throttle_state,
sizeof(ThrottleState));
bs_dest->throttled_reqs[0] = bs_src->throttled_reqs[0];
bs_dest->throttled_reqs[1] = bs_src->throttled_reqs[1];
bs_dest->io_limits_enabled = bs_src->io_limits_enabled;
/* r/w error */
bs_dest->on_read_error = bs_src->on_read_error;
bs_dest->on_write_error = bs_src->on_write_error;
/* i/o status */
bs_dest->iostatus_enabled = bs_src->iostatus_enabled;
bs_dest->iostatus = bs_src->iostatus;
/* dirty bitmap */
bs_dest->dirty_bitmaps = bs_src->dirty_bitmaps;
/* reference count */
bs_dest->refcnt = bs_src->refcnt;
/* job */
bs_dest->in_use = bs_src->in_use;
bs_dest->job = bs_src->job;
/* keep the same entry in bdrv_states */
pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
bs_src->device_name);
bs_dest->device_list = bs_src->device_list;
}
/*
* Swap bs contents for two image chains while they are live,
* while keeping required fields on the BlockDriverState that is
* actually attached to a device.
*
* This will modify the BlockDriverState fields, and swap contents
* between bs_new and bs_old. Both bs_new and bs_old are modified.
*
* bs_new is required to be anonymous.
*
* This function does not create any image files.
*/
void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
{
BlockDriverState tmp;
/* The code needs to swap the node_name but simply swapping node_list won't
* work so first remove the nodes from the graph list, do the swap then
* insert them back if needed.
*/
if (bs_new->node_name[0] != '\0') {
QTAILQ_REMOVE(&graph_bdrv_states, bs_new, node_list);
}
if (bs_old->node_name[0] != '\0') {
QTAILQ_REMOVE(&graph_bdrv_states, bs_old, node_list);
}
/* bs_new must be anonymous and shouldn't have anything fancy enabled */
assert(bs_new->device_name[0] == '\0');
assert(QLIST_EMPTY(&bs_new->dirty_bitmaps));
assert(bs_new->job == NULL);
assert(bs_new->dev == NULL);
assert(bs_new->in_use == 0);
assert(bs_new->io_limits_enabled == false);
assert(!throttle_have_timer(&bs_new->throttle_state));
tmp = *bs_new;
*bs_new = *bs_old;
*bs_old = tmp;
/* there are some fields that should not be swapped, move them back */
bdrv_move_feature_fields(&tmp, bs_old);
bdrv_move_feature_fields(bs_old, bs_new);
bdrv_move_feature_fields(bs_new, &tmp);
/* bs_new shouldn't be in bdrv_states even after the swap! */
assert(bs_new->device_name[0] == '\0');
/* Check a few fields that should remain attached to the device */
assert(bs_new->dev == NULL);
assert(bs_new->job == NULL);
assert(bs_new->in_use == 0);
assert(bs_new->io_limits_enabled == false);
assert(!throttle_have_timer(&bs_new->throttle_state));
/* insert the nodes back into the graph node list if needed */
if (bs_new->node_name[0] != '\0') {
QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs_new, node_list);
}
if (bs_old->node_name[0] != '\0') {
QTAILQ_INSERT_TAIL(&graph_bdrv_states, bs_old, node_list);
}
bdrv_rebind(bs_new);
bdrv_rebind(bs_old);
}
/*
* Add new bs contents at the top of an image chain while the chain is
* live, while keeping required fields on the top layer.
*
* This will modify the BlockDriverState fields, and swap contents
* between bs_new and bs_top. Both bs_new and bs_top are modified.
*
* bs_new is required to be anonymous.
*
* This function does not create any image files.
*/
void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
{
bdrv_swap(bs_new, bs_top);
/* The contents of 'tmp' will become bs_top, as we are
* swapping bs_new and bs_top contents. */
bs_top->backing_hd = bs_new;
bs_top->open_flags &= ~BDRV_O_NO_BACKING;
pstrcpy(bs_top->backing_file, sizeof(bs_top->backing_file),
bs_new->filename);
pstrcpy(bs_top->backing_format, sizeof(bs_top->backing_format),
bs_new->drv ? bs_new->drv->format_name : "");
}
static void bdrv_delete(BlockDriverState *bs)
{
assert(!bs->dev);
assert(!bs->job);
assert(!bs->in_use);
assert(!bs->refcnt);
assert(QLIST_EMPTY(&bs->dirty_bitmaps));
bdrv_close(bs);
/* remove from list, if necessary */
bdrv_make_anon(bs);
g_free(bs);
}
int bdrv_attach_dev(BlockDriverState *bs, void *dev)
/* TODO change to DeviceState *dev when all users are qdevified */
{
if (bs->dev) {
return -EBUSY;
}
bs->dev = dev;
bdrv_iostatus_reset(bs);
return 0;
}
/* TODO qdevified devices don't use this, remove when devices are qdevified */
void bdrv_attach_dev_nofail(BlockDriverState *bs, void *dev)
{
if (bdrv_attach_dev(bs, dev) < 0) {
abort();
}
}
void bdrv_detach_dev(BlockDriverState *bs, void *dev)
/* TODO change to DeviceState *dev when all users are qdevified */
{
assert(bs->dev == dev);
bs->dev = NULL;
bs->dev_ops = NULL;
bs->dev_opaque = NULL;
bs->guest_block_size = 512;
}
/* TODO change to return DeviceState * when all users are qdevified */
void *bdrv_get_attached_dev(BlockDriverState *bs)
{
return bs->dev;
}
void bdrv_set_dev_ops(BlockDriverState *bs, const BlockDevOps *ops,
void *opaque)
{
bs->dev_ops = ops;
bs->dev_opaque = opaque;
}
void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
enum MonitorEvent ev,
BlockErrorAction action, bool is_read)
{
QObject *data;
const char *action_str;
switch (action) {
case BDRV_ACTION_REPORT:
action_str = "report";
break;
case BDRV_ACTION_IGNORE:
action_str = "ignore";
break;
case BDRV_ACTION_STOP:
action_str = "stop";
break;
default:
abort();
}
data = qobject_from_jsonf("{ 'device': %s, 'action': %s, 'operation': %s }",
bdrv->device_name,
action_str,
is_read ? "read" : "write");
monitor_protocol_event(ev, data);
qobject_decref(data);
}
static void bdrv_emit_qmp_eject_event(BlockDriverState *bs, bool ejected)
{
QObject *data;
data = qobject_from_jsonf("{ 'device': %s, 'tray-open': %i }",
bdrv_get_device_name(bs), ejected);
monitor_protocol_event(QEVENT_DEVICE_TRAY_MOVED, data);
qobject_decref(data);
}
static void bdrv_dev_change_media_cb(BlockDriverState *bs, bool load)
{
if (bs->dev_ops && bs->dev_ops->change_media_cb) {
bool tray_was_closed = !bdrv_dev_is_tray_open(bs);
bs->dev_ops->change_media_cb(bs->dev_opaque, load);
if (tray_was_closed) {
/* tray open */
bdrv_emit_qmp_eject_event(bs, true);
}
if (load) {
/* tray close */
bdrv_emit_qmp_eject_event(bs, false);
}
}
}
bool bdrv_dev_has_removable_media(BlockDriverState *bs)
{
return !bs->dev || (bs->dev_ops && bs->dev_ops->change_media_cb);
}
void bdrv_dev_eject_request(BlockDriverState *bs, bool force)
{
if (bs->dev_ops && bs->dev_ops->eject_request_cb) {
bs->dev_ops->eject_request_cb(bs->dev_opaque, force);
}
}
bool bdrv_dev_is_tray_open(BlockDriverState *bs)
{
if (bs->dev_ops && bs->dev_ops->is_tray_open) {
return bs->dev_ops->is_tray_open(bs->dev_opaque);
}
return false;
}
static void bdrv_dev_resize_cb(BlockDriverState *bs)
{
if (bs->dev_ops && bs->dev_ops->resize_cb) {
bs->dev_ops->resize_cb(bs->dev_opaque);
}
}
bool bdrv_dev_is_medium_locked(BlockDriverState *bs)
{
if (bs->dev_ops && bs->dev_ops->is_medium_locked) {
return bs->dev_ops->is_medium_locked(bs->dev_opaque);
}
return false;
}
/*
* Run consistency checks on an image
*
* Returns 0 if the check could be completed (it doesn't mean that the image is
* free of errors) or -errno when an internal error occurred. The results of the
* check are stored in res.
*/
int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix)
{
if (bs->drv->bdrv_check == NULL) {
return -ENOTSUP;
}
memset(res, 0, sizeof(*res));
return bs->drv->bdrv_check(bs, res, fix);
}
#define COMMIT_BUF_SECTORS 2048
/* commit COW file into the raw image */
int bdrv_commit(BlockDriverState *bs)
{
BlockDriver *drv = bs->drv;
int64_t sector, total_sectors, length, backing_length;
int n, ro, open_flags;
int ret = 0;
uint8_t *buf = NULL;
char filename[PATH_MAX];
if (!drv)
return -ENOMEDIUM;
if (!bs->backing_hd) {
return -ENOTSUP;
}
if (bdrv_in_use(bs) || bdrv_in_use(bs->backing_hd)) {
return -EBUSY;
}
ro = bs->backing_hd->read_only;
/* Use pstrcpy (not strncpy): filename must be NUL-terminated. */
pstrcpy(filename, sizeof(filename), bs->backing_hd->filename);
open_flags = bs->backing_hd->open_flags;
if (ro) {
if (bdrv_reopen(bs->backing_hd, open_flags | BDRV_O_RDWR, NULL)) {
return -EACCES;
}
}
length = bdrv_getlength(bs);
if (length < 0) {
ret = length;
goto ro_cleanup;
}
backing_length = bdrv_getlength(bs->backing_hd);
if (backing_length < 0) {
ret = backing_length;
goto ro_cleanup;
}
/* If our top snapshot is larger than the backing file image,
* grow the backing file image if possible. If not possible,
* we must return an error */
if (length > backing_length) {
ret = bdrv_truncate(bs->backing_hd, length);
if (ret < 0) {
goto ro_cleanup;
}
}
total_sectors = length >> BDRV_SECTOR_BITS;
buf = g_malloc(COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
for (sector = 0; sector < total_sectors; sector += n) {
ret = bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n);
if (ret < 0) {
goto ro_cleanup;
}
if (ret) {
ret = bdrv_read(bs, sector, buf, n);
if (ret < 0) {
goto ro_cleanup;
}
ret = bdrv_write(bs->backing_hd, sector, buf, n);
if (ret < 0) {
goto ro_cleanup;
}
}
}
if (drv->bdrv_make_empty) {
ret = drv->bdrv_make_empty(bs);
if (ret < 0) {
goto ro_cleanup;
}
bdrv_flush(bs);
}
/*
* Make sure all data we wrote to the backing device is actually
* stable on disk.
*/
if (bs->backing_hd) {
bdrv_flush(bs->backing_hd);
}
ret = 0;
ro_cleanup:
g_free(buf);
if (ro) {
/* ignoring error return here */
bdrv_reopen(bs->backing_hd, open_flags & ~BDRV_O_RDWR, NULL);
}
return ret;
}
int bdrv_commit_all(void)
{
BlockDriverState *bs;
QTAILQ_FOREACH(bs, &bdrv_states, device_list) {
if (bs->drv && bs->backing_hd) {
int ret = bdrv_commit(bs);
if (ret < 0) {
return ret;
}
}
}
return 0;
}
/**
* Remove an active request from the tracked requests list
*
* This function should be called when a tracked request is completing.
*/
static void tracked_request_end(BdrvTrackedRequest *req)
{
if (req->serialising) {
req->bs->serialising_in_flight--;
}
QLIST_REMOVE(req, list);
qemu_co_queue_restart_all(&req->wait_queue);
}
/**
* Add an active request to the tracked requests list
*/
static void tracked_request_begin(BdrvTrackedRequest *req,
BlockDriverState *bs,
int64_t offset,
unsigned int bytes, bool is_write)
{
*req = (BdrvTrackedRequest){
.bs = bs,
.offset = offset,
.bytes = bytes,
.is_write = is_write,
.co = qemu_coroutine_self(),
.serialising = false,
.overlap_offset = offset,
.overlap_bytes = bytes,
};
qemu_co_queue_init(&req->wait_queue);
QLIST_INSERT_HEAD(&bs->tracked_requests, req, list);
}
static void mark_request_serialising(BdrvTrackedRequest *req, uint64_t align)
{
int64_t overlap_offset = req->offset & ~(align - 1);
unsigned int overlap_bytes = ROUND_UP(req->offset + req->bytes, align)
- overlap_offset;
if (!req->serialising) {
req->bs->serialising_in_flight++;
req->serialising = true;
}
req->overlap_offset = MIN(req->overlap_offset, overlap_offset);
req->overlap_bytes = MAX(req->overlap_bytes, overlap_bytes);
}
/**
* Round a region to cluster boundaries
*/
void bdrv_round_to_clusters(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
int64_t *cluster_sector_num,
int *cluster_nb_sectors)
{
BlockDriverInfo bdi;
if (bdrv_get_info(bs, &bdi) < 0 || bdi.cluster_size == 0) {
*cluster_sector_num = sector_num;
*cluster_nb_sectors = nb_sectors;
} else {
int64_t c = bdi.cluster_size / BDRV_SECTOR_SIZE;
*cluster_sector_num = QEMU_ALIGN_DOWN(sector_num, c);
*cluster_nb_sectors = QEMU_ALIGN_UP(sector_num - *cluster_sector_num +
nb_sectors, c);
}
}
static int bdrv_get_cluster_size(BlockDriverState *bs)
{
BlockDriverInfo bdi;
int ret;
ret = bdrv_get_info(bs, &bdi);
if (ret < 0 || bdi.cluster_size == 0) {
return bs->request_alignment;
} else {
return bdi.cluster_size;
}
}
static bool tracked_request_overlaps(BdrvTrackedRequest *req,
int64_t offset, unsigned int bytes)
{
/* aaaa bbbb */
if (offset >= req->overlap_offset + req->overlap_bytes) {
return false;
}
/* bbbb aaaa */
if (req->overlap_offset >= offset + bytes) {
return false;
}
return true;
}
static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self)
{
BlockDriverState *bs = self->bs;
BdrvTrackedRequest *req;
bool retry;
bool waited = false;
if (!bs->serialising_in_flight) {
return false;
}
do {
retry = false;
QLIST_FOREACH(req, &bs->tracked_requests, list) {
if (req == self || (!req->serialising && !self->serialising)) {
continue;
}
if (tracked_request_overlaps(req, self->overlap_offset,
self->overlap_bytes))
{
/* Hitting this means there was a reentrant request, for
* example, a block driver issuing nested requests. This must
* never happen since it means deadlock.
*/
assert(qemu_coroutine_self() != req->co);
/* If the request is already (indirectly) waiting for us, or
* will wait for us as soon as it wakes up, then just go on
* (instead of producing a deadlock in the former case). */
if (!req->waiting_for) {
self->waiting_for = req;
qemu_co_queue_wait(&req->wait_queue);
self->waiting_for = NULL;
retry = true;
waited = true;
break;
}
}
}
} while (retry);
return waited;
}
/*
* Return values:
* 0 - success
* -EINVAL - backing format specified, but no file
* -ENOSPC - can't update the backing file because no space is left in the
* image file header
* -ENOTSUP - format driver doesn't support changing the backing file
*/
int bdrv_change_backing_file(BlockDriverState *bs,
const char *backing_file, const char *backing_fmt)
{
BlockDriver *drv = bs->drv;
int ret;
/* Backing file format doesn't make sense without a backing file */
if (backing_fmt && !backing_file) {
return -EINVAL;
}
if (drv->bdrv_change_backing_file != NULL) {
ret = drv->bdrv_change_backing_file(bs, backing_file, backing_fmt);
} else {
ret = -ENOTSUP;
}
if (ret == 0) {
pstrcpy(bs->backing_file, sizeof(bs->backing_file), backing_file ?: "");
pstrcpy(bs->backing_format, sizeof(bs->backing_format), backing_fmt ?: "");
}
return ret;
}
/*
* Finds the image layer in the chain that has 'bs' as its backing file.
*
* active is the current topmost image.
*
* Returns NULL if bs is not found in active's image chain,
* or if active == bs.
*/
BlockDriverState *bdrv_find_overlay(BlockDriverState *active,
BlockDriverState *bs)
{
BlockDriverState *overlay = NULL;
BlockDriverState *intermediate;
assert(active != NULL);
assert(bs != NULL);
/* if bs is the same as active, then by definition it has no overlay
*/
if (active == bs) {
return NULL;
}
intermediate = active;
while (intermediate->backing_hd) {
if (intermediate->backing_hd == bs) {
overlay = intermediate;
break;
}
intermediate = intermediate->backing_hd;
}
return overlay;
}
typedef struct BlkIntermediateStates {
BlockDriverState *bs;
QSIMPLEQ_ENTRY(BlkIntermediateStates) entry;
} BlkIntermediateStates;
/*
* Drops images above 'base' up to and including 'top', and sets the image
* above 'top' to have base as its backing file.
*
* Requires that the overlay to 'top' is opened r/w, so that the backing file
* information in 'bs' can be properly updated.
*
* E.g., this will convert the following chain:
* bottom <- base <- intermediate <- top <- active
*
* to
*
* bottom <- base <- active
*
* It is allowed for bottom==base, in which case it converts:
*
* base <- intermediate <- top <- active
*
* to
*
* base <- active
*
* Error conditions:
* if active == top, that is considered an error
*
*/
int bdrv_drop_intermediate(BlockDriverState *active, BlockDriverState *top,
BlockDriverState *base)
{
BlockDriverState *intermediate;
BlockDriverState *base_bs = NULL;
BlockDriverState *new_top_bs = NULL;
BlkIntermediateStates *intermediate_state, *next;
int ret = -EIO;
QSIMPLEQ_HEAD(states_to_delete, BlkIntermediateStates) states_to_delete;
QSIMPLEQ_INIT(&states_to_delete);
if (!top->drv || !base->drv) {
goto exit;
}
new_top_bs = bdrv_find_overlay(active, top);
if (new_top_bs == NULL) {
/* we could not find the image above 'top', this is an error */
goto exit;
}
/* special case of new_top_bs->backing_hd already pointing to base - nothing
* to do, no intermediate images */
if (new_top_bs->backing_hd == base) {
ret = 0;
goto exit;
}
intermediate = top;
/* now we will go down through the list, and add each BDS we find
* into our deletion queue, until we hit the 'base'
*/
while (intermediate) {
intermediate_state = g_malloc0(sizeof(BlkIntermediateStates));
intermediate_state->bs = intermediate;
QSIMPLEQ_INSERT_TAIL(&states_to_delete, intermediate_state, entry);
if (intermediate->backing_hd == base) {
base_bs = intermediate->backing_hd;
break;
}
intermediate = intermediate->backing_hd;
}
if (base_bs == NULL) {
/* something went wrong, we did not end at the base. safely
* unravel everything, and exit with error */
goto exit;
}
/* success - we can delete the intermediate states, and link top->base */
ret = bdrv_change_backing_file(new_top_bs, base_bs->filename,
base_bs->drv ? base_bs->drv->format_name : "");
if (ret) {
goto exit;
}
new_top_bs->backing_hd = base_bs;
bdrv_refresh_limits(new_top_bs);
QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
/* so that bdrv_close() does not recursively close the chain */
intermediate_state->bs->backing_hd = NULL;
bdrv_unref(intermediate_state->bs);
}
ret = 0;
exit:
QSIMPLEQ_FOREACH_SAFE(intermediate_state, &states_to_delete, entry, next) {
g_free(intermediate_state);
}
return ret;
}
static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
size_t size)
{
int64_t len;
if (size > INT_MAX) {
return -EIO;
}
if (!bdrv_is_inserted(bs))
return -ENOMEDIUM;
if (bs->growable)
return 0;
len = bdrv_getlength(bs);
if (offset < 0)
return -EIO;
if ((offset > len) || (len - offset < size))
return -EIO;
return 0;
}
static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
return -EIO;
}
return bdrv_check_byte_request(bs, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE);
}
typedef struct RwCo {
BlockDriverState *bs;
int64_t offset;
QEMUIOVector *qiov;
bool is_write;
int ret;
BdrvRequestFlags flags;
} RwCo;
static void coroutine_fn bdrv_rw_co_entry(void *opaque)
{
RwCo *rwco = opaque;
if (!rwco->is_write) {
rwco->ret = bdrv_co_do_preadv(rwco->bs, rwco->offset,
rwco->qiov->size, rwco->qiov,
rwco->flags);
} else {
rwco->ret = bdrv_co_do_pwritev(rwco->bs, rwco->offset,
rwco->qiov->size, rwco->qiov,
rwco->flags);
}
}
/*
* Process a vectored synchronous request using coroutines
*/
static int bdrv_prwv_co(BlockDriverState *bs, int64_t offset,
QEMUIOVector *qiov, bool is_write,
BdrvRequestFlags flags)
{
Coroutine *co;
RwCo rwco = {
.bs = bs,
.offset = offset,
.qiov = qiov,
.is_write = is_write,
.ret = NOT_DONE,
.flags = flags,
};
/**
* In sync call context, when the vcpu is blocked, this throttling timer
* will not fire; so the I/O throttling function has to be disabled here
* if it has been enabled.
*/
if (bs->io_limits_enabled) {
fprintf(stderr, "Disabling I/O throttling on '%s' due "
"to synchronous I/O.\n", bdrv_get_device_name(bs));
bdrv_io_limits_disable(bs);
}
if (qemu_in_coroutine()) {
/* Fast-path if already in coroutine context */
bdrv_rw_co_entry(&rwco);
} else {
co = qemu_coroutine_create(bdrv_rw_co_entry);
qemu_coroutine_enter(co, &rwco);
while (rwco.ret == NOT_DONE) {
qemu_aio_wait();
}
}
return rwco.ret;
}
/*
* Process a synchronous request using coroutines
*/
static int bdrv_rw_co(BlockDriverState *bs, int64_t sector_num, uint8_t *buf,
int nb_sectors, bool is_write, BdrvRequestFlags flags)
{
QEMUIOVector qiov;
struct iovec iov = {
.iov_base = (void *)buf,
.iov_len = nb_sectors * BDRV_SECTOR_SIZE,
};
if (nb_sectors < 0 || nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
return -EINVAL;
}
qemu_iovec_init_external(&qiov, &iov, 1);
return bdrv_prwv_co(bs, sector_num << BDRV_SECTOR_BITS,
&qiov, is_write, flags);
}
/* return < 0 if error. See bdrv_write() for the return codes */
int bdrv_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
return bdrv_rw_co(bs, sector_num, buf, nb_sectors, false, 0);
}
/* Just like bdrv_read(), but with I/O throttling temporarily disabled */
int bdrv_read_unthrottled(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
bool enabled;
int ret;
enabled = bs->io_limits_enabled;
bs->io_limits_enabled = false;
ret = bdrv_read(bs, sector_num, buf, nb_sectors);
bs->io_limits_enabled = enabled;
return ret;
}
/* Return < 0 if error. Important errors are:
-EIO generic I/O error (may happen for all errors)
-ENOMEDIUM No media inserted.
-EINVAL Invalid sector number or nb_sectors
-EACCES Trying to write a read-only device
*/
int bdrv_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
return bdrv_rw_co(bs, sector_num, (uint8_t *)buf, nb_sectors, true, 0);
}
int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, BdrvRequestFlags flags)
{
return bdrv_rw_co(bs, sector_num, NULL, nb_sectors, true,
BDRV_REQ_ZERO_WRITE | flags);
}
/*
* Completely zero out a block device with the help of bdrv_write_zeroes.
* The operation is sped up by checking the block status and only writing
* zeroes to the device if they currently do not return zeroes. Optional
* flags are passed through to bdrv_write_zeroes (e.g. BDRV_REQ_MAY_UNMAP).
*
* Returns < 0 on error, 0 on success. For error codes see bdrv_write().
*/
int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
{
int64_t target_size;
int64_t ret, nb_sectors, sector_num = 0;
int n;
target_size = bdrv_getlength(bs);
if (target_size < 0) {
return target_size;
}
target_size /= BDRV_SECTOR_SIZE;
for (;;) {
nb_sectors = target_size - sector_num;
if (nb_sectors <= 0) {
return 0;
}
if (nb_sectors > INT_MAX) {
nb_sectors = INT_MAX;
}
ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
if (ret < 0) {
error_report("error getting block status at sector %" PRId64 ": %s",
sector_num, strerror(-ret));
return ret;
}
if (ret & BDRV_BLOCK_ZERO) {
sector_num += n;
continue;
}
ret = bdrv_write_zeroes(bs, sector_num, n, flags);
if (ret < 0) {
error_report("error writing zeroes at sector %" PRId64 ": %s",
sector_num, strerror(-ret));
return ret;
}
sector_num += n;
}
}
int bdrv_pread(BlockDriverState *bs, int64_t offset, void *buf, int bytes)
{
QEMUIOVector qiov;
struct iovec iov = {
.iov_base = (void *)buf,
.iov_len = bytes,
};
int ret;
if (bytes < 0) {
return -EINVAL;
}
qemu_iovec_init_external(&qiov, &iov, 1);
ret = bdrv_prwv_co(bs, offset, &qiov, false, 0);
if (ret < 0) {
return ret;
}
return bytes;
}
int bdrv_pwritev(BlockDriverState *bs, int64_t offset, QEMUIOVector *qiov)
{
int ret;
ret = bdrv_prwv_co(bs, offset, qiov, true, 0);
if (ret < 0) {
return ret;
}
return qiov->size;
}
int bdrv_pwrite(BlockDriverState *bs, int64_t offset,
const void *buf, int bytes)
{
QEMUIOVector qiov;
struct iovec iov = {
.iov_base = (void *) buf,
.iov_len = bytes,
};
if (bytes < 0) {
return -EINVAL;
}
qemu_iovec_init_external(&qiov, &iov, 1);
return bdrv_pwritev(bs, offset, &qiov);
}
/*
* Writes to the file and ensures that no writes are reordered across this
* request (acts as a barrier)
*
* Returns 0 on success, -errno in error cases.
*/
int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
const void *buf, int count)
{
int ret;
ret = bdrv_pwrite(bs, offset, buf, count);
if (ret < 0) {
return ret;
}
/* No flush needed for cache modes that already do it */
if (bs->enable_write_cache) {
bdrv_flush(bs);
}
return 0;
}
static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov)
{
/* Perform I/O through a temporary buffer so that users who scribble over
* their read buffer while the operation is in progress do not end up
* modifying the image file. This is critical for zero-copy guest I/O
* where anything might happen inside guest memory.
*/
void *bounce_buffer;
BlockDriver *drv = bs->drv;
struct iovec iov;
QEMUIOVector bounce_qiov;
int64_t cluster_sector_num;
int cluster_nb_sectors;
size_t skip_bytes;
int ret;
/* Cover entire cluster so no additional backing file I/O is required when
* allocating cluster in the image file.
*/
bdrv_round_to_clusters(bs, sector_num, nb_sectors,
&cluster_sector_num, &cluster_nb_sectors);
trace_bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors,
cluster_sector_num, cluster_nb_sectors);
iov.iov_len = cluster_nb_sectors * BDRV_SECTOR_SIZE;
iov.iov_base = bounce_buffer = qemu_blockalign(bs, iov.iov_len);
qemu_iovec_init_external(&bounce_qiov, &iov, 1);
ret = drv->bdrv_co_readv(bs, cluster_sector_num, cluster_nb_sectors,
&bounce_qiov);
if (ret < 0) {
goto err;
}
if (drv->bdrv_co_write_zeroes &&
buffer_is_zero(bounce_buffer, iov.iov_len)) {
ret = bdrv_co_do_write_zeroes(bs, cluster_sector_num,
cluster_nb_sectors, 0);
} else {
/* This does not change the data on the disk, it is not necessary
* to flush even in cache=writethrough mode.
*/
ret = drv->bdrv_co_writev(bs, cluster_sector_num, cluster_nb_sectors,
&bounce_qiov);
}
if (ret < 0) {
/* It might be okay to ignore write errors for guest requests. If this
* is a deliberate copy-on-read then we don't want to ignore the error.
* Simply report it in all cases.
*/
goto err;
}
skip_bytes = (sector_num - cluster_sector_num) * BDRV_SECTOR_SIZE;
qemu_iovec_from_buf(qiov, 0, bounce_buffer + skip_bytes,
nb_sectors * BDRV_SECTOR_SIZE);
err:
qemu_vfree(bounce_buffer);
return ret;
}
/*
* Forwards an already correctly aligned request to the BlockDriver. This
* handles copy on read and zeroing after EOF; any other features must be
* implemented by the caller.
*/
static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
int64_t align, QEMUIOVector *qiov, int flags)
{
BlockDriver *drv = bs->drv;
int ret;
int64_t sector_num = offset >> BDRV_SECTOR_BITS;
unsigned int nb_sectors = bytes >> BDRV_SECTOR_BITS;
assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
/* Handle Copy on Read and associated serialisation */
if (flags & BDRV_REQ_COPY_ON_READ) {
/* If we touch the same cluster it counts as an overlap. This
* guarantees that allocating writes will be serialized and not race
* with each other for the same cluster. For example, in copy-on-read
* it ensures that the CoR read and write operations are atomic and
* guest writes cannot interleave between them. */
mark_request_serialising(req, bdrv_get_cluster_size(bs));
}
wait_serialising_requests(req);
if (flags & BDRV_REQ_COPY_ON_READ) {
int pnum;
ret = bdrv_is_allocated(bs, sector_num, nb_sectors, &pnum);
if (ret < 0) {
goto out;
}
if (!ret || pnum != nb_sectors) {
ret = bdrv_co_do_copy_on_readv(bs, sector_num, nb_sectors, qiov);
goto out;
}
}
/* Forward the request to the BlockDriver */
if (!(bs->zero_beyond_eof && bs->growable)) {
ret = drv->bdrv_co_readv(bs, sector_num, nb_sectors, qiov);
} else {
/* Read zeros after EOF of growable BDSes */
int64_t len, total_sectors, max_nb_sectors;
len = bdrv_getlength(bs);
if (len < 0) {
ret = len;
goto out;
}
total_sectors = DIV_ROUND_UP(len, BDRV_SECTOR_SIZE);
max_nb_sectors = ROUND_UP(MAX(0, total_sectors - sector_num),
align >> BDRV_SECTOR_BITS);
if (max_nb_sectors > 0) {
ret = drv->bdrv_co_readv(bs, sector_num,
MIN(nb_sectors, max_nb_sectors), qiov);
} else {
ret = 0;
}
/* Reading beyond end of file is supposed to produce zeroes */
if (ret == 0 && total_sectors < sector_num + nb_sectors) {
uint64_t offset = MAX(0, total_sectors - sector_num);
uint64_t bytes = (sector_num + nb_sectors - offset) *
BDRV_SECTOR_SIZE;
qemu_iovec_memset(qiov, offset * BDRV_SECTOR_SIZE, 0, bytes);
}
}
out:
return ret;
}
/*
* Handle a read request in coroutine context
*/
static int coroutine_fn bdrv_co_do_preadv(BlockDriverState *bs,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
BlockDriver *drv = bs->drv;
BdrvTrackedRequest req;
/* TODO Lift BDRV_SECTOR_SIZE restriction in BlockDriver interface */
uint64_t align = MAX(BDRV_SECTOR_SIZE, bs->request_alignment);
uint8_t *head_buf = NULL;
uint8_t *tail_buf = NULL;
QEMUIOVector local_qiov;
bool use_local_qiov = false;
int ret;
if (!drv) {
return -ENOMEDIUM;
}
if (bdrv_check_byte_request(bs, offset, bytes)) {
return -EIO;
}
if (bs->copy_on_read) {
flags |= BDRV_REQ_COPY_ON_READ;
}
/* throttling disk I/O */
if (bs->io_limits_enabled) {
bdrv_io_limits_intercept(bs, bytes, false);
}
/* Align read if necessary by padding qiov */
if (offset & (align - 1)) {
head_buf = qemu_blockalign(bs, align);
qemu_iovec_init(&local_qiov, qiov->niov + 2);
qemu_iovec_add(&local_qiov, head_buf, offset & (align - 1));
qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
use_local_qiov = true;
bytes += offset & (align - 1);
offset = offset & ~(align - 1);
}
if ((offset + bytes) & (align - 1)) {
if (!use_local_qiov) {
qemu_iovec_init(&local_qiov, qiov->niov + 1);
qemu_iovec_concat(&local_qiov, qiov, 0, qiov->size);
use_local_qiov =