/*
* QEMU host block devices
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* This work is licensed under the terms of the GNU GPL, version 2 or
* later. See the COPYING file in the top-level directory.
*
* This file incorporates work covered by the following copyright and
* permission notice:
*
* Copyright (c) 2003-2008 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "system/block-backend.h"
#include "system/blockdev.h"
#include "hw/block/block.h"
#include "block/blockjob.h"
#include "block/dirty-bitmap.h"
#include "block/qdict.h"
#include "block/throttle-groups.h"
#include "monitor/monitor.h"
#include "qemu/error-report.h"
#include "qemu/option.h"
#include "qemu/qemu-print.h"
#include "qemu/config-file.h"
#include "qapi/qapi-commands-block.h"
#include "qapi/qapi-commands-transaction.h"
#include "qapi/qapi-visit-block-core.h"
#include "qobject/qdict.h"
#include "qobject/qnum.h"
#include "qobject/qstring.h"
#include "qapi/error.h"
#include "qapi/qmp/qerror.h"
#include "qobject/qlist.h"
#include "qapi/qobject-output-visitor.h"
#include "system/system.h"
#include "system/iothread.h"
#include "block/block_int.h"
#include "block/trace.h"
#include "system/runstate.h"
#include "system/replay.h"
#include "qemu/cutils.h"
#include "qemu/help_option.h"
#include "qemu/main-loop.h"
#include "qemu/throttle-options.h"
/* Protected by BQL */
QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
QTAILQ_HEAD_INITIALIZER(monitor_bdrv_states);
void bdrv_set_monitor_owned(BlockDriverState *bs)
{
GLOBAL_STATE_CODE();
QTAILQ_INSERT_TAIL(&monitor_bdrv_states, bs, monitor_list);
}
static const char *const if_name[IF_COUNT] = {
[IF_NONE] = "none",
[IF_IDE] = "ide",
[IF_SCSI] = "scsi",
[IF_FLOPPY] = "floppy",
[IF_PFLASH] = "pflash",
[IF_MTD] = "mtd",
[IF_SD] = "sd",
[IF_VIRTIO] = "virtio",
[IF_XEN] = "xen",
};
static int if_max_devs[IF_COUNT] = {
/*
* Do not change these numbers! They govern how drive option
* index maps to unit and bus. That mapping is ABI.
*
* All controllers used to implement if=T drives need to support
* if_max_devs[T] units, for any T with if_max_devs[T] != 0.
* Otherwise, some index values map to "impossible" bus, unit
* values.
*
* For instance, if you change [IF_SCSI] to 255, -drive
* if=scsi,index=12 no longer means bus=1,unit=5, but
* bus=0,unit=12. With an lsi53c895a controller (7 units max),
* the drive can't be set up. Regression.
*/
[IF_IDE] = 2,
[IF_SCSI] = 7,
};
/**
* Boards may call this to offer board-by-board overrides
* of the default, global values.
*/
void override_max_devs(BlockInterfaceType type, int max_devs)
{
BlockBackend *blk;
DriveInfo *dinfo;
GLOBAL_STATE_CODE();
if (max_devs <= 0) {
return;
}
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
dinfo = blk_legacy_dinfo(blk);
if (dinfo->type == type) {
fprintf(stderr, "Cannot override units-per-bus property of"
" the %s interface, because a drive of that type has"
" already been added.\n", if_name[type]);
g_assert_not_reached();
}
}
if_max_devs[type] = max_devs;
}
/*
* We automatically delete the drive when a device using it gets
* unplugged. Questionable feature, but we can't just drop it.
* Device models call blockdev_mark_auto_del() to schedule the
* automatic deletion, and generic qdev code calls blockdev_auto_del()
* when deletion is actually safe.
*/
void blockdev_mark_auto_del(BlockBackend *blk)
{
DriveInfo *dinfo = blk_legacy_dinfo(blk);
BlockJob *job;
GLOBAL_STATE_CODE();
if (!dinfo) {
return;
}
JOB_LOCK_GUARD();
do {
job = block_job_next_locked(NULL);
while (job && (job->job.cancelled ||
job->job.deferred_to_main_loop ||
!block_job_has_bdrv(job, blk_bs(blk))))
{
job = block_job_next_locked(job);
}
if (job) {
/*
* This drops the job lock temporarily and polls, so we need to
* restart processing the list from the start after this.
*/
job_cancel_locked(&job->job, false);
}
} while (job);
dinfo->auto_del = 1;
}
void blockdev_auto_del(BlockBackend *blk)
{
DriveInfo *dinfo = blk_legacy_dinfo(blk);
GLOBAL_STATE_CODE();
if (dinfo && dinfo->auto_del) {
monitor_remove_blk(blk);
blk_unref(blk);
}
}
static int drive_index_to_bus_id(BlockInterfaceType type, int index)
{
int max_devs = if_max_devs[type];
return max_devs ? index / max_devs : 0;
}
static int drive_index_to_unit_id(BlockInterfaceType type, int index)
{
int max_devs = if_max_devs[type];
return max_devs ? index % max_devs : index;
}
QemuOpts *drive_add(BlockInterfaceType type, int index, const char *file,
const char *optstr)
{
QemuOpts *opts;
GLOBAL_STATE_CODE();
opts = qemu_opts_parse_noisily(qemu_find_opts("drive"), optstr, false);
if (!opts) {
return NULL;
}
if (type != IF_DEFAULT) {
qemu_opt_set(opts, "if", if_name[type], &error_abort);
}
if (index >= 0) {
qemu_opt_set_number(opts, "index", index, &error_abort);
}
if (file)
qemu_opt_set(opts, "file", file, &error_abort);
return opts;
}
DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)
{
BlockBackend *blk;
DriveInfo *dinfo;
GLOBAL_STATE_CODE();
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
dinfo = blk_legacy_dinfo(blk);
if (dinfo && dinfo->type == type
&& dinfo->bus == bus && dinfo->unit == unit) {
return dinfo;
}
}
return NULL;
}
/*
* Check board claimed all -drive that are meant to be claimed.
* Fatal error if any remain unclaimed.
*/
void drive_check_orphaned(void)
{
BlockBackend *blk;
DriveInfo *dinfo;
Location loc;
bool orphans = false;
GLOBAL_STATE_CODE();
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
dinfo = blk_legacy_dinfo(blk);
/*
* Ignore default drives, because we create certain default
* drives unconditionally, then leave them unclaimed. Not the
* users fault.
* Ignore IF_VIRTIO or IF_XEN, because it gets desugared into
* -device, so we can leave failing to -device.
* Ignore IF_NONE, because leaving unclaimed IF_NONE remains
* available for device_add is a feature.
*/
if (dinfo->is_default || dinfo->type == IF_VIRTIO
|| dinfo->type == IF_XEN || dinfo->type == IF_NONE) {
continue;
}
if (!blk_get_attached_dev(blk)) {
loc_push_none(&loc);
qemu_opts_loc_restore(dinfo->opts);
error_report("machine type does not support"
" if=%s,bus=%d,unit=%d",
if_name[dinfo->type], dinfo->bus, dinfo->unit);
loc_pop(&loc);
orphans = true;
}
}
if (orphans) {
exit(1);
}
}
DriveInfo *drive_get_by_index(BlockInterfaceType type, int index)
{
GLOBAL_STATE_CODE();
return drive_get(type,
drive_index_to_bus_id(type, index),
drive_index_to_unit_id(type, index));
}
int drive_get_max_bus(BlockInterfaceType type)
{
int max_bus;
BlockBackend *blk;
DriveInfo *dinfo;
GLOBAL_STATE_CODE();
max_bus = -1;
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
dinfo = blk_legacy_dinfo(blk);
if (dinfo && dinfo->type == type && dinfo->bus > max_bus) {
max_bus = dinfo->bus;
}
}
return max_bus;
}
static void bdrv_format_print(void *opaque, const char *name)
{
qemu_printf(" %s", name);
}
typedef struct {
QEMUBH *bh;
BlockDriverState *bs;
} BDRVPutRefBH;
static int parse_block_error_action(const char *buf, bool is_read, Error **errp)
{
if (!strcmp(buf, "ignore")) {
return BLOCKDEV_ON_ERROR_IGNORE;
} else if (!is_read && !strcmp(buf, "enospc")) {
return BLOCKDEV_ON_ERROR_ENOSPC;
} else if (!strcmp(buf, "stop")) {
return BLOCKDEV_ON_ERROR_STOP;
} else if (!strcmp(buf, "report")) {
return BLOCKDEV_ON_ERROR_REPORT;
} else {
error_setg(errp, "'%s' invalid %s error action",
buf, is_read ? "read" : "write");
return -1;
}
}
static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
Error **errp)
{
const QListEntry *entry;
for (entry = qlist_first(intervals); entry; entry = qlist_next(entry)) {
switch (qobject_type(entry->value)) {
case QTYPE_QSTRING: {
uint64_t length;
const char *str = qstring_get_str(qobject_to(QString,
entry->value));
if (parse_uint_full(str, 10, &length) == 0 &&
length > 0 && length <= UINT_MAX) {
block_acct_add_interval(stats, (unsigned) length);
} else {
error_setg(errp, "Invalid interval length: %s", str);
return false;
}
break;
}
case QTYPE_QNUM: {
int64_t length = qnum_get_int(qobject_to(QNum, entry->value));
if (length > 0 && length <= UINT_MAX) {
block_acct_add_interval(stats, (unsigned) length);
} else {
error_setg(errp, "Invalid interval length: %" PRId64, length);
return false;
}
break;
}
default:
error_setg(errp, "The specification of stats-intervals is invalid");
return false;
}
}
return true;
}
typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
/* All parameters but @opts are optional and may be set to NULL. */
static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
const char **throttling_group, ThrottleConfig *throttle_cfg,
BlockdevDetectZeroesOptions *detect_zeroes, Error **errp)
{
Error *local_error = NULL;
const char *aio;
if (bdrv_flags) {
if (qemu_opt_get_bool(opts, "copy-on-read", false)) {
*bdrv_flags |= BDRV_O_COPY_ON_READ;
}
if ((aio = qemu_opt_get(opts, "aio")) != NULL) {
if (bdrv_parse_aio(aio, bdrv_flags) < 0) {
error_setg(errp, "invalid aio option");
return;
}
}
}
/* disk I/O throttling */
if (throttling_group) {
*throttling_group = qemu_opt_get(opts, "throttling.group");
}
if (throttle_cfg) {
throttle_config_init(throttle_cfg);
throttle_cfg->buckets[THROTTLE_BPS_TOTAL].avg =
qemu_opt_get_number(opts, "throttling.bps-total", 0);
throttle_cfg->buckets[THROTTLE_BPS_READ].avg =
qemu_opt_get_number(opts, "throttling.bps-read", 0);
throttle_cfg->buckets[THROTTLE_BPS_WRITE].avg =
qemu_opt_get_number(opts, "throttling.bps-write", 0);
throttle_cfg->buckets[THROTTLE_OPS_TOTAL].avg =
qemu_opt_get_number(opts, "throttling.iops-total", 0);
throttle_cfg->buckets[THROTTLE_OPS_READ].avg =
qemu_opt_get_number(opts, "throttling.iops-read", 0);
throttle_cfg->buckets[THROTTLE_OPS_WRITE].avg =
qemu_opt_get_number(opts, "throttling.iops-write", 0);
throttle_cfg->buckets[THROTTLE_BPS_TOTAL].max =
qemu_opt_get_number(opts, "throttling.bps-total-max", 0);
throttle_cfg->buckets[THROTTLE_BPS_READ].max =
qemu_opt_get_number(opts, "throttling.bps-read-max", 0);
throttle_cfg->buckets[THROTTLE_BPS_WRITE].max =
qemu_opt_get_number(opts, "throttling.bps-write-max", 0);
throttle_cfg->buckets[THROTTLE_OPS_TOTAL].max =
qemu_opt_get_number(opts, "throttling.iops-total-max", 0);
throttle_cfg->buckets[THROTTLE_OPS_READ].max =
qemu_opt_get_number(opts, "throttling.iops-read-max", 0);
throttle_cfg->buckets[THROTTLE_OPS_WRITE].max =
qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
throttle_cfg->buckets[THROTTLE_BPS_TOTAL].burst_length =
qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
throttle_cfg->buckets[THROTTLE_BPS_READ].burst_length =
qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
throttle_cfg->buckets[THROTTLE_BPS_WRITE].burst_length =
qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_TOTAL].burst_length =
qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_READ].burst_length =
qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_WRITE].burst_length =
qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
throttle_cfg->op_size =
qemu_opt_get_number(opts, "throttling.iops-size", 0);
if (!throttle_is_valid(throttle_cfg, errp)) {
return;
}
}
if (detect_zeroes) {
*detect_zeroes =
qapi_enum_parse(&BlockdevDetectZeroesOptions_lookup,
qemu_opt_get(opts, "detect-zeroes"),
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_error);
if (local_error) {
error_propagate(errp, local_error);
return;
}
}
}
static OnOffAuto account_get_opt(QemuOpts *opts, const char *name)
{
if (!qemu_opt_find(opts, name)) {
return ON_OFF_AUTO_AUTO;
}
if (qemu_opt_get_bool(opts, name, true)) {
return ON_OFF_AUTO_ON;
}
return ON_OFF_AUTO_OFF;
}
/* Takes the ownership of bs_opts */
static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
Error **errp)
{
const char *buf;
int bdrv_flags = 0;
int on_read_error, on_write_error;
OnOffAuto account_invalid, account_failed;
bool writethrough, read_only;
BlockBackend *blk;
BlockDriverState *bs;
ThrottleConfig cfg;
int snapshot = 0;
Error *error = NULL;
QemuOpts *opts;
QDict *interval_dict = NULL;
QList *interval_list = NULL;
const char *id;
BlockdevDetectZeroesOptions detect_zeroes =
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
const char *throttling_group = NULL;
/* Check common options by copying from bs_opts to opts, all other options
* stay in bs_opts for processing by bdrv_open(). */
id = qdict_get_try_str(bs_opts, "id");
opts = qemu_opts_create(&qemu_common_drive_opts, id, 1, errp);
if (!opts) {
goto err_no_opts;
}
if (!qemu_opts_absorb_qdict(opts, bs_opts, errp)) {
goto early_err;
}
if (id) {
qdict_del(bs_opts, "id");
}
/* extract parameters */
snapshot = qemu_opt_get_bool(opts, "snapshot", 0);
account_invalid = account_get_opt(opts, "stats-account-invalid");
account_failed = account_get_opt(opts, "stats-account-failed");
writethrough = !qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true);
id = qemu_opts_id(opts);
qdict_extract_subqdict(bs_opts, &interval_dict, "stats-intervals.");
qdict_array_split(interval_dict, &interval_list);
if (qdict_size(interval_dict) != 0) {
error_setg(errp, "Invalid option stats-intervals.%s",
qdict_first(interval_dict)->key);
goto early_err;
}
extract_common_blockdev_options(opts, &bdrv_flags, &throttling_group, &cfg,
&detect_zeroes, &error);
if (error) {
error_propagate(errp, error);
goto early_err;
}
if ((buf = qemu_opt_get(opts, "format")) != NULL) {
if (is_help_option(buf)) {
qemu_printf("Supported formats:");
bdrv_iterate_format(bdrv_format_print, NULL, false);
qemu_printf("\nSupported formats (read-only):");
bdrv_iterate_format(bdrv_format_print, NULL, true);
qemu_printf("\n");
goto early_err;
}
if (qdict_haskey(bs_opts, "driver")) {
error_setg(errp, "Cannot specify both 'driver' and 'format'");
goto early_err;
}
qdict_put_str(bs_opts, "driver", buf);
}
on_write_error = BLOCKDEV_ON_ERROR_ENOSPC;
if ((buf = qemu_opt_get(opts, "werror")) != NULL) {
on_write_error = parse_block_error_action(buf, 0, &error);
if (error) {
error_propagate(errp, error);
goto early_err;
}
}
on_read_error = BLOCKDEV_ON_ERROR_REPORT;
if ((buf = qemu_opt_get(opts, "rerror")) != NULL) {
on_read_error = parse_block_error_action(buf, 1, &error);
if (error) {
error_propagate(errp, error);
goto early_err;
}
}
if (snapshot) {
bdrv_flags |= BDRV_O_SNAPSHOT;
}
read_only = qemu_opt_get_bool(opts, BDRV_OPT_READ_ONLY, false);
/* init */
if ((!file || !*file) && !qdict_size(bs_opts)) {
BlockBackendRootState *blk_rs;
blk = blk_new(qemu_get_aio_context(), 0, BLK_PERM_ALL);
blk_rs = blk_get_root_state(blk);
blk_rs->open_flags = bdrv_flags | (read_only ? 0 : BDRV_O_RDWR);
blk_rs->detect_zeroes = detect_zeroes;
|