sim-card
/
qemu
Archived
10
0
Fork 0
This repository has been archived on 2022-03-30. You can view files and clone it, but cannot push or open issues or pull requests.
qemu/block_int.h

250 lines
9.2 KiB
C
Raw Normal View History

/*
* 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.
*/
#ifndef BLOCK_INT_H
#define BLOCK_INT_H
#include "block.h"
#include "qemu-option.h"
#include "qemu-queue.h"
#define BLOCK_FLAG_ENCRYPT 1
#define BLOCK_FLAG_COMPRESS 2
#define BLOCK_FLAG_COMPAT6 4
#define BLOCK_OPT_SIZE "size"
#define BLOCK_OPT_ENCRYPT "encryption"
#define BLOCK_OPT_COMPAT6 "compat6"
#define BLOCK_OPT_BACKING_FILE "backing_file"
#define BLOCK_OPT_BACKING_FMT "backing_fmt"
#define BLOCK_OPT_CLUSTER_SIZE "cluster_size"
#define BLOCK_OPT_PREALLOC "preallocation"
typedef struct AIOPool {
void (*cancel)(BlockDriverAIOCB *acb);
int aiocb_size;
BlockDriverAIOCB *free_aiocb;
} AIOPool;
struct BlockDriver {
const char *format_name;
int instance_size;
int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
int (*bdrv_probe_device)(const char *filename);
int (*bdrv_open)(BlockDriverState *bs, int flags);
int (*bdrv_file_open)(BlockDriverState *bs, const char *filename, int flags);
int (*bdrv_read)(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors);
int (*bdrv_write)(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors);
void (*bdrv_close)(BlockDriverState *bs);
int (*bdrv_create)(const char *filename, QEMUOptionParameter *options);
void (*bdrv_flush)(BlockDriverState *bs);
int (*bdrv_is_allocated)(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum);
int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
int (*bdrv_make_empty)(BlockDriverState *bs);
/* aio */
BlockDriverAIOCB *(*bdrv_aio_readv)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
BlockDriverAIOCB *(*bdrv_aio_writev)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
BlockDriverAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque);
int (*bdrv_aio_multiwrite)(BlockDriverState *bs, BlockRequest *reqs,
int num_reqs);
int (*bdrv_merge_requests)(BlockDriverState *bs, BlockRequest* a,
BlockRequest *b);
const char *protocol_name;
int (*bdrv_truncate)(BlockDriverState *bs, int64_t offset);
int64_t (*bdrv_getlength)(BlockDriverState *bs);
int (*bdrv_write_compressed)(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors);
int (*bdrv_snapshot_create)(BlockDriverState *bs,
QEMUSnapshotInfo *sn_info);
int (*bdrv_snapshot_goto)(BlockDriverState *bs,
const char *snapshot_id);
int (*bdrv_snapshot_delete)(BlockDriverState *bs, const char *snapshot_id);
int (*bdrv_snapshot_list)(BlockDriverState *bs,
QEMUSnapshotInfo **psn_info);
int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
int (*bdrv_save_vmstate)(BlockDriverState *bs, const uint8_t *buf,
int64_t pos, int size);
int (*bdrv_load_vmstate)(BlockDriverState *bs, uint8_t *buf,
int64_t pos, int size);
int (*bdrv_change_backing_file)(BlockDriverState *bs,
const char *backing_file, const char *backing_fmt);
/* removable device specific */
int (*bdrv_is_inserted)(BlockDriverState *bs);
int (*bdrv_media_changed)(BlockDriverState *bs);
int (*bdrv_eject)(BlockDriverState *bs, int eject_flag);
int (*bdrv_set_locked)(BlockDriverState *bs, int locked);
/* to control generic scsi devices */
int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf);
BlockDriverAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockDriverCompletionFunc *cb, void *opaque);
/* List of options for creating images, terminated by name == NULL */
QEMUOptionParameter *create_options;
/*
* Returns 0 for completed check, -errno for internal errors.
* The check results are stored in result.
*/
int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result);
void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
/* Set if newly created images are not guaranteed to contain only zeros */
int no_zero_init;
QLIST_ENTRY(BlockDriver) list;
};
struct BlockDriverState {
int64_t total_sectors; /* if we are reading a disk image, give its
size in sectors */
int read_only; /* if true, the media is read only */
int keep_read_only; /* if true, the media was requested to stay read only */
int open_flags; /* flags used to open the file, re-used for re-open */
int removable; /* if true, the media can be removed */
int locked; /* if true, the media cannot temporarily be ejected */
int encrypted; /* if true, the media is encrypted */
int valid_key; /* if true, a valid encryption key has been set */
int sg; /* if true, the device is a /dev/sg* */
Make default invocation of block drivers safer (v3) CVE-2008-2004 described a vulnerability in QEMU whereas a malicious user could trick the block probing code into accessing arbitrary files in a guest. To mitigate this, we added an explicit format parameter to -drive which disabling block probing. Fast forward to today, and the vast majority of users do not use this parameter. libvirt does not use this by default nor does virt-manager. Most users want block probing so we should try to make it safer. This patch adds some logic to the raw device which attempts to detect a write operation to the beginning of a raw device. If the first 4 bytes happen to match an image file that has a backing file that we support, it scrubs the signature to all zeros. If a user specifies an explicit format parameter, this behavior is disabled. I contend that while a legitimate guest could write such a signature to the header, we would behave incorrectly anyway upon the next invocation of QEMU. This simply changes the incorrect behavior to not involve a security vulnerability. I've tested this pretty extensively both in the positive and negative case. I'm not 100% confident in the block layer's ability to deal with zero sized writes particularly with respect to the aio functions so some additional eyes would be appreciated. Even in the case of a single sector write, we have to make sure to invoked the completion from a bottom half so just removing the zero sized write is not an option. Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-07-14 15:58:00 +00:00
int probed; /* if true, format was probed automatically */
/* event callback when inserting/removing */
void (*change_cb)(void *opaque);
void *change_opaque;
BlockDriver *drv; /* NULL means no media */
void *opaque;
DeviceState *peer;
char filename[1024];
char backing_file[1024]; /* if non zero, the image is a diff of
this file image */
char backing_format[16]; /* if non-zero and backing_file exists */
int is_temporary;
int media_changed;
BlockDriverState *backing_hd;
BlockDriverState *file;
/* async read/write emulation */
void *sync_aiocb;
/* I/O stats (display with "info blockstats"). */
uint64_t rd_bytes;
uint64_t wr_bytes;
uint64_t rd_ops;
uint64_t wr_ops;
uint64_t wr_highest_sector;
/* Whether the disk can expand beyond total_sectors */
int growable;
/* the memory alignment required for the buffers handled by this driver */
int buffer_alignment;
/* do we need to tell the quest if we have a volatile write cache? */
int enable_write_cache;
/* NOTE: the following infos are only hints for real hardware
drivers. They are not used by the block driver */
int cyls, heads, secs, translation;
int type;
BlockErrorAction on_read_error, on_write_error;
char device_name[32];
unsigned long *dirty_bitmap;
int64_t dirty_count;
QTAILQ_ENTRY(BlockDriverState) list;
void *private;
};
struct BlockDriverAIOCB {
AIOPool *pool;
BlockDriverState *bs;
BlockDriverCompletionFunc *cb;
void *opaque;
BlockDriverAIOCB *next;
};
void get_tmp_filename(char *filename, int size);
void *qemu_aio_get(AIOPool *pool, BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque);
void qemu_aio_release(void *p);
void *qemu_blockalign(BlockDriverState *bs, size_t size);
#ifdef _WIN32
int is_windows_drive(const char *filename);
#endif
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
typedef struct BlockConf {
BlockDriverState *bs;
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
uint16_t physical_block_size;
uint16_t logical_block_size;
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
uint16_t min_io_size;
uint32_t opt_io_size;
} BlockConf;
static inline unsigned int get_physical_block_exp(BlockConf *conf)
{
unsigned int exp = 0, size;
for (size = conf->physical_block_size;
size > conf->logical_block_size;
size >>= 1) {
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
exp++;
}
return exp;
}
#define DEFINE_BLOCK_PROPERTIES(_state, _conf) \
DEFINE_PROP_DRIVE("drive", _state, _conf.bs), \
DEFINE_PROP_UINT16("logical_block_size", _state, \
_conf.logical_block_size, 512), \
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
DEFINE_PROP_UINT16("physical_block_size", _state, \
_conf.physical_block_size, 512), \
DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0), \
DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0)
block: add topology qdev properties Add three new qdev properties to export block topology information to the guest. This is needed to get optimal I/O alignment for RAID arrays or SSDs. The options are: - physical_block_size to specify the physical block size of the device, this is going to increase from 512 bytes to 4096 kilobytes for many modern storage devices - min_io_size to specify the minimal I/O size without performance impact, this is typically set to the RAID chunk size for arrays. - opt_io_size to specify the optimal sustained I/O size, this is typically the RAID stripe width for arrays. I decided to not auto-probe these values from blkid which might easily be possible as I don't know how to deal with these issues on migration. Note that we specificly only set the physical_block_size, and not the logial one which is the unit all I/O is described in. The reason for that is that IDE does not support increasing the logical block size and at last for now I want to stick to one meachnisms in queue and allow for easy switching of transports for a given backing image which would not be possible if scsi and virtio use real 4k sectors, while ide only uses the physical block exponent. To make this more common for the different block drivers introduce a new BlockConf structure holding all common block properties and a DEFINE_BLOCK_PROPERTIES macro to add them all together, mirroring what is done for network drivers. Also switch over all block drivers to use it, except for the floppy driver which has weird driveA/driveB properties and probably won't require any advanced block options ever. Example usage for a virtio device with 4k physical block size and 8k optimal I/O size: -drive file=scratch.img,media=disk,cache=none,id=scratch \ -device virtio-blk-pci,drive=scratch,physical_block_size=4096,opt_io_size=8192 aliguori: updated patch to take into account BLOCK events Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2010-02-10 22:37:09 +00:00
#endif /* BLOCK_INT_H */