qemu/include/block/block_int.h

669 lines
26 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/accounting.h"
#include "block/block.h"
#include "qemu/option.h"
#include "qemu/queue.h"
#include "block/coroutine.h"
#include "qemu/timer.h"
#include "qapi-types.h"
#include "qemu/hbitmap.h"
#include "block/snapshot.h"
#include "qemu/main-loop.h"
#include "qemu/throttle.h"
#define BLOCK_FLAG_ENCRYPT 1
#define BLOCK_FLAG_COMPAT6 4
#define BLOCK_FLAG_LAZY_REFCOUNTS 8
#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_TABLE_SIZE "table_size"
#define BLOCK_OPT_PREALLOC "preallocation"
#define BLOCK_OPT_SUBFMT "subformat"
#define BLOCK_OPT_COMPAT_LEVEL "compat"
#define BLOCK_OPT_LAZY_REFCOUNTS "lazy_refcounts"
#define BLOCK_OPT_ADAPTER_TYPE "adapter_type"
#define BLOCK_OPT_REDUNDANCY "redundancy"
#define BLOCK_OPT_NOCOW "nocow"
#define BLOCK_OPT_OBJECT_SIZE "object_size"
#define BLOCK_OPT_REFCOUNT_BITS "refcount_bits"
#define BLOCK_PROBE_BUF_SIZE 512
typedef struct BdrvTrackedRequest {
BlockDriverState *bs;
int64_t offset;
unsigned int bytes;
bool is_write;
bool serialising;
int64_t overlap_offset;
unsigned int overlap_bytes;
QLIST_ENTRY(BdrvTrackedRequest) list;
Coroutine *co; /* owner, used for deadlock detection */
CoQueue wait_queue; /* coroutines blocked on this request */
struct BdrvTrackedRequest *waiting_for;
} BdrvTrackedRequest;
struct BlockDriver {
const char *format_name;
int instance_size;
/* set to true if the BlockDriver is a block filter */
bool is_filter;
/* for snapshots block filter like Quorum can implement the
* following recursive callback.
* It's purpose is to recurse on the filter children while calling
* bdrv_recurse_is_first_non_filter on them.
* For a sample implementation look in the future Quorum block filter.
*/
bool (*bdrv_recurse_is_first_non_filter)(BlockDriverState *bs,
BlockDriverState *candidate);
int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
int (*bdrv_probe_device)(const char *filename);
/* Any driver implementing this callback is expected to be able to handle
* NULL file names in its .bdrv_open() implementation */
void (*bdrv_parse_filename)(const char *filename, QDict *options, Error **errp);
/* Drivers not implementing bdrv_parse_filename nor bdrv_open should have
* this field set to true, except ones that are defined only by their
* child's bs.
* An example of the last type will be the quorum block driver.
*/
bool bdrv_needs_filename;
/* Set if a driver can support backing files */
bool supports_backing;
/* For handling image reopen for split or non-split files */
int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp);
void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
int (*bdrv_open)(BlockDriverState *bs, QDict *options, int flags,
Error **errp);
int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags,
Error **errp);
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);
void (*bdrv_rebind)(BlockDriverState *bs);
int (*bdrv_create)(const char *filename, QemuOpts *opts, Error **errp);
int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
int (*bdrv_make_empty)(BlockDriverState *bs);
void (*bdrv_refresh_filename)(BlockDriverState *bs);
/* aio */
BlockAIOCB *(*bdrv_aio_readv)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *(*bdrv_aio_writev)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque);
BlockAIOCB *(*bdrv_aio_discard)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
BlockCompletionFunc *cb, void *opaque);
int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
/*
* Efficiently zero a region of the disk image. Typically an image format
* would use a compact metadata representation to implement this. This
* function pointer may be NULL and .bdrv_co_writev() will be called
* instead.
*/
int coroutine_fn (*bdrv_co_write_zeroes)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, BdrvRequestFlags flags);
int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors);
int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum);
/*
* Invalidate any cached meta-data.
*/
void (*bdrv_invalidate_cache)(BlockDriverState *bs, Error **errp);
/*
* Flushes all data that was already written to the OS all the way down to
* the disk (for example raw-posix calls fsync()).
*/
int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
/*
* Flushes all internal caches to the OS. The data may still sit in a
* writeback cache of the host OS, but it will survive a crash of the qemu
* process.
*/
int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
const char *protocol_name;
int (*bdrv_truncate)(BlockDriverState *bs, int64_t offset);
2013-10-29 19:18:58 +08:00
int64_t (*bdrv_getlength)(BlockDriverState *bs);
2013-10-29 19:18:58 +08:00
bool has_variable_length;
int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
2013-10-29 19:18:58 +08:00
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,
const char *name,
Error **errp);
int (*bdrv_snapshot_list)(BlockDriverState *bs,
QEMUSnapshotInfo **psn_info);
int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp);
int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs);
int (*bdrv_save_vmstate)(BlockDriverState *bs, QEMUIOVector *qiov,
int64_t pos);
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);
void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
/* to control generic scsi devices */
int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf);
BlockAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque);
/* List of options for creating images, terminated by name == NULL */
QemuOptsList *create_opts;
/*
* Returns 0 for completed check, -errno for internal errors.
* The check results are stored in result.
*/
int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result,
BdrvCheckMode fix);
int (*bdrv_amend_options)(BlockDriverState *bs, QemuOpts *opts,
BlockDriverAmendStatusCB *status_cb);
void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
/* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
const char *tag);
int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
const char *tag);
int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
void (*bdrv_refresh_limits)(BlockDriverState *bs, Error **errp);
/*
* Returns 1 if newly created images are guaranteed to contain only
* zeros, 0 otherwise.
*/
int (*bdrv_has_zero_init)(BlockDriverState *bs);
/* Remove fd handlers, timers, and other event loop callbacks so the event
* loop is no longer in use. Called with no in-flight requests and in
* depth-first traversal order with parents before child nodes.
*/
void (*bdrv_detach_aio_context)(BlockDriverState *bs);
/* Add fd handlers, timers, and other event loop callbacks so I/O requests
* can be processed again. Called with no in-flight requests and in
* depth-first traversal order with child nodes before parent nodes.
*/
void (*bdrv_attach_aio_context)(BlockDriverState *bs,
AioContext *new_context);
/* io queue for linux-aio */
void (*bdrv_io_plug)(BlockDriverState *bs);
void (*bdrv_io_unplug)(BlockDriverState *bs);
void (*bdrv_flush_io_queue)(BlockDriverState *bs);
/**
* Try to get @bs's logical and physical block size.
* On success, store them in @bsz and return zero.
* On failure, return negative errno.
*/
int (*bdrv_probe_blocksizes)(BlockDriverState *bs, BlockSizes *bsz);
/**
* Try to get @bs's geometry (cyls, heads, sectors)
* On success, store them in @geo and return 0.
* On failure return -errno.
* Only drivers that want to override guest geometry implement this
* callback; see hd_geometry_guess().
*/
int (*bdrv_probe_geometry)(BlockDriverState *bs, HDGeometry *geo);
QLIST_ENTRY(BlockDriver) list;
};
typedef struct BlockLimits {
/* maximum number of sectors that can be discarded at once */
int max_discard;
/* optimal alignment for discard requests in sectors */
int64_t discard_alignment;
/* maximum number of sectors that can zeroized at once */
int max_write_zeroes;
/* optimal alignment for write zeroes requests in sectors */
int64_t write_zeroes_alignment;
/* optimal transfer length in sectors */
int opt_transfer_length;
/* maximal transfer length in sectors */
int max_transfer_length;
/* memory alignment so that no bounce buffer is needed */
size_t min_mem_alignment;
/* memory alignment for bounce buffer */
size_t opt_mem_alignment;
} BlockLimits;
typedef struct BdrvOpBlocker BdrvOpBlocker;
typedef struct BdrvAioNotifier {
void (*attached_aio_context)(AioContext *new_context, void *opaque);
void (*detach_aio_context)(void *opaque);
void *opaque;
QLIST_ENTRY(BdrvAioNotifier) list;
} BdrvAioNotifier;
struct BdrvChildRole {
int (*inherit_flags)(int parent_flags);
};
extern const BdrvChildRole child_file;
extern const BdrvChildRole child_format;
struct BdrvChild {
BlockDriverState *bs;
const BdrvChildRole *role;
QLIST_ENTRY(BdrvChild) next;
};
/*
* Note: the function bdrv_append() copies and swaps contents of
* BlockDriverStates, so if you add new fields to this struct, please
* inspect bdrv_append() to determine if the new fields need to be
* copied as well.
*/
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 open_flags; /* flags used to open the file, re-used for re-open */
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* */
int copy_on_read; /* if true, copy read backing sectors into image
note this is a reference count */
raw: Prohibit dangerous writes for probed images If the user neglects to specify the image format, QEMU probes the image to guess it automatically, for convenience. Relying on format probing is insecure for raw images (CVE-2008-2004). If the guest writes a suitable header to the device, the next probe will recognize a format chosen by the guest. A malicious guest can abuse this to gain access to host files, e.g. by crafting a QCOW2 header with backing file /etc/shadow. Commit 1e72d3b (April 2008) provided -drive parameter format to let users disable probing. Commit f965509 (March 2009) extended QCOW2 to optionally store the backing file format, to let users disable backing file probing. QED has had a flag to suppress probing since the beginning (2010), set whenever a raw backing file is assigned. All of these additions that allow to avoid format probing have to be specified explicitly. The default still allows the attack. In order to fix this, commit 79368c8 (July 2010) put probed raw images in a restricted mode, in which they wouldn't be able to overwrite the first few bytes of the image so that they would identify as a different image. If a write to the first sector would write one of the signatures of another driver, qemu would instead zero out the first four bytes. This patch was later reverted in commit 8b33d9e (September 2010) because it didn't get the handling of unaligned qiov members right. Today's block layer that is based on coroutines and has qiov utility functions makes it much easier to get this functionality right, so this patch implements it. The other differences of this patch to the old one are that it doesn't silently write something different than the guest requested by zeroing out some bytes (it fails the request instead) and that it doesn't maintain a list of signatures in the raw driver (it calls the usual probe function instead). Note that this change doesn't introduce new breakage for false positive cases where the guest legitimately writes data into the first sector that matches the signatures of an image format (e.g. for nested virt): These cases were broken before, only the failure mode changes from corruption after the next restart (when the wrong format is probed) to failing the problematic write request. Also note that like in the original patch, the restrictions only apply if the image format has been guessed by probing. Explicitly specifying a format allows guests to write anything they like. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 1416497234-29880-8-git-send-email-kwolf@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2014-11-20 23:27:12 +08:00
bool probed;
BlockDriver *drv; /* NULL means no media */
void *opaque;
BlockBackend *blk; /* owning backend, if any */
AioContext *aio_context; /* event loop used for fd handlers, timers, etc */
/* long-running tasks intended to always use the same AioContext as this
* BDS may register themselves in this list to be notified of changes
* regarding this BDS's context */
QLIST_HEAD(, BdrvAioNotifier) aio_notifiers;
char filename[PATH_MAX];
char backing_file[PATH_MAX]; /* if non zero, the image is a diff of
this file image */
char backing_format[16]; /* if non-zero and backing_file exists */
QDict *full_open_options;
char exact_filename[PATH_MAX];
BlockDriverState *backing_hd;
BdrvChild *backing_child;
BlockDriverState *file;
BdrvChild *file_child;
NotifierList close_notifiers;
/* Callback before write request is processed */
NotifierWithReturnList before_write_notifiers;
/* number of in-flight serialising requests */
unsigned int serialising_in_flight;
/* I/O throttling */
CoQueue throttled_reqs[2];
bool io_limits_enabled;
/* The following fields are protected by the ThrottleGroup lock.
* See the ThrottleGroup documentation for details. */
ThrottleState *throttle_state;
ThrottleTimers throttle_timers;
unsigned pending_reqs[2];
QLIST_ENTRY(BlockDriverState) round_robin;
/* I/O stats (display with "info blockstats"). */
BlockAcctStats stats;
/* I/O Limits */
BlockLimits bl;
/* Whether produces zeros when read beyond eof */
bool zero_beyond_eof;
/* Alignment requirement for offset/length of I/O requests */
unsigned int request_alignment;
/* the block size for which the guest device expects atomicity */
int guest_block_size;
/* 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 */
BlockdevOnError on_read_error, on_write_error;
bool iostatus_enabled;
BlockDeviceIoStatus iostatus;
/* the following member gives a name to every node on the bs graph. */
char node_name[32];
/* element of the list of named nodes building the graph */
QTAILQ_ENTRY(BlockDriverState) node_list;
/* element of the list of "drives" the guest sees */
QTAILQ_ENTRY(BlockDriverState) device_list;
QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps;
int refcnt;
QLIST_HEAD(, BdrvTrackedRequest) tracked_requests;
/* operation blockers */
QLIST_HEAD(, BdrvOpBlocker) op_blockers[BLOCK_OP_TYPE_MAX];
/* long-running background operation */
BlockJob *job;
/* The node that this node inherited default options from (and a reopen on
* which can affect this node by changing these defaults). This is always a
* parent node of this node. */
BlockDriverState *inherits_from;
QLIST_HEAD(, BdrvChild) children;
QDict *options;
BlockdevDetectZeroesOptions detect_zeroes;
/* The error object in use for blocking operations on backing_hd */
Error *backing_blocker;
block: add event when disk usage exceeds threshold Managing applications, like oVirt (http://www.ovirt.org), make extensive use of thin-provisioned disk images. To let the guest run smoothly and be not unnecessarily paused, oVirt sets a disk usage threshold (so called 'high water mark') based on the occupation of the device, and automatically extends the image once the threshold is reached or exceeded. In order to detect the crossing of the threshold, oVirt has no choice but aggressively polling the QEMU monitor using the query-blockstats command. This lead to unnecessary system load, and is made even worse under scale: deployments with hundreds of VMs are no longer rare. To fix this, this patch adds: * A new monitor command `block-set-write-threshold', to set a mark for a given block device. * A new event `BLOCK_WRITE_THRESHOLD', to report if a block device usage exceeds the threshold. * A new `write_threshold' field into the `BlockDeviceInfo' structure, to report the configured threshold. This will allow the managing application to use smarter and more efficient monitoring, greatly reducing the need of polling. [Updated qemu-iotests 067 output to add the new 'write_threshold' property. --Stefan] [Changed g_assert_false() to !g_assert() to fix the build on older glib versions. --Kevin] Signed-off-by: Francesco Romani <fromani@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 1421068273-692-1-git-send-email-fromani@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2015-01-12 21:11:13 +08:00
/* threshold limit for writes, in bytes. "High water mark". */
uint64_t write_threshold_offset;
NotifierWithReturn write_threshold_notifier;
};
/* Essential block drivers which must always be statically linked into qemu, and
* which therefore can be accessed without using bdrv_find_format() */
extern BlockDriver bdrv_file;
extern BlockDriver bdrv_raw;
extern BlockDriver bdrv_qcow2;
/**
* bdrv_setup_io_funcs:
*
* Prepare a #BlockDriver for I/O request processing by populating
* unimplemented coroutine and AIO interfaces with generic wrapper functions
* that fall back to implemented interfaces.
*/
void bdrv_setup_io_funcs(BlockDriver *bdrv);
int get_tmp_filename(char *filename, int size);
raw: Prohibit dangerous writes for probed images If the user neglects to specify the image format, QEMU probes the image to guess it automatically, for convenience. Relying on format probing is insecure for raw images (CVE-2008-2004). If the guest writes a suitable header to the device, the next probe will recognize a format chosen by the guest. A malicious guest can abuse this to gain access to host files, e.g. by crafting a QCOW2 header with backing file /etc/shadow. Commit 1e72d3b (April 2008) provided -drive parameter format to let users disable probing. Commit f965509 (March 2009) extended QCOW2 to optionally store the backing file format, to let users disable backing file probing. QED has had a flag to suppress probing since the beginning (2010), set whenever a raw backing file is assigned. All of these additions that allow to avoid format probing have to be specified explicitly. The default still allows the attack. In order to fix this, commit 79368c8 (July 2010) put probed raw images in a restricted mode, in which they wouldn't be able to overwrite the first few bytes of the image so that they would identify as a different image. If a write to the first sector would write one of the signatures of another driver, qemu would instead zero out the first four bytes. This patch was later reverted in commit 8b33d9e (September 2010) because it didn't get the handling of unaligned qiov members right. Today's block layer that is based on coroutines and has qiov utility functions makes it much easier to get this functionality right, so this patch implements it. The other differences of this patch to the old one are that it doesn't silently write something different than the guest requested by zeroing out some bytes (it fails the request instead) and that it doesn't maintain a list of signatures in the raw driver (it calls the usual probe function instead). Note that this change doesn't introduce new breakage for false positive cases where the guest legitimately writes data into the first sector that matches the signatures of an image format (e.g. for nested virt): These cases were broken before, only the failure mode changes from corruption after the next restart (when the wrong format is probed) to failing the problematic write request. Also note that like in the original patch, the restrictions only apply if the image format has been guessed by probing. Explicitly specifying a format allows guests to write anything they like. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Reviewed-by: Max Reitz <mreitz@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 1416497234-29880-8-git-send-email-kwolf@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2014-11-20 23:27:12 +08:00
BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
const char *filename);
void bdrv_set_io_limits(BlockDriverState *bs,
ThrottleConfig *cfg);
/**
* bdrv_add_before_write_notifier:
*
* Register a callback that is invoked before write requests are processed but
* after any throttling or waiting for overlapping requests.
*/
void bdrv_add_before_write_notifier(BlockDriverState *bs,
NotifierWithReturn *notifier);
/**
* bdrv_detach_aio_context:
*
* May be called from .bdrv_detach_aio_context() to detach children from the
* current #AioContext. This is only needed by block drivers that manage their
* own children. Both ->file and ->backing_hd are automatically handled and
* block drivers should not call this function on them explicitly.
*/
void bdrv_detach_aio_context(BlockDriverState *bs);
/**
* bdrv_attach_aio_context:
*
* May be called from .bdrv_attach_aio_context() to attach children to the new
* #AioContext. This is only needed by block drivers that manage their own
* children. Both ->file and ->backing_hd are automatically handled and block
* drivers should not call this function on them explicitly.
*/
void bdrv_attach_aio_context(BlockDriverState *bs,
AioContext *new_context);
/**
* bdrv_add_aio_context_notifier:
*
* If a long-running job intends to be always run in the same AioContext as a
* certain BDS, it may use this function to be notified of changes regarding the
* association of the BDS to an AioContext.
*
* attached_aio_context() is called after the target BDS has been attached to a
* new AioContext; detach_aio_context() is called before the target BDS is being
* detached from its old AioContext.
*/
void bdrv_add_aio_context_notifier(BlockDriverState *bs,
void (*attached_aio_context)(AioContext *new_context, void *opaque),
void (*detach_aio_context)(void *opaque), void *opaque);
/**
* bdrv_remove_aio_context_notifier:
*
* Unsubscribe of change notifications regarding the BDS's AioContext. The
* parameters given here have to be the same as those given to
* bdrv_add_aio_context_notifier().
*/
void bdrv_remove_aio_context_notifier(BlockDriverState *bs,
void (*aio_context_attached)(AioContext *,
void *),
void (*aio_context_detached)(void *),
void *opaque);
#ifdef _WIN32
int is_windows_drive(const char *filename);
#endif
/**
* stream_start:
* @bs: Block device to operate on.
* @base: Block device that will become the new base, or %NULL to
* flatten the whole backing file chain onto @bs.
* @base_id: The file name that will be written to @bs as the new
* backing file if the job completes. Ignored if @base is %NULL.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
* Start a streaming operation on @bs. Clusters that are unallocated
* in @bs, but allocated in any image between @base and @bs (both
* exclusive) will be written to @bs. At the end of a successful
* streaming job, the backing file of @bs will be changed to
* @base_id in the written image and to @base in the live BlockDriverState.
*/
void stream_start(BlockDriverState *bs, BlockDriverState *base,
const char *base_id, int64_t speed, BlockdevOnError on_error,
BlockCompletionFunc *cb,
void *opaque, Error **errp);
/**
* commit_start:
* @bs: Active block device.
* @top: Top block device to be committed.
* @base: Block device that will be written into, and become the new top.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @backing_file_str: String to use as the backing file in @top's overlay
* @errp: Error object.
*
*/
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, BlockCompletionFunc *cb,
void *opaque, const char *backing_file_str, Error **errp);
/**
* commit_active_start:
* @bs: Active block device to be committed.
* @base: Block device that will be written into, and become the new top.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
*/
void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
int64_t speed,
BlockdevOnError on_error,
BlockCompletionFunc *cb,
void *opaque, Error **errp);
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 22:49:23 +08:00
/*
* mirror_start:
* @bs: Block device to operate on.
* @target: Block device to write to.
* @replaces: Block graph node name to replace once the mirror is done. Can
* only be used when full mirroring is selected.
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 22:49:23 +08:00
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @granularity: The chosen granularity for the dirty bitmap.
* @buf_size: The amount of data that can be in flight at one time.
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 22:49:23 +08:00
* @mode: Whether to collapse all images in the chain to the target.
* @on_source_error: The action to take upon error reading from the source.
* @on_target_error: The action to take upon error writing to the target.
* @unmap: Whether to unmap target where source sectors only contain zeroes.
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 22:49:23 +08:00
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
* Start a mirroring operation on @bs. Clusters that are allocated
* in @bs will be written to @bs until the job is cancelled or
* manually completed. At the end of a successful mirroring job,
* @bs will be switched to read from @target.
*/
void mirror_start(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, uint32_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
bool unmap,
BlockCompletionFunc *cb,
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 22:49:23 +08:00
void *opaque, Error **errp);
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 23:13:11 +08:00
/*
* backup_start:
* @bs: Block device to operate on.
* @target: Block device to write to.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
Implement sync modes for drive-backup. This patch adds sync-modes to the drive-backup interface and implements the FULL, NONE and TOP modes of synchronization. FULL performs as before copying the entire contents of the drive while preserving the point-in-time using CoW. NONE only copies new writes to the target drive. TOP copies changes to the topmost drive image and preserves the point-in-time using CoW. For sync mode TOP are creating a new target image using the same backing file as the original disk image. Then any new data that has been laid on top of it since creation is copied in the main backup_run() loop. There is an extra check in the 'TOP' case so that we don't bother to copy all the data of the backing file as it already exists in the target. This is where the bdrv_co_is_allocated() is used to determine if the data exists in the topmost layer or below. Also any new data being written is intercepted via the write_notifier hook which ends up calling backup_do_cow() to copy old data out before it gets overwritten. For mode 'NONE' we create the new target image and only copy in the original data from the disk image starting from the time the call was made. This preserves the point in time data by only copying the parts that are *going to change* to the target image. This way we can reconstruct the final image by checking to see if the given block exists in the new target image first, and if it does not, you can get it from the original image. This is basically an optimization allowing you to do point-in-time snapshots with low overhead vs the 'FULL' version. Since there is no old data to copy out the loop in backup_run() for the NONE case just calls qemu_coroutine_yield() which only wakes up after an event (usually cancel in this case). The rest is handled by the before_write notifier which again calls backup_do_cow() to write out the old data so it can be preserved. Signed-off-by: Ian Main <imain@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-07-27 02:39:04 +08:00
* @sync_mode: What parts of the disk image should be copied to the destination.
* @sync_bitmap: The dirty bitmap if sync_mode is MIRROR_SYNC_MODE_INCREMENTAL.
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 23:13:11 +08:00
* @on_source_error: The action to take upon error reading from the source.
* @on_target_error: The action to take upon error writing to the target.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
*
* Start a backup operation on @bs. Clusters in @bs are written to @target
* until the job is cancelled or manually completed.
*/
void backup_start(BlockDriverState *bs, BlockDriverState *target,
Implement sync modes for drive-backup. This patch adds sync-modes to the drive-backup interface and implements the FULL, NONE and TOP modes of synchronization. FULL performs as before copying the entire contents of the drive while preserving the point-in-time using CoW. NONE only copies new writes to the target drive. TOP copies changes to the topmost drive image and preserves the point-in-time using CoW. For sync mode TOP are creating a new target image using the same backing file as the original disk image. Then any new data that has been laid on top of it since creation is copied in the main backup_run() loop. There is an extra check in the 'TOP' case so that we don't bother to copy all the data of the backing file as it already exists in the target. This is where the bdrv_co_is_allocated() is used to determine if the data exists in the topmost layer or below. Also any new data being written is intercepted via the write_notifier hook which ends up calling backup_do_cow() to copy old data out before it gets overwritten. For mode 'NONE' we create the new target image and only copy in the original data from the disk image starting from the time the call was made. This preserves the point in time data by only copying the parts that are *going to change* to the target image. This way we can reconstruct the final image by checking to see if the given block exists in the new target image first, and if it does not, you can get it from the original image. This is basically an optimization allowing you to do point-in-time snapshots with low overhead vs the 'FULL' version. Since there is no old data to copy out the loop in backup_run() for the NONE case just calls qemu_coroutine_yield() which only wakes up after an event (usually cancel in this case). The rest is handled by the before_write notifier which again calls backup_do_cow() to write out the old data so it can be preserved. Signed-off-by: Ian Main <imain@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-07-27 02:39:04 +08:00
int64_t speed, MirrorSyncMode sync_mode,
BdrvDirtyBitmap *sync_bitmap,
Implement sync modes for drive-backup. This patch adds sync-modes to the drive-backup interface and implements the FULL, NONE and TOP modes of synchronization. FULL performs as before copying the entire contents of the drive while preserving the point-in-time using CoW. NONE only copies new writes to the target drive. TOP copies changes to the topmost drive image and preserves the point-in-time using CoW. For sync mode TOP are creating a new target image using the same backing file as the original disk image. Then any new data that has been laid on top of it since creation is copied in the main backup_run() loop. There is an extra check in the 'TOP' case so that we don't bother to copy all the data of the backing file as it already exists in the target. This is where the bdrv_co_is_allocated() is used to determine if the data exists in the topmost layer or below. Also any new data being written is intercepted via the write_notifier hook which ends up calling backup_do_cow() to copy old data out before it gets overwritten. For mode 'NONE' we create the new target image and only copy in the original data from the disk image starting from the time the call was made. This preserves the point in time data by only copying the parts that are *going to change* to the target image. This way we can reconstruct the final image by checking to see if the given block exists in the new target image first, and if it does not, you can get it from the original image. This is basically an optimization allowing you to do point-in-time snapshots with low overhead vs the 'FULL' version. Since there is no old data to copy out the loop in backup_run() for the NONE case just calls qemu_coroutine_yield() which only wakes up after an event (usually cancel in this case). The rest is handled by the before_write notifier which again calls backup_do_cow() to write out the old data so it can be preserved. Signed-off-by: Ian Main <imain@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-07-27 02:39:04 +08:00
BlockdevOnError on_source_error,
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 23:13:11 +08:00
BlockdevOnError on_target_error,
BlockCompletionFunc *cb, void *opaque,
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 23:13:11 +08:00
Error **errp);
void blk_dev_change_media_cb(BlockBackend *blk, bool load);
bool blk_dev_has_removable_media(BlockBackend *blk);
void blk_dev_eject_request(BlockBackend *blk, bool force);
bool blk_dev_is_tray_open(BlockBackend *blk);
bool blk_dev_is_medium_locked(BlockBackend *blk);
void blk_dev_resize_cb(BlockBackend *blk);
void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector, int nr_sectors);
#endif /* BLOCK_INT_H */