2018-04-21 16:29:21 +03:00
|
|
|
/*
|
|
|
|
* Copy-on-read filter block driver
|
|
|
|
*
|
|
|
|
* Copyright (c) 2018 Red Hat, Inc.
|
|
|
|
*
|
|
|
|
* Author:
|
|
|
|
* Max Reitz <mreitz@redhat.com>
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License as
|
|
|
|
* published by the Free Software Foundation; either version 2 or
|
|
|
|
* (at your option) version 3 of the License.
|
|
|
|
*
|
|
|
|
* This program is distributed in the hope that it will be useful,
|
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
|
* GNU General Public License for more details.
|
|
|
|
*
|
|
|
|
* You should have received a copy of the GNU General Public License
|
|
|
|
* along with this program; if not, see <http://www.gnu.org/licenses/>.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include "qemu/osdep.h"
|
|
|
|
#include "block/block_int.h"
|
2019-05-23 17:35:07 +03:00
|
|
|
#include "qemu/module.h"
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
|
|
|
|
static int cor_open(BlockDriverState *bs, QDict *options, int flags,
|
|
|
|
Error **errp)
|
|
|
|
{
|
|
|
|
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file, false,
|
|
|
|
errp);
|
|
|
|
if (!bs->file) {
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2018-04-21 16:29:26 +03:00
|
|
|
bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
|
2019-03-22 15:42:39 +03:00
|
|
|
(BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
|
2018-04-21 16:29:21 +03:00
|
|
|
|
2018-04-21 16:29:26 +03:00
|
|
|
bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
|
2019-03-22 15:42:39 +03:00
|
|
|
((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
|
|
|
|
bs->file->bs->supported_zero_flags);
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
#define PERM_PASSTHROUGH (BLK_PERM_CONSISTENT_READ \
|
|
|
|
| BLK_PERM_WRITE \
|
|
|
|
| BLK_PERM_RESIZE)
|
|
|
|
#define PERM_UNCHANGED (BLK_PERM_ALL & ~PERM_PASSTHROUGH)
|
|
|
|
|
|
|
|
static void cor_child_perm(BlockDriverState *bs, BdrvChild *c,
|
|
|
|
const BdrvChildRole *role,
|
|
|
|
BlockReopenQueue *reopen_queue,
|
|
|
|
uint64_t perm, uint64_t shared,
|
|
|
|
uint64_t *nperm, uint64_t *nshared)
|
|
|
|
{
|
2019-07-29 13:45:14 +03:00
|
|
|
*nperm = perm & PERM_PASSTHROUGH;
|
|
|
|
*nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED;
|
2018-04-21 16:29:21 +03:00
|
|
|
|
2019-07-29 13:45:14 +03:00
|
|
|
/* We must not request write permissions for an inactive node, the child
|
|
|
|
* cannot provide it. */
|
|
|
|
if (!(bs->open_flags & BDRV_O_INACTIVE)) {
|
|
|
|
*nperm |= BLK_PERM_WRITE_UNCHANGED;
|
|
|
|
}
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int64_t cor_getlength(BlockDriverState *bs)
|
|
|
|
{
|
|
|
|
return bdrv_getlength(bs->file->bs);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
block: Convert .bdrv_truncate callback to coroutine_fn
bdrv_truncate() is an operation that can block (even for a quite long
time, depending on the PreallocMode) in I/O paths that shouldn't block.
Convert it to a coroutine_fn so that we have the infrastructure for
drivers to make their .bdrv_co_truncate implementation asynchronous.
This change could potentially introduce new race conditions because
bdrv_truncate() isn't necessarily executed atomically any more. Whether
this is a problem needs to be evaluated for each block driver that
supports truncate:
* file-posix/win32, gluster, iscsi, nfs, rbd, ssh, sheepdog: The
protocol drivers are trivially safe because they don't actually yield
yet, so there is no change in behaviour.
* copy-on-read, crypto, raw-format: Essentially just filter drivers that
pass the request to a child node, no problem.
* qcow2: The implementation modifies metadata, so it needs to hold
s->lock to be safe with concurrent I/O requests. In order to avoid
double locking, this requires pulling the locking out into
preallocate_co() and using qcow2_write_caches() instead of
bdrv_flush().
* qed: Does a single header update, this is fine without locking.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
2018-06-21 18:54:35 +03:00
|
|
|
static int coroutine_fn cor_co_truncate(BlockDriverState *bs, int64_t offset,
|
|
|
|
PreallocMode prealloc, Error **errp)
|
2018-04-21 16:29:21 +03:00
|
|
|
{
|
block: Convert .bdrv_truncate callback to coroutine_fn
bdrv_truncate() is an operation that can block (even for a quite long
time, depending on the PreallocMode) in I/O paths that shouldn't block.
Convert it to a coroutine_fn so that we have the infrastructure for
drivers to make their .bdrv_co_truncate implementation asynchronous.
This change could potentially introduce new race conditions because
bdrv_truncate() isn't necessarily executed atomically any more. Whether
this is a problem needs to be evaluated for each block driver that
supports truncate:
* file-posix/win32, gluster, iscsi, nfs, rbd, ssh, sheepdog: The
protocol drivers are trivially safe because they don't actually yield
yet, so there is no change in behaviour.
* copy-on-read, crypto, raw-format: Essentially just filter drivers that
pass the request to a child node, no problem.
* qcow2: The implementation modifies metadata, so it needs to hold
s->lock to be safe with concurrent I/O requests. In order to avoid
double locking, this requires pulling the locking out into
preallocate_co() and using qcow2_write_caches() instead of
bdrv_flush().
* qed: Does a single header update, this is fine without locking.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
2018-06-21 18:54:35 +03:00
|
|
|
return bdrv_co_truncate(bs->file, offset, prealloc, errp);
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_preadv(BlockDriverState *bs,
|
|
|
|
uint64_t offset, uint64_t bytes,
|
|
|
|
QEMUIOVector *qiov, int flags)
|
|
|
|
{
|
|
|
|
return bdrv_co_preadv(bs->file, offset, bytes, qiov,
|
|
|
|
flags | BDRV_REQ_COPY_ON_READ);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_pwritev(BlockDriverState *bs,
|
|
|
|
uint64_t offset, uint64_t bytes,
|
|
|
|
QEMUIOVector *qiov, int flags)
|
|
|
|
{
|
|
|
|
|
|
|
|
return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_pwrite_zeroes(BlockDriverState *bs,
|
|
|
|
int64_t offset, int bytes,
|
|
|
|
BdrvRequestFlags flags)
|
|
|
|
{
|
|
|
|
return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_pdiscard(BlockDriverState *bs,
|
|
|
|
int64_t offset, int bytes)
|
|
|
|
{
|
2018-07-10 09:31:17 +03:00
|
|
|
return bdrv_co_pdiscard(bs->file, offset, bytes);
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void cor_eject(BlockDriverState *bs, bool eject_flag)
|
|
|
|
{
|
|
|
|
bdrv_eject(bs->file->bs, eject_flag);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static void cor_lock_medium(BlockDriverState *bs, bool locked)
|
|
|
|
{
|
|
|
|
bdrv_lock_medium(bs->file->bs, locked);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static bool cor_recurse_is_first_non_filter(BlockDriverState *bs,
|
|
|
|
BlockDriverState *candidate)
|
|
|
|
{
|
|
|
|
return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2019-03-18 18:48:01 +03:00
|
|
|
static BlockDriver bdrv_copy_on_read = {
|
2018-04-21 16:29:21 +03:00
|
|
|
.format_name = "copy-on-read",
|
|
|
|
|
|
|
|
.bdrv_open = cor_open,
|
|
|
|
.bdrv_child_perm = cor_child_perm,
|
|
|
|
|
|
|
|
.bdrv_getlength = cor_getlength,
|
block: Convert .bdrv_truncate callback to coroutine_fn
bdrv_truncate() is an operation that can block (even for a quite long
time, depending on the PreallocMode) in I/O paths that shouldn't block.
Convert it to a coroutine_fn so that we have the infrastructure for
drivers to make their .bdrv_co_truncate implementation asynchronous.
This change could potentially introduce new race conditions because
bdrv_truncate() isn't necessarily executed atomically any more. Whether
this is a problem needs to be evaluated for each block driver that
supports truncate:
* file-posix/win32, gluster, iscsi, nfs, rbd, ssh, sheepdog: The
protocol drivers are trivially safe because they don't actually yield
yet, so there is no change in behaviour.
* copy-on-read, crypto, raw-format: Essentially just filter drivers that
pass the request to a child node, no problem.
* qcow2: The implementation modifies metadata, so it needs to hold
s->lock to be safe with concurrent I/O requests. In order to avoid
double locking, this requires pulling the locking out into
preallocate_co() and using qcow2_write_caches() instead of
bdrv_flush().
* qed: Does a single header update, this is fine without locking.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
2018-06-21 18:54:35 +03:00
|
|
|
.bdrv_co_truncate = cor_co_truncate,
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
.bdrv_co_preadv = cor_co_preadv,
|
|
|
|
.bdrv_co_pwritev = cor_co_pwritev,
|
|
|
|
.bdrv_co_pwrite_zeroes = cor_co_pwrite_zeroes,
|
|
|
|
.bdrv_co_pdiscard = cor_co_pdiscard,
|
|
|
|
|
|
|
|
.bdrv_eject = cor_eject,
|
|
|
|
.bdrv_lock_medium = cor_lock_medium,
|
|
|
|
|
|
|
|
.bdrv_co_block_status = bdrv_co_block_status_from_file,
|
|
|
|
|
|
|
|
.bdrv_recurse_is_first_non_filter = cor_recurse_is_first_non_filter,
|
|
|
|
|
|
|
|
.has_variable_length = true,
|
|
|
|
.is_filter = true,
|
|
|
|
};
|
|
|
|
|
|
|
|
static void bdrv_copy_on_read_init(void)
|
|
|
|
{
|
|
|
|
bdrv_register(&bdrv_copy_on_read);
|
|
|
|
}
|
|
|
|
|
|
|
|
block_init(bdrv_copy_on_read_init);
|