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"
|
2020-12-16 09:16:53 +03:00
|
|
|
#include "qapi/error.h"
|
2020-12-16 09:16:55 +03:00
|
|
|
#include "qapi/qmp/qdict.h"
|
2020-12-16 09:16:53 +03:00
|
|
|
#include "block/copy-on-read.h"
|
|
|
|
|
|
|
|
|
|
|
|
typedef struct BDRVStateCOR {
|
2020-12-16 09:16:55 +03:00
|
|
|
BlockDriverState *bottom_bs;
|
|
|
|
bool chain_frozen;
|
2020-12-16 09:16:53 +03:00
|
|
|
} BDRVStateCOR;
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
|
|
|
|
static int cor_open(BlockDriverState *bs, QDict *options, int flags,
|
|
|
|
Error **errp)
|
|
|
|
{
|
2020-12-16 09:16:55 +03:00
|
|
|
BlockDriverState *bottom_bs = NULL;
|
2020-12-16 09:16:53 +03:00
|
|
|
BDRVStateCOR *state = bs->opaque;
|
2020-12-16 09:16:55 +03:00
|
|
|
/* Find a bottom node name, if any */
|
|
|
|
const char *bottom_node = qdict_get_try_str(options, "bottom");
|
2020-12-16 09:16:53 +03:00
|
|
|
|
2020-05-13 14:05:36 +03:00
|
|
|
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
|
|
|
|
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
|
|
|
|
false, errp);
|
2018-04-21 16:29:21 +03:00
|
|
|
if (!bs->file) {
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2020-12-16 09:16:58 +03:00
|
|
|
bs->supported_read_flags = BDRV_REQ_PREFETCH;
|
|
|
|
|
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
|
|
|
|
2020-12-16 09:16:55 +03:00
|
|
|
if (bottom_node) {
|
|
|
|
bottom_bs = bdrv_find_node(bottom_node);
|
|
|
|
if (!bottom_bs) {
|
|
|
|
error_setg(errp, "Bottom node '%s' not found", bottom_node);
|
|
|
|
qdict_del(options, "bottom");
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
qdict_del(options, "bottom");
|
|
|
|
|
|
|
|
if (!bottom_bs->drv) {
|
|
|
|
error_setg(errp, "Bottom node '%s' not opened", bottom_node);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bottom_bs->drv->is_filter) {
|
|
|
|
error_setg(errp, "Bottom node '%s' is a filter", bottom_node);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (bdrv_freeze_backing_chain(bs, bottom_bs, errp) < 0) {
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
state->chain_frozen = true;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We do freeze the chain, so it shouldn't be removed. Still, storing a
|
|
|
|
* pointer worth bdrv_ref().
|
|
|
|
*/
|
|
|
|
bdrv_ref(bottom_bs);
|
|
|
|
}
|
|
|
|
state->bottom_bs = bottom_bs;
|
2020-12-16 09:16:53 +03:00
|
|
|
|
|
|
|
/*
|
|
|
|
* We don't need to call bdrv_child_refresh_perms() now as the permissions
|
|
|
|
* will be updated later when the filter node gets its parent.
|
|
|
|
*/
|
|
|
|
|
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,
|
2020-05-13 14:05:16 +03:00
|
|
|
BdrvChildRole role,
|
2018-04-21 16:29:21 +03:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2020-12-16 09:16:51 +03:00
|
|
|
static int coroutine_fn cor_co_preadv_part(BlockDriverState *bs,
|
block: use int64_t instead of uint64_t in driver read handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver read handlers parameters which are already 64bit to
signed type.
While being here, convert also flags parameter to be BdrvRequestFlags.
Now let's consider all callers. Simple
git grep '\->bdrv_\(aio\|co\)_preadv\(_part\)\?'
shows that's there three callers of driver function:
bdrv_driver_preadv() in block/io.c, passes int64_t, checked by
bdrv_check_qiov_request() to be non-negative.
qcow2_load_vmstate() does bdrv_check_qiov_request().
do_perform_cow_read() has uint64_t argument. And a lot of things in
qcow2 driver are uint64_t, so converting it is big job. But we must
not work with requests that don't satisfy bdrv_check_qiov_request(),
so let's just assert it here.
Still, the functions may be called directly, not only by drv->...
Let's check:
git grep '\.bdrv_\(aio\|co\)_preadv\(_part\)\?\s*=' | \
awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \
while read func; do git grep "$func(" | \
grep -v "$func(BlockDriverState"; done
The only one such caller:
QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1);
...
ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0);
in tests/unit/test-bdrv-drain.c, and it's OK obviously.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-4-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
[eblake: fix typos]
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:27:59 +03:00
|
|
|
int64_t offset, int64_t bytes,
|
2020-12-16 09:16:51 +03:00
|
|
|
QEMUIOVector *qiov,
|
|
|
|
size_t qiov_offset,
|
block: use int64_t instead of uint64_t in driver read handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver read handlers parameters which are already 64bit to
signed type.
While being here, convert also flags parameter to be BdrvRequestFlags.
Now let's consider all callers. Simple
git grep '\->bdrv_\(aio\|co\)_preadv\(_part\)\?'
shows that's there three callers of driver function:
bdrv_driver_preadv() in block/io.c, passes int64_t, checked by
bdrv_check_qiov_request() to be non-negative.
qcow2_load_vmstate() does bdrv_check_qiov_request().
do_perform_cow_read() has uint64_t argument. And a lot of things in
qcow2 driver are uint64_t, so converting it is big job. But we must
not work with requests that don't satisfy bdrv_check_qiov_request(),
so let's just assert it here.
Still, the functions may be called directly, not only by drv->...
Let's check:
git grep '\.bdrv_\(aio\|co\)_preadv\(_part\)\?\s*=' | \
awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \
while read func; do git grep "$func(" | \
grep -v "$func(BlockDriverState"; done
The only one such caller:
QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, &data, 1);
...
ret = bdrv_replace_test_co_preadv(bs, 0, 1, &qiov, 0);
in tests/unit/test-bdrv-drain.c, and it's OK obviously.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-4-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
[eblake: fix typos]
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:27:59 +03:00
|
|
|
BdrvRequestFlags flags)
|
2018-04-21 16:29:21 +03:00
|
|
|
{
|
2020-12-16 09:16:55 +03:00
|
|
|
int64_t n;
|
|
|
|
int local_flags;
|
|
|
|
int ret;
|
|
|
|
BDRVStateCOR *state = bs->opaque;
|
|
|
|
|
|
|
|
if (!state->bottom_bs) {
|
|
|
|
return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset,
|
|
|
|
flags | BDRV_REQ_COPY_ON_READ);
|
|
|
|
}
|
|
|
|
|
|
|
|
while (bytes) {
|
|
|
|
local_flags = flags;
|
|
|
|
|
|
|
|
/* In case of failure, try to copy-on-read anyway */
|
|
|
|
ret = bdrv_is_allocated(bs->file->bs, offset, bytes, &n);
|
|
|
|
if (ret <= 0) {
|
|
|
|
ret = bdrv_is_allocated_above(bdrv_backing_chain_next(bs->file->bs),
|
|
|
|
state->bottom_bs, true, offset,
|
|
|
|
n, &n);
|
|
|
|
if (ret > 0 || ret < 0) {
|
|
|
|
local_flags |= BDRV_REQ_COPY_ON_READ;
|
|
|
|
}
|
|
|
|
/* Finish earlier if the end of a backing file has been reached */
|
|
|
|
if (n == 0) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-12-16 09:16:58 +03:00
|
|
|
/* Skip if neither read nor write are needed */
|
|
|
|
if ((local_flags & (BDRV_REQ_PREFETCH | BDRV_REQ_COPY_ON_READ)) !=
|
|
|
|
BDRV_REQ_PREFETCH) {
|
|
|
|
ret = bdrv_co_preadv_part(bs->file, offset, n, qiov, qiov_offset,
|
|
|
|
local_flags);
|
|
|
|
if (ret < 0) {
|
|
|
|
return ret;
|
|
|
|
}
|
2020-12-16 09:16:55 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
offset += n;
|
|
|
|
qiov_offset += n;
|
|
|
|
bytes -= n;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2020-12-16 09:16:51 +03:00
|
|
|
static int coroutine_fn cor_co_pwritev_part(BlockDriverState *bs,
|
block: use int64_t instead of uint64_t in driver write handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver write handlers parameters which are already 64bit to
signed type.
While being here, convert also flags parameter to be BdrvRequestFlags.
Now let's consider all callers. Simple
git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?'
shows that's there three callers of driver function:
bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in
block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to
be non-negative.
qcow2_save_vmstate() does bdrv_check_qiov_request().
Still, the functions may be called directly, not only by drv->...
Let's check:
git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \
awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \
while read func; do git grep "$func(" | \
grep -v "$func(BlockDriverState"; done
shows several callers:
qcow2:
qcow2_co_truncate() write at most up to @offset, which is checked in
generic qcow2_co_truncate() by bdrv_check_request().
qcow2_co_pwritev_compressed_task() pass the request (or part of the
request) that already went through normal write path, so it should
be OK
qcow:
qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch
quorum:
quorum_co_pwrite_zeroes() pass int64_t and int - OK
throttle:
throttle_co_pwritev_compressed() pass int64_t, it's updated by this
patch
vmdk:
vmdk_co_pwritev_compressed() pass int64_t, it's updated by this
patch
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:00 +03:00
|
|
|
int64_t offset,
|
|
|
|
int64_t bytes,
|
2020-12-16 09:16:51 +03:00
|
|
|
QEMUIOVector *qiov,
|
block: use int64_t instead of uint64_t in driver write handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver write handlers parameters which are already 64bit to
signed type.
While being here, convert also flags parameter to be BdrvRequestFlags.
Now let's consider all callers. Simple
git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?'
shows that's there three callers of driver function:
bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in
block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to
be non-negative.
qcow2_save_vmstate() does bdrv_check_qiov_request().
Still, the functions may be called directly, not only by drv->...
Let's check:
git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \
awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \
while read func; do git grep "$func(" | \
grep -v "$func(BlockDriverState"; done
shows several callers:
qcow2:
qcow2_co_truncate() write at most up to @offset, which is checked in
generic qcow2_co_truncate() by bdrv_check_request().
qcow2_co_pwritev_compressed_task() pass the request (or part of the
request) that already went through normal write path, so it should
be OK
qcow:
qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch
quorum:
quorum_co_pwrite_zeroes() pass int64_t and int - OK
throttle:
throttle_co_pwritev_compressed() pass int64_t, it's updated by this
patch
vmdk:
vmdk_co_pwritev_compressed() pass int64_t, it's updated by this
patch
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:00 +03:00
|
|
|
size_t qiov_offset,
|
|
|
|
BdrvRequestFlags flags)
|
2018-04-21 16:29:21 +03:00
|
|
|
{
|
2020-12-16 09:16:51 +03:00
|
|
|
return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset,
|
|
|
|
flags);
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_pwrite_zeroes(BlockDriverState *bs,
|
block: use int64_t instead of int in driver write_zeroes handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver write_zeroes handlers bytes parameter to int64_t.
The only caller of all updated function is bdrv_co_do_pwrite_zeroes().
bdrv_co_do_pwrite_zeroes() itself is of course OK with widening of
callee parameter type. Also, bdrv_co_do_pwrite_zeroes()'s
max_write_zeroes is limited to INT_MAX. So, updated functions all are
safe, they will not get "bytes" larger than before.
Still, let's look through all updated functions, and add assertions to
the ones which are actually unprepared to values larger than INT_MAX.
For these drivers also set explicit max_pwrite_zeroes limit.
Let's go:
blkdebug: calculations can't overflow, thanks to
bdrv_check_qiov_request() in generic layer. rule_check() and
bdrv_co_pwrite_zeroes() both have 64bit argument.
blklogwrites: pass to blk_log_writes_co_log() with 64bit argument.
blkreplay, copy-on-read, filter-compress: pass to
bdrv_co_pwrite_zeroes() which is OK
copy-before-write: Calls cbw_do_copy_before_write() and
bdrv_co_pwrite_zeroes, both have 64bit argument.
file-posix: both handler calls raw_do_pwrite_zeroes, which is updated.
In raw_do_pwrite_zeroes() calculations are OK due to
bdrv_check_qiov_request(), bytes go to RawPosixAIOData::aio_nbytes
which is uint64_t.
Check also where that uint64_t gets handed:
handle_aiocb_write_zeroes_block() passes a uint64_t[2] to
ioctl(BLKZEROOUT), handle_aiocb_write_zeroes() calls do_fallocate()
which takes off_t (and we compile to always have 64-bit off_t), as
does handle_aiocb_write_zeroes_unmap. All look safe.
gluster: bytes go to GlusterAIOCB::size which is int64_t and to
glfs_zerofill_async works with off_t.
iscsi: Aha, here we deal with iscsi_writesame16_task() that has
uint32_t num_blocks argument and iscsi_writesame16_task() has
uint16_t argument. Make comments, add assertions and clarify
max_pwrite_zeroes calculation.
iscsi_allocmap_() functions already has int64_t argument
is_byte_request_lun_aligned is simple to update, do it.
mirror_top: pass to bdrv_mirror_top_do_write which has uint64_t
argument
nbd: Aha, here we have protocol limitation, and NBDRequest::len is
uint32_t. max_pwrite_zeroes is cleanly set to 32bit value, so we are
OK for now.
nvme: Again, protocol limitation. And no inherent limit for
write-zeroes at all. But from code that calculates cdw12 it's obvious
that we do have limit and alignment. Let's clarify it. Also,
obviously the code is not prepared to handle bytes=0. Let's handle
this case too.
trace events already 64bit
preallocate: pass to handle_write() and bdrv_co_pwrite_zeroes(), both
64bit.
rbd: pass to qemu_rbd_start_co() which is 64bit.
qcow2: offset + bytes and alignment still works good (thanks to
bdrv_check_qiov_request()), so tail calculation is OK
qcow2_subcluster_zeroize() has 64bit argument, should be OK
trace events updated
qed: qed_co_request wants int nb_sectors. Also in code we have size_t
used for request length which may be 32bit. So, let's just keep
INT_MAX as a limit (aligning it down to pwrite_zeroes_alignment) and
don't care.
raw-format: Is OK. raw_adjust_offset and bdrv_co_pwrite_zeroes are both
64bit.
throttle: Both throttle_group_co_io_limits_intercept() and
bdrv_co_pwrite_zeroes() are 64bit.
vmdk: pass to vmdk_pwritev which is 64bit
quorum: pass to quorum_co_pwritev() which is 64bit
Hooray!
At this point all block drivers are prepared to support 64bit
write-zero requests, or have explicitly set max_pwrite_zeroes.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-8-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
[eblake: use <= rather than < in assertions relying on max_pwrite_zeroes]
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:03 +03:00
|
|
|
int64_t offset, int64_t bytes,
|
2018-04-21 16:29:21 +03:00
|
|
|
BdrvRequestFlags flags)
|
|
|
|
{
|
|
|
|
return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int coroutine_fn cor_co_pdiscard(BlockDriverState *bs,
|
block: use int64_t instead of int in driver discard handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver discard handlers bytes parameter to int64_t.
The only caller of all updated function is bdrv_co_pdiscard in
block/io.c. It is already prepared to work with 64bit requests, but
pass at most max(bs->bl.max_pdiscard, INT_MAX) to the driver.
Let's look at all updated functions:
blkdebug: all calculations are still OK, thanks to
bdrv_check_qiov_request().
both rule_check and bdrv_co_pdiscard are 64bit
blklogwrites: pass to blk_loc_writes_co_log which is 64bit
blkreplay, copy-on-read, filter-compress: pass to bdrv_co_pdiscard, OK
copy-before-write: pass to bdrv_co_pdiscard which is 64bit and to
cbw_do_copy_before_write which is 64bit
file-posix: one handler calls raw_account_discard() is 64bit and both
handlers calls raw_do_pdiscard(). Update raw_do_pdiscard, which pass
to RawPosixAIOData::aio_nbytes, which is 64bit (and calls
raw_account_discard())
gluster: somehow, third argument of glfs_discard_async is size_t.
Let's set max_pdiscard accordingly.
iscsi: iscsi_allocmap_set_invalid is 64bit,
!is_byte_request_lun_aligned is 64bit.
list.num is uint32_t. Let's clarify max_pdiscard and
pdiscard_alignment.
mirror_top: pass to bdrv_mirror_top_do_write() which is
64bit
nbd: protocol limitation. max_pdiscard is alredy set strict enough,
keep it as is for now.
nvme: buf.nlb is uint32_t and we do shift. So, add corresponding limits
to nvme_refresh_limits().
preallocate: pass to bdrv_co_pdiscard() which is 64bit.
rbd: pass to qemu_rbd_start_co() which is 64bit.
qcow2: calculations are still OK, thanks to bdrv_check_qiov_request(),
qcow2_cluster_discard() is 64bit.
raw-format: raw_adjust_offset() is 64bit, bdrv_co_pdiscard too.
throttle: pass to bdrv_co_pdiscard() which is 64bit and to
throttle_group_co_io_limits_intercept() which is 64bit as well.
test-block-iothread: bytes argument is unused
Great! Now all drivers are prepared to handle 64bit discard requests,
or else have explicit max_pdiscard limits.
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-11-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:06 +03:00
|
|
|
int64_t offset, int64_t bytes)
|
2018-04-21 16:29:21 +03:00
|
|
|
{
|
2018-07-10 09:31:17 +03:00
|
|
|
return bdrv_co_pdiscard(bs->file, offset, bytes);
|
2018-04-21 16:29:21 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
|
2019-11-28 18:12:36 +03:00
|
|
|
static int coroutine_fn cor_co_pwritev_compressed(BlockDriverState *bs,
|
block: use int64_t instead of uint64_t in driver write handlers
We are generally moving to int64_t for both offset and bytes parameters
on all io paths.
Main motivation is realization of 64-bit write_zeroes operation for
fast zeroing large disk chunks, up to the whole disk.
We chose signed type, to be consistent with off_t (which is signed) and
with possibility for signed return type (where negative value means
error).
So, convert driver write handlers parameters which are already 64bit to
signed type.
While being here, convert also flags parameter to be BdrvRequestFlags.
Now let's consider all callers. Simple
git grep '\->bdrv_\(aio\|co\)_pwritev\(_part\)\?'
shows that's there three callers of driver function:
bdrv_driver_pwritev() and bdrv_driver_pwritev_compressed() in
block/io.c, both pass int64_t, checked by bdrv_check_qiov_request() to
be non-negative.
qcow2_save_vmstate() does bdrv_check_qiov_request().
Still, the functions may be called directly, not only by drv->...
Let's check:
git grep '\.bdrv_\(aio\|co\)_pwritev\(_part\)\?\s*=' | \
awk '{print $4}' | sed 's/,//' | sed 's/&//' | sort | uniq | \
while read func; do git grep "$func(" | \
grep -v "$func(BlockDriverState"; done
shows several callers:
qcow2:
qcow2_co_truncate() write at most up to @offset, which is checked in
generic qcow2_co_truncate() by bdrv_check_request().
qcow2_co_pwritev_compressed_task() pass the request (or part of the
request) that already went through normal write path, so it should
be OK
qcow:
qcow_co_pwritev_compressed() pass int64_t, it's updated by this patch
quorum:
quorum_co_pwrite_zeroes() pass int64_t and int - OK
throttle:
throttle_co_pwritev_compressed() pass int64_t, it's updated by this
patch
vmdk:
vmdk_co_pwritev_compressed() pass int64_t, it's updated by this
patch
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20210903102807.27127-5-vsementsov@virtuozzo.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
2021-09-03 13:28:00 +03:00
|
|
|
int64_t offset,
|
|
|
|
int64_t bytes,
|
2019-11-28 18:12:36 +03:00
|
|
|
QEMUIOVector *qiov)
|
|
|
|
{
|
|
|
|
return bdrv_co_pwritev(bs->file, offset, bytes, qiov,
|
|
|
|
BDRV_REQ_WRITE_COMPRESSED);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2020-12-16 09:16:55 +03:00
|
|
|
static void cor_close(BlockDriverState *bs)
|
|
|
|
{
|
|
|
|
BDRVStateCOR *s = bs->opaque;
|
|
|
|
|
|
|
|
if (s->chain_frozen) {
|
|
|
|
s->chain_frozen = false;
|
|
|
|
bdrv_unfreeze_backing_chain(bs, s->bottom_bs);
|
|
|
|
}
|
|
|
|
|
|
|
|
bdrv_unref(s->bottom_bs);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
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",
|
2020-12-16 09:16:53 +03:00
|
|
|
.instance_size = sizeof(BDRVStateCOR),
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
.bdrv_open = cor_open,
|
2020-12-16 09:16:55 +03:00
|
|
|
.bdrv_close = cor_close,
|
2018-04-21 16:29:21 +03:00
|
|
|
.bdrv_child_perm = cor_child_perm,
|
|
|
|
|
|
|
|
.bdrv_getlength = cor_getlength,
|
|
|
|
|
2020-12-16 09:16:51 +03:00
|
|
|
.bdrv_co_preadv_part = cor_co_preadv_part,
|
|
|
|
.bdrv_co_pwritev_part = cor_co_pwritev_part,
|
2018-04-21 16:29:21 +03:00
|
|
|
.bdrv_co_pwrite_zeroes = cor_co_pwrite_zeroes,
|
|
|
|
.bdrv_co_pdiscard = cor_co_pdiscard,
|
2019-11-28 18:12:36 +03:00
|
|
|
.bdrv_co_pwritev_compressed = cor_co_pwritev_compressed,
|
2018-04-21 16:29:21 +03:00
|
|
|
|
|
|
|
.bdrv_eject = cor_eject,
|
|
|
|
.bdrv_lock_medium = cor_lock_medium,
|
|
|
|
|
|
|
|
.has_variable_length = true,
|
|
|
|
.is_filter = true,
|
|
|
|
};
|
|
|
|
|
2020-12-16 09:16:53 +03:00
|
|
|
|
|
|
|
void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs)
|
|
|
|
{
|
|
|
|
BDRVStateCOR *s = cor_filter_bs->opaque;
|
|
|
|
|
2020-12-16 09:16:55 +03:00
|
|
|
/* unfreeze, as otherwise bdrv_replace_node() will fail */
|
|
|
|
if (s->chain_frozen) {
|
|
|
|
s->chain_frozen = false;
|
|
|
|
bdrv_unfreeze_backing_chain(cor_filter_bs, s->bottom_bs);
|
|
|
|
}
|
2021-05-06 22:41:43 +03:00
|
|
|
bdrv_drop_filter(cor_filter_bs, &error_abort);
|
2020-12-16 09:16:53 +03:00
|
|
|
bdrv_unref(cor_filter_bs);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2018-04-21 16:29:21 +03:00
|
|
|
static void bdrv_copy_on_read_init(void)
|
|
|
|
{
|
|
|
|
bdrv_register(&bdrv_copy_on_read);
|
|
|
|
}
|
|
|
|
|
|
|
|
block_init(bdrv_copy_on_read_init);
|