qemu-e2k/block/copy-on-read.c

289 lines
8.7 KiB
C
Raw Normal View History

/*
* 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"
#include "qemu/module.h"
#include "qapi/error.h"
#include "qapi/qmp/qdict.h"
#include "block/copy-on-read.h"
typedef struct BDRVStateCOR {
BlockDriverState *bottom_bs;
bool chain_frozen;
} BDRVStateCOR;
static int cor_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BlockDriverState *bottom_bs = NULL;
BDRVStateCOR *state = bs->opaque;
/* Find a bottom node name, if any */
const char *bottom_node = qdict_get_try_str(options, "bottom");
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
BDRV_CHILD_FILTERED | BDRV_CHILD_PRIMARY,
false, errp);
if (!bs->file) {
return -EINVAL;
}
bs->supported_read_flags = BDRV_REQ_PREFETCH;
bs->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED |
(BDRV_REQ_FUA & bs->file->bs->supported_write_flags);
bs->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED |
((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) &
bs->file->bs->supported_zero_flags);
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;
/*
* 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.
*/
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,
BdrvChildRole role,
BlockReopenQueue *reopen_queue,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
*nperm = perm & PERM_PASSTHROUGH;
*nshared = (shared & PERM_PASSTHROUGH) | PERM_UNCHANGED;
/* 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;
}
}
static int64_t cor_getlength(BlockDriverState *bs)
{
return bdrv_getlength(bs->file->bs);
}
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 12:27:59 +02:00
int64_t offset, int64_t bytes,
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 12:27:59 +02:00
BdrvRequestFlags flags)
{
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;
}
}
/* 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;
}
}
offset += n;
qiov_offset += n;
bytes -= n;
}
return 0;
}
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 12:28:00 +02:00
int64_t offset,
int64_t bytes,
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 12:28:00 +02:00
size_t qiov_offset,
BdrvRequestFlags flags)
{
return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset,
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)
{
return bdrv_co_pdiscard(bs->file, offset, bytes);
}
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 12:28:00 +02:00
int64_t offset,
int64_t bytes,
QEMUIOVector *qiov)
{
return bdrv_co_pwritev(bs->file, offset, bytes, qiov,
BDRV_REQ_WRITE_COMPRESSED);
}
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 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);
}
static BlockDriver bdrv_copy_on_read = {
.format_name = "copy-on-read",
.instance_size = sizeof(BDRVStateCOR),
.bdrv_open = cor_open,
.bdrv_close = cor_close,
.bdrv_child_perm = cor_child_perm,
.bdrv_getlength = cor_getlength,
.bdrv_co_preadv_part = cor_co_preadv_part,
.bdrv_co_pwritev_part = cor_co_pwritev_part,
.bdrv_co_pwrite_zeroes = cor_co_pwrite_zeroes,
.bdrv_co_pdiscard = cor_co_pdiscard,
.bdrv_co_pwritev_compressed = cor_co_pwritev_compressed,
.bdrv_eject = cor_eject,
.bdrv_lock_medium = cor_lock_medium,
.has_variable_length = true,
.is_filter = true,
};
void bdrv_cor_filter_drop(BlockDriverState *cor_filter_bs)
{
BDRVStateCOR *s = cor_filter_bs->opaque;
/* 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);
}
bdrv_drop_filter(cor_filter_bs, &error_abort);
bdrv_unref(cor_filter_bs);
}
static void bdrv_copy_on_read_init(void)
{
bdrv_register(&bdrv_copy_on_read);
}
block_init(bdrv_copy_on_read_init);