xemu/block/copy-before-write.c
Vladimir Sementsov-Ogievskiy 0c8022876f 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>
2021-09-29 13:46:32 -05:00

258 lines
7.6 KiB
C

/*
* copy-before-write filter driver
*
* The driver performs Copy-Before-Write (CBW) operation: it is injected above
* some node, and before each write it copies _old_ data to the target node.
*
* Copyright (c) 2018-2021 Virtuozzo International GmbH.
*
* Author:
* Sementsov-Ogievskiy Vladimir <vsementsov@virtuozzo.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 of the License, or
* (at your option) any later version.
*
* 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 "sysemu/block-backend.h"
#include "qemu/cutils.h"
#include "qapi/error.h"
#include "block/block_int.h"
#include "block/qdict.h"
#include "block/block-copy.h"
#include "block/copy-before-write.h"
typedef struct BDRVCopyBeforeWriteState {
BlockCopyState *bcs;
BdrvChild *target;
} BDRVCopyBeforeWriteState;
static coroutine_fn int cbw_co_preadv(
BlockDriverState *bs, int64_t offset, int64_t bytes,
QEMUIOVector *qiov, BdrvRequestFlags flags)
{
return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
}
static coroutine_fn int cbw_do_copy_before_write(BlockDriverState *bs,
uint64_t offset, uint64_t bytes, BdrvRequestFlags flags)
{
BDRVCopyBeforeWriteState *s = bs->opaque;
uint64_t off, end;
int64_t cluster_size = block_copy_cluster_size(s->bcs);
if (flags & BDRV_REQ_WRITE_UNCHANGED) {
return 0;
}
off = QEMU_ALIGN_DOWN(offset, cluster_size);
end = QEMU_ALIGN_UP(offset + bytes, cluster_size);
return block_copy(s->bcs, off, end - off, true);
}
static int coroutine_fn cbw_co_pdiscard(BlockDriverState *bs,
int64_t offset, int64_t bytes)
{
int ret = cbw_do_copy_before_write(bs, offset, bytes, 0);
if (ret < 0) {
return ret;
}
return bdrv_co_pdiscard(bs->file, offset, bytes);
}
static int coroutine_fn cbw_co_pwrite_zeroes(BlockDriverState *bs,
int64_t offset, int64_t bytes, BdrvRequestFlags flags)
{
int ret = cbw_do_copy_before_write(bs, offset, bytes, flags);
if (ret < 0) {
return ret;
}
return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
}
static coroutine_fn int cbw_co_pwritev(BlockDriverState *bs,
int64_t offset,
int64_t bytes,
QEMUIOVector *qiov,
BdrvRequestFlags flags)
{
int ret = cbw_do_copy_before_write(bs, offset, bytes, flags);
if (ret < 0) {
return ret;
}
return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
}
static int coroutine_fn cbw_co_flush(BlockDriverState *bs)
{
if (!bs->file) {
return 0;
}
return bdrv_co_flush(bs->file->bs);
}
static void cbw_refresh_filename(BlockDriverState *bs)
{
pstrcpy(bs->exact_filename, sizeof(bs->exact_filename),
bs->file->bs->filename);
}
static void cbw_child_perm(BlockDriverState *bs, BdrvChild *c,
BdrvChildRole role,
BlockReopenQueue *reopen_queue,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
{
if (!(role & BDRV_CHILD_FILTERED)) {
/*
* Target child
*
* Share write to target (child_file), to not interfere
* with guest writes to its disk which may be in target backing chain.
* Can't resize during a backup block job because we check the size
* only upfront.
*/
*nshared = BLK_PERM_ALL & ~BLK_PERM_RESIZE;
*nperm = BLK_PERM_WRITE;
} else {
/* Source child */
bdrv_default_perms(bs, c, role, reopen_queue,
perm, shared, nperm, nshared);
if (!QLIST_EMPTY(&bs->parents)) {
if (perm & BLK_PERM_WRITE) {
*nperm = *nperm | BLK_PERM_CONSISTENT_READ;
}
*nshared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
}
}
}
static int cbw_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVCopyBeforeWriteState *s = bs->opaque;
BdrvDirtyBitmap *copy_bitmap;
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;
}
s->target = bdrv_open_child(NULL, options, "target", bs, &child_of_bds,
BDRV_CHILD_DATA, false, errp);
if (!s->target) {
return -EINVAL;
}
bs->total_sectors = bs->file->bs->total_sectors;
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);
s->bcs = block_copy_state_new(bs->file, s->target, errp);
if (!s->bcs) {
error_prepend(errp, "Cannot create block-copy-state: ");
return -EINVAL;
}
copy_bitmap = block_copy_dirty_bitmap(s->bcs);
bdrv_set_dirty_bitmap(copy_bitmap, 0, bdrv_dirty_bitmap_size(copy_bitmap));
return 0;
}
static void cbw_close(BlockDriverState *bs)
{
BDRVCopyBeforeWriteState *s = bs->opaque;
block_copy_state_free(s->bcs);
s->bcs = NULL;
}
BlockDriver bdrv_cbw_filter = {
.format_name = "copy-before-write",
.instance_size = sizeof(BDRVCopyBeforeWriteState),
.bdrv_open = cbw_open,
.bdrv_close = cbw_close,
.bdrv_co_preadv = cbw_co_preadv,
.bdrv_co_pwritev = cbw_co_pwritev,
.bdrv_co_pwrite_zeroes = cbw_co_pwrite_zeroes,
.bdrv_co_pdiscard = cbw_co_pdiscard,
.bdrv_co_flush = cbw_co_flush,
.bdrv_refresh_filename = cbw_refresh_filename,
.bdrv_child_perm = cbw_child_perm,
.is_filter = true,
};
BlockDriverState *bdrv_cbw_append(BlockDriverState *source,
BlockDriverState *target,
const char *filter_node_name,
BlockCopyState **bcs,
Error **errp)
{
ERRP_GUARD();
BDRVCopyBeforeWriteState *state;
BlockDriverState *top;
QDict *opts;
assert(source->total_sectors == target->total_sectors);
opts = qdict_new();
qdict_put_str(opts, "driver", "copy-before-write");
if (filter_node_name) {
qdict_put_str(opts, "node-name", filter_node_name);
}
qdict_put_str(opts, "file", bdrv_get_node_name(source));
qdict_put_str(opts, "target", bdrv_get_node_name(target));
top = bdrv_insert_node(source, opts, BDRV_O_RDWR, errp);
if (!top) {
return NULL;
}
state = top->opaque;
*bcs = state->bcs;
return top;
}
void bdrv_cbw_drop(BlockDriverState *bs)
{
bdrv_drop_filter(bs, &error_abort);
bdrv_unref(bs);
}
static void cbw_init(void)
{
bdrv_register(&bdrv_cbw_filter);
}
block_init(cbw_init);