Skip to content
Snippets Groups Projects
  • Vladimir Sementsov-Ogievskiy's avatar
    0c802287
    block: use int64_t instead of int in driver discard handlers · 0c802287
    Vladimir Sementsov-Ogievskiy authored
    
    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: default avatarVladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
    Message-Id: <20210903102807.27127-11-vsementsov@virtuozzo.com>
    Reviewed-by: default avatarEric Blake <eblake@redhat.com>
    Signed-off-by: default avatarEric Blake <eblake@redhat.com>
    0c802287
    History
    block: use int64_t instead of int in driver discard handlers
    Vladimir Sementsov-Ogievskiy authored
    
    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: default avatarVladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
    Message-Id: <20210903102807.27127-11-vsementsov@virtuozzo.com>
    Reviewed-by: default avatarEric Blake <eblake@redhat.com>
    Signed-off-by: default avatarEric Blake <eblake@redhat.com>
filter-compress.c 4.95 KiB
/*
 * Compress filter block driver
 *
 * Copyright (c) 2019 Virtuozzo International GmbH
 *
 * Author:
 *   Andrey Shinkevich <andrey.shinkevich@virtuozzo.com>
 *   (based on block/copy-on-read.c by Max Reitz)
 *
 * 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) any later version 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"


static int compress_open(BlockDriverState *bs, QDict *options, int flags,
                         Error **errp)
{
    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;
    }

    if (!bs->file->bs->drv || !block_driver_can_compress(bs->file->bs->drv)) {
        error_setg(errp,
                   "Compression is not supported for underlying format: %s",
                   bdrv_get_format_name(bs->file->bs) ?: "(no format)");

        return -ENOTSUP;
    }

    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);

    return 0;
}


static int64_t compress_getlength(BlockDriverState *bs)
{
    return bdrv_getlength(bs->file->bs);
}


static int coroutine_fn compress_co_preadv_part(BlockDriverState *bs,
                                                int64_t offset, int64_t bytes,
                                                QEMUIOVector *qiov,
                                                size_t qiov_offset,
                                                BdrvRequestFlags flags)
{
    return bdrv_co_preadv_part(bs->file, offset, bytes, qiov, qiov_offset,
                               flags);
}


static int coroutine_fn compress_co_pwritev_part(BlockDriverState *bs,
                                                 int64_t offset,
                                                 int64_t bytes,
                                                 QEMUIOVector *qiov,
                                                 size_t qiov_offset,
                                                 BdrvRequestFlags flags)
{
    return bdrv_co_pwritev_part(bs->file, offset, bytes, qiov, qiov_offset,
                                flags | BDRV_REQ_WRITE_COMPRESSED);
}


static int coroutine_fn compress_co_pwrite_zeroes(BlockDriverState *bs,
                                                  int64_t offset, int64_t bytes,
                                                  BdrvRequestFlags flags)
{
    return bdrv_co_pwrite_zeroes(bs->file, offset, bytes, flags);
}


static int coroutine_fn compress_co_pdiscard(BlockDriverState *bs,
                                             int64_t offset, int64_t bytes)
{
    return bdrv_co_pdiscard(bs->file, offset, bytes);
}


static void compress_refresh_limits(BlockDriverState *bs, Error **errp)
{
    BlockDriverInfo bdi;
    int ret;

    if (!bs->file) {
        return;
    }

    ret = bdrv_get_info(bs->file->bs, &bdi);
    if (ret < 0 || bdi.cluster_size == 0) {
        return;
    }

    bs->bl.request_alignment = bdi.cluster_size;
}


static void compress_eject(BlockDriverState *bs, bool eject_flag)
{
    bdrv_eject(bs->file->bs, eject_flag);
}


static void compress_lock_medium(BlockDriverState *bs, bool locked)
{
    bdrv_lock_medium(bs->file->bs, locked);
}


static BlockDriver bdrv_compress = {
    .format_name                        = "compress",

    .bdrv_open                          = compress_open,
    .bdrv_child_perm                    = bdrv_default_perms,

    .bdrv_getlength                     = compress_getlength,
    .bdrv_co_preadv_part                = compress_co_preadv_part,
    .bdrv_co_pwritev_part               = compress_co_pwritev_part,
    .bdrv_co_pwrite_zeroes              = compress_co_pwrite_zeroes,
    .bdrv_co_pdiscard                   = compress_co_pdiscard,
    .bdrv_refresh_limits                = compress_refresh_limits,

    .bdrv_eject                         = compress_eject,
    .bdrv_lock_medium                   = compress_lock_medium,

    .has_variable_length                = true,
    .is_filter                          = true,
};

static void bdrv_compress_init(void)
{
    bdrv_register(&bdrv_compress);
}

block_init(bdrv_compress_init);