mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-30 21:09:38 +03:00
9b1677fb5a
When ZFS overwrites a whole block, it does not bother to read the old content from disk. It is a good optimization, but if the buffer fill fails due to page fault or something else, the buffer ends up corrupted, neither keeping old content, nor getting the new one. On FreeBSD this is additionally complicated by page faults being blocked by VFS layer, always returning EFAULT on attempt to write from mmap()'ed but not yet cached address range. Normally it is not a big problem, since after original failure VFS will retry the write after reading the required data. The problem becomes worse in specific case when somebody tries to write into a file its own mmap()'ed content from the same location. In that situation the only copy of the data is getting corrupted on the page fault and the following retries only fixate the status quo. Block cloning makes this issue easier to reproduce, since it does not read the old data, unlike traditional file copy, that may work by chance. This patch provides the fill status to dmu_buf_fill_done(), that in case of error can destroy the corrupted buffer as if no write happened. One more complication in case of block cloning is that if error is possible during fill, dmu_buf_will_fill() must read the data via fall-back to dmu_buf_will_dirty(). It is required to allow in case of error restoring the buffer to a state after the cloning, not not before it, that would happen if we just call dbuf_undirty(). Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Rob Norris <robn@despairlabs.com> Signed-off-by: Alexander Motin <mav@FreeBSD.org> Sponsored by: iXsystems, Inc. Closes #15665
82 lines
2.7 KiB
C
82 lines
2.7 KiB
C
/*
|
|
* Copyright (c) 2010 Pawel Jakub Dawidek <pjd@FreeBSD.org>
|
|
* All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHORS AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
#ifndef _OPENSOLARIS_SYS_UIO_H_
|
|
#define _OPENSOLARIS_SYS_UIO_H_
|
|
|
|
#ifndef _STANDALONE
|
|
|
|
#include_next <sys/uio.h>
|
|
#include <sys/_uio.h>
|
|
#include <sys/debug.h>
|
|
|
|
typedef struct iovec iovec_t;
|
|
typedef enum uio_seg zfs_uio_seg_t;
|
|
typedef enum uio_rw zfs_uio_rw_t;
|
|
|
|
typedef struct zfs_uio {
|
|
struct uio *uio;
|
|
} zfs_uio_t;
|
|
|
|
#define GET_UIO_STRUCT(u) (u)->uio
|
|
#define zfs_uio_segflg(u) GET_UIO_STRUCT(u)->uio_segflg
|
|
#define zfs_uio_offset(u) GET_UIO_STRUCT(u)->uio_offset
|
|
#define zfs_uio_resid(u) GET_UIO_STRUCT(u)->uio_resid
|
|
#define zfs_uio_iovcnt(u) GET_UIO_STRUCT(u)->uio_iovcnt
|
|
#define zfs_uio_iovlen(u, idx) GET_UIO_STRUCT(u)->uio_iov[(idx)].iov_len
|
|
#define zfs_uio_iovbase(u, idx) GET_UIO_STRUCT(u)->uio_iov[(idx)].iov_base
|
|
#define zfs_uio_td(u) GET_UIO_STRUCT(u)->uio_td
|
|
#define zfs_uio_rw(u) GET_UIO_STRUCT(u)->uio_rw
|
|
#define zfs_uio_fault_disable(u, set)
|
|
#define zfs_uio_prefaultpages(size, u) (0)
|
|
|
|
static inline void
|
|
zfs_uio_setoffset(zfs_uio_t *uio, offset_t off)
|
|
{
|
|
zfs_uio_offset(uio) = off;
|
|
}
|
|
|
|
static inline void
|
|
zfs_uio_advance(zfs_uio_t *uio, ssize_t size)
|
|
{
|
|
zfs_uio_resid(uio) -= size;
|
|
zfs_uio_offset(uio) += size;
|
|
}
|
|
|
|
static __inline void
|
|
zfs_uio_init(zfs_uio_t *uio, struct uio *uio_s)
|
|
{
|
|
GET_UIO_STRUCT(uio) = uio_s;
|
|
}
|
|
|
|
int zfs_uio_fault_move(void *p, size_t n, zfs_uio_rw_t dir, zfs_uio_t *uio);
|
|
|
|
#endif /* !_STANDALONE */
|
|
|
|
#endif /* !_OPENSOLARIS_SYS_UIO_H_ */
|