zfs/include/os/linux/spl/sys/uio.h

181 lines
4.6 KiB
C
Raw Normal View History

/*
* Copyright (C) 2007-2010 Lawrence Livermore National Security, LLC.
* Copyright (C) 2007 The Regents of the University of California.
* Copyright (c) 2015 by Chunwei Chen. All rights reserved.
* Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
* Written by Brian Behlendorf <behlendorf1@llnl.gov>.
* UCRL-CODE-235197
*
* This file is part of the SPL, Solaris Porting Layer.
*
* The SPL 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.
*
* The SPL 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 the SPL. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef _SPL_UIO_H
#define _SPL_UIO_H
#include <sys/debug.h>
#include <linux/uio.h>
#include <linux/blkdev.h>
#include <linux/blkdev_compat.h>
#include <linux/mm.h>
#include <linux/bio.h>
#include <asm/uaccess.h>
#include <sys/types.h>
#if defined(HAVE_VFS_IOV_ITER) && defined(HAVE_FAULT_IN_IOV_ITER_READABLE)
#define iov_iter_fault_in_readable(a, b) fault_in_iov_iter_readable(a, b)
#endif
typedef struct iovec iovec_t;
typedef enum zfs_uio_rw {
UIO_READ = 0,
UIO_WRITE = 1,
} zfs_uio_rw_t;
typedef enum zfs_uio_seg {
UIO_USERSPACE = 0,
UIO_SYSSPACE = 1,
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
UIO_BVEC = 2,
#if defined(HAVE_VFS_IOV_ITER)
UIO_ITER = 3,
#endif
} zfs_uio_seg_t;
typedef struct zfs_uio {
union {
const struct iovec *uio_iov;
const struct bio_vec *uio_bvec;
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
#if defined(HAVE_VFS_IOV_ITER)
struct iov_iter *uio_iter;
#endif
};
int uio_iovcnt;
offset_t uio_loffset;
zfs_uio_seg_t uio_segflg;
boolean_t uio_fault_disable;
uint16_t uio_fmode;
uint16_t uio_extflg;
ssize_t uio_resid;
2022-06-09 14:10:38 +00:00
size_t uio_skip;
2022-06-09 14:10:38 +00:00
struct request *rq;
} zfs_uio_t;
2022-06-09 14:10:38 +00:00
#define zfs_uio_segflg(u) (u)->uio_segflg
#define zfs_uio_offset(u) (u)->uio_loffset
#define zfs_uio_resid(u) (u)->uio_resid
#define zfs_uio_iovcnt(u) (u)->uio_iovcnt
#define zfs_uio_iovlen(u, idx) (u)->uio_iov[(idx)].iov_len
#define zfs_uio_iovbase(u, idx) (u)->uio_iov[(idx)].iov_base
#define zfs_uio_fault_disable(u, set) (u)->uio_fault_disable = set
#define zfs_uio_rlimit_fsize(z, u) (0)
#define zfs_uio_fault_move(p, n, rw, u) zfs_uiomove((p), (n), (rw), (u))
extern int zfs_uio_prefaultpages(ssize_t, zfs_uio_t *);
static inline void
zfs_uio_setoffset(zfs_uio_t *uio, offset_t off)
{
uio->uio_loffset = off;
}
static inline void
dmu: Allow buffer fills to fail 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
2023-12-15 17:51:41 +00:00
zfs_uio_advance(zfs_uio_t *uio, ssize_t size)
{
uio->uio_resid -= size;
uio->uio_loffset += size;
}
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
static inline void
zfs_uio_iovec_init(zfs_uio_t *uio, const struct iovec *iov,
unsigned long nr_segs, offset_t offset, zfs_uio_seg_t seg, ssize_t resid,
size_t skip)
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
{
ASSERT(seg == UIO_USERSPACE || seg == UIO_SYSSPACE);
uio->uio_iov = iov;
uio->uio_iovcnt = nr_segs;
uio->uio_loffset = offset;
uio->uio_segflg = seg;
uio->uio_fault_disable = B_FALSE;
uio->uio_fmode = 0;
uio->uio_extflg = 0;
uio->uio_resid = resid;
uio->uio_skip = skip;
}
static inline void
2022-06-09 14:10:38 +00:00
zfs_uio_bvec_init(zfs_uio_t *uio, struct bio *bio, struct request *rq)
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
{
2022-06-09 14:10:38 +00:00
/* Either bio or rq will be set, but not both */
ASSERT3P(uio, !=, bio);
if (bio) {
uio->uio_iovcnt = bio->bi_vcnt - BIO_BI_IDX(bio);
uio->uio_bvec = &bio->bi_io_vec[BIO_BI_IDX(bio)];
} else {
uio->uio_bvec = NULL;
uio->uio_iovcnt = 0;
}
uio->uio_loffset = io_offset(bio, rq);
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
uio->uio_segflg = UIO_BVEC;
uio->uio_fault_disable = B_FALSE;
uio->uio_fmode = 0;
uio->uio_extflg = 0;
2022-06-09 14:10:38 +00:00
uio->uio_resid = io_size(bio, rq);
if (bio) {
uio->uio_skip = BIO_BI_SKIP(bio);
} else {
uio->uio_skip = 0;
}
uio->rq = rq;
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
}
#if defined(HAVE_VFS_IOV_ITER)
static inline void
zfs_uio_iov_iter_init(zfs_uio_t *uio, struct iov_iter *iter, offset_t offset,
Linux 5.10 compat: use iov_iter in uio structure As of the 5.10 kernel the generic splice compatibility code has been removed. All filesystems are now responsible for registering a ->splice_read and ->splice_write callback to support this operation. The good news is the VFS provided generic_file_splice_read() and iter_file_splice_write() callbacks can be used provided the ->iter_read and ->iter_write callback support pipes. However, this is currently not the case and only iovecs and bvecs (not pipes) are ever attached to the uio structure. This commit changes that by allowing full iov_iter structures to be attached to uios. Ever since the 4.9 kernel the iov_iter structure has supported iovecs, kvecs, bvevs, and pipes so it's desirable to pass the entire thing when possible. In conjunction with this the uio helper functions (i.e uiomove(), uiocopy(), etc) have been updated to understand the new UIO_ITER type. Note that using the kernel provided uio_iter interfaces allowed the existing Linux specific uio handling code to be simplified. When there's no longer a need to support kernel's older than 4.9, then it will be possible to remove the iovec and bvec members from the uio structure and always use a uio_iter. Until then we need to maintain all of the existing types for older kernels. Some additional refactoring and cleanup was included in this change: - Added checks to configure to detect available iov_iter interfaces. Some are available all the way back to the 3.10 kernel and are used when available. In particular, uio_prefaultpages() now always uses iov_iter_fault_in_readable() which is available for all supported kernels. - The unused UIO_USERISPACE type has been removed. It is no longer needed now that the uio_seg enum is platform specific. - Moved zfs_uio.c from the zcommon.ko module to the Linux specific platform code for the zfs.ko module. This gets it out of libzfs where it was never needed and keeps this Linux specific code out of the common sources. - Removed unnecessary O_APPEND handling from zfs_iter_write(), this is redundant and O_APPEND is already handled in zfs_write(); Reviewed-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #11351
2020-12-18 16:48:26 +00:00
ssize_t resid, size_t skip)
{
uio->uio_iter = iter;
uio->uio_iovcnt = iter->nr_segs;
uio->uio_loffset = offset;
uio->uio_segflg = UIO_ITER;
uio->uio_fault_disable = B_FALSE;
uio->uio_fmode = 0;
uio->uio_extflg = 0;
uio->uio_resid = resid;
uio->uio_skip = skip;
}
#endif
#if defined(HAVE_ITER_IOV)
#define zfs_uio_iter_iov(iter) iter_iov((iter))
#else
#define zfs_uio_iter_iov(iter) (iter)->iov
#endif
#if defined(HAVE_IOV_ITER_TYPE)
#define zfs_uio_iov_iter_type(iter) iov_iter_type((iter))
#else
#define zfs_uio_iov_iter_type(iter) (iter)->type
#endif
#endif /* SPL_UIO_H */