mirror_zfs/include/os/linux/spl/sys/uio.h
Brian Behlendorf 58bc86c5cb 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();

NOTE: Cleanly applying this kernel compatibility change required
applying the following commits.  This makes the change larger than
it absolutely needs to be, but the resulting code matches what's in
the branch branch.  This is both more tested and makes it easier to
apply any future backports in this area.

7cf4cd824 Remove incorrect assertion
783be694f Reduce confusion in zfs_write
af5626ac2 Return EFAULT at the end of zfs_write() when set
cc1f85be8 Simplify offset and length limit in zfs_write
9585538d0 Const some unchanging variables in zfs_write
86e74dc16 Remove redundant oid parameter to update_pages
b3d723fb0 Factor uid, gid, and projid out of loop in zfs_write
3d40b6554 Share zfs_fsync, zfs_read, zfs_write, et al between Linux and FreeBSD

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
2020-12-23 14:35:39 -08:00

210 lines
5.0 KiB
C

/*
* 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>
typedef struct iovec iovec_t;
typedef enum uio_rw {
UIO_READ = 0,
UIO_WRITE = 1,
} uio_rw_t;
typedef enum uio_seg {
UIO_USERSPACE = 0,
UIO_SYSSPACE = 1,
UIO_BVEC = 2,
#if defined(HAVE_VFS_IOV_ITER)
UIO_ITER = 3,
#endif
} uio_seg_t;
typedef struct uio {
union {
const struct iovec *uio_iov;
const struct bio_vec *uio_bvec;
#if defined(HAVE_VFS_IOV_ITER)
struct iov_iter *uio_iter;
#endif
};
int uio_iovcnt;
offset_t uio_loffset;
uio_seg_t uio_segflg;
boolean_t uio_fault_disable;
uint16_t uio_fmode;
uint16_t uio_extflg;
ssize_t uio_resid;
size_t uio_skip;
} uio_t;
typedef struct aio_req {
uio_t *aio_uio;
void *aio_private;
} aio_req_t;
typedef enum xuio_type {
UIOTYPE_ASYNCIO,
UIOTYPE_ZEROCOPY,
} xuio_type_t;
#define UIOA_IOV_MAX 16
typedef struct uioa_page_s {
int uioa_pfncnt;
void **uioa_ppp;
caddr_t uioa_base;
size_t uioa_len;
} uioa_page_t;
typedef struct xuio {
uio_t xu_uio;
enum xuio_type xu_type;
union {
struct {
uint32_t xu_a_state;
ssize_t xu_a_mbytes;
uioa_page_t *xu_a_lcur;
void **xu_a_lppp;
void *xu_a_hwst[4];
uioa_page_t xu_a_locked[UIOA_IOV_MAX];
} xu_aio;
struct {
int xu_zc_rw;
void *xu_zc_priv;
} xu_zc;
} xu_ext;
} xuio_t;
#define XUIO_XUZC_PRIV(xuio) xuio->xu_ext.xu_zc.xu_zc_priv
#define XUIO_XUZC_RW(xuio) xuio->xu_ext.xu_zc.xu_zc_rw
#define uio_segflg(uio) (uio)->uio_segflg
#define uio_offset(uio) (uio)->uio_loffset
#define uio_resid(uio) (uio)->uio_resid
#define uio_iovcnt(uio) (uio)->uio_iovcnt
#define uio_iovlen(uio, idx) (uio)->uio_iov[(idx)].iov_len
#define uio_iovbase(uio, idx) (uio)->uio_iov[(idx)].iov_base
#define uio_fault_disable(uio, set) (uio)->uio_fault_disable = set
static inline void
uio_iov_at_index(uio_t *uio, uint_t idx, void **base, uint64_t *len)
{
*base = uio_iovbase(uio, idx);
*len = uio_iovlen(uio, idx);
}
static inline void
uio_advance(uio_t *uio, size_t size)
{
uio->uio_resid -= size;
uio->uio_loffset += size;
}
static inline offset_t
uio_index_at_offset(uio_t *uio, offset_t off, uint_t *vec_idx)
{
*vec_idx = 0;
while (*vec_idx < uio_iovcnt(uio) && off >= uio_iovlen(uio, *vec_idx)) {
off -= uio_iovlen(uio, *vec_idx);
(*vec_idx)++;
}
return (off);
}
static inline void
iov_iter_init_compat(struct iov_iter *iter, unsigned int dir,
const struct iovec *iov, unsigned long nr_segs, size_t count)
{
#if defined(HAVE_IOV_ITER_INIT)
iov_iter_init(iter, dir, iov, nr_segs, count);
#elif defined(HAVE_IOV_ITER_INIT_LEGACY)
iov_iter_init(iter, iov, nr_segs, count, 0);
#else
#error "Unsupported kernel"
#endif
}
static inline void
uio_iovec_init(uio_t *uio, const struct iovec *iov, unsigned long nr_segs,
offset_t offset, uio_seg_t seg, ssize_t resid, size_t skip)
{
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
uio_bvec_init(uio_t *uio, struct bio *bio)
{
uio->uio_bvec = &bio->bi_io_vec[BIO_BI_IDX(bio)];
uio->uio_iovcnt = bio->bi_vcnt - BIO_BI_IDX(bio);
uio->uio_loffset = BIO_BI_SECTOR(bio) << 9;
uio->uio_segflg = UIO_BVEC;
uio->uio_fault_disable = B_FALSE;
uio->uio_fmode = 0;
uio->uio_extflg = 0;
uio->uio_resid = BIO_BI_SIZE(bio);
uio->uio_skip = BIO_BI_SKIP(bio);
}
#if defined(HAVE_VFS_IOV_ITER)
static inline void
uio_iov_iter_init(uio_t *uio, struct iov_iter *iter, offset_t offset,
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
#endif /* SPL_UIO_H */