mirror_zfs/include/os/linux/spl/sys/uio.h
Brian Atkinson a10e552b99
Adding Direct IO Support
Adding O_DIRECT support to ZFS to bypass the ARC for writes/reads.

O_DIRECT support in ZFS will always ensure there is coherency between
buffered and O_DIRECT IO requests. This ensures that all IO requests,
whether buffered or direct, will see the same file contents at all
times. Just as in other FS's , O_DIRECT does not imply O_SYNC. While
data is written directly to VDEV disks, metadata will not be synced
until the associated  TXG is synced.
For both O_DIRECT read and write request the offset and request sizes,
at a minimum, must be PAGE_SIZE aligned. In the event they are not,
then EINVAL is returned unless the direct property is set to always (see
below).

For O_DIRECT writes:
The request also must be block aligned (recordsize) or the write
request will take the normal (buffered) write path. In the event that
request is block aligned and a cached copy of the buffer in the ARC,
then it will be discarded from the ARC forcing all further reads to
retrieve the data from disk.

For O_DIRECT reads:
The only alignment restrictions are PAGE_SIZE alignment. In the event
that the requested data is in buffered (in the ARC) it will just be
copied from the ARC into the user buffer.

For both O_DIRECT writes and reads the O_DIRECT flag will be ignored in
the event that file contents are mmap'ed. In this case, all requests
that are at least PAGE_SIZE aligned will just fall back to the buffered
paths. If the request however is not PAGE_SIZE aligned, EINVAL will
be returned as always regardless if the file's contents are mmap'ed.

Since O_DIRECT writes go through the normal ZIO pipeline, the
following operations are supported just as with normal buffered writes:
Checksum
Compression
Encryption
Erasure Coding
There is one caveat for the data integrity of O_DIRECT writes that is
distinct for each of the OS's supported by ZFS.
FreeBSD - FreeBSD is able to place user pages under write protection so
          any data in the user buffers and written directly down to the
	  VDEV disks is guaranteed to not change. There is no concern
	  with data integrity and O_DIRECT writes.
Linux - Linux is not able to place anonymous user pages under write
        protection. Because of this, if the user decides to manipulate
	the page contents while the write operation is occurring, data
	integrity can not be guaranteed. However, there is a module
	parameter `zfs_vdev_direct_write_verify` that controls the
	if a O_DIRECT writes that can occur to a top-level VDEV before
	a checksum verify is run before the contents of the I/O buffer
        are committed to disk. In the event of a checksum verification
	failure the write will return EIO. The number of O_DIRECT write
	checksum verification errors can be observed by doing
	`zpool status -d`, which will list all verification errors that
	have occurred on a top-level VDEV. Along with `zpool status`, a
	ZED event will be issues as `dio_verify` when a checksum
	verification error occurs.

ZVOLs and dedup is not currently supported with Direct I/O.

A new dataset property `direct` has been added with the following 3
allowable values:
disabled - Accepts O_DIRECT flag, but silently ignores it and treats
	   the request as a buffered IO request.
standard - Follows the alignment restrictions  outlined above for
	   write/read IO requests when the O_DIRECT flag is used.
always   - Treats every write/read IO request as though it passed
           O_DIRECT and will do O_DIRECT if the alignment restrictions
	   are met otherwise will redirect through the ARC. This
	   property will not allow a request to fail.

There is also a module parameter zfs_dio_enabled that can be used to
force all reads and writes through the ARC. By setting this module
parameter to 0, it mimics as if the  direct dataset property is set to
disabled.

Reviewed-by: Brian Behlendorf <behlendorf@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Atkinson <batkinson@lanl.gov>
Co-authored-by: Mark Maybee <mark.maybee@delphix.com>
Co-authored-by: Matt Macy <mmacy@FreeBSD.org>
Co-authored-by: Brian Behlendorf <behlendorf@llnl.gov>
Closes #10018
2024-09-14 13:47:59 -07:00

210 lines
5.6 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>
#include <sys/string.h>
/*
* uio_extflg: extended flags
*/
#define UIO_DIRECT 0x0001 /* Direct I/O request */
#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,
UIO_BVEC = 2,
#if defined(HAVE_VFS_IOV_ITER)
UIO_ITER = 3,
#endif
} zfs_uio_seg_t;
/*
* This structures is used when doing Direct I/O.
*/
typedef struct {
struct page **pages; /* Mapped pages */
long npages; /* Number of mapped pages */
} zfs_uio_dio_t;
typedef struct zfs_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; /* Number of iovecs */
offset_t uio_soffset; /* Starting logical offset */
offset_t uio_loffset; /* Current logical offset */
zfs_uio_seg_t uio_segflg; /* Segment type */
boolean_t uio_fault_disable;
uint16_t uio_fmode; /* Access mode (unused) */
uint16_t uio_extflg; /* Extra flags (UIO_DIRECT) */
ssize_t uio_resid; /* Residual unprocessed bytes */
size_t uio_skip; /* Skipped bytes in current iovec */
zfs_uio_dio_t uio_dio; /* Direct I/O user pages */
struct request *rq;
} zfs_uio_t;
#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_soffset(u) (u)->uio_soffset
#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
zfs_uio_setsoffset(zfs_uio_t *uio, offset_t off)
{
ASSERT3U(zfs_uio_offset(uio), ==, off);
zfs_uio_soffset(uio) = off;
}
static inline void
zfs_uio_advance(zfs_uio_t *uio, ssize_t size)
{
uio->uio_resid -= size;
uio->uio_loffset += size;
}
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)
{
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;
uio->uio_soffset = uio->uio_loffset;
memset(&uio->uio_dio, 0, sizeof (zfs_uio_dio_t));
}
static inline void
zfs_uio_bvec_init(zfs_uio_t *uio, struct bio *bio, struct request *rq)
{
/* 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);
uio->uio_segflg = UIO_BVEC;
uio->uio_fault_disable = B_FALSE;
uio->uio_fmode = 0;
uio->uio_extflg = 0;
uio->uio_resid = io_size(bio, rq);
if (bio) {
uio->uio_skip = BIO_BI_SKIP(bio);
} else {
uio->uio_skip = 0;
}
uio->rq = rq;
uio->uio_soffset = uio->uio_loffset;
memset(&uio->uio_dio, 0, sizeof (zfs_uio_dio_t));
}
#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,
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;
uio->uio_soffset = uio->uio_loffset;
memset(&uio->uio_dio, 0, sizeof (zfs_uio_dio_t));
}
#endif /* HAVE_VFS_IOV_ITER */
#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 */