mirror_zfs/lib/libspl/include/sys/uio.h

139 lines
3.7 KiB
C
Raw Normal View History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License, Version 1.0 only
* (the "License"). You may not use this file except in compliance
* with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or https://opensource.org/licenses/CDDL-1.0.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2005 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
/* Copyright (c) 1984, 1986, 1987, 1988, 1989 AT&T */
/* All Rights Reserved */
/*
* University Copyright- Copyright (c) 1982, 1986, 1988
* The Regents of the University of California
* All Rights Reserved
*
* University Acknowledgment- Portions of this document are derived from
* software developed by the University of California, Berkeley, and its
* contributors.
*/
#ifndef _LIBSPL_SYS_UIO_H
#define _LIBSPL_SYS_UIO_H
#include <sys/types.h>
#include_next <sys/uio.h>
#ifdef __APPLE__
#include <sys/_types/_iovec_t.h>
#endif
#include <stdint.h>
typedef struct iovec iovec_t;
#if defined(__linux__) || defined(__APPLE__)
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,
} zfs_uio_seg_t;
#elif defined(__FreeBSD__)
typedef enum uio_seg zfs_uio_seg_t;
#endif
typedef struct zfs_uio {
struct iovec *uio_iov; /* pointer to array of iovecs */
int uio_iovcnt; /* number of iovecs */
offset_t uio_loffset; /* file offset */
zfs_uio_seg_t uio_segflg; /* address space (kernel or user) */
uint16_t uio_fmode; /* file mode flags */
uint16_t uio_extflg; /* extended flags */
ssize_t uio_resid; /* residual count */
} zfs_uio_t;
#define zfs_uio_segflg(uio) (uio)->uio_segflg
#define zfs_uio_offset(uio) (uio)->uio_loffset
#define zfs_uio_resid(uio) (uio)->uio_resid
#define zfs_uio_iovcnt(uio) (uio)->uio_iovcnt
#define zfs_uio_iovlen(uio, idx) (uio)->uio_iov[(idx)].iov_len
#define zfs_uio_iovbase(uio, idx) (uio)->uio_iov[(idx)].iov_base
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 23:47:59 +03:00
static inline boolean_t
zfs_dio_page_aligned(void *buf)
{
return ((((unsigned long)(buf) & (PAGESIZE - 1)) == 0) ?
B_TRUE : B_FALSE);
}
static inline boolean_t
zfs_dio_offset_aligned(uint64_t offset, uint64_t blksz)
{
return ((IS_P2ALIGNED(offset, blksz)) ? B_TRUE : B_FALSE);
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 23:47:59 +03:00
}
static inline boolean_t
zfs_dio_size_aligned(uint64_t size, uint64_t blksz)
{
return (((size % blksz) == 0) ? B_TRUE : B_FALSE);
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 23:47:59 +03:00
}
static inline boolean_t
zfs_dio_aligned(uint64_t offset, uint64_t size, uint64_t blksz)
{
return ((zfs_dio_offset_aligned(offset, blksz) &&
zfs_dio_size_aligned(size, blksz)) ? B_TRUE : B_FALSE);
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 23:47:59 +03:00
}
static inline void
zfs_uio_iov_at_index(zfs_uio_t *uio, uint_t idx, void **base, uint64_t *len)
{
*base = zfs_uio_iovbase(uio, idx);
*len = zfs_uio_iovlen(uio, idx);
}
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 20:51:41 +03:00
zfs_uio_advance(zfs_uio_t *uio, ssize_t size)
{
uio->uio_resid -= size;
uio->uio_loffset += size;
}
static inline offset_t
zfs_uio_index_at_offset(zfs_uio_t *uio, offset_t off, uint_t *vec_idx)
{
*vec_idx = 0;
while (*vec_idx < (uint_t)zfs_uio_iovcnt(uio) &&
off >= (offset_t)zfs_uio_iovlen(uio, *vec_idx)) {
off -= zfs_uio_iovlen(uio, *vec_idx);
(*vec_idx)++;
}
return (off);
}
#endif /* _SYS_UIO_H */