linux-stable/include/linux/uio.h
Linus Torvalds 3acbdbf42e dax + libnvdimm for v5.17
- Simplify the dax_operations API
   - Eliminate bdev_dax_pgoff() in favor of the filesystem maintaining
     and applying a partition offset to all its DAX iomap operations.
   - Remove wrappers and device-mapper stacked callbacks for
     ->copy_from_iter() and ->copy_to_iter() in favor of moving
     block_device relative offset responsibility to the
     dax_direct_access() caller.
   - Remove the need for an @bdev in filesystem-DAX infrastructure
   - Remove unused uio helpers copy_from_iter_flushcache() and
     copy_mc_to_iter() as only the non-check_copy_size() versions are
     used for DAX.
 - Prepare XFS for the pending (next merge window) DAX+reflink support
 - Remove deprecated DEV_DAX_PMEM_COMPAT support
 - Cleanup a straggling misuse of the GUID api
 
 Tags offered after the branch was cut:
 Reviewed-by: Mike Snitzer <snitzer@redhat.com>
 Link: https://lore.kernel.org/r/Ydb/3P+8nvjCjYfO@redhat.com
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSbo+XnGs+rwLz9XGXfioYZHlFsZwUCYd3dTAAKCRDfioYZHlFs
 Z//UAP9zetoTE+O7zJG7CXja4jSopSadbdbh6QKSXaqfKBPvQQD+N4US3wA2bGv8
 f/qCY62j2Hj3hUTGHs9RvTyw3JsSYAA=
 =QvDs
 -----END PGP SIGNATURE-----

Merge tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull dax and libnvdimm updates from Dan Williams:
 "The bulk of this is a rework of the dax_operations API after
  discovering the obstacles it posed to the work-in-progress DAX+reflink
  support for XFS and other copy-on-write filesystem mechanics.

  Primarily the need to plumb a block_device through the API to handle
  partition offsets was a sticking point and Christoph untangled that
  dependency in addition to other cleanups to make landing the
  DAX+reflink support easier.

  The DAX_PMEM_COMPAT option has been around for 4 years and not only
  are distributions shipping userspace that understand the current
  configuration API, but some are not even bothering to turn this option
  on anymore, so it seems a good time to remove it per the deprecation
  schedule. Recall that this was added after the device-dax subsystem
  moved from /sys/class/dax to /sys/bus/dax for its sysfs organization.
  All recent functionality depends on /sys/bus/dax.

  Some other miscellaneous cleanups and reflink prep patches are
  included as well.

  Summary:

   - Simplify the dax_operations API:

      - Eliminate bdev_dax_pgoff() in favor of the filesystem
        maintaining and applying a partition offset to all its DAX iomap
        operations.

      - Remove wrappers and device-mapper stacked callbacks for
        ->copy_from_iter() and ->copy_to_iter() in favor of moving
        block_device relative offset responsibility to the
        dax_direct_access() caller.

      - Remove the need for an @bdev in filesystem-DAX infrastructure

      - Remove unused uio helpers copy_from_iter_flushcache() and
        copy_mc_to_iter() as only the non-check_copy_size() versions are
        used for DAX.

   - Prepare XFS for the pending (next merge window) DAX+reflink support

   - Remove deprecated DEV_DAX_PMEM_COMPAT support

   - Cleanup a straggling misuse of the GUID api"

* tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (38 commits)
  iomap: Fix error handling in iomap_zero_iter()
  ACPI: NFIT: Import GUID before use
  dax: remove the copy_from_iter and copy_to_iter methods
  dax: remove the DAXDEV_F_SYNC flag
  dax: simplify dax_synchronous and set_dax_synchronous
  uio: remove copy_from_iter_flushcache() and copy_mc_to_iter()
  iomap: turn the byte variable in iomap_zero_iter into a ssize_t
  memremap: remove support for external pgmap refcounts
  fsdax: don't require CONFIG_BLOCK
  iomap: build the block based code conditionally
  dax: fix up some of the block device related ifdefs
  fsdax: shift partition offset handling into the file systems
  dax: return the partition offset from fs_dax_get_by_bdev
  iomap: add a IOMAP_DAX flag
  xfs: pass the mapping flags to xfs_bmbt_to_iomap
  xfs: use xfs_direct_write_iomap_ops for DAX zeroing
  xfs: move dax device handling into xfs_{alloc,free}_buftarg
  ext4: cleanup the dax handling in ext4_fill_super
  ext2: cleanup the dax handling in ext2_fill_super
  fsdax: decouple zeroing from the iomap buffered I/O code
  ...
2022-01-12 15:46:11 -08:00

309 lines
8.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Berkeley style UIO structures - Alan Cox 1994.
*/
#ifndef __LINUX_UIO_H
#define __LINUX_UIO_H
#include <linux/kernel.h>
#include <linux/thread_info.h>
#include <linux/mm_types.h>
#include <uapi/linux/uio.h>
struct page;
struct pipe_inode_info;
struct kvec {
void *iov_base; /* and that should *never* hold a userland pointer */
size_t iov_len;
};
enum iter_type {
/* iter types */
ITER_IOVEC,
ITER_KVEC,
ITER_BVEC,
ITER_PIPE,
ITER_XARRAY,
ITER_DISCARD,
};
struct iov_iter_state {
size_t iov_offset;
size_t count;
unsigned long nr_segs;
};
struct iov_iter {
u8 iter_type;
bool nofault;
bool data_source;
size_t iov_offset;
size_t count;
union {
const struct iovec *iov;
const struct kvec *kvec;
const struct bio_vec *bvec;
struct xarray *xarray;
struct pipe_inode_info *pipe;
};
union {
unsigned long nr_segs;
struct {
unsigned int head;
unsigned int start_head;
};
loff_t xarray_start;
};
};
static inline enum iter_type iov_iter_type(const struct iov_iter *i)
{
return i->iter_type;
}
static inline void iov_iter_save_state(struct iov_iter *iter,
struct iov_iter_state *state)
{
state->iov_offset = iter->iov_offset;
state->count = iter->count;
state->nr_segs = iter->nr_segs;
}
static inline bool iter_is_iovec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_IOVEC;
}
static inline bool iov_iter_is_kvec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_KVEC;
}
static inline bool iov_iter_is_bvec(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_BVEC;
}
static inline bool iov_iter_is_pipe(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_PIPE;
}
static inline bool iov_iter_is_discard(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_DISCARD;
}
static inline bool iov_iter_is_xarray(const struct iov_iter *i)
{
return iov_iter_type(i) == ITER_XARRAY;
}
static inline unsigned char iov_iter_rw(const struct iov_iter *i)
{
return i->data_source ? WRITE : READ;
}
/*
* Total number of bytes covered by an iovec.
*
* NOTE that it is not safe to use this function until all the iovec's
* segment lengths have been validated. Because the individual lengths can
* overflow a size_t when added together.
*/
static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
{
unsigned long seg;
size_t ret = 0;
for (seg = 0; seg < nr_segs; seg++)
ret += iov[seg].iov_len;
return ret;
}
static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
{
return (struct iovec) {
.iov_base = iter->iov->iov_base + iter->iov_offset,
.iov_len = min(iter->count,
iter->iov->iov_len - iter->iov_offset),
};
}
size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
size_t bytes, struct iov_iter *i);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
void iov_iter_revert(struct iov_iter *i, size_t bytes);
size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset,
size_t bytes, struct iov_iter *i)
{
return copy_page_to_iter(&folio->page, offset, bytes, i);
}
static __always_inline __must_check
size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, true)))
return 0;
else
return _copy_to_iter(addr, bytes, i);
}
static __always_inline __must_check
size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
else
return _copy_from_iter(addr, bytes, i);
}
static __always_inline __must_check
bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i)
{
size_t copied = copy_from_iter(addr, bytes, i);
if (likely(copied == bytes))
return true;
iov_iter_revert(i, copied);
return false;
}
static __always_inline __must_check
size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
else
return _copy_from_iter_nocache(addr, bytes, i);
}
static __always_inline __must_check
bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
{
size_t copied = copy_from_iter_nocache(addr, bytes, i);
if (likely(copied == bytes))
return true;
iov_iter_revert(i, copied);
return false;
}
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/*
* Note, users like pmem that depend on the stricter semantics of
* _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for
* IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the
* destination is flushed from the cache on return.
*/
size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i);
#else
#define _copy_from_iter_flushcache _copy_from_iter_nocache
#endif
#ifdef CONFIG_ARCH_HAS_COPY_MC
size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
#else
#define _copy_mc_to_iter _copy_to_iter
#endif
size_t iov_iter_zero(size_t bytes, struct iov_iter *);
unsigned long iov_iter_alignment(const struct iov_iter *i);
unsigned long iov_iter_gap_alignment(const struct iov_iter *i);
void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov,
unsigned long nr_segs, size_t count);
void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec,
unsigned long nr_segs, size_t count);
void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec,
unsigned long nr_segs, size_t count);
void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe,
size_t count);
void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
loff_t start, size_t count);
ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
size_t maxsize, unsigned maxpages, size_t *start);
ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages,
size_t maxsize, size_t *start);
int iov_iter_npages(const struct iov_iter *i, int maxpages);
void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state);
const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags);
static inline size_t iov_iter_count(const struct iov_iter *i)
{
return i->count;
}
/*
* Cap the iov_iter by given limit; note that the second argument is
* *not* the new size - it's upper limit for such. Passing it a value
* greater than the amount of data in iov_iter is fine - it'll just do
* nothing in that case.
*/
static inline void iov_iter_truncate(struct iov_iter *i, u64 count)
{
/*
* count doesn't have to fit in size_t - comparison extends both
* operands to u64 here and any value that would be truncated by
* conversion in assignement is by definition greater than all
* values of size_t, including old i->count.
*/
if (i->count > count)
i->count = count;
}
/*
* reexpand a previously truncated iterator; count must be no more than how much
* we had shrunk it.
*/
static inline void iov_iter_reexpand(struct iov_iter *i, size_t count)
{
i->count = count;
}
struct csum_state {
__wsum csum;
size_t off;
};
size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csstate, struct iov_iter *i);
size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
static __always_inline __must_check
bool csum_and_copy_from_iter_full(void *addr, size_t bytes,
__wsum *csum, struct iov_iter *i)
{
size_t copied = csum_and_copy_from_iter(addr, bytes, csum, i);
if (likely(copied == bytes))
return true;
iov_iter_revert(i, copied);
return false;
}
size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
struct iov_iter *i);
struct iovec *iovec_from_user(const struct iovec __user *uvector,
unsigned long nr_segs, unsigned long fast_segs,
struct iovec *fast_iov, bool compat);
ssize_t import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
struct iov_iter *i);
ssize_t __import_iovec(int type, const struct iovec __user *uvec,
unsigned nr_segs, unsigned fast_segs, struct iovec **iovp,
struct iov_iter *i, bool compat);
int import_single_range(int type, void __user *buf, size_t len,
struct iovec *iov, struct iov_iter *i);
#endif