alistair23-linux/include/linux/uio.h
Linus Torvalds a2d79c7174 for-5.3/io_uring-20190711
-----BEGIN PGP SIGNATURE-----
 
 iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl0nUl4QHGF4Ym9lQGtl
 cm5lbC5kawAKCRD301j7KXHgplCaEACa7c7ybRgV6CZpS9PXXVqBJqYILRLBXsnn
 MXomrSdjKMs0Y928RAQHFNWh3HaHHtdvSmFvwOpfF5lyrYXVfc9MQ7brqarDp1t2
 f4jvkL63BVG2Zs/VL8QVAz+CwtCF39hduzUR/Y9j/4+rJNhSBMNJLY0nlB5weCTy
 MJetnLoQ9ETA2+xu49vAM/PFJgBynNUAyUer918y8QysJRj90/VnhieQmrVb4tpG
 Q4yZFKq4YPDs0tLEX4Nj6eJERcyW/4MC2oZ0aPXU4g2Dc3SVWaSNOo5WpkP+crGt
 0dbyLmhomteE6+Kaco1hAWIkG/RuvgiMzDizryi0enXP51edV3Vnwyg3MQSUhcnf
 Pn7vrDkajKBE9rFGlLy8V4gkKdS8XJQy2xA1MWm3aWgGl4v0j64EXIe0IhIK30vU
 25A9jLDcdgr74+Lw+vWLLd+oeGD0iFf6wiEp+3jzEdtfVNE/lD6yilTzbdz2V0UK
 8T1sRLMEkaG7CbxOVc1UAfcvObjuqQihEI0fQvl4yxV178h8mtWB87YmV2S2EhzP
 v6FSxiC1yZ7J+rwb/Mff7+1GoOgzrpS/zESk2WMTgcwVdiwFfv5eIC26ZNWObJ/x
 IY+4xRgTf2dEsjBeumOuBzxTfzrZb+pTO4GCa4O+t0UDQRIwl0y20pTXKtxU3y/U
 gKPXEjgXrQ==
 =jDiB
 -----END PGP SIGNATURE-----

Merge tag 'for-5.3/io_uring-20190711' of git://git.kernel.dk/linux-block

Pull io_uring updates from Jens Axboe:
 "This contains:

   - Support for recvmsg/sendmsg as first class opcodes.

     I don't envision going much further down this path, as there are
     plans in progress to support potentially any system call in an
     async fashion through io_uring. But I think it does make sense to
     have certain core ops available directly, especially those that can
     support a "try this non-blocking" flag/mode. (me)

   - Handle generic short reads automatically.

     This can happen fairly easily if parts of the buffered read is
     cached. Since the application needs to issue another request for
     the remainder, just do this internally and save kernel/user
     roundtrip while providing a nicer more robust API. (me)

   - Support for linked SQEs.

     This allows SQEs to depend on each other, enabling an application
     to eg queue a read-from-this-file,write-to-that-file pair. (me)

   - Fix race in stopping SQ thread (Jackie)"

* tag 'for-5.3/io_uring-20190711' of git://git.kernel.dk/linux-block:
  io_uring: fix io_sq_thread_stop running in front of io_sq_thread
  io_uring: add support for recvmsg()
  io_uring: add support for sendmsg()
  io_uring: add support for sqe links
  io_uring: punt short reads to async context
  uio: make import_iovec()/compat_import_iovec() return bytes on success
2019-07-13 10:36:53 -07:00

289 lines
8.5 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 <crypto/hash.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 = 4,
ITER_KVEC = 8,
ITER_BVEC = 16,
ITER_PIPE = 32,
ITER_DISCARD = 64,
};
struct iov_iter {
/*
* Bit 0 is the read/write bit, set if we're writing.
* Bit 1 is the BVEC_FLAG_NO_REF bit, set if type is a bvec and
* the caller isn't expecting to drop a page reference when done.
*/
unsigned int type;
size_t iov_offset;
size_t count;
union {
const struct iovec *iov;
const struct kvec *kvec;
const struct bio_vec *bvec;
struct pipe_inode_info *pipe;
};
union {
unsigned long nr_segs;
struct {
int idx;
int start_idx;
};
};
};
static inline enum iter_type iov_iter_type(const struct iov_iter *i)
{
return i->type & ~(READ | WRITE);
}
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 unsigned char iov_iter_rw(const struct iov_iter *i)
{
return i->type & (READ | WRITE);
}
/*
* 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 iov_iter_copy_from_user_atomic(struct page *page,
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
void iov_iter_revert(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(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);
bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i);
size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *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)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return false;
else
return _copy_from_iter_full(addr, bytes, i);
}
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)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return false;
else
return _copy_from_iter_full_nocache(addr, bytes, i);
}
#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_UACCESS_MCSAFE
size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i);
#else
#define _copy_to_iter_mcsafe _copy_to_iter
#endif
static __always_inline __must_check
size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, false)))
return 0;
else
return _copy_from_iter_flushcache(addr, bytes, i);
}
static __always_inline __must_check
size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i)
{
if (unlikely(!check_copy_size(addr, bytes, true)))
return 0;
else
return _copy_to_iter_mcsafe(addr, bytes, i);
}
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);
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);
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;
}
size_t csum_and_copy_to_iter(const void *addr, size_t bytes, void *csump, struct iov_iter *i);
size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i);
size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
struct iov_iter *i);
ssize_t import_iovec(int type, const struct iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iov, struct iov_iter *i);
#ifdef CONFIG_COMPAT
struct compat_iovec;
ssize_t compat_import_iovec(int type, const struct compat_iovec __user * uvector,
unsigned nr_segs, unsigned fast_segs,
struct iovec **iov, struct iov_iter *i);
#endif
int import_single_range(int type, void __user *buf, size_t len,
struct iovec *iov, struct iov_iter *i);
int iov_iter_for_each_range(struct iov_iter *i, size_t bytes,
int (*f)(struct kvec *vec, void *context),
void *context);
#endif