summaryrefslogtreecommitdiff
path: root/include/linux/uio.h
blob: 00cebe2b70de7ef3d74c814d4c59b4539c3d55da (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
/* 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;

typedef unsigned int __bitwise iov_iter_extraction_t;

struct kvec {
	void *iov_base; /* and that should *never* hold a userland pointer */
	size_t iov_len;
};

enum iter_type {
	/* iter types */
	ITER_UBUF,
	ITER_IOVEC,
	ITER_BVEC,
	ITER_KVEC,
	ITER_XARRAY,
	ITER_DISCARD,
};

#define ITER_SOURCE	1	// == WRITE
#define ITER_DEST	0	// == READ

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;
	/*
	 * Hack alert: overlay ubuf_iovec with iovec + count, so
	 * that the members resolve correctly regardless of the type
	 * of iterator used. This means that you can use:
	 *
	 * &iter->__ubuf_iovec or iter->__iov
	 *
	 * interchangably for the user_backed cases, hence simplifying
	 * some of the cases that need to deal with both.
	 */
	union {
		/*
		 * This really should be a const, but we cannot do that without
		 * also modifying any of the zero-filling iter init functions.
		 * Leave it non-const for now, but it should be treated as such.
		 */
		struct iovec __ubuf_iovec;
		struct {
			union {
				/* use iter_iov() to get the current vec */
				const struct iovec *__iov;
				const struct kvec *kvec;
				const struct bio_vec *bvec;
				struct xarray *xarray;
				void __user *ubuf;
			};
			size_t count;
		};
	};
	union {
		unsigned long nr_segs;
		loff_t xarray_start;
	};
};

static inline const struct iovec *iter_iov(const struct iov_iter *iter)
{
	if (iter->iter_type == ITER_UBUF)
		return (const struct iovec *) &iter->__ubuf_iovec;
	return iter->__iov;
}

#define iter_iov_addr(iter)	(iter_iov(iter)->iov_base + (iter)->iov_offset)
#define iter_iov_len(iter)	(iter_iov(iter)->iov_len - (iter)->iov_offset)

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_ubuf(const struct iov_iter *i)
{
	return iov_iter_type(i) == ITER_UBUF;
}

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_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;
}

static inline bool user_backed_iter(const struct iov_iter *i)
{
	return iter_is_ubuf(i) || iter_is_iovec(i);
}

/*
 * 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;
}

size_t copy_page_from_iter_atomic(struct page *page, size_t 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 inline size_t copy_folio_from_iter_atomic(struct folio *folio,
		size_t offset, size_t bytes, struct iov_iter *i)
{
	return copy_page_from_iter_atomic(&folio->page, offset, bytes, i);
}

size_t copy_page_to_iter_nofault(struct page *page, unsigned offset,
				 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 (check_copy_size(addr, bytes, true))
		return _copy_to_iter(addr, bytes, i);
	return 0;
}

static __always_inline __must_check
size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i)
{
	if (check_copy_size(addr, bytes, false))
		return _copy_from_iter(addr, bytes, i);
	return 0;
}

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 (check_copy_size(addr, bytes, false))
		return _copy_from_iter_nocache(addr, bytes, i);
	return 0;
}

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 *);
bool iov_iter_is_aligned(const struct iov_iter *i, unsigned addr_mask,
			unsigned len_mask);
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_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_pages2(struct iov_iter *i, struct page **pages,
			size_t maxsize, unsigned maxpages, size_t *start);
ssize_t iov_iter_get_pages_alloc2(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;
}

static inline int
iov_iter_npages_cap(struct iov_iter *i, int maxpages, size_t max_bytes)
{
	size_t shorted = 0;
	int npages;

	if (iov_iter_count(i) > max_bytes) {
		shorted = iov_iter_count(i) - max_bytes;
		iov_iter_truncate(i, max_bytes);
	}
	npages = iov_iter_npages(i, maxpages);
	if (shorted)
		iov_iter_reexpand(i, iov_iter_count(i) + shorted);

	return npages;
}

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_ubuf(int type, void __user *buf, size_t len, struct iov_iter *i);

static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
			void __user *buf, size_t count)
{
	WARN_ON(direction & ~(READ | WRITE));
	*i = (struct iov_iter) {
		.iter_type = ITER_UBUF,
		.data_source = direction,
		.ubuf = buf,
		.count = count,
		.nr_segs = 1
	};
}
/* Flags for iov_iter_get/extract_pages*() */
/* Allow P2PDMA on the extracted pages */
#define ITER_ALLOW_P2PDMA	((__force iov_iter_extraction_t)0x01)

ssize_t iov_iter_extract_pages(struct iov_iter *i, struct page ***pages,
			       size_t maxsize, unsigned int maxpages,
			       iov_iter_extraction_t extraction_flags,
			       size_t *offset0);

/**
 * iov_iter_extract_will_pin - Indicate how pages from the iterator will be retained
 * @iter: The iterator
 *
 * Examine the iterator and indicate by returning true or false as to how, if
 * at all, pages extracted from the iterator will be retained by the extraction
 * function.
 *
 * %true indicates that the pages will have a pin placed in them that the
 * caller must unpin.  This is must be done for DMA/async DIO to force fork()
 * to forcibly copy a page for the child (the parent must retain the original
 * page).
 *
 * %false indicates that no measures are taken and that it's up to the caller
 * to retain the pages.
 */
static inline bool iov_iter_extract_will_pin(const struct iov_iter *iter)
{
	return user_backed_iter(iter);
}

struct sg_table;
ssize_t extract_iter_to_sg(struct iov_iter *iter, size_t len,
			   struct sg_table *sgtable, unsigned int sg_max,
			   iov_iter_extraction_t extraction_flags);

#endif