summaryrefslogtreecommitdiffstats
path: root/sys/kern/subr_uio.c
blob: 87892fd82798bf5c0f4f13a2ccef5116892879ed (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
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
/*-
 * Copyright (c) 1982, 1986, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * Copyright (c) 2014 The FreeBSD Foundation
 *
 * Portions of this software were developed by Konstantin Belousov
 * under sponsorship from the FreeBSD Foundation.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)kern_subr.c	8.3 (Berkeley) 1/21/94
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mman.h>
#include <sys/proc.h>
#include <sys/resourcevar.h>
#include <sys/rwlock.h>
#include <sys/sched.h>
#include <sys/sysctl.h>
#include <sys/vnode.h>

#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_extern.h>
#include <vm/vm_page.h>
#include <vm/vm_pageout.h>
#include <vm/vm_map.h>

SYSCTL_INT(_kern, KERN_IOV_MAX, iov_max, CTLFLAG_RD, SYSCTL_NULL_INT_PTR, UIO_MAXIOV,
	"Maximum number of elements in an I/O vector; sysconf(_SC_IOV_MAX)");

static int uiomove_faultflag(void *cp, int n, struct uio *uio, int nofault);

int
copyin_nofault(const void *udaddr, void *kaddr, size_t len)
{
	int error, save;

	save = vm_fault_disable_pagefaults();
	error = copyin(udaddr, kaddr, len);
	vm_fault_enable_pagefaults(save);
	return (error);
}

int
copyout_nofault(const void *kaddr, void *udaddr, size_t len)
{
	int error, save;

	save = vm_fault_disable_pagefaults();
	error = copyout(kaddr, udaddr, len);
	vm_fault_enable_pagefaults(save);
	return (error);
}

#define	PHYS_PAGE_COUNT(len)	(howmany(len, PAGE_SIZE) + 1)

int
physcopyin(void *src, vm_paddr_t dst, size_t len)
{
	vm_page_t m[PHYS_PAGE_COUNT(len)];
	struct iovec iov[1];
	struct uio uio;
	int i;

	iov[0].iov_base = src;
	iov[0].iov_len = len;
	uio.uio_iov = iov;
	uio.uio_iovcnt = 1;
	uio.uio_offset = 0;
	uio.uio_resid = len;
	uio.uio_segflg = UIO_SYSSPACE;
	uio.uio_rw = UIO_WRITE;
	for (i = 0; i < PHYS_PAGE_COUNT(len); i++, dst += PAGE_SIZE)
		m[i] = PHYS_TO_VM_PAGE(dst);
	return (uiomove_fromphys(m, dst & PAGE_MASK, len, &uio));
}

int
physcopyout(vm_paddr_t src, void *dst, size_t len)
{
	vm_page_t m[PHYS_PAGE_COUNT(len)];
	struct iovec iov[1];
	struct uio uio;
	int i;

	iov[0].iov_base = dst;
	iov[0].iov_len = len;
	uio.uio_iov = iov;
	uio.uio_iovcnt = 1;
	uio.uio_offset = 0;
	uio.uio_resid = len;
	uio.uio_segflg = UIO_SYSSPACE;
	uio.uio_rw = UIO_READ;
	for (i = 0; i < PHYS_PAGE_COUNT(len); i++, src += PAGE_SIZE)
		m[i] = PHYS_TO_VM_PAGE(src);
	return (uiomove_fromphys(m, src & PAGE_MASK, len, &uio));
}

#undef PHYS_PAGE_COUNT

int
uiomove(void *cp, int n, struct uio *uio)
{

	return (uiomove_faultflag(cp, n, uio, 0));
}

int
uiomove_nofault(void *cp, int n, struct uio *uio)
{

	return (uiomove_faultflag(cp, n, uio, 1));
}

static int
uiomove_faultflag(void *cp, int n, struct uio *uio, int nofault)
{
	struct thread *td;
	struct iovec *iov;
	size_t cnt;
	int error, newflags, save;

	td = curthread;
	error = 0;

	KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
	    ("uiomove: mode"));
	KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_td == td,
	    ("uiomove proc"));
	if (!nofault)
		WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL,
		    "Calling uiomove()");

	/* XXX does it make a sense to set TDP_DEADLKTREAT for UIO_SYSSPACE ? */
	newflags = TDP_DEADLKTREAT;
	if (uio->uio_segflg == UIO_USERSPACE && nofault) {
		/*
		 * Fail if a non-spurious page fault occurs.
		 */
		newflags |= TDP_NOFAULTING | TDP_RESETSPUR;
	}
	save = curthread_pflags_set(newflags);

	while (n > 0 && uio->uio_resid) {
		iov = uio->uio_iov;
		cnt = iov->iov_len;
		if (cnt == 0) {
			uio->uio_iov++;
			uio->uio_iovcnt--;
			continue;
		}
		if (cnt > n)
			cnt = n;

		switch (uio->uio_segflg) {

		case UIO_USERSPACE:
			maybe_yield();
			if (uio->uio_rw == UIO_READ)
				error = copyout(cp, iov->iov_base, cnt);
			else
				error = copyin(iov->iov_base, cp, cnt);
			if (error)
				goto out;
			break;

		case UIO_SYSSPACE:
			if (uio->uio_rw == UIO_READ)
				bcopy(cp, iov->iov_base, cnt);
			else
				bcopy(iov->iov_base, cp, cnt);
			break;
		case UIO_NOCOPY:
			break;
		}
		iov->iov_base = (char *)iov->iov_base + cnt;
		iov->iov_len -= cnt;
		uio->uio_resid -= cnt;
		uio->uio_offset += cnt;
		cp = (char *)cp + cnt;
		n -= cnt;
	}
out:
	curthread_pflags_restore(save);
	return (error);
}

/*
 * Wrapper for uiomove() that validates the arguments against a known-good
 * kernel buffer.  Currently, uiomove accepts a signed (n) argument, which
 * is almost definitely a bad thing, so we catch that here as well.  We
 * return a runtime failure, but it might be desirable to generate a runtime
 * assertion failure instead.
 */
int
uiomove_frombuf(void *buf, int buflen, struct uio *uio)
{
	size_t offset, n;

	if (uio->uio_offset < 0 || uio->uio_resid < 0 ||
	    (offset = uio->uio_offset) != uio->uio_offset)
		return (EINVAL);
	if (buflen <= 0 || offset >= buflen)
		return (0);
	if ((n = buflen - offset) > IOSIZE_MAX)
		return (EINVAL);
	return (uiomove((char *)buf + offset, n, uio));
}

/*
 * Give next character to user as result of read.
 */
int
ureadc(int c, struct uio *uio)
{
	struct iovec *iov;
	char *iov_base;

	WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL,
	    "Calling ureadc()");

again:
	if (uio->uio_iovcnt == 0 || uio->uio_resid == 0)
		panic("ureadc");
	iov = uio->uio_iov;
	if (iov->iov_len == 0) {
		uio->uio_iovcnt--;
		uio->uio_iov++;
		goto again;
	}
	switch (uio->uio_segflg) {

	case UIO_USERSPACE:
		if (subyte(iov->iov_base, c) < 0)
			return (EFAULT);
		break;

	case UIO_SYSSPACE:
		iov_base = iov->iov_base;
		*iov_base = c;
		break;

	case UIO_NOCOPY:
		break;
	}
	iov->iov_base = (char *)iov->iov_base + 1;
	iov->iov_len--;
	uio->uio_resid--;
	uio->uio_offset++;
	return (0);
}

int
copyinfrom(const void * __restrict src, void * __restrict dst, size_t len,
    int seg)
{
	int error = 0;

	switch (seg) {
	case UIO_USERSPACE:
		error = copyin(src, dst, len);
		break;
	case UIO_SYSSPACE:
		bcopy(src, dst, len);
		break;
	default:
		panic("copyinfrom: bad seg %d\n", seg);
	}
	return (error);
}

int
copyinstrfrom(const void * __restrict src, void * __restrict dst, size_t len,
    size_t * __restrict copied, int seg)
{
	int error = 0;

	switch (seg) {
	case UIO_USERSPACE:
		error = copyinstr(src, dst, len, copied);
		break;
	case UIO_SYSSPACE:
		error = copystr(src, dst, len, copied);
		break;
	default:
		panic("copyinstrfrom: bad seg %d\n", seg);
	}
	return (error);
}

int
copyiniov(const struct iovec *iovp, u_int iovcnt, struct iovec **iov, int error)
{
	u_int iovlen;

	*iov = NULL;
	if (iovcnt > UIO_MAXIOV)
		return (error);
	iovlen = iovcnt * sizeof (struct iovec);
	*iov = malloc(iovlen, M_IOV, M_WAITOK);
	error = copyin(iovp, *iov, iovlen);
	if (error) {
		free(*iov, M_IOV);
		*iov = NULL;
	}
	return (error);
}

int
copyinuio(const struct iovec *iovp, u_int iovcnt, struct uio **uiop)
{
	struct iovec *iov;
	struct uio *uio;
	u_int iovlen;
	int error, i;

	*uiop = NULL;
	if (iovcnt > UIO_MAXIOV)
		return (EINVAL);
	iovlen = iovcnt * sizeof (struct iovec);
	uio = malloc(iovlen + sizeof *uio, M_IOV, M_WAITOK);
	iov = (struct iovec *)(uio + 1);
	error = copyin(iovp, iov, iovlen);
	if (error) {
		free(uio, M_IOV);
		return (error);
	}
	uio->uio_iov = iov;
	uio->uio_iovcnt = iovcnt;
	uio->uio_segflg = UIO_USERSPACE;
	uio->uio_offset = -1;
	uio->uio_resid = 0;
	for (i = 0; i < iovcnt; i++) {
		if (iov->iov_len > IOSIZE_MAX - uio->uio_resid) {
			free(uio, M_IOV);
			return (EINVAL);
		}
		uio->uio_resid += iov->iov_len;
		iov++;
	}
	*uiop = uio;
	return (0);
}

struct uio *
cloneuio(struct uio *uiop)
{
	struct uio *uio;
	int iovlen;

	iovlen = uiop->uio_iovcnt * sizeof (struct iovec);
	uio = malloc(iovlen + sizeof *uio, M_IOV, M_WAITOK);
	*uio = *uiop;
	uio->uio_iov = (struct iovec *)(uio + 1);
	bcopy(uiop->uio_iov, uio->uio_iov, iovlen);
	return (uio);
}

/*
 * Map some anonymous memory in user space of size sz, rounded up to the page
 * boundary.
 */
int
copyout_map(struct thread *td, vm_offset_t *addr, size_t sz)
{
	struct vmspace *vms;
	int error;
	vm_size_t size;

	vms = td->td_proc->p_vmspace;

	/*
	 * Map somewhere after heap in process memory.
	 */
	PROC_LOCK(td->td_proc);
	*addr = round_page((vm_offset_t)vms->vm_daddr +
	    lim_max(td->td_proc, RLIMIT_DATA));
	PROC_UNLOCK(td->td_proc);

	/* round size up to page boundry */
	size = (vm_size_t)round_page(sz);

	error = vm_mmap(&vms->vm_map, addr, size, PROT_READ | PROT_WRITE,
	    VM_PROT_ALL, MAP_PRIVATE | MAP_ANON, OBJT_DEFAULT, NULL, 0);

	return (error);
}

/*
 * Unmap memory in user space.
 */
int
copyout_unmap(struct thread *td, vm_offset_t addr, size_t sz)
{
	vm_map_t map;
	vm_size_t size;

	if (sz == 0)
		return (0);

	map = &td->td_proc->p_vmspace->vm_map;
	size = (vm_size_t)round_page(sz);

	if (vm_map_remove(map, addr, addr + size) != KERN_SUCCESS)
		return (EINVAL);

	return (0);
}

#ifdef NO_FUEWORD
/*
 * XXXKIB The temporal implementation of fue*() functions which do not
 * handle usermode -1 properly, mixing it with the fault code.  Keep
 * this until MD code is written.  Currently sparc64, mips and arm do
 * not have proper implementation.
 */

int
fueword(volatile const void *base, long *val)
{
	long res;

	res = fuword(base);
	if (res == -1)
		return (-1);
	*val = res;
	return (0);
}

int
fueword32(volatile const void *base, int32_t *val)
{
	int32_t res;

	res = fuword32(base);
	if (res == -1)
		return (-1);
	*val = res;
	return (0);
}

#ifdef _LP64
int
fueword64(volatile const void *base, int64_t *val)
{
	int32_t res;

	res = fuword64(base);
	if (res == -1)
		return (-1);
	*val = res;
	return (0);
}
#endif

int
casueword32(volatile uint32_t *base, uint32_t oldval, uint32_t *oldvalp,
    uint32_t newval)
{
	int32_t ov;

	ov = casuword32(base, oldval, newval);
	if (ov == -1)
		return (-1);
	*oldvalp = ov;
	return (0);
}

int
casueword(volatile u_long *p, u_long oldval, u_long *oldvalp, u_long newval)
{
	u_long ov;

	ov = casuword(p, oldval, newval);
	if (ov == -1)
		return (-1);
	*oldvalp = ov;
	return (0);
}
#else /* NO_FUEWORD */
int32_t
fuword32(volatile const void *addr)
{
	int rv;
	int32_t val;

	rv = fueword32(addr, &val);
	return (rv == -1 ? -1 : val);
}

#ifdef _LP64
int64_t
fuword64(volatile const void *addr)
{
	int rv;
	int64_t val;

	rv = fueword64(addr, &val);
	return (rv == -1 ? -1 : val);
}
#endif /* _LP64 */

long
fuword(volatile const void *addr)
{
	long val;
	int rv;

	rv = fueword(addr, &val);
	return (rv == -1 ? -1 : val);
}

uint32_t
casuword32(volatile uint32_t *addr, uint32_t old, uint32_t new)
{
	int rv;
	uint32_t val;

	rv = casueword32(addr, old, &val, new);
	return (rv == -1 ? -1 : val);
}

u_long
casuword(volatile u_long *addr, u_long old, u_long new)
{
	int rv;
	u_long val;

	rv = casueword(addr, old, &val, new);
	return (rv == -1 ? -1 : val);
}

#endif /* NO_FUEWORD */
OpenPOWER on IntegriCloud