summaryrefslogtreecommitdiff
path: root/io_uring/register.c
blob: e3c20be5a198033fbb2c1289f8b901068918bbff (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Code related to the io_uring_register() syscall
 *
 * Copyright (C) 2023 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/refcount.h>
#include <linux/bits.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/compat.h>
#include <linux/io_uring.h>
#include <linux/io_uring_types.h>

#include "io_uring.h"
#include "opdef.h"
#include "tctx.h"
#include "rsrc.h"
#include "sqpoll.h"
#include "register.h"
#include "cancel.h"
#include "kbuf.h"
#include "napi.h"
#include "eventfd.h"

#define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
				 IORING_REGISTER_LAST + IORING_OP_LAST)

static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
			   unsigned nr_args)
{
	struct io_uring_probe *p;
	size_t size;
	int i, ret;

	if (nr_args > IORING_OP_LAST)
		nr_args = IORING_OP_LAST;

	size = struct_size(p, ops, nr_args);
	p = kzalloc(size, GFP_KERNEL);
	if (!p)
		return -ENOMEM;

	ret = -EFAULT;
	if (copy_from_user(p, arg, size))
		goto out;
	ret = -EINVAL;
	if (memchr_inv(p, 0, size))
		goto out;

	p->last_op = IORING_OP_LAST - 1;

	for (i = 0; i < nr_args; i++) {
		p->ops[i].op = i;
		if (io_uring_op_supported(i))
			p->ops[i].flags = IO_URING_OP_SUPPORTED;
	}
	p->ops_len = i;

	ret = 0;
	if (copy_to_user(arg, p, size))
		ret = -EFAULT;
out:
	kfree(p);
	return ret;
}

int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id)
{
	const struct cred *creds;

	creds = xa_erase(&ctx->personalities, id);
	if (creds) {
		put_cred(creds);
		return 0;
	}

	return -EINVAL;
}


static int io_register_personality(struct io_ring_ctx *ctx)
{
	const struct cred *creds;
	u32 id;
	int ret;

	creds = get_current_cred();

	ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
			XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
	if (ret < 0) {
		put_cred(creds);
		return ret;
	}
	return id;
}

static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
					   void __user *arg, unsigned int nr_args)
{
	struct io_uring_restriction *res;
	size_t size;
	int i, ret;

	/* Restrictions allowed only if rings started disabled */
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	/* We allow only a single restrictions registration */
	if (ctx->restrictions.registered)
		return -EBUSY;

	if (!arg || nr_args > IORING_MAX_RESTRICTIONS)
		return -EINVAL;

	size = array_size(nr_args, sizeof(*res));
	if (size == SIZE_MAX)
		return -EOVERFLOW;

	res = memdup_user(arg, size);
	if (IS_ERR(res))
		return PTR_ERR(res);

	ret = 0;

	for (i = 0; i < nr_args; i++) {
		switch (res[i].opcode) {
		case IORING_RESTRICTION_REGISTER_OP:
			if (res[i].register_op >= IORING_REGISTER_LAST) {
				ret = -EINVAL;
				goto out;
			}

			__set_bit(res[i].register_op,
				  ctx->restrictions.register_op);
			break;
		case IORING_RESTRICTION_SQE_OP:
			if (res[i].sqe_op >= IORING_OP_LAST) {
				ret = -EINVAL;
				goto out;
			}

			__set_bit(res[i].sqe_op, ctx->restrictions.sqe_op);
			break;
		case IORING_RESTRICTION_SQE_FLAGS_ALLOWED:
			ctx->restrictions.sqe_flags_allowed = res[i].sqe_flags;
			break;
		case IORING_RESTRICTION_SQE_FLAGS_REQUIRED:
			ctx->restrictions.sqe_flags_required = res[i].sqe_flags;
			break;
		default:
			ret = -EINVAL;
			goto out;
		}
	}

out:
	/* Reset all restrictions if an error happened */
	if (ret != 0)
		memset(&ctx->restrictions, 0, sizeof(ctx->restrictions));
	else
		ctx->restrictions.registered = true;

	kfree(res);
	return ret;
}

static int io_register_enable_rings(struct io_ring_ctx *ctx)
{
	if (!(ctx->flags & IORING_SETUP_R_DISABLED))
		return -EBADFD;

	if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) {
		WRITE_ONCE(ctx->submitter_task, get_task_struct(current));
		/*
		 * Lazy activation attempts would fail if it was polled before
		 * submitter_task is set.
		 */
		if (wq_has_sleeper(&ctx->poll_wq))
			io_activate_pollwq(ctx);
	}

	if (ctx->restrictions.registered)
		ctx->restricted = 1;

	ctx->flags &= ~IORING_SETUP_R_DISABLED;
	if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
		wake_up(&ctx->sq_data->wait);
	return 0;
}

static __cold int __io_register_iowq_aff(struct io_ring_ctx *ctx,
					 cpumask_var_t new_mask)
{
	int ret;

	if (!(ctx->flags & IORING_SETUP_SQPOLL)) {
		ret = io_wq_cpu_affinity(current->io_uring, new_mask);
	} else {
		mutex_unlock(&ctx->uring_lock);
		ret = io_sqpoll_wq_cpu_affinity(ctx, new_mask);
		mutex_lock(&ctx->uring_lock);
	}

	return ret;
}

static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
				       void __user *arg, unsigned len)
{
	cpumask_var_t new_mask;
	int ret;

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
		return -ENOMEM;

	cpumask_clear(new_mask);
	if (len > cpumask_size())
		len = cpumask_size();

#ifdef CONFIG_COMPAT
	if (in_compat_syscall())
		ret = compat_get_bitmap(cpumask_bits(new_mask),
					(const compat_ulong_t __user *)arg,
					len * 8 /* CHAR_BIT */);
	else
#endif
		ret = copy_from_user(new_mask, arg, len);

	if (ret) {
		free_cpumask_var(new_mask);
		return -EFAULT;
	}

	ret = __io_register_iowq_aff(ctx, new_mask);
	free_cpumask_var(new_mask);
	return ret;
}

static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
{
	return __io_register_iowq_aff(ctx, NULL);
}

static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
					       void __user *arg)
	__must_hold(&ctx->uring_lock)
{
	struct io_tctx_node *node;
	struct io_uring_task *tctx = NULL;
	struct io_sq_data *sqd = NULL;
	__u32 new_count[2];
	int i, ret;

	if (copy_from_user(new_count, arg, sizeof(new_count)))
		return -EFAULT;
	for (i = 0; i < ARRAY_SIZE(new_count); i++)
		if (new_count[i] > INT_MAX)
			return -EINVAL;

	if (ctx->flags & IORING_SETUP_SQPOLL) {
		sqd = ctx->sq_data;
		if (sqd) {
			/*
			 * Observe the correct sqd->lock -> ctx->uring_lock
			 * ordering. Fine to drop uring_lock here, we hold
			 * a ref to the ctx.
			 */
			refcount_inc(&sqd->refs);
			mutex_unlock(&ctx->uring_lock);
			mutex_lock(&sqd->lock);
			mutex_lock(&ctx->uring_lock);
			if (sqd->thread)
				tctx = sqd->thread->io_uring;
		}
	} else {
		tctx = current->io_uring;
	}

	BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));

	for (i = 0; i < ARRAY_SIZE(new_count); i++)
		if (new_count[i])
			ctx->iowq_limits[i] = new_count[i];
	ctx->iowq_limits_set = true;

	if (tctx && tctx->io_wq) {
		ret = io_wq_max_workers(tctx->io_wq, new_count);
		if (ret)
			goto err;
	} else {
		memset(new_count, 0, sizeof(new_count));
	}

	if (sqd) {
		mutex_unlock(&ctx->uring_lock);
		mutex_unlock(&sqd->lock);
		io_put_sq_data(sqd);
		mutex_lock(&ctx->uring_lock);
	}

	if (copy_to_user(arg, new_count, sizeof(new_count)))
		return -EFAULT;

	/* that's it for SQPOLL, only the SQPOLL task creates requests */
	if (sqd)
		return 0;

	/* now propagate the restriction to all registered users */
	list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
		tctx = node->task->io_uring;
		if (WARN_ON_ONCE(!tctx->io_wq))
			continue;

		for (i = 0; i < ARRAY_SIZE(new_count); i++)
			new_count[i] = ctx->iowq_limits[i];
		/* ignore errors, it always returns zero anyway */
		(void)io_wq_max_workers(tctx->io_wq, new_count);
	}
	return 0;
err:
	if (sqd) {
		mutex_unlock(&ctx->uring_lock);
		mutex_unlock(&sqd->lock);
		io_put_sq_data(sqd);
		mutex_lock(&ctx->uring_lock);
	}
	return ret;
}

static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
			       void __user *arg, unsigned nr_args)
	__releases(ctx->uring_lock)
	__acquires(ctx->uring_lock)
{
	int ret;

	/*
	 * We don't quiesce the refs for register anymore and so it can't be
	 * dying as we're holding a file ref here.
	 */
	if (WARN_ON_ONCE(percpu_ref_is_dying(&ctx->refs)))
		return -ENXIO;

	if (ctx->submitter_task && ctx->submitter_task != current)
		return -EEXIST;

	if (ctx->restricted) {
		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
		if (!test_bit(opcode, ctx->restrictions.register_op))
			return -EACCES;
	}

	switch (opcode) {
	case IORING_REGISTER_BUFFERS:
		ret = -EFAULT;
		if (!arg)
			break;
		ret = io_sqe_buffers_register(ctx, arg, nr_args, NULL);
		break;
	case IORING_UNREGISTER_BUFFERS:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_buffers_unregister(ctx);
		break;
	case IORING_REGISTER_FILES:
		ret = -EFAULT;
		if (!arg)
			break;
		ret = io_sqe_files_register(ctx, arg, nr_args, NULL);
		break;
	case IORING_UNREGISTER_FILES:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_sqe_files_unregister(ctx);
		break;
	case IORING_REGISTER_FILES_UPDATE:
		ret = io_register_files_update(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_EVENTFD:
		ret = -EINVAL;
		if (nr_args != 1)
			break;
		ret = io_eventfd_register(ctx, arg, 0);
		break;
	case IORING_REGISTER_EVENTFD_ASYNC:
		ret = -EINVAL;
		if (nr_args != 1)
			break;
		ret = io_eventfd_register(ctx, arg, 1);
		break;
	case IORING_UNREGISTER_EVENTFD:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_eventfd_unregister(ctx);
		break;
	case IORING_REGISTER_PROBE:
		ret = -EINVAL;
		if (!arg || nr_args > 256)
			break;
		ret = io_probe(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_PERSONALITY:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_register_personality(ctx);
		break;
	case IORING_UNREGISTER_PERSONALITY:
		ret = -EINVAL;
		if (arg)
			break;
		ret = io_unregister_personality(ctx, nr_args);
		break;
	case IORING_REGISTER_ENABLE_RINGS:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_register_enable_rings(ctx);
		break;
	case IORING_REGISTER_RESTRICTIONS:
		ret = io_register_restrictions(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_FILES2:
		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_FILE);
		break;
	case IORING_REGISTER_FILES_UPDATE2:
		ret = io_register_rsrc_update(ctx, arg, nr_args,
					      IORING_RSRC_FILE);
		break;
	case IORING_REGISTER_BUFFERS2:
		ret = io_register_rsrc(ctx, arg, nr_args, IORING_RSRC_BUFFER);
		break;
	case IORING_REGISTER_BUFFERS_UPDATE:
		ret = io_register_rsrc_update(ctx, arg, nr_args,
					      IORING_RSRC_BUFFER);
		break;
	case IORING_REGISTER_IOWQ_AFF:
		ret = -EINVAL;
		if (!arg || !nr_args)
			break;
		ret = io_register_iowq_aff(ctx, arg, nr_args);
		break;
	case IORING_UNREGISTER_IOWQ_AFF:
		ret = -EINVAL;
		if (arg || nr_args)
			break;
		ret = io_unregister_iowq_aff(ctx);
		break;
	case IORING_REGISTER_IOWQ_MAX_WORKERS:
		ret = -EINVAL;
		if (!arg || nr_args != 2)
			break;
		ret = io_register_iowq_max_workers(ctx, arg);
		break;
	case IORING_REGISTER_RING_FDS:
		ret = io_ringfd_register(ctx, arg, nr_args);
		break;
	case IORING_UNREGISTER_RING_FDS:
		ret = io_ringfd_unregister(ctx, arg, nr_args);
		break;
	case IORING_REGISTER_PBUF_RING:
		ret = -EINVAL;
		if (!arg || nr_args != 1)
			break;
		ret = io_register_pbuf_ring(ctx, arg);
		break;
	case IORING_UNREGISTER_PBUF_RING:
		ret = -EINVAL;
		if (!arg || nr_args != 1)
			break;
		ret = io_unregister_pbuf_ring(ctx, arg);
		break;
	case IORING_REGISTER_SYNC_CANCEL:
		ret = -EINVAL;
		if (!arg || nr_args != 1)
			break;
		ret = io_sync_cancel(ctx, arg);
		break;
	case IORING_REGISTER_FILE_ALLOC_RANGE:
		ret = -EINVAL;
		if (!arg || nr_args)
			break;
		ret = io_register_file_alloc_range(ctx, arg);
		break;
	case IORING_REGISTER_PBUF_STATUS:
		ret = -EINVAL;
		if (!arg || nr_args != 1)
			break;
		ret = io_register_pbuf_status(ctx, arg);
		break;
	case IORING_REGISTER_NAPI:
		ret = -EINVAL;
		if (!arg || nr_args != 1)
			break;
		ret = io_register_napi(ctx, arg);
		break;
	case IORING_UNREGISTER_NAPI:
		ret = -EINVAL;
		if (nr_args != 1)
			break;
		ret = io_unregister_napi(ctx, arg);
		break;
	default:
		ret = -EINVAL;
		break;
	}

	return ret;
}

SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
		void __user *, arg, unsigned int, nr_args)
{
	struct io_ring_ctx *ctx;
	long ret = -EBADF;
	struct file *file;
	bool use_registered_ring;

	use_registered_ring = !!(opcode & IORING_REGISTER_USE_REGISTERED_RING);
	opcode &= ~IORING_REGISTER_USE_REGISTERED_RING;

	if (opcode >= IORING_REGISTER_LAST)
		return -EINVAL;

	if (use_registered_ring) {
		/*
		 * Ring fd has been registered via IORING_REGISTER_RING_FDS, we
		 * need only dereference our task private array to find it.
		 */
		struct io_uring_task *tctx = current->io_uring;

		if (unlikely(!tctx || fd >= IO_RINGFD_REG_MAX))
			return -EINVAL;
		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
		file = tctx->registered_rings[fd];
		if (unlikely(!file))
			return -EBADF;
	} else {
		file = fget(fd);
		if (unlikely(!file))
			return -EBADF;
		ret = -EOPNOTSUPP;
		if (!io_is_uring_fops(file))
			goto out_fput;
	}

	ctx = file->private_data;

	mutex_lock(&ctx->uring_lock);
	ret = __io_uring_register(ctx, opcode, arg, nr_args);
	mutex_unlock(&ctx->uring_lock);
	trace_io_uring_register(ctx, opcode, ctx->nr_user_files, ctx->nr_user_bufs, ret);
out_fput:
	if (!use_registered_ring)
		fput(file);
	return ret;
}