summaryrefslogtreecommitdiff
path: root/io_uring/sqpoll.c
blob: 65b5dbe3c850ed564432c76f17e64739d430f2fe (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Contains the core associated with submission side polling of the SQ
 * ring, offloading submissions from the application to a kernel thread.
 */
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/audit.h>
#include <linux/security.h>
#include <linux/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "sqpoll.h"

#define IORING_SQPOLL_CAP_ENTRIES_VALUE 8

enum {
	IO_SQ_THREAD_SHOULD_STOP = 0,
	IO_SQ_THREAD_SHOULD_PARK,
};

void io_sq_thread_unpark(struct io_sq_data *sqd)
	__releases(&sqd->lock)
{
	WARN_ON_ONCE(sqd->thread == current);

	/*
	 * Do the dance but not conditional clear_bit() because it'd race with
	 * other threads incrementing park_pending and setting the bit.
	 */
	clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	if (atomic_dec_return(&sqd->park_pending))
		set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	mutex_unlock(&sqd->lock);
}

void io_sq_thread_park(struct io_sq_data *sqd)
	__acquires(&sqd->lock)
{
	WARN_ON_ONCE(sqd->thread == current);

	atomic_inc(&sqd->park_pending);
	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
	mutex_lock(&sqd->lock);
	if (sqd->thread)
		wake_up_process(sqd->thread);
}

void io_sq_thread_stop(struct io_sq_data *sqd)
{
	WARN_ON_ONCE(sqd->thread == current);
	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));

	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
	mutex_lock(&sqd->lock);
	if (sqd->thread)
		wake_up_process(sqd->thread);
	mutex_unlock(&sqd->lock);
	wait_for_completion(&sqd->exited);
}

void io_put_sq_data(struct io_sq_data *sqd)
{
	if (refcount_dec_and_test(&sqd->refs)) {
		WARN_ON_ONCE(atomic_read(&sqd->park_pending));

		io_sq_thread_stop(sqd);
		kfree(sqd);
	}
}

static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
{
	struct io_ring_ctx *ctx;
	unsigned sq_thread_idle = 0;

	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
		sq_thread_idle = max(sq_thread_idle, ctx->sq_thread_idle);
	sqd->sq_thread_idle = sq_thread_idle;
}

void io_sq_thread_finish(struct io_ring_ctx *ctx)
{
	struct io_sq_data *sqd = ctx->sq_data;

	if (sqd) {
		io_sq_thread_park(sqd);
		list_del_init(&ctx->sqd_list);
		io_sqd_update_thread_idle(sqd);
		io_sq_thread_unpark(sqd);

		io_put_sq_data(sqd);
		ctx->sq_data = NULL;
	}
}

static struct io_sq_data *io_attach_sq_data(struct io_uring_params *p)
{
	struct io_ring_ctx *ctx_attach;
	struct io_sq_data *sqd;
	struct fd f;

	f = fdget(p->wq_fd);
	if (!f.file)
		return ERR_PTR(-ENXIO);
	if (!io_is_uring_fops(f.file)) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}

	ctx_attach = f.file->private_data;
	sqd = ctx_attach->sq_data;
	if (!sqd) {
		fdput(f);
		return ERR_PTR(-EINVAL);
	}
	if (sqd->task_tgid != current->tgid) {
		fdput(f);
		return ERR_PTR(-EPERM);
	}

	refcount_inc(&sqd->refs);
	fdput(f);
	return sqd;
}

static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
					 bool *attached)
{
	struct io_sq_data *sqd;

	*attached = false;
	if (p->flags & IORING_SETUP_ATTACH_WQ) {
		sqd = io_attach_sq_data(p);
		if (!IS_ERR(sqd)) {
			*attached = true;
			return sqd;
		}
		/* fall through for EPERM case, setup new sqd/task */
		if (PTR_ERR(sqd) != -EPERM)
			return sqd;
	}

	sqd = kzalloc(sizeof(*sqd), GFP_KERNEL);
	if (!sqd)
		return ERR_PTR(-ENOMEM);

	atomic_set(&sqd->park_pending, 0);
	refcount_set(&sqd->refs, 1);
	INIT_LIST_HEAD(&sqd->ctx_list);
	mutex_init(&sqd->lock);
	init_waitqueue_head(&sqd->wait);
	init_completion(&sqd->exited);
	return sqd;
}

static inline bool io_sqd_events_pending(struct io_sq_data *sqd)
{
	return READ_ONCE(sqd->state);
}

static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
{
	unsigned int to_submit;
	int ret = 0;

	to_submit = io_sqring_entries(ctx);
	/* if we're handling multiple rings, cap submit size for fairness */
	if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
		to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;

	if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
		const struct cred *creds = NULL;

		if (ctx->sq_creds != current_cred())
			creds = override_creds(ctx->sq_creds);

		mutex_lock(&ctx->uring_lock);
		if (!wq_list_empty(&ctx->iopoll_list))
			io_do_iopoll(ctx, true);

		/*
		 * Don't submit if refs are dying, good for io_uring_register(),
		 * but also it is relied upon by io_ring_exit_work()
		 */
		if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
		    !(ctx->flags & IORING_SETUP_R_DISABLED))
			ret = io_submit_sqes(ctx, to_submit);
		mutex_unlock(&ctx->uring_lock);

		if (to_submit && wq_has_sleeper(&ctx->sqo_sq_wait))
			wake_up(&ctx->sqo_sq_wait);
		if (creds)
			revert_creds(creds);
	}

	return ret;
}

static bool io_sqd_handle_event(struct io_sq_data *sqd)
{
	bool did_sig = false;
	struct ksignal ksig;

	if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
	    signal_pending(current)) {
		mutex_unlock(&sqd->lock);
		if (signal_pending(current))
			did_sig = get_signal(&ksig);
		cond_resched();
		mutex_lock(&sqd->lock);
		sqd->sq_cpu = raw_smp_processor_id();
	}
	return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
}

static int io_sq_thread(void *data)
{
	struct io_sq_data *sqd = data;
	struct io_ring_ctx *ctx;
	unsigned long timeout = 0;
	char buf[TASK_COMM_LEN];
	DEFINE_WAIT(wait);

	snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
	set_task_comm(current, buf);

	/* reset to our pid after we've set task_comm, for fdinfo */
	sqd->task_pid = current->pid;

	if (sqd->sq_cpu != -1) {
		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
	} else {
		set_cpus_allowed_ptr(current, cpu_online_mask);
		sqd->sq_cpu = raw_smp_processor_id();
	}

	mutex_lock(&sqd->lock);
	while (1) {
		bool cap_entries, sqt_spin = false;

		if (io_sqd_events_pending(sqd) || signal_pending(current)) {
			if (io_sqd_handle_event(sqd))
				break;
			timeout = jiffies + sqd->sq_thread_idle;
		}

		cap_entries = !list_is_singular(&sqd->ctx_list);
		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
			int ret = __io_sq_thread(ctx, cap_entries);

			if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
				sqt_spin = true;
		}
		if (io_run_task_work())
			sqt_spin = true;

		if (sqt_spin || !time_after(jiffies, timeout)) {
			if (sqt_spin)
				timeout = jiffies + sqd->sq_thread_idle;
			if (unlikely(need_resched())) {
				mutex_unlock(&sqd->lock);
				cond_resched();
				mutex_lock(&sqd->lock);
				sqd->sq_cpu = raw_smp_processor_id();
			}
			continue;
		}

		prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
		if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
			bool needs_sched = true;

			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
				atomic_or(IORING_SQ_NEED_WAKEUP,
						&ctx->rings->sq_flags);
				if ((ctx->flags & IORING_SETUP_IOPOLL) &&
				    !wq_list_empty(&ctx->iopoll_list)) {
					needs_sched = false;
					break;
				}

				/*
				 * Ensure the store of the wakeup flag is not
				 * reordered with the load of the SQ tail
				 */
				smp_mb__after_atomic();

				if (io_sqring_entries(ctx)) {
					needs_sched = false;
					break;
				}
			}

			if (needs_sched) {
				mutex_unlock(&sqd->lock);
				schedule();
				mutex_lock(&sqd->lock);
				sqd->sq_cpu = raw_smp_processor_id();
			}
			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
				atomic_andnot(IORING_SQ_NEED_WAKEUP,
						&ctx->rings->sq_flags);
		}

		finish_wait(&sqd->wait, &wait);
		timeout = jiffies + sqd->sq_thread_idle;
	}

	io_uring_cancel_generic(true, sqd);
	sqd->thread = NULL;
	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
		atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
	io_run_task_work();
	mutex_unlock(&sqd->lock);

	complete(&sqd->exited);
	do_exit(0);
}

void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
{
	DEFINE_WAIT(wait);

	do {
		if (!io_sqring_full(ctx))
			break;
		prepare_to_wait(&ctx->sqo_sq_wait, &wait, TASK_INTERRUPTIBLE);

		if (!io_sqring_full(ctx))
			break;
		schedule();
	} while (!signal_pending(current));

	finish_wait(&ctx->sqo_sq_wait, &wait);
}

__cold int io_sq_offload_create(struct io_ring_ctx *ctx,
				struct io_uring_params *p)
{
	int ret;

	/* Retain compatibility with failing for an invalid attach attempt */
	if ((ctx->flags & (IORING_SETUP_ATTACH_WQ | IORING_SETUP_SQPOLL)) ==
				IORING_SETUP_ATTACH_WQ) {
		struct fd f;

		f = fdget(p->wq_fd);
		if (!f.file)
			return -ENXIO;
		if (!io_is_uring_fops(f.file)) {
			fdput(f);
			return -EINVAL;
		}
		fdput(f);
	}
	if (ctx->flags & IORING_SETUP_SQPOLL) {
		struct task_struct *tsk;
		struct io_sq_data *sqd;
		bool attached;

		ret = security_uring_sqpoll();
		if (ret)
			return ret;

		sqd = io_get_sq_data(p, &attached);
		if (IS_ERR(sqd)) {
			ret = PTR_ERR(sqd);
			goto err;
		}

		ctx->sq_creds = get_current_cred();
		ctx->sq_data = sqd;
		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
		if (!ctx->sq_thread_idle)
			ctx->sq_thread_idle = HZ;

		io_sq_thread_park(sqd);
		list_add(&ctx->sqd_list, &sqd->ctx_list);
		io_sqd_update_thread_idle(sqd);
		/* don't attach to a dying SQPOLL thread, would be racy */
		ret = (attached && !sqd->thread) ? -ENXIO : 0;
		io_sq_thread_unpark(sqd);

		if (ret < 0)
			goto err;
		if (attached)
			return 0;

		if (p->flags & IORING_SETUP_SQ_AFF) {
			int cpu = p->sq_thread_cpu;

			ret = -EINVAL;
			if (cpu >= nr_cpu_ids || !cpu_online(cpu))
				goto err_sqpoll;
			sqd->sq_cpu = cpu;
		} else {
			sqd->sq_cpu = -1;
		}

		sqd->task_pid = current->pid;
		sqd->task_tgid = current->tgid;
		tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
		if (IS_ERR(tsk)) {
			ret = PTR_ERR(tsk);
			goto err_sqpoll;
		}

		sqd->thread = tsk;
		ret = io_uring_alloc_task_context(tsk, ctx);
		wake_up_new_task(tsk);
		if (ret)
			goto err;
	} else if (p->flags & IORING_SETUP_SQ_AFF) {
		/* Can't have SQ_AFF without SQPOLL */
		ret = -EINVAL;
		goto err;
	}

	return 0;
err_sqpoll:
	complete(&ctx->sq_data->exited);
err:
	io_sq_thread_finish(ctx);
	return ret;
}

__cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx,
				     cpumask_var_t mask)
{
	struct io_sq_data *sqd = ctx->sq_data;
	int ret = -EINVAL;

	if (sqd) {
		io_sq_thread_park(sqd);
		/* Don't set affinity for a dying thread */
		if (sqd->thread)
			ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
		io_sq_thread_unpark(sqd);
	}

	return ret;
}