summaryrefslogtreecommitdiffstats
path: root/io_uring/tctx.c
blob: 7f97d97fef0a9652dd2804f0d6c9c3a9263b97e8 (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
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/nospec.h>
#include <linux/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "tctx.h"

static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
					struct task_struct *task)
{
	struct io_wq_hash *hash;
	struct io_wq_data data;
	unsigned int concurrency;

	mutex_lock(&ctx->uring_lock);
	hash = ctx->hash_map;
	if (!hash) {
		hash = kzalloc(sizeof(*hash), GFP_KERNEL);
		if (!hash) {
			mutex_unlock(&ctx->uring_lock);
			return ERR_PTR(-ENOMEM);
		}
		refcount_set(&hash->refs, 1);
		init_waitqueue_head(&hash->wait);
		ctx->hash_map = hash;
	}
	mutex_unlock(&ctx->uring_lock);

	data.hash = hash;
	data.task = task;
	data.free_work = io_wq_free_work;
	data.do_work = io_wq_submit_work;

	/* Do QD, or 4 * CPUS, whatever is smallest */
	concurrency = min(ctx->sq_entries, 4 * num_online_cpus());

	return io_wq_create(concurrency, &data);
}

void __io_uring_free(struct task_struct *tsk)
{
	struct io_uring_task *tctx = tsk->io_uring;

	WARN_ON_ONCE(!xa_empty(&tctx->xa));
	WARN_ON_ONCE(tctx->io_wq);
	WARN_ON_ONCE(tctx->cached_refs);

	percpu_counter_destroy(&tctx->inflight);
	kfree(tctx);
	tsk->io_uring = NULL;
}

__cold int io_uring_alloc_task_context(struct task_struct *task,
				       struct io_ring_ctx *ctx)
{
	struct io_uring_task *tctx;
	int ret;

	tctx = kzalloc(sizeof(*tctx), GFP_KERNEL);
	if (unlikely(!tctx))
		return -ENOMEM;

	ret = percpu_counter_init(&tctx->inflight, 0, GFP_KERNEL);
	if (unlikely(ret)) {
		kfree(tctx);
		return ret;
	}

	tctx->io_wq = io_init_wq_offload(ctx, task);
	if (IS_ERR(tctx->io_wq)) {
		ret = PTR_ERR(tctx->io_wq);
		percpu_counter_destroy(&tctx->inflight);
		kfree(tctx);
		return ret;
	}

	xa_init(&tctx->xa);
	init_waitqueue_head(&tctx->wait);
	atomic_set(&tctx->in_idle, 0);
	atomic_set(&tctx->inflight_tracked, 0);
	task->io_uring = tctx;
	init_llist_head(&tctx->task_list);
	init_task_work(&tctx->task_work, tctx_task_work);
	return 0;
}

static int io_register_submitter(struct io_ring_ctx *ctx)
{
	int ret = 0;

	mutex_lock(&ctx->uring_lock);
	if (!ctx->submitter_task)
		ctx->submitter_task = get_task_struct(current);
	else if (ctx->submitter_task != current)
		ret = -EEXIST;
	mutex_unlock(&ctx->uring_lock);

	return ret;
}

int __io_uring_add_tctx_node(struct io_ring_ctx *ctx, bool submitter)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_tctx_node *node;
	int ret;

	if ((ctx->flags & IORING_SETUP_SINGLE_ISSUER) && submitter) {
		ret = io_register_submitter(ctx);
		if (ret)
			return ret;
	}

	if (unlikely(!tctx)) {
		ret = io_uring_alloc_task_context(current, ctx);
		if (unlikely(ret))
			return ret;

		tctx = current->io_uring;
		if (ctx->iowq_limits_set) {
			unsigned int limits[2] = { ctx->iowq_limits[0],
						   ctx->iowq_limits[1], };

			ret = io_wq_max_workers(tctx->io_wq, limits);
			if (ret)
				return ret;
		}
	}
	if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
		node = kmalloc(sizeof(*node), GFP_KERNEL);
		if (!node)
			return -ENOMEM;
		node->ctx = ctx;
		node->task = current;

		ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
					node, GFP_KERNEL));
		if (ret) {
			kfree(node);
			return ret;
		}

		mutex_lock(&ctx->uring_lock);
		list_add(&node->ctx_node, &ctx->tctx_list);
		mutex_unlock(&ctx->uring_lock);
	}
	if (submitter)
		tctx->last = ctx;
	return 0;
}

/*
 * Remove this io_uring_file -> task mapping.
 */
__cold void io_uring_del_tctx_node(unsigned long index)
{
	struct io_uring_task *tctx = current->io_uring;
	struct io_tctx_node *node;

	if (!tctx)
		return;
	node = xa_erase(&tctx->xa, index);
	if (!node)
		return;

	WARN_ON_ONCE(current != node->task);
	WARN_ON_ONCE(list_empty(&node->ctx_node));

	mutex_lock(&node->ctx->uring_lock);
	list_del(&node->ctx_node);
	mutex_unlock(&node->ctx->uring_lock);

	if (tctx->last == node->ctx)
		tctx->last = NULL;
	kfree(node);
}

__cold void io_uring_clean_tctx(struct io_uring_task *tctx)
{
	struct io_wq *wq = tctx->io_wq;
	struct io_tctx_node *node;
	unsigned long index;

	xa_for_each(&tctx->xa, index, node) {
		io_uring_del_tctx_node(index);
		cond_resched();
	}
	if (wq) {
		/*
		 * Must be after io_uring_del_tctx_node() (removes nodes under
		 * uring_lock) to avoid race with io_uring_try_cancel_iowq().
		 */
		io_wq_put_and_exit(wq);
		tctx->io_wq = NULL;
	}
}

void io_uring_unreg_ringfd(void)
{
	struct io_uring_task *tctx = current->io_uring;
	int i;

	for (i = 0; i < IO_RINGFD_REG_MAX; i++) {
		if (tctx->registered_rings[i]) {
			fput(tctx->registered_rings[i]);
			tctx->registered_rings[i] = NULL;
		}
	}
}

static int io_ring_add_registered_fd(struct io_uring_task *tctx, int fd,
				     int start, int end)
{
	struct file *file;
	int offset;

	for (offset = start; offset < end; offset++) {
		offset = array_index_nospec(offset, IO_RINGFD_REG_MAX);
		if (tctx->registered_rings[offset])
			continue;

		file = fget(fd);
		if (!file) {
			return -EBADF;
		} else if (!io_is_uring_fops(file)) {
			fput(file);
			return -EOPNOTSUPP;
		}
		tctx->registered_rings[offset] = file;
		return offset;
	}

	return -EBUSY;
}

/*
 * Register a ring fd to avoid fdget/fdput for each io_uring_enter()
 * invocation. User passes in an array of struct io_uring_rsrc_update
 * with ->data set to the ring_fd, and ->offset given for the desired
 * index. If no index is desired, application may set ->offset == -1U
 * and we'll find an available index. Returns number of entries
 * successfully processed, or < 0 on error if none were processed.
 */
int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg,
		       unsigned nr_args)
{
	struct io_uring_rsrc_update __user *arg = __arg;
	struct io_uring_rsrc_update reg;
	struct io_uring_task *tctx;
	int ret, i;

	if (!nr_args || nr_args > IO_RINGFD_REG_MAX)
		return -EINVAL;

	mutex_unlock(&ctx->uring_lock);
	ret = __io_uring_add_tctx_node(ctx, false);
	mutex_lock(&ctx->uring_lock);
	if (ret)
		return ret;

	tctx = current->io_uring;
	for (i = 0; i < nr_args; i++) {
		int start, end;

		if (copy_from_user(&reg, &arg[i], sizeof(reg))) {
			ret = -EFAULT;
			break;
		}

		if (reg.resv) {
			ret = -EINVAL;
			break;
		}

		if (reg.offset == -1U) {
			start = 0;
			end = IO_RINGFD_REG_MAX;
		} else {
			if (reg.offset >= IO_RINGFD_REG_MAX) {
				ret = -EINVAL;
				break;
			}
			start = reg.offset;
			end = start + 1;
		}

		ret = io_ring_add_registered_fd(tctx, reg.data, start, end);
		if (ret < 0)
			break;

		reg.offset = ret;
		if (copy_to_user(&arg[i], &reg, sizeof(reg))) {
			fput(tctx->registered_rings[reg.offset]);
			tctx->registered_rings[reg.offset] = NULL;
			ret = -EFAULT;
			break;
		}
	}

	return i ? i : ret;
}

int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg,
			 unsigned nr_args)
{
	struct io_uring_rsrc_update __user *arg = __arg;
	struct io_uring_task *tctx = current->io_uring;
	struct io_uring_rsrc_update reg;
	int ret = 0, i;

	if (!nr_args || nr_args > IO_RINGFD_REG_MAX)
		return -EINVAL;
	if (!tctx)
		return 0;

	for (i = 0; i < nr_args; i++) {
		if (copy_from_user(&reg, &arg[i], sizeof(reg))) {
			ret = -EFAULT;
			break;
		}
		if (reg.resv || reg.data || reg.offset >= IO_RINGFD_REG_MAX) {
			ret = -EINVAL;
			break;
		}

		reg.offset = array_index_nospec(reg.offset, IO_RINGFD_REG_MAX);
		if (tctx->registered_rings[reg.offset]) {
			fput(tctx->registered_rings[reg.offset]);
			tctx->registered_rings[reg.offset] = NULL;
		}
	}

	return i ? i : ret;
}