summaryrefslogtreecommitdiff
path: root/kernel/sched/membarrier.c
blob: e23e74d52db54ff260f1084902578916aebf1c97 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 *
 * membarrier system call
 */
#include "sched.h"

/*
 * Bitmask made from a "or" of all commands within enum membarrier_cmd,
 * except MEMBARRIER_CMD_QUERY.
 */
#ifdef CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE
#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK			\
	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE			\
	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE)
#else
#define MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK	0
#endif

#ifdef CONFIG_RSEQ
#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK		\
	(MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ			\
	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
#else
#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK	0
#endif

#define MEMBARRIER_CMD_BITMASK						\
	(MEMBARRIER_CMD_GLOBAL | MEMBARRIER_CMD_GLOBAL_EXPEDITED	\
	| MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED			\
	| MEMBARRIER_CMD_PRIVATE_EXPEDITED				\
	| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED			\
	| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK)

static void ipi_mb(void *info)
{
	smp_mb();	/* IPIs should be serializing but paranoid. */
}

static void ipi_rseq(void *info)
{
	rseq_preempt(current);
}

static void ipi_sync_rq_state(void *info)
{
	struct mm_struct *mm = (struct mm_struct *) info;

	if (current->mm != mm)
		return;
	this_cpu_write(runqueues.membarrier_state,
		       atomic_read(&mm->membarrier_state));
	/*
	 * Issue a memory barrier after setting
	 * MEMBARRIER_STATE_GLOBAL_EXPEDITED in the current runqueue to
	 * guarantee that no memory access following registration is reordered
	 * before registration.
	 */
	smp_mb();
}

void membarrier_exec_mmap(struct mm_struct *mm)
{
	/*
	 * Issue a memory barrier before clearing membarrier_state to
	 * guarantee that no memory access prior to exec is reordered after
	 * clearing this state.
	 */
	smp_mb();
	atomic_set(&mm->membarrier_state, 0);
	/*
	 * Keep the runqueue membarrier_state in sync with this mm
	 * membarrier_state.
	 */
	this_cpu_write(runqueues.membarrier_state, 0);
}

static int membarrier_global_expedited(void)
{
	int cpu;
	cpumask_var_t tmpmask;

	if (num_online_cpus() == 1)
		return 0;

	/*
	 * Matches memory barriers around rq->curr modification in
	 * scheduler.
	 */
	smp_mb();	/* system call entry is not a mb. */

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	cpus_read_lock();
	rcu_read_lock();
	for_each_online_cpu(cpu) {
		struct task_struct *p;

		/*
		 * Skipping the current CPU is OK even through we can be
		 * migrated at any point. The current CPU, at the point
		 * where we read raw_smp_processor_id(), is ensured to
		 * be in program order with respect to the caller
		 * thread. Therefore, we can skip this CPU from the
		 * iteration.
		 */
		if (cpu == raw_smp_processor_id())
			continue;

		if (!(READ_ONCE(cpu_rq(cpu)->membarrier_state) &
		    MEMBARRIER_STATE_GLOBAL_EXPEDITED))
			continue;

		/*
		 * Skip the CPU if it runs a kernel thread. The scheduler
		 * leaves the prior task mm in place as an optimization when
		 * scheduling a kthread.
		 */
		p = rcu_dereference(cpu_rq(cpu)->curr);
		if (p->flags & PF_KTHREAD)
			continue;

		__cpumask_set_cpu(cpu, tmpmask);
	}
	rcu_read_unlock();

	preempt_disable();
	smp_call_function_many(tmpmask, ipi_mb, NULL, 1);
	preempt_enable();

	free_cpumask_var(tmpmask);
	cpus_read_unlock();

	/*
	 * Memory barrier on the caller thread _after_ we finished
	 * waiting for the last IPI. Matches memory barriers around
	 * rq->curr modification in scheduler.
	 */
	smp_mb();	/* exit from system call is not a mb */
	return 0;
}

static int membarrier_private_expedited(int flags, int cpu_id)
{
	cpumask_var_t tmpmask;
	struct mm_struct *mm = current->mm;
	smp_call_func_t ipi_func = ipi_mb;

	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
			return -EINVAL;
		if (!(atomic_read(&mm->membarrier_state) &
		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY))
			return -EPERM;
	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
		if (!IS_ENABLED(CONFIG_RSEQ))
			return -EINVAL;
		if (!(atomic_read(&mm->membarrier_state) &
		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY))
			return -EPERM;
		ipi_func = ipi_rseq;
	} else {
		WARN_ON_ONCE(flags);
		if (!(atomic_read(&mm->membarrier_state) &
		      MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY))
			return -EPERM;
	}

	if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1)
		return 0;

	/*
	 * Matches memory barriers around rq->curr modification in
	 * scheduler.
	 */
	smp_mb();	/* system call entry is not a mb. */

	if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	cpus_read_lock();

	if (cpu_id >= 0) {
		struct task_struct *p;

		if (cpu_id >= nr_cpu_ids || !cpu_online(cpu_id))
			goto out;
		if (cpu_id == raw_smp_processor_id())
			goto out;
		rcu_read_lock();
		p = rcu_dereference(cpu_rq(cpu_id)->curr);
		if (!p || p->mm != mm) {
			rcu_read_unlock();
			goto out;
		}
		rcu_read_unlock();
	} else {
		int cpu;

		rcu_read_lock();
		for_each_online_cpu(cpu) {
			struct task_struct *p;

			/*
			 * Skipping the current CPU is OK even through we can be
			 * migrated at any point. The current CPU, at the point
			 * where we read raw_smp_processor_id(), is ensured to
			 * be in program order with respect to the caller
			 * thread. Therefore, we can skip this CPU from the
			 * iteration.
			 */
			if (cpu == raw_smp_processor_id())
				continue;
			p = rcu_dereference(cpu_rq(cpu)->curr);
			if (p && p->mm == mm)
				__cpumask_set_cpu(cpu, tmpmask);
		}
		rcu_read_unlock();
	}

	preempt_disable();
	if (cpu_id >= 0)
		smp_call_function_single(cpu_id, ipi_func, NULL, 1);
	else
		smp_call_function_many(tmpmask, ipi_func, NULL, 1);
	preempt_enable();

out:
	if (cpu_id < 0)
		free_cpumask_var(tmpmask);
	cpus_read_unlock();

	/*
	 * Memory barrier on the caller thread _after_ we finished
	 * waiting for the last IPI. Matches memory barriers around
	 * rq->curr modification in scheduler.
	 */
	smp_mb();	/* exit from system call is not a mb */

	return 0;
}

static int sync_runqueues_membarrier_state(struct mm_struct *mm)
{
	int membarrier_state = atomic_read(&mm->membarrier_state);
	cpumask_var_t tmpmask;
	int cpu;

	if (atomic_read(&mm->mm_users) == 1 || num_online_cpus() == 1) {
		this_cpu_write(runqueues.membarrier_state, membarrier_state);

		/*
		 * For single mm user, we can simply issue a memory barrier
		 * after setting MEMBARRIER_STATE_GLOBAL_EXPEDITED in the
		 * mm and in the current runqueue to guarantee that no memory
		 * access following registration is reordered before
		 * registration.
		 */
		smp_mb();
		return 0;
	}

	if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
		return -ENOMEM;

	/*
	 * For mm with multiple users, we need to ensure all future
	 * scheduler executions will observe @mm's new membarrier
	 * state.
	 */
	synchronize_rcu();

	/*
	 * For each cpu runqueue, if the task's mm match @mm, ensure that all
	 * @mm's membarrier state set bits are also set in in the runqueue's
	 * membarrier state. This ensures that a runqueue scheduling
	 * between threads which are users of @mm has its membarrier state
	 * updated.
	 */
	cpus_read_lock();
	rcu_read_lock();
	for_each_online_cpu(cpu) {
		struct rq *rq = cpu_rq(cpu);
		struct task_struct *p;

		p = rcu_dereference(rq->curr);
		if (p && p->mm == mm)
			__cpumask_set_cpu(cpu, tmpmask);
	}
	rcu_read_unlock();

	preempt_disable();
	smp_call_function_many(tmpmask, ipi_sync_rq_state, mm, 1);
	preempt_enable();

	free_cpumask_var(tmpmask);
	cpus_read_unlock();

	return 0;
}

static int membarrier_register_global_expedited(void)
{
	struct task_struct *p = current;
	struct mm_struct *mm = p->mm;
	int ret;

	if (atomic_read(&mm->membarrier_state) &
	    MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY)
		return 0;
	atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED, &mm->membarrier_state);
	ret = sync_runqueues_membarrier_state(mm);
	if (ret)
		return ret;
	atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
		  &mm->membarrier_state);

	return 0;
}

static int membarrier_register_private_expedited(int flags)
{
	struct task_struct *p = current;
	struct mm_struct *mm = p->mm;
	int ready_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
	    set_state = MEMBARRIER_STATE_PRIVATE_EXPEDITED,
	    ret;

	if (flags == MEMBARRIER_FLAG_SYNC_CORE) {
		if (!IS_ENABLED(CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE))
			return -EINVAL;
		ready_state =
			MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY;
	} else if (flags == MEMBARRIER_FLAG_RSEQ) {
		if (!IS_ENABLED(CONFIG_RSEQ))
			return -EINVAL;
		ready_state =
			MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY;
	} else {
		WARN_ON_ONCE(flags);
	}

	/*
	 * We need to consider threads belonging to different thread
	 * groups, which use the same mm. (CLONE_VM but not
	 * CLONE_THREAD).
	 */
	if ((atomic_read(&mm->membarrier_state) & ready_state) == ready_state)
		return 0;
	if (flags & MEMBARRIER_FLAG_SYNC_CORE)
		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE;
	if (flags & MEMBARRIER_FLAG_RSEQ)
		set_state |= MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ;
	atomic_or(set_state, &mm->membarrier_state);
	ret = sync_runqueues_membarrier_state(mm);
	if (ret)
		return ret;
	atomic_or(ready_state, &mm->membarrier_state);

	return 0;
}

/**
 * sys_membarrier - issue memory barriers on a set of threads
 * @cmd:    Takes command values defined in enum membarrier_cmd.
 * @flags:  Currently needs to be 0 for all commands other than
 *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: in the latter
 *          case it can be MEMBARRIER_CMD_FLAG_CPU, indicating that @cpu_id
 *          contains the CPU on which to interrupt (= restart)
 *          the RSEQ critical section.
 * @cpu_id: if @flags == MEMBARRIER_CMD_FLAG_CPU, indicates the cpu on which
 *          RSEQ CS should be interrupted (@cmd must be
 *          MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ).
 *
 * If this system call is not implemented, -ENOSYS is returned. If the
 * command specified does not exist, not available on the running
 * kernel, or if the command argument is invalid, this system call
 * returns -EINVAL. For a given command, with flags argument set to 0,
 * if this system call returns -ENOSYS or -EINVAL, it is guaranteed to
 * always return the same value until reboot. In addition, it can return
 * -ENOMEM if there is not enough memory available to perform the system
 * call.
 *
 * All memory accesses performed in program order from each targeted thread
 * is guaranteed to be ordered with respect to sys_membarrier(). If we use
 * the semantic "barrier()" to represent a compiler barrier forcing memory
 * accesses to be performed in program order across the barrier, and
 * smp_mb() to represent explicit memory barriers forcing full memory
 * ordering across the barrier, we have the following ordering table for
 * each pair of barrier(), sys_membarrier() and smp_mb():
 *
 * The pair ordering is detailed as (O: ordered, X: not ordered):
 *
 *                        barrier()   smp_mb() sys_membarrier()
 *        barrier()          X           X            O
 *        smp_mb()           X           O            O
 *        sys_membarrier()   O           O            O
 */
SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
{
	switch (cmd) {
	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
		if (unlikely(flags && flags != MEMBARRIER_CMD_FLAG_CPU))
			return -EINVAL;
		break;
	default:
		if (unlikely(flags))
			return -EINVAL;
	}

	if (!(flags & MEMBARRIER_CMD_FLAG_CPU))
		cpu_id = -1;

	switch (cmd) {
	case MEMBARRIER_CMD_QUERY:
	{
		int cmd_mask = MEMBARRIER_CMD_BITMASK;

		if (tick_nohz_full_enabled())
			cmd_mask &= ~MEMBARRIER_CMD_GLOBAL;
		return cmd_mask;
	}
	case MEMBARRIER_CMD_GLOBAL:
		/* MEMBARRIER_CMD_GLOBAL is not compatible with nohz_full. */
		if (tick_nohz_full_enabled())
			return -EINVAL;
		if (num_online_cpus() > 1)
			synchronize_rcu();
		return 0;
	case MEMBARRIER_CMD_GLOBAL_EXPEDITED:
		return membarrier_global_expedited();
	case MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED:
		return membarrier_register_global_expedited();
	case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
		return membarrier_private_expedited(0, cpu_id);
	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
		return membarrier_register_private_expedited(0);
	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE:
		return membarrier_private_expedited(MEMBARRIER_FLAG_SYNC_CORE, cpu_id);
	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE:
		return membarrier_register_private_expedited(MEMBARRIER_FLAG_SYNC_CORE);
	case MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ:
		return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
	case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
		return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
	default:
		return -EINVAL;
	}
}