summaryrefslogtreecommitdiff
path: root/include/linux/preempt.h
blob: 97ba7c920653d3b10ed90a4055615cc318fcde23 (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_PREEMPT_H
#define __LINUX_PREEMPT_H

/*
 * include/linux/preempt.h - macros for accessing and manipulating
 * preempt_count (used for kernel preemption, interrupt count, etc.)
 */

#include <linux/linkage.h>
#include <linux/list.h>

/*
 * We put the hardirq and softirq counter into the preemption
 * counter. The bitmask has the following meaning:
 *
 * - bits 0-7 are the preemption count (max preemption depth: 256)
 * - bits 8-15 are the softirq count (max # of softirqs: 256)
 *
 * The hardirq count could in theory be the same as the number of
 * interrupts in the system, but we run all interrupt handlers with
 * interrupts disabled, so we cannot have nesting interrupts. Though
 * there are a few palaeontologic drivers which reenable interrupts in
 * the handler, so we need more than one bit here.
 *
 *         PREEMPT_MASK:	0x000000ff
 *         SOFTIRQ_MASK:	0x0000ff00
 *         HARDIRQ_MASK:	0x000f0000
 *             NMI_MASK:	0x00f00000
 * PREEMPT_NEED_RESCHED:	0x80000000
 */
#define PREEMPT_BITS	8
#define SOFTIRQ_BITS	8
#define HARDIRQ_BITS	4
#define NMI_BITS	4

#define PREEMPT_SHIFT	0
#define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
#define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)

#define __IRQ_MASK(x)	((1UL << (x))-1)

#define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
#define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
#define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)

#define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
#define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
#define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
#define NMI_OFFSET	(1UL << NMI_SHIFT)

#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)

#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)

/*
 * Disable preemption until the scheduler is running -- use an unconditional
 * value so that it also works on !PREEMPT_COUNT kernels.
 *
 * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
 */
#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET

/*
 * Initial preempt_count value; reflects the preempt_count schedule invariant
 * which states that during context switches:
 *
 *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
 *
 * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
 * Note: See finish_task_switch().
 */
#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)

/* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */
#include <asm/preempt.h>

#define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
				 | NMI_MASK))

/*
 * Are we doing bottom half or hardware interrupt processing?
 *
 * in_irq()       - We're in (hard) IRQ context
 * in_softirq()   - We have BH disabled, or are processing softirqs
 * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled
 * in_serving_softirq() - We're in softirq context
 * in_nmi()       - We're in NMI context
 * in_task()	  - We're in task context
 *
 * Note: due to the BH disabled confusion: in_softirq(),in_interrupt() really
 *       should not be used in new code.
 */
#define in_irq()		(hardirq_count())
#define in_softirq()		(softirq_count())
#define in_interrupt()		(irq_count())
#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
#define in_nmi()		(preempt_count() & NMI_MASK)
#define in_task()		(!(preempt_count() & \
				   (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))

/*
 * The preempt_count offset after preempt_disable();
 */
#if defined(CONFIG_PREEMPT_COUNT)
# define PREEMPT_DISABLE_OFFSET	PREEMPT_OFFSET
#else
# define PREEMPT_DISABLE_OFFSET	0
#endif

/*
 * The preempt_count offset after spin_lock()
 */
#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET

/*
 * The preempt_count offset needed for things like:
 *
 *  spin_lock_bh()
 *
 * Which need to disable both preemption (CONFIG_PREEMPT_COUNT) and
 * softirqs, such that unlock sequences of:
 *
 *  spin_unlock();
 *  local_bh_enable();
 *
 * Work as expected.
 */
#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)

/*
 * Are we running in atomic context?  WARNING: this macro cannot
 * always detect atomic context; in particular, it cannot know about
 * held spinlocks in non-preemptible kernels.  Thus it should not be
 * used in the general case to determine whether sleeping is possible.
 * Do not use in_atomic() in driver code.
 */
#define in_atomic()	(preempt_count() != 0)

/*
 * Check whether we were atomic before we did preempt_disable():
 * (used by the scheduler)
 */
#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)

#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE)
extern void preempt_count_add(int val);
extern void preempt_count_sub(int val);
#define preempt_count_dec_and_test() \
	({ preempt_count_sub(1); should_resched(0); })
#else
#define preempt_count_add(val)	__preempt_count_add(val)
#define preempt_count_sub(val)	__preempt_count_sub(val)
#define preempt_count_dec_and_test() __preempt_count_dec_and_test()
#endif

#define __preempt_count_inc() __preempt_count_add(1)
#define __preempt_count_dec() __preempt_count_sub(1)

#define preempt_count_inc() preempt_count_add(1)
#define preempt_count_dec() preempt_count_sub(1)

#ifdef CONFIG_PREEMPT_COUNT

#define preempt_disable() \
do { \
	preempt_count_inc(); \
	barrier(); \
} while (0)

#define sched_preempt_enable_no_resched() \
do { \
	barrier(); \
	preempt_count_dec(); \
} while (0)

#define preempt_enable_no_resched() sched_preempt_enable_no_resched()

#define preemptible()	(preempt_count() == 0 && !irqs_disabled())

#ifdef CONFIG_PREEMPTION
#define preempt_enable() \
do { \
	barrier(); \
	if (unlikely(preempt_count_dec_and_test())) \
		__preempt_schedule(); \
} while (0)

#define preempt_enable_notrace() \
do { \
	barrier(); \
	if (unlikely(__preempt_count_dec_and_test())) \
		__preempt_schedule_notrace(); \
} while (0)

#define preempt_check_resched() \
do { \
	if (should_resched(0)) \
		__preempt_schedule(); \
} while (0)

#else /* !CONFIG_PREEMPTION */
#define preempt_enable() \
do { \
	barrier(); \
	preempt_count_dec(); \
} while (0)

#define preempt_enable_notrace() \
do { \
	barrier(); \
	__preempt_count_dec(); \
} while (0)

#define preempt_check_resched() do { } while (0)
#endif /* CONFIG_PREEMPTION */

#define preempt_disable_notrace() \
do { \
	__preempt_count_inc(); \
	barrier(); \
} while (0)

#define preempt_enable_no_resched_notrace() \
do { \
	barrier(); \
	__preempt_count_dec(); \
} while (0)

#else /* !CONFIG_PREEMPT_COUNT */

/*
 * Even if we don't have any preemption, we need preempt disable/enable
 * to be barriers, so that we don't have things like get_user/put_user
 * that can cause faults and scheduling migrate into our preempt-protected
 * region.
 */
#define preempt_disable()			barrier()
#define sched_preempt_enable_no_resched()	barrier()
#define preempt_enable_no_resched()		barrier()
#define preempt_enable()			barrier()
#define preempt_check_resched()			do { } while (0)

#define preempt_disable_notrace()		barrier()
#define preempt_enable_no_resched_notrace()	barrier()
#define preempt_enable_notrace()		barrier()
#define preemptible()				0

#endif /* CONFIG_PREEMPT_COUNT */

#ifdef MODULE
/*
 * Modules have no business playing preemption tricks.
 */
#undef sched_preempt_enable_no_resched
#undef preempt_enable_no_resched
#undef preempt_enable_no_resched_notrace
#undef preempt_check_resched
#endif

#define preempt_set_need_resched() \
do { \
	set_preempt_need_resched(); \
} while (0)
#define preempt_fold_need_resched() \
do { \
	if (tif_need_resched()) \
		set_preempt_need_resched(); \
} while (0)

#ifdef CONFIG_PREEMPT_NOTIFIERS

struct preempt_notifier;

/**
 * preempt_ops - notifiers called when a task is preempted and rescheduled
 * @sched_in: we're about to be rescheduled:
 *    notifier: struct preempt_notifier for the task being scheduled
 *    cpu:  cpu we're scheduled on
 * @sched_out: we've just been preempted
 *    notifier: struct preempt_notifier for the task being preempted
 *    next: the task that's kicking us out
 *
 * Please note that sched_in and out are called under different
 * contexts.  sched_out is called with rq lock held and irq disabled
 * while sched_in is called without rq lock and irq enabled.  This
 * difference is intentional and depended upon by its users.
 */
struct preempt_ops {
	void (*sched_in)(struct preempt_notifier *notifier, int cpu);
	void (*sched_out)(struct preempt_notifier *notifier,
			  struct task_struct *next);
};

/**
 * preempt_notifier - key for installing preemption notifiers
 * @link: internal use
 * @ops: defines the notifier functions to be called
 *
 * Usually used in conjunction with container_of().
 */
struct preempt_notifier {
	struct hlist_node link;
	struct preempt_ops *ops;
};

void preempt_notifier_inc(void);
void preempt_notifier_dec(void);
void preempt_notifier_register(struct preempt_notifier *notifier);
void preempt_notifier_unregister(struct preempt_notifier *notifier);

static inline void preempt_notifier_init(struct preempt_notifier *notifier,
				     struct preempt_ops *ops)
{
	INIT_HLIST_NODE(&notifier->link);
	notifier->ops = ops;
}

#endif

#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)

/*
 * Migrate-Disable and why it is (strongly) undesired.
 *
 * The premise of the Real-Time schedulers we have on Linux
 * (SCHED_FIFO/SCHED_DEADLINE) is that M CPUs can/will run M tasks
 * concurrently, provided there are sufficient runnable tasks, also known as
 * work-conserving. For instance SCHED_DEADLINE tries to schedule the M
 * earliest deadline threads, and SCHED_FIFO the M highest priority threads.
 *
 * The correctness of various scheduling models depends on this, but is it
 * broken by migrate_disable() that doesn't imply preempt_disable(). Where
 * preempt_disable() implies an immediate priority ceiling, preemptible
 * migrate_disable() allows nesting.
 *
 * The worst case is that all tasks preempt one another in a migrate_disable()
 * region and stack on a single CPU. This then reduces the available bandwidth
 * to a single CPU. And since Real-Time schedulability theory considers the
 * Worst-Case only, all Real-Time analysis shall revert to single-CPU
 * (instantly solving the SMP analysis problem).
 *
 *
 * The reason we have it anyway.
 *
 * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a
 * number of primitives into becoming preemptible, they would also allow
 * migration. This turns out to break a bunch of per-cpu usage. To this end,
 * all these primitives employ migirate_disable() to restore this implicit
 * assumption.
 *
 * This is a 'temporary' work-around at best. The correct solution is getting
 * rid of the above assumptions and reworking the code to employ explicit
 * per-cpu locking or short preempt-disable regions.
 *
 * The end goal must be to get rid of migrate_disable(), alternatively we need
 * a schedulability theory that does not depend on abritrary migration.
 *
 *
 * Notes on the implementation.
 *
 * The implementation is particularly tricky since existing code patterns
 * dictate neither migrate_disable() nor migrate_enable() is allowed to block.
 * This means that it cannot use cpus_read_lock() to serialize against hotplug,
 * nor can it easily migrate itself into a pending affinity mask change on
 * migrate_enable().
 *
 *
 * Note: even non-work-conserving schedulers like semi-partitioned depends on
 *       migration, so migrate_disable() is not only a problem for
 *       work-conserving schedulers.
 *
 */
extern void migrate_disable(void);
extern void migrate_enable(void);

#elif defined(CONFIG_PREEMPT_RT)

static inline void migrate_disable(void) { }
static inline void migrate_enable(void) { }

#else /* !CONFIG_PREEMPT_RT */

/**
 * migrate_disable - Prevent migration of the current task
 *
 * Maps to preempt_disable() which also disables preemption. Use
 * migrate_disable() to annotate that the intent is to prevent migration,
 * but not necessarily preemption.
 *
 * Can be invoked nested like preempt_disable() and needs the corresponding
 * number of migrate_enable() invocations.
 */
static __always_inline void migrate_disable(void)
{
	preempt_disable();
}

/**
 * migrate_enable - Allow migration of the current task
 *
 * Counterpart to migrate_disable().
 *
 * As migrate_disable() can be invoked nested, only the outermost invocation
 * reenables migration.
 *
 * Currently mapped to preempt_enable().
 */
static __always_inline void migrate_enable(void)
{
	preempt_enable();
}

#endif /* CONFIG_SMP && CONFIG_PREEMPT_RT */

#endif /* __LINUX_PREEMPT_H */