Blame view

kernel/posix-cpu-timers.c 45.1 KB
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1
2
3
4
5
6
  /*
   * Implement CPU time clocks for the POSIX clock interface.
   */
  
  #include <linux/sched.h>
  #include <linux/posix-timers.h>
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
7
  #include <linux/errno.h>
f8bd2258e   Roman Zippel   remove div_long_l...
8
9
  #include <linux/math64.h>
  #include <asm/uaccess.h>
bb34d92f6   Frank Mayhar   timers: fix itime...
10
  #include <linux/kernel_stat.h>
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
11

f06febc96   Frank Mayhar   timers: fix itime...
12
  /*
f06febc96   Frank Mayhar   timers: fix itime...
13
14
15
16
17
18
19
20
   * Called after updating RLIMIT_CPU to set timer expiration if necessary.
   */
  void update_rlimit_cpu(unsigned long rlim_new)
  {
  	cputime_t cputime;
  
  	cputime = secs_to_cputime(rlim_new);
  	if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
8f2e58656   Oleg Nesterov   posix-timers: fix...
21
  	    cputime_gt(current->signal->it_prof_expires, cputime)) {
f06febc96   Frank Mayhar   timers: fix itime...
22
23
24
25
26
  		spin_lock_irq(&current->sighand->siglock);
  		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
  		spin_unlock_irq(&current->sighand->siglock);
  	}
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
27
  static int check_clock(const clockid_t which_clock)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
28
29
30
31
32
33
34
35
36
37
38
39
  {
  	int error = 0;
  	struct task_struct *p;
  	const pid_t pid = CPUCLOCK_PID(which_clock);
  
  	if (CPUCLOCK_WHICH(which_clock) >= CPUCLOCK_MAX)
  		return -EINVAL;
  
  	if (pid == 0)
  		return 0;
  
  	read_lock(&tasklist_lock);
8dc86af00   Pavel Emelyanov   Use find_task_by_...
40
  	p = find_task_by_vpid(pid);
bac0abd61   Pavel Emelyanov   Isolate some expl...
41
42
  	if (!p || !(CPUCLOCK_PERTHREAD(which_clock) ?
  		   same_thread_group(p, current) : thread_group_leader(p))) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
43
44
45
46
47
48
49
50
  		error = -EINVAL;
  	}
  	read_unlock(&tasklist_lock);
  
  	return error;
  }
  
  static inline union cpu_time_count
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
51
  timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
52
53
54
55
  {
  	union cpu_time_count ret;
  	ret.sched = 0;		/* high half always zero when .cpu used */
  	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
ee500f274   Oleg Nesterov   [PATCH] fix 32bit...
56
  		ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
57
58
59
60
61
  	} else {
  		ret.cpu = timespec_to_cputime(tp);
  	}
  	return ret;
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
62
  static void sample_to_timespec(const clockid_t which_clock,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
63
64
65
  			       union cpu_time_count cpu,
  			       struct timespec *tp)
  {
f8bd2258e   Roman Zippel   remove div_long_l...
66
67
68
  	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
  		*tp = ns_to_timespec(cpu.sched);
  	else
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
69
  		cputime_to_timespec(cpu.cpu, tp);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
70
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
71
  static inline int cpu_time_before(const clockid_t which_clock,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
72
73
74
75
76
77
78
79
80
  				  union cpu_time_count now,
  				  union cpu_time_count then)
  {
  	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
  		return now.sched < then.sched;
  	}  else {
  		return cputime_lt(now.cpu, then.cpu);
  	}
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
81
  static inline void cpu_time_add(const clockid_t which_clock,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
82
83
84
85
86
87
88
89
90
  				union cpu_time_count *acc,
  			        union cpu_time_count val)
  {
  	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
  		acc->sched += val.sched;
  	}  else {
  		acc->cpu = cputime_add(acc->cpu, val.cpu);
  	}
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
91
  static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
92
93
94
95
96
97
98
99
100
101
102
103
  						union cpu_time_count a,
  						union cpu_time_count b)
  {
  	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
  		a.sched -= b.sched;
  	}  else {
  		a.cpu = cputime_sub(a.cpu, b.cpu);
  	}
  	return a;
  }
  
  /*
ac08c2649   Thomas Gleixner   [PATCH] posix-cpu...
104
105
106
107
108
109
110
111
112
113
114
115
116
   * Divide and limit the result to res >= 1
   *
   * This is necessary to prevent signal delivery starvation, when the result of
   * the division would be rounded down to 0.
   */
  static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div)
  {
  	cputime_t res = cputime_div(time, div);
  
  	return max_t(cputime_t, res, 1);
  }
  
  /*
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
117
118
119
   * Update expiry time from increment, and increase overrun count,
   * given the current clock sample.
   */
7a4ed937a   Oleg Nesterov   [PATCH] Fix cpu t...
120
  static void bump_cpu_timer(struct k_itimer *timer,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
  				  union cpu_time_count now)
  {
  	int i;
  
  	if (timer->it.cpu.incr.sched == 0)
  		return;
  
  	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
  		unsigned long long delta, incr;
  
  		if (now.sched < timer->it.cpu.expires.sched)
  			return;
  		incr = timer->it.cpu.incr.sched;
  		delta = now.sched + incr - timer->it.cpu.expires.sched;
  		/* Don't use (incr*2 < delta), incr*2 might overflow. */
  		for (i = 0; incr < delta - incr; i++)
  			incr = incr << 1;
  		for (; i >= 0; incr >>= 1, i--) {
7a4ed937a   Oleg Nesterov   [PATCH] Fix cpu t...
139
  			if (delta < incr)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
  				continue;
  			timer->it.cpu.expires.sched += incr;
  			timer->it_overrun += 1 << i;
  			delta -= incr;
  		}
  	} else {
  		cputime_t delta, incr;
  
  		if (cputime_lt(now.cpu, timer->it.cpu.expires.cpu))
  			return;
  		incr = timer->it.cpu.incr.cpu;
  		delta = cputime_sub(cputime_add(now.cpu, incr),
  				    timer->it.cpu.expires.cpu);
  		/* Don't use (incr*2 < delta), incr*2 might overflow. */
  		for (i = 0; cputime_lt(incr, cputime_sub(delta, incr)); i++)
  			     incr = cputime_add(incr, incr);
  		for (; i >= 0; incr = cputime_halve(incr), i--) {
7a4ed937a   Oleg Nesterov   [PATCH] Fix cpu t...
157
  			if (cputime_lt(delta, incr))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
  				continue;
  			timer->it.cpu.expires.cpu =
  				cputime_add(timer->it.cpu.expires.cpu, incr);
  			timer->it_overrun += 1 << i;
  			delta = cputime_sub(delta, incr);
  		}
  	}
  }
  
  static inline cputime_t prof_ticks(struct task_struct *p)
  {
  	return cputime_add(p->utime, p->stime);
  }
  static inline cputime_t virt_ticks(struct task_struct *p)
  {
  	return p->utime;
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
175

a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
176
  int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
  {
  	int error = check_clock(which_clock);
  	if (!error) {
  		tp->tv_sec = 0;
  		tp->tv_nsec = ((NSEC_PER_SEC + HZ - 1) / HZ);
  		if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
  			/*
  			 * If sched_clock is using a cycle counter, we
  			 * don't have any idea of its true resolution
  			 * exported, but it is much more than 1s/HZ.
  			 */
  			tp->tv_nsec = 1;
  		}
  	}
  	return error;
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
193
  int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
  {
  	/*
  	 * You can never reset a CPU clock, but we check for other errors
  	 * in the call before failing with EPERM.
  	 */
  	int error = check_clock(which_clock);
  	if (error == 0) {
  		error = -EPERM;
  	}
  	return error;
  }
  
  
  /*
   * Sample a per-thread clock for the given task.
   */
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
210
  static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
211
212
213
214
215
216
217
218
219
220
221
222
  			    union cpu_time_count *cpu)
  {
  	switch (CPUCLOCK_WHICH(which_clock)) {
  	default:
  		return -EINVAL;
  	case CPUCLOCK_PROF:
  		cpu->cpu = prof_ticks(p);
  		break;
  	case CPUCLOCK_VIRT:
  		cpu->cpu = virt_ticks(p);
  		break;
  	case CPUCLOCK_SCHED:
c5f8d9958   Hidetoshi Seto   posixtimers, sche...
223
  		cpu->sched = task_sched_runtime(p);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
224
225
226
227
  		break;
  	}
  	return 0;
  }
4cd4c1b40   Peter Zijlstra   timers: split pro...
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
  void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
  {
  	struct sighand_struct *sighand;
  	struct signal_struct *sig;
  	struct task_struct *t;
  
  	*times = INIT_CPUTIME;
  
  	rcu_read_lock();
  	sighand = rcu_dereference(tsk->sighand);
  	if (!sighand)
  		goto out;
  
  	sig = tsk->signal;
  
  	t = tsk;
  	do {
  		times->utime = cputime_add(times->utime, t->utime);
  		times->stime = cputime_add(times->stime, t->stime);
  		times->sum_exec_runtime += t->se.sum_exec_runtime;
  
  		t = next_thread(t);
  	} while (t != tsk);
  
  	times->utime = cputime_add(times->utime, sig->utime);
  	times->stime = cputime_add(times->stime, sig->stime);
  	times->sum_exec_runtime += sig->sum_sched_runtime;
  out:
  	rcu_read_unlock();
  }
4da94d49b   Peter Zijlstra   timers: fix TIMER...
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
  static void update_gt_cputime(struct task_cputime *a, struct task_cputime *b)
  {
  	if (cputime_gt(b->utime, a->utime))
  		a->utime = b->utime;
  
  	if (cputime_gt(b->stime, a->stime))
  		a->stime = b->stime;
  
  	if (b->sum_exec_runtime > a->sum_exec_runtime)
  		a->sum_exec_runtime = b->sum_exec_runtime;
  }
  
  void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
  {
  	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
  	struct task_cputime sum;
  	unsigned long flags;
  
  	spin_lock_irqsave(&cputimer->lock, flags);
  	if (!cputimer->running) {
  		cputimer->running = 1;
  		/*
  		 * The POSIX timer interface allows for absolute time expiry
  		 * values through the TIMER_ABSTIME flag, therefore we have
  		 * to synchronize the timer to the clock every time we start
  		 * it.
  		 */
  		thread_group_cputime(tsk, &sum);
  		update_gt_cputime(&cputimer->cputime, &sum);
  	}
  	*times = cputimer->cputime;
  	spin_unlock_irqrestore(&cputimer->lock, flags);
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
291
292
293
  /*
   * Sample a process (thread group) clock for the given group_leader task.
   * Must be called with tasklist_lock held for reading.
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
294
   */
bb34d92f6   Frank Mayhar   timers: fix itime...
295
296
297
  static int cpu_clock_sample_group(const clockid_t which_clock,
  				  struct task_struct *p,
  				  union cpu_time_count *cpu)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
298
  {
f06febc96   Frank Mayhar   timers: fix itime...
299
  	struct task_cputime cputime;
eccdaeafa   Petr Tesarik   posix-cpu-timers:...
300
  	switch (CPUCLOCK_WHICH(which_clock)) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
301
302
303
  	default:
  		return -EINVAL;
  	case CPUCLOCK_PROF:
c5f8d9958   Hidetoshi Seto   posixtimers, sche...
304
  		thread_group_cputime(p, &cputime);
f06febc96   Frank Mayhar   timers: fix itime...
305
  		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
306
307
  		break;
  	case CPUCLOCK_VIRT:
c5f8d9958   Hidetoshi Seto   posixtimers, sche...
308
  		thread_group_cputime(p, &cputime);
f06febc96   Frank Mayhar   timers: fix itime...
309
  		cpu->cpu = cputime.utime;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
310
311
  		break;
  	case CPUCLOCK_SCHED:
c5f8d9958   Hidetoshi Seto   posixtimers, sche...
312
  		cpu->sched = thread_group_sched_runtime(p);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
313
314
315
316
  		break;
  	}
  	return 0;
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
317

a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
318
  int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  {
  	const pid_t pid = CPUCLOCK_PID(which_clock);
  	int error = -EINVAL;
  	union cpu_time_count rtn;
  
  	if (pid == 0) {
  		/*
  		 * Special case constant value for our own clocks.
  		 * We don't have to do any lookup to find ourselves.
  		 */
  		if (CPUCLOCK_PERTHREAD(which_clock)) {
  			/*
  			 * Sampling just ourselves we can do with no locking.
  			 */
  			error = cpu_clock_sample(which_clock,
  						 current, &rtn);
  		} else {
  			read_lock(&tasklist_lock);
  			error = cpu_clock_sample_group(which_clock,
  						       current, &rtn);
  			read_unlock(&tasklist_lock);
  		}
  	} else {
  		/*
  		 * Find the given PID, and validate that the caller
  		 * should be able to see it.
  		 */
  		struct task_struct *p;
1f2ea0837   Paul E. McKenney   [PATCH] posix tim...
347
  		rcu_read_lock();
8dc86af00   Pavel Emelyanov   Use find_task_by_...
348
  		p = find_task_by_vpid(pid);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
349
350
  		if (p) {
  			if (CPUCLOCK_PERTHREAD(which_clock)) {
bac0abd61   Pavel Emelyanov   Isolate some expl...
351
  				if (same_thread_group(p, current)) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
352
353
354
  					error = cpu_clock_sample(which_clock,
  								 p, &rtn);
  				}
1f2ea0837   Paul E. McKenney   [PATCH] posix tim...
355
356
  			} else {
  				read_lock(&tasklist_lock);
bac0abd61   Pavel Emelyanov   Isolate some expl...
357
  				if (thread_group_leader(p) && p->signal) {
1f2ea0837   Paul E. McKenney   [PATCH] posix tim...
358
359
360
361
362
  					error =
  					    cpu_clock_sample_group(which_clock,
  							           p, &rtn);
  				}
  				read_unlock(&tasklist_lock);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
363
364
  			}
  		}
1f2ea0837   Paul E. McKenney   [PATCH] posix tim...
365
  		rcu_read_unlock();
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  	}
  
  	if (error)
  		return error;
  	sample_to_timespec(which_clock, rtn, tp);
  	return 0;
  }
  
  
  /*
   * Validate the clockid_t for a new CPU-clock timer, and initialize the timer.
   * This is called from sys_timer_create with the new timer already locked.
   */
  int posix_cpu_timer_create(struct k_itimer *new_timer)
  {
  	int ret = 0;
  	const pid_t pid = CPUCLOCK_PID(new_timer->it_clock);
  	struct task_struct *p;
  
  	if (CPUCLOCK_WHICH(new_timer->it_clock) >= CPUCLOCK_MAX)
  		return -EINVAL;
  
  	INIT_LIST_HEAD(&new_timer->it.cpu.entry);
  	new_timer->it.cpu.incr.sched = 0;
  	new_timer->it.cpu.expires.sched = 0;
  
  	read_lock(&tasklist_lock);
  	if (CPUCLOCK_PERTHREAD(new_timer->it_clock)) {
  		if (pid == 0) {
  			p = current;
  		} else {
8dc86af00   Pavel Emelyanov   Use find_task_by_...
397
  			p = find_task_by_vpid(pid);
bac0abd61   Pavel Emelyanov   Isolate some expl...
398
  			if (p && !same_thread_group(p, current))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
399
400
401
402
403
404
  				p = NULL;
  		}
  	} else {
  		if (pid == 0) {
  			p = current->group_leader;
  		} else {
8dc86af00   Pavel Emelyanov   Use find_task_by_...
405
  			p = find_task_by_vpid(pid);
bac0abd61   Pavel Emelyanov   Isolate some expl...
406
  			if (p && !thread_group_leader(p))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
  				p = NULL;
  		}
  	}
  	new_timer->it.cpu.task = p;
  	if (p) {
  		get_task_struct(p);
  	} else {
  		ret = -EINVAL;
  	}
  	read_unlock(&tasklist_lock);
  
  	return ret;
  }
  
  /*
   * Clean up a CPU-clock timer that is about to be destroyed.
   * This is called from timer deletion with the timer already locked.
   * If we return TIMER_RETRY, it's necessary to release the timer's lock
   * and try again.  (This happens when the timer is in the middle of firing.)
   */
  int posix_cpu_timer_del(struct k_itimer *timer)
  {
  	struct task_struct *p = timer->it.cpu.task;
108150ea7   Oleg Nesterov   [PATCH] posix-tim...
430
  	int ret = 0;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
431

108150ea7   Oleg Nesterov   [PATCH] posix-tim...
432
  	if (likely(p != NULL)) {
9465bee86   Linus Torvalds   Revert "Fix cpu t...
433
434
435
436
437
438
439
440
  		read_lock(&tasklist_lock);
  		if (unlikely(p->signal == NULL)) {
  			/*
  			 * We raced with the reaping of the task.
  			 * The deletion should have cleared us off the list.
  			 */
  			BUG_ON(!list_empty(&timer->it.cpu.entry));
  		} else {
9465bee86   Linus Torvalds   Revert "Fix cpu t...
441
  			spin_lock(&p->sighand->siglock);
108150ea7   Oleg Nesterov   [PATCH] posix-tim...
442
443
444
445
  			if (timer->it.cpu.firing)
  				ret = TIMER_RETRY;
  			else
  				list_del(&timer->it.cpu.entry);
9465bee86   Linus Torvalds   Revert "Fix cpu t...
446
447
448
  			spin_unlock(&p->sighand->siglock);
  		}
  		read_unlock(&tasklist_lock);
108150ea7   Oleg Nesterov   [PATCH] posix-tim...
449
450
451
  
  		if (!ret)
  			put_task_struct(p);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
452
  	}
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
453

108150ea7   Oleg Nesterov   [PATCH] posix-tim...
454
  	return ret;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
455
456
457
458
459
460
461
462
463
464
  }
  
  /*
   * Clean out CPU timers still ticking when a thread exited.  The task
   * pointer is cleared, and the expiry time is replaced with the residual
   * time for later timer_gettime calls to return.
   * This must be called with the siglock held.
   */
  static void cleanup_timers(struct list_head *head,
  			   cputime_t utime, cputime_t stime,
41b86e9c5   Ingo Molnar   sched: make posix...
465
  			   unsigned long long sum_exec_runtime)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
466
467
468
469
470
  {
  	struct cpu_timer_list *timer, *next;
  	cputime_t ptime = cputime_add(utime, stime);
  
  	list_for_each_entry_safe(timer, next, head, entry) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
471
472
473
474
475
476
477
478
479
480
481
  		list_del_init(&timer->entry);
  		if (cputime_lt(timer->expires.cpu, ptime)) {
  			timer->expires.cpu = cputime_zero;
  		} else {
  			timer->expires.cpu = cputime_sub(timer->expires.cpu,
  							 ptime);
  		}
  	}
  
  	++head;
  	list_for_each_entry_safe(timer, next, head, entry) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
482
483
484
485
486
487
488
489
490
491
492
  		list_del_init(&timer->entry);
  		if (cputime_lt(timer->expires.cpu, utime)) {
  			timer->expires.cpu = cputime_zero;
  		} else {
  			timer->expires.cpu = cputime_sub(timer->expires.cpu,
  							 utime);
  		}
  	}
  
  	++head;
  	list_for_each_entry_safe(timer, next, head, entry) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
493
  		list_del_init(&timer->entry);
41b86e9c5   Ingo Molnar   sched: make posix...
494
  		if (timer->expires.sched < sum_exec_runtime) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
495
496
  			timer->expires.sched = 0;
  		} else {
41b86e9c5   Ingo Molnar   sched: make posix...
497
  			timer->expires.sched -= sum_exec_runtime;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
498
499
500
501
502
503
504
505
506
507
508
509
  		}
  	}
  }
  
  /*
   * These are both called with the siglock held, when the current thread
   * is being reaped.  When the final (leader) thread in the group is reaped,
   * posix_cpu_timers_exit_group will be called after posix_cpu_timers_exit.
   */
  void posix_cpu_timers_exit(struct task_struct *tsk)
  {
  	cleanup_timers(tsk->cpu_timers,
41b86e9c5   Ingo Molnar   sched: make posix...
510
  		       tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
511
512
513
514
  
  }
  void posix_cpu_timers_exit_group(struct task_struct *tsk)
  {
f06febc96   Frank Mayhar   timers: fix itime...
515
  	struct task_cputime cputime;
ca531a0a5   Oleg Nesterov   [PATCH] posix-tim...
516

3fccfd67d   Peter Zijlstra   timers: split pro...
517
  	thread_group_cputimer(tsk, &cputime);
f06febc96   Frank Mayhar   timers: fix itime...
518
519
  	cleanup_timers(tsk->signal->cpu_timers,
  		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
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
  }
  
  static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
  {
  	/*
  	 * That's all for this thread or process.
  	 * We leave our residual in expires to be reported.
  	 */
  	put_task_struct(timer->it.cpu.task);
  	timer->it.cpu.task = NULL;
  	timer->it.cpu.expires = cpu_time_sub(timer->it_clock,
  					     timer->it.cpu.expires,
  					     now);
  }
  
  /*
   * Insert the timer on the appropriate list before any timers that
   * expire later.  This must be called with the tasklist_lock held
   * for reading, and interrupts disabled.
   */
  static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
  {
  	struct task_struct *p = timer->it.cpu.task;
  	struct list_head *head, *listpos;
  	struct cpu_timer_list *const nt = &timer->it.cpu;
  	struct cpu_timer_list *next;
  	unsigned long i;
  
  	head = (CPUCLOCK_PERTHREAD(timer->it_clock) ?
  		p->cpu_timers : p->signal->cpu_timers);
  	head += CPUCLOCK_WHICH(timer->it_clock);
  
  	BUG_ON(!irqs_disabled());
  	spin_lock(&p->sighand->siglock);
  
  	listpos = head;
  	if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) {
  		list_for_each_entry(next, head, entry) {
70ab81c2e   Linus Torvalds   posix cpu timers:...
558
  			if (next->expires.sched > nt->expires.sched)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
559
  				break;
70ab81c2e   Linus Torvalds   posix cpu timers:...
560
  			listpos = &next->entry;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
561
562
563
  		}
  	} else {
  		list_for_each_entry(next, head, entry) {
70ab81c2e   Linus Torvalds   posix cpu timers:...
564
  			if (cputime_gt(next->expires.cpu, nt->expires.cpu))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
565
  				break;
70ab81c2e   Linus Torvalds   posix cpu timers:...
566
  			listpos = &next->entry;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
  		}
  	}
  	list_add(&nt->entry, listpos);
  
  	if (listpos == head) {
  		/*
  		 * We are the new earliest-expiring timer.
  		 * If we are a thread timer, there can always
  		 * be a process timer telling us to stop earlier.
  		 */
  
  		if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
  			switch (CPUCLOCK_WHICH(timer->it_clock)) {
  			default:
  				BUG();
  			case CPUCLOCK_PROF:
f06febc96   Frank Mayhar   timers: fix itime...
583
  				if (cputime_eq(p->cputime_expires.prof_exp,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
584
  					       cputime_zero) ||
f06febc96   Frank Mayhar   timers: fix itime...
585
  				    cputime_gt(p->cputime_expires.prof_exp,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
586
  					       nt->expires.cpu))
f06febc96   Frank Mayhar   timers: fix itime...
587
588
  					p->cputime_expires.prof_exp =
  						nt->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
589
590
  				break;
  			case CPUCLOCK_VIRT:
f06febc96   Frank Mayhar   timers: fix itime...
591
  				if (cputime_eq(p->cputime_expires.virt_exp,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
592
  					       cputime_zero) ||
f06febc96   Frank Mayhar   timers: fix itime...
593
  				    cputime_gt(p->cputime_expires.virt_exp,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
594
  					       nt->expires.cpu))
f06febc96   Frank Mayhar   timers: fix itime...
595
596
  					p->cputime_expires.virt_exp =
  						nt->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
597
598
  				break;
  			case CPUCLOCK_SCHED:
f06febc96   Frank Mayhar   timers: fix itime...
599
600
601
602
603
  				if (p->cputime_expires.sched_exp == 0 ||
  				    p->cputime_expires.sched_exp >
  							nt->expires.sched)
  					p->cputime_expires.sched_exp =
  						nt->expires.sched;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
604
605
606
607
  				break;
  			}
  		} else {
  			/*
f06febc96   Frank Mayhar   timers: fix itime...
608
  			 * For a process timer, set the cached expiration time.
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
609
610
611
612
613
614
615
616
617
618
  			 */
  			switch (CPUCLOCK_WHICH(timer->it_clock)) {
  			default:
  				BUG();
  			case CPUCLOCK_VIRT:
  				if (!cputime_eq(p->signal->it_virt_expires,
  						cputime_zero) &&
  				    cputime_lt(p->signal->it_virt_expires,
  					       timer->it.cpu.expires.cpu))
  					break;
f06febc96   Frank Mayhar   timers: fix itime...
619
620
621
  				p->signal->cputime_expires.virt_exp =
  					timer->it.cpu.expires.cpu;
  				break;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
622
623
624
625
626
627
628
629
630
631
  			case CPUCLOCK_PROF:
  				if (!cputime_eq(p->signal->it_prof_expires,
  						cputime_zero) &&
  				    cputime_lt(p->signal->it_prof_expires,
  					       timer->it.cpu.expires.cpu))
  					break;
  				i = p->signal->rlim[RLIMIT_CPU].rlim_cur;
  				if (i != RLIM_INFINITY &&
  				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
  					break;
f06febc96   Frank Mayhar   timers: fix itime...
632
633
634
  				p->signal->cputime_expires.prof_exp =
  					timer->it.cpu.expires.cpu;
  				break;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
635
  			case CPUCLOCK_SCHED:
f06febc96   Frank Mayhar   timers: fix itime...
636
637
  				p->signal->cputime_expires.sched_exp =
  					timer->it.cpu.expires.sched;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
  				break;
  			}
  		}
  	}
  
  	spin_unlock(&p->sighand->siglock);
  }
  
  /*
   * The timer is locked, fire it and arrange for its reload.
   */
  static void cpu_timer_fire(struct k_itimer *timer)
  {
  	if (unlikely(timer->sigq == NULL)) {
  		/*
  		 * This a special case for clock_nanosleep,
  		 * not a normal timer from sys_timer_create.
  		 */
  		wake_up_process(timer->it_process);
  		timer->it.cpu.expires.sched = 0;
  	} else if (timer->it.cpu.incr.sched == 0) {
  		/*
  		 * One-shot timer.  Clear it as soon as it's fired.
  		 */
  		posix_timer_event(timer, 0);
  		timer->it.cpu.expires.sched = 0;
  	} else if (posix_timer_event(timer, ++timer->it_requeue_pending)) {
  		/*
  		 * The signal did not get queued because the signal
  		 * was ignored, so we won't get any callback to
  		 * reload the timer.  But we need to keep it
  		 * ticking in case the signal is deliverable next time.
  		 */
  		posix_cpu_timer_schedule(timer);
  	}
  }
  
  /*
3997ad317   Peter Zijlstra   timers: more cons...
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
   * Sample a process (thread group) timer for the given group_leader task.
   * Must be called with tasklist_lock held for reading.
   */
  static int cpu_timer_sample_group(const clockid_t which_clock,
  				  struct task_struct *p,
  				  union cpu_time_count *cpu)
  {
  	struct task_cputime cputime;
  
  	thread_group_cputimer(p, &cputime);
  	switch (CPUCLOCK_WHICH(which_clock)) {
  	default:
  		return -EINVAL;
  	case CPUCLOCK_PROF:
  		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
  		break;
  	case CPUCLOCK_VIRT:
  		cpu->cpu = cputime.utime;
  		break;
  	case CPUCLOCK_SCHED:
  		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
  		break;
  	}
  	return 0;
  }
  
  /*
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
   * Guts of sys_timer_settime for CPU timers.
   * This is called with the timer locked and interrupts disabled.
   * If we return TIMER_RETRY, it's necessary to release the timer's lock
   * and try again.  (This happens when the timer is in the middle of firing.)
   */
  int posix_cpu_timer_set(struct k_itimer *timer, int flags,
  			struct itimerspec *new, struct itimerspec *old)
  {
  	struct task_struct *p = timer->it.cpu.task;
  	union cpu_time_count old_expires, new_expires, val;
  	int ret;
  
  	if (unlikely(p == NULL)) {
  		/*
  		 * Timer refers to a dead task's clock.
  		 */
  		return -ESRCH;
  	}
  
  	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
  
  	read_lock(&tasklist_lock);
  	/*
  	 * We need the tasklist_lock to protect against reaping that
  	 * clears p->signal.  If p has just been reaped, we can no
  	 * longer get any information about it at all.
  	 */
  	if (unlikely(p->signal == NULL)) {
  		read_unlock(&tasklist_lock);
  		put_task_struct(p);
  		timer->it.cpu.task = NULL;
  		return -ESRCH;
  	}
  
  	/*
  	 * Disarm any old timer after extracting its expiry time.
  	 */
  	BUG_ON(!irqs_disabled());
a69ac4a78   Oleg Nesterov   [PATCH] posix-tim...
741
742
  
  	ret = 0;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
743
744
  	spin_lock(&p->sighand->siglock);
  	old_expires = timer->it.cpu.expires;
a69ac4a78   Oleg Nesterov   [PATCH] posix-tim...
745
746
747
748
749
  	if (unlikely(timer->it.cpu.firing)) {
  		timer->it.cpu.firing = -1;
  		ret = TIMER_RETRY;
  	} else
  		list_del_init(&timer->it.cpu.entry);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
750
751
752
753
754
755
756
757
758
759
760
761
762
  	spin_unlock(&p->sighand->siglock);
  
  	/*
  	 * We need to sample the current value to convert the new
  	 * value from to relative and absolute, and to convert the
  	 * old value from absolute to relative.  To set a process
  	 * timer, we need a sample to balance the thread expiry
  	 * times (in arm_timer).  With an absolute time, we must
  	 * check if it's already passed.  In short, we need a sample.
  	 */
  	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
  		cpu_clock_sample(timer->it_clock, p, &val);
  	} else {
3997ad317   Peter Zijlstra   timers: more cons...
763
  		cpu_timer_sample_group(timer->it_clock, p, &val);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
  	}
  
  	if (old) {
  		if (old_expires.sched == 0) {
  			old->it_value.tv_sec = 0;
  			old->it_value.tv_nsec = 0;
  		} else {
  			/*
  			 * Update the timer in case it has
  			 * overrun already.  If it has,
  			 * we'll report it as having overrun
  			 * and with the next reloaded timer
  			 * already ticking, though we are
  			 * swallowing that pending
  			 * notification here to install the
  			 * new setting.
  			 */
  			bump_cpu_timer(timer, val);
  			if (cpu_time_before(timer->it_clock, val,
  					    timer->it.cpu.expires)) {
  				old_expires = cpu_time_sub(
  					timer->it_clock,
  					timer->it.cpu.expires, val);
  				sample_to_timespec(timer->it_clock,
  						   old_expires,
  						   &old->it_value);
  			} else {
  				old->it_value.tv_nsec = 1;
  				old->it_value.tv_sec = 0;
  			}
  		}
  	}
a69ac4a78   Oleg Nesterov   [PATCH] posix-tim...
796
  	if (unlikely(ret)) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
797
798
799
800
801
802
803
  		/*
  		 * We are colliding with the timer actually firing.
  		 * Punt after filling in the timer's old value, and
  		 * disable this firing since we are already reporting
  		 * it as an overrun (thanks to bump_cpu_timer above).
  		 */
  		read_unlock(&tasklist_lock);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
  		goto out;
  	}
  
  	if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) {
  		cpu_time_add(timer->it_clock, &new_expires, val);
  	}
  
  	/*
  	 * Install the new expiry time (or zero).
  	 * For a timer with no notification action, we don't actually
  	 * arm the timer (we'll just fake it for timer_gettime).
  	 */
  	timer->it.cpu.expires = new_expires;
  	if (new_expires.sched != 0 &&
  	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
  	    cpu_time_before(timer->it_clock, val, new_expires)) {
  		arm_timer(timer, val);
  	}
  
  	read_unlock(&tasklist_lock);
  
  	/*
  	 * Install the new reload setting, and
  	 * set up the signal and overrun bookkeeping.
  	 */
  	timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
  						&new->it_interval);
  
  	/*
  	 * This acts as a modification timestamp for the timer,
  	 * so any automatic reload attempt will punt on seeing
  	 * that we have reset the timer manually.
  	 */
  	timer->it_requeue_pending = (timer->it_requeue_pending + 2) &
  		~REQUEUE_PENDING;
  	timer->it_overrun_last = 0;
  	timer->it_overrun = -1;
  
  	if (new_expires.sched != 0 &&
  	    (timer->it_sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE &&
  	    !cpu_time_before(timer->it_clock, val, new_expires)) {
  		/*
  		 * The designated time already passed, so we notify
  		 * immediately, even if the thread never runs to
  		 * accumulate more time on this clock.
  		 */
  		cpu_timer_fire(timer);
  	}
  
  	ret = 0;
   out:
  	if (old) {
  		sample_to_timespec(timer->it_clock,
  				   timer->it.cpu.incr, &old->it_interval);
  	}
  	return ret;
  }
  
  void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
  {
  	union cpu_time_count now;
  	struct task_struct *p = timer->it.cpu.task;
  	int clear_dead;
  
  	/*
  	 * Easy part: convert the reload time.
  	 */
  	sample_to_timespec(timer->it_clock,
  			   timer->it.cpu.incr, &itp->it_interval);
  
  	if (timer->it.cpu.expires.sched == 0) {	/* Timer not armed at all.  */
  		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
  		return;
  	}
  
  	if (unlikely(p == NULL)) {
  		/*
  		 * This task already died and the timer will never fire.
  		 * In this case, expires is actually the dead value.
  		 */
  	dead:
  		sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
  				   &itp->it_value);
  		return;
  	}
  
  	/*
  	 * Sample the clock to take the difference with the expiry time.
  	 */
  	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
  		cpu_clock_sample(timer->it_clock, p, &now);
  		clear_dead = p->exit_state;
  	} else {
  		read_lock(&tasklist_lock);
  		if (unlikely(p->signal == NULL)) {
  			/*
  			 * The process has been reaped.
  			 * We can't even collect a sample any more.
  			 * Call the timer disarmed, nothing else to do.
  			 */
  			put_task_struct(p);
  			timer->it.cpu.task = NULL;
  			timer->it.cpu.expires.sched = 0;
  			read_unlock(&tasklist_lock);
  			goto dead;
  		} else {
3997ad317   Peter Zijlstra   timers: more cons...
910
  			cpu_timer_sample_group(timer->it_clock, p, &now);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
  			clear_dead = (unlikely(p->exit_state) &&
  				      thread_group_empty(p));
  		}
  		read_unlock(&tasklist_lock);
  	}
  
  	if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) {
  		if (timer->it.cpu.incr.sched == 0 &&
  		    cpu_time_before(timer->it_clock,
  				    timer->it.cpu.expires, now)) {
  			/*
  			 * Do-nothing timer expired and has no reload,
  			 * so it's as if it was never set.
  			 */
  			timer->it.cpu.expires.sched = 0;
  			itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
  			return;
  		}
  		/*
  		 * Account for any expirations and reloads that should
  		 * have happened.
  		 */
  		bump_cpu_timer(timer, now);
  	}
  
  	if (unlikely(clear_dead)) {
  		/*
  		 * We've noticed that the thread is dead, but
  		 * not yet reaped.  Take this opportunity to
  		 * drop our task ref.
  		 */
  		clear_dead_task(timer, now);
  		goto dead;
  	}
  
  	if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) {
  		sample_to_timespec(timer->it_clock,
  				   cpu_time_sub(timer->it_clock,
  						timer->it.cpu.expires, now),
  				   &itp->it_value);
  	} else {
  		/*
  		 * The timer should have expired already, but the firing
  		 * hasn't taken place yet.  Say it's just about to expire.
  		 */
  		itp->it_value.tv_nsec = 1;
  		itp->it_value.tv_sec = 0;
  	}
  }
  
  /*
   * Check for any per-thread CPU timers that have fired and move them off
   * the tsk->cpu_timers[N] list onto the firing list.  Here we update the
   * tsk->it_*_expires values to reflect the remaining thread CPU timers.
   */
  static void check_thread_timers(struct task_struct *tsk,
  				struct list_head *firing)
  {
e80eda94d   Linus Torvalds   Posix timers: lim...
969
  	int maxfire;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
970
  	struct list_head *timers = tsk->cpu_timers;
78f2c7db6   Peter Zijlstra   sched: SCHED_FIFO...
971
  	struct signal_struct *const sig = tsk->signal;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
972

e80eda94d   Linus Torvalds   Posix timers: lim...
973
  	maxfire = 20;
f06febc96   Frank Mayhar   timers: fix itime...
974
  	tsk->cputime_expires.prof_exp = cputime_zero;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
975
  	while (!list_empty(timers)) {
b5e618181   Pavel Emelianov   Introduce a handy...
976
  		struct cpu_timer_list *t = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
977
978
  						      struct cpu_timer_list,
  						      entry);
e80eda94d   Linus Torvalds   Posix timers: lim...
979
  		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
f06febc96   Frank Mayhar   timers: fix itime...
980
  			tsk->cputime_expires.prof_exp = t->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
981
982
983
984
985
986
987
  			break;
  		}
  		t->firing = 1;
  		list_move_tail(&t->entry, firing);
  	}
  
  	++timers;
e80eda94d   Linus Torvalds   Posix timers: lim...
988
  	maxfire = 20;
f06febc96   Frank Mayhar   timers: fix itime...
989
  	tsk->cputime_expires.virt_exp = cputime_zero;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
990
  	while (!list_empty(timers)) {
b5e618181   Pavel Emelianov   Introduce a handy...
991
  		struct cpu_timer_list *t = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
992
993
  						      struct cpu_timer_list,
  						      entry);
e80eda94d   Linus Torvalds   Posix timers: lim...
994
  		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
f06febc96   Frank Mayhar   timers: fix itime...
995
  			tsk->cputime_expires.virt_exp = t->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
996
997
998
999
1000
1001
1002
  			break;
  		}
  		t->firing = 1;
  		list_move_tail(&t->entry, firing);
  	}
  
  	++timers;
e80eda94d   Linus Torvalds   Posix timers: lim...
1003
  	maxfire = 20;
f06febc96   Frank Mayhar   timers: fix itime...
1004
  	tsk->cputime_expires.sched_exp = 0;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1005
  	while (!list_empty(timers)) {
b5e618181   Pavel Emelianov   Introduce a handy...
1006
  		struct cpu_timer_list *t = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1007
1008
  						      struct cpu_timer_list,
  						      entry);
41b86e9c5   Ingo Molnar   sched: make posix...
1009
  		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
f06febc96   Frank Mayhar   timers: fix itime...
1010
  			tsk->cputime_expires.sched_exp = t->expires.sched;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1011
1012
1013
1014
1015
  			break;
  		}
  		t->firing = 1;
  		list_move_tail(&t->entry, firing);
  	}
78f2c7db6   Peter Zijlstra   sched: SCHED_FIFO...
1016
1017
1018
1019
1020
1021
1022
  
  	/*
  	 * Check for the special case thread timers.
  	 */
  	if (sig->rlim[RLIMIT_RTTIME].rlim_cur != RLIM_INFINITY) {
  		unsigned long hard = sig->rlim[RLIMIT_RTTIME].rlim_max;
  		unsigned long *soft = &sig->rlim[RLIMIT_RTTIME].rlim_cur;
5a52dd500   Peter Zijlstra   sched: rt-watchdo...
1023
1024
  		if (hard != RLIM_INFINITY &&
  		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
78f2c7db6   Peter Zijlstra   sched: SCHED_FIFO...
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
  			/*
  			 * At the hard limit, we just die.
  			 * No need to calculate anything else now.
  			 */
  			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
  			return;
  		}
  		if (tsk->rt.timeout > DIV_ROUND_UP(*soft, USEC_PER_SEC/HZ)) {
  			/*
  			 * At the soft limit, send a SIGXCPU every second.
  			 */
  			if (sig->rlim[RLIMIT_RTTIME].rlim_cur
  			    < sig->rlim[RLIMIT_RTTIME].rlim_max) {
  				sig->rlim[RLIMIT_RTTIME].rlim_cur +=
  								USEC_PER_SEC;
  			}
81d50bb25   Hiroshi Shimamoto   posix-timers: pri...
1041
1042
1043
1044
  			printk(KERN_INFO
  				"RT Watchdog Timeout: %s[%d]
  ",
  				tsk->comm, task_pid_nr(tsk));
78f2c7db6   Peter Zijlstra   sched: SCHED_FIFO...
1045
1046
1047
  			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
  		}
  	}
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1048
  }
3fccfd67d   Peter Zijlstra   timers: split pro...
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
  static void stop_process_timers(struct task_struct *tsk)
  {
  	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
  	unsigned long flags;
  
  	if (!cputimer->running)
  		return;
  
  	spin_lock_irqsave(&cputimer->lock, flags);
  	cputimer->running = 0;
  	spin_unlock_irqrestore(&cputimer->lock, flags);
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1061
1062
1063
1064
1065
1066
1067
1068
  /*
   * Check for any per-thread CPU timers that have fired and move them
   * off the tsk->*_timers list onto the firing list.  Per-thread timers
   * have already been taken off.
   */
  static void check_process_timers(struct task_struct *tsk,
  				 struct list_head *firing)
  {
e80eda94d   Linus Torvalds   Posix timers: lim...
1069
  	int maxfire;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1070
  	struct signal_struct *const sig = tsk->signal;
f06febc96   Frank Mayhar   timers: fix itime...
1071
  	cputime_t utime, ptime, virt_expires, prof_expires;
41b86e9c5   Ingo Molnar   sched: make posix...
1072
  	unsigned long long sum_sched_runtime, sched_expires;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1073
  	struct list_head *timers = sig->cpu_timers;
f06febc96   Frank Mayhar   timers: fix itime...
1074
  	struct task_cputime cputime;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1075
1076
1077
1078
1079
1080
1081
1082
1083
  
  	/*
  	 * Don't sample the current process CPU clocks if there are no timers.
  	 */
  	if (list_empty(&timers[CPUCLOCK_PROF]) &&
  	    cputime_eq(sig->it_prof_expires, cputime_zero) &&
  	    sig->rlim[RLIMIT_CPU].rlim_cur == RLIM_INFINITY &&
  	    list_empty(&timers[CPUCLOCK_VIRT]) &&
  	    cputime_eq(sig->it_virt_expires, cputime_zero) &&
4cd4c1b40   Peter Zijlstra   timers: split pro...
1084
1085
  	    list_empty(&timers[CPUCLOCK_SCHED])) {
  		stop_process_timers(tsk);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1086
  		return;
4cd4c1b40   Peter Zijlstra   timers: split pro...
1087
  	}
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1088
1089
1090
1091
  
  	/*
  	 * Collect the current process totals.
  	 */
4cd4c1b40   Peter Zijlstra   timers: split pro...
1092
  	thread_group_cputimer(tsk, &cputime);
f06febc96   Frank Mayhar   timers: fix itime...
1093
1094
1095
  	utime = cputime.utime;
  	ptime = cputime_add(utime, cputime.stime);
  	sum_sched_runtime = cputime.sum_exec_runtime;
e80eda94d   Linus Torvalds   Posix timers: lim...
1096
  	maxfire = 20;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1097
1098
  	prof_expires = cputime_zero;
  	while (!list_empty(timers)) {
ee7dd205b   WANG Cong   posix-timers: fix...
1099
  		struct cpu_timer_list *tl = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1100
1101
  						      struct cpu_timer_list,
  						      entry);
ee7dd205b   WANG Cong   posix-timers: fix...
1102
1103
  		if (!--maxfire || cputime_lt(ptime, tl->expires.cpu)) {
  			prof_expires = tl->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1104
1105
  			break;
  		}
ee7dd205b   WANG Cong   posix-timers: fix...
1106
1107
  		tl->firing = 1;
  		list_move_tail(&tl->entry, firing);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1108
1109
1110
  	}
  
  	++timers;
e80eda94d   Linus Torvalds   Posix timers: lim...
1111
  	maxfire = 20;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1112
1113
  	virt_expires = cputime_zero;
  	while (!list_empty(timers)) {
ee7dd205b   WANG Cong   posix-timers: fix...
1114
  		struct cpu_timer_list *tl = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1115
1116
  						      struct cpu_timer_list,
  						      entry);
ee7dd205b   WANG Cong   posix-timers: fix...
1117
1118
  		if (!--maxfire || cputime_lt(utime, tl->expires.cpu)) {
  			virt_expires = tl->expires.cpu;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1119
1120
  			break;
  		}
ee7dd205b   WANG Cong   posix-timers: fix...
1121
1122
  		tl->firing = 1;
  		list_move_tail(&tl->entry, firing);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1123
1124
1125
  	}
  
  	++timers;
e80eda94d   Linus Torvalds   Posix timers: lim...
1126
  	maxfire = 20;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1127
1128
  	sched_expires = 0;
  	while (!list_empty(timers)) {
ee7dd205b   WANG Cong   posix-timers: fix...
1129
  		struct cpu_timer_list *tl = list_first_entry(timers,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1130
1131
  						      struct cpu_timer_list,
  						      entry);
ee7dd205b   WANG Cong   posix-timers: fix...
1132
1133
  		if (!--maxfire || sum_sched_runtime < tl->expires.sched) {
  			sched_expires = tl->expires.sched;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1134
1135
  			break;
  		}
ee7dd205b   WANG Cong   posix-timers: fix...
1136
1137
  		tl->firing = 1;
  		list_move_tail(&tl->entry, firing);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
  	}
  
  	/*
  	 * Check for the special case process timers.
  	 */
  	if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
  		if (cputime_ge(ptime, sig->it_prof_expires)) {
  			/* ITIMER_PROF fires and reloads.  */
  			sig->it_prof_expires = sig->it_prof_incr;
  			if (!cputime_eq(sig->it_prof_expires, cputime_zero)) {
  				sig->it_prof_expires = cputime_add(
  					sig->it_prof_expires, ptime);
  			}
  			__group_send_sig_info(SIGPROF, SEND_SIG_PRIV, tsk);
  		}
  		if (!cputime_eq(sig->it_prof_expires, cputime_zero) &&
  		    (cputime_eq(prof_expires, cputime_zero) ||
  		     cputime_lt(sig->it_prof_expires, prof_expires))) {
  			prof_expires = sig->it_prof_expires;
  		}
  	}
  	if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
  		if (cputime_ge(utime, sig->it_virt_expires)) {
  			/* ITIMER_VIRTUAL fires and reloads.  */
  			sig->it_virt_expires = sig->it_virt_incr;
  			if (!cputime_eq(sig->it_virt_expires, cputime_zero)) {
  				sig->it_virt_expires = cputime_add(
  					sig->it_virt_expires, utime);
  			}
  			__group_send_sig_info(SIGVTALRM, SEND_SIG_PRIV, tsk);
  		}
  		if (!cputime_eq(sig->it_virt_expires, cputime_zero) &&
  		    (cputime_eq(virt_expires, cputime_zero) ||
  		     cputime_lt(sig->it_virt_expires, virt_expires))) {
  			virt_expires = sig->it_virt_expires;
  		}
  	}
  	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
  		unsigned long psecs = cputime_to_secs(ptime);
  		cputime_t x;
  		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_max) {
  			/*
  			 * At the hard limit, we just die.
  			 * No need to calculate anything else now.
  			 */
  			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
  			return;
  		}
  		if (psecs >= sig->rlim[RLIMIT_CPU].rlim_cur) {
  			/*
  			 * At the soft limit, send a SIGXCPU every second.
  			 */
  			__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
  			if (sig->rlim[RLIMIT_CPU].rlim_cur
  			    < sig->rlim[RLIMIT_CPU].rlim_max) {
  				sig->rlim[RLIMIT_CPU].rlim_cur++;
  			}
  		}
  		x = secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
  		if (cputime_eq(prof_expires, cputime_zero) ||
  		    cputime_lt(x, prof_expires)) {
  			prof_expires = x;
  		}
  	}
f06febc96   Frank Mayhar   timers: fix itime...
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
  	if (!cputime_eq(prof_expires, cputime_zero) &&
  	    (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) ||
  	     cputime_gt(sig->cputime_expires.prof_exp, prof_expires)))
  		sig->cputime_expires.prof_exp = prof_expires;
  	if (!cputime_eq(virt_expires, cputime_zero) &&
  	    (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) ||
  	     cputime_gt(sig->cputime_expires.virt_exp, virt_expires)))
  		sig->cputime_expires.virt_exp = virt_expires;
  	if (sched_expires != 0 &&
  	    (sig->cputime_expires.sched_exp == 0 ||
  	     sig->cputime_expires.sched_exp > sched_expires))
  		sig->cputime_expires.sched_exp = sched_expires;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
  }
  
  /*
   * This is called from the signal code (via do_schedule_next_timer)
   * when the last timer signal was delivered and we have to reload the timer.
   */
  void posix_cpu_timer_schedule(struct k_itimer *timer)
  {
  	struct task_struct *p = timer->it.cpu.task;
  	union cpu_time_count now;
  
  	if (unlikely(p == NULL))
  		/*
  		 * The task was cleaned up already, no future firings.
  		 */
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1229
  		goto out;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1230
1231
1232
1233
1234
1235
1236
1237
1238
  
  	/*
  	 * Fetch the current sample and update the timer's expiry time.
  	 */
  	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
  		cpu_clock_sample(timer->it_clock, p, &now);
  		bump_cpu_timer(timer, now);
  		if (unlikely(p->exit_state)) {
  			clear_dead_task(timer, now);
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1239
  			goto out;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
  		}
  		read_lock(&tasklist_lock); /* arm_timer needs it.  */
  	} else {
  		read_lock(&tasklist_lock);
  		if (unlikely(p->signal == NULL)) {
  			/*
  			 * The process has been reaped.
  			 * We can't even collect a sample any more.
  			 */
  			put_task_struct(p);
  			timer->it.cpu.task = p = NULL;
  			timer->it.cpu.expires.sched = 0;
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1252
  			goto out_unlock;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1253
1254
1255
1256
1257
1258
1259
  		} else if (unlikely(p->exit_state) && thread_group_empty(p)) {
  			/*
  			 * We've noticed that the thread is dead, but
  			 * not yet reaped.  Take this opportunity to
  			 * drop our task ref.
  			 */
  			clear_dead_task(timer, now);
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1260
  			goto out_unlock;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1261
  		}
3997ad317   Peter Zijlstra   timers: more cons...
1262
  		cpu_timer_sample_group(timer->it_clock, p, &now);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1263
1264
1265
1266
1267
1268
1269
1270
  		bump_cpu_timer(timer, now);
  		/* Leave the tasklist_lock locked for the call below.  */
  	}
  
  	/*
  	 * Now re-arm for the new expiry time.
  	 */
  	arm_timer(timer, now);
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1271
  out_unlock:
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1272
  	read_unlock(&tasklist_lock);
708f430dc   Roland McGrath   [PATCH] posix-cpu...
1273
1274
1275
1276
1277
  
  out:
  	timer->it_overrun_last = timer->it_overrun;
  	timer->it_overrun = -1;
  	++timer->it_requeue_pending;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1278
  }
f06febc96   Frank Mayhar   timers: fix itime...
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
  /**
   * task_cputime_zero - Check a task_cputime struct for all zero fields.
   *
   * @cputime:	The struct to compare.
   *
   * Checks @cputime to see if all fields are zero.  Returns true if all fields
   * are zero, false if any field is nonzero.
   */
  static inline int task_cputime_zero(const struct task_cputime *cputime)
  {
  	if (cputime_eq(cputime->utime, cputime_zero) &&
  	    cputime_eq(cputime->stime, cputime_zero) &&
  	    cputime->sum_exec_runtime == 0)
  		return 1;
  	return 0;
  }
  
  /**
   * task_cputime_expired - Compare two task_cputime entities.
   *
   * @sample:	The task_cputime structure to be checked for expiration.
   * @expires:	Expiration times, against which @sample will be checked.
   *
   * Checks @sample against @expires to see if any field of @sample has expired.
   * Returns true if any field of the former is greater than the corresponding
   * field of the latter if the latter field is set.  Otherwise returns false.
   */
  static inline int task_cputime_expired(const struct task_cputime *sample,
  					const struct task_cputime *expires)
  {
  	if (!cputime_eq(expires->utime, cputime_zero) &&
  	    cputime_ge(sample->utime, expires->utime))
  		return 1;
  	if (!cputime_eq(expires->stime, cputime_zero) &&
  	    cputime_ge(cputime_add(sample->utime, sample->stime),
  		       expires->stime))
  		return 1;
  	if (expires->sum_exec_runtime != 0 &&
  	    sample->sum_exec_runtime >= expires->sum_exec_runtime)
  		return 1;
  	return 0;
  }
  
  /**
   * fastpath_timer_check - POSIX CPU timers fast path.
   *
   * @tsk:	The task (thread) being checked.
f06febc96   Frank Mayhar   timers: fix itime...
1326
   *
bb34d92f6   Frank Mayhar   timers: fix itime...
1327
1328
1329
1330
   * Check the task and thread group timers.  If both are zero (there are no
   * timers set) return false.  Otherwise snapshot the task and thread group
   * timers and compare them with the corresponding expiration times.  Return
   * true if a timer has expired, else return false.
f06febc96   Frank Mayhar   timers: fix itime...
1331
   */
bb34d92f6   Frank Mayhar   timers: fix itime...
1332
  static inline int fastpath_timer_check(struct task_struct *tsk)
f06febc96   Frank Mayhar   timers: fix itime...
1333
  {
ad133ba3d   Oleg Nesterov   sched, signals: f...
1334
  	struct signal_struct *sig;
bb34d92f6   Frank Mayhar   timers: fix itime...
1335

ad133ba3d   Oleg Nesterov   sched, signals: f...
1336
1337
  	/* tsk == current, ensure it is safe to use ->signal/sighand */
  	if (unlikely(tsk->exit_state))
f06febc96   Frank Mayhar   timers: fix itime...
1338
  		return 0;
bb34d92f6   Frank Mayhar   timers: fix itime...
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
  
  	if (!task_cputime_zero(&tsk->cputime_expires)) {
  		struct task_cputime task_sample = {
  			.utime = tsk->utime,
  			.stime = tsk->stime,
  			.sum_exec_runtime = tsk->se.sum_exec_runtime
  		};
  
  		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
  			return 1;
  	}
ad133ba3d   Oleg Nesterov   sched, signals: f...
1350
1351
  
  	sig = tsk->signal;
bb34d92f6   Frank Mayhar   timers: fix itime...
1352
1353
  	if (!task_cputime_zero(&sig->cputime_expires)) {
  		struct task_cputime group_sample;
4cd4c1b40   Peter Zijlstra   timers: split pro...
1354
  		thread_group_cputimer(tsk, &group_sample);
bb34d92f6   Frank Mayhar   timers: fix itime...
1355
1356
1357
  		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
  			return 1;
  	}
37bebc70d   Oleg Nesterov   posix timers: fix...
1358
1359
  
  	return sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY;
f06febc96   Frank Mayhar   timers: fix itime...
1360
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
  /*
   * This is called from the timer interrupt handler.  The irq handler has
   * already updated our counts.  We need to check if any timers fire now.
   * Interrupts are disabled.
   */
  void run_posix_cpu_timers(struct task_struct *tsk)
  {
  	LIST_HEAD(firing);
  	struct k_itimer *timer, *next;
  
  	BUG_ON(!irqs_disabled());
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1372
  	/*
f06febc96   Frank Mayhar   timers: fix itime...
1373
  	 * The fast path checks that there are no expired thread or thread
bb34d92f6   Frank Mayhar   timers: fix itime...
1374
  	 * group timers.  If that's so, just return.
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1375
  	 */
bb34d92f6   Frank Mayhar   timers: fix itime...
1376
  	if (!fastpath_timer_check(tsk))
f06febc96   Frank Mayhar   timers: fix itime...
1377
  		return;
5ce73a4a5   Ingo Molnar   timers: fix itime...
1378

bb34d92f6   Frank Mayhar   timers: fix itime...
1379
1380
1381
1382
1383
1384
1385
1386
  	spin_lock(&tsk->sighand->siglock);
  	/*
  	 * Here we take off tsk->signal->cpu_timers[N] and
  	 * tsk->cpu_timers[N] all the timers that are firing, and
  	 * put them on the firing list.
  	 */
  	check_thread_timers(tsk, &firing);
  	check_process_timers(tsk, &firing);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1387

bb34d92f6   Frank Mayhar   timers: fix itime...
1388
1389
1390
1391
1392
1393
1394
1395
1396
  	/*
  	 * We must release these locks before taking any timer's lock.
  	 * There is a potential race with timer deletion here, as the
  	 * siglock now protects our private firing list.  We have set
  	 * the firing flag in each timer, so that a deletion attempt
  	 * that gets the timer lock before we do will give it up and
  	 * spin until we've taken care of that timer below.
  	 */
  	spin_unlock(&tsk->sighand->siglock);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1397
1398
1399
1400
1401
1402
1403
1404
  
  	/*
  	 * Now that all the timers on our list have the firing flag,
  	 * noone will touch their list entries but us.  We'll take
  	 * each timer's lock before clearing its firing flag, so no
  	 * timer call will interfere.
  	 */
  	list_for_each_entry_safe(timer, next, &firing, it.cpu.entry) {
6e85c5ba7   H Hartley Sweeten   kernel/posix-cpu-...
1405
  		int cpu_firing;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1406
1407
  		spin_lock(&timer->it_lock);
  		list_del_init(&timer->it.cpu.entry);
6e85c5ba7   H Hartley Sweeten   kernel/posix-cpu-...
1408
  		cpu_firing = timer->it.cpu.firing;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1409
1410
1411
1412
1413
1414
  		timer->it.cpu.firing = 0;
  		/*
  		 * The firing flag is -1 if we collided with a reset
  		 * of the timer, which already reported this
  		 * almost-firing as an overrun.  So don't generate an event.
  		 */
6e85c5ba7   H Hartley Sweeten   kernel/posix-cpu-...
1415
  		if (likely(cpu_firing >= 0))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1416
  			cpu_timer_fire(timer);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1417
1418
1419
1420
1421
1422
  		spin_unlock(&timer->it_lock);
  	}
  }
  
  /*
   * Set one of the process-wide special case CPU timers.
f06febc96   Frank Mayhar   timers: fix itime...
1423
1424
1425
   * The tsk->sighand->siglock must be held by the caller.
   * The *newval argument is relative and we update it to be absolute, *oldval
   * is absolute and we update it to be relative.
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1426
1427
1428
1429
1430
1431
1432
1433
   */
  void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
  			   cputime_t *newval, cputime_t *oldval)
  {
  	union cpu_time_count now;
  	struct list_head *head;
  
  	BUG_ON(clock_idx == CPUCLOCK_SCHED);
4cd4c1b40   Peter Zijlstra   timers: split pro...
1434
  	cpu_timer_sample_group(clock_idx, tsk, &now);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
  
  	if (oldval) {
  		if (!cputime_eq(*oldval, cputime_zero)) {
  			if (cputime_le(*oldval, now.cpu)) {
  				/* Just about to fire. */
  				*oldval = jiffies_to_cputime(1);
  			} else {
  				*oldval = cputime_sub(*oldval, now.cpu);
  			}
  		}
  
  		if (cputime_eq(*newval, cputime_zero))
  			return;
  		*newval = cputime_add(*newval, now.cpu);
  
  		/*
  		 * If the RLIMIT_CPU timer will expire before the
  		 * ITIMER_PROF timer, we have nothing else to do.
  		 */
  		if (tsk->signal->rlim[RLIMIT_CPU].rlim_cur
  		    < cputime_to_secs(*newval))
  			return;
  	}
  
  	/*
  	 * Check whether there are any process timers already set to fire
  	 * before this one.  If so, we don't have anything more to do.
  	 */
  	head = &tsk->signal->cpu_timers[clock_idx];
  	if (list_empty(head) ||
b5e618181   Pavel Emelianov   Introduce a handy...
1465
  	    cputime_ge(list_first_entry(head,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1466
1467
  				  struct cpu_timer_list, entry)->expires.cpu,
  		       *newval)) {
f06febc96   Frank Mayhar   timers: fix itime...
1468
1469
1470
1471
1472
1473
1474
1475
  		switch (clock_idx) {
  		case CPUCLOCK_PROF:
  			tsk->signal->cputime_expires.prof_exp = *newval;
  			break;
  		case CPUCLOCK_VIRT:
  			tsk->signal->cputime_expires.virt_exp = *newval;
  			break;
  		}
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1476
1477
  	}
  }
e4b765551   Toyo Abe   [PATCH] posix-tim...
1478
1479
  static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
  			    struct timespec *rqtp, struct itimerspec *it)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1480
  {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1481
1482
1483
1484
  	struct k_itimer timer;
  	int error;
  
  	/*
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1485
1486
1487
1488
1489
1490
1491
1492
1493
  	 * Set up a temporary timer and then wait for it to go off.
  	 */
  	memset(&timer, 0, sizeof timer);
  	spin_lock_init(&timer.it_lock);
  	timer.it_clock = which_clock;
  	timer.it_overrun = -1;
  	error = posix_cpu_timer_create(&timer);
  	timer.it_process = current;
  	if (!error) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1494
  		static struct itimerspec zero_it;
e4b765551   Toyo Abe   [PATCH] posix-tim...
1495
1496
1497
  
  		memset(it, 0, sizeof *it);
  		it->it_value = *rqtp;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1498
1499
  
  		spin_lock_irq(&timer.it_lock);
e4b765551   Toyo Abe   [PATCH] posix-tim...
1500
  		error = posix_cpu_timer_set(&timer, flags, it, NULL);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
  		if (error) {
  			spin_unlock_irq(&timer.it_lock);
  			return error;
  		}
  
  		while (!signal_pending(current)) {
  			if (timer.it.cpu.expires.sched == 0) {
  				/*
  				 * Our timer fired and was reset.
  				 */
  				spin_unlock_irq(&timer.it_lock);
  				return 0;
  			}
  
  			/*
  			 * Block until cpu_timer_fire (or a signal) wakes us.
  			 */
  			__set_current_state(TASK_INTERRUPTIBLE);
  			spin_unlock_irq(&timer.it_lock);
  			schedule();
  			spin_lock_irq(&timer.it_lock);
  		}
  
  		/*
  		 * We were interrupted by a signal.
  		 */
  		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
e4b765551   Toyo Abe   [PATCH] posix-tim...
1528
  		posix_cpu_timer_set(&timer, 0, &zero_it, it);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1529
  		spin_unlock_irq(&timer.it_lock);
e4b765551   Toyo Abe   [PATCH] posix-tim...
1530
  		if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) {
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1531
1532
1533
1534
1535
  			/*
  			 * It actually did fire already.
  			 */
  			return 0;
  		}
e4b765551   Toyo Abe   [PATCH] posix-tim...
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
  		error = -ERESTART_RESTARTBLOCK;
  	}
  
  	return error;
  }
  
  int posix_cpu_nsleep(const clockid_t which_clock, int flags,
  		     struct timespec *rqtp, struct timespec __user *rmtp)
  {
  	struct restart_block *restart_block =
  	    &current_thread_info()->restart_block;
  	struct itimerspec it;
  	int error;
  
  	/*
  	 * Diagnose required errors first.
  	 */
  	if (CPUCLOCK_PERTHREAD(which_clock) &&
  	    (CPUCLOCK_PID(which_clock) == 0 ||
  	     CPUCLOCK_PID(which_clock) == current->pid))
  		return -EINVAL;
  
  	error = do_cpu_nanosleep(which_clock, flags, rqtp, &it);
  
  	if (error == -ERESTART_RESTARTBLOCK) {
  
  	       	if (flags & TIMER_ABSTIME)
  			return -ERESTARTNOHAND;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1564
  		/*
e4b765551   Toyo Abe   [PATCH] posix-tim...
1565
1566
1567
  	 	 * Report back to the user the time still remaining.
  	 	 */
  		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1568
  			return -EFAULT;
1711ef386   Toyo Abe   [PATCH] posix-tim...
1569
  		restart_block->fn = posix_cpu_nsleep_restart;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1570
  		restart_block->arg0 = which_clock;
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1571
  		restart_block->arg1 = (unsigned long) rmtp;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1572
1573
  		restart_block->arg2 = rqtp->tv_sec;
  		restart_block->arg3 = rqtp->tv_nsec;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1574
  	}
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1575
1576
  	return error;
  }
1711ef386   Toyo Abe   [PATCH] posix-tim...
1577
  long posix_cpu_nsleep_restart(struct restart_block *restart_block)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1578
1579
  {
  	clockid_t which_clock = restart_block->arg0;
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1580
1581
  	struct timespec __user *rmtp;
  	struct timespec t;
e4b765551   Toyo Abe   [PATCH] posix-tim...
1582
1583
  	struct itimerspec it;
  	int error;
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1584
1585
1586
1587
  
  	rmtp = (struct timespec __user *) restart_block->arg1;
  	t.tv_sec = restart_block->arg2;
  	t.tv_nsec = restart_block->arg3;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1588
  	restart_block->fn = do_no_restart_syscall;
e4b765551   Toyo Abe   [PATCH] posix-tim...
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
  	error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it);
  
  	if (error == -ERESTART_RESTARTBLOCK) {
  		/*
  	 	 * Report back to the user the time still remaining.
  	 	 */
  		if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp))
  			return -EFAULT;
  
  		restart_block->fn = posix_cpu_nsleep_restart;
  		restart_block->arg0 = which_clock;
  		restart_block->arg1 = (unsigned long) rmtp;
  		restart_block->arg2 = t.tv_sec;
  		restart_block->arg3 = t.tv_nsec;
  	}
  	return error;
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1605
1606
1607
1608
1609
  }
  
  
  #define PROCESS_CLOCK	MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED)
  #define THREAD_CLOCK	MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED)
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1610
1611
  static int process_cpu_clock_getres(const clockid_t which_clock,
  				    struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1612
1613
1614
  {
  	return posix_cpu_clock_getres(PROCESS_CLOCK, tp);
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1615
1616
  static int process_cpu_clock_get(const clockid_t which_clock,
  				 struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1617
1618
1619
1620
1621
1622
1623
1624
  {
  	return posix_cpu_clock_get(PROCESS_CLOCK, tp);
  }
  static int process_cpu_timer_create(struct k_itimer *timer)
  {
  	timer->it_clock = PROCESS_CLOCK;
  	return posix_cpu_timer_create(timer);
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1625
  static int process_cpu_nsleep(const clockid_t which_clock, int flags,
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1626
1627
  			      struct timespec *rqtp,
  			      struct timespec __user *rmtp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1628
  {
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1629
  	return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp);
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1630
  }
1711ef386   Toyo Abe   [PATCH] posix-tim...
1631
1632
1633
1634
  static long process_cpu_nsleep_restart(struct restart_block *restart_block)
  {
  	return -EINVAL;
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1635
1636
  static int thread_cpu_clock_getres(const clockid_t which_clock,
  				   struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1637
1638
1639
  {
  	return posix_cpu_clock_getres(THREAD_CLOCK, tp);
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1640
1641
  static int thread_cpu_clock_get(const clockid_t which_clock,
  				struct timespec *tp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1642
1643
1644
1645
1646
1647
1648
1649
  {
  	return posix_cpu_clock_get(THREAD_CLOCK, tp);
  }
  static int thread_cpu_timer_create(struct k_itimer *timer)
  {
  	timer->it_clock = THREAD_CLOCK;
  	return posix_cpu_timer_create(timer);
  }
a924b04dd   Thomas Gleixner   [PATCH] hrtimer: ...
1650
  static int thread_cpu_nsleep(const clockid_t which_clock, int flags,
97735f25d   Thomas Gleixner   [PATCH] hrtimer: ...
1651
  			      struct timespec *rqtp, struct timespec __user *rmtp)
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1652
1653
1654
  {
  	return -EINVAL;
  }
1711ef386   Toyo Abe   [PATCH] posix-tim...
1655
1656
1657
1658
  static long thread_cpu_nsleep_restart(struct restart_block *restart_block)
  {
  	return -EINVAL;
  }
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1659
1660
1661
1662
1663
1664
1665
1666
1667
  
  static __init int init_posix_cpu_timers(void)
  {
  	struct k_clock process = {
  		.clock_getres = process_cpu_clock_getres,
  		.clock_get = process_cpu_clock_get,
  		.clock_set = do_posix_clock_nosettime,
  		.timer_create = process_cpu_timer_create,
  		.nsleep = process_cpu_nsleep,
1711ef386   Toyo Abe   [PATCH] posix-tim...
1668
  		.nsleep_restart = process_cpu_nsleep_restart,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1669
1670
1671
1672
1673
1674
1675
  	};
  	struct k_clock thread = {
  		.clock_getres = thread_cpu_clock_getres,
  		.clock_get = thread_cpu_clock_get,
  		.clock_set = do_posix_clock_nosettime,
  		.timer_create = thread_cpu_timer_create,
  		.nsleep = thread_cpu_nsleep,
1711ef386   Toyo Abe   [PATCH] posix-tim...
1676
  		.nsleep_restart = thread_cpu_nsleep_restart,
1da177e4c   Linus Torvalds   Linux-2.6.12-rc2
1677
1678
1679
1680
1681
1682
1683
1684
  	};
  
  	register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
  	register_posix_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
  
  	return 0;
  }
  __initcall(init_posix_cpu_timers);