summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/vtime.c
blob: f216a1b2f82570de92365007e5da8158ebbd0714 (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
452
453
454
455
// SPDX-License-Identifier: GPL-2.0
/*
 *    Virtual cpu timer based timer functions.
 *
 *    Copyright IBM Corp. 2004, 2012
 *    Author(s): Jan Glauber <jan.glauber@de.ibm.com>
 */

#include <linux/kernel_stat.h>
#include <linux/sched/cputime.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/types.h>
#include <linux/time.h>
#include <asm/alternative.h>
#include <asm/vtimer.h>
#include <asm/vtime.h>
#include <asm/cpu_mf.h>
#include <asm/smp.h>

#include "entry.h"

static void virt_timer_expire(void);

static LIST_HEAD(virt_timer_list);
static DEFINE_SPINLOCK(virt_timer_lock);
static atomic64_t virt_timer_current;
static atomic64_t virt_timer_elapsed;

DEFINE_PER_CPU(u64, mt_cycles[8]);
static DEFINE_PER_CPU(u64, mt_scaling_mult) = { 1 };
static DEFINE_PER_CPU(u64, mt_scaling_div) = { 1 };
static DEFINE_PER_CPU(u64, mt_scaling_jiffies);

static inline u64 get_vtimer(void)
{
	u64 timer;

	asm volatile("stpt %0" : "=Q" (timer));
	return timer;
}

static inline void set_vtimer(u64 expires)
{
	u64 timer;

	asm volatile(
		"	stpt	%0\n"	/* Store current cpu timer value */
		"	spt	%1"	/* Set new value imm. afterwards */
		: "=Q" (timer) : "Q" (expires));
	S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
	S390_lowcore.last_update_timer = expires;
}

static inline int virt_timer_forward(u64 elapsed)
{
	BUG_ON(!irqs_disabled());

	if (list_empty(&virt_timer_list))
		return 0;
	elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed);
	return elapsed >= atomic64_read(&virt_timer_current);
}

static void update_mt_scaling(void)
{
	u64 cycles_new[8], *cycles_old;
	u64 delta, fac, mult, div;
	int i;

	stcctm(MT_DIAG, smp_cpu_mtid + 1, cycles_new);
	cycles_old = this_cpu_ptr(mt_cycles);
	fac = 1;
	mult = div = 0;
	for (i = 0; i <= smp_cpu_mtid; i++) {
		delta = cycles_new[i] - cycles_old[i];
		div += delta;
		mult *= i + 1;
		mult += delta * fac;
		fac *= i + 1;
	}
	div *= fac;
	if (div > 0) {
		/* Update scaling factor */
		__this_cpu_write(mt_scaling_mult, mult);
		__this_cpu_write(mt_scaling_div, div);
		memcpy(cycles_old, cycles_new,
		       sizeof(u64) * (smp_cpu_mtid + 1));
	}
	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
}

static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
{
	u64 delta;

	delta = new - *tsk_vtime;
	*tsk_vtime = new;
	return delta;
}


static inline u64 scale_vtime(u64 vtime)
{
	u64 mult = __this_cpu_read(mt_scaling_mult);
	u64 div = __this_cpu_read(mt_scaling_div);

	if (smp_cpu_mtid)
		return vtime * mult / div;
	return vtime;
}

static void account_system_index_scaled(struct task_struct *p, u64 cputime,
					enum cpu_usage_stat index)
{
	p->stimescaled += cputime_to_nsecs(scale_vtime(cputime));
	account_system_index_time(p, cputime_to_nsecs(cputime), index);
}

/*
 * Update process times based on virtual cpu times stored by entry.S
 * to the lowcore fields user_timer, system_timer & steal_clock.
 */
static int do_account_vtime(struct task_struct *tsk)
{
	u64 timer, clock, user, guest, system, hardirq, softirq;

	timer = S390_lowcore.last_update_timer;
	clock = S390_lowcore.last_update_clock;
	/* Use STORE CLOCK by default, STORE CLOCK FAST if available. */
	alternative_io("stpt %0\n .insn s,0xb2050000,%1\n",
		       "stpt %0\n .insn s,0xb27c0000,%1\n",
		       25,
		       ASM_OUTPUT2("=Q" (S390_lowcore.last_update_timer),
				   "=Q" (S390_lowcore.last_update_clock)),
		       ASM_NO_INPUT_CLOBBER("cc"));
	clock = S390_lowcore.last_update_clock - clock;
	timer -= S390_lowcore.last_update_timer;

	if (hardirq_count())
		S390_lowcore.hardirq_timer += timer;
	else
		S390_lowcore.system_timer += timer;

	/* Update MT utilization calculation */
	if (smp_cpu_mtid &&
	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
		update_mt_scaling();

	/* Calculate cputime delta */
	user = update_tsk_timer(&tsk->thread.user_timer,
				READ_ONCE(S390_lowcore.user_timer));
	guest = update_tsk_timer(&tsk->thread.guest_timer,
				 READ_ONCE(S390_lowcore.guest_timer));
	system = update_tsk_timer(&tsk->thread.system_timer,
				  READ_ONCE(S390_lowcore.system_timer));
	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
				   READ_ONCE(S390_lowcore.hardirq_timer));
	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
				   READ_ONCE(S390_lowcore.softirq_timer));
	S390_lowcore.steal_timer +=
		clock - user - guest - system - hardirq - softirq;

	/* Push account value */
	if (user) {
		account_user_time(tsk, cputime_to_nsecs(user));
		tsk->utimescaled += cputime_to_nsecs(scale_vtime(user));
	}

	if (guest) {
		account_guest_time(tsk, cputime_to_nsecs(guest));
		tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest));
	}

	if (system)
		account_system_index_scaled(tsk, system, CPUTIME_SYSTEM);
	if (hardirq)
		account_system_index_scaled(tsk, hardirq, CPUTIME_IRQ);
	if (softirq)
		account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);

	return virt_timer_forward(user + guest + system + hardirq + softirq);
}

void vtime_task_switch(struct task_struct *prev)
{
	do_account_vtime(prev);
	prev->thread.user_timer = S390_lowcore.user_timer;
	prev->thread.guest_timer = S390_lowcore.guest_timer;
	prev->thread.system_timer = S390_lowcore.system_timer;
	prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
	prev->thread.softirq_timer = S390_lowcore.softirq_timer;
	S390_lowcore.user_timer = current->thread.user_timer;
	S390_lowcore.guest_timer = current->thread.guest_timer;
	S390_lowcore.system_timer = current->thread.system_timer;
	S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
	S390_lowcore.softirq_timer = current->thread.softirq_timer;
}

/*
 * In s390, accounting pending user time also implies
 * accounting system time in order to correctly compute
 * the stolen time accounting.
 */
void vtime_flush(struct task_struct *tsk)
{
	u64 steal, avg_steal;

	if (do_account_vtime(tsk))
		virt_timer_expire();

	steal = S390_lowcore.steal_timer;
	avg_steal = S390_lowcore.avg_steal_timer / 2;
	if ((s64) steal > 0) {
		S390_lowcore.steal_timer = 0;
		account_steal_time(cputime_to_nsecs(steal));
		avg_steal += steal;
	}
	S390_lowcore.avg_steal_timer = avg_steal;
}

static u64 vtime_delta(void)
{
	u64 timer = S390_lowcore.last_update_timer;

	S390_lowcore.last_update_timer = get_vtimer();

	return timer - S390_lowcore.last_update_timer;
}

/*
 * Update process times based on virtual cpu times stored by entry.S
 * to the lowcore fields user_timer, system_timer & steal_clock.
 */
void vtime_account_kernel(struct task_struct *tsk)
{
	u64 delta = vtime_delta();

	if (tsk->flags & PF_VCPU)
		S390_lowcore.guest_timer += delta;
	else
		S390_lowcore.system_timer += delta;

	virt_timer_forward(delta);
}
EXPORT_SYMBOL_GPL(vtime_account_kernel);

void vtime_account_softirq(struct task_struct *tsk)
{
	u64 delta = vtime_delta();

	S390_lowcore.softirq_timer += delta;

	virt_timer_forward(delta);
}

void vtime_account_hardirq(struct task_struct *tsk)
{
	u64 delta = vtime_delta();

	S390_lowcore.hardirq_timer += delta;

	virt_timer_forward(delta);
}

/*
 * Sorted add to a list. List is linear searched until first bigger
 * element is found.
 */
static void list_add_sorted(struct vtimer_list *timer, struct list_head *head)
{
	struct vtimer_list *tmp;

	list_for_each_entry(tmp, head, entry) {
		if (tmp->expires > timer->expires) {
			list_add_tail(&timer->entry, &tmp->entry);
			return;
		}
	}
	list_add_tail(&timer->entry, head);
}

/*
 * Handler for expired virtual CPU timer.
 */
static void virt_timer_expire(void)
{
	struct vtimer_list *timer, *tmp;
	unsigned long elapsed;
	LIST_HEAD(cb_list);

	/* walk timer list, fire all expired timers */
	spin_lock(&virt_timer_lock);
	elapsed = atomic64_read(&virt_timer_elapsed);
	list_for_each_entry_safe(timer, tmp, &virt_timer_list, entry) {
		if (timer->expires < elapsed)
			/* move expired timer to the callback queue */
			list_move_tail(&timer->entry, &cb_list);
		else
			timer->expires -= elapsed;
	}
	if (!list_empty(&virt_timer_list)) {
		timer = list_first_entry(&virt_timer_list,
					 struct vtimer_list, entry);
		atomic64_set(&virt_timer_current, timer->expires);
	}
	atomic64_sub(elapsed, &virt_timer_elapsed);
	spin_unlock(&virt_timer_lock);

	/* Do callbacks and recharge periodic timers */
	list_for_each_entry_safe(timer, tmp, &cb_list, entry) {
		list_del_init(&timer->entry);
		timer->function(timer->data);
		if (timer->interval) {
			/* Recharge interval timer */
			timer->expires = timer->interval +
				atomic64_read(&virt_timer_elapsed);
			spin_lock(&virt_timer_lock);
			list_add_sorted(timer, &virt_timer_list);
			spin_unlock(&virt_timer_lock);
		}
	}
}

void init_virt_timer(struct vtimer_list *timer)
{
	timer->function = NULL;
	INIT_LIST_HEAD(&timer->entry);
}
EXPORT_SYMBOL(init_virt_timer);

static inline int vtimer_pending(struct vtimer_list *timer)
{
	return !list_empty(&timer->entry);
}

static void internal_add_vtimer(struct vtimer_list *timer)
{
	if (list_empty(&virt_timer_list)) {
		/* First timer, just program it. */
		atomic64_set(&virt_timer_current, timer->expires);
		atomic64_set(&virt_timer_elapsed, 0);
		list_add(&timer->entry, &virt_timer_list);
	} else {
		/* Update timer against current base. */
		timer->expires += atomic64_read(&virt_timer_elapsed);
		if (likely((s64) timer->expires <
			   (s64) atomic64_read(&virt_timer_current)))
			/* The new timer expires before the current timer. */
			atomic64_set(&virt_timer_current, timer->expires);
		/* Insert new timer into the list. */
		list_add_sorted(timer, &virt_timer_list);
	}
}

static void __add_vtimer(struct vtimer_list *timer, int periodic)
{
	unsigned long flags;

	timer->interval = periodic ? timer->expires : 0;
	spin_lock_irqsave(&virt_timer_lock, flags);
	internal_add_vtimer(timer);
	spin_unlock_irqrestore(&virt_timer_lock, flags);
}

/*
 * add_virt_timer - add a oneshot virtual CPU timer
 */
void add_virt_timer(struct vtimer_list *timer)
{
	__add_vtimer(timer, 0);
}
EXPORT_SYMBOL(add_virt_timer);

/*
 * add_virt_timer_int - add an interval virtual CPU timer
 */
void add_virt_timer_periodic(struct vtimer_list *timer)
{
	__add_vtimer(timer, 1);
}
EXPORT_SYMBOL(add_virt_timer_periodic);

static int __mod_vtimer(struct vtimer_list *timer, u64 expires, int periodic)
{
	unsigned long flags;
	int rc;

	BUG_ON(!timer->function);

	if (timer->expires == expires && vtimer_pending(timer))
		return 1;
	spin_lock_irqsave(&virt_timer_lock, flags);
	rc = vtimer_pending(timer);
	if (rc)
		list_del_init(&timer->entry);
	timer->interval = periodic ? expires : 0;
	timer->expires = expires;
	internal_add_vtimer(timer);
	spin_unlock_irqrestore(&virt_timer_lock, flags);
	return rc;
}

/*
 * returns whether it has modified a pending timer (1) or not (0)
 */
int mod_virt_timer(struct vtimer_list *timer, u64 expires)
{
	return __mod_vtimer(timer, expires, 0);
}
EXPORT_SYMBOL(mod_virt_timer);

/*
 * returns whether it has modified a pending timer (1) or not (0)
 */
int mod_virt_timer_periodic(struct vtimer_list *timer, u64 expires)
{
	return __mod_vtimer(timer, expires, 1);
}
EXPORT_SYMBOL(mod_virt_timer_periodic);

/*
 * Delete a virtual timer.
 *
 * returns whether the deleted timer was pending (1) or not (0)
 */
int del_virt_timer(struct vtimer_list *timer)
{
	unsigned long flags;

	if (!vtimer_pending(timer))
		return 0;
	spin_lock_irqsave(&virt_timer_lock, flags);
	list_del_init(&timer->entry);
	spin_unlock_irqrestore(&virt_timer_lock, flags);
	return 1;
}
EXPORT_SYMBOL(del_virt_timer);

/*
 * Start the virtual CPU timer on the current CPU.
 */
void vtime_init(void)
{
	/* set initial cpu timer */
	set_vtimer(VTIMER_MAX_SLICE);
	/* Setup initial MT scaling values */
	if (smp_cpu_mtid) {
		__this_cpu_write(mt_scaling_jiffies, jiffies);
		__this_cpu_write(mt_scaling_mult, 1);
		__this_cpu_write(mt_scaling_div, 1);
		stcctm(MT_DIAG, smp_cpu_mtid + 1, this_cpu_ptr(mt_cycles));
	}
}