summaryrefslogtreecommitdiffstats
path: root/mm/damon/core.c
blob: 947486a150ce28ce5b4f779d0415aedaf8355dce (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
/*
 * Data Access Monitor
 *
 * Author: SeongJae Park <sjpark@amazon.de>
 */

#define pr_fmt(fmt) "damon: " fmt

#include <linux/damon.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/slab.h>

static DEFINE_MUTEX(damon_lock);
static int nr_running_ctxs;

/*
 * Construct a damon_region struct
 *
 * Returns the pointer to the new struct if success, or NULL otherwise
 */
struct damon_region *damon_new_region(unsigned long start, unsigned long end)
{
	struct damon_region *region;

	region = kmalloc(sizeof(*region), GFP_KERNEL);
	if (!region)
		return NULL;

	region->ar.start = start;
	region->ar.end = end;
	region->nr_accesses = 0;
	INIT_LIST_HEAD(&region->list);

	return region;
}

/*
 * Add a region between two other regions
 */
inline void damon_insert_region(struct damon_region *r,
		struct damon_region *prev, struct damon_region *next)
{
	__list_add(&r->list, &prev->list, &next->list);
}

void damon_add_region(struct damon_region *r, struct damon_target *t)
{
	list_add_tail(&r->list, &t->regions_list);
}

static void damon_del_region(struct damon_region *r)
{
	list_del(&r->list);
}

static void damon_free_region(struct damon_region *r)
{
	kfree(r);
}

void damon_destroy_region(struct damon_region *r)
{
	damon_del_region(r);
	damon_free_region(r);
}

/*
 * Construct a damon_target struct
 *
 * Returns the pointer to the new struct if success, or NULL otherwise
 */
struct damon_target *damon_new_target(unsigned long id)
{
	struct damon_target *t;

	t = kmalloc(sizeof(*t), GFP_KERNEL);
	if (!t)
		return NULL;

	t->id = id;
	INIT_LIST_HEAD(&t->regions_list);

	return t;
}

void damon_add_target(struct damon_ctx *ctx, struct damon_target *t)
{
	list_add_tail(&t->list, &ctx->region_targets);
}

static void damon_del_target(struct damon_target *t)
{
	list_del(&t->list);
}

void damon_free_target(struct damon_target *t)
{
	struct damon_region *r, *next;

	damon_for_each_region_safe(r, next, t)
		damon_free_region(r);
	kfree(t);
}

void damon_destroy_target(struct damon_target *t)
{
	damon_del_target(t);
	damon_free_target(t);
}

struct damon_ctx *damon_new_ctx(void)
{
	struct damon_ctx *ctx;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
	if (!ctx)
		return NULL;

	ctx->sample_interval = 5 * 1000;
	ctx->aggr_interval = 100 * 1000;
	ctx->primitive_update_interval = 60 * 1000 * 1000;

	ktime_get_coarse_ts64(&ctx->last_aggregation);
	ctx->last_primitive_update = ctx->last_aggregation;

	mutex_init(&ctx->kdamond_lock);

	INIT_LIST_HEAD(&ctx->region_targets);

	return ctx;
}

static void damon_destroy_targets(struct damon_ctx *ctx)
{
	struct damon_target *t, *next_t;

	if (ctx->primitive.cleanup) {
		ctx->primitive.cleanup(ctx);
		return;
	}

	damon_for_each_target_safe(t, next_t, ctx)
		damon_destroy_target(t);
}

void damon_destroy_ctx(struct damon_ctx *ctx)
{
	damon_destroy_targets(ctx);
	kfree(ctx);
}

/**
 * damon_set_attrs() - Set attributes for the monitoring.
 * @ctx:		monitoring context
 * @sample_int:		time interval between samplings
 * @aggr_int:		time interval between aggregations
 * @primitive_upd_int:	time interval between monitoring primitive updates
 *
 * This function should not be called while the kdamond is running.
 * Every time interval is in micro-seconds.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
		    unsigned long aggr_int, unsigned long primitive_upd_int)
{
	ctx->sample_interval = sample_int;
	ctx->aggr_interval = aggr_int;
	ctx->primitive_update_interval = primitive_upd_int;

	return 0;
}

static bool damon_kdamond_running(struct damon_ctx *ctx)
{
	bool running;

	mutex_lock(&ctx->kdamond_lock);
	running = ctx->kdamond != NULL;
	mutex_unlock(&ctx->kdamond_lock);

	return running;
}

static int kdamond_fn(void *data);

/*
 * __damon_start() - Starts monitoring with given context.
 * @ctx:	monitoring context
 *
 * This function should be called while damon_lock is hold.
 *
 * Return: 0 on success, negative error code otherwise.
 */
static int __damon_start(struct damon_ctx *ctx)
{
	int err = -EBUSY;

	mutex_lock(&ctx->kdamond_lock);
	if (!ctx->kdamond) {
		err = 0;
		ctx->kdamond_stop = false;
		ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
				nr_running_ctxs);
		if (IS_ERR(ctx->kdamond)) {
			err = PTR_ERR(ctx->kdamond);
			ctx->kdamond = 0;
		}
	}
	mutex_unlock(&ctx->kdamond_lock);

	return err;
}

/**
 * damon_start() - Starts the monitorings for a given group of contexts.
 * @ctxs:	an array of the pointers for contexts to start monitoring
 * @nr_ctxs:	size of @ctxs
 *
 * This function starts a group of monitoring threads for a group of monitoring
 * contexts.  One thread per each context is created and run in parallel.  The
 * caller should handle synchronization between the threads by itself.  If a
 * group of threads that created by other 'damon_start()' call is currently
 * running, this function does nothing but returns -EBUSY.
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_start(struct damon_ctx **ctxs, int nr_ctxs)
{
	int i;
	int err = 0;

	mutex_lock(&damon_lock);
	if (nr_running_ctxs) {
		mutex_unlock(&damon_lock);
		return -EBUSY;
	}

	for (i = 0; i < nr_ctxs; i++) {
		err = __damon_start(ctxs[i]);
		if (err)
			break;
		nr_running_ctxs++;
	}
	mutex_unlock(&damon_lock);

	return err;
}

/*
 * __damon_stop() - Stops monitoring of given context.
 * @ctx:	monitoring context
 *
 * Return: 0 on success, negative error code otherwise.
 */
static int __damon_stop(struct damon_ctx *ctx)
{
	mutex_lock(&ctx->kdamond_lock);
	if (ctx->kdamond) {
		ctx->kdamond_stop = true;
		mutex_unlock(&ctx->kdamond_lock);
		while (damon_kdamond_running(ctx))
			usleep_range(ctx->sample_interval,
					ctx->sample_interval * 2);
		return 0;
	}
	mutex_unlock(&ctx->kdamond_lock);

	return -EPERM;
}

/**
 * damon_stop() - Stops the monitorings for a given group of contexts.
 * @ctxs:	an array of the pointers for contexts to stop monitoring
 * @nr_ctxs:	size of @ctxs
 *
 * Return: 0 on success, negative error code otherwise.
 */
int damon_stop(struct damon_ctx **ctxs, int nr_ctxs)
{
	int i, err = 0;

	for (i = 0; i < nr_ctxs; i++) {
		/* nr_running_ctxs is decremented in kdamond_fn */
		err = __damon_stop(ctxs[i]);
		if (err)
			return err;
	}

	return err;
}

/*
 * damon_check_reset_time_interval() - Check if a time interval is elapsed.
 * @baseline:	the time to check whether the interval has elapsed since
 * @interval:	the time interval (microseconds)
 *
 * See whether the given time interval has passed since the given baseline
 * time.  If so, it also updates the baseline to current time for next check.
 *
 * Return:	true if the time interval has passed, or false otherwise.
 */
static bool damon_check_reset_time_interval(struct timespec64 *baseline,
		unsigned long interval)
{
	struct timespec64 now;

	ktime_get_coarse_ts64(&now);
	if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) <
			interval * 1000)
		return false;
	*baseline = now;
	return true;
}

/*
 * Check whether it is time to flush the aggregated information
 */
static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
{
	return damon_check_reset_time_interval(&ctx->last_aggregation,
			ctx->aggr_interval);
}

/*
 * Reset the aggregated monitoring results ('nr_accesses' of each region).
 */
static void kdamond_reset_aggregated(struct damon_ctx *c)
{
	struct damon_target *t;

	damon_for_each_target(t, c) {
		struct damon_region *r;

		damon_for_each_region(r, t)
			r->nr_accesses = 0;
	}
}

/*
 * Check whether it is time to check and apply the target monitoring regions
 *
 * Returns true if it is.
 */
static bool kdamond_need_update_primitive(struct damon_ctx *ctx)
{
	return damon_check_reset_time_interval(&ctx->last_primitive_update,
			ctx->primitive_update_interval);
}

/*
 * Check whether current monitoring should be stopped
 *
 * The monitoring is stopped when either the user requested to stop, or all
 * monitoring targets are invalid.
 *
 * Returns true if need to stop current monitoring.
 */
static bool kdamond_need_stop(struct damon_ctx *ctx)
{
	struct damon_target *t;
	bool stop;

	mutex_lock(&ctx->kdamond_lock);
	stop = ctx->kdamond_stop;
	mutex_unlock(&ctx->kdamond_lock);
	if (stop)
		return true;

	if (!ctx->primitive.target_valid)
		return false;

	damon_for_each_target(t, ctx) {
		if (ctx->primitive.target_valid(t))
			return false;
	}

	return true;
}

static void set_kdamond_stop(struct damon_ctx *ctx)
{
	mutex_lock(&ctx->kdamond_lock);
	ctx->kdamond_stop = true;
	mutex_unlock(&ctx->kdamond_lock);
}

/*
 * The monitoring daemon that runs as a kernel thread
 */
static int kdamond_fn(void *data)
{
	struct damon_ctx *ctx = (struct damon_ctx *)data;
	struct damon_target *t;
	struct damon_region *r, *next;

	mutex_lock(&ctx->kdamond_lock);
	pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
	mutex_unlock(&ctx->kdamond_lock);

	if (ctx->primitive.init)
		ctx->primitive.init(ctx);
	if (ctx->callback.before_start && ctx->callback.before_start(ctx))
		set_kdamond_stop(ctx);

	while (!kdamond_need_stop(ctx)) {
		if (ctx->primitive.prepare_access_checks)
			ctx->primitive.prepare_access_checks(ctx);
		if (ctx->callback.after_sampling &&
				ctx->callback.after_sampling(ctx))
			set_kdamond_stop(ctx);

		usleep_range(ctx->sample_interval, ctx->sample_interval + 1);

		if (ctx->primitive.check_accesses)
			ctx->primitive.check_accesses(ctx);

		if (kdamond_aggregate_interval_passed(ctx)) {
			if (ctx->callback.after_aggregation &&
					ctx->callback.after_aggregation(ctx))
				set_kdamond_stop(ctx);
			kdamond_reset_aggregated(ctx);
			if (ctx->primitive.reset_aggregated)
				ctx->primitive.reset_aggregated(ctx);
		}

		if (kdamond_need_update_primitive(ctx)) {
			if (ctx->primitive.update)
				ctx->primitive.update(ctx);
		}
	}
	damon_for_each_target(t, ctx) {
		damon_for_each_region_safe(r, next, t)
			damon_destroy_region(r);
	}

	if (ctx->callback.before_terminate &&
			ctx->callback.before_terminate(ctx))
		set_kdamond_stop(ctx);
	if (ctx->primitive.cleanup)
		ctx->primitive.cleanup(ctx);

	pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid);
	mutex_lock(&ctx->kdamond_lock);
	ctx->kdamond = NULL;
	mutex_unlock(&ctx->kdamond_lock);

	mutex_lock(&damon_lock);
	nr_running_ctxs--;
	mutex_unlock(&damon_lock);

	do_exit(0);
}