summaryrefslogtreecommitdiff
path: root/mm/damon/paddr.c
blob: a9ff35341d65d22d89dec521c374ab9bb58a4f64 (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
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
// SPDX-License-Identifier: GPL-2.0
/*
 * DAMON Primitives for The Physical Address Space
 *
 * Author: SeongJae Park <sj@kernel.org>
 */

#define pr_fmt(fmt) "damon-pa: " fmt

#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/memory-tiers.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>

#include "../internal.h"
#include "ops-common.h"

static bool damon_folio_mkold_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr, void *arg)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);

	while (page_vma_mapped_walk(&pvmw)) {
		addr = pvmw.address;
		if (pvmw.pte)
			damon_ptep_mkold(pvmw.pte, vma, addr);
		else
			damon_pmdp_mkold(pvmw.pmd, vma, addr);
	}
	return true;
}

static void damon_folio_mkold(struct folio *folio)
{
	struct rmap_walk_control rwc = {
		.rmap_one = damon_folio_mkold_one,
		.anon_lock = folio_lock_anon_vma_read,
	};
	bool need_lock;

	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
		folio_set_idle(folio);
		return;
	}

	need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
	if (need_lock && !folio_trylock(folio))
		return;

	rmap_walk(folio, &rwc);

	if (need_lock)
		folio_unlock(folio);

}

static void damon_pa_mkold(unsigned long paddr)
{
	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));

	if (!folio)
		return;

	damon_folio_mkold(folio);
	folio_put(folio);
}

static void __damon_pa_prepare_access_check(struct damon_region *r)
{
	r->sampling_addr = damon_rand(r->ar.start, r->ar.end);

	damon_pa_mkold(r->sampling_addr);
}

static void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct damon_region *r;

	damon_for_each_target(t, ctx) {
		damon_for_each_region(r, t)
			__damon_pa_prepare_access_check(r);
	}
}

static bool damon_folio_young_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr, void *arg)
{
	bool *accessed = arg;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);

	*accessed = false;
	while (page_vma_mapped_walk(&pvmw)) {
		addr = pvmw.address;
		if (pvmw.pte) {
			*accessed = pte_young(ptep_get(pvmw.pte)) ||
				!folio_test_idle(folio) ||
				mmu_notifier_test_young(vma->vm_mm, addr);
		} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			*accessed = pmd_young(pmdp_get(pvmw.pmd)) ||
				!folio_test_idle(folio) ||
				mmu_notifier_test_young(vma->vm_mm, addr);
#else
			WARN_ON_ONCE(1);
#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
		}
		if (*accessed) {
			page_vma_mapped_walk_done(&pvmw);
			break;
		}
	}

	/* If accessed, stop walking */
	return *accessed == false;
}

static bool damon_folio_young(struct folio *folio)
{
	bool accessed = false;
	struct rmap_walk_control rwc = {
		.arg = &accessed,
		.rmap_one = damon_folio_young_one,
		.anon_lock = folio_lock_anon_vma_read,
	};
	bool need_lock;

	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
		if (folio_test_idle(folio))
			return false;
		else
			return true;
	}

	need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
	if (need_lock && !folio_trylock(folio))
		return false;

	rmap_walk(folio, &rwc);

	if (need_lock)
		folio_unlock(folio);

	return accessed;
}

static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz)
{
	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
	bool accessed;

	if (!folio)
		return false;

	accessed = damon_folio_young(folio);
	*folio_sz = folio_size(folio);
	folio_put(folio);
	return accessed;
}

static void __damon_pa_check_access(struct damon_region *r,
		struct damon_attrs *attrs)
{
	static unsigned long last_addr;
	static unsigned long last_folio_sz = PAGE_SIZE;
	static bool last_accessed;

	/* If the region is in the last checked page, reuse the result */
	if (ALIGN_DOWN(last_addr, last_folio_sz) ==
				ALIGN_DOWN(r->sampling_addr, last_folio_sz)) {
		damon_update_region_access_rate(r, last_accessed, attrs);
		return;
	}

	last_accessed = damon_pa_young(r->sampling_addr, &last_folio_sz);
	damon_update_region_access_rate(r, last_accessed, attrs);

	last_addr = r->sampling_addr;
}

static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct damon_region *r;
	unsigned int max_nr_accesses = 0;

	damon_for_each_target(t, ctx) {
		damon_for_each_region(r, t) {
			__damon_pa_check_access(r, &ctx->attrs);
			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
		}
	}

	return max_nr_accesses;
}

static bool __damos_pa_filter_out(struct damos_filter *filter,
		struct folio *folio)
{
	bool matched = false;
	struct mem_cgroup *memcg;

	switch (filter->type) {
	case DAMOS_FILTER_TYPE_ANON:
		matched = folio_test_anon(folio);
		break;
	case DAMOS_FILTER_TYPE_MEMCG:
		rcu_read_lock();
		memcg = folio_memcg_check(folio);
		if (!memcg)
			matched = false;
		else
			matched = filter->memcg_id == mem_cgroup_id(memcg);
		rcu_read_unlock();
		break;
	case DAMOS_FILTER_TYPE_YOUNG:
		matched = damon_folio_young(folio);
		if (matched)
			damon_folio_mkold(folio);
		break;
	default:
		break;
	}

	return matched == filter->matching;
}

/*
 * damos_pa_filter_out - Return true if the page should be filtered out.
 */
static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio)
{
	struct damos_filter *filter;

	damos_for_each_filter(filter, scheme) {
		if (__damos_pa_filter_out(filter, folio))
			return true;
	}
	return false;
}

static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
{
	unsigned long addr, applied;
	LIST_HEAD(folio_list);
	bool install_young_filter = true;
	struct damos_filter *filter;

	/* check access in page level again by default */
	damos_for_each_filter(filter, s) {
		if (filter->type == DAMOS_FILTER_TYPE_YOUNG) {
			install_young_filter = false;
			break;
		}
	}
	if (install_young_filter) {
		filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, true);
		if (!filter)
			return 0;
		damos_add_filter(s, filter);
	}

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		folio_clear_referenced(folio);
		folio_test_clear_young(folio);
		if (!folio_isolate_lru(folio))
			goto put_folio;
		if (folio_test_unevictable(folio))
			folio_putback_lru(folio);
		else
			list_add(&folio->lru, &folio_list);
put_folio:
		folio_put(folio);
	}
	if (install_young_filter)
		damos_destroy_filter(filter);
	applied = reclaim_pages(&folio_list);
	cond_resched();
	return applied * PAGE_SIZE;
}

static inline unsigned long damon_pa_mark_accessed_or_deactivate(
		struct damon_region *r, struct damos *s, bool mark_accessed)
{
	unsigned long addr, applied = 0;

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		if (mark_accessed)
			folio_mark_accessed(folio);
		else
			folio_deactivate(folio);
		applied += folio_nr_pages(folio);
put_folio:
		folio_put(folio);
	}
	return applied * PAGE_SIZE;
}

static unsigned long damon_pa_mark_accessed(struct damon_region *r,
	struct damos *s)
{
	return damon_pa_mark_accessed_or_deactivate(r, s, true);
}

static unsigned long damon_pa_deactivate_pages(struct damon_region *r,
	struct damos *s)
{
	return damon_pa_mark_accessed_or_deactivate(r, s, false);
}

static unsigned int __damon_pa_migrate_folio_list(
		struct list_head *migrate_folios, struct pglist_data *pgdat,
		int target_nid)
{
	unsigned int nr_succeeded = 0;
	nodemask_t allowed_mask = NODE_MASK_NONE;
	struct migration_target_control mtc = {
		/*
		 * Allocate from 'node', or fail quickly and quietly.
		 * When this happens, 'page' will likely just be discarded
		 * instead of migrated.
		 */
		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
			__GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT,
		.nid = target_nid,
		.nmask = &allowed_mask
	};

	if (pgdat->node_id == target_nid || target_nid == NUMA_NO_NODE)
		return 0;

	if (list_empty(migrate_folios))
		return 0;

	/* Migration ignores all cpuset and mempolicy settings */
	migrate_pages(migrate_folios, alloc_migrate_folio, NULL,
		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DAMON,
		      &nr_succeeded);

	return nr_succeeded;
}

static unsigned int damon_pa_migrate_folio_list(struct list_head *folio_list,
						struct pglist_data *pgdat,
						int target_nid)
{
	unsigned int nr_migrated = 0;
	struct folio *folio;
	LIST_HEAD(ret_folios);
	LIST_HEAD(migrate_folios);

	while (!list_empty(folio_list)) {
		struct folio *folio;

		cond_resched();

		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);

		if (!folio_trylock(folio))
			goto keep;

		/* Relocate its contents to another node. */
		list_add(&folio->lru, &migrate_folios);
		folio_unlock(folio);
		continue;
keep:
		list_add(&folio->lru, &ret_folios);
	}
	/* 'folio_list' is always empty here */

	/* Migrate folios selected for migration */
	nr_migrated += __damon_pa_migrate_folio_list(
			&migrate_folios, pgdat, target_nid);
	/*
	 * Folios that could not be migrated are still in @migrate_folios.  Add
	 * those back on @folio_list
	 */
	if (!list_empty(&migrate_folios))
		list_splice_init(&migrate_folios, folio_list);

	try_to_unmap_flush();

	list_splice(&ret_folios, folio_list);

	while (!list_empty(folio_list)) {
		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);
		folio_putback_lru(folio);
	}

	return nr_migrated;
}

static unsigned long damon_pa_migrate_pages(struct list_head *folio_list,
					    int target_nid)
{
	int nid;
	unsigned long nr_migrated = 0;
	LIST_HEAD(node_folio_list);
	unsigned int noreclaim_flag;

	if (list_empty(folio_list))
		return nr_migrated;

	noreclaim_flag = memalloc_noreclaim_save();

	nid = folio_nid(lru_to_folio(folio_list));
	do {
		struct folio *folio = lru_to_folio(folio_list);

		if (nid == folio_nid(folio)) {
			list_move(&folio->lru, &node_folio_list);
			continue;
		}

		nr_migrated += damon_pa_migrate_folio_list(&node_folio_list,
							   NODE_DATA(nid),
							   target_nid);
		nid = folio_nid(lru_to_folio(folio_list));
	} while (!list_empty(folio_list));

	nr_migrated += damon_pa_migrate_folio_list(&node_folio_list,
						   NODE_DATA(nid),
						   target_nid);

	memalloc_noreclaim_restore(noreclaim_flag);

	return nr_migrated;
}

static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s)
{
	unsigned long addr, applied;
	LIST_HEAD(folio_list);

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		if (!folio_isolate_lru(folio))
			goto put_folio;
		list_add(&folio->lru, &folio_list);
put_folio:
		folio_put(folio);
	}
	applied = damon_pa_migrate_pages(&folio_list, s->target_nid);
	cond_resched();
	return applied * PAGE_SIZE;
}


static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
		struct damon_target *t, struct damon_region *r,
		struct damos *scheme)
{
	switch (scheme->action) {
	case DAMOS_PAGEOUT:
		return damon_pa_pageout(r, scheme);
	case DAMOS_LRU_PRIO:
		return damon_pa_mark_accessed(r, scheme);
	case DAMOS_LRU_DEPRIO:
		return damon_pa_deactivate_pages(r, scheme);
	case DAMOS_MIGRATE_HOT:
	case DAMOS_MIGRATE_COLD:
		return damon_pa_migrate(r, scheme);
	case DAMOS_STAT:
		break;
	default:
		/* DAMOS actions that not yet supported by 'paddr'. */
		break;
	}
	return 0;
}

static int damon_pa_scheme_score(struct damon_ctx *context,
		struct damon_target *t, struct damon_region *r,
		struct damos *scheme)
{
	switch (scheme->action) {
	case DAMOS_PAGEOUT:
		return damon_cold_score(context, r, scheme);
	case DAMOS_LRU_PRIO:
		return damon_hot_score(context, r, scheme);
	case DAMOS_LRU_DEPRIO:
		return damon_cold_score(context, r, scheme);
	case DAMOS_MIGRATE_HOT:
		return damon_hot_score(context, r, scheme);
	case DAMOS_MIGRATE_COLD:
		return damon_cold_score(context, r, scheme);
	default:
		break;
	}

	return DAMOS_MAX_SCORE;
}

static int __init damon_pa_initcall(void)
{
	struct damon_operations ops = {
		.id = DAMON_OPS_PADDR,
		.init = NULL,
		.update = NULL,
		.prepare_access_checks = damon_pa_prepare_access_checks,
		.check_accesses = damon_pa_check_accesses,
		.reset_aggregated = NULL,
		.target_valid = NULL,
		.cleanup = NULL,
		.apply_scheme = damon_pa_apply_scheme,
		.get_scheme_score = damon_pa_scheme_score,
	};

	return damon_register_ops(&ops);
};

subsys_initcall(damon_pa_initcall);