summaryrefslogtreecommitdiffstats
path: root/mm/damon/vaddr.c
blob: 35fe49080ee99636f045d3f8c785319947eadf4f (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
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
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
// SPDX-License-Identifier: GPL-2.0
/*
 * DAMON Primitives for Virtual Address Spaces
 *
 * Author: SeongJae Park <sjpark@amazon.de>
 */

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

#include <asm-generic/mman-common.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagewalk.h>

#include "prmtv-common.h"

#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
#undef DAMON_MIN_REGION
#define DAMON_MIN_REGION 1
#endif

/*
 * 't->id' should be the pointer to the relevant 'struct pid' having reference
 * count.  Caller must put the returned task, unless it is NULL.
 */
#define damon_get_task_struct(t) \
	(get_pid_task((struct pid *)t->id, PIDTYPE_PID))

/*
 * Get the mm_struct of the given target
 *
 * Caller _must_ put the mm_struct after use, unless it is NULL.
 *
 * Returns the mm_struct of the target on success, NULL on failure
 */
static struct mm_struct *damon_get_mm(struct damon_target *t)
{
	struct task_struct *task;
	struct mm_struct *mm;

	task = damon_get_task_struct(t);
	if (!task)
		return NULL;

	mm = get_task_mm(task);
	put_task_struct(task);
	return mm;
}

/*
 * Functions for the initial monitoring target regions construction
 */

/*
 * Size-evenly split a region into 'nr_pieces' small regions
 *
 * Returns 0 on success, or negative error code otherwise.
 */
static int damon_va_evenly_split_region(struct damon_target *t,
		struct damon_region *r, unsigned int nr_pieces)
{
	unsigned long sz_orig, sz_piece, orig_end;
	struct damon_region *n = NULL, *next;
	unsigned long start;

	if (!r || !nr_pieces)
		return -EINVAL;

	orig_end = r->ar.end;
	sz_orig = r->ar.end - r->ar.start;
	sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, DAMON_MIN_REGION);

	if (!sz_piece)
		return -EINVAL;

	r->ar.end = r->ar.start + sz_piece;
	next = damon_next_region(r);
	for (start = r->ar.end; start + sz_piece <= orig_end;
			start += sz_piece) {
		n = damon_new_region(start, start + sz_piece);
		if (!n)
			return -ENOMEM;
		damon_insert_region(n, r, next, t);
		r = n;
	}
	/* complement last region for possible rounding error */
	if (n)
		n->ar.end = orig_end;

	return 0;
}

static unsigned long sz_range(struct damon_addr_range *r)
{
	return r->end - r->start;
}

static void swap_ranges(struct damon_addr_range *r1,
			struct damon_addr_range *r2)
{
	struct damon_addr_range tmp;

	tmp = *r1;
	*r1 = *r2;
	*r2 = tmp;
}

/*
 * Find three regions separated by two biggest unmapped regions
 *
 * vma		the head vma of the target address space
 * regions	an array of three address ranges that results will be saved
 *
 * This function receives an address space and finds three regions in it which
 * separated by the two biggest unmapped regions in the space.  Please refer to
 * below comments of '__damon_va_init_regions()' function to know why this is
 * necessary.
 *
 * Returns 0 if success, or negative error code otherwise.
 */
static int __damon_va_three_regions(struct vm_area_struct *vma,
				       struct damon_addr_range regions[3])
{
	struct damon_addr_range gap = {0}, first_gap = {0}, second_gap = {0};
	struct vm_area_struct *last_vma = NULL;
	unsigned long start = 0;
	struct rb_root rbroot;

	/* Find two biggest gaps so that first_gap > second_gap > others */
	for (; vma; vma = vma->vm_next) {
		if (!last_vma) {
			start = vma->vm_start;
			goto next;
		}

		if (vma->rb_subtree_gap <= sz_range(&second_gap)) {
			rbroot.rb_node = &vma->vm_rb;
			vma = rb_entry(rb_last(&rbroot),
					struct vm_area_struct, vm_rb);
			goto next;
		}

		gap.start = last_vma->vm_end;
		gap.end = vma->vm_start;
		if (sz_range(&gap) > sz_range(&second_gap)) {
			swap_ranges(&gap, &second_gap);
			if (sz_range(&second_gap) > sz_range(&first_gap))
				swap_ranges(&second_gap, &first_gap);
		}
next:
		last_vma = vma;
	}

	if (!sz_range(&second_gap) || !sz_range(&first_gap))
		return -EINVAL;

	/* Sort the two biggest gaps by address */
	if (first_gap.start > second_gap.start)
		swap_ranges(&first_gap, &second_gap);

	/* Store the result */
	regions[0].start = ALIGN(start, DAMON_MIN_REGION);
	regions[0].end = ALIGN(first_gap.start, DAMON_MIN_REGION);
	regions[1].start = ALIGN(first_gap.end, DAMON_MIN_REGION);
	regions[1].end = ALIGN(second_gap.start, DAMON_MIN_REGION);
	regions[2].start = ALIGN(second_gap.end, DAMON_MIN_REGION);
	regions[2].end = ALIGN(last_vma->vm_end, DAMON_MIN_REGION);

	return 0;
}

/*
 * Get the three regions in the given target (task)
 *
 * Returns 0 on success, negative error code otherwise.
 */
static int damon_va_three_regions(struct damon_target *t,
				struct damon_addr_range regions[3])
{
	struct mm_struct *mm;
	int rc;

	mm = damon_get_mm(t);
	if (!mm)
		return -EINVAL;

	mmap_read_lock(mm);
	rc = __damon_va_three_regions(mm->mmap, regions);
	mmap_read_unlock(mm);

	mmput(mm);
	return rc;
}

/*
 * Initialize the monitoring target regions for the given target (task)
 *
 * t	the given target
 *
 * Because only a number of small portions of the entire address space
 * is actually mapped to the memory and accessed, monitoring the unmapped
 * regions is wasteful.  That said, because we can deal with small noises,
 * tracking every mapping is not strictly required but could even incur a high
 * overhead if the mapping frequently changes or the number of mappings is
 * high.  The adaptive regions adjustment mechanism will further help to deal
 * with the noise by simply identifying the unmapped areas as a region that
 * has no access.  Moreover, applying the real mappings that would have many
 * unmapped areas inside will make the adaptive mechanism quite complex.  That
 * said, too huge unmapped areas inside the monitoring target should be removed
 * to not take the time for the adaptive mechanism.
 *
 * For the reason, we convert the complex mappings to three distinct regions
 * that cover every mapped area of the address space.  Also the two gaps
 * between the three regions are the two biggest unmapped areas in the given
 * address space.  In detail, this function first identifies the start and the
 * end of the mappings and the two biggest unmapped areas of the address space.
 * Then, it constructs the three regions as below:
 *
 *     [mappings[0]->start, big_two_unmapped_areas[0]->start)
 *     [big_two_unmapped_areas[0]->end, big_two_unmapped_areas[1]->start)
 *     [big_two_unmapped_areas[1]->end, mappings[nr_mappings - 1]->end)
 *
 * As usual memory map of processes is as below, the gap between the heap and
 * the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed
 * region and the stack will be two biggest unmapped regions.  Because these
 * gaps are exceptionally huge areas in usual address space, excluding these
 * two biggest unmapped regions will be sufficient to make a trade-off.
 *
 *   <heap>
 *   <BIG UNMAPPED REGION 1>
 *   <uppermost mmap()-ed region>
 *   (other mmap()-ed regions and small unmapped regions)
 *   <lowermost mmap()-ed region>
 *   <BIG UNMAPPED REGION 2>
 *   <stack>
 */
static void __damon_va_init_regions(struct damon_ctx *ctx,
				     struct damon_target *t)
{
	struct damon_region *r;
	struct damon_addr_range regions[3];
	unsigned long sz = 0, nr_pieces;
	int i;

	if (damon_va_three_regions(t, regions)) {
		pr_err("Failed to get three regions of target %lu\n", t->id);
		return;
	}

	for (i = 0; i < 3; i++)
		sz += regions[i].end - regions[i].start;
	if (ctx->min_nr_regions)
		sz /= ctx->min_nr_regions;
	if (sz < DAMON_MIN_REGION)
		sz = DAMON_MIN_REGION;

	/* Set the initial three regions of the target */
	for (i = 0; i < 3; i++) {
		r = damon_new_region(regions[i].start, regions[i].end);
		if (!r) {
			pr_err("%d'th init region creation failed\n", i);
			return;
		}
		damon_add_region(r, t);

		nr_pieces = (regions[i].end - regions[i].start) / sz;
		damon_va_evenly_split_region(t, r, nr_pieces);
	}
}

/* Initialize '->regions_list' of every target (task) */
void damon_va_init(struct damon_ctx *ctx)
{
	struct damon_target *t;

	damon_for_each_target(t, ctx) {
		/* the user may set the target regions as they want */
		if (!damon_nr_regions(t))
			__damon_va_init_regions(ctx, t);
	}
}

/*
 * Functions for the dynamic monitoring target regions update
 */

/*
 * Check whether a region is intersecting an address range
 *
 * Returns true if it is.
 */
static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re)
{
	return !(r->ar.end <= re->start || re->end <= r->ar.start);
}

/*
 * Update damon regions for the three big regions of the given target
 *
 * t		the given target
 * bregions	the three big regions of the target
 */
static void damon_va_apply_three_regions(struct damon_target *t,
		struct damon_addr_range bregions[3])
{
	struct damon_region *r, *next;
	unsigned int i;

	/* Remove regions which are not in the three big regions now */
	damon_for_each_region_safe(r, next, t) {
		for (i = 0; i < 3; i++) {
			if (damon_intersect(r, &bregions[i]))
				break;
		}
		if (i == 3)
			damon_destroy_region(r, t);
	}

	/* Adjust intersecting regions to fit with the three big regions */
	for (i = 0; i < 3; i++) {
		struct damon_region *first = NULL, *last;
		struct damon_region *newr;
		struct damon_addr_range *br;

		br = &bregions[i];
		/* Get the first and last regions which intersects with br */
		damon_for_each_region(r, t) {
			if (damon_intersect(r, br)) {
				if (!first)
					first = r;
				last = r;
			}
			if (r->ar.start >= br->end)
				break;
		}
		if (!first) {
			/* no damon_region intersects with this big region */
			newr = damon_new_region(
					ALIGN_DOWN(br->start,
						DAMON_MIN_REGION),
					ALIGN(br->end, DAMON_MIN_REGION));
			if (!newr)
				continue;
			damon_insert_region(newr, damon_prev_region(r), r, t);
		} else {
			first->ar.start = ALIGN_DOWN(br->start,
					DAMON_MIN_REGION);
			last->ar.end = ALIGN(br->end, DAMON_MIN_REGION);
		}
	}
}

/*
 * Update regions for current memory mappings
 */
void damon_va_update(struct damon_ctx *ctx)
{
	struct damon_addr_range three_regions[3];
	struct damon_target *t;

	damon_for_each_target(t, ctx) {
		if (damon_va_three_regions(t, three_regions))
			continue;
		damon_va_apply_three_regions(t, three_regions);
	}
}

static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
		unsigned long next, struct mm_walk *walk)
{
	pte_t *pte;
	spinlock_t *ptl;

	if (pmd_huge(*pmd)) {
		ptl = pmd_lock(walk->mm, pmd);
		if (pmd_huge(*pmd)) {
			damon_pmdp_mkold(pmd, walk->mm, addr);
			spin_unlock(ptl);
			return 0;
		}
		spin_unlock(ptl);
	}

	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		return 0;
	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
	if (!pte_present(*pte))
		goto out;
	damon_ptep_mkold(pte, walk->mm, addr);
out:
	pte_unmap_unlock(pte, ptl);
	return 0;
}

static const struct mm_walk_ops damon_mkold_ops = {
	.pmd_entry = damon_mkold_pmd_entry,
};

static void damon_va_mkold(struct mm_struct *mm, unsigned long addr)
{
	mmap_read_lock(mm);
	walk_page_range(mm, addr, addr + 1, &damon_mkold_ops, NULL);
	mmap_read_unlock(mm);
}

/*
 * Functions for the access checking of the regions
 */

static void damon_va_prepare_access_check(struct damon_ctx *ctx,
			struct mm_struct *mm, struct damon_region *r)
{
	r->sampling_addr = damon_rand(r->ar.start, r->ar.end);

	damon_va_mkold(mm, r->sampling_addr);
}

void damon_va_prepare_access_checks(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct mm_struct *mm;
	struct damon_region *r;

	damon_for_each_target(t, ctx) {
		mm = damon_get_mm(t);
		if (!mm)
			continue;
		damon_for_each_region(r, t)
			damon_va_prepare_access_check(ctx, mm, r);
		mmput(mm);
	}
}

struct damon_young_walk_private {
	unsigned long *page_sz;
	bool young;
};

static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr,
		unsigned long next, struct mm_walk *walk)
{
	pte_t *pte;
	spinlock_t *ptl;
	struct page *page;
	struct damon_young_walk_private *priv = walk->private;

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	if (pmd_huge(*pmd)) {
		ptl = pmd_lock(walk->mm, pmd);
		if (!pmd_huge(*pmd)) {
			spin_unlock(ptl);
			goto regular_page;
		}
		page = damon_get_page(pmd_pfn(*pmd));
		if (!page)
			goto huge_out;
		if (pmd_young(*pmd) || !page_is_idle(page) ||
					mmu_notifier_test_young(walk->mm,
						addr)) {
			*priv->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
			priv->young = true;
		}
		put_page(page);
huge_out:
		spin_unlock(ptl);
		return 0;
	}

regular_page:
#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */

	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
		return -EINVAL;
	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
	if (!pte_present(*pte))
		goto out;
	page = damon_get_page(pte_pfn(*pte));
	if (!page)
		goto out;
	if (pte_young(*pte) || !page_is_idle(page) ||
			mmu_notifier_test_young(walk->mm, addr)) {
		*priv->page_sz = PAGE_SIZE;
		priv->young = true;
	}
	put_page(page);
out:
	pte_unmap_unlock(pte, ptl);
	return 0;
}

static const struct mm_walk_ops damon_young_ops = {
	.pmd_entry = damon_young_pmd_entry,
};

static bool damon_va_young(struct mm_struct *mm, unsigned long addr,
		unsigned long *page_sz)
{
	struct damon_young_walk_private arg = {
		.page_sz = page_sz,
		.young = false,
	};

	mmap_read_lock(mm);
	walk_page_range(mm, addr, addr + 1, &damon_young_ops, &arg);
	mmap_read_unlock(mm);
	return arg.young;
}

/*
 * Check whether the region was accessed after the last preparation
 *
 * mm	'mm_struct' for the given virtual address space
 * r	the region to be checked
 */
static void damon_va_check_access(struct damon_ctx *ctx,
			       struct mm_struct *mm, struct damon_region *r)
{
	static struct mm_struct *last_mm;
	static unsigned long last_addr;
	static unsigned long last_page_sz = PAGE_SIZE;
	static bool last_accessed;

	/* If the region is in the last checked page, reuse the result */
	if (mm == last_mm && (ALIGN_DOWN(last_addr, last_page_sz) ==
				ALIGN_DOWN(r->sampling_addr, last_page_sz))) {
		if (last_accessed)
			r->nr_accesses++;
		return;
	}

	last_accessed = damon_va_young(mm, r->sampling_addr, &last_page_sz);
	if (last_accessed)
		r->nr_accesses++;

	last_mm = mm;
	last_addr = r->sampling_addr;
}

unsigned int damon_va_check_accesses(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct mm_struct *mm;
	struct damon_region *r;
	unsigned int max_nr_accesses = 0;

	damon_for_each_target(t, ctx) {
		mm = damon_get_mm(t);
		if (!mm)
			continue;
		damon_for_each_region(r, t) {
			damon_va_check_access(ctx, mm, r);
			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
		}
		mmput(mm);
	}

	return max_nr_accesses;
}

/*
 * Functions for the target validity check and cleanup
 */

bool damon_va_target_valid(void *target)
{
	struct damon_target *t = target;
	struct task_struct *task;

	task = damon_get_task_struct(t);
	if (task) {
		put_task_struct(task);
		return true;
	}

	return false;
}

#ifndef CONFIG_ADVISE_SYSCALLS
static int damos_madvise(struct damon_target *target, struct damon_region *r,
			int behavior)
{
	return -EINVAL;
}
#else
static int damos_madvise(struct damon_target *target, struct damon_region *r,
			int behavior)
{
	struct mm_struct *mm;
	int ret = -ENOMEM;

	mm = damon_get_mm(target);
	if (!mm)
		goto out;

	ret = do_madvise(mm, PAGE_ALIGN(r->ar.start),
			PAGE_ALIGN(r->ar.end - r->ar.start), behavior);
	mmput(mm);
out:
	return ret;
}
#endif	/* CONFIG_ADVISE_SYSCALLS */

int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
		struct damon_region *r, struct damos *scheme)
{
	int madv_action;

	switch (scheme->action) {
	case DAMOS_WILLNEED:
		madv_action = MADV_WILLNEED;
		break;
	case DAMOS_COLD:
		madv_action = MADV_COLD;
		break;
	case DAMOS_PAGEOUT:
		madv_action = MADV_PAGEOUT;
		break;
	case DAMOS_HUGEPAGE:
		madv_action = MADV_HUGEPAGE;
		break;
	case DAMOS_NOHUGEPAGE:
		madv_action = MADV_NOHUGEPAGE;
		break;
	case DAMOS_STAT:
		return 0;
	default:
		pr_warn("Wrong action %d\n", scheme->action);
		return -EINVAL;
	}

	return damos_madvise(t, r, madv_action);
}

int damon_va_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_pageout_score(context, r, scheme);
	default:
		break;
	}

	return DAMOS_MAX_SCORE;
}

void damon_va_set_primitives(struct damon_ctx *ctx)
{
	ctx->primitive.init = damon_va_init;
	ctx->primitive.update = damon_va_update;
	ctx->primitive.prepare_access_checks = damon_va_prepare_access_checks;
	ctx->primitive.check_accesses = damon_va_check_accesses;
	ctx->primitive.reset_aggregated = NULL;
	ctx->primitive.target_valid = damon_va_target_valid;
	ctx->primitive.cleanup = NULL;
	ctx->primitive.apply_scheme = damon_va_apply_scheme;
	ctx->primitive.get_scheme_score = damon_va_scheme_score;
}

#include "vaddr-test.h"