summaryrefslogtreecommitdiff
path: root/include/linux/mm_inline.h
blob: 9ae7def16cb2a9dd14f653eb78eefd753ce5c0c0 (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef LINUX_MM_INLINE_H
#define LINUX_MM_INLINE_H

#include <linux/atomic.h>
#include <linux/huge_mm.h>
#include <linux/mm_types.h>
#include <linux/swap.h>
#include <linux/string.h>
#include <linux/userfaultfd_k.h>
#include <linux/swapops.h>

/**
 * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
 * @folio: The folio to test.
 *
 * We would like to get this info without a page flag, but the state
 * needs to survive until the folio is last deleted from the LRU, which
 * could be as far down as __page_cache_release.
 *
 * Return: An integer (not a boolean!) used to sort a folio onto the
 * right LRU list and to account folios correctly.
 * 1 if @folio is a regular filesystem backed page cache folio
 * or a lazily freed anonymous folio (e.g. via MADV_FREE).
 * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
 * ram or swap backed folio.
 */
static inline int folio_is_file_lru(struct folio *folio)
{
	return !folio_test_swapbacked(folio);
}

static inline int page_is_file_lru(struct page *page)
{
	return folio_is_file_lru(page_folio(page));
}

static __always_inline void __update_lru_size(struct lruvec *lruvec,
				enum lru_list lru, enum zone_type zid,
				long nr_pages)
{
	struct pglist_data *pgdat = lruvec_pgdat(lruvec);

	lockdep_assert_held(&lruvec->lru_lock);
	WARN_ON_ONCE(nr_pages != (int)nr_pages);

	__mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
	__mod_zone_page_state(&pgdat->node_zones[zid],
				NR_ZONE_LRU_BASE + lru, nr_pages);
}

static __always_inline void update_lru_size(struct lruvec *lruvec,
				enum lru_list lru, enum zone_type zid,
				long nr_pages)
{
	__update_lru_size(lruvec, lru, zid, nr_pages);
#ifdef CONFIG_MEMCG
	mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
#endif
}

/**
 * __folio_clear_lru_flags - Clear page lru flags before releasing a page.
 * @folio: The folio that was on lru and now has a zero reference.
 */
static __always_inline void __folio_clear_lru_flags(struct folio *folio)
{
	VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio);

	__folio_clear_lru(folio);

	/* this shouldn't happen, so leave the flags to bad_page() */
	if (folio_test_active(folio) && folio_test_unevictable(folio))
		return;

	__folio_clear_active(folio);
	__folio_clear_unevictable(folio);
}

/**
 * folio_lru_list - Which LRU list should a folio be on?
 * @folio: The folio to test.
 *
 * Return: The LRU list a folio should be on, as an index
 * into the array of LRU lists.
 */
static __always_inline enum lru_list folio_lru_list(struct folio *folio)
{
	enum lru_list lru;

	VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);

	if (folio_test_unevictable(folio))
		return LRU_UNEVICTABLE;

	lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
	if (folio_test_active(folio))
		lru += LRU_ACTIVE;

	return lru;
}

#ifdef CONFIG_LRU_GEN

#ifdef CONFIG_LRU_GEN_ENABLED
static inline bool lru_gen_enabled(void)
{
	DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]);

	return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]);
}
#else
static inline bool lru_gen_enabled(void)
{
	DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]);

	return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]);
}
#endif

static inline bool lru_gen_in_fault(void)
{
	return current->in_lru_fault;
}

static inline int lru_gen_from_seq(unsigned long seq)
{
	return seq % MAX_NR_GENS;
}

static inline int lru_hist_from_seq(unsigned long seq)
{
	return seq % NR_HIST_GENS;
}

static inline int lru_tier_from_refs(int refs)
{
	VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));

	/* see the comment in folio_lru_refs() */
	return order_base_2(refs + 1);
}

static inline int folio_lru_refs(struct folio *folio)
{
	unsigned long flags = READ_ONCE(folio->flags);
	bool workingset = flags & BIT(PG_workingset);

	/*
	 * Return the number of accesses beyond PG_referenced, i.e., N-1 if the
	 * total number of accesses is N>1, since N=0,1 both map to the first
	 * tier. lru_tier_from_refs() will account for this off-by-one. Also see
	 * the comment on MAX_NR_TIERS.
	 */
	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
}

static inline int folio_lru_gen(struct folio *folio)
{
	unsigned long flags = READ_ONCE(folio->flags);

	return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
}

static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
{
	unsigned long max_seq = lruvec->lrugen.max_seq;

	VM_WARN_ON_ONCE(gen >= MAX_NR_GENS);

	/* see the comment on MIN_NR_GENS */
	return gen == lru_gen_from_seq(max_seq) || gen == lru_gen_from_seq(max_seq - 1);
}

static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *folio,
				       int old_gen, int new_gen)
{
	int type = folio_is_file_lru(folio);
	int zone = folio_zonenum(folio);
	int delta = folio_nr_pages(folio);
	enum lru_list lru = type * LRU_INACTIVE_FILE;
	struct lru_gen_folio *lrugen = &lruvec->lrugen;

	VM_WARN_ON_ONCE(old_gen != -1 && old_gen >= MAX_NR_GENS);
	VM_WARN_ON_ONCE(new_gen != -1 && new_gen >= MAX_NR_GENS);
	VM_WARN_ON_ONCE(old_gen == -1 && new_gen == -1);

	if (old_gen >= 0)
		WRITE_ONCE(lrugen->nr_pages[old_gen][type][zone],
			   lrugen->nr_pages[old_gen][type][zone] - delta);
	if (new_gen >= 0)
		WRITE_ONCE(lrugen->nr_pages[new_gen][type][zone],
			   lrugen->nr_pages[new_gen][type][zone] + delta);

	/* addition */
	if (old_gen < 0) {
		if (lru_gen_is_active(lruvec, new_gen))
			lru += LRU_ACTIVE;
		__update_lru_size(lruvec, lru, zone, delta);
		return;
	}

	/* deletion */
	if (new_gen < 0) {
		if (lru_gen_is_active(lruvec, old_gen))
			lru += LRU_ACTIVE;
		__update_lru_size(lruvec, lru, zone, -delta);
		return;
	}

	/* promotion */
	if (!lru_gen_is_active(lruvec, old_gen) && lru_gen_is_active(lruvec, new_gen)) {
		__update_lru_size(lruvec, lru, zone, -delta);
		__update_lru_size(lruvec, lru + LRU_ACTIVE, zone, delta);
	}

	/* demotion requires isolation, e.g., lru_deactivate_fn() */
	VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
}

static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
	unsigned long seq;
	unsigned long flags;
	int gen = folio_lru_gen(folio);
	int type = folio_is_file_lru(folio);
	int zone = folio_zonenum(folio);
	struct lru_gen_folio *lrugen = &lruvec->lrugen;

	VM_WARN_ON_ONCE_FOLIO(gen != -1, folio);

	if (folio_test_unevictable(folio) || !lrugen->enabled)
		return false;
	/*
	 * There are three common cases for this page:
	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
	 *    migrated, add it to the youngest generation.
	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
	 *    not in swapcache or a dirty page pending writeback, add it to the
	 *    second oldest generation.
	 * 3. Everything else (clean, cold) is added to the oldest generation.
	 */
	if (folio_test_active(folio))
		seq = lrugen->max_seq;
	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
		 (folio_test_reclaim(folio) &&
		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
		seq = lrugen->min_seq[type] + 1;
	else
		seq = lrugen->min_seq[type];

	gen = lru_gen_from_seq(seq);
	flags = (gen + 1UL) << LRU_GEN_PGOFF;
	/* see the comment on MIN_NR_GENS about PG_active */
	set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);

	lru_gen_update_size(lruvec, folio, -1, gen);
	/* for folio_rotate_reclaimable() */
	if (reclaiming)
		list_add_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
	else
		list_add(&folio->lru, &lrugen->folios[gen][type][zone]);

	return true;
}

static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
	unsigned long flags;
	int gen = folio_lru_gen(folio);

	if (gen < 0)
		return false;

	VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
	VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);

	/* for folio_migrate_flags() */
	flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0;
	flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags);
	gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;

	lru_gen_update_size(lruvec, folio, gen, -1);
	list_del(&folio->lru);

	return true;
}

#else /* !CONFIG_LRU_GEN */

static inline bool lru_gen_enabled(void)
{
	return false;
}

static inline bool lru_gen_in_fault(void)
{
	return false;
}

static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
	return false;
}

static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
{
	return false;
}

#endif /* CONFIG_LRU_GEN */

static __always_inline
void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
{
	enum lru_list lru = folio_lru_list(folio);

	if (lru_gen_add_folio(lruvec, folio, false))
		return;

	update_lru_size(lruvec, lru, folio_zonenum(folio),
			folio_nr_pages(folio));
	if (lru != LRU_UNEVICTABLE)
		list_add(&folio->lru, &lruvec->lists[lru]);
}

static __always_inline
void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
{
	enum lru_list lru = folio_lru_list(folio);

	if (lru_gen_add_folio(lruvec, folio, true))
		return;

	update_lru_size(lruvec, lru, folio_zonenum(folio),
			folio_nr_pages(folio));
	/* This is not expected to be used on LRU_UNEVICTABLE */
	list_add_tail(&folio->lru, &lruvec->lists[lru]);
}

static __always_inline
void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
{
	enum lru_list lru = folio_lru_list(folio);

	if (lru_gen_del_folio(lruvec, folio, false))
		return;

	if (lru != LRU_UNEVICTABLE)
		list_del(&folio->lru);
	update_lru_size(lruvec, lru, folio_zonenum(folio),
			-folio_nr_pages(folio));
}

#ifdef CONFIG_ANON_VMA_NAME
/* mmap_lock should be read-locked */
static inline void anon_vma_name_get(struct anon_vma_name *anon_name)
{
	if (anon_name)
		kref_get(&anon_name->kref);
}

static inline void anon_vma_name_put(struct anon_vma_name *anon_name)
{
	if (anon_name)
		kref_put(&anon_name->kref, anon_vma_name_free);
}

static inline
struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name)
{
	/* Prevent anon_name refcount saturation early on */
	if (kref_read(&anon_name->kref) < REFCOUNT_MAX) {
		anon_vma_name_get(anon_name);
		return anon_name;

	}
	return anon_vma_name_alloc(anon_name->name);
}

static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
				     struct vm_area_struct *new_vma)
{
	struct anon_vma_name *anon_name = anon_vma_name(orig_vma);

	if (anon_name)
		new_vma->anon_name = anon_vma_name_reuse(anon_name);
}

static inline void free_anon_vma_name(struct vm_area_struct *vma)
{
	/*
	 * Not using anon_vma_name because it generates a warning if mmap_lock
	 * is not held, which might be the case here.
	 */
	anon_vma_name_put(vma->anon_name);
}

static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
				    struct anon_vma_name *anon_name2)
{
	if (anon_name1 == anon_name2)
		return true;

	return anon_name1 && anon_name2 &&
		!strcmp(anon_name1->name, anon_name2->name);
}

#else /* CONFIG_ANON_VMA_NAME */
static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {}
static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {}
static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
				     struct vm_area_struct *new_vma) {}
static inline void free_anon_vma_name(struct vm_area_struct *vma) {}

static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
				    struct anon_vma_name *anon_name2)
{
	return true;
}

#endif  /* CONFIG_ANON_VMA_NAME */

static inline void init_tlb_flush_pending(struct mm_struct *mm)
{
	atomic_set(&mm->tlb_flush_pending, 0);
}

static inline void inc_tlb_flush_pending(struct mm_struct *mm)
{
	atomic_inc(&mm->tlb_flush_pending);
	/*
	 * The only time this value is relevant is when there are indeed pages
	 * to flush. And we'll only flush pages after changing them, which
	 * requires the PTL.
	 *
	 * So the ordering here is:
	 *
	 *	atomic_inc(&mm->tlb_flush_pending);
	 *	spin_lock(&ptl);
	 *	...
	 *	set_pte_at();
	 *	spin_unlock(&ptl);
	 *
	 *				spin_lock(&ptl)
	 *				mm_tlb_flush_pending();
	 *				....
	 *				spin_unlock(&ptl);
	 *
	 *	flush_tlb_range();
	 *	atomic_dec(&mm->tlb_flush_pending);
	 *
	 * Where the increment if constrained by the PTL unlock, it thus
	 * ensures that the increment is visible if the PTE modification is
	 * visible. After all, if there is no PTE modification, nobody cares
	 * about TLB flushes either.
	 *
	 * This very much relies on users (mm_tlb_flush_pending() and
	 * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
	 * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
	 * locks (PPC) the unlock of one doesn't order against the lock of
	 * another PTL.
	 *
	 * The decrement is ordered by the flush_tlb_range(), such that
	 * mm_tlb_flush_pending() will not return false unless all flushes have
	 * completed.
	 */
}

static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
	/*
	 * See inc_tlb_flush_pending().
	 *
	 * This cannot be smp_mb__before_atomic() because smp_mb() simply does
	 * not order against TLB invalidate completion, which is what we need.
	 *
	 * Therefore we must rely on tlb_flush_*() to guarantee order.
	 */
	atomic_dec(&mm->tlb_flush_pending);
}

static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
	/*
	 * Must be called after having acquired the PTL; orders against that
	 * PTLs release and therefore ensures that if we observe the modified
	 * PTE we must also observe the increment from inc_tlb_flush_pending().
	 *
	 * That is, it only guarantees to return true if there is a flush
	 * pending for _this_ PTL.
	 */
	return atomic_read(&mm->tlb_flush_pending);
}

static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
{
	/*
	 * Similar to mm_tlb_flush_pending(), we must have acquired the PTL
	 * for which there is a TLB flush pending in order to guarantee
	 * we've seen both that PTE modification and the increment.
	 *
	 * (no requirement on actually still holding the PTL, that is irrelevant)
	 */
	return atomic_read(&mm->tlb_flush_pending) > 1;
}

#ifdef CONFIG_MMU
/*
 * Computes the pte marker to copy from the given source entry into dst_vma.
 * If no marker should be copied, returns 0.
 * The caller should insert a new pte created with make_pte_marker().
 */
static inline pte_marker copy_pte_marker(
		swp_entry_t entry, struct vm_area_struct *dst_vma)
{
	pte_marker srcm = pte_marker_get(entry);
	/* Always copy error entries. */
	pte_marker dstm = srcm & PTE_MARKER_POISONED;

	/* Only copy PTE markers if UFFD register matches. */
	if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma))
		dstm |= PTE_MARKER_UFFD_WP;

	return dstm;
}
#endif

/*
 * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
 * replace a none pte.  NOTE!  This should only be called when *pte is already
 * cleared so we will never accidentally replace something valuable.  Meanwhile
 * none pte also means we are not demoting the pte so tlb flushed is not needed.
 * E.g., when pte cleared the caller should have taken care of the tlb flush.
 *
 * Must be called with pgtable lock held so that no thread will see the none
 * pte, and if they see it, they'll fault and serialize at the pgtable lock.
 *
 * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled.
 */
static inline void
pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
			      pte_t *pte, pte_t pteval)
{
#ifdef CONFIG_PTE_MARKER_UFFD_WP
	bool arm_uffd_pte = false;

	/* The current status of the pte should be "cleared" before calling */
	WARN_ON_ONCE(!pte_none(ptep_get(pte)));

	/*
	 * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole
	 * thing, because when zapping either it means it's dropping the
	 * page, or in TTU where the present pte will be quickly replaced
	 * with a swap pte.  There's no way of leaking the bit.
	 */
	if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
		return;

	/* A uffd-wp wr-protected normal pte */
	if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
		arm_uffd_pte = true;

	/*
	 * A uffd-wp wr-protected swap pte.  Note: this should even cover an
	 * existing pte marker with uffd-wp bit set.
	 */
	if (unlikely(pte_swp_uffd_wp_any(pteval)))
		arm_uffd_pte = true;

	if (unlikely(arm_uffd_pte))
		set_pte_at(vma->vm_mm, addr, pte,
			   make_pte_marker(PTE_MARKER_UFFD_WP));
#endif
}

static inline bool vma_has_recency(struct vm_area_struct *vma)
{
	if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
		return false;

	if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE))
		return false;

	return true;
}

#endif