summaryrefslogtreecommitdiff
path: root/mm/sparse-vmemmap.c
blob: dbbd1a7e65f334179dce5faf291b5a29b0b5f084 (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
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
// SPDX-License-Identifier: GPL-2.0
/*
 * Virtual Memory Map support
 *
 * (C) 2007 sgi. Christoph Lameter.
 *
 * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
 * virt_to_page, page_address() to be implemented as a base offset
 * calculation without memory access.
 *
 * However, virtual mappings need a page table and TLBs. Many Linux
 * architectures already map their physical space using 1-1 mappings
 * via TLBs. For those arches the virtual memory map is essentially
 * for free if we use the same page size as the 1-1 mappings. In that
 * case the overhead consists of a few additional pages that are
 * allocated to create a view of memory for vmemmap.
 *
 * The architecture is expected to provide a vmemmap_populate() function
 * to instantiate the mapping.
 */
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/memblock.h>
#include <linux/memremap.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/sched.h>
#include <linux/pgtable.h>
#include <linux/bootmem_info.h>

#include <asm/dma.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>

#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
/**
 * struct vmemmap_remap_walk - walk vmemmap page table
 *
 * @remap_pte:		called for each lowest-level entry (PTE).
 * @nr_walked:		the number of walked pte.
 * @reuse_page:		the page which is reused for the tail vmemmap pages.
 * @reuse_addr:		the virtual address of the @reuse_page page.
 * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
 *			or is mapped from.
 */
struct vmemmap_remap_walk {
	void (*remap_pte)(pte_t *pte, unsigned long addr,
			  struct vmemmap_remap_walk *walk);
	unsigned long nr_walked;
	struct page *reuse_page;
	unsigned long reuse_addr;
	struct list_head *vmemmap_pages;
};

static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
{
	pmd_t __pmd;
	int i;
	unsigned long addr = start;
	struct page *page = pmd_page(*pmd);
	pte_t *pgtable = pte_alloc_one_kernel(&init_mm);

	if (!pgtable)
		return -ENOMEM;

	pmd_populate_kernel(&init_mm, &__pmd, pgtable);

	for (i = 0; i < PMD_SIZE / PAGE_SIZE; i++, addr += PAGE_SIZE) {
		pte_t entry, *pte;
		pgprot_t pgprot = PAGE_KERNEL;

		entry = mk_pte(page + i, pgprot);
		pte = pte_offset_kernel(&__pmd, addr);
		set_pte_at(&init_mm, addr, pte, entry);
	}

	spin_lock(&init_mm.page_table_lock);
	if (likely(pmd_leaf(*pmd))) {
		/*
		 * Higher order allocations from buddy allocator must be able to
		 * be treated as indepdenent small pages (as they can be freed
		 * individually).
		 */
		if (!PageReserved(page))
			split_page(page, get_order(PMD_SIZE));

		/* Make pte visible before pmd. See comment in pmd_install(). */
		smp_wmb();
		pmd_populate_kernel(&init_mm, pmd, pgtable);
		flush_tlb_kernel_range(start, start + PMD_SIZE);
	} else {
		pte_free_kernel(&init_mm, pgtable);
	}
	spin_unlock(&init_mm.page_table_lock);

	return 0;
}

static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
{
	int leaf;

	spin_lock(&init_mm.page_table_lock);
	leaf = pmd_leaf(*pmd);
	spin_unlock(&init_mm.page_table_lock);

	if (!leaf)
		return 0;

	return __split_vmemmap_huge_pmd(pmd, start);
}

static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
			      unsigned long end,
			      struct vmemmap_remap_walk *walk)
{
	pte_t *pte = pte_offset_kernel(pmd, addr);

	/*
	 * The reuse_page is found 'first' in table walk before we start
	 * remapping (which is calling @walk->remap_pte).
	 */
	if (!walk->reuse_page) {
		walk->reuse_page = pte_page(*pte);
		/*
		 * Because the reuse address is part of the range that we are
		 * walking, skip the reuse address range.
		 */
		addr += PAGE_SIZE;
		pte++;
		walk->nr_walked++;
	}

	for (; addr != end; addr += PAGE_SIZE, pte++) {
		walk->remap_pte(pte, addr, walk);
		walk->nr_walked++;
	}
}

static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		int ret;

		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK);
		if (ret)
			return ret;

		next = pmd_addr_end(addr, end);
		vmemmap_pte_range(pmd, addr, next, walk);
	} while (pmd++, addr = next, addr != end);

	return 0;
}

static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(p4d, addr);
	do {
		int ret;

		next = pud_addr_end(addr, end);
		ret = vmemmap_pmd_range(pud, addr, next, walk);
		if (ret)
			return ret;
	} while (pud++, addr = next, addr != end);

	return 0;
}

static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_offset(pgd, addr);
	do {
		int ret;

		next = p4d_addr_end(addr, end);
		ret = vmemmap_pud_range(p4d, addr, next, walk);
		if (ret)
			return ret;
	} while (p4d++, addr = next, addr != end);

	return 0;
}

static int vmemmap_remap_range(unsigned long start, unsigned long end,
			       struct vmemmap_remap_walk *walk)
{
	unsigned long addr = start;
	unsigned long next;
	pgd_t *pgd;

	VM_BUG_ON(!IS_ALIGNED(start, PAGE_SIZE));
	VM_BUG_ON(!IS_ALIGNED(end, PAGE_SIZE));

	pgd = pgd_offset_k(addr);
	do {
		int ret;

		next = pgd_addr_end(addr, end);
		ret = vmemmap_p4d_range(pgd, addr, next, walk);
		if (ret)
			return ret;
	} while (pgd++, addr = next, addr != end);

	/*
	 * We only change the mapping of the vmemmap virtual address range
	 * [@start + PAGE_SIZE, end), so we only need to flush the TLB which
	 * belongs to the range.
	 */
	flush_tlb_kernel_range(start + PAGE_SIZE, end);

	return 0;
}

/*
 * Free a vmemmap page. A vmemmap page can be allocated from the memblock
 * allocator or buddy allocator. If the PG_reserved flag is set, it means
 * that it allocated from the memblock allocator, just free it via the
 * free_bootmem_page(). Otherwise, use __free_page().
 */
static inline void free_vmemmap_page(struct page *page)
{
	if (PageReserved(page))
		free_bootmem_page(page);
	else
		__free_page(page);
}

/* Free a list of the vmemmap pages */
static void free_vmemmap_page_list(struct list_head *list)
{
	struct page *page, *next;

	list_for_each_entry_safe(page, next, list, lru) {
		list_del(&page->lru);
		free_vmemmap_page(page);
	}
}

static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
			      struct vmemmap_remap_walk *walk)
{
	/*
	 * Remap the tail pages as read-only to catch illegal write operation
	 * to the tail pages.
	 */
	pgprot_t pgprot = PAGE_KERNEL_RO;
	pte_t entry = mk_pte(walk->reuse_page, pgprot);
	struct page *page = pte_page(*pte);

	list_add_tail(&page->lru, walk->vmemmap_pages);
	set_pte_at(&init_mm, addr, pte, entry);
}

/*
 * How many struct page structs need to be reset. When we reuse the head
 * struct page, the special metadata (e.g. page->flags or page->mapping)
 * cannot copy to the tail struct page structs. The invalid value will be
 * checked in the free_tail_pages_check(). In order to avoid the message
 * of "corrupted mapping in tail page". We need to reset at least 3 (one
 * head struct page struct and two tail struct page structs) struct page
 * structs.
 */
#define NR_RESET_STRUCT_PAGE		3

static inline void reset_struct_pages(struct page *start)
{
	int i;
	struct page *from = start + NR_RESET_STRUCT_PAGE;

	for (i = 0; i < NR_RESET_STRUCT_PAGE; i++)
		memcpy(start + i, from, sizeof(*from));
}

static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
				struct vmemmap_remap_walk *walk)
{
	pgprot_t pgprot = PAGE_KERNEL;
	struct page *page;
	void *to;

	BUG_ON(pte_page(*pte) != walk->reuse_page);

	page = list_first_entry(walk->vmemmap_pages, struct page, lru);
	list_del(&page->lru);
	to = page_to_virt(page);
	copy_page(to, (void *)walk->reuse_addr);
	reset_struct_pages(to);

	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
}

/**
 * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
 *			to the page which @reuse is mapped to, then free vmemmap
 *			which the range are mapped to.
 * @start:	start address of the vmemmap virtual address range that we want
 *		to remap.
 * @end:	end address of the vmemmap virtual address range that we want to
 *		remap.
 * @reuse:	reuse address.
 *
 * Return: %0 on success, negative error code otherwise.
 */
int vmemmap_remap_free(unsigned long start, unsigned long end,
		       unsigned long reuse)
{
	int ret;
	LIST_HEAD(vmemmap_pages);
	struct vmemmap_remap_walk walk = {
		.remap_pte	= vmemmap_remap_pte,
		.reuse_addr	= reuse,
		.vmemmap_pages	= &vmemmap_pages,
	};

	/*
	 * In order to make remapping routine most efficient for the huge pages,
	 * the routine of vmemmap page table walking has the following rules
	 * (see more details from the vmemmap_pte_range()):
	 *
	 * - The range [@start, @end) and the range [@reuse, @reuse + PAGE_SIZE)
	 *   should be continuous.
	 * - The @reuse address is part of the range [@reuse, @end) that we are
	 *   walking which is passed to vmemmap_remap_range().
	 * - The @reuse address is the first in the complete range.
	 *
	 * So we need to make sure that @start and @reuse meet the above rules.
	 */
	BUG_ON(start - reuse != PAGE_SIZE);

	mmap_read_lock(&init_mm);
	ret = vmemmap_remap_range(reuse, end, &walk);
	if (ret && walk.nr_walked) {
		end = reuse + walk.nr_walked * PAGE_SIZE;
		/*
		 * vmemmap_pages contains pages from the previous
		 * vmemmap_remap_range call which failed.  These
		 * are pages which were removed from the vmemmap.
		 * They will be restored in the following call.
		 */
		walk = (struct vmemmap_remap_walk) {
			.remap_pte	= vmemmap_restore_pte,
			.reuse_addr	= reuse,
			.vmemmap_pages	= &vmemmap_pages,
		};

		vmemmap_remap_range(reuse, end, &walk);
	}
	mmap_read_unlock(&init_mm);

	free_vmemmap_page_list(&vmemmap_pages);

	return ret;
}

static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
				   gfp_t gfp_mask, struct list_head *list)
{
	unsigned long nr_pages = (end - start) >> PAGE_SHIFT;
	int nid = page_to_nid((struct page *)start);
	struct page *page, *next;

	while (nr_pages--) {
		page = alloc_pages_node(nid, gfp_mask, 0);
		if (!page)
			goto out;
		list_add_tail(&page->lru, list);
	}

	return 0;
out:
	list_for_each_entry_safe(page, next, list, lru)
		__free_pages(page, 0);
	return -ENOMEM;
}

/**
 * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end)
 *			 to the page which is from the @vmemmap_pages
 *			 respectively.
 * @start:	start address of the vmemmap virtual address range that we want
 *		to remap.
 * @end:	end address of the vmemmap virtual address range that we want to
 *		remap.
 * @reuse:	reuse address.
 * @gfp_mask:	GFP flag for allocating vmemmap pages.
 *
 * Return: %0 on success, negative error code otherwise.
 */
int vmemmap_remap_alloc(unsigned long start, unsigned long end,
			unsigned long reuse, gfp_t gfp_mask)
{
	LIST_HEAD(vmemmap_pages);
	struct vmemmap_remap_walk walk = {
		.remap_pte	= vmemmap_restore_pte,
		.reuse_addr	= reuse,
		.vmemmap_pages	= &vmemmap_pages,
	};

	/* See the comment in the vmemmap_remap_free(). */
	BUG_ON(start - reuse != PAGE_SIZE);

	if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages))
		return -ENOMEM;

	mmap_read_lock(&init_mm);
	vmemmap_remap_range(reuse, end, &walk);
	mmap_read_unlock(&init_mm);

	return 0;
}
#endif /* CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP */

/*
 * Allocate a block of memory to be used to back the virtual memory map
 * or to back the page tables that are used to create the mapping.
 * Uses the main allocators if they are available, else bootmem.
 */

static void * __ref __earlyonly_bootmem_alloc(int node,
				unsigned long size,
				unsigned long align,
				unsigned long goal)
{
	return memblock_alloc_try_nid_raw(size, align, goal,
					       MEMBLOCK_ALLOC_ACCESSIBLE, node);
}

void * __meminit vmemmap_alloc_block(unsigned long size, int node)
{
	/* If the main allocator is up use that, fallback to bootmem. */
	if (slab_is_available()) {
		gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
		int order = get_order(size);
		static bool warned;
		struct page *page;

		page = alloc_pages_node(node, gfp_mask, order);
		if (page)
			return page_address(page);

		if (!warned) {
			warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL,
				   "vmemmap alloc failure: order:%u", order);
			warned = true;
		}
		return NULL;
	} else
		return __earlyonly_bootmem_alloc(node, size, size,
				__pa(MAX_DMA_ADDRESS));
}

static void * __meminit altmap_alloc_block_buf(unsigned long size,
					       struct vmem_altmap *altmap);

/* need to make sure size is all the same during early stage */
void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node,
					 struct vmem_altmap *altmap)
{
	void *ptr;

	if (altmap)
		return altmap_alloc_block_buf(size, altmap);

	ptr = sparse_buffer_alloc(size);
	if (!ptr)
		ptr = vmemmap_alloc_block(size, node);
	return ptr;
}

static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
{
	return altmap->base_pfn + altmap->reserve + altmap->alloc
		+ altmap->align;
}

static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
{
	unsigned long allocated = altmap->alloc + altmap->align;

	if (altmap->free > allocated)
		return altmap->free - allocated;
	return 0;
}

static void * __meminit altmap_alloc_block_buf(unsigned long size,
					       struct vmem_altmap *altmap)
{
	unsigned long pfn, nr_pfns, nr_align;

	if (size & ~PAGE_MASK) {
		pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
				__func__, size);
		return NULL;
	}

	pfn = vmem_altmap_next_pfn(altmap);
	nr_pfns = size >> PAGE_SHIFT;
	nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
	nr_align = ALIGN(pfn, nr_align) - pfn;
	if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
		return NULL;

	altmap->alloc += nr_pfns;
	altmap->align += nr_align;
	pfn += nr_align;

	pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
			__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
	return __va(__pfn_to_phys(pfn));
}

void __meminit vmemmap_verify(pte_t *pte, int node,
				unsigned long start, unsigned long end)
{
	unsigned long pfn = pte_pfn(*pte);
	int actual_node = early_pfn_to_nid(pfn);

	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
		pr_warn("[%lx-%lx] potential offnode page_structs\n",
			start, end - 1);
}

pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
				       struct vmem_altmap *altmap,
				       struct page *reuse)
{
	pte_t *pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte)) {
		pte_t entry;
		void *p;

		if (!reuse) {
			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
			if (!p)
				return NULL;
		} else {
			/*
			 * When a PTE/PMD entry is freed from the init_mm
			 * there's a a free_pages() call to this page allocated
			 * above. Thus this get_page() is paired with the
			 * put_page_testzero() on the freeing path.
			 * This can only called by certain ZONE_DEVICE path,
			 * and through vmemmap_populate_compound_pages() when
			 * slab is available.
			 */
			get_page(reuse);
			p = page_to_virt(reuse);
		}
		entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
		set_pte_at(&init_mm, addr, pte, entry);
	}
	return pte;
}

static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
{
	void *p = vmemmap_alloc_block(size, node);

	if (!p)
		return NULL;
	memset(p, 0, size);

	return p;
}

pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
{
	pmd_t *pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pmd_populate_kernel(&init_mm, pmd, p);
	}
	return pmd;
}

pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
{
	pud_t *pud = pud_offset(p4d, addr);
	if (pud_none(*pud)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pud_populate(&init_mm, pud, p);
	}
	return pud;
}

p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
{
	p4d_t *p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		p4d_populate(&init_mm, p4d, p);
	}
	return p4d;
}

pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
{
	pgd_t *pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pgd_populate(&init_mm, pgd, p);
	}
	return pgd;
}

static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node,
					      struct vmem_altmap *altmap,
					      struct page *reuse)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	pgd = vmemmap_pgd_populate(addr, node);
	if (!pgd)
		return NULL;
	p4d = vmemmap_p4d_populate(pgd, addr, node);
	if (!p4d)
		return NULL;
	pud = vmemmap_pud_populate(p4d, addr, node);
	if (!pud)
		return NULL;
	pmd = vmemmap_pmd_populate(pud, addr, node);
	if (!pmd)
		return NULL;
	pte = vmemmap_pte_populate(pmd, addr, node, altmap, reuse);
	if (!pte)
		return NULL;
	vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);

	return pte;
}

static int __meminit vmemmap_populate_range(unsigned long start,
					    unsigned long end, int node,
					    struct vmem_altmap *altmap,
					    struct page *reuse)
{
	unsigned long addr = start;
	pte_t *pte;

	for (; addr < end; addr += PAGE_SIZE) {
		pte = vmemmap_populate_address(addr, node, altmap, reuse);
		if (!pte)
			return -ENOMEM;
	}

	return 0;
}

int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
					 int node, struct vmem_altmap *altmap)
{
	return vmemmap_populate_range(start, end, node, altmap, NULL);
}

/*
 * For compound pages bigger than section size (e.g. x86 1G compound
 * pages with 2M subsection size) fill the rest of sections as tail
 * pages.
 *
 * Note that memremap_pages() resets @nr_range value and will increment
 * it after each range successful onlining. Thus the value or @nr_range
 * at section memmap populate corresponds to the in-progress range
 * being onlined here.
 */
static bool __meminit reuse_compound_section(unsigned long start_pfn,
					     struct dev_pagemap *pgmap)
{
	unsigned long nr_pages = pgmap_vmemmap_nr(pgmap);
	unsigned long offset = start_pfn -
		PHYS_PFN(pgmap->ranges[pgmap->nr_range].start);

	return !IS_ALIGNED(offset, nr_pages) && nr_pages > PAGES_PER_SUBSECTION;
}

static pte_t * __meminit compound_section_tail_page(unsigned long addr)
{
	pte_t *pte;

	addr -= PAGE_SIZE;

	/*
	 * Assuming sections are populated sequentially, the previous section's
	 * page data can be reused.
	 */
	pte = pte_offset_kernel(pmd_off_k(addr), addr);
	if (!pte)
		return NULL;

	return pte;
}

static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
						     unsigned long start,
						     unsigned long end, int node,
						     struct dev_pagemap *pgmap)
{
	unsigned long size, addr;
	pte_t *pte;
	int rc;

	if (reuse_compound_section(start_pfn, pgmap)) {
		pte = compound_section_tail_page(start);
		if (!pte)
			return -ENOMEM;

		/*
		 * Reuse the page that was populated in the prior iteration
		 * with just tail struct pages.
		 */
		return vmemmap_populate_range(start, end, node, NULL,
					      pte_page(*pte));
	}

	size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
	for (addr = start; addr < end; addr += size) {
		unsigned long next = addr, last = addr + size;

		/* Populate the head page vmemmap page */
		pte = vmemmap_populate_address(addr, node, NULL, NULL);
		if (!pte)
			return -ENOMEM;

		/* Populate the tail pages vmemmap page */
		next = addr + PAGE_SIZE;
		pte = vmemmap_populate_address(next, node, NULL, NULL);
		if (!pte)
			return -ENOMEM;

		/*
		 * Reuse the previous page for the rest of tail pages
		 * See layout diagram in Documentation/vm/vmemmap_dedup.rst
		 */
		next += PAGE_SIZE;
		rc = vmemmap_populate_range(next, last, node, NULL,
					    pte_page(*pte));
		if (rc)
			return -ENOMEM;
	}

	return 0;
}

struct page * __meminit __populate_section_memmap(unsigned long pfn,
		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
		struct dev_pagemap *pgmap)
{
	unsigned long start = (unsigned long) pfn_to_page(pfn);
	unsigned long end = start + nr_pages * sizeof(struct page);
	int r;

	if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
		return NULL;

	if (is_power_of_2(sizeof(struct page)) &&
	    pgmap && pgmap_vmemmap_nr(pgmap) > 1 && !altmap)
		r = vmemmap_populate_compound_pages(pfn, start, end, nid, pgmap);
	else
		r = vmemmap_populate(start, end, nid, altmap);

	if (r < 0)
		return NULL;

	return pfn_to_page(pfn);
}