summaryrefslogtreecommitdiffstats
path: root/mm/sparse-vmemmap.c
blob: a044a130405b295158bd5fd476aaea36127e3a8f (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
// 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 <asm/dma.h>
#include <asm/pgalloc.h>

/*
 * 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(ptep_get(pte));
	int actual_node = early_pfn_to_nid(pfn);

	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
		pr_warn_once("[%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(ptep_get(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 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;
}

void __weak __meminit pmd_init(void *addr)
{
}

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;
		pmd_init(p);
		pud_populate(&init_mm, pud, p);
	}
	return pud;
}

void __weak __meminit pud_init(void *addr)
{
}

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;
		pud_init(p);
		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);
}

void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
				      unsigned long addr, unsigned long next)
{
}

int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
				       unsigned long addr, unsigned long next)
{
	return 0;
}

int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
					 int node, struct vmem_altmap *altmap)
{
	unsigned long addr;
	unsigned long next;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;

	for (addr = start; addr < end; addr = next) {
		next = pmd_addr_end(addr, end);

		pgd = vmemmap_pgd_populate(addr, node);
		if (!pgd)
			return -ENOMEM;

		p4d = vmemmap_p4d_populate(pgd, addr, node);
		if (!p4d)
			return -ENOMEM;

		pud = vmemmap_pud_populate(p4d, addr, node);
		if (!pud)
			return -ENOMEM;

		pmd = pmd_offset(pud, addr);
		if (pmd_none(READ_ONCE(*pmd))) {
			void *p;

			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
			if (p) {
				vmemmap_set_pmd(pmd, p, node, addr, next);
				continue;
			} else if (altmap) {
				/*
				 * No fallback: In any case we care about, the
				 * altmap should be reasonably sized and aligned
				 * such that vmemmap_alloc_block_buf() will always
				 * succeed. For consistency with the PTE case,
				 * return an error here as failure could indicate
				 * a configuration issue with the size of the altmap.
				 */
				return -ENOMEM;
			}
		} else if (vmemmap_check_pmd(pmd, node, addr, next))
			continue;
		if (vmemmap_populate_basepages(addr, next, node, altmap))
			return -ENOMEM;
	}
	return 0;
}

/*
 * 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(ptep_get(pte)));
	}

	size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
	for (addr = start; addr < end; addr += size) {
		unsigned long next, 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/mm/vmemmap_dedup.rst
		 */
		next += PAGE_SIZE;
		rc = vmemmap_populate_range(next, last, node, NULL,
					    pte_page(ptep_get(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 (vmemmap_can_optimize(altmap, pgmap))
		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);
}