aboutsummaryrefslogtreecommitdiff
path: root/mm/hmm.c
blob: f2aa63b94d9bd8903157a9d25e48df96f762b3a7 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright 2013 Red Hat Inc.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Refer to include/linux/hmm.h for information about heterogeneous memory
 * management or HMM for short.
 */
#include <linux/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>

#include "internal.h"

struct hmm_vma_walk {
	struct hmm_range	*range;
	unsigned long		last;
};

enum {
	HMM_NEED_FAULT = 1 << 0,
	HMM_NEED_WRITE_FAULT = 1 << 1,
	HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
};

static int hmm_pfns_fill(unsigned long addr, unsigned long end,
			 struct hmm_range *range, unsigned long cpu_flags)
{
	unsigned long i = (addr - range->start) >> PAGE_SHIFT;

	for (; addr < end; addr += PAGE_SIZE, i++)
		range->hmm_pfns[i] = cpu_flags;
	return 0;
}

/*
 * hmm_vma_fault() - fault in a range lacking valid pmd or pte(s)
 * @addr: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @required_fault: HMM_NEED_* flags
 * @walk: mm_walk structure
 * Return: -EBUSY after page fault, or page fault error
 *
 * This function will be called whenever pmd_none() or pte_none() returns true,
 * or whenever there is no page directory covering the virtual address range.
 */
static int hmm_vma_fault(unsigned long addr, unsigned long end,
			 unsigned int required_fault, struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct vm_area_struct *vma = walk->vma;
	unsigned int fault_flags = FAULT_FLAG_REMOTE;

	WARN_ON_ONCE(!required_fault);
	hmm_vma_walk->last = addr;

	if (required_fault & HMM_NEED_WRITE_FAULT) {
		if (!(vma->vm_flags & VM_WRITE))
			return -EPERM;
		fault_flags |= FAULT_FLAG_WRITE;
	}

	for (; addr < end; addr += PAGE_SIZE)
		if (handle_mm_fault(vma, addr, fault_flags, NULL) &
		    VM_FAULT_ERROR)
			return -EFAULT;
	return -EBUSY;
}

static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
				       unsigned long pfn_req_flags,
				       unsigned long cpu_flags)
{
	struct hmm_range *range = hmm_vma_walk->range;

	/*
	 * So we not only consider the individual per page request we also
	 * consider the default flags requested for the range. The API can
	 * be used 2 ways. The first one where the HMM user coalesces
	 * multiple page faults into one request and sets flags per pfn for
	 * those faults. The second one where the HMM user wants to pre-
	 * fault a range with specific flags. For the latter one it is a
	 * waste to have the user pre-fill the pfn arrays with a default
	 * flags value.
	 */
	pfn_req_flags &= range->pfn_flags_mask;
	pfn_req_flags |= range->default_flags;

	/* We aren't ask to do anything ... */
	if (!(pfn_req_flags & HMM_PFN_REQ_FAULT))
		return 0;

	/* Need to write fault ? */
	if ((pfn_req_flags & HMM_PFN_REQ_WRITE) &&
	    !(cpu_flags & HMM_PFN_WRITE))
		return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;

	/* If CPU page table is not valid then we need to fault */
	if (!(cpu_flags & HMM_PFN_VALID))
		return HMM_NEED_FAULT;
	return 0;
}

static unsigned int
hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
		     const unsigned long hmm_pfns[], unsigned long npages,
		     unsigned long cpu_flags)
{
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned int required_fault = 0;
	unsigned long i;

	/*
	 * If the default flags do not request to fault pages, and the mask does
	 * not allow for individual pages to be faulted, then
	 * hmm_pte_need_fault() will always return 0.
	 */
	if (!((range->default_flags | range->pfn_flags_mask) &
	      HMM_PFN_REQ_FAULT))
		return 0;

	for (i = 0; i < npages; ++i) {
		required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i],
						     cpu_flags);
		if (required_fault == HMM_NEED_ALL_BITS)
			return required_fault;
	}
	return required_fault;
}

static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
			     __always_unused int depth, struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned int required_fault;
	unsigned long i, npages;
	unsigned long *hmm_pfns;

	i = (addr - range->start) >> PAGE_SHIFT;
	npages = (end - addr) >> PAGE_SHIFT;
	hmm_pfns = &range->hmm_pfns[i];
	required_fault =
		hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0);
	if (!walk->vma) {
		if (required_fault)
			return -EFAULT;
		return hmm_pfns_fill(addr, end, range, HMM_PFN_ERROR);
	}
	if (required_fault)
		return hmm_vma_fault(addr, end, required_fault, walk);
	return hmm_pfns_fill(addr, end, range, 0);
}

static inline unsigned long hmm_pfn_flags_order(unsigned long order)
{
	return order << HMM_PFN_ORDER_SHIFT;
}

static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
						 pmd_t pmd)
{
	if (pmd_protnone(pmd))
		return 0;
	return (pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
				 HMM_PFN_VALID) |
	       hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
			      unsigned long end, unsigned long hmm_pfns[],
			      pmd_t pmd)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned long pfn, npages, i;
	unsigned int required_fault;
	unsigned long cpu_flags;

	npages = (end - addr) >> PAGE_SHIFT;
	cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
	required_fault =
		hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, cpu_flags);
	if (required_fault)
		return hmm_vma_fault(addr, end, required_fault, walk);

	pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
		hmm_pfns[i] = pfn | cpu_flags;
	return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
/* stub to allow the code below to compile */
int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
		unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
						 pte_t pte)
{
	if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
		return 0;
	return pte_write(pte) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
}

static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
			      unsigned long end, pmd_t *pmdp, pte_t *ptep,
			      unsigned long *hmm_pfn)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned int required_fault;
	unsigned long cpu_flags;
	pte_t pte = *ptep;
	uint64_t pfn_req_flags = *hmm_pfn;

	if (pte_none_mostly(pte)) {
		required_fault =
			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
		if (required_fault)
			goto fault;
		*hmm_pfn = 0;
		return 0;
	}

	if (!pte_present(pte)) {
		swp_entry_t entry = pte_to_swp_entry(pte);

		/*
		 * Don't fault in device private pages owned by the caller,
		 * just report the PFN.
		 */
		if (is_device_private_entry(entry) &&
		    pfn_swap_entry_to_page(entry)->pgmap->owner ==
		    range->dev_private_owner) {
			cpu_flags = HMM_PFN_VALID;
			if (is_writable_device_private_entry(entry))
				cpu_flags |= HMM_PFN_WRITE;
			*hmm_pfn = swp_offset(entry) | cpu_flags;
			return 0;
		}

		required_fault =
			hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
		if (!required_fault) {
			*hmm_pfn = 0;
			return 0;
		}

		if (!non_swap_entry(entry))
			goto fault;

		if (is_device_private_entry(entry))
			goto fault;

		if (is_device_exclusive_entry(entry))
			goto fault;

		if (is_migration_entry(entry)) {
			pte_unmap(ptep);
			hmm_vma_walk->last = addr;
			migration_entry_wait(walk->mm, pmdp, addr);
			return -EBUSY;
		}

		/* Report error for everything else */
		pte_unmap(ptep);
		return -EFAULT;
	}

	cpu_flags = pte_to_hmm_pfn_flags(range, pte);
	required_fault =
		hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
	if (required_fault)
		goto fault;

	/*
	 * Bypass devmap pte such as DAX page when all pfn requested
	 * flags(pfn_req_flags) are fulfilled.
	 * Since each architecture defines a struct page for the zero page, just
	 * fall through and treat it like a normal page.
	 */
	if (!vm_normal_page(walk->vma, addr, pte) &&
	    !pte_devmap(pte) &&
	    !is_zero_pfn(pte_pfn(pte))) {
		if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
			pte_unmap(ptep);
			return -EFAULT;
		}
		*hmm_pfn = HMM_PFN_ERROR;
		return 0;
	}

	*hmm_pfn = pte_pfn(pte) | cpu_flags;
	return 0;

fault:
	pte_unmap(ptep);
	/* Fault any virtual address we were asked to fault */
	return hmm_vma_fault(addr, end, required_fault, walk);
}

static int hmm_vma_walk_pmd(pmd_t *pmdp,
			    unsigned long start,
			    unsigned long end,
			    struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned long *hmm_pfns =
		&range->hmm_pfns[(start - range->start) >> PAGE_SHIFT];
	unsigned long npages = (end - start) >> PAGE_SHIFT;
	unsigned long addr = start;
	pte_t *ptep;
	pmd_t pmd;

again:
	pmd = READ_ONCE(*pmdp);
	if (pmd_none(pmd))
		return hmm_vma_walk_hole(start, end, -1, walk);

	if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
			hmm_vma_walk->last = addr;
			pmd_migration_entry_wait(walk->mm, pmdp);
			return -EBUSY;
		}
		return hmm_pfns_fill(start, end, range, 0);
	}

	if (!pmd_present(pmd)) {
		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
			return -EFAULT;
		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
	}

	if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
		/*
		 * No need to take pmd_lock here, even if some other thread
		 * is splitting the huge pmd we will get that event through
		 * mmu_notifier callback.
		 *
		 * So just read pmd value and check again it's a transparent
		 * huge or device mapping one and compute corresponding pfn
		 * values.
		 */
		pmd = pmd_read_atomic(pmdp);
		barrier();
		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
			goto again;

		return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
	}

	/*
	 * We have handled all the valid cases above ie either none, migration,
	 * huge or transparent huge. At this point either it is a valid pmd
	 * entry pointing to pte directory or it is a bad pmd that will not
	 * recover.
	 */
	if (pmd_bad(pmd)) {
		if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
			return -EFAULT;
		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
	}

	ptep = pte_offset_map(pmdp, addr);
	for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) {
		int r;

		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns);
		if (r) {
			/* hmm_vma_handle_pte() did pte_unmap() */
			return r;
		}
	}
	pte_unmap(ptep - 1);
	return 0;
}

#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
    defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
						 pud_t pud)
{
	if (!pud_present(pud))
		return 0;
	return (pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
				 HMM_PFN_VALID) |
	       hmm_pfn_flags_order(PUD_SHIFT - PAGE_SHIFT);
}

static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
		struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	unsigned long addr = start;
	pud_t pud;
	spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);

	if (!ptl)
		return 0;

	/* Normally we don't want to split the huge page */
	walk->action = ACTION_CONTINUE;

	pud = READ_ONCE(*pudp);
	if (pud_none(pud)) {
		spin_unlock(ptl);
		return hmm_vma_walk_hole(start, end, -1, walk);
	}

	if (pud_huge(pud) && pud_devmap(pud)) {
		unsigned long i, npages, pfn;
		unsigned int required_fault;
		unsigned long *hmm_pfns;
		unsigned long cpu_flags;

		if (!pud_present(pud)) {
			spin_unlock(ptl);
			return hmm_vma_walk_hole(start, end, -1, walk);
		}

		i = (addr - range->start) >> PAGE_SHIFT;
		npages = (end - addr) >> PAGE_SHIFT;
		hmm_pfns = &range->hmm_pfns[i];

		cpu_flags = pud_to_hmm_pfn_flags(range, pud);
		required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns,
						      npages, cpu_flags);
		if (required_fault) {
			spin_unlock(ptl);
			return hmm_vma_fault(addr, end, required_fault, walk);
		}

		pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
		for (i = 0; i < npages; ++i, ++pfn)
			hmm_pfns[i] = pfn | cpu_flags;
		goto out_unlock;
	}

	/* Ask for the PUD to be split */
	walk->action = ACTION_SUBTREE;

out_unlock:
	spin_unlock(ptl);
	return 0;
}
#else
#define hmm_vma_walk_pud	NULL
#endif

#ifdef CONFIG_HUGETLB_PAGE
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
				      unsigned long start, unsigned long end,
				      struct mm_walk *walk)
{
	unsigned long addr = start, i, pfn;
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	struct vm_area_struct *vma = walk->vma;
	unsigned int required_fault;
	unsigned long pfn_req_flags;
	unsigned long cpu_flags;
	spinlock_t *ptl;
	pte_t entry;

	ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
	entry = huge_ptep_get(pte);

	i = (start - range->start) >> PAGE_SHIFT;
	pfn_req_flags = range->hmm_pfns[i];
	cpu_flags = pte_to_hmm_pfn_flags(range, entry) |
		    hmm_pfn_flags_order(huge_page_order(hstate_vma(vma)));
	required_fault =
		hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
	if (required_fault) {
		spin_unlock(ptl);
		return hmm_vma_fault(addr, end, required_fault, walk);
	}

	pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
	for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
		range->hmm_pfns[i] = pfn | cpu_flags;

	spin_unlock(ptl);
	return 0;
}
#else
#define hmm_vma_walk_hugetlb_entry NULL
#endif /* CONFIG_HUGETLB_PAGE */

static int hmm_vma_walk_test(unsigned long start, unsigned long end,
			     struct mm_walk *walk)
{
	struct hmm_vma_walk *hmm_vma_walk = walk->private;
	struct hmm_range *range = hmm_vma_walk->range;
	struct vm_area_struct *vma = walk->vma;

	if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) &&
	    vma->vm_flags & VM_READ)
		return 0;

	/*
	 * vma ranges that don't have struct page backing them or map I/O
	 * devices directly cannot be handled by hmm_range_fault().
	 *
	 * If the vma does not allow read access, then assume that it does not
	 * allow write access either. HMM does not support architectures that
	 * allow write without read.
	 *
	 * If a fault is requested for an unsupported range then it is a hard
	 * failure.
	 */
	if (hmm_range_need_fault(hmm_vma_walk,
				 range->hmm_pfns +
					 ((start - range->start) >> PAGE_SHIFT),
				 (end - start) >> PAGE_SHIFT, 0))
		return -EFAULT;

	hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);

	/* Skip this vma and continue processing the next vma. */
	return 1;
}

static const struct mm_walk_ops hmm_walk_ops = {
	.pud_entry	= hmm_vma_walk_pud,
	.pmd_entry	= hmm_vma_walk_pmd,
	.pte_hole	= hmm_vma_walk_hole,
	.hugetlb_entry	= hmm_vma_walk_hugetlb_entry,
	.test_walk	= hmm_vma_walk_test,
};

/**
 * hmm_range_fault - try to fault some address in a virtual address range
 * @range:	argument structure
 *
 * Returns 0 on success or one of the following error codes:
 *
 * -EINVAL:	Invalid arguments or mm or virtual address is in an invalid vma
 *		(e.g., device file vma).
 * -ENOMEM:	Out of memory.
 * -EPERM:	Invalid permission (e.g., asking for write and range is read
 *		only).
 * -EBUSY:	The range has been invalidated and the caller needs to wait for
 *		the invalidation to finish.
 * -EFAULT:     A page was requested to be valid and could not be made valid
 *              ie it has no backing VMA or it is illegal to access
 *
 * This is similar to get_user_pages(), except that it can read the page tables
 * without mutating them (ie causing faults).
 */
int hmm_range_fault(struct hmm_range *range)
{
	struct hmm_vma_walk hmm_vma_walk = {
		.range = range,
		.last = range->start,
	};
	struct mm_struct *mm = range->notifier->mm;
	int ret;

	mmap_assert_locked(mm);

	do {
		/* If range is no longer valid force retry. */
		if (mmu_interval_check_retry(range->notifier,
					     range->notifier_seq))
			return -EBUSY;
		ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
				      &hmm_walk_ops, &hmm_vma_walk);
		/*
		 * When -EBUSY is returned the loop restarts with
		 * hmm_vma_walk.last set to an address that has not been stored
		 * in pfns. All entries < last in the pfn array are set to their
		 * output, and all >= are still at their input values.
		 */
	} while (ret == -EBUSY);
	return ret;
}
EXPORT_SYMBOL(hmm_range_fault);