summaryrefslogtreecommitdiffstats
path: root/mm/hmm.c
blob: 172984848d51910a5fda8dbffe38898ccd4b87aa (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
/*
 * Copyright 2013 Red Hat Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * Authors: Jérôme Glisse <jglisse@redhat.com>
 */
/*
 * Refer to include/linux/hmm.h for information about heterogeneous memory
 * management or HMM for short.
 */
#include <linux/mm.h>
#include <linux/hmm.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/mmu_notifier.h>


#ifdef CONFIG_HMM
static const struct mmu_notifier_ops hmm_mmu_notifier_ops;

/*
 * struct hmm - HMM per mm struct
 *
 * @mm: mm struct this HMM struct is bound to
 * @lock: lock protecting ranges list
 * @sequence: we track updates to the CPU page table with a sequence number
 * @ranges: list of range being snapshotted
 * @mirrors: list of mirrors for this mm
 * @mmu_notifier: mmu notifier to track updates to CPU page table
 * @mirrors_sem: read/write semaphore protecting the mirrors list
 */
struct hmm {
	struct mm_struct	*mm;
	spinlock_t		lock;
	atomic_t		sequence;
	struct list_head	ranges;
	struct list_head	mirrors;
	struct mmu_notifier	mmu_notifier;
	struct rw_semaphore	mirrors_sem;
};

/*
 * hmm_register - register HMM against an mm (HMM internal)
 *
 * @mm: mm struct to attach to
 *
 * This is not intended to be used directly by device drivers. It allocates an
 * HMM struct if mm does not have one, and initializes it.
 */
static struct hmm *hmm_register(struct mm_struct *mm)
{
	struct hmm *hmm = READ_ONCE(mm->hmm);
	bool cleanup = false;

	/*
	 * The hmm struct can only be freed once the mm_struct goes away,
	 * hence we should always have pre-allocated an new hmm struct
	 * above.
	 */
	if (hmm)
		return hmm;

	hmm = kmalloc(sizeof(*hmm), GFP_KERNEL);
	if (!hmm)
		return NULL;
	INIT_LIST_HEAD(&hmm->mirrors);
	init_rwsem(&hmm->mirrors_sem);
	atomic_set(&hmm->sequence, 0);
	hmm->mmu_notifier.ops = NULL;
	INIT_LIST_HEAD(&hmm->ranges);
	spin_lock_init(&hmm->lock);
	hmm->mm = mm;

	/*
	 * We should only get here if hold the mmap_sem in write mode ie on
	 * registration of first mirror through hmm_mirror_register()
	 */
	hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops;
	if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) {
		kfree(hmm);
		return NULL;
	}

	spin_lock(&mm->page_table_lock);
	if (!mm->hmm)
		mm->hmm = hmm;
	else
		cleanup = true;
	spin_unlock(&mm->page_table_lock);

	if (cleanup) {
		mmu_notifier_unregister(&hmm->mmu_notifier, mm);
		kfree(hmm);
	}

	return mm->hmm;
}

void hmm_mm_destroy(struct mm_struct *mm)
{
	kfree(mm->hmm);
}
#endif /* CONFIG_HMM */

#if IS_ENABLED(CONFIG_HMM_MIRROR)
static void hmm_invalidate_range(struct hmm *hmm,
				 enum hmm_update_type action,
				 unsigned long start,
				 unsigned long end)
{
	struct hmm_mirror *mirror;
	struct hmm_range *range;

	spin_lock(&hmm->lock);
	list_for_each_entry(range, &hmm->ranges, list) {
		unsigned long addr, idx, npages;

		if (end < range->start || start >= range->end)
			continue;

		range->valid = false;
		addr = max(start, range->start);
		idx = (addr - range->start) >> PAGE_SHIFT;
		npages = (min(range->end, end) - addr) >> PAGE_SHIFT;
		memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages);
	}
	spin_unlock(&hmm->lock);

	down_read(&hmm->mirrors_sem);
	list_for_each_entry(mirror, &hmm->mirrors, list)
		mirror->ops->sync_cpu_device_pagetables(mirror, action,
							start, end);
	up_read(&hmm->mirrors_sem);
}

static void hmm_invalidate_range_start(struct mmu_notifier *mn,
				       struct mm_struct *mm,
				       unsigned long start,
				       unsigned long end)
{
	struct hmm *hmm = mm->hmm;

	VM_BUG_ON(!hmm);

	atomic_inc(&hmm->sequence);
}

static void hmm_invalidate_range_end(struct mmu_notifier *mn,
				     struct mm_struct *mm,
				     unsigned long start,
				     unsigned long end)
{
	struct hmm *hmm = mm->hmm;

	VM_BUG_ON(!hmm);

	hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end);
}

static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
	.invalidate_range_start	= hmm_invalidate_range_start,
	.invalidate_range_end	= hmm_invalidate_range_end,
};

/*
 * hmm_mirror_register() - register a mirror against an mm
 *
 * @mirror: new mirror struct to register
 * @mm: mm to register against
 *
 * To start mirroring a process address space, the device driver must register
 * an HMM mirror struct.
 *
 * THE mm->mmap_sem MUST BE HELD IN WRITE MODE !
 */
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
	/* Sanity check */
	if (!mm || !mirror || !mirror->ops)
		return -EINVAL;

	mirror->hmm = hmm_register(mm);
	if (!mirror->hmm)
		return -ENOMEM;

	down_write(&mirror->hmm->mirrors_sem);
	list_add(&mirror->list, &mirror->hmm->mirrors);
	up_write(&mirror->hmm->mirrors_sem);

	return 0;
}
EXPORT_SYMBOL(hmm_mirror_register);

/*
 * hmm_mirror_unregister() - unregister a mirror
 *
 * @mirror: new mirror struct to register
 *
 * Stop mirroring a process address space, and cleanup.
 */
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
	struct hmm *hmm = mirror->hmm;

	down_write(&hmm->mirrors_sem);
	list_del(&mirror->list);
	up_write(&hmm->mirrors_sem);
}
EXPORT_SYMBOL(hmm_mirror_unregister);

static void hmm_pfns_special(hmm_pfn_t *pfns,
			     unsigned long addr,
			     unsigned long end)
{
	for (; addr < end; addr += PAGE_SIZE, pfns++)
		*pfns = HMM_PFN_SPECIAL;
}

static int hmm_pfns_bad(unsigned long addr,
			unsigned long end,
			struct mm_walk *walk)
{
	struct hmm_range *range = walk->private;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, i++)
		pfns[i] = HMM_PFN_ERROR;

	return 0;
}

static int hmm_vma_walk_hole(unsigned long addr,
			     unsigned long end,
			     struct mm_walk *walk)
{
	struct hmm_range *range = walk->private;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, i++)
		pfns[i] = HMM_PFN_EMPTY;

	return 0;
}

static int hmm_vma_walk_clear(unsigned long addr,
			      unsigned long end,
			      struct mm_walk *walk)
{
	struct hmm_range *range = walk->private;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long i;

	i = (addr - range->start) >> PAGE_SHIFT;
	for (; addr < end; addr += PAGE_SIZE, i++)
		pfns[i] = 0;

	return 0;
}

static int hmm_vma_walk_pmd(pmd_t *pmdp,
			    unsigned long start,
			    unsigned long end,
			    struct mm_walk *walk)
{
	struct hmm_range *range = walk->private;
	struct vm_area_struct *vma = walk->vma;
	hmm_pfn_t *pfns = range->pfns;
	unsigned long addr = start, i;
	hmm_pfn_t flag;
	pte_t *ptep;

	i = (addr - range->start) >> PAGE_SHIFT;
	flag = vma->vm_flags & VM_READ ? HMM_PFN_READ : 0;

again:
	if (pmd_none(*pmdp))
		return hmm_vma_walk_hole(start, end, walk);

	if (pmd_huge(*pmdp) && vma->vm_flags & VM_HUGETLB)
		return hmm_pfns_bad(start, end, walk);

	if (pmd_devmap(*pmdp) || pmd_trans_huge(*pmdp)) {
		unsigned long pfn;
		pmd_t pmd;

		/*
		 * No need to take pmd_lock here, even if some other threads
		 * is splitting the huge pmd we will get that event through
		 * mmu_notifier callback.
		 *
		 * So just read pmd value and check again its 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;
		if (pmd_protnone(pmd))
			return hmm_vma_walk_clear(start, end, walk);

		pfn = pmd_pfn(pmd) + pte_index(addr);
		flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
		for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
			pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
		return 0;
	}

	if (pmd_bad(*pmdp))
		return hmm_pfns_bad(start, end, walk);

	ptep = pte_offset_map(pmdp, addr);
	for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
		pte_t pte = *ptep;

		pfns[i] = 0;

		if (pte_none(pte) || !pte_present(pte)) {
			pfns[i] = HMM_PFN_EMPTY;
			continue;
		}

		pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
		pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
	}
	pte_unmap(ptep - 1);

	return 0;
}

/*
 * hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses
 * @vma: virtual memory area containing the virtual address range
 * @range: used to track snapshot validity
 * @start: range virtual start address (inclusive)
 * @end: range virtual end address (exclusive)
 * @entries: array of hmm_pfn_t: provided by the caller, filled in by function
 * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, 0 success
 *
 * This snapshots the CPU page table for a range of virtual addresses. Snapshot
 * validity is tracked by range struct. See hmm_vma_range_done() for further
 * information.
 *
 * The range struct is initialized here. It tracks the CPU page table, but only
 * if the function returns success (0), in which case the caller must then call
 * hmm_vma_range_done() to stop CPU page table update tracking on this range.
 *
 * NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS
 * MEMORY CORRUPTION ! YOU HAVE BEEN WARNED !
 */
int hmm_vma_get_pfns(struct vm_area_struct *vma,
		     struct hmm_range *range,
		     unsigned long start,
		     unsigned long end,
		     hmm_pfn_t *pfns)
{
	struct mm_walk mm_walk;
	struct hmm *hmm;

	/* FIXME support hugetlb fs */
	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
		hmm_pfns_special(pfns, start, end);
		return -EINVAL;
	}

	/* Sanity check, this really should not happen ! */
	if (start < vma->vm_start || start >= vma->vm_end)
		return -EINVAL;
	if (end < vma->vm_start || end > vma->vm_end)
		return -EINVAL;

	hmm = hmm_register(vma->vm_mm);
	if (!hmm)
		return -ENOMEM;
	/* Caller must have registered a mirror, via hmm_mirror_register() ! */
	if (!hmm->mmu_notifier.ops)
		return -EINVAL;

	/* Initialize range to track CPU page table update */
	range->start = start;
	range->pfns = pfns;
	range->end = end;
	spin_lock(&hmm->lock);
	range->valid = true;
	list_add_rcu(&range->list, &hmm->ranges);
	spin_unlock(&hmm->lock);

	mm_walk.vma = vma;
	mm_walk.mm = vma->vm_mm;
	mm_walk.private = range;
	mm_walk.pte_entry = NULL;
	mm_walk.test_walk = NULL;
	mm_walk.hugetlb_entry = NULL;
	mm_walk.pmd_entry = hmm_vma_walk_pmd;
	mm_walk.pte_hole = hmm_vma_walk_hole;

	walk_page_range(start, end, &mm_walk);

	return 0;
}
EXPORT_SYMBOL(hmm_vma_get_pfns);

/*
 * hmm_vma_range_done() - stop tracking change to CPU page table over a range
 * @vma: virtual memory area containing the virtual address range
 * @range: range being tracked
 * Returns: false if range data has been invalidated, true otherwise
 *
 * Range struct is used to track updates to the CPU page table after a call to
 * either hmm_vma_get_pfns() or hmm_vma_fault(). Once the device driver is done
 * using the data,  or wants to lock updates to the data it got from those
 * functions, it must call the hmm_vma_range_done() function, which will then
 * stop tracking CPU page table updates.
 *
 * Note that device driver must still implement general CPU page table update
 * tracking either by using hmm_mirror (see hmm_mirror_register()) or by using
 * the mmu_notifier API directly.
 *
 * CPU page table update tracking done through hmm_range is only temporary and
 * to be used while trying to duplicate CPU page table contents for a range of
 * virtual addresses.
 *
 * There are two ways to use this :
 * again:
 *   hmm_vma_get_pfns(vma, range, start, end, pfns);
 *   trans = device_build_page_table_update_transaction(pfns);
 *   device_page_table_lock();
 *   if (!hmm_vma_range_done(vma, range)) {
 *     device_page_table_unlock();
 *     goto again;
 *   }
 *   device_commit_transaction(trans);
 *   device_page_table_unlock();
 *
 * Or:
 *   hmm_vma_get_pfns(vma, range, start, end, pfns);
 *   device_page_table_lock();
 *   hmm_vma_range_done(vma, range);
 *   device_update_page_table(pfns);
 *   device_page_table_unlock();
 */
bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range)
{
	unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
	struct hmm *hmm;

	if (range->end <= range->start) {
		BUG();
		return false;
	}

	hmm = hmm_register(vma->vm_mm);
	if (!hmm) {
		memset(range->pfns, 0, sizeof(*range->pfns) * npages);
		return false;
	}

	spin_lock(&hmm->lock);
	list_del_rcu(&range->list);
	spin_unlock(&hmm->lock);

	return range->valid;
}
EXPORT_SYMBOL(hmm_vma_range_done);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */