summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/mmu_context_iommu.c
blob: a712a650a8b6d49e499cfabd64fa784fc1ea8bfe (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
/*
 *  IOMMU helpers in MMU context.
 *
 *  Copyright (C) 2015 IBM Corp. <aik@ozlabs.ru>
 *
 *  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.
 *
 */

#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/rculist.h>
#include <linux/vmalloc.h>
#include <linux/mutex.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <linux/sizes.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>

static DEFINE_MUTEX(mem_list_mutex);

#define MM_IOMMU_TABLE_GROUP_PAGE_DIRTY	0x1
#define MM_IOMMU_TABLE_GROUP_PAGE_MASK	~(SZ_4K - 1)

struct mm_iommu_table_group_mem_t {
	struct list_head next;
	struct rcu_head rcu;
	unsigned long used;
	atomic64_t mapped;
	unsigned int pageshift;
	u64 ua;			/* userspace address */
	u64 entries;		/* number of entries in hpas[] */
	u64 *hpas;		/* vmalloc'ed */
#define MM_IOMMU_TABLE_INVALID_HPA	((uint64_t)-1)
	u64 dev_hpa;		/* Device memory base address */
};

static long mm_iommu_adjust_locked_vm(struct mm_struct *mm,
		unsigned long npages, bool incr)
{
	long ret = 0, locked, lock_limit;

	if (!npages)
		return 0;

	down_write(&mm->mmap_sem);

	if (incr) {
		locked = mm->locked_vm + npages;
		lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			ret = -ENOMEM;
		else
			mm->locked_vm += npages;
	} else {
		if (WARN_ON_ONCE(npages > mm->locked_vm))
			npages = mm->locked_vm;
		mm->locked_vm -= npages;
	}

	pr_debug("[%d] RLIMIT_MEMLOCK HASH64 %c%ld %ld/%ld\n",
			current ? current->pid : 0,
			incr ? '+' : '-',
			npages << PAGE_SHIFT,
			mm->locked_vm << PAGE_SHIFT,
			rlimit(RLIMIT_MEMLOCK));
	up_write(&mm->mmap_sem);

	return ret;
}

bool mm_iommu_preregistered(struct mm_struct *mm)
{
	return !list_empty(&mm->context.iommu_group_mem_list);
}
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);

/*
 * Taken from alloc_migrate_target with changes to remove CMA allocations
 */
struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
{
	gfp_t gfp_mask = GFP_USER;
	struct page *new_page;

	if (PageCompound(page))
		return NULL;

	if (PageHighMem(page))
		gfp_mask |= __GFP_HIGHMEM;

	/*
	 * We don't want the allocation to force an OOM if possibe
	 */
	new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
	return new_page;
}

static int mm_iommu_move_page_from_cma(struct page *page)
{
	int ret = 0;
	LIST_HEAD(cma_migrate_pages);

	/* Ignore huge pages for now */
	if (PageCompound(page))
		return -EBUSY;

	lru_add_drain();
	ret = isolate_lru_page(page);
	if (ret)
		return ret;

	list_add(&page->lru, &cma_migrate_pages);
	put_page(page); /* Drop the gup reference */

	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
				NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
	if (ret) {
		if (!list_empty(&cma_migrate_pages))
			putback_movable_pages(&cma_migrate_pages);
	}

	return 0;
}

static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
		unsigned long entries, unsigned long dev_hpa,
		struct mm_iommu_table_group_mem_t **pmem)
{
	struct mm_iommu_table_group_mem_t *mem;
	long i, j, ret = 0, locked_entries = 0;
	unsigned int pageshift;
	unsigned long flags;
	unsigned long cur_ua;
	struct page *page = NULL;

	mutex_lock(&mem_list_mutex);

	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
			next) {
		/* Overlap? */
		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
				(ua < (mem->ua +
				       (mem->entries << PAGE_SHIFT)))) {
			ret = -EINVAL;
			goto unlock_exit;
		}

	}

	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
		if (ret)
			goto unlock_exit;

		locked_entries = entries;
	}

	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
	if (!mem) {
		ret = -ENOMEM;
		goto unlock_exit;
	}

	if (dev_hpa != MM_IOMMU_TABLE_INVALID_HPA) {
		mem->pageshift = __ffs(dev_hpa | (entries << PAGE_SHIFT));
		mem->dev_hpa = dev_hpa;
		goto good_exit;
	}
	mem->dev_hpa = MM_IOMMU_TABLE_INVALID_HPA;

	/*
	 * For a starting point for a maximum page size calculation
	 * we use @ua and @entries natural alignment to allow IOMMU pages
	 * smaller than huge pages but still bigger than PAGE_SIZE.
	 */
	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
	if (!mem->hpas) {
		kfree(mem);
		ret = -ENOMEM;
		goto unlock_exit;
	}

	for (i = 0; i < entries; ++i) {
		cur_ua = ua + (i << PAGE_SHIFT);
		if (1 != get_user_pages_fast(cur_ua,
					1/* pages */, 1/* iswrite */, &page)) {
			ret = -EFAULT;
			for (j = 0; j < i; ++j)
				put_page(pfn_to_page(mem->hpas[j] >>
						PAGE_SHIFT));
			vfree(mem->hpas);
			kfree(mem);
			goto unlock_exit;
		}
		/*
		 * If we get a page from the CMA zone, since we are going to
		 * be pinning these entries, we might as well move them out
		 * of the CMA zone if possible. NOTE: faulting in + migration
		 * can be expensive. Batching can be considered later
		 */
		if (is_migrate_cma_page(page)) {
			if (mm_iommu_move_page_from_cma(page))
				goto populate;
			if (1 != get_user_pages_fast(cur_ua,
						1/* pages */, 1/* iswrite */,
						&page)) {
				ret = -EFAULT;
				for (j = 0; j < i; ++j)
					put_page(pfn_to_page(mem->hpas[j] >>
								PAGE_SHIFT));
				vfree(mem->hpas);
				kfree(mem);
				goto unlock_exit;
			}
		}
populate:
		pageshift = PAGE_SHIFT;
		if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
			pte_t *pte;
			struct page *head = compound_head(page);
			unsigned int compshift = compound_order(head);
			unsigned int pteshift;

			local_irq_save(flags); /* disables as well */
			pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);

			/* Double check it is still the same pinned page */
			if (pte && pte_page(*pte) == head &&
			    pteshift == compshift + PAGE_SHIFT)
				pageshift = max_t(unsigned int, pteshift,
						PAGE_SHIFT);
			local_irq_restore(flags);
		}
		mem->pageshift = min(mem->pageshift, pageshift);
		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
	}

good_exit:
	atomic64_set(&mem->mapped, 1);
	mem->used = 1;
	mem->ua = ua;
	mem->entries = entries;
	*pmem = mem;

	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);

unlock_exit:
	if (locked_entries && ret)
		mm_iommu_adjust_locked_vm(mm, locked_entries, false);

	mutex_unlock(&mem_list_mutex);

	return ret;
}

long mm_iommu_new(struct mm_struct *mm, unsigned long ua, unsigned long entries,
		struct mm_iommu_table_group_mem_t **pmem)
{
	return mm_iommu_do_alloc(mm, ua, entries, MM_IOMMU_TABLE_INVALID_HPA,
			pmem);
}
EXPORT_SYMBOL_GPL(mm_iommu_new);

long mm_iommu_newdev(struct mm_struct *mm, unsigned long ua,
		unsigned long entries, unsigned long dev_hpa,
		struct mm_iommu_table_group_mem_t **pmem)
{
	return mm_iommu_do_alloc(mm, ua, entries, dev_hpa, pmem);
}
EXPORT_SYMBOL_GPL(mm_iommu_newdev);

static void mm_iommu_unpin(struct mm_iommu_table_group_mem_t *mem)
{
	long i;
	struct page *page = NULL;

	if (!mem->hpas)
		return;

	for (i = 0; i < mem->entries; ++i) {
		if (!mem->hpas[i])
			continue;

		page = pfn_to_page(mem->hpas[i] >> PAGE_SHIFT);
		if (!page)
			continue;

		if (mem->hpas[i] & MM_IOMMU_TABLE_GROUP_PAGE_DIRTY)
			SetPageDirty(page);

		put_page(page);
		mem->hpas[i] = 0;
	}
}

static void mm_iommu_do_free(struct mm_iommu_table_group_mem_t *mem)
{

	mm_iommu_unpin(mem);
	vfree(mem->hpas);
	kfree(mem);
}

static void mm_iommu_free(struct rcu_head *head)
{
	struct mm_iommu_table_group_mem_t *mem = container_of(head,
			struct mm_iommu_table_group_mem_t, rcu);

	mm_iommu_do_free(mem);
}

static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
{
	list_del_rcu(&mem->next);
	call_rcu(&mem->rcu, mm_iommu_free);
}

long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
{
	long ret = 0;
	unsigned long entries, dev_hpa;

	mutex_lock(&mem_list_mutex);

	if (mem->used == 0) {
		ret = -ENOENT;
		goto unlock_exit;
	}

	--mem->used;
	/* There are still users, exit */
	if (mem->used)
		goto unlock_exit;

	/* Are there still mappings? */
	if (atomic_cmpxchg(&mem->mapped, 1, 0) != 1) {
		++mem->used;
		ret = -EBUSY;
		goto unlock_exit;
	}

	/* @mapped became 0 so now mappings are disabled, release the region */
	entries = mem->entries;
	dev_hpa = mem->dev_hpa;
	mm_iommu_release(mem);

	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
		mm_iommu_adjust_locked_vm(mm, entries, false);

unlock_exit:
	mutex_unlock(&mem_list_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_put);

struct mm_iommu_table_group_mem_t *mm_iommu_lookup(struct mm_struct *mm,
		unsigned long ua, unsigned long size)
{
	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;

	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
		if ((mem->ua <= ua) &&
				(ua + size <= mem->ua +
				 (mem->entries << PAGE_SHIFT))) {
			ret = mem;
			break;
		}
	}

	return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_lookup);

struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(struct mm_struct *mm,
		unsigned long ua, unsigned long size)
{
	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;

	list_for_each_entry_lockless(mem, &mm->context.iommu_group_mem_list,
			next) {
		if ((mem->ua <= ua) &&
				(ua + size <= mem->ua +
				 (mem->entries << PAGE_SHIFT))) {
			ret = mem;
			break;
		}
	}

	return ret;
}

struct mm_iommu_table_group_mem_t *mm_iommu_get(struct mm_struct *mm,
		unsigned long ua, unsigned long entries)
{
	struct mm_iommu_table_group_mem_t *mem, *ret = NULL;

	mutex_lock(&mem_list_mutex);

	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
		if ((mem->ua == ua) && (mem->entries == entries)) {
			ret = mem;
			++mem->used;
			break;
		}
	}

	mutex_unlock(&mem_list_mutex);

	return ret;
}
EXPORT_SYMBOL_GPL(mm_iommu_get);

long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
	u64 *va;

	if (entry >= mem->entries)
		return -EFAULT;

	if (pageshift > mem->pageshift)
		return -EFAULT;

	if (!mem->hpas) {
		*hpa = mem->dev_hpa + (ua - mem->ua);
		return 0;
	}

	va = &mem->hpas[entry];
	*hpa = (*va & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);

	return 0;
}
EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);

long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
{
	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
	unsigned long *pa;

	if (entry >= mem->entries)
		return -EFAULT;

	if (pageshift > mem->pageshift)
		return -EFAULT;

	if (!mem->hpas) {
		*hpa = mem->dev_hpa + (ua - mem->ua);
		return 0;
	}

	pa = (void *) vmalloc_to_phys(&mem->hpas[entry]);
	if (!pa)
		return -EFAULT;

	*hpa = (*pa & MM_IOMMU_TABLE_GROUP_PAGE_MASK) | (ua & ~PAGE_MASK);

	return 0;
}

extern void mm_iommu_ua_mark_dirty_rm(struct mm_struct *mm, unsigned long ua)
{
	struct mm_iommu_table_group_mem_t *mem;
	long entry;
	void *va;
	unsigned long *pa;

	mem = mm_iommu_lookup_rm(mm, ua, PAGE_SIZE);
	if (!mem)
		return;

	if (mem->dev_hpa != MM_IOMMU_TABLE_INVALID_HPA)
		return;

	entry = (ua - mem->ua) >> PAGE_SHIFT;
	va = &mem->hpas[entry];

	pa = (void *) vmalloc_to_phys(va);
	if (!pa)
		return;

	*pa |= MM_IOMMU_TABLE_GROUP_PAGE_DIRTY;
}

bool mm_iommu_is_devmem(struct mm_struct *mm, unsigned long hpa,
		unsigned int pageshift, unsigned long *size)
{
	struct mm_iommu_table_group_mem_t *mem;
	unsigned long end;

	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list, next) {
		if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
			continue;

		end = mem->dev_hpa + (mem->entries << PAGE_SHIFT);
		if ((mem->dev_hpa <= hpa) && (hpa < end)) {
			/*
			 * Since the IOMMU page size might be bigger than
			 * PAGE_SIZE, the amount of preregistered memory
			 * starting from @hpa might be smaller than 1<<pageshift
			 * and the caller needs to distinguish this situation.
			 */
			*size = min(1UL << pageshift, end - hpa);
			return true;
		}
	}

	return false;
}
EXPORT_SYMBOL_GPL(mm_iommu_is_devmem);

long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem)
{
	if (atomic64_inc_not_zero(&mem->mapped))
		return 0;

	/* Last mm_iommu_put() has been called, no more mappings allowed() */
	return -ENXIO;
}
EXPORT_SYMBOL_GPL(mm_iommu_mapped_inc);

void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem)
{
	atomic64_add_unless(&mem->mapped, -1, 1);
}
EXPORT_SYMBOL_GPL(mm_iommu_mapped_dec);

void mm_iommu_init(struct mm_struct *mm)
{
	INIT_LIST_HEAD_RCU(&mm->context.iommu_group_mem_list);
}