summaryrefslogtreecommitdiff
path: root/drivers/iommu/amd/io_pgtable.c
blob: 9d9a7fde59e75dcbdbff9fecd5cda23fc9c3faf7 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * CPU-agnostic AMD IO page table allocator.
 *
 * Copyright (C) 2020 Advanced Micro Devices, Inc.
 * Author: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
 */

#define pr_fmt(fmt)     "AMD-Vi: " fmt
#define dev_fmt(fmt)    pr_fmt(fmt)

#include <linux/atomic.h>
#include <linux/bitops.h>
#include <linux/io-pgtable.h>
#include <linux/kernel.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/dma-mapping.h>

#include <asm/barrier.h>

#include "amd_iommu_types.h"
#include "amd_iommu.h"
#include "../iommu-pages.h"

static void v1_tlb_flush_all(void *cookie)
{
}

static void v1_tlb_flush_walk(unsigned long iova, size_t size,
				  size_t granule, void *cookie)
{
}

static void v1_tlb_add_page(struct iommu_iotlb_gather *gather,
					 unsigned long iova, size_t granule,
					 void *cookie)
{
}

static const struct iommu_flush_ops v1_flush_ops = {
	.tlb_flush_all	= v1_tlb_flush_all,
	.tlb_flush_walk = v1_tlb_flush_walk,
	.tlb_add_page	= v1_tlb_add_page,
};

/*
 * Helper function to get the first pte of a large mapping
 */
static u64 *first_pte_l7(u64 *pte, unsigned long *page_size,
			 unsigned long *count)
{
	unsigned long pte_mask, pg_size, cnt;
	u64 *fpte;

	pg_size  = PTE_PAGE_SIZE(*pte);
	cnt      = PAGE_SIZE_PTE_COUNT(pg_size);
	pte_mask = ~((cnt << 3) - 1);
	fpte     = (u64 *)(((unsigned long)pte) & pte_mask);

	if (page_size)
		*page_size = pg_size;

	if (count)
		*count = cnt;

	return fpte;
}

/****************************************************************************
 *
 * The functions below are used the create the page table mappings for
 * unity mapped regions.
 *
 ****************************************************************************/

static void free_pt_page(u64 *pt, struct list_head *freelist)
{
	struct page *p = virt_to_page(pt);

	list_add_tail(&p->lru, freelist);
}

static void free_pt_lvl(u64 *pt, struct list_head *freelist, int lvl)
{
	u64 *p;
	int i;

	for (i = 0; i < 512; ++i) {
		/* PTE present? */
		if (!IOMMU_PTE_PRESENT(pt[i]))
			continue;

		/* Large PTE? */
		if (PM_PTE_LEVEL(pt[i]) == 0 ||
		    PM_PTE_LEVEL(pt[i]) == 7)
			continue;

		/*
		 * Free the next level. No need to look at l1 tables here since
		 * they can only contain leaf PTEs; just free them directly.
		 */
		p = IOMMU_PTE_PAGE(pt[i]);
		if (lvl > 2)
			free_pt_lvl(p, freelist, lvl - 1);
		else
			free_pt_page(p, freelist);
	}

	free_pt_page(pt, freelist);
}

static void free_sub_pt(u64 *root, int mode, struct list_head *freelist)
{
	switch (mode) {
	case PAGE_MODE_NONE:
	case PAGE_MODE_7_LEVEL:
		break;
	case PAGE_MODE_1_LEVEL:
		free_pt_page(root, freelist);
		break;
	case PAGE_MODE_2_LEVEL:
	case PAGE_MODE_3_LEVEL:
	case PAGE_MODE_4_LEVEL:
	case PAGE_MODE_5_LEVEL:
	case PAGE_MODE_6_LEVEL:
		free_pt_lvl(root, freelist, mode);
		break;
	default:
		BUG();
	}
}

void amd_iommu_domain_set_pgtable(struct protection_domain *domain,
				  u64 *root, int mode)
{
	u64 pt_root;

	/* lowest 3 bits encode pgtable mode */
	pt_root = mode & 7;
	pt_root |= (u64)root;

	amd_iommu_domain_set_pt_root(domain, pt_root);
}

/*
 * This function is used to add another level to an IO page table. Adding
 * another level increases the size of the address space by 9 bits to a size up
 * to 64 bits.
 */
static bool increase_address_space(struct protection_domain *domain,
				   unsigned long address,
				   gfp_t gfp)
{
	unsigned long flags;
	bool ret = true;
	u64 *pte;

	pte = iommu_alloc_page_node(domain->nid, gfp);
	if (!pte)
		return false;

	spin_lock_irqsave(&domain->lock, flags);

	if (address <= PM_LEVEL_SIZE(domain->iop.mode))
		goto out;

	ret = false;
	if (WARN_ON_ONCE(domain->iop.mode == PAGE_MODE_6_LEVEL))
		goto out;

	*pte = PM_LEVEL_PDE(domain->iop.mode, iommu_virt_to_phys(domain->iop.root));

	domain->iop.root  = pte;
	domain->iop.mode += 1;
	amd_iommu_update_and_flush_device_table(domain);
	amd_iommu_domain_flush_complete(domain);

	/*
	 * Device Table needs to be updated and flushed before the new root can
	 * be published.
	 */
	amd_iommu_domain_set_pgtable(domain, pte, domain->iop.mode);

	pte = NULL;
	ret = true;

out:
	spin_unlock_irqrestore(&domain->lock, flags);
	iommu_free_page(pte);

	return ret;
}

static u64 *alloc_pte(struct protection_domain *domain,
		      unsigned long address,
		      unsigned long page_size,
		      u64 **pte_page,
		      gfp_t gfp,
		      bool *updated)
{
	int level, end_lvl;
	u64 *pte, *page;

	BUG_ON(!is_power_of_2(page_size));

	while (address > PM_LEVEL_SIZE(domain->iop.mode)) {
		/*
		 * Return an error if there is no memory to update the
		 * page-table.
		 */
		if (!increase_address_space(domain, address, gfp))
			return NULL;
	}


	level   = domain->iop.mode - 1;
	pte     = &domain->iop.root[PM_LEVEL_INDEX(level, address)];
	address = PAGE_SIZE_ALIGN(address, page_size);
	end_lvl = PAGE_SIZE_LEVEL(page_size);

	while (level > end_lvl) {
		u64 __pte, __npte;
		int pte_level;

		__pte     = *pte;
		pte_level = PM_PTE_LEVEL(__pte);

		/*
		 * If we replace a series of large PTEs, we need
		 * to tear down all of them.
		 */
		if (IOMMU_PTE_PRESENT(__pte) &&
		    pte_level == PAGE_MODE_7_LEVEL) {
			unsigned long count, i;
			u64 *lpte;

			lpte = first_pte_l7(pte, NULL, &count);

			/*
			 * Unmap the replicated PTEs that still match the
			 * original large mapping
			 */
			for (i = 0; i < count; ++i)
				cmpxchg64(&lpte[i], __pte, 0ULL);

			*updated = true;
			continue;
		}

		if (!IOMMU_PTE_PRESENT(__pte) ||
		    pte_level == PAGE_MODE_NONE) {
			page = iommu_alloc_page_node(domain->nid, gfp);

			if (!page)
				return NULL;

			__npte = PM_LEVEL_PDE(level, iommu_virt_to_phys(page));

			/* pte could have been changed somewhere. */
			if (!try_cmpxchg64(pte, &__pte, __npte))
				iommu_free_page(page);
			else if (IOMMU_PTE_PRESENT(__pte))
				*updated = true;

			continue;
		}

		/* No level skipping support yet */
		if (pte_level != level)
			return NULL;

		level -= 1;

		pte = IOMMU_PTE_PAGE(__pte);

		if (pte_page && level == end_lvl)
			*pte_page = pte;

		pte = &pte[PM_LEVEL_INDEX(level, address)];
	}

	return pte;
}

/*
 * This function checks if there is a PTE for a given dma address. If
 * there is one, it returns the pointer to it.
 */
static u64 *fetch_pte(struct amd_io_pgtable *pgtable,
		      unsigned long address,
		      unsigned long *page_size)
{
	int level;
	u64 *pte;

	*page_size = 0;

	if (address > PM_LEVEL_SIZE(pgtable->mode))
		return NULL;

	level	   =  pgtable->mode - 1;
	pte	   = &pgtable->root[PM_LEVEL_INDEX(level, address)];
	*page_size =  PTE_LEVEL_PAGE_SIZE(level);

	while (level > 0) {

		/* Not Present */
		if (!IOMMU_PTE_PRESENT(*pte))
			return NULL;

		/* Large PTE */
		if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL ||
		    PM_PTE_LEVEL(*pte) == PAGE_MODE_NONE)
			break;

		/* No level skipping support yet */
		if (PM_PTE_LEVEL(*pte) != level)
			return NULL;

		level -= 1;

		/* Walk to the next level */
		pte	   = IOMMU_PTE_PAGE(*pte);
		pte	   = &pte[PM_LEVEL_INDEX(level, address)];
		*page_size = PTE_LEVEL_PAGE_SIZE(level);
	}

	/*
	 * If we have a series of large PTEs, make
	 * sure to return a pointer to the first one.
	 */
	if (PM_PTE_LEVEL(*pte) == PAGE_MODE_7_LEVEL)
		pte = first_pte_l7(pte, page_size, NULL);

	return pte;
}

static void free_clear_pte(u64 *pte, u64 pteval, struct list_head *freelist)
{
	u64 *pt;
	int mode;

	while (!try_cmpxchg64(pte, &pteval, 0))
		pr_warn("AMD-Vi: IOMMU pte changed since we read it\n");

	if (!IOMMU_PTE_PRESENT(pteval))
		return;

	pt   = IOMMU_PTE_PAGE(pteval);
	mode = IOMMU_PTE_MODE(pteval);

	free_sub_pt(pt, mode, freelist);
}

/*
 * Generic mapping functions. It maps a physical address into a DMA
 * address space. It allocates the page table pages if necessary.
 * In the future it can be extended to a generic mapping function
 * supporting all features of AMD IOMMU page tables like level skipping
 * and full 64 bit address spaces.
 */
static int iommu_v1_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
			      phys_addr_t paddr, size_t pgsize, size_t pgcount,
			      int prot, gfp_t gfp, size_t *mapped)
{
	struct protection_domain *dom = io_pgtable_ops_to_domain(ops);
	LIST_HEAD(freelist);
	bool updated = false;
	u64 __pte, *pte;
	int ret, i, count;
	size_t size = pgcount << __ffs(pgsize);
	unsigned long o_iova = iova;

	BUG_ON(!IS_ALIGNED(iova, pgsize));
	BUG_ON(!IS_ALIGNED(paddr, pgsize));

	ret = -EINVAL;
	if (!(prot & IOMMU_PROT_MASK))
		goto out;

	while (pgcount > 0) {
		count = PAGE_SIZE_PTE_COUNT(pgsize);
		pte   = alloc_pte(dom, iova, pgsize, NULL, gfp, &updated);

		ret = -ENOMEM;
		if (!pte)
			goto out;

		for (i = 0; i < count; ++i)
			free_clear_pte(&pte[i], pte[i], &freelist);

		if (!list_empty(&freelist))
			updated = true;

		if (count > 1) {
			__pte = PAGE_SIZE_PTE(__sme_set(paddr), pgsize);
			__pte |= PM_LEVEL_ENC(7) | IOMMU_PTE_PR | IOMMU_PTE_FC;
		} else
			__pte = __sme_set(paddr) | IOMMU_PTE_PR | IOMMU_PTE_FC;

		if (prot & IOMMU_PROT_IR)
			__pte |= IOMMU_PTE_IR;
		if (prot & IOMMU_PROT_IW)
			__pte |= IOMMU_PTE_IW;

		for (i = 0; i < count; ++i)
			pte[i] = __pte;

		iova  += pgsize;
		paddr += pgsize;
		pgcount--;
		if (mapped)
			*mapped += pgsize;
	}

	ret = 0;

out:
	if (updated) {
		unsigned long flags;

		spin_lock_irqsave(&dom->lock, flags);
		/*
		 * Flush domain TLB(s) and wait for completion. Any Device-Table
		 * Updates and flushing already happened in
		 * increase_address_space().
		 */
		amd_iommu_domain_flush_pages(dom, o_iova, size);
		spin_unlock_irqrestore(&dom->lock, flags);
	}

	/* Everything flushed out, free pages now */
	iommu_put_pages_list(&freelist);

	return ret;
}

static unsigned long iommu_v1_unmap_pages(struct io_pgtable_ops *ops,
					  unsigned long iova,
					  size_t pgsize, size_t pgcount,
					  struct iommu_iotlb_gather *gather)
{
	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
	unsigned long long unmapped;
	unsigned long unmap_size;
	u64 *pte;
	size_t size = pgcount << __ffs(pgsize);

	BUG_ON(!is_power_of_2(pgsize));

	unmapped = 0;

	while (unmapped < size) {
		pte = fetch_pte(pgtable, iova, &unmap_size);
		if (pte) {
			int i, count;

			count = PAGE_SIZE_PTE_COUNT(unmap_size);
			for (i = 0; i < count; i++)
				pte[i] = 0ULL;
		} else {
			return unmapped;
		}

		iova = (iova & ~(unmap_size - 1)) + unmap_size;
		unmapped += unmap_size;
	}

	return unmapped;
}

static phys_addr_t iommu_v1_iova_to_phys(struct io_pgtable_ops *ops, unsigned long iova)
{
	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
	unsigned long offset_mask, pte_pgsize;
	u64 *pte, __pte;

	pte = fetch_pte(pgtable, iova, &pte_pgsize);

	if (!pte || !IOMMU_PTE_PRESENT(*pte))
		return 0;

	offset_mask = pte_pgsize - 1;
	__pte	    = __sme_clr(*pte & PM_ADDR_MASK);

	return (__pte & ~offset_mask) | (iova & offset_mask);
}

static bool pte_test_and_clear_dirty(u64 *ptep, unsigned long size,
				     unsigned long flags)
{
	bool test_only = flags & IOMMU_DIRTY_NO_CLEAR;
	bool dirty = false;
	int i, count;

	/*
	 * 2.2.3.2 Host Dirty Support
	 * When a non-default page size is used , software must OR the
	 * Dirty bits in all of the replicated host PTEs used to map
	 * the page. The IOMMU does not guarantee the Dirty bits are
	 * set in all of the replicated PTEs. Any portion of the page
	 * may have been written even if the Dirty bit is set in only
	 * one of the replicated PTEs.
	 */
	count = PAGE_SIZE_PTE_COUNT(size);
	for (i = 0; i < count && test_only; i++) {
		if (test_bit(IOMMU_PTE_HD_BIT, (unsigned long *)&ptep[i])) {
			dirty = true;
			break;
		}
	}

	for (i = 0; i < count && !test_only; i++) {
		if (test_and_clear_bit(IOMMU_PTE_HD_BIT,
				       (unsigned long *)&ptep[i])) {
			dirty = true;
		}
	}

	return dirty;
}

static int iommu_v1_read_and_clear_dirty(struct io_pgtable_ops *ops,
					 unsigned long iova, size_t size,
					 unsigned long flags,
					 struct iommu_dirty_bitmap *dirty)
{
	struct amd_io_pgtable *pgtable = io_pgtable_ops_to_data(ops);
	unsigned long end = iova + size - 1;

	do {
		unsigned long pgsize = 0;
		u64 *ptep, pte;

		ptep = fetch_pte(pgtable, iova, &pgsize);
		if (ptep)
			pte = READ_ONCE(*ptep);
		if (!ptep || !IOMMU_PTE_PRESENT(pte)) {
			pgsize = pgsize ?: PTE_LEVEL_PAGE_SIZE(0);
			iova += pgsize;
			continue;
		}

		/*
		 * Mark the whole IOVA range as dirty even if only one of
		 * the replicated PTEs were marked dirty.
		 */
		if (pte_test_and_clear_dirty(ptep, pgsize, flags))
			iommu_dirty_bitmap_record(dirty, iova, pgsize);
		iova += pgsize;
	} while (iova < end);

	return 0;
}

/*
 * ----------------------------------------------------
 */
static void v1_free_pgtable(struct io_pgtable *iop)
{
	struct amd_io_pgtable *pgtable = container_of(iop, struct amd_io_pgtable, iop);
	struct protection_domain *dom;
	LIST_HEAD(freelist);

	if (pgtable->mode == PAGE_MODE_NONE)
		return;

	dom = container_of(pgtable, struct protection_domain, iop);

	/* Page-table is not visible to IOMMU anymore, so free it */
	BUG_ON(pgtable->mode < PAGE_MODE_NONE ||
	       pgtable->mode > PAGE_MODE_6_LEVEL);

	free_sub_pt(pgtable->root, pgtable->mode, &freelist);

	/* Update data structure */
	amd_iommu_domain_clr_pt_root(dom);

	/* Make changes visible to IOMMUs */
	amd_iommu_domain_update(dom);

	iommu_put_pages_list(&freelist);
}

static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
{
	struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg);

	cfg->pgsize_bitmap  = AMD_IOMMU_PGSIZES,
	cfg->ias            = IOMMU_IN_ADDR_BIT_SIZE,
	cfg->oas            = IOMMU_OUT_ADDR_BIT_SIZE,
	cfg->tlb            = &v1_flush_ops;

	pgtable->iop.ops.map_pages    = iommu_v1_map_pages;
	pgtable->iop.ops.unmap_pages  = iommu_v1_unmap_pages;
	pgtable->iop.ops.iova_to_phys = iommu_v1_iova_to_phys;
	pgtable->iop.ops.read_and_clear_dirty = iommu_v1_read_and_clear_dirty;

	return &pgtable->iop;
}

struct io_pgtable_init_fns io_pgtable_amd_iommu_v1_init_fns = {
	.alloc	= v1_alloc_pgtable,
	.free	= v1_free_pgtable,
};