summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/pat.c
blob: 82d097ce3091cdd25686ed4badf4484901587f4d (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
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
/*
 * Handle caching attributes in page tables (PAT)
 *
 * Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
 *          Suresh B Siddha <suresh.b.siddha@intel.com>
 *
 * Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen.
 */

#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/fs.h>

#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include <asm/fcntl.h>
#include <asm/e820.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/pat.h>
#include <asm/io.h>

#ifdef CONFIG_X86_PAT
int __read_mostly pat_enabled = 1;

static inline void pat_disable(const char *reason)
{
	pat_enabled = 0;
	printk(KERN_INFO "%s\n", reason);
}

static int __init nopat(char *str)
{
	pat_disable("PAT support disabled.");
	return 0;
}
early_param("nopat", nopat);
#else
static inline void pat_disable(const char *reason)
{
	(void)reason;
}
#endif


static int debug_enable;

static int __init pat_debug_setup(char *str)
{
	debug_enable = 1;
	return 0;
}
__setup("debugpat", pat_debug_setup);

#define dprintk(fmt, arg...) \
	do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)


static u64 __read_mostly boot_pat_state;

enum {
	PAT_UC = 0,		/* uncached */
	PAT_WC = 1,		/* Write combining */
	PAT_WT = 4,		/* Write Through */
	PAT_WP = 5,		/* Write Protected */
	PAT_WB = 6,		/* Write Back (default) */
	PAT_UC_MINUS = 7,	/* UC, but can be overriden by MTRR */
};

#define PAT(x, y)	((u64)PAT_ ## y << ((x)*8))

void pat_init(void)
{
	u64 pat;

	if (!pat_enabled)
		return;

	if (!cpu_has_pat) {
		if (!boot_pat_state) {
			pat_disable("PAT not supported by CPU.");
			return;
		} else {
			/*
			 * If this happens we are on a secondary CPU, but
			 * switched to PAT on the boot CPU. We have no way to
			 * undo PAT.
			 */
			printk(KERN_ERR "PAT enabled, "
			       "but not supported by secondary CPU\n");
			BUG();
		}
	}

	/* Set PWT to Write-Combining. All other bits stay the same */
	/*
	 * PTE encoding used in Linux:
	 *      PAT
	 *      |PCD
	 *      ||PWT
	 *      |||
	 *      000 WB		_PAGE_CACHE_WB
	 *      001 WC		_PAGE_CACHE_WC
	 *      010 UC-		_PAGE_CACHE_UC_MINUS
	 *      011 UC		_PAGE_CACHE_UC
	 * PAT bit unused
	 */
	pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
	      PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);

	/* Boot CPU check */
	if (!boot_pat_state)
		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);

	wrmsrl(MSR_IA32_CR_PAT, pat);
	printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
	       smp_processor_id(), boot_pat_state, pat);
}

#undef PAT

static char *cattr_name(unsigned long flags)
{
	switch (flags & _PAGE_CACHE_MASK) {
	case _PAGE_CACHE_UC:		return "uncached";
	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
	case _PAGE_CACHE_WB:		return "write-back";
	case _PAGE_CACHE_WC:		return "write-combining";
	default:			return "broken";
	}
}

/*
 * The global memtype list keeps track of memory type for specific
 * physical memory areas. Conflicting memory types in different
 * mappings can cause CPU cache corruption. To avoid this we keep track.
 *
 * The list is sorted based on starting address and can contain multiple
 * entries for each address (this allows reference counting for overlapping
 * areas). All the aliases have the same cache attributes of course.
 * Zero attributes are represented as holes.
 *
 * Currently the data structure is a list because the number of mappings
 * are expected to be relatively small. If this should be a problem
 * it could be changed to a rbtree or similar.
 *
 * memtype_lock protects the whole list.
 */

struct memtype {
	u64			start;
	u64			end;
	unsigned long		type;
	struct list_head	nd;
};

static LIST_HEAD(memtype_list);
static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype list */

/*
 * Does intersection of PAT memory type and MTRR memory type and returns
 * the resulting memory type as PAT understands it.
 * (Type in pat and mtrr will not have same value)
 * The intersection is based on "Effective Memory Type" tables in IA-32
 * SDM vol 3a
 */
static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
{
	/*
	 * Look for MTRR hint to get the effective type in case where PAT
	 * request is for WB.
	 */
	if (req_type == _PAGE_CACHE_WB) {
		u8 mtrr_type;

		mtrr_type = mtrr_type_lookup(start, end);
		if (mtrr_type != MTRR_TYPE_WRBACK)
			return _PAGE_CACHE_UC_MINUS;

		return _PAGE_CACHE_WB;
	}

	return req_type;
}

static int
chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
{
	if (new->type != entry->type) {
		if (type) {
			new->type = entry->type;
			*type = entry->type;
		} else
			goto conflict;
	}

	 /* check overlaps with more than one entry in the list */
	list_for_each_entry_continue(entry, &memtype_list, nd) {
		if (new->end <= entry->start)
			break;
		else if (new->type != entry->type)
			goto conflict;
	}
	return 0;

 conflict:
	printk(KERN_INFO "%s:%d conflicting memory types "
	       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start,
	       new->end, cattr_name(new->type), cattr_name(entry->type));
	return -EBUSY;
}

static struct memtype *cached_entry;
static u64 cached_start;

static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
{
	int ram_page = 0, not_rampage = 0;
	unsigned long page_nr;

	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
	     ++page_nr) {
		/*
		 * For legacy reasons, physical address range in the legacy ISA
		 * region is tracked as non-RAM. This will allow users of
		 * /dev/mem to map portions of legacy ISA region, even when
		 * some of those portions are listed(or not even listed) with
		 * different e820 types(RAM/reserved/..)
		 */
		if (page_nr >= (ISA_END_ADDRESS >> PAGE_SHIFT) &&
		    page_is_ram(page_nr))
			ram_page = 1;
		else
			not_rampage = 1;

		if (ram_page == not_rampage)
			return -1;
	}

	return ram_page;
}

/*
 * For RAM pages, mark the pages as non WB memory type using
 * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
 * set_memory_wc() on a RAM page at a time before marking it as WB again.
 * This is ok, because only one driver will be owning the page and
 * doing set_memory_*() calls.
 *
 * For now, we use PageNonWB to track that the RAM page is being mapped
 * as non WB. In future, we will have to use one more flag
 * (or some other mechanism in page_struct) to distinguish between
 * UC and WC mapping.
 */
static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
				  unsigned long *new_type)
{
	struct page *page;
	u64 pfn, end_pfn;

	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
		page = pfn_to_page(pfn);
		if (page_mapped(page) || PageNonWB(page))
			goto out;

		SetPageNonWB(page);
	}
	return 0;

out:
	end_pfn = pfn;
	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
		page = pfn_to_page(pfn);
		ClearPageNonWB(page);
	}

	return -EINVAL;
}

static int free_ram_pages_type(u64 start, u64 end)
{
	struct page *page;
	u64 pfn, end_pfn;

	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
		page = pfn_to_page(pfn);
		if (page_mapped(page) || !PageNonWB(page))
			goto out;

		ClearPageNonWB(page);
	}
	return 0;

out:
	end_pfn = pfn;
	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
		page = pfn_to_page(pfn);
		SetPageNonWB(page);
	}
	return -EINVAL;
}

/*
 * req_type typically has one of the:
 * - _PAGE_CACHE_WB
 * - _PAGE_CACHE_WC
 * - _PAGE_CACHE_UC_MINUS
 * - _PAGE_CACHE_UC
 *
 * req_type will have a special case value '-1', when requester want to inherit
 * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS.
 *
 * If new_type is NULL, function will return an error if it cannot reserve the
 * region with req_type. If new_type is non-NULL, function will return
 * available type in new_type in case of no error. In case of any error
 * it will return a negative return value.
 */
int reserve_memtype(u64 start, u64 end, unsigned long req_type,
		    unsigned long *new_type)
{
	struct memtype *new, *entry;
	unsigned long actual_type;
	struct list_head *where;
	int is_range_ram;
	int err = 0;

	BUG_ON(start >= end); /* end is exclusive */

	if (!pat_enabled) {
		/* This is identical to page table setting without PAT */
		if (new_type) {
			if (req_type == -1)
				*new_type = _PAGE_CACHE_WB;
			else if (req_type == _PAGE_CACHE_WC)
				*new_type = _PAGE_CACHE_UC_MINUS;
			else
				*new_type = req_type & _PAGE_CACHE_MASK;
		}
		return 0;
	}

	/* Low ISA region is always mapped WB in page table. No need to track */
	if (is_ISA_range(start, end - 1)) {
		if (new_type)
			*new_type = _PAGE_CACHE_WB;
		return 0;
	}

	/*
	 * Call mtrr_lookup to get the type hint. This is an
	 * optimization for /dev/mem mmap'ers into WB memory (BIOS
	 * tools and ACPI tools). Use WB request for WB memory and use
	 * UC_MINUS otherwise.
	 */
	actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);

	if (new_type)
		*new_type = actual_type;

	is_range_ram = pat_pagerange_is_ram(start, end);
	if (is_range_ram == 1)
		return reserve_ram_pages_type(start, end, req_type,
					      new_type);
	else if (is_range_ram < 0)
		return -EINVAL;

	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
	if (!new)
		return -ENOMEM;

	new->start	= start;
	new->end	= end;
	new->type	= actual_type;

	spin_lock(&memtype_lock);

	if (cached_entry && start >= cached_start)
		entry = cached_entry;
	else
		entry = list_entry(&memtype_list, struct memtype, nd);

	/* Search for existing mapping that overlaps the current range */
	where = NULL;
	list_for_each_entry_continue(entry, &memtype_list, nd) {
		if (end <= entry->start) {
			where = entry->nd.prev;
			cached_entry = list_entry(where, struct memtype, nd);
			break;
		} else if (start <= entry->start) { /* end > entry->start */
			err = chk_conflict(new, entry, new_type);
			if (!err) {
				dprintk("Overlap at 0x%Lx-0x%Lx\n",
					entry->start, entry->end);
				where = entry->nd.prev;
				cached_entry = list_entry(where,
							struct memtype, nd);
			}
			break;
		} else if (start < entry->end) { /* start > entry->start */
			err = chk_conflict(new, entry, new_type);
			if (!err) {
				dprintk("Overlap at 0x%Lx-0x%Lx\n",
					entry->start, entry->end);
				cached_entry = list_entry(entry->nd.prev,
							struct memtype, nd);

				/*
				 * Move to right position in the linked
				 * list to add this new entry
				 */
				list_for_each_entry_continue(entry,
							&memtype_list, nd) {
					if (start <= entry->start) {
						where = entry->nd.prev;
						break;
					}
				}
			}
			break;
		}
	}

	if (err) {
		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
		       "track %s, req %s\n",
		       start, end, cattr_name(new->type), cattr_name(req_type));
		kfree(new);
		spin_unlock(&memtype_lock);

		return err;
	}

	cached_start = start;

	if (where)
		list_add(&new->nd, where);
	else
		list_add_tail(&new->nd, &memtype_list);

	spin_unlock(&memtype_lock);

	dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
		start, end, cattr_name(new->type), cattr_name(req_type),
		new_type ? cattr_name(*new_type) : "-");

	return err;
}

int free_memtype(u64 start, u64 end)
{
	struct memtype *entry;
	int err = -EINVAL;
	int is_range_ram;

	if (!pat_enabled)
		return 0;

	/* Low ISA region is always mapped WB. No need to track */
	if (is_ISA_range(start, end - 1))
		return 0;

	is_range_ram = pat_pagerange_is_ram(start, end);
	if (is_range_ram == 1)
		return free_ram_pages_type(start, end);
	else if (is_range_ram < 0)
		return -EINVAL;

	spin_lock(&memtype_lock);
	list_for_each_entry(entry, &memtype_list, nd) {
		if (entry->start == start && entry->end == end) {
			if (cached_entry == entry || cached_start == start)
				cached_entry = NULL;

			list_del(&entry->nd);
			kfree(entry);
			err = 0;
			break;
		}
	}
	spin_unlock(&memtype_lock);

	if (err) {
		printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
			current->comm, current->pid, start, end);
	}

	dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);

	return err;
}


/**
 * io_reserve_memtype - Request a memory type mapping for a region of memory
 * @start: start (physical address) of the region
 * @end: end (physical address) of the region
 * @type: A pointer to memtype, with requested type. On success, requested
 * or any other compatible type that was available for the region is returned
 *
 * On success, returns 0
 * On failure, returns non-zero
 */
int io_reserve_memtype(resource_size_t start, resource_size_t end,
			unsigned long *type)
{
	unsigned long req_type = *type;
	unsigned long new_type;
	int ret;

	WARN_ON_ONCE(iomem_map_sanity_check(start, end - start));

	ret = reserve_memtype(start, end, req_type, &new_type);
	if (ret)
		goto out_err;

	if (!is_new_memtype_allowed(req_type, new_type))
		goto out_free;

	if (kernel_map_sync_memtype(start, end - start, new_type) < 0)
		goto out_free;

	*type = new_type;
	return 0;

out_free:
	free_memtype(start, end);
	ret = -EBUSY;
out_err:
	return ret;
}

/**
 * io_free_memtype - Release a memory type mapping for a region of memory
 * @start: start (physical address) of the region
 * @end: end (physical address) of the region
 */
void io_free_memtype(resource_size_t start, resource_size_t end)
{
	free_memtype(start, end);
}

pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
				unsigned long size, pgprot_t vma_prot)
{
	return vma_prot;
}

#ifdef CONFIG_STRICT_DEVMEM
/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM*/
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	return 1;
}
#else
/* This check is needed to avoid cache aliasing when PAT is enabled */
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	u64 from = ((u64)pfn) << PAGE_SHIFT;
	u64 to = from + size;
	u64 cursor = from;

	if (!pat_enabled)
		return 1;

	while (cursor < to) {
		if (!devmem_is_allowed(pfn)) {
			printk(KERN_INFO
		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
				current->comm, from, to);
			return 0;
		}
		cursor += PAGE_SIZE;
		pfn++;
	}
	return 1;
}
#endif /* CONFIG_STRICT_DEVMEM */

int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
				unsigned long size, pgprot_t *vma_prot)
{
	unsigned long flags = _PAGE_CACHE_WB;

	if (!range_is_allowed(pfn, size))
		return 0;

	if (file->f_flags & O_SYNC) {
		flags = _PAGE_CACHE_UC_MINUS;
	}

#ifdef CONFIG_X86_32
	/*
	 * On the PPro and successors, the MTRRs are used to set
	 * memory types for physical addresses outside main memory,
	 * so blindly setting UC or PWT on those pages is wrong.
	 * For Pentiums and earlier, the surround logic should disable
	 * caching for the high addresses through the KEN pin, but
	 * we maintain the tradition of paranoia in this code.
	 */
	if (!pat_enabled &&
	    !(boot_cpu_has(X86_FEATURE_MTRR) ||
	      boot_cpu_has(X86_FEATURE_K6_MTRR) ||
	      boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
	      boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
	    (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
		flags = _PAGE_CACHE_UC;
	}
#endif

	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
			     flags);
	return 1;
}

/*
 * Change the memory type for the physial address range in kernel identity
 * mapping space if that range is a part of identity map.
 */
int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
{
	unsigned long id_sz;

	if (base >= __pa(high_memory))
		return 0;

	id_sz = (__pa(high_memory) < base + size) ?
				__pa(high_memory) - base :
				size;

	if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
		printk(KERN_INFO
			"%s:%d ioremap_change_attr failed %s "
			"for %Lx-%Lx\n",
			current->comm, current->pid,
			cattr_name(flags),
			base, (unsigned long long)(base + size));
		return -EINVAL;
	}
	return 0;
}

/*
 * Internal interface to reserve a range of physical memory with prot.
 * Reserved non RAM regions only and after successful reserve_memtype,
 * this func also keeps identity mapping (if any) in sync with this new prot.
 */
static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
				int strict_prot)
{
	int is_ram = 0;
	int ret;
	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
	unsigned long flags = want_flags;

	is_ram = pat_pagerange_is_ram(paddr, paddr + size);

	/*
	 * reserve_pfn_range() doesn't support RAM pages. Maintain the current
	 * behavior with RAM pages by returning success.
	 */
	if (is_ram != 0)
		return 0;

	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
	if (ret)
		return ret;

	if (flags != want_flags) {
		if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) {
			free_memtype(paddr, paddr + size);
			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
				" for %Lx-%Lx, got %s\n",
				current->comm, current->pid,
				cattr_name(want_flags),
				(unsigned long long)paddr,
				(unsigned long long)(paddr + size),
				cattr_name(flags));
			return -EINVAL;
		}
		/*
		 * We allow returning different type than the one requested in
		 * non strict case.
		 */
		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
				      (~_PAGE_CACHE_MASK)) |
				     flags);
	}

	if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
		free_memtype(paddr, paddr + size);
		return -EINVAL;
	}
	return 0;
}

/*
 * Internal interface to free a range of physical memory.
 * Frees non RAM regions only.
 */
static void free_pfn_range(u64 paddr, unsigned long size)
{
	int is_ram;

	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
	if (is_ram == 0)
		free_memtype(paddr, paddr + size);
}

/*
 * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
 * copied through copy_page_range().
 *
 * If the vma has a linear pfn mapping for the entire range, we get the prot
 * from pte and reserve the entire vma range with single reserve_pfn_range call.
 */
int track_pfn_vma_copy(struct vm_area_struct *vma)
{
	resource_size_t paddr;
	unsigned long prot;
	unsigned long vma_size = vma->vm_end - vma->vm_start;
	pgprot_t pgprot;

	/*
	 * For now, only handle remap_pfn_range() vmas where
	 * is_linear_pfn_mapping() == TRUE. Handling of
	 * vm_insert_pfn() is TBD.
	 */
	if (is_linear_pfn_mapping(vma)) {
		/*
		 * reserve the whole chunk covered by vma. We need the
		 * starting address and protection from pte.
		 */
		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
			WARN_ON_ONCE(1);
			return -EINVAL;
		}
		pgprot = __pgprot(prot);
		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
	}

	return 0;
}

/*
 * track_pfn_vma_new is called when a _new_ pfn mapping is being established
 * for physical range indicated by pfn and size.
 *
 * prot is passed in as a parameter for the new mapping. If the vma has a
 * linear pfn mapping for the entire range reserve the entire vma range with
 * single reserve_pfn_range call.
 */
int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
			unsigned long pfn, unsigned long size)
{
	resource_size_t paddr;
	unsigned long vma_size = vma->vm_end - vma->vm_start;

	/*
	 * For now, only handle remap_pfn_range() vmas where
	 * is_linear_pfn_mapping() == TRUE. Handling of
	 * vm_insert_pfn() is TBD.
	 */
	if (is_linear_pfn_mapping(vma)) {
		/* reserve the whole chunk starting from vm_pgoff */
		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
		return reserve_pfn_range(paddr, vma_size, prot, 0);
	}

	return 0;
}

/*
 * untrack_pfn_vma is called while unmapping a pfnmap for a region.
 * untrack can be called for a specific region indicated by pfn and size or
 * can be for the entire vma (in which case size can be zero).
 */
void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
			unsigned long size)
{
	resource_size_t paddr;
	unsigned long vma_size = vma->vm_end - vma->vm_start;

	/*
	 * For now, only handle remap_pfn_range() vmas where
	 * is_linear_pfn_mapping() == TRUE. Handling of
	 * vm_insert_pfn() is TBD.
	 */
	if (is_linear_pfn_mapping(vma)) {
		/* free the whole chunk starting from vm_pgoff */
		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
		free_pfn_range(paddr, vma_size);
		return;
	}
}

pgprot_t pgprot_writecombine(pgprot_t prot)
{
	if (pat_enabled)
		return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
	else
		return pgprot_noncached(prot);
}
EXPORT_SYMBOL_GPL(pgprot_writecombine);

#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)

/* get Nth element of the linked list */
static struct memtype *memtype_get_idx(loff_t pos)
{
	struct memtype *list_node, *print_entry;
	int i = 1;

	print_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
	if (!print_entry)
		return NULL;

	spin_lock(&memtype_lock);
	list_for_each_entry(list_node, &memtype_list, nd) {
		if (pos == i) {
			*print_entry = *list_node;
			spin_unlock(&memtype_lock);
			return print_entry;
		}
		++i;
	}
	spin_unlock(&memtype_lock);
	kfree(print_entry);

	return NULL;
}

static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
{
	if (*pos == 0) {
		++*pos;
		seq_printf(seq, "PAT memtype list:\n");
	}

	return memtype_get_idx(*pos);
}

static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return memtype_get_idx(*pos);
}

static void memtype_seq_stop(struct seq_file *seq, void *v)
{
}

static int memtype_seq_show(struct seq_file *seq, void *v)
{
	struct memtype *print_entry = (struct memtype *)v;

	seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type),
			print_entry->start, print_entry->end);
	kfree(print_entry);

	return 0;
}

static struct seq_operations memtype_seq_ops = {
	.start = memtype_seq_start,
	.next  = memtype_seq_next,
	.stop  = memtype_seq_stop,
	.show  = memtype_seq_show,
};

static int memtype_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &memtype_seq_ops);
}

static const struct file_operations memtype_fops = {
	.open    = memtype_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release,
};

static int __init pat_memtype_list_init(void)
{
	debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir,
				NULL, &memtype_fops);
	return 0;
}

late_initcall(pat_memtype_list_init);

#endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */