aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/ioremap.c
blob: adc77904fc3ed32ab66ba27f1b8a07d9123f7cb6 (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
/*
 * Re-map IO memory to kernel address space so that we can access it.
 * This is needed for high PCI addresses that aren't mapped in the
 * 640k-1MB IO memory area on PC's
 *
 * (C) Copyright 1995 1996 Linus Torvalds
 */

#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/io.h>
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mmiotrace.h>
#include <linux/mem_encrypt.h>
#include <linux/efi.h>

#include <asm/set_memory.h>
#include <asm/e820/api.h>
#include <asm/fixmap.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/pat.h>
#include <asm/setup.h>

#include "physaddr.h"

struct ioremap_mem_flags {
	bool system_ram;
	bool desc_other;
};

/*
 * Fix up the linear direct mapping of the kernel to avoid cache attribute
 * conflicts.
 */
int ioremap_change_attr(unsigned long vaddr, unsigned long size,
			enum page_cache_mode pcm)
{
	unsigned long nrpages = size >> PAGE_SHIFT;
	int err;

	switch (pcm) {
	case _PAGE_CACHE_MODE_UC:
	default:
		err = _set_memory_uc(vaddr, nrpages);
		break;
	case _PAGE_CACHE_MODE_WC:
		err = _set_memory_wc(vaddr, nrpages);
		break;
	case _PAGE_CACHE_MODE_WT:
		err = _set_memory_wt(vaddr, nrpages);
		break;
	case _PAGE_CACHE_MODE_WB:
		err = _set_memory_wb(vaddr, nrpages);
		break;
	}

	return err;
}

static bool __ioremap_check_ram(struct resource *res)
{
	unsigned long start_pfn, stop_pfn;
	unsigned long i;

	if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
		return false;

	start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
	stop_pfn = (res->end + 1) >> PAGE_SHIFT;
	if (stop_pfn > start_pfn) {
		for (i = 0; i < (stop_pfn - start_pfn); ++i)
			if (pfn_valid(start_pfn + i) &&
			    !PageReserved(pfn_to_page(start_pfn + i)))
				return true;
	}

	return false;
}

static int __ioremap_check_desc_other(struct resource *res)
{
	return (res->desc != IORES_DESC_NONE);
}

static int __ioremap_res_check(struct resource *res, void *arg)
{
	struct ioremap_mem_flags *flags = arg;

	if (!flags->system_ram)
		flags->system_ram = __ioremap_check_ram(res);

	if (!flags->desc_other)
		flags->desc_other = __ioremap_check_desc_other(res);

	return flags->system_ram && flags->desc_other;
}

/*
 * To avoid multiple resource walks, this function walks resources marked as
 * IORESOURCE_MEM and IORESOURCE_BUSY and looking for system RAM and/or a
 * resource described not as IORES_DESC_NONE (e.g. IORES_DESC_ACPI_TABLES).
 */
static void __ioremap_check_mem(resource_size_t addr, unsigned long size,
				struct ioremap_mem_flags *flags)
{
	u64 start, end;

	start = (u64)addr;
	end = start + size - 1;
	memset(flags, 0, sizeof(*flags));

	walk_mem_res(start, end, flags, __ioremap_res_check);
}

/*
 * Remap an arbitrary physical address space into the kernel virtual
 * address space. It transparently creates kernel huge I/O mapping when
 * the physical address is aligned by a huge page size (1GB or 2MB) and
 * the requested size is at least the huge page size.
 *
 * NOTE: MTRRs can override PAT memory types with a 4KB granularity.
 * Therefore, the mapping code falls back to use a smaller page toward 4KB
 * when a mapping range is covered by non-WB type of MTRRs.
 *
 * NOTE! We need to allow non-page-aligned mappings too: we will obviously
 * have to convert them into an offset in a page-aligned mapping, but the
 * caller shouldn't need to know that small detail.
 */
static void __iomem *__ioremap_caller(resource_size_t phys_addr,
		unsigned long size, enum page_cache_mode pcm, void *caller)
{
	unsigned long offset, vaddr;
	resource_size_t last_addr;
	const resource_size_t unaligned_phys_addr = phys_addr;
	const unsigned long unaligned_size = size;
	struct ioremap_mem_flags mem_flags;
	struct vm_struct *area;
	enum page_cache_mode new_pcm;
	pgprot_t prot;
	int retval;
	void __iomem *ret_addr;

	/* Don't allow wraparound or zero size */
	last_addr = phys_addr + size - 1;
	if (!size || last_addr < phys_addr)
		return NULL;

	if (!phys_addr_valid(phys_addr)) {
		printk(KERN_WARNING "ioremap: invalid physical address %llx\n",
		       (unsigned long long)phys_addr);
		WARN_ON_ONCE(1);
		return NULL;
	}

	__ioremap_check_mem(phys_addr, size, &mem_flags);

	/*
	 * Don't allow anybody to remap normal RAM that we're using..
	 */
	if (mem_flags.system_ram) {
		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
			  &phys_addr, &last_addr);
		return NULL;
	}

	/*
	 * Mappings have to be page-aligned
	 */
	offset = phys_addr & ~PAGE_MASK;
	phys_addr &= PHYSICAL_PAGE_MASK;
	size = PAGE_ALIGN(last_addr+1) - phys_addr;

	retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
						pcm, &new_pcm);
	if (retval) {
		printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
		return NULL;
	}

	if (pcm != new_pcm) {
		if (!is_new_memtype_allowed(phys_addr, size, pcm, new_pcm)) {
			printk(KERN_ERR
		"ioremap error for 0x%llx-0x%llx, requested 0x%x, got 0x%x\n",
				(unsigned long long)phys_addr,
				(unsigned long long)(phys_addr + size),
				pcm, new_pcm);
			goto err_free_memtype;
		}
		pcm = new_pcm;
	}

	/*
	 * If the page being mapped is in memory and SEV is active then
	 * make sure the memory encryption attribute is enabled in the
	 * resulting mapping.
	 */
	prot = PAGE_KERNEL_IO;
	if (sev_active() && mem_flags.desc_other)
		prot = pgprot_encrypted(prot);

	switch (pcm) {
	case _PAGE_CACHE_MODE_UC:
	default:
		prot = __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_UC));
		break;
	case _PAGE_CACHE_MODE_UC_MINUS:
		prot = __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
		break;
	case _PAGE_CACHE_MODE_WC:
		prot = __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_WC));
		break;
	case _PAGE_CACHE_MODE_WT:
		prot = __pgprot(pgprot_val(prot) |
				cachemode2protval(_PAGE_CACHE_MODE_WT));
		break;
	case _PAGE_CACHE_MODE_WB:
		break;
	}

	/*
	 * Ok, go for it..
	 */
	area = get_vm_area_caller(size, VM_IOREMAP, caller);
	if (!area)
		goto err_free_memtype;
	area->phys_addr = phys_addr;
	vaddr = (unsigned long) area->addr;

	if (kernel_map_sync_memtype(phys_addr, size, pcm))
		goto err_free_area;

	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
		goto err_free_area;

	ret_addr = (void __iomem *) (vaddr + offset);
	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);

	/*
	 * Check if the request spans more than any BAR in the iomem resource
	 * tree.
	 */
	if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size))
		pr_warn("caller %pS mapping multiple BARs\n", caller);

	return ret_addr;
err_free_area:
	free_vm_area(area);
err_free_memtype:
	free_memtype(phys_addr, phys_addr + size);
	return NULL;
}

/**
 * ioremap_nocache     -   map bus memory into CPU space
 * @phys_addr:    bus address of the memory
 * @size:      size of the resource to map
 *
 * ioremap_nocache performs a platform specific sequence of operations to
 * make bus memory CPU accessible via the readb/readw/readl/writeb/
 * writew/writel functions and the other mmio helpers. The returned
 * address is not guaranteed to be usable directly as a virtual
 * address.
 *
 * This version of ioremap ensures that the memory is marked uncachable
 * on the CPU as well as honouring existing caching rules from things like
 * the PCI bus. Note that there are other caches and buffers on many
 * busses. In particular driver authors should read up on PCI writes
 *
 * It's useful if some control registers are in such an area and
 * write combining or read caching is not desirable:
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
{
	/*
	 * Ideally, this should be:
	 *	pat_enabled() ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
	 *
	 * Till we fix all X drivers to use ioremap_wc(), we will use
	 * UC MINUS. Drivers that are certain they need or can already
	 * be converted over to strong UC can use ioremap_uc().
	 */
	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;

	return __ioremap_caller(phys_addr, size, pcm,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_nocache);

/**
 * ioremap_uc     -   map bus memory into CPU space as strongly uncachable
 * @phys_addr:    bus address of the memory
 * @size:      size of the resource to map
 *
 * ioremap_uc performs a platform specific sequence of operations to
 * make bus memory CPU accessible via the readb/readw/readl/writeb/
 * writew/writel functions and the other mmio helpers. The returned
 * address is not guaranteed to be usable directly as a virtual
 * address.
 *
 * This version of ioremap ensures that the memory is marked with a strong
 * preference as completely uncachable on the CPU when possible. For non-PAT
 * systems this ends up setting page-attribute flags PCD=1, PWT=1. For PAT
 * systems this will set the PAT entry for the pages as strong UC.  This call
 * will honor existing caching rules from things like the PCI bus. Note that
 * there are other caches and buffers on many busses. In particular driver
 * authors should read up on PCI writes.
 *
 * It's useful if some control registers are in such an area and
 * write combining or read caching is not desirable:
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_uc(resource_size_t phys_addr, unsigned long size)
{
	enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC;

	return __ioremap_caller(phys_addr, size, pcm,
				__builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(ioremap_uc);

/**
 * ioremap_wc	-	map memory into CPU space write combined
 * @phys_addr:	bus address of the memory
 * @size:	size of the resource to map
 *
 * This version of ioremap ensures that the memory is marked write combining.
 * Write combining allows faster writes to some hardware devices.
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
					__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_wc);

/**
 * ioremap_wt	-	map memory into CPU space write through
 * @phys_addr:	bus address of the memory
 * @size:	size of the resource to map
 *
 * This version of ioremap ensures that the memory is marked write through.
 * Write through stores data into memory while keeping the cache up-to-date.
 *
 * Must be freed with iounmap.
 */
void __iomem *ioremap_wt(resource_size_t phys_addr, unsigned long size)
{
	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WT,
					__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_wt);

void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
	return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_cache);

void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
				unsigned long prot_val)
{
	return __ioremap_caller(phys_addr, size,
				pgprot2cachemode(__pgprot(prot_val)),
				__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_prot);

/**
 * iounmap - Free a IO remapping
 * @addr: virtual address from ioremap_*
 *
 * Caller must ensure there is only one unmapping for the same pointer.
 */
void iounmap(volatile void __iomem *addr)
{
	struct vm_struct *p, *o;

	if ((void __force *)addr <= high_memory)
		return;

	/*
	 * The PCI/ISA range special-casing was removed from __ioremap()
	 * so this check, in theory, can be removed. However, there are
	 * cases where iounmap() is called for addresses not obtained via
	 * ioremap() (vga16fb for example). Add a warning so that these
	 * cases can be caught and fixed.
	 */
	if ((void __force *)addr >= phys_to_virt(ISA_START_ADDRESS) &&
	    (void __force *)addr < phys_to_virt(ISA_END_ADDRESS)) {
		WARN(1, "iounmap() called for ISA range not obtained using ioremap()\n");
		return;
	}

	mmiotrace_iounmap(addr);

	addr = (volatile void __iomem *)
		(PAGE_MASK & (unsigned long __force)addr);

	/* Use the vm area unlocked, assuming the caller
	   ensures there isn't another iounmap for the same address
	   in parallel. Reuse of the virtual address is prevented by
	   leaving it in the global lists until we're done with it.
	   cpa takes care of the direct mappings. */
	p = find_vm_area((void __force *)addr);

	if (!p) {
		printk(KERN_ERR "iounmap: bad address %p\n", addr);
		dump_stack();
		return;
	}

	free_memtype(p->phys_addr, p->phys_addr + get_vm_area_size(p));

	/* Finally remove it */
	o = remove_vm_area((void __force *)addr);
	BUG_ON(p != o || o == NULL);
	kfree(p);
}
EXPORT_SYMBOL(iounmap);

int __init arch_ioremap_pud_supported(void)
{
#ifdef CONFIG_X86_64
	return boot_cpu_has(X86_FEATURE_GBPAGES);
#else
	return 0;
#endif
}

int __init arch_ioremap_pmd_supported(void)
{
	return boot_cpu_has(X86_FEATURE_PSE);
}

/*
 * Convert a physical pointer to a virtual kernel pointer for /dev/mem
 * access
 */
void *xlate_dev_mem_ptr(phys_addr_t phys)
{
	unsigned long start  = phys &  PAGE_MASK;
	unsigned long offset = phys & ~PAGE_MASK;
	void *vaddr;

	/* memremap() maps if RAM, otherwise falls back to ioremap() */
	vaddr = memremap(start, PAGE_SIZE, MEMREMAP_WB);

	/* Only add the offset on success and return NULL if memremap() failed */
	if (vaddr)
		vaddr += offset;

	return vaddr;
}

void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
{
	memunmap((void *)((unsigned long)addr & PAGE_MASK));
}

/*
 * Examine the physical address to determine if it is an area of memory
 * that should be mapped decrypted.  If the memory is not part of the
 * kernel usable area it was accessed and created decrypted, so these
 * areas should be mapped decrypted. And since the encryption key can
 * change across reboots, persistent memory should also be mapped
 * decrypted.
 *
 * If SEV is active, that implies that BIOS/UEFI also ran encrypted so
 * only persistent memory should be mapped decrypted.
 */
static bool memremap_should_map_decrypted(resource_size_t phys_addr,
					  unsigned long size)
{
	int is_pmem;

	/*
	 * Check if the address is part of a persistent memory region.
	 * This check covers areas added by E820, EFI and ACPI.
	 */
	is_pmem = region_intersects(phys_addr, size, IORESOURCE_MEM,
				    IORES_DESC_PERSISTENT_MEMORY);
	if (is_pmem != REGION_DISJOINT)
		return true;

	/*
	 * Check if the non-volatile attribute is set for an EFI
	 * reserved area.
	 */
	if (efi_enabled(EFI_BOOT)) {
		switch (efi_mem_type(phys_addr)) {
		case EFI_RESERVED_TYPE:
			if (efi_mem_attributes(phys_addr) & EFI_MEMORY_NV)
				return true;
			break;
		default:
			break;
		}
	}

	/* Check if the address is outside kernel usable area */
	switch (e820__get_entry_type(phys_addr, phys_addr + size - 1)) {
	case E820_TYPE_RESERVED:
	case E820_TYPE_ACPI:
	case E820_TYPE_NVS:
	case E820_TYPE_UNUSABLE:
		/* For SEV, these areas are encrypted */
		if (sev_active())
			break;
		/* Fallthrough */

	case E820_TYPE_PRAM:
		return true;
	default:
		break;
	}

	return false;
}

/*
 * Examine the physical address to determine if it is EFI data. Check
 * it against the boot params structure and EFI tables and memory types.
 */
static bool memremap_is_efi_data(resource_size_t phys_addr,
				 unsigned long size)
{
	u64 paddr;

	/* Check if the address is part of EFI boot/runtime data */
	if (!efi_enabled(EFI_BOOT))
		return false;

	paddr = boot_params.efi_info.efi_memmap_hi;
	paddr <<= 32;
	paddr |= boot_params.efi_info.efi_memmap;
	if (phys_addr == paddr)
		return true;

	paddr = boot_params.efi_info.efi_systab_hi;
	paddr <<= 32;
	paddr |= boot_params.efi_info.efi_systab;
	if (phys_addr == paddr)
		return true;

	if (efi_is_table_address(phys_addr))
		return true;

	switch (efi_mem_type(phys_addr)) {
	case EFI_BOOT_SERVICES_DATA:
	case EFI_RUNTIME_SERVICES_DATA:
		return true;
	default:
		break;
	}

	return false;
}

/*
 * Examine the physical address to determine if it is boot data by checking
 * it against the boot params setup_data chain.
 */
static bool memremap_is_setup_data(resource_size_t phys_addr,
				   unsigned long size)
{
	struct setup_data *data;
	u64 paddr, paddr_next;

	paddr = boot_params.hdr.setup_data;
	while (paddr) {
		unsigned int len;

		if (phys_addr == paddr)
			return true;

		data = memremap(paddr, sizeof(*data),
				MEMREMAP_WB | MEMREMAP_DEC);

		paddr_next = data->next;
		len = data->len;

		memunmap(data);

		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
			return true;

		paddr = paddr_next;
	}

	return false;
}

/*
 * Examine the physical address to determine if it is boot data by checking
 * it against the boot params setup_data chain (early boot version).
 */
static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
						unsigned long size)
{
	struct setup_data *data;
	u64 paddr, paddr_next;

	paddr = boot_params.hdr.setup_data;
	while (paddr) {
		unsigned int len;

		if (phys_addr == paddr)
			return true;

		data = early_memremap_decrypted(paddr, sizeof(*data));

		paddr_next = data->next;
		len = data->len;

		early_memunmap(data, sizeof(*data));

		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
			return true;

		paddr = paddr_next;
	}

	return false;
}

/*
 * Architecture function to determine if RAM remap is allowed. By default, a
 * RAM remap will map the data as encrypted. Determine if a RAM remap should
 * not be done so that the data will be mapped decrypted.
 */
bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
				 unsigned long flags)
{
	if (!mem_encrypt_active())
		return true;

	if (flags & MEMREMAP_ENC)
		return true;

	if (flags & MEMREMAP_DEC)
		return false;

	if (sme_active()) {
		if (memremap_is_setup_data(phys_addr, size) ||
		    memremap_is_efi_data(phys_addr, size))
			return false;
	}

	return !memremap_should_map_decrypted(phys_addr, size);
}

/*
 * Architecture override of __weak function to adjust the protection attributes
 * used when remapping memory. By default, early_memremap() will map the data
 * as encrypted. Determine if an encrypted mapping should not be done and set
 * the appropriate protection attributes.
 */
pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
					     unsigned long size,
					     pgprot_t prot)
{
	bool encrypted_prot;

	if (!mem_encrypt_active())
		return prot;

	encrypted_prot = true;

	if (sme_active()) {
		if (early_memremap_is_setup_data(phys_addr, size) ||
		    memremap_is_efi_data(phys_addr, size))
			encrypted_prot = false;
	}

	if (encrypted_prot && memremap_should_map_decrypted(phys_addr, size))
		encrypted_prot = false;

	return encrypted_prot ? pgprot_encrypted(prot)
			      : pgprot_decrypted(prot);
}

bool phys_mem_access_encrypted(unsigned long phys_addr, unsigned long size)
{
	return arch_memremap_can_ram_remap(phys_addr, size, 0);
}

#ifdef CONFIG_AMD_MEM_ENCRYPT
/* Remap memory with encryption */
void __init *early_memremap_encrypted(resource_size_t phys_addr,
				      unsigned long size)
{
	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC);
}

/*
 * Remap memory with encryption and write-protected - cannot be called
 * before pat_init() is called
 */
void __init *early_memremap_encrypted_wp(resource_size_t phys_addr,
					 unsigned long size)
{
	/* Be sure the write-protect PAT entry is set for write-protect */
	if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP)
		return NULL;

	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_ENC_WP);
}

/* Remap memory without encryption */
void __init *early_memremap_decrypted(resource_size_t phys_addr,
				      unsigned long size)
{
	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC);
}

/*
 * Remap memory without encryption and write-protected - cannot be called
 * before pat_init() is called
 */
void __init *early_memremap_decrypted_wp(resource_size_t phys_addr,
					 unsigned long size)
{
	/* Be sure the write-protect PAT entry is set for write-protect */
	if (__pte2cachemode_tbl[_PAGE_CACHE_MODE_WP] != _PAGE_CACHE_MODE_WP)
		return NULL;

	return early_memremap_prot(phys_addr, size, __PAGE_KERNEL_NOENC_WP);
}
#endif	/* CONFIG_AMD_MEM_ENCRYPT */

static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss;

static inline pmd_t * __init early_ioremap_pmd(unsigned long addr)
{
	/* Don't assume we're using swapper_pg_dir at this point */
	pgd_t *base = __va(read_cr3_pa());
	pgd_t *pgd = &base[pgd_index(addr)];
	p4d_t *p4d = p4d_offset(pgd, addr);
	pud_t *pud = pud_offset(p4d, addr);
	pmd_t *pmd = pmd_offset(pud, addr);

	return pmd;
}

static inline pte_t * __init early_ioremap_pte(unsigned long addr)
{
	return &bm_pte[pte_index(addr)];
}

bool __init is_early_ioremap_ptep(pte_t *ptep)
{
	return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)];
}

void __init early_ioremap_init(void)
{
	pmd_t *pmd;

#ifdef CONFIG_X86_64
	BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
#else
	WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1));
#endif

	early_ioremap_setup();

	pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN));
	memset(bm_pte, 0, sizeof(bm_pte));
	pmd_populate_kernel(&init_mm, pmd, bm_pte);

	/*
	 * The boot-ioremap range spans multiple pmds, for which
	 * we are not prepared:
	 */
#define __FIXADDR_TOP (-PAGE_SIZE)
	BUILD_BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));
#undef __FIXADDR_TOP
	if (pmd != early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END))) {
		WARN_ON(1);
		printk(KERN_WARNING "pmd %p != %p\n",
		       pmd, early_ioremap_pmd(fix_to_virt(FIX_BTMAP_END)));
		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
			fix_to_virt(FIX_BTMAP_BEGIN));
		printk(KERN_WARNING "fix_to_virt(FIX_BTMAP_END):   %08lx\n",
			fix_to_virt(FIX_BTMAP_END));

		printk(KERN_WARNING "FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
		printk(KERN_WARNING "FIX_BTMAP_BEGIN:     %d\n",
		       FIX_BTMAP_BEGIN);
	}
}

void __init __early_set_fixmap(enum fixed_addresses idx,
			       phys_addr_t phys, pgprot_t flags)
{
	unsigned long addr = __fix_to_virt(idx);
	pte_t *pte;

	if (idx >= __end_of_fixed_addresses) {
		BUG();
		return;
	}
	pte = early_ioremap_pte(addr);

	/* Sanitize 'prot' against any unsupported bits: */
	pgprot_val(flags) &= __default_kernel_pte_mask;

	if (pgprot_val(flags))
		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
	else
		pte_clear(&init_mm, addr, pte);
	__flush_tlb_one_kernel(addr);
}