Bootlin

Embedded Linux Experts

   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
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
/*
 * AMD Memory Encryption Support
 *
 * Copyright (C) 2016 Advanced Micro Devices, Inc.
 *
 * Author: Tom Lendacky <thomas.lendacky@amd.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define DISABLE_BRANCH_PROFILING

#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/swiotlb.h>
#include <linux/mem_encrypt.h>

#include <asm/tlbflush.h>
#include <asm/fixmap.h>
#include <asm/setup.h>
#include <asm/bootparam.h>
#include <asm/set_memory.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
#include <asm/processor-flags.h>
#include <asm/msr.h>
#include <asm/cmdline.h>

#include "mm_internal.h"

static char sme_cmdline_arg[] __initdata = "mem_encrypt";
static char sme_cmdline_on[]  __initdata = "on";
static char sme_cmdline_off[] __initdata = "off";

/*
 * Since SME related variables are set early in the boot process they must
 * reside in the .data section so as not to be zeroed out when the .bss
 * section is later cleared.
 */
u64 sme_me_mask __section(.data) = 0;
EXPORT_SYMBOL(sme_me_mask);
DEFINE_STATIC_KEY_FALSE(sev_enable_key);
EXPORT_SYMBOL_GPL(sev_enable_key);

static bool sev_enabled __section(.data);

/* Buffer used for early in-place encryption by BSP, no locking needed */
static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE);

/*
 * This routine does not change the underlying encryption setting of the
 * page(s) that map this memory. It assumes that eventually the memory is
 * meant to be accessed as either encrypted or decrypted but the contents
 * are currently not in the desired state.
 *
 * This routine follows the steps outlined in the AMD64 Architecture
 * Programmer's Manual Volume 2, Section 7.10.8 Encrypt-in-Place.
 */
static void __init __sme_early_enc_dec(resource_size_t paddr,
				       unsigned long size, bool enc)
{
	void *src, *dst;
	size_t len;

	if (!sme_me_mask)
		return;

	wbinvd();

	/*
	 * There are limited number of early mapping slots, so map (at most)
	 * one page at time.
	 */
	while (size) {
		len = min_t(size_t, sizeof(sme_early_buffer), size);

		/*
		 * Create mappings for the current and desired format of
		 * the memory. Use a write-protected mapping for the source.
		 */
		src = enc ? early_memremap_decrypted_wp(paddr, len) :
			    early_memremap_encrypted_wp(paddr, len);

		dst = enc ? early_memremap_encrypted(paddr, len) :
			    early_memremap_decrypted(paddr, len);

		/*
		 * If a mapping can't be obtained to perform the operation,
		 * then eventual access of that area in the desired mode
		 * will cause a crash.
		 */
		BUG_ON(!src || !dst);

		/*
		 * Use a temporary buffer, of cache-line multiple size, to
		 * avoid data corruption as documented in the APM.
		 */
		memcpy(sme_early_buffer, src, len);
		memcpy(dst, sme_early_buffer, len);

		early_memunmap(dst, len);
		early_memunmap(src, len);

		paddr += len;
		size -= len;
	}
}

void __init sme_early_encrypt(resource_size_t paddr, unsigned long size)
{
	__sme_early_enc_dec(paddr, size, true);
}

void __init sme_early_decrypt(resource_size_t paddr, unsigned long size)
{
	__sme_early_enc_dec(paddr, size, false);
}

static void __init __sme_early_map_unmap_mem(void *vaddr, unsigned long size,
					     bool map)
{
	unsigned long paddr = (unsigned long)vaddr - __PAGE_OFFSET;
	pmdval_t pmd_flags, pmd;

	/* Use early_pmd_flags but remove the encryption mask */
	pmd_flags = __sme_clr(early_pmd_flags);

	do {
		pmd = map ? (paddr & PMD_MASK) + pmd_flags : 0;
		__early_make_pgtable((unsigned long)vaddr, pmd);

		vaddr += PMD_SIZE;
		paddr += PMD_SIZE;
		size = (size <= PMD_SIZE) ? 0 : size - PMD_SIZE;
	} while (size);

	__native_flush_tlb();
}

void __init sme_unmap_bootdata(char *real_mode_data)
{
	struct boot_params *boot_data;
	unsigned long cmdline_paddr;

	if (!sme_active())
		return;

	/* Get the command line address before unmapping the real_mode_data */
	boot_data = (struct boot_params *)real_mode_data;
	cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);

	__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), false);

	if (!cmdline_paddr)
		return;

	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, false);
}

void __init sme_map_bootdata(char *real_mode_data)
{
	struct boot_params *boot_data;
	unsigned long cmdline_paddr;

	if (!sme_active())
		return;

	__sme_early_map_unmap_mem(real_mode_data, sizeof(boot_params), true);

	/* Get the command line address after mapping the real_mode_data */
	boot_data = (struct boot_params *)real_mode_data;
	cmdline_paddr = boot_data->hdr.cmd_line_ptr | ((u64)boot_data->ext_cmd_line_ptr << 32);

	if (!cmdline_paddr)
		return;

	__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
}

void __init sme_early_init(void)
{
	unsigned int i;

	if (!sme_me_mask)
		return;

	early_pmd_flags = __sme_set(early_pmd_flags);

	__supported_pte_mask = __sme_set(__supported_pte_mask);

	/* Update the protection map with memory encryption mask */
	for (i = 0; i < ARRAY_SIZE(protection_map); i++)
		protection_map[i] = pgprot_encrypted(protection_map[i]);

	if (sev_active())
		swiotlb_force = SWIOTLB_FORCE;
}

static void *sev_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
		       gfp_t gfp, unsigned long attrs)
{
	unsigned long dma_mask;
	unsigned int order;
	struct page *page;
	void *vaddr = NULL;

	dma_mask = dma_alloc_coherent_mask(dev, gfp);
	order = get_order(size);

	/*
	 * Memory will be memset to zero after marking decrypted, so don't
	 * bother clearing it before.
	 */
	gfp &= ~__GFP_ZERO;

	page = alloc_pages_node(dev_to_node(dev), gfp, order);
	if (page) {
		dma_addr_t addr;

		/*
		 * Since we will be clearing the encryption bit, check the
		 * mask with it already cleared.
		 */
		addr = __sme_clr(phys_to_dma(dev, page_to_phys(page)));
		if ((addr + size) > dma_mask) {
			__free_pages(page, get_order(size));
		} else {
			vaddr = page_address(page);
			*dma_handle = addr;
		}
	}

	if (!vaddr)
		vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, gfp);

	if (!vaddr)
		return NULL;

	/* Clear the SME encryption bit for DMA use if not swiotlb area */
	if (!is_swiotlb_buffer(dma_to_phys(dev, *dma_handle))) {
		set_memory_decrypted((unsigned long)vaddr, 1 << order);
		memset(vaddr, 0, PAGE_SIZE << order);
		*dma_handle = __sme_clr(*dma_handle);
	}

	return vaddr;
}

static void sev_free(struct device *dev, size_t size, void *vaddr,
		     dma_addr_t dma_handle, unsigned long attrs)
{
	/* Set the SME encryption bit for re-use if not swiotlb area */
	if (!is_swiotlb_buffer(dma_to_phys(dev, dma_handle)))
		set_memory_encrypted((unsigned long)vaddr,
				     1 << get_order(size));

	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
}

static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
{
	pgprot_t old_prot, new_prot;
	unsigned long pfn, pa, size;
	pte_t new_pte;

	switch (level) {
	case PG_LEVEL_4K:
		pfn = pte_pfn(*kpte);
		old_prot = pte_pgprot(*kpte);
		break;
	case PG_LEVEL_2M:
		pfn = pmd_pfn(*(pmd_t *)kpte);
		old_prot = pmd_pgprot(*(pmd_t *)kpte);
		break;
	case PG_LEVEL_1G:
		pfn = pud_pfn(*(pud_t *)kpte);
		old_prot = pud_pgprot(*(pud_t *)kpte);
		break;
	default:
		return;
	}

	new_prot = old_prot;
	if (enc)
		pgprot_val(new_prot) |= _PAGE_ENC;
	else
		pgprot_val(new_prot) &= ~_PAGE_ENC;

	/* If prot is same then do nothing. */
	if (pgprot_val(old_prot) == pgprot_val(new_prot))
		return;

	pa = pfn << page_level_shift(level);
	size = page_level_size(level);

	/*
	 * We are going to perform in-place en-/decryption and change the
	 * physical page attribute from C=1 to C=0 or vice versa. Flush the
	 * caches to ensure that data gets accessed with the correct C-bit.
	 */
	clflush_cache_range(__va(pa), size);

	/* Encrypt/decrypt the contents in-place */
	if (enc)
		sme_early_encrypt(pa, size);
	else
		sme_early_decrypt(pa, size);

	/* Change the page encryption mask. */
	new_pte = pfn_pte(pfn, new_prot);
	set_pte_atomic(kpte, new_pte);
}

static int __init early_set_memory_enc_dec(unsigned long vaddr,
					   unsigned long size, bool enc)
{
	unsigned long vaddr_end, vaddr_next;
	unsigned long psize, pmask;
	int split_page_size_mask;
	int level, ret;
	pte_t *kpte;

	vaddr_next = vaddr;
	vaddr_end = vaddr + size;

	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
		kpte = lookup_address(vaddr, &level);
		if (!kpte || pte_none(*kpte)) {
			ret = 1;
			goto out;
		}

		if (level == PG_LEVEL_4K) {
			__set_clr_pte_enc(kpte, level, enc);
			vaddr_next = (vaddr & PAGE_MASK) + PAGE_SIZE;
			continue;
		}

		psize = page_level_size(level);
		pmask = page_level_mask(level);

		/*
		 * Check whether we can change the large page in one go.
		 * We request a split when the address is not aligned and
		 * the number of pages to set/clear encryption bit is smaller
		 * than the number of pages in the large page.
		 */
		if (vaddr == (vaddr & pmask) &&
		    ((vaddr_end - vaddr) >= psize)) {
			__set_clr_pte_enc(kpte, level, enc);
			vaddr_next = (vaddr & pmask) + psize;
			continue;
		}

		/*
		 * The virtual address is part of a larger page, create the next
		 * level page table mapping (4K or 2M). If it is part of a 2M
		 * page then we request a split of the large page into 4K
		 * chunks. A 1GB large page is split into 2M pages, resp.
		 */
		if (level == PG_LEVEL_2M)
			split_page_size_mask = 0;
		else
			split_page_size_mask = 1 << PG_LEVEL_2M;

		kernel_physical_mapping_init(__pa(vaddr & pmask),
					     __pa((vaddr_end & pmask) + psize),
					     split_page_size_mask);
	}

	ret = 0;

out:
	__flush_tlb_all();
	return ret;
}

int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size)
{
	return early_set_memory_enc_dec(vaddr, size, false);
}

int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size)
{
	return early_set_memory_enc_dec(vaddr, size, true);
}

/*
 * SME and SEV are very similar but they are not the same, so there are
 * times that the kernel will need to distinguish between SME and SEV. The
 * sme_active() and sev_active() functions are used for this.  When a
 * distinction isn't needed, the mem_encrypt_active() function can be used.
 *
 * The trampoline code is a good example for this requirement.  Before
 * paging is activated, SME will access all memory as decrypted, but SEV
 * will access all memory as encrypted.  So, when APs are being brought
 * up under SME the trampoline area cannot be encrypted, whereas under SEV
 * the trampoline area must be encrypted.
 */
bool sme_active(void)
{
	return sme_me_mask && !sev_enabled;
}
EXPORT_SYMBOL(sme_active);

bool sev_active(void)
{
	return sme_me_mask && sev_enabled;
}
EXPORT_SYMBOL(sev_active);

static const struct dma_map_ops sev_dma_ops = {
	.alloc                  = sev_alloc,
	.free                   = sev_free,
	.map_page               = swiotlb_map_page,
	.unmap_page             = swiotlb_unmap_page,
	.map_sg                 = swiotlb_map_sg_attrs,
	.unmap_sg               = swiotlb_unmap_sg_attrs,
	.sync_single_for_cpu    = swiotlb_sync_single_for_cpu,
	.sync_single_for_device = swiotlb_sync_single_for_device,
	.sync_sg_for_cpu        = swiotlb_sync_sg_for_cpu,
	.sync_sg_for_device     = swiotlb_sync_sg_for_device,
	.mapping_error          = swiotlb_dma_mapping_error,
};

/* Architecture __weak replacement functions */
void __init mem_encrypt_init(void)
{
	if (!sme_me_mask)
		return;

	/* Call into SWIOTLB to update the SWIOTLB DMA buffers */
	swiotlb_update_mem_attributes();

	/*
	 * With SEV, DMA operations cannot use encryption. New DMA ops
	 * are required in order to mark the DMA areas as decrypted or
	 * to use bounce buffers.
	 */
	if (sev_active())
		dma_ops = &sev_dma_ops;

	/*
	 * With SEV, we need to unroll the rep string I/O instructions.
	 */
	if (sev_active())
		static_branch_enable(&sev_enable_key);

	pr_info("AMD %s active\n",
		sev_active() ? "Secure Encrypted Virtualization (SEV)"
			     : "Secure Memory Encryption (SME)");
}

void swiotlb_set_mem_attributes(void *vaddr, unsigned long size)
{
	WARN(PAGE_ALIGN(size) != size,
	     "size is not page-aligned (%#lx)\n", size);

	/* Make the SWIOTLB buffer area decrypted */
	set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT);
}

struct sme_populate_pgd_data {
	void	*pgtable_area;
	pgd_t	*pgd;

	pmdval_t pmd_flags;
	pteval_t pte_flags;
	unsigned long paddr;

	unsigned long vaddr;
	unsigned long vaddr_end;
};

static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
{
	unsigned long pgd_start, pgd_end, pgd_size;
	pgd_t *pgd_p;

	pgd_start = ppd->vaddr & PGDIR_MASK;
	pgd_end = ppd->vaddr_end & PGDIR_MASK;

	pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t);

	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);

	memset(pgd_p, 0, pgd_size);
}

#define PGD_FLAGS		_KERNPG_TABLE_NOENC
#define P4D_FLAGS		_KERNPG_TABLE_NOENC
#define PUD_FLAGS		_KERNPG_TABLE_NOENC
#define PMD_FLAGS		_KERNPG_TABLE_NOENC

#define PMD_FLAGS_LARGE		(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)

#define PMD_FLAGS_DEC		PMD_FLAGS_LARGE
#define PMD_FLAGS_DEC_WP	((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
				 (_PAGE_PAT | _PAGE_PWT))

#define PMD_FLAGS_ENC		(PMD_FLAGS_LARGE | _PAGE_ENC)

#define PTE_FLAGS		(__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL)

#define PTE_FLAGS_DEC		PTE_FLAGS
#define PTE_FLAGS_DEC_WP	((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
				 (_PAGE_PAT | _PAGE_PWT))

#define PTE_FLAGS_ENC		(PTE_FLAGS | _PAGE_ENC)

static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd)
{
	pgd_t *pgd_p;
	p4d_t *p4d_p;
	pud_t *pud_p;
	pmd_t *pmd_p;

	pgd_p = ppd->pgd + pgd_index(ppd->vaddr);
	if (native_pgd_val(*pgd_p)) {
		if (IS_ENABLED(CONFIG_X86_5LEVEL))
			p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
		else
			pud_p = (pud_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK);
	} else {
		pgd_t pgd;

		if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
			p4d_p = ppd->pgtable_area;
			memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D);
			ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D;

			pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS);
		} else {
			pud_p = ppd->pgtable_area;
			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;

			pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS);
		}
		native_set_pgd(pgd_p, pgd);
	}

	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
		p4d_p += p4d_index(ppd->vaddr);
		if (native_p4d_val(*p4d_p)) {
			pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK);
		} else {
			p4d_t p4d;

			pud_p = ppd->pgtable_area;
			memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD);
			ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD;

			p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS);
			native_set_p4d(p4d_p, p4d);
		}
	}

	pud_p += pud_index(ppd->vaddr);
	if (native_pud_val(*pud_p)) {
		if (native_pud_val(*pud_p) & _PAGE_PSE)
			return NULL;

		pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK);
	} else {
		pud_t pud;

		pmd_p = ppd->pgtable_area;
		memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD);
		ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD;

		pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS);
		native_set_pud(pud_p, pud);
	}

	return pmd_p;
}

static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd)
{
	pmd_t *pmd_p;

	pmd_p = sme_prepare_pgd(ppd);
	if (!pmd_p)
		return;

	pmd_p += pmd_index(ppd->vaddr);
	if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE))
		native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags));
}

static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
{
	pmd_t *pmd_p;
	pte_t *pte_p;

	pmd_p = sme_prepare_pgd(ppd);
	if (!pmd_p)
		return;

	pmd_p += pmd_index(ppd->vaddr);
	if (native_pmd_val(*pmd_p)) {
		if (native_pmd_val(*pmd_p) & _PAGE_PSE)
			return;

		pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK);
	} else {
		pmd_t pmd;

		pte_p = ppd->pgtable_area;
		memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE);
		ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE;

		pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS);
		native_set_pmd(pmd_p, pmd);
	}

	pte_p += pte_index(ppd->vaddr);
	if (!native_pte_val(*pte_p))
		native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags));
}

static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd)
{
	while (ppd->vaddr < ppd->vaddr_end) {
		sme_populate_pgd_large(ppd);

		ppd->vaddr += PMD_PAGE_SIZE;
		ppd->paddr += PMD_PAGE_SIZE;
	}
}

static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd)
{
	while (ppd->vaddr < ppd->vaddr_end) {
		sme_populate_pgd(ppd);

		ppd->vaddr += PAGE_SIZE;
		ppd->paddr += PAGE_SIZE;
	}
}

static void __init __sme_map_range(struct sme_populate_pgd_data *ppd,
				   pmdval_t pmd_flags, pteval_t pte_flags)
{
	unsigned long vaddr_end;

	ppd->pmd_flags = pmd_flags;
	ppd->pte_flags = pte_flags;

	/* Save original end value since we modify the struct value */
	vaddr_end = ppd->vaddr_end;

	/* If start is not 2MB aligned, create PTE entries */
	ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE);
	__sme_map_range_pte(ppd);

	/* Create PMD entries */
	ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK;
	__sme_map_range_pmd(ppd);

	/* If end is not 2MB aligned, create PTE entries */
	ppd->vaddr_end = vaddr_end;
	__sme_map_range_pte(ppd);
}

static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd)
{
	__sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC);
}

static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd)
{
	__sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC);
}

static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd)
{
	__sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP);
}

static unsigned long __init sme_pgtable_calc(unsigned long len)
{
	unsigned long p4d_size, pud_size, pmd_size, pte_size;
	unsigned long total;

	/*
	 * Perform a relatively simplistic calculation of the pagetable
	 * entries that are needed. Those mappings will be covered mostly
	 * by 2MB PMD entries so we can conservatively calculate the required
	 * number of P4D, PUD and PMD structures needed to perform the
	 * mappings.  For mappings that are not 2MB aligned, PTE mappings
	 * would be needed for the start and end portion of the address range
	 * that fall outside of the 2MB alignment.  This results in, at most,
	 * two extra pages to hold PTE entries for each range that is mapped.
	 * Incrementing the count for each covers the case where the addresses
	 * cross entries.
	 */
	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
		p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
		p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D;
		pud_size = (ALIGN(len, P4D_SIZE) / P4D_SIZE) + 1;
		pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
	} else {
		p4d_size = 0;
		pud_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1;
		pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
	}
	pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1;
	pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;
	pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE;

	total = p4d_size + pud_size + pmd_size + pte_size;

	/*
	 * Now calculate the added pagetable structures needed to populate
	 * the new pagetables.
	 */
	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
		p4d_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE;
		p4d_size *= sizeof(p4d_t) * PTRS_PER_P4D;
		pud_size = ALIGN(total, P4D_SIZE) / P4D_SIZE;
		pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
	} else {
		p4d_size = 0;
		pud_size = ALIGN(total, PGDIR_SIZE) / PGDIR_SIZE;
		pud_size *= sizeof(pud_t) * PTRS_PER_PUD;
	}
	pmd_size = ALIGN(total, PUD_SIZE) / PUD_SIZE;
	pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD;

	total += p4d_size + pud_size + pmd_size;

	return total;
}

void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp)
{
	unsigned long workarea_start, workarea_end, workarea_len;
	unsigned long execute_start, execute_end, execute_len;
	unsigned long kernel_start, kernel_end, kernel_len;
	unsigned long initrd_start, initrd_end, initrd_len;
	struct sme_populate_pgd_data ppd;
	unsigned long pgtable_area_len;
	unsigned long decrypted_base;

	if (!sme_active())
		return;

	/*
	 * Prepare for encrypting the kernel and initrd by building new
	 * pagetables with the necessary attributes needed to encrypt the
	 * kernel in place.
	 *
	 *   One range of virtual addresses will map the memory occupied
	 *   by the kernel and initrd as encrypted.
	 *
	 *   Another range of virtual addresses will map the memory occupied
	 *   by the kernel and initrd as decrypted and write-protected.
	 *
	 *     The use of write-protect attribute will prevent any of the
	 *     memory from being cached.
	 */

	/* Physical addresses gives us the identity mapped virtual addresses */
	kernel_start = __pa_symbol(_text);
	kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE);
	kernel_len = kernel_end - kernel_start;

	initrd_start = 0;
	initrd_end = 0;
	initrd_len = 0;
#ifdef CONFIG_BLK_DEV_INITRD
	initrd_len = (unsigned long)bp->hdr.ramdisk_size |
		     ((unsigned long)bp->ext_ramdisk_size << 32);
	if (initrd_len) {
		initrd_start = (unsigned long)bp->hdr.ramdisk_image |
			       ((unsigned long)bp->ext_ramdisk_image << 32);
		initrd_end = PAGE_ALIGN(initrd_start + initrd_len);
		initrd_len = initrd_end - initrd_start;
	}
#endif

	/* Set the encryption workarea to be immediately after the kernel */
	workarea_start = kernel_end;

	/*
	 * Calculate required number of workarea bytes needed:
	 *   executable encryption area size:
	 *     stack page (PAGE_SIZE)
	 *     encryption routine page (PAGE_SIZE)
	 *     intermediate copy buffer (PMD_PAGE_SIZE)
	 *   pagetable structures for the encryption of the kernel
	 *   pagetable structures for workarea (in case not currently mapped)
	 */
	execute_start = workarea_start;
	execute_end = execute_start + (PAGE_SIZE * 2) + PMD_PAGE_SIZE;
	execute_len = execute_end - execute_start;

	/*
	 * One PGD for both encrypted and decrypted mappings and a set of
	 * PUDs and PMDs for each of the encrypted and decrypted mappings.
	 */
	pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD;
	pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2;
	if (initrd_len)
		pgtable_area_len += sme_pgtable_calc(initrd_len) * 2;

	/* PUDs and PMDs needed in the current pagetables for the workarea */
	pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len);

	/*
	 * The total workarea includes the executable encryption area and
	 * the pagetable area. The start of the workarea is already 2MB
	 * aligned, align the end of the workarea on a 2MB boundary so that
	 * we don't try to create/allocate PTE entries from the workarea
	 * before it is mapped.
	 */
	workarea_len = execute_len + pgtable_area_len;
	workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE);

	/*
	 * Set the address to the start of where newly created pagetable
	 * structures (PGDs, PUDs and PMDs) will be allocated. New pagetable
	 * structures are created when the workarea is added to the current
	 * pagetables and when the new encrypted and decrypted kernel
	 * mappings are populated.
	 */
	ppd.pgtable_area = (void *)execute_end;

	/*
	 * Make sure the current pagetable structure has entries for
	 * addressing the workarea.
	 */
	ppd.pgd = (pgd_t *)native_read_cr3_pa();
	ppd.paddr = workarea_start;
	ppd.vaddr = workarea_start;
	ppd.vaddr_end = workarea_end;
	sme_map_range_decrypted(&ppd);

	/* Flush the TLB - no globals so cr3 is enough */
	native_write_cr3(__native_read_cr3());

	/*
	 * A new pagetable structure is being built to allow for the kernel
	 * and initrd to be encrypted. It starts with an empty PGD that will
	 * then be populated with new PUDs and PMDs as the encrypted and
	 * decrypted kernel mappings are created.
	 */
	ppd.pgd = ppd.pgtable_area;
	memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD);
	ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD;

	/*
	 * A different PGD index/entry must be used to get different
	 * pagetable entries for the decrypted mapping. Choose the next
	 * PGD index and convert it to a virtual address to be used as
	 * the base of the mapping.
	 */
	decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1);
	if (initrd_len) {
		unsigned long check_base;

		check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1);
		decrypted_base = max(decrypted_base, check_base);
	}
	decrypted_base <<= PGDIR_SHIFT;

	/* Add encrypted kernel (identity) mappings */
	ppd.paddr = kernel_start;
	ppd.vaddr = kernel_start;
	ppd.vaddr_end = kernel_end;
	sme_map_range_encrypted(&ppd);

	/* Add decrypted, write-protected kernel (non-identity) mappings */
	ppd.paddr = kernel_start;
	ppd.vaddr = kernel_start + decrypted_base;
	ppd.vaddr_end = kernel_end + decrypted_base;
	sme_map_range_decrypted_wp(&ppd);

	if (initrd_len) {
		/* Add encrypted initrd (identity) mappings */
		ppd.paddr = initrd_start;
		ppd.vaddr = initrd_start;
		ppd.vaddr_end = initrd_end;
		sme_map_range_encrypted(&ppd);
		/*
		 * Add decrypted, write-protected initrd (non-identity) mappings
		 */
		ppd.paddr = initrd_start;
		ppd.vaddr = initrd_start + decrypted_base;
		ppd.vaddr_end = initrd_end + decrypted_base;
		sme_map_range_decrypted_wp(&ppd);
	}

	/* Add decrypted workarea mappings to both kernel mappings */
	ppd.paddr = workarea_start;
	ppd.vaddr = workarea_start;
	ppd.vaddr_end = workarea_end;
	sme_map_range_decrypted(&ppd);

	ppd.paddr = workarea_start;
	ppd.vaddr = workarea_start + decrypted_base;
	ppd.vaddr_end = workarea_end + decrypted_base;
	sme_map_range_decrypted(&ppd);

	/* Perform the encryption */
	sme_encrypt_execute(kernel_start, kernel_start + decrypted_base,
			    kernel_len, workarea_start, (unsigned long)ppd.pgd);

	if (initrd_len)
		sme_encrypt_execute(initrd_start, initrd_start + decrypted_base,
				    initrd_len, workarea_start,
				    (unsigned long)ppd.pgd);

	/*
	 * At this point we are running encrypted.  Remove the mappings for
	 * the decrypted areas - all that is needed for this is to remove
	 * the PGD entry/entries.
	 */
	ppd.vaddr = kernel_start + decrypted_base;
	ppd.vaddr_end = kernel_end + decrypted_base;
	sme_clear_pgd(&ppd);

	if (initrd_len) {
		ppd.vaddr = initrd_start + decrypted_base;
		ppd.vaddr_end = initrd_end + decrypted_base;
		sme_clear_pgd(&ppd);
	}

	ppd.vaddr = workarea_start + decrypted_base;
	ppd.vaddr_end = workarea_end + decrypted_base;
	sme_clear_pgd(&ppd);

	/* Flush the TLB - no globals so cr3 is enough */
	native_write_cr3(__native_read_cr3());
}

void __init __nostackprotector sme_enable(struct boot_params *bp)
{
	const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
	unsigned int eax, ebx, ecx, edx;
	unsigned long feature_mask;
	bool active_by_default;
	unsigned long me_mask;
	char buffer[16];
	u64 msr;

	/* Check for the SME/SEV support leaf */
	eax = 0x80000000;
	ecx = 0;
	native_cpuid(&eax, &ebx, &ecx, &edx);
	if (eax < 0x8000001f)
		return;

#define AMD_SME_BIT	BIT(0)
#define AMD_SEV_BIT	BIT(1)
	/*
	 * Set the feature mask (SME or SEV) based on whether we are
	 * running under a hypervisor.
	 */
	eax = 1;
	ecx = 0;
	native_cpuid(&eax, &ebx, &ecx, &edx);
	feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT;

	/*
	 * Check for the SME/SEV feature:
	 *   CPUID Fn8000_001F[EAX]
	 *   - Bit 0 - Secure Memory Encryption support
	 *   - Bit 1 - Secure Encrypted Virtualization support
	 *   CPUID Fn8000_001F[EBX]
	 *   - Bits 5:0 - Pagetable bit position used to indicate encryption
	 */
	eax = 0x8000001f;
	ecx = 0;
	native_cpuid(&eax, &ebx, &ecx, &edx);
	if (!(eax & feature_mask))
		return;

	me_mask = 1UL << (ebx & 0x3f);

	/* Check if memory encryption is enabled */
	if (feature_mask == AMD_SME_BIT) {
		/* For SME, check the SYSCFG MSR */
		msr = __rdmsr(MSR_K8_SYSCFG);
		if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
			return;
	} else {
		/* For SEV, check the SEV MSR */
		msr = __rdmsr(MSR_AMD64_SEV);
		if (!(msr & MSR_AMD64_SEV_ENABLED))
			return;

		/* SEV state cannot be controlled by a command line option */
		sme_me_mask = me_mask;
		sev_enabled = true;
		return;
	}

	/*
	 * Fixups have not been applied to phys_base yet and we're running
	 * identity mapped, so we must obtain the address to the SME command
	 * line argument data using rip-relative addressing.
	 */
	asm ("lea sme_cmdline_arg(%%rip), %0"
	     : "=r" (cmdline_arg)
	     : "p" (sme_cmdline_arg));
	asm ("lea sme_cmdline_on(%%rip), %0"
	     : "=r" (cmdline_on)
	     : "p" (sme_cmdline_on));
	asm ("lea sme_cmdline_off(%%rip), %0"
	     : "=r" (cmdline_off)
	     : "p" (sme_cmdline_off));

	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
		active_by_default = true;
	else
		active_by_default = false;

	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
				     ((u64)bp->ext_cmd_line_ptr << 32));

	cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer));

	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
		sme_me_mask = me_mask;
	else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
		sme_me_mask = 0;
	else
		sme_me_mask = active_by_default ? me_mask : 0;
}