summaryrefslogtreecommitdiffstats
path: root/arch/x86/virt/svm/sev.c
blob: 0ae10535c699982e15f20026a3e8012e52c41f32 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * AMD SVM-SEV Host Support.
 *
 * Copyright (C) 2023 Advanced Micro Devices, Inc.
 *
 * Author: Ashish Kalra <ashish.kalra@amd.com>
 *
 */

#include <linux/cc_platform.h>
#include <linux/printk.h>
#include <linux/mm_types.h>
#include <linux/set_memory.h>
#include <linux/memblock.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/cpumask.h>
#include <linux/iommu.h>
#include <linux/amd-iommu.h>

#include <asm/sev.h>
#include <asm/processor.h>
#include <asm/setup.h>
#include <asm/svm.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/apic.h>
#include <asm/cpuid.h>
#include <asm/cmdline.h>
#include <asm/iommu.h>

/*
 * The RMP entry format is not architectural. The format is defined in PPR
 * Family 19h Model 01h, Rev B1 processor.
 */
struct rmpentry {
	union {
		struct {
			u64 assigned	: 1,
			    pagesize	: 1,
			    immutable	: 1,
			    rsvd1	: 9,
			    gpa		: 39,
			    asid	: 10,
			    vmsa	: 1,
			    validated	: 1,
			    rsvd2	: 1;
		};
		u64 lo;
	};
	u64 hi;
} __packed;

/*
 * The first 16KB from the RMP_BASE is used by the processor for the
 * bookkeeping, the range needs to be added during the RMP entry lookup.
 */
#define RMPTABLE_CPU_BOOKKEEPING_SZ	0x4000

/* Mask to apply to a PFN to get the first PFN of a 2MB page */
#define PFN_PMD_MASK	GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT)

static u64 probed_rmp_base, probed_rmp_size;
static struct rmpentry *rmptable __ro_after_init;
static u64 rmptable_max_pfn __ro_after_init;

static LIST_HEAD(snp_leaked_pages_list);
static DEFINE_SPINLOCK(snp_leaked_pages_list_lock);

static unsigned long snp_nr_leaked_pages;

#undef pr_fmt
#define pr_fmt(fmt)	"SEV-SNP: " fmt

static int __mfd_enable(unsigned int cpu)
{
	u64 val;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return 0;

	rdmsrl(MSR_AMD64_SYSCFG, val);

	val |= MSR_AMD64_SYSCFG_MFDM;

	wrmsrl(MSR_AMD64_SYSCFG, val);

	return 0;
}

static __init void mfd_enable(void *arg)
{
	__mfd_enable(smp_processor_id());
}

static int __snp_enable(unsigned int cpu)
{
	u64 val;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return 0;

	rdmsrl(MSR_AMD64_SYSCFG, val);

	val |= MSR_AMD64_SYSCFG_SNP_EN;
	val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN;

	wrmsrl(MSR_AMD64_SYSCFG, val);

	return 0;
}

static __init void snp_enable(void *arg)
{
	__snp_enable(smp_processor_id());
}

#define RMP_ADDR_MASK GENMASK_ULL(51, 13)

bool snp_probe_rmptable_info(void)
{
	u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;

	rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
	rdmsrl(MSR_AMD64_RMP_END, rmp_end);

	if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) {
		pr_err("Memory for the RMP table has not been reserved by BIOS\n");
		return false;
	}

	if (rmp_base > rmp_end) {
		pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end);
		return false;
	}

	rmp_sz = rmp_end - rmp_base + 1;

	/*
	 * Calculate the amount the memory that must be reserved by the BIOS to
	 * address the whole RAM, including the bookkeeping area. The RMP itself
	 * must also be covered.
	 */
	max_rmp_pfn = max_pfn;
	if (PHYS_PFN(rmp_end) > max_pfn)
		max_rmp_pfn = PHYS_PFN(rmp_end);

	calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;

	if (calc_rmp_sz > rmp_sz) {
		pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
		       calc_rmp_sz, rmp_sz);
		return false;
	}

	probed_rmp_base = rmp_base;
	probed_rmp_size = rmp_sz;

	pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
		probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);

	return true;
}

static void __init __snp_fixup_e820_tables(u64 pa)
{
	if (IS_ALIGNED(pa, PMD_SIZE))
		return;

	/*
	 * Handle cases where the RMP table placement by the BIOS is not
	 * 2M aligned and the kexec kernel could try to allocate
	 * from within that chunk which then causes a fatal RMP fault.
	 *
	 * The e820_table needs to be updated as it is converted to
	 * kernel memory resources and used by KEXEC_FILE_LOAD syscall
	 * to load kexec segments.
	 *
	 * The e820_table_firmware needs to be updated as it is exposed
	 * to sysfs and used by the KEXEC_LOAD syscall to load kexec
	 * segments.
	 *
	 * The e820_table_kexec needs to be updated as it passed to
	 * the kexec-ed kernel.
	 */
	pa = ALIGN_DOWN(pa, PMD_SIZE);
	if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) {
		pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
		e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
		e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
		e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
	}
}

void __init snp_fixup_e820_tables(void)
{
	__snp_fixup_e820_tables(probed_rmp_base);
	__snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size);
}

/*
 * Do the necessary preparations which are verified by the firmware as
 * described in the SNP_INIT_EX firmware command description in the SNP
 * firmware ABI spec.
 */
static int __init snp_rmptable_init(void)
{
	void *rmptable_start;
	u64 rmptable_size;
	u64 val;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return 0;

	if (!amd_iommu_snp_en)
		goto nosnp;

	if (!probed_rmp_size)
		goto nosnp;

	rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
	if (!rmptable_start) {
		pr_err("Failed to map RMP table\n");
		return 1;
	}

	/*
	 * Check if SEV-SNP is already enabled, this can happen in case of
	 * kexec boot.
	 */
	rdmsrl(MSR_AMD64_SYSCFG, val);
	if (val & MSR_AMD64_SYSCFG_SNP_EN)
		goto skip_enable;

	memset(rmptable_start, 0, probed_rmp_size);

	/* Flush the caches to ensure that data is written before SNP is enabled. */
	wbinvd_on_all_cpus();

	/* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */
	on_each_cpu(mfd_enable, NULL, 1);

	on_each_cpu(snp_enable, NULL, 1);

skip_enable:
	rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ;
	rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ;

	rmptable = (struct rmpentry *)rmptable_start;
	rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1;

	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL);

	/*
	 * Setting crash_kexec_post_notifiers to 'true' to ensure that SNP panic
	 * notifier is invoked to do SNP IOMMU shutdown before kdump.
	 */
	crash_kexec_post_notifiers = true;

	return 0;

nosnp:
	cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
	return -ENOSYS;
}

/*
 * This must be called after the IOMMU has been initialized.
 */
device_initcall(snp_rmptable_init);

static struct rmpentry *get_rmpentry(u64 pfn)
{
	if (WARN_ON_ONCE(pfn > rmptable_max_pfn))
		return ERR_PTR(-EFAULT);

	return &rmptable[pfn];
}

static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
{
	struct rmpentry *large_entry, *entry;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return ERR_PTR(-ENODEV);

	entry = get_rmpentry(pfn);
	if (IS_ERR(entry))
		return entry;

	/*
	 * Find the authoritative RMP entry for a PFN. This can be either a 4K
	 * RMP entry or a special large RMP entry that is authoritative for a
	 * whole 2M area.
	 */
	large_entry = get_rmpentry(pfn & PFN_PMD_MASK);
	if (IS_ERR(large_entry))
		return large_entry;

	*level = RMP_TO_PG_LEVEL(large_entry->pagesize);

	return entry;
}

int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level)
{
	struct rmpentry *e;

	e = __snp_lookup_rmpentry(pfn, level);
	if (IS_ERR(e))
		return PTR_ERR(e);

	*assigned = !!e->assigned;
	return 0;
}
EXPORT_SYMBOL_GPL(snp_lookup_rmpentry);

/*
 * Dump the raw RMP entry for a particular PFN. These bits are documented in the
 * PPR for a particular CPU model and provide useful information about how a
 * particular PFN is being utilized by the kernel/firmware at the time certain
 * unexpected events occur, such as RMP faults.
 */
static void dump_rmpentry(u64 pfn)
{
	u64 pfn_i, pfn_end;
	struct rmpentry *e;
	int level;

	e = __snp_lookup_rmpentry(pfn, &level);
	if (IS_ERR(e)) {
		pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n",
		       pfn, PTR_ERR(e));
		return;
	}

	if (e->assigned) {
		pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n",
			pfn, e->lo, e->hi);
		return;
	}

	/*
	 * If the RMP entry for a particular PFN is not in an assigned state,
	 * then it is sometimes useful to get an idea of whether or not any RMP
	 * entries for other PFNs within the same 2MB region are assigned, since
	 * those too can affect the ability to access a particular PFN in
	 * certain situations, such as when the PFN is being accessed via a 2MB
	 * mapping in the host page table.
	 */
	pfn_i = ALIGN_DOWN(pfn, PTRS_PER_PMD);
	pfn_end = pfn_i + PTRS_PER_PMD;

	pr_info("PFN 0x%llx unassigned, dumping non-zero entries in 2M PFN region: [0x%llx - 0x%llx]\n",
		pfn, pfn_i, pfn_end);

	while (pfn_i < pfn_end) {
		e = __snp_lookup_rmpentry(pfn_i, &level);
		if (IS_ERR(e)) {
			pr_err("Error %ld reading RMP entry for PFN 0x%llx\n",
			       PTR_ERR(e), pfn_i);
			pfn_i++;
			continue;
		}

		if (e->lo || e->hi)
			pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi);
		pfn_i++;
	}
}

void snp_dump_hva_rmpentry(unsigned long hva)
{
	unsigned long paddr;
	unsigned int level;
	pgd_t *pgd;
	pte_t *pte;

	pgd = __va(read_cr3_pa());
	pgd += pgd_index(hva);
	pte = lookup_address_in_pgd(pgd, hva, &level);

	if (!pte) {
		pr_err("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva);
		return;
	}

	paddr = PFN_PHYS(pte_pfn(*pte)) | (hva & ~page_level_mask(level));
	dump_rmpentry(PHYS_PFN(paddr));
}

/*
 * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the
 * Validated bit.
 */
int psmash(u64 pfn)
{
	unsigned long paddr = pfn << PAGE_SHIFT;
	int ret;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return -ENODEV;

	if (!pfn_valid(pfn))
		return -EINVAL;

	/* Binutils version 2.36 supports the PSMASH mnemonic. */
	asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF"
		      : "=a" (ret)
		      : "a" (paddr)
		      : "memory", "cc");

	return ret;
}
EXPORT_SYMBOL_GPL(psmash);

/*
 * If the kernel uses a 2MB or larger directmap mapping to write to an address,
 * and that mapping contains any 4KB pages that are set to private in the RMP
 * table, an RMP #PF will trigger and cause a host crash. Hypervisor code that
 * owns the PFNs being transitioned will never attempt such a write, but other
 * kernel tasks writing to other PFNs in the range may trigger these checks
 * inadvertently due a large directmap mapping that happens to overlap such a
 * PFN.
 *
 * Prevent this by splitting any 2MB+ mappings that might end up containing a
 * mix of private/shared PFNs as a result of a subsequent RMPUPDATE for the
 * PFN/rmp_level passed in.
 *
 * Note that there is no attempt here to scan all the RMP entries for the 2MB
 * physical range, since it would only be worthwhile in determining if a
 * subsequent RMPUPDATE for a 4KB PFN would result in all the entries being of
 * the same shared/private state, thus avoiding the need to split the mapping.
 * But that would mean the entries are currently in a mixed state, and so the
 * mapping would have already been split as a result of prior transitions.
 * And since the 4K split is only done if the mapping is 2MB+, and there isn't
 * currently a mechanism in place to restore 2MB+ mappings, such a check would
 * not provide any usable benefit.
 *
 * More specifics on how these checks are carried out can be found in APM
 * Volume 2, "RMP and VMPL Access Checks".
 */
static int adjust_direct_map(u64 pfn, int rmp_level)
{
	unsigned long vaddr;
	unsigned int level;
	int npages, ret;
	pte_t *pte;

	/*
	 * pfn_to_kaddr() will return a vaddr only within the direct
	 * map range.
	 */
	vaddr = (unsigned long)pfn_to_kaddr(pfn);

	/* Only 4KB/2MB RMP entries are supported by current hardware. */
	if (WARN_ON_ONCE(rmp_level > PG_LEVEL_2M))
		return -EINVAL;

	if (!pfn_valid(pfn))
		return -EINVAL;

	if (rmp_level == PG_LEVEL_2M &&
	    (!IS_ALIGNED(pfn, PTRS_PER_PMD) || !pfn_valid(pfn + PTRS_PER_PMD - 1)))
		return -EINVAL;

	/*
	 * If an entire 2MB physical range is being transitioned, then there is
	 * no risk of RMP #PFs due to write accesses from overlapping mappings,
	 * since even accesses from 1GB mappings will be treated as 2MB accesses
	 * as far as RMP table checks are concerned.
	 */
	if (rmp_level == PG_LEVEL_2M)
		return 0;

	pte = lookup_address(vaddr, &level);
	if (!pte || pte_none(*pte))
		return 0;

	if (level == PG_LEVEL_4K)
		return 0;

	npages = page_level_size(rmp_level) / PAGE_SIZE;
	ret = set_memory_4k(vaddr, npages);
	if (ret)
		pr_warn("Failed to split direct map for PFN 0x%llx, ret: %d\n",
			pfn, ret);

	return ret;
}

/*
 * It is expected that those operations are seldom enough so that no mutual
 * exclusion of updaters is needed and thus the overlap error condition below
 * should happen very rarely and would get resolved relatively quickly by
 * the firmware.
 *
 * If not, one could consider introducing a mutex or so here to sync concurrent
 * RMP updates and thus diminish the amount of cases where firmware needs to
 * lock 2M ranges to protect against concurrent updates.
 *
 * The optimal solution would be range locking to avoid locking disjoint
 * regions unnecessarily but there's no support for that yet.
 */
static int rmpupdate(u64 pfn, struct rmp_state *state)
{
	unsigned long paddr = pfn << PAGE_SHIFT;
	int ret, level;

	if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		return -ENODEV;

	level = RMP_TO_PG_LEVEL(state->pagesize);

	if (adjust_direct_map(pfn, level))
		return -EFAULT;

	do {
		/* Binutils version 2.36 supports the RMPUPDATE mnemonic. */
		asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE"
			     : "=a" (ret)
			     : "a" (paddr), "c" ((unsigned long)state)
			     : "memory", "cc");
	} while (ret == RMPUPDATE_FAIL_OVERLAP);

	if (ret) {
		pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n",
		       pfn, level, ret);
		dump_rmpentry(pfn);
		dump_stack();
		return -EFAULT;
	}

	return 0;
}

/* Transition a page to guest-owned/private state in the RMP table. */
int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable)
{
	struct rmp_state state;

	memset(&state, 0, sizeof(state));
	state.assigned = 1;
	state.asid = asid;
	state.immutable = immutable;
	state.gpa = gpa;
	state.pagesize = PG_LEVEL_TO_RMP(level);

	return rmpupdate(pfn, &state);
}
EXPORT_SYMBOL_GPL(rmp_make_private);

/* Transition a page to hypervisor-owned/shared state in the RMP table. */
int rmp_make_shared(u64 pfn, enum pg_level level)
{
	struct rmp_state state;

	memset(&state, 0, sizeof(state));
	state.pagesize = PG_LEVEL_TO_RMP(level);

	return rmpupdate(pfn, &state);
}
EXPORT_SYMBOL_GPL(rmp_make_shared);

void snp_leak_pages(u64 pfn, unsigned int npages)
{
	struct page *page = pfn_to_page(pfn);

	pr_warn("Leaking PFN range 0x%llx-0x%llx\n", pfn, pfn + npages);

	spin_lock(&snp_leaked_pages_list_lock);
	while (npages--) {

		/*
		 * Reuse the page's buddy list for chaining into the leaked
		 * pages list. This page should not be on a free list currently
		 * and is also unsafe to be added to a free list.
		 */
		if (likely(!PageCompound(page)) ||

			/*
			 * Skip inserting tail pages of compound page as
			 * page->buddy_list of tail pages is not usable.
			 */
		    (PageHead(page) && compound_nr(page) <= npages))
			list_add_tail(&page->buddy_list, &snp_leaked_pages_list);

		dump_rmpentry(pfn);
		snp_nr_leaked_pages++;
		pfn++;
		page++;
	}
	spin_unlock(&snp_leaked_pages_list_lock);
}
EXPORT_SYMBOL_GPL(snp_leak_pages);

void kdump_sev_callback(void)
{
	/*
	 * Do wbinvd() on remote CPUs when SNP is enabled in order to
	 * safely do SNP_SHUTDOWN on the local CPU.
	 */
	if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
		wbinvd();
}