summaryrefslogtreecommitdiff
path: root/arch/arm64/kvm/pkvm.c
blob: cf56958b1492a486f7e549c95d1f5ec828349a6b (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2020 - Google LLC
 * Author: Quentin Perret <qperret@google.com>
 */

#include <linux/kvm_host.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
#include <linux/sort.h>

#include <asm/kvm_pkvm.h>

#include "hyp_constants.h"

static struct memblock_region *hyp_memory = kvm_nvhe_sym(hyp_memory);
static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr);

phys_addr_t hyp_mem_base;
phys_addr_t hyp_mem_size;

static int cmp_hyp_memblock(const void *p1, const void *p2)
{
	const struct memblock_region *r1 = p1;
	const struct memblock_region *r2 = p2;

	return r1->base < r2->base ? -1 : (r1->base > r2->base);
}

static void __init sort_memblock_regions(void)
{
	sort(hyp_memory,
	     *hyp_memblock_nr_ptr,
	     sizeof(struct memblock_region),
	     cmp_hyp_memblock,
	     NULL);
}

static int __init register_memblock_regions(void)
{
	struct memblock_region *reg;

	for_each_mem_region(reg) {
		if (*hyp_memblock_nr_ptr >= HYP_MEMBLOCK_REGIONS)
			return -ENOMEM;

		hyp_memory[*hyp_memblock_nr_ptr] = *reg;
		(*hyp_memblock_nr_ptr)++;
	}
	sort_memblock_regions();

	return 0;
}

void __init kvm_hyp_reserve(void)
{
	u64 hyp_mem_pages = 0;
	int ret;

	if (!is_hyp_mode_available() || is_kernel_in_hyp_mode())
		return;

	if (kvm_get_mode() != KVM_MODE_PROTECTED)
		return;

	ret = register_memblock_regions();
	if (ret) {
		*hyp_memblock_nr_ptr = 0;
		kvm_err("Failed to register hyp memblocks: %d\n", ret);
		return;
	}

	hyp_mem_pages += hyp_s1_pgtable_pages();
	hyp_mem_pages += host_s2_pgtable_pages();
	hyp_mem_pages += hyp_vm_table_pages();
	hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE);

	/*
	 * Try to allocate a PMD-aligned region to reduce TLB pressure once
	 * this is unmapped from the host stage-2, and fallback to PAGE_SIZE.
	 */
	hyp_mem_size = hyp_mem_pages << PAGE_SHIFT;
	hyp_mem_base = memblock_phys_alloc(ALIGN(hyp_mem_size, PMD_SIZE),
					   PMD_SIZE);
	if (!hyp_mem_base)
		hyp_mem_base = memblock_phys_alloc(hyp_mem_size, PAGE_SIZE);
	else
		hyp_mem_size = ALIGN(hyp_mem_size, PMD_SIZE);

	if (!hyp_mem_base) {
		kvm_err("Failed to reserve hyp memory\n");
		return;
	}

	kvm_info("Reserved %lld MiB at 0x%llx\n", hyp_mem_size >> 20,
		 hyp_mem_base);
}

/*
 * Allocates and donates memory for hypervisor VM structs at EL2.
 *
 * Allocates space for the VM state, which includes the hyp vm as well as
 * the hyp vcpus.
 *
 * Stores an opaque handler in the kvm struct for future reference.
 *
 * Return 0 on success, negative error code on failure.
 */
static int __pkvm_create_hyp_vm(struct kvm *host_kvm)
{
	size_t pgd_sz, hyp_vm_sz, hyp_vcpu_sz;
	struct kvm_vcpu *host_vcpu;
	pkvm_handle_t handle;
	void *pgd, *hyp_vm;
	unsigned long idx;
	int ret;

	if (host_kvm->created_vcpus < 1)
		return -EINVAL;

	pgd_sz = kvm_pgtable_stage2_pgd_size(host_kvm->arch.vtcr);

	/*
	 * The PGD pages will be reclaimed using a hyp_memcache which implies
	 * page granularity. So, use alloc_pages_exact() to get individual
	 * refcounts.
	 */
	pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT);
	if (!pgd)
		return -ENOMEM;

	/* Allocate memory to donate to hyp for vm and vcpu pointers. */
	hyp_vm_sz = PAGE_ALIGN(size_add(PKVM_HYP_VM_SIZE,
					size_mul(sizeof(void *),
						 host_kvm->created_vcpus)));
	hyp_vm = alloc_pages_exact(hyp_vm_sz, GFP_KERNEL_ACCOUNT);
	if (!hyp_vm) {
		ret = -ENOMEM;
		goto free_pgd;
	}

	/* Donate the VM memory to hyp and let hyp initialize it. */
	ret = kvm_call_hyp_nvhe(__pkvm_init_vm, host_kvm, hyp_vm, pgd);
	if (ret < 0)
		goto free_vm;

	handle = ret;

	host_kvm->arch.pkvm.handle = handle;

	/* Donate memory for the vcpus at hyp and initialize it. */
	hyp_vcpu_sz = PAGE_ALIGN(PKVM_HYP_VCPU_SIZE);
	kvm_for_each_vcpu(idx, host_vcpu, host_kvm) {
		void *hyp_vcpu;

		/* Indexing of the vcpus to be sequential starting at 0. */
		if (WARN_ON(host_vcpu->vcpu_idx != idx)) {
			ret = -EINVAL;
			goto destroy_vm;
		}

		hyp_vcpu = alloc_pages_exact(hyp_vcpu_sz, GFP_KERNEL_ACCOUNT);
		if (!hyp_vcpu) {
			ret = -ENOMEM;
			goto destroy_vm;
		}

		ret = kvm_call_hyp_nvhe(__pkvm_init_vcpu, handle, host_vcpu,
					hyp_vcpu);
		if (ret) {
			free_pages_exact(hyp_vcpu, hyp_vcpu_sz);
			goto destroy_vm;
		}
	}

	return 0;

destroy_vm:
	pkvm_destroy_hyp_vm(host_kvm);
	return ret;
free_vm:
	free_pages_exact(hyp_vm, hyp_vm_sz);
free_pgd:
	free_pages_exact(pgd, pgd_sz);
	return ret;
}

int pkvm_create_hyp_vm(struct kvm *host_kvm)
{
	int ret = 0;

	mutex_lock(&host_kvm->lock);
	if (!host_kvm->arch.pkvm.handle)
		ret = __pkvm_create_hyp_vm(host_kvm);
	mutex_unlock(&host_kvm->lock);

	return ret;
}

void pkvm_destroy_hyp_vm(struct kvm *host_kvm)
{
	if (host_kvm->arch.pkvm.handle) {
		WARN_ON(kvm_call_hyp_nvhe(__pkvm_teardown_vm,
					  host_kvm->arch.pkvm.handle));
	}

	host_kvm->arch.pkvm.handle = 0;
	free_hyp_memcache(&host_kvm->arch.pkvm.teardown_mc);
}

int pkvm_init_host_vm(struct kvm *host_kvm)
{
	mutex_init(&host_kvm->lock);
	return 0;
}