aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/kvm.c
blob: cbadc730496a67409d4a8d7eefcfb965761083ed (plain) (blame)
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
/*
 * KVM paravirt_ops implementation
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 *
 * Copyright (C) 2007, Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 * Copyright IBM Corporation, 2007
 *   Authors: Anthony Liguori <aliguori@us.ibm.com>
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/kvm_para.h>
#include <linux/cpu.h>
#include <linux/mm.h>
#include <linux/highmem.h>

/*
 * No need for any "IO delay" on KVM
 */
static void kvm_io_delay(void)
{
}

static void kvm_mmu_op(void *buffer, unsigned len)
{
	int r;
	unsigned long a1, a2;

	do {
		a1 = __pa(buffer);
		a2 = 0;   /* on i386 __pa() always returns <4G */
		r = kvm_hypercall3(KVM_HC_MMU_OP, len, a1, a2);
		buffer += r;
		len -= r;
	} while (len);
}

static void kvm_mmu_write(void *dest, u64 val)
{
	__u64 pte_phys;
	struct kvm_mmu_op_write_pte wpte;

#ifdef CONFIG_HIGHPTE
	struct page *page;
	unsigned long dst = (unsigned long) dest;

	page = kmap_atomic_to_page(dest);
	pte_phys = page_to_pfn(page);
	pte_phys <<= PAGE_SHIFT;
	pte_phys += (dst & ~(PAGE_MASK));
#else
	pte_phys = (unsigned long)__pa(dest);
#endif
	wpte.header.op = KVM_MMU_OP_WRITE_PTE;
	wpte.pte_val = val;
	wpte.pte_phys = pte_phys;

	kvm_mmu_op(&wpte, sizeof wpte);
}

/*
 * We only need to hook operations that are MMU writes.  We hook these so that
 * we can use lazy MMU mode to batch these operations.  We could probably
 * improve the performance of the host code if we used some of the information
 * here to simplify processing of batched writes.
 */
static void kvm_set_pte(pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_set_pte_at(struct mm_struct *mm, unsigned long addr,
			   pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
	kvm_mmu_write(pmdp, pmd_val(pmd));
}

#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
static void kvm_set_pte_atomic(pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_set_pte_present(struct mm_struct *mm, unsigned long addr,
				pte_t *ptep, pte_t pte)
{
	kvm_mmu_write(ptep, pte_val(pte));
}

static void kvm_pte_clear(struct mm_struct *mm,
			  unsigned long addr, pte_t *ptep)
{
	kvm_mmu_write(ptep, 0);
}

static void kvm_pmd_clear(pmd_t *pmdp)
{
	kvm_mmu_write(pmdp, 0);
}
#endif

static void kvm_set_pud(pud_t *pudp, pud_t pud)
{
	kvm_mmu_write(pudp, pud_val(pud));
}

#if PAGETABLE_LEVELS == 4
static void kvm_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
	kvm_mmu_write(pgdp, pgd_val(pgd));
}
#endif
#endif /* PAGETABLE_LEVELS >= 3 */

static void kvm_flush_tlb(void)
{
	struct kvm_mmu_op_flush_tlb ftlb = {
		.header.op = KVM_MMU_OP_FLUSH_TLB,
	};

	kvm_mmu_op(&ftlb, sizeof ftlb);
}

static void kvm_release_pt(u32 pfn)
{
	struct kvm_mmu_op_release_pt rpt = {
		.header.op = KVM_MMU_OP_RELEASE_PT,
		.pt_phys = (u64)pfn << PAGE_SHIFT,
	};

	kvm_mmu_op(&rpt, sizeof rpt);
}

static void paravirt_ops_setup(void)
{
	pv_info.name = "KVM";
	pv_info.paravirt_enabled = 1;

	if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
		pv_cpu_ops.io_delay = kvm_io_delay;

	if (kvm_para_has_feature(KVM_FEATURE_MMU_OP)) {
		pv_mmu_ops.set_pte = kvm_set_pte;
		pv_mmu_ops.set_pte_at = kvm_set_pte_at;
		pv_mmu_ops.set_pmd = kvm_set_pmd;
#if PAGETABLE_LEVELS >= 3
#ifdef CONFIG_X86_PAE
		pv_mmu_ops.set_pte_atomic = kvm_set_pte_atomic;
		pv_mmu_ops.set_pte_present = kvm_set_pte_present;
		pv_mmu_ops.pte_clear = kvm_pte_clear;
		pv_mmu_ops.pmd_clear = kvm_pmd_clear;
#endif
		pv_mmu_ops.set_pud = kvm_set_pud;
#if PAGETABLE_LEVELS == 4
		pv_mmu_ops.set_pgd = kvm_set_pgd;
#endif
#endif
		pv_mmu_ops.flush_tlb_user = kvm_flush_tlb;
		pv_mmu_ops.release_pte = kvm_release_pt;
		pv_mmu_ops.release_pmd = kvm_release_pt;
		pv_mmu_ops.release_pud = kvm_release_pt;
	}
}

void __init kvm_guest_init(void)
{
	if (!kvm_para_available())
		return;

	paravirt_ops_setup();
}