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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* AMD Memory Encryption Support
*
* Copyright (C) 2019 SUSE
*
* Author: Joerg Roedel <jroedel@suse.de>
*/
#define pr_fmt(fmt) "SEV: " fmt
#include <linux/bug.h>
#include <linux/kernel.h>
#include <asm/cpu_entry_area.h>
#include <asm/msr.h>
#include <asm/ptrace.h>
#include <asm/sev.h>
#include <asm/sev-internal.h>
static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
unsigned long sp = regs->sp;
/* User-mode RSP is not trusted */
if (user_mode(regs))
return false;
/* SYSCALL gap still has user-mode RSP */
if (ip_within_syscall_gap(regs))
return false;
return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
}
/*
* This function handles the case when an NMI is raised in the #VC
* exception handler entry code, before the #VC handler has switched off
* its IST stack. In this case, the IST entry for #VC must be adjusted,
* so that any nested #VC exception will not overwrite the stack
* contents of the interrupted #VC handler.
*
* The IST entry is adjusted unconditionally so that it can be also be
* unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
* nested sev_es_ist_exit() call may adjust back the IST entry too
* early.
*
* The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
* on the NMI IST stack, as they are only called from NMI handling code
* right now.
*/
void noinstr __sev_es_ist_enter(struct pt_regs *regs)
{
unsigned long old_ist, new_ist;
/* Read old IST entry */
new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
/*
* If NMI happened while on the #VC IST stack, set the new IST
* value below regs->sp, so that the interrupted stack frame is
* not overwritten by subsequent #VC exceptions.
*/
if (on_vc_stack(regs))
new_ist = regs->sp;
/*
* Reserve additional 8 bytes and store old IST value so this
* adjustment can be unrolled in __sev_es_ist_exit().
*/
new_ist -= sizeof(old_ist);
*(unsigned long *)new_ist = old_ist;
/* Set new IST entry */
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
}
void noinstr __sev_es_ist_exit(void)
{
unsigned long ist;
/* Read IST entry */
ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
return;
/* Read back old IST entry and write it to the TSS */
this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
}
void noinstr __sev_es_nmi_complete(void)
{
struct ghcb_state state;
struct ghcb *ghcb;
ghcb = __sev_get_ghcb(&state);
vc_ghcb_invalidate(ghcb);
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
ghcb_set_sw_exit_info_1(ghcb, 0);
ghcb_set_sw_exit_info_2(ghcb, 0);
sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
VMGEXIT();
__sev_put_ghcb(&state);
}
/*
* Nothing shall interrupt this code path while holding the per-CPU
* GHCB. The backup GHCB is only for NMIs interrupting this path.
*
* Callers must disable local interrupts around it.
*/
noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
{
struct sev_es_runtime_data *data;
struct ghcb *ghcb;
WARN_ON(!irqs_disabled());
data = this_cpu_read(runtime_data);
ghcb = &data->ghcb_page;
if (unlikely(data->ghcb_active)) {
/* GHCB is already in use - save its contents */
if (unlikely(data->backup_ghcb_active)) {
/*
* Backup-GHCB is also already in use. There is no way
* to continue here so just kill the machine. To make
* panic() work, mark GHCBs inactive so that messages
* can be printed out.
*/
data->ghcb_active = false;
data->backup_ghcb_active = false;
instrumentation_begin();
panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
instrumentation_end();
}
/* Mark backup_ghcb active before writing to it */
data->backup_ghcb_active = true;
state->ghcb = &data->backup_ghcb;
/* Backup GHCB content */
*state->ghcb = *ghcb;
} else {
state->ghcb = NULL;
data->ghcb_active = true;
}
return ghcb;
}
noinstr void __sev_put_ghcb(struct ghcb_state *state)
{
struct sev_es_runtime_data *data;
struct ghcb *ghcb;
WARN_ON(!irqs_disabled());
data = this_cpu_read(runtime_data);
ghcb = &data->ghcb_page;
if (state->ghcb) {
/* Restore GHCB from Backup */
*ghcb = *state->ghcb;
data->backup_ghcb_active = false;
state->ghcb = NULL;
} else {
/*
* Invalidate the GHCB so a VMGEXIT instruction issued
* from userspace won't appear to be valid.
*/
vc_ghcb_invalidate(ghcb);
data->ghcb_active = false;
}
}
|
