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
|
/*
* Machine check exception handling.
*
* 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, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
* Copyright 2013 IBM Corporation
* Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
*/
#undef DEBUG
#define pr_fmt(fmt) "mce: " fmt
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/percpu.h>
#include <linux/export.h>
#include <asm/mce.h>
static DEFINE_PER_CPU(int, mce_nest_count);
static DEFINE_PER_CPU(struct machine_check_event[MAX_MC_EVT], mce_event);
static void mce_set_error_info(struct machine_check_event *mce,
struct mce_error_info *mce_err)
{
mce->error_type = mce_err->error_type;
switch (mce_err->error_type) {
case MCE_ERROR_TYPE_UE:
mce->u.ue_error.ue_error_type = mce_err->u.ue_error_type;
break;
case MCE_ERROR_TYPE_SLB:
mce->u.slb_error.slb_error_type = mce_err->u.slb_error_type;
break;
case MCE_ERROR_TYPE_ERAT:
mce->u.erat_error.erat_error_type = mce_err->u.erat_error_type;
break;
case MCE_ERROR_TYPE_TLB:
mce->u.tlb_error.tlb_error_type = mce_err->u.tlb_error_type;
break;
case MCE_ERROR_TYPE_UNKNOWN:
default:
break;
}
}
/*
* Decode and save high level MCE information into per cpu buffer which
* is an array of machine_check_event structure.
*/
void save_mce_event(struct pt_regs *regs, long handled,
struct mce_error_info *mce_err,
uint64_t addr)
{
uint64_t srr1;
int index = __get_cpu_var(mce_nest_count)++;
struct machine_check_event *mce = &__get_cpu_var(mce_event[index]);
/*
* Return if we don't have enough space to log mce event.
* mce_nest_count may go beyond MAX_MC_EVT but that's ok,
* the check below will stop buffer overrun.
*/
if (index >= MAX_MC_EVT)
return;
/* Populate generic machine check info */
mce->version = MCE_V1;
mce->srr0 = regs->nip;
mce->srr1 = regs->msr;
mce->gpr3 = regs->gpr[3];
mce->in_use = 1;
mce->initiator = MCE_INITIATOR_CPU;
if (handled)
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
mce->severity = MCE_SEV_ERROR_SYNC;
srr1 = regs->msr;
/*
* Populate the mce error_type and type-specific error_type.
*/
mce_set_error_info(mce, mce_err);
if (!addr)
return;
if (mce->error_type == MCE_ERROR_TYPE_TLB) {
mce->u.tlb_error.effective_address_provided = true;
mce->u.tlb_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_SLB) {
mce->u.slb_error.effective_address_provided = true;
mce->u.slb_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_ERAT) {
mce->u.erat_error.effective_address_provided = true;
mce->u.erat_error.effective_address = addr;
} else if (mce->error_type == MCE_ERROR_TYPE_UE) {
mce->u.ue_error.effective_address_provided = true;
mce->u.ue_error.effective_address = addr;
}
return;
}
/*
* get_mce_event:
* mce Pointer to machine_check_event structure to be filled.
* release Flag to indicate whether to free the event slot or not.
* 0 <= do not release the mce event. Caller will invoke
* release_mce_event() once event has been consumed.
* 1 <= release the slot.
*
* return 1 = success
* 0 = failure
*
* get_mce_event() will be called by platform specific machine check
* handle routine and in KVM.
* When we call get_mce_event(), we are still in interrupt context and
* preemption will not be scheduled until ret_from_expect() routine
* is called.
*/
int get_mce_event(struct machine_check_event *mce, bool release)
{
int index = __get_cpu_var(mce_nest_count) - 1;
struct machine_check_event *mc_evt;
int ret = 0;
/* Sanity check */
if (index < 0)
return ret;
/* Check if we have MCE info to process. */
if (index < MAX_MC_EVT) {
mc_evt = &__get_cpu_var(mce_event[index]);
/* Copy the event structure and release the original */
if (mce)
*mce = *mc_evt;
if (release)
mc_evt->in_use = 0;
ret = 1;
}
/* Decrement the count to free the slot. */
if (release)
__get_cpu_var(mce_nest_count)--;
return ret;
}
void release_mce_event(void)
{
get_mce_event(NULL, true);
}
|
