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
|
From f3174d9652f9f5a198677a5cc789506612461803 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Sep 2019 15:09:56 -0500
Subject: [PATCH 3900/4256] drm/amdgpu/ras: fix and update the documentation
for RAS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Add new sections to amdgpu.rst, fix up formatting issues,
add additional documentation to each section.
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
Documentation/gpu/amdgpu.rst | 24 ++++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 53 +++++++++++++++++++++----
2 files changed, 68 insertions(+), 9 deletions(-)
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 80db5d89cd49..5b9eaf23558e 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -79,12 +79,32 @@ AMDGPU XGMI Support
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
:internal:
-AMDGPU RAS debugfs control interface
-====================================
+AMDGPU RAS Support
+==================
+
+RAS debugfs/sysfs Control and Error Injection Interfaces
+--------------------------------------------------------
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
:doc: AMDGPU RAS debugfs control interface
+RAS Error Count sysfs Interface
+-------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+ :doc: AMDGPU RAS sysfs Error Count Interface
+
+RAS EEPROM debugfs Interface
+----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+ :doc: AMDGPU RAS debugfs EEPROM table reset interface
+
+RAS VRAM Bad Pages sysfs Interface
+----------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+ :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
:internal:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f5aea49f2ab3..48541adb12fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -314,7 +314,18 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
/**
* DOC: AMDGPU RAS debugfs EEPROM table reset interface
*
- * Usage: echo 1 > ../ras/ras_eeprom_reset will reset EEPROM table to 0 entries.
+ * Some boards contain an EEPROM which is used to persistently store a list of
+ * bad pages containing ECC errors detected in vram. This interface provides
+ * a way to reset the EEPROM, e.g., after testing error injection.
+ *
+ * Usage:
+ *
+ * .. code-block:: bash
+ *
+ * echo 1 > ../ras/ras_eeprom_reset
+ *
+ * will reset EEPROM table to 0 entries.
+ *
*/
static ssize_t amdgpu_ras_debugfs_eeprom_write(struct file *f, const char __user *buf,
size_t size, loff_t *pos)
@@ -341,6 +352,27 @@ static const struct file_operations amdgpu_ras_debugfs_eeprom_ops = {
.llseek = default_llseek
};
+/**
+ * DOC: AMDGPU RAS sysfs Error Count Interface
+ *
+ * It allows user to read the error count for each IP block on the gpu through
+ * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count
+ *
+ * It outputs the multiple lines which report the uncorrected (ue) and corrected
+ * (ce) error counts.
+ *
+ * The format of one line is below,
+ *
+ * [ce|ue]: count
+ *
+ * Example:
+ *
+ * .. code-block:: bash
+ *
+ * ue: 0
+ * ce: 1
+ *
+ */
static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -785,8 +817,8 @@ static char *amdgpu_ras_badpage_flags_str(unsigned int flags)
};
}
-/*
- * DOC: ras sysfs gpu_vram_bad_pages interface
+/**
+ * DOC: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
*
* It allows user to read the bad pages of vram on the gpu through
* /sys/class/drm/card[0/1/2...]/device/ras/gpu_vram_bad_pages
@@ -798,14 +830,21 @@ static char *amdgpu_ras_badpage_flags_str(unsigned int flags)
*
* gpu pfn and gpu page size are printed in hex format.
* flags can be one of below character,
+ *
* R: reserved, this gpu page is reserved and not able to use.
+ *
* P: pending for reserve, this gpu page is marked as bad, will be reserved
- * in next window of page_reserve.
+ * in next window of page_reserve.
+ *
* F: unable to reserve. this gpu page can't be reserved due to some reasons.
*
- * examples:
- * 0x00000001 : 0x00001000 : R
- * 0x00000002 : 0x00001000 : P
+ * Examples:
+ *
+ * .. code-block:: bash
+ *
+ * 0x00000001 : 0x00001000 : R
+ * 0x00000002 : 0x00001000 : P
+ *
*/
static ssize_t amdgpu_ras_sysfs_badpages_read(struct file *f,
--
2.17.1
|
