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
|
From 9b2167f3c47600d84667fb2ee5676035826d288a Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Mon, 21 Oct 2019 16:56:00 +0800
Subject: [PATCH 4272/4736] drm/amdgpu: refine reboot debugfs operation in ras
case (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Ras reboot debugfs node allows user one easy control to avoid
gpu recovery hang problem and directly reboot system per card
basis, after ras uncorrectable error happens. However, it is
one common entry, which should get rid of ras_ctrl node and
remove ip dependence when inputting by user. So add one new
auto_reboot node in ras debugfs dir to achieve this.
v2: in commit mssage, add justification why ras reboot debugfs
node is needed.
v3: use debugfs_create_bool to create debugfs file for boolean value
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 19 ++++++++++++-------
1 file changed, 12 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1ca613014126..5b532cd254cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -151,8 +151,6 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
op = 1;
else if (sscanf(str, "inject %32s %8s", block_name, err) == 2)
op = 2;
- else if (sscanf(str, "reboot %32s", block_name) == 1)
- op = 3;
else if (str[0] && str[1] && str[2] && str[3])
/* ascii string, but commands are not matched. */
return -EINVAL;
@@ -216,12 +214,11 @@ static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
* value to the address.
*
* Second member: struct ras_debug_if::op.
- * It has four kinds of operations.
+ * It has three kinds of operations.
*
* - 0: disable RAS on the block. Take ::head as its data.
* - 1: enable RAS on the block. Take ::head as its data.
* - 2: inject errors on the block. Take ::inject as its data.
- * - 3: reboot on unrecoverable error
*
* How to use the interface?
* programs:
@@ -303,9 +300,6 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
/* data.inject.address is offset instead of absolute gpu address */
ret = amdgpu_ras_error_inject(adev, &data.inject);
break;
- case 3:
- amdgpu_ras_get_context(adev)->reboot = true;
- break;
default:
ret = -EINVAL;
break;
@@ -1035,6 +1029,17 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
adev, &amdgpu_ras_debugfs_ctrl_ops);
debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO, con->dir,
adev, &amdgpu_ras_debugfs_eeprom_ops);
+
+ /*
+ * After one uncorrectable error happens, usually GPU recovery will
+ * be scheduled. But due to the known problem in GPU recovery failing
+ * to bring GPU back, below interface provides one direct way to
+ * user to reboot system automatically in such case within
+ * ERREVENT_ATHUB_INTERRUPT generated. Normal GPU recovery routine
+ * will never be called.
+ */
+ debugfs_create_bool("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
+ &con->reboot);
}
void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
--
2.17.1
|
