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
|
From f53d8dd9e21fd2833db36302e1d4205fb2cc9a05 Mon Sep 17 00:00:00 2001
From: Guchun Chen <guchun.chen@amd.com>
Date: Fri, 16 Aug 2019 15:06:52 +0800
Subject: [PATCH 3541/4256] drm/amdgpu: correct ras error count type
Use unsigned long type for the same ras count variable.
This will avoid overflow on 64 bit system.
Change-Id: I011406d81bad69a65433b63960e1691c4959bbc5
Signed-off-by: Guchun Chen <guchun.chen@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h | 4 ++--
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 6 +++---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 2 +-
4 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index acd44860c7d5..0c52d1d5f011 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -357,7 +357,7 @@ static int amdgpu_ctx_query2(struct amdgpu_device *adev,
{
struct amdgpu_ctx *ctx;
struct amdgpu_ctx_mgr *mgr;
- uint32_t ras_counter;
+ unsigned long ras_counter;
if (!fpriv)
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
index f22da13dfffd..442ee4c9e53e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h
@@ -51,8 +51,8 @@ struct amdgpu_ctx {
enum drm_sched_priority override_priority;
struct mutex lock;
atomic_t guilty;
- uint32_t ras_counter_ce;
- uint32_t ras_counter_ue;
+ unsigned long ras_counter_ce;
+ unsigned long ras_counter_ue;
};
struct amdgpu_ctx_mgr {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 50c13b02d234..df4b9ae39c5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -686,7 +686,7 @@ int amdgpu_ras_error_cure(struct amdgpu_device *adev,
}
/* get the total error counts on all IPs */
-int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
bool is_ce)
{
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -694,7 +694,7 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
struct ras_err_data data = {0, 0};
if (!con)
- return -EINVAL;
+ return 0;
list_for_each_entry(obj, &con->head, node) {
struct ras_query_if info = {
@@ -702,7 +702,7 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
};
if (amdgpu_ras_error_query(adev, &info))
- return -EINVAL;
+ return 0;
data.ce_count += info.ce_count;
data.ue_count += info.ue_count;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 2765f2dbb1e6..02a51e3dfa14 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -484,7 +484,7 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
void amdgpu_ras_resume(struct amdgpu_device *adev);
void amdgpu_ras_suspend(struct amdgpu_device *adev);
-int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
bool is_ce);
/* error handling functions */
--
2.17.1
|