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
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
|
From d303ea8dbbb910cd6b02367b063a2a908cf26e15 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 28 May 2019 14:17:25 -0500
Subject: [PATCH 2040/2940] drm/amdgpu: fix a race in GPU reset with IB test
(v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Split late_init into two functions, one (do_late_init) which
just does the hw init, and late_init which calls do_late_init
and schedules the IB test work. Call do_late_init in
the GPU reset code to run the init code, but not schedule
the IB test code. The IB test code is called directly
in the gpu reset code so no need to run the IB tests
in a separate work thread. If we do, we end up racing.
v2: Rework late_init. Pull out the mgpu fan boost and xgmi
pstate code into late_init so they get called in all cases.
rename the late_init worker thread to delayed work since it's
just the IB tests now which can happen later. Schedule the
work at init and resume time. It's not needed at reset time
because the IB tests are called directly.
Reviewed-by: Christian König <christian.koenig@amd.com>
Cc: Xinhui Pan <xinhui.pan@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Chaudhary Amit Kumar <Chaudharyamit.Kumar@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 116 +++++++++++----------
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 +-
3 files changed, 61 insertions(+), 59 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e79bcfc1499c..b99fef62357f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -961,7 +961,7 @@ struct amdgpu_device {
const struct amdgpu_df_funcs *df_funcs;
/* delayed work_func for deferring clockgating during resume */
- struct delayed_work late_init_work;
+ struct delayed_work delayed_init_work;
struct amdgpu_virt virt;
/* firmware VRAM reservation */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 1228adcfab49..84a9f0745d77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1904,6 +1904,43 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power
return 0;
}
+static int amdgpu_device_enable_mgpu_fan_boost(void)
+{
+ struct amdgpu_gpu_instance *gpu_ins;
+ struct amdgpu_device *adev;
+ int i, ret = 0;
+
+ mutex_lock(&mgpu_info.mutex);
+
+ /*
+ * MGPU fan boost feature should be enabled
+ * only when there are two or more dGPUs in
+ * the system
+ */
+ if (mgpu_info.num_dgpu < 2)
+ goto out;
+
+ for (i = 0; i < mgpu_info.num_dgpu; i++) {
+ gpu_ins = &(mgpu_info.gpu_ins[i]);
+ adev = gpu_ins->adev;
+ if (!(adev->flags & AMD_IS_APU) &&
+ !gpu_ins->mgpu_fan_enabled &&
+ adev->powerplay.pp_funcs &&
+ adev->powerplay.pp_funcs->enable_mgpu_fan_boost) {
+ ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
+ if (ret)
+ break;
+
+ gpu_ins->mgpu_fan_enabled = 1;
+ }
+ }
+
+out:
+ mutex_unlock(&mgpu_info.mutex);
+
+ return ret;
+}
+
/**
* amdgpu_device_ip_late_init - run late init for hardware IPs
*
@@ -1937,11 +1974,15 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
amdgpu_device_set_cg_state(adev, AMD_CG_STATE_GATE);
amdgpu_device_set_pg_state(adev, AMD_PG_STATE_GATE);
- queue_delayed_work(system_wq, &adev->late_init_work,
- msecs_to_jiffies(AMDGPU_RESUME_MS));
-
amdgpu_device_fill_reset_magic(adev);
+ r = amdgpu_device_enable_mgpu_fan_boost();
+ if (r)
+ DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
+
+ /* set to low pstate by default */
+ amdgpu_xgmi_set_pstate(adev, 0);
+
return 0;
}
@@ -2040,65 +2081,20 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
return 0;
}
-static int amdgpu_device_enable_mgpu_fan_boost(void)
-{
- struct amdgpu_gpu_instance *gpu_ins;
- struct amdgpu_device *adev;
- int i, ret = 0;
-
- mutex_lock(&mgpu_info.mutex);
-
- /*
- * MGPU fan boost feature should be enabled
- * only when there are two or more dGPUs in
- * the system
- */
- if (mgpu_info.num_dgpu < 2)
- goto out;
-
- for (i = 0; i < mgpu_info.num_dgpu; i++) {
- gpu_ins = &(mgpu_info.gpu_ins[i]);
- adev = gpu_ins->adev;
- if (!(adev->flags & AMD_IS_APU) &&
- !gpu_ins->mgpu_fan_enabled &&
- adev->powerplay.pp_funcs &&
- adev->powerplay.pp_funcs->enable_mgpu_fan_boost) {
- ret = amdgpu_dpm_enable_mgpu_fan_boost(adev);
- if (ret)
- break;
-
- gpu_ins->mgpu_fan_enabled = 1;
- }
- }
-
-out:
- mutex_unlock(&mgpu_info.mutex);
-
- return ret;
-}
-
/**
- * amdgpu_device_ip_late_init_func_handler - work handler for ib test
+ * amdgpu_device_delayed_init_work_handler - work handler for IB tests
*
* @work: work_struct.
*/
-static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
+static void amdgpu_device_delayed_init_work_handler(struct work_struct *work)
{
struct amdgpu_device *adev =
- container_of(work, struct amdgpu_device, late_init_work.work);
+ container_of(work, struct amdgpu_device, delayed_init_work.work);
int r;
r = amdgpu_ib_ring_tests(adev);
if (r)
DRM_ERROR("ib ring test failed (%d).\n", r);
-
- r = amdgpu_device_enable_mgpu_fan_boost();
- if (r)
- DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
-
- /*set to low pstate by default */
- amdgpu_xgmi_set_pstate(adev, 0);
-
}
static void amdgpu_device_delay_enable_gfx_off(struct work_struct *work)
@@ -2571,8 +2567,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
INIT_LIST_HEAD(&adev->ring_lru_list);
spin_lock_init(&adev->ring_lru_list_lock);
- INIT_DELAYED_WORK(&adev->late_init_work,
- amdgpu_device_ip_late_init_func_handler);
+ INIT_DELAYED_WORK(&adev->delayed_init_work,
+ amdgpu_device_delayed_init_work_handler);
INIT_DELAYED_WORK(&adev->gfx.gfx_off_delay_work,
amdgpu_device_delay_enable_gfx_off);
@@ -2806,6 +2802,9 @@ int amdgpu_device_init(struct amdgpu_device *adev,
/* must succeed. */
amdgpu_ras_resume(adev);
+ queue_delayed_work(system_wq, &adev->delayed_init_work,
+ msecs_to_jiffies(AMDGPU_RESUME_MS));
+
r = device_create_file(adev->dev, &dev_attr_pcie_replay_count);
if (r) {
dev_err(adev->dev, "Could not create pcie_replay_count");
@@ -2853,7 +2852,7 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
adev->firmware.gpu_info_fw = NULL;
}
adev->accel_working = false;
- cancel_delayed_work_sync(&adev->late_init_work);
+ cancel_delayed_work_sync(&adev->delayed_init_work);
/* free i2c buses */
if (!amdgpu_device_has_dc_support(adev))
amdgpu_i2c_fini(adev);
@@ -2916,7 +2915,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
if (fbcon)
amdgpu_fbdev_set_suspend(adev, 1);
- cancel_delayed_work_sync(&adev->late_init_work);
+ cancel_delayed_work_sync(&adev->delayed_init_work);
if (!amdgpu_device_has_dc_support(adev)) {
/* turn off display hw */
@@ -3036,6 +3035,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
if (r)
return r;
+ queue_delayed_work(system_wq, &adev->delayed_init_work,
+ msecs_to_jiffies(AMDGPU_RESUME_MS));
+
if (!amdgpu_device_has_dc_support(adev)) {
/* pin cursors */
list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -3059,7 +3061,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
return r;
/* Make sure IB tests flushed */
- flush_delayed_work(&adev->late_init_work);
+ flush_delayed_work(&adev->delayed_init_work);
/* blat the mode back in */
if (fbcon) {
@@ -3647,7 +3649,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
dev_info(adev->dev, "GPU reset begin!\n");
- cancel_delayed_work_sync(&adev->late_init_work);
+ cancel_delayed_work_sync(&adev->delayed_init_work);
hive = amdgpu_get_xgmi_hive(adev, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index dfa59c31e5e0..2cdaacef0226 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1003,7 +1003,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
int r, pasid;
/* Ensure IB tests are run on ring */
- flush_delayed_work(&adev->late_init_work);
+ flush_delayed_work(&adev->delayed_init_work);
file_priv->driver_priv = NULL;
--
2.17.1
|
