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
267
268
269
270
|
From 14b62f16474e181a70e786caee45908cd6a45fdf Mon Sep 17 00:00:00 2001
From: Monk Liu <Monk.Liu@amd.com>
Date: Mon, 25 Dec 2017 11:59:27 +0800
Subject: [PATCH 3624/4131] drm/amdgpu: cleanups for vram lost handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
1)create a routine "handle_vram_lost" to do the vram
recovery, and put it into amdgpu_device_reset/reset_sriov,
this way no need of the extra paramter to hold the
VRAM LOST information and the related macros can be removed.
3)show vram_recover failure if time out, and set TMO equal to
lockup_timeout if vram_recover is under SRIOV runtime mode.
4)report error if any ip reset failed for SR-IOV
Change-Id: I686e2b6133844c14948c206a2315c064a78c1d9c
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Kalyan Alle <kalyan.alle@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 4 -
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 138 +++++++++++++++--------------
2 files changed, 72 insertions(+), 70 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 37e43fd..d784389 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -183,10 +183,6 @@ extern int amdgpu_cik_support;
#define CIK_CURSOR_WIDTH 128
#define CIK_CURSOR_HEIGHT 128
-/* GPU RESET flags */
-#define AMDGPU_RESET_INFO_VRAM_LOST (1 << 0)
-#define AMDGPU_RESET_INFO_FULLRESET (1 << 1)
-
struct amdgpu_device;
struct amdgpu_ib;
struct amdgpu_cs_parser;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5a83045..84adc73 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1620,6 +1620,8 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
r = block->version->funcs->hw_init(adev);
DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+ if (r)
+ return r;
}
}
@@ -1653,6 +1655,8 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
r = block->version->funcs->hw_init(adev);
DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+ if (r)
+ return r;
}
}
@@ -2502,17 +2506,71 @@ static int amdgpu_device_recover_vram_from_shadow(struct amdgpu_device *adev,
return r;
}
+static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
+{
+ struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
+ struct amdgpu_bo *bo, *tmp;
+ struct dma_fence *fence = NULL, *next = NULL;
+ long r = 1;
+ int i = 0;
+ long tmo;
+
+ if (amdgpu_sriov_runtime(adev))
+ tmo = msecs_to_jiffies(amdgpu_lockup_timeout);
+ else
+ tmo = msecs_to_jiffies(100);
+
+ DRM_INFO("recover vram bo from shadow start\n");
+ mutex_lock(&adev->shadow_list_lock);
+ list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
+ next = NULL;
+ amdgpu_device_recover_vram_from_shadow(adev, ring, bo, &next);
+ if (fence) {
+ r = dma_fence_wait_timeout(fence, false, tmo);
+ if (r == 0)
+ pr_err("wait fence %p[%d] timeout\n", fence, i);
+ else if (r < 0)
+ pr_err("wait fence %p[%d] interrupted\n", fence, i);
+ if (r < 1) {
+ dma_fence_put(fence);
+ fence = next;
+ break;
+ }
+ i++;
+ }
+
+ dma_fence_put(fence);
+ fence = next;
+ }
+ mutex_unlock(&adev->shadow_list_lock);
+
+ if (fence) {
+ r = dma_fence_wait_timeout(fence, false, tmo);
+ if (r == 0)
+ pr_err("wait fence %p[%d] timeout\n", fence, i);
+ else if (r < 0)
+ pr_err("wait fence %p[%d] interrupted\n", fence, i);
+
+ }
+ dma_fence_put(fence);
+
+ if (r > 0)
+ DRM_INFO("recover vram bo from shadow done\n");
+ else
+ DRM_ERROR("recover vram bo from shadow failed\n");
+
+ return (r > 0?0:1);
+}
+
/*
* amdgpu_device_reset - reset ASIC/GPU for bare-metal or passthrough
*
* @adev: amdgpu device pointer
- * @reset_flags: output param tells caller the reset result
*
* attempt to do soft-reset or full-reset and reinitialize Asic
* return 0 means successed otherwise failed
*/
-static int amdgpu_device_reset(struct amdgpu_device *adev,
- uint64_t* reset_flags)
+static int amdgpu_device_reset(struct amdgpu_device *adev)
{
bool need_full_reset, vram_lost = 0;
int r;
@@ -2527,7 +2585,6 @@ static int amdgpu_device_reset(struct amdgpu_device *adev,
DRM_INFO("soft reset failed, will fallback to full reset!\n");
need_full_reset = true;
}
-
}
if (need_full_reset) {
@@ -2576,13 +2633,8 @@ static int amdgpu_device_reset(struct amdgpu_device *adev,
}
}
- if (reset_flags) {
- if (vram_lost)
- (*reset_flags) |= AMDGPU_RESET_INFO_VRAM_LOST;
-
- if (need_full_reset)
- (*reset_flags) |= AMDGPU_RESET_INFO_FULLRESET;
- }
+ if (!r && ((need_full_reset && !(adev->flags & AMD_IS_APU)) || vram_lost))
+ r = amdgpu_device_handle_vram_lost(adev);
return r;
}
@@ -2591,14 +2643,11 @@ static int amdgpu_device_reset(struct amdgpu_device *adev,
* amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
*
* @adev: amdgpu device pointer
- * @reset_flags: output param tells caller the reset result
*
* do VF FLR and reinitialize Asic
* return 0 means successed otherwise failed
*/
-static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
- uint64_t *reset_flags,
- bool from_hypervisor)
+static int amdgpu_device_reset_sriov(struct amdgpu_device *adev, bool from_hypervisor)
{
int r;
@@ -2619,27 +2668,18 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
/* now we are okay to resume SMC/CP/SDMA */
r = amdgpu_device_ip_reinit_late_sriov(adev);
+ amdgpu_virt_release_full_gpu(adev, true);
if (r)
goto error;
amdgpu_irq_gpu_reset_resume_helper(adev);
r = amdgpu_ib_ring_tests(adev);
- if (r)
- dev_err(adev->dev, "[GPU_RESET] ib ring test failed (%d).\n", r);
+ if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
+ atomic_inc(&adev->vram_lost_counter);
+ r = amdgpu_device_handle_vram_lost(adev);
+ }
error:
- /* release full control of GPU after ib test */
- amdgpu_virt_release_full_gpu(adev, true);
-
- if (reset_flags) {
- if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
- (*reset_flags) |= AMDGPU_RESET_INFO_VRAM_LOST;
- atomic_inc(&adev->vram_lost_counter);
- }
-
- /* VF FLR or hotlink reset is always full-reset */
- (*reset_flags) |= AMDGPU_RESET_INFO_FULLRESET;
- }
return r;
}
@@ -2658,7 +2698,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
struct amdgpu_job *job, bool force)
{
struct drm_atomic_state *state = NULL;
- uint64_t reset_flags = 0;
int i, r, resched;
if (!force && !amdgpu_device_ip_check_soft_reset(adev)) {
@@ -2706,42 +2745,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
}
if (amdgpu_sriov_vf(adev))
- r = amdgpu_device_reset_sriov(adev, &reset_flags, job ? false : true);
- else
- r = amdgpu_device_reset(adev, &reset_flags);
-
- if (!r) {
- if (((reset_flags & AMDGPU_RESET_INFO_FULLRESET) && !(adev->flags & AMD_IS_APU)) ||
- (reset_flags & AMDGPU_RESET_INFO_VRAM_LOST)) {
- struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
- struct amdgpu_bo *bo, *tmp;
- struct dma_fence *fence = NULL, *next = NULL;
-
- DRM_INFO("recover vram bo from shadow\n");
- mutex_lock(&adev->shadow_list_lock);
- list_for_each_entry_safe(bo, tmp, &adev->shadow_list, shadow_list) {
- next = NULL;
- amdgpu_device_recover_vram_from_shadow(adev, ring, bo, &next);
- if (fence) {
- r = dma_fence_wait(fence, false);
- if (r) {
- WARN(r, "recovery from shadow isn't completed\n");
- break;
- }
- }
-
- dma_fence_put(fence);
- fence = next;
- }
- mutex_unlock(&adev->shadow_list_lock);
- if (fence) {
- r = dma_fence_wait(fence, false);
- if (r)
- WARN(r, "recovery from shadow isn't completed\n");
- }
- dma_fence_put(fence);
- }
- }
+ r = amdgpu_device_reset_sriov(adev, job ? false : true);
+ else
+ r = amdgpu_device_reset(adev);
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
--
2.7.4
|
