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
|
From 08e5fb8014201d89613db69476b1888500505519 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Tue, 12 Dec 2017 14:09:30 -0500
Subject: [PATCH 2961/4131] drm/amdgpu: Add gpu_recovery parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Add new parameter to control GPU recovery procedure.
v2:
Add auto logic where reset is disabled for bare metal and enabled
for SR-IOV.
Allow forced reset from debugfs.
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 3 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 9 ++++++++-
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++++
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 2 +-
drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c | 2 +-
drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c | 2 +-
8 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 81e019a..d827b85 100755
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -128,6 +128,7 @@ extern int amdgpu_param_buf_per_se;
extern int amdgpu_job_hang_limit;
extern int amdgpu_lbpw;
extern int amdgpu_compute_multipipe;
+extern int amdgpu_gpu_recovery;
#ifdef CONFIG_DRM_AMDGPU_SI
extern int amdgpu_si_support;
@@ -1985,7 +1986,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
#define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
/* Common functions */
-int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job);
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job* job, bool force);
bool amdgpu_need_backup(struct amdgpu_device *adev);
void amdgpu_pci_config_reset(struct amdgpu_device *adev);
bool amdgpu_need_post(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3866998..285aa9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3039,11 +3039,12 @@ static int amdgpu_reset_sriov(struct amdgpu_device *adev, uint64_t *reset_flags,
*
* @adev: amdgpu device pointer
* @job: which job trigger hang
+ * @force forces reset regardless of amdgpu_gpu_recovery
*
* Attempt to reset the GPU if it has hung (all asics).
* Returns 0 for success or an error on failure.
*/
-int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)
+int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job, bool force)
{
struct drm_atomic_state *state = NULL;
uint64_t reset_flags = 0;
@@ -3053,6 +3054,12 @@ int amdgpu_gpu_recover(struct amdgpu_device *adev, struct amdgpu_job *job)
DRM_INFO("No hardware hang detected. Did some blocks stall?\n");
return 0;
}
+
+ if (!force && (amdgpu_gpu_recovery == 0 ||
+ (amdgpu_gpu_recovery == -1 && !amdgpu_sriov_vf(adev)))) {
+ DRM_INFO("GPU recovery disabled.\n");
+ return 0;
+ }
dev_info(adev->dev, "GPU reset begin!\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 43c42c7..710e33e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -129,6 +129,7 @@ int amdgpu_param_buf_per_se = 0;
int amdgpu_job_hang_limit = 0;
int amdgpu_lbpw = -1;
int amdgpu_compute_multipipe = -1;
+int amdgpu_gpu_recovery = -1; /* auto */
MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
@@ -284,6 +285,9 @@ module_param_named(lbpw, amdgpu_lbpw, int, 0444);
MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
+MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto");
+module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
+
#ifdef CONFIG_DRM_AMDGPU_SI
int amdgpu_si_support = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index ddd43c6..8e5d055 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -705,7 +705,7 @@ static int amdgpu_debugfs_gpu_recover(struct seq_file *m, void *data)
struct amdgpu_device *adev = dev->dev_private;
seq_printf(m, "gpu recover\n");
- amdgpu_gpu_recover(adev, NULL);
+ amdgpu_gpu_recover(adev, NULL, true);
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 2ac1d98..c6e2dcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -88,7 +88,7 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
reset_work);
if (!amdgpu_sriov_vf(adev))
- amdgpu_gpu_recover(adev, NULL);
+ amdgpu_gpu_recover(adev, NULL, false);
}
/* Disable *all* interrupts */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9ca22a4..2087d7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,7 +37,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
atomic_read(&job->ring->fence_drv.last_seq),
job->ring->fence_drv.sync_seq);
- amdgpu_gpu_recover(job->adev, job);
+ amdgpu_gpu_recover(job->adev, job, false);
}
int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 71f5690..7ade56d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -253,7 +253,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
}
/* Trigger recovery due to world switch failure */
- amdgpu_gpu_recover(adev, NULL);
+ amdgpu_gpu_recover(adev, NULL, false);
}
static int xgpu_ai_set_mailbox_rcv_irq(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
index df52824..e05823d 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
@@ -521,7 +521,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
}
/* Trigger recovery due to world switch failure */
- amdgpu_gpu_recover(adev, NULL);
+ amdgpu_gpu_recover(adev, NULL, false);
}
static int xgpu_vi_set_mailbox_rcv_irq(struct amdgpu_device *adev,
--
2.7.4
|
