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
|
From e0f9bf14f8d78ede12f7a6df26539c2db3730857 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Thu, 12 Jul 2018 15:15:21 +0200
Subject: [PATCH 0101/2940] drm/amdgpu: use new scheduler load balancing for
VMs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Instead of the fixed round robin use let the scheduler balance the load
of page table updates.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 ++----------
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 7 +++----
drivers/gpu/drm/amd/amdgpu/cik_sdma.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 12 +++++++-----
drivers/gpu/drm/amd/amdgpu/si_dma.c | 12 +++++++-----
8 files changed, 41 insertions(+), 40 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c78e25255f98..63668764bf5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2348,7 +2348,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
adev->mman.buffer_funcs = NULL;
adev->mman.buffer_funcs_ring = NULL;
adev->vm_manager.vm_pte_funcs = NULL;
- adev->vm_manager.vm_pte_num_rings = 0;
+ adev->vm_manager.vm_pte_num_rqs = 0;
adev->gmc.gmc_funcs = NULL;
adev->fence_context = dma_fence_context_alloc(AMDGPU_MAX_RINGS);
bitmap_zero(adev->gfx.pipe_reserve_bitmap, AMDGPU_MAX_COMPUTE_QUEUES);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6a84526e20e0..baeef7ca6f97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2595,9 +2595,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
struct amdgpu_bo *root;
const unsigned align = min(AMDGPU_VM_PTB_ALIGN_SIZE,
AMDGPU_VM_PTE_COUNT(adev) * 8);
- unsigned ring_instance;
- struct amdgpu_ring *ring;
- struct drm_sched_rq *rq;
unsigned long size;
uint64_t flags;
int r, i;
@@ -2613,12 +2610,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
INIT_LIST_HEAD(&vm->freed);
/* create scheduler entity for page table updates */
-
- ring_instance = atomic_inc_return(&adev->vm_manager.vm_pte_next_ring);
- ring_instance %= adev->vm_manager.vm_pte_num_rings;
- ring = adev->vm_manager.vm_pte_rings[ring_instance];
- rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
- r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL);
+ r = drm_sched_entity_init(&vm->entity, adev->vm_manager.vm_pte_rqs,
+ adev->vm_manager.vm_pte_num_rqs, NULL);
if (r)
return r;
@@ -2927,7 +2920,6 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
adev->vm_manager.seqno[i] = 0;
- atomic_set(&adev->vm_manager.vm_pte_next_ring, 0);
spin_lock_init(&adev->vm_manager.prt_lock);
atomic_set(&adev->vm_manager.num_prt_users, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 9b0eafd64363..ab1d23e4b8ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -265,10 +265,9 @@ struct amdgpu_vm_manager {
/* vram base address for page table entry */
u64 vram_base_offset;
/* vm pte handling */
- const struct amdgpu_vm_pte_funcs *vm_pte_funcs;
- struct amdgpu_ring *vm_pte_rings[AMDGPU_MAX_RINGS];
- unsigned vm_pte_num_rings;
- atomic_t vm_pte_next_ring;
+ const struct amdgpu_vm_pte_funcs *vm_pte_funcs;
+ struct drm_sched_rq *vm_pte_rqs[AMDGPU_MAX_RINGS];
+ unsigned vm_pte_num_rqs;
/* partial resident texture handling */
spinlock_t prt_lock;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index d0fa2aac2388..154b1499b07e 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -1386,15 +1386,17 @@ static const struct amdgpu_vm_pte_funcs cik_sdma_vm_pte_funcs = {
static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev)
{
+ struct drm_gpu_scheduler *sched;
unsigned i;
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ sched = &adev->sdma.instance[i].ring.sched;
+ adev->vm_manager.vm_pte_rqs[i] =
+ &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+ }
+ adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 15ae4bc9c072..c403bdf8ad70 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -1312,15 +1312,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v2_4_vm_pte_funcs = {
static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev)
{
+ struct drm_gpu_scheduler *sched;
unsigned i;
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ sched = &adev->sdma.instance[i].ring.sched;
+ adev->vm_manager.vm_pte_rqs[i] =
+ &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+ }
+ adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 1e07ff274d73..2677d6a1bf42 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -1752,15 +1752,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v3_0_vm_pte_funcs = {
static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev)
{
+ struct drm_gpu_scheduler *sched;
unsigned i;
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ sched = &adev->sdma.instance[i].ring.sched;
+ adev->vm_manager.vm_pte_rqs[i] =
+ &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+ }
+ adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 2e61d3a63ed0..ee0213edca8e 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -1799,15 +1799,17 @@ static const struct amdgpu_vm_pte_funcs sdma_v4_0_vm_pte_funcs = {
static void sdma_v4_0_set_vm_pte_funcs(struct amdgpu_device *adev)
{
+ struct drm_gpu_scheduler *sched;
unsigned i;
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v4_0_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ sched = &adev->sdma.instance[i].ring.sched;
+ adev->vm_manager.vm_pte_rqs[i] =
+ &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+ }
+ adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dma.c b/drivers/gpu/drm/amd/amdgpu/si_dma.c
index b75d901ba3c4..fafaf259b17b 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dma.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dma.c
@@ -879,15 +879,17 @@ static const struct amdgpu_vm_pte_funcs si_dma_vm_pte_funcs = {
static void si_dma_set_vm_pte_funcs(struct amdgpu_device *adev)
{
+ struct drm_gpu_scheduler *sched;
unsigned i;
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &si_dma_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ sched = &adev->sdma.instance[i].ring.sched;
+ adev->vm_manager.vm_pte_rqs[i] =
+ &sched->sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+ }
+ adev->vm_manager.vm_pte_num_rqs = adev->sdma.num_instances;
}
}
--
2.17.1
|
