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
|
From 600319c61505c30dcb4f72eea9d23aa94c8ea50d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Wed, 16 Aug 2017 11:13:48 +0200
Subject: [PATCH 1791/4131] drm/amdgpu: add support for per VM BOs v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Per VM BOs are handled like VM PDs and PTs. They are always valid and don't
need to be specified in the BO lists.
v2: validate PDs/PTs first
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 79 ++++++++++++++++++++++++----------
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 3 +-
3 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 8072f2f..1b903a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -865,7 +865,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
}
- r = amdgpu_vm_clear_moved(adev, vm, &p->job->sync);
+ r = amdgpu_vm_handle_moved(adev, vm, &p->job->sync);
if (amdgpu_vm_debug && p->bo_list) {
/* Invalidate all BOs to test for userspace bugs */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 13ab876..904f67b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -195,14 +195,18 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
spin_unlock(&glob->lru_lock);
}
- if (vm->use_cpu_for_update) {
+ if (bo->tbo.type == ttm_bo_type_kernel &&
+ vm->use_cpu_for_update) {
r = amdgpu_bo_kmap(bo, NULL);
if (r)
return r;
}
spin_lock(&vm->status_lock);
- list_move(&bo_base->vm_status, &vm->relocated);
+ if (bo->tbo.type != ttm_bo_type_kernel)
+ list_move(&bo_base->vm_status, &vm->moved);
+ else
+ list_move(&bo_base->vm_status, &vm->relocated);
}
spin_unlock(&vm->status_lock);
@@ -2013,20 +2017,23 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
}
/**
- * amdgpu_vm_clear_moved - clear moved BOs in the PT
+ * amdgpu_vm_handle_moved - handle moved BOs in the PT
*
* @adev: amdgpu_device pointer
* @vm: requested vm
+ * @sync: sync object to add fences to
*
- * Make sure all moved BOs are cleared in the PT.
+ * Make sure all BOs which are moved are updated in the PTs.
* Returns 0 for success.
*
- * PTs have to be reserved and mutex must be locked!
+ * PTs have to be reserved!
*/
-int amdgpu_vm_clear_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
- struct amdgpu_sync *sync)
+int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
+ struct amdgpu_vm *vm,
+ struct amdgpu_sync *sync)
{
struct amdgpu_bo_va *bo_va = NULL;
+ bool clear;
int r = 0;
spin_lock(&vm->status_lock);
@@ -2035,7 +2042,10 @@ int amdgpu_vm_clear_moved(struct amdgpu_device *adev, struct amdgpu_vm *vm,
struct amdgpu_bo_va, base.vm_status);
spin_unlock(&vm->status_lock);
- r = amdgpu_vm_bo_update(adev, bo_va, true);
+ /* Per VM BOs never need to bo cleared in the page tables */
+ clear = bo_va->base.bo->tbo.resv != vm->root.base.bo->tbo.resv;
+
+ r = amdgpu_vm_bo_update(adev, bo_va, clear);
if (r)
return r;
@@ -2087,6 +2097,37 @@ struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
return bo_va;
}
+
+/**
+ * amdgpu_vm_bo_insert_mapping - insert a new mapping
+ *
+ * @adev: amdgpu_device pointer
+ * @bo_va: bo_va to store the address
+ * @mapping: the mapping to insert
+ *
+ * Insert a new mapping into all structures.
+ */
+static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
+ struct amdgpu_bo_va *bo_va,
+ struct amdgpu_bo_va_mapping *mapping)
+{
+ struct amdgpu_vm *vm = bo_va->base.vm;
+ struct amdgpu_bo *bo = bo_va->base.bo;
+
+ list_add(&mapping->list, &bo_va->invalids);
+ amdgpu_vm_it_insert(mapping, &vm->va);
+
+ if (mapping->flags & AMDGPU_PTE_PRT)
+ amdgpu_vm_prt_get(adev);
+
+ if (bo && bo->tbo.resv == vm->root.base.bo->tbo.resv) {
+ spin_lock(&vm->status_lock);
+ list_move(&bo_va->base.vm_status, &vm->moved);
+ spin_unlock(&vm->status_lock);
+ }
+ trace_amdgpu_vm_bo_map(bo_va, mapping);
+}
+
/**
* amdgpu_vm_bo_map - map bo inside a vm
*
@@ -2138,18 +2179,12 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
if (!mapping)
return -ENOMEM;
- INIT_LIST_HEAD(&mapping->list);
mapping->start = saddr;
mapping->last = eaddr;
mapping->offset = offset;
mapping->flags = flags;
- list_add(&mapping->list, &bo_va->invalids);
- amdgpu_vm_it_insert(mapping, &vm->va);
-
- if (flags & AMDGPU_PTE_PRT)
- amdgpu_vm_prt_get(adev);
- trace_amdgpu_vm_bo_map(bo_va, mapping);
+ amdgpu_vm_bo_insert_map(adev, bo_va, mapping);
return 0;
}
@@ -2176,7 +2211,6 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
{
struct amdgpu_bo_va_mapping *mapping;
struct amdgpu_bo *bo = bo_va->base.bo;
- struct amdgpu_vm *vm = bo_va->base.vm;
uint64_t eaddr;
int r;
@@ -2210,12 +2244,7 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
mapping->offset = offset;
mapping->flags = flags;
- list_add(&mapping->list, &bo_va->invalids);
- amdgpu_vm_it_insert(mapping, &vm->va);
-
- if (flags & AMDGPU_PTE_PRT)
- amdgpu_vm_prt_get(adev);
- trace_amdgpu_vm_bo_map(bo_va, mapping);
+ amdgpu_vm_bo_insert_map(adev, bo_va, mapping);
return 0;
}
@@ -2430,7 +2459,11 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
bo_base->moved = true;
if (evicted && bo->tbo.resv == vm->root.base.bo->tbo.resv) {
spin_lock(&bo_base->vm->status_lock);
- list_move(&bo_base->vm_status, &vm->evicted);
+ if (bo->tbo.type == ttm_bo_type_kernel)
+ list_move(&bo_base->vm_status, &vm->evicted);
+ else
+ list_move_tail(&bo_base->vm_status,
+ &vm->evicted);
spin_unlock(&bo_base->vm->status_lock);
continue;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 415e659..8792e86 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -255,7 +255,8 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
struct amdgpu_vm *vm,
struct dma_fence **fence);
int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
- struct amdgpu_vm *vm);
+ struct amdgpu_vm *vm,
+ struct amdgpu_sync *sync);
int amdgpu_vm_bo_update(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
bool clear);
--
2.7.4
|
