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
|
From fe6b8b00e138be63714408057f957a245d3b0122 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>
Date: Tue, 5 Dec 2017 15:23:26 +0100
Subject: [PATCH 2968/4131] drm/amdgpu: implement 2+1 PD support for Raven v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Instead of falling back to 2 level and very limited address space use
2+1 PD support and 128TB + 512GB of virtual address space.
v2: cleanup defines, rebase on top of level enum
v3: fix inverted check in hardware setup
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-and-Tested-by: Chunming Zhou <david1.zhou@amd.com>
Conflicts:
drivers/gpu/drm/amd/amdgpu/amdgpu.h
Change-Id: Ib754b7fe1b0d7b75c8e493a9c2b1e212bb23892c
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 6 ++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 42 ++++++++++++++++++---------
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 26 ++++++++++++++---
drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 49 ++++++++++++++++++++------------
5 files changed, 89 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index d827b85..46e72fa 100755
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -558,6 +558,7 @@ struct amdgpu_mc {
u64 private_aperture_end;
/* protects concurrent invalidation */
spinlock_t invalidate_lock;
+ bool translate_further;
struct kfd_vm_fault_info *vm_fault_info;
atomic_t vm_fault_info_updated;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 5e8d115..189b5c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -74,6 +74,12 @@ struct amdgpu_bo_list_entry;
/* PDE is handled as PTE for VEGA10 */
#define AMDGPU_PDE_PTE (1ULL << 54)
+/* PTE is handled as PDE for VEGA10 (Translate Further) */
+#define AMDGPU_PTE_TF (1ULL << 56)
+
+/* PDE Block Fragment Size for VEGA10 */
+#define AMDGPU_PDE_BFS(a) ((uint64_t)a << 59)
+
/* VEGA10 only */
#define AMDGPU_PTE_MTYPE(a) ((uint64_t)a << 57)
#define AMDGPU_PTE_MTYPE_MASK AMDGPU_PTE_MTYPE(3ULL)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 1d392f1..56f5fe4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -143,8 +143,15 @@ static void gfxhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
WREG32_SOC15(GC, 0, mmVM_L2_CNTL2, tmp);
tmp = mmVM_L2_CNTL3_DEFAULT;
- tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
- tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ if (adev->mc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+ } else {
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ }
WREG32_SOC15(GC, 0, mmVM_L2_CNTL3, tmp);
tmp = mmVM_L2_CNTL4_DEFAULT;
@@ -182,31 +189,40 @@ static void gfxhub_v1_0_disable_identity_aperture(struct amdgpu_device *adev)
static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
{
- int i;
+ unsigned num_level, block_size;
uint32_t tmp;
+ int i;
+
+ num_level = adev->vm_manager.num_level;
+ block_size = adev->vm_manager.block_size;
+ if (adev->mc.translate_further)
+ num_level -= 1;
+ else
+ block_size -= 9;
for (i = 0; i <= 14; i++) {
tmp = RREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL, i);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH,
- adev->vm_manager.num_level);
+ num_level);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT,
+ 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- PAGE_TABLE_BLOCK_SIZE,
- adev->vm_manager.block_size - 9);
+ PAGE_TABLE_BLOCK_SIZE,
+ block_size);
/* Send no-retry XNACK on fault to suppress VM fault storm. */
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 5871379..d45aaef 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -476,6 +476,21 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
*addr = adev->vm_manager.vram_base_offset + *addr -
adev->mc.vram_start;
BUG_ON(*addr & 0xFFFF00000000003FULL);
+
+ if (!adev->mc.translate_further)
+ return;
+
+ if (level == AMDGPU_VM_PDB1) {
+ /* Set the block fragment size */
+ if (!(*flags & AMDGPU_PDE_PTE))
+ *flags |= AMDGPU_PDE_BFS(0x9);
+
+ } else if (level == AMDGPU_VM_PDB0) {
+ if (*flags & AMDGPU_PDE_PTE)
+ *flags &= ~AMDGPU_PDE_PTE;
+ else
+ *flags |= AMDGPU_PTE_TF;
+ }
}
static const struct amdgpu_gart_funcs gmc_v9_0_gart_funcs = {
@@ -778,11 +793,14 @@ static int gmc_v9_0_sw_init(void *handle)
switch (adev->asic_type) {
case CHIP_RAVEN:
adev->mc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
- if (adev->rev_id == 0x0 || adev->rev_id == 0x1)
+ if (adev->rev_id == 0x0 || adev->rev_id == 0x1) {
amdgpu_vm_adjust_size(adev, 256 * 1024, 9, 3, 48);
- else
- /* vm_size is 64GB for legacy 2-level page support */
- amdgpu_vm_adjust_size(adev, 64, 9, 1, 48);
+ } else {
+ /* vm_size is 128TB + 512GB for legacy 3-level page support */
+ amdgpu_vm_adjust_size(adev, 128 * 1024 + 512, 9, 2, 48);
+ adev->mc.translate_further =
+ adev->vm_manager.num_level > 1;
+ }
break;
case CHIP_VEGA10:
/* XXX Don't know how to get VRAM type yet. */
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 0c5a76f..ffd5b7e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -155,10 +155,15 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL2, tmp);
- tmp = mmVM_L2_CNTL3_DEFAULT;
- tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
- tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
- WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp);
+ if (adev->mc.translate_further) {
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 12);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+ } else {
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3, BANK_SELECT, 9);
+ tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
+ L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+ }
tmp = mmVM_L2_CNTL4_DEFAULT;
tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
@@ -196,32 +201,40 @@ static void mmhub_v1_0_disable_identity_aperture(struct amdgpu_device *adev)
static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
{
- int i;
+ unsigned num_level, block_size;
uint32_t tmp;
+ int i;
+
+ num_level = adev->vm_manager.num_level;
+ block_size = adev->vm_manager.block_size;
+ if (adev->mc.translate_further)
+ num_level -= 1;
+ else
+ block_size -= 9;
for (i = 0; i <= 14; i++) {
tmp = RREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL, i);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, ENABLE_CONTEXT, 1);
+ tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL, PAGE_TABLE_DEPTH,
+ num_level);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- ENABLE_CONTEXT, 1);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- PAGE_TABLE_DEPTH, adev->vm_manager.num_level);
- tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT,
+ 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ PDE0_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ VALID_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ READ_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ WRITE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
+ EXECUTE_PROTECTION_FAULT_ENABLE_DEFAULT, 1);
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
- PAGE_TABLE_BLOCK_SIZE,
- adev->vm_manager.block_size - 9);
+ PAGE_TABLE_BLOCK_SIZE,
+ block_size);
/* Send no-retry XNACK on fault to suppress VM fault storm. */
tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
--
2.7.4
|
