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
|
/*
* Copyright (c) 2015, NVIDIA CORPORATION. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#include <subdev/fb.h>
#include <core/mm.h>
#include <core/device.h>
#ifdef __KERNEL__
#include <linux/dma-attrs.h>
#endif
#include "priv.h"
struct gk20a_instobj_priv {
struct nvkm_instobj base;
/* Must be second member here - see nouveau_gpuobj_map_vm() */
struct nvkm_mem *mem;
/* Pointed by mem */
struct nvkm_mem _mem;
void *cpuaddr;
dma_addr_t handle;
struct dma_attrs attrs;
struct nvkm_mm_node r;
};
struct gk20a_instmem_priv {
struct nvkm_instmem base;
spinlock_t lock;
u64 addr;
};
static u32
gk20a_instobj_rd32(struct nvkm_object *object, u64 offset)
{
struct gk20a_instmem_priv *priv = (void *)nvkm_instmem(object);
struct gk20a_instobj_priv *node = (void *)object;
unsigned long flags;
u64 base = (node->mem->offset + offset) & 0xffffff00000ULL;
u64 addr = (node->mem->offset + offset) & 0x000000fffffULL;
u32 data;
spin_lock_irqsave(&priv->lock, flags);
if (unlikely(priv->addr != base)) {
nv_wr32(priv, 0x001700, base >> 16);
priv->addr = base;
}
data = nv_rd32(priv, 0x700000 + addr);
spin_unlock_irqrestore(&priv->lock, flags);
return data;
}
static void
gk20a_instobj_wr32(struct nvkm_object *object, u64 offset, u32 data)
{
struct gk20a_instmem_priv *priv = (void *)nvkm_instmem(object);
struct gk20a_instobj_priv *node = (void *)object;
unsigned long flags;
u64 base = (node->mem->offset + offset) & 0xffffff00000ULL;
u64 addr = (node->mem->offset + offset) & 0x000000fffffULL;
spin_lock_irqsave(&priv->lock, flags);
if (unlikely(priv->addr != base)) {
nv_wr32(priv, 0x001700, base >> 16);
priv->addr = base;
}
nv_wr32(priv, 0x700000 + addr, data);
spin_unlock_irqrestore(&priv->lock, flags);
}
static void
gk20a_instobj_dtor(struct nvkm_object *object)
{
struct gk20a_instobj_priv *node = (void *)object;
struct gk20a_instmem_priv *priv = (void *)nvkm_instmem(node);
struct device *dev = nv_device_base(nv_device(priv));
if (unlikely(!node->handle))
return;
dma_free_attrs(dev, node->mem->size << PAGE_SHIFT, node->cpuaddr,
node->handle, &node->attrs);
nvkm_instobj_destroy(&node->base);
}
static int
gk20a_instobj_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
struct nvkm_oclass *oclass, void *data, u32 _size,
struct nvkm_object **pobject)
{
struct nvkm_instobj_args *args = data;
struct gk20a_instmem_priv *priv = (void *)nvkm_instmem(parent);
struct device *dev = nv_device_base(nv_device(priv));
struct gk20a_instobj_priv *node;
u32 size, align;
u32 npages;
int ret;
nv_debug(parent, "%s: size: %x align: %x\n", __func__,
args->size, args->align);
size = max((args->size + 4095) & ~4095, (u32)4096);
align = max((args->align + 4095) & ~4095, (u32)4096);
npages = size >> PAGE_SHIFT;
ret = nvkm_instobj_create_(parent, engine, oclass, sizeof(*node),
(void **)&node);
*pobject = nv_object(node);
if (ret)
return ret;
node->mem = &node->_mem;
init_dma_attrs(&node->attrs);
/*
* We will access this memory through PRAMIN and thus do not need a
* consistent CPU pointer
*/
dma_set_attr(DMA_ATTR_NON_CONSISTENT, &node->attrs);
dma_set_attr(DMA_ATTR_WEAK_ORDERING, &node->attrs);
dma_set_attr(DMA_ATTR_WRITE_COMBINE, &node->attrs);
dma_set_attr(DMA_ATTR_NO_KERNEL_MAPPING, &node->attrs);
node->cpuaddr = dma_alloc_attrs(dev, npages << PAGE_SHIFT,
&node->handle, GFP_KERNEL,
&node->attrs);
if (!node->cpuaddr) {
nv_error(priv, "cannot allocate DMA memory\n");
return -ENOMEM;
}
/* alignment check */
if (unlikely(node->handle & (align - 1)))
nv_warn(priv, "memory not aligned as requested: %pad (0x%x)\n",
&node->handle, align);
node->mem->offset = node->handle;
node->mem->size = size >> 12;
node->mem->memtype = 0;
node->mem->page_shift = 12;
INIT_LIST_HEAD(&node->mem->regions);
node->r.type = 12;
node->r.offset = node->handle >> 12;
node->r.length = npages;
list_add_tail(&node->r.rl_entry, &node->mem->regions);
node->base.addr = node->mem->offset;
node->base.size = size;
nv_debug(parent, "alloc size: 0x%x, align: 0x%x, gaddr: 0x%llx\n",
size, align, node->mem->offset);
return 0;
}
static struct nvkm_instobj_impl
gk20a_instobj_oclass = {
.base.ofuncs = &(struct nvkm_ofuncs) {
.ctor = gk20a_instobj_ctor,
.dtor = gk20a_instobj_dtor,
.init = _nvkm_instobj_init,
.fini = _nvkm_instobj_fini,
.rd32 = gk20a_instobj_rd32,
.wr32 = gk20a_instobj_wr32,
},
};
static int
gk20a_instmem_fini(struct nvkm_object *object, bool suspend)
{
struct gk20a_instmem_priv *priv = (void *)object;
priv->addr = ~0ULL;
return nvkm_instmem_fini(&priv->base, suspend);
}
static int
gk20a_instmem_ctor(struct nvkm_object *parent, struct nvkm_object *engine,
struct nvkm_oclass *oclass, void *data, u32 size,
struct nvkm_object **pobject)
{
struct gk20a_instmem_priv *priv;
int ret;
ret = nvkm_instmem_create(parent, engine, oclass, &priv);
*pobject = nv_object(priv);
if (ret)
return ret;
spin_lock_init(&priv->lock);
return 0;
}
struct nvkm_oclass *
gk20a_instmem_oclass = &(struct nvkm_instmem_impl) {
.base.handle = NV_SUBDEV(INSTMEM, 0xea),
.base.ofuncs = &(struct nvkm_ofuncs) {
.ctor = gk20a_instmem_ctor,
.dtor = _nvkm_instmem_dtor,
.init = _nvkm_instmem_init,
.fini = gk20a_instmem_fini,
},
.instobj = &gk20a_instobj_oclass.base,
}.base;
|
