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
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
|
/*
* Copyright(c) 2011-2016 Intel 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 (including the next
* paragraph) 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.
*
* Authors:
* Eddie Dong <eddie.dong@intel.com>
* Kevin Tian <kevin.tian@intel.com>
*
* Contributors:
* Zhi Wang <zhi.a.wang@intel.com>
* Changbin Du <changbin.du@intel.com>
* Zhenyu Wang <zhenyuw@linux.intel.com>
* Tina Zhang <tina.zhang@intel.com>
* Bing Niu <bing.niu@intel.com>
*
*/
#include "i915_drv.h"
#include "gvt.h"
#include "trace.h"
struct render_mmio {
int ring_id;
i915_reg_t reg;
u32 mask;
bool in_context;
u32 value;
};
static struct render_mmio gen8_render_mmio_list[] __cacheline_aligned = {
{RCS, _MMIO(0x229c), 0xffff, false},
{RCS, _MMIO(0x2248), 0x0, false},
{RCS, _MMIO(0x2098), 0x0, false},
{RCS, _MMIO(0x20c0), 0xffff, true},
{RCS, _MMIO(0x24d0), 0, false},
{RCS, _MMIO(0x24d4), 0, false},
{RCS, _MMIO(0x24d8), 0, false},
{RCS, _MMIO(0x24dc), 0, false},
{RCS, _MMIO(0x24e0), 0, false},
{RCS, _MMIO(0x24e4), 0, false},
{RCS, _MMIO(0x24e8), 0, false},
{RCS, _MMIO(0x24ec), 0, false},
{RCS, _MMIO(0x24f0), 0, false},
{RCS, _MMIO(0x24f4), 0, false},
{RCS, _MMIO(0x24f8), 0, false},
{RCS, _MMIO(0x24fc), 0, false},
{RCS, _MMIO(0x7004), 0xffff, true},
{RCS, _MMIO(0x7008), 0xffff, true},
{RCS, _MMIO(0x7000), 0xffff, true},
{RCS, _MMIO(0x7010), 0xffff, true},
{RCS, _MMIO(0x7300), 0xffff, true},
{RCS, _MMIO(0x83a4), 0xffff, true},
{BCS, _MMIO(0x2229c), 0xffff, false},
{BCS, _MMIO(0x2209c), 0xffff, false},
{BCS, _MMIO(0x220c0), 0xffff, false},
{BCS, _MMIO(0x22098), 0x0, false},
{BCS, _MMIO(0x22028), 0x0, false},
};
static struct render_mmio gen9_render_mmio_list[] __cacheline_aligned = {
{RCS, _MMIO(0x229c), 0xffff, false},
{RCS, _MMIO(0x2248), 0x0, false},
{RCS, _MMIO(0x2098), 0x0, false},
{RCS, _MMIO(0x20c0), 0xffff, true},
{RCS, _MMIO(0x24d0), 0, false},
{RCS, _MMIO(0x24d4), 0, false},
{RCS, _MMIO(0x24d8), 0, false},
{RCS, _MMIO(0x24dc), 0, false},
{RCS, _MMIO(0x24e0), 0, false},
{RCS, _MMIO(0x24e4), 0, false},
{RCS, _MMIO(0x24e8), 0, false},
{RCS, _MMIO(0x24ec), 0, false},
{RCS, _MMIO(0x24f0), 0, false},
{RCS, _MMIO(0x24f4), 0, false},
{RCS, _MMIO(0x24f8), 0, false},
{RCS, _MMIO(0x24fc), 0, false},
{RCS, _MMIO(0x7004), 0xffff, true},
{RCS, _MMIO(0x7008), 0xffff, true},
{RCS, _MMIO(0x7000), 0xffff, true},
{RCS, _MMIO(0x7010), 0xffff, true},
{RCS, _MMIO(0x7300), 0xffff, true},
{RCS, _MMIO(0x83a4), 0xffff, true},
{RCS, _MMIO(0x40e0), 0, false},
{RCS, _MMIO(0x40e4), 0, false},
{RCS, _MMIO(0x2580), 0xffff, true},
{RCS, _MMIO(0x7014), 0xffff, true},
{RCS, _MMIO(0x20ec), 0xffff, false},
{RCS, _MMIO(0xb118), 0, false},
{RCS, _MMIO(0xe100), 0xffff, true},
{RCS, _MMIO(0xe180), 0xffff, true},
{RCS, _MMIO(0xe184), 0xffff, true},
{RCS, _MMIO(0xe188), 0xffff, true},
{RCS, _MMIO(0xe194), 0xffff, true},
{RCS, _MMIO(0x4de0), 0, false},
{RCS, _MMIO(0x4de4), 0, false},
{RCS, _MMIO(0x4de8), 0, false},
{RCS, _MMIO(0x4dec), 0, false},
{RCS, _MMIO(0x4df0), 0, false},
{RCS, _MMIO(0x4df4), 0, false},
{BCS, _MMIO(0x2229c), 0xffff, false},
{BCS, _MMIO(0x2209c), 0xffff, false},
{BCS, _MMIO(0x220c0), 0xffff, false},
{BCS, _MMIO(0x22098), 0x0, false},
{BCS, _MMIO(0x22028), 0x0, false},
{VCS2, _MMIO(0x1c028), 0xffff, false},
{VECS, _MMIO(0x1a028), 0xffff, false},
{RCS, _MMIO(0x7304), 0xffff, true},
{RCS, _MMIO(0x2248), 0x0, false},
{RCS, _MMIO(0x940c), 0x0, false},
{RCS, _MMIO(0x4ab8), 0x0, false},
{RCS, _MMIO(0x4ab0), 0x0, false},
{RCS, _MMIO(0x20d4), 0x0, false},
{RCS, _MMIO(0xb004), 0x0, false},
{RCS, _MMIO(0x20a0), 0x0, false},
{RCS, _MMIO(0x20e4), 0xffff, false},
};
static u32 gen9_render_mocs[I915_NUM_ENGINES][64];
static u32 gen9_render_mocs_L3[32];
static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
enum forcewake_domains fw;
i915_reg_t reg;
u32 regs[] = {
[RCS] = 0x4260,
[VCS] = 0x4264,
[VCS2] = 0x4268,
[BCS] = 0x426c,
[VECS] = 0x4270,
};
if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
return;
if (!test_and_clear_bit(ring_id, (void *)vgpu->tlb_handle_pending))
return;
reg = _MMIO(regs[ring_id]);
/* WaForceWakeRenderDuringMmioTLBInvalidate:skl
* we need to put a forcewake when invalidating RCS TLB caches,
* otherwise device can go to RC6 state and interrupt invalidation
* process
*/
fw = intel_uncore_forcewake_for_reg(dev_priv, reg,
FW_REG_READ | FW_REG_WRITE);
if (ring_id == RCS && (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)))
fw |= FORCEWAKE_RENDER;
intel_uncore_forcewake_get(dev_priv, fw);
I915_WRITE_FW(reg, 0x1);
if (wait_for_atomic((I915_READ_FW(reg) == 0), 50))
gvt_vgpu_err("timeout in invalidate ring (%d) tlb\n", ring_id);
else
vgpu_vreg(vgpu, regs[ring_id]) = 0;
intel_uncore_forcewake_put(dev_priv, fw);
gvt_dbg_core("invalidate TLB for ring %d\n", ring_id);
}
static void load_mocs(struct intel_vgpu *vgpu, int ring_id)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
i915_reg_t offset, l3_offset;
u32 regs[] = {
[RCS] = 0xc800,
[VCS] = 0xc900,
[VCS2] = 0xca00,
[BCS] = 0xcc00,
[VECS] = 0xcb00,
};
int i;
if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
return;
offset.reg = regs[ring_id];
for (i = 0; i < 64; i++) {
gen9_render_mocs[ring_id][i] = I915_READ(offset);
I915_WRITE(offset, vgpu_vreg(vgpu, offset));
POSTING_READ(offset);
offset.reg += 4;
}
if (ring_id == RCS) {
l3_offset.reg = 0xb020;
for (i = 0; i < 32; i++) {
gen9_render_mocs_L3[i] = I915_READ(l3_offset);
I915_WRITE(l3_offset, vgpu_vreg(vgpu, l3_offset));
POSTING_READ(l3_offset);
l3_offset.reg += 4;
}
}
}
static void restore_mocs(struct intel_vgpu *vgpu, int ring_id)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
i915_reg_t offset, l3_offset;
u32 regs[] = {
[RCS] = 0xc800,
[VCS] = 0xc900,
[VCS2] = 0xca00,
[BCS] = 0xcc00,
[VECS] = 0xcb00,
};
int i;
if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
return;
offset.reg = regs[ring_id];
for (i = 0; i < 64; i++) {
vgpu_vreg(vgpu, offset) = I915_READ(offset);
I915_WRITE(offset, gen9_render_mocs[ring_id][i]);
POSTING_READ(offset);
offset.reg += 4;
}
if (ring_id == RCS) {
l3_offset.reg = 0xb020;
for (i = 0; i < 32; i++) {
vgpu_vreg(vgpu, l3_offset) = I915_READ(l3_offset);
I915_WRITE(l3_offset, gen9_render_mocs_L3[i]);
POSTING_READ(l3_offset);
l3_offset.reg += 4;
}
}
}
#define CTX_CONTEXT_CONTROL_VAL 0x03
/* Switch ring mmio values (context) from host to a vgpu. */
static void switch_mmio_to_vgpu(struct intel_vgpu *vgpu, int ring_id)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
struct render_mmio *mmio;
u32 v;
int i, array_size;
u32 *reg_state = vgpu->shadow_ctx->engine[ring_id].lrc_reg_state;
u32 ctx_ctrl = reg_state[CTX_CONTEXT_CONTROL_VAL];
u32 inhibit_mask =
_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
if (IS_SKYLAKE(vgpu->gvt->dev_priv)
|| IS_KABYLAKE(vgpu->gvt->dev_priv)) {
mmio = gen9_render_mmio_list;
array_size = ARRAY_SIZE(gen9_render_mmio_list);
load_mocs(vgpu, ring_id);
} else {
mmio = gen8_render_mmio_list;
array_size = ARRAY_SIZE(gen8_render_mmio_list);
}
for (i = 0; i < array_size; i++, mmio++) {
if (mmio->ring_id != ring_id)
continue;
mmio->value = I915_READ(mmio->reg);
/*
* if it is an inhibit context, load in_context mmio
* into HW by mmio write. If it is not, skip this mmio
* write.
*/
if (mmio->in_context &&
((ctx_ctrl & inhibit_mask) != inhibit_mask) &&
i915.enable_execlists)
continue;
if (mmio->mask)
v = vgpu_vreg(vgpu, mmio->reg) | (mmio->mask << 16);
else
v = vgpu_vreg(vgpu, mmio->reg);
I915_WRITE(mmio->reg, v);
POSTING_READ(mmio->reg);
trace_render_mmio(vgpu->id, "load",
i915_mmio_reg_offset(mmio->reg),
mmio->value, v);
}
handle_tlb_pending_event(vgpu, ring_id);
}
/* Switch ring mmio values (context) from vgpu to host. */
static void switch_mmio_to_host(struct intel_vgpu *vgpu, int ring_id)
{
struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
struct render_mmio *mmio;
u32 v;
int i, array_size;
if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
mmio = gen9_render_mmio_list;
array_size = ARRAY_SIZE(gen9_render_mmio_list);
restore_mocs(vgpu, ring_id);
} else {
mmio = gen8_render_mmio_list;
array_size = ARRAY_SIZE(gen8_render_mmio_list);
}
for (i = 0; i < array_size; i++, mmio++) {
if (mmio->ring_id != ring_id)
continue;
vgpu_vreg(vgpu, mmio->reg) = I915_READ(mmio->reg);
if (mmio->mask) {
vgpu_vreg(vgpu, mmio->reg) &= ~(mmio->mask << 16);
v = mmio->value | (mmio->mask << 16);
} else
v = mmio->value;
I915_WRITE(mmio->reg, v);
POSTING_READ(mmio->reg);
trace_render_mmio(vgpu->id, "restore",
i915_mmio_reg_offset(mmio->reg),
mmio->value, v);
}
}
/**
* intel_gvt_switch_render_mmio - switch mmio context of specific engine
* @pre: the last vGPU that own the engine
* @next: the vGPU to switch to
* @ring_id: specify the engine
*
* If pre is null indicates that host own the engine. If next is null
* indicates that we are switching to host workload.
*/
void intel_gvt_switch_mmio(struct intel_vgpu *pre,
struct intel_vgpu *next, int ring_id)
{
if (WARN_ON(!pre && !next))
return;
gvt_dbg_render("switch ring %d from %s to %s\n", ring_id,
pre ? "vGPU" : "host", next ? "vGPU" : "HOST");
/**
* TODO: Optimize for vGPU to vGPU switch by merging
* switch_mmio_to_host() and switch_mmio_to_vgpu().
*/
if (pre)
switch_mmio_to_host(pre, ring_id);
if (next)
switch_mmio_to_vgpu(next, ring_id);
}
|
