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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
*/
#include <media/v4l2-mem2mem.h>
#include "iris_buffer.h"
#include "iris_instance.h"
#define PIXELS_4K 4096
#define MAX_WIDTH 4096
#define MAX_HEIGHT 2304
#define Y_STRIDE_ALIGN 128
#define UV_STRIDE_ALIGN 128
#define Y_SCANLINE_ALIGN 32
#define UV_SCANLINE_ALIGN 16
#define UV_SCANLINE_ALIGN_QC08C 32
#define META_STRIDE_ALIGNED 64
#define META_SCANLINE_ALIGNED 16
#define NUM_MBS_4K (DIV_ROUND_UP(MAX_WIDTH, 16) * DIV_ROUND_UP(MAX_HEIGHT, 16))
/*
* NV12:
* YUV 4:2:0 image with a plane of 8 bit Y samples followed
* by an interleaved U/V plane containing 8 bit 2x2 subsampled
* colour difference samples.
*
* <-Y/UV_Stride (aligned to 128)->
* <------- Width ------->
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . ^ ^
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . | |
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . Height |
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . | y_scanlines (aligned to 32)
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . | |
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . | |
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . | |
* Y Y Y Y Y Y Y Y Y Y Y Y . . . . V |
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . V
* U V U V U V U V U V U V . . . . ^
* U V U V U V U V U V U V . . . . |
* U V U V U V U V U V U V . . . . |
* U V U V U V U V U V U V . . . . uv_scanlines (aligned to 16)
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . V
* . . . . . . . . . . . . . . . . --> Buffer size aligned to 4K
*
* y_stride : Width aligned to 128
* uv_stride : Width aligned to 128
* y_scanlines: Height aligned to 32
* uv_scanlines: Height/2 aligned to 16
* Total size = align((y_stride * y_scanlines
* + uv_stride * uv_scanlines , 4096)
*
* Note: All the alignments are hardware requirements.
*/
static u32 iris_yuv_buffer_size_nv12(struct iris_inst *inst)
{
u32 y_plane, uv_plane, y_stride, uv_stride, y_scanlines, uv_scanlines;
struct v4l2_format *f = inst->fmt_dst;
y_stride = ALIGN(f->fmt.pix_mp.width, Y_STRIDE_ALIGN);
uv_stride = ALIGN(f->fmt.pix_mp.width, UV_STRIDE_ALIGN);
y_scanlines = ALIGN(f->fmt.pix_mp.height, Y_SCANLINE_ALIGN);
uv_scanlines = ALIGN((f->fmt.pix_mp.height + 1) >> 1, UV_SCANLINE_ALIGN);
y_plane = y_stride * y_scanlines;
uv_plane = uv_stride * uv_scanlines;
return ALIGN(y_plane + uv_plane, PIXELS_4K);
}
/*
* QC08C:
* Compressed Macro-tile format for NV12.
* Contains 4 planes in the following order -
* (A) Y_Meta_Plane
* (B) Y_UBWC_Plane
* (C) UV_Meta_Plane
* (D) UV_UBWC_Plane
*
* Y_Meta_Plane consists of meta information to decode compressed
* tile data in Y_UBWC_Plane.
* Y_UBWC_Plane consists of Y data in compressed macro-tile format.
* UBWC decoder block will use the Y_Meta_Plane data together with
* Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples.
*
* UV_Meta_Plane consists of meta information to decode compressed
* tile data in UV_UBWC_Plane.
* UV_UBWC_Plane consists of UV data in compressed macro-tile format.
* UBWC decoder block will use UV_Meta_Plane data together with
* UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2
* subsampled color difference samples.
*
* Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
* and randomly accessible. There is no dependency between tiles.
*
* <----- y_meta_stride ----> (aligned to 64)
* <-------- Width ------>
* M M M M M M M M M M M M . . ^ ^
* M M M M M M M M M M M M . . | |
* M M M M M M M M M M M M . . Height |
* M M M M M M M M M M M M . . | y_meta_scanlines (aligned to 16)
* M M M M M M M M M M M M . . | |
* M M M M M M M M M M M M . . | |
* M M M M M M M M M M M M . . | |
* M M M M M M M M M M M M . . V |
* . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . -------> Buffer size aligned to 4k
* . . . . . . . . . . . . . . V
* <--Compressed tile y_stride---> (aligned to 128)
* <------- Width ------->
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . ^ ^
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . | |
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . Height |
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . | Macro_tile y_scanlines (aligned to 32)
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . | |
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . | |
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . | |
* Y* Y* Y* Y* Y* Y* Y* Y* . . . . V |
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k
* . . . . . . . . . . . . . . . . V
* <----- uv_meta_stride ----> (aligned to 64)
* M M M M M M M M M M M M . . ^
* M M M M M M M M M M M M . . |
* M M M M M M M M M M M M . . |
* M M M M M M M M M M M M . . uv_meta_scanlines (aligned to 16)
* . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . V
* . . . . . . . . . . . . . . -------> Buffer size aligned to 4k
* <--Compressed tile uv_stride---> (aligned to 128)
* U* V* U* V* U* V* U* V* . . . . ^
* U* V* U* V* U* V* U* V* . . . . |
* U* V* U* V* U* V* U* V* . . . . |
* U* V* U* V* U* V* U* V* . . . . uv_scanlines (aligned to 32)
* . . . . . . . . . . . . . . . . |
* . . . . . . . . . . . . . . . . V
* . . . . . . . . . . . . . . . . -------> Buffer size aligned to 4k
*
* y_stride: width aligned to 128
* uv_stride: width aligned to 128
* y_scanlines: height aligned to 32
* uv_scanlines: height aligned to 32
* y_plane: buffer size aligned to 4096
* uv_plane: buffer size aligned to 4096
* y_meta_stride: width aligned to 64
* y_meta_scanlines: height aligned to 16
* y_meta_plane: buffer size aligned to 4096
* uv_meta_stride: width aligned to 64
* uv_meta_scanlines: height aligned to 16
* uv_meta_plane: buffer size aligned to 4096
*
* Total size = align( y_plane + uv_plane +
* y_meta_plane + uv_meta_plane, 4096)
*
* Note: All the alignments are hardware requirements.
*/
static u32 iris_yuv_buffer_size_qc08c(struct iris_inst *inst)
{
u32 y_plane, uv_plane, y_stride, uv_stride;
struct v4l2_format *f = inst->fmt_dst;
u32 uv_meta_stride, uv_meta_plane;
u32 y_meta_stride, y_meta_plane;
y_meta_stride = ALIGN(DIV_ROUND_UP(f->fmt.pix_mp.width, META_STRIDE_ALIGNED >> 1),
META_STRIDE_ALIGNED);
y_meta_plane = y_meta_stride * ALIGN(DIV_ROUND_UP(f->fmt.pix_mp.height,
META_SCANLINE_ALIGNED >> 1),
META_SCANLINE_ALIGNED);
y_meta_plane = ALIGN(y_meta_plane, PIXELS_4K);
y_stride = ALIGN(f->fmt.pix_mp.width, Y_STRIDE_ALIGN);
y_plane = ALIGN(y_stride * ALIGN(f->fmt.pix_mp.height, Y_SCANLINE_ALIGN), PIXELS_4K);
uv_meta_stride = ALIGN(DIV_ROUND_UP(f->fmt.pix_mp.width / 2, META_STRIDE_ALIGNED >> 2),
META_STRIDE_ALIGNED);
uv_meta_plane = uv_meta_stride * ALIGN(DIV_ROUND_UP(f->fmt.pix_mp.height / 2,
META_SCANLINE_ALIGNED >> 1),
META_SCANLINE_ALIGNED);
uv_meta_plane = ALIGN(uv_meta_plane, PIXELS_4K);
uv_stride = ALIGN(f->fmt.pix_mp.width, UV_STRIDE_ALIGN);
uv_plane = ALIGN(uv_stride * ALIGN(f->fmt.pix_mp.height / 2, UV_SCANLINE_ALIGN_QC08C),
PIXELS_4K);
return ALIGN(y_meta_plane + y_plane + uv_meta_plane + uv_plane, PIXELS_4K);
}
static u32 iris_bitstream_buffer_size(struct iris_inst *inst)
{
struct platform_inst_caps *caps = inst->core->iris_platform_data->inst_caps;
u32 base_res_mbs = NUM_MBS_4K;
u32 frame_size, num_mbs;
u32 div_factor = 2;
num_mbs = iris_get_mbpf(inst);
if (num_mbs > NUM_MBS_4K) {
div_factor = 4;
base_res_mbs = caps->max_mbpf;
}
/*
* frame_size = YUVsize / div_factor
* where YUVsize = resolution_in_MBs * MBs_in_pixel * 3 / 2
*/
frame_size = base_res_mbs * (16 * 16) * 3 / 2 / div_factor;
return ALIGN(frame_size, PIXELS_4K);
}
int iris_get_buffer_size(struct iris_inst *inst,
enum iris_buffer_type buffer_type)
{
switch (buffer_type) {
case BUF_INPUT:
return iris_bitstream_buffer_size(inst);
case BUF_OUTPUT:
return iris_yuv_buffer_size_nv12(inst);
case BUF_DPB:
return iris_yuv_buffer_size_qc08c(inst);
default:
return 0;
}
}
void iris_vb2_queue_error(struct iris_inst *inst)
{
struct v4l2_m2m_ctx *m2m_ctx = inst->m2m_ctx;
struct vb2_queue *q;
q = v4l2_m2m_get_src_vq(m2m_ctx);
vb2_queue_error(q);
q = v4l2_m2m_get_dst_vq(m2m_ctx);
vb2_queue_error(q);
}
|
