1/*
2 * Copyright 2011 Joakim Sindholt <opensource@zhasha.com>
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * on the rights to use, copy, modify, merge, publish, distribute, sub
8 * license, and/or sell copies of the Software, and to permit persons to whom
9 * the Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHOR(S) AND/OR THEIR SUPPLIERS BE LIABLE FOR ANY CLAIM,
19 * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
20 * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
21 * USE OR OTHER DEALINGS IN THE SOFTWARE. */
22
23#ifndef _NINE_PIXELSHADER9_H_
24#define _NINE_PIXELSHADER9_H_
25
26#include "iunknown.h"
27#include "nine_shader.h"
28#include "nine_state.h"
29#include "basetexture9.h"
30#include "nine_ff.h"
31#include "surface9.h"
32
33struct nine_lconstf;
34
35struct NinePixelShader9
36{
37    struct NineUnknown base;
38    struct nine_shader_variant variant;
39
40    struct {
41        const DWORD *tokens;
42        DWORD size;
43        uint8_t version; /* (major << 4) | minor */
44    } byte_code;
45
46    uint8_t bumpenvmat_needed;
47    uint16_t sampler_mask;
48    uint8_t rt_mask;
49
50    boolean int_slots_used[NINE_MAX_CONST_I];
51    boolean bool_slots_used[NINE_MAX_CONST_B];
52
53    unsigned const_int_slots;
54    unsigned const_bool_slots;
55
56    struct nine_shader_constant_combination *c_combinations;
57
58    uint64_t ff_key[6];
59    void *ff_cso;
60
61    uint64_t last_key;
62    void *last_cso;
63    unsigned *last_const_ranges;
64    unsigned last_const_used_size; /* in bytes */
65
66    uint64_t next_key;
67};
68static inline struct NinePixelShader9 *
69NinePixelShader9( void *data )
70{
71    return (struct NinePixelShader9 *)data;
72}
73
74static inline BOOL
75NinePixelShader9_UpdateKey( struct NinePixelShader9 *ps,
76                            struct nine_context *context )
77{
78    uint16_t samplers_shadow;
79    uint16_t samplers_fetch4;
80    uint16_t samplers_ps1_types;
81    uint8_t projected;
82    uint64_t key;
83    BOOL res;
84
85    samplers_shadow = (uint16_t)((context->samplers_shadow & NINE_PS_SAMPLERS_MASK) >> NINE_SAMPLER_PS(0));
86    samplers_fetch4 = (uint16_t)((context->samplers_fetch4 & NINE_PS_SAMPLERS_MASK) >> NINE_SAMPLER_PS(0));
87    key = samplers_shadow & ps->sampler_mask;
88    samplers_fetch4 &= ps->sampler_mask;
89
90    if (unlikely(ps->byte_code.version < 0x20)) {
91        /* variable targets */
92        uint32_t m = ps->sampler_mask;
93        samplers_ps1_types = 0;
94        while (m) {
95            int s = ffs(m) - 1;
96            m &= ~(1 << s);
97            samplers_ps1_types |= (context->texture[s].enabled ? context->texture[s].pstype : 1) << (s * 2);
98        }
99        /* Note: For ps 1.X, only samplers 0 1 2 and 3 are available (except 1.4 where 4 and 5 are available).
100         * ps < 1.4: samplers_shadow 4b, samplers_ps1_types 8b, projected 8b
101         * ps 1.4: samplers_shadow 6b, samplers_ps1_types 12b
102         * Tot ps X.X samplers_shadow + extra: 20b */
103        assert((ps->byte_code.version < 0x14 && !(ps->sampler_mask & 0xFFF0)) || !(ps->sampler_mask & 0xFFC0));
104
105        if (unlikely(ps->byte_code.version < 0x14)) {
106            key |= samplers_ps1_types << 4;
107            projected = nine_ff_get_projected_key_programmable(context);
108            key |= ((uint64_t) projected) << 12;
109        } else {
110            key |= samplers_ps1_types << 6;
111        }
112    }
113
114    if (ps->byte_code.version < 0x30) {
115        key |= ((uint64_t)context->rs[D3DRS_FOGENABLE]) << 20;
116        key |= ((uint64_t)context->rs[D3DRS_FOGTABLEMODE]) << 21;
117    }
118
119    /* centroid interpolation automatically used for color ps inputs */
120    if (context->rt[0]->base.info.nr_samples)
121        key |= ((uint64_t)1) << 22;
122
123    if ((ps->const_int_slots > 0 || ps->const_bool_slots > 0) && context->inline_constants)
124        key |= ((uint64_t)nine_shader_constant_combination_key(&ps->c_combinations,
125                                                               ps->int_slots_used,
126                                                               ps->bool_slots_used,
127                                                               (void *)context->ps_const_i,
128                                                               context->ps_const_b)) << 24;
129
130    key |= ((uint64_t)(context->rs[NINED3DRS_FETCH4] & samplers_fetch4)) << 32;
131    res = ps->last_key != key;
132    if (res)
133        ps->next_key = key;
134    return res;
135}
136
137void *
138NinePixelShader9_GetVariant( struct NinePixelShader9 *ps,
139                             unsigned **const_ranges,
140                             unsigned *const_used_size );
141
142/*** public ***/
143
144HRESULT
145NinePixelShader9_new( struct NineDevice9 *pDevice,
146                      struct NinePixelShader9 **ppOut,
147                      const DWORD *pFunction, void *cso );
148
149HRESULT
150NinePixelShader9_ctor( struct NinePixelShader9 *,
151                       struct NineUnknownParams *pParams,
152                       const DWORD *pFunction, void *cso );
153
154void
155NinePixelShader9_dtor( struct NinePixelShader9 * );
156
157HRESULT NINE_WINAPI
158NinePixelShader9_GetFunction( struct NinePixelShader9 *This,
159                              void *pData,
160                              UINT *pSizeOfData );
161
162#endif /* _NINE_PIXELSHADER9_H_ */
163