November 2023 - Wine-commits

Zebediah Figura : vkd3d-shader/ir: Synthesize HS inputs with the register index and write mask of the signature element.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 852eefc01df90c4202212944ecc4af4bac7a5fae URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/852eefc01df90c4202212944ecc4a… Author: Zebediah Figura <zfigura(a)codeweavers.com> Date: Tue Oct 24 16:55:16 2023 -0500 vkd3d-shader/ir: Synthesize HS inputs with the register index and write mask of the signature element. This pass was written as if to output normalized I/O, but it runs before the I/O normalization pass. Fixes: 98b5e2c6e01199d714d18fccfe54826a680aecbf --- libs/vkd3d-shader/ir.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/libs/vkd3d-shader/ir.c b/libs/vkd3d-shader/ir.c index 1d4c0cb1..16e5948f 100644 --- a/libs/vkd3d-shader/ir.c +++ b/libs/vkd3d-shader/ir.c @@ -449,7 +449,8 @@ static enum vkd3d_result control_point_normaliser_emit_hs_input(struct control_p shader_dst_param_io_init(param, e, VKD3DSPR_INPUT, 2); param->reg.idx[0].offset = input_control_point_count; - param->reg.idx[1].offset = i; + param->reg.idx[1].offset = e->register_index; + param->write_mask = e->mask; ++ins; }

1 0

Francisco Casas : tests: Rename array-index-expr.shader_test as non-const-indexing.shader_test.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 3deb3b5a211b1468937a1469d2b55084e5746389 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/3deb3b5a211b1468937a1469d2b55… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Fri Nov 3 13:02:38 2023 -0300 tests: Rename array-index-expr.shader_test as non-const-indexing.shader_test. --- Makefile.am | 2 +- .../{array-index-expr.shader_test => non-const-indexing.shader_test} | 0 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile.am b/Makefile.am index 531a2705..14b5cf09 100644 --- a/Makefile.am +++ b/Makefile.am @@ -53,7 +53,6 @@ vkd3d_shader_tests = \ tests/hlsl/arithmetic-int.shader_test \ tests/hlsl/arithmetic-uint.shader_test \ tests/hlsl/array-dimension.shader_test \ - tests/hlsl/array-index-expr.shader_test \ tests/hlsl/array-parameters.shader_test \ tests/hlsl/array-size-expr.shader_test \ tests/hlsl/asfloat.shader_test \ @@ -134,6 +133,7 @@ vkd3d_shader_tests = \ tests/hlsl/multiple-rt.shader_test \ tests/hlsl/nested-arrays.shader_test \ tests/hlsl/nointerpolation.shader_test \ + tests/hlsl/non-const-indexing.shader_test \ tests/hlsl/normalize.shader_test \ tests/hlsl/numeric-constructor-truncation.shader_test \ tests/hlsl/numeric-types.shader_test \ diff --git a/tests/hlsl/array-index-expr.shader_test b/tests/hlsl/non-const-indexing.shader_test similarity index 100% rename from tests/hlsl/array-index-expr.shader_test rename to tests/hlsl/non-const-indexing.shader_test

1 0

Francisco Casas : tests: Add aditional relative addressing tests.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 915f9f1373035fc9db788bd35aa1cf1d29d315a9 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/915f9f1373035fc9db788bd35aa1c… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Wed Oct 11 19:50:05 2023 -0300 tests: Add aditional relative addressing tests. --- tests/hlsl/non-const-indexing.shader_test | 78 +++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) diff --git a/tests/hlsl/non-const-indexing.shader_test b/tests/hlsl/non-const-indexing.shader_test index b7d91ea0..9f79f610 100644 --- a/tests/hlsl/non-const-indexing.shader_test +++ b/tests/hlsl/non-const-indexing.shader_test @@ -49,6 +49,22 @@ todo(sm>=6) draw quad probe all rgba (14.0, 14.0, 14.0, 14.0) +[pixel shader todo] +float i; + +float4 main() : sv_target +{ + float a[4] = {1, 2, 3, 4}; + + return a[i]; +} + +[test] +uniform 0 float 2.3 +todo draw quad +todo probe all rgba (3, 3, 3, 3) + + [pixel shader] uniform float i; @@ -116,3 +132,65 @@ float4 main() : sv_target uniform 0 float4 0 0 2.4 0 todo draw quad probe all rgba (1.0, 120.0, 90.0, 4.0) + + +% SM1 doesn't support relative addressing if it is used in a l-value. +[require] +shader model >= 4.0 + +[pixel shader todo] +int i, j; + +float4 main() : sv_target +{ + float mut1[4] = {1, 2, 3, 4}; + float mut2[4] = {5, 6, 7, 8}; + + mut1[i] = 100; + mut2[j] = mut1[j]; + + return float4(mut2[0], mut2[1], mut2[2], mut2[3]); +} + +[test] +uniform 0 int 0 +uniform 1 int 0 +todo draw quad +todo probe all rgba (100, 6, 7, 8) +uniform 0 int 2 +uniform 1 int 2 +todo draw quad +todo probe all rgba (5, 6, 100, 8) +uniform 0 int 1 +uniform 1 int 3 +todo draw quad +todo probe all rgba (5, 6, 7, 4) + + +[pixel shader todo] +float a, b, c, d; +float e, f, g, h; +int i, j; + +float4 main() : sv_target +{ + + float arr1[8] = {a, a, b, b, c, c, d, d}; + float arr2[8] = {e, e, f, f, g, g, h, h}; + + arr1[i] = arr2[i]; + arr2[j] = arr1[j]; + + return 1000 * float4(arr1[0], arr1[4], arr2[0], arr2[4]) + + 100 * float4(arr1[1], arr1[5], arr2[1], arr2[5]) + + 10 * float4(arr1[2], arr1[6], arr2[2], arr2[6]) + + 1 * float4(arr1[3], arr1[7], arr2[3], arr2[7]); +} + +[test] +uniform 0 float4 1 2 3 4 +uniform 4 float4 5 6 7 8 +uniform 8 int 3 +uniform 9 int 4 +todo draw quad +todo probe all rgba (1126, 3344, 5566, 3788)

1 0

Francisco Casas : vkd3d-shader/tpf: Encode dst and src registers using the same function.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 043526a9f7e4eb6fe9f73a8436aef48ba6292140 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/043526a9f7e4eb6fe9f73a8436aef… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Wed Oct 4 22:10:06 2023 -0300 vkd3d-shader/tpf: Encode dst and src registers using the same function. This function will also be required to encode rel_addr registers. --- libs/vkd3d-shader/tpf.c | 96 +++++++++++++++++++++++++++---------------------- 1 file changed, 54 insertions(+), 42 deletions(-) diff --git a/libs/vkd3d-shader/tpf.c b/libs/vkd3d-shader/tpf.c index fbc04f61..74dad536 100644 --- a/libs/vkd3d-shader/tpf.c +++ b/libs/vkd3d-shader/tpf.c @@ -146,6 +146,9 @@ STATIC_ASSERT(SM4_MAX_SRC_COUNT <= SPIRV_MAX_SRC_COUNT); #define VKD3D_SM4_SWIZZLE_SHIFT 4 #define VKD3D_SM4_SWIZZLE_MASK (0xffu << VKD3D_SM4_SWIZZLE_SHIFT) +#define VKD3D_SM4_SCALAR_DIM_SHIFT 4 +#define VKD3D_SM4_SCALAR_DIM_MASK (0x3u << VKD3D_SM4_SCALAR_DIM_SHIFT) + #define VKD3D_SM4_VERSION_MAJOR(version) (((version) >> 4) & 0xf) #define VKD3D_SM4_VERSION_MINOR(version) (((version) >> 0) & 0xf) @@ -513,7 +516,8 @@ enum vkd3d_sm4_swizzle_type VKD3D_SM4_SWIZZLE_VEC4 = 0x1, VKD3D_SM4_SWIZZLE_SCALAR = 0x2, - VKD3D_SM4_SWIZZLE_INVALID = ~0u, + VKD3D_SM4_SWIZZLE_DEFAULT = ~0u - 1, + VKD3D_SM4_SWIZZLE_INVALID = ~0u, }; enum vkd3d_sm4_dimension @@ -3837,32 +3841,67 @@ static void sm4_src_from_node(const struct tpf_writer *tpf, struct vkd3d_shader_ } } -static void sm4_write_dst_register(const struct tpf_writer *tpf, const struct vkd3d_shader_dst_param *dst) +static uint32_t sm4_encode_register(const struct tpf_writer *tpf, const struct vkd3d_shader_register *reg, + enum vkd3d_sm4_swizzle_type sm4_swizzle_type, uint32_t sm4_swizzle) { const struct vkd3d_sm4_register_type_info *register_type_info; - struct vkd3d_bytecode_buffer *buffer = tpf->buffer; - uint32_t sm4_reg_type, reg_dim; + uint32_t sm4_reg_type, sm4_reg_dim; uint32_t token = 0; - unsigned int j; - register_type_info = get_info_from_vkd3d_register_type(&tpf->lookup, dst->reg.type); + register_type_info = get_info_from_vkd3d_register_type(&tpf->lookup, reg->type); if (!register_type_info) { - FIXME("Unhandled vkd3d-shader register type %#x.\n", dst->reg.type); + FIXME("Unhandled vkd3d-shader register type %#x.\n", reg->type); sm4_reg_type = VKD3D_SM4_RT_TEMP; + if (sm4_swizzle_type == VKD3D_SM4_SWIZZLE_DEFAULT) + sm4_swizzle_type = VKD3D_SM4_SWIZZLE_VEC4; } else { sm4_reg_type = register_type_info->sm4_type; + if (sm4_swizzle_type == VKD3D_SM4_SWIZZLE_DEFAULT) + sm4_swizzle_type = register_type_info->default_src_swizzle_type; } - - reg_dim = sm4_dimension_from_vsir_dimension(dst->reg.dimension); + sm4_reg_dim = sm4_dimension_from_vsir_dimension(reg->dimension); token |= sm4_reg_type << VKD3D_SM4_REGISTER_TYPE_SHIFT; - token |= dst->reg.idx_count << VKD3D_SM4_REGISTER_ORDER_SHIFT; - token |= reg_dim << VKD3D_SM4_DIMENSION_SHIFT; - if (reg_dim == VKD3D_SM4_DIMENSION_VEC4) - token |= dst->write_mask << VKD3D_SM4_WRITEMASK_SHIFT; + token |= reg->idx_count << VKD3D_SM4_REGISTER_ORDER_SHIFT; + token |= sm4_reg_dim << VKD3D_SM4_DIMENSION_SHIFT; + + if (sm4_reg_dim == VKD3D_SM4_DIMENSION_VEC4) + { + token |= (uint32_t)sm4_swizzle_type << VKD3D_SM4_SWIZZLE_TYPE_SHIFT; + + switch (sm4_swizzle_type) + { + case VKD3D_SM4_SWIZZLE_NONE: + assert(sm4_swizzle || register_is_constant(reg)); + token |= (sm4_swizzle << VKD3D_SM4_WRITEMASK_SHIFT) & VKD3D_SM4_WRITEMASK_MASK; + break; + + case VKD3D_SM4_SWIZZLE_VEC4: + token |= (sm4_swizzle << VKD3D_SM4_SWIZZLE_SHIFT) & VKD3D_SM4_SWIZZLE_MASK; + break; + + case VKD3D_SM4_SWIZZLE_SCALAR: + token |= (sm4_swizzle << VKD3D_SM4_SCALAR_DIM_SHIFT) & VKD3D_SM4_SCALAR_DIM_MASK; + break; + + default: + vkd3d_unreachable(); + } + } + + return token; +} + +static void sm4_write_dst_register(const struct tpf_writer *tpf, const struct vkd3d_shader_dst_param *dst) +{ + struct vkd3d_bytecode_buffer *buffer = tpf->buffer; + uint32_t token = 0; + unsigned int j; + + token = sm4_encode_register(tpf, &dst->reg, VKD3D_SM4_SWIZZLE_NONE, dst->write_mask); put_u32(buffer, token); for (j = 0; j < dst->reg.idx_count; ++j) @@ -3874,38 +3913,11 @@ static void sm4_write_dst_register(const struct tpf_writer *tpf, const struct vk static void sm4_write_src_register(const struct tpf_writer *tpf, const struct vkd3d_shader_src_param *src) { - const struct vkd3d_sm4_register_type_info *register_type_info; struct vkd3d_bytecode_buffer *buffer = tpf->buffer; - uint32_t sm4_reg_type, reg_dim; uint32_t token = 0, mod_token = 0; unsigned int j; - register_type_info = get_info_from_vkd3d_register_type(&tpf->lookup, src->reg.type); - if (!register_type_info) - { - FIXME("Unhandled vkd3d-shader register type %#x.\n", src->reg.type); - sm4_reg_type = VKD3D_SM4_RT_TEMP; - } - else - { - sm4_reg_type = register_type_info->sm4_type; - } - - reg_dim = sm4_dimension_from_vsir_dimension(src->reg.dimension); - - token |= sm4_reg_type << VKD3D_SM4_REGISTER_TYPE_SHIFT; - token |= src->reg.idx_count << VKD3D_SM4_REGISTER_ORDER_SHIFT; - token |= reg_dim << VKD3D_SM4_DIMENSION_SHIFT; - if (reg_dim == VKD3D_SM4_DIMENSION_VEC4) - { - uint32_t swizzle_type = (uint32_t)register_type_info->default_src_swizzle_type; - - token |= swizzle_type << VKD3D_SM4_SWIZZLE_TYPE_SHIFT; - if (swizzle_type == VKD3D_SM4_SWIZZLE_SCALAR) - token |= (swizzle_to_sm4(src->swizzle) & 0x3) << VKD3D_SM4_SWIZZLE_SHIFT; - else - token |= swizzle_to_sm4(src->swizzle) << VKD3D_SM4_SWIZZLE_SHIFT; - } + token = sm4_encode_register(tpf, &src->reg, VKD3D_SM4_SWIZZLE_DEFAULT, swizzle_to_sm4(src->swizzle)); switch (src->modifiers) { @@ -3954,7 +3966,7 @@ static void sm4_write_src_register(const struct tpf_writer *tpf, const struct vk if (src->reg.type == VKD3DSPR_IMMCONST) { put_u32(buffer, src->reg.u.immconst_uint[0]); - if (reg_dim == VKD3D_SM4_DIMENSION_VEC4) + if (src->reg.dimension == VSIR_DIMENSION_VEC4) { put_u32(buffer, src->reg.u.immconst_uint[1]); put_u32(buffer, src->reg.u.immconst_uint[2]);

1 0

Francisco Casas : vkd3d-shader/tpf: Write register index addressing.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 617a20bffc28111f9d9942e312d377646d15d78b URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/617a20bffc28111f9d9942e312d37… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Wed Oct 4 22:10:06 2023 -0300 vkd3d-shader/tpf: Write register index addressing. --- libs/vkd3d-shader/tpf.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/libs/vkd3d-shader/tpf.c b/libs/vkd3d-shader/tpf.c index 74dad536..79ea39d3 100644 --- a/libs/vkd3d-shader/tpf.c +++ b/libs/vkd3d-shader/tpf.c @@ -3841,6 +3841,20 @@ static void sm4_src_from_node(const struct tpf_writer *tpf, struct vkd3d_shader_ } } +static unsigned int sm4_get_index_addressing_from_reg(const struct vkd3d_shader_register *reg, + unsigned int i) +{ + if (reg->idx[i].rel_addr) + { + if (reg->idx[i].offset == 0) + return VKD3D_SM4_ADDRESSING_RELATIVE; + else + return VKD3D_SM4_ADDRESSING_RELATIVE | VKD3D_SM4_ADDRESSING_OFFSET; + } + + return 0; +} + static uint32_t sm4_encode_register(const struct tpf_writer *tpf, const struct vkd3d_shader_register *reg, enum vkd3d_sm4_swizzle_type sm4_swizzle_type, uint32_t sm4_swizzle) { @@ -3867,6 +3881,12 @@ static uint32_t sm4_encode_register(const struct tpf_writer *tpf, const struct v token |= sm4_reg_type << VKD3D_SM4_REGISTER_TYPE_SHIFT; token |= reg->idx_count << VKD3D_SM4_REGISTER_ORDER_SHIFT; token |= sm4_reg_dim << VKD3D_SM4_DIMENSION_SHIFT; + if (reg->idx_count > 0) + token |= sm4_get_index_addressing_from_reg(reg, 0) << VKD3D_SM4_ADDRESSING_SHIFT0; + if (reg->idx_count > 1) + token |= sm4_get_index_addressing_from_reg(reg, 1) << VKD3D_SM4_ADDRESSING_SHIFT1; + if (reg->idx_count > 2) + token |= sm4_get_index_addressing_from_reg(reg, 2) << VKD3D_SM4_ADDRESSING_SHIFT2; if (sm4_reg_dim == VKD3D_SM4_DIMENSION_VEC4) {

1 0

Francisco Casas : vkd3d-shader/tpf: Support writing relative addressing indexes.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: e10d41d7994ab2d6d1d424d7f1fd737e08891b69 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/e10d41d7994ab2d6d1d424d7f1fd7… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Fri Oct 6 02:06:23 2023 -0300 vkd3d-shader/tpf: Support writing relative addressing indexes. --- libs/vkd3d-shader/tpf.c | 40 ++++++++++++++++++++++++++++++++-------- 1 file changed, 32 insertions(+), 8 deletions(-) diff --git a/libs/vkd3d-shader/tpf.c b/libs/vkd3d-shader/tpf.c index 79ea39d3..70ee4124 100644 --- a/libs/vkd3d-shader/tpf.c +++ b/libs/vkd3d-shader/tpf.c @@ -3915,6 +3915,36 @@ static uint32_t sm4_encode_register(const struct tpf_writer *tpf, const struct v return token; } +static void sm4_write_register_index(const struct tpf_writer *tpf, const struct vkd3d_shader_register *reg, + unsigned int j) +{ + unsigned int addressing = sm4_get_index_addressing_from_reg(reg, j); + struct vkd3d_bytecode_buffer *buffer = tpf->buffer; + unsigned int k; + + if (addressing & VKD3D_SM4_ADDRESSING_RELATIVE) + { + const struct vkd3d_shader_src_param *idx_src = reg->idx[j].rel_addr; + uint32_t idx_src_token; + + assert(idx_src); + assert(!idx_src->modifiers); + assert(idx_src->reg.type != VKD3DSPR_IMMCONST); + idx_src_token = sm4_encode_register(tpf, &idx_src->reg, VKD3D_SM4_SWIZZLE_SCALAR, idx_src->swizzle); + + put_u32(buffer, idx_src_token); + for (k = 0; k < idx_src->reg.idx_count; ++k) + { + put_u32(buffer, idx_src->reg.idx[k].offset); + assert(!idx_src->reg.idx[k].rel_addr); + } + } + else + { + put_u32(tpf->buffer, reg->idx[j].offset); + } +} + static void sm4_write_dst_register(const struct tpf_writer *tpf, const struct vkd3d_shader_dst_param *dst) { struct vkd3d_bytecode_buffer *buffer = tpf->buffer; @@ -3925,10 +3955,7 @@ static void sm4_write_dst_register(const struct tpf_writer *tpf, const struct vk put_u32(buffer, token); for (j = 0; j < dst->reg.idx_count; ++j) - { - put_u32(buffer, dst->reg.idx[j].offset); - assert(!dst->reg.idx[j].rel_addr); - } + sm4_write_register_index(tpf, &dst->reg, j); } static void sm4_write_src_register(const struct tpf_writer *tpf, const struct vkd3d_shader_src_param *src) @@ -3978,10 +4005,7 @@ static void sm4_write_src_register(const struct tpf_writer *tpf, const struct vk } for (j = 0; j < src->reg.idx_count; ++j) - { - put_u32(buffer, src->reg.idx[j].offset); - assert(!src->reg.idx[j].rel_addr); - } + sm4_write_register_index(tpf, &src->reg, j); if (src->reg.type == VKD3DSPR_IMMCONST) {

1 0

Francisco Casas : vkd3d-shader/tpf: Move sm4_register_from_node() up.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 281796c526ce77619937e68d56c32ad1a1dabe66 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/281796c526ce77619937e68d56c32… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Fri Oct 6 11:52:45 2023 -0300 vkd3d-shader/tpf: Move sm4_register_from_node() up. --- libs/vkd3d-shader/tpf.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/libs/vkd3d-shader/tpf.c b/libs/vkd3d-shader/tpf.c index 70ee4124..b7fcfca5 100644 --- a/libs/vkd3d-shader/tpf.c +++ b/libs/vkd3d-shader/tpf.c @@ -3637,6 +3637,17 @@ struct sm4_instruction unsigned int idx_count; }; +static void sm4_register_from_node(struct vkd3d_shader_register *reg, uint32_t *writemask, + const struct hlsl_ir_node *instr) +{ + assert(instr->reg.allocated); + reg->type = VKD3DSPR_TEMP; + reg->dimension = VSIR_DIMENSION_VEC4; + reg->idx[0].offset = instr->reg.id; + reg->idx_count = 1; + *writemask = instr->reg.writemask; +} + static void sm4_register_from_deref(struct hlsl_ctx *ctx, struct vkd3d_shader_register *reg, uint32_t *writemask, const struct hlsl_deref *deref) { @@ -3778,17 +3789,6 @@ static void sm4_src_from_deref(const struct tpf_writer *tpf, struct vkd3d_shader } } -static void sm4_register_from_node(struct vkd3d_shader_register *reg, uint32_t *writemask, - const struct hlsl_ir_node *instr) -{ - assert(instr->reg.allocated); - reg->type = VKD3DSPR_TEMP; - reg->dimension = VSIR_DIMENSION_VEC4; - reg->idx[0].offset = instr->reg.id; - reg->idx_count = 1; - *writemask = instr->reg.writemask; -} - static void sm4_dst_from_node(struct vkd3d_shader_dst_param *dst, const struct hlsl_ir_node *instr) { sm4_register_from_node(&dst->reg, &dst->write_mask, instr);

1 0

Francisco Casas : vkd3d-shader/tpf: Support relative addressing for indexable temps in SM4.
by Alexandre Julliard 07 Nov '23

07 Nov '23

Module: vkd3d Branch: master Commit: 0ef25ad137d076490b87edabfd573546ae9b8ff4 URL: https://gitlab.winehq.org/wine/vkd3d/-/commit/0ef25ad137d076490b87edabfd573… Author: Francisco Casas <fcasas(a)codeweavers.com> Date: Fri Oct 6 13:16:48 2023 -0300 vkd3d-shader/tpf: Support relative addressing for indexable temps in SM4. For relative addressing, the vkd3d_shader_registers must point to another vkd3d_shader_src_param. For now, use the sm4_instruction to save them, since the only purpose of this struct is to be used as paramter for write_sm4_instruction. --- libs/vkd3d-shader/tpf.c | 86 +++++++++++++++++++++++-------- tests/hlsl/function-return.shader_test | 22 ++++---- tests/hlsl/matrix-indexing.shader_test | 6 +-- tests/hlsl/non-const-indexing.shader_test | 66 ++++++++++++------------ tests/hlsl/return.shader_test | 22 ++++---- 5 files changed, 123 insertions(+), 79 deletions(-)

1 0

Paul Gofman : ntdll: Handle LFH blocks allocated in large blocks in heap_validate_ptr().
by Alexandre Julliard 06 Nov '23

06 Nov '23

Module: wine Branch: master Commit: 1063cf81967c0929d7f08ff53d542b56209732e0 URL: https://gitlab.winehq.org/wine/wine/-/commit/1063cf81967c0929d7f08ff53d542b… Author: Paul Gofman <pgofman(a)codeweavers.com> Date: Mon Oct 30 17:54:13 2023 -0600 ntdll: Handle LFH blocks allocated in large blocks in heap_validate_ptr(). Wine-Bug: https://bugs.winehq.org/show_bug.cgi?id=55842 --- dlls/ntdll/heap.c | 62 ++++++++++++++++++++++++++++++++----------------------- 1 file changed, 36 insertions(+), 26 deletions(-) diff --git a/dlls/ntdll/heap.c b/dlls/ntdll/heap.c index b5e2076ffae..93ad5c73ba1 100644 --- a/dlls/ntdll/heap.c +++ b/dlls/ntdll/heap.c @@ -1050,17 +1050,17 @@ static NTSTATUS heap_free_large( struct heap *heap, ULONG flags, struct block *b } -/*********************************************************************** - * find_large_block - */ -static BOOL find_large_block( const struct heap *heap, const struct block *block ) +static ARENA_LARGE *find_arena_large( const struct heap *heap, const struct block *block, BOOL heap_walk ) { ARENA_LARGE *arena; LIST_FOR_EACH_ENTRY( arena, &heap->large_list, ARENA_LARGE, entry ) - if (block == &arena->block) return TRUE; + { + if (contains( &arena->block, arena->block_size, block, 1 )) + return !heap_walk || block == &arena->block ? arena : NULL; + } - return FALSE; + return NULL; } static BOOL validate_large_block( const struct heap *heap, const struct block *block ) @@ -1220,11 +1220,35 @@ static BOOL validate_free_block( const struct heap *heap, const SUBHEAP *subheap static BOOL validate_used_block( const struct heap *heap, const SUBHEAP *subheap, const struct block *block, unsigned int expected_block_type ) { - const char *err = NULL, *base = subheap_base( subheap ), *commit_end = subheap_commit_end( subheap ); + const char *err = NULL, *base = NULL, *commit_end; DWORD flags = heap->flags; const struct block *next; + ARENA_LARGE *arena_large; int i; + if (subheap) + { + base = subheap_base( subheap ); + commit_end = subheap_commit_end( subheap ); + } + else if ((arena_large = find_arena_large( heap, block, FALSE ))) + { + if (!validate_large_block( heap, &arena_large->block )) return FALSE; + if (block == &arena_large->block) return TRUE; + + if (contains( &arena_large->block + 1, arena_large->data_size, block, sizeof(*block) ) + && block_get_flags( block ) & BLOCK_FLAG_LFH) + { + base = (char *)arena_large; + commit_end = (char *)(arena_large + 1) + arena_large->data_size; + } + } + if (!base) + { + WARN( "heap %p, ptr %p: block region not found.\n", heap, block + 1 ); + return FALSE; + } + if ((ULONG_PTR)(block + 1) % BLOCK_ALIGN) err = "invalid block BLOCK_ALIGN"; else if (block_get_type( block ) != BLOCK_TYPE_USED && block_get_type( block ) != BLOCK_TYPE_DEAD) @@ -1237,9 +1261,8 @@ static BOOL validate_used_block( const struct heap *heap, const SUBHEAP *subheap err = "invalid block size"; else if (block->tail_size > block_get_size( block ) - sizeof(*block)) err = "invalid block unused size"; - else if ((next = next_block( subheap, block )) && (block_get_flags( next ) & BLOCK_FLAG_PREV_FREE) && - /* LFH blocks do not use BLOCK_FLAG_PREV_FREE or back pointer */ - !(block_get_flags( block ) & BLOCK_FLAG_LFH)) + else if (!(block_get_flags( block ) & BLOCK_FLAG_LFH) /* LFH blocks do not use BLOCK_FLAG_PREV_FREE or back pointer */ + && (next = next_block( subheap, block )) && (block_get_flags( next ) & BLOCK_FLAG_PREV_FREE)) err = "invalid next block flags"; else if (block_get_flags( block ) & BLOCK_FLAG_PREV_FREE) { @@ -1280,20 +1303,8 @@ static BOOL validate_used_block( const struct heap *heap, const SUBHEAP *subheap static BOOL heap_validate_ptr( const struct heap *heap, const void *ptr ) { const struct block *block = (struct block *)ptr - 1; - const SUBHEAP *subheap; - - if (!(subheap = find_subheap( heap, block, FALSE ))) - { - if (!find_large_block( heap, block )) - { - WARN("heap %p, ptr %p: block region not found\n", heap, ptr ); - return FALSE; - } - return validate_large_block( heap, block ); - } - - return validate_used_block( heap, subheap, block, BLOCK_TYPE_USED ); + return validate_used_block( heap, find_subheap( heap, block, FALSE ), block, BLOCK_TYPE_USED ); } static BOOL heap_validate( const struct heap *heap ) @@ -2448,7 +2459,7 @@ static NTSTATUS heap_walk_blocks( const struct heap *heap, const SUBHEAP *subhea static NTSTATUS heap_walk( const struct heap *heap, struct rtl_heap_entry *entry ) { const char *data = entry->lpData; - const ARENA_LARGE *large = NULL; + const ARENA_LARGE *large; const struct block *block; const struct list *next; const SUBHEAP *subheap; @@ -2459,9 +2470,8 @@ static NTSTATUS heap_walk( const struct heap *heap, struct rtl_heap_entry *entry else if (entry->wFlags & RTL_HEAP_ENTRY_BUSY) block = (struct block *)data - 1; else block = (struct block *)(data - sizeof(struct list)) - 1; - if (find_large_block( heap, block )) + if ((large = find_arena_large( heap, block, TRUE ))) { - large = CONTAINING_RECORD( block, ARENA_LARGE, block ); next = &large->entry; } else if ((subheap = find_subheap( heap, block, TRUE )))

1 0

Paul Gofman : ntdll: Fix pending free block validation in heap_validate() for LFH blocks.
by Alexandre Julliard 06 Nov '23

06 Nov '23

Module: wine Branch: master Commit: ae010a1a95934233246d93aea66374f9012d6c93 URL: https://gitlab.winehq.org/wine/wine/-/commit/ae010a1a95934233246d93aea66374… Author: Paul Gofman <pgofman(a)codeweavers.com> Date: Mon Oct 30 19:43:51 2023 -0600 ntdll: Fix pending free block validation in heap_validate() for LFH blocks. --- dlls/ntdll/heap.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/dlls/ntdll/heap.c b/dlls/ntdll/heap.c index 93ad5c73ba1..e3388e1bc8a 100644 --- a/dlls/ntdll/heap.c +++ b/dlls/ntdll/heap.c @@ -1343,15 +1343,11 @@ static BOOL heap_validate( const struct heap *heap ) { if (!(block = heap->pending_free[i])) break; - subheap = find_subheap( heap, block, FALSE ); - if (!subheap) + if (!validate_used_block( heap, find_subheap( heap, block, FALSE ), block, BLOCK_TYPE_DEAD )) { - ERR( "heap %p: cannot find valid subheap for delayed freed block %p\n", heap, block ); - if (TRACE_ON(heap)) heap_dump( heap ); + ERR( "heap %p: failed to to validate delayed free block %p\n", heap, block ); return FALSE; } - - if (!validate_used_block( heap, subheap, block, BLOCK_TYPE_DEAD )) return FALSE; } for (; i < MAX_FREE_PENDING; i++)

1 0