graphics: unify buffer bindings and depth target handling

2026-10-20 10:56:58 +02:00 · 2026-07-27 10:08:08 +02:00
parent f43567e12c
commit 142b3c20fa
17 changed files with 669 additions and 564 deletions
@@ -87,7 +87,7 @@ static bool UsesStencilOpValue(uint8_t fail, uint8_t pass, uint8_t depth_fail) {

 // NOLINTNEXTLINE(readability-function-cognitive-complexity)
 void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandBuffer& buffer,
-                                          RenderDepthInfo& r) {
+                                              RenderDepthInfo& r) {
 	KYTY_PROFILER_FUNCTION();
 	(void)submit_id;
 	const auto& hw = buffer.GetRegisters();
@@ -102,31 +102,34 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 	if (!depth_active && !stencil_active) {
 		return;
 	}
+	if (!z.z_info.HasValidTextureCompatibility() ||
+	    !z.stencil_info.HasValidTextureCompatibility()) {
+		DepthFatal("invalid PS5 depth texture-compatibility encoding");
+	}
 	const bool attachment_unbound =
 	    z.z_info.format == Prospero::GpuEnumValue(Prospero::DepthFormat::kInvalid) &&
 	    z.stencil_info.format == Prospero::GpuEnumValue(Prospero::StencilFormat::kInvalid) &&
-	    z.z_info.tile_mode_index == 0 && z.z_info.num_samples == 0 &&
-	    z.z_info.zrange_precision <= 1 && !z.z_info.expclear_enabled &&
-	    !z.z_info.embedded_sample_locations && !z.z_info.partially_resident &&
-	    z.z_info.num_mip_levels == 0 && z.z_info.plane_compression == 0 &&
-	    z.stencil_info.tile_mode_index == 0 && z.stencil_info.tile_split == 0 &&
-	    !z.stencil_info.expclear_enabled && !z.stencil_info.texture_compatible_stencil &&
-	    !z.stencil_info.partially_resident && z.depth_view.slice_start == 0 &&
-	    z.depth_view.slice_max == 0 && z.depth_view.current_mip_level == 0 &&
-	    !z.depth_view.depth_write_disable && !z.depth_view.stencil_write_disable &&
-	    z.depth_info.addr5_swizzle_mask == 0 && z.depth_info.array_mode == 0 &&
-	    z.depth_info.pipe_config == 0 && z.depth_info.bank_width == 0 &&
-	    z.depth_info.bank_height == 0 && z.depth_info.macro_tile_aspect == 0 &&
-	    z.depth_info.num_banks == 0 && z.htile_surface.linear == 0 &&
-	    z.htile_surface.full_cache == 0 && z.htile_surface.htile_uses_preload_win == 0 &&
-	    z.htile_surface.preload == 0 && z.htile_surface.prefetch_width == 0 &&
-	    z.htile_surface.prefetch_height == 0 && z.htile_surface.dst_outside_zero_to_one == 0 &&
-	    z.z_read_base_addr == 0 && z.z_write_base_addr == 0 && z.stencil_read_base_addr == 0 &&
+	    z.z_info.num_samples == 0 &&
+	    z.z_info.texture_compatibility == Prospero::TextureCompatiblePlaneCompression::kDisable &&
+	    !z.z_info.expclear_enabled && !z.z_info.partially_resident && z.z_info.max_mip_level == 0 &&
+	    z.stencil_info.texture_compatibility == Prospero::TextureCompatibleStencil::kDisable &&
+	    !z.stencil_info.expclear_enabled && !z.stencil_info.partially_resident &&
+	    z.depth_view.slice_start == 0 && z.depth_view.slice_max == 0 &&
+	    z.depth_view.current_mip_level == 0 && !z.depth_view.depth_write_disable &&
+	    !z.depth_view.stencil_write_disable && z.depth_info.addr5_swizzle_mask == 0 &&
+	    z.depth_info.array_mode == 0 && z.depth_info.pipe_config == 0 &&
+	    z.depth_info.bank_width == 0 && z.depth_info.bank_height == 0 &&
+	    z.depth_info.macro_tile_aspect == 0 && z.depth_info.num_banks == 0 &&
+	    z.htile_surface.linear == 0 && z.htile_surface.full_cache == 0 &&
+	    z.htile_surface.htile_uses_preload_win == 0 && z.htile_surface.preload == 0 &&
+	    z.htile_surface.prefetch_width == 0 && z.htile_surface.prefetch_height == 0 &&
+	    z.htile_surface.dst_outside_zero_to_one == 0 && z.z_read_base_addr == 0 &&
+	    z.z_write_base_addr == 0 && z.stencil_read_base_addr == 0 &&
 	    z.stencil_write_base_addr == 0 && z.htile_data_base_addr == 0 &&
 	    // DB_DEPTH_SIZE_XY is independent state and may remain programmed after the attachment
 	    // formats and addresses are unbound. A zero encoding is the valid 1x1 value, so its
 	    // presence alone must not manufacture a depth attachment.
-	    !z.z_info.tile_surface_enable && !z.width_height_valid && !z.pitch_height_valid &&
+	    !z.z_info.htile_acceleration && !z.width_height_valid && !z.pitch_height_valid &&
 	    z.size.x_max == 0 && z.size.y_max == 0 && z.pitch_div8_minus1 == 0 &&
 	    z.height_div8_minus1 == 0 && z.slice_div64_minus1 == 0 && z.width == 0 && z.height == 0;
 	if (attachment_unbound) {
@@ -138,13 +141,13 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 	}
 	const bool has_stencil =
 	    z.stencil_info.format != Prospero::GpuEnumValue(Prospero::StencilFormat::kInvalid);
-	const bool has_htile = z.z_info.tile_surface_enable;
+	const bool has_htile = z.z_info.htile_acceleration;
 	const auto samples   = render_sample_count(z.z_info.num_samples);
 	if (samples == 0) {
 		DepthFatal("unsupported depth fragment count: %u", z.z_info.num_samples);
 	}
 	const bool htile_stencil_compat = depth_htile_stencil_acceleration_compatible(
-	    has_stencil, has_htile, z.stencil_info.tile_stencil_disable);
+	    has_stencil, has_htile, z.stencil_info.htile_stencil_disabled);
 	const auto view = ResolveTargetViewInfo(z.depth_view.slice_start, z.depth_view.slice_max);
 	switch (view.type) {
 		case TargetViewType::Image2D: break;
@@ -155,14 +158,10 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 			DepthFatal("invalid depth view: base=%u last=%u", z.depth_view.slice_start,
 			           z.depth_view.slice_max);
 	}
-	// Prospero defines the compression-disable bits as tile writeback policy. Vulkan attachments
-	// expose the same logical depth/stencil values regardless of the driver's backing compression.
 	if ((stencil_active && !has_stencil) || rc.resummarize_enable || rc.copy_centroid ||
 	    rc.copy_sample != 0 || z.z_info.expclear_enabled || z.stencil_info.expclear_enabled ||
-	    z.z_info.embedded_sample_locations || z.z_info.partially_resident ||
-	    z.stencil_info.partially_resident || z.z_info.plane_compression != 0 ||
-	    z.z_info.num_mip_levels != 0 || z.z_info.tile_mode_index != 0 ||
-	    z.z_info.zrange_precision > 1 || z.depth_view.current_mip_level != 0 ||
+	    z.z_info.partially_resident || z.stencil_info.partially_resident ||
+	    z.z_info.max_mip_level != 0 || z.depth_view.current_mip_level != 0 ||
 	    z.depth_info.addr5_swizzle_mask != 0 || z.depth_info.array_mode != 0 ||
 	    z.depth_info.pipe_config != 0 || z.depth_info.bank_width != 0 ||
 	    z.depth_info.bank_height != 0 || z.depth_info.macro_tile_aspect != 0 ||
@@ -176,27 +175,16 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 		DepthFatal("unsupported depth register state");
 	}
 	if (has_stencil) {
-		// Prospero defines Hi-Stencil as HTile-backed acceleration of the logical stencil plane.
-		// Keep the plane native in Vulkan while tracking HTile separately.
 		if (z.stencil_info.format != Prospero::GpuEnumValue(Prospero::StencilFormat::k8UInt) ||
-		    z.stencil_info.tile_mode_index != 0 || z.stencil_info.tile_split != 0 ||
-		    !htile_stencil_compat || z.stencil_info.texture_compatible_stencil ||
-		    z.stencil_read_base_addr == 0 ||
+		    !htile_stencil_compat || z.stencil_read_base_addr == 0 ||
 		    z.stencil_write_base_addr != z.stencil_read_base_addr ||
 		    (z.stencil_read_base_addr & 0xffffu) != 0 || z.depth_view.stencil_write_disable) {
 			DepthFatal("unsupported stencil attachment state");
 		}
-		if (!z.stencil_info.tile_stencil_disable) {
-			static std::atomic_bool logged = false;
-			if (!logged.load(std::memory_order_relaxed) &&
-			    !logged.exchange(true, std::memory_order_relaxed)) {
-				LOGF("DepthTarget: compatibility: using native stencil with PS5 HTILE "
-				     "acceleration\n");
-			}
-		}
 	} else if (z.stencil_read_base_addr != 0 || z.stencil_write_base_addr != 0 ||
-	           z.stencil_info.tile_mode_index != 0 || z.stencil_info.tile_split != 0 ||
-	           !htile_stencil_compat || z.stencil_info.texture_compatible_stencil) {
+	           !htile_stencil_compat ||
+	           z.stencil_info.texture_compatibility !=
+	               Prospero::TextureCompatibleStencil::kDisable) {
 		DepthFatal("stencil state without an active stencil attachment");
 	}
 	if (has_htile) {
@@ -271,16 +259,16 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 	    (has_htile && htile_backing_size > TRACKER_ADDRESS_SIZE - z.htile_data_base_addr)) {
 		DepthFatal("layered depth backing range is invalid");
 	}
-	r.htile                = has_htile;
-	r.width                = width;
-	r.height               = height;
-	r.samples              = samples;
-	r.depth_buffer_size    = depth_backing_size;
-	r.depth_buffer_vaddr   = z.z_read_base_addr;
-	r.stencil_buffer_size  = has_stencil ? stencil_backing_size : 0;
-	r.stencil_buffer_vaddr = has_stencil ? z.stencil_read_base_addr : 0;
-	r.htile_buffer_size    = has_htile ? htile_backing_size : 0;
-	r.htile_buffer_vaddr   = has_htile ? z.htile_data_base_addr : 0;
+	r.htile                   = has_htile;
+	r.width                   = width;
+	r.height                  = height;
+	r.samples                 = samples;
+	r.depth_buffer_size       = depth_backing_size;
+	r.depth_buffer_vaddr      = z.z_read_base_addr;
+	r.stencil_buffer_size     = has_stencil ? stencil_backing_size : 0;
+	r.stencil_buffer_vaddr    = has_stencil ? z.stencil_read_base_addr : 0;
+	r.htile_buffer_size       = has_htile ? htile_backing_size : 0;
+	r.htile_buffer_vaddr      = has_htile ? z.htile_data_base_addr : 0;
 	r.depth_clear_enable      = rc.depth_clear_enable;
 	r.depth_meta_clear_enable = false;
 	r.depth_load_clear_enable = r.depth_clear_enable;
@@ -334,13 +322,13 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 		r.size[1]  = r.stencil_buffer_size;
 	}
 	TextureCache::ImageDesc desc {};
-	desc.type              = TextureCache::BindingType::DepthTarget;
-	desc.info.data         = {r.depth_buffer_vaddr, r.depth_buffer_size};
-	desc.info.stencil      = {r.stencil_buffer_vaddr, r.stencil_buffer_size};
-	desc.info.pixel_format = r.format;
-	desc.info.guest_format = guest_format;
-	desc.info.type   = Prospero::ImageType::kColor2D;
-	desc.info.extent = {width, height, 1};
+	desc.type                 = TextureCache::BindingType::DepthTarget;
+	desc.info.data            = {r.depth_buffer_vaddr, r.depth_buffer_size};
+	desc.info.stencil         = {r.stencil_buffer_vaddr, r.stencil_buffer_size};
+	desc.info.pixel_format    = r.format;
+	desc.info.guest_format    = guest_format;
+	desc.info.type            = Prospero::ImageType::kColor2D;
+	desc.info.extent          = {width, height, 1};
 	desc.info.resources       = {1, view.image_layers};
 	desc.info.pitch           = pitch;
 	desc.info.bytes_per_block = bytes;
@@ -350,20 +338,20 @@ void RenderExecutor::ResolveRenderDepthTarget(uint64_t submit_id, RenderCommandB
 	desc.info.metadata.range  = {r.htile_buffer_vaddr, r.htile_buffer_size};
 	desc.info.metadata.kind   = has_htile ? ImageMetadataKind::Htile : ImageMetadataKind::None;
 	desc.info.metadata.stencil_compressed =
-	    has_stencil && has_htile && !z.stencil_info.tile_stencil_disable;
+	    has_stencil && has_htile && !z.stencil_info.htile_stencil_disabled;
 	desc.view_info.format = r.format;
 	desc.view_info.type =
 	    view.layer_count == 1 ? vk::ImageViewType::e2D : vk::ImageViewType::e2DArray;
-	desc.view_info.aspect              = ImageViewOps::DepthAspectMask(r.format);
-	desc.view_info.base_level          = 0;
-	desc.view_info.level_count         = 1;
-	desc.view_info.base_layer          = view.base_layer;
-	desc.view_info.layer_count         = view.layer_count;
-	desc.view_info.usage               = vk::ImageUsageFlagBits::eDepthStencilAttachment;
-	r.desc       = std::move(desc);
-	auto& cache  = m_context.GetTextureCache();
-	r.image_id   = cache.FindImage(r.desc);
-	r.image_view = nullptr;
+	desc.view_info.aspect      = ImageViewOps::DepthAspectMask(r.format);
+	desc.view_info.base_level  = 0;
+	desc.view_info.level_count = 1;
+	desc.view_info.base_layer  = view.base_layer;
+	desc.view_info.layer_count = view.layer_count;
+	desc.view_info.usage       = vk::ImageUsageFlagBits::eDepthStencilAttachment;
+	r.desc                     = std::move(desc);
+	auto& cache                = m_context.GetTextureCache();
+	r.image_id                 = cache.FindImage(r.desc);
+	r.image_view               = nullptr;
 	BindRenderTarget(r.image_id);
 }

@@ -372,7 +360,7 @@ vk::ImageAspectFlags RenderDepthInfo::AttachmentWriteAspects() const {
 		return {};
 	}

-	const auto available = ImageViewOps::DepthAspectMask(format);
+	const auto           available = ImageViewOps::DepthAspectMask(format);
 	vk::ImageAspectFlags writes {};
 	if ((available & vk::ImageAspectFlagBits::eDepth) &&
 	    (depth_load_clear_enable || (depth_test_enable && depth_write_enable))) {
@@ -415,9 +403,8 @@ vk::ImageAspectFlags RenderDepthInfo::AttachmentWriteAspects() const {
 		       (can_pass && depth_fail && state.depthFailOp != vk::StencilOp::eKeep);
 	};
 	if (stencil_clear_enable ||
-	    (stencil_test_enable &&
-	     (face_writes(stencil_static_front, stencil_dynamic_front) ||
-	      face_writes(stencil_static_back, stencil_dynamic_back)))) {
+	    (stencil_test_enable && (face_writes(stencil_static_front, stencil_dynamic_front) ||
+	                             face_writes(stencil_static_back, stencil_dynamic_back)))) {
 		writes |= vk::ImageAspectFlagBits::eStencil;
 	}
 	return writes;