From e7eb4dba78eb8ae13b3b15d433bdc383860c990e Mon Sep 17 00:00:00 2001
From: CamilleLaVey <camillelavey99@gmail.com>
Date: Sun, 23 Nov 2025 14:46:48 -0400
Subject: [PATCH] [vk, texture_cache, vendor] Adding path for hardware resolve
 on shader stencil export/ MSAA image blits

---
 .../renderer_vulkan/vk_texture_cache.cpp      | 11 ++++++++
 .../vulkan_common/vulkan_device.cpp           | 26 +++++++++++++++++--
 src/video_core/vulkan_common/vulkan_device.h  |  8 ++++++
 3 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/src/video_core/renderer_vulkan/vk_texture_cache.cpp b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
index 136a11f78d..baddfe8cbf 100644
--- a/src/video_core/renderer_vulkan/vk_texture_cache.cpp
+++ b/src/video_core/renderer_vulkan/vk_texture_cache.cpp
@@ -1104,6 +1104,8 @@ void TextureCacheRuntime::BlitImage(Framebuffer* dst_framebuffer, ImageView& dst
                 UNREACHABLE();
             }
         }();
+        // Use shader-based depth/stencil blits if hardware doesn't support the format
+        // Note: MSAA resolves (MSAA->single) use vkCmdResolveImage which works fine
         if (!can_blit_depth_stencil) {
             UNIMPLEMENTED_IF(is_src_msaa || is_dst_msaa);
             blit_image_helper.BlitDepthStencil(dst_framebuffer, src, dst_region, src_region,
@@ -1118,6 +1120,15 @@ void TextureCacheRuntime::BlitImage(Framebuffer* dst_framebuffer, ImageView& dst
     const VkImage src_image = src.ImageHandle();
     const VkImageSubresourceLayers dst_layers = MakeSubresourceLayers(&dst);
     const VkImageSubresourceLayers src_layers = MakeSubresourceLayers(&src);
+    const bool is_msaa_to_msaa = is_src_msaa && is_dst_msaa;
+    
+    // NVIDIA 510+ and Intel crash on MSAA->MSAA blits (scaling operations)
+    // Fall back to 3D helpers for MSAA scaling
+    if (is_msaa_to_msaa && device.CantBlitMSAA()) {
+        // This should be handled by NeedsScaleHelper() and use 3D helpers instead
+        UNIMPLEMENTED_MSG("MSAA to MSAA blit not supported on this driver");
+        return;
+    }
     const bool is_resolve = is_src_msaa && !is_dst_msaa;
     scheduler.RequestOutsideRenderPassOperationContext();
     scheduler.Record([filter, dst_region, src_region, dst_image, src_image, dst_layers, src_layers,
diff --git a/src/video_core/vulkan_common/vulkan_device.cpp b/src/video_core/vulkan_common/vulkan_device.cpp
index e6224228ae..ceb01ca741 100644
--- a/src/video_core/vulkan_common/vulkan_device.cpp
+++ b/src/video_core/vulkan_common/vulkan_device.cpp
@@ -545,9 +545,29 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
         }
 
         if (nv_major_version >= 510) {
-            LOG_WARNING(Render_Vulkan, "NVIDIA Drivers >= 510 do not support MSAA image blits");
+            LOG_WARNING(Render_Vulkan, 
+                        "NVIDIA Drivers >= 510 do not support MSAA->MSAA image blits. "
+                        "MSAA scaling will use 3D helpers. MSAA resolves work normally.");
             cant_blit_msaa = true;
         }
+
+        // Mali/ NVIDIA proprietary drivers: Shader stencil export not supported
+        // Use hardware depth/stencil blits instead when available
+        if (!extensions.shader_stencil_export) {
+            LOG_INFO(Render_Vulkan,
+                     "NVIDIA: VK_EXT_shader_stencil_export not supported, using hardware blits "
+                     "for depth/stencil operations");
+            LOG_INFO(Render_Vulkan, "  D24S8 hardware blit support: {}",
+                     is_blit_depth24_stencil8_supported);
+            LOG_INFO(Render_Vulkan, "  D32S8 hardware blit support: {}",
+                     is_blit_depth32_stencil8_supported);
+            
+            if (!is_blit_depth24_stencil8_supported && !is_blit_depth32_stencil8_supported) {
+                LOG_WARNING(Render_Vulkan,
+                            "NVIDIA: Neither shader export nor hardware blits available for "
+                            "depth/stencil. Performance may be degraded.");
+            }
+        }
     }
 
     sets_per_pool = 64;
@@ -586,7 +606,9 @@ Device::Device(VkInstance instance_, vk::PhysicalDevice physical_, VkSurfaceKHR
     }
 
     if (is_intel_windows) {
-        LOG_WARNING(Render_Vulkan, "Intel proprietary drivers do not support MSAA image blits");
+        LOG_WARNING(Render_Vulkan, 
+                    "Intel proprietary drivers do not support MSAA->MSAA image blits. "
+                    "MSAA scaling will use 3D helpers. MSAA resolves work normally.");
         cant_blit_msaa = true;
     }
 
diff --git a/src/video_core/vulkan_common/vulkan_device.h b/src/video_core/vulkan_common/vulkan_device.h
index 86f258a373..b3c477ca9c 100644
--- a/src/video_core/vulkan_common/vulkan_device.h
+++ b/src/video_core/vulkan_common/vulkan_device.h
@@ -493,10 +493,18 @@ public:
     }
 
     /// Returns true if the device supports VK_EXT_shader_stencil_export.
+    /// Note: Most Mali/NVIDIA drivers don't support this. Use hardware blits as fallback.
     bool IsExtShaderStencilExportSupported() const {
         return extensions.shader_stencil_export;
     }
 
+    /// Returns true if depth/stencil operations can be performed efficiently.
+    /// Either through shader export or hardware blits.
+    bool CanPerformDepthStencilOperations() const {
+        return extensions.shader_stencil_export || is_blit_depth24_stencil8_supported ||
+               is_blit_depth32_stencil8_supported;
+    }
+
     /// Returns true if the device supports VK_EXT_depth_range_unrestricted.
     bool IsExtDepthRangeUnrestrictedSupported() const {
         return extensions.depth_range_unrestricted;