2 files changed, 35 insertions, 5 deletions

diff --git a/src/video_core/buffer_cache/buffer_base.h b/src/video_core/buffer_cache/buffer_base.h
index f9a6472cf..92d77eef2 100644
--- a/src/video_core/buffer_cache/buffer_base.h
+++ b/src/video_core/buffer_cache/buffer_base.h
@@ -535,7 +535,7 @@ private:
         const u64* const state_words = Array<type>();
         const u64 num_query_words = size / BYTES_PER_WORD + 1;
         const u64 word_begin = offset / BYTES_PER_WORD;
-        const u64 word_end = std::min(word_begin + num_query_words, NumWords());
+        const u64 word_end = std::min<u64>(word_begin + num_query_words, NumWords());
         const u64 page_limit = Common::DivCeil(offset + size, BYTES_PER_PAGE);
         u64 page_index = (offset / BYTES_PER_PAGE) % PAGES_PER_WORD;
         for (u64 word_index = word_begin; word_index < word_end; ++word_index, page_index = 0) {
diff --git a/src/video_core/buffer_cache/buffer_cache.h b/src/video_core/buffer_cache/buffer_cache.h
index 2ba33543c..6881b34c4 100644
--- a/src/video_core/buffer_cache/buffer_cache.h
+++ b/src/video_core/buffer_cache/buffer_cache.h
@@ -19,6 +19,7 @@
 #include "common/literals.h"
 #include "common/lru_cache.h"
 #include "common/microprofile.h"
+#include "common/polyfill_ranges.h"
 #include "common/settings.h"
 #include "core/memory.h"
 #include "video_core/buffer_cache/buffer_base.h"
@@ -992,7 +993,20 @@ void BufferCache<P>::BindHostIndexBuffer() {
     TouchBuffer(buffer, index_buffer.buffer_id);
     const u32 offset = buffer.Offset(index_buffer.cpu_addr);
     const u32 size = index_buffer.size;
-    SynchronizeBuffer(buffer, index_buffer.cpu_addr, size);
+    if (maxwell3d->inline_index_draw_indexes.size()) {
+        if constexpr (USE_MEMORY_MAPS) {
+            auto upload_staging = runtime.UploadStagingBuffer(size);
+            std::array<BufferCopy, 1> copies{
+                {BufferCopy{.src_offset = upload_staging.offset, .dst_offset = 0, .size = size}}};
+            std::memcpy(upload_staging.mapped_span.data(),
+                        maxwell3d->inline_index_draw_indexes.data(), size);
+            runtime.CopyBuffer(buffer, upload_staging.buffer, copies);
+        } else {
+            buffer.ImmediateUpload(0, maxwell3d->inline_index_draw_indexes);
+        }
+    } else {
+        SynchronizeBuffer(buffer, index_buffer.cpu_addr, size);
+    }
     if constexpr (HAS_FULL_INDEX_AND_PRIMITIVE_SUPPORT) {
         const u32 new_offset = offset + maxwell3d->regs.index_buffer.first *
                                             maxwell3d->regs.index_buffer.FormatSizeInBytes();
@@ -1275,7 +1289,15 @@ void BufferCache<P>::UpdateIndexBuffer() {
     }
     flags[Dirty::IndexBuffer] = false;
     last_index_count = index_array.count;
-
+    if (maxwell3d->inline_index_draw_indexes.size()) {
+        auto inline_index_size = static_cast<u32>(maxwell3d->inline_index_draw_indexes.size());
+        index_buffer = Binding{
+            .cpu_addr = 0,
+            .size = inline_index_size,
+            .buffer_id = CreateBuffer(0, inline_index_size),
+        };
+        return;
+    }
     const GPUVAddr gpu_addr_begin = index_array.StartAddress();
     const GPUVAddr gpu_addr_end = index_array.EndAddress();
     const std::optional<VAddr> cpu_addr = gpu_memory->GpuToCpuAddress(gpu_addr_begin);
@@ -1491,6 +1513,14 @@ typename BufferCache<P>::OverlapResult BufferCache<P>::ResolveOverlaps(VAddr cpu
     VAddr end = cpu_addr + wanted_size;
     int stream_score = 0;
     bool has_stream_leap = false;
+    if (begin == 0) {
+        return OverlapResult{
+            .ids = std::move(overlap_ids),
+            .begin = begin,
+            .end = end,
+            .has_stream_leap = has_stream_leap,
+        };
+    }
     for (; cpu_addr >> YUZU_PAGEBITS < Common::DivCeil(end, YUZU_PAGESIZE);
          cpu_addr += YUZU_PAGESIZE) {
         const BufferId overlap_id = page_table[cpu_addr >> YUZU_PAGEBITS];
@@ -1713,12 +1743,12 @@ bool BufferCache<P>::InlineMemory(VAddr dest_address, size_t copy_size,
     SynchronizeBuffer(buffer, dest_address, static_cast<u32>(copy_size));
 
     if constexpr (USE_MEMORY_MAPS) {
+        auto upload_staging = runtime.UploadStagingBuffer(copy_size);
         std::array copies{BufferCopy{
-            .src_offset = 0,
+            .src_offset = upload_staging.offset,
             .dst_offset = buffer.Offset(dest_address),
             .size = copy_size,
         }};
-        auto upload_staging = runtime.UploadStagingBuffer(copy_size);
         u8* const src_pointer = upload_staging.mapped_span.data();
         std::memcpy(src_pointer, inlined_buffer.data(), copy_size);
         runtime.CopyBuffer(buffer, upload_staging.buffer, copies);