video_core/dma_pusher: Simplyfy Step() logic.

As fetching command list headers and and the list of command headers is a fixed 1:1 relation now, they can be implemented within a single call.
This cleans up the Step() logic quite a bit.

src/video_core/dma_pusher.cpp

@@ -33,16 +33,34 @@ void DmaPusher::DispatchCalls() {
 }
 
 bool DmaPusher::Step() {
-    if (dma_get != dma_put) {
+    if (!ib_enable || dma_pushbuffer.empty()) {
+        // pushbuffer empty and IB empty or nonexistent - nothing to do
+        return false;
+    }
+
+    const CommandList& command_list{dma_pushbuffer.front()};
+    const CommandListHeader& command_list_header{command_list[dma_pushbuffer_subindex++]};
+    GPUVAddr dma_get = command_list_header.addr;
+    GPUVAddr dma_put = dma_get + command_list_header.size * sizeof(u32);
+    bool non_main = command_list_header.is_non_main;
+
+    if (dma_pushbuffer_subindex >= command_list.size()) {
+        // We've gone through the current list, remove it from the queue
+        dma_pushbuffer.pop();
+        dma_pushbuffer_subindex = 0;
+    }
+
+    if (command_list_header.size == 0) {
+        return true;
+    }
+
     // Push buffer non-empty, read a word
     const auto address = gpu.MemoryManager().GpuToCpuAddress(dma_get);
     ASSERT_MSG(address, "Invalid GPU address");
 
-        GPUVAddr size = dma_put - dma_get;
-        ASSERT_MSG(size % sizeof(CommandHeader) == 0, "Invalid aligned GPU addresses");
-        command_headers.resize(size / sizeof(CommandHeader));
+    command_headers.resize(command_list_header.size);
 
-        Memory::ReadBlock(*address, command_headers.data(), size);
+    Memory::ReadBlock(*address, command_headers.data(), command_list_header.size * sizeof(u32));
 
     for (const CommandHeader& command_header : command_headers) {
 
@@ -93,28 +111,9 @@ bool DmaPusher::Step() {
         }
     }
 
-        dma_get = dma_put;
-
     if (!non_main) {
         // TODO (degasus): This is dead code, as dma_mget is never read.
-            dma_mget = dma_get;
-        }
-    } else if (ib_enable && !dma_pushbuffer.empty()) {
-        // Current pushbuffer empty, but we have more IB entries to read
-        const CommandList& command_list{dma_pushbuffer.front()};
-        const CommandListHeader& command_list_header{command_list[dma_pushbuffer_subindex++]};
-        dma_get = command_list_header.addr;
-        dma_put = dma_get + command_list_header.size * sizeof(u32);
-        non_main = command_list_header.is_non_main;
-
-        if (dma_pushbuffer_subindex >= command_list.size()) {
-            // We've gone through the current list, remove it from the queue
-            dma_pushbuffer.pop();
-            dma_pushbuffer_subindex = 0;
-        }
-    } else {
-        // Otherwise, pushbuffer empty and IB empty or nonexistent - nothing to do
-        return {};
+        dma_mget = dma_put;
     }
 
     return true;

src/video_core/dma_pusher.h

@@ -91,11 +91,8 @@ private:
     DmaState dma_state{};
     bool dma_increment_once{};
 
-    GPUVAddr dma_put{};   ///< pushbuffer current end address
-    GPUVAddr dma_get{};   ///< pushbuffer current read address
     GPUVAddr dma_mget{};  ///< main pushbuffer last read address
     bool ib_enable{true}; ///< IB mode enabled
-    bool non_main{};      ///< non-main pushbuffer active
 };
 
 } // namespace Tegra