nx2: get title 4 past the difficulty confirm

- MME: implement MME_DMA_READ / MME_DMA_READ_FIFOED (Turing macros read query
  results into their load FIFO; the conditional-render macro at 0x142 needs it).
- vi2 present waits up to 4 s for the frame fence (was 250 ms) so shader
  compile stalls don't let the game lap its equal-value gate semaphores.
- Native QMD: fire the third release slot at word 52, which NVN2 patches for
  queue-to-queue syncs (compute queue releasing a gate the 3D queue waits on).
- Compute class SET_REPORT_SEMAPHORE (0x6c0-0x6c3) releases.
- Ampere lowering: AOFFI, any LOP3 truth table, STG RZ, LDG 0x981, IABS,
  I2FP rounding, IMAD negated addend, SHFL 0x989 (all 77 title-4 shaders lower).
- Debug: EDEN_NX2_SEM_WATCH=<addr> traces acquires, releases, method
  arguments and compute macro emits for one semaphore block;
  EDEN_NX2_KEY_SCRIPT scripted key presses; per-submit logs moved to TRACE.

1 files changed, 6 insertions, 1 deletions

diff --git a/src/video_core/query_cache/query_cache.h b/src/video_core/query_cache/query_cache.h
index 11b2f631a5..930e5626aa 100644
--- a/src/video_core/query_cache/query_cache.h
+++ b/src/video_core/query_cache/query_cache.h
@@ -234,7 +234,12 @@ void QueryCacheBase<Traits>::CounterReport(GPUVAddr addr, QueryType counter_type
                                            QueryPropertiesFlags flags, u32 payload, u32 subreport) {
     const bool has_timestamp = True(flags & QueryPropertiesFlags::HasTimeout);
     const bool is_fence = True(flags & QueryPropertiesFlags::IsAFence);
-    if (static const bool trace = std::getenv("EDEN_NX2_QUERY_TRACE") != nullptr; trace) {
+    static const GPUVAddr watch = [] {
+        const char* value = std::getenv("EDEN_NX2_SEM_WATCH");
+        return value ? GPUVAddr{std::strtoull(value, nullptr, 16)} : GPUVAddr{};
+    }();
+    if (static const bool trace = std::getenv("EDEN_NX2_QUERY_TRACE") != nullptr;
+        trace || (watch != 0 && (addr & ~GPUVAddr{0xf}) == watch)) {
         LOG_INFO(HW_GPU, "nx2 report addr={:#x} type={} flags={:#x} payload={:#x}", addr,
                  static_cast<u32>(counter_type), static_cast<u32>(flags), payload);
     }