Performance diagnostics and small wins for title 1

- eden-cli: SDL called SDL_AppIterate back to back, keeping a host core at
  100% polling input; run the main callbacks at 240 Hz.
- EDEN_NX2_IDLE_SPIN_US: optional spin before an idle core blocks (measured:
  no gain on title 1, so off by default).
- EDEN_NX2_SVC_TRACE=<first>:<last>: trace SVCs (with thread ids) for a range
  of presents only.
- MME DMA reads flush GPU-written memory first (never triggered on title 1,
  kept for correctness); render-enable override histogram instead of the
  first-400 log.

Measured on title 1's title screen (RTX 4070 Laptop): GPU ~20% busy, the six
emulated cores ~0.9 host cores in total, Eden's GPU thread 45-70% busy and
largely waiting: on host fences for semaphore acquires (GPU accuracy High
delays every release to host completion), on ASTC upload Finish(), and in a
1 ms poll sleep. gpu_accuracy=Low: ~12.5 -> ~16 fps.

1 files changed, 18 insertions, 1 deletions

diff --git a/src/core/hle/kernel/physical_core.cpp b/src/core/hle/kernel/physical_core.cpp
index c5236c64e3..c3ae7629aa 100644
--- a/src/core/hle/kernel/physical_core.cpp
+++ b/src/core/hle/kernel/physical_core.cpp
@@ -4,6 +4,9 @@
 // SPDX-FileCopyrightText: Copyright 2020 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
+#include <chrono>
+#include <cstdlib>
+#include <thread>
 #include "common/scope_exit.h"
 #include "common/settings.h"
 #include "core/core.h"
@@ -222,8 +225,22 @@ void PhysicalCore::LogBacktrace(KernelCore& kernel) {
 }
 
 void PhysicalCore::Idle() {
+    // Guest job systems hand work between cores many times per frame; blocking at once adds the
+    // host's thread wake-up latency to every handoff. EDEN_NX2_IDLE_SPIN_US=<n>: poll for that
+    // many microseconds before blocking.
+    static const auto spin = std::chrono::microseconds{[] {
+        const char* text = std::getenv("EDEN_NX2_IDLE_SPIN_US");
+        return text ? std::strtoll(text, nullptr, 10) : 0LL;
+    }()};
+    if (spin.count() > 0) {
+        const auto deadline = std::chrono::steady_clock::now() + spin;
+        while (!m_is_interrupted.load(std::memory_order_acquire) &&
+               std::chrono::steady_clock::now() < deadline) {
+            std::this_thread::yield();
+        }
+    }
     std::unique_lock lk{m_guard};
-    m_on_interrupt.wait(lk, [this] { return m_is_interrupted; });
+    m_on_interrupt.wait(lk, [this] { return m_is_interrupted.load(); });
 }
 
 bool PhysicalCore::IsInterrupted() const {