[ir] resolve conditional Phi inputs when tracking bindless texture handles

Due to causing the platform windows to crash when a controller is activated.

- [x] I have read and followed the [Contribution Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/CONTRIBUTING.md#code-contributions).
- [x] I have read and followed the [AI Policy](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/AI.md).
- [x] I have read and followed the [Coding Guidelines](https://git.eden-emu.dev/eden-emu/eden/src/branch/master/docs/policies/Coding.md) to the best of my ability.

-------------------

Co-authored-by: Your Name <John@John.localdomain>
Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4545
Reviewed-by: lizzie <lizzie@eden-emu.dev>
Reviewed-by: Maufeat <sahyno1996@gmail.com>

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/model/BooleanSetting.kt

@@ -16,6 +16,7 @@ enum class BooleanSetting(override val key: String) : AbstractBooleanSetting {
     RENDERER_USE_SPEED_LIMIT("use_speed_limit"),
     USE_CUSTOM_CPU_TICKS("use_custom_cpu_ticks"),
     SKIP_CPU_INNER_INVALIDATION("skip_cpu_inner_invalidation"),
+    NCE_INVALIDATION_GPU_READBACK("nce_invalidation_gpu_readback"),
     FIX_BLOOM_EFFECTS("fix_bloom_effects"),
     EMULATE_BGR565("emulate_bgr565"),
     RESCALE_HACK("rescale_hack"),

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/model/view/SettingsItem.kt

@@ -859,6 +859,13 @@ abstract class SettingsItem(
                     descriptionId = R.string.skip_cpu_inner_invalidation_description
                 )
             )
+            put(
+                SwitchSetting(
+                    BooleanSetting.NCE_INVALIDATION_GPU_READBACK,
+                    titleId = R.string.nce_invalidation_gpu_readback,
+                    descriptionId = R.string.nce_invalidation_gpu_readback_description
+                )
+            )
             put(
                 SwitchSetting(
                     BooleanSetting.FIX_BLOOM_EFFECTS,

src/android/app/src/main/java/org/yuzu/yuzu_emu/features/settings/ui/SettingsFragmentPresenter.kt

@@ -554,6 +554,7 @@ class SettingsFragmentPresenter(
             add(HeaderSetting(R.string.hacks))
 
             add(BooleanSetting.SKIP_CPU_INNER_INVALIDATION.key)
+            add(BooleanSetting.NCE_INVALIDATION_GPU_READBACK.key)
             add(BooleanSetting.FIX_BLOOM_EFFECTS.key)
             add(BooleanSetting.EMULATE_BGR565.key)
             add(BooleanSetting.RENDERER_ASYNCHRONOUS_SHADERS.key)

src/android/app/src/main/res/values-ar/strings.xml

@@ -587,6 +587,8 @@
     <string name="fast_gpu_time_description">يجعل اللعبة تعتقد أن عمل وحدة معالجة الرسومات ينتهي بشكل أسرع مما هو عليه في الواقع، لذلك تتوقف عن خفض الدقة ومسافة العرض لتتناسب مع سرعات جهاز Switch.</string>
     <string name="skip_cpu_inner_invalidation">تخطي إبطال صلاحية وحدة المعالجة المركزية الداخلية</string>
     <string name="skip_cpu_inner_invalidation_description">يتخطى بعض عمليات إبطال ذاكرة التخزين المؤقتة من جانب وحدة المعالجة المركزية أثناء تحديثات الذاكرة، مما يقلل من استخدام وحدة المعالجة المركزية ويحسن أداءها. قد يتسبب ذلك في حدوث أعطال أو تعطل في بعض الألعاب.</string>
+    <string name="nce_invalidation_gpu_readback">إعادة قراءة وحدة معالجة الرسومات قبل إبطال صلاحية NCE</string>
+    <string name="nce_invalidation_gpu_readback_description">إصلاح مؤقت. يعالج مشكلة تعطل لعبة Ender Magnolia (وغيرها من ألعاب UE). قد يؤدي إلى انخفاض في الأداء. يجري العمل على تحسينه.</string>
     <string name="fix_bloom_effects">إصلاح تأثيرات التوهج</string>
     <string name="fix_bloom_effects_description">يقلل من ضبابية التوهج في LA/EOW  (Adreno A6XX - A7XX/ Turnip)، ويزيل التوهج في Burnout. تحذير: قد يسبب تشوهات رسومية في ألعاب أخرى.</string>
     <string name="emulate_bgr565">محاكاة BGR565</string>

src/android/app/src/main/res/values-zh-rTW/strings.xml

@@ -577,6 +577,8 @@
     <string name="fast_gpu_time_description">讓遊戲誤以為 GPU 工作能更快完成，避免遊戲為了配合 Switch 的時脈而降低解析度與渲染距離</string>
     <string name="skip_cpu_inner_invalidation">跳過 CPU 內部失效處理</string>
     <string name="skip_cpu_inner_invalidation_description">在記憶體更新期間跳過某些 CPU 端快取的失效處理，減少 CPU 使用率並提高其性能。可能會導致某些遊戲出現故障或當機</string>
+    <string name="nce_invalidation_gpu_readback">在 NCE 無效化前進行 GPU 回讀</string>
+    <string name="nce_invalidation_gpu_readback_description">（暫時性功能）修復 \"終結者瑪格諾莉亞：霧中綻放\" 及其它使用虛幻引擎之遊戲中的當機問題，可能會降低效能。此功能正在改善中</string>
     <string name="fix_bloom_effects">修正光暈特效</string>
     <string name="fix_bloom_effects_description">在 \"薩爾達傳說：織夢島\" 和 \"薩爾達傳說：智慧的再現\" 中減少光暈模糊的問題並移除 \"橫衝直撞：狂飆樂園重製版\" 中的光暈效果（適用於 Adreno A6XX - A7XX/ Turnip）。警告：可能會在其它遊戲中導致圖形異常</string>
     <string name="emulate_bgr565">模擬 BGR565</string>

src/android/app/src/main/res/values/strings.xml

@@ -593,6 +593,8 @@
     <string name="fast_gpu_time_description">Makes the game believe GPU work finishes faster than it does, so it stops lowering resolution and render distance to fit the Switch\'s clocks.</string>
     <string name="skip_cpu_inner_invalidation">Skip CPU Inner Invalidation</string>
     <string name="skip_cpu_inner_invalidation_description">Skips certain CPU-side cache invalidations during memory updates, reducing CPU usage and improving it\'s performance. This may cause glitches or crashes on some games.</string>
+    <string name="nce_invalidation_gpu_readback">GPU Readback Before NCE Invalidation</string>
+    <string name="nce_invalidation_gpu_readback_description">Temporary. Fix Ender Magnolia (and other UE titles) crashes. May reduce performance. Improvement in progress.</string>
     <string name="fix_bloom_effects">Fix Bloom Effects</string>
     <string name="fix_bloom_effects_description">Reduces bloom blur in LA/EOW (Adreno A6XX - A7XX/ Turnip), removes bloom in Burnout. Warning: may cause graphical artifacts in other games.</string>
     <string name="emulate_bgr565">Emulate BGR565</string>

src/common/settings.h

@@ -639,6 +639,8 @@ struct Values {
                                                         Specialization::Default,
                                                         true,
                                                         true};
+    SwitchableSetting<bool> nce_invalidation_gpu_readback{
+        linkage, false, "nce_invalidation_gpu_readback", Category::RendererHacks};
     SwitchableSetting<bool> async_presentation{linkage,
 #ifdef __ANDROID__
                                                true,

src/input_common/drivers/joycon.cpp

@@ -83,21 +83,20 @@ void Joycons::ScanThread(std::stop_token stop_token) {
     constexpr u16 nintendo_vendor_id = 0x057e;
     Common::SetCurrentThreadName("JoyconScanThread");
 
-    auto last_ret = 0u;
     do {
-        auto ret = SDL_hid_device_change_count();
-        if (last_ret == 0u || last_ret != ret) {
-            last_ret = ret;
-            SDL_hid_device_info* devs = SDL_hid_enumerate(nintendo_vendor_id, 0x0);
-            for (auto* cur_dev = devs; cur_dev; cur_dev = cur_dev->next) {
-                if (IsDeviceNew(cur_dev)) {
-                    LOG_DEBUG(Input, "Device Found,type : {:04X} {:04X}", cur_dev->vendor_id, cur_dev->product_id);
-                    RegisterNewDevice(cur_dev);
-                }
-                cur_dev = cur_dev->next;
+        SDL_hid_device_info* devs = SDL_hid_enumerate(nintendo_vendor_id, 0x0);
+        SDL_hid_device_info* cur_dev = devs;
+
+        while (cur_dev) {
+            if (IsDeviceNew(cur_dev)) {
+                LOG_DEBUG(Input, "Device Found,type : {:04X} {:04X}", cur_dev->vendor_id,
+                          cur_dev->product_id);
+                RegisterNewDevice(cur_dev);
             }
-            SDL_hid_free_enumeration(devs);
+            cur_dev = cur_dev->next;
         }
+
+        SDL_hid_free_enumeration(devs);
     } while (Common::StoppableTimedWait(stop_token, std::chrono::seconds{5}));
 }
 

src/qt_common/config/shared_translation.cpp

@@ -194,6 +194,10 @@ std::unique_ptr<TranslationMap> InitializeTranslations(QObject* parent) {
     INSERT(Settings, skip_cpu_inner_invalidation, tr("Skip CPU Inner Invalidation"),
            tr("Skips certain cache invalidations during memory updates, reducing CPU usage and "
               "improving latency. This may cause soft-crashes."));
+    INSERT(Settings, nce_invalidation_gpu_readback,
+           tr("GPU Readback Before NCE Invalidation"),
+           tr("Flushes GPU buffer data back to guest memory before NCE invalidates the whole "
+              "guest page, preserving it while the CPU store proceeds."));
     INSERT(Settings, vsync_mode, tr("VSync Mode:"),
            tr("FIFO (VSync) does not drop frames or exhibit tearing but is limited by the screen "
               "refresh rate.\nFIFO Relaxed allows tearing as it recovers from a slow down.\n"

src/shader_recompiler/frontend/ir/breadth_first_search.h

@@ -1,8 +1,12 @@
+// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
+// SPDX-License-Identifier: GPL-3.0-or-later
+
 // SPDX-FileCopyrightText: Copyright 2021 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #pragma once
 
+#include <functional>
 #include <optional>
 #include <type_traits>
 #include <queue>
@@ -13,9 +17,10 @@
 
 namespace Shader::IR {
 
-template <typename Pred>
-auto BreadthFirstSearch(const Value& value, Pred&& pred)
+template <typename Pred, typename Resolve = std::identity>
+auto BreadthFirstSearch(Value value, Pred&& pred, Resolve&& resolve = {})
     -> std::invoke_result_t<Pred, const Inst*> {
+    value = resolve(value);
     if (value.IsImmediate()) {
         // Nothing to do with immediates
         return std::nullopt;
@@ -36,7 +41,7 @@ auto BreadthFirstSearch(const Value& value, Pred&& pred)
         }
         // Visit the right most arguments first
         for (size_t arg = inst->NumArgs(); arg--;) {
-            const Value arg_value{inst->Arg(arg)};
+            const Value arg_value{resolve(inst->Arg(arg))};
             if (arg_value.IsImmediate()) {
                 continue;
             }

src/shader_recompiler/ir_opt/texture_pass.cpp

@@ -31,6 +31,60 @@ struct TextureInst {
 
 using TextureInstVector = boost::container::small_vector<TextureInst, 24>;
 
+const IR::Block* ConditionalHeader(const IR::Block* body) {
+    const auto predecessors{body->ImmPredecessors()};
+    const auto successors{body->ImmSuccessors()};
+    if (predecessors.size() != 1 || successors.size() != 1) return nullptr;
+    const IR::Block* const header{predecessors[0]};
+    const auto targets{header->ImmSuccessors()};
+    if (targets.size() != 2 || targets[0] != body || targets[1] != successors[0] ||
+        targets[1]->ImmPredecessors().size() != 2 || header->empty() ||
+        header->back().GetOpcode() != IR::Opcode::ConditionRef) {
+        return nullptr;
+    }
+    return header;
+}
+
+std::pair<IR::Value, bool> Condition(IR::Value value) {
+    bool negated{};
+    while (const IR::Inst* inst = value.TryInstRecursive()) {
+        if (inst->GetOpcode() == IR::Opcode::LogicalNot) negated = !negated;
+        else if (inst->GetOpcode() != IR::Opcode::ConditionRef) break;
+        value = inst->Arg(0);
+    }
+    return {value.Resolve(), negated};
+}
+
+IR::Value ResolveConditionalPhi(IR::Value value, const IR::Block* block) {
+    if (!value.Resolve().IsPhi() || !(block = ConditionalHeader(block))) return value;
+    const auto [condition, negated]{Condition(block->back().Arg(0))};
+    boost::container::small_vector<const IR::Block*, 16> visited;
+    while (value.Resolve().IsPhi() && std::ranges::find(visited, block) == visited.end()) {
+        visited.push_back(block);
+        const IR::Inst* const phi{value.InstRecursive()};
+        const auto predecessors{block->ImmPredecessors()};
+        if (predecessors.size() == 1) {
+            block = predecessors[0];
+            continue;
+        }
+        if (predecessors.size() != 2 || phi->NumArgs() != 2) break;
+        const IR::Block* body{predecessors[0]};
+        const IR::Block* header{ConditionalHeader(body)};
+        if (header != predecessors[1]) {
+            body = predecessors[1];
+            header = ConditionalHeader(body);
+            if (header != predecessors[0]) break;
+        }
+        const auto [other_condition, other_negated]{Condition(header->back().Arg(0))};
+        if (condition == other_condition && (phi->PhiBlock(0) == header || phi->PhiBlock(0) == body)) {
+            const IR::Block* const incoming{negated == other_negated ? body : header};
+            value = phi->Arg(phi->PhiBlock(0) == incoming ? 0 : 1);
+        }
+        block = header;
+    }
+    return value;
+}
+
 constexpr u32 DESCRIPTOR_SIZE = 8;
 constexpr u32 DESCRIPTOR_SIZE_SHIFT = u32(std::countr_zero(DESCRIPTOR_SIZE));
 constexpr u32 DESCRIPTOR_MAX_COUNT = 1024;
@@ -299,23 +353,23 @@ static inline bool IsTexturePixelFormatIntegerCached(Environment& env,
 }
 
 
-std::optional<ConstBufferAddr> Track(const IR::Value& value, Environment& env, const HostTranslateInfo& host_info);
-static inline std::optional<ConstBufferAddr> TrackCached(const IR::Value& v, Environment& env, const HostTranslateInfo& host_info) {
-    if (const IR::Inst* key = v.InstRecursive()) {
+std::optional<ConstBufferAddr> Track(const IR::Value& value, Environment& env, const HostTranslateInfo& host_info, const IR::Block* block);
+static inline std::optional<ConstBufferAddr> TrackCached(const IR::Value& v, Environment& env, const HostTranslateInfo& host_info, const IR::Block* block) {
+    if (const IR::Inst* key = v.TryInstRecursive()) {
         if (auto it = env.track_cache.find(key); it != env.track_cache.end()) return it->second;
-        auto found = Track(v, env, host_info);
+        auto found = Track(v, env, host_info, block);
         if (found) env.track_cache.emplace(key, *found);
         return found;
     }
-    return Track(v, env, host_info);
+    return Track(v, env, host_info, block);
 }
 
-std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environment& env, const HostTranslateInfo& host_info);
+std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environment& env, const HostTranslateInfo& host_info, const IR::Block* block);
 
-std::optional<ConstBufferAddr> Track(const IR::Value& value, Environment& env, const HostTranslateInfo& host_info) {
-    return IR::BreadthFirstSearch(value, [&env, &host_info](const IR::Inst* inst) {
-        return TryGetConstBuffer(inst, env, host_info);
-    });
+std::optional<ConstBufferAddr> Track(const IR::Value& value, Environment& env, const HostTranslateInfo& host_info, const IR::Block* block) {
+    return IR::BreadthFirstSearch(value, [&env, &host_info, block](const IR::Inst* inst) {
+        return TryGetConstBuffer(inst, env, host_info, block);
+    }, [&](IR::Value operand) { return ResolveConditionalPhi(operand, block); });
 }
 
 std::optional<u32> TryGetConstant(IR::Value& value, Environment& env) {
@@ -339,13 +393,13 @@ std::optional<u32> TryGetConstant(IR::Value& value, Environment& env) {
     return ReadCbufCached(env, index_number, offset_number);
 }
 
-std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environment& env, const HostTranslateInfo& host_info) {
+std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environment& env, const HostTranslateInfo& host_info, const IR::Block* block) {
     switch (inst->GetOpcode()) {
     default:
         return std::nullopt;
     case IR::Opcode::BitwiseOr32: {
-        std::optional lhs{TrackCached(inst->Arg(0), env, host_info)};
-        std::optional rhs{TrackCached(inst->Arg(1), env, host_info)};
+        std::optional lhs{TrackCached(inst->Arg(0), env, host_info, block)};
+        std::optional rhs{TrackCached(inst->Arg(1), env, host_info, block)};
         if (!lhs || !rhs) {
             return std::nullopt;
         }
@@ -375,7 +429,7 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
         if (!shift.IsImmediate()) {
             return std::nullopt;
         }
-        std::optional lhs{TrackCached(inst->Arg(0), env, host_info)};
+        std::optional lhs{TrackCached(inst->Arg(0), env, host_info, block)};
         if (lhs) {
             lhs->shift_left = shift.U32();
         }
@@ -403,7 +457,7 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
                 return std::nullopt;
             } while (false);
         }
-        std::optional lhs{TrackCached(op1, env, host_info)};
+        std::optional lhs{TrackCached(op1, env, host_info, block)};
         if (lhs) {
             lhs->shift_left = static_cast<u32>(std::countr_zero(op2.U32()));
         }
@@ -469,7 +523,7 @@ std::optional<ConstBufferAddr> TryGetConstBuffer(const IR::Inst* inst, Environme
 TextureInst MakeInst(Environment& env, IR::Block* block, IR::Inst& inst, const HostTranslateInfo& host_info) {
     ConstBufferAddr addr;
     if (IsBindless(inst)) {
-        const std::optional<ConstBufferAddr> track_addr{TrackCached(inst.Arg(0), env, host_info)};
+        const std::optional<ConstBufferAddr> track_addr{TrackCached(inst.Arg(0), env, host_info, block)};
 
         if (!track_addr) {
             throw NotImplementedException("Failed to track bindless texture constant buffer");
@@ -671,6 +725,7 @@ void TexturePass(Environment& env, IR::Program& program, const HostTranslateInfo
     env.track_cache.clear();
     TextureInstVector to_replace;
     for (IR::Block* const block : program.post_order_blocks) {
+        env.track_cache.clear();
         for (IR::Inst& inst : block->Instructions()) {
             if (!IsTextureInstruction(inst)) {
                 continue;

src/video_core/gpu.cpp

@@ -227,17 +227,17 @@ struct GPU::Impl {
 
     /// Notify rasterizer that any caches of the specified region should be invalidated
     void InvalidateRegion(DAddr addr, u64 size, bool preserve_gpu_writes) {
-        if (preserve_gpu_writes) {
+        if (Settings::values.nce_invalidation_gpu_readback.GetValue()) {
             VideoCore::RasterizerInterface* rasterizer = renderer->ReadRasterizer();
-            if (!rasterizer->TryCacheInvalidation(addr, size)) {
+            if (preserve_gpu_writes && rasterizer->MustFlushRegion(addr, size, VideoCommon::CacheType::BufferCache)) {
                 const u64 fence = RequestSyncOperation([rasterizer, addr, size] {
                     rasterizer->FlushRegion(addr, size, VideoCommon::CacheType::BufferCache);
                     rasterizer->OnCacheInvalidation(addr, size);
                 });
                 gpu_thread.TickGPU(is_async);
                 WaitForSyncOperation(fence);
+                return;
             }
-            return;
         }
         gpu_thread.InvalidateRegion(addr, size);
     }

src/video_core/rasterizer_interface.h

@@ -1,6 +1,3 @@
-// SPDX-FileCopyrightText: Copyright 2026 Eden Emulator Project
-// SPDX-License-Identifier: GPL-3.0-or-later
-
 // SPDX-FileCopyrightText: Copyright 2018 yuzu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
@@ -114,12 +111,6 @@ public:
     /// Notify rasterizer that any caches of the specified region are desync with guest
     virtual void OnCacheInvalidation(PAddr addr, u64 size) = 0;
 
-    virtual bool TryCacheInvalidation(DAddr addr, u64 size) {
-        if (MustFlushRegion(addr, size, VideoCommon::CacheType::BufferCache)) return false;
-        OnCacheInvalidation(addr, size);
-        return true;
-    }
-
     virtual bool OnCPUWrite(PAddr addr, u64 size) = 0;
 
     /// Sync memory between guest and host.

src/video_core/renderer_vulkan/vk_rasterizer.cpp

@@ -798,18 +798,6 @@ void RasterizerVulkan::OnCacheInvalidation(DAddr addr, u64 size) {
     pipeline_cache.InvalidateRegion(addr, size);
 }
 
-bool RasterizerVulkan::TryCacheInvalidation(DAddr addr, u64 size) {
-    if (addr == 0 || size == 0) return true;
-    {
-        std::scoped_lock lock{buffer_cache.mutex, texture_cache.mutex};
-        if (buffer_cache.IsRegionGpuModified(addr, size)) return false;
-        texture_cache.WriteMemory(addr, size);
-        buffer_cache.WriteMemory(addr, size);
-    }
-    pipeline_cache.InvalidateRegion(addr, size);
-    return true;
-}
-
 void RasterizerVulkan::InvalidateGPUCache() {
     gpu.InvalidateGPUCache();
 }

src/video_core/renderer_vulkan/vk_rasterizer.h

@@ -106,7 +106,6 @@ public:
                           VideoCommon::CacheType which = VideoCommon::CacheType::All) override;
     void InnerInvalidation(std::span<const std::pair<DAddr, std::size_t>> sequences) override;
     void OnCacheInvalidation(DAddr addr, u64 size) override;
-    bool TryCacheInvalidation(DAddr addr, u64 size) override;
     bool OnCPUWrite(DAddr addr, u64 size) override;
     void InvalidateGPUCache() override;
     void UnmapMemory(DAddr addr, u64 size) override;