[patcher, ro, settings] runtime tls patch (#4492) optimization and nuke toggle (#4502) (#4523)

- [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.

-------------------
This is a follow up for the biomutant fix. By the time i knew it was shallow, coz i was running patchtext routine even for svc and modules, causing a routine which were needed to run 14 times to run 4000+ instead.
Since some perf loss was reported in 30 sep nightly, and it caused ac3r to not boot, we had added a temp toggle, which is now being removed as optimizations + fix are in.

Reviewed-on: https://git.eden-emu.dev/eden-emu/eden/pulls/4523
Reviewed-by: lizzie <lizzie@eden-emu.dev>
Reviewed-by: MaranBr <maranbr@eden-emu.dev>

1 files changed, 42 insertions, 0 deletions

diff --git a/src/core/arm/nce/patcher.cpp b/src/core/arm/nce/patcher.cpp
index 7d2041d4d2..f21d7cacdc 100644
--- a/src/core/arm/nce/patcher.cpp
+++ b/src/core/arm/nce/patcher.cpp
@@ -45,6 +45,23 @@ Patcher::Patcher() : c(m_patch_instructions), c_pre(m_patch_instructions_pre) {
     WriteLoadContext(c_pre);
 }
 
+Patcher::Patcher(std::span<const u8> text) : c(m_patch_instructions), c_pre(m_patch_instructions_pre) {
+    modules.emplace_back();
+    curr_patch = &modules.back();
+    const auto words = std::span<const u32>{reinterpret_cast<const u32*>(text.data()), text.size() / sizeof(u32)};
+    for (u32 i = ModuleCodeIndex; i < static_cast<u32>(words.size()); ++i) {
+        const uintptr_t offset = i * sizeof(u32);
+        if (auto mrs = MRS{words[i]}; mrs.Verify() && mrs.GetRt() != 31 && (mrs.GetSystemReg() == TpidrEl0 || mrs.GetSystemReg() == TpidrroEl0)) {
+            BranchToPatch(offset);
+            const auto src_reg = mrs.GetSystemReg() == TpidrroEl0 ? oaknut::SystemReg::TPIDRRO_EL0 : oaknut::SystemReg::TPIDR_EL0;
+            WriteMrsHandler(offset + sizeof(u32), oaknut::XReg{static_cast<int>(mrs.GetRt())}, src_reg);
+        } else if (auto msr = MSR{words[i]}; msr.Verify() && msr.GetSystemReg() == TpidrEl0) {
+            BranchToPatch(offset);
+            WriteMsrHandler(offset + sizeof(u32), oaknut::XReg{static_cast<int>(msr.GetRt())});
+        }
+    }
+}
+
 Patcher::~Patcher() = default;
 
 bool Patcher::PatchText(std::span<const u8> program_image, const Kernel::CodeSet::Segment& code) {
@@ -182,6 +199,31 @@ bool Patcher::PatchText(std::span<const u8> program_image, const Kernel::CodeSet
     return true;
 }
 
+std::span<const u32> Patcher::RelocateRuntimeTls(
+    s64 patch_offset, std::vector<InstructionPatch>& out_patches) {
+    const auto& patch = modules.front();
+    const auto can_branch = [](s64 offset) {
+        return offset % 4 == 0 && offset >= -static_cast<s64>(MaxRelativeBranch) && offset < static_cast<s64>(MaxRelativeBranch);
+    };
+    out_patches.clear();
+    out_patches.reserve(patch.m_branch_to_patch_relocations.size());
+    for (const auto& rel : patch.m_branch_to_patch_relocations) {
+        const s64 offset = patch_offset + rel.patch_offset - static_cast<s64>(rel.module_offset);
+        if (!can_branch(offset)) {return {};}
+        u32 replacement;
+        oaknut::CodeGenerator rc{&replacement};
+        rc.B(offset);
+        out_patches.push_back({rel.module_offset, replacement});
+    }
+    for (const auto& rel : patch.m_branch_to_module_relocations) {
+        const s64 offset = static_cast<s64>(rel.module_offset) - patch_offset - rel.patch_offset;
+        if (!can_branch(offset)) {return {};}
+        oaknut::CodeGenerator rc{m_patch_instructions.data() + rel.patch_offset / sizeof(u32)};
+        rc.B(offset);
+    }
+    return m_patch_instructions;
+}
+
 bool Patcher::RelocateAndCopy(Common::ProcessAddress load_base, const Kernel::CodeSet::Segment& code, std::vector<u8>& program_image, EntryTrampolines* out_trampolines) {
     const size_t patch_size = GetSectionSize();
     const size_t pre_patch_size = GetPreSectionSize();