From 2ce379f0b36310540322589a3aaae8773bf59938 Mon Sep 17 00:00:00 2001
From: Pavel Kopyl <pavelkopyl@gmail.com>
Date: Thu, 8 Feb 2024 14:05:06 +0100
Subject: [PATCH] [LLD] Adding EVM architecture to LLD.

---
 lld/ELF/Arch/EVM.cpp   | 94 ++++++++++++++++++++++++++++++++++++++++++
 lld/ELF/CMakeLists.txt |  1 +
 lld/ELF/Driver.cpp     |  3 ++
 lld/ELF/InputFiles.cpp |  4 ++
 lld/ELF/Target.cpp     |  4 ++
 lld/ELF/Target.h       |  3 ++
 6 files changed, 109 insertions(+)
 create mode 100644 lld/ELF/Arch/EVM.cpp

diff --git a/lld/ELF/Arch/EVM.cpp b/lld/ELF/Arch/EVM.cpp
new file mode 100644
index 000000000000..920017817c9a
--- /dev/null
+++ b/lld/ELF/Arch/EVM.cpp
@@ -0,0 +1,94 @@
+//===- EVM.cpp ------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// EVM is a stack-based virtual machine with a word size of 256 bits intendent
+// for execution of smart contracts in Ethereum blockchain environment.
+//
+// Since it is a baremetal programming, there's usually no loader to load
+// ELF files on EVMs. You are expected to link your program against address
+// 0 and pull out a .text section from the result using objcopy, so that you
+// can write the linked code to on-chip flush memory. You can do that with
+// the following commands:
+//
+//   ld.lld -Ttext=0 -o foo foo.o
+//   objcopy -O binary --only-section=.text foo output.bin
+//
+//===----------------------------------------------------------------------===//
+
+#include "InputFiles.h"
+#include "Symbols.h"
+#include "Target.h"
+#include "lld/Common/ErrorHandler.h"
+#include "llvm/BinaryFormat/ELF.h"
+#include "llvm/Support/Endian.h"
+
+using namespace llvm;
+using namespace llvm::object;
+using namespace llvm::support::endian;
+using namespace llvm::ELF;
+using namespace lld;
+using namespace lld::elf;
+
+namespace {
+class EVM final : public TargetInfo {
+public:
+  uint32_t calcEFlags() const override;
+  RelExpr getRelExpr(RelType type, const Symbol &s,
+                     const uint8_t *loc) const override;
+  void relocate(uint8_t *loc, const Relocation &rel,
+                uint64_t val) const override;
+};
+} // namespace
+
+RelExpr EVM::getRelExpr(RelType type, const Symbol &s,
+                        const uint8_t *loc) const {
+  switch (type) {
+  case R_EVM_DATA:
+    return R_ABS;
+  default:
+    error(getErrorLocation(loc) + "unknown relocation (" + Twine(type) +
+          ") against symbol " + toString(s));
+    return R_NONE;
+  }
+}
+
+void EVM::relocate(uint8_t *loc, const Relocation &rel, uint64_t val) const {
+  switch (rel.type) {
+  case R_EVM_DATA: {
+    if (val > std::numeric_limits<uint32_t>::max())
+      llvm_unreachable("R_EVM_DATA: to big relocation value");
+    write32be(loc, val);
+    break;
+  }
+  default:
+    llvm_unreachable("unknown relocation");
+  }
+}
+
+TargetInfo *elf::getEVMTargetInfo() {
+  static EVM target;
+  return &target;
+}
+
+static uint32_t getEFlags(InputFile *file) {
+  return cast<ObjFile<ELF32LE>>(file)->getObj().getHeader().e_flags;
+}
+
+uint32_t EVM::calcEFlags() const {
+  assert(!ctx.objectFiles.empty());
+
+  const uint32_t flags = getEFlags(ctx.objectFiles[0]);
+  for (InputFile *f : ArrayRef(ctx.objectFiles).slice(1)) {
+    const uint32_t objFlags = getEFlags(f);
+    if ((objFlags /* & EF_EVM_ARCH_MASK*/) != (flags /* & EF_EVM_ARCH_MASK*/))
+      error(toString(f) +
+            ": cannot link object files with incompatible target ISA");
+  }
+
+  return flags;
+}
diff --git a/lld/ELF/CMakeLists.txt b/lld/ELF/CMakeLists.txt
index df509c29b4d8..b4d3c36323c3 100644
--- a/lld/ELF/CMakeLists.txt
+++ b/lld/ELF/CMakeLists.txt
@@ -24,6 +24,7 @@ add_lld_library(lldELF
   Arch/AMDGPU.cpp
   Arch/ARM.cpp
   Arch/AVR.cpp
+  Arch/EVM.cpp
   Arch/EraVM.cpp
   Arch/Hexagon.cpp
   Arch/LoongArch.cpp
diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp
index 2ce13c10342f..a1850456ed45 100644
--- a/lld/ELF/Driver.cpp
+++ b/lld/ELF/Driver.cpp
@@ -52,6 +52,9 @@
 #include "llvm/Config/llvm-config.h"
 #include "llvm/LTO/LTO.h"
 #include "llvm/Object/Archive.h"
+// EVM local begin
+#include "llvm/Object/ELF.h"
+// EVM local end
 #include "llvm/Remarks/HotnessThresholdParser.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compression.h"
diff --git a/lld/ELF/InputFiles.cpp b/lld/ELF/InputFiles.cpp
index 2ecdd74cd6b3..b5c8ba088fa7 100644
--- a/lld/ELF/InputFiles.cpp
+++ b/lld/ELF/InputFiles.cpp
@@ -1614,6 +1614,10 @@ static uint16_t getBitcodeMachineKind(StringRef path, const Triple &t) {
     return t.isOSIAMCU() ? EM_IAMCU : EM_386;
   case Triple::x86_64:
     return EM_X86_64;
+  // EVM local begin
+  case Triple::evm:
+    return EM_EVM;
+  // EVM local end
   default:
     error(path + ": could not infer e_machine from bitcode target triple " +
           t.str());
diff --git a/lld/ELF/Target.cpp b/lld/ELF/Target.cpp
index d29d0d156950..08d8d5b0804d 100644
--- a/lld/ELF/Target.cpp
+++ b/lld/ELF/Target.cpp
@@ -91,6 +91,10 @@ TargetInfo *elf::getTarget() {
     return getSPARCV9TargetInfo();
   case EM_X86_64:
     return getX86_64TargetInfo();
+  // EVM local begin
+  case EM_EVM:
+    return getEVMTargetInfo();
+    // EVM local end
   }
   llvm_unreachable("unknown target machine");
 }
diff --git a/lld/ELF/Target.h b/lld/ELF/Target.h
index a77fe0213ae0..3097bc2bae60 100644
--- a/lld/ELF/Target.h
+++ b/lld/ELF/Target.h
@@ -188,6 +188,9 @@ TargetInfo *getRISCVTargetInfo();
 TargetInfo *getSPARCV9TargetInfo();
 TargetInfo *getX86TargetInfo();
 TargetInfo *getX86_64TargetInfo();
+// EVM local begin
+TargetInfo *getEVMTargetInfo();
+// EVM local end
 template <class ELFT> TargetInfo *getMipsTargetInfo();
 
 struct ErrorPlace {