swift-reflection-dump: ELF ObjectMemoryReader support for relocations

Collect the relative and symbol relocations from ELF images in order to resolve pointer values
read from disk. This allows us to enable symbolic-referencing-all-the-things for ELF platforms.

Author: jckarter

lib/IRGen/IRGenMangler.cpp

@@ -119,10 +119,11 @@ IRGenMangler::withSymbolicReferences(IRGenModule &IGM,
         }
       }
 
-      // TODO: ObjectMemoryReader for ELF and PE platforms still does not
+      // TODO: ObjectMemoryReader for PE platforms still does not
       // implement symbol relocations. For now, on non-Mach-O platforms,
       // only symbolic reference things in the same module.
-      if (IGM.TargetInfo.OutputObjectFormat != llvm::Triple::MachO) {
+      if (IGM.TargetInfo.OutputObjectFormat != llvm::Triple::MachO
+          && IGM.TargetInfo.OutputObjectFormat != llvm::Triple::ELF) {
         auto formalAccessScope = type->getFormalAccessScope(nullptr, true);
         if ((formalAccessScope.isPublic() || formalAccessScope.isInternal()) &&
             (!IGM.CurSourceFile ||

test/Reflection/typeref_lowering.swift

@@ -1,7 +1,11 @@
 // REQUIRES: no_asan
 // RUN: %empty-directory(%t)
+
 // RUN: %target-build-swift -Xfrontend -disable-availability-checking %S/Inputs/TypeLowering.swift -parse-as-library -emit-module -emit-library -module-name TypeLowering -o %t/%target-library-name(TypesToReflect)
+// RUN: %target-build-swift -Xfrontend -disable-availability-checking %S/Inputs/TypeLowering.swift %S/Inputs/main.swift -emit-module -emit-executable -module-name TypeLowering -o %t/TypesToReflect
+
 // RUN: %target-swift-reflection-dump -binary-filename %t/%target-library-name(TypesToReflect) -binary-filename %platform-module-dir/%target-library-name(swiftCore) -dump-type-lowering < %s | %FileCheck %s --check-prefix=CHECK-%target-ptrsize
+// RUN: %target-swift-reflection-dump -binary-filename %t/TypesToReflect -binary-filename %platform-module-dir/%target-library-name(swiftCore) -dump-type-lowering < %s | %FileCheck %s --check-prefix=CHECK-%target-ptrsize
 
 12TypeLowering11BasicStructV
 // CHECK-64:      (struct TypeLowering.BasicStruct)

tools/swift-reflection-dump/swift-reflection-dump.cpp

@@ -25,6 +25,7 @@
 #include "llvm/Object/ELF.h"
 #include "llvm/Object/ELFObjectFile.h"
 #include "llvm/Object/MachOUniversal.h"
+#include "llvm/Object/RelocationResolver.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Error.h"
 
@@ -96,7 +97,11 @@ class Image {
   const ObjectFile *O;
   uint64_t HeaderAddress;
   std::vector<Segment> Segments;
-  llvm::DenseMap<uint64_t, StringRef> DynamicRelocations;
+  struct DynamicRelocation {
+    StringRef Symbol;
+    uint64_t Offset;
+  };
+  llvm::DenseMap<uint64_t, DynamicRelocation> DynamicRelocations;
 
   void scanMachO(const MachOObjectFile *O) {
     using namespace llvm::MachO;
@@ -144,7 +149,25 @@ class Image {
         llvm::consumeError(std::move(error));
         break;
       }
-      DynamicRelocations.insert({bind.address(), bind.symbolName()});
+      
+      // The offset from the symbol is stored at the target address.
+      uint64_t Offset;
+      auto OffsetContent = getContentsAtAddress(bind.address(),
+                                                O->getBytesInAddress());
+      if (OffsetContent.empty())
+        continue;
+      
+      if (O->getBytesInAddress() == 8) {
+        memcpy(&Offset, OffsetContent.data(), sizeof(Offset));
+      } else if (O->getBytesInAddress() == 4) {
+        uint32_t OffsetValue;
+        memcpy(&OffsetValue, OffsetContent.data(), sizeof(OffsetValue));
+        Offset = OffsetValue;
+      } else {
+        assert(false && "unexpected word size?!");
+      }
+      
+      DynamicRelocations.insert({bind.address(), {bind.symbolName(), Offset}});
     }
     if (error) {
       llvm::consumeError(std::move(error));
@@ -160,7 +183,6 @@ class Image {
     auto phdrs = O->getELFFile()->program_headers();
     if (!phdrs) {
       llvm::consumeError(phdrs.takeError());
-      return;
     }
 
     for (auto &ph : *phdrs) {
@@ -175,6 +197,45 @@ class Image {
       Segments.push_back({ph.p_vaddr, contents});
       HeaderAddress = std::min(HeaderAddress, (uint64_t)ph.p_vaddr);
     }
+        
+    // Collect the dynamic relocations.
+    auto resolver = getRelocationResolver(*O);
+    auto resolverSupports = resolver.first;
+    auto resolve = resolver.second;
+    
+    if (!resolverSupports || !resolve)
+      return;
+    
+    auto machine = O->getELFFile()->getHeader()->e_machine;
+    auto relativeRelocType = getELFRelativeRelocationType(machine);
+    
+    for (auto &S : static_cast<const ELFObjectFileBase*>(O)
+                                             ->dynamic_relocation_sections()) {
+      bool isRela = O->getSection(S.getRawDataRefImpl())->sh_type
+        == llvm::ELF::SHT_RELA;
+
+      for (const RelocationRef &R : S.relocations()) {
+        // `getRelocationResolver` doesn't handle RELATIVE relocations, so we
+        // have to do that ourselves.
+        if (isRela && R.getType() == relativeRelocType) {
+          auto rela = O->getRela(R.getRawDataRefImpl());
+          DynamicRelocations.insert({R.getOffset(),
+            {{}, HeaderAddress + rela->r_addend}});
+          continue;
+        }
+        
+        if (!resolverSupports(R.getType()))
+          continue;
+        auto symbol = R.getSymbol();
+        auto name = symbol->getName();
+        if (!name) {
+          llvm::consumeError(name.takeError());
+          continue;
+        }
+        uint64_t offset = resolve(R, 0, 0);
+        DynamicRelocations.insert({R.getOffset(), {*name, offset}});
+      }
+    }
   }
 
   void scanELF(const ELFObjectFileBase *O) {
@@ -186,6 +247,8 @@ class Image {
       scanELFType(le64);
     } else if (auto be64 = dyn_cast<ELFObjectFile<ELF64BE>>(O)) {
       scanELFType(be64);
+    } else {
+      return;
     }
 
     // FIXME: ReflectionContext tries to read bits of the ELF structure that
@@ -215,6 +278,8 @@ class Image {
       Segments.push_back({SectionBase, SectionContent});
     }
 
+    // FIXME: We need to map the header at least, but how much of it does
+    // Windows typically map?
     Segments.push_back({HeaderAddress, O->getData()});
   }
 
@@ -272,7 +337,8 @@ class Image {
     if (found == DynamicRelocations.end())
       result = RemoteAbsolutePointer("", pointerValue);
     else
-      result = RemoteAbsolutePointer(found->second, pointerValue);
+      result = RemoteAbsolutePointer(found->second.Symbol,
+                                     found->second.Offset);
     return result;
   }
 };