[COFF] Add support for delay loading DLLs on ARM

[mstorsjo]

Summary

Is it ok to make the static functions in Chunks.cpp non-static like this, or should they be namespaced/moved any further if they are to be used from other files?

[mstorsjo]

Updated to set the thumb bit via | 1 instead of + 1, moved the setting of the bit into the 32 bit if/else branch, since it won't be used on 64 bit - not as such at least.

[ruiu]

LGTM

COFF/Chunks.h

public:
   Baserel(uint32_t V, uint8_t Ty) : RVA(V), Type(Ty) {}
   explicit Baserel(uint32_t V) : Baserel(V, getDefaultType()) {}
   uint8_t getDefaultType();
 
   uint32_t RVA;
   uint8_t Type;
 };
 
+void applyMOV32T(uint8_t *Off, uint32_t V);
+void applyBranch24T(uint8_t *Off, int32_t V);
+
 } // namespace coff
 } // namespace lld
 
 #endif

COFF/Chunks.cpp

 static uint16_t readMOV(uint8_t *Off) {
   uint16_t Opcode1 = read16le(Off);
   uint16_t Opcode2 = read16le(Off + 2);
   uint16_t Imm = (Opcode2 & 0x00ff) | ((Opcode2 >> 4) & 0x0700);
   Imm |= ((Opcode1 << 1) & 0x0800) | ((Opcode1 & 0x000f) << 12);
   return Imm;
 }
 
-static void applyMOV32T(uint8_t *Off, uint32_t V) {
+void applyMOV32T(uint8_t *Off, uint32_t V) {
   uint16_t ImmW = readMOV(Off);     // read MOVW operand
   uint16_t ImmT = readMOV(Off + 4); // read MOVT operand
   uint32_t Imm = ImmW | (ImmT << 16);
   V += Imm;                         // add the immediate offset
   applyMOV(Off, V);           // set MOVW operand
   applyMOV(Off + 4, V >> 16); // set MOVT operand
 }
 
 static void applyBranch20T(uint8_t *Off, int32_t V) {
   uint32_t S = V < 0 ? 1 : 0;
   uint32_t J1 = (V >> 19) & 1;
   uint32_t J2 = (V >> 18) & 1;
   or16(Off, (S << 10) | ((V >> 12) & 0x3f));
   or16(Off + 2, (J1 << 13) | (J2 << 11) | ((V >> 1) & 0x7ff));
 }
 
-static void applyBranch24T(uint8_t *Off, int32_t V) {
+void applyBranch24T(uint8_t *Off, int32_t V) {
   if (!isInt<25>(V))
     fatal("relocation out of range");
   uint32_t S = V < 0 ? 1 : 0;
   uint32_t J1 = ((~V >> 23) & 1) ^ S;
   uint32_t J2 = ((~V >> 22) & 1) ^ S;
   or16(Off, (S << 10) | ((V >> 12) & 0x3ff));
   // Clear out the J1 and J2 bits which may be set.
   write16le(Off + 2, (read16le(Off + 2) & 0xd000) | (J1 << 13) | (J2 << 11) | ((V >> 1) & 0x7ff));
void BaserelChunk::writeTo(uint8_t *Buf) const {
   memcpy(Buf + OutputSectionOff, Data.data(), Data.size());
 }
 
 uint8_t Baserel::getDefaultType() {
   switch (Config->Machine) {
   case AMD64:
     return IMAGE_REL_BASED_DIR64;
   case I386:
+  case ARMNT:
     return IMAGE_REL_BASED_HIGHLOW;
   default:
     llvm_unreachable("unknown machine type");
   }
 }
 
 } // namespace coff
 } // namespace lld

COFF/DLL.cpp

static const uint8_t ThunkX86[] = {
     0x68, 0, 0, 0, 0,  // push  offset ___imp__<FUNCNAME>
     0x68, 0, 0, 0, 0,  // push  offset ___DELAY_IMPORT_DESCRIPTOR_<DLLNAME>_dll
     0xE8, 0, 0, 0, 0,  // call  ___delayLoadHelper2@8
     0x5A,              // pop   edx
     0x59,              // pop   ecx
     0xFF, 0xE0,        // jmp   eax
 };
 
+static const uint8_t ThunkARM[] = {
+    0x40, 0xf2, 0x00, 0x0c, // mov.w   ip, #0 __imp_<FUNCNAME>
+    0xc0, 0xf2, 0x00, 0x0c, // mov.t   ip, #0 __imp_<FUNCNAME>
+    0x2d, 0xe9, 0x0f, 0x48, // push.w  {r0, r1, r2, r3, r11, lr}
+    0x0d, 0xf2, 0x10, 0x0b, // addw    r11, sp, #16
+    0x2d, 0xed, 0x10, 0x0b, // vpush   {d0, d1, d2, d3, d4, d5, d6, d7}
+    0x61, 0x46,             // mov     r1, ip
+    0x40, 0xf2, 0x00, 0x00, // mov.w   r0, #0 DELAY_IMPORT_DESCRIPTOR
+    0xc0, 0xf2, 0x00, 0x00, // mov.t   r0, #0 DELAY_IMPORT_DESCRIPTOR
+    0x00, 0xf0, 0x00, 0xd0, // bl      #0 __delayLoadHelper2
+    0x84, 0x46,             // mov     ip, r0
+    0xbd, 0xec, 0x10, 0x0b, // vpop    {d0, d1, d2, d3, d4, d5, d6, d7}
+    0xbd, 0xe8, 0x0f, 0x48, // pop.w   {r0, r1, r2, r3, r11, lr}
+    0x60, 0x47,             // bx      ip
+};
+
 // A chunk for the delay import thunk.
 class ThunkChunkX64 : public Chunk {
 public:
   ThunkChunkX64(Defined *I, Chunk *D, Defined *H)
       : Imp(I), Desc(D), Helper(H) {}
 
   size_t getSize() const override { return sizeof(ThunkX64); }
 
void getBaserels(std::vector<Baserel> *Res) override {
     Res->emplace_back(RVA + 8);
   }
 
   Defined *Imp = nullptr;
   Chunk *Desc = nullptr;
   Defined *Helper = nullptr;
 };
 
+class ThunkChunkARM : public Chunk {
+public:
+  ThunkChunkARM(Defined *I, Chunk *D, Defined *H)
+      : Imp(I), Desc(D), Helper(H) {}
+
+  size_t getSize() const override { return sizeof(ThunkARM); }
+
+  void writeTo(uint8_t *Buf) const override {
+    memcpy(Buf + OutputSectionOff, ThunkARM, sizeof(ThunkARM));
+    applyMOV32T(Buf + OutputSectionOff + 0, Imp->getRVA() + Config->ImageBase);
+    applyMOV32T(Buf + OutputSectionOff + 22, Desc->getRVA() + Config->ImageBase);
+    applyBranch24T(Buf + OutputSectionOff + 30, Helper->getRVA() - RVA - 34);
+  }
+
+  void getBaserels(std::vector<Baserel> *Res) override {
+    Res->emplace_back(RVA + 0, IMAGE_REL_BASED_ARM_MOV32T);
+    Res->emplace_back(RVA + 22, IMAGE_REL_BASED_ARM_MOV32T);
+  }
+
+  Defined *Imp = nullptr;
+  Chunk *Desc = nullptr;
+  Defined *Helper = nullptr;
+};
+
 // A chunk for the import descriptor table.
 class DelayAddressChunk : public Chunk {
 public:
   explicit DelayAddressChunk(Chunk *C) : Thunk(C) { Align = ptrSize(); }
   size_t getSize() const override { return ptrSize(); }
 
   void writeTo(uint8_t *Buf) const override {
+    uint32_t Offset = 0;
+    // Pointer to thumb code must have the LSB set, so adjust it.
+    if (Config->Machine == ARMNT)
+      Offset = 1;
     if (Config->is64()) {
-      write64le(Buf + OutputSectionOff, Thunk->getRVA() + Config->ImageBase);
+      write64le(Buf + OutputSectionOff, Thunk->getRVA() + Config->ImageBase + Offset);
     } else {
-      write32le(Buf + OutputSectionOff, Thunk->getRVA() + Config->ImageBase);
+      write32le(Buf + OutputSectionOff, Thunk->getRVA() + Config->ImageBase + Offset);
     }
   }
 
   void getBaserels(std::vector<Baserel> *Res) override {
     Res->emplace_back(RVA);
   }
 
   Chunk *Thunk;

 }
 
 Chunk *DelayLoadContents::newThunkChunk(DefinedImportData *S, Chunk *Dir) {
   switch (Config->Machine) {
   case AMD64:
     return make<ThunkChunkX64>(S, Dir, Helper);
   case I386:
     return make<ThunkChunkX86>(S, Dir, Helper);
+  case ARMNT:
+    return make<ThunkChunkARM>(S, Dir, Helper);
   default:
     llvm_unreachable("unsupported machine type");
   }
 }
 
 EdataContents::EdataContents() {
   uint16_t MaxOrdinal = 0;
   for (Export &E : Config->Exports)

test/COFF/delayimports-armnt.test

+# REQUIRES: arm
+# RUN: yaml2obj < %s > %t.obj
+# RUN: lld-link %t.obj %p/Inputs/library.lib /subsystem:console \
+# RUN:   /entry:mainCRTStartup /alternatename:__delayLoadHelper2=mainCRTStartup \
+# RUN:   /delayload:library.dll /out:%t.exe
+# RUN: llvm-readobj -coff-imports %t.exe | FileCheck -check-prefix=IMPORT %s
+# RUN: llvm-readobj -coff-basereloc %t.exe | FileCheck -check-prefix=BASEREL %s
+# RUN: llvm-objdump -d %t.exe | FileCheck -check-prefix=DISASM %s
+
+# IMPORT:      Format: COFF-ARM
+# IMPORT-NEXT: Arch: thumb
+# IMPORT-NEXT: AddressSize: 32bit
+# IMPORT-NEXT: DelayImport {
+# IMPORT-NEXT:   Name: library.dll
+# IMPORT-NEXT:   Attributes: 0x1
+# IMPORT-NEXT:   ModuleHandle: 0x3000
+# IMPORT-NEXT:   ImportAddressTable: 0x3008
+# IMPORT-NEXT:   ImportNameTable: 0x2040
+# IMPORT-NEXT:   BoundDelayImportTable: 0x0
+# IMPORT-NEXT:   UnloadDelayImportTable: 0x0
+# IMPORT-NEXT:   Import {
+# IMPORT-NEXT:     Symbol: function (0)
+# IMPORT-NEXT:     Address: 0x401019
+# IMPORT-NEXT:   }
+# IMPORT-NEXT: }
+#
+# BASEREL:      BaseReloc [
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: ARM_MOV32(T)
+# BASEREL-NEXT:     Address: 0x1000
+# BASEREL-NEXT:   }
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: ARM_MOV32(T)
+# BASEREL-NEXT:     Address: 0x100C
+# BASEREL-NEXT:   }
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: ARM_MOV32(T)
+# BASEREL-NEXT:     Address: 0x1018
+# BASEREL-NEXT:   }
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: ARM_MOV32(T)
+# BASEREL-NEXT:     Address: 0x102E
+# BASEREL-NEXT:   }
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: HIGHLOW
+# BASEREL-NEXT:     Address: 0x3008
+# BASEREL-NEXT:   }
+# BASEREL-NEXT:   Entry {
+# BASEREL-NEXT:     Type: ABSOLUTE
+# BASEREL-NEXT:     Address: 0x3000
+# BASEREL-NEXT:   }
+# BASEREL-NEXT: ]
+#
+# DISASM:      401018:       43 f2 08 0c     movw    r12, #12296
+# DISASM-NEXT: 40101c:       c0 f2 40 0c     movt    r12, #64
+# DISASM-NEXT: 401020:       2d e9 0f 48     push.w  {r0, r1, r2, r3, r11, lr}
+# DISASM-NEXT: 401024:       0d f2 10 0b     addw    r11, sp, #16
+# DISASM-NEXT: 401028:       2d ed 10 0b     vpush   {d0, d1, d2, d3, d4, d5, d6, d7}
+# DISASM-NEXT: 40102c:       61 46           mov     r1, r12
+# DISASM-NEXT: 40102e:       42 f2 00 00     movw    r0, #8192
+# DISASM-NEXT: 401032:       c0 f2 40 00     movt    r0, #64
+# DISASM-NEXT: 401036:       ff f7 e3 ff     bl      #-58
+# DISASM-NEXT: 40103a:       84 46           mov     r12, r0
+# DISASM-NEXT: 40103c:       bd ec 10 0b     vpop    {d0, d1, d2, d3, d4, d5, d6, d7}
+# DISASM-NEXT: 401040:       bd e8 0f 48     pop.w   {r0, r1, r2, r3, r11, lr}
+# DISASM-NEXT: 401044:       60 47           bx      r12
+
+--- !COFF
+header:
+  Machine:         IMAGE_FILE_MACHINE_ARMNT
+  Characteristics: [  ]
+sections:
+  - Name:            .text
+    Characteristics: [ IMAGE_SCN_CNT_CODE, IMAGE_SCN_MEM_PURGEABLE, IMAGE_SCN_MEM_16BIT, IMAGE_SCN_MEM_EXECUTE, IMAGE_SCN_MEM_READ ]
+    Alignment:       4
+    SectionData:     40F20000C0F2000000680047
+    Relocations:
+      - VirtualAddress:  0
+        SymbolName:      __imp_function
+        Type:            17
+symbols:
+  - Name:            .text
+    Value:           0
+    SectionNumber:   1
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_STATIC
+    SectionDefinition:
+      Length:          12
+      NumberOfRelocations: 1
+      NumberOfLinenumbers: 0
+      CheckSum:        0
+      Number:          1
+  - Name:            mainCRTStartup
+    Value:           0
+    SectionNumber:   1
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_FUNCTION
+    StorageClass:    IMAGE_SYM_CLASS_EXTERNAL
+  - Name:            __imp_function
+    Value:           0
+    SectionNumber:   0
+    SimpleType:      IMAGE_SYM_TYPE_NULL
+    ComplexType:     IMAGE_SYM_DTYPE_NULL
+    StorageClass:    IMAGE_SYM_CLASS_EXTERNAL
+...