[LLD] [COFF] Add support for the remaining ARM64 relocations

[mstorsjo]

Summary

Now only IMAGE_REL_ARM64_ABSOLUTE and IMAGE_REL_ARM64_TOKEN are unhandled.

Also add range checks for the existing BRANCH26 relocation.

[ruiu]

LGTM

COFF/Chunks.cpp

void SectionChunk::applyRelARM(uint8_t *Off, uint16_t Type, OutputSection *OS,
   default:
     fatal("unsupported relocation type 0x" + Twine::utohexstr(Type));
   }
 }
 
 // Interpret the existing immediate value as a byte offset to the
 // target symbol, then update the instruction with the immediate as
 // the page offset from the current instruction to the target.
-static void applyArm64Addr(uint8_t *Off, uint64_t S, uint64_t P) {
+static void applyArm64Addr(uint8_t *Off, uint64_t S, uint64_t P, int Shift) {
   uint32_t Orig = read32le(Off);
   uint64_t Imm = ((Orig >> 29) & 0x3) | ((Orig >> 3) & 0x1FFFFC);
   S += Imm;
-  Imm = (S >> 12) - (P >> 12);
+  Imm = (S >> Shift) - (P >> Shift);
   uint32_t ImmLo = (Imm & 0x3) << 29;
   uint32_t ImmHi = (Imm & 0x1FFFFC) << 3;
   uint64_t Mask = (0x3 << 29) | (0x1FFFFC << 3);
   write32le(Off, (Orig & ~Mask) | ImmLo | ImmHi);
 }
 
 // Update the immediate field in a AARCH64 ldr, str, and add instruction.
 // Optionally limit the range of the written immediate by one or more bits

 }
 
 static void applySecRelLdr(const SectionChunk *Sec, uint8_t *Off,
                            OutputSection *OS, uint64_t S) {
   if (checkSecRel(Sec, OS))
     applyArm64Ldr(Off, (S - OS->getRVA()) & 0xfff);
 }
 
+static void applyArm64Branch26(uint8_t *Off, int64_t V) {
+  if (!isInt<28>(V))
+    fatal("relocation out of range");
+  or32(Off, (V & 0x0FFFFFFC) >> 2);
+}
+
+static void applyArm64Branch19(uint8_t *Off, int64_t V) {
+  if (!isInt<21>(V))
+    fatal("relocation out of range");
+  or32(Off, (V & 0x001FFFFC) << 3);
+}
+
+static void applyArm64Branch14(uint8_t *Off, int64_t V) {
+  if (!isInt<16>(V))
+    fatal("relocation out of range");
+  or32(Off, (V & 0x0000FFFC) << 3);
+}
+
 void SectionChunk::applyRelARM64(uint8_t *Off, uint16_t Type, OutputSection *OS,
                                  uint64_t S, uint64_t P) const {
   switch (Type) {
-  case IMAGE_REL_ARM64_PAGEBASE_REL21: applyArm64Addr(Off, S, P); break;
+  case IMAGE_REL_ARM64_PAGEBASE_REL21: applyArm64Addr(Off, S, P, 12); break;
+  case IMAGE_REL_ARM64_REL21:          applyArm64Addr(Off, S, P, 0); break;
   case IMAGE_REL_ARM64_PAGEOFFSET_12A: applyArm64Imm(Off, S & 0xfff, 0); break;
   case IMAGE_REL_ARM64_PAGEOFFSET_12L: applyArm64Ldr(Off, S & 0xfff); break;
-  case IMAGE_REL_ARM64_BRANCH26:       or32(Off, ((S - P) & 0x0FFFFFFC) >> 2); break;
+  case IMAGE_REL_ARM64_BRANCH26:       applyArm64Branch26(Off, S - P); break;
+  case IMAGE_REL_ARM64_BRANCH19:       applyArm64Branch19(Off, S - P); break;
+  case IMAGE_REL_ARM64_BRANCH14:       applyArm64Branch14(Off, S - P); break;
   case IMAGE_REL_ARM64_ADDR32:         add32(Off, S + Config->ImageBase); break;
   case IMAGE_REL_ARM64_ADDR32NB:       add32(Off, S); break;
   case IMAGE_REL_ARM64_ADDR64:         add64(Off, S + Config->ImageBase); break;
   case IMAGE_REL_ARM64_SECREL:         applySecRel(this, Off, OS, S); break;
   case IMAGE_REL_ARM64_SECREL_LOW12A:  applySecRelLow12A(this, Off, OS, S); break;
   case IMAGE_REL_ARM64_SECREL_HIGH12A: applySecRelHigh12A(this, Off, OS, S); break;
   case IMAGE_REL_ARM64_SECREL_LOW12L:  applySecRelLdr(this, Off, OS, S); break;
+  case IMAGE_REL_ARM64_SECTION:        applySecIdx(Off, OS); break;
   default:
     fatal("unsupported relocation type 0x" + Twine::utohexstr(Type));
   }
 }
 
 void SectionChunk::writeTo(uint8_t *Buf) const {
   if (!hasData())
     return;
void ImportThunkChunkARM::writeTo(uint8_t *Buf) const {
   memcpy(Buf + OutputSectionOff, ImportThunkARM, sizeof(ImportThunkARM));
   // Fix mov.w and mov.t operands.
   applyMOV32T(Buf + OutputSectionOff, ImpSymbol->getRVA() + Config->ImageBase);
 }
 
 void ImportThunkChunkARM64::writeTo(uint8_t *Buf) const {
   int64_t Off = ImpSymbol->getRVA() & 0xfff;
   memcpy(Buf + OutputSectionOff, ImportThunkARM64, sizeof(ImportThunkARM64));
-  applyArm64Addr(Buf + OutputSectionOff, ImpSymbol->getRVA(), RVA);
+  applyArm64Addr(Buf + OutputSectionOff, ImpSymbol->getRVA(), RVA, 12);
   applyArm64Ldr(Buf + OutputSectionOff + 4, Off);
 }
 
 void LocalImportChunk::getBaserels(std::vector<Baserel> *Res) {
   Res->emplace_back(getRVA());
 }
 
 size_t LocalImportChunk::getSize() const {

test/COFF/Inputs/far-arm64-abs.s

+.global too_far26
+.global too_far19
+.global too_far14
+too_far26 = 0x08011000
+too_far19 = 0x00111000
+too_far14 = 0x00021000

test/COFF/arm64-branch-range.test

+// REQUIRES: aarch64
+
+// RUN: echo -e '.globl _start\n _start:\n bl too_far26\n' > %t.main26.s
+// RUN: echo -e '.globl _start\n _start:\n b.ne too_far19\n' > %t.main19.s
+// RUN: echo -e '.globl _start\n _start:\n tbz x0, #0, too_far14\n' > %t.main14.s
+
+// RUN: llvm-mc -filetype=obj -triple=aarch64-windows %t.main26.s -o %t.main26.obj
+// RUN: llvm-mc -filetype=obj -triple=aarch64-windows %t.main19.s -o %t.main19.obj
+// RUN: llvm-mc -filetype=obj -triple=aarch64-windows %t.main14.s -o %t.main14.obj
+// RUN: llvm-mc -filetype=obj -triple=aarch64-windows %S/Inputs/far-arm64-abs.s -o %t.far.obj
+
+// RUN: not lld-link -base:0x10000 -entry:_start -subsystem:console %t.main26.obj %t.far.obj -out:%t.exe 2>&1 | FileCheck %s
+// RUN: not lld-link -base:0x10000 -entry:_start -subsystem:console %t.main19.obj %t.far.obj -out:%t.exe 2>&1 | FileCheck %s
+// RUN: not lld-link -base:0x10000 -entry:_start -subsystem:console %t.main14.obj %t.far.obj -out:%t.exe 2>&1 | FileCheck %s
+
+// CHECK: relocation out of range

test/COFF/arm64-relocs-imports.test

 # BEFORE:       6c:       c0 03 5f d6     ret
 # BEFORE:       70:       08 00 00 00     <unknown>
 # BEFORE:       74:       00 00 00 00     <unknown>
 # BEFORE:       78:       01 00 00 00     <unknown>
 # BEFORE:       7c:       01 00 00 00     <unknown>
 # BEFORE:       80:       00 00 00 91     add     x0, x0, #0
 # BEFORE:       84:       00 00 40 91     add     x0, x0, #0, lsl #12
 # BEFORE:       88:       00 00 40 f9     ldr     x0, [x0]
+# BEFORE:       8c:       01 00 00 00     <unknown>
+# BEFORE:       90:       20 1a 09 30     adr x0, #74565
+# BEFORE:       94:       01 00 00 54     b.ne    #0
+# BEFORE:       98:       00 00 00 36     tbz     w0, #0, #0
 
 # AFTER: Disassembly of section .text:
 # AFTER:  140001000:      fe 0f 1f f8     str     x30, [sp, #-16]!
 # AFTER:  140001004:      00 00 00 b0     adrp    x0, #4096
 # AFTER:  140001008:      00 18 00 91     add     x0, x0, #6
-# AFTER:  14000100c:      20 00 00 94     bl      #128
+# AFTER:  14000100c:      24 00 00 94     bl      #144
 # AFTER:  140001010:      00 21 40 39     ldrb    w0, [x8, #8]
 # AFTER:  140001014:      00 11 40 79     ldrh    w0, [x8, #8]
 # AFTER:  140001018:      00 09 40 b9     ldr     w0, [x8, #8]
 # AFTER:  14000101c:      00 05 40 f9     ldr     x0, [x8, #8]
 # AFTER:  140001020:      00 21 00 39     strb    w0, [x8, #8]
 # AFTER:  140001024:      00 11 00 79     strh    w0, [x8, #8]
 # AFTER:  140001028:      00 09 00 b9     str     w0, [x8, #8]
 # AFTER:  14000102c:      00 05 00 f9     str     x0, [x8, #8]

 # AFTER:  14000106c:      c0 03 5f d6     ret
 # AFTER:  140001070:      10 20 00 40     <unknown>
 # AFTER:  140001074:      01 00 00 00     <unknown>
 # AFTER:  140001078:      09 20 00 00     <unknown>
 # AFTER:  14000107c:      09 00 00 00     <unknown>
 # AFTER:  140001080:      00 20 0e 91     add     x0, x0, #904
 # AFTER:  140001084:      00 04 40 91     add     x0, x0, #1, lsl #12
 # AFTER:  140001088:      00 c4 41 f9     ldr     x0, [x0, #904]
-# AFTER:  14000108c:      10 00 00 b0     adrp    x16, #4096
-# AFTER:  140001090:      10 2a 40 f9     ldr     x16, [x16, #80]
-# AFTER:  140001094:      00 02 1f d6     br      x16
+# AFTER:  14000108c:      03 00 00 00     <unknown>
+# AFTER:  140001090:      e0 95 09 30     adr     x0, #78525
+# AFTER:  140001094:      41 00 00 54     b.ne    #8
+# AFTER:  140001098:      20 00 00 36     tbz     w0, #0, #4
+# AFTER:  14000109c:      10 00 00 b0     adrp    x16, #4096
+# AFTER:  1400010a0:      10 2a 40 f9     ldr     x16, [x16, #80]
+# AFTER:  1400010a4:      00 02 1f d6     br      x16
 
 --- !COFF
 header:
   Machine:         IMAGE_FILE_MACHINE_ARM64
   Characteristics: [  ]
 sections:
   - Name:            .text
     Characteristics: [ IMAGE_SCN_CNT_CODE, IMAGE_SCN_MEM_EXECUTE, IMAGE_SCN_MEM_READ ]
     Alignment:       4
-    SectionData:     FE0F1FF80000009000080091000000940001403900014079000140B9000140F90001003900010079000100B9000100F90001403D0001407D000140BD000140FD0001C03D0001003D0001007D000100BD000100FD0001803D000540F9201A01B000FC4FF9E0031F2AFE0741F8C0035FD6080000000000000001000000010000000000009100004091000040f9
+    SectionData:     FE0F1FF80000009000080091000000940001403900014079000140B9000140F90001003900010079000100B9000100F90001403D0001407D000140BD000140FD0001C03D0001003D0001007D000100BD000100FD0001803D000540F9201A01B000FC4FF9E0031F2AFE0741F8C0035FD6080000000000000001000000010000000000009100004091000040f901000000201a09300100005400000036
     Relocations:
       - VirtualAddress:  4
         SymbolName:      .Lstr
         Type:            IMAGE_REL_ARM64_PAGEBASE_REL21
       - VirtualAddress:  8
         SymbolName:      .Lstr
         Type:            IMAGE_REL_ARM64_PAGEOFFSET_12A
       - VirtualAddress:  12
Relocations:
         SymbolName:      .Lglobal5000
         Type:            IMAGE_REL_ARM64_SECREL_LOW12A
       - VirtualAddress:  132
         SymbolName:      .Lglobal5000
         Type:            IMAGE_REL_ARM64_SECREL_HIGH12A
       - VirtualAddress:  136
         SymbolName:      .Lglobal5000
         Type:            IMAGE_REL_ARM64_SECREL_LOW12L
+      - VirtualAddress:  140
+        SymbolName:      .Lglobal
+        Type:            IMAGE_REL_ARM64_SECTION
+      - VirtualAddress:  144
+        SymbolName:      .Lglobal
+        Type:            IMAGE_REL_ARM64_REL21
+      - VirtualAddress:  148
+        SymbolName:      function
+        Type:            IMAGE_REL_ARM64_BRANCH19
+      - VirtualAddress:  152
+        SymbolName:      function
+        Type:            IMAGE_REL_ARM64_BRANCH14
   - Name:            .data
     Characteristics: [ IMAGE_SCN_CNT_INITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
     Alignment:       4
     SectionData:     ''
   - Name:            .bss
     Characteristics: [ IMAGE_SCN_CNT_UNINITIALIZED_DATA, IMAGE_SCN_MEM_READ, IMAGE_SCN_MEM_WRITE ]
     Alignment:       4
     SectionData:     ''