[MC][ARM] Make .reloc support arbitrary relocation types

Generalizes D61992. In GNU as, the .reloc directive supports arbitrary relocation types.

A MCFixupKind value `V` larger than or equal to FirstLiteralRelocationKind
is used to represent the relocation type whose number is V-FirstLiteralRelocationKind.

This is useful for linker tests. Without the feature the assembler
cannot produce certain relocation records (e.g.  R_ARM_ALU_PC_G0/R_ARM_LDR_PC_G0)
This helps move forward D75349 and D76575.

Differential Revision: https://reviews.llvm.org/D76746

include/llvm/MC/MCFixup.h

@@ -55,9 +55,14 @@ enum MCFixupKind {
 
   FirstTargetFixupKind = 128,
 
-  // Limit range of target fixups, in case we want to pack more efficiently
-  // later.
-  MaxTargetFixupKind = (1 << 8)
+  /// The range [FirstLiteralRelocationKind, MaxTargetFixupKind) is used for
+  /// relocations coming from .reloc directive. Fixup kind
+  /// FirstLiteralRelocationKind+V represents the relocation type with number V.
+  FirstLiteralRelocationKind = 256,
+
+  /// Set limit to accommodate the highest reloc type in use for all Targets,
+  /// currently R_AARCH64_IRELATIVE at 1032, including room for expansion.
+  MaxFixupKind = FirstLiteralRelocationKind + 1032 + 32,
 };
 
 /// Encode information on a single operation to perform on a byte
@@ -92,7 +97,7 @@ class MCFixup {
 public:
   static MCFixup create(uint32_t Offset, const MCExpr *Value,
                         MCFixupKind Kind, SMLoc Loc = SMLoc()) {
-    assert(Kind < MaxTargetFixupKind && "Kind out of range!");
+    assert(Kind <= MaxFixupKind && "Kind out of range!");
     MCFixup FI;
     FI.Value = Value;
     FI.Offset = Offset;

lib/Target/ARM/MCTargetDesc/ARMAsmBackend.cpp

@@ -48,10 +48,17 @@ public:
 } // end anonymous namespace
 
 Optional<MCFixupKind> ARMAsmBackend::getFixupKind(StringRef Name) const {
-  if (STI.getTargetTriple().isOSBinFormatELF() && Name == "R_ARM_NONE")
-    return FK_NONE;
+  if (!STI.getTargetTriple().isOSBinFormatELF())
+    return None;
 
-  return MCAsmBackend::getFixupKind(Name);
+  unsigned Type = llvm::StringSwitch<unsigned>(Name)
+#define ELF_RELOC(X, Y) .Case(#X, Y)
+#include "llvm/BinaryFormat/ELFRelocs/ARM.def"
+#undef ELF_RELOC
+                      .Default(-1u);
+  if (Type == -1u)
+    return None;
+  return static_cast<MCFixupKind>(FirstLiteralRelocationKind + Type);
 }
 
 const MCFixupKindInfo &ARMAsmBackend::getFixupKindInfo(MCFixupKind Kind) const {
@@ -172,6 +179,11 @@ const MCFixupKindInfo &ARMAsmBackend::getFixupKindInfo(MCFixupKind Kind) const {
       {"fixup_le", 0, 32, MCFixupKindInfo::FKF_IsPCRel}
   };
 
+  // Fixup kinds from .reloc directive are like R_ARM_NONE. They do not require
+  // any extra processing.
+  if (Kind >= FirstLiteralRelocationKind)
+    return MCAsmBackend::getFixupKindInfo(FK_NONE);
+
   if (Kind < FirstTargetFixupKind)
     return MCAsmBackend::getFixupKindInfo(Kind);
 
@@ -438,7 +450,6 @@ unsigned ARMAsmBackend::adjustFixupValue(const MCAssembler &Asm,
   default:
     Ctx.reportError(Fixup.getLoc(), "bad relocation fixup type");
     return 0;
-  case FK_NONE:
   case FK_Data_1:
   case FK_Data_2:
   case FK_Data_4:
@@ -871,7 +882,7 @@ bool ARMAsmBackend::shouldForceRelocation(const MCAssembler &Asm,
   const MCSymbolRefExpr *A = Target.getSymA();
   const MCSymbol *Sym = A ? &A->getSymbol() : nullptr;
   const unsigned FixupKind = Fixup.getKind();
-  if (FixupKind == FK_NONE)
+  if (FixupKind >= FirstLiteralRelocationKind)
     return true;
   if (FixupKind == ARM::fixup_arm_thumb_bl) {
     assert(Sym && "How did we resolve this?");
@@ -915,9 +926,6 @@ static unsigned getFixupKindNumBytes(unsigned Kind) {
   default:
     llvm_unreachable("Unknown fixup kind!");
 
-  case FK_NONE:
-    return 0;
-
   case FK_Data_1:
   case ARM::fixup_arm_thumb_bcc:
   case ARM::fixup_arm_thumb_cp:
@@ -979,9 +987,6 @@ static unsigned getFixupKindContainerSizeBytes(unsigned Kind) {
   default:
     llvm_unreachable("Unknown fixup kind!");
 
-  case FK_NONE:
-    return 0;
-
   case FK_Data_1:
     return 1;
   case FK_Data_2:
@@ -1037,7 +1042,10 @@ void ARMAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
                                MutableArrayRef<char> Data, uint64_t Value,
                                bool IsResolved,
                                const MCSubtargetInfo* STI) const {
-  unsigned NumBytes = getFixupKindNumBytes(Fixup.getKind());
+  unsigned Kind = Fixup.getKind();
+  if (Kind >= FirstLiteralRelocationKind)
+    return;
+  unsigned NumBytes = getFixupKindNumBytes(Kind);
   MCContext &Ctx = Asm.getContext();
   Value = adjustFixupValue(Asm, Fixup, Target, Value, IsResolved, Ctx, STI);
   if (!Value)
@@ -1049,7 +1057,7 @@ void ARMAsmBackend::applyFixup(const MCAssembler &Asm, const MCFixup &Fixup,
   // Used to point to big endian bytes.
   unsigned FullSizeBytes;
   if (Endian == support::big) {
-    FullSizeBytes = getFixupKindContainerSizeBytes(Fixup.getKind());
+    FullSizeBytes = getFixupKindContainerSizeBytes(Kind);
     assert((Offset + FullSizeBytes) <= Data.size() && "Invalid fixup size!");
     assert(NumBytes <= FullSizeBytes && "Invalid fixup size!");
   }

lib/Target/ARM/MCTargetDesc/ARMELFObjectWriter.cpp

@@ -79,6 +79,9 @@ unsigned ARMELFObjectWriter::GetRelocTypeInner(const MCValue &Target,
                                                const MCFixup &Fixup,
                                                bool IsPCRel,
                                                MCContext &Ctx) const {
+  unsigned Kind = Fixup.getTargetKind();
+  if (Kind >= FirstLiteralRelocationKind)
+    return Kind - FirstLiteralRelocationKind;
   MCSymbolRefExpr::VariantKind Modifier = Target.getAccessVariant();
 
   if (IsPCRel) {
@@ -152,12 +155,10 @@ unsigned ARMELFObjectWriter::GetRelocTypeInner(const MCValue &Target,
       return ELF::R_ARM_THM_BF18;
     }
   }
-  switch (Fixup.getTargetKind()) {
+  switch (Kind) {
   default:
     Ctx.reportFatalError(Fixup.getLoc(), "unsupported relocation on symbol");
     return ELF::R_ARM_NONE;
-  case FK_NONE:
-    return ELF::R_ARM_NONE;
   case FK_Data_1:
     switch (Modifier) {
     default:

test/MC/ARM/reloc-directive-err.s

@@ -0,0 +1,6 @@
+# RUN: llvm-mc -triple=armv7 %s 2>&1 | FileCheck --check-prefix=PRINT %s
+# RUN: not llvm-mc -filetype=obj -triple=armv7 %s -o /dev/null 2>&1 | FileCheck %s
+
+# PRINT: .reloc 0, R_INVALID, 0
+# CHECK: {{.*}}.s:[[# @LINE+1]]:11: error: unknown relocation name
+.reloc 0, R_INVALID, 0

test/MC/ARM/reloc-directive.s

@@ -17,6 +17,10 @@
   .reloc 4, R_ARM_NONE, foo+4
   .reloc 0, R_ARM_NONE, 8
 
+  .reloc 0, R_ARM_ALU_PC_G0, .data+2
+  .reloc 0, R_ARM_LDR_PC_G0, foo+3
+  .reloc 0, R_ARM_THM_ALU_PREL_11_0, 5
+
 .data
 .globl foo
 foo:
@@ -27,11 +31,17 @@ foo:
 # PRINT: .reloc 8, R_ARM_NONE, .data
 # PRINT: .reloc 4, R_ARM_NONE, foo+4
 # PRINT: .reloc 0, R_ARM_NONE, 8
+# PRINT: .reloc 0, R_ARM_ALU_PC_G0, .data+2
+# PRINT: .reloc 0, R_ARM_LDR_PC_G0, foo+3
+# PRINT: .reloc 0, R_ARM_THM_ALU_PREL_11_0, 5
 
 # ARM relocations use the Elf32_Rel format. Addends are neither stored in the
 # relocation entries nor applied in the referenced locations.
 # CHECK:      0x8 R_ARM_NONE .data 0x0
 # CHECK-NEXT: 0x4 R_ARM_NONE foo 0x0
 # CHECK-NEXT: 0x0 R_ARM_NONE - 0x0
+# CHECK-NEXT: 0x0 R_ARM_ALU_PC_G0 .data 0x0
+# CHECK-NEXT: 0x0 R_ARM_LDR_PC_G0 foo 0x0
+# CHECK-NEXT: 0x0 R_ARM_THM_ALU_PREL_11_0 - 0x0
 
 # HEX: 0x00000000 00000000 00000000