[X86][MC] Support R_X86_64_CODE_4_GOTPC32_TLSDESC

For

  lea name@tlsdesc(%rip), %reg

add

  R_X86_64_CODE_4_GOTPC32_TLSDESC = 45

if the instruction starts at 4 bytes before the relocation offset. This should
be used if reg is one of the additional general-purpose registers, r16-r31, in
Intel APX.  It is similar to R_X86_64_GOTPC32_TLSDESC and linker optimization
must take the different instruction encoding into account.

Linker can convert the instructions with R_X86_64_CODE_4_GOTPC32_TLSDESC to

  mov $name@tpoff, %reg

if the first byte of the instruction at the relocation offset - 4 is
0xd5 (namely, encoded w/REX2 prefix) when possible.

Binutils patch: bminor/binutils-gdb@a533c8d
Binutils mailthread: https://sourceware.org/pipermail/binutils/2023-December/131463.html
ABI discussion: https://groups.google.com/g/x86-64-abi/c/ACwD-UQXVDs/m/vrgTenKyFwAJ
Blog: https://kanrobert.github.io/rfc/All-about-APX-relocation

Author: fzou1

llvm/include/llvm/BinaryFormat/ELFRelocs/x86_64.def

@@ -44,3 +44,4 @@ ELF_RELOC(R_X86_64_IRELATIVE,   37)
 ELF_RELOC(R_X86_64_GOTPCRELX,   41)
 ELF_RELOC(R_X86_64_REX_GOTPCRELX,    42)
 ELF_RELOC(R_X86_64_REX2_GOTPCRELX,    43)
+ELF_RELOC(R_X86_64_CODE_4_GOTPC32_TLSDESC,    45)

llvm/lib/Target/X86/MCTargetDesc/X86ELFObjectWriter.cpp

@@ -191,6 +191,8 @@ static unsigned getRelocType64(MCContext &Ctx, SMLoc Loc,
   case MCSymbolRefExpr::VK_TLSCALL:
     return ELF::R_X86_64_TLSDESC_CALL;
   case MCSymbolRefExpr::VK_TLSDESC:
+    if ((unsigned)Kind == X86::reloc_riprel_4byte_relax_rex2)
+      return ELF::R_X86_64_CODE_4_GOTPC32_TLSDESC;
     return ELF::R_X86_64_GOTPC32_TLSDESC;
   case MCSymbolRefExpr::VK_TLSGD:
     checkIs32(Ctx, Loc, Type);

llvm/lib/Target/X86/MCTargetDesc/X86MCCodeEmitter.cpp

@@ -666,6 +666,7 @@ void X86MCCodeEmitter::emitMemModRMByte(
       case X86::SBB64rm:
       case X86::SUB64rm:
       case X86::XOR64rm:
+      case X86::LEA64r:
         return Kind == REX2  ? X86::reloc_riprel_4byte_relax_rex2
                : Kind == REX ? X86::reloc_riprel_4byte_relax_rex
                              : X86::reloc_riprel_4byte_relax;

llvm/test/MC/X86/tlsdesc-64.s

@@ -17,3 +17,15 @@
 leaq a@tlsdesc(%rip), %rax
 call *a@tlscall(%rax)
 addq %fs:0, %rax
+
+# PRINT:      leaq a@tlsdesc(%rip), %r16
+# PRINT-NEXT: callq *a@tlscall(%r16)
+
+# CHECK:      12: leaq (%rip), %r16  # 0x1a <{{.*}}>
+# CHECK-NEXT:   0000000000000016: R_X86_64_CODE_4_GOTPC32_TLSDESC a-0x4
+# CHECK-NEXT: 1a: callq *(%r16)
+# CHECK-NEXT:   000000000000001a: R_X86_64_TLSDESC_CALL a
+
+leaq a@tlsdesc(%rip), %r16
+call *a@tlscall(%r16)
+addq %fs:0, %r16