PowerPC TPREL16_HA/LO reloc optimization

In the TLS GD/LD to LE optimization, ld replaces a sequence like

 addi 3,2,x@got@tlsgd		R_PPC64_GOT_TLSGD16	x
 bl __tls_get_addr(x@tlsgd)	R_PPC64_TLSGD		x
				R_PPC64_REL24		__tls_get_addr
 nop

with

 addis 3,13,x@tprel@ha		R_PPC64_TPREL16_HA	x
 addi 3,3,x@tprel@l		R_PPC64_TPREL16_LO	x
 nop

When the tprel offset is small, this can be further optimized to

 nop
 addi 3,13,x@tprel
 nop

bfd/
	* elf64-ppc.c (struct ppc_link_hash_table): Add do_tls_opt.
	(ppc64_elf_tls_optimize): Set it.
	(ppc64_elf_relocate_section): Nop addis on TPREL16_HA, and convert
	insn on TPREL16_LO and TPREL16_LO_DS relocs to use r13 when
	addis would add zero.
	* elf32-ppc.c (struct ppc_elf_link_hash_table): Add do_tls_opt.
	(ppc_elf_tls_optimize): Set it.
	(ppc_elf_relocate_section): Nop addis on TPREL16_HA, and convert
	insn on TPREL16_LO relocs to use r2 when addis would add zero.
gold/
	* powerpc.cc (Target_powerpc::Relocate::relocate): Nop addis on
	TPREL16_HA, and convert insn on TPREL16_LO and TPREL16_LO_DS
	relocs to use r2/r13 when addis would add zero.
ld/
	* testsuite/ld-powerpc/tls.s: Add calls with tls markers.
	* testsuite/ld-powerpc/tls32.s: Likewise.
	* testsuite/ld-powerpc/powerpc.exp: Run tls marker tests.
	* testsuite/ld-powerpc/tls.d: Adjust for TPREL16_HA/LO optimization.
	* testsuite/ld-powerpc/tlsexe.d: Likewise.
	* testsuite/ld-powerpc/tlsexetoc.d: Likewise.
	* testsuite/ld-powerpc/tlsld.d: Likewise.
	* testsuite/ld-powerpc/tlsmark.d: Likewise.
	* testsuite/ld-powerpc/tlsopt4.d: Likewise.
	* testsuite/ld-powerpc/tlstoc.d: Likewise.

1 files changed, 32 insertions, 0 deletions

diff --git a/gold/powerpc.cc b/gold/powerpc.cc
index 7f3f025..ff116e3 100644
--- a/gold/powerpc.cc
+++ b/gold/powerpc.cc
@@ -8974,6 +8974,38 @@ Target_powerpc<size, big_endian>::Relocate::relocate(
 	    }
 	  break;
 
+	case elfcpp::R_POWERPC_TPREL16_HA:
+	  if (parameters->options().tls_optimize() && value + 0x8000 < 0x10000)
+	    {
+	      Insn* iview = reinterpret_cast<Insn*>(view - d_offset);
+	      Insn insn = elfcpp::Swap<32, big_endian>::readval(iview);
+	      if ((insn & ((0x3f << 26) | 0x1f << 16))
+		  != ((15u << 26) | ((size == 32 ? 2 : 13) << 16)))
+		;
+	      else
+		{
+		  elfcpp::Swap<32, big_endian>::writeval(iview, nop);
+		  return true;
+		}
+	    }
+	  break;
+
+	case elfcpp::R_PPC64_TPREL16_LO_DS:
+	  if (size == 32)
+	    // R_PPC_TLSGD, R_PPC_TLSLD
+	    break;
+	  // Fall through.
+	case elfcpp::R_POWERPC_TPREL16_LO:
+	  if (parameters->options().tls_optimize() && value + 0x8000 < 0x10000)
+	    {
+	      Insn* iview = reinterpret_cast<Insn*>(view - d_offset);
+	      Insn insn = elfcpp::Swap<32, big_endian>::readval(iview);
+	      insn &= ~(0x1f << 16);
+	      insn |= (size == 32 ? 2 : 13) << 16;
+	      elfcpp::Swap<32, big_endian>::writeval(iview, insn);
+	    }
+	  break;
+
 	case elfcpp::R_PPC64_ENTRY:
 	  value = (target->got_section()->output_section()->address()
 		   + object->toc_base_offset());