Correct PowerPC64 local-dynamic TLS linker optimization

The linker hardcoded r3 into a local-dynamic to local-exec TLS
optimization sequence.  This is normally the case since r3 is required
as a parameter to (the optimized out) __tls_get_addr call.  However,
it is possible for a compiler, LLVM in this case, to set up the
parameter value in another register then copy it to r3 before the
call.

When fixing this problem, I noticed that ppc32 had another bug when
optimizing away one of the TLS insns to a nop.

The patch also tidies a mask used by global-dynamic to initial-exec
TLS optimization, to just select the fields needed.  Leaving the
offset in the instruction wasn't a bug since it will be overwritten
anyway.

bfd/
	* elf64-ppc.c (ppc64_elf_relocate_section): Correct GOT_TLSLD
	optimization.  Tidy mask for GOT_TLSGD optimization.
	* elf32-ppc.c (ppc_elf_relocate_section): Likewise.  Correct
	location of nop zapping high insn too.
ld/testsuite/
	* ld-powerpc/tlsld.d, * ld-powerpc/tlsld.s: New test.
	* ld-powerpc/tlsld32.d, * ld-powerpc/tlsld32.s: New test.
	* ld-powerpc/powerpc.exp: Run them.  Move tocvar and tocnovar.

3 files changed, 26 insertions, 9 deletions

diff --git a/bfd/ChangeLog b/bfd/ChangeLog
index f5a50fa..464400f 100644
--- a/bfd/ChangeLog
+++ b/bfd/ChangeLog
@@ -1,3 +1,10 @@
+2015-01-29  Alan Modra  <amodra@gmail.com>
+
+	* elf64-ppc.c (ppc64_elf_relocate_section): Correct GOT_TLSLD
+	optimization.  Tidy mask for GOT_TLSGD optimization.
+	* elf32-ppc.c (ppc_elf_relocate_section): Likewise.  Correct
+	location of nop zapping high insn too.
+
 2015-01-28  Alan Modra  <amodra@gmail.com>
 
 	* elf64-ppc.h (struct ppc64_elf_params): Add "object_in_toc".
diff --git a/bfd/elf32-ppc.c b/bfd/elf32-ppc.c
index 7adb0f6..c467f14 100644
--- a/bfd/elf32-ppc.c
+++ b/bfd/elf32-ppc.c
@@ -7760,8 +7760,8 @@ ppc_elf_relocate_section (bfd *output_bfd,
 			  + R_PPC_GOT_TPREL16);
 	      else
 		{
-		  bfd_put_32 (output_bfd, NOP, contents + rel->r_offset);
 		  rel->r_offset -= d_offset;
+		  bfd_put_32 (output_bfd, NOP, contents + rel->r_offset);
 		  r_type = R_PPC_NONE;
 		}
 	      rel->r_info = ELF32_R_INFO (r_symndx, r_type);
@@ -7794,12 +7794,16 @@ ppc_elf_relocate_section (bfd *output_bfd,
 		  && branch_reloc_hash_match (input_bfd, rel + 1,
 					      htab->tls_get_addr))
 		offset = rel[1].r_offset;
+	      /* We read the low GOT_TLS insn because we need to keep
+		 the destination reg.  It may be something other than
+		 the usual r3, and moved to r3 before the call by
+		 intervening code.  */
+	      insn1 = bfd_get_32 (output_bfd,
+				  contents + rel->r_offset - d_offset);
 	      if ((tls_mask & tls_gd) != 0)
 		{
 		  /* IE */
-		  insn1 = bfd_get_32 (output_bfd,
-				      contents + rel->r_offset - d_offset);
-		  insn1 &= (1 << 26) - 1;
+		  insn1 &= (0x1f << 21) | (0x1f << 16);
 		  insn1 |= 32 << 26;	/* lwz */
 		  if (offset != (bfd_vma) -1)
 		    {
@@ -7814,7 +7818,8 @@ ppc_elf_relocate_section (bfd *output_bfd,
 	      else
 		{
 		  /* LE */
-		  insn1 = 0x3c620000;	/* addis 3,2,0 */
+		  insn1 &= 0x1f << 21;
+		  insn1 |= 0x3c020000;	/* addis r,2,0 */
 		  if (tls_gd == 0)
 		    {
 		      /* Was an LD reloc.  */
diff --git a/bfd/elf64-ppc.c b/bfd/elf64-ppc.c
index da37465..d597fec 100644
--- a/bfd/elf64-ppc.c
+++ b/bfd/elf64-ppc.c
@@ -13417,12 +13417,16 @@ ppc64_elf_relocate_section (bfd *output_bfd,
 					      htab->tls_get_addr,
 					      htab->tls_get_addr_fd))
 		offset = rel[1].r_offset;
+	      /* We read the low GOT_TLS (or TOC16) insn because we
+		 need to keep the destination reg.  It may be
+		 something other than the usual r3, and moved to r3
+		 before the call by intervening code.  */
+	      insn1 = bfd_get_32 (output_bfd,
+				  contents + rel->r_offset - d_offset);
 	      if ((tls_mask & tls_gd) != 0)
 		{
 		  /* IE */
-		  insn1 = bfd_get_32 (output_bfd,
-				      contents + rel->r_offset - d_offset);
-		  insn1 &= (1 << 26) - (1 << 2);
+		  insn1 &= (0x1f << 21) | (0x1f << 16);
 		  insn1 |= 58 << 26;	/* ld */
 		  insn2 = 0x7c636a14;	/* add 3,3,13 */
 		  if (offset != (bfd_vma) -1)
@@ -13437,7 +13441,8 @@ ppc64_elf_relocate_section (bfd *output_bfd,
 	      else
 		{
 		  /* LE */
-		  insn1 = 0x3c6d0000;	/* addis 3,13,0 */
+		  insn1 &= 0x1f << 21;
+		  insn1 |= 0x3c0d0000;	/* addis r,13,0 */
 		  insn2 = 0x38630000;	/* addi 3,3,0 */
 		  if (tls_gd == 0)
 		    {