PowerPC PLT stub tidy

This is in preparation for the next patch adding Spectre variant 2
mitigation for PowerPC and PowerPC64.  Besides tidying code involved
in stub output (to reduce the number of places where bctr is output),
the patch adds some user visible features:

1) PowerPC64 ELFv2 global entry stubs now are aligned under the
   control of --plt-align, with a default alignment of 32 bytes.
2) PowerPC64 __glink_PLTresolve is no longer padded out with nops.
3) PowerPC32 PLT stubs are aligned under the control of --plt-align,
   with the default alignment being 16 bytes as before.
4) The PowerPC32 branch/nop table emitted before __glink_PLTresolve
   is now smaller in many cases.  It was sized incorrectly when the
   __tls_get_addr_opt stub was used, and unnecessarily included space
   for local ifuncs.

bfd/
	* elf32-ppc.c (GLINK_ENTRY_SIZE): Add parameters, handle
	__tls_get_addr_opt, and alignment sizing.
	(TLS_GET_ADDR_GLINK_SIZE): Delete.
	(is_nonpic_glink_stub): Don't use GLINK_ENTRY_SIZE.
	(ppc_elf_get_synthetic_symtab): Recognize stubs spaced at 4, 6,
	or 8 insns.
	(ppc_elf_link_hash_table_create): Init new ppc_elf_params field.
	(allocate_dynrelocs): Use new GLINK_ENTRY_SIZE.
	(ppc_elf_size_dynamic_sections): Likewise.  Size branch table
	by PLT reloc count.
	(write_glink_stub): Handle __tls_get_addr_opt stub.
	Pad out to size given by GLINK_ENTRY_SIZE.
	(ppc_elf_relocate_section): Adjust write_glink_stub call.
	(ppc_elf_finish_dynamic_symbol): Likewise.
	(ppc_elf_finish_dynamic_sections): Write PLTresolve without using
	insn array since so many need rewriting.
	* elf32-ppc.h (struct ppc_elf_params): Add plt_stub_align.
	* elf64-ppc.c (GLINK_PLTRESOLVE_SIZE): Rename from
	GLINK_CALL_STUB_SIZE.  Add htab param and evaluate to size without
	nops.  Adjust all uses.
	(ppc64_elf_get_synthetic_symtab): Don't use GLINK_CALL_STUB_SIZE
	in glink_vma calculation.
	(struct ppc_link_hash_table): Add global_entry section pointer.
	(create_linkage_sections): Create separate section for global
	entry stubs.
	(PPC_LO, PPC_HI, PPC_HA): Move earlier.
	(size_global_entry_stubs): Handle sizing for aligned stubs.
	(ppc64_elf_size_dynamic_sections): Handle global_entry alloc,
	and don't stash end of glink branch table in rawsize.
	(ppc_build_one_stub): Rewrite stub size calculations.
	(build_global_entry_stubs): Use new section.
	(ppc64_elf_build_stubs): Don't pad __glink_PLTresolve with nops.
	Build lazy link stubs out to end of section.  Build global entry
	stubs in new section.
gold/
	* options.h (plt_align): Support for PowerPC32 too.
	* powerpc.cc (Stub_table::stub_align): Heed --plt-align for 32-bit.
	(Stub_table::plt_call_size, branch_stub_size): Tidy.
	(Stub_table::plt_call_align): Implement using stub_align.
	(Output_data_glink::global_entry_align): New function.
	(Output_data_glink::global_entry_off): New function.
	(Output_data_glink::global_entry_address): Use global_entry_off.
	(Output_data_glink::pltresolve_size): New function, replacing
	pltresolve_size_ constant.  Update all uses.
	(Output_data_glink::add_global_entry): Align offset.
	(Output_data_glink::set_final_data_size): Use global_entry_align.
	(Stub_table::do_write): Don't pad __glink_PLTrelsolve with nops.
	Tidy stub output.  Use global_entry_off.
ld/
	* emultempl/ppc32elf.em (params): Init new field.
	(enum ppc32_opt): New enum to define OPTION_* values.  Add
	OPTION_PLT_ALIGN and OPTION_NO_PLT_ALIGN.
	(PARSE_AND_LIST_LONGOPTS): Handle new options.
	(PARSE_AND_LIST_ARGS_CASES): Likewise.
	(PARSE_AND_LIST_OPTIONS): Likewise.  Break up help output.
	* emultempl/ppc64elf.em (ppc_add_stub_section): Init alignment
	correctly for negative --plt-stub-align.
	* testsuite/ld-powerpc/elfv2exe.d,
	* testsuite/ld-powerpc/elfv2so.d,
	* testsuite/ld-powerpc/relbrlt.d,
	* testsuite/ld-powerpc/relbrlt.s,
	* testsuite/ld-powerpc/tlsexe.d,
	* testsuite/ld-powerpc/tlsexe.r,
	* testsuite/ld-powerpc/tlsexe32.d,
	* testsuite/ld-powerpc/tlsexe32.g,
	* testsuite/ld-powerpc/tlsexe32.r,
	* testsuite/ld-powerpc/tlsexetoc.d,
	* testsuite/ld-powerpc/tlsexetoc.r,
	* testsuite/ld-powerpc/tlsopt5_32.d,
	* testsuite/ld-powerpc/tlsso.d,
	* testsuite/ld-powerpc/tlstocso.d: Update for changed stub order.

2 files changed, 66 insertions, 22 deletions

diff --git a/ld/emultempl/ppc32elf.em b/ld/emultempl/ppc32elf.em
index 6852e9b..70dd5a0 100644
--- a/ld/emultempl/ppc32elf.em
+++ b/ld/emultempl/ppc32elf.em
@@ -38,7 +38,8 @@ static int notlsopt = 0;
 /* Choose the correct place for .got.  */
 static int old_got = 0;
 
-static struct ppc_elf_params params = { PLT_UNSET, -1, 0, 0, 0, 0, 0, 0, 0 };
+static struct ppc_elf_params params = { PLT_UNSET, 0, -1,
+					0, 0, 0, 0, 0, 0, 0 };
 
 static void
 ppc_after_open_output (void)
@@ -239,17 +240,22 @@ fi
 # parse_args and list_options functions.
 #
 PARSE_AND_LIST_PROLOGUE=${PARSE_AND_LIST_PROLOGUE}'
-#define OPTION_NO_TLS_OPT		321
-#define OPTION_NO_TLS_GET_ADDR_OPT	(OPTION_NO_TLS_OPT + 1)
-#define OPTION_NEW_PLT			(OPTION_NO_TLS_GET_ADDR_OPT + 1)
-#define OPTION_OLD_PLT			(OPTION_NEW_PLT + 1)
-#define OPTION_OLD_GOT			(OPTION_OLD_PLT + 1)
-#define OPTION_STUBSYMS			(OPTION_OLD_GOT + 1)
-#define OPTION_NO_STUBSYMS		(OPTION_STUBSYMS + 1)
-#define OPTION_PPC476_WORKAROUND	(OPTION_NO_STUBSYMS + 1)
-#define OPTION_NO_PPC476_WORKAROUND	(OPTION_PPC476_WORKAROUND + 1)
-#define OPTION_NO_PICFIXUP		(OPTION_NO_PPC476_WORKAROUND + 1)
-#define OPTION_VLE_RELOC_FIXUP		(OPTION_NO_PICFIXUP + 1)
+enum ppc32_opt
+{
+  OPTION_NO_TLS_OPT = 321,
+  OPTION_NO_TLS_GET_ADDR_OPT,
+  OPTION_NEW_PLT,
+  OPTION_OLD_PLT,
+  OPTION_PLT_ALIGN,
+  OPTION_NO_PLT_ALIGN,
+  OPTION_OLD_GOT,
+  OPTION_STUBSYMS,
+  OPTION_NO_STUBSYMS,
+  OPTION_PPC476_WORKAROUND,
+  OPTION_NO_PPC476_WORKAROUND,
+  OPTION_NO_PICFIXUP,
+  OPTION_VLE_RELOC_FIXUP
+};
 '
 
 PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
@@ -261,6 +267,8 @@ if test -z "$VXWORKS_BASE_EM_FILE" ; then
   PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
   { "secure-plt", no_argument, NULL, OPTION_NEW_PLT },
   { "bss-plt", no_argument, NULL, OPTION_OLD_PLT },
+  { "plt-align", no_argument, NULL, OPTION_PLT_ALIGN },
+  { "no-plt-align", no_argument, NULL, OPTION_NO_PLT_ALIGN },
   { "sdata-got", no_argument, NULL, OPTION_OLD_GOT },'
 fi
 PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
@@ -272,21 +280,47 @@ PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
 
 PARSE_AND_LIST_OPTIONS=${PARSE_AND_LIST_OPTIONS}'
   fprintf (file, _("\
-  --emit-stub-syms            Label linker stubs with a symbol.\n\
-  --no-emit-stub-syms         Don'\''t label linker stubs with a symbol.\n\
-  --no-tls-optimize           Don'\''t try to optimize TLS accesses.\n\
-  --no-tls-get-addr-optimize  Don'\''t use a special __tls_get_addr call.\n'
+  --emit-stub-syms            Label linker stubs with a symbol.\n"
+		   ));
+  fprintf (file, _("\
+  --no-emit-stub-syms         Don'\''t label linker stubs with a symbol.\n"
+		   ));
+  fprintf (file, _("\
+  --no-tls-optimize           Don'\''t try to optimize TLS accesses.\n"
+		   ));
+  fprintf (file, _("\
+  --no-tls-get-addr-optimize  Don'\''t use a special __tls_get_addr call.\n"
+		   ));'
 if test -z "$VXWORKS_BASE_EM_FILE" ; then
   PARSE_AND_LIST_OPTIONS=${PARSE_AND_LIST_OPTIONS}'\
-  --secure-plt                Use new-style PLT if possible.\n\
-  --bss-plt                   Force old-style BSS PLT.\n\
-  --sdata-got                 Force GOT location just before .sdata.\n'
+  fprintf (file, _("\
+  --secure-plt                Use new-style PLT if possible.\n"
+		   ));
+  fprintf (file, _("\
+  --bss-plt                   Force old-style BSS PLT.\n"
+		   ));
+  fprintf (file, _("\
+  --plt-align                 Align PLT call stubs to fit cache lines.\n"
+		   ));
+  fprintf (file, _("\
+  --no-plt-align              Dont'\''t align individual PLT call stubs.\n"
+		   ));
+  fprintf (file, _("\
+  --sdata-got                 Force GOT location just before .sdata.\n"
+		   ));'
 fi
 PARSE_AND_LIST_OPTIONS=${PARSE_AND_LIST_OPTIONS}'\
+  fprintf (file, _("\
   --ppc476-workaround [=pagesize]\n\
-                              Avoid a cache bug on ppc476.\n\
-  --no-ppc476-workaround      Disable workaround.\n\
-  --no-pic-fixup              Don'\''t edit non-pic to pic.\n\
+                              Avoid a cache bug on ppc476.\n"
+		   ));
+  fprintf (file, _("\
+  --no-ppc476-workaround      Disable workaround.\n"
+		   ));
+  fprintf (file, _("\
+  --no-pic-fixup              Don'\''t edit non-pic to pic.\n"
+		   ));
+  fprintf (file, _("\
   --vle-reloc-fixup           Correct old object file 16A/16D relocation.\n"
 		   ));
 '
@@ -316,6 +350,14 @@ PARSE_AND_LIST_ARGS_CASES=${PARSE_AND_LIST_ARGS_CASES}'
       params.plt_style = PLT_OLD;
       break;
 
+    case OPTION_PLT_ALIGN:
+      params.plt_stub_align = 5;
+      break;
+
+    case OPTION_NO_PLT_ALIGN:
+      params.plt_stub_align = 0;
+      break;
+
     case OPTION_OLD_GOT:
       old_got = 1;
       break;
diff --git a/ld/emultempl/ppc64elf.em b/ld/emultempl/ppc64elf.em
index 76eeb07..840bd44 100644
--- a/ld/emultempl/ppc64elf.em
+++ b/ld/emultempl/ppc64elf.em
@@ -412,6 +412,8 @@ ppc_add_stub_section (const char *stub_sec_name, asection *input_section)
       || !bfd_set_section_alignment (stub_file->the_bfd, stub_sec,
 				     (params.plt_stub_align > 5
 				      ? params.plt_stub_align
+				      : params.plt_stub_align < -5
+				      ? -params.plt_stub_align
 				      : 5)))
     goto err_ret;