ppc476 icache bug workaround

This implements a work-around for an icache bug on 476 that can cause
execution of stale instructions when control falls through from one
page to the next.  The idea is to prevent such fall-through by
replacing the last instruction on a page with a branch to a patch
area containing the instruction, then branch to the next page.

The patch also fixes a number of bugs in the existing support for long
branch trampolines.

bfd/
	* elf32-ppc.c (struct ppc_elf_link_hash_table): Add params.
	Delete emit_stub_syms, no_tls_get_addr_opt.  Update all uses.
	(ppc_elf_link_params): New function.
	(ppc_elf_create_glink): Align .glink to 64 bytes for ppc476
	workaround.
	(ppc_elf_select_plt_layout): Remove plt_style and emit_stub_syms
	parameters.  Use htab->params instead.
	(ppc_elf_tls_setup): Remove no_tls_get_addr_opt parameter.
	(ppc_elf_size_dynamic_sections): Align __glink_PLTresolve to
	64 bytes for ppc476 workaround.
	(struct ppc_elf_relax_info): New.
	(ppc_elf_relax_section): Exclude linker created sections and
	those too small to hold one instruction.  Don't add another
	branch 	around trampolines on later relax passes.  Don't
	generate trampolines for undefined symbols when !relocatable,
	nor for plugin symbols.  Allocate space for ppc476 workaround
	patch area.  Free fixups on error return path.
	(ppc_elf_relocate_section): Handle ppc476 workaround patching.
	* elf32-ppc.h (struct ppc_elf_params): New.
	(ppc_elf_select_plt_layout, ppc_elf_tls_setup): Update prototype.
	(ppc_elf_link_params): Declare.
	* section.c (SEC_INFO_TYPE_TARGET): Define.
	* bfd-in2.h: Regenerate.
ld/
	* emultempl/ppc32elf.em (no_tls_get_addr_opt, emit_stub_syms)
	plt_style): Delete.  Adjust all refs to instead use..
	(params): ..this.  New variable.
	(ppc_after_open_output): New function.  Tweak params and pass to
	ppc_elf_link_params.
	(ppc_after_open): Adjust ppc_elf_select_plt_layout call.
	(ppc_before_allocation): Adjust ppc_elf_tls_setup call.  Enable
	relaxation for ppc476 workaround.
	(PARSE_AND_LIST_*): Add --{no-,}ppc476-workaround support.
	(LDEMUL_CREATE_OUTPUT_SECTION_STATEMENTS): Define.

bfd/ChangeLog

@@ -1,3 +1,29 @@
+2014-02-03  Alan Modra  <amodra@gmail.com>
+
+	* elf32-ppc.c (struct ppc_elf_link_hash_table): Add params.
+	Delete emit_stub_syms, no_tls_get_addr_opt.  Update all uses.
+	(ppc_elf_link_params): New function.
+	(ppc_elf_create_glink): Align .glink to 64 bytes for ppc476
+	workaround.
+	(ppc_elf_select_plt_layout): Remove plt_style and emit_stub_syms
+	parameters.  Use htab->params instead.
+	(ppc_elf_tls_setup): Remove no_tls_get_addr_opt parameter.
+	(ppc_elf_size_dynamic_sections): Align __glink_PLTresolve to
+	64 bytes for ppc476 workaround.
+	(struct ppc_elf_relax_info): New.
+	(ppc_elf_relax_section): Exclude linker created sections and
+	those too small to hold one instruction.  Don't add another
+	branch 	around trampolines on later relax passes.  Don't
+	generate trampolines for undefined symbols when !relocatable,
+	nor for plugin symbols.  Allocate space for ppc476 workaround
+	patch area.  Free fixups on error return path.
+	(ppc_elf_relocate_section): Handle ppc476 workaround patching.
+	* elf32-ppc.h (struct ppc_elf_params): New.
+	(ppc_elf_select_plt_layout, ppc_elf_tls_setup): Update prototype.
+	(ppc_elf_link_params): Declare.
+	* section.c (SEC_INFO_TYPE_TARGET): Define.
+	* bfd-in2.h: Regenerate.
+
 2014-02-02  Sandra Loosemore  <sandra@codesourcery.com>
 
 	* elf32-nios2.c (struct elf32_nios2_link_hash_table): Add

bfd/bfd-in2.h

@@ -1437,6 +1437,7 @@ typedef struct bfd_section
 #define SEC_INFO_TYPE_MERGE     2
 #define SEC_INFO_TYPE_EH_FRAME  3
 #define SEC_INFO_TYPE_JUST_SYMS 4
+#define SEC_INFO_TYPE_TARGET    5
 
   /* Nonzero if this section uses RELA relocations, rather than REL.  */
   unsigned int use_rela_p:1;

bfd/elf32-ppc.h

@@ -26,9 +26,29 @@ enum ppc_elf_plt_type
   PLT_VXWORKS
 };
 
-int ppc_elf_select_plt_layout (bfd *, struct bfd_link_info *,
-			       enum ppc_elf_plt_type, int);
-asection *ppc_elf_tls_setup (bfd *, struct bfd_link_info *, int);
+/* Various options passed from the linker to bfd backend.  */
+struct ppc_elf_params
+{
+  /* Chooses the type of .plt.  */
+  enum ppc_elf_plt_type plt_style;
+
+  /* Whether to emit symbols for stubs.  */
+  int emit_stub_syms;
+
+  /* Whether to emit special stub for __tls_get_addr calls.  */
+  int no_tls_get_addr_opt;
+
+  /* Insert trampolines for branches that won't reach their destination.  */
+  int branch_trampolines;
+
+  /* Avoid execution falling into new page.  */
+  int ppc476_workaround;
+  int pagesize;
+};
+
+void ppc_elf_link_params (struct bfd_link_info *, struct ppc_elf_params *);
+int ppc_elf_select_plt_layout (bfd *, struct bfd_link_info *);
+asection *ppc_elf_tls_setup (bfd *, struct bfd_link_info *);
 bfd_boolean ppc_elf_tls_optimize (bfd *, struct bfd_link_info *);
 void ppc_elf_set_sdata_syms (bfd *, struct bfd_link_info *);
 extern bfd_boolean ppc_elf_modify_segment_map (bfd *,

bfd/section.c

@@ -388,6 +388,7 @@ CODE_FRAGMENT
 .#define SEC_INFO_TYPE_MERGE     2
 .#define SEC_INFO_TYPE_EH_FRAME  3
 .#define SEC_INFO_TYPE_JUST_SYMS 4
+.#define SEC_INFO_TYPE_TARGET    5
 .
 .  {* Nonzero if this section uses RELA relocations, rather than REL.  *}
 .  unsigned int use_rela_p:1;

ld/ChangeLog

@@ -1,3 +1,16 @@
+2014-02-03  Alan Modra  <amodra@gmail.com>
+
+	* emultempl/ppc32elf.em (no_tls_get_addr_opt, emit_stub_syms)
+	plt_style): Delete.  Adjust all refs to instead use..
+	(params): ..this.  New variable.
+	(ppc_after_open_output): New function.  Tweak params and pass to
+	ppc_elf_link_params.
+	(ppc_after_open): Adjust ppc_elf_select_plt_layout call.
+	(ppc_before_allocation): Adjust ppc_elf_tls_setup call.  Enable
+	relaxation for ppc476 workaround.
+	(PARSE_AND_LIST_*): Add --{no-,}ppc476-workaround support.
+	(LDEMUL_CREATE_OUTPUT_SECTION_STATEMENTS): Define.
+
 2014-02-02  Sebastian Huber  <sebastian.huber@embedded-brains.de>
 
 	* ld/ld.texinfo: Change ALIGN_WITH_INPUT documentation.

ld/emultempl/ppc32elf.em

@@ -35,15 +35,24 @@ fragment <<EOF
 
 /* Whether to run tls optimization.  */
 static int notlsopt = 0;
-static int no_tls_get_addr_opt = 0;
 
-/* Whether to emit symbols for stubs.  */
-static int emit_stub_syms = -1;
-
-/* Chooses the correct place for .plt and .got.  */
-static enum ppc_elf_plt_type plt_style = PLT_UNSET;
+/* Choose the correct place for .got.  */
 static int old_got = 0;
 
+static struct ppc_elf_params params = { PLT_UNSET, -1, 0, 0, 0, 0 };
+
+static void
+ppc_after_open_output (void)
+{
+  if (params.emit_stub_syms < 0)
+    params.emit_stub_syms = link_info.emitrelocations || link_info.shared;
+  if (params.pagesize == 0)
+    params.pagesize = config.commonpagesize;
+  if (link_info.relocatable)
+    params.ppc476_workaround = 0;
+  ppc_elf_link_params (&link_info, &params);
+}
+
 static void
 ppc_after_open (void)
 {
@@ -57,10 +66,7 @@ ppc_after_open (void)
       lang_output_section_statement_type *plt_os[2];
       lang_output_section_statement_type *got_os[2];
 
-      if (emit_stub_syms < 0)
-	emit_stub_syms = link_info.emitrelocations || link_info.shared;
-      new_plt = ppc_elf_select_plt_layout (link_info.output_bfd, &link_info,
-					   plt_style, emit_stub_syms);
+      new_plt = ppc_elf_select_plt_layout (link_info.output_bfd, &link_info);
       if (new_plt < 0)
 	einfo ("%X%P: select_plt_layout problem %E\n");
 
@@ -107,8 +113,7 @@ ppc_before_allocation (void)
 {
   if (is_ppc_elf (link_info.output_bfd))
     {
-      if (ppc_elf_tls_setup (link_info.output_bfd, &link_info,
-			     no_tls_get_addr_opt)
+      if (ppc_elf_tls_setup (link_info.output_bfd, &link_info)
 	  && !notlsopt)
 	{
 	  if (!ppc_elf_tls_optimize (link_info.output_bfd, &link_info))
@@ -121,9 +126,12 @@ ppc_before_allocation (void)
 
   gld${EMULATION_NAME}_before_allocation ();
 
+  if (RELAXATION_ENABLED)
+    params.branch_trampolines = 1;
+
   /* Turn on relaxation if executable sections have addresses that
      might make branches overflow.  */
-  if (RELAXATION_DISABLED_BY_DEFAULT)
+  else if (!RELAXATION_DISABLED_BY_USER)
     {
       bfd_vma low = (bfd_vma) -1;
       bfd_vma high = 0;
@@ -150,8 +158,11 @@ ppc_before_allocation (void)
 	    high = o->vma + o->rawsize - 1;
 	}
       if (high > low && high - low > (1 << 25) - 1)
-	ENABLE_RELAXATION;
+	params.branch_trampolines = 1;
     }
+
+  if (params.ppc476_workaround || params.branch_trampolines)
+    ENABLE_RELAXATION;
 }
 
 EOF
@@ -186,6 +197,8 @@ PARSE_AND_LIST_PROLOGUE=${PARSE_AND_LIST_PROLOGUE}'
 #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)
 '
 
 PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
@@ -196,6 +209,8 @@ PARSE_AND_LIST_LONGOPTS=${PARSE_AND_LIST_LONGOPTS}'
   { "secure-plt", no_argument, NULL, OPTION_NEW_PLT },
   { "bss-plt", no_argument, NULL, OPTION_OLD_PLT },
   { "sdata-got", no_argument, NULL, OPTION_OLD_GOT },
+  { "ppc476-workaround", optional_argument, NULL, OPTION_PPC476_WORKAROUND },
+  { "no-ppc476-workaround", no_argument, NULL, OPTION_NO_PPC476_WORKAROUND },
 '
 
 PARSE_AND_LIST_OPTIONS=${PARSE_AND_LIST_OPTIONS}'
@@ -206,17 +221,20 @@ PARSE_AND_LIST_OPTIONS=${PARSE_AND_LIST_OPTIONS}'
   --no-tls-get-addr-optimize  Don'\''t use a special __tls_get_addr call.\n\
   --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"
+  --sdata-got                 Force GOT location just before .sdata.\n\
+  --ppc476-workaround [=pagesize]\n\
+                              Avoid a cache bug on ppc476.\n\
+  --no-ppc476-workaround      Disable workaround.\n"
 		   ));
 '
 
 PARSE_AND_LIST_ARGS_CASES=${PARSE_AND_LIST_ARGS_CASES}'
     case OPTION_STUBSYMS:
-      emit_stub_syms = 1;
+      params.emit_stub_syms = 1;
       break;
 
     case OPTION_NO_STUBSYMS:
-      emit_stub_syms = 0;
+      params.emit_stub_syms = 0;
       break;
 
     case OPTION_NO_TLS_OPT:
@@ -224,15 +242,15 @@ PARSE_AND_LIST_ARGS_CASES=${PARSE_AND_LIST_ARGS_CASES}'
       break;
 
     case OPTION_NO_TLS_GET_ADDR_OPT:
-      no_tls_get_addr_opt = 1;
+      params.no_tls_get_addr_opt = 1;
       break;
 
     case OPTION_NEW_PLT:
-      plt_style = PLT_NEW;
+      params.plt_style = PLT_NEW;
       break;
 
     case OPTION_OLD_PLT:
-      plt_style = PLT_OLD;
+      params.plt_style = PLT_OLD;
       break;
 
     case OPTION_OLD_GOT:
@@ -241,11 +259,29 @@ PARSE_AND_LIST_ARGS_CASES=${PARSE_AND_LIST_ARGS_CASES}'
 
     case OPTION_TRADITIONAL_FORMAT:
       notlsopt = 1;
-      no_tls_get_addr_opt = 1;
+      params.no_tls_get_addr_opt = 1;
       return FALSE;
+
+    case OPTION_PPC476_WORKAROUND:
+      params.ppc476_workaround = 1;
+      if (optarg != NULL)
+	{
+	  char *end;
+	  params.pagesize = strtoul (optarg, &end, 0);
+	  if (*end
+	      || (params.pagesize < 4096 && params.pagesize != 0)
+	      || params.pagesize != (params.pagesize & -params.pagesize))
+	    einfo (_("%P%F: invalid pagesize `%s'\''\n"), optarg);
+	}
+      break;
+
+    case OPTION_NO_PPC476_WORKAROUND:
+      params.ppc476_workaround = 0;
+      break;
 '
 
 # Put these extra ppc32elf routines in ld_${EMULATION_NAME}_emulation
 #
+LDEMUL_CREATE_OUTPUT_SECTION_STATEMENTS=ppc_after_open_output
 LDEMUL_AFTER_OPEN=ppc_after_open
 LDEMUL_BEFORE_ALLOCATION=ppc_before_allocation