[PATCH] Use GCC LTO wrapper to get real symbols from LTO IR objects

["H.J. Lu" <hjl dot tools at gmail dot com>]

GCC LTO wrapper is needed to extract real symbols from LTO IR objects.
This patch does the following:

1. Set up GCC LTO wrapper for each LTO IR object.
2. Run GCC LTO wrapper to get the real object.
3. Extract symbol info from the real object.
4. Cleanup afterwards.

bfd/

	PR binutils/25355
	* plugin.c (bfd_plugin_close_and_cleanup): Removed.
	(plugin_list_entry): Add all_symbols_read, cleanup_handler,
	gcc, lto_wrapper, resolution_file, resolution_option, gcc_env,
	real_bfd, real_nsyms, real_syms, lto_nsyms and lto_syms.
	(get_lto_wrapper): New.
	(setup_lto_wrapper_env): Likewise.
	(current_plugin): Likewise.
	(register_all_symbols_read): Likewise.
	(register_cleanup): Likewise.
	(get_symbols): Likewise.
	(add_input_file): Likewise.
	(bfd_plugin_close_and_cleanup): Likewise.
	(claim_file): Removed.
	(register_claim_file): Set current_plugin->claim_file.
	(add_symbols): Make a copy of LTO symbols.  Set lto_nsyms and
	lto_syms in current_plugin.
	(try_claim): Use current_plugin->claim_file.  Call LTO plugin
	all_symbols_read handler.  Copy real symbols to plugin_data.
	Call LTO plugin cleanup handler.  Clean up for LTO wrapper.
	(try_load_plugin): Don't reuse the previous plugin for LTO
	wrapper.  Set up GCC LTO wrapper if possible.  Don't set
	plugin_list_iter->claim_file.
	(bfd_plugin_canonicalize_symtab): Use real LTO symbols if
	possible.
	* plugin.h (plugin_data_struct): Add real_bfd, real_nsyms and
	real_syms.

ld/

	PR binutils/25355
	* testsuite/ld-plugin/lto.exp: Run PR binutils/25355 test.
	* testsuite/ld-plugin/pr25355.c: New file.
	* testsuite/ld-plugin/pr25355.d: Likewise.
	* testsuite/lib/ld-lib.exp (run_cc_link_tests): Support
	compile only dump.
---
 bfd/plugin.c                     | 415 +++++++++++++++++++++++++++++--
 bfd/plugin.h                     |   3 +
 ld/testsuite/ld-plugin/lto.exp   |   5 +
 ld/testsuite/ld-plugin/pr25355.c |   2 +
 ld/testsuite/ld-plugin/pr25355.d |   4 +
 ld/testsuite/lib/ld-lib.exp      |   1 +
 6 files changed, 410 insertions(+), 20 deletions(-)
 create mode 100644 ld/testsuite/ld-plugin/pr25355.c
 create mode 100644 ld/testsuite/ld-plugin/pr25355.d

diff --git a/bfd/plugin.c b/bfd/plugin.c
index 537ab603110..891ce00fc34 100644
--- a/bfd/plugin.c
+++ b/bfd/plugin.c
@@ -69,7 +69,6 @@ dlerror (void)
 
 #endif /* !defined (HAVE_DLFCN_H) && defined (HAVE_WINDOWS_H)  */
 
-#define bfd_plugin_close_and_cleanup		      _bfd_generic_close_and_cleanup
 #define bfd_plugin_bfd_free_cached_info		      _bfd_generic_bfd_free_cached_info
 #define bfd_plugin_new_section_hook		      _bfd_generic_new_section_hook
 #define bfd_plugin_get_section_contents		      _bfd_generic_get_section_contents
@@ -124,13 +123,254 @@ message (int level ATTRIBUTE_UNUSED,
   return LDPS_OK;
 }
 
+struct plugin_list_entry
+{
+  void *handle;
+  ld_plugin_claim_file_handler claim_file;
+  ld_plugin_all_symbols_read_handler all_symbols_read;
+  ld_plugin_all_symbols_read_handler cleanup_handler;
+  char *gcc;
+  char *lto_wrapper;
+  char *resolution_file;
+  char *resolution_option;
+  char *gcc_env;
+  bfd *real_bfd;
+  long real_nsyms;
+  asymbol **real_syms;
+  int lto_nsyms;
+  const struct ld_plugin_symbol *lto_syms;
+  struct plugin_list_entry *next;
+};
+
+/* Use GCC LTO wrapper to covert LTO IR object to the real object.  */
+
+static void
+get_lto_wrapper (struct plugin_list_entry *plugin, const char *pname)
+{
+  struct stat st;
+  const char *real_name;
+  const char *base_name;
+  size_t length;
+  const char *target_start = NULL;
+  const char *target_end = NULL;
+  size_t target_length = 0;
+  char *gcc_name;
+  char *wrapper_name;
+  char *p;
+  char dir_seperator = '\0';
+
+  /* Check for PREFIX/libexec/gcc/TARGET/VERSION/liblto_plugin.so.  */
+  real_name = lrealpath (pname);
+  base_name = lbasename (real_name);
+
+  /* The directory length in plugin pathname.  */
+  length = base_name - real_name;
+
+  /* Skip if there is no PREFIX.  */
+  if (!length)
+    return;
+
+  p = (char *) real_name + length - 1;
+  if (IS_DIR_SEPARATOR (*p))
+    {
+      int level = 0;
+      for (; p != real_name; p--)
+	if (IS_DIR_SEPARATOR (*p))
+	  {
+	    level++;
+	    if (level == 2)
+	      target_end = p;
+	    else if (level == 3)
+	      {
+		target_start = p + 1;
+		target_length = target_end - target_start;
+	      }
+	    else if (level == 5)
+	      {
+		dir_seperator = *p;
+		break;
+	      }
+	  }
+    }
+
+  /* Skip if there is no TARGET nor PREFIX.  */
+  if (!target_length || !dir_seperator)
+    return;
+
+  gcc_name = bfd_malloc (length + target_length + sizeof ("gcc"));
+  memcpy (gcc_name, real_name, length);
+
+  /* Get PREFIX/bin/.  */
+  p += gcc_name - real_name;
+  memcpy (p + 1, "bin", 3);
+  p[4] = dir_seperator;
+
+  /* Try PREFIX/bin/TARGET-gcc first.  */
+  memcpy (p + 5, target_start, target_length);
+  p[5 + target_length] = '-';
+  memcpy (p + 5 + target_length + 1, "gcc", sizeof ("gcc"));
+  if (stat (gcc_name, &st) != 0 || !S_ISREG (st.st_mode))
+    {
+      /* Then try PREFIX/bin/gcc.  */
+      memcpy (p + 5, "gcc", sizeof ("gcc"));
+      if (stat (gcc_name, &st) != 0 || !S_ISREG (st.st_mode))
+	{
+	  free (gcc_name);
+	  return;
+	}
+    }
+
+  /* lto-wrapper should be in the same directory with LTO plugin.  */
+  wrapper_name = bfd_malloc (length + sizeof ("lto-wrapper"));
+  memcpy (wrapper_name, real_name, length);
+  memcpy (wrapper_name + length, "lto-wrapper", sizeof ("lto-wrapper"));
+  if (stat (wrapper_name, &st) == 0 && S_ISREG (st.st_mode))
+    {
+      char *resolution_file = make_temp_file (".res");
+
+      if (resolution_file)
+	{
+	  plugin->gcc = gcc_name;
+	  plugin->lto_wrapper = wrapper_name;
+	  plugin->gcc_env = concat ("COLLECT_GCC=", gcc_name, NULL);
+	  plugin->resolution_file = resolution_file;
+	  plugin->resolution_option = concat ("-fresolution=",
+					      resolution_file, NULL);
+	  return;
+	}
+    }
+
+  free (gcc_name);
+  free (wrapper_name);
+}
+
+/* Set environment variables for GCC LTO wrapper to covert LTO IR
+   object to the real object.  */
+
+static int
+setup_lto_wrapper_env (struct plugin_list_entry *plugin)
+{
+  return (putenv (plugin->gcc_env)
+	  || putenv ("COLLECT_GCC_OPTIONS="));
+}
+
+static struct plugin_list_entry * plugin_list = NULL;
+static struct plugin_list_entry *current_plugin = NULL;
+
 /* Register a claim-file handler. */
-static ld_plugin_claim_file_handler claim_file = NULL;
 
 static enum ld_plugin_status
 register_claim_file (ld_plugin_claim_file_handler handler)
 {
-  claim_file = handler;
+  current_plugin->claim_file = handler;
+  return LDPS_OK;
+}
+
+/* Register an all-symbols-read handler.  */
+
+static enum ld_plugin_status
+register_all_symbols_read (ld_plugin_all_symbols_read_handler handler)
+{
+  current_plugin->all_symbols_read = handler;
+  return LDPS_OK;
+}
+
+/* Register a cleanup handler.  */
+
+static enum ld_plugin_status
+register_cleanup (ld_plugin_all_symbols_read_handler handler)
+{
+  current_plugin->cleanup_handler = handler;
+  return LDPS_OK;
+}
+
+/* Get the symbol resolution info for a plugin-claimed input file.  */
+
+static enum ld_plugin_status
+get_symbols (const void *handle ATTRIBUTE_UNUSED, int nsyms,
+	     struct ld_plugin_symbol *syms)
+{
+  if (syms)
+    {
+      int n;
+      for (n = 0; n < nsyms; n++)
+	{
+	  switch (syms[n].def)
+	    {
+	    default:
+	      BFD_ASSERT (0);
+	      break;
+	    case LDPK_UNDEF:
+	    case LDPK_WEAKUNDEF:
+	      syms[n].resolution = LDPR_UNDEF;
+	      break;
+	    case LDPK_DEF:
+	    case LDPK_WEAKDEF:
+	    case LDPK_COMMON:
+	      /* Tell plugin that LTO symbol has references from regular
+		 object code. */
+	      syms[n].resolution  = LDPR_PREVAILING_DEF;
+	      break;
+	    }
+      }
+    }
+
+  return LDPS_OK;
+}
+
+/* Add a new (real) input file generated by a plugin.  */
+
+static enum ld_plugin_status
+add_input_file (const char *pathname)
+{
+  /* Get symbols from the real LTO object.  */
+  char **matching;
+  long real_symsize;
+  long real_nsyms;
+  asymbol **real_syms;
+  int lto_nsyms;
+  bfd_boolean lto_symbol_found;
+  const struct ld_plugin_symbol *lto_syms;
+  bfd *rbfd;
+  int i, j;
+
+  rbfd = bfd_openr (pathname, NULL);
+  if (!bfd_check_format_matches (rbfd, bfd_object, &matching))
+    BFD_ASSERT (0);
+
+  real_symsize = bfd_get_symtab_upper_bound (rbfd);
+  if (real_symsize < 0)
+    BFD_ASSERT (0);
+
+  real_syms = (asymbol **) xmalloc (real_symsize);
+  real_nsyms = bfd_canonicalize_symtab (rbfd, real_syms);
+  if (real_nsyms < 0)
+    BFD_ASSERT (0);
+
+  /* NB: LTO plugin may generate more than one real object from one
+     LTO IR object.  We use the one which contains LTO symbols.  */
+  lto_syms = current_plugin->lto_syms;
+  lto_nsyms = current_plugin->lto_nsyms;
+  lto_symbol_found = FALSE;
+  for (i = 0; i < lto_nsyms; i++)
+    for (j = 0; j < real_nsyms; j++)
+      if (real_syms[j]->name
+	  && strcmp (lto_syms[i].name, real_syms[j]->name) == 0)
+	{
+	  lto_symbol_found = TRUE;
+	  break;
+	}
+
+  if (lto_symbol_found)
+    {
+      current_plugin->real_nsyms = real_nsyms;
+      current_plugin->real_syms = real_syms;
+      /* NB: We can't close RBFD which own the real symbol info.  */
+      current_plugin->real_bfd = rbfd;
+    }
+  else
+    bfd_close (rbfd);
+
   return LDPS_OK;
 }
 
@@ -140,11 +380,23 @@ add_symbols (void * handle,
 	     const struct ld_plugin_symbol * syms)
 {
   bfd *abfd = handle;
+  struct ld_plugin_symbol *copy_of_syms;
   struct plugin_data_struct *plugin_data =
     bfd_alloc (abfd, sizeof (plugin_data_struct));
+  int i;
+
+  /* NB: LTO symbols are owned by LTO plugin.  Create a copy so that we
+     can use it in bfd_plugin_canonicalize_symtab.  */
+  copy_of_syms = bfd_alloc (abfd, nsyms * sizeof (*syms));
+  memcpy (copy_of_syms, syms, nsyms * sizeof (*syms));
+  for (i = 0; i < nsyms; i++)
+    copy_of_syms[i].name = xstrdup (syms[i].name);
 
   plugin_data->nsyms = nsyms;
-  plugin_data->syms = syms;
+  plugin_data->syms = copy_of_syms;
+
+  current_plugin->lto_nsyms = nsyms;
+  current_plugin->lto_syms = copy_of_syms;
 
   if (nsyms != 0)
     abfd->flags |= HAS_SYMS;
@@ -214,26 +466,52 @@ try_claim (bfd *abfd)
   file.handle = abfd;
   if (!bfd_plugin_open_input (abfd, &file))
     return 0;
-  if (claim_file)
-    claim_file (&file, &claimed);
+  if (current_plugin->claim_file)
+    {
+      current_plugin->claim_file (&file, &claimed);
+      if (claimed)
+	{
+	  if (current_plugin->all_symbols_read)
+	    {
+	      struct plugin_data_struct *plugin_data
+		= abfd->tdata.plugin_data;
+
+	      /* Get real symbols from LTO wrapper.  */
+	      current_plugin->all_symbols_read ();
+
+	      /* Copy real symbols to plugin_data.  */
+	      if (plugin_data)
+		{
+		  plugin_data->real_bfd = current_plugin->real_bfd;
+		  plugin_data->real_nsyms = current_plugin->real_nsyms;
+		  plugin_data->real_syms = current_plugin->real_syms;
+		}
+
+	      /* Clean up LTO plugin.  */
+	      if (current_plugin->cleanup_handler)
+		current_plugin->cleanup_handler ();
+	    }
+	}
+
+      if (current_plugin->lto_wrapper)
+	{
+	  /* Clean up for LTO wrapper.  */
+	  unlink (current_plugin->resolution_file);
+	  free (current_plugin->lto_wrapper);
+	  free (current_plugin->gcc);
+	  free (current_plugin->gcc_env);
+	  free (current_plugin->resolution_option);
+	}
+    }
   close (file.fd);
   return claimed;
 }
 
-struct plugin_list_entry
-{
-  void *                        handle;
-  ld_plugin_claim_file_handler  claim_file;
-  struct plugin_list_entry *    next;
-};
-
-static struct plugin_list_entry * plugin_list = NULL;
-
 static int
 try_load_plugin (const char *pname, bfd *abfd, int *has_plugin_p)
 {
   void *plugin_handle = NULL;
-  struct ld_plugin_tv tv[4];
+  struct ld_plugin_tv tv[12];
   int i;
   ld_plugin_onload onload;
   enum ld_plugin_status status;
@@ -241,6 +519,16 @@ try_load_plugin (const char *pname, bfd *abfd, int *has_plugin_p)
 
   *has_plugin_p = 0;
 
+  /* NB: Each object is inddependent.  Reuse the previous plugin from
+     the last LTO wrapper run will lead to wrong LTO data.  */
+  if (current_plugin
+      && current_plugin->handle
+      && current_plugin->all_symbols_read)
+    {
+      dlclose (current_plugin->handle);
+      memset (current_plugin, 0, sizeof (*current_plugin));
+    }
+
   plugin_handle = dlopen (pname, RTLD_NOW);
   if (!plugin_handle)
     {
@@ -259,6 +547,7 @@ try_load_plugin (const char *pname, bfd *abfd, int *has_plugin_p)
 	    return 0;
 
 	  register_claim_file (plugin_list_iter->claim_file);
+	  current_plugin = plugin_list_iter;
 	  goto have_claim_file;
 	}
     }
@@ -266,8 +555,8 @@ try_load_plugin (const char *pname, bfd *abfd, int *has_plugin_p)
   plugin_list_iter = bfd_malloc (sizeof *plugin_list_iter);
   if (plugin_list_iter == NULL)
     return 0;
+  memset (plugin_list_iter, 0, sizeof (*plugin_list_iter));
   plugin_list_iter->handle = plugin_handle;
-  plugin_list_iter->claim_file = NULL;
   plugin_list_iter->next = plugin_list;
   plugin_list = plugin_list_iter;
 
@@ -287,23 +576,64 @@ try_load_plugin (const char *pname, bfd *abfd, int *has_plugin_p)
   tv[i].tv_tag = LDPT_ADD_SYMBOLS;
   tv[i].tv_u.tv_add_symbols = add_symbols;
 
+  get_lto_wrapper (plugin_list_iter, pname);
+  if (plugin_list_iter->lto_wrapper)
+    {
+      ++i;
+      tv[i].tv_tag = LDPT_REGISTER_ALL_SYMBOLS_READ_HOOK;
+      tv[i].tv_u.tv_register_all_symbols_read = register_all_symbols_read;
+
+      ++i;
+      tv[i].tv_tag = LDPT_REGISTER_CLEANUP_HOOK;
+      tv[i].tv_u.tv_register_cleanup = register_cleanup;
+
+      ++i;
+      tv[i].tv_tag = LDPT_GET_SYMBOLS;
+      tv[i].tv_u.tv_get_symbols = get_symbols;
+
+      ++i;
+      tv[i].tv_tag = LDPT_GET_SYMBOLS_V2;
+      tv[i].tv_u.tv_get_symbols = get_symbols;
+
+      ++i;
+      tv[i].tv_tag = LDPT_OPTION;
+      tv[i].tv_u.tv_string = plugin_list_iter->lto_wrapper;
+
+      ++i;
+      tv[i].tv_tag = LDPT_OPTION;
+      tv[i].tv_u.tv_string = plugin_list_iter->resolution_option;
+
+      ++i;
+      tv[i].tv_tag = LDPT_LINKER_OUTPUT;
+      tv[i].tv_u.tv_val = LDPO_EXEC;
+
+      ++i;
+      tv[i].tv_tag = LDPT_ADD_INPUT_FILE;
+      tv[i].tv_u.tv_add_input_file = add_input_file;
+    }
+
   ++i;
   tv[i].tv_tag = LDPT_NULL;
   tv[i].tv_u.tv_val = 0;
 
+  current_plugin = plugin_list_iter;
+
+  /* LTO plugin will call handler hooks to set up plugin handlers.  */
   status = (*onload)(tv);
 
   if (status != LDPS_OK)
     return 0;
 
-  plugin_list_iter->claim_file = claim_file;
+  if (plugin_list_iter->lto_wrapper
+      && setup_lto_wrapper_env (plugin_list_iter))
+    return 0;
 
 have_claim_file:
   *has_plugin_p = 1;
 
   abfd->plugin_format = bfd_plugin_no;
 
-  if (!claim_file)
+  if (!current_plugin->claim_file)
     return 0;
 
   if (!try_claim (abfd))
@@ -562,7 +892,15 @@ bfd_plugin_canonicalize_symtab (bfd *abfd,
 			SEC_ALLOC | SEC_LOAD | SEC_CODE | SEC_HAS_CONTENTS);
   static asection fake_common_section
     = BFD_FAKE_SECTION (fake_common_section, NULL, "plug", 0, SEC_IS_COMMON);
-  int i;
+  int i, j;
+  long real_nsyms;
+  asymbol **real_syms;
+
+  real_syms = plugin_data->real_syms;
+  if (real_syms)
+    real_nsyms = plugin_data->real_nsyms;
+  else
+    real_nsyms = 0;
 
   for (i = 0; i < nsyms; i++)
     {
@@ -587,6 +925,15 @@ bfd_plugin_canonicalize_symtab (bfd *abfd,
 	case LDPK_DEF:
 	case LDPK_WEAKDEF:
 	  s->section = &fake_section;
+	  if (real_nsyms)
+	    /* Use real LTO symbols if possible.  */
+	    for (j = 0; j < real_nsyms; j++)
+	      if (real_syms[j]->name
+		  && strcmp (syms[i].name, real_syms[j]->name) == 0)
+		{
+		  s->section = real_syms[j]->section;
+		  break;
+		}
 	  break;
 	default:
 	  BFD_ASSERT (0);
@@ -635,6 +982,34 @@ bfd_plugin_sizeof_headers (bfd *a ATTRIBUTE_UNUSED,
   return 0;
 }
 
+static bfd_boolean
+bfd_plugin_close_and_cleanup (bfd *abfd)
+{
+  struct plugin_data_struct *plugin_data;
+
+  if (abfd->format != bfd_archive
+      && (plugin_data = abfd->tdata.plugin_data))
+    {
+      const struct ld_plugin_symbol *syms = plugin_data->syms;
+
+      if (plugin_data->real_bfd)
+	bfd_close (plugin_data->real_bfd);
+
+      if (plugin_data->real_syms)
+	free (plugin_data->real_syms);
+
+      if (syms)
+	{
+	  long nsyms = plugin_data->nsyms;
+	  int i;
+	  for (i = 0; i < nsyms; i++)
+	    free (syms[i].name);
+	}
+    }
+
+  return _bfd_generic_close_and_cleanup (abfd);
+}
+
 const bfd_target plugin_vec =
 {
   "plugin",			/* Name.  */
diff --git a/bfd/plugin.h b/bfd/plugin.h
index 098bf084554..05c3573933d 100644
--- a/bfd/plugin.h
+++ b/bfd/plugin.h
@@ -33,6 +33,9 @@ typedef struct plugin_data_struct
 {
   int nsyms;
   const struct ld_plugin_symbol *syms;
+  bfd *real_bfd;
+  long real_nsyms;
+  asymbol **real_syms;
 }
 plugin_data_struct;
 
diff --git a/ld/testsuite/ld-plugin/lto.exp b/ld/testsuite/ld-plugin/lto.exp
index 9b03b7b3977..1b44b0da3fd 100644
--- a/ld/testsuite/ld-plugin/lto.exp
+++ b/ld/testsuite/ld-plugin/lto.exp
@@ -234,6 +234,11 @@ set lto_link_tests [list \
   [list "Build pr24406-2b.o" \
    "" "-O2 -fno-lto" \
    {pr24406-2b.c}] \
+  [list "pr25355.o" \
+   "" \
+   "-flto -fno-common $lto_no_fat" \
+   {pr25355.c} \
+   [list [list "nm" "$plug_opt" "pr25355.d"]]] \
 ]
 
 if { [at_least_gcc_version 4 7] } {
diff --git a/ld/testsuite/ld-plugin/pr25355.c b/ld/testsuite/ld-plugin/pr25355.c
new file mode 100644
index 00000000000..99f01fb5c89
--- /dev/null
+++ b/ld/testsuite/ld-plugin/pr25355.c
@@ -0,0 +1,2 @@
+int nm_test_var;
+int nm_test_var2 = 1234;
diff --git a/ld/testsuite/ld-plugin/pr25355.d b/ld/testsuite/ld-plugin/pr25355.d
new file mode 100644
index 00000000000..98d10aba1cf
--- /dev/null
+++ b/ld/testsuite/ld-plugin/pr25355.d
@@ -0,0 +1,4 @@
+#...
+[0-9a-f]+ B _?nm_test_var
+[0-9a-f]+ D _?nm_test_var2
+#pass
diff --git a/ld/testsuite/lib/ld-lib.exp b/ld/testsuite/lib/ld-lib.exp
index 08e2d6978af..015eda6eb97 100644
--- a/ld/testsuite/lib/ld-lib.exp
+++ b/ld/testsuite/lib/ld-lib.exp
@@ -928,6 +928,7 @@ proc run_cc_link_tests { ldtests } {
 
 	if { $binfile eq "tmpdir/" } {
 	    # compile only
+	    set binfile $objfile
 	} elseif { [regexp ".*\\.a$" $binfile] } {
 	    if { ![ar_simple_create $ar $ldflags $binfile "$objfiles"] } {
 		set failed 1
-- 
2.24.1