[RFC][PATCH] Check ELF relocs after opening all all input files

["H.J. Lu" <hongjiu dot lu at intel dot com>]

Delaying checking ELF relocations until opening all input files so
that symbol information is final when relocations are checked.  This
is only enabled for x86 targets.

Any comments, feedbacks?


H.J.
---
bfd/

	* elf-bfd.h (_bfd_elf_link_check_relocs): New.
	* elf32-i386.c (elf_i386_tls_transition): Use
	info->callbacks->einfo instead of _bfd_error_handler on
	error.
	* elflink.c (_bfd_elf_link_check_relocs): New function.
	(elf_link_add_object_symbols): Call _bfd_elf_link_check_relocs
	if check_relocs_after_open_input is FALSE.

include/

	* bfdlink.h (bfd_link_info): Add check_relocs_after_open_input.

ld/

	* ldmisc.c (vfinfo): Add support for %x and %lx.
	* emulparams/elf32_x86_64.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	New.
	* emulparams/elf_i386.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/elf_i386_be.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/elf_i386_chaos.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/elf_i386_ldso.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/elf_i386_vxworks.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/elf_x86_64.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emulparams/i386nto.sh (CHECK_RELOCS_AFTER_OPEN_INPUT):
	Likewise.
	* emultempl/elf32.em (gld${EMULATION_NAME}_before_parse):
	Set check_relocs_after_open_input to TRUE if
	CHECK_RELOCS_AFTER_OPEN_INPUT is yes.
	(gld${EMULATION_NAME}_after_open): Call
	_bfd_elf_link_check_relocs on all inputs if
	check_relocs_after_open_input is TRUE.
---
 bfd/elf-bfd.h                     |   2 +
 bfd/elf32-i386.c                  |  10 ++--
 bfd/elf64-x86-64.c                |   8 +--
 bfd/elflink.c                     | 117 +++++++++++++++++++++-----------------
 include/bfdlink.h                 |   4 ++
 ld/emulparams/elf32_x86_64.sh     |   1 +
 ld/emulparams/elf_i386.sh         |   1 +
 ld/emulparams/elf_i386_be.sh      |   1 +
 ld/emulparams/elf_i386_chaos.sh   |   1 +
 ld/emulparams/elf_i386_ldso.sh    |   1 +
 ld/emulparams/elf_i386_vxworks.sh |   1 +
 ld/emulparams/elf_x86_64.sh       |   1 +
 ld/emulparams/i386nto.sh          |   1 +
 ld/emultempl/elf32.em             |  11 ++++
 ld/ldmisc.c                       |  13 +++++
 15 files changed, 113 insertions(+), 60 deletions(-)

diff --git a/bfd/elf-bfd.h b/bfd/elf-bfd.h
index 5c93d78..5dce70e 100644
--- a/bfd/elf-bfd.h
+++ b/bfd/elf-bfd.h
@@ -2261,6 +2261,8 @@ extern bfd_boolean bfd_elf_link_add_symbols
   (bfd *, struct bfd_link_info *);
 extern bfd_boolean _bfd_elf_add_dynamic_entry
   (struct bfd_link_info *, bfd_vma, bfd_vma);
+extern bfd_boolean _bfd_elf_link_check_relocs
+  (bfd *, struct bfd_link_info *);
 
 extern bfd_boolean bfd_elf_link_record_dynamic_symbol
   (struct bfd_link_info *, struct elf_link_hash_entry *);
diff --git a/bfd/elf32-i386.c b/bfd/elf32-i386.c
index 470fcd1..d745a89 100644
--- a/bfd/elf32-i386.c
+++ b/bfd/elf32-i386.c
@@ -1491,11 +1491,11 @@ elf_i386_tls_transition (struct bfd_link_info *info, bfd *abfd,
 	    }
 	}
 
-      (*_bfd_error_handler)
-	(_("%B: TLS transition from %s to %s against `%s' at 0x%lx "
-	   "in section `%A' failed"),
-	 abfd, sec, from->name, to->name, name,
-	 (unsigned long) rel->r_offset);
+      info->callbacks->einfo
+	(_("%B%X: TLS transition from %s to %s against `%s' at 0x%lx "
+	   "in section `%A' failed\n"),
+	 abfd, from->name, to->name, name,
+	 (unsigned long) rel->r_offset, sec);
       bfd_set_error (bfd_error_bad_value);
       return FALSE;
     }
diff --git a/bfd/elf64-x86-64.c b/bfd/elf64-x86-64.c
index 5533b4a..14dc3a1 100644
--- a/bfd/elf64-x86-64.c
+++ b/bfd/elf64-x86-64.c
@@ -1572,11 +1572,11 @@ elf_x86_64_tls_transition (struct bfd_link_info *info, bfd *abfd,
 	    }
 	}
 
-      (*_bfd_error_handler)
-	(_("%B: TLS transition from %s to %s against `%s' at 0x%lx "
+      info->callbacks->einfo
+	(_("%B%X: TLS transition from %s to %s against `%s' at 0x%lx "
 	   "in section `%A' failed"),
-	 abfd, sec, from->name, to->name, name,
-	 (unsigned long) rel->r_offset);
+	 abfd, from->name, to->name, name,
+	 (unsigned long) rel->r_offset, sec);
       bfd_set_error (bfd_error_bad_value);
       return FALSE;
     }
diff --git a/bfd/elflink.c b/bfd/elflink.c
index 37638b2..5af334a 100644
--- a/bfd/elflink.c
+++ b/bfd/elflink.c
@@ -3480,6 +3480,69 @@ _bfd_elf_notice_as_needed (bfd *ibfd,
   return (*info->callbacks->notice) (info, NULL, NULL, ibfd, NULL, act, 0);
 }
 
+/* Check relocations an ELF object file.  */
+
+bfd_boolean
+_bfd_elf_link_check_relocs (bfd *abfd, struct bfd_link_info *info)
+{
+  const struct elf_backend_data *bed = get_elf_backend_data (abfd);
+  struct elf_link_hash_table *htab = elf_hash_table (info);
+
+  /* If this object is the same format as the output object, and it is
+     not a shared library, then let the backend look through the
+     relocs.
+
+     This is required to build global offset table entries and to
+     arrange for dynamic relocs.  It is not required for the
+     particular common case of linking non PIC code, even when linking
+     against shared libraries, but unfortunately there is no way of
+     knowing whether an object file has been compiled PIC or not.
+     Looking through the relocs is not particularly time consuming.
+     The problem is that we must either (1) keep the relocs in memory,
+     which causes the linker to require additional runtime memory or
+     (2) read the relocs twice from the input file, which wastes time.
+     This would be a good case for using mmap.
+
+     I have no idea how to handle linking PIC code into a file of a
+     different format.  It probably can't be done.  */
+  if ((abfd->flags & DYNAMIC) == 0
+      && is_elf_hash_table (htab)
+      && bed->check_relocs != NULL
+      && elf_object_id (abfd) == elf_hash_table_id (htab)
+      && (*bed->relocs_compatible) (abfd->xvec, info->output_bfd->xvec))
+    {
+      asection *o;
+
+      for (o = abfd->sections; o != NULL; o = o->next)
+	{
+	  Elf_Internal_Rela *internal_relocs;
+	  bfd_boolean ok;
+
+	  if ((o->flags & SEC_RELOC) == 0
+	      || o->reloc_count == 0
+	      || ((info->strip == strip_all || info->strip == strip_debugger)
+		  && (o->flags & SEC_DEBUGGING) != 0)
+	      || bfd_is_abs_section (o->output_section))
+	    continue;
+
+	  internal_relocs = _bfd_elf_link_read_relocs (abfd, o, NULL, NULL,
+						       info->keep_memory);
+	  if (internal_relocs == NULL)
+	    return FALSE;
+
+	  ok = (*bed->check_relocs) (abfd, info, o, internal_relocs);
+
+	  if (elf_section_data (o)->relocs != internal_relocs)
+	    free (internal_relocs);
+
+	  if (! ok)
+	    return FALSE;
+	}
+    }
+
+  return TRUE;
+}
+
 /* Add symbols from an ELF object file to the linker hash table.  */
 
 static bfd_boolean
@@ -4950,57 +5013,9 @@ error_free_dyn:
       && !(*bed->check_directives) (abfd, info))
     return FALSE;
 
-  /* If this object is the same format as the output object, and it is
-     not a shared library, then let the backend look through the
-     relocs.
-
-     This is required to build global offset table entries and to
-     arrange for dynamic relocs.  It is not required for the
-     particular common case of linking non PIC code, even when linking
-     against shared libraries, but unfortunately there is no way of
-     knowing whether an object file has been compiled PIC or not.
-     Looking through the relocs is not particularly time consuming.
-     The problem is that we must either (1) keep the relocs in memory,
-     which causes the linker to require additional runtime memory or
-     (2) read the relocs twice from the input file, which wastes time.
-     This would be a good case for using mmap.
-
-     I have no idea how to handle linking PIC code into a file of a
-     different format.  It probably can't be done.  */
-  if (! dynamic
-      && is_elf_hash_table (htab)
-      && bed->check_relocs != NULL
-      && elf_object_id (abfd) == elf_hash_table_id (htab)
-      && (*bed->relocs_compatible) (abfd->xvec, info->output_bfd->xvec))
-    {
-      asection *o;
-
-      for (o = abfd->sections; o != NULL; o = o->next)
-	{
-	  Elf_Internal_Rela *internal_relocs;
-	  bfd_boolean ok;
-
-	  if ((o->flags & SEC_RELOC) == 0
-	      || o->reloc_count == 0
-	      || ((info->strip == strip_all || info->strip == strip_debugger)
-		  && (o->flags & SEC_DEBUGGING) != 0)
-	      || bfd_is_abs_section (o->output_section))
-	    continue;
-
-	  internal_relocs = _bfd_elf_link_read_relocs (abfd, o, NULL, NULL,
-						       info->keep_memory);
-	  if (internal_relocs == NULL)
-	    goto error_return;
-
-	  ok = (*bed->check_relocs) (abfd, info, o, internal_relocs);
-
-	  if (elf_section_data (o)->relocs != internal_relocs)
-	    free (internal_relocs);
-
-	  if (! ok)
-	    goto error_return;
-	}
-    }
+  if (!info->check_relocs_after_open_input
+      && !_bfd_elf_link_check_relocs (abfd, info))
+    return FALSE;
 
   /* If this is a non-traditional link, try to optimize the handling
      of the .stab/.stabstr sections.  */
diff --git a/include/bfdlink.h b/include/bfdlink.h
index a285f6d..90467b5 100644
--- a/include/bfdlink.h
+++ b/include/bfdlink.h
@@ -440,6 +440,10 @@ struct bfd_link_info
   /* TRUE if the linker script contained an explicit PHDRS command.  */
   unsigned int user_phdrs: 1;
 
+  /* TRUE if we should check relocations after all input files have
+     been opened.  */
+  unsigned int check_relocs_after_open_input: 1;
+
   /* TRUE if BND prefix in PLT entries is always generated.  */
   unsigned int bndplt: 1;
 
diff --git a/ld/emulparams/elf32_x86_64.sh b/ld/emulparams/elf32_x86_64.sh
index 967c1b4..9050730 100644
--- a/ld/emulparams/elf32_x86_64.sh
+++ b/ld/emulparams/elf32_x86_64.sh
@@ -6,6 +6,7 @@
 SCRIPT_NAME=elf
 ELFSIZE=32
 OUTPUT_FORMAT="elf32-x86-64"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_REL_RELOCS=yes
 TEXT_START_ADDR=0x400000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/elf_i386.sh b/ld/emulparams/elf_i386.sh
index 3451bb2..b08e661 100644
--- a/ld/emulparams/elf_i386.sh
+++ b/ld/emulparams/elf_i386.sh
@@ -4,6 +4,7 @@
 . ${srcdir}/emulparams/call_nop.sh
 SCRIPT_NAME=elf
 OUTPUT_FORMAT="elf32-i386"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_RELA_RELOCS=yes
 TEXT_START_ADDR=0x08048000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/elf_i386_be.sh b/ld/emulparams/elf_i386_be.sh
index 70db443..4a24b02 100644
--- a/ld/emulparams/elf_i386_be.sh
+++ b/ld/emulparams/elf_i386_be.sh
@@ -3,6 +3,7 @@
 . ${srcdir}/emulparams/call_nop.sh
 SCRIPT_NAME=elf
 OUTPUT_FORMAT="elf32-i386"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_RELA_RELOCS=yes
 TEXT_START_ADDR=0x80000000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/elf_i386_chaos.sh b/ld/emulparams/elf_i386_chaos.sh
index aa36cb5..5349108 100644
--- a/ld/emulparams/elf_i386_chaos.sh
+++ b/ld/emulparams/elf_i386_chaos.sh
@@ -4,6 +4,7 @@
 . ${srcdir}/emulparams/call_nop.sh
 SCRIPT_NAME=elf_chaos
 OUTPUT_FORMAT="elf32-i386"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 TEXT_START_ADDR=0x40000000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
 ARCH=i386
diff --git a/ld/emulparams/elf_i386_ldso.sh b/ld/emulparams/elf_i386_ldso.sh
index 1328520..dc4eef4 100644
--- a/ld/emulparams/elf_i386_ldso.sh
+++ b/ld/emulparams/elf_i386_ldso.sh
@@ -4,6 +4,7 @@
 . ${srcdir}/emulparams/call_nop.sh
 SCRIPT_NAME=elf
 OUTPUT_FORMAT="elf32-i386"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_RELA_RELOCS=yes
 TEXT_START_ADDR=0x08048000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/elf_i386_vxworks.sh b/ld/emulparams/elf_i386_vxworks.sh
index aaea8c4..ac1bbeb 100644
--- a/ld/emulparams/elf_i386_vxworks.sh
+++ b/ld/emulparams/elf_i386_vxworks.sh
@@ -1,5 +1,6 @@
 SCRIPT_NAME=elf
 OUTPUT_FORMAT="elf32-i386-vxworks"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_RELA_RELOCS=yes
 TEXT_START_ADDR=0x08048000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/elf_x86_64.sh b/ld/emulparams/elf_x86_64.sh
index e935f90..6055204 100644
--- a/ld/emulparams/elf_x86_64.sh
+++ b/ld/emulparams/elf_x86_64.sh
@@ -6,6 +6,7 @@
 SCRIPT_NAME=elf
 ELFSIZE=64
 OUTPUT_FORMAT="elf64-x86-64"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_REL_RELOCS=yes
 TEXT_START_ADDR=0x400000
 MAXPAGESIZE="CONSTANT (MAXPAGESIZE)"
diff --git a/ld/emulparams/i386nto.sh b/ld/emulparams/i386nto.sh
index 626f9c1..51284be 100644
--- a/ld/emulparams/i386nto.sh
+++ b/ld/emulparams/i386nto.sh
@@ -1,5 +1,6 @@
 SCRIPT_NAME=elf
 OUTPUT_FORMAT="elf32-i386"
+CHECK_RELOCS_AFTER_OPEN_INPUT=yes
 NO_RELA_RELOCS=yes
 TEXT_START_ADDR=0x08048000
 TEXT_START_SYMBOLS='_btext = .;'
diff --git a/ld/emultempl/elf32.em b/ld/emultempl/elf32.em
index 3e9f684..1cfe65c 100644
--- a/ld/emultempl/elf32.em
+++ b/ld/emultempl/elf32.em
@@ -104,6 +104,7 @@ gld${EMULATION_NAME}_before_parse (void)
   config.has_shared = `if test -n "$GENERATE_SHLIB_SCRIPT" ; then echo TRUE ; else echo FALSE ; fi`;
   config.separate_code = `if test "x${SEPARATE_CODE}" = xyes ; then echo TRUE ; else echo FALSE ; fi`;
   `if test -n "$CALL_NOP_BYTE" ; then echo link_info.call_nop_byte = $CALL_NOP_BYTE; fi`;
+  link_info.check_relocs_after_open_input = `if test "x${CHECK_RELOCS_AFTER_OPEN_INPUT}" = xyes ; then echo TRUE ; else echo FALSE ; fi`;
 }
 
 EOF
@@ -1025,6 +1026,16 @@ gld${EMULATION_NAME}_after_open (void)
   if (!is_elf_hash_table (htab))
     return;
 
+  if (link_info.check_relocs_after_open_input)
+    {
+      bfd *abfd;
+
+      for (abfd = link_info.input_bfds;
+	   abfd != (bfd *) NULL; abfd = abfd->link.next)
+	if (!_bfd_elf_link_check_relocs (abfd, &link_info))
+	  return;
+    }
+
   if (emit_note_gnu_build_id != NULL)
     {
       bfd *abfd;
diff --git a/ld/ldmisc.c b/ld/ldmisc.c
index 70e12ea..a744586 100644
--- a/ld/ldmisc.c
+++ b/ld/ldmisc.c
@@ -58,6 +58,8 @@
  %d integer, like printf
  %ld long, like printf
  %lu unsigned long, like printf
+ %x integer in hex, like printf
+ %lx long in hex, like printf
  %p native (host) void* pointer, like printf
  %s arbitrary string, like printf
  %u integer, like printf
@@ -409,6 +411,11 @@ vfinfo (FILE *fp, const char *fmt, va_list arg, bfd_boolean is_warning)
 	      fprintf (fp, "%u", va_arg (arg, unsigned int));
 	      break;
 
+	    case 'x':
+	      /* integer in hex, like printf */
+	      fprintf (fp, "%x", va_arg (arg, int));
+	      break;
+
 	    case 'l':
 	      if (*fmt == 'd')
 		{
@@ -422,6 +429,12 @@ vfinfo (FILE *fp, const char *fmt, va_list arg, bfd_boolean is_warning)
 		  ++fmt;
 		  break;
 		}
+	      else if (*fmt == 'x')
+		{
+		  fprintf (fp, "%lx", va_arg (arg, long));
+		  ++fmt;
+		  break;
+		}
 	      /* Fall thru */
 
 	    default:
-- 
2.5.5