Re: coffread.c extension for DLLs without debugging symbols

["Raoul Gough" <RaoulGough@yahoo.co.uk>]

[-- Attachment #1: Type: text/plain, Size: 1034 bytes --]

"Andrew Cagney" <ac131313@redhat.com> wrote in message
news:3E1A2656.7080906@redhat.com...
> Raoul, looks like a little bit of paper work will be needed.  I'll
> follow up privatly.

The paperwork is reportedly on its way to me now. I've since got a new
version of the patch together, which introduces coff-pe-read.c. I'm
pretty sure I've got the Makefile right - I added coff-pe-read.o to
both SFILES and COMMON_OBS since they already involved coffread.o
(anything that needs coffread.o now also needs coff-pe-read.o).

I've also fixed the problem with relocated DLLs, and AFAIK all
formatting issues. The maintainer will have to add the FSF copyright
notices, since I suppose the FSF doesn't acknowledge ownership until
the forms go through. I guess you also can't put any of this in CVS
until the forms have been processed?

BTW, I have some more patches on the way, because I've found what some
problems with the general handling of DLL relocation on Windows. I'll
post these separately when they're ready.

Regards,
Raoul Gough.

[-- Attachment #2: ChangeLog_entry.txt --]
[-- Type: text/plain, Size: 506 bytes --]

2003-01-10  Raoul Gough  <RaoulGough@yahoo.co.uk>

	* coff-pe-read.c: New file - support reading of minimal symbols
	from a portable executable using the export table.
	* coff-pe-read.h: New file
	* coffread.c: #include coff-pe-read.h
	(coff_symtab_read): call read_pe_exported_syms iff no recognized
	debugging symbols found.
	* Makefile.in (SFILES): add coff-pe-read.o
	(coff_pe_read_h): define
	(COMMON_OBS): add coff-pe-read.o
	(coffread.o): add coff_pe_read_h dependency
	(coff-pe-read.o): New target

[-- Attachment #3: coff-pe-read.h --]
[-- Type: application/octet-stream, Size: 394 bytes --]

/* Interface to coff-pe-read.c (portable-executable-specific symbol reader).

   Contributed by Raoul M. Gough (RaoulGough@yahoo.co.uk). */

#if !defined (COFF_PE_READ_H)
#define COFF_PE_READ_H

struct objfile;

/* Read the export table and convert it to minimal symbol table entries */
void read_pe_exported_syms (struct objfile *objfile);

#endif /* !defined (COFF_PE_READ_H) */

[-- Attachment #4: coff-pe-read.c --]
[-- Type: application/octet-stream, Size: 9599 bytes --]

/* Read the export table symbols from a portable executable and
   convert to internal format, for GDB. Used as a last resort if no
   debugging symbols recognized.

   Contributed by Raoul M. Gough (RaoulGough@yahoo.co.uk). */

#include "coff-pe-read.h"

#include "bfd.h"

#include "defs.h"
#include "gdbtypes.h"

#include "symtab.h"
#include "symfile.h"
#include "objfiles.h"

/* Internal section information */

struct read_pe_section_data
{
  CORE_ADDR vma_offset;               /* Offset to loaded address of section.*/
  unsigned long rva_start;            /* Start offset within the pe. */
  unsigned long rva_end;              /* End offset within the pe. */
  enum minimal_symbol_type ms_type;   /* Type to assign symbols in section. */
};

#define PE_SECTION_INDEX_TEXT     0
#define PE_SECTION_INDEX_DATA     1
#define PE_SECTION_INDEX_BSS      2
#define PE_SECTION_TABLE_SIZE     3
#define PE_SECTION_INDEX_INVALID -1
\f
/* Get the index of the named section in our own array, which contains
   text, data and bss in that order. Return PE_SECTION_INDEX_INVALID
   if passed an unrecognised section name. */

static int
read_pe_section_index (const char *section_name)
{
  if (strcmp (section_name, ".text") == 0)
    {
      return PE_SECTION_INDEX_TEXT;
    }

  else if (strcmp (section_name, ".data") == 0)
    {
      return PE_SECTION_INDEX_DATA;
    }

  else if (strcmp (section_name, ".bss") == 0)
    {
      return PE_SECTION_INDEX_BSS;
    }

  else
    {
      return PE_SECTION_INDEX_INVALID;
    }
}

/* Record the virtual memory address of a section. */

static void
get_section_vmas (bfd *abfd, asection *sectp, void *context)
{
  struct read_pe_section_data *sections = context;
  int sectix = read_pe_section_index (sectp->name);

  if (sectix != PE_SECTION_INDEX_INVALID)
    {
      /* Data within the section start at rva_start in the pe and at
         bfd_get_section_vma() within memory. Store the offset. */

      sections[sectix].vma_offset
	= bfd_get_section_vma (abfd, sectp) - sections[sectix].rva_start;
    }
}
\f
/* Create a minimal symbol entry for an exported symbol. */

static void
add_pe_exported_sym (char *sym_name,
		     unsigned long func_rva,
		     const struct read_pe_section_data *section_data,
		     const char *dll_name,
		     struct objfile *objfile)
{
  /* Add the stored offset to get the loaded address of the symbol. */

  CORE_ADDR vma = func_rva + section_data->vma_offset;

  char *qualified_name = 0;
  int dll_name_len = strlen (dll_name);
  int count;

  /* Generate a (hopefully unique) qualified name using the first part
     of the dll name, e.g. KERNEL32!AddAtomA. This matches the style
     used by windbg from the "Microsoft Debugging Tools for Windows". */

  qualified_name = xmalloc (dll_name_len + strlen (sym_name) + 2);

  strncpy (qualified_name, dll_name, dll_name_len);
  qualified_name[dll_name_len] = '!';
  strcpy (qualified_name + dll_name_len + 1, sym_name);

  prim_record_minimal_symbol (qualified_name,
			      vma,
			      section_data->ms_type,
			      objfile);

  xfree (qualified_name);

  /* Enter the plain name as well, which might not be unique. */
  prim_record_minimal_symbol (sym_name,
			      vma,
			      section_data->ms_type,
			      objfile);
}

/* Truncate a dll_name at the first dot character. */

static void
read_pe_truncate_name (char *dll_name)
{
  while (*dll_name)
    {
      if ((*dll_name) == '.')
	{
	  *dll_name = '\0'; /* truncates and causes loop exit. */
	}

      else
	{
	  ++dll_name;
	}
    }
}
\f
/* Low-level support functions, direct from the ld module pe-dll.c. */
static unsigned int
pe_get16 (bfd *abfd, int where)
{
  unsigned char b[2];

  bfd_seek (abfd, (file_ptr) where, SEEK_SET);
  bfd_bread (b, (bfd_size_type) 2, abfd);
  return b[0] + (b[1] << 8);
}

static unsigned int
pe_get32 (bfd *abfd, int where)
{
  unsigned char b[4];

  bfd_seek (abfd, (file_ptr) where, SEEK_SET);
  bfd_bread (b, (bfd_size_type) 4, abfd);
  return b[0] + (b[1] << 8) + (b[2] << 16) + (b[3] << 24);
}

static unsigned int
pe_as32 (void *ptr)
{
  unsigned char *b = ptr;

  return b[0] + (b[1] << 8) + (b[2] << 16) + (b[3] << 24);
}
\f
/* Read the (non-debug) export symbol table from a portable
   executable. Code originally lifted from the ld function
   pe_implied_import_dll in pe-dll.c. */

void
read_pe_exported_syms (struct objfile *objfile)
{
  bfd *dll = objfile->obfd;
  unsigned long pe_header_offset, opthdr_ofs, num_entries, i;
  unsigned long export_rva, export_size, nsections, secptr, expptr;
  unsigned long exp_funcbase;
  unsigned char *expdata, *erva;
  unsigned long name_rvas, ordinals, nexp, ordbase;
  char *dll_name;

  /* Array elements are for text, data and bss in that order
     Initialization with start_rva > end_rva guarantees that
     unused sections won't be matched. */
  struct read_pe_section_data section_data[PE_SECTION_TABLE_SIZE]
    = { {0, 1, 0, mst_text},
	{0, 1, 0, mst_data},
	{0, 1, 0, mst_bss} };

  struct cleanup *back_to = 0;

  char const *target = bfd_get_target (objfile->obfd);

  if ((strcmp (target, "pe-i386") != 0) && (strcmp (target, "pei-i386") != 0))
    {
      /* This is not an i386 format file. Abort now, because the code
	 is untested on anything else. *FIXME* test on further
	 architectures and loosen or remove this test. */
      return;
    }

  /* Get pe_header, optional header and numbers of export entries.  */
  pe_header_offset = pe_get32 (dll, 0x3c);
  opthdr_ofs = pe_header_offset + 4 + 20;
  num_entries = pe_get32 (dll, opthdr_ofs + 92);

  if (num_entries < 1) /* No exports.  */
    {
      return;
    }

  export_rva = pe_get32 (dll, opthdr_ofs + 96);
  export_size = pe_get32 (dll, opthdr_ofs + 100);
  nsections = pe_get16 (dll, pe_header_offset + 4 + 2);
  secptr = (pe_header_offset + 4 + 20 +
	    pe_get16 (dll, pe_header_offset + 4 + 16));
  expptr = 0;

  /* Get the rva and size of the export section.  */ 
  for (i = 0; i < nsections; i++)
    {
      char sname[8];
      unsigned long secptr1 = secptr + 40 * i;
      unsigned long vaddr = pe_get32 (dll, secptr1 + 12);
      unsigned long vsize = pe_get32 (dll, secptr1 + 16);
      unsigned long fptr = pe_get32 (dll, secptr1 + 20);

      bfd_seek (dll, (file_ptr) secptr1, SEEK_SET);
      bfd_bread (sname, (bfd_size_type) 8, dll);

      if (vaddr <= export_rva && vaddr + vsize > export_rva)
	{
	  expptr = fptr + (export_rva - vaddr);
	  if (export_rva + export_size > vaddr + vsize)
	    export_size = vsize - (export_rva - vaddr);
	  break;
	}
    }

  if (export_size == 0)
    {
      /* Empty export table. */
      return;
    }

  /* Scan sections and store the base and size of the relevant sections. */
  for (i = 0; i < nsections; i++)
    {
      unsigned long secptr1 = secptr + 40 * i;
      unsigned long vsize = pe_get32 (dll, secptr1 + 8);
      unsigned long vaddr = pe_get32 (dll, secptr1 + 12);
      unsigned long flags = pe_get32 (dll, secptr1 + 36);
      char sec_name[9];
      int sectix;

      sec_name[8] = '\0';
      bfd_seek (dll, (file_ptr) secptr1 + 0, SEEK_SET);
      bfd_bread (sec_name, (bfd_size_type) 8, dll);

      sectix = read_pe_section_index (sec_name);

      if (sectix != PE_SECTION_INDEX_INVALID)
	{
	  section_data[sectix].rva_start = vaddr;
	  section_data[sectix].rva_end = vaddr + vsize;
	}
    }

  expdata = (unsigned char *) xmalloc (export_size);
  back_to = make_cleanup (xfree, expdata);

  bfd_seek (dll, (file_ptr) expptr, SEEK_SET);
  bfd_bread (expdata, (bfd_size_type) export_size, dll);
  erva = expdata - export_rva;

  nexp = pe_as32 (expdata + 24);
  name_rvas = pe_as32 (expdata + 32);
  ordinals = pe_as32 (expdata + 36);
  ordbase = pe_as32 (expdata + 16);
  exp_funcbase = pe_as32 (expdata + 28);

  /* Use internal dll name instead of full pathname. */
  dll_name = pe_as32 (expdata + 12) + erva;

  bfd_map_over_sections (dll, get_section_vmas, section_data);

  /* Adjust the vma_offsets in case this PE got relocated. This
     assumes that *all* sections share the same relocation offset
     as the text section. */
  for (i = 0; i < PE_SECTION_TABLE_SIZE; i++)
    {
      section_data[i].vma_offset
	+= ANOFFSET (objfile->section_offsets, SECT_OFF_TEXT (objfile));
    }

  printf_filtered ("Minimal symbols from %s...", dll_name);
  wrap_here ("");

  /* Truncate name at first dot. Should maybe also convert to all
     lower case for convenience on Windows. */
  read_pe_truncate_name (dll_name);

  /* Iterate through the list of symbols.  */
  for (i = 0; i < nexp; i++)
    {
      /* Pointer to the names vector.  */
      unsigned long name_rva = pe_as32 (erva + name_rvas + i * 4);

      /* Pointer to the function address vector.  */ 
      unsigned long func_rva = pe_as32 (erva + exp_funcbase + i * 4);

      /* Find this symbol's section in our own array. */
      int sectix = 0;

      for (sectix = 0; sectix < PE_SECTION_TABLE_SIZE; ++sectix)
	{
	  if ((func_rva >= section_data[sectix].rva_start)
	      && (func_rva < section_data[sectix].rva_end))
	    {
	      add_pe_exported_sym (erva + name_rva,
				   func_rva,
				   section_data + sectix,
				   dll_name,
				   objfile);
	      break;
	    }
	}
    }

  /* discard expdata. */
  do_cleanups (back_to);
}




[-- Attachment #5: Makefile.in.diff --]
[-- Type: application/octet-stream, Size: 3073 bytes --]

Index: Makefile.in
===================================================================
RCS file: /cvs/src/src/gdb/Makefile.in,v
retrieving revision 1.310
diff -c -p -r1.310 Makefile.in
*** Makefile.in	6 Jan 2003 20:45:30 -0000	1.310
--- Makefile.in	10 Jan 2003 22:32:08 -0000
*************** SFILES = ada-exp.y ada-lang.c ada-typepr
*** 501,507 ****
  	ax-general.c ax-gdb.c \
  	bcache.c blockframe.c breakpoint.c buildsym.c builtin-regs.c \
  	c-exp.y c-lang.c c-typeprint.c c-valprint.c \
! 	charset.c cli-out.c coffread.c complaints.c completer.c corefile.c \
  	cp-abi.c cp-support.c cp-valprint.c \
  	dbxread.c demangle.c disasm.c doublest.c \
  	dummy-frame.c dwarfread.c dwarf2read.c \
--- 501,508 ----
  	ax-general.c ax-gdb.c \
  	bcache.c blockframe.c breakpoint.c buildsym.c builtin-regs.c \
  	c-exp.y c-lang.c c-typeprint.c c-valprint.c \
! 	charset.c cli-out.c coffread.c coff-pe-read.c \
! 	complaints.c completer.c corefile.c \
  	cp-abi.c cp-support.c cp-valprint.c \
  	dbxread.c demangle.c disasm.c doublest.c \
  	dummy-frame.c dwarfread.c dwarf2read.c \
*************** call_cmds_h = call-cmds.h
*** 598,603 ****
--- 599,605 ----
  ch_lang_h = ch-lang.h
  cli_out_h = cli-out.h
  coff_solib_h = coff-solib.h
+ coff_pe_read_h = coff-pe-read.h
  command_h = command.h
  complaints_h = complaints.h
  completer_h = completer.h
*************** COMMON_OBS = version.o blockframe.o brea
*** 817,823 ****
  	kod.o kod-cisco.o \
  	gdb-events.o \
  	exec.o bcache.o objfiles.o minsyms.o maint.o demangle.o \
! 	dbxread.o coffread.o elfread.o \
  	dwarfread.o dwarf2read.o mipsread.o stabsread.o corefile.o \
  	c-lang.o f-lang.o \
  	ui-out.o cli-out.o \
--- 819,825 ----
  	kod.o kod-cisco.o \
  	gdb-events.o \
  	exec.o bcache.o objfiles.o minsyms.o maint.o demangle.o \
! 	dbxread.o coffread.o coff-pe-read.o elfread.o \
  	dwarfread.o dwarf2read.o mipsread.o stabsread.o corefile.o \
  	c-lang.o f-lang.o \
  	ui-out.o cli-out.o \
*************** coffread.o: coffread.c $(defs_h) $(symta
*** 1570,1576 ****
  	$(breakpoint_h) $(bfd_h) $(gdb_obstack_h) $(gdb_string_h) \
  	$(coff_internal_h) $(libcoff_h) $(symfile_h) $(objfiles_h) \
  	$(buildsym_h) $(gdb_stabs_h) $(stabsread_h) $(complaints_h) \
! 	$(target_h) $(gdb_assert_h)
  complaints.o: complaints.c $(defs_h) $(complaints_h) $(gdb_assert_h) \
  	$(command_h) $(gdbcmd_h)
  completer.o: completer.c $(defs_h) $(symtab_h) $(gdbtypes_h) $(expression_h) \
--- 1572,1580 ----
  	$(breakpoint_h) $(bfd_h) $(gdb_obstack_h) $(gdb_string_h) \
  	$(coff_internal_h) $(libcoff_h) $(symfile_h) $(objfiles_h) \
  	$(buildsym_h) $(gdb_stabs_h) $(stabsread_h) $(complaints_h) \
! 	$(target_h) $(gdb_assert_h) $(coff_pe_read_h)
! coff-pe-read.o: coff-pe-read.c $(bfd_h) $(defs_h) $(symtab_h) \
! 	$(gdbtypes_h) $(symfile_h) $(objfiles_h) $(coff_pe_read_h)
  complaints.o: complaints.c $(defs_h) $(complaints_h) $(gdb_assert_h) \
  	$(command_h) $(gdbcmd_h)
  completer.o: completer.c $(defs_h) $(symtab_h) $(gdbtypes_h) $(expression_h) \

[-- Attachment #6: coffread.c.diff --]
[-- Type: application/octet-stream, Size: 882 bytes --]

Index: coffread.c
===================================================================
RCS file: /cvs/src/src/gdb/coffread.c,v
retrieving revision 1.32
diff -c -p -r1.32 coffread.c
*** coffread.c	17 Dec 2002 00:39:07 -0000	1.32
--- coffread.c	10 Jan 2003 22:33:35 -0000
***************
*** 45,50 ****
--- 45,52 ----
  #include "target.h"
  #include "gdb_assert.h"
  
+ #include "coff-pe-read.h"
+ 
  extern void _initialize_coffread (void);
  
  struct coff_symfile_info
*************** coff_symtab_read (long symtab_offset, un
*** 1084,1089 ****
--- 1086,1098 ----
  	  process_coff_symbol (cs, &main_aux, objfile);
  	  break;
  	}
+     }
+ 
+   if ((nsyms == 0) && (pe_file))
+     {
+       /* We've got no debugging symbols, but it's is a portable
+ 	 executable, so try to read the export table */
+       read_pe_exported_syms (objfile);
      }
  
    if (last_source_file)