dyn_load.c

Boost provides free peer-reviewed portable C++ source libraries. We emphasize libraries that work

/*
 * Copyright (c) 1991-1994 by Xerox Corporation.  All rights reserved.
 * Copyright (c) 1997 by Silicon Graphics.  All rights reserved.
 *
 * THIS MATERIAL IS PROVIDED AS IS, WITH ABSOLUTELY NO WARRANTY EXPRESSED
 * OR IMPLIED.  ANY USE IS AT YOUR OWN RISK.
 *
 * Permission is hereby granted to use or copy this program
 * for any purpose,  provided the above notices are retained on all copies.
 * Permission to modify the code and to distribute modified code is granted,
 * provided the above notices are retained, and a notice that the code was
 * modified is included with the above copyright notice.
 *
 * Original author: Bill Janssen
 * Heavily modified by Hans Boehm and others
 */

/*
 * This is incredibly OS specific code for tracking down data sections in
 * dynamic libraries.  There appears to be no way of doing this quickly
 * without groveling through undocumented data structures.  We would argue
 * that this is a bug in the design of the dlopen interface.  THIS CODE
 * MAY BREAK IN FUTURE OS RELEASES.  If this matters to you, don't hesitate
 * to let your vendor know ...
 *
 * None of this is safe with dlclose and incremental collection.
 * But then not much of anything is safe in the presence of dlclose.
 */
#if (defined(__linux__) || defined(__GLIBC__) || defined(__GNU__)) \
     && !defined(_GNU_SOURCE)
    /* Can't test LINUX, since this must be defined before other includes */
#   define _GNU_SOURCE
#endif
#if !defined(MACOS) && !defined(_WIN32_WCE)
#  include <sys/types.h>
#endif
#include "private/gc_priv.h"

/* BTL: avoid circular redefinition of dlopen if GC_SOLARIS_THREADS defined */
# if (defined(GC_PTHREADS) || defined(GC_SOLARIS_THREADS)) \
      && defined(dlopen) && !defined(GC_USE_LD_WRAP)
    /* To support threads in Solaris, gc.h interposes on dlopen by       */
    /* defining "dlopen" to be "GC_dlopen", which is implemented below.  */
    /* However, both GC_FirstDLOpenedLinkMap() and GC_dlopen() use the   */
    /* real system dlopen() in their implementation. We first remove     */
    /* gc.h's dlopen definition and restore it later, after GC_dlopen(). */
#   undef dlopen
#   define GC_must_restore_redefined_dlopen
# else
#   undef GC_must_restore_redefined_dlopen
# endif

/* A user-supplied routine that is called to determine if a DSO must
   be scanned by the gc.  */
static int (*GC_has_static_roots)(const char *, void *, size_t);


#if (defined(DYNAMIC_LOADING) || defined(MSWIN32) || defined(MSWINCE)) \
    && !defined(PCR)
#if !defined(SOLARISDL) && !defined(IRIX5) && \
    !defined(MSWIN32) && !defined(MSWINCE) && \
    !(defined(ALPHA) && defined(OSF1)) && \
    !defined(HPUX) && !(defined(LINUX) && defined(__ELF__)) && \
    !defined(AIX) && !defined(SCO_ELF) && !defined(DGUX) && \
    !(defined(FREEBSD) && defined(__ELF__)) && \
    !(defined(NETBSD) && defined(__ELF__)) && !defined(HURD) && \
    !defined(DARWIN) && !defined(CYGWIN32)
 --> We only know how to find data segments of dynamic libraries for the
 --> above.  Additional SVR4 variants might not be too
 --> hard to add.
#endif

#include <stdio.h>
#ifdef SOLARISDL
#   include <sys/elf.h>
#   include <dlfcn.h>
#   include <link.h>
#endif

#if defined(NETBSD)
#   include <machine/elf_machdep.h>
#   define ELFSIZE ARCH_ELFSIZE
#endif

#if defined(LINUX) && defined(__ELF__) || defined(SCO_ELF) || \
    (defined(FREEBSD) && defined(__ELF__)) || defined(DGUX) || \
    (defined(NETBSD) && defined(__ELF__)) || defined(HURD)
#   include <stddef.h>
#   include <elf.h>
#   include <link.h>
#endif

/* Newer versions of GNU/Linux define this macro.  We
 * define it similarly for any ELF systems that don't.  */
#  ifndef ElfW
#    if defined(FREEBSD)
#      if __ELF_WORD_SIZE == 32
#        define ElfW(type) Elf32_##type
#      else
#        define ElfW(type) Elf64_##type
#      endif
#    elif defined(NETBSD)
#      if ELFSIZE == 32
#        define ElfW(type) Elf32_##type
#      else
#        define ElfW(type) Elf64_##type
#      endif
#    else
#      if !defined(ELF_CLASS) || ELF_CLASS == ELFCLASS32
#        define ElfW(type) Elf32_##type
#      else
#        define ElfW(type) Elf64_##type
#      endif
#    endif
#  endif

#if defined(SOLARISDL) && !defined(USE_PROC_FOR_LIBRARIES)

#ifdef LINT
    Elf32_Dyn _DYNAMIC;
#endif

static struct link_map *
GC_FirstDLOpenedLinkMap()
{
    extern ElfW(Dyn) _DYNAMIC;
    ElfW(Dyn) *dp;
    struct r_debug *r;
    static struct link_map * cachedResult = 0;
    static ElfW(Dyn) *dynStructureAddr = 0;
    			/* BTL: added to avoid Solaris 5.3 ld.so _DYNAMIC bug */

#   ifdef SUNOS53_SHARED_LIB
	/* BTL: Avoid the Solaris 5.3 bug that _DYNAMIC isn't being set	*/
	/* up properly in dynamically linked .so's. This means we have	*/
	/* to use its value in the set of original object files loaded	*/
	/* at program startup.						*/
	if( dynStructureAddr == 0 ) {
	  void* startupSyms = dlopen(0, RTLD_LAZY);
	  dynStructureAddr = (ElfW(Dyn)*)dlsym(startupSyms, "_DYNAMIC");
		}
#   else
	dynStructureAddr = &_DYNAMIC;
#   endif

    if( dynStructureAddr == 0) {
        return(0);
    }
    if( cachedResult == 0 ) {
        int tag;
        for( dp = ((ElfW(Dyn) *)(&_DYNAMIC)); (tag = dp->d_tag) != 0; dp++ ) {
            if( tag == DT_DEBUG ) {
                struct link_map *lm
                        = ((struct r_debug *)(dp->d_un.d_ptr))->r_map;
                if( lm != 0 ) cachedResult = lm->l_next; /* might be NIL */
                break;
            }
        }
    }
    return cachedResult;
}

#endif /* SOLARISDL ... */

/* BTL: added to fix circular dlopen definition if GC_SOLARIS_THREADS defined */
# if defined(GC_must_restore_redefined_dlopen)
#   define dlopen GC_dlopen
# endif

# if defined(SOLARISDL)
/* Add dynamic library data sections to the root set.		*/
# if !defined(PCR) && !defined(GC_SOLARIS_THREADS) && defined(THREADS)
	--> fix mutual exclusion with dlopen
# endif

# ifndef USE_PROC_FOR_LIBRARIES
void GC_register_dynamic_libraries()
{
  struct link_map *lm = GC_FirstDLOpenedLinkMap();
  

  for (lm = GC_FirstDLOpenedLinkMap();
       lm != (struct link_map *) 0;  lm = lm->l_next)
    {
	ElfW(Ehdr) * e;
        ElfW(Phdr) * p;
        unsigned long offset;
        char * start;
        register int i;
        
	e = (ElfW(Ehdr) *) lm->l_addr;
        p = ((ElfW(Phdr) *)(((char *)(e)) + e->e_phoff));
        offset = ((unsigned long)(lm->l_addr));
        for( i = 0; i < (int)(e->e_phnum); ((i++),(p++)) ) {
          switch( p->p_type ) {
            case PT_LOAD:
              {
                if( !(p->p_flags & PF_W) ) break;
                start = ((char *)(p->p_vaddr)) + offset;
                GC_add_roots_inner(
                  start,
                  start + p->p_memsz,
                  TRUE
                );
              }
              break;
            default:
              break;
          }
	}
    }
}

# endif /* !USE_PROC ... */
# endif /* SOLARISDL */

#if defined(LINUX) && defined(__ELF__) || defined(SCO_ELF) || \
    (defined(FREEBSD) && defined(__ELF__)) || defined(DGUX) || \
    (defined(NETBSD) && defined(__ELF__)) || defined(HURD)


#ifdef USE_PROC_FOR_LIBRARIES

#include <string.h>

#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>

#define MAPS_BUF_SIZE (32*1024)

extern ssize_t GC_repeat_read(int fd, char *buf, size_t count);
	/* Repeatedly read until buffer is filled, or EOF is encountered */
	/* Defined in os_dep.c.  					 */

char *GC_parse_map_entry(char *buf_ptr, ptr_t *start, ptr_t *end,
                         char **prot, unsigned int *maj_dev,
			 char **mapping_name);
char *GC_get_maps(void);
	/* From os_dep.c	*/

word GC_register_map_entries(char *maps)
{
    char *prot;
    char *buf_ptr = maps;
    int count;
    ptr_t start, end;
    unsigned int maj_dev;
    ptr_t least_ha, greatest_ha;
    unsigned i;
    ptr_t datastart = (ptr_t)(DATASTART);

    /* Compute heap bounds. FIXME: Should work if heap and roots are 	*/
    /* interleaved?							*/
	least_ha = (ptr_t)(word)(-1);
	greatest_ha = 0;
	for (i = 0; i < GC_n_heap_sects; ++i) {
	    ptr_t sect_start = GC_heap_sects[i].hs_start;
	    ptr_t sect_end = sect_start + GC_heap_sects[i].hs_bytes;
	    if (sect_start < least_ha) least_ha = sect_start;
	    if (sect_end > greatest_ha) greatest_ha = sect_end;
        }
    	if (greatest_ha < (ptr_t)GC_scratch_last_end_ptr)
	    greatest_ha = (ptr_t)GC_scratch_last_end_ptr; 

    for (;;) {
        buf_ptr = GC_parse_map_entry(buf_ptr, &start, &end, &prot, &maj_dev, 0);
	if (buf_ptr == NULL) return 1;
	if (prot[1] == 'w') {
	    /* This is a writable mapping.  Add it to		*/
	    /* the root set unless it is already otherwise	*/
	    /* accounted for.					*/
	    if (start <= GC_stackbottom && end >= GC_stackbottom) {
		/* Stack mapping; discard	*/
		continue;
	    }
#	    ifdef THREADS
	      /* This may fail, since a thread may already be 		*/
	      /* unregistered, but its thread stack may still be there.	*/
	      /* That can fail because the stack may disappear while	*/
	      /* we're marking.  Thus the marker is, and has to be	*/
	      /* prepared to recover from segmentation faults.		*/
	      if (GC_segment_is_thread_stack(start, end)) continue;
	      /* FIXME: REDIRECT_MALLOC actually works with threads on	*/
	      /* LINUX/IA64 if we omit this check.  The problem is that	*/
	      /* thread stacks contain pointers to dynamic thread	*/
	      /* vectors, which may be reused due to thread caching.	*/
	      /* Currently they may not be marked if the thread is 	*/
	      /* still live.						*/
	      /* For dead threads, we trace the whole stack, which is	*/
	      /* very suboptimal for performance reasons.		*/
#	    endif
	    /* We no longer exclude the main data segment.		*/
	    if (start < least_ha && end > least_ha) {
		end = least_ha;
	    }
	    if (start < greatest_ha && end > greatest_ha) {
		start = greatest_ha;
	    }
	    if (start >= least_ha && end <= greatest_ha) continue;
	    GC_add_roots_inner((char *)start, (char *)end, TRUE);
	}
    }
    return 1;
}

void GC_register_dynamic_libraries()
{
    if (!GC_register_map_entries(GC_get_maps()))
        ABORT("Failed to read /proc for library registration.");
}

/* We now take care of the main data segment ourselves: */
GC_bool GC_register_main_static_data()
{
    return FALSE;
}
  
# define HAVE_REGISTER_MAIN_STATIC_DATA

#endif /* USE_PROC_FOR_LIBRARIES */

#if !defined(USE_PROC_FOR_LIBRARIES)
/* The following is the preferred way to walk dynamic libraries	*/
/* For glibc 2.2.4+.  Unfortunately, it doesn't work for older	*/
/* versions.  Thanks to Jakub Jelinek for most of the code.	*/

# if (defined(LINUX) || defined (__GLIBC__)) /* Are others OK here, too? */ \
     && (__GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2) \
         || (__GLIBC__ == 2 && __GLIBC_MINOR__ == 2 && defined(DT_CONFIG))) 

/* We have the header files for a glibc that includes dl_iterate_phdr.	*/
/* It may still not be available in the library on the target system.   */
/* Thus we also treat it as a weak symbol.				*/
#define HAVE_DL_ITERATE_PHDR

static int GC_register_dynlib_callback(info, size, ptr)
     struct dl_phdr_info * info;
     size_t size;
     void * ptr;
{
  const ElfW(Phdr) * p;
  char * start;
  register int i;

  /* Make sure struct dl_phdr_info is at least as big as we need.  */
  if (size < offsetof (struct dl_phdr_info, dlpi_phnum)
      + sizeof (info->dlpi_phnum))
    return -1;

  p = info->dlpi_phdr;
  for( i = 0; i < (int)(info->dlpi_phnum); ((i++),(p++)) ) {
    switch( p->p_type ) {
      case PT_LOAD:
	{
	  if( !(p->p_flags & PF_W) ) break;
	  start = ((char *)(p->p_vaddr)) + info->dlpi_addr;

	  if (GC_has_static_roots
	      && !GC_has_static_roots(info->dlpi_name, start, p->p_memsz))
	    break;

	  GC_add_roots_inner(start, start + p->p_memsz, TRUE);
	}
      break;
      default:
	break;
    }
  }

  * (int *)ptr = 1;	/* Signal that we were called */
  return 0;
}     

/* Return TRUE if we succeed, FALSE if dl_iterate_phdr wasn't there. */

#pragma weak dl_iterate_phdr

GC_bool GC_register_dynamic_libraries_dl_iterate_phdr()
{
  if (dl_iterate_phdr) {
    int did_something = 0;
    dl_iterate_phdr(GC_register_dynlib_callback, &did_something);
    if (!did_something) {
	/* dl_iterate_phdr may forget the static data segment in	*/
	/* statically linked executables.				*/
	GC_add_roots_inner(DATASTART, (char *)(DATAEND), TRUE);
#       if defined(DATASTART2)
          GC_add_roots_inner(DATASTART2, (char *)(DATAEND2), TRUE);
#       endif
    }

    return TRUE;
  } else {
    return FALSE;
  }
}