libdw: Resolve alt file on first use.

Add a new alt_fd field to the Dwarf struct. This tracks whether we tried
to open the alt file ourselves. This is used in dwarf_getalt to see if
we should try to find and open the alt file ourselves (if the user hasn't
called dwarf_setalt yet). dwarf_formref_die and dwarf_formstring now call
dwarf_getalt instead of accessing the alt_dwarf Dwarf field directly.

For applications using libdwfl nothing changes (dwfl will find, set and
clean up the alt file). For programs that set the alt file themselves
already through other means, nothing changes. But for applications that
don't create the Dwarf through libdwfl and don't set the alt file already
libdw will now try to find and set it on first access. If found the
application will now not get errors for missing alt files.

Add a simple testcase based on the existing allfcts test which already
tries to set the alt file, but is too simplistic to find it in some
subdir (relative to the main debug file).

Signed-off-by: Mark Wielaard <mark@klomp.org>

10 files changed, 231 insertions, 15 deletions

diff --git a/libdw/ChangeLog b/libdw/ChangeLog
index 479dd42b..cb5e61ac 100644
--- a/libdw/ChangeLog
+++ b/libdw/ChangeLog
@@ -1,3 +1,22 @@
+2018-01-22  Mark Wielaard  <mark@klomp.org>
+
+	* Makefile.am (AM_CPPFLAGS): Add -I libdwelf.
+	* dwarf_begin_elf.c (dwarf_begin_elf): Initialize Dwarf alt_fd to -1.
+	* dwarf_end.c (dwarf_end): Call dwarf_end and close on the alt_dwarf
+	and alt_fd if we allocated them.
+	* dwarf_fromref_die.c (dwarf_formref_die): Call dwarf_getalt.
+	* dwarf_formstring.c (dwarf_formstring): Likewise.
+	* dwarf_getalt.c (__libdw_filepath): New internal function.
+	(find_debug_altlink): New static function.
+	(dwarf_getalt): Check Dwarf alt_dwarf and call find_debug_altlink.
+	Cache result.
+	* dwarf_setalt.c (dwarf_setalt): Clean up Dwarf alt_dwarf and alt_fd
+	if we allocated.
+	* libdw.h (dwarf_getalt): Extend documentation.
+	(dwarf_setalt): Likewise.
+	* libdwP.h (struct Dwarf): Add alt_fd field.
+	(filepath): Declare new internal function.
+
 2018-01-14  Petr Machata  <pmachata@gmail.com>
 
 	* dwarf_formsdata.c (dwarf_formsdata):
diff --git a/libdw/Makefile.am b/libdw/Makefile.am
index 8ee46802..8545b5b4 100644
--- a/libdw/Makefile.am
+++ b/libdw/Makefile.am
@@ -1,6 +1,6 @@
 ## Process this file with automake to create Makefile.in
 ##
-## Copyright (C) 2002-2010, 2012, 2014, 2016 Red Hat, Inc.
+## Copyright (C) 2002-2010, 2012, 2014, 2016, 2018 Red Hat, Inc.
 ## This file is part of elfutils.
 ##
 ## This file is free software; you can redistribute it and/or modify
@@ -31,7 +31,7 @@ include $(top_srcdir)/config/eu.am
 if BUILD_STATIC
 AM_CFLAGS += $(fpic_CFLAGS)
 endif
-AM_CPPFLAGS += -I$(srcdir)/../libelf
+AM_CPPFLAGS += -I$(srcdir)/../libelf -I$(srcdir)/../libdwelf
 VERSION = 1
 
 lib_LIBRARIES = libdw.a
diff --git a/libdw/dwarf_begin_elf.c b/libdw/dwarf_begin_elf.c
index 7c3fe103..6834ac53 100644
--- a/libdw/dwarf_begin_elf.c
+++ b/libdw/dwarf_begin_elf.c
@@ -1,5 +1,5 @@
 /* Create descriptor from ELF descriptor for processing file.
-   Copyright (C) 2002-2011, 2014, 2015 Red Hat, Inc.
+   Copyright (C) 2002-2011, 2014, 2015, 2018 Red Hat, Inc.
    This file is part of elfutils.
    Written by Ulrich Drepper <drepper@redhat.com>, 2002.
 
@@ -326,6 +326,7 @@ dwarf_begin_elf (Elf *elf, Dwarf_Cmd cmd, Elf_Scn *scngrp)
     result->other_byte_order = true;
 
   result->elf = elf;
+  result->alt_fd = -1;
 
   /* Initialize the memory handling.  */
   result->mem_default_size = mem_default_size;
diff --git a/libdw/dwarf_end.c b/libdw/dwarf_end.c
index 6c6d985a..f6915abf 100644
--- a/libdw/dwarf_end.c
+++ b/libdw/dwarf_end.c
@@ -1,5 +1,5 @@
 /* Release debugging handling context.
-   Copyright (C) 2002-2011, 2014 Red Hat, Inc.
+   Copyright (C) 2002-2011, 2014, 2018 Red Hat, Inc.
    This file is part of elfutils.
    Written by Ulrich Drepper <drepper@redhat.com>, 2002.
 
@@ -35,6 +35,7 @@
 #include <stdlib.h>
 #include <assert.h>
 #include <string.h>
+#include <unistd.h>
 
 #include "libdwP.h"
 #include "cfi.h"
@@ -103,6 +104,13 @@ dwarf_end (Dwarf *dwarf)
 	  free (dwarf->fake_loc_cu);
 	}
 
+      /* Did we find and allocate the alt Dwarf ourselves?  */
+      if (dwarf->alt_fd != -1)
+	{
+	  INTUSE(dwarf_end) (dwarf->alt_dwarf);
+	  close (dwarf->alt_fd);
+	}
+
       /* Free the context descriptor.  */
       free (dwarf);
     }
diff --git a/libdw/dwarf_formref_die.c b/libdw/dwarf_formref_die.c
index 7e2b11a2..704816f8 100644
--- a/libdw/dwarf_formref_die.c
+++ b/libdw/dwarf_formref_die.c
@@ -1,5 +1,5 @@
 /* Look up the DIE in a reference-form attribute.
-   Copyright (C) 2005-2010 Red Hat, Inc.
+   Copyright (C) 2005-2010, 2018 Red Hat, Inc.
    This file is part of elfutils.
 
    This file is free software; you can redistribute it and/or modify
@@ -53,7 +53,7 @@ dwarf_formref_die (Dwarf_Attribute *attr, Dwarf_Die *result)
 			  : cu->offset_size);
 
       Dwarf *dbg_ret = (attr->form == DW_FORM_GNU_ref_alt
-			? cu->dbg->alt_dwarf : cu->dbg);
+			? INTUSE(dwarf_getalt) (cu->dbg) : cu->dbg);
 
       if (dbg_ret == NULL)
 	{
diff --git a/libdw/dwarf_formstring.c b/libdw/dwarf_formstring.c
index 83abd53d..4eae0ede 100644
--- a/libdw/dwarf_formstring.c
+++ b/libdw/dwarf_formstring.c
@@ -1,5 +1,5 @@
 /* Return string associated with given attribute.
-   Copyright (C) 2003-2010, 2013 Red Hat, Inc.
+   Copyright (C) 2003-2010, 2013, 2018 Red Hat, Inc.
    This file is part of elfutils.
    Written by Ulrich Drepper <drepper@redhat.com>, 2003.
 
@@ -48,7 +48,8 @@ dwarf_formstring (Dwarf_Attribute *attrp)
     return (const char *) attrp->valp;
 
   Dwarf *dbg = attrp->cu->dbg;
-  Dwarf *dbg_ret = attrp->form == DW_FORM_GNU_strp_alt ? dbg->alt_dwarf : dbg;
+  Dwarf *dbg_ret = (attrp->form == DW_FORM_GNU_strp_alt
+		    ? INTUSE(dwarf_getalt) (dbg) : dbg);
 
   if (unlikely (dbg_ret == NULL))
     {
diff --git a/libdw/dwarf_getalt.c b/libdw/dwarf_getalt.c
index cc434f03..3e5af151 100644
--- a/libdw/dwarf_getalt.c
+++ b/libdw/dwarf_getalt.c
@@ -1,5 +1,5 @@
 /* Retrieves the DWARF descriptor for debugaltlink data.
-   Copyright (C) 2014 Red Hat, Inc.
+   Copyright (C) 2014, 2018 Red Hat, Inc.
    This file is part of elfutils.
 
    This file is free software; you can redistribute it and/or modify
@@ -31,12 +31,166 @@
 #endif
 
 #include "libdwP.h"
+#include "libelfP.h"
+#include "libdwelfP.h"
+#include "system.h"
+
+#include <inttypes.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+
+char *
+internal_function
+__libdw_filepath (int fd, const char *dir, const char *file)
+{
+  if (file == NULL)
+    return NULL;
+
+  if (file[0] == '/')
+    return strdup (file);
+
+  if (dir != NULL && dir[0] == '/')
+    {
+      size_t dirlen = strlen (dir);
+      size_t filelen = strlen (file);
+      size_t len = dirlen + 1 + filelen + 1;
+      char *path = malloc (len);
+      if (path != NULL)
+	{
+	  char *c = mempcpy (path, dir, dirlen);
+	  if (dir[dirlen - 1] != '/')
+	    *c++ = '/';
+	  mempcpy (c, file, filelen + 1);
+	}
+      return path;
+    }
+
+  if (fd >= 0)
+    {
+      /* strlen ("/proc/self/fd/") = 14 + strlen (<MAXINT>) = 10 + 1 = 25.  */
+      char devfdpath[25];
+      sprintf (devfdpath, "/proc/self/fd/%u", fd);
+      char *fdpath = realpath (devfdpath, NULL);
+      char *path = NULL;
+      char *fddir;
+      if (fdpath != NULL && fdpath[0] == '/'
+	  && (fddir = strrchr (fdpath, '/')) != NULL)
+	{
+	  *++fddir = '\0';
+	  size_t fdpathlen = strlen (fdpath);
+	  size_t dirlen = dir != NULL ? strlen (dir) : 0;
+	  size_t filelen = strlen (file);
+	  size_t len = fdpathlen + 1 + dirlen + 1 + filelen + 1;
+	  path = malloc (len);
+	  if (path != NULL)
+	    {
+	      char *c = mempcpy (path, fdpath, fdpathlen);
+	      if (dirlen > 0)
+		{
+		  c = mempcpy (c, dir, dirlen);
+		  if (dir[dirlen - 1] != '/')
+		    *c++ = '/';
+		}
+	      mempcpy (c, file, filelen + 1);
+	    }
+	}
+      free (fdpath);
+      return path;
+    }
+
+  return NULL;
+}
+
+static void
+find_debug_altlink (Dwarf *dbg)
+{
+  const char *altname;
+  const void *build_id;
+  ssize_t build_id_len = INTUSE(dwelf_dwarf_gnu_debugaltlink) (dbg,
+							       &altname,
+							       &build_id);
+
+  /* Couldn't even get the debugaltlink.  It probably doesn't exist.  */
+  if (build_id_len <= 0)
+    return;
+
+  const uint8_t *id = (const uint8_t *) build_id;
+  size_t id_len = build_id_len;
+  int fd = -1;
+
+  /* We only look in the standard path.  And relative to the dbg file.  */
+#define DEBUGINFO_PATH "/usr/lib/debug"
+
+  /* We don't handle very short or really large build-ids.  We need at
+     at least 3 and allow for up to 64 (normally ids are 20 long).  */
+#define MIN_BUILD_ID_BYTES 3
+#define MAX_BUILD_ID_BYTES 64
+  if (id_len >= MIN_BUILD_ID_BYTES && id_len <= MAX_BUILD_ID_BYTES)
+    {
+      /* Note sizeof a string literal includes the trailing zero.  */
+      char id_path[sizeof DEBUGINFO_PATH - 1 + sizeof "/.build-id/" - 1
+		   + 2 + 1 + (MAX_BUILD_ID_BYTES - 2) * 2 + sizeof ".debug"];
+      sprintf (&id_path[0], "%s%s", DEBUGINFO_PATH, "/.build-id/");
+      sprintf (&id_path[sizeof DEBUGINFO_PATH - 1 + sizeof "/.build-id/" - 1],
+	       "%02" PRIx8 "/", (uint8_t) id[0]);
+      for (size_t i = 1; i < id_len; ++i)
+	sprintf (&id_path[sizeof DEBUGINFO_PATH - 1 + sizeof "/.build-id/" - 1
+			  + 3 + (i - 1) * 2], "%02" PRIx8, (uint8_t) id[i]);
+      strcpy (&id_path[sizeof DEBUGINFO_PATH - 1 + sizeof "/.build-id/" - 1
+		       + 3 + (id_len - 1) * 2], ".debug");
+
+      fd = TEMP_FAILURE_RETRY (open (id_path, O_RDONLY));
+    }
+
+  /* Fall back on (possible relative) alt file path.  */
+  if (fd < 0)
+    {
+      char *altpath = __libdw_filepath (dbg->elf->fildes, NULL, altname);
+      if (altpath != NULL)
+	{
+	  fd = TEMP_FAILURE_RETRY (open (altpath, O_RDONLY));
+	  free (altpath);
+	}
+    }
+
+  if (fd >= 0)
+    {
+      Dwarf *alt = dwarf_begin (fd, O_RDONLY);
+      if (alt != NULL)
+	{
+	  dbg->alt_dwarf = alt;
+	  dbg->alt_fd = fd;
+	}
+      else
+	close (fd);
+    }
+}
 
 Dwarf *
 dwarf_getalt (Dwarf *main)
 {
-  if (main == NULL)
+  /* Only try once.  */
+  if (main == NULL || main->alt_dwarf == (void *) -1)
     return NULL;
+
+  if (main->alt_dwarf != NULL)
+    return main->alt_dwarf;
+
+  find_debug_altlink (main);
+
+  /* If we found nothing, make sure we don't try again.  */
+  if (main->alt_dwarf == NULL)
+    {
+      main->alt_dwarf = (void *) -1;
+      return NULL;
+    }
+
   return main->alt_dwarf;
 }
 INTDEF (dwarf_getalt)
diff --git a/libdw/dwarf_setalt.c b/libdw/dwarf_setalt.c
index 9bd566ff..9051b8e0 100644
--- a/libdw/dwarf_setalt.c
+++ b/libdw/dwarf_setalt.c
@@ -1,5 +1,5 @@
 /* Provides the data referenced by the .gnu_debugaltlink section.
-   Copyright (C) 2014 Red Hat, Inc.
+   Copyright (C) 2014, 2018 Red Hat, Inc.
    This file is part of elfutils.
 
    This file is free software; you can redistribute it and/or modify
@@ -32,9 +32,18 @@
 
 #include "libdwP.h"
 
+#include <unistd.h>
+
 void
 dwarf_setalt (Dwarf *main, Dwarf *alt)
 {
+  if (main->alt_fd != -1)
+    {
+      INTUSE(dwarf_end) (main->alt_dwarf);
+      close (main->alt_fd);
+      main->alt_fd = -1;
+    }
+
   main->alt_dwarf = alt;
 }
 INTDEF (dwarf_setalt)
diff --git a/libdw/libdw.h b/libdw/libdw.h
index e42c0873..1dcc8153 100644
--- a/libdw/libdw.h
+++ b/libdw/libdw.h
@@ -1,5 +1,5 @@
 /* Interfaces for libdw.
-   Copyright (C) 2002-2010, 2013, 2014, 2016 Red Hat, Inc.
+   Copyright (C) 2002-2010, 2013, 2014, 2016, 2018 Red Hat, Inc.
    This file is part of elfutils.
 
    This file is free software; you can redistribute it and/or modify
@@ -250,7 +250,9 @@ extern Elf *dwarf_getelf (Dwarf *dwarf);
 extern Dwarf *dwarf_cu_getdwarf (Dwarf_CU *cu);
 
 /* Retrieves the DWARF descriptor for debugaltlink data.  Returns NULL
-   if no alternate debug data has been supplied.  */
+   if no alternate debug data has been supplied yet.  libdw will try
+   to set the alt file on first use of an alt FORM if not yet explicitly
+   provided by dwarf_setalt.  */
 extern Dwarf *dwarf_getalt (Dwarf *main);
 
 /* Provides the data referenced by the .gnu_debugaltlink section.  The
@@ -258,7 +260,9 @@ extern Dwarf *dwarf_getalt (Dwarf *main);
    same build ID).  It is the responsibility of the caller to ensure
    that the data referenced by ALT stays valid while it is used by
    MAIN, until dwarf_setalt is called on MAIN with a different
-   descriptor, or dwarf_end.  */
+   descriptor, or dwarf_end.  Must be called before inspecting DIEs
+   that might have alt FORMs.  Otherwise libdw will try to set the
+   alt file itself on first use.  */
 extern void dwarf_setalt (Dwarf *main, Dwarf *alt);
 
 /* Release debugging handling context.  */
diff --git a/libdw/libdwP.h b/libdw/libdwP.h
index fbb8ed08..0681aa15 100644
--- a/libdw/libdwP.h
+++ b/libdw/libdwP.h
@@ -1,5 +1,5 @@
 /* Internal definitions for libdwarf.
-   Copyright (C) 2002-2011, 2013-2017 Red Hat, Inc.
+   Copyright (C) 2002-2011, 2013-2018 Red Hat, Inc.
    This file is part of elfutils.
    Written by Ulrich Drepper <drepper@redhat.com>, 2002.
 
@@ -154,6 +154,10 @@ struct Dwarf
   /* If true, we allocated the ELF descriptor ourselves.  */
   bool free_elf;
 
+  /* If >= 0, we allocated the alt_dwarf ourselves and must end it and
+     close this file descriptor.  */
+  int alt_fd;
+
   /* Information for traversing the .debug_pubnames section.  This is
      an array and separately allocated with malloc.  */
   struct pubnames_s
@@ -760,6 +764,22 @@ int __libdw_getsrclines (Dwarf *dbg, Dwarf_Off debug_line_offset,
 /* Load and return value of DW_AT_comp_dir from CUDIE.  */
 const char *__libdw_getcompdir (Dwarf_Die *cudie);
 
+/* Given a file descriptor, dir and file returns a full path.  If the
+   file is absolute (starts with a /) a copy of file is returned.  If
+   the file isn't absolute, but dir is absolute, then a path that is
+   the concatenation of dir and file is returned.  If neither file,
+   nor dir is absolute, the path will be constructed using dir (if not
+   NULL) and file relative to the path of the given file descriptor
+   (if valid).
+
+   The file descriptor may be -1 and the dir may be NULL (in which
+   case they aren't used). If file is NULL, or no full path can be
+   constructed NULL is returned.
+
+   The caller is responsible for freeing the result if not NULL.  */
+char * filepath (int fd, const char *dir, const char *file)
+  internal_function;
+
 
 /* Aliases to avoid PLTs.  */
 INTDECL (dwarf_aggregate_size)