diff mbox series

[2/2] elf: Always call destructors in reverse constructor order

Message ID dc8b3c5769667256401da0a949f91194b1e0653f.1639515239.git.fweimer@redhat.com
State Superseded
Headers show
Series Predictable ELF destructor ordering | expand

Checks

Context Check Description
dj/TryBot-apply_patch success Patch applied to master at the time it was sent
dj/TryBot-32bit success Build for i686

Commit Message

Florian Weimer Dec. 14, 2021, 9:02 p.m. UTC
The current implementation of dlclose (and process exit) re-sorts
the link maps before calling ELF destructors.  Destructor order
is not the reverse of the constructor order as a result: The second
sort took relocation dependencies into account until recently, and
other differences can result from ambiguous inputs, such as cycles.
(After the changes in this commit, there is still a required
difference due to dlopen/dlclose ordering by the application,
but the previous discrepancies went beyond that.)

A new global (namespace-spanning) list of link maps,
_dl_init_called_list, is updated right before ELF constructors are
called from _dl_init.

In dl_close_worker, the maps variable, an on-stack variable length
array, is eliminated.  (VLAs are problematic, and dlclose should not
call malloc because it cannot readily deal with malloc failure.)
Marking still-used objects uses the namespace list directly, with
next and next_idx replacing the done_index variable.

After marking, _dl_init_called_list is used to call the destructors
of now-unused maps in reverse destructor order.  These destructors
can call dlopen.  Previously, new objects do not have l_map_used set.
This had to change: There is no copy of the link map list anymore,
so processing would cover newly opened (and unmarked) mappings,
unloading them.  Now, _dl_init (indirectly) sets l_map_used, to.
(dlclose is handled by the existing reentrancy guard.)

After _dl_init_called_list traversal, two more loops follow.  The
processing order changes to the original link map order in the
namespace.  Previously, dependency order was used.  The difference
should not matter because relocation dependencies could already
reorder link maps in the old code.

The changes to _dl_fini remove the sorting step and replace it with
a traversal of the _dl_init_called_list.  The l_direct_opencount
decrement outside the loader lock is removed because it appears
incorrect: the counter manipulation could race with other dynamic
loader operations.

tst-bz15311 is updated: the output now shows the reversed destructor
order compared to construction.
---
 elf/dl-close.c             | 130 +++++++++++++---------
 elf/dl-fini.c              | 216 ++++++++++++++-----------------------
 elf/dl-init.c              |  14 +++
 elf/dso-sort-tests-1.def   |   2 +-
 include/link.h             |   4 +
 sysdeps/generic/ldsodefs.h |   4 +
 6 files changed, 182 insertions(+), 188 deletions(-)
diff mbox series

Patch

diff --git a/elf/dl-close.c b/elf/dl-close.c
index 5d31389c91..19eadc8ede 100644
--- a/elf/dl-close.c
+++ b/elf/dl-close.c
@@ -167,30 +167,31 @@  _dl_close_worker (struct link_map *map, bool force)
 
   bool any_tls = false;
   const unsigned int nloaded = ns->_ns_nloaded;
-  struct link_map *maps[nloaded];
 
-  /* Run over the list and assign indexes to the link maps and enter
-     them into the MAPS array.  */
+  /* Run over the list and assign indexes to the link maps.  */
   int idx = 0;
   for (struct link_map *l = ns->_ns_loaded; l != NULL; l = l->l_next)
     {
       l->l_map_used = 0;
       l->l_map_done = 0;
       l->l_idx = idx;
-      maps[idx] = l;
       ++idx;
     }
   assert (idx == nloaded);
 
-  /* Keep track of the lowest index link map we have covered already.  */
-  int done_index = -1;
-  while (++done_index < nloaded)
+  /* Keep marking link maps until no new link maps are found.  */
+  for (struct link_map *l = ns->_ns_loaded; l != NULL; )
     {
-      struct link_map *l = maps[done_index];
+      /* next is reset to earlier link maps for remarking.  */
+      struct link_map *next = l->l_next;
+      int next_idx = l->l_idx + 1; /* next->l_idx, but covers next == NULL.  */
 
       if (l->l_map_done)
-	/* Already handled.  */
-	continue;
+	{
+	  /* Already handled.  */
+	  l = next;
+	  continue;
+	}
 
       /* Check whether this object is still used.  */
       if (l->l_type == lt_loaded
@@ -200,7 +201,10 @@  _dl_close_worker (struct link_map *map, bool force)
 	     acquire is sufficient and correct.  */
 	  && atomic_load_acquire (&l->l_tls_dtor_count) == 0
 	  && !l->l_map_used)
-	continue;
+	{
+	  l = next;
+	  continue;
+	}
 
       /* We need this object and we handle it now.  */
       l->l_map_used = 1;
@@ -227,8 +231,11 @@  _dl_close_worker (struct link_map *map, bool force)
 			 already processed it, then we need to go back
 			 and process again from that point forward to
 			 ensure we keep all of its dependencies also.  */
-		      if ((*lp)->l_idx - 1 < done_index)
-			done_index = (*lp)->l_idx - 1;
+		      if ((*lp)->l_idx < next_idx)
+			{
+			  next = *lp;
+			  next_idx = next->l_idx;
+			}
 		    }
 		}
 
@@ -248,51 +255,50 @@  _dl_close_worker (struct link_map *map, bool force)
 		if (!jmap->l_map_used)
 		  {
 		    jmap->l_map_used = 1;
-		    if (jmap->l_idx - 1 < done_index)
-		      done_index = jmap->l_idx - 1;
+		    if (jmap->l_idx < next_idx)
+		      {
+			  next = jmap;
+			  next_idx = next->l_idx;
+		      }
 		  }
 	      }
 	  }
-    }
 
-  /* Sort the entries.  We can skip looking for the binary itself which is
-     at the front of the search list for the main namespace.  */
-  _dl_sort_maps (maps, nloaded, (nsid == LM_ID_BASE));
+      l = next;
+    }
 
   /* Call all termination functions at once.  */
 #ifdef SHARED
   bool do_audit = GLRO(dl_naudit) > 0 && !ns->_ns_loaded->l_auditing;
 #endif
-  bool unload_any = false;
-  bool scope_mem_left = false;
-  unsigned int unload_global = 0;
-  unsigned int first_loaded = ~0;
-  for (unsigned int i = 0; i < nloaded; ++i)
-    {
-      struct link_map *imap = maps[i];
 
-      /* All elements must be in the same namespace.  */
-      assert (imap->l_ns == nsid);
+  /* Call the destructors in reverse constructor order, and remove the
+     closed link maps from the list.  */
+  for (struct link_map **init_called_head = &_dl_init_called_list;
+       *init_called_head != NULL; )
+    {
+      struct link_map *imap = *init_called_head;
 
-      if (!imap->l_map_used)
+      /* _dl_init_called_list is global, to produce a global odering.
+	 Ignore the other namespaces (and link maps that are still used).  */
+      if (imap->l_ns != nsid || imap->l_map_used)
+	init_called_head = &imap->l_init_called_next;
+      else
 	{
 	  assert (imap->l_type == lt_loaded && !imap->l_nodelete_active);
 
-	  /* Call its termination function.  Do not do it for
-	     half-cooked objects.  Temporarily disable exception
-	     handling, so that errors are fatal.  */
-	  if (imap->l_init_called)
-	    {
-	      /* When debugging print a message first.  */
-	      if (__builtin_expect (GLRO(dl_debug_mask) & DL_DEBUG_IMPCALLS,
-				    0))
-		_dl_debug_printf ("\ncalling fini: %s [%lu]\n\n",
-				  imap->l_name, nsid);
-
-	      if (imap->l_info[DT_FINI_ARRAY] != NULL
-		  || imap->l_info[DT_FINI] != NULL)
-		_dl_catch_exception (NULL, call_destructors, imap);
-	    }
+	  /* _dl_init_called_list is updated at the same time as
+	     l_init_called.  */
+	  assert (imap->l_init_called);
+
+	  /* When debugging print a message first.  */
+	  if (__builtin_expect (GLRO(dl_debug_mask) & DL_DEBUG_IMPCALLS, 0))
+	    _dl_debug_printf ("\ncalling fini: %s [%lu]\n\n",
+			      imap->l_name, nsid);
+
+	  if (imap->l_info[DT_FINI_ARRAY] != NULL
+	      || imap->l_info[DT_FINI] != NULL)
+	    _dl_catch_exception (NULL, call_destructors, imap);
 
 #ifdef SHARED
 	  /* Auditing checkpoint: we remove an object.  */
@@ -313,7 +319,26 @@  _dl_close_worker (struct link_map *map, bool force)
 		}
 	    }
 #endif
+	  /* Unlink this link map.  */
+	  *init_called_head = imap->l_init_called_next;
+	}
+    }
+
+
+  bool unload_any = false;
+  bool scope_mem_left = false;
+  unsigned int unload_global = 0;
 
+  /* For skipping un-unloadable link maps in the second loop.  */
+  struct link_map *first_loaded = ns->_ns_loaded;
+
+  /* Iterate over the namespace to find objects to unload.  Some
+     unloadable objects may not be on _dl_init_called_list due to
+     dlopen failure.  */
+  for (struct link_map *imap = first_loaded; imap != NULL; imap = imap->l_next)
+    {
+      if (!imap->l_map_used)
+	{
 	  /* This object must not be used anymore.  */
 	  imap->l_removed = 1;
 
@@ -324,8 +349,8 @@  _dl_close_worker (struct link_map *map, bool force)
 	    ++unload_global;
 
 	  /* Remember where the first dynamically loaded object is.  */
-	  if (i < first_loaded)
-	    first_loaded = i;
+	  if (first_loaded == NULL)
+	      first_loaded = imap;
 	}
       /* Else imap->l_map_used.  */
       else if (imap->l_type == lt_loaded)
@@ -461,8 +486,8 @@  _dl_close_worker (struct link_map *map, bool force)
 	    imap->l_loader = NULL;
 
 	  /* Remember where the first dynamically loaded object is.  */
-	  if (i < first_loaded)
-	    first_loaded = i;
+	  if (first_loaded == NULL)
+	      first_loaded = imap;
 	}
     }
 
@@ -551,10 +576,11 @@  _dl_close_worker (struct link_map *map, bool force)
 
   /* Check each element of the search list to see if all references to
      it are gone.  */
-  for (unsigned int i = first_loaded; i < nloaded; ++i)
+  for (struct link_map *imap = first_loaded; imap != NULL; )
     {
-      struct link_map *imap = maps[i];
-      if (!imap->l_map_used)
+      if (imap->l_map_used)
+	imap = imap->l_next;
+      else
 	{
 	  assert (imap->l_type == lt_loaded);
 
@@ -762,7 +788,9 @@  _dl_close_worker (struct link_map *map, bool force)
 	  if (imap == GL(dl_initfirst))
 	    GL(dl_initfirst) = NULL;
 
+	  struct link_map *next = imap->l_next;
 	  free (imap);
+	  imap = next;
 	}
     }
 
diff --git a/elf/dl-fini.c b/elf/dl-fini.c
index 1aa47bc7c5..bb76bea27f 100644
--- a/elf/dl-fini.c
+++ b/elf/dl-fini.c
@@ -29,154 +29,98 @@  typedef void (*fini_t) (void);
 void
 _dl_fini (void)
 {
-  /* Lots of fun ahead.  We have to call the destructors for all still
-     loaded objects, in all namespaces.  The problem is that the ELF
-     specification now demands that dependencies between the modules
-     are taken into account.  I.e., the destructor for a module is
-     called before the ones for any of its dependencies.
-
-     To make things more complicated, we cannot simply use the reverse
-     order of the constructors.  Since the user might have loaded objects
-     using `dlopen' there are possibly several other modules with its
-     dependencies to be taken into account.  Therefore we have to start
-     determining the order of the modules once again from the beginning.  */
-
-  /* We run the destructors of the main namespaces last.  As for the
-     other namespaces, we pick run the destructors in them in reverse
-     order of the namespace ID.  */
+  /* Call destructors strictly in the reverse order of constructors.
+     This causes fewer surprises than some arbitrary reordering based
+     on new (relocation) dependencies.  None of the objects are
+     unmapped, so applications can deal with this if their DSOs remain
+     in a consistent state after destructors have run.  */
+
+  /* Protect against concurrent loads and unloads.  */
+  __rtld_lock_lock_recursive (GL(dl_load_lock));
+
+  /* Ignore objects which are opened during shutdown.  */
+  struct link_map *local_init_called_list = _dl_init_called_list;
+
+  for (struct link_map *l = local_init_called_list; l != NULL;
+       l = l->l_init_called_next)
+      /* Bump l_direct_opencount of all objects so that they
+	 are not dlclose()ed from underneath us.  */
+      ++l->l_direct_opencount;
+
+  /* After this point, Everything linked from local_init_called_list
+     cannot be unloaded because of the reference counter update.  */
+  __rtld_lock_unlock_recursive (GL(dl_load_lock));
+
+  /* Perform two passes: One for non-audit modules, one for audit
+     modules.  */
 #ifdef SHARED
-  int do_audit = 0;
- again:
+  int last_pass = GLRO(dl_naudit) > 0;
+  for (int do_audit = 0; do_audit <= last_pass; ++do_audit)
 #endif
-  for (Lmid_t ns = GL(dl_nns) - 1; ns >= 0; --ns)
-    {
-      /* Protect against concurrent loads and unloads.  */
-      __rtld_lock_lock_recursive (GL(dl_load_lock));
-
-      unsigned int nloaded = GL(dl_ns)[ns]._ns_nloaded;
-      /* No need to do anything for empty namespaces or those used for
-	 auditing DSOs.  */
-      if (nloaded == 0
+    for (struct link_map *l = local_init_called_list; l != NULL;
+	 l = l->l_init_called_next)
+      {
 #ifdef SHARED
-	  || GL(dl_ns)[ns]._ns_loaded->l_auditing != do_audit
+	if (GL(dl_ns)[l->l_ns]._ns_loaded->l_auditing != do_audit)
+	  continue;
 #endif
-	  )
-	__rtld_lock_unlock_recursive (GL(dl_load_lock));
-      else
-	{
-	  /* Now we can allocate an array to hold all the pointers and
-	     copy the pointers in.  */
-	  struct link_map *maps[nloaded];
-
-	  unsigned int i;
-	  struct link_map *l;
-	  assert (nloaded != 0 || GL(dl_ns)[ns]._ns_loaded == NULL);
-	  for (l = GL(dl_ns)[ns]._ns_loaded, i = 0; l != NULL; l = l->l_next)
-	    /* Do not handle ld.so in secondary namespaces.  */
-	    if (l == l->l_real)
-	      {
-		assert (i < nloaded);
 
-		maps[i] = l;
-		l->l_idx = i;
-		++i;
+	if (l->l_init_called)
+	  {
+	    /* Make sure nothing happens if we are called twice.  */
+	    l->l_init_called = 0;
 
-		/* Bump l_direct_opencount of all objects so that they
-		   are not dlclose()ed from underneath us.  */
-		++l->l_direct_opencount;
+	    /* Is there a destructor function?  */
+	    if (l->l_info[DT_FINI_ARRAY] != NULL
+		|| (ELF_INITFINI && l->l_info[DT_FINI] != NULL))
+	      {
+		/* When debugging print a message first.  */
+		if (__builtin_expect (GLRO(dl_debug_mask)
+				      & DL_DEBUG_IMPCALLS, 0))
+		  _dl_debug_printf ("\ncalling fini: %s [%lu]\n\n",
+				    DSO_FILENAME (l->l_name),
+				    l->l_ns);
+
+		/* First see whether an array is given.  */
+		if (l->l_info[DT_FINI_ARRAY] != NULL)
+		  {
+		    ElfW(Addr) *array =
+		      (ElfW(Addr) *) (l->l_addr
+				      + l->l_info[DT_FINI_ARRAY]->d_un.d_ptr);
+		    unsigned int i = (l->l_info[DT_FINI_ARRAYSZ]->d_un.d_val
+				      / sizeof (ElfW(Addr)));
+		    while (i-- > 0)
+		      ((fini_t) array[i]) ();
+		  }
+
+		/* Next try the old-style destructor.  */
+		if (ELF_INITFINI && l->l_info[DT_FINI] != NULL)
+		  DL_CALL_DT_FINI
+		    (l, l->l_addr + l->l_info[DT_FINI]->d_un.d_ptr);
 	      }
-	  assert (ns != LM_ID_BASE || i == nloaded);
-	  assert (ns == LM_ID_BASE || i == nloaded || i == nloaded - 1);
-	  unsigned int nmaps = i;
-
-	  /* Now we have to do the sorting.  We can skip looking for the
-	     binary itself which is at the front of the search list for
-	     the main namespace.  */
-	  _dl_sort_maps (maps, nmaps, (ns == LM_ID_BASE));
-
-	  /* We do not rely on the linked list of loaded object anymore
-	     from this point on.  We have our own list here (maps).  The
-	     various members of this list cannot vanish since the open
-	     count is too high and will be decremented in this loop.  So
-	     we release the lock so that some code which might be called
-	     from a destructor can directly or indirectly access the
-	     lock.  */
-	  __rtld_lock_unlock_recursive (GL(dl_load_lock));
-
-	  /* 'maps' now contains the objects in the right order.  Now
-	     call the destructors.  We have to process this array from
-	     the front.  */
-	  for (i = 0; i < nmaps; ++i)
-	    {
-	      struct link_map *l = maps[i];
-
-	      if (l->l_init_called)
-		{
-		  /* Make sure nothing happens if we are called twice.  */
-		  l->l_init_called = 0;
-
-		  /* Is there a destructor function?  */
-		  if (l->l_info[DT_FINI_ARRAY] != NULL
-		      || (ELF_INITFINI && l->l_info[DT_FINI] != NULL))
-		    {
-		      /* When debugging print a message first.  */
-		      if (__builtin_expect (GLRO(dl_debug_mask)
-					    & DL_DEBUG_IMPCALLS, 0))
-			_dl_debug_printf ("\ncalling fini: %s [%lu]\n\n",
-					  DSO_FILENAME (l->l_name),
-					  ns);
-
-		      /* First see whether an array is given.  */
-		      if (l->l_info[DT_FINI_ARRAY] != NULL)
-			{
-			  ElfW(Addr) *array =
-			    (ElfW(Addr) *) (l->l_addr
-					    + l->l_info[DT_FINI_ARRAY]->d_un.d_ptr);
-			  unsigned int i = (l->l_info[DT_FINI_ARRAYSZ]->d_un.d_val
-					    / sizeof (ElfW(Addr)));
-			  while (i-- > 0)
-			    ((fini_t) array[i]) ();
-			}
-
-		      /* Next try the old-style destructor.  */
-		      if (ELF_INITFINI && l->l_info[DT_FINI] != NULL)
-			DL_CALL_DT_FINI
-			  (l, l->l_addr + l->l_info[DT_FINI]->d_un.d_ptr);
-		    }
 
 #ifdef SHARED
-		  /* Auditing checkpoint: another object closed.  */
-		  if (!do_audit && __builtin_expect (GLRO(dl_naudit) > 0, 0))
-		    {
-		      struct audit_ifaces *afct = GLRO(dl_audit);
-		      for (unsigned int cnt = 0; cnt < GLRO(dl_naudit); ++cnt)
-			{
-			  if (afct->objclose != NULL)
-			    {
-			      struct auditstate *state
-				= link_map_audit_state (l, cnt);
-			      /* Return value is ignored.  */
-			      (void) afct->objclose (&state->cookie);
-			    }
-			  afct = afct->next;
-			}
-		    }
+	    /* Auditing checkpoint: another object closed.  */
+	    if (!do_audit && __builtin_expect (GLRO(dl_naudit) > 0, 0))
+	      {
+		struct audit_ifaces *afct = GLRO(dl_audit);
+		for (unsigned int cnt = 0; cnt < GLRO(dl_naudit); ++cnt)
+		  {
+		    if (afct->objclose != NULL)
+		      {
+			struct auditstate *state
+			  = link_map_audit_state (l, cnt);
+			/* Return value is ignored.  */
+			(void) afct->objclose (&state->cookie);
+		      }
+		    afct = afct->next;
+		  }
+	      }
 #endif
-		}
-
-	      /* Correct the previous increment.  */
-	      --l->l_direct_opencount;
-	    }
-	}
-    }
+	  }
+      }
 
 #ifdef SHARED
-  if (! do_audit && GLRO(dl_naudit) > 0)
-    {
-      do_audit = 1;
-      goto again;
-    }
-
   if (__glibc_unlikely (GLRO(dl_debug_mask) & DL_DEBUG_STATISTICS))
     _dl_debug_printf ("\nruntime linker statistics:\n"
 		      "           final number of relocations: %lu\n"
diff --git a/elf/dl-init.c b/elf/dl-init.c
index f924d26642..a6dcfdb25d 100644
--- a/elf/dl-init.c
+++ b/elf/dl-init.c
@@ -21,6 +21,7 @@ 
 #include <ldsodefs.h>
 #include <elf-initfini.h>
 
+struct link_map *_dl_init_called_list;
 
 static void
 call_init (struct link_map *l, int argc, char **argv, char **env)
@@ -38,6 +39,19 @@  call_init (struct link_map *l, int argc, char **argv, char **env)
      dependency.  */
   l->l_init_called = 1;
 
+  /* Help an already-running dlclose: The just-loaded object must not
+     be removed during the current pass.  (No effect if no dlclose in
+     progress.)  */
+  l->l_map_used = 1;
+
+  /* Record execution before starting any initializers.  This way, if
+     the initializers themselves call dlopen, their ELF destructors
+     will eventually be run before this object is destructed, matching
+     that their ELF constructors have run before this object was
+     constructed.  */
+  l->l_init_called_next = _dl_init_called_list;
+  _dl_init_called_list = l;
+
   /* Check for object which constructors we do not run here.  */
   if (__builtin_expect (l->l_name[0], 'a') == '\0'
       && l->l_type == lt_executable)
diff --git a/elf/dso-sort-tests-1.def b/elf/dso-sort-tests-1.def
index c2398408cd..96c4533c3b 100644
--- a/elf/dso-sort-tests-1.def
+++ b/elf/dso-sort-tests-1.def
@@ -59,4 +59,4 @@  output: b>a>{}<a<b
 # The below expected outputs are what the two algorithms currently produce
 # respectively, for regression testing purposes.
 tst-bz15311: {+a;+e;+f;+g;+d;%d;-d;-g;-f;-e;-a};a->b->c->d;d=>[ba];c=>a;b=>e=>a;c=>f=>b;d=>g=>c
-output: {+a[d>c>b>a>];+e[e>];+f[f>];+g[g>];+d[];%d(b(e(a()))a()g(c(a()f(b(e(a()))))));-d[];-g[];-f[];-e[];-a[<a<b<c<d<e<f<g];}
+output: {+a[d>c>b>a>];+e[e>];+f[f>];+g[g>];+d[];%d(b(e(a()))a()g(c(a()f(b(e(a()))))));-d[];-g[];-f[];-e[];-a[<g<f<e<a<b<c<d];}
diff --git a/include/link.h b/include/link.h
index c1c382ccfa..ce2b000dcd 100644
--- a/include/link.h
+++ b/include/link.h
@@ -277,6 +277,10 @@  struct link_map
     /* List of object in order of the init and fini calls.  */
     struct link_map **l_initfini;
 
+    /* Linked list of objects in reverse ELF constructor execution
+       order.  Head of list is stored in _dl_init_called_list.  */
+    struct link_map *l_init_called_next;
+
     /* List of the dependencies introduced through symbol binding.  */
     struct link_map_reldeps
       {
diff --git a/sysdeps/generic/ldsodefs.h b/sysdeps/generic/ldsodefs.h
index a66b68eaea..fd591cf280 100644
--- a/sysdeps/generic/ldsodefs.h
+++ b/sysdeps/generic/ldsodefs.h
@@ -1111,6 +1111,10 @@  extern int _dl_check_map_versions (struct link_map *map, int verbose,
 extern void _dl_init (struct link_map *main_map, int argc, char **argv,
 		      char **env) attribute_hidden;
 
+/* List of ELF objects in reverse order of their constructor
+   invocation.  */
+extern struct link_map *_dl_init_called_list attribute_hidden;
+
 /* Call the finalizer functions of all shared objects whose
    initializer functions have completed.  */
 extern void _dl_fini (void) attribute_hidden;