nptl: Move changing of stack permissions into ld.so

All the stack lists are now in _rtld_global, so it is possible
to change stack permissions directly from there, instead of
calling into libpthread to do the change.

Tested-by: Carlos O'Donell <carlos@redhat.com>
Reviewed-by: Carlos O'Donell <carlos@redhat.com>

elf/dl-load.c

@@ -1368,7 +1368,11 @@ _dl_map_object_from_fd (const char *name, const char *origname, int fd,
       check_consistency ();
 #endif
 
+#if PTHREAD_IN_LIBC
+      errval = _dl_make_stacks_executable (stack_endp);
+#else
       errval = (*GL(dl_make_stack_executable_hook)) (stack_endp);
+#endif
       if (errval)
 	{
 	  errstring = N_("\

elf/dl-support.c

@@ -183,12 +183,6 @@ uint64_t _dl_hwcap_mask __attribute__ ((nocommon));
  * executable but this isn't true for all platforms.  */
 ElfW(Word) _dl_stack_flags = DEFAULT_STACK_PERMS;
 
-/* If loading a shared object requires that we make the stack executable
-   when it was not, we do it by calling this function.
-   It returns an errno code or zero on success.  */
-int (*_dl_make_stack_executable_hook) (void **) = _dl_make_stack_executable;
-
-
 #if THREAD_GSCOPE_IN_TCB
 list_t _dl_stack_used;
 list_t _dl_stack_user;
@@ -197,6 +191,10 @@ size_t _dl_stack_cache_actsize;
 uintptr_t _dl_in_flight_stack;
 int _dl_stack_cache_lock;
 #else
+/* If loading a shared object requires that we make the stack executable
+   when it was not, we do it by calling this function.
+   It returns an errno code or zero on success.  */
+int (*_dl_make_stack_executable_hook) (void **) = _dl_make_stack_executable;
 int _dl_thread_gscope_count;
 void (*_dl_init_static_tls) (struct link_map *) = &_dl_nothread_init_static_tls;
 #endif

elf/rtld.c

@@ -1125,9 +1125,11 @@ dl_main (const ElfW(Phdr) *phdr,
 
   __tls_pre_init_tp ();
 
+#if !PTHREAD_IN_LIBC
   /* The explicit initialization here is cheaper than processing the reloc
      in the _rtld_local definition's initializer.  */
   GL(dl_make_stack_executable_hook) = &_dl_make_stack_executable;
+#endif
 
   /* Process the environment variable which control the behaviour.  */
   process_envvars (&state);

nptl/allocatestack.c

@@ -291,31 +291,6 @@ queue_stack (struct pthread *stack)
     free_stacks (stack_cache_maxsize);
 }
 
-
-static int
-change_stack_perm (struct pthread *pd)
-{
-#ifdef NEED_SEPARATE_REGISTER_STACK
-  size_t pagemask = __getpagesize () - 1;
-  void *stack = (pd->stackblock
-		 + (((((pd->stackblock_size - pd->guardsize) / 2)
-		      & pagemask) + pd->guardsize) & pagemask));
-  size_t len = pd->stackblock + pd->stackblock_size - stack;
-#elif _STACK_GROWS_DOWN
-  void *stack = pd->stackblock + pd->guardsize;
-  size_t len = pd->stackblock_size - pd->guardsize;
-#elif _STACK_GROWS_UP
-  void *stack = pd->stackblock;
-  size_t len = (uintptr_t) pd - pd->guardsize - (uintptr_t) pd->stackblock;
-#else
-# error "Define either _STACK_GROWS_DOWN or _STACK_GROWS_UP"
-#endif
-  if (__mprotect (stack, len, PROT_READ | PROT_WRITE | PROT_EXEC) != 0)
-    return errno;
-
-  return 0;
-}
-
 /* Return the guard page position on allocated stack.  */
 static inline char *
 __attribute ((always_inline))
@@ -625,7 +600,7 @@ allocate_stack (const struct pthread_attr *attr, struct pthread **pdp,
 	  if (__builtin_expect ((GL(dl_stack_flags) & PF_X) != 0
 				&& (prot & PROT_EXEC) == 0, 0))
 	    {
-	      int err = change_stack_perm (pd);
+	      int err = __nptl_change_stack_perm (pd);
 	      if (err != 0)
 		{
 		  /* Free the stack memory we just allocated.  */
@@ -780,42 +755,6 @@ __deallocate_stack (struct pthread *pd)
   lll_unlock (GL (dl_stack_cache_lock), LLL_PRIVATE);
 }
 
-
-int
-__make_stacks_executable (void **stack_endp)
-{
-  /* First the main thread's stack.  */
-  int err = _dl_make_stack_executable (stack_endp);
-  if (err != 0)
-    return err;
-
-  lll_lock (GL (dl_stack_cache_lock), LLL_PRIVATE);
-
-  list_t *runp;
-  list_for_each (runp, &GL (dl_stack_used))
-    {
-      err = change_stack_perm (list_entry (runp, struct pthread, list));
-      if (err != 0)
-	break;
-    }
-
-  /* Also change the permission for the currently unused stacks.  This
-     might be wasted time but better spend it here than adding a check
-     in the fast path.  */
-  if (err == 0)
-    list_for_each (runp, &GL (dl_stack_cache))
-      {
-	err = change_stack_perm (list_entry (runp, struct pthread, list));
-	if (err != 0)
-	  break;
-      }
-
-  lll_unlock (GL (dl_stack_cache_lock), LLL_PRIVATE);
-
-  return err;
-}
-
-
 /* In case of a fork() call the memory allocation in the child will be
    the same but only one thread is running.  All stacks except that of
    the one running thread are not used anymore.  We have to recycle

nptl/nptl-init.c

@@ -173,10 +173,6 @@ __pthread_initialize_minimal_internal (void)
   __default_pthread_attr.internal.guardsize = GLRO (dl_pagesize);
   lll_unlock (__default_pthread_attr_lock, LLL_PRIVATE);
 
-#ifdef SHARED
-  GL(dl_make_stack_executable_hook) = &__make_stacks_executable;
-#endif
-
   /* Register the fork generation counter with the libc.  */
   __libc_pthread_init (__reclaim_stacks);
 }

nptl/pthreadP.h

@@ -335,8 +335,11 @@ extern void __deallocate_stack (struct pthread *pd) attribute_hidden;
    function also re-initializes the lock for the stack cache.  */
 extern void __reclaim_stacks (void) attribute_hidden;
 
-/* Make all threads's stacks executable.  */
+/* Change the permissions of a thread stack.  Called from
-extern int __make_stacks_executable (void **stack_endp) attribute_hidden;
+   _dl_make_stacks_executable and pthread_create.  */
+int
+__nptl_change_stack_perm (struct pthread *pd);
+rtld_hidden_proto (__nptl_change_stack_perm)
 
 /* longjmp handling.  */
 extern void __pthread_cleanup_upto (__jmp_buf target, char *targetframe);

sysdeps/generic/ldsodefs.h

@@ -416,10 +416,12 @@ struct rtld_global
 #endif
 #include <dl-procruntime.c>
 
+#if !PTHREAD_IN_LIBC
   /* If loading a shared object requires that we make the stack executable
      when it was not, we do it by calling this function.
      It returns an errno code or zero on success.  */
   EXTERN int (*_dl_make_stack_executable_hook) (void **);
+#endif
 
   /* Prevailing state of the stack, PF_X indicating it's executable.  */
   EXTERN ElfW(Word) _dl_stack_flags;
@@ -717,10 +719,17 @@ extern const ElfW(Phdr) *_dl_phdr;
 extern size_t _dl_phnum;
 #endif
 
+#if PTHREAD_IN_LIBC
+/* This function changes the permissions of all stacks (not just those
+   of the main stack).  */
+int _dl_make_stacks_executable (void **stack_endp) attribute_hidden;
+#else
 /* This is the initial value of GL(dl_make_stack_executable_hook).
-   A threads library can change it.  */
+   A threads library can change it.  The ld.so implementation changes
+   the permissions of the main stack only.  */
 extern int _dl_make_stack_executable (void **stack_endp);
 rtld_hidden_proto (_dl_make_stack_executable)
+#endif
 
 /* Variable pointing to the end of the stack (or close to it).  This value
    must be constant over the runtime of the application.  Some programs

sysdeps/unix/sysv/linux/Versions

@@ -181,3 +181,9 @@ libc {
     __netlink_assert_response;
   }
 }
+
+ld {
+  GLIBC_PRIVATE {
+    __nptl_change_stack_perm;
+  }
+}

sysdeps/unix/sysv/linux/dl-execstack.c

@@ -16,20 +16,21 @@
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
-#include <ldsodefs.h>
-#include <sys/mman.h>
 #include <errno.h>
+#include <ldsodefs.h>
 #include <libintl.h>
-#include <stdbool.h>
+#include <list.h>
+#include <nptl/pthreadP.h>
 #include <stackinfo.h>
+#include <stdbool.h>
+#include <sys/mman.h>
 #include <sysdep.h>
-
+#include <unistd.h>
 
 extern int __stack_prot attribute_relro attribute_hidden;
 
-
+static int
-int
+make_main_stack_executable (void **stack_endp)
-_dl_make_stack_executable (void **stack_endp)
 {
   /* This gives us the highest/lowest page that needs to be changed.  */
   uintptr_t page = ((uintptr_t) *stack_endp
@@ -56,4 +57,63 @@ _dl_make_stack_executable (void **stack_endp)
 
   return result;
 }
-rtld_hidden_def (_dl_make_stack_executable)
+
+int
+_dl_make_stacks_executable (void **stack_endp)
+{
+  /* First the main thread's stack.  */
+  int err = make_main_stack_executable (stack_endp);
+  if (err != 0)
+    return err;
+
+  lll_lock (GL (dl_stack_cache_lock), LLL_PRIVATE);
+
+  list_t *runp;
+  list_for_each (runp, &GL (dl_stack_used))
+    {
+      err = __nptl_change_stack_perm (list_entry (runp, struct pthread, list));
+      if (err != 0)
+	break;
+    }
+
+  /* Also change the permission for the currently unused stacks.  This
+     might be wasted time but better spend it here than adding a check
+     in the fast path.  */
+  if (err == 0)
+    list_for_each (runp, &GL (dl_stack_cache))
+      {
+	err = __nptl_change_stack_perm (list_entry (runp, struct pthread,
+						    list));
+	if (err != 0)
+	  break;
+      }
+
+  lll_unlock (GL (dl_stack_cache_lock), LLL_PRIVATE);
+
+  return err;
+}
+
+int
+__nptl_change_stack_perm (struct pthread *pd)
+{
+#ifdef NEED_SEPARATE_REGISTER_STACK
+  size_t pagemask = __getpagesize () - 1;
+  void *stack = (pd->stackblock
+		 + (((((pd->stackblock_size - pd->guardsize) / 2)
+		      & pagemask) + pd->guardsize) & pagemask));
+  size_t len = pd->stackblock + pd->stackblock_size - stack;
+#elif _STACK_GROWS_DOWN
+  void *stack = pd->stackblock + pd->guardsize;
+  size_t len = pd->stackblock_size - pd->guardsize;
+#elif _STACK_GROWS_UP
+  void *stack = pd->stackblock;
+  size_t len = (uintptr_t) pd - pd->guardsize - (uintptr_t) pd->stackblock;
+#else
+# error "Define either _STACK_GROWS_DOWN or _STACK_GROWS_UP"
+#endif
+  if (__mprotect (stack, len, PROT_READ | PROT_WRITE | PROT_EXEC) != 0)
+    return errno;
+
+  return 0;
+}
+rtld_hidden_def (__nptl_change_stack_perm)