[PATCH 03/12] Initialize the stack guard earlier when linking statically.

[Nix <nix at esperi dot org dot uk>]

From: Nick Alcock <nick.alcock@oracle.com>

The address of the stack canary is stored in a per-thread variable,
which means that we must ensure that the TLS area is intialized before
calling any -fstack-protector'ed functions.  For dynamically linked
applications, we ensure this (in a later patch) by disabling
-fstack-protector for the whole dynamic linker, but for static
applications the AT_ENTRY address is called directly by the kernel, so
we must deal with the problem differently.

So split out the part of pthread initialization that sets up the TCB
(and, more generally, the TLS area) into a separate function (twice --
there is one implementation in libpthread.a, and another outside it for
programs that do not link with libpthread), then call it at
initialization time. Call that, and move the stack guard initialization
above the DL_SYSDEP_OSCHECK hook, which if set will probably call
functions which are stack-protected (it does on Linux and NaCL too).

(Side note: on x86, the DL_SYSDEP_OSCHECK hook involves calling
_dl_discover_osversion(), which on older kernels can involve opening and
parsing files and once upon a time, long ago, went wrong if the
apply_irel() clause was not moved up above that hook call as well.
However, this no longer goes wrong on any system I have access to,
so I am willing to call this a separate bug: I can't see any obvious
connection to the stack-guard canary, at any rate.  I'm noting it here
purely because it crept into the patch and might potentially need
putting back in at some future date, if I'm wrong about this.)
---
 csu/libc-start.c | 20 ++++++++++++--------
 csu/libc-tls.c   |  8 ++++++++
 nptl/nptl-init.c | 11 +++++++----
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/csu/libc-start.c b/csu/libc-start.c
index f4aa01a..140b079 100644
--- a/csu/libc-start.c
+++ b/csu/libc-start.c
@@ -33,6 +33,7 @@ extern int __libc_multiple_libcs;
 #ifndef SHARED
 # include <dl-osinfo.h>
 extern void __pthread_initialize_minimal (void);
+extern void __pthread_initialize_tcb_internal (void);
 # ifndef THREAD_SET_STACK_GUARD
 /* Only exported for architectures that don't store the stack guard canary
    in thread local area.  */
@@ -178,6 +179,17 @@ LIBC_START_MAIN (int (*main) (int, char **, char ** MAIN_AUXVEC_DECL),
         }
     }
 
+  /* The stack guard goes into the TCB.  */
+  __pthread_initialize_tcb_internal ();
+
+  /* Set up the stack checker's canary.  */
+  uintptr_t stack_chk_guard = _dl_setup_stack_chk_guard (_dl_random);
+# ifdef THREAD_SET_STACK_GUARD
+  THREAD_SET_STACK_GUARD (stack_chk_guard);
+# else
+  __stack_chk_guard = stack_chk_guard;
+# endif
+
 # ifdef DL_SYSDEP_OSCHECK
   if (!__libc_multiple_libcs)
     {
@@ -195,14 +207,6 @@ LIBC_START_MAIN (int (*main) (int, char **, char ** MAIN_AUXVEC_DECL),
      we need to setup errno.  */
   __pthread_initialize_minimal ();
 
-  /* Set up the stack checker's canary.  */
-  uintptr_t stack_chk_guard = _dl_setup_stack_chk_guard (_dl_random);
-# ifdef THREAD_SET_STACK_GUARD
-  THREAD_SET_STACK_GUARD (stack_chk_guard);
-# else
-  __stack_chk_guard = stack_chk_guard;
-# endif
-
   /* Set up the pointer guard value.  */
   uintptr_t pointer_chk_guard = _dl_setup_pointer_guard (_dl_random,
 							 stack_chk_guard);
diff --git a/csu/libc-tls.c b/csu/libc-tls.c
index d6425e0..3d67a64 100644
--- a/csu/libc-tls.c
+++ b/csu/libc-tls.c
@@ -241,5 +241,13 @@ void
 __attribute__ ((weak))
 __pthread_initialize_minimal (void)
 {
+}
+
+/* This is the minimal initialization function used when libpthread is
+   not used.  */
+void
+__attribute__ ((weak))
+__pthread_initialize_tcb_internal (void)
+{
   __libc_setup_tls (TLS_INIT_TCB_SIZE, TLS_INIT_TCB_ALIGN);
 }
diff --git a/nptl/nptl-init.c b/nptl/nptl-init.c
index bdbdfed..a4626be 100644
--- a/nptl/nptl-init.c
+++ b/nptl/nptl-init.c
@@ -296,21 +296,24 @@ extern void **__libc_dl_error_tsd (void) __attribute__ ((const));
 /* This can be set by the debugger before initialization is complete.  */
 static bool __nptl_initial_report_events __attribute_used__;
 
+#ifndef SHARED
 void
-__pthread_initialize_minimal_internal (void)
+__pthread_initialize_tcb_internal (void)
 {
-#ifndef SHARED
   /* Unlike in the dynamically linked case the dynamic linker has not
      taken care of initializing the TLS data structures.  */
   __libc_setup_tls (TLS_TCB_SIZE, TLS_TCB_ALIGN);
 
-  /* We must prevent gcc from being clever and move any of the
+  /* We must prevent gcc from being clever after inlining and moving any of the
      following code ahead of the __libc_setup_tls call.  This function
      will initialize the thread register which is subsequently
      used.  */
   __asm __volatile ("");
+}
 #endif
-
+void
+__pthread_initialize_minimal_internal (void)
+{
   /* Minimal initialization of the thread descriptor.  */
   struct pthread *pd = THREAD_SELF;
   __pthread_initialize_pids (pd);
-- 
2.7.0.198.g6dd47b6