Fix known issues which blow up the process after dlopen("libthr.so")

(or loading a dso linked to libthr.so into process which was not
linked against threading library).

- Remove libthr interposers of the libc functions, including
  __error(). Instead, functions calls are indirected through the
  interposing table, similar to how pthread stubs in libc are already
  done.  Libc by default points either to syscall trampolines or to
  existing libc implementations.  On libthr load, libthr rewrites the
  pointers to the cancellable implementations already in libthr.  The
  interposition table is separate from pthreads stubs indirection
  table to not pull pthreads stubs into static binaries.

- Postpone the malloc(3) internal mutexes initialization until libthr
  is loaded.  This avoids recursion between calloc(3) and static
  pthread_mutex_t initialization.

- Reinstall signal handlers with wrapper on libthr load.  The
  _rtld_is_dlopened(3) is used to avoid useless calls to sigaction(2)
  when libthr is statically referenced from the main binary.

In the process, fix openat(2), swapcontext(2) and setcontext(2)
interposing.  The libc symbols were exported at different versions
than libthr interposers.  Export both libc and libthr versions from
libc now, with default set to the higher version from libthr.

Remove unused and disconnected swapcontext(3) userspace implementation
from libc/gen.

No objections from:	deischen
Tested by:	pho, antoine (exp-run) (previous versions)
Sponsored by:	The FreeBSD Foundation
MFC after:	1 week

3 files changed, 25 insertions, 6 deletions

diff --git a/contrib/jemalloc/include/jemalloc/internal/mutex.h b/contrib/jemalloc/include/jemalloc/internal/mutex.h
index 564d604..dcd9147 100644
--- a/contrib/jemalloc/include/jemalloc/internal/mutex.h
+++ b/contrib/jemalloc/include/jemalloc/internal/mutex.h
@@ -49,6 +49,7 @@ bool	malloc_mutex_init(malloc_mutex_t *mutex);
 void	malloc_mutex_prefork(malloc_mutex_t *mutex);
 void	malloc_mutex_postfork_parent(malloc_mutex_t *mutex);
 void	malloc_mutex_postfork_child(malloc_mutex_t *mutex);
+bool	malloc_mutex_first_thread(void);
 bool	mutex_boot(void);
 
 #endif /* JEMALLOC_H_EXTERNS */
diff --git a/contrib/jemalloc/src/jemalloc.c b/contrib/jemalloc/src/jemalloc.c
index 9e5f2df..1ffa064 100644
--- a/contrib/jemalloc/src/jemalloc.c
+++ b/contrib/jemalloc/src/jemalloc.c
@@ -2061,6 +2061,13 @@ jemalloc_postfork_child(void)
 	ctl_postfork_child();
 }
 
+void
+_malloc_first_thread(void)
+{
+
+	(void)malloc_mutex_first_thread();
+}
+
 /******************************************************************************/
 /*
  * The following functions are used for TLS allocation/deallocation in static
diff --git a/contrib/jemalloc/src/mutex.c b/contrib/jemalloc/src/mutex.c
index 6f5954e..0f90d05 100644
--- a/contrib/jemalloc/src/mutex.c
+++ b/contrib/jemalloc/src/mutex.c
@@ -67,15 +67,15 @@ pthread_create(pthread_t *__restrict thread,
 JEMALLOC_EXPORT int	_pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex,
     void *(calloc_cb)(size_t, size_t));
 
-__weak_reference(_pthread_mutex_init_calloc_cb_stub,
-    _pthread_mutex_init_calloc_cb);
-
+#pragma weak _pthread_mutex_init_calloc_cb
 int
-_pthread_mutex_init_calloc_cb_stub(pthread_mutex_t *mutex,
+_pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex,
     void *(calloc_cb)(size_t, size_t))
 {
 
-	return (0);
+	return (((int (*)(pthread_mutex_t *, void *(*)(size_t, size_t)))
+	    __libc_interposing[INTERPOS__pthread_mutex_init_calloc_cb])(
+	   mutex, calloc_cb));
 }
 #endif
 
@@ -144,7 +144,7 @@ malloc_mutex_postfork_child(malloc_mutex_t *mutex)
 }
 
 bool
-mutex_boot(void)
+malloc_mutex_first_thread(void)
 {
 
 #ifdef JEMALLOC_MUTEX_INIT_CB
@@ -158,3 +158,14 @@ mutex_boot(void)
 #endif
 	return (false);
 }
+
+bool
+mutex_boot(void)
+{
+
+#ifndef JEMALLOC_MUTEX_INIT_CB
+	return (malloc_mutex_first_thread());
+#else
+	return (false);
+#endif
+}