Fix the problem with the C++ exception handling for the multithreaded

programs.

From the PR description:
The gcc runtime's _Unwind_Find_FDE function, invoked during exception
handling's stack unwinding, is not safe to execute from within multiple
threads. FreeBSD' s dl_iterate_phdr() however permits multiple threads
to pass through it though. The result is surprisingly reliable infinite
looping of one or more threads if they just happen to be unwinding at
the same time.

Introduce the new lock that is write locked around the dl_iterate_pdr,
thus providing required exclusion for the stack unwinders.

PR:	threads/123062
Submitted by:	Andy Newman <an at atrn org>
Reviewed by:	kan
MFC after:	2 weeks

libexec/rtld-elf/rtld.c

@@ -2129,9 +2129,10 @@ dl_iterate_phdr(__dl_iterate_hdr_callback callback, void *param)
 {
     struct dl_phdr_info phdr_info;
     const Obj_Entry *obj;
-    int error, lockstate;
+    int error, bind_lockstate, phdr_lockstate;
 
-    lockstate = rlock_acquire(rtld_bind_lock);
+    phdr_lockstate = wlock_acquire(rtld_phdr_lock);
+    bind_lockstate = rlock_acquire(rtld_bind_lock);
 
     error = 0;
 
@@ -2150,7 +2151,8 @@ dl_iterate_phdr(__dl_iterate_hdr_callback callback, void *param)
 		break;
 
     }
-    rlock_release(rtld_bind_lock, lockstate);
+    rlock_release(rtld_bind_lock, bind_lockstate);
+    wlock_release(rtld_phdr_lock, phdr_lockstate);
 
     return (error);
 }

libexec/rtld-elf/rtld_lock.c

@@ -171,14 +171,15 @@ thread_mask_clear(int mask)
 	lockinfo.thread_clr_flag(mask);
 }
 
-#define	RTLD_LOCK_CNT	2
+#define	RTLD_LOCK_CNT	3
 struct rtld_lock {
 	void	*handle;
 	int	 mask;
 } rtld_locks[RTLD_LOCK_CNT];
 
 rtld_lock_t	rtld_bind_lock = &rtld_locks[0];
 rtld_lock_t	rtld_libc_lock = &rtld_locks[1];
+rtld_lock_t	rtld_phdr_lock = &rtld_locks[2];
 
 int
 rlock_acquire(rtld_lock_t lock)

libexec/rtld-elf/rtld_lock.h

@@ -52,6 +52,7 @@ typedef struct rtld_lock *rtld_lock_t;
 
 extern rtld_lock_t	rtld_bind_lock;
 extern rtld_lock_t	rtld_libc_lock;
+extern rtld_lock_t	rtld_phdr_lock;
 
 int	rlock_acquire(rtld_lock_t);
 int 	wlock_acquire(rtld_lock_t);