add support for init/fini array in main program, and greatly simplify

modern (4.7.x and later) gcc uses init/fini arrays, rather than the
legacy _init/_fini function pasting and crtbegin/crtend ctors/dtors
system, on most or all archs. some archs had already switched a long
time ago. without following this change, global ctors/dtors will cease
to work under musl when building with new gcc versions.

the most surprising part of this patch is that it actually reduces the
size of the init code, for both static and shared libc. this is
achieved by (1) unifying the handling main program and shared
libraries in the dynamic linker, and (2) eliminating the
glibc-inspired rube goldberg machine for passing around init and fini
function pointers. to clarify, some background:

the function signature for __libc_start_main was based on glibc, as
part of the original goal of being able to run some glibc-linked
binaries. it worked by having the crt1 code, which is linked into
every application, static or dynamic, obtain and pass pointers to the
init and fini functions, which __libc_start_main is then responsible
for using and recording for later use, as necessary. however, in
neither the static-linked nor dynamic-linked case do we actually need
crt1.o's help. with dynamic linking, all the pointers are available in
the _DYNAMIC block. with static linking, it's safe to simply access
the _init/_fini and __init_array_start, etc. symbols directly.

obviously changing the __libc_start_main function signature in an
incompatible way would break both old musl-linked programs and
glibc-linked programs, so let's not do that. instead, the function can
just ignore the information it doesn't need. new archs need not even
provide the useless args in their versions of crt1.o. existing archs
should continue to provide it as long as there is an interest in
having newly-linked applications be able to run on old versions of
musl; at some point in the future, this support can be removed.

4 files changed, 33 insertions, 26 deletions

diff --git a/src/env/__libc_start_main.c b/src/env/__libc_start_main.c
index aef9f9ec..2a8698bb 100644
--- a/src/env/__libc_start_main.c
+++ b/src/env/__libc_start_main.c
@@ -5,6 +5,13 @@ void __init_tls(size_t *);
 void __init_security(size_t *);
 void __init_ldso_ctors(void);
 
+#ifndef SHARED
+static void dummy() {}
+weak_alias(dummy, _init);
+extern void (*const __init_array_start)() __attribute__((weak));
+extern void (*const __init_array_end)() __attribute__((weak));
+#endif
+
 #define AUX_CNT 38
 
 extern size_t __hwcap, __sysinfo;
@@ -29,23 +36,16 @@ void __init_libc(char **envp, char *pn)
 	__init_security(aux);
 }
 
-int __libc_start_main(
-	int (*main)(int, char **, char **), int argc, char **argv,
-	int (*init)(int, char **, char **), void (*fini)(void),
-	void (*ldso_fini)(void))
+int __libc_start_main(int (*main)(int,char **,char **), int argc, char **argv)
 {
 	char **envp = argv+argc+1;
 
+#ifndef SHARED
 	__init_libc(envp, argv[0]);
-
-	libc.ldso_fini = ldso_fini;
-	libc.fini = fini;
-
-	/* Execute constructors (static) linked into the application */
-	if (init) init(argc, argv, envp);
-
-#ifdef SHARED
-	__init_ldso_ctors();
+	_init();
+	uintptr_t a = (uintptr_t)&__init_array_start;
+	for (; a<(uintptr_t)&__init_array_end; a+=sizeof(void(*)()))
+		(*(void (**)())a)();
 #endif
 
 	/* Pass control to to application */
diff --git a/src/exit/exit.c b/src/exit/exit.c
index e4932b5b..f259c982 100644
--- a/src/exit/exit.c
+++ b/src/exit/exit.c
@@ -14,6 +14,12 @@ weak_alias(dummy, __funcs_on_exit);
 weak_alias(dummy, __flush_on_exit);
 weak_alias(dummy, __seek_on_exit);
 
+#ifndef SHARED
+weak_alias(dummy, _fini);
+extern void (*const __fini_array_start)() __attribute__((weak));
+extern void (*const __fini_array_end)() __attribute__((weak));
+#endif
+
 _Noreturn void exit(int code)
 {
 	static int lock;
@@ -22,8 +28,14 @@ _Noreturn void exit(int code)
 	while (a_swap(&lock, 1)) __syscall(SYS_pause);
 
 	__funcs_on_exit();
-	if (libc.fini) libc.fini();
-	if (libc.ldso_fini) libc.ldso_fini();
+
+#ifndef SHARED
+	uintptr_t a = (uintptr_t)&__fini_array_end;
+	for (; a>(uintptr_t)&__fini_array_start; a-=sizeof(void(*)()))
+		(*(void (**)())(a-sizeof(void(*)())))();
+	_fini();
+#endif
+
 	__flush_on_exit();
 	__seek_on_exit();
 
diff --git a/src/internal/libc.h b/src/internal/libc.h
index c9416f07..c8fbe3fd 100644
--- a/src/internal/libc.h
+++ b/src/internal/libc.h
@@ -9,9 +9,6 @@ struct __libc {
 	int threaded;
 	int secure;
 	size_t *auxv;
-	int (*atexit)(void (*)(void));
-	void (*fini)(void);
-	void (*ldso_fini)(void);
 	volatile int threads_minus_1;
 	int canceldisable;
 	FILE *ofl_head;
diff --git a/src/ldso/dynlink.c b/src/ldso/dynlink.c
index 829696ff..3a0bf95d 100644
--- a/src/ldso/dynlink.c
+++ b/src/ldso/dynlink.c
@@ -91,6 +91,7 @@ struct symdef {
 
 void __init_ssp(size_t *);
 void *__install_initial_tls(void *);
+void __init_libc(char **, char *);
 
 static struct dso *head, *tail, *ldso, *fini_head;
 static char *env_path, *sys_path, *r_path;
@@ -841,6 +842,7 @@ void *__dynlink(int argc, char **argv)
 	char *env_preload=0;
 	size_t vdso_base;
 	size_t *auxv;
+	char **envp = argv+argc+1;
 
 	/* Find aux vector just past environ[] */
 	for (i=argc+1; argv[i]; i++)
@@ -953,7 +955,6 @@ void *__dynlink(int argc, char **argv)
 		tls_align = MAXP2(tls_align, app->tls_align);
 	}
 	app->global = 1;
-	app->constructed = 1;
 	decode_dyn(app);
 
 	/* Attach to vdso, if provided by the kernel */
@@ -1038,15 +1039,12 @@ void *__dynlink(int argc, char **argv)
 	_dl_debug_state();
 
 	if (ssp_used) __init_ssp((void *)aux[AT_RANDOM]);
-
-	errno = 0;
-	return (void *)aux[AT_ENTRY];
-}
-
-void __init_ldso_ctors(void)
-{
+	__init_libc(envp, argv[0]);
 	atexit(do_fini);
+	errno = 0;
 	do_init_fini(tail);
+
+	return (void *)aux[AT_ENTRY];
 }
 
 void *dlopen(const char *file, int mode)