separate __tls_get_addr implementation from dynamic linker/init_tls

such separation serves multiple purposes:

- by having the common path for __tls_get_addr alone in its own
  function with a tail call to the slow case, code generation is
  greatly improved.

- by having __tls_get_addr in it own file, it can be replaced on a
  per-arch basis as needed, for optimization or ABI-specific purposes.

- by removing __tls_get_addr from __init_tls.c, a few bytes of code
  are shaved off of static binaries (which are unlikely to use this
  function unless the linker messed up).

1 files changed, 17 insertions, 0 deletions

diff --git a/src/thread/__tls_get_addr.c b/src/thread/__tls_get_addr.c
new file mode 100644
index 00000000..28ec7f02
--- /dev/null
+++ b/src/thread/__tls_get_addr.c
@@ -0,0 +1,17 @@
+#include <stddef.h>
+#include "pthread_impl.h"
+#include "libc.h"
+
+void *__tls_get_new(size_t *) ATTR_LIBC_VISIBILITY;
+
+void *__tls_get_addr(size_t *v)
+{
+	pthread_t self = __pthread_self();
+#ifdef SHARED
+	if (v[0]<=(size_t)self->dtv[0])
+		return (char *)self->dtv[v[0]]+v[1];
+	return __tls_get_new(v);
+#else
+	return (char *)self->dtv[1]+v[1];
+#endif
+}