From a5bff443c7f23ad5c4abb70d3ce2c59aed2ec13a Mon Sep 17 00:00:00 2001
From: Shenghou Ma <minux@golang.org>
Date: Fri, 26 Dec 2014 01:17:42 -0500
Subject: [PATCH] runtime/cgo: darwin/arm cgo support

Change-Id: I936be12eed95b99d1d20ed16fb785182e1817b33
Reviewed-on: https://go-review.googlesource.com/2124
Reviewed-by: David Crawshaw <crawshaw@golang.org>
---
 src/runtime/cgo/cgo.go           |  2 +-
 src/runtime/cgo/gcc_arm.S        |  4 ++
 src/runtime/cgo/gcc_darwin_arm.c | 99 ++++++++++++++++++++++++++++++++
 3 files changed, 104 insertions(+), 1 deletion(-)
 create mode 100644 src/runtime/cgo/gcc_darwin_arm.c

diff --git a/src/runtime/cgo/cgo.go b/src/runtime/cgo/cgo.go
index 8528692f7b..9a41399cd6 100644
--- a/src/runtime/cgo/cgo.go
+++ b/src/runtime/cgo/cgo.go
@@ -11,7 +11,7 @@ package cgo
 
 /*
 
-#cgo darwin LDFLAGS: -lpthread
+#cgo darwin,!arm LDFLAGS: -lpthread
 #cgo dragonfly LDFLAGS: -lpthread
 #cgo freebsd LDFLAGS: -lpthread
 #cgo android LDFLAGS: -llog
diff --git a/src/runtime/cgo/gcc_arm.S b/src/runtime/cgo/gcc_arm.S
index d5833bfad0..980ab579e4 100644
--- a/src/runtime/cgo/gcc_arm.S
+++ b/src/runtime/cgo/gcc_arm.S
@@ -11,6 +11,10 @@
 #define EXT(s) s
 #endif
 
+// Apple's ld64 wants 4-byte alignment for ARM code sections.
+// .align in both Apple as and GNU as treat n as aligning to 2**n bytes.
+.align	2
+
 /*
  * void crosscall_arm1(void (*fn)(void), void (*setg_gcc)(void *g), void *g)
  *
diff --git a/src/runtime/cgo/gcc_darwin_arm.c b/src/runtime/cgo/gcc_darwin_arm.c
new file mode 100644
index 0000000000..d56c55777d
--- /dev/null
+++ b/src/runtime/cgo/gcc_darwin_arm.c
@@ -0,0 +1,99 @@
+// Copyright 2014 The Go Authors.  All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+#include <string.h> /* for strerror */
+#include <pthread.h>
+#include <signal.h>
+#include <limits.h>
+#include "libcgo.h"
+
+#define magic (0xe696c4f4U)
+
+// inittls allocates a thread-local storage slot for g.
+//
+// It finds the first available slot using pthread_key_create and uses
+// it as the offset value for runtime.tlsg.
+static void
+inittls(void **tlsg, void **tlsbase)
+{
+	pthread_key_t k;
+	int i, err;
+
+	err = pthread_key_create(&k, nil);
+	if(err != 0) {
+		fprintf(stderr, "runtime/cgo: pthread_key_create failed: %d\n", err);
+		abort();
+	}
+	//fprintf(stderr, "runtime/cgo: k = %d, tlsbase = %p\n", (int)k, tlsbase); // debug
+	pthread_setspecific(k, (void*)magic);
+	// The first key should be at 258.
+	for (i=0; i<PTHREAD_KEYS_MAX; i++) {
+		if (*(tlsbase+i) == (void*)magic) {
+			*tlsg = (void*)(i*sizeof(void *));
+			pthread_setspecific(k, 0);
+			return;
+		}
+	}
+	fprintf(stderr, "runtime/cgo: could not find pthread key.\n");
+	abort();
+}
+
+static void *threadentry(void*);
+void (*setg_gcc)(void*);
+
+void
+_cgo_sys_thread_start(ThreadStart *ts)
+{
+	pthread_attr_t attr;
+	sigset_t ign, oset;
+	pthread_t p;
+	size_t size;
+	int err;
+
+	sigfillset(&ign);
+	pthread_sigmask(SIG_SETMASK, &ign, &oset);
+
+	pthread_attr_init(&attr);
+	size = 0;
+	pthread_attr_getstacksize(&attr, &size);
+	// Leave stacklo=0 and set stackhi=size; mstack will do the rest.
+	ts->g->stackhi = size;
+	err = pthread_create(&p, &attr, threadentry, ts);
+
+	pthread_sigmask(SIG_SETMASK, &oset, nil);
+
+	if (err != 0) {
+		fprintf(stderr, "runtime/cgo: pthread_create failed: %s\n", strerror(err));
+		abort();
+	}
+}
+
+extern void crosscall_arm1(void (*fn)(void), void (*setg_gcc)(void*), void *g);
+static void*
+threadentry(void *v)
+{
+	ThreadStart ts;
+
+	ts = *(ThreadStart*)v;
+	free(v);
+
+	crosscall_arm1(ts.fn, setg_gcc, (void*)ts.g);
+	return nil;
+}
+
+void
+x_cgo_init(G *g, void (*setg)(void*), void **tlsg, void **tlsbase)
+{
+	pthread_attr_t attr;
+	size_t size;
+
+	setg_gcc = setg;
+	pthread_attr_init(&attr);
+	pthread_attr_getstacksize(&attr, &size);
+	g->stacklo = (uintptr)&attr - size + 4096;
+	pthread_attr_destroy(&attr);
+
+	// yes, tlsbase from mrc might not be correctly aligned.
+	inittls(tlsg, (void**)((uintptr)tlsbase & ~3));
+}
-- 
2.50.0