runtime: get a better g0 stack bound in needm

Currently, when C calls into Go the first time, we grab an M
using needm, which sets m.g0's stack bounds using the SP. We don't
know how big the stack is, so we simply assume 32K. Previously,
when the Go function returns to C, we drop the M, and the next
time C calls into Go, we put a new stack bound on the g0 based on
the current SP. After CL 392854, we don't drop the M, and the next
time C calls into Go, we reuse the same g0, without recomputing
the stack bounds. If the C code uses quite a bit of stack space
before calling into Go, the SP may be well below the 32K stack
bound we assumed, so the runtime thinks the g0 stack overflows.

This CL makes needm get a more accurate stack bound from
pthread. (In some platforms this may still be a guess as we don't
know exactly where we are in the C stack), but it is probably
better than simply assuming 32K.

For #59294.

Change-Id: Ie52a8f931e0648d8753e4c1dbe45468b8748b527
Reviewed-on: https://go-review.googlesource.com/c/go/+/479915
Run-TryBot: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Michael Knyszek <mknyszek@google.com>

4 files changed, 69 insertions, 0 deletions

diff --git a/src/runtime/cgo/callbacks.go b/src/runtime/cgo/callbacks.go
index 792dd7d086..3c246a88b6 100644
--- a/src/runtime/cgo/callbacks.go
+++ b/src/runtime/cgo/callbacks.go
@@ -141,3 +141,12 @@ var _cgo_yield unsafe.Pointer
 
 //go:cgo_export_static _cgo_topofstack
 //go:cgo_export_dynamic _cgo_topofstack
+
+// x_cgo_getstackbound gets the thread's C stack size and
+// set the G's stack bound based on the stack size.
+
+//go:cgo_import_static x_cgo_getstackbound
+//go:linkname x_cgo_getstackbound x_cgo_getstackbound
+//go:linkname _cgo_getstackbound _cgo_getstackbound
+var x_cgo_getstackbound byte
+var _cgo_getstackbound = &x_cgo_getstackbound
diff --git a/src/runtime/cgo/gcc_stack_darwin.c b/src/runtime/cgo/gcc_stack_darwin.c
new file mode 100644
index 0000000000..2cc9b76196
--- /dev/null
+++ b/src/runtime/cgo/gcc_stack_darwin.c
@@ -0,0 +1,21 @@
+// Copyright 2023 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 <pthread.h>
+#include "libcgo.h"
+
+void
+x_cgo_getstackbound(G *g)
+{
+	void* addr;
+	size_t size;
+	pthread_t p;
+
+	p = pthread_self();
+	addr = pthread_get_stackaddr_np(p); // high address (!)
+	size = pthread_get_stacksize_np(p);
+	g->stacklo = (uintptr)addr - size;
+	// NOTE: don't change g->stackhi. We are called from asmcgocall
+	// which saves the stack depth based on g->stackhi.
+}
diff --git a/src/runtime/cgo/gcc_stack_unix.c b/src/runtime/cgo/gcc_stack_unix.c
new file mode 100644
index 0000000000..3826322661
--- /dev/null
+++ b/src/runtime/cgo/gcc_stack_unix.c
@@ -0,0 +1,32 @@
+// Copyright 2023 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.
+
+//go:build unix && !darwin
+
+#ifndef _GNU_SOURCE // pthread_getattr_np
+#define _GNU_SOURCE
+#endif
+
+#include <pthread.h>
+#include "libcgo.h"
+
+void
+x_cgo_getstackbound(G *g)
+{
+	pthread_attr_t attr;
+	void *addr;
+	size_t size;
+
+	pthread_attr_init(&attr);
+#if defined(__GLIBC__) || defined(__sun)
+	pthread_getattr_np(pthread_self(), &attr);  // GNU extension
+	pthread_attr_getstack(&attr, &addr, &size); // low address
+#else
+	pthread_attr_getstacksize(&attr, &size);
+	addr = __builtin_frame_address(0) + 4096 - size;
+#endif
+	g->stacklo = (uintptr)addr;
+	// NOTE: don't change g->stackhi. We are called from asmcgocall
+	// which saves the stack depth based on g->stackhi.
+}
diff --git a/src/runtime/cgo/gcc_stack_windows.c b/src/runtime/cgo/gcc_stack_windows.c
new file mode 100644
index 0000000000..9fcb59cf1a
--- /dev/null
+++ b/src/runtime/cgo/gcc_stack_windows.c
@@ -0,0 +1,7 @@
+// Copyright 2023 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 "libcgo.h"
+
+void x_cgo_getstackbound(G *g) {} // no-op for now