cmd/dist,cmd/go,runtime: add support for cgo on linux/riscv64

Fixes #36641

Change-Id: I51868d83ce341d78d33b221d184c5a5110c60d14
Reviewed-on: https://go-review.googlesource.com/c/go/+/263598
Trust: Joel Sing <joel@sing.id.au>
Run-TryBot: Joel Sing <joel@sing.id.au>
TryBot-Result: Go Bot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>

3 files changed, 238 insertions, 0 deletions

diff --git a/src/runtime/cgo/asm_riscv64.s b/src/runtime/cgo/asm_riscv64.s
new file mode 100644
index 0000000000..b4ddbb020f
--- /dev/null
+++ b/src/runtime/cgo/asm_riscv64.s
@@ -0,0 +1,84 @@
+// Copyright 2020 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.
+
+// +build riscv64
+
+#include "textflag.h"
+
+// Called by C code generated by cmd/cgo.
+// func crosscall2(fn, a unsafe.Pointer, n int32, ctxt uintptr)
+// Saves C callee-saved registers and calls cgocallback with three arguments.
+// fn is the PC of a func(a unsafe.Pointer) function.
+TEXT crosscall2(SB),NOSPLIT|NOFRAME,$0
+	/*
+	 * Push arguments for fn (X10, X11, X13), along with all callee-save
+	 * registers. Note that at procedure entry the first argument is at
+	 * 8(X2).
+	 */
+	ADD	$(-8*31), X2
+	MOV	X10, (8*1)(X2) // fn unsafe.Pointer
+	MOV	X11, (8*2)(X2) // a unsafe.Pointer
+	MOV	X13, (8*3)(X2) // ctxt uintptr
+	MOV	X8, (8*4)(X2)
+	MOV	X9, (8*5)(X2)
+	MOV	X18, (8*6)(X2)
+	MOV	X19, (8*7)(X2)
+	MOV	X20, (8*8)(X2)
+	MOV	X21, (8*9)(X2)
+	MOV	X22, (8*10)(X2)
+	MOV	X23, (8*11)(X2)
+	MOV	X24, (8*12)(X2)
+	MOV	X25, (8*13)(X2)
+	MOV	X26, (8*14)(X2)
+	MOV	g, (8*15)(X2)
+	MOV	X3, (8*16)(X2)
+	MOV	X4, (8*17)(X2)
+	MOV	X1, (8*18)(X2)
+	MOVD	F8, (8*19)(X2)
+	MOVD	F9, (8*20)(X2)
+	MOVD	F18, (8*21)(X2)
+	MOVD	F19, (8*22)(X2)
+	MOVD	F20, (8*23)(X2)
+	MOVD	F21, (8*24)(X2)
+	MOVD	F22, (8*25)(X2)
+	MOVD	F23, (8*26)(X2)
+	MOVD	F24, (8*27)(X2)
+	MOVD	F25, (8*28)(X2)
+	MOVD	F26, (8*29)(X2)
+	MOVD	F27, (8*30)(X2)
+
+	// Initialize Go ABI environment
+	CALL	runtime·load_g(SB)
+	CALL	runtime·cgocallback(SB)
+
+	MOV	(8*4)(X2), X8
+	MOV	(8*5)(X2), X9
+	MOV	(8*6)(X2), X18
+	MOV	(8*7)(X2), X19
+	MOV	(8*8)(X2), X20
+	MOV	(8*9)(X2), X21
+	MOV	(8*10)(X2), X22
+	MOV	(8*11)(X2), X23
+	MOV	(8*12)(X2), X24
+	MOV	(8*13)(X2), X25
+	MOV	(8*14)(X2), X26
+	MOV	(8*15)(X2), g
+	MOV	(8*16)(X2), X3
+	MOV	(8*17)(X2), X4
+	MOV	(8*18)(X2), X1
+	MOVD	(8*19)(X2), F8
+	MOVD	(8*20)(X2), F9
+	MOVD	(8*21)(X2), F18
+	MOVD	(8*22)(X2), F19
+	MOVD	(8*23)(X2), F20
+	MOVD	(8*24)(X2), F21
+	MOVD	(8*25)(X2), F22
+	MOVD	(8*26)(X2), F23
+	MOVD	(8*27)(X2), F24
+	MOVD	(8*28)(X2), F25
+	MOVD	(8*29)(X2), F26
+	MOVD	(8*30)(X2), F27
+	ADD	$(8*31), X2
+
+	RET
diff --git a/src/runtime/cgo/gcc_linux_riscv64.c b/src/runtime/cgo/gcc_linux_riscv64.c
new file mode 100644
index 0000000000..22b76c2fcc
--- /dev/null
+++ b/src/runtime/cgo/gcc_linux_riscv64.c
@@ -0,0 +1,74 @@
+// Copyright 2020 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 <string.h>
+#include <signal.h>
+#include "libcgo.h"
+#include "libcgo_unix.h"
+
+static void *threadentry(void*);
+
+void (*x_cgo_inittls)(void **tlsg, void **tlsbase);
+static 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);
+
+	// Not sure why the memset is necessary here,
+	// but without it, we get a bogus stack size
+	// out of pthread_attr_getstacksize.  C'est la Linux.
+	memset(&attr, 0, sizeof attr);
+	pthread_attr_init(&attr);
+	size = 0;
+	pthread_attr_getstacksize(&attr, &size);
+	// Leave stacklo=0 and set stackhi=size; mstart will do the rest.
+	ts->g->stackhi = size;
+	err = _cgo_try_pthread_create(&p, &attr, threadentry, ts);
+
+	pthread_sigmask(SIG_SETMASK, &oset, nil);
+
+	if (err != 0) {
+		fatalf("pthread_create failed: %s", strerror(err));
+	}
+}
+
+extern void crosscall1(void (*fn)(void), void (*setg_gcc)(void*), void *g);
+static void*
+threadentry(void *v)
+{
+	ThreadStart ts;
+
+	ts = *(ThreadStart*)v;
+	free(v);
+
+	crosscall1(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);
+
+	if (x_cgo_inittls) {
+		x_cgo_inittls(tlsg, tlsbase);
+	}
+}
diff --git a/src/runtime/cgo/gcc_riscv64.S b/src/runtime/cgo/gcc_riscv64.S
new file mode 100644
index 0000000000..f429dc64ee
--- /dev/null
+++ b/src/runtime/cgo/gcc_riscv64.S
@@ -0,0 +1,80 @@
+// Copyright 2020 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.
+
+/*
+ * void crosscall1(void (*fn)(void), void (*setg_gcc)(void *g), void *g)
+ *
+ * Calling into the gc tool chain, where all registers are caller save.
+ * Called from standard RISCV ELF psABI, where x8-x9, x18-x27, f8-f9 and
+ * f18-f27 are callee-save, so they must be saved explicitly, along with
+ * x1 (LR).
+ */
+.globl crosscall1
+crosscall1:
+	sd	x1, -200(sp)
+	addi	sp, sp, -200
+	sd	x8, 8(sp)
+	sd	x9, 16(sp)
+	sd	x18, 24(sp)
+	sd	x19, 32(sp)
+	sd	x20, 40(sp)
+	sd	x21, 48(sp)
+	sd	x22, 56(sp)
+	sd	x23, 64(sp)
+	sd	x24, 72(sp)
+	sd	x25, 80(sp)
+	sd	x26, 88(sp)
+	sd	x27, 96(sp)
+	fsd	f8, 104(sp)
+	fsd	f9, 112(sp)
+	fsd	f18, 120(sp)
+	fsd	f19, 128(sp)
+	fsd	f20, 136(sp)
+	fsd	f21, 144(sp)
+	fsd	f22, 152(sp)
+	fsd	f23, 160(sp)
+	fsd	f24, 168(sp)
+	fsd	f25, 176(sp)
+	fsd	f26, 184(sp)
+	fsd	f27, 192(sp)
+
+	// a0 = *fn, a1 = *setg_gcc, a2 = *g
+	mv	s1, a0
+	mv	s0, a1
+	mv	a0, a2
+	jalr	ra, s0	// call setg_gcc (clobbers x30 aka g)
+	jalr	ra, s1	// call fn
+
+	ld	x1, 0(sp)
+	ld	x8, 8(sp)
+	ld	x9, 16(sp)
+	ld	x18, 24(sp)
+	ld	x19, 32(sp)
+	ld	x20, 40(sp)
+	ld	x21, 48(sp)
+	ld	x22, 56(sp)
+	ld	x23, 64(sp)
+	ld	x24, 72(sp)
+	ld	x25, 80(sp)
+	ld	x26, 88(sp)
+	ld	x27, 96(sp)
+	fld	f8, 104(sp)
+	fld	f9, 112(sp)
+	fld	f18, 120(sp)
+	fld	f19, 128(sp)
+	fld	f20, 136(sp)
+	fld	f21, 144(sp)
+	fld	f22, 152(sp)
+	fld	f23, 160(sp)
+	fld	f24, 168(sp)
+	fld	f25, 176(sp)
+	fld	f26, 184(sp)
+	fld	f27, 192(sp)
+	addi	sp, sp, 200
+
+	jr	ra
+
+#ifdef __ELF__
+.section .note.GNU-stack,"",%progbits
+#endif