runtime/cgo: save and restore R31 for crosscall1 on loong64

According to the Loong64 procedure call standard [1], R31 is a static
register and therefore needs to be saved and restored.

Also, the R2 (thread pointer) register has been removed here, as it is
not involved in allocation.

[1]: https://github.com/loongson/la-abi-specs/blob/release/lapcs.adoc

Change-Id: I02e5d4bedf131e491f1a262aa3cbc0896cbc9488
Reviewed-on: https://go-review.googlesource.com/c/go/+/700817
LUCI-TryBot-Result: Go LUCI <[email protected]>
Reviewed-by: sophie zhao <[email protected]>
Reviewed-by: Meidan Li <[email protected]>
Reviewed-by: Cherry Mui <[email protected]>
Reviewed-by: Michael Pratt <[email protected]>

Author: abner-chenc

src/runtime/cgo/gcc_loong64.S

@@ -8,23 +8,23 @@
  * 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 lp64d ABI, where $r1, $r3, $r23-$r30, and $f24-$f31
+ * Called from standard lp64d ABI, where $r1, $r3, $r22-$r31, and $f24-$f31
  * are callee-save, so they must be saved explicitly, along with $r1 (LR).
  */
 .globl crosscall1
 crosscall1:
 	addi.d	$r3, $r3, -160
 	st.d	$r1, $r3, 0
-	st.d	$r23, $r3, 8
-	st.d	$r24, $r3, 16
-	st.d	$r25, $r3, 24
-	st.d	$r26, $r3, 32
-	st.d	$r27, $r3, 40
-	st.d	$r28, $r3, 48
-	st.d	$r29, $r3, 56
-	st.d	$r30, $r3, 64
-	st.d	$r2, $r3, 72
-	st.d	$r22, $r3, 80
+	st.d	$r22, $r3, 8
+	st.d	$r23, $r3, 16
+	st.d	$r24, $r3, 24
+	st.d	$r25, $r3, 32
+	st.d	$r26, $r3, 40
+	st.d	$r27, $r3, 48
+	st.d	$r28, $r3, 56
+	st.d	$r29, $r3, 64
+	st.d	$r30, $r3, 72
+	st.d	$r31, $r3, 80
 	fst.d	$f24, $r3, 88
 	fst.d	$f25, $r3, 96
 	fst.d	$f26, $r3, 104
@@ -40,16 +40,16 @@ crosscall1:
 	jirl	$r1, $r5, 0	// call setg_gcc (clobbers R4)
 	jirl	$r1, $r23, 0	// call fn
 
-	ld.d	$r23, $r3, 8
-	ld.d	$r24, $r3, 16
-	ld.d	$r25, $r3, 24
-	ld.d	$r26, $r3, 32
-	ld.d	$r27, $r3, 40
-	ld.d	$r28, $r3, 48
-	ld.d	$r29, $r3, 56
-	ld.d	$r30, $r3, 64
-	ld.d	$r2, $r3, 72
-	ld.d	$r22, $r3, 80
+	ld.d	$r22, $r3, 8
+	ld.d	$r23, $r3, 16
+	ld.d	$r24, $r3, 24
+	ld.d	$r25, $r3, 32
+	ld.d	$r26, $r3, 40
+	ld.d	$r27, $r3, 48
+	ld.d	$r28, $r3, 56
+	ld.d	$r29, $r3, 64
+	ld.d	$r30, $r3, 72
+	ld.d	$r31, $r3, 80
 	fld.d	$f24, $r3, 88
 	fld.d	$f25, $r3, 96
 	fld.d	$f26, $r3, 104