runtime/cgo: save and restore X3 (aka GP) for crosscall1 on riscv64

The C code that is calling crosscall1 may depend on the GP register, which Go code
will currently clobber. Save and restore both X3 (aka GP) and X4 (aka TP) in this
code path (note that the Go code does not currently clobber X4, however there is
minimal downside to saving and restoring it here, which then also matches crosscall2).

Updates #47100

Change-Id: Icbb706d7889d5dc59de3efb2b510fa6ea2069496
Reviewed-on: https://go-review.googlesource.com/c/go/+/334870
Trust: Joel Sing <joel@sing.id.au>
Trust: Meng Zhuo <mzh@golangcn.org>
Reviewed-by: Meng Zhuo <mzh@golangcn.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
Run-TryBot: Meng Zhuo <mzh@golangcn.org>

diff --git a/src/runtime/cgo/gcc_riscv64.S b/src/runtime/cgo/gcc_riscv64.S
index f429dc64ee69d7b86cd34a45f11687d3d0ef3634..fdc77496d9e25899880a92263ff5ba8ca9563a8c 100644 (file)
--- a/src/runtime/cgo/gcc_riscv64.S
+++ b/src/runtime/cgo/gcc_riscv64.S
@@ -8,36 +8,38 @@
  * 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).
+ * x1 (LR), x3 (GP) and x4 (TP).
  */
 .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)
+       sd      x1, -216(sp)
+       addi    sp, sp, -216
+       sd      x3, 8(sp)
+       sd      x4, 16(sp)
+       sd      x8, 24(sp)
+       sd      x9, 32(sp)
+       sd      x18, 40(sp)
+       sd      x19, 48(sp)
+       sd      x20, 56(sp)
+       sd      x21, 64(sp)
+       sd      x22, 72(sp)
+       sd      x23, 80(sp)
+       sd      x24, 88(sp)
+       sd      x25, 96(sp)
+       sd      x26, 104(sp)
+       sd      x27, 112(sp)
+       fsd     f8, 120(sp)
+       fsd     f9, 128(sp)
+       fsd     f18, 136(sp)
+       fsd     f19, 144(sp)
+       fsd     f20, 152(sp)
+       fsd     f21, 160(sp)
+       fsd     f22, 168(sp)
+       fsd     f23, 176(sp)
+       fsd     f24, 184(sp)
+       fsd     f25, 192(sp)
+       fsd     f26, 200(sp)
+       fsd     f27, 208(sp)
 
        // a0 = *fn, a1 = *setg_gcc, a2 = *g
        mv      s1, a0
@@ -47,31 +49,33 @@ crosscall1:
        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
+       ld      x3, 8(sp)
+       ld      x4, 16(sp)
+       ld      x8, 24(sp)
+       ld      x9, 32(sp)
+       ld      x18, 40(sp)
+       ld      x19, 48(sp)
+       ld      x20, 56(sp)
+       ld      x21, 64(sp)
+       ld      x22, 72(sp)
+       ld      x23, 80(sp)
+       ld      x24, 88(sp)
+       ld      x25, 96(sp)
+       ld      x26, 104(sp)
+       ld      x27, 112(sp)
+       fld     f8, 120(sp)
+       fld     f9, 128(sp)
+       fld     f18, 136(sp)
+       fld     f19, 144(sp)
+       fld     f20, 152(sp)
+       fld     f21, 160(sp)
+       fld     f22, 168(sp)
+       fld     f23, 176(sp)
+       fld     f24, 184(sp)
+       fld     f25, 192(sp)
+       fld     f26, 200(sp)
+       fld     f27, 208(sp)
+       addi    sp, sp, 216
 
        jr      ra