[libunwind][PowerPC] Fix saving/restoring VSX registers on LE systems

Currently, libunwind just uses stxvd2x/lxvd2x to save/restore
VSX registers respectively. This puts the registers in
doubleword-reversed order into memory on little endian systems.
If both the save and restore are done the same way, this
isn't a problem. However if the unwinder is just restoring
a callee-saved register, it will restore it in the wrong
order (since function prologues save them in the correct order).
This patch adds the necessary swaps before the saves and after
the restores.

Differential revision: https://reviews.llvm.org/D137599

(cherry picked from commit 372820b)

Author: nemanjai

libcxxabi/test/vendor/ibm/vec_reg_restore-le.pass.cpp

@@ -0,0 +1,90 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+// Check that the PowerPC vector registers are restored properly during
+// unwinding.
+
+// REQUIRES: target=powerpc{{(64)?}}le-unknown-linux-gnu
+// UNSUPPORTED: no-exceptions
+
+// Callee-saved VSR's 62 and 63 (vr30, vr31 respectively) are set to 16 bytes
+// with values 1, 2 respectively in main. In order to ensure the two doublewords
+// in each register are different, they are merged. Then they are reset to 16
+// bytes with values 9 and 12 respectively in a callee and an exception is
+// thrown. When catching an exception in main, the values in the two registers
+// need to be the original ones (including the correct doubleword order).
+
+#include <cassert>
+#include <cstdlib>
+
+int __attribute__((noinline)) test2(int i) {
+  if (i > 3)
+    throw i;
+  srand(i);
+  return rand();
+}
+
+int __attribute__((noinline)) test(int i) {
+  // Clobber VS63 and VS62 in the function body.
+  // Set VS63 to 16 bytes each with value 9
+  asm volatile("vspltisb 31, 9" : : : "v31");
+
+  // Set VS62 to 16 bytes each with value 12
+  asm volatile("vspltisb 30, 12" : : : "v30");
+  return test2(i);
+}
+
+#define cmpVS63(vec, result)                                                   \
+  {                                                                            \
+    vector unsigned char gbg;                                                  \
+    asm volatile("vcmpequb. %[gbg], 31, %[veca];"                              \
+                 "mfocrf %[res], 2;"                                           \
+                 "rlwinm %[res], %[res], 25, 31, 31"                           \
+                 : [res] "=r"(result), [gbg] "=v"(gbg)                         \
+                 : [veca] "v"(vec)                                             \
+                 : "cr6");                                                     \
+  }
+
+#define cmpVS62(vec, result)                                                   \
+  {                                                                            \
+    vector unsigned char gbg;                                                  \
+    asm volatile("vcmpequb. %[gbg], 30, %[veca];"                              \
+                 "mfocrf %[res], 2;"                                           \
+                 "rlwinm %[res], %[res], 25, 31, 31"                           \
+                 : [res] "=r"(result), [gbg] "=v"(gbg)                         \
+                 : [veca] "v"(vec)                                             \
+                 : "cr6");                                                     \
+  }
+
+int main(int, char **) {
+  // Set VS63 to 16 bytes each with value 1.
+  asm volatile("vspltisb 31, 1" : : : "v31");
+
+  // Set VS62 to 16 bytes each with value 2.
+  asm volatile("vspltisb 30, 2" : : : "v30");
+
+  // Mix doublewords for both VS62 and VS63.
+  asm volatile("xxmrghd 63, 63, 62");
+  asm volatile("xxmrghd 62, 63, 62");
+
+  vector unsigned long long expectedVS63Value = {0x202020202020202,
+                                                 0x101010101010101};
+  vector unsigned long long expectedVS62Value = {0x202020202020202,
+                                                 0x101010101010101};
+  try {
+    test(4);
+  } catch (int num) {
+    // If the unwinder restores VS63 and VS62 correctly, they should contain
+    // 0x01's and 0x02's respectively instead of 0x09's and 0x12's.
+    bool isEqualVS63, isEqualVS62;
+    cmpVS63(expectedVS63Value, isEqualVS63);
+    cmpVS62(expectedVS62Value, isEqualVS62);
+    assert(isEqualVS63 && isEqualVS62);
+  }
+  return 0;
+}

libunwind/src/UnwindRegistersRestore.S

@@ -194,9 +194,20 @@ DEFINE_LIBUNWIND_FUNCTION(_ZN9libunwind15Registers_ppc646jumptoEv)
   addi  4, 3, PPC64_OFFS_FP
 
 // load VS register
+#ifdef __LITTLE_ENDIAN__
+// For little-endian targets, we need a swap since lxvd2x will load the register
+// in the incorrect doubleword order.
+// FIXME: when supporting targets older than Power9 on LE is no longer required,
+//        this can be changed to simply `lxv n, (16 * n)(4)`.
 #define PPC64_LVS(n)         \
   lxvd2x  n, 0, 4           ;\
+  xxswapd n, n              ;\
   addi    4, 4, 16
+#else
+#define PPC64_LVS(n)         \
+  lxvd2x  n, 0, 4           ;\
+  addi    4, 4, 16
+#endif
 
   // restore the first 32 VS regs (and also all floating point regs)
   PPC64_LVS(0)
@@ -232,9 +243,16 @@ DEFINE_LIBUNWIND_FUNCTION(_ZN9libunwind15Registers_ppc646jumptoEv)
   PPC64_LVS(30)
   PPC64_LVS(31)
 
+#ifdef __LITTLE_ENDIAN__
+#define PPC64_CLVS_RESTORE(n)                    \
+  addi   4, 3, PPC64_OFFS_FP + n * 16           ;\
+  lxvd2x n, 0, 4                                ;\
+  xxswapd n, n
+#else
 #define PPC64_CLVS_RESTORE(n)                    \
   addi   4, 3, PPC64_OFFS_FP + n * 16           ;\
   lxvd2x n, 0, 4
+#endif
 
 #if !defined(_AIX)
   // use VRSAVE to conditionally restore the remaining VS regs, that are

libunwind/src/UnwindRegistersSave.S

@@ -351,9 +351,20 @@ DEFINE_LIBUNWIND_FUNCTION(__unw_getcontext)
   addi  4, 3, PPC64_OFFS_FP
 
 // store VS register
+#ifdef __LITTLE_ENDIAN__
+// For little-endian targets, we need a swap since stxvd2x will store the
+// register in the incorrect doubleword order.
+// FIXME: when supporting targets older than Power9 on LE is no longer required
+//        this can be changed to simply `stxv n, 16 * n(4)`.
 #define PPC64_STVS(n)      \
+  xxswapd n, n            ;\
   stxvd2x n, 0, 4         ;\
   addi    4, 4, 16
+#else
+#define PPC64_STVS(n)      \
+  stxvd2x n, 0, 4         ;\
+  addi    4, 4, 16
+#endif
 
   PPC64_STVS(0)
   PPC64_STVS(1)