[XRay] Implement powerpc64le xray.

Summary:
powerpc64 big-endian is not supported, but I believe that most logic can
be shared, except for xray_powerpc64.cc.

Also add a function InvalidateInstructionCache to xray_util.h, which is
copied from llvm/Support/Memory.cpp. I'm not sure if I need to add a unittest,
and I don't know how.

Reviewers: dberris, echristo, iteratee, kbarton, hfinkel

Subscribers: mehdi_amini, nemanjai, mgorny, llvm-commits

Differential Revision: https://reviews.llvm.org/D29742

git-svn-id: https://llvm.org/svn/llvm-project/compiler-rt/trunk@294781 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 95 insertions, 0 deletions

diff --git a/lib/xray/xray_powerpc64.cc b/lib/xray/xray_powerpc64.cc
new file mode 100644
index 000000000..6c5e18ff4
--- /dev/null
+++ b/lib/xray/xray_powerpc64.cc
@@ -0,0 +1,95 @@
+//===-- xray_AArch64.cc -----------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file is a part of XRay, a dynamic runtime instrumentation system.
+//
+// Implementation of powerpc64 and powerpc64le routines.
+//
+//===----------------------------------------------------------------------===//
+#include "sanitizer_common/sanitizer_common.h"
+#include "xray_defs.h"
+#include "xray_interface_internal.h"
+#include "xray_utils.h"
+#include <atomic>
+#include <cassert>
+#include <cstring>
+
+#ifndef __LITTLE_ENDIAN__
+#error powerpc64 big endian is not supported for now.
+#endif
+
+namespace {
+
+constexpr unsigned long long JumpOverInstNum = 7;
+
+void clearCache(void *Addr, size_t Len) {
+  const size_t LineSize = 32;
+
+  const intptr_t Mask = ~(LineSize - 1);
+  const intptr_t StartLine = ((intptr_t)Addr) & Mask;
+  const intptr_t EndLine = ((intptr_t)Addr + Len + LineSize - 1) & Mask;
+
+  for (intptr_t Line = StartLine; Line < EndLine; Line += LineSize)
+    asm volatile("dcbf 0, %0" : : "r"(Line));
+  asm volatile("sync");
+
+  for (intptr_t Line = StartLine; Line < EndLine; Line += LineSize)
+    asm volatile("icbi 0, %0" : : "r"(Line));
+  asm volatile("isync");
+}
+
+} // namespace
+
+extern "C" void __clear_cache(void *start, void *end);
+
+namespace __xray {
+
+bool patchFunctionEntry(const bool Enable, uint32_t FuncId,
+                        const XRaySledEntry &Sled) XRAY_NEVER_INSTRUMENT {
+  if (Enable) {
+    // lis 0, FuncId[16..32]
+    // li 0, FuncId[0..15]
+    *reinterpret_cast<uint64_t *>(Sled.Address) =
+        (0x3c000000ull + (FuncId >> 16)) +
+        ((0x60000000ull + (FuncId & 0xffff)) << 32);
+  } else {
+    // b +JumpOverInstNum instructions.
+    *reinterpret_cast<uint32_t *>(Sled.Address) =
+        0x48000000ull + (JumpOverInstNum << 2);
+  }
+  clearCache(reinterpret_cast<void *>(Sled.Address), 8);
+  return true;
+}
+
+bool patchFunctionExit(const bool Enable, uint32_t FuncId,
+                       const XRaySledEntry &Sled) XRAY_NEVER_INSTRUMENT {
+  if (Enable) {
+    // lis 0, FuncId[16..32]
+    // li 0, FuncId[0..15]
+    *reinterpret_cast<uint64_t *>(Sled.Address) =
+        (0x3c000000ull + (FuncId >> 16)) +
+        ((0x60000000ull + (FuncId & 0xffff)) << 32);
+  } else {
+    // Copy the blr/b instruction after JumpOverInstNum instructions.
+    *reinterpret_cast<uint32_t *>(Sled.Address) =
+        *(reinterpret_cast<uint32_t *>(Sled.Address) + JumpOverInstNum);
+  }
+  clearCache(reinterpret_cast<void *>(Sled.Address), 8);
+  return true;
+}
+
+bool patchFunctionTailExit(const bool Enable, const uint32_t FuncId,
+                           const XRaySledEntry &Sled) XRAY_NEVER_INSTRUMENT {
+  return patchFunctionExit(Enable, FuncId, Sled);
+}
+
+// FIXME: Maybe implement this better?
+bool probeRequiredCPUFeatures() XRAY_NEVER_INSTRUMENT { return true; }
+
+} // namespace __xray