Re-commit r294826 and r294781, with a fix on the cmake file to only

compile on powerpc64le.

I cannot locally reproduce this test failure:
http://lab.llvm.org:8011/builders/sanitizer-ppc64le-linux/builds/1363/steps/test%20standalone%20compiler-rt/logs/stdio

Let's see how the buildbot goes.

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

llvm-svn: 295017

compiler-rt/cmake/config-ix.cmake

@@ -183,7 +183,7 @@ set(ALL_SAFESTACK_SUPPORTED_ARCH ${X86} ${X86_64} ${ARM64} ${MIPS32} ${MIPS64})
 set(ALL_CFI_SUPPORTED_ARCH ${X86} ${X86_64} ${MIPS64})
 set(ALL_ESAN_SUPPORTED_ARCH ${X86_64} ${MIPS64})
 set(ALL_SCUDO_SUPPORTED_ARCH ${X86} ${X86_64} ${ARM32} ${ARM64})
-set(ALL_XRAY_SUPPORTED_ARCH ${X86_64} ${ARM32} ${ARM64})
+set(ALL_XRAY_SUPPORTED_ARCH ${X86_64} ${ARM32} ${ARM64} powerpc64le)
 
 if(APPLE)
   include(CompilerRTDarwinUtils)

compiler-rt/lib/xray/CMakeLists.txt

@@ -29,6 +29,12 @@ set(aarch64_SOURCES
   xray_trampoline_AArch64.S
   ${XRAY_SOURCES})
 
+set(powerpc64le_SOURCES
+        xray_powerpc64.cc
+        xray_trampoline_powerpc64.cc
+        xray_trampoline_powerpc64.S
+        ${XRAY_SOURCES})
+
 include_directories(..)
 include_directories(../../include)
 

compiler-rt/lib/xray/xray_interface.cc

@@ -35,6 +35,8 @@ static const int16_t cSledLength = 12;
 static const int16_t cSledLength = 32;
 #elif defined(__arm__)
 static const int16_t cSledLength = 28;
+#elif defined(__powerpc64__)
+static const int16_t cSledLength = 8;
 #else
 #error "Unsupported CPU Architecture"
 #endif /* CPU architecture */

compiler-rt/lib/xray/xray_powerpc64.cc

@@ -0,0 +1,95 @@
+//===-- xray_powerpc64.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

compiler-rt/lib/xray/xray_powerpc64.inc

@@ -0,0 +1,37 @@
+//===-- xray_powerpc64.inc --------------------------------------*- 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.
+//
+//===----------------------------------------------------------------------===//
+
+#include <cstdint>
+#include <mutex>
+#include <sys/platform/ppc.h>
+
+#include "xray_defs.h"
+
+namespace __xray {
+
+ALWAYS_INLINE uint64_t readTSC(uint8_t &CPU) XRAY_NEVER_INSTRUMENT {
+  CPU = 0;
+  return __ppc_get_timebase();
+}
+
+inline uint64_t getTSCFrequency() XRAY_NEVER_INSTRUMENT {
+  static std::mutex M;
+  std::lock_guard<std::mutex> Guard(M);
+  return __ppc_get_timebase_freq();
+}
+
+inline bool probeRequiredCPUFeatures() XRAY_NEVER_INSTRUMENT {
+  return true;
+}
+
+} // namespace __xray

compiler-rt/lib/xray/xray_trampoline_powerpc64.S

@@ -0,0 +1,171 @@
+	.text
+	.abiversion 2
+	.globl	__xray_FunctionEntry
+	.p2align	4
+__xray_FunctionEntry:
+	std 0, 16(1)
+	stdu 1, -408(1)
+# Spill r3-r10, f1-f13, and vsr34-vsr45, which are parameter registers.
+# If this appears to be slow, the caller needs to pass in number of generic,
+# floating point, and vector parameters, so that we only spill those live ones.
+	std 3, 32(1)
+	ld 3, 400(1) # FuncId
+	std 4, 40(1)
+	std 5, 48(1)
+	std 6, 56(1)
+	std 7, 64(1)
+	std 8, 72(1)
+	std 9, 80(1)
+	std 10, 88(1)
+	addi 4, 1, 96
+	stxsdx 1, 0, 4
+	addi 4, 1, 104
+	stxsdx 2, 0, 4
+	addi 4, 1, 112
+	stxsdx 3, 0, 4
+	addi 4, 1, 120
+	stxsdx 4, 0, 4
+	addi 4, 1, 128
+	stxsdx 5, 0, 4
+	addi 4, 1, 136
+	stxsdx 6, 0, 4
+	addi 4, 1, 144
+	stxsdx 7, 0, 4
+	addi 4, 1, 152
+	stxsdx 8, 0, 4
+	addi 4, 1, 160
+	stxsdx 9, 0, 4
+	addi 4, 1, 168
+	stxsdx 10, 0, 4
+	addi 4, 1, 176
+	stxsdx 11, 0, 4
+	addi 4, 1, 184
+	stxsdx 12, 0, 4
+	addi 4, 1, 192
+	stxsdx 13, 0, 4
+	addi 4, 1, 200
+	stxvd2x 34, 0, 4
+	addi 4, 1, 216
+	stxvd2x 35, 0, 4
+	addi 4, 1, 232
+	stxvd2x 36, 0, 4
+	addi 4, 1, 248
+	stxvd2x 37, 0, 4
+	addi 4, 1, 264
+	stxvd2x 38, 0, 4
+	addi 4, 1, 280
+	stxvd2x 39, 0, 4
+	addi 4, 1, 296
+	stxvd2x 40, 0, 4
+	addi 4, 1, 312
+	stxvd2x 41, 0, 4
+	addi 4, 1, 328
+	stxvd2x 42, 0, 4
+	addi 4, 1, 344
+	stxvd2x 43, 0, 4
+	addi 4, 1, 360
+	stxvd2x 44, 0, 4
+	addi 4, 1, 376
+	stxvd2x 45, 0, 4
+	std 2, 392(1)
+	mflr 0
+	std 0, 400(1)
+
+	li 4, 0
+	bl _ZN6__xray23CallXRayPatchedFunctionEi13XRayEntryType
+	nop
+
+	addi 4, 1, 96
+	lxsdx 1, 0, 4
+	addi 4, 1, 104
+	lxsdx 2, 0, 4
+	addi 4, 1, 112
+	lxsdx 3, 0, 4
+	addi 4, 1, 120
+	lxsdx 4, 0, 4
+	addi 4, 1, 128
+	lxsdx 5, 0, 4
+	addi 4, 1, 136
+	lxsdx 6, 0, 4
+	addi 4, 1, 144
+	lxsdx 7, 0, 4
+	addi 4, 1, 152
+	lxsdx 8, 0, 4
+	addi 4, 1, 160
+	lxsdx 9, 0, 4
+	addi 4, 1, 168
+	lxsdx 10, 0, 4
+	addi 4, 1, 176
+	lxsdx 11, 0, 4
+	addi 4, 1, 184
+	lxsdx 12, 0, 4
+	addi 4, 1, 192
+	lxsdx 13, 0, 4
+	addi 4, 1, 200
+	lxvd2x 34, 0, 4
+	addi 4, 1, 216
+	lxvd2x 35, 0, 4
+	addi 4, 1, 232
+	lxvd2x 36, 0, 4
+	addi 4, 1, 248
+	lxvd2x 37, 0, 4
+	addi 4, 1, 264
+	lxvd2x 38, 0, 4
+	addi 4, 1, 280
+	lxvd2x 39, 0, 4
+	addi 4, 1, 296
+	lxvd2x 40, 0, 4
+	addi 4, 1, 312
+	lxvd2x 41, 0, 4
+	addi 4, 1, 328
+	lxvd2x 42, 0, 4
+	addi 4, 1, 344
+	lxvd2x 43, 0, 4
+	addi 4, 1, 360
+	lxvd2x 44, 0, 4
+	addi 4, 1, 376
+	lxvd2x 45, 0, 4
+	ld 0, 400(1)
+	mtlr 0
+	ld 2, 392(1)
+	ld 3, 32(1)
+	ld 4, 40(1)
+	ld 5, 48(1)
+	ld 6, 56(1)
+	ld 7, 64(1)
+	ld 8, 72(1)
+	ld 9, 80(1)
+	ld 10, 88(1)
+
+	addi 1, 1, 408
+	ld 0, 16(1)
+	blr
+
+	.globl	__xray_FunctionExit
+	.p2align	4
+__xray_FunctionExit:
+	std 0, 16(1)
+	ld 0, -8(1) # FuncId
+	stdu 1, -72(1)
+# Spill r3, f1, and vsr34, the return value registers.
+	std 3, 32(1)
+	mr 3, 0
+	addi 4, 1, 40
+	stxsdx 1, 0, 4
+	addi 4, 1, 48
+	stxvd2x 34, 0, 4
+	mflr 0
+	std 0, 64(1)
+	li 4, 1
+	bl _ZN6__xray23CallXRayPatchedFunctionEi13XRayEntryType
+	nop
+	ld 0, 64(1)
+	mtlr 0
+	ld 3, 32(1)
+	addi 4, 1, 40
+	lxsdx 1, 0, 4
+	addi 4, 1, 48
+	lxvd2x 34, 0, 4
+	addi 1, 1, 72
+	ld 0, 16(1)
+	blr

compiler-rt/lib/xray/xray_trampoline_powerpc64.cc

@@ -0,0 +1,15 @@
+#include <atomic>
+#include <xray/xray_interface.h>
+
+namespace __xray {
+
+extern std::atomic<void (*)(int32_t, XRayEntryType)> XRayPatchedFunction;
+
+// Implement this in C++ instead of assembly, to avoid dealing with ToC by hand.
+void CallXRayPatchedFunction(int32_t FuncId, XRayEntryType Type) {
+  auto fptr = __xray::XRayPatchedFunction.load();
+  if (fptr != nullptr)
+    (*fptr)(FuncId, Type);
+}
+
+} // namespace __xray

compiler-rt/lib/xray/xray_tsc.h

@@ -15,6 +15,8 @@
 
 #if defined(__x86_64__)
 #include "xray_x86_64.inc"
+#elif defined(__powerpc64__)
+#include "xray_powerpc64.inc"
 #elif defined(__arm__) || defined(__aarch64__)
 // Emulated TSC.
 // There is no instruction like RDTSCP in user mode on ARM. ARM's CP15 does