MFC 261991:

Upgrade our copy of llvm/clang to 3.4 release.  This version supports
all of the features in the current working draft of the upcoming C++
standard, provisionally named C++1y.

The code generator's performance is greatly increased, and the loop
auto-vectorizer is now enabled at -Os and -O2 in addition to -O3.  The
PowerPC backend has made several major improvements to code generation
quality and compile time, and the X86, SPARC, ARM32, Aarch64 and SystemZ
backends have all seen major feature work.

Release notes for llvm and clang can be found here:
<http://llvm.org/releases/3.4/docs/ReleaseNotes.html>
<http://llvm.org/releases/3.4/tools/clang/docs/ReleaseNotes.html>

MFC 262121 (by emaste):

Update lldb for clang/llvm 3.4 import

This commit largely restores the lldb source to the upstream r196259
snapshot with the addition of threaded inferior support and a few bug
fixes.

Specific upstream lldb revisions restored include:
   SVN      git
  181387  779e6ac
  181703  7bef4e2
  182099  b31044e
  182650  f2dcf35
  182683  0d91b80
  183862  15c1774
  183929  99447a6
  184177  0b2934b
  184948  4dc3761
  184954  007e7bc
  186990  eebd175

Sponsored by:	DARPA, AFRL

MFC 262186 (by emaste):

Fix mismerge in r262121

A break statement was lost in the merge.  The error had no functional
impact, but restore it to reduce the diff against upstream.

MFC 262303:

Pull in r197521 from upstream clang trunk (by rdivacky):

  Use the integrated assembler by default on FreeBSD/ppc and ppc64.

Requested by:	jhibbits

MFC 262611:

Pull in r196874 from upstream llvm trunk:

  Fix a crash that occurs when PWD is invalid.

  MCJIT needs to be able to run in hostile environments, even when PWD
  is invalid. There's no need to crash MCJIT in this case.

  The obvious fix is to simply leave MCContext's CompilationDir empty
  when PWD can't be determined. This way, MCJIT clients,
  and other clients that link with LLVM don't need a valid working directory.

  If we do want to guarantee valid CompilationDir, that should be done
  only for clients of getCompilationDir(). This is as simple as checking
  for an empty string.

  The only current use of getCompilationDir is EmitGenDwarfInfo, which
  won't conceivably run with an invalid working dir. However, in the
  purely hypothetically and untestable case that this happens, the
  AT_comp_dir will be omitted from the compilation_unit DIE.

This should help fix assertions occurring with ports-mgmt/tinderbox,
when it is using jails, and sometimes invalidates clang's current
working directory.

Reported by:	decke

MFC 262809:

Pull in r203007 from upstream clang trunk:

  Don't produce an alias between destructors with different calling conventions.

  Fixes pr19007.

(Please note that is an LLVM PR identifier, not a FreeBSD one.)

This should fix Firefox and/or libxul crashes (due to problems with
regparm/stdcall calling conventions) on i386.

Reported by:	multiple users on freebsd-current
PR:		bin/187103

MFC 263048:

Repair recognition of "CC" as an alias for the C++ compiler, since it
was silently broken by upstream for a Windows-specific use-case.

Apparently some versions of CMake still rely on this archaic feature...

Reported by:	rakuco

MFC 263049:

Garbage collect the old way of adding the libstdc++ include directories
in clang's InitHeaderSearch.cpp.  This has been superseded by David
Chisnall's commit in r255321.

Moreover, if libc++ is used, the libstdc++ include directories should
not be in the search path at all.  These directories are now only used
if you pass -stdlib=libstdc++.

1 files changed, 163 insertions, 54 deletions

diff --git a/contrib/llvm/lib/Support/Host.cpp b/contrib/llvm/lib/Support/Host.cpp
index a7c7a95..6e9a5c9 100644
--- a/contrib/llvm/lib/Support/Host.cpp
+++ b/contrib/llvm/lib/Support/Host.cpp
@@ -52,8 +52,54 @@ using namespace llvm;
 
 /// GetX86CpuIDAndInfo - Execute the specified cpuid and return the 4 values in the
 /// specified arguments.  If we can't run cpuid on the host, return true.
-static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX,
-                            unsigned *rEBX, unsigned *rECX, unsigned *rEDX) {
+static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX, unsigned *rEBX,
+                               unsigned *rECX, unsigned *rEDX) {
+#if defined(__GNUC__) || defined(__clang__)
+  #if defined(__x86_64__) || defined(_M_AMD64) || defined (_M_X64)
+    // gcc doesn't know cpuid would clobber ebx/rbx. Preseve it manually.
+    asm ("movq\t%%rbx, %%rsi\n\t"
+         "cpuid\n\t"
+         "xchgq\t%%rbx, %%rsi\n\t"
+         : "=a" (*rEAX),
+           "=S" (*rEBX),
+           "=c" (*rECX),
+           "=d" (*rEDX)
+         :  "a" (value));
+    return false;
+  #elif defined(i386) || defined(__i386__) || defined(__x86__) || defined(_M_IX86)
+    asm ("movl\t%%ebx, %%esi\n\t"
+         "cpuid\n\t"
+         "xchgl\t%%ebx, %%esi\n\t"
+         : "=a" (*rEAX),
+           "=S" (*rEBX),
+           "=c" (*rECX),
+           "=d" (*rEDX)
+         :  "a" (value));
+    return false;
+// pedantic #else returns to appease -Wunreachable-code (so we don't generate
+// postprocessed code that looks like "return true; return false;")
+  #else
+    return true;
+  #endif
+#elif defined(_MSC_VER)
+  // The MSVC intrinsic is portable across x86 and x64.
+  int registers[4];
+  __cpuid(registers, value);
+  *rEAX = registers[0];
+  *rEBX = registers[1];
+  *rECX = registers[2];
+  *rEDX = registers[3];
+  return false;
+#else
+  return true;
+#endif
+}
+
+/// GetX86CpuIDAndInfoEx - Execute the specified cpuid with subleaf and return the
+/// 4 values in the specified arguments.  If we can't run cpuid on the host,
+/// return true.
+bool GetX86CpuIDAndInfoEx(unsigned value, unsigned subleaf, unsigned *rEAX,
+                          unsigned *rEBX, unsigned *rECX, unsigned *rEDX) {
 #if defined(__x86_64__) || defined(_M_AMD64) || defined (_M_X64)
   #if defined(__GNUC__)
     // gcc doesn't know cpuid would clobber ebx/rbx. Preseve it manually.
@@ -64,16 +110,22 @@ static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX,
            "=S" (*rEBX),
            "=c" (*rECX),
            "=d" (*rEDX)
-         :  "a" (value));
+         :  "a" (value),
+            "c" (subleaf));
     return false;
   #elif defined(_MSC_VER)
-    int registers[4];
-    __cpuid(registers, value);
-    *rEAX = registers[0];
-    *rEBX = registers[1];
-    *rECX = registers[2];
-    *rEDX = registers[3];
-    return false;
+    // __cpuidex was added in MSVC++ 9.0 SP1
+    #if (_MSC_VER > 1500) || (_MSC_VER == 1500 && _MSC_FULL_VER >= 150030729)
+      int registers[4];
+      __cpuidex(registers, value, subleaf);
+      *rEAX = registers[0];
+      *rEBX = registers[1];
+      *rECX = registers[2];
+      *rEDX = registers[3];
+      return false;
+    #else
+      return true;
+    #endif
   #else
     return true;
   #endif
@@ -86,11 +138,13 @@ static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX,
            "=S" (*rEBX),
            "=c" (*rECX),
            "=d" (*rEDX)
-         :  "a" (value));
+         :  "a" (value),
+            "c" (subleaf));
     return false;
   #elif defined(_MSC_VER)
     __asm {
       mov   eax,value
+      mov   ecx,subleaf
       cpuid
       mov   esi,rEAX
       mov   dword ptr [esi],eax
@@ -102,8 +156,6 @@ static bool GetX86CpuIDAndInfo(unsigned value, unsigned *rEAX,
       mov   dword ptr [esi],edx
     }
     return false;
-// pedantic #else returns to appease -Wunreachable-code (so we don't generate
-// postprocessed code that looks like "return true; return false;")
   #else
     return true;
   #endif
@@ -148,21 +200,27 @@ std::string sys::getHostCPUName() {
   unsigned Model  = 0;
   DetectX86FamilyModel(EAX, Family, Model);
 
+  union {
+    unsigned u[3];
+    char     c[12];
+  } text;
+
+  GetX86CpuIDAndInfo(0, &EAX, text.u+0, text.u+2, text.u+1);
+
+  unsigned MaxLeaf = EAX;
   bool HasSSE3 = (ECX & 0x1);
+  bool HasSSE41 = (ECX & 0x80000);
   // If CPUID indicates support for XSAVE, XRESTORE and AVX, and XGETBV 
   // indicates that the AVX registers will be saved and restored on context
   // switch, then we have full AVX support.
   const unsigned AVXBits = (1 << 27) | (1 << 28);
   bool HasAVX = ((ECX & AVXBits) == AVXBits) && OSHasAVXSupport();
+  bool HasAVX2 = HasAVX && MaxLeaf >= 0x7 &&
+                 !GetX86CpuIDAndInfoEx(0x7, 0x0, &EAX, &EBX, &ECX, &EDX) &&
+                 (EBX & 0x20);
   GetX86CpuIDAndInfo(0x80000001, &EAX, &EBX, &ECX, &EDX);
   bool Em64T = (EDX >> 29) & 0x1;
 
-  union {
-    unsigned u[3];
-    char     c[12];
-  } text;
-
-  GetX86CpuIDAndInfo(0, &EAX, text.u+0, text.u+2, text.u+1);
   if (memcmp(text.c, "GenuineIntel", 12) == 0) {
     switch (Family) {
     case 3:
@@ -244,7 +302,8 @@ std::string sys::getHostCPUName() {
                // 17h. All processors are manufactured using the 45 nm process.
                //
                // 45nm: Penryn , Wolfdale, Yorkfield (XE)
-        return "penryn";
+        // Not all Penryn processors support SSE 4.1 (such as the Pentium brand)
+        return HasSSE41 ? "penryn" : "core2";
 
       case 26: // Intel Core i7 processor and Intel Xeon processor. All
                // processors are manufactured using the 45 nm process.
@@ -269,10 +328,20 @@ std::string sys::getHostCPUName() {
 
       // Ivy Bridge:
       case 58:
+      case 62: // Ivy Bridge EP
         // Not all Ivy Bridge processors support AVX (such as the Pentium
         // versions instead of the i7 versions).
         return HasAVX ? "core-avx-i" : "corei7";
 
+      // Haswell:
+      case 60:
+      case 63:
+      case 69:
+      case 70:
+        // Not all Haswell processors support AVX too (such as the Pentium
+        // versions instead of the i7 versions).
+        return HasAVX2 ? "core-avx2" : "corei7";
+
       case 28: // Most 45 nm Intel Atom processors
       case 38: // 45 nm Atom Lincroft
       case 39: // 32 nm Atom Medfield
@@ -280,6 +349,12 @@ std::string sys::getHostCPUName() {
       case 54: // 32 nm Atom Midview
         return "atom";
 
+      // Atom Silvermont codes from the Intel software optimization guide.
+      case 55:
+      case 74:
+      case 77:
+        return "slm";
+
       default: return (Em64T) ? "x86-64" : "i686";
       }
     case 15: {
@@ -357,9 +432,11 @@ std::string sys::getHostCPUName() {
       case 21:
         if (!HasAVX) // If the OS doesn't support AVX provide a sane fallback.
           return "btver1";
-        if (Model > 15 && Model <= 31)
-          return "bdver2";
-        return "bdver1";
+        if (Model >= 0x30)
+          return "bdver3"; // 30h-3Fh: Steamroller
+        if (Model >= 0x10)
+          return "bdver2"; // 10h-1Fh: Piledriver
+        return "bdver1";   // 00h-0Fh: Bulldozer
       case 22:
         if (!HasAVX) // If the OS doesn't support AVX provide a sane fallback.
           return "btver1";
@@ -544,6 +621,48 @@ std::string sys::getHostCPUName() {
 
   return "generic";
 }
+#elif defined(__linux__) && defined(__s390x__)
+std::string sys::getHostCPUName() {
+  // STIDP is a privileged operation, so use /proc/cpuinfo instead.
+  // Note: We cannot mmap /proc/cpuinfo here and then process the resulting
+  // memory buffer because the 'file' has 0 size (it can be read from only
+  // as a stream).
+
+  std::string Err;
+  DataStreamer *DS = getDataFileStreamer("/proc/cpuinfo", &Err);
+  if (!DS) {
+    DEBUG(dbgs() << "Unable to open /proc/cpuinfo: " << Err << "\n");
+    return "generic";
+  }
+
+  // The "processor 0:" line comes after a fair amount of other information,
+  // including a cache breakdown, but this should be plenty.
+  char buffer[2048];
+  size_t CPUInfoSize = DS->GetBytes((unsigned char*) buffer, sizeof(buffer));
+  delete DS;
+
+  StringRef Str(buffer, CPUInfoSize);
+  SmallVector<StringRef, 32> Lines;
+  Str.split(Lines, "\n");
+  for (unsigned I = 0, E = Lines.size(); I != E; ++I) {
+    if (Lines[I].startswith("processor ")) {
+      size_t Pos = Lines[I].find("machine = ");
+      if (Pos != StringRef::npos) {
+        Pos += sizeof("machine = ") - 1;
+        unsigned int Id;
+        if (!Lines[I].drop_front(Pos).getAsInteger(10, Id)) {
+          if (Id >= 2827)
+            return "zEC12";
+          if (Id >= 2817)
+            return "z196";
+        }
+      }
+      break;
+    }
+  }
+  
+  return "generic";
+}
 #else
 std::string sys::getHostCPUName() {
   return "generic";
@@ -570,41 +689,31 @@ bool sys::getHostCPUFeatures(StringMap<bool> &Features) {
   SmallVector<StringRef, 32> Lines;
   Str.split(Lines, "\n");
 
-  // Look for the CPU implementer line.
-  StringRef Implementer;
-  for (unsigned I = 0, E = Lines.size(); I != E; ++I)
-    if (Lines[I].startswith("CPU implementer"))
-      Implementer = Lines[I].substr(15).ltrim("\t :");
-
-  if (Implementer == "0x41") { // ARM Ltd.
-    SmallVector<StringRef, 32> CPUFeatures;
+  SmallVector<StringRef, 32> CPUFeatures;
 
-    // Look for the CPU features.
-    for (unsigned I = 0, E = Lines.size(); I != E; ++I)
-      if (Lines[I].startswith("Features")) {
-        Lines[I].split(CPUFeatures, " ");
-        break;
-      }
-
-    for (unsigned I = 0, E = CPUFeatures.size(); I != E; ++I) {
-      StringRef LLVMFeatureStr = StringSwitch<StringRef>(CPUFeatures[I])
-        .Case("half", "fp16")
-        .Case("neon", "neon")
-        .Case("vfpv3", "vfp3")
-        .Case("vfpv3d16", "d16")
-        .Case("vfpv4", "vfp4")
-        .Case("idiva", "hwdiv-arm")
-        .Case("idivt", "hwdiv")
-        .Default("");
-
-      if (LLVMFeatureStr != "")
-        Features.GetOrCreateValue(LLVMFeatureStr).setValue(true);
+  // Look for the CPU features.
+  for (unsigned I = 0, E = Lines.size(); I != E; ++I)
+    if (Lines[I].startswith("Features")) {
+      Lines[I].split(CPUFeatures, " ");
+      break;
     }
 
-    return true;
+  for (unsigned I = 0, E = CPUFeatures.size(); I != E; ++I) {
+    StringRef LLVMFeatureStr = StringSwitch<StringRef>(CPUFeatures[I])
+      .Case("half", "fp16")
+      .Case("neon", "neon")
+      .Case("vfpv3", "vfp3")
+      .Case("vfpv3d16", "d16")
+      .Case("vfpv4", "vfp4")
+      .Case("idiva", "hwdiv-arm")
+      .Case("idivt", "hwdiv")
+      .Default("");
+
+    if (LLVMFeatureStr != "")
+      Features.GetOrCreateValue(LLVMFeatureStr).setValue(true);
   }
 
-  return false;
+  return true;
 }
 #else
 bool sys::getHostCPUFeatures(StringMap<bool> &Features){
@@ -613,7 +722,7 @@ bool sys::getHostCPUFeatures(StringMap<bool> &Features){
 #endif
 
 std::string sys::getProcessTriple() {
-  Triple PT(LLVM_HOST_TRIPLE);
+  Triple PT(Triple::normalize(LLVM_HOST_TRIPLE));
 
   if (sizeof(void *) == 8 && PT.isArch32Bit())
     PT = PT.get64BitArchVariant();