[𝘀𝗽𝗿] changes introduced through rebase

Created using spr 1.3.4

[skip ci]

Author: nikic

.github/CODEOWNERS

@@ -35,6 +35,10 @@
 clang/lib/AST/Interp/ @tbaederr
 clang/test/AST/Interp/ @tbaederr
 
+/clang/include/clang/CIR @lanza @bcardosolopes
+/clang/lib/CIR @lanza @bcardosolopes
+/clang/tools/cir-* @lanza @bcardosolopes
+
 /lldb/ @JDevlieghere
 
 # MLIR Interfaces.

bolt/include/bolt/Profile/DataAggregator.h

@@ -198,14 +198,8 @@ class DataAggregator : public DataReader {
   /// A trace is region of code executed between two LBR entries supplied in
   /// execution order.
   ///
-  /// Return true if the trace is valid, false otherwise.
-  bool
-  recordTrace(BinaryFunction &BF, const LBREntry &First, const LBREntry &Second,
-              uint64_t Count,
-              SmallVector<std::pair<uint64_t, uint64_t>, 16> &Branches) const;
-
   /// Return a vector of offsets corresponding to a trace in a function
-  /// (see recordTrace() above).
+  /// if the trace is valid, std::nullopt otherwise.
   std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
   getFallthroughsInTrace(BinaryFunction &BF, const LBREntry &First,
                          const LBREntry &Second, uint64_t Count = 1) const;

bolt/include/bolt/Rewrite/RewriteInstance.h

@@ -422,8 +422,13 @@ class RewriteInstance {
   /// Section name used for extra BOLT code in addition to .text.
   static StringRef getBOLTTextSectionName() { return ".bolt.text"; }
 
+  /// Symbol markers for BOLT reserved area.
+  static StringRef getBOLTReservedStart() { return "__bolt_reserved_start"; }
+  static StringRef getBOLTReservedEnd() { return "__bolt_reserved_end"; }
+
   /// Common section names.
   static StringRef getEHFrameSectionName() { return ".eh_frame"; }
+  static StringRef getEHFrameHdrSectionName() { return ".eh_frame_hdr"; }
   static StringRef getRelaDynSectionName() { return ".rela.dyn"; }
 
   /// FILE symbol name used for local fragments of global functions.
@@ -493,6 +498,9 @@ class RewriteInstance {
   /// Store all non-zero symbols in this map for a quick address lookup.
   std::map<uint64_t, llvm::object::SymbolRef> FileSymRefs;
 
+  /// FILE symbols used for disambiguating split function parents.
+  std::vector<ELFSymbolRef> FileSymbols;
+
   std::unique_ptr<DWARFRewriter> DebugInfoRewriter;
 
   std::unique_ptr<BoltAddressTranslation> BAT;

bolt/include/bolt/Utils/NameResolver.h

@@ -28,10 +28,23 @@ class NameResolver {
   static constexpr char Sep = '/';
 
 public:
-  /// Return unique version of the \p Name in the form "Name<Sep><Number>".
+  /// Return the number of uniquified versions of a given \p Name.
+  uint64_t getUniquifiedNameCount(StringRef Name) const {
+    if (Counters.contains(Name))
+      return Counters.at(Name);
+    return 0;
+  }
+
+  /// Return unique version of the \p Name in the form "Name<Sep><ID>".
+  std::string getUniqueName(StringRef Name, const uint64_t ID) const {
+    return (Name + Twine(Sep) + Twine(ID)).str();
+  }
+
+  /// Register new version of \p Name and return unique version in the form
+  /// "Name<Sep><Number>".
   std::string uniquify(StringRef Name) {
     const uint64_t ID = ++Counters[Name];
-    return (Name + Twine(Sep) + Twine(ID)).str();
+    return getUniqueName(Name, ID);
   }
 
   /// For uniquified \p Name, return the original form (that may no longer be

bolt/lib/Profile/DataAggregator.cpp

@@ -861,14 +861,17 @@ bool DataAggregator::doTrace(const LBREntry &First, const LBREntry &Second,
   return true;
 }
 
-bool DataAggregator::recordTrace(
-    BinaryFunction &BF, const LBREntry &FirstLBR, const LBREntry &SecondLBR,
-    uint64_t Count,
-    SmallVector<std::pair<uint64_t, uint64_t>, 16> &Branches) const {
+std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
+DataAggregator::getFallthroughsInTrace(BinaryFunction &BF,
+                                       const LBREntry &FirstLBR,
+                                       const LBREntry &SecondLBR,
+                                       uint64_t Count) const {
+  SmallVector<std::pair<uint64_t, uint64_t>, 16> Branches;
+
   BinaryContext &BC = BF.getBinaryContext();
 
   if (!BF.isSimple())
-    return false;
+    return std::nullopt;
 
   assert(BF.hasCFG() && "can only record traces in CFG state");
 
@@ -877,13 +880,13 @@ bool DataAggregator::recordTrace(
   const uint64_t To = SecondLBR.From - BF.getAddress();
 
   if (From > To)
-    return false;
+    return std::nullopt;
 
   const BinaryBasicBlock *FromBB = BF.getBasicBlockContainingOffset(From);
   const BinaryBasicBlock *ToBB = BF.getBasicBlockContainingOffset(To);
 
   if (!FromBB || !ToBB)
-    return false;
+    return std::nullopt;
 
   // Adjust FromBB if the first LBR is a return from the last instruction in
   // the previous block (that instruction should be a call).
@@ -907,7 +910,7 @@ bool DataAggregator::recordTrace(
   // within the same basic block, e.g. when two call instructions are in the
   // same block. In this case we skip the processing.
   if (FromBB == ToBB)
-    return true;
+    return Branches;
 
   // Process blocks in the original layout order.
   BinaryBasicBlock *BB = BF.getLayout().getBlock(FromBB->getIndex());
@@ -921,7 +924,7 @@ bool DataAggregator::recordTrace(
       LLVM_DEBUG(dbgs() << "no fall-through for the trace:\n"
                         << "  " << FirstLBR << '\n'
                         << "  " << SecondLBR << '\n');
-      return false;
+      return std::nullopt;
     }
 
     const MCInst *Instr = BB->getLastNonPseudoInstr();
@@ -945,20 +948,7 @@ bool DataAggregator::recordTrace(
     BI.Count += Count;
   }
 
-  return true;
-}
-
-std::optional<SmallVector<std::pair<uint64_t, uint64_t>, 16>>
-DataAggregator::getFallthroughsInTrace(BinaryFunction &BF,
-                                       const LBREntry &FirstLBR,
-                                       const LBREntry &SecondLBR,
-                                       uint64_t Count) const {
-  SmallVector<std::pair<uint64_t, uint64_t>, 16> Res;
-
-  if (!recordTrace(BF, FirstLBR, SecondLBR, Count, Res))
-    return std::nullopt;
-
-  return Res;
+  return Branches;
 }
 
 bool DataAggregator::recordEntry(BinaryFunction &BF, uint64_t To, bool Mispred,

bolt/lib/Rewrite/LinuxKernelRewriter.cpp

@@ -248,6 +248,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
   /// Update ORC data in the binary.
   Error rewriteORCTables();
 
+  /// Validate written ORC tables after binary emission.
+  Error validateORCTables();
+
   /// Static call table handling.
   Error readStaticCalls();
   Error rewriteStaticCalls();
@@ -358,6 +361,9 @@ class LinuxKernelRewriter final : public MetadataRewriter {
     if (Error E = updateStaticKeysJumpTablePostEmit())
       return E;
 
+    if (Error E = validateORCTables())
+      return E;
+
     return Error::success();
   }
 };
@@ -837,6 +843,32 @@ Error LinuxKernelRewriter::rewriteORCTables() {
   return Error::success();
 }
 
+Error LinuxKernelRewriter::validateORCTables() {
+  if (!ORCUnwindIPSection)
+    return Error::success();
+
+  const uint64_t IPSectionAddress = ORCUnwindIPSection->getAddress();
+  DataExtractor IPDE = DataExtractor(ORCUnwindIPSection->getOutputContents(),
+                                     BC.AsmInfo->isLittleEndian(),
+                                     BC.AsmInfo->getCodePointerSize());
+  DataExtractor::Cursor IPCursor(0);
+  uint64_t PrevIP = 0;
+  for (uint32_t Index = 0; Index < NumORCEntries; ++Index) {
+    const uint64_t IP =
+        IPSectionAddress + IPCursor.tell() + (int32_t)IPDE.getU32(IPCursor);
+    if (!IPCursor)
+      return createStringError(errc::executable_format_error,
+                               "out of bounds while reading ORC IP table: %s",
+                               toString(IPCursor.takeError()).c_str());
+
+    assert(IP >= PrevIP && "Unsorted ORC table detected");
+    (void)PrevIP;
+    PrevIP = IP;
+  }
+
+  return Error::success();
+}
+
 /// The static call site table is created by objtool and contains entries in the
 /// following format:
 ///