Merge branch 'main' into llrint-fix

Author: pratheekhassan21

.ci/generate_test_report_lib.py

@@ -267,7 +267,7 @@ def plural(num_tests):
             report.extend(
                 [
                     "",
-                    "All tests passed but another part of the build **failed**. "
+                    "All executed tests passed, but another part of the build **failed**. "
                     "Information about the build failure could not be automatically "
                     "obtained.",
                     "",
@@ -278,7 +278,7 @@ def plural(num_tests):
             report.extend(
                 [
                     "",
-                    "All tests passed but another part of the build **failed**. Click on "
+                    "All executed tests passed, but another part of the build **failed**. Click on "
                     "a failure below to see the details.",
                     "",
                 ]

.ci/generate_test_report_lib_test.py

@@ -343,7 +343,7 @@ def test_no_failures_build_failed(self):
 
               * 1 test passed
 
-              All tests passed but another part of the build **failed**. Information about the build failure could not be automatically obtained.
+              All executed tests passed, but another part of the build **failed**. Information about the build failure could not be automatically obtained.
 
               Download the build's log file to see the details.
               
@@ -390,7 +390,7 @@ def test_no_failures_build_failed_ninja_log(self):
 
                     * 1 test passed
 
-                    All tests passed but another part of the build **failed**. Click on a failure below to see the details.
+                    All executed tests passed, but another part of the build **failed**. Click on a failure below to see the details.
 
                     <details>
                     <summary>test/4.stamp</summary>
@@ -476,7 +476,7 @@ def test_no_failures_multiple_build_failed_ninja_log(self):
 
                     * 1 test passed
 
-                    All tests passed but another part of the build **failed**. Click on a failure below to see the details.
+                    All executed tests passed, but another part of the build **failed**. Click on a failure below to see the details.
 
                     <details>
                     <summary>touch test/2.stamp</summary>
@@ -978,7 +978,7 @@ def test_generate_report_end_to_end(self):
 
                     * 1 test passed
 
-                    All tests passed but another part of the build **failed**. Click on a failure below to see the details.
+                    All executed tests passed, but another part of the build **failed**. Click on a failure below to see the details.
 
                     <details>
                     <summary>test/4.stamp</summary>

.github/workflows/libc-overlay-tests.yml

@@ -16,7 +16,7 @@ jobs:
       # Set fail-fast to false to ensure that feedback is delivered for all matrix combinations.
       fail-fast: false
       matrix:
-        os: [ubuntu-24.04, ubuntu-24.04-arm, windows-2022, windows-2025, macos-14]
+        os: [ubuntu-24.04, ubuntu-24.04-arm, windows-2022, windows-2025, macos-15]
         include:
           # TODO: add linux gcc when it is fixed
           - os: ubuntu-24.04
@@ -35,7 +35,7 @@ jobs:
             compiler:
               c_compiler: clang-cl
               cpp_compiler: clang-cl
-          - os: macos-14
+          - os: macos-15
             compiler:
               c_compiler: clang
               cpp_compiler: clang++

.github/workflows/release-documentation.yml

@@ -92,4 +92,4 @@ jobs:
           git config user.name "llvmbot"
           git commit -a -m "Add ${{ inputs.release-version }} documentation"
           git push --force  "https://[email protected]/llvmbot/www-releases.git" HEAD:refs/heads/${{ inputs.release-version }}
-          gh pr create -f -B main -H ${{ inputs.release-version }} -R llvmbot/www-releases
+          gh pr create -f -B main -H llvmbot:${{ inputs.release-version }}

bolt/README.md

@@ -202,6 +202,26 @@ $ merge-fdata *.fdata > combined.fdata
 Use `combined.fdata` for **Step 3** above to generate a universally optimized
 binary.
 
+## Identifying a Binary Modified By BOLT
+
+A binary that has been modified by BOLT will include a `bolt_info` note and may
+have extra sections with `bolt` in their name.
+
+You can use `readelf` to find these:
+```
+$ readelf -S <your-binary> | grep bolt
+  [11] .bolt.org.eh_frame PROGBITS <...>
+<...>
+  [39] .note.bolt_info   NOTE <...>
+```
+The note can be displayed with:
+```
+$ readelf -p .note.bolt_info <your-binary>
+String dump of section '.note.bolt_info':
+  <...>
+  [    10]  BOLT revision: <...>
+```
+
 ## License
 
 BOLT is licensed under the [Apache License v2.0 with LLVM Exceptions](./LICENSE.TXT).

bolt/include/bolt/Core/BinaryContext.h

@@ -943,10 +943,11 @@ class BinaryContext {
   /// that should be used by the branch. For example, main or secondary entry
   /// point.
   ///
-  /// If \p Address is an invalid destination, such as a constant island, return
-  /// nullptr and mark \p BF as ignored, since we cannot properly handle a
-  /// branch to a constant island.
-  MCSymbol *handleExternalBranchTarget(uint64_t Address, BinaryFunction &BF);
+  /// This function also performs validations: If \p Address points to an
+  /// invalid instruction or lies within a constant island, return nullptr and
+  /// mark both \p Source and \p Target as ignored.
+  MCSymbol *handleExternalBranchTarget(uint64_t Address, BinaryFunction &Source,
+                                       BinaryFunction &Target);
 
   /// Analyze memory contents at the given \p Address and return the type of
   /// memory contents (such as a possible jump table).

bolt/include/bolt/Core/BinaryFunction.h

@@ -385,6 +385,10 @@ class BinaryFunction {
   /// True if the function should not have an associated symbol table entry.
   bool IsAnonymous{false};
 
+  /// Indicates whether branch validation has already been performed,
+  /// to avoid redundant processing.
+  bool NeedBranchValidation{true};
+
   /// Name for the section this function code should reside in.
   std::string CodeSectionName;
 
@@ -2320,6 +2324,11 @@ class BinaryFunction {
   /// zero-value bytes.
   bool isZeroPaddingAt(uint64_t Offset) const;
 
+  /// Validate if the target of any internal direct branch/call is a valid
+  /// executable instruction.
+  /// Return true if all the targets are valid, false otherwise.
+  bool validateInternalBranches();
+
   /// Check that entry points have an associated instruction at their
   /// offsets after disassembly.
   void postProcessEntryPoints();

bolt/lib/Core/BinaryContext.cpp

@@ -531,20 +531,40 @@ BinaryContext::handleAddressRef(uint64_t Address, BinaryFunction &BF,
 }
 
 MCSymbol *BinaryContext::handleExternalBranchTarget(uint64_t Address,
-                                                    BinaryFunction &BF) {
-  if (BF.isInConstantIsland(Address)) {
-    BF.setIgnored();
-    this->outs() << "BOLT-WARNING: ignoring entry point at address 0x"
-                 << Twine::utohexstr(Address)
-                 << " in constant island of function " << BF << '\n';
-    return nullptr;
+                                                    BinaryFunction &Source,
+                                                    BinaryFunction &Target) {
+  const uint64_t Offset = Address - Target.getAddress();
+  assert(Offset < Target.getSize() &&
+         "Address should be inside the referenced function");
+
+  bool IsValid = true;
+  if (Source.NeedBranchValidation) {
+    if (Target.CurrentState == BinaryFunction::State::Disassembled &&
+        !Target.getInstructionAtOffset(Offset)) {
+      this->errs()
+          << "BOLT-WARNING: corrupted control flow detected in function "
+          << Source
+          << ": an external branch/call targets an invalid instruction "
+          << "in function " << Target << " at address 0x"
+          << Twine::utohexstr(Address) << "; ignoring both functions\n";
+      IsValid = false;
+    }
+    if (Target.isInConstantIsland(Address)) {
+      this->errs() << "BOLT-WARNING: ignoring entry point at address 0x"
+                   << Twine::utohexstr(Address)
+                   << " in constant island of function " << Target << '\n';
+      IsValid = false;
+    }
   }
 
-  const uint64_t Offset = Address - BF.getAddress();
-  assert(Offset < BF.getSize() &&
-         "Address should be inside the referenced function");
+  if (!IsValid) {
+    Source.NeedBranchValidation = false;
+    Source.setIgnored();
+    Target.setIgnored();
+    return nullptr;
+  }
 
-  return Offset ? BF.addEntryPointAtOffset(Offset) : BF.getSymbol();
+  return Offset ? Target.addEntryPointAtOffset(Offset) : Target.getSymbol();
 }
 
 MemoryContentsType BinaryContext::analyzeMemoryAt(uint64_t Address,
@@ -1433,7 +1453,7 @@ void BinaryContext::processInterproceduralReferences() {
 
       // Create an extra entry point if needed. Can also render the target
       // function ignored if the reference is invalid.
-      handleExternalBranchTarget(Address, *TargetFunction);
+      handleExternalBranchTarget(Address, Function, *TargetFunction);
 
       continue;
     }
@@ -1868,6 +1888,9 @@ void BinaryContext::preprocessDebugInfo() {
 
   preprocessDWODebugInfo();
 
+  // Check if required DWO files are missing.
+  uint64_t NumMissingDWOs = 0;
+
   // Populate MCContext with DWARF files from all units.
   StringRef GlobalPrefix = AsmInfo->getPrivateGlobalPrefix();
   for (const std::unique_ptr<DWARFUnit> &CU : DwCtx->compile_units()) {
@@ -1889,19 +1912,23 @@ void BinaryContext::preprocessDebugInfo() {
       std::optional<MD5::MD5Result> Checksum;
       if (LineTable->Prologue.ContentTypes.HasMD5)
         Checksum = LineTable->Prologue.FileNames[0].Checksum;
-      std::optional<const char *> Name =
+      const char *Name =
           dwarf::toString(CU->getUnitDIE().find(dwarf::DW_AT_name), nullptr);
       if (std::optional<uint64_t> DWOID = CU->getDWOId()) {
         auto Iter = DWOCUs.find(*DWOID);
         if (Iter == DWOCUs.end()) {
-          this->errs() << "BOLT-ERROR: DWO CU was not found for " << Name
-                       << '\n';
-          exit(1);
+          const char *DWOName =
+              dwarf::toString(CU->getUnitDIE().find(dwarf::DW_AT_dwo_name),
+                              "<missing DW_AT_dwo_name>");
+          this->errs() << "BOLT-ERROR: unable to load " << DWOName
+                       << " for DWO_id 0x" << Twine::utohexstr(*DWOID) << '\n';
+          NumMissingDWOs++;
+          continue;
         }
         Name = dwarf::toString(
             Iter->second->getUnitDIE().find(dwarf::DW_AT_name), nullptr);
       }
-      BinaryLineTable.setRootFile(CU->getCompilationDir(), *Name, Checksum,
+      BinaryLineTable.setRootFile(CU->getCompilationDir(), Name, Checksum,
                                   std::nullopt);
     }
 
@@ -1936,6 +1963,14 @@ void BinaryContext::preprocessDebugInfo() {
                             DwarfVersion));
     }
   }
+
+  if (NumMissingDWOs) {
+    this->errs() << "BOLT-ERROR: " << NumMissingDWOs
+                 << " required DWO file(s) not found. Unable to update debug"
+                    " info. Use --comp-dir-override to locate the file(s) or"
+                    " --update-debug-sections=0 to remove debug info\n";
+    exit(1);
+  }
 }
 
 bool BinaryContext::shouldEmit(const BinaryFunction &Function) const {

bolt/lib/Core/BinaryFunction.cpp

@@ -1038,8 +1038,10 @@ MCSymbol *BinaryFunction::getOrCreateLocalLabel(uint64_t Address) {
 
   // For AArch64, check if this address is part of a constant island.
   if (BC.isAArch64()) {
-    if (MCSymbol *IslandSym = getOrCreateIslandAccess(Address))
+    if (MCSymbol *IslandSym = getOrCreateIslandAccess(Address)) {
+      Labels[Offset] = IslandSym;
       return IslandSym;
+    }
   }
 
   if (Offset == getSize())
@@ -1692,7 +1694,7 @@ bool BinaryFunction::scanExternalRefs() {
       // Get a reference symbol for the function when address is a valid code
       // reference.
       BranchTargetSymbol =
-          BC.handleExternalBranchTarget(TargetAddress, *TargetFunction);
+          BC.handleExternalBranchTarget(TargetAddress, *this, *TargetFunction);
       if (!BranchTargetSymbol)
         continue;
     }
@@ -1900,6 +1902,36 @@ bool BinaryFunction::scanExternalRefs() {
   return Success;
 }
 
+bool BinaryFunction::validateInternalBranches() {
+  if (!isSimple() || TrapsOnEntry)
+    return true;
+
+  for (const auto &KV : Labels) {
+    MCSymbol *Label = KV.second;
+    if (getSecondaryEntryPointSymbol(Label))
+      continue;
+
+    const uint32_t Offset = KV.first;
+    // Skip empty functions and out-of-bounds offsets,
+    // as they may not be disassembled.
+    if (!Offset || (Offset > getSize()))
+      continue;
+
+    if (!getInstructionAtOffset(Offset) ||
+        isInConstantIsland(getAddress() + Offset)) {
+      BC.errs() << "BOLT-WARNING: corrupted control flow detected in function "
+                << *this << ": an internal branch/call targets an invalid "
+                << "instruction at address 0x"
+                << Twine::utohexstr(getAddress() + Offset)
+                << "; ignoring this function\n";
+      setIgnored();
+      return false;
+    }
+  }
+
+  return true;
+}
+
 void BinaryFunction::postProcessEntryPoints() {
   if (!isSimple())
     return;

bolt/lib/Passes/PAuthGadgetScanner.cpp

@@ -547,7 +547,7 @@ class SrcSafetyAnalysis {
 
     // Being trusted is a strictly stronger property than being
     // safe-to-dereference.
-    assert(!Next.TrustedRegs.test(Next.SafeToDerefRegs) &&
+    assert(Next.TrustedRegs.subsetOf(Next.SafeToDerefRegs) &&
            "SafeToDerefRegs should contain all TrustedRegs");
 
     return Next;