[DLCov] Origin-Tracking: Add debugify support (#143594)

This patch is part of a series that adds origin-tracking to the debugify
source location coverage checks, allowing us to report symbolized stack
traces of the point where missing source locations appear.

This patch completes the feature, having debugify handle origin stack
traces by symbolizing them when an associated bug is found and printing
them into the JSON report file as part of the bug entry. This patch also
updates the script that parses the JSON report and creates a
human-readable HTML report, adding an "Origin" entry to the table that
contains an expandable textbox containing the symbolized stack trace.

1 files changed, 74 insertions, 10 deletions

diff --git a/llvm/lib/Transforms/Utils/Debugify.cpp b/llvm/lib/Transforms/Utils/Debugify.cpp
index 5f70bc4..a1f030a 100644
--- a/llvm/lib/Transforms/Utils/Debugify.cpp
+++ b/llvm/lib/Transforms/Utils/Debugify.cpp
@@ -16,8 +16,10 @@
 #include "llvm/Transforms/Utils/Debugify.h"
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/StringExtras.h"
+#include "llvm/Config/llvm-config.h"
 #include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/DebugInfo.h"
+#include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/InstIterator.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
@@ -28,6 +30,11 @@
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/JSON.h"
 #include <optional>
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+// We need the Signals header to operate on stacktraces if we're using DebugLoc
+// origin-tracking.
+#include "llvm/Support/Signals.h"
+#endif
 
 #define DEBUG_TYPE "debugify"
 
@@ -59,6 +66,54 @@ cl::opt<Level> DebugifyLevel(
 
 raw_ostream &dbg() { return Quiet ? nulls() : errs(); }
 
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+// These maps refer to addresses in the current LLVM process, so we can reuse
+// them everywhere - therefore, we store them at file scope.
+static SymbolizedAddressMap SymbolizedAddrs;
+static AddressSet UnsymbolizedAddrs;
+
+std::string symbolizeStackTrace(const Instruction *I) {
+  // We flush the set of unsymbolized addresses at the latest possible moment,
+  // i.e. now.
+  if (!UnsymbolizedAddrs.empty()) {
+    sys::symbolizeAddresses(UnsymbolizedAddrs, SymbolizedAddrs);
+    UnsymbolizedAddrs.clear();
+  }
+  const DbgLocOrigin::StackTracesTy &OriginStackTraces =
+      I->getDebugLoc().getOriginStackTraces();
+  std::string Result;
+  raw_string_ostream OS(Result);
+  for (size_t TraceIdx = 0; TraceIdx < OriginStackTraces.size(); ++TraceIdx) {
+    if (TraceIdx != 0)
+      OS << "========================================\n";
+    auto &[Depth, StackTrace] = OriginStackTraces[TraceIdx];
+    unsigned VirtualFrameNo = 0;
+    for (int Frame = 0; Frame < Depth; ++Frame) {
+      assert(SymbolizedAddrs.contains(StackTrace[Frame]) &&
+             "Expected each address to have been symbolized.");
+      for (std::string &SymbolizedFrame : SymbolizedAddrs[StackTrace[Frame]]) {
+        OS << right_justify(formatv("#{0}", VirtualFrameNo++).str(),
+                            std::log10(Depth) + 2)
+           << ' ' << SymbolizedFrame << '\n';
+      }
+    }
+  }
+  return Result;
+}
+void collectStackAddresses(Instruction &I) {
+  auto &OriginStackTraces = I.getDebugLoc().getOriginStackTraces();
+  for (auto &[Depth, StackTrace] : OriginStackTraces) {
+    for (int Frame = 0; Frame < Depth; ++Frame) {
+      void *Addr = StackTrace[Frame];
+      if (!SymbolizedAddrs.contains(Addr))
+        UnsymbolizedAddrs.insert(Addr);
+    }
+  }
+}
+#else
+void collectStackAddresses(Instruction &I) {}
+#endif // LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+
 uint64_t getAllocSizeInBits(Module &M, Type *Ty) {
   return Ty->isSized() ? M.getDataLayout().getTypeAllocSizeInBits(Ty) : 0;
 }
@@ -375,6 +430,8 @@ bool llvm::collectDebugInfoMetadata(Module &M,
         LLVM_DEBUG(dbgs() << "  Collecting info for inst: " << I << '\n');
         DebugInfoBeforePass.InstToDelete.insert({&I, &I});
 
+        // Track the addresses to symbolize, if the feature is enabled.
+        collectStackAddresses(I);
         DebugInfoBeforePass.DILocations.insert({&I, hasLoc(I)});
       }
     }
@@ -450,14 +507,23 @@ static bool checkInstructions(const DebugInstMap &DILocsBefore,
     auto BBName = BB->hasName() ? BB->getName() : "no-name";
     auto InstName = Instruction::getOpcodeName(Instr->getOpcode());
 
+    auto CreateJSONBugEntry = [&](const char *Action) {
+      Bugs.push_back(llvm::json::Object({
+          {"metadata", "DILocation"},
+          {"fn-name", FnName.str()},
+          {"bb-name", BBName.str()},
+          {"instr", InstName},
+          {"action", Action},
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+          {"origin", symbolizeStackTrace(Instr)},
+#endif
+      }));
+    };
+
     auto InstrIt = DILocsBefore.find(Instr);
     if (InstrIt == DILocsBefore.end()) {
       if (ShouldWriteIntoJSON)
-        Bugs.push_back(llvm::json::Object({{"metadata", "DILocation"},
-                                           {"fn-name", FnName.str()},
-                                           {"bb-name", BBName.str()},
-                                           {"instr", InstName},
-                                           {"action", "not-generate"}}));
+        CreateJSONBugEntry("not-generate");
       else
         dbg() << "WARNING: " << NameOfWrappedPass
               << " did not generate DILocation for " << *Instr
@@ -470,11 +536,7 @@ static bool checkInstructions(const DebugInstMap &DILocsBefore,
       // If the instr had the !dbg attached before the pass, consider it as
       // a debug info issue.
       if (ShouldWriteIntoJSON)
-        Bugs.push_back(llvm::json::Object({{"metadata", "DILocation"},
-                                           {"fn-name", FnName.str()},
-                                           {"bb-name", BBName.str()},
-                                           {"instr", InstName},
-                                           {"action", "drop"}}));
+        CreateJSONBugEntry("drop");
       else
         dbg() << "WARNING: " << NameOfWrappedPass << " dropped DILocation of "
               << *Instr << " (BB: " << BBName << ", Fn: " << FnName
@@ -612,6 +674,8 @@ bool llvm::checkDebugInfoMetadata(Module &M,
 
         LLVM_DEBUG(dbgs() << "  Collecting info for inst: " << I << '\n');
 
+        // Track the addresses to symbolize, if the feature is enabled.
+        collectStackAddresses(I);
         DebugInfoAfterPass.DILocations.insert({&I, hasLoc(I)});
       }
     }