[DLCov] Origin-Tracking: Collect stack traces in DebugLoc (#146678)

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 adds the logic for collecting stack traces in DebugLoc
instances. We do not symbolize the stack traces in this patch - that
only happens when we decide to actually print them, which will be the
responsibility of debugify. The collection happens in the constructor of
a DebugLoc that has neither a valid location nor an annotation; we also
collect an extra stack trace every time we call setDebugLoc, as
sometimes the more interesting point is not where the DebugLoc was
constructed, but where it was applied to an instruction. This takes the
form of a getCopied() method on DebugLoc, which is the identity function
in normal builds, but adds an extra stack trace in origin-tracking
builds.

Author: SLTozer

llvm/include/llvm/IR/DebugLoc.h

@@ -27,6 +27,21 @@ namespace llvm {
   class Function;
 
 #if LLVM_ENABLE_DEBUGLOC_TRACKING_COVERAGE
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+  struct DbgLocOrigin {
+    static constexpr unsigned long MaxDepth = 16;
+    using StackTracesTy =
+        SmallVector<std::pair<int, std::array<void *, MaxDepth>>, 0>;
+    StackTracesTy StackTraces;
+    DbgLocOrigin(bool ShouldCollectTrace);
+    void addTrace();
+    const StackTracesTy &getOriginStackTraces() const { return StackTraces; };
+  };
+#else
+  struct DbgLocOrigin {
+    DbgLocOrigin(bool) {}
+  };
+#endif
   // Used to represent different "kinds" of DebugLoc, expressing that the
   // instruction it is part of is either normal and should contain a valid
   // DILocation, or otherwise describing the reason why the instruction does
@@ -55,22 +70,29 @@ namespace llvm {
     Temporary
   };
 
-  // Extends TrackingMDNodeRef to also store a DebugLocKind, allowing Debugify
-  // to ignore intentionally-empty DebugLocs.
-  class DILocAndCoverageTracking : public TrackingMDNodeRef {
+  // Extends TrackingMDNodeRef to also store a DebugLocKind and Origin,
+  // allowing Debugify to ignore intentionally-empty DebugLocs and display the
+  // code responsible for generating unintentionally-empty DebugLocs.
+  // Currently we only need to track the Origin of this DILoc when using a
+  // DebugLoc that is not annotated (i.e. has DebugLocKind::Normal) and has a
+  // null DILocation, so only collect the origin stacktrace in those cases.
+  class DILocAndCoverageTracking : public TrackingMDNodeRef,
+                                   public DbgLocOrigin {
   public:
     DebugLocKind Kind;
     // Default constructor for empty DebugLocs.
     DILocAndCoverageTracking()
-        : TrackingMDNodeRef(nullptr), Kind(DebugLocKind::Normal) {}
-    // Valid or nullptr MDNode*, normal DebugLocKind.
+        : TrackingMDNodeRef(nullptr), DbgLocOrigin(true),
+          Kind(DebugLocKind::Normal) {}
+    // Valid or nullptr MDNode*, no annotative DebugLocKind.
     DILocAndCoverageTracking(const MDNode *Loc)
-        : TrackingMDNodeRef(const_cast<MDNode *>(Loc)),
+        : TrackingMDNodeRef(const_cast<MDNode *>(Loc)), DbgLocOrigin(!Loc),
           Kind(DebugLocKind::Normal) {}
     LLVM_ABI DILocAndCoverageTracking(const DILocation *Loc);
     // Explicit DebugLocKind, which always means a nullptr MDNode*.
     DILocAndCoverageTracking(DebugLocKind Kind)
-        : TrackingMDNodeRef(nullptr), Kind(Kind) {}
+        : TrackingMDNodeRef(nullptr),
+          DbgLocOrigin(Kind == DebugLocKind::Normal), Kind(Kind) {}
   };
   template <> struct simplify_type<DILocAndCoverageTracking> {
     using SimpleType = MDNode *;
@@ -187,6 +209,19 @@ namespace llvm {
 #endif // LLVM_ENABLE_DEBUGLOC_TRACKING_COVERAGE
     }
 
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+    const DbgLocOrigin::StackTracesTy &getOriginStackTraces() const {
+      return Loc.getOriginStackTraces();
+    }
+    DebugLoc getCopied() const {
+      DebugLoc NewDL = *this;
+      NewDL.Loc.addTrace();
+      return NewDL;
+    }
+#else
+    DebugLoc getCopied() const { return *this; }
+#endif
+
     /// Get the underlying \a DILocation.
     ///
     /// \pre !*this or \c isa<DILocation>(getAsMDNode()).

llvm/include/llvm/IR/Instruction.h

@@ -507,7 +507,7 @@ class Instruction : public User,
   LLVM_ABI bool extractProfTotalWeight(uint64_t &TotalVal) const;
 
   /// Set the debug location information for this instruction.
-  void setDebugLoc(DebugLoc Loc) { DbgLoc = std::move(Loc); }
+  void setDebugLoc(DebugLoc Loc) { DbgLoc = std::move(Loc).getCopied(); }
 
   /// Return the debug location for this node as a DebugLoc.
   const DebugLoc &getDebugLoc() const { return DbgLoc; }

llvm/lib/CodeGen/BranchFolding.cpp

@@ -42,6 +42,7 @@
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
+#include "llvm/Config/llvm-config.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/Function.h"
@@ -933,7 +934,13 @@ bool BranchFolder::TryTailMergeBlocks(MachineBasicBlock *SuccBB,
 
   // Sort by hash value so that blocks with identical end sequences sort
   // together.
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+  // If origin-tracking is enabled then MergePotentialElt is no longer a POD
+  // type, so we need std::sort instead.
+  std::sort(MergePotentials.begin(), MergePotentials.end());
+#else
   array_pod_sort(MergePotentials.begin(), MergePotentials.end());
+#endif
 
   // Walk through equivalence sets looking for actual exact matches.
   while (MergePotentials.size() > 1) {

llvm/lib/IR/DebugLoc.cpp

@@ -9,11 +9,35 @@
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/Config/llvm-config.h"
 #include "llvm/IR/DebugInfo.h"
+
+#if LLVM_ENABLE_DEBUGLOC_TRACKING_ORIGIN
+#include "llvm/Support/Signals.h"
+
+namespace llvm {
+DbgLocOrigin::DbgLocOrigin(bool ShouldCollectTrace) {
+  if (!ShouldCollectTrace)
+    return;
+  auto &[Depth, StackTrace] = StackTraces.emplace_back();
+  Depth = sys::getStackTrace(StackTrace);
+}
+void DbgLocOrigin::addTrace() {
+  // We only want to add new stacktraces if we already have one: addTrace exists
+  // to provide more context to how missing DebugLocs have propagated through
+  // the program, but by design if there is no existing stacktrace then we have
+  // decided not to track this DebugLoc as being "missing".
+  if (StackTraces.empty())
+    return;
+  auto &[Depth, StackTrace] = StackTraces.emplace_back();
+  Depth = sys::getStackTrace(StackTrace);
+}
+} // namespace llvm
+#endif
+
 using namespace llvm;
 
 #if LLVM_ENABLE_DEBUGLOC_TRACKING_COVERAGE
 DILocAndCoverageTracking::DILocAndCoverageTracking(const DILocation *L)
-    : TrackingMDNodeRef(const_cast<DILocation *>(L)),
+    : TrackingMDNodeRef(const_cast<DILocation *>(L)), DbgLocOrigin(!L),
       Kind(DebugLocKind::Normal) {}
 #endif // LLVM_ENABLE_DEBUGLOC_TRACKING_COVERAGE