[MachineDebugify] Insert synthetic DBG_VALUE instructions

Summary:
Teach MachineDebugify how to insert DBG_VALUE instructions.  This can
help find bugs causing CodeGen differences when debug info is present.
DBG_VALUE instructions are only emitted when -debugify-level is set to
locations+variables.

There is essentially no attempt made to match up DBG_VALUE register
operands with the local variables they ought to correspond to. I'm not
sure how to improve the situation. In some cases (MachineMemOperand?)
it's possible to find the IR instruction a MachineInstr corresponds to,
but in general this seems to call for "undoing" the work done by ISel.

Reviewers: dsanders, aprantl

Subscribers: hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D78135

1 files changed, 87 insertions, 3 deletions

diff --git a/llvm/lib/CodeGen/MachineDebugify.cpp b/llvm/lib/CodeGen/MachineDebugify.cpp
index bc607ca..bf57ec0 100644
--- a/llvm/lib/CodeGen/MachineDebugify.cpp
+++ b/llvm/lib/CodeGen/MachineDebugify.cpp
@@ -7,16 +7,23 @@
 //===----------------------------------------------------------------------===//
 ///
 /// \file This pass attaches synthetic debug info to everything. It can be used
-/// to create targeted tests for debug info preservation.
+/// to create targeted tests for debug info preservation, or test for CodeGen
+/// differences with vs. without debug info.
 ///
 /// This isn't intended to have feature parity with Debugify.
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/Passes.h"
+#include "llvm/CodeGen/TargetInstrInfo.h"
+#include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/DIBuilder.h"
 #include "llvm/IR/DebugInfo.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Transforms/Utils/Debugify.h"
 
@@ -31,13 +38,15 @@ bool applyDebugifyMetadataToMachineFunction(MachineModuleInfo &MMI,
   if (!MaybeMF)
     return false;
   MachineFunction &MF = *MaybeMF;
+  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
 
   DISubprogram *SP = F.getSubprogram();
   assert(SP && "IR Debugify just created it?");
 
-  LLVMContext &Ctx = F.getParent()->getContext();
-  unsigned NextLine = SP->getLine();
+  Module &M = *F.getParent();
+  LLVMContext &Ctx = M.getContext();
 
+  unsigned NextLine = SP->getLine();
   for (MachineBasicBlock &MBB : MF) {
     for (MachineInstr &MI : MBB) {
       // This will likely emit line numbers beyond the end of the imagined
@@ -48,6 +57,81 @@ bool applyDebugifyMetadataToMachineFunction(MachineModuleInfo &MMI,
     }
   }
 
+  // Find local variables defined by debugify. No attempt is made to match up
+  // MIR-level regs to the 'correct' IR-level variables: there isn't a simple
+  // way to do that, and it isn't necessary to find interesting CodeGen bugs.
+  // Instead, simply keep track of one variable per line. Later, we can insert
+  // DBG_VALUE insts that point to these local variables. Emitting DBG_VALUEs
+  // which cover a wide range of lines can help stress the debug info passes:
+  // if we can't do that, fall back to using the local variable which precedes
+  // all the others.
+  Function *DbgValF = M.getFunction("llvm.dbg.value");
+  DbgValueInst *EarliestDVI = nullptr;
+  DenseMap<unsigned, DILocalVariable *> Line2Var;
+  DIExpression *Expr = nullptr;
+  if (DbgValF) {
+    for (const Use &U : DbgValF->uses()) {
+      auto *DVI = dyn_cast<DbgValueInst>(U.getUser());
+      if (!DVI || DVI->getFunction() != &F)
+        continue;
+      unsigned Line = DVI->getDebugLoc().getLine();
+      assert(Line != 0 && "debugify should not insert line 0 locations");
+      Line2Var[Line] = DVI->getVariable();
+      if (!EarliestDVI || Line < EarliestDVI->getDebugLoc().getLine())
+        EarliestDVI = DVI;
+      Expr = DVI->getExpression();
+    }
+  }
+  if (Line2Var.empty())
+    return true;
+
+  // Now, try to insert a DBG_VALUE instruction after each real instruction.
+  // Do this by introducing debug uses of each register definition. If that is
+  // not possible (e.g. we have a phi or a meta instruction), emit a constant.
+  uint64_t NextImm = 0;
+  const MCInstrDesc &DbgValDesc = TII.get(TargetOpcode::DBG_VALUE);
+  for (MachineBasicBlock &MBB : MF) {
+    MachineBasicBlock::iterator FirstNonPHIIt = MBB.getFirstNonPHI();
+    for (auto I = MBB.begin(), E = MBB.end(); I != E; ) {
+      MachineInstr &MI = *I;
+      ++I;
+
+      // `I` may point to a DBG_VALUE created in the previous loop iteration.
+      if (MI.isDebugInstr())
+        continue;
+
+      // It's not allowed to insert DBG_VALUEs after a terminator.
+      if (MI.isTerminator())
+        continue;
+
+      // Find a suitable insertion point for the DBG_VALUE.
+      auto InsertBeforeIt = MI.isPHI() ? FirstNonPHIIt : I;
+
+      // Find a suitable local variable for the DBG_VALUE.
+      unsigned Line = MI.getDebugLoc().getLine();
+      if (!Line2Var.count(Line))
+        Line = EarliestDVI->getDebugLoc().getLine();
+      DILocalVariable *LocalVar = Line2Var[Line];
+      assert(LocalVar && "No variable for current line?");
+
+      // Emit DBG_VALUEs for register definitions.
+      SmallVector<MachineOperand *, 4> RegDefs;
+      for (MachineOperand &MO : MI.operands())
+        if (MO.isReg() && MO.isDef() && MO.getReg())
+          RegDefs.push_back(&MO);
+      for (MachineOperand *MO : RegDefs)
+        BuildMI(MBB, InsertBeforeIt, MI.getDebugLoc(), DbgValDesc,
+                /*IsIndirect=*/false, *MO, LocalVar, Expr);
+
+      // OK, failing that, emit a constant DBG_VALUE.
+      if (RegDefs.empty()) {
+        auto ImmOp = MachineOperand::CreateImm(NextImm++);
+        BuildMI(MBB, InsertBeforeIt, MI.getDebugLoc(), DbgValDesc,
+                /*IsIndirect=*/false, ImmOp, LocalVar, Expr);
+      }
+    }
+  }
+
   return true;
 }