Re-reapply: Recover debug intrinsics when killing duplicated/empty blocks

This reverts commit 636c93ed11a5f98b5c3ff88241460d61cb7785bb.

The original patch caused build failures on TSan buildbots. Commit 6ded69f294a9
fixes this issue by reducing the rate at which empty debug intrinsics
propagate, reducing the memory footprint and preventing a fatal spike.

2 files changed, 64 insertions, 22 deletions

diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
index aad9602..23f3854 100644
--- a/llvm/lib/Transforms/Utils/Local.cpp
+++ b/llvm/lib/Transforms/Utils/Local.cpp
@@ -505,15 +505,19 @@ void llvm::RecursivelyDeleteTriviallyDeadInstructions(
     I->eraseFromParent();
   }
 }
+void llvm::setDbgVariableUndef(DbgVariableIntrinsic *DVI) {
+  Value *DbgValue = DVI->getVariableLocation(false);
+  Value *Undef = UndefValue::get(DbgValue ? DbgValue->getType()
+                                          : Type::getInt1Ty(DVI->getContext()));
+  DVI->setOperand(
+      0, MetadataAsValue::get(DVI->getContext(), ValueAsMetadata::get(Undef)));
+}
 
 bool llvm::replaceDbgUsesWithUndef(Instruction *I) {
   SmallVector<DbgVariableIntrinsic *, 1> DbgUsers;
   findDbgUsers(DbgUsers, I);
-  for (auto *DII : DbgUsers) {
-    Value *Undef = UndefValue::get(I->getType());
-    DII->setOperand(0, MetadataAsValue::get(DII->getContext(),
-                                            ValueAsMetadata::get(Undef)));
-  }
+  for (auto *DII : DbgUsers)
+    setDbgVariableUndef(DII);
   return !DbgUsers.empty();
 }
 
@@ -1061,6 +1065,19 @@ bool llvm::TryToSimplifyUncondBranchFromEmptyBlock(BasicBlock *BB,
       assert(PN->use_empty() && "There shouldn't be any uses here!");
       PN->eraseFromParent();
     }
+    // If Succ has multiple predecessors, each debug intrinsic in BB may or may
+    // not be valid when we reach Succ, so the debug variable should be set
+    // undef since its value is unknown.
+    Instruction *DbgInsertPoint = Succ->getFirstNonPHI();
+    while (DbgInfoIntrinsic *DI = dyn_cast<DbgInfoIntrinsic>(&BB->front())) {
+      if (auto DVI = dyn_cast<DbgVariableIntrinsic>(DI)) {
+        if (!isa<DbgDeclareInst>(DVI))
+          setDbgVariableUndef(DVI);
+        DVI->moveBefore(DbgInsertPoint);
+      } else {
+        break;
+      }
+    }
   }
 
   // If the unconditional branch we replaced contains llvm.loop metadata, we
diff --git a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
index 222f8af..0f8a9b4 100644
--- a/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyCFG.cpp
@@ -13,6 +13,7 @@
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetOperations.h"
@@ -38,6 +39,7 @@
 #include "llvm/IR/ConstantRange.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
+#include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/IR/DerivedTypes.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalValue.h"
@@ -1250,14 +1252,38 @@ static bool HoistThenElseCodeToIf(BranchInst *BI,
 
   Instruction *I1 = &*BB1_Itr++, *I2 = &*BB2_Itr++;
   // Skip debug info if it is not identical.
-  DbgInfoIntrinsic *DBI1 = dyn_cast<DbgInfoIntrinsic>(I1);
-  DbgInfoIntrinsic *DBI2 = dyn_cast<DbgInfoIntrinsic>(I2);
-  if (!DBI1 || !DBI2 || !DBI1->isIdenticalToWhenDefined(DBI2)) {
-    while (isa<DbgInfoIntrinsic>(I1))
-      I1 = &*BB1_Itr++;
-    while (isa<DbgInfoIntrinsic>(I2))
-      I2 = &*BB2_Itr++;
-  }
+
+  // If the terminator instruction is hoisted, and any variable locations have
+  // non-identical debug intrinsics, then those variable locations must be set
+  // as undef.
+  // FIXME: If each block contains identical debug variable intrinsics in a
+  // different order, they will be considered non-identical and be dropped.
+  MapVector<DebugVariable, DbgVariableIntrinsic *> UndefDVIs;
+
+  auto SkipDbgInfo = [&UndefDVIs](Instruction *&I,
+                                  BasicBlock::iterator &BB_Itr) {
+    while (isa<DbgInfoIntrinsic>(I)) {
+      if (DbgVariableIntrinsic *DVI = dyn_cast<DbgVariableIntrinsic>(I))
+        UndefDVIs.insert(
+            {DebugVariable(DVI->getVariable(), DVI->getExpression(),
+                           DVI->getDebugLoc()->getInlinedAt()),
+             DVI});
+      I = &*BB_Itr++;
+    }
+  };
+
+  auto SkipNonIdenticalDbgInfo =
+      [&BB1_Itr, &BB2_Itr, &SkipDbgInfo](Instruction *&I1, Instruction *&I2) {
+        DbgInfoIntrinsic *DBI1 = dyn_cast<DbgInfoIntrinsic>(I1);
+        DbgInfoIntrinsic *DBI2 = dyn_cast<DbgInfoIntrinsic>(I2);
+        if (!DBI1 || !DBI2 || !DBI1->isIdenticalToWhenDefined(DBI2)) {
+          SkipDbgInfo(I1, BB1_Itr);
+          SkipDbgInfo(I2, BB2_Itr);
+        }
+      };
+
+  SkipNonIdenticalDbgInfo(I1, I2);
+
   // FIXME: Can we define a safety predicate for CallBr?
   if (isa<PHINode>(I1) || !I1->isIdenticalToWhenDefined(I2) ||
       (isa<InvokeInst>(I1) && !isSafeToHoistInvoke(BB1, BB2, I1, I2)) ||
@@ -1330,15 +1356,7 @@ static bool HoistThenElseCodeToIf(BranchInst *BI,
 
     I1 = &*BB1_Itr++;
     I2 = &*BB2_Itr++;
-    // Skip debug info if it is not identical.
-    DbgInfoIntrinsic *DBI1 = dyn_cast<DbgInfoIntrinsic>(I1);
-    DbgInfoIntrinsic *DBI2 = dyn_cast<DbgInfoIntrinsic>(I2);
-    if (!DBI1 || !DBI2 || !DBI1->isIdenticalToWhenDefined(DBI2)) {
-      while (isa<DbgInfoIntrinsic>(I1))
-        I1 = &*BB1_Itr++;
-      while (isa<DbgInfoIntrinsic>(I2))
-        I2 = &*BB2_Itr++;
-    }
+    SkipNonIdenticalDbgInfo(I1, I2);
   } while (I1->isIdenticalToWhenDefined(I2));
 
   return true;
@@ -1374,6 +1392,13 @@ HoistTerminator:
   }
 
   // Okay, it is safe to hoist the terminator.
+  for (auto DIVariableInst : UndefDVIs) {
+    DbgVariableIntrinsic *DVI = DIVariableInst.second;
+    DVI->moveBefore(BI);
+    if (DVI->getVariableLocation())
+      setDbgVariableUndef(DVI);
+  }
+
   Instruction *NT = I1->clone();
   BIParent->getInstList().insert(BI->getIterator(), NT);
   if (!NT->getType()->isVoidTy()) {