[GVN] Restrict equality propagation for pointers

UsmanNadeem · UsmanNadeem · commit f4ebdf067e22 · 2024-02-26T13:52:57.000-08:00
Reviving https://reviews.llvm.org/D143129 This patch does the following: Adds the following functions: - replaceDominatedUsesWithIf() that takes a callback. - canReplacePointersIfEqual(...) returns true if the underlying object is the same, and for null and const dereferencable pointer replacements. - canReplacePointersIfEqualInUse(...) returns true for the above as well as if the use is in icmp/ptrtoint or phi/selects feeding into them. Updates GVN using the functions above so that the pointer replacements are only made using the above API. Change-Id: I4927ea452734458be028854ef0e5cbcd81955910
diff --git a/llvm/include/llvm/Analysis/Loads.h b/llvm/include/llvm/Analysis/Loads.h
@@ -173,14 +173,15 @@ Value *findAvailablePtrLoadStore(const MemoryLocation &Loc, Type *AccessTy,
                                  unsigned MaxInstsToScan, BatchAAResults *AA,
                                  bool *IsLoadCSE, unsigned *NumScanedInst);
 
-/// Returns true if a pointer value \p A can be replace with another pointer
-/// value \B if they are deemed equal through some means (e.g. information from
+/// Returns true if a pointer value \p From can be replaced with another pointer
+/// value \To if they are deemed equal through some means (e.g. information from
 /// conditions).
-/// NOTE: the current implementations is incomplete and unsound. It does not
-/// reject all invalid cases yet, but will be made stricter in the future. In
-/// particular this means returning true means unknown if replacement is safe.
-bool canReplacePointersIfEqual(Value *A, Value *B, const DataLayout &DL,
-                               Instruction *CtxI);
+/// NOTE: The current implementation allows replacement in Icmp and PtrToInt
+/// instructions, as well as when we are replacing with a null pointer.
+/// Additionally it also allows replacement of pointers when both pointers have
+/// the same underlying object.
+bool canReplacePointersIfEqual(const Value *From, const Value *To);
+bool canReplacePointersInUseIfEqual(const Use &U, const Value *To);
 }
 
 #endif
diff --git a/llvm/include/llvm/Transforms/Utils/Local.h b/llvm/include/llvm/Transforms/Utils/Local.h
@@ -432,6 +432,18 @@ unsigned replaceDominatedUsesWith(Value *From, Value *To, DominatorTree &DT,
 /// the end of the given BasicBlock. Returns the number of replacements made.
 unsigned replaceDominatedUsesWith(Value *From, Value *To, DominatorTree &DT,
                                   const BasicBlock *BB);
+/// Replace each use of 'From' with 'To' if that use is dominated by
+/// the given edge and the callback ShouldReplace returns true. Returns the
+/// number of replacements made.
+unsigned replaceDominatedUsesWithIf(
+    Value *From, Value *To, DominatorTree &DT, const BasicBlockEdge &Edge,
+    function_ref<bool(const Use &U, const Value *To)> ShouldReplace);
+/// Replace each use of 'From' with 'To' if that use is dominated by
+/// the end of the given BasicBlock and the callback ShouldReplace returns true.
+/// Returns the number of replacements made.
+unsigned replaceDominatedUsesWithIf(
+    Value *From, Value *To, DominatorTree &DT, const BasicBlock *BB,
+    function_ref<bool(const Use &U, const Value *To)> ShouldReplace);
 
 /// Return true if this call calls a gc leaf function.
 ///
diff --git a/llvm/lib/Analysis/Loads.cpp b/llvm/lib/Analysis/Loads.cpp
@@ -708,22 +708,66 @@ Value *llvm::FindAvailableLoadedValue(LoadInst *Load, BatchAAResults &AA,
   return Available;
 }
 
-bool llvm::canReplacePointersIfEqual(Value *A, Value *B, const DataLayout &DL,
-                                     Instruction *CtxI) {
-  Type *Ty = A->getType();
-  assert(Ty == B->getType() && Ty->isPointerTy() &&
-         "values must have matching pointer types");
-
-  // NOTE: The checks in the function are incomplete and currently miss illegal
-  // cases! The current implementation is a starting point and the
-  // implementation should be made stricter over time.
-  if (auto *C = dyn_cast<Constant>(B)) {
-    // Do not allow replacing a pointer with a constant pointer, unless it is
-    // either null or at least one byte is dereferenceable.
-    APInt OneByte(DL.getPointerTypeSizeInBits(Ty), 1);
-    return C->isNullValue() ||
-           isDereferenceableAndAlignedPointer(B, Align(1), OneByte, DL, CtxI);
-  }
+// Returns true if a use is either in an ICmp/PtrToInt or a Phi/Select that only
+// feeds into them.
+static bool isPointerUseReplacable(const Use &U, int MaxLookup = 6) {
+  if (MaxLookup == 0)
+    return false;
+
+  const User *User = U.getUser();
+  if (isa<ICmpInst>(User))
+    return true;
+  if (isa<PtrToIntInst>(User))
+    return true;
+  if (isa<PHINode, SelectInst>(User) &&
+      all_of(User->uses(), [&](const Use &Use) {
+        return isPointerUseReplacable(Use, MaxLookup - 1);
+      }))
+    return true;
+
+  return false;
+}
+
+static const DataLayout &getDLFromVal(const Value *V) {
+  if (const Argument *A = dyn_cast<Argument>(V))
+    return A->getParent()->getParent()->getDataLayout();
+  if (const Instruction *I = dyn_cast<Instruction>(V))
+    return I->getModule()->getDataLayout();
+  if (const GlobalValue *GV = dyn_cast<GlobalValue>(V))
+    return GV->getParent()->getDataLayout();
+  llvm_unreachable("Unknown Value type");
+}
+
+// Returns true if `To` is a null pointer, constant dereferenceable pointer or
+// both pointers have the same underlying objects.
+static bool isPointerAlwaysReplacable(const Value *From, const Value *To) {
+  if (isa<ConstantPointerNull>(To))
+    return true;
+  if (isa<Constant>(To) &&
+      isDereferenceablePointer(To, Type::getInt8Ty(To->getContext()),
+                               getDLFromVal(From)))
+    return true;
+  if (getUnderlyingObject(From) == getUnderlyingObject(To))
+    return true;
+  return false;
+}
+
+bool llvm::canReplacePointersInUseIfEqual(const Use &U, const Value *To) {
+  assert(U->getType() == To->getType() && "values must have matching types");
+  // Not a pointer, just return true.
+  if (!To->getType()->isPointerTy())
+    return true;
+
+  if (isPointerAlwaysReplacable(&*U, To))
+    return true;
+  return isPointerUseReplacable(U);
+}
+
+bool llvm::canReplacePointersIfEqual(const Value *From, const Value *To) {
+  assert(From->getType() == To->getType() && "values must have matching types");
+  // Not a pointer, just return true.
+  if (!From->getType()->isPointerTy())
+    return true;
 
-  return true;
+  return isPointerAlwaysReplacable(From, To);
 }
diff --git a/llvm/lib/Transforms/Scalar/GVN.cpp b/llvm/lib/Transforms/Scalar/GVN.cpp
@@ -33,6 +33,7 @@
 #include "llvm/Analysis/GlobalsModRef.h"
 #include "llvm/Analysis/InstructionPrecedenceTracking.h"
 #include "llvm/Analysis/InstructionSimplify.h"
+#include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Analysis/MemoryDependenceAnalysis.h"
@@ -2443,7 +2444,8 @@ bool GVNPass::propagateEquality(Value *LHS, Value *RHS,
     // using the leader table is about compiling faster, not optimizing better).
     // The leader table only tracks basic blocks, not edges. Only add to if we
     // have the simple case where the edge dominates the end.
-    if (RootDominatesEnd && !isa<Instruction>(RHS))
+    if (RootDominatesEnd && !isa<Instruction>(RHS) &&
+        canReplacePointersIfEqual(LHS, RHS))
       addToLeaderTable(LVN, RHS, Root.getEnd());
 
     // Replace all occurrences of 'LHS' with 'RHS' everywhere in the scope.  As
@@ -2452,14 +2454,18 @@ bool GVNPass::propagateEquality(Value *LHS, Value *RHS,
     if (!LHS->hasOneUse()) {
       unsigned NumReplacements =
           DominatesByEdge
-              ? replaceDominatedUsesWith(LHS, RHS, *DT, Root)
-              : replaceDominatedUsesWith(LHS, RHS, *DT, Root.getStart());
-
-      Changed |= NumReplacements > 0;
-      NumGVNEqProp += NumReplacements;
-      // Cached information for anything that uses LHS will be invalid.
-      if (MD)
-        MD->invalidateCachedPointerInfo(LHS);
+              ? replaceDominatedUsesWithIf(LHS, RHS, *DT, Root,
+                                           canReplacePointersInUseIfEqual)
+              : replaceDominatedUsesWithIf(LHS, RHS, *DT, Root.getStart(),
+                                           canReplacePointersInUseIfEqual);
+
+      if (NumReplacements > 0) {
+        Changed = true;
+        NumGVNEqProp += NumReplacements;
+        // Cached information for anything that uses LHS will be invalid.
+        if (MD)
+          MD->invalidateCachedPointerInfo(LHS);
+      }
     }
 
     // Now try to deduce additional equalities from this one. For example, if
diff --git a/llvm/lib/Transforms/Utils/Local.cpp b/llvm/lib/Transforms/Utils/Local.cpp
@@ -3395,15 +3395,18 @@ void llvm::patchReplacementInstruction(Instruction *I, Value *Repl) {
 }
 
 template <typename RootType, typename DominatesFn>
-static unsigned replaceDominatedUsesWith(Value *From, Value *To,
-                                         const RootType &Root,
-                                         const DominatesFn &Dominates) {
+static unsigned replaceDominatedUsesWith(
+    Value *From, Value *To, const RootType &Root, const DominatesFn &Dominates,
+    std::optional<function_ref<bool(const Use &U, const Value *To)>>
+        ShouldReplace) {
   assert(From->getType() == To->getType());
 
   unsigned Count = 0;
   for (Use &U : llvm::make_early_inc_range(From->uses())) {
     if (!Dominates(Root, U))
       continue;
+    if (ShouldReplace.has_value() && !ShouldReplace.value()(U, To))
+      continue;
     LLVM_DEBUG(dbgs() << "Replace dominated use of '";
                From->printAsOperand(dbgs());
                dbgs() << "' with " << *To << " in " << *U.getUser() << "\n");
@@ -3434,7 +3437,7 @@ unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
   auto Dominates = [&DT](const BasicBlockEdge &Root, const Use &U) {
     return DT.dominates(Root, U);
   };
-  return ::replaceDominatedUsesWith(From, To, Root, Dominates);
+  return ::replaceDominatedUsesWith(From, To, Root, Dominates, std::nullopt);
 }
 
 unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
@@ -3443,9 +3446,26 @@ unsigned llvm::replaceDominatedUsesWith(Value *From, Value *To,
   auto Dominates = [&DT](const BasicBlock *BB, const Use &U) {
     return DT.dominates(BB, U);
   };
-  return ::replaceDominatedUsesWith(From, To, BB, Dominates);
+  return ::replaceDominatedUsesWith(From, To, BB, Dominates, std::nullopt);
+}
+
+unsigned llvm::replaceDominatedUsesWithIf(
+    Value *From, Value *To, DominatorTree &DT, const BasicBlockEdge &Root,
+    function_ref<bool(const Use &U, const Value *To)> ShouldReplace) {
+  auto Dominates = [&DT](const BasicBlockEdge &Root, const Use &U) {
+    return DT.dominates(Root, U);
+  };
+  return ::replaceDominatedUsesWith(From, To, Root, Dominates, ShouldReplace);
 }
 
+unsigned llvm::replaceDominatedUsesWithIf(
+    Value *From, Value *To, DominatorTree &DT, const BasicBlock *BB,
+    function_ref<bool(const Use &U, const Value *To)> ShouldReplace) {
+  auto Dominates = [&DT](const BasicBlock *BB, const Use &U) {
+    return DT.dominates(BB, U);
+  };
+  return ::replaceDominatedUsesWith(From, To, BB, Dominates, ShouldReplace);
+}
 bool llvm::callsGCLeafFunction(const CallBase *Call,
                                const TargetLibraryInfo &TLI) {
   // Check if the function is specifically marked as a gc leaf function.
diff --git a/llvm/test/Transforms/GVN/condprop.ll b/llvm/test/Transforms/GVN/condprop.ll
diff --git a/llvm/unittests/Analysis/LoadsTest.cpp b/llvm/unittests/Analysis/LoadsTest.cpp
