From b3d10920e13446efaebb201612328cf0644709f8 Mon Sep 17 00:00:00 2001
From: Fangrui Song <maskray@google.com>
Date: Wed, 10 Jun 2020 22:32:43 -0700
Subject: [PATCH] Restore part of D80450 [CUDA][HIP] Fix implicit HD function
 resolution

The "if (S.getLangOpts().CUDA && Cand1.Function && Cand2.Function) {"
part is known to be problematic but the root cause isn't clear yet.
---
 clang/include/clang/Sema/Sema.h |  2 ++
 clang/lib/Sema/SemaCUDA.cpp     | 14 ++++++++++++++
 clang/lib/Sema/SemaOverload.cpp | 37 ++++++++++++++++++++++++-------------
 3 files changed, 40 insertions(+), 13 deletions(-)

diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h
index e7e6dc4..6f074fb 100644
--- a/clang/include/clang/Sema/Sema.h
+++ b/clang/include/clang/Sema/Sema.h
@@ -11698,6 +11698,8 @@ public:
     return IdentifyCUDATarget(dyn_cast<FunctionDecl>(CurContext));
   }
 
+  static bool isCUDAImplicitHostDeviceFunction(const FunctionDecl *D);
+
   // CUDA function call preference. Must be ordered numerically from
   // worst to best.
   enum CUDAFunctionPreference {
diff --git a/clang/lib/Sema/SemaCUDA.cpp b/clang/lib/Sema/SemaCUDA.cpp
index 5d6c151..f54d97a 100644
--- a/clang/lib/Sema/SemaCUDA.cpp
+++ b/clang/lib/Sema/SemaCUDA.cpp
@@ -211,6 +211,20 @@ Sema::IdentifyCUDAPreference(const FunctionDecl *Caller,
   llvm_unreachable("All cases should've been handled by now.");
 }
 
+template <typename AttrT> static bool hasImplicitAttr(const FunctionDecl *D) {
+  if (!D)
+    return false;
+  if (auto *A = D->getAttr<AttrT>())
+    return A->isImplicit();
+  return D->isImplicit();
+}
+
+bool Sema::isCUDAImplicitHostDeviceFunction(const FunctionDecl *D) {
+  bool IsImplicitDevAttr = hasImplicitAttr<CUDADeviceAttr>(D);
+  bool IsImplicitHostAttr = hasImplicitAttr<CUDAHostAttr>(D);
+  return IsImplicitDevAttr && IsImplicitHostAttr;
+}
+
 void Sema::EraseUnwantedCUDAMatches(
     const FunctionDecl *Caller,
     SmallVectorImpl<std::pair<DeclAccessPair, FunctionDecl *>> &Matches) {
diff --git a/clang/lib/Sema/SemaOverload.cpp b/clang/lib/Sema/SemaOverload.cpp
index 319a4b5..e57264d 100644
--- a/clang/lib/Sema/SemaOverload.cpp
+++ b/clang/lib/Sema/SemaOverload.cpp
@@ -9397,16 +9397,22 @@ static Comparison compareEnableIfAttrs(const Sema &S, const FunctionDecl *Cand1,
   return Comparison::Equal;
 }
 
-static bool isBetterMultiversionCandidate(const OverloadCandidate &Cand1,
-                                          const OverloadCandidate &Cand2) {
+static Comparison
+isBetterMultiversionCandidate(const OverloadCandidate &Cand1,
+                              const OverloadCandidate &Cand2) {
   if (!Cand1.Function || !Cand1.Function->isMultiVersion() || !Cand2.Function ||
       !Cand2.Function->isMultiVersion())
-    return false;
+    return Comparison::Equal;
 
-  // If Cand1 is invalid, it cannot be a better match, if Cand2 is invalid, this
-  // is obviously better.
-  if (Cand1.Function->isInvalidDecl()) return false;
-  if (Cand2.Function->isInvalidDecl()) return true;
+  // If both are invalid, they are equal. If one of them is invalid, the other
+  // is better.
+  if (Cand1.Function->isInvalidDecl()) {
+    if (Cand2.Function->isInvalidDecl())
+      return Comparison::Equal;
+    return Comparison::Worse;
+  }
+  if (Cand2.Function->isInvalidDecl())
+    return Comparison::Better;
 
   // If this is a cpu_dispatch/cpu_specific multiversion situation, prefer
   // cpu_dispatch, else arbitrarily based on the identifiers.
@@ -9416,16 +9422,18 @@ static bool isBetterMultiversionCandidate(const OverloadCandidate &Cand1,
   const auto *Cand2CPUSpec = Cand2.Function->getAttr<CPUSpecificAttr>();
 
   if (!Cand1CPUDisp && !Cand2CPUDisp && !Cand1CPUSpec && !Cand2CPUSpec)
-    return false;
+    return Comparison::Equal;
 
   if (Cand1CPUDisp && !Cand2CPUDisp)
-    return true;
+    return Comparison::Better;
   if (Cand2CPUDisp && !Cand1CPUDisp)
-    return false;
+    return Comparison::Worse;
 
   if (Cand1CPUSpec && Cand2CPUSpec) {
     if (Cand1CPUSpec->cpus_size() != Cand2CPUSpec->cpus_size())
-      return Cand1CPUSpec->cpus_size() < Cand2CPUSpec->cpus_size();
+      return Cand1CPUSpec->cpus_size() < Cand2CPUSpec->cpus_size()
+                 ? Comparison::Better
+                 : Comparison::Worse;
 
     std::pair<CPUSpecificAttr::cpus_iterator, CPUSpecificAttr::cpus_iterator>
         FirstDiff = std::mismatch(
@@ -9438,7 +9446,9 @@ static bool isBetterMultiversionCandidate(const OverloadCandidate &Cand1,
     assert(FirstDiff.first != Cand1CPUSpec->cpus_end() &&
            "Two different cpu-specific versions should not have the same "
            "identifier list, otherwise they'd be the same decl!");
-    return (*FirstDiff.first)->getName() < (*FirstDiff.second)->getName();
+    return (*FirstDiff.first)->getName() < (*FirstDiff.second)->getName()
+               ? Comparison::Better
+               : Comparison::Worse;
   }
   llvm_unreachable("No way to get here unless both had cpu_dispatch");
 }
@@ -9745,7 +9755,8 @@ bool clang::isBetterOverloadCandidate(
   if (HasPS1 != HasPS2 && HasPS1)
     return true;
 
-  return isBetterMultiversionCandidate(Cand1, Cand2);
+  Comparison MV = isBetterMultiversionCandidate(Cand1, Cand2);
+  return MV == Comparison::Better;
 }
 
 /// Determine whether two declarations are "equivalent" for the purposes of
-- 
2.7.4