[Clang] Drop functions with incompatible target-features when using mlink-builtin-bitcode

[jmmartinez]

Moved into https://github.com/llvm/llvm-project/pull/65737

clang/lib/CodeGen/CGCall.h

public:
 
   bool isNull() const { return !Addr.isValid(); }
   bool isVolatile() const { return IsVolatile; }
   Address getValue() const { return Addr; }
   bool isUnused() const { return IsUnused; }
   bool isExternallyDestructed() const { return IsExternallyDestructed; }
 };
 
+/// If \p F "target-features" are incompatible with the \p TargetOpts features,
+/// it is correct to drop the function. \return true if \p F is dropped
+bool dropFunctionWithIncompatibleAttributes(llvm::Function &F,
+                                            const TargetOptions &TargetOpts);
+
 /// Helper to add attributes to \p F according to the CodeGenOptions and
 /// LangOptions without requiring a CodeGenModule to be constructed.
 void mergeDefaultFunctionDefinitionAttributes(llvm::Function &F,
                                               const CodeGenOptions &CodeGenOpts,
                                               const LangOptions &LangOpts,
                                               const TargetOptions &TargetOpts,
                                               bool WillInternalize);
 

clang/lib/CodeGen/CGCall.cpp

void clang::CodeGen::mergeDefaultFunctionDefinitionAttributes(
     llvm::Function &F, const CodeGenOptions &CodeGenOpts,
     const LangOptions &LangOpts, const TargetOptions &TargetOpts,
     bool WillInternalize) {
 
   ::mergeDefaultFunctionDefinitionAttributes(F, CodeGenOpts, LangOpts,
                                              TargetOpts, WillInternalize);
 }
 
+bool CodeGen::dropFunctionWithIncompatibleAttributes(
+    llvm::Function &F, const TargetOptions &TargetOpts) {
+  auto FFeatures = F.getFnAttribute("target-features");
+  if (!FFeatures.isValid())
+    return false;
+
+  const auto &TFeatures = TargetOpts.FeatureMap;
+  for (StringRef Feature : llvm::split(FFeatures.getValueAsString(), ',')) {
+    bool EnabledForFunc = Feature[0] == '+';
+    StringRef Name = Feature.substr(1);
+    auto TEntry = TFeatures.find(Name);
+    if (TEntry != TFeatures.end() && TEntry->second != EnabledForFunc) {
+      F.replaceAllUsesWith(llvm::ConstantPointerNull::get(F.getType()));
+      F.eraseFromParent();
+      return true;
+    }
+  }
+  return false;
+}
+
 void CodeGenModule::getTrivialDefaultFunctionAttributes(
     StringRef Name, bool HasOptnone, bool AttrOnCallSite,
     llvm::AttrBuilder &FuncAttrs) {
   ::getTrivialDefaultFunctionAttributes(Name, HasOptnone, getCodeGenOpts(),
                                         getLangOpts(), AttrOnCallSite,
                                         FuncAttrs);
 }
 

clang/lib/CodeGen/CodeGenAction.cpp

void HandleInterestingDecl(DeclGroupRef D) override {
         HandleTopLevelDecl(D);
     }
 
     // Links each entry in LinkModules into our module.  Returns true on error.
     bool LinkInModules(llvm::Module *M) {
       for (auto &LM : LinkModules) {
         assert(LM.Module && "LinkModule does not actually have a module");
         if (LM.PropagateAttrs)
-          for (Function &F : *LM.Module) {
+          for (Function &F : llvm::make_early_inc_range(*LM.Module)) {
             // Skip intrinsics. Keep consistent with how intrinsics are created
             // in LLVM IR.
             if (F.isIntrinsic())
               continue;
+            if (CodeGen::dropFunctionWithIncompatibleAttributes(F, TargetOpts))
+              continue;
             CodeGen::mergeDefaultFunctionDefinitionAttributes(
                 F, CodeGenOpts, LangOpts, TargetOpts, LM.Internalize);
           }
 
         CurLinkModule = LM.Module.get();
 
         bool Err;
         if (LM.Internalize) {

clang/test/CodeGen/link-builtin-bitcode.c

 // Build two version of the bitcode library, one with a target-cpu set and one without
 // RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx803 -DBITCODE -emit-llvm-bc -o %t-lib.bc %s
 // RUN: %clang_cc1 -triple amdgcn-- -DBITCODE -emit-llvm-bc -o %t-lib.no-cpu.bc %s
 
 // RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx90a -emit-llvm-bc -o %t.bc %s
 // RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx90a -emit-llvm \
-// RUN:   -mlink-builtin-bitcode %t-lib.bc -o - %t.bc | FileCheck %s --check-prefixes=CHECK,CPU
+// RUN:   -mlink-builtin-bitcode %t-lib.bc -o - %t.bc | FileCheck %s
 
 // RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx90a -emit-llvm-bc -o %t.bc %s
 // RUN: %clang_cc1 -triple amdgcn-- -target-cpu gfx90a -emit-llvm \
-// RUN:   -mlink-builtin-bitcode %t-lib.no-cpu.bc -o - %t.bc | FileCheck %s --check-prefixes=CHECK,NOCPU
+// RUN:   -mlink-builtin-bitcode %t-lib.no-cpu.bc -o - %t.bc | FileCheck %s
 
 #ifdef BITCODE
 int no_attr(void) { return 42; }
 int __attribute__((target("gfx8-insts"))) attr_in_target(void) { return 42; }
 int __attribute__((target("extended-image-insts"))) attr_not_in_target(void) { return 42; }
 int __attribute__((target("no-gfx9-insts"))) attr_incompatible(void) { return 42; }
 int x = 12;
 #endif

 // CHECK-SAME: () #[[ATTR_COMPATIBLE:[0-9]+]] {
 
 // CHECK-LABEL: define internal i32 @attr_in_target
 // CHECK-SAME: () #[[ATTR_COMPATIBLE:[0-9]+]] {
 
 // CHECK-LABEL: define internal i32 @attr_not_in_target
 // CHECK-SAME: () #[[ATTR_EXTEND:[0-9]+]] {
 
-// CHECK-LABEL: @attr_incompatible
-// CHECK-SAME: () #[[ATTR_INCOMPATIBLE:[0-9]+]] {
+// CHECK-NOT: @attr_incompatible
 
 // CHECK: attributes #[[ATTR_BAR]] = { noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" }
 // CHECK: attributes #[[ATTR_COMPATIBLE]] = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64" }
 // CHECK: attributes #[[ATTR_EXTEND]] = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+atomic-buffer-global-pk-add-f16-insts,+atomic-fadd-rtn-insts,+ci-insts,+dl-insts,+dot1-insts,+dot10-insts,+dot2-insts,+dot3-insts,+dot4-insts,+dot5-insts,+dot6-insts,+dot7-insts,+dpp,+gfx8-insts,+gfx9-insts,+gfx90a-insts,+gws,+image-insts,+mai-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,+extended-image-insts" }
-// CPU: attributes #[[ATTR_INCOMPATIBLE]] = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx90a" "target-features"="+16-bit-insts,+ci-insts,+dpp,+gfx8-insts,+s-memrealtime,+s-memtime-inst,+wavefrontsize64,-gfx9-insts" }
-// NOCPU: attributes #[[ATTR_INCOMPATIBLE]] = { convergent noinline nounwind optnone "no-trapping-math"="true" "stack-protector-buffer-size"="8" "target-cpu"="gfx90a" "target-features"="-gfx9-insts" }