Preserve blockaddress use edges in the module splitter.

[eugenis]

Summary

"blockaddress" can not apply to an external function. All
blockaddress constant uses must belong to the same module as the
definition of the target function.

[pcc]

lib/Transforms/Utils/SplitModule.cpp

125

I don't think you need the PreserveLocals && part here, as the RHS can only be true if the LHS is true.

[eugenis]

lib/Transforms/Utils/SplitModule.cpp

125

good point, removed

[pcc]

LGTM

[eugenis]

r265061

lib/Transforms/Utils/SplitModule.cpp

 
 #define DEBUG_TYPE "split-module"
 
 #include "llvm/Transforms/Utils/SplitModule.h"
 #include "llvm/ADT/EquivalenceClasses.h"
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/SetVector.h"
+#include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalObject.h"
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/IR/Module.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/MD5.h"
static void addNonConstUser(ClusterMapType &GVtoClusterMap,
   } else if (isa<GlobalAlias>(U) || isa<Function>(U) ||
              isa<GlobalVariable>(U)) {
     GVtoClusterMap.unionSets(GV, cast<GlobalValue>(U));
   } else {
     llvm_unreachable("Underimplemented use case");
   }
 }
 
+// Adds all GlobalValue users of V to the same cluster as GV.
+static void addAllGlobalValueUsers(ClusterMapType &GVtoClusterMap,
+                                   const GlobalValue *GV, const Value *V) {
+  for (auto *U : V->users()) {
+    SmallVector<const User *, 4> Worklist;
+    Worklist.push_back(U);
+    while (!Worklist.empty()) {
+      const User *UU = Worklist.pop_back_val();
+      // For each constant that is not a GV (a pure const) recurse.
+      if (isa<Constant>(UU) && !isa<GlobalValue>(UU)) {
+        Worklist.append(UU->user_begin(), UU->user_end());
+        continue;
+      }
+      addNonConstUser(GVtoClusterMap, GV, UU);
+    }
+  }
+}
+
 // Find partitions for module in the way that no locals need to be
 // globalized.
 // Try to balance pack those partitions into N files since this roughly equals
 // thread balancing for the backend codegen step.
 static void findPartitions(Module *M, ClusterIDMapType &ClusterIDMap,
                            unsigned N) {
   // At this point module should have the proper mix of globals and locals.
   // As we attempt to partition this module, we must not change any
   // locals to globals.
-
   DEBUG(dbgs() << "Partition module with (" << M->size() << ")functions\n");
   ClusterMapType GVtoClusterMap;
   ComdatMembersType ComdatMembers;
 
   auto recordGVSet = [&GVtoClusterMap, &ComdatMembers](GlobalValue &GV) {
     if (GV.isDeclaration())
       return;
 
auto recordGVSet = [&GVtoClusterMap, &ComdatMembers](GlobalValue &GV) {
 
     // For aliases we should not separate them from their aliasees regardless
     // of linkage.
     if (GlobalAlias *GA = dyn_cast<GlobalAlias>(&GV)) {
       if (const GlobalObject *Base = GA->getBaseObject())
         GVtoClusterMap.unionSets(&GV, Base);
     }
 
-    // Further only iterate over local GVs.
-    if (!GV.hasLocalLinkage())
-      return;
-
-    for (auto *U : GV.users()) {
-      SmallVector<const User *, 4> Worklist;
-      Worklist.push_back(U);
-      while (!Worklist.empty()) {
-        const User *UU = Worklist.pop_back_val();
-        // For each constant that is not a GV (a pure const) recurse.
-        if (isa<Constant>(UU) && !isa<GlobalValue>(UU)) {
-          Worklist.append(UU->user_begin(), UU->user_end());
+    if (const Function *F = dyn_cast<Function>(&GV)) {
+      for (const BasicBlock &BB : *F) {
+        BlockAddress *BA = BlockAddress::lookup(&BB);
+        if (!BA || !BA->isConstantUsed())
           continue;
-        }
-        addNonConstUser(GVtoClusterMap, &GV, UU);
+        addAllGlobalValueUsers(GVtoClusterMap, F, BA);
       }
     }
+
+    if (GV.hasLocalLinkage())
+      addAllGlobalValueUsers(GVtoClusterMap, &GV, &GV);
   };
 
   std::for_each(M->begin(), M->end(), recordGVSet);
   std::for_each(M->global_begin(), M->global_end(), recordGVSet);
   std::for_each(M->alias_begin(), M->alias_end(), recordGVSet);
 
   // Assigned all GVs to merged clusters while balancing number of objects in
   // each.
void llvm::SplitModule(
     bool PreserveLocals) {
   if (!PreserveLocals) {
     for (Function &F : *M)
       externalize(&F);
     for (GlobalVariable &GV : M->globals())
       externalize(&GV);
     for (GlobalAlias &GA : M->aliases())
       externalize(&GA);
-
-    // FIXME: We should be able to reuse M as the last partition instead of
-    // cloning it.
-    for (unsigned I = 0; I != N; ++I) {
-      ValueToValueMapTy VMap;
-      std::unique_ptr<Module> MPart(
-          CloneModule(M.get(), VMap, [=](const GlobalValue *GV) {
-            return isInPartition(GV, I, N);
-          }));
-      if (I != 0)
-        MPart->setModuleInlineAsm("");
-      ModuleCallback(std::move(MPart));
-    }
-  } else {
-    // This performs splitting without a need for externalization, which might not
-    // always be possible.
-    ClusterIDMapType ClusterIDMap;
-    findPartitions(M.get(), ClusterIDMap, N);
+
 
-    for (unsigned I = 0; I < N; ++I) {
-      ValueToValueMapTy VMap;
-      std::unique_ptr<Module> MPart(
-          CloneModule(M.get(), VMap, [&](const GlobalValue *GV) {
-             if (ClusterIDMap.count(GV))
-               return (ClusterIDMap[GV] == I);
-             else
-               return isInPartition(GV, I, N);
-          }));
-      if (I != 0)
-        MPart->setModuleInlineAsm("");
-      ModuleCallback(std::move(MPart));
-    }
-  }
-}
+  // FIXME: We should be able to reuse M as the last partition instead of
+  // cloning it.

test/tools/llvm-split/blockaddress.ll

+; Test that blockaddress target is in the same partition.
+; RUN: llvm-split -j5 -o %t %s
+; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 %s
+; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1234 %s
+; RUN: llvm-dis -o - %t2 | FileCheck --check-prefix=CHECK1234 %s
+; RUN: llvm-dis -o - %t3 | FileCheck --check-prefix=CHECK1234 %s
+; RUN: llvm-dis -o - %t4 | FileCheck --check-prefix=CHECK1234 %s
+
+; CHECK0:    @xxx = global [2 x i8*] [i8* blockaddress(@f, %exit), i8* blockaddress(@g, %exit)]
+; CHECK1234: @xxx = external global [2 x i8*]
+; CHECK1234-NOT: blockaddress
+@xxx = global [2 x i8*] [i8* blockaddress(@f, %exit), i8* blockaddress(@g, %exit)]
+
+; CHECK0:    define i32 @f()
+; CHECK1234: declare i32 @f()
+define i32 @f(){
+entry:
+  br label %exit
+exit:
+  ret i32 0
+}
+
+; CHECK0:    define i32 @g()
+; CHECK1234: declare i32 @g()
+define i32 @g(){
+entry:
+  br label %exit
+exit:
+  ret i32 0
+}
+
+; CHECK0:    define i8* @h()
+; CHECK1234: declare i8* @h()
+define i8* @h(){
+entry:
+  ret i8* blockaddress(@f, %exit)
+}