Don't try to sink addresses that we can't recreate

Author: e-kud

llvm/lib/CodeGen/CodeGenPrepare.cpp

@@ -5790,8 +5790,7 @@ static BasicBlock::iterator findInsertPos(Value *Addr, Instruction *MemoryInst,
   // instruction after it.
   if (SunkAddr) {
     if (Instruction *AddrInst = dyn_cast<Instruction>(SunkAddr))
-      return AddrInst->isTerminator() ? MemoryInst->getIterator()
-                                      : std::next(AddrInst->getIterator());
+      return std::next(AddrInst->getIterator());
   }
 
   // Find the first user of Addr in current BB.
@@ -6100,6 +6099,13 @@ bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
       }
 
       if (!ResultIndex) {
+        auto PtrInst = dyn_cast<Instruction>(ResultPtr);
+        // Here we know that we have just a pointer without any offsets.  If
+        // this pointer comes from a different from the current basic block we
+        // need to know how to recreate it in another basic block.
+        // Currently we don't support recreation of any of instruction.
+        if (PtrInst && PtrInst->getParent() != MemoryInst->getParent())
+          return Modified;
         SunkAddr = ResultPtr;
       } else {
         if (ResultPtr->getType() != I8PtrTy)

llvm/test/Transforms/CodeGenPrepare/X86/sink-addr-recreate.ll

@@ -0,0 +1,42 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -p 'require<profile-summary>,codegenprepare' -cgpp-huge-func=0 < %s | FileCheck %s
+
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-grtev4-linux-gnu"
+
+; Test a scenario when the address cannot be recreated in the current basic block
+
+declare ptr @get_ptr(i64)
+define void @address_terminator() personality ptr null {
+; CHECK-LABEL: define void @address_terminator() personality ptr null {
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    [[PTR:%.*]] = invoke ptr @get_ptr(i64 0)
+; CHECK-NEXT:            to label %[[BODY_1:.*]] unwind label %[[EHCLEANUP:.*]]
+; CHECK:       [[EHCLEANUP]]:
+; CHECK-NEXT:    [[PAD:%.*]] = cleanuppad within none []
+; CHECK-NEXT:    cleanupret from [[PAD]] unwind to caller
+; CHECK:       [[BODY_1]]:
+; CHECK-NEXT:    [[GEP1:%.*]] = bitcast ptr [[PTR]] to ptr
+; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[GEP1]], align 4
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast ptr [[PTR]] to ptr
+; CHECK-NEXT:    [[UNUSED:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
+; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP0]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %ptr = invoke ptr @get_ptr(i64 0) to label %body.1 unwind label %ehcleanup
+
+body.2:
+  %unused = load <4 x i32>, ptr %gep, align 4
+  store <4 x i32> zeroinitializer, ptr %gep, align 4
+  ret void
+
+ehcleanup:
+  %pad = cleanuppad within none []
+  cleanupret from %pad unwind to caller
+
+body.1:
+  %gep = getelementptr { i32 }, ptr %ptr, i64 0, i32 0
+  store <4 x i32> zeroinitializer, ptr %gep, align 4
+  br label %body.2
+}

llvm/test/Transforms/CodeGenPrepare/X86/sink-addr-reuse.ll

@@ -42,38 +42,3 @@ bb3:
 bb7:
   ret void
 }
-
-; Test a scenario when the address is the last instruction in the basic block.
-
-define void @adress_terminator() personality ptr null {
-; CHECK-LABEL: define void @adress_terminator() personality ptr null {
-; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    [[PTR:%.*]] = invoke ptr null(i64 0)
-; CHECK-NEXT:            to label %[[BODY_1:.*]] unwind label %[[EHCLEANUP:.*]]
-; CHECK:       [[EHCLEANUP]]:
-; CHECK-NEXT:    [[TMP0:%.*]] = cleanuppad within none []
-; CHECK-NEXT:    cleanupret from [[TMP0]] unwind to caller
-; CHECK:       [[BODY_1]]:
-; CHECK-NEXT:    [[TMP1:%.*]] = bitcast ptr [[PTR]] to ptr
-; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[TMP1]], align 4
-; CHECK-NEXT:    [[V0:%.*]] = load <4 x i32>, ptr [[PTR]], align 4
-; CHECK-NEXT:    store <4 x i32> zeroinitializer, ptr [[PTR]], align 4
-; CHECK-NEXT:    ret void
-;
-entry:
-  %ptr = invoke ptr null(i64 0) to label %body.1 unwind label %ehcleanup
-
-body.2:
-  %v0 = load <4 x i32>, ptr %2, align 4
-  store <4 x i32> zeroinitializer, ptr %2, align 4
-  ret void
-
-ehcleanup:
-  %1 = cleanuppad within none []
-  cleanupret from %1 unwind to caller
-
-body.1:
-  %2 = getelementptr { i32 }, ptr %ptr, i64 0, i32 0
-  store <4 x i32> zeroinitializer, ptr %2, align 4
-  br label %body.2
-}