Index: llvm/lib/Analysis/InlineCost.cpp
===================================================================
--- llvm/lib/Analysis/InlineCost.cpp
+++ llvm/lib/Analysis/InlineCost.cpp
@@ -272,6 +272,7 @@
   bool visitCmpInst(CmpInst &I);
   bool visitSub(BinaryOperator &I);
   bool visitBinaryOperator(BinaryOperator &I);
+  bool visitUnaryOperator(UnaryOperator &I);
   bool visitLoad(LoadInst &I);
   bool visitStore(StoreInst &I);
   bool visitExtractValue(ExtractValueInst &I);
@@ -1103,6 +1104,38 @@
   return false;
 }
 
+bool CallAnalyzer::visitUnaryOperator(UnaryOperator &I) {
+  Value *Op = I.getOperand(0);
+  Constant *COp = dyn_cast<Constant>(Op);
+  if (!COp)
+    COp = SimplifiedValues.lookup(Op);
+
+  Value *SimpleV = nullptr;
+  if (auto FI = dyn_cast<FPMathOperator>(&I))
+    SimpleV = SimplifyFPUnOp(I.getOpcode(), COp ? COp : Op,
+                             FI->getFastMathFlags(), DL);
+  else
+    SimpleV = SimplifyUnOp(I.getOpcode(), COp ? COp : Op, DL);
+
+  if (Constant *C = dyn_cast_or_null<Constant>(SimpleV))
+    SimplifiedValues[&I] = C;
+
+  if (SimpleV)
+    return true;
+
+  // Disable any SROA on arguments to arbitrary, unsimplified unary operators.
+  disableSROA(Op);
+
+  // If the instruction is floating point, and the target says this operation
+  // is expensive, this may eventually become a library call. Treat the cost
+  // as such.
+  if (I.getType()->isFloatingPointTy() &&
+      TTI.getFPOpCost(I.getType()) == TargetTransformInfo::TCC_Expensive)
+    addCost(InlineConstants::CallPenalty);
+
+  return false;
+}
+
 bool CallAnalyzer::visitLoad(LoadInst &I) {
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;
Index: llvm/lib/Analysis/InstructionSimplify.cpp
===================================================================
--- llvm/lib/Analysis/InstructionSimplify.cpp
+++ llvm/lib/Analysis/InstructionSimplify.cpp
@@ -4589,6 +4589,10 @@
   }
 }
 
+Value *llvm::SimplifyUnOp(unsigned Opcode, Value *Op, const SimplifyQuery &Q) {
+  return ::simplifyUnOp(Opcode, Op, Q, RecursionLimit);
+}
+
 Value *llvm::SimplifyFPUnOp(unsigned Opcode, Value *Op, FastMathFlags FMF,
                             const SimplifyQuery &Q) {
   return ::simplifyFPUnOp(Opcode, Op, FMF, Q, RecursionLimit);
Index: llvm/test/Transforms/Inline/ARM/inline-fp.ll
===================================================================
--- llvm/test/Transforms/Inline/ARM/inline-fp.ll
+++ llvm/test/Transforms/Inline/ARM/inline-fp.ll
@@ -12,6 +12,8 @@
 ; NOFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; NOFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
+; NOFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
 
 ; FULLFP-DAG: single inlined into test_single with (cost=0, threshold=75)
 ; FULLFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
@@ -21,6 +23,8 @@
 ; FULLFP-DAG: double inlined into test_double with (cost=-15000, threshold=75)
 ; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; FULLFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
+; FULLFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
 
 ; SINGLEFP-DAG: single inlined into test_single with (cost=0, threshold=75)
 ; SINGLEFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
@@ -30,6 +34,8 @@
 ; SINGLEFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; SINGLEFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
+; SINGLEFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=125, threshold=75)
 
 define i32 @test_single(i32 %a, i8 %b, i32 %c, i8 %d) #0 {
   %call = call float @single(i32 %a, i8 zeroext %b)
@@ -55,6 +61,12 @@
   ret i32 0
 }
 
+define i32 @test_single_force_soft_fneg(i32 %a, i8 %b, i32 %c, i8 %d) #1 {
+  %call = call float @single_force_soft_fneg(i32 %a, i8 zeroext %b) #1
+  %call2 = call float @single_force_soft_fneg(i32 %c, i8 zeroext %d) #1
+  ret i32 0
+}
+
 define internal float @single(i32 %response, i8 zeroext %value1) #0 {
 entry:
   %conv = zext i8 %value1 to i32
@@ -106,6 +118,20 @@
   ret float %div
 }
 
+; Make sure fneg is considered expensive
+define internal float @single_force_soft_fneg(i32 %response, i8 zeroext %value1) #1 {
+entry:
+  %conv = zext i8 %value1 to i32
+  %sub = add nsw i32 %conv, -1
+  %conv1 = sitofp i32 %sub to float
+  %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
+  %mul = fneg float %0
+  %conv2 = sitofp i32 %response to float
+  %sub3 = fsub float %conv2, %mul
+  %div = fdiv float %sub3, %mul
+  ret float %div
+}
+
 declare float @llvm.pow.f32(float, float) optsize minsize
 declare double @llvm.pow.f64(double, double) optsize minsize