Index: lib/Analysis/IPA/InlineCost.cpp
===================================================================
--- lib/Analysis/IPA/InlineCost.cpp
+++ lib/Analysis/IPA/InlineCost.cpp
@@ -72,6 +72,12 @@
   // The called function.
   Function &F;
 
+  // The callsite being analyzed - used to inspect call site specific
+  // attributes since these can be more precise than the ones on the callee
+  // itself. Please do not use this to do analysis in the caller function; we
+  // want the inline cost query to be easily cacheable.
+  CallSite CS;
+
   int Threshold;
   int Cost;
 
@@ -124,6 +130,8 @@
   bool simplifyCallSite(Function *F, CallSite CS);
   ConstantInt *stripAndComputeInBoundsConstantOffsets(Value *&V);
 
+  bool isKnownNonNullInCallee(Value *V);
+
   // Custom analysis routines.
   bool analyzeBlock(BasicBlock *BB, SmallPtrSetImpl<const Value *> &EphValues);
 
@@ -162,8 +170,8 @@
 
 public:
   CallAnalyzer(const TargetTransformInfo &TTI, AssumptionCacheTracker *ACT,
-               Function &Callee, int Threshold)
-      : TTI(TTI), ACT(ACT), F(Callee), Threshold(Threshold), Cost(0),
+               Function &Callee, int Threshold, CallSite CSArg)
+    : TTI(TTI), ACT(ACT), F(Callee), CS(CSArg), Threshold(Threshold), Cost(0),
         IsCallerRecursive(false), IsRecursiveCall(false),
         ExposesReturnsTwice(false), HasDynamicAlloca(false),
         ContainsNoDuplicateCall(false), HasReturn(false), HasIndirectBr(false),
@@ -514,6 +522,28 @@
   return false;
 }
 
+bool CallAnalyzer::isKnownNonNullInCallee(Value *V) {
+  // Does the *call site* have the NonNull attribute set on an argument?  We
+  // use the attribute on the call site to memoize any analysis done in the
+  // caller. This will also trip if the callee function has a non-null
+  // parameter attribute, but that's a less interesting case because hopefully
+  // the callee would already have been simplified based on that.
+  if (Argument *A = dyn_cast<Argument>(V)) {
+    unsigned ArgNo = A->getArgNo();
+    if (CS.paramHasAttr(ArgNo+1, Attribute::NonNull))
+      return true;
+  }
+  
+  // Is this an alloca in the caller?
+  if (isAllocaDerivedArg(V)) {
+    // We can actually predict the result of comparisons between an
+    // alloca-derived value and null. Note that this fires regardless of
+    // SROA firing.
+    return true;
+  }
+  return false;
+}
+
 bool CallAnalyzer::visitCmpInst(CmpInst &I) {
   Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
   // First try to handle simplified comparisons.
@@ -555,18 +585,14 @@
   }
 
   // If the comparison is an equality comparison with null, we can simplify it
-  // for any alloca-derived argument.
-  if (I.isEquality() && isa<ConstantPointerNull>(I.getOperand(1)))
-    if (isAllocaDerivedArg(I.getOperand(0))) {
-      // We can actually predict the result of comparisons between an
-      // alloca-derived value and null. Note that this fires regardless of
-      // SROA firing.
-      bool IsNotEqual = I.getPredicate() == CmpInst::ICMP_NE;
-      SimplifiedValues[&I] = IsNotEqual ? ConstantInt::getTrue(I.getType())
-                                        : ConstantInt::getFalse(I.getType());
-      return true;
-    }
-
+  // if we know the value (argument) can't be null
+  if (I.isEquality() && isa<ConstantPointerNull>(I.getOperand(1)) &&
+      isKnownNonNullInCallee(I.getOperand(0))) {
+    bool IsNotEqual = I.getPredicate() == CmpInst::ICMP_NE;
+    SimplifiedValues[&I] = IsNotEqual ? ConstantInt::getTrue(I.getType())
+                                      : ConstantInt::getFalse(I.getType());
+    return true;
+  }
   // Finally check for SROA candidates in comparisons.
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;
@@ -857,7 +883,7 @@
   // during devirtualization and so we want to give it a hefty bonus for
   // inlining, but cap that bonus in the event that inlining wouldn't pan
   // out. Pretend to inline the function, with a custom threshold.
-  CallAnalyzer CA(TTI, ACT, *F, InlineConstants::IndirectCallThreshold);
+  CallAnalyzer CA(TTI, ACT, *F, InlineConstants::IndirectCallThreshold, CS);
   if (CA.analyzeCall(CS)) {
     // We were able to inline the indirect call! Subtract the cost from the
     // bonus we want to apply, but don't go below zero.
@@ -1474,7 +1500,7 @@
   DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
         << "...\n");
 
-  CallAnalyzer CA(TTIWP->getTTI(*Callee), ACT, *Callee, Threshold);
+  CallAnalyzer CA(TTIWP->getTTI(*Callee), ACT, *Callee, Threshold, CS);
   bool ShouldInline = CA.analyzeCall(CS);
 
   DEBUG(CA.dump());
Index: test/Transforms/Inline/nonnull.ll
===================================================================
--- /dev/null
+++ test/Transforms/Inline/nonnull.ll
@@ -0,0 +1,45 @@
+; RUN: opt -S -inline %s | FileCheck %s
+
+declare void @foo()
+declare void @bar()
+
+define void @callee(i8* %arg) {
+  %cmp = icmp eq i8* %arg, null
+  br i1 %cmp, label %expensive, label %done
+
+; This block is designed to be too expensive to inline.  We can only inline
+; callee if this block is known to be dead.
+expensive:
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  call void @foo()
+  ret void
+
+done:
+  call void @bar()
+  ret void
+}
+
+; Positive test - arg is known non null
+define void @caller(i8* nonnull %arg) {
+; CHECK-LABEL: @caller
+; CHECK: call void @bar()
+  call void @callee(i8* nonnull %arg)
+  ret void
+}
+
+; Negative test - arg is not known to be non null
+define void @caller2(i8* %arg) {
+; CHECK-LABEL: @caller2
+; CHECK: call void @callee(
+  call void @callee(i8* %arg)
+  ret void
+}
+