diff --git a/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index 396ebc15c6d..f9e0992ea14 100644
--- a/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -1176,8 +1176,9 @@ bool TargetLowering::SimplifyDemandedBits(SDValue Op,
     // the RHS.
     if (ConstantSDNode *RHSC = dyn_cast<ConstantSDNode>(Op.getOperand(1))) {
       APInt LHSZero, LHSOne;
+      // Do not increment Depth here; that can cause an infinite loop.
       TLO.DAG.ComputeMaskedBits(Op.getOperand(0), NewMask,
-                                LHSZero, LHSOne, Depth+1);
+                                LHSZero, LHSOne, Depth);
       // If the LHS already has zeros where RHSC does, this and is dead.
       if ((LHSZero & NewMask) == (~RHSC->getAPIntValue() & NewMask))
         return TLO.CombineTo(Op, Op.getOperand(0));
diff --git a/test/CodeGen/X86/2011-01-10-DagCombineHang.ll b/test/CodeGen/X86/2011-01-10-DagCombineHang.ll
new file mode 100644
index 00000000000..bf438b82edf
--- /dev/null
+++ b/test/CodeGen/X86/2011-01-10-DagCombineHang.ll
@@ -0,0 +1,15 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin10
+; This formerly got DagCombine into a loop, PR 8916.
+
+define i32 @foo(i64 %x, i64 %y, i64 %z, i32 %a, i32 %b) {
+entry:
+  %"alloca point" = bitcast i32 0 to i32          ; <i32> [#uses=0]
+  %t1 = shl i64 %x, 15
+  %t2 = and i64 %t1, 4294934528
+  %t3 = or i64 %t2, %y
+  %t4 = xor i64 %z, %t3
+  %t5 = trunc i64 %t4 to i32
+  %t6 = add i32 %a, %t5
+  %t7 = add i32 %t6, %b
+  ret i32 %t7
+}