diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 75d6013..38c7c05 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -2967,11 +2967,37 @@
       N0.getOperand(1).getOpcode() == ISD::Constant) {
     uint64_t c1 = cast<ConstantSDNode>(N0.getOperand(1))->getZExtValue();
     uint64_t c2 = N1C->getZExtValue();
-    if (c1 + c2 > OpSizeInBits)
+    if (c1 + c2 >= OpSizeInBits)
       return DAG.getConstant(0, VT);
     return DAG.getNode(ISD::SHL, N->getDebugLoc(), VT, N0.getOperand(0),
                        DAG.getConstant(c1 + c2, N1.getValueType()));
   }
+
+  // fold (shl (ext (shl x, c1)), c2) -> (ext (shl x, (add c1, c2)))
+  // For this to be valid, the second form must not preserve any of the bits
+  // that are shifted out by the inner shift in the first form.  This means
+  // the outer shift size must be >= the number of bits added by the ext.
+  // As a corollary, we don't care what kind of ext it is.
+  if (N1C && (N0.getOpcode() == ISD::ZERO_EXTEND ||
+              N0.getOpcode() == ISD::ANY_EXTEND ||
+              N0.getOpcode() == ISD::SIGN_EXTEND) &&
+      N0.getOperand(0).getOpcode() == ISD::SHL &&
+      isa<ConstantSDNode>(N0.getOperand(0)->getOperand(1))) {
+    uint64_t c1 = 
+      cast<ConstantSDNode>(N0.getOperand(0)->getOperand(1))->getZExtValue();
+    uint64_t c2 = N1C->getZExtValue();
+    EVT InnerShiftVT = N0.getOperand(0).getValueType();
+    uint64_t InnerShiftSize = InnerShiftVT.getScalarType().getSizeInBits();
+    if (c2 >= OpSizeInBits - InnerShiftSize) {
+      if (c1 + c2 >= OpSizeInBits)
+        return DAG.getConstant(0, VT);
+      return DAG.getNode(ISD::SHL, N0->getDebugLoc(), VT,
+                         DAG.getNode(N0.getOpcode(), N0->getDebugLoc(), VT,
+                                     N0.getOperand(0)->getOperand(0)),
+                         DAG.getConstant(c1 + c2, N1.getValueType()));
+    }
+  }
+
   // fold (shl (srl x, c1), c2) -> (shl (and x, (shl -1, c1)), (sub c2, c1)) or
   //                               (srl (and x, (shl -1, c1)), (sub c1, c2))
   if (N1C && N0.getOpcode() == ISD::SRL &&
@@ -3165,7 +3191,7 @@
       N0.getOperand(1).getOpcode() == ISD::Constant) {
     uint64_t c1 = cast<ConstantSDNode>(N0.getOperand(1))->getZExtValue();
     uint64_t c2 = N1C->getZExtValue();
-    if (c1 + c2 > OpSizeInBits)
+    if (c1 + c2 >= OpSizeInBits)
       return DAG.getConstant(0, VT);
     return DAG.getNode(ISD::SRL, N->getDebugLoc(), VT, N0.getOperand(0),
                        DAG.getConstant(c1 + c2, N1.getValueType()));
@@ -3178,7 +3204,8 @@
     uint64_t c1 = 
       cast<ConstantSDNode>(N0.getOperand(0)->getOperand(1))->getZExtValue();
     uint64_t c2 = N1C->getZExtValue();
-    EVT InnerShiftVT = N0.getOperand(0)->getOperand(1).getValueType();
+    EVT InnerShiftVT = N0.getOperand(0).getValueType();
+    EVT ShiftCountVT = N0.getOperand(0)->getOperand(1).getValueType();
     uint64_t InnerShiftSize = InnerShiftVT.getScalarType().getSizeInBits();
     // This is only valid if the OpSizeInBits + c1 = size of inner shift.
     if (c1 + OpSizeInBits == InnerShiftSize) {
@@ -3187,7 +3214,7 @@
       return DAG.getNode(ISD::TRUNCATE, N0->getDebugLoc(), VT,
                          DAG.getNode(ISD::SRL, N0->getDebugLoc(), InnerShiftVT, 
                                      N0.getOperand(0)->getOperand(0),
-                                     DAG.getConstant(c1 + c2, InnerShiftVT)));
+                                     DAG.getConstant(c1 + c2, ShiftCountVT)));
     }
   }
 
diff --git a/test/CodeGen/X86/divide-by-constant.ll b/test/CodeGen/X86/divide-by-constant.ll
index ab3bd94..545662f 100644
--- a/test/CodeGen/X86/divide-by-constant.ll
+++ b/test/CodeGen/X86/divide-by-constant.ll
@@ -29,9 +29,9 @@
   ret i8 %div
 
 ; CHECK: test3:
-; CHECK: imull	$171, %eax, %eax
-; CHECK-NEXT: shrb	%ah
-; CHECK-NEXT: movzbl	%ah, %eax
+; CHECK: movzbl  8(%esp), %eax
+; CHECK-NEXT: imull	$171, %eax, %eax
+; CHECK-NEXT: shrl	$9, %eax
 ; CHECK-NEXT: ret
 }
 
diff --git a/test/CodeGen/X86/x86-64-extend-shift.ll b/test/CodeGen/X86/x86-64-extend-shift.ll
new file mode 100644
index 0000000..6852785
--- /dev/null
+++ b/test/CodeGen/X86/x86-64-extend-shift.ll
@@ -0,0 +1,10 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
+; Formerly there were two shifts.
+
+define i64 @baz(i32 %A) nounwind {
+; CHECK:  shlq  $49, %rax
+        %tmp1 = shl i32 %A, 17
+        %tmp2 = zext i32 %tmp1 to i64
+        %tmp3 = shl i64 %tmp2, 32
+        ret i64 %tmp3
+}