diff --git a/lib/CodeGen/CGBlocks.cpp b/lib/CodeGen/CGBlocks.cpp
index e3658ab..94ab61d 100644
--- a/lib/CodeGen/CGBlocks.cpp
+++ b/lib/CodeGen/CGBlocks.cpp
@@ -199,13 +199,14 @@
     Qualifiers::ObjCLifetime Lifetime;
     const BlockDecl::Capture *Capture; // null for 'this'
     llvm::Type *Type;
+    QualType FieldType;
 
     BlockLayoutChunk(CharUnits align, CharUnits size,
                      Qualifiers::ObjCLifetime lifetime,
                      const BlockDecl::Capture *capture,
-                     llvm::Type *type)
+                     llvm::Type *type, QualType fieldType)
       : Alignment(align), Size(size), Lifetime(lifetime),
-        Capture(capture), Type(type) {}
+        Capture(capture), Type(type), FieldType(fieldType) {}
 
     /// Tell the block info that this chunk has the given field index.
     void setIndex(CGBlockInfo &info, unsigned index, CharUnits offset) {
@@ -213,8 +214,8 @@
         info.CXXThisIndex = index;
         info.CXXThisOffset = offset;
       } else {
-        info.Captures.insert({Capture->getVariable(),
-                              CGBlockInfo::Capture::makeIndex(index, offset)});
+        auto C = CGBlockInfo::Capture::makeIndex(index, offset, FieldType);
+        info.Captures.insert({Capture->getVariable(), C});
       }
     }
   };
@@ -363,7 +364,7 @@
 
     layout.push_back(BlockLayoutChunk(tinfo.second, tinfo.first,
                                       Qualifiers::OCL_None,
-                                      nullptr, llvmType));
+                                      nullptr, llvmType, thisType));
   }
 
   // Next, all the block captures.
@@ -380,7 +381,7 @@
 
       layout.push_back(BlockLayoutChunk(align, CGM.getPointerSize(),
                                         Qualifiers::OCL_None, &CI,
-                                        CGM.VoidPtrTy));
+                                        CGM.VoidPtrTy, variable->getType()));
       continue;
     }
 
@@ -436,6 +437,14 @@
     }
 
     QualType VT = variable->getType();
+
+    // If the variable is captured by an enclosing block or lambda expression,
+    // use the type of the capture field.
+    if (CGF->BlockInfo && CI.isNested())
+      VT = CGF->BlockInfo->getCapture(variable).fieldType();
+    else if (auto *FD = CGF->LambdaCaptureFields.lookup(variable))
+      VT = FD->getType();
+
     CharUnits size = C.getTypeSizeInChars(VT);
     CharUnits align = C.getDeclAlign(variable);
     
@@ -444,7 +453,8 @@
     llvm::Type *llvmType =
       CGM.getTypes().ConvertTypeForMem(VT);
     
-    layout.push_back(BlockLayoutChunk(align, size, lifetime, &CI, llvmType));
+    layout.push_back(
+        BlockLayoutChunk(align, size, lifetime, &CI, llvmType, VT));
   }
 
   // If that was everything, we're done here.
@@ -775,7 +785,7 @@
     // Ignore constant captures.
     if (capture.isConstant()) continue;
 
-    QualType type = variable->getType();
+    QualType type = capture.fieldType();
 
     // This will be a [[type]]*, except that a byref entry will just be
     // an i8**.
@@ -1033,9 +1043,8 @@
                                  variable->getName());
   }
 
-  if (auto refType = variable->getType()->getAs<ReferenceType>()) {
+  if (auto refType = capture.fieldType()->getAs<ReferenceType>())
     addr = EmitLoadOfReference(addr, refType);
-  }
 
   return addr;
 }
diff --git a/lib/CodeGen/CGBlocks.h b/lib/CodeGen/CGBlocks.h
index aaf0679..80e255f 100644
--- a/lib/CodeGen/CGBlocks.h
+++ b/lib/CodeGen/CGBlocks.h
@@ -159,6 +159,11 @@
     EHScopeStack::stable_iterator Cleanup;
     CharUnits::QuantityType Offset;
 
+    /// Type of the capture field. Normally, this is identical to the type of
+    /// the capture's VarDecl, but can be different if there is an enclosing
+    /// lambda.
+    QualType FieldType;
+
   public:
     bool isIndex() const { return (Data & 1) != 0; }
     bool isConstant() const { return !isIndex(); }
@@ -185,10 +190,16 @@
       return reinterpret_cast<llvm::Value*>(Data);
     }
 
-    static Capture makeIndex(unsigned index, CharUnits offset) {
+    QualType fieldType() const {
+      return FieldType;
+    }
+
+    static Capture makeIndex(unsigned index, CharUnits offset,
+                             QualType FieldType) {
       Capture v;
       v.Data = (index << 1) | 1;
       v.Offset = offset.getQuantity();
+      v.FieldType = FieldType;
       return v;
     }
 
diff --git a/test/CodeGenObjCXX/lambda-expressions.mm b/test/CodeGenObjCXX/lambda-expressions.mm
index 0c309c0..d987083 100644
--- a/test/CodeGenObjCXX/lambda-expressions.mm
+++ b/test/CodeGenObjCXX/lambda-expressions.mm
@@ -4,6 +4,8 @@
 typedef int (^fp)();
 fp f() { auto x = []{ return 3; }; return x; }
 
+// ARC: %[[LAMBDACLASS:.*]] = type { i32 }
+
 // MRC: @OBJC_METH_VAR_NAME{{.*}} = private global [5 x i8] c"copy\00"
 // MRC: @OBJC_METH_VAR_NAME{{.*}} = private global [12 x i8] c"autorelease\00"
 // MRC-LABEL: define i32 ()* @_Z1fv(
@@ -60,6 +62,40 @@
 }
 @end
 
+// ARC: define void @_ZN13LambdaCapture4foo1ERi(i32* dereferenceable(4) %{{.*}})
+// ARC:   %[[CAPTURE0:.*]] = getelementptr inbounds %[[LAMBDACLASS]], %[[LAMBDACLASS]]* %{{.*}}, i32 0, i32 0
+// ARC:   store i32 %{{.*}}, i32* %[[CAPTURE0]]
+
+// ARC: define internal void @"_ZZN13LambdaCapture4foo1ERiENK3$_3clEv"(%[[LAMBDACLASS]]* %{{.*}})
+// ARC:   %[[BLOCK:.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>
+// ARC:   %[[CAPTURE1:.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>* %[[BLOCK]], i32 0, i32 5
+// ARC:   store i32 %{{.*}}, i32* %[[CAPTURE1]]
+
+// ARC: define internal void @"___ZZN13LambdaCapture4foo1ERiENK3$_3clEv_block_invoke"
+// ARC:   %[[CAPTURE2:.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>* %{{.*}}, i32 0, i32 5
+// ARC:   store i32 %{{.*}}, i32* %[[CAPTURE2]]
+
+// ARC: define internal void @"___ZZN13LambdaCapture4foo1ERiENK3$_3clEv_block_invoke_2"(i8* %{{.*}})
+// ARC:   %[[CAPTURE3:.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32 }>* %{{.*}}, i32 0, i32 5
+// ARC:   %[[V1:.*]] = load i32, i32* %[[CAPTURE3]]
+// ARC:   store i32 %[[V1]], i32* @_ZN13LambdaCapture1iE
+
+namespace LambdaCapture {
+  int i;
+  void foo1(int &a) {
+    auto lambda = [a]{
+      auto block1 = ^{
+        auto block2 = ^{
+          i = a;
+        };
+        block2();
+      };
+      block1();
+    };
+    lambda();
+  }
+}
+
 // ARC-LABEL: define linkonce_odr i32 ()* @_ZZNK13StaticMembersIfE1fMUlvE_clEvENKUlvE_cvU13block_pointerFivEEv
 
 // Check lines for BlockInLambda test below