diff --git a/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp
diff --git a/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.h b/llvm/lib/CodeGen/SelectionDAG/StatepointLowering.h
@@ -0,0 +1,138 @@
+//===-- StatepointLowering.h - SDAGBuilder's statepoint code -*- C++ -*---===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file includes support code use by SelectionDAGBuilder when lowering a
+// statepoint sequence in SelectionDAG IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_CODEGEN_SELECTIONDAG_STATEPOINTLOWERING_H
+#define LLVM_LIB_CODEGEN_SELECTIONDAG_STATEPOINTLOWERING_H
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/CodeGen/SelectionDAG.h"
+#include "llvm/CodeGen/SelectionDAGNodes.h"
+#include <vector>
+
+namespace llvm {
+class SelectionDAGBuilder;
+
+/// This class tracks both per-statepoint and per-selectiondag information.
+/// For each statepoint it tracks locations of it's gc valuess (incoming and
+/// relocated) and list of gcreloc calls scheduled for visiting (this is
+/// used for a debug mode consistency check only).  The spill slot tracking
+/// works in concert with information in FunctionLoweringInfo.
+class StatepointLoweringState {
+public:
+  StatepointLoweringState() : NextSlotToAllocate(0) {
+  }
+
+  /// Reset all state tracking for a newly encountered safepoint.  Also
+  /// performs some consistency checking.
+  void startNewStatepoint(SelectionDAGBuilder &Builder);
+
+  /// Clear the memory usage of this object.  This is called from
+  /// SelectionDAGBuilder::clear.  We require this is never called in the
+  /// midst of processing a statepoint sequence.
+  void clear();
+
+  /// Returns the spill location of a value incoming to the current
+  /// statepoint.  Will return SDValue() if this value hasn't been
+  /// spilled.  Otherwise, the value has already been spilled and no
+  /// further action is required by the caller.
+  SDValue getLocation(SDValue val) {
+    if (!Locations.count(val))
+      return SDValue();
+    return Locations[val];
+  }
+  void setLocation(SDValue val, SDValue Location) {
+    assert(!Locations.count(val) &&
+           "Trying to allocate already allocated location");
+    Locations[val] = Location;
+  }
+
+  /// Returns the relocated value for a given input pointer. Will
+  /// return SDValue() if this value hasn't yet been reloaded from
+  /// it's stack slot after the statepoint.  Otherwise, the value
+  /// has already been reloaded and the SDValue of that reload will
+  /// be returned. Note that VMState values are spilled but not
+  /// reloaded (since they don't change at the safepoint unless
+  /// also listed in the GC pointer section) and will thus never
+  /// be in this map
+  SDValue getRelocLocation(SDValue val) {
+    if (!RelocLocations.count(val))
+      return SDValue();
+    return RelocLocations[val];
+  }
+  void setRelocLocation(SDValue val, SDValue Location) {
+    assert(!RelocLocations.count(val) &&
+           "Trying to allocate already allocated location");
+    RelocLocations[val] = Location;
+  }
+
+  /// Record the fact that we expect to encounter a given gc_relocate
+  /// before the next statepoint.  If we don't see it, we'll report
+  /// an assertion.
+  void scheduleRelocCall(const CallInst &RelocCall) {
+    PendingGCRelocateCalls.push_back(&RelocCall);
+  }
+  /// Remove this gc_relocate from the list we're expecting to see
+  /// before the next statepoint.  If we weren't expecting to see
+  /// it, we'll report an assertion.
+  void relocCallVisited(const CallInst &RelocCall) {
+    SmallVectorImpl<const CallInst *>::iterator itr =
+        std::find(PendingGCRelocateCalls.begin(), PendingGCRelocateCalls.end(),
+                  &RelocCall);
+    assert(itr != PendingGCRelocateCalls.end() &&
+           "Visited unexpected gcrelocate call");
+    PendingGCRelocateCalls.erase(itr);
+  }
+
+  // TODO: Should add consistency tracking to ensure we encounter
+  // expected gc_result calls too.
+
+  /// Get a stack slot we can use to store an value of type ValueType.  This
+  /// will hopefully be a recylced slot from another statepoint.
+  SDValue allocateStackSlot(EVT ValueType, SelectionDAGBuilder &Builder);
+
+  void reserveStackSlot(int Offset) {
+    assert(Offset >= 0 && Offset < (int)AllocatedStackSlots.size() &&
+           "out of bounds");
+    assert(!AllocatedStackSlots[Offset] && "already reserved!");
+    assert(NextSlotToAllocate <= (unsigned)Offset && "consistency!");
+    AllocatedStackSlots[Offset] = true;
+  }
+  bool isStackSlotAllocated(int Offset) {
+    assert(Offset >= 0 && Offset < (int)AllocatedStackSlots.size() &&
+           "out of bounds");
+    return AllocatedStackSlots[Offset];
+  }
+
+private:
+  /// Maps pre-relocation value (gc pointer directly incoming into statepoint)
+  /// into it's location (currently only stack slots)
+  DenseMap<SDValue, SDValue> Locations;
+  /// Map pre-relocated value into it's new relocated location
+  DenseMap<SDValue, SDValue> RelocLocations;
+
+  /// A boolean indicator for each slot listed in the FunctionInfo as to
+  /// whether it has been used in the current statepoint.  Since we try to
+  /// preserve stack slots across safepoints, there can be gaps in which
+  /// slots have been allocated.
+  SmallVector<bool, 50> AllocatedStackSlots;
+
+  /// Points just beyond the last slot known to have been allocated
+  unsigned NextSlotToAllocate;
+
+  /// Keep track of pending gcrelocate calls for consistency check
+  SmallVector<const CallInst *, 10> PendingGCRelocateCalls;
+};
+} // end namespace llvm
+
+#endif // LLVM_LIB_CODEGEN_SELECTIONDAG_STATEPOINTLOWERING_H
diff --git a/llvm/lib/IR/CMakeLists.txt b/llvm/lib/IR/CMakeLists.txt
@@ -36,6 +36,7 @@ add_llvm_library(LLVMCore
   Pass.cpp
   PassManager.cpp
   PassRegistry.cpp
+  Statepoint.cpp
   Type.cpp
   TypeFinder.cpp
   Use.cpp

diff --git a/llvm/lib/IR/Statepoint.cpp b/llvm/lib/IR/Statepoint.cpp
@@ -0,0 +1,62 @@
+//===-- IR/Statepoint.cpp -- gc.statepoint utilities ---  -----------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// 
+//===----------------------------------------------------------------------===//
+
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Constant.h"
+#include "llvm/IR/Constants.h"
+#include "llvm/Support/CommandLine.h"
+
+#include "llvm/IR/Statepoint.h"
+
+using namespace std;
+using namespace llvm;
+
+bool llvm::isStatepoint(const ImmutableCallSite &CS) {
+  const Function *F = CS.getCalledFunction();
+  return (F && F->getIntrinsicID() == Intrinsic::experimental_gc_statepoint);
+}
+bool llvm::isStatepoint(const Instruction *inst) {
+  if (isa<InvokeInst>(inst) || isa<CallInst>(inst)) {
+    ImmutableCallSite CS(inst);
+    return isStatepoint(CS);
+  }
+  return false;
+}
+bool llvm::isStatepoint(const Instruction &inst) {
+  return isStatepoint(&inst);
+}
+
+bool llvm::isGCRelocate(const ImmutableCallSite &CS) {
+  return isGCRelocate(CS.getInstruction());
+}
+bool llvm::isGCRelocate(const Instruction *inst) {
+  if (const CallInst *call = dyn_cast<CallInst>(inst)) {
+    if (const Function *F = call->getCalledFunction()) {
+      return F->getIntrinsicID() == Intrinsic::experimental_gc_relocate;
+    }
+  }
+  return false;
+}
+
+bool llvm::isGCResult(const ImmutableCallSite &CS) {
+  return isGCResult(CS.getInstruction());
+}
+bool llvm::isGCResult(const Instruction *inst) {
+  if (const CallInst *call = cast<CallInst>(inst)) {
+    if (Function *F = call->getCalledFunction()) {
+      return (F->getIntrinsicID() == Intrinsic::experimental_gc_result_int ||
+              F->getIntrinsicID() == Intrinsic::experimental_gc_result_float ||
+              F->getIntrinsicID() == Intrinsic::experimental_gc_result_ptr);
+    }
+  }
+  return false;
+}
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -18,6 +18,7 @@
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/PatternMatch.h"
+#include "llvm/IR/Statepoint.h"
 #include "llvm/Transforms/Utils/BuildLibCalls.h"
 #include "llvm/Transforms/Utils/Local.h"
 using namespace llvm;
@@ -1165,6 +1166,14 @@ static bool isSafeToEliminateVarargsCast(const CallSite CS,
   if (!CI->isLosslessCast())
     return false;
 
+  // If this is a GC intrinsic, avoid munging types.  We need types for
+  // statepoint reconstruction in SelectionDAG.
+  // TODO: This is probably something which should be expanded to all
+  // intrinsics since the entire point of intrinsics is that
+  // they are understandable by the optimizer.
+  if (isStatepoint(CS) || isGCRelocate(CS) || isGCResult(CS))
+    return false;
+
   // The size of ByVal or InAlloca arguments is derived from the type, so we
   // can't change to a type with a different size.  If the size were
   // passed explicitly we could avoid this check.

diff --git a/llvm/test/CodeGen/X86/statepoint-call-lowering.ll b/llvm/test/CodeGen/X86/statepoint-call-lowering.ll
@@ -0,0 +1,74 @@
+; RUN: llc < %s | FileCheck %s
+; This file contains a collection of basic tests to ensure we didn't
+; screw up normal call lowering when there are no deopt or gc arguments.
+
+target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+declare zeroext i1 @return_i1()
+declare zeroext i32 @return_i32()
+declare i32* @return_i32ptr()
+declare float @return_float()
+
+define i1 @test_i1_return() {
+; CHECK-LABEL: test_i1_return
+; This is just checking that a i1 gets lowered normally when there's no extra
+; state arguments to the statepoint
+; CHECK: pushq %rax
+; CHECK: callq return_i1
+; CHECK: popq %rdx
+; CHECK: retq
+entry:
+  %safepoint_token = tail call i32 (i1 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()* @return_i1, i32 0, i32 0, i32 0)
+  %call1 = call zeroext i1 @llvm.experimental.gc.result.int.i1(i32 %safepoint_token)
+  ret i1 %call1
+}
+
+define i32 @test_i32_return() {
+; CHECK-LABEL: test_i32_return
+; CHECK: pushq %rax
+; CHECK: callq return_i32
+; CHECK: popq %rdx
+; CHECK: retq
+entry:
+  %safepoint_token = tail call i32 (i32 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i32f(i32 ()* @return_i32, i32 0, i32 0, i32 0)
+  %call1 = call zeroext i32 @llvm.experimental.gc.result.int.i32(i32 %safepoint_token)
+  ret i32 %call1
+}
+
+define i32* @test_i32ptr_return() {
+; CHECK-LABEL: test_i32ptr_return
+; CHECK: pushq %rax
+; CHECK: callq return_i32ptr
+; CHECK: popq %rdx
+; CHECK: retq
+entry:
+  %safepoint_token = tail call i32 (i32* ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_p0i32f(i32* ()* @return_i32ptr, i32 0, i32 0, i32 0)
+  %call1 = call i32* @llvm.experimental.gc.result.ptr.p0i32(i32 %safepoint_token)
+  ret i32* %call1
+}
+
+define float @test_float_return() {
+; CHECK-LABEL: test_float_return
+; CHECK: pushq %rax
+; CHECK: callq return_float
+; CHECK: popq %rax
+; CHECK: retq
+entry:
+  %safepoint_token = tail call i32 (float ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_f32f(float ()* @return_float, i32 0, i32 0, i32 0)
+  %call1 = call float @llvm.experimental.gc.result.float.f32(i32 %safepoint_token)
+  ret float %call1
+}
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()*, i32, i32, ...)
+declare i1 @llvm.experimental.gc.result.int.i1(i32)
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_i32f(i32 ()*, i32, i32, ...)
+declare i32 @llvm.experimental.gc.result.int.i32(i32)
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_p0i32f(i32* ()*, i32, i32, ...)
+declare i32* @llvm.experimental.gc.result.ptr.p0i32(i32)
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_f32f(float ()*, i32, i32, ...)
+declare float @llvm.experimental.gc.result.float.f32(i32)
+
diff --git a/llvm/test/CodeGen/X86/statepoint-stack-usage.ll b/llvm/test/CodeGen/X86/statepoint-stack-usage.ll
@@ -0,0 +1,60 @@
+; RUN: llc < %s | FileCheck %s
+
+target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+; This test is checking to make sure that we reuse the same stack slots
+; for GC values spilled over two different call sites.  Since the order
+; of GC arguments differ, niave lowering code would insert loads and 
+; stores to rearrange items on the stack.  We need to make sure (for
+; performance) that this doesn't happen.
+define i32 @back_to_back_calls(i32* %a, i32* %b, i32* %c) #1 {
+; CHECK-LABEL: back_to_back_calls
+; The exact stores don't matter, but there need to be three stack slots created
+; CHECK: movq	%rdx, 16(%rsp)
+; CHECK: movq	%rdi, 8(%rsp)
+; CHECK: movq	%rsi, (%rsp)
+  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
+  %a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
+  %b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
+  %c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
+; CHECK: callq
+; This is the key check.  There should NOT be any memory moves here
+; CHECK-NOT: movq
+  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
+  %a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
+  %b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
+  %c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
+; CHECK: callq
+  ret i32 1
+}
+
+; This test simply checks that minor changes in vm state don't prevent slots
+; being reused for gc values.  
+define i32 @reserve_first(i32* %a, i32* %b, i32* %c) #1 {
+; CHECK-LABEL: reserve_first
+; The exact stores don't matter, but there need to be three stack slots created
+; CHECK: movq	%rdx, 16(%rsp)
+; CHECK: movq	%rdi, 8(%rsp)
+; CHECK: movq	%rsi, (%rsp)
+  %safepoint_token = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0, i32* %a, i32* %b, i32* %c)
+  %a1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 9)
+  %b1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 10)
+  %c1 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token, i32 9, i32 11)
+; CHECK: callq
+; This is the key check.  There should NOT be any memory moves here
+; CHECK-NOT: movq
+  %safepoint_token2 = tail call i32 (void ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()* undef, i32 0, i32 0, i32 5, i32* %a1, i32 0, i32* %c1, i32 0, i32 0, i32* %c1, i32* %b1, i32* %a1)
+  %a2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 11)
+  %b2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 10)
+  %c2 = tail call coldcc i32* @llvm.experimental.gc.relocate.p0i32(i32 %safepoint_token2, i32 9, i32 9)
+; CHECK: callq
+  ret i32 1
+}
+
+; Function Attrs: nounwind
+declare i32* @llvm.experimental.gc.relocate.p0i32(i32, i32, i32) #3
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_isVoidf(void ()*, i32, i32, ...)
+
+attributes #1 = { uwtable }
diff --git a/llvm/test/CodeGen/X86/statepoint-stackmap-format.ll b/llvm/test/CodeGen/X86/statepoint-stackmap-format.ll
@@ -0,0 +1,111 @@
+; RUN: llc < %s | FileCheck %s
+; This test is a sanity check to ensure statepoints are generating StackMap
+; sections correctly.  This is not intended to be a rigorous test of the 
+; StackMap format (see the stackmap tests for that).
+
+target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+declare zeroext i1 @return_i1()
+
+define i1 @test(i32 addrspace(1)* %ptr) {
+; CHECK-LABEL: test
+; Do we see one spill for the local value and the store to the
+; alloca?
+; CHECK: subq	$24, %rsp
+; CHECK: movq	$0, 8(%rsp)
+; CHECK: movq	%rdi, (%rsp)
+; CHECK: callq return_i1
+; CHECK: addq	$24, %rsp
+; CHECK: retq
+entry:
+  %metadata1 = alloca i32 addrspace(1)*, i32 2, align 8
+  store i32 addrspace(1)* null, i32 addrspace(1)** %metadata1
+; NOTE: Currently NOT testing alloca lowering in the StackMap format.  Its 
+; known to be broken.  
+  %safepoint_token = tail call i32 (i1 ()*, i32, i32, ...)* @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()* @return_i1, i32 0, i32 0, i32 2, i32 addrspace(1)* %ptr, i32 addrspace(1)* null)
+  %call1 = call zeroext i1 @llvm.experimental.gc.result.int.i1(i32 %safepoint_token)
+  %a = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 4, i32 4)
+  %b = call i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32 %safepoint_token, i32 5, i32 5)
+; 
+  ret i1 %call1
+}
+
+declare i32 @llvm.experimental.gc.statepoint.p0f_i1f(i1 ()*, i32, i32, ...)
+declare i1 @llvm.experimental.gc.result.int.i1(i32)
+declare i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(i32, i32, i32) #3
+
+
+; CHECK-LABEL: .section .llvm_stackmaps
+; CHECK-NEXT:  __LLVM_StackMaps:
+; Header
+; CHECK-NEXT:   .byte 1
+; CHECK-NEXT:   .byte 0
+; CHECK-NEXT:   .short 0
+; Num Functions
+; CHECK-NEXT:   .long 1
+; Num LargeConstants
+; CHECK-NEXT:   .long 0
+; Num Callsites
+; CHECK-NEXT:   .long 1
+
+; Functions and stack size
+; CHECK-NEXT:   .quad test
+; CHECK-NEXT:   .quad 24
+
+; Large Constants
+; Statepoint ID only
+; CHECK: .quad	2882400000
+
+; Callsites
+; Constant arguments
+; CHECK: .long	.Ltmp1-test
+; CHECK: .short	0
+; CHECK: .short	8
+; SmallConstant (0)
+; CHECK: .byte	4
+; CHECK: .byte	8
+; CHECK: .short	0
+; CHECK: .long	0
+; SmallConstant (2)
+; CHECK: .byte	4
+; CHECK: .byte	8
+; CHECK: .short	0
+; CHECK: .long	2
+; Direct Spill Slot [RSP+0]
+; CHECK: .byte	2
+; CHECK: .byte	8
+; CHECK: .short	7
+; CHECK: .long	0
+; SmallConstant  (0)
+; CHECK: .byte	4
+; CHECK: .byte	8
+; CHECK: .short	0
+; CHECK: .long	0
+; SmallConstant  (0)
+; CHECK: .byte	4
+; CHECK: .byte	8
+; CHECK: .short	0
+; CHECK: .long	0
+; SmallConstant  (0)
+; CHECK: .byte	4
+; CHECK: .byte	8
+; CHECK: .short	0
+; CHECK: .long	0
+; Direct Spill Slot [RSP+0]
+; CHECK: .byte	2
+; CHECK: .byte	8
+; CHECK: .short	7
+; CHECK: .long	0
+; Direct Spill Slot [RSP+0]
+; CHECK: .byte	2
+; CHECK: .byte	8
+; CHECK: .short	7
+; CHECK: .long	0
+
+; No Padding or LiveOuts
+; CHECK: .short	0
+; CHECK: .short	0
+; CHECK: .align	8
+
+