[llvm-branch-commits] [clang] 363720c - [X86] Add a Pass that builds a Condensed CFG for Load Value Injection (LVI) Gadgets

Tom Stellard via llvm-branch-commits llvm-branch-commits at lists.llvm.org
Wed Jun 24 09:36:07 PDT 2020


Author: Scott Constable
Date: 2020-06-24T09:31:04-07:00
New Revision: 363720c2b0f60b512c5f5b8bfbf010f86d078152

URL: https://github.com/llvm/llvm-project/commit/363720c2b0f60b512c5f5b8bfbf010f86d078152
DIFF: https://github.com/llvm/llvm-project/commit/363720c2b0f60b512c5f5b8bfbf010f86d078152.diff

LOG: [X86] Add a Pass that builds a Condensed CFG for Load Value Injection (LVI) Gadgets

Adds a new data structure, ImmutableGraph, and uses RDF to find LVI gadgets and add them to a MachineGadgetGraph.

More specifically, a new X86 machine pass finds Load Value Injection (LVI) gadgets consisting of a load from memory (i.e., SOURCE), and any operation that may transmit the value loaded from memory over a covert channel, or use the value loaded from memory to determine a branch/call target (i.e., SINK).

Also adds a new target feature to X86: +lvi-load-hardening

The feature can be added via the clang CLI using -mlvi-hardening.

Differential Revision: https://reviews.llvm.org/D75936

Added: 
    llvm/lib/Target/X86/ImmutableGraph.h
    llvm/lib/Target/X86/X86LoadValueInjectionLoadHardening.cpp
    llvm/test/CodeGen/X86/lvi-hardening-gadget-graph.ll

Modified: 
    clang/include/clang/Driver/Options.td
    clang/lib/Driver/ToolChains/Arch/X86.cpp
    clang/test/Driver/x86-target-features.c
    llvm/lib/Target/X86/CMakeLists.txt
    llvm/lib/Target/X86/X86.h
    llvm/lib/Target/X86/X86.td
    llvm/lib/Target/X86/X86Subtarget.h
    llvm/lib/Target/X86/X86TargetMachine.cpp
    llvm/test/CodeGen/X86/O0-pipeline.ll
    llvm/test/CodeGen/X86/O3-pipeline.ll

Removed: 
    


################################################################################
diff  --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index f57effa2c40e..391c895a453b 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -2267,6 +2267,10 @@ def mspeculative_load_hardening : Flag<["-"], "mspeculative-load-hardening">,
   Group<m_Group>, Flags<[CoreOption,CC1Option]>;
 def mno_speculative_load_hardening : Flag<["-"], "mno-speculative-load-hardening">,
   Group<m_Group>, Flags<[CoreOption]>;
+def mlvi_hardening : Flag<["-"], "mlvi-hardening">, Group<m_Group>, Flags<[CoreOption,DriverOption]>,
+  HelpText<"Enable all mitigations for Load Value Injection (LVI)">;
+def mno_lvi_hardening : Flag<["-"], "mno-lvi-hardening">, Group<m_Group>, Flags<[CoreOption,DriverOption]>,
+  HelpText<"Disable mitigations for Load Value Injection (LVI)">;
 def mlvi_cfi : Flag<["-"], "mlvi-cfi">, Group<m_Group>, Flags<[CoreOption,DriverOption]>,
   HelpText<"Enable only control-flow mitigations for Load Value Injection (LVI)">;
 def mno_lvi_cfi : Flag<["-"], "mno-lvi-cfi">, Group<m_Group>, Flags<[CoreOption,DriverOption]>,

diff  --git a/clang/lib/Driver/ToolChains/Arch/X86.cpp b/clang/lib/Driver/ToolChains/Arch/X86.cpp
index 477e04485bf1..d170b7ac3a77 100644
--- a/clang/lib/Driver/ToolChains/Arch/X86.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/X86.cpp
@@ -173,7 +173,13 @@ void x86::getX86TargetFeatures(const Driver &D, const llvm::Triple &Triple,
   }
 
   auto LVIOpt = clang::driver::options::ID::OPT_INVALID;
-  if (Args.hasFlag(options::OPT_mlvi_cfi, options::OPT_mno_lvi_cfi, false)) {
+  if (Args.hasFlag(options::OPT_mlvi_hardening, options::OPT_mno_lvi_hardening,
+                   false)) {
+    Features.push_back("+lvi-load-hardening");
+    Features.push_back("+lvi-cfi"); // load hardening implies CFI protection
+    LVIOpt = options::OPT_mlvi_hardening;
+  } else if (Args.hasFlag(options::OPT_mlvi_cfi, options::OPT_mno_lvi_cfi,
+                          false)) {
     Features.push_back("+lvi-cfi");
     LVIOpt = options::OPT_mlvi_cfi;
   }

diff  --git a/clang/test/Driver/x86-target-features.c b/clang/test/Driver/x86-target-features.c
index 4f133b5dd683..fd9bf0878693 100644
--- a/clang/test/Driver/x86-target-features.c
+++ b/clang/test/Driver/x86-target-features.c
@@ -166,6 +166,18 @@
 // RUN: %clang -target i386-linux-gnu -mlvi-cfi -mretpoline-external-thunk %s -### -o %t.o 2>&1 | FileCheck -check-prefix=LVICFI-RETPOLINE-EXTERNAL-THUNK %s
 // LVICFI-RETPOLINE-EXTERNAL-THUNK: error: invalid argument 'mretpoline-external-thunk' not allowed with 'mlvi-cfi'
 
+// RUN: %clang -target i386-linux-gnu -mlvi-hardening %s -### -o %t.o 2>&1 | FileCheck -check-prefix=LVIHARDENING %s
+// RUN: %clang -target i386-linux-gnu -mno-lvi-hardening %s -### -o %t.o 2>&1 | FileCheck -check-prefix=NO-LVIHARDENING %s
+// LVIHARDENING: "-target-feature" "+lvi-load-hardening" "-target-feature" "+lvi-cfi"
+// NO-LVIHARDENING-NOT: lvi
+
+// RUN: %clang -target i386-linux-gnu -mlvi-hardening -mspeculative-load-hardening %s -### -o %t.o 2>&1 | FileCheck -check-prefix=LVIHARDENING-SLH %s
+// LVIHARDENING-SLH: error: invalid argument 'mspeculative-load-hardening' not allowed with 'mlvi-hardening'
+// RUN: %clang -target i386-linux-gnu -mlvi-hardening -mretpoline %s -### -o %t.o 2>&1 | FileCheck -check-prefix=LVIHARDENING-RETPOLINE %s
+// LVIHARDENING-RETPOLINE: error: invalid argument 'mretpoline' not allowed with 'mlvi-hardening'
+// RUN: %clang -target i386-linux-gnu -mlvi-hardening -mretpoline-external-thunk %s -### -o %t.o 2>&1 | FileCheck -check-prefix=LVIHARDENING-RETPOLINE-EXTERNAL-THUNK %s
+// LVIHARDENING-RETPOLINE-EXTERNAL-THUNK: error: invalid argument 'mretpoline-external-thunk' not allowed with 'mlvi-hardening'
+
 // RUN: %clang -target i386-linux-gnu -mwaitpkg %s -### -o %t.o 2>&1 | FileCheck -check-prefix=WAITPKG %s
 // RUN: %clang -target i386-linux-gnu -mno-waitpkg %s -### -o %t.o 2>&1 | FileCheck -check-prefix=NO-WAITPKG %s
 // WAITPKG: "-target-feature" "+waitpkg"

diff  --git a/llvm/lib/Target/X86/CMakeLists.txt b/llvm/lib/Target/X86/CMakeLists.txt
index 6b60aaf6d855..524e043c7df8 100644
--- a/llvm/lib/Target/X86/CMakeLists.txt
+++ b/llvm/lib/Target/X86/CMakeLists.txt
@@ -52,6 +52,7 @@ set(sources
   X86InstrInfo.cpp
   X86EvexToVex.cpp
   X86LegalizerInfo.cpp
+  X86LoadValueInjectionLoadHardening.cpp
   X86LoadValueInjectionRetHardening.cpp
   X86MCInstLower.cpp
   X86MachineFunctionInfo.cpp

diff  --git a/llvm/lib/Target/X86/ImmutableGraph.h b/llvm/lib/Target/X86/ImmutableGraph.h
new file mode 100644
index 000000000000..5833017037a5
--- /dev/null
+++ b/llvm/lib/Target/X86/ImmutableGraph.h
@@ -0,0 +1,446 @@
+//==========-- ImmutableGraph.h - A fast DAG implementation ---------=========//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// Description: ImmutableGraph is a fast DAG implementation that cannot be
+/// modified, except by creating a new ImmutableGraph. ImmutableGraph is
+/// implemented as two arrays: one containing nodes, and one containing edges.
+/// The advantages to this implementation are two-fold:
+/// 1. Iteration and traversal operations benefit from cache locality.
+/// 2. Operations on sets of nodes/edges are efficient, and representations of
+///    those sets in memory are compact. For instance, a set of edges is
+///    implemented as a bit vector, wherein each bit corresponds to one edge in
+///    the edge array. This implies a lower bound of 64x spatial improvement
+///    over, e.g., an llvm::DenseSet or llvm::SmallSet. It also means that
+///    insert/erase/contains operations complete in negligible constant time:
+///    insert and erase require one load and one store, and contains requires
+///    just one load.
+///
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIB_TARGET_X86_IMMUTABLEGRAPH_H
+#define LLVM_LIB_TARGET_X86_IMMUTABLEGRAPH_H
+
+#include "llvm/ADT/BitVector.h"
+#include "llvm/ADT/GraphTraits.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Support/raw_ostream.h"
+#include <algorithm>
+#include <iterator>
+#include <utility>
+#include <vector>
+
+namespace llvm {
+
+template <typename NodeValueT, typename EdgeValueT> class ImmutableGraph {
+  using Traits = GraphTraits<ImmutableGraph<NodeValueT, EdgeValueT> *>;
+  template <typename> friend class ImmutableGraphBuilder;
+
+public:
+  using node_value_type = NodeValueT;
+  using edge_value_type = EdgeValueT;
+  using size_type = int;
+  class Node;
+  class Edge {
+    friend class ImmutableGraph;
+    template <typename> friend class ImmutableGraphBuilder;
+
+    const Node *Dest;
+    edge_value_type Value;
+
+  public:
+    const Node *getDest() const { return Dest; };
+    const edge_value_type &getValue() const { return Value; }
+  };
+  class Node {
+    friend class ImmutableGraph;
+    template <typename> friend class ImmutableGraphBuilder;
+
+    const Edge *Edges;
+    node_value_type Value;
+
+  public:
+    const node_value_type &getValue() const { return Value; }
+
+    const Edge *edges_begin() const { return Edges; }
+    // Nodes are allocated sequentially. Edges for a node are stored together.
+    // The end of this Node's edges is the beginning of the next node's edges.
+    // An extra node was allocated to hold the end pointer for the last real
+    // node.
+    const Edge *edges_end() const { return (this + 1)->Edges; }
+    ArrayRef<Edge> edges() const {
+      return makeArrayRef(edges_begin(), edges_end());
+    }
+  };
+
+protected:
+  ImmutableGraph(std::unique_ptr<Node[]> Nodes, std::unique_ptr<Edge[]> Edges,
+                 size_type NodesSize, size_type EdgesSize)
+      : Nodes(std::move(Nodes)), Edges(std::move(Edges)), NodesSize(NodesSize),
+        EdgesSize(EdgesSize) {}
+  ImmutableGraph(const ImmutableGraph &) = delete;
+  ImmutableGraph(ImmutableGraph &&) = delete;
+  ImmutableGraph &operator=(const ImmutableGraph &) = delete;
+  ImmutableGraph &operator=(ImmutableGraph &&) = delete;
+
+public:
+  ArrayRef<Node> nodes() const { return makeArrayRef(Nodes.get(), NodesSize); }
+  const Node *nodes_begin() const { return nodes().begin(); }
+  const Node *nodes_end() const { return nodes().end(); }
+
+  ArrayRef<Edge> edges() const { return makeArrayRef(Edges.get(), EdgesSize); }
+  const Edge *edges_begin() const { return edges().begin(); }
+  const Edge *edges_end() const { return edges().end(); }
+
+  size_type nodes_size() const { return NodesSize; }
+  size_type edges_size() const { return EdgesSize; }
+
+  // Node N must belong to this ImmutableGraph.
+  size_type getNodeIndex(const Node &N) const {
+    return std::distance(nodes_begin(), &N);
+  }
+  // Edge E must belong to this ImmutableGraph.
+  size_type getEdgeIndex(const Edge &E) const {
+    return std::distance(edges_begin(), &E);
+  }
+
+  // FIXME: Could NodeSet and EdgeSet be templated to share code?
+  class NodeSet {
+    const ImmutableGraph &G;
+    BitVector V;
+
+  public:
+    NodeSet(const ImmutableGraph &G, bool ContainsAll = false)
+        : G{G}, V{static_cast<unsigned>(G.nodes_size()), ContainsAll} {}
+    bool insert(const Node &N) {
+      size_type Idx = G.getNodeIndex(N);
+      bool AlreadyExists = V.test(Idx);
+      V.set(Idx);
+      return !AlreadyExists;
+    }
+    void erase(const Node &N) {
+      size_type Idx = G.getNodeIndex(N);
+      V.reset(Idx);
+    }
+    bool contains(const Node &N) const {
+      size_type Idx = G.getNodeIndex(N);
+      return V.test(Idx);
+    }
+    void clear() { V.reset(); }
+    size_type empty() const { return V.none(); }
+    /// Return the number of elements in the set
+    size_type count() const { return V.count(); }
+    /// Return the size of the set's domain
+    size_type size() const { return V.size(); }
+    /// Set union
+    NodeSet &operator|=(const NodeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V |= RHS.V;
+      return *this;
+    }
+    /// Set intersection
+    NodeSet &operator&=(const NodeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V &= RHS.V;
+      return *this;
+    }
+    /// Set disjoint union
+    NodeSet &operator^=(const NodeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V ^= RHS.V;
+      return *this;
+    }
+
+    using index_iterator = typename BitVector::const_set_bits_iterator;
+    index_iterator index_begin() const { return V.set_bits_begin(); }
+    index_iterator index_end() const { return V.set_bits_end(); }
+    void set(size_type Idx) { V.set(Idx); }
+    void reset(size_type Idx) { V.reset(Idx); }
+
+    class iterator {
+      const NodeSet &Set;
+      size_type Current;
+
+      void advance() {
+        assert(Current != -1);
+        Current = Set.V.find_next(Current);
+      }
+
+    public:
+      iterator(const NodeSet &Set, size_type Begin)
+          : Set{Set}, Current{Begin} {}
+      iterator operator++(int) {
+        iterator Tmp = *this;
+        advance();
+        return Tmp;
+      }
+      iterator &operator++() {
+        advance();
+        return *this;
+      }
+      Node *operator*() const {
+        assert(Current != -1);
+        return Set.G.nodes_begin() + Current;
+      }
+      bool operator==(const iterator &other) const {
+        assert(&this->Set == &other.Set);
+        return this->Current == other.Current;
+      }
+      bool operator!=(const iterator &other) const { return !(*this == other); }
+    };
+
+    iterator begin() const { return iterator{*this, V.find_first()}; }
+    iterator end() const { return iterator{*this, -1}; }
+  };
+
+  class EdgeSet {
+    const ImmutableGraph &G;
+    BitVector V;
+
+  public:
+    EdgeSet(const ImmutableGraph &G, bool ContainsAll = false)
+        : G{G}, V{static_cast<unsigned>(G.edges_size()), ContainsAll} {}
+    bool insert(const Edge &E) {
+      size_type Idx = G.getEdgeIndex(E);
+      bool AlreadyExists = V.test(Idx);
+      V.set(Idx);
+      return !AlreadyExists;
+    }
+    void erase(const Edge &E) {
+      size_type Idx = G.getEdgeIndex(E);
+      V.reset(Idx);
+    }
+    bool contains(const Edge &E) const {
+      size_type Idx = G.getEdgeIndex(E);
+      return V.test(Idx);
+    }
+    void clear() { V.reset(); }
+    bool empty() const { return V.none(); }
+    /// Return the number of elements in the set
+    size_type count() const { return V.count(); }
+    /// Return the size of the set's domain
+    size_type size() const { return V.size(); }
+    /// Set union
+    EdgeSet &operator|=(const EdgeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V |= RHS.V;
+      return *this;
+    }
+    /// Set intersection
+    EdgeSet &operator&=(const EdgeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V &= RHS.V;
+      return *this;
+    }
+    /// Set disjoint union
+    EdgeSet &operator^=(const EdgeSet &RHS) {
+      assert(&this->G == &RHS.G);
+      V ^= RHS.V;
+      return *this;
+    }
+
+    using index_iterator = typename BitVector::const_set_bits_iterator;
+    index_iterator index_begin() const { return V.set_bits_begin(); }
+    index_iterator index_end() const { return V.set_bits_end(); }
+    void set(size_type Idx) { V.set(Idx); }
+    void reset(size_type Idx) { V.reset(Idx); }
+
+    class iterator {
+      const EdgeSet &Set;
+      size_type Current;
+
+      void advance() {
+        assert(Current != -1);
+        Current = Set.V.find_next(Current);
+      }
+
+    public:
+      iterator(const EdgeSet &Set, size_type Begin)
+          : Set{Set}, Current{Begin} {}
+      iterator operator++(int) {
+        iterator Tmp = *this;
+        advance();
+        return Tmp;
+      }
+      iterator &operator++() {
+        advance();
+        return *this;
+      }
+      Edge *operator*() const {
+        assert(Current != -1);
+        return Set.G.edges_begin() + Current;
+      }
+      bool operator==(const iterator &other) const {
+        assert(&this->Set == &other.Set);
+        return this->Current == other.Current;
+      }
+      bool operator!=(const iterator &other) const { return !(*this == other); }
+    };
+
+    iterator begin() const { return iterator{*this, V.find_first()}; }
+    iterator end() const { return iterator{*this, -1}; }
+  };
+
+private:
+  std::unique_ptr<Node[]> Nodes;
+  std::unique_ptr<Edge[]> Edges;
+  size_type NodesSize;
+  size_type EdgesSize;
+};
+
+template <typename GraphT> class ImmutableGraphBuilder {
+  using node_value_type = typename GraphT::node_value_type;
+  using edge_value_type = typename GraphT::edge_value_type;
+  static_assert(
+      std::is_base_of<ImmutableGraph<node_value_type, edge_value_type>,
+                      GraphT>::value,
+      "Template argument to ImmutableGraphBuilder must derive from "
+      "ImmutableGraph<>");
+  using size_type = typename GraphT::size_type;
+  using NodeSet = typename GraphT::NodeSet;
+  using Node = typename GraphT::Node;
+  using EdgeSet = typename GraphT::EdgeSet;
+  using Edge = typename GraphT::Edge;
+  using BuilderEdge = std::pair<edge_value_type, size_type>;
+  using EdgeList = std::vector<BuilderEdge>;
+  using BuilderVertex = std::pair<node_value_type, EdgeList>;
+  using VertexVec = std::vector<BuilderVertex>;
+
+public:
+  using BuilderNodeRef = size_type;
+
+  BuilderNodeRef addVertex(const node_value_type &V) {
+    auto I = AdjList.emplace(AdjList.end(), V, EdgeList{});
+    return std::distance(AdjList.begin(), I);
+  }
+
+  void addEdge(const edge_value_type &E, BuilderNodeRef From,
+               BuilderNodeRef To) {
+    AdjList[From].second.emplace_back(E, To);
+  }
+
+  bool empty() const { return AdjList.empty(); }
+
+  template <typename... ArgT> std::unique_ptr<GraphT> get(ArgT &&... Args) {
+    size_type VertexSize = AdjList.size(), EdgeSize = 0;
+    for (const auto &V : AdjList) {
+      EdgeSize += V.second.size();
+    }
+    auto VertexArray =
+        std::make_unique<Node[]>(VertexSize + 1 /* terminator node */);
+    auto EdgeArray = std::make_unique<Edge[]>(EdgeSize);
+    size_type VI = 0, EI = 0;
+    for (; VI < VertexSize; ++VI) {
+      VertexArray[VI].Value = std::move(AdjList[VI].first);
+      VertexArray[VI].Edges = &EdgeArray[EI];
+      auto NumEdges = static_cast<size_type>(AdjList[VI].second.size());
+      for (size_type VEI = 0; VEI < NumEdges; ++VEI, ++EI) {
+        auto &E = AdjList[VI].second[VEI];
+        EdgeArray[EI].Value = std::move(E.first);
+        EdgeArray[EI].Dest = &VertexArray[E.second];
+      }
+    }
+    assert(VI == VertexSize && EI == EdgeSize && "ImmutableGraph malformed");
+    VertexArray[VI].Edges = &EdgeArray[EdgeSize]; // terminator node
+    return std::make_unique<GraphT>(std::move(VertexArray),
+                                    std::move(EdgeArray), VertexSize, EdgeSize,
+                                    std::forward<ArgT>(Args)...);
+  }
+
+  template <typename... ArgT>
+  static std::unique_ptr<GraphT> trim(const GraphT &G, const NodeSet &TrimNodes,
+                                      const EdgeSet &TrimEdges,
+                                      ArgT &&... Args) {
+    size_type NewVertexSize = G.nodes_size() - TrimNodes.count();
+    size_type NewEdgeSize = G.edges_size() - TrimEdges.count();
+    auto NewVertexArray =
+        std::make_unique<Node[]>(NewVertexSize + 1 /* terminator node */);
+    auto NewEdgeArray = std::make_unique<Edge[]>(NewEdgeSize);
+
+    // Walk the nodes and determine the new index for each node.
+    size_type NewNodeIndex = 0;
+    std::vector<size_type> RemappedNodeIndex(G.nodes_size());
+    for (const Node &N : G.nodes()) {
+      if (TrimNodes.contains(N))
+        continue;
+      RemappedNodeIndex[G.getNodeIndex(N)] = NewNodeIndex++;
+    }
+    assert(NewNodeIndex == NewVertexSize &&
+           "Should have assigned NewVertexSize indices");
+
+    size_type VertexI = 0, EdgeI = 0;
+    for (const Node &N : G.nodes()) {
+      if (TrimNodes.contains(N))
+        continue;
+      NewVertexArray[VertexI].Value = N.getValue();
+      NewVertexArray[VertexI].Edges = &NewEdgeArray[EdgeI];
+      for (const Edge &E : N.edges()) {
+        if (TrimEdges.contains(E))
+          continue;
+        NewEdgeArray[EdgeI].Value = E.getValue();
+        size_type DestIdx = G.getNodeIndex(*E.getDest());
+        size_type NewIdx = RemappedNodeIndex[DestIdx];
+        assert(NewIdx < NewVertexSize);
+        NewEdgeArray[EdgeI].Dest = &NewVertexArray[NewIdx];
+        ++EdgeI;
+      }
+      ++VertexI;
+    }
+    assert(VertexI == NewVertexSize && EdgeI == NewEdgeSize &&
+           "Gadget graph malformed");
+    NewVertexArray[VertexI].Edges = &NewEdgeArray[NewEdgeSize]; // terminator
+    return std::make_unique<GraphT>(std::move(NewVertexArray),
+                                    std::move(NewEdgeArray), NewVertexSize,
+                                    NewEdgeSize, std::forward<ArgT>(Args)...);
+  }
+
+private:
+  VertexVec AdjList;
+};
+
+template <typename NodeValueT, typename EdgeValueT>
+struct GraphTraits<ImmutableGraph<NodeValueT, EdgeValueT> *> {
+  using GraphT = ImmutableGraph<NodeValueT, EdgeValueT>;
+  using NodeRef = typename GraphT::Node const *;
+  using EdgeRef = typename GraphT::Edge const &;
+
+  static NodeRef edge_dest(EdgeRef E) { return E.getDest(); }
+  using ChildIteratorType =
+      mapped_iterator<typename GraphT::Edge const *, decltype(&edge_dest)>;
+
+  static NodeRef getEntryNode(GraphT *G) { return G->nodes_begin(); }
+  static ChildIteratorType child_begin(NodeRef N) {
+    return {N->edges_begin(), &edge_dest};
+  }
+  static ChildIteratorType child_end(NodeRef N) {
+    return {N->edges_end(), &edge_dest};
+  }
+
+  static NodeRef getNode(typename GraphT::Node const &N) { return NodeRef{&N}; }
+  using nodes_iterator =
+      mapped_iterator<typename GraphT::Node const *, decltype(&getNode)>;
+  static nodes_iterator nodes_begin(GraphT *G) {
+    return {G->nodes_begin(), &getNode};
+  }
+  static nodes_iterator nodes_end(GraphT *G) {
+    return {G->nodes_end(), &getNode};
+  }
+
+  using ChildEdgeIteratorType = typename GraphT::Edge const *;
+
+  static ChildEdgeIteratorType child_edge_begin(NodeRef N) {
+    return N->edges_begin();
+  }
+  static ChildEdgeIteratorType child_edge_end(NodeRef N) {
+    return N->edges_end();
+  }
+  static typename GraphT::size_type size(GraphT *G) { return G->nodes_size(); }
+};
+
+} // end namespace llvm
+
+#endif // LLVM_LIB_TARGET_X86_IMMUTABLEGRAPH_H

diff  --git a/llvm/lib/Target/X86/X86.h b/llvm/lib/Target/X86/X86.h
index 06b8ae8754aa..39b2f814defa 100644
--- a/llvm/lib/Target/X86/X86.h
+++ b/llvm/lib/Target/X86/X86.h
@@ -133,6 +133,7 @@ InstructionSelector *createX86InstructionSelector(const X86TargetMachine &TM,
                                                   X86Subtarget &,
                                                   X86RegisterBankInfo &);
 
+FunctionPass *createX86LoadValueInjectionLoadHardeningPass();
 FunctionPass *createX86LoadValueInjectionRetHardeningPass();
 FunctionPass *createX86SpeculativeLoadHardeningPass();
 
@@ -149,6 +150,7 @@ void initializeX86DomainReassignmentPass(PassRegistry &);
 void initializeX86ExecutionDomainFixPass(PassRegistry &);
 void initializeX86ExpandPseudoPass(PassRegistry &);
 void initializeX86FlagsCopyLoweringPassPass(PassRegistry &);
+void initializeX86LoadValueInjectionLoadHardeningPassPass(PassRegistry &);
 void initializeX86LoadValueInjectionRetHardeningPassPass(PassRegistry &);
 void initializeX86OptimizeLEAPassPass(PassRegistry &);
 void initializeX86SpeculativeLoadHardeningPassPass(PassRegistry &);

diff  --git a/llvm/lib/Target/X86/X86.td b/llvm/lib/Target/X86/X86.td
index edc474825760..bb8952f54e3a 100644
--- a/llvm/lib/Target/X86/X86.td
+++ b/llvm/lib/Target/X86/X86.td
@@ -435,6 +435,13 @@ def FeatureLVIControlFlowIntegrity
           "LFENCE instruction to serialize control flow. Also decompose RET "
           "instructions into a POP+LFENCE+JMP sequence.">;
 
+// Mitigate LVI attacks against data loads
+def FeatureLVILoadHardening
+    : SubtargetFeature<
+          "lvi-load-hardening", "UseLVILoadHardening", "true",
+          "Insert LFENCE instructions to prevent data speculatively injected "
+          "into loads from being used maliciously.">;
+
 // Direct Move instructions.
 def FeatureMOVDIRI  : SubtargetFeature<"movdiri", "HasMOVDIRI", "true",
                                        "Support movdiri instruction">;

diff  --git a/llvm/lib/Target/X86/X86LoadValueInjectionLoadHardening.cpp b/llvm/lib/Target/X86/X86LoadValueInjectionLoadHardening.cpp
new file mode 100644
index 000000000000..563b225c5ef9
--- /dev/null
+++ b/llvm/lib/Target/X86/X86LoadValueInjectionLoadHardening.cpp
@@ -0,0 +1,521 @@
+//==-- X86LoadValueInjectionLoadHardening.cpp - LVI load hardening for x86 --=//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+///
+/// Description: This pass finds Load Value Injection (LVI) gadgets consisting
+/// of a load from memory (i.e., SOURCE), and any operation that may transmit
+/// the value loaded from memory over a covert channel, or use the value loaded
+/// from memory to determine a branch/call target (i.e., SINK).
+///
+//===----------------------------------------------------------------------===//
+
+#include "ImmutableGraph.h"
+#include "X86.h"
+#include "X86Subtarget.h"
+#include "X86TargetMachine.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/Statistic.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineDominanceFrontier.h"
+#include "llvm/CodeGen/MachineDominators.h"
+#include "llvm/CodeGen/MachineFunction.h"
+#include "llvm/CodeGen/MachineFunctionPass.h"
+#include "llvm/CodeGen/MachineInstr.h"
+#include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineLoopInfo.h"
+#include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/RDFGraph.h"
+#include "llvm/CodeGen/RDFLiveness.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/DOTGraphTraits.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/GraphWriter.h"
+#include "llvm/Support/raw_ostream.h"
+
+using namespace llvm;
+
+#define PASS_KEY "x86-lvi-load"
+#define DEBUG_TYPE PASS_KEY
+
+STATISTIC(NumFunctionsConsidered, "Number of functions analyzed");
+STATISTIC(NumFunctionsMitigated, "Number of functions for which mitigations "
+                                 "were deployed");
+STATISTIC(NumGadgets, "Number of LVI gadgets detected during analysis");
+
+static cl::opt<bool> NoConditionalBranches(
+    PASS_KEY "-no-cbranch",
+    cl::desc("Don't treat conditional branches as disclosure gadgets. This "
+             "may improve performance, at the cost of security."),
+    cl::init(false), cl::Hidden);
+
+static cl::opt<bool> EmitDot(
+    PASS_KEY "-dot",
+    cl::desc(
+        "For each function, emit a dot graph depicting potential LVI gadgets"),
+    cl::init(false), cl::Hidden);
+
+static cl::opt<bool> EmitDotOnly(
+    PASS_KEY "-dot-only",
+    cl::desc("For each function, emit a dot graph depicting potential LVI "
+             "gadgets, and do not insert any fences"),
+    cl::init(false), cl::Hidden);
+
+static cl::opt<bool> EmitDotVerify(
+    PASS_KEY "-dot-verify",
+    cl::desc("For each function, emit a dot graph to stdout depicting "
+             "potential LVI gadgets, used for testing purposes only"),
+    cl::init(false), cl::Hidden);
+
+namespace {
+
+struct MachineGadgetGraph : ImmutableGraph<MachineInstr *, int> {
+  static constexpr int GadgetEdgeSentinel = -1;
+  static constexpr MachineInstr *const ArgNodeSentinel = nullptr;
+
+  using GraphT = ImmutableGraph<MachineInstr *, int>;
+  using Node = typename GraphT::Node;
+  using Edge = typename GraphT::Edge;
+  using size_type = typename GraphT::size_type;
+  MachineGadgetGraph(std::unique_ptr<Node[]> Nodes,
+                     std::unique_ptr<Edge[]> Edges, size_type NodesSize,
+                     size_type EdgesSize, int NumFences = 0, int NumGadgets = 0)
+      : GraphT(std::move(Nodes), std::move(Edges), NodesSize, EdgesSize),
+        NumFences(NumFences), NumGadgets(NumGadgets) {}
+  static inline bool isCFGEdge(const Edge &E) {
+    return E.getValue() != GadgetEdgeSentinel;
+  }
+  static inline bool isGadgetEdge(const Edge &E) {
+    return E.getValue() == GadgetEdgeSentinel;
+  }
+  int NumFences;
+  int NumGadgets;
+};
+
+class X86LoadValueInjectionLoadHardeningPass : public MachineFunctionPass {
+public:
+  X86LoadValueInjectionLoadHardeningPass() : MachineFunctionPass(ID) {}
+
+  StringRef getPassName() const override {
+    return "X86 Load Value Injection (LVI) Load Hardening";
+  }
+  void getAnalysisUsage(AnalysisUsage &AU) const override;
+  bool runOnMachineFunction(MachineFunction &MF) override;
+
+  static char ID;
+
+private:
+  using GraphBuilder = ImmutableGraphBuilder<MachineGadgetGraph>;
+  using EdgeSet = MachineGadgetGraph::EdgeSet;
+  using NodeSet = MachineGadgetGraph::NodeSet;
+  using Gadget = std::pair<MachineInstr *, MachineInstr *>;
+
+  const X86Subtarget *STI;
+  const TargetInstrInfo *TII;
+  const TargetRegisterInfo *TRI;
+
+  std::unique_ptr<MachineGadgetGraph>
+  getGadgetGraph(MachineFunction &MF, const MachineLoopInfo &MLI,
+                 const MachineDominatorTree &MDT,
+                 const MachineDominanceFrontier &MDF) const;
+
+  bool instrUsesRegToAccessMemory(const MachineInstr &I, unsigned Reg) const;
+  bool instrUsesRegToBranch(const MachineInstr &I, unsigned Reg) const;
+  inline bool isFence(const MachineInstr *MI) const {
+    return MI && (MI->getOpcode() == X86::LFENCE ||
+                  (STI->useLVIControlFlowIntegrity() && MI->isCall()));
+  }
+};
+
+} // end anonymous namespace
+
+namespace llvm {
+
+template <>
+struct GraphTraits<MachineGadgetGraph *>
+    : GraphTraits<ImmutableGraph<MachineInstr *, int> *> {};
+
+template <>
+struct DOTGraphTraits<MachineGadgetGraph *> : DefaultDOTGraphTraits {
+  using GraphType = MachineGadgetGraph;
+  using Traits = llvm::GraphTraits<GraphType *>;
+  using NodeRef = typename Traits::NodeRef;
+  using EdgeRef = typename Traits::EdgeRef;
+  using ChildIteratorType = typename Traits::ChildIteratorType;
+  using ChildEdgeIteratorType = typename Traits::ChildEdgeIteratorType;
+
+  DOTGraphTraits(bool isSimple = false) : DefaultDOTGraphTraits(isSimple) {}
+
+  std::string getNodeLabel(NodeRef Node, GraphType *) {
+    if (Node->getValue() == MachineGadgetGraph::ArgNodeSentinel)
+      return "ARGS";
+
+    std::string Str;
+    raw_string_ostream OS(Str);
+    OS << *Node->getValue();
+    return OS.str();
+  }
+
+  static std::string getNodeAttributes(NodeRef Node, GraphType *) {
+    MachineInstr *MI = Node->getValue();
+    if (MI == MachineGadgetGraph::ArgNodeSentinel)
+      return "color = blue";
+    if (MI->getOpcode() == X86::LFENCE)
+      return "color = green";
+    return "";
+  }
+
+  static std::string getEdgeAttributes(NodeRef, ChildIteratorType E,
+                                       GraphType *) {
+    int EdgeVal = (*E.getCurrent()).getValue();
+    return EdgeVal >= 0 ? "label = " + std::to_string(EdgeVal)
+                        : "color = red, style = \"dashed\"";
+  }
+};
+
+} // end namespace llvm
+
+constexpr MachineInstr *MachineGadgetGraph::ArgNodeSentinel;
+constexpr int MachineGadgetGraph::GadgetEdgeSentinel;
+
+char X86LoadValueInjectionLoadHardeningPass::ID = 0;
+
+void X86LoadValueInjectionLoadHardeningPass::getAnalysisUsage(
+    AnalysisUsage &AU) const {
+  MachineFunctionPass::getAnalysisUsage(AU);
+  AU.addRequired<MachineLoopInfo>();
+  AU.addRequired<MachineDominatorTree>();
+  AU.addRequired<MachineDominanceFrontier>();
+  AU.setPreservesCFG();
+}
+
+static void WriteGadgetGraph(raw_ostream &OS, MachineFunction &MF,
+                             MachineGadgetGraph *G) {
+  WriteGraph(OS, G, /*ShortNames*/ false,
+             "Speculative gadgets for \"" + MF.getName() + "\" function");
+}
+
+bool X86LoadValueInjectionLoadHardeningPass::runOnMachineFunction(
+    MachineFunction &MF) {
+  LLVM_DEBUG(dbgs() << "***** " << getPassName() << " : " << MF.getName()
+                    << " *****\n");
+  STI = &MF.getSubtarget<X86Subtarget>();
+  if (!STI->useLVILoadHardening())
+    return false;
+
+  // FIXME: support 32-bit
+  if (!STI->is64Bit())
+    report_fatal_error("LVI load hardening is only supported on 64-bit", false);
+
+  // Don't skip functions with the "optnone" attr but participate in opt-bisect.
+  const Function &F = MF.getFunction();
+  if (!F.hasOptNone() && skipFunction(F))
+    return false;
+
+  ++NumFunctionsConsidered;
+  TII = STI->getInstrInfo();
+  TRI = STI->getRegisterInfo();
+  LLVM_DEBUG(dbgs() << "Building gadget graph...\n");
+  const auto &MLI = getAnalysis<MachineLoopInfo>();
+  const auto &MDT = getAnalysis<MachineDominatorTree>();
+  const auto &MDF = getAnalysis<MachineDominanceFrontier>();
+  std::unique_ptr<MachineGadgetGraph> Graph = getGadgetGraph(MF, MLI, MDT, MDF);
+  LLVM_DEBUG(dbgs() << "Building gadget graph... Done\n");
+  if (Graph == nullptr)
+    return false; // didn't find any gadgets
+
+  if (EmitDotVerify) {
+    WriteGadgetGraph(outs(), MF, Graph.get());
+    return false;
+  }
+
+  if (EmitDot || EmitDotOnly) {
+    LLVM_DEBUG(dbgs() << "Emitting gadget graph...\n");
+    std::error_code FileError;
+    std::string FileName = "lvi.";
+    FileName += MF.getName();
+    FileName += ".dot";
+    raw_fd_ostream FileOut(FileName, FileError);
+    if (FileError)
+      errs() << FileError.message();
+    WriteGadgetGraph(FileOut, MF, Graph.get());
+    FileOut.close();
+    LLVM_DEBUG(dbgs() << "Emitting gadget graph... Done\n");
+    if (EmitDotOnly)
+      return false;
+  }
+
+  return 0;
+}
+
+std::unique_ptr<MachineGadgetGraph>
+X86LoadValueInjectionLoadHardeningPass::getGadgetGraph(
+    MachineFunction &MF, const MachineLoopInfo &MLI,
+    const MachineDominatorTree &MDT,
+    const MachineDominanceFrontier &MDF) const {
+  using namespace rdf;
+
+  // Build the Register Dataflow Graph using the RDF framework
+  TargetOperandInfo TOI{*TII};
+  DataFlowGraph DFG{MF, *TII, *TRI, MDT, MDF, TOI};
+  DFG.build();
+  Liveness L{MF.getRegInfo(), DFG};
+  L.computePhiInfo();
+
+  GraphBuilder Builder;
+  using GraphIter = typename GraphBuilder::BuilderNodeRef;
+  DenseMap<MachineInstr *, GraphIter> NodeMap;
+  int FenceCount = 0, GadgetCount = 0;
+  auto MaybeAddNode = [&NodeMap, &Builder](MachineInstr *MI) {
+    auto Ref = NodeMap.find(MI);
+    if (Ref == NodeMap.end()) {
+      auto I = Builder.addVertex(MI);
+      NodeMap[MI] = I;
+      return std::pair<GraphIter, bool>{I, true};
+    }
+    return std::pair<GraphIter, bool>{Ref->getSecond(), false};
+  };
+
+  // The `Transmitters` map memoizes transmitters found for each def. If a def
+  // has not yet been analyzed, then it will not appear in the map. If a def
+  // has been analyzed and was determined not to have any transmitters, then
+  // its list of transmitters will be empty.
+  DenseMap<NodeId, std::vector<NodeId>> Transmitters;
+
+  // Analyze all machine instructions to find gadgets and LFENCEs, adding
+  // each interesting value to `Nodes`
+  auto AnalyzeDef = [&](NodeAddr<DefNode *> SourceDef) {
+    SmallSet<NodeId, 8> UsesVisited, DefsVisited;
+    std::function<void(NodeAddr<DefNode *>)> AnalyzeDefUseChain =
+        [&](NodeAddr<DefNode *> Def) {
+          if (Transmitters.find(Def.Id) != Transmitters.end())
+            return; // Already analyzed `Def`
+
+          // Use RDF to find all the uses of `Def`
+          rdf::NodeSet Uses;
+          RegisterRef DefReg = DFG.getPRI().normalize(Def.Addr->getRegRef(DFG));
+          for (auto UseID : L.getAllReachedUses(DefReg, Def)) {
+            auto Use = DFG.addr<UseNode *>(UseID);
+            if (Use.Addr->getFlags() & NodeAttrs::PhiRef) { // phi node
+              NodeAddr<PhiNode *> Phi = Use.Addr->getOwner(DFG);
+              for (auto I : L.getRealUses(Phi.Id)) {
+                if (DFG.getPRI().alias(RegisterRef(I.first), DefReg)) {
+                  for (auto UA : I.second)
+                    Uses.emplace(UA.first);
+                }
+              }
+            } else { // not a phi node
+              Uses.emplace(UseID);
+            }
+          }
+
+          // For each use of `Def`, we want to know whether:
+          // (1) The use can leak the Def'ed value,
+          // (2) The use can further propagate the Def'ed value to more defs
+          for (auto UseID : Uses) {
+            if (!UsesVisited.insert(UseID).second)
+              continue; // Already visited this use of `Def`
+
+            auto Use = DFG.addr<UseNode *>(UseID);
+            assert(!(Use.Addr->getFlags() & NodeAttrs::PhiRef));
+            MachineOperand &UseMO = Use.Addr->getOp();
+            MachineInstr &UseMI = *UseMO.getParent();
+            assert(UseMO.isReg());
+
+            // We naively assume that an instruction propagates any loaded
+            // uses to all defs unless the instruction is a call, in which
+            // case all arguments will be treated as gadget sources during
+            // analysis of the callee function.
+            if (UseMI.isCall())
+              continue;
+
+            // Check whether this use can transmit (leak) its value.
+            if (instrUsesRegToAccessMemory(UseMI, UseMO.getReg()) ||
+                (!NoConditionalBranches &&
+                 instrUsesRegToBranch(UseMI, UseMO.getReg()))) {
+              Transmitters[Def.Id].push_back(Use.Addr->getOwner(DFG).Id);
+              if (UseMI.mayLoad())
+                continue; // Found a transmitting load -- no need to continue
+                          // traversing its defs (i.e., this load will become
+                          // a new gadget source anyways).
+            }
+
+            // Check whether the use propagates to more defs.
+            NodeAddr<InstrNode *> Owner{Use.Addr->getOwner(DFG)};
+            rdf::NodeList AnalyzedChildDefs;
+            for (auto &ChildDef :
+                 Owner.Addr->members_if(DataFlowGraph::IsDef, DFG)) {
+              if (!DefsVisited.insert(ChildDef.Id).second)
+                continue; // Already visited this def
+              if (Def.Addr->getAttrs() & NodeAttrs::Dead)
+                continue;
+              if (Def.Id == ChildDef.Id)
+                continue; // `Def` uses itself (e.g., increment loop counter)
+
+              AnalyzeDefUseChain(ChildDef);
+
+              // `Def` inherits all of its child defs' transmitters.
+              for (auto TransmitterId : Transmitters[ChildDef.Id])
+                Transmitters[Def.Id].push_back(TransmitterId);
+            }
+          }
+
+          // Note that this statement adds `Def.Id` to the map if no
+          // transmitters were found for `Def`.
+          auto &DefTransmitters = Transmitters[Def.Id];
+
+          // Remove duplicate transmitters
+          llvm::sort(DefTransmitters);
+          DefTransmitters.erase(
+              std::unique(DefTransmitters.begin(), DefTransmitters.end()),
+              DefTransmitters.end());
+        };
+
+    // Find all of the transmitters
+    AnalyzeDefUseChain(SourceDef);
+    auto &SourceDefTransmitters = Transmitters[SourceDef.Id];
+    if (SourceDefTransmitters.empty())
+      return; // No transmitters for `SourceDef`
+
+    MachineInstr *Source = SourceDef.Addr->getFlags() & NodeAttrs::PhiRef
+                               ? MachineGadgetGraph::ArgNodeSentinel
+                               : SourceDef.Addr->getOp().getParent();
+    auto GadgetSource = MaybeAddNode(Source);
+    // Each transmitter is a sink for `SourceDef`.
+    for (auto TransmitterId : SourceDefTransmitters) {
+      MachineInstr *Sink = DFG.addr<StmtNode *>(TransmitterId).Addr->getCode();
+      auto GadgetSink = MaybeAddNode(Sink);
+      // Add the gadget edge to the graph.
+      Builder.addEdge(MachineGadgetGraph::GadgetEdgeSentinel,
+                      GadgetSource.first, GadgetSink.first);
+      ++GadgetCount;
+    }
+  };
+
+  LLVM_DEBUG(dbgs() << "Analyzing def-use chains to find gadgets\n");
+  // Analyze function arguments
+  NodeAddr<BlockNode *> EntryBlock = DFG.getFunc().Addr->getEntryBlock(DFG);
+  for (NodeAddr<PhiNode *> ArgPhi :
+       EntryBlock.Addr->members_if(DataFlowGraph::IsPhi, DFG)) {
+    NodeList Defs = ArgPhi.Addr->members_if(DataFlowGraph::IsDef, DFG);
+    llvm::for_each(Defs, AnalyzeDef);
+  }
+  // Analyze every instruction in MF
+  for (NodeAddr<BlockNode *> BA : DFG.getFunc().Addr->members(DFG)) {
+    for (NodeAddr<StmtNode *> SA :
+         BA.Addr->members_if(DataFlowGraph::IsCode<NodeAttrs::Stmt>, DFG)) {
+      MachineInstr *MI = SA.Addr->getCode();
+      if (isFence(MI)) {
+        MaybeAddNode(MI);
+        ++FenceCount;
+      } else if (MI->mayLoad()) {
+        NodeList Defs = SA.Addr->members_if(DataFlowGraph::IsDef, DFG);
+        llvm::for_each(Defs, AnalyzeDef);
+      }
+    }
+  }
+  LLVM_DEBUG(dbgs() << "Found " << FenceCount << " fences\n");
+  LLVM_DEBUG(dbgs() << "Found " << GadgetCount << " gadgets\n");
+  if (GadgetCount == 0)
+    return nullptr;
+  NumGadgets += GadgetCount;
+
+  // Traverse CFG to build the rest of the graph
+  SmallSet<MachineBasicBlock *, 8> BlocksVisited;
+  std::function<void(MachineBasicBlock *, GraphIter, unsigned)> TraverseCFG =
+      [&](MachineBasicBlock *MBB, GraphIter GI, unsigned ParentDepth) {
+        unsigned LoopDepth = MLI.getLoopDepth(MBB);
+        if (!MBB->empty()) {
+          // Always add the first instruction in each block
+          auto NI = MBB->begin();
+          auto BeginBB = MaybeAddNode(&*NI);
+          Builder.addEdge(ParentDepth, GI, BeginBB.first);
+          if (!BlocksVisited.insert(MBB).second)
+            return;
+
+          // Add any instructions within the block that are gadget components
+          GI = BeginBB.first;
+          while (++NI != MBB->end()) {
+            auto Ref = NodeMap.find(&*NI);
+            if (Ref != NodeMap.end()) {
+              Builder.addEdge(LoopDepth, GI, Ref->getSecond());
+              GI = Ref->getSecond();
+            }
+          }
+
+          // Always add the terminator instruction, if one exists
+          auto T = MBB->getFirstTerminator();
+          if (T != MBB->end()) {
+            auto EndBB = MaybeAddNode(&*T);
+            if (EndBB.second)
+              Builder.addEdge(LoopDepth, GI, EndBB.first);
+            GI = EndBB.first;
+          }
+        }
+        for (MachineBasicBlock *Succ : MBB->successors())
+          TraverseCFG(Succ, GI, LoopDepth);
+      };
+  // ArgNodeSentinel is a pseudo-instruction that represents MF args in the
+  // GadgetGraph
+  GraphIter ArgNode = MaybeAddNode(MachineGadgetGraph::ArgNodeSentinel).first;
+  TraverseCFG(&MF.front(), ArgNode, 0);
+  std::unique_ptr<MachineGadgetGraph> G{Builder.get(FenceCount, GadgetCount)};
+  LLVM_DEBUG(dbgs() << "Found " << G->nodes_size() << " nodes\n");
+  return G;
+}
+
+bool X86LoadValueInjectionLoadHardeningPass::instrUsesRegToAccessMemory(
+    const MachineInstr &MI, unsigned Reg) const {
+  if (!MI.mayLoadOrStore() || MI.getOpcode() == X86::MFENCE ||
+      MI.getOpcode() == X86::SFENCE || MI.getOpcode() == X86::LFENCE)
+    return false;
+
+  // FIXME: This does not handle pseudo loading instruction like TCRETURN*
+  const MCInstrDesc &Desc = MI.getDesc();
+  int MemRefBeginIdx = X86II::getMemoryOperandNo(Desc.TSFlags);
+  if (MemRefBeginIdx < 0) {
+    LLVM_DEBUG(dbgs() << "Warning: unable to obtain memory operand for loading "
+                         "instruction:\n";
+               MI.print(dbgs()); dbgs() << '\n';);
+    return false;
+  }
+  MemRefBeginIdx += X86II::getOperandBias(Desc);
+
+  const MachineOperand &BaseMO =
+      MI.getOperand(MemRefBeginIdx + X86::AddrBaseReg);
+  const MachineOperand &IndexMO =
+      MI.getOperand(MemRefBeginIdx + X86::AddrIndexReg);
+  return (BaseMO.isReg() && BaseMO.getReg() != X86::NoRegister &&
+          TRI->regsOverlap(BaseMO.getReg(), Reg)) ||
+         (IndexMO.isReg() && IndexMO.getReg() != X86::NoRegister &&
+          TRI->regsOverlap(IndexMO.getReg(), Reg));
+}
+
+bool X86LoadValueInjectionLoadHardeningPass::instrUsesRegToBranch(
+    const MachineInstr &MI, unsigned Reg) const {
+  if (!MI.isConditionalBranch())
+    return false;
+  for (const MachineOperand &Use : MI.uses())
+    if (Use.isReg() && Use.getReg() == Reg)
+      return true;
+  return false;
+}
+
+INITIALIZE_PASS_BEGIN(X86LoadValueInjectionLoadHardeningPass, PASS_KEY,
+                      "X86 LVI load hardening", false, false)
+INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
+INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
+INITIALIZE_PASS_DEPENDENCY(MachineDominanceFrontier)
+INITIALIZE_PASS_END(X86LoadValueInjectionLoadHardeningPass, PASS_KEY,
+                    "X86 LVI load hardening", false, false)
+
+FunctionPass *llvm::createX86LoadValueInjectionLoadHardeningPass() {
+  return new X86LoadValueInjectionLoadHardeningPass();
+}

diff  --git a/llvm/lib/Target/X86/X86Subtarget.h b/llvm/lib/Target/X86/X86Subtarget.h
index eb5c293e5cbf..af5153243c8b 100644
--- a/llvm/lib/Target/X86/X86Subtarget.h
+++ b/llvm/lib/Target/X86/X86Subtarget.h
@@ -427,6 +427,10 @@ class X86Subtarget final : public X86GenSubtargetInfo {
   /// POP+LFENCE+JMP sequence.
   bool UseLVIControlFlowIntegrity = false;
 
+  /// Insert LFENCE instructions to prevent data speculatively injected into
+  /// loads from being used maliciously.
+  bool UseLVILoadHardening = false;
+
   /// Use software floating point for code generation.
   bool UseSoftFloat = false;
 
@@ -727,6 +731,7 @@ class X86Subtarget final : public X86GenSubtargetInfo {
   bool preferMaskRegisters() const { return PreferMaskRegisters; }
   bool useGLMDivSqrtCosts() const { return UseGLMDivSqrtCosts; }
   bool useLVIControlFlowIntegrity() const { return UseLVIControlFlowIntegrity; }
+  bool useLVILoadHardening() const { return UseLVILoadHardening; }
 
   unsigned getPreferVectorWidth() const { return PreferVectorWidth; }
   unsigned getRequiredVectorWidth() const { return RequiredVectorWidth; }

diff  --git a/llvm/lib/Target/X86/X86TargetMachine.cpp b/llvm/lib/Target/X86/X86TargetMachine.cpp
index e374b16e0e3d..680a52b54385 100644
--- a/llvm/lib/Target/X86/X86TargetMachine.cpp
+++ b/llvm/lib/Target/X86/X86TargetMachine.cpp
@@ -82,6 +82,7 @@ extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeX86Target() {
   initializeX86SpeculativeLoadHardeningPassPass(PR);
   initializeX86FlagsCopyLoweringPassPass(PR);
   initializeX86CondBrFoldingPassPass(PR);
+  initializeX86LoadValueInjectionLoadHardeningPassPass(PR);
   initializeX86LoadValueInjectionRetHardeningPassPass(PR);
   initializeX86OptimizeLEAPassPass(PR);
 }
@@ -497,6 +498,7 @@ void X86PassConfig::addMachineSSAOptimization() {
 
 void X86PassConfig::addPostRegAlloc() {
   addPass(createX86FloatingPointStackifierPass());
+  addPass(createX86LoadValueInjectionLoadHardeningPass());
 }
 
 void X86PassConfig::addPreSched2() { addPass(createX86ExpandPseudoPass()); }

diff  --git a/llvm/test/CodeGen/X86/O0-pipeline.ll b/llvm/test/CodeGen/X86/O0-pipeline.ll
index cd1442102d31..bdd61bcc285c 100644
--- a/llvm/test/CodeGen/X86/O0-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O0-pipeline.ll
@@ -55,6 +55,10 @@
 ; CHECK-NEXT:       Fast Register Allocator
 ; CHECK-NEXT:       Bundle Machine CFG Edges
 ; CHECK-NEXT:       X86 FP Stackifier
+; CHECK-NEXT:       MachineDominator Tree Construction
+; CHECK-NEXT:       Machine Natural Loop Construction
+; CHECK-NEXT:       Machine Dominance Frontier Construction
+; CHECK-NEXT:       X86 Load Value Injection (LVI) Load Hardening
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       Prologue/Epilogue Insertion & Frame Finalization
@@ -82,3 +86,4 @@
 define void @f() {
   ret void
 }
+

diff  --git a/llvm/test/CodeGen/X86/O3-pipeline.ll b/llvm/test/CodeGen/X86/O3-pipeline.ll
index 1d487bc266de..75a4f41ffc66 100644
--- a/llvm/test/CodeGen/X86/O3-pipeline.ll
+++ b/llvm/test/CodeGen/X86/O3-pipeline.ll
@@ -138,9 +138,11 @@
 ; CHECK-NEXT:       Machine Loop Invariant Code Motion
 ; CHECK-NEXT:       Bundle Machine CFG Edges
 ; CHECK-NEXT:       X86 FP Stackifier
+; CHECK-NEXT:       MachineDominator Tree Construction
+; CHECK-NEXT:       Machine Dominance Frontier Construction
+; CHECK-NEXT:       X86 Load Value Injection (LVI) Load Hardening
 ; CHECK-NEXT:       PostRA Machine Sink
 ; CHECK-NEXT:       Machine Block Frequency Analysis
-; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
@@ -191,3 +193,4 @@
 define void @f() {
   ret void
 }
+

diff  --git a/llvm/test/CodeGen/X86/lvi-hardening-gadget-graph.ll b/llvm/test/CodeGen/X86/lvi-hardening-gadget-graph.ll
new file mode 100644
index 000000000000..ba2ce26142b5
--- /dev/null
+++ b/llvm/test/CodeGen/X86/lvi-hardening-gadget-graph.ll
@@ -0,0 +1,129 @@
+; RUN: llc -verify-machineinstrs -mtriple=x86_64-unknown -x86-lvi-load-dot-verify -o %t < %s | FileCheck %s
+
+; Function Attrs: noinline nounwind optnone uwtable
+define dso_local i32 @test(i32* %untrusted_user_ptr, i32* %secret, i32 %secret_size) #0 {
+entry:
+  %untrusted_user_ptr.addr = alloca i32*, align 8
+  %secret.addr = alloca i32*, align 8
+  %secret_size.addr = alloca i32, align 4
+  %ret_val = alloca i32, align 4
+  %i = alloca i32, align 4
+  store i32* %untrusted_user_ptr, i32** %untrusted_user_ptr.addr, align 8
+  store i32* %secret, i32** %secret.addr, align 8
+  store i32 %secret_size, i32* %secret_size.addr, align 4
+  store i32 0, i32* %ret_val, align 4
+  call void @llvm.x86.sse2.lfence()
+  store i32 0, i32* %i, align 4
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %0 = load i32, i32* %i, align 4
+  %1 = load i32, i32* %secret_size.addr, align 4
+  %cmp = icmp slt i32 %0, %1
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %2 = load i32, i32* %i, align 4
+  %rem = srem i32 %2, 2
+  %cmp1 = icmp eq i32 %rem, 0
+  br i1 %cmp1, label %if.then, label %if.else
+
+if.then:                                          ; preds = %for.body
+  %3 = load i32*, i32** %secret.addr, align 8
+  %4 = load i32, i32* %ret_val, align 4
+  %idxprom = sext i32 %4 to i64
+  %arrayidx = getelementptr inbounds i32, i32* %3, i64 %idxprom
+  %5 = load i32, i32* %arrayidx, align 4
+  %6 = load i32*, i32** %untrusted_user_ptr.addr, align 8
+  store i32 %5, i32* %6, align 4
+  br label %if.end
+
+if.else:                                          ; preds = %for.body
+  %7 = load i32*, i32** %secret.addr, align 8
+  %8 = load i32, i32* %ret_val, align 4
+  %idxprom2 = sext i32 %8 to i64
+  %arrayidx3 = getelementptr inbounds i32, i32* %7, i64 %idxprom2
+  store i32 42, i32* %arrayidx3, align 4
+  br label %if.end
+
+if.end:                                           ; preds = %if.else, %if.then
+  %9 = load i32*, i32** %untrusted_user_ptr.addr, align 8
+  %10 = load i32, i32* %9, align 4
+  store i32 %10, i32* %ret_val, align 4
+  br label %for.inc
+
+for.inc:                                          ; preds = %if.end
+  %11 = load i32, i32* %i, align 4
+  %inc = add nsw i32 %11, 1
+  store i32 %inc, i32* %i, align 4
+  br label %for.cond
+
+for.end:                                          ; preds = %for.cond
+  %12 = load i32, i32* %ret_val, align 4
+  ret i32 %12
+}
+
+; CHECK:      digraph "Speculative gadgets for \"test\" function" {
+; CHECK-NEXT: label="Speculative gadgets for \"test\" function";
+; CHECK:      Node0x{{[0-9a-f]+}} [shape=record,color = green,label="{LFENCE\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 0];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $eax = MOV32rm %stack.4.i, 1, $noreg, 0, $noreg :: (dereferenceable load 4 from %ir.i)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{JCC_1 %bb.6, 13, implicit killed $eflags\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{CMP32rm killed renamable $eax, %stack.2.secret_size.addr, 1, $noreg, 0, $noreg, implicit-def $eflags :: (dereferenceable load 4 from %ir.secret_size.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $eax = MOV32rm %stack.4.i, 1, $noreg, 0, $noreg :: (dereferenceable load 4 from %ir.i)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{JCC_1 %bb.4, 5, implicit killed $eflags\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rax = MOV64rm %stack.1.secret.addr, 1, $noreg, 0, $noreg :: (dereferenceable load 8 from %ir.secret.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $eax = MOV32rm killed renamable $rax, 4, killed renamable $rcx, 0, $noreg :: (load 4 from %ir.arrayidx)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rcx = MOVSX64rm32 %stack.3.ret_val, 1, $noreg, 0, $noreg :: (dereferenceable load 4 from %ir.ret_val)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rcx = MOV64rm %stack.0.untrusted_user_ptr.addr, 1, $noreg, 0, $noreg :: (dereferenceable load 8 from %ir.untrusted_user_ptr.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{MOV32mr killed renamable $rcx, 1, $noreg, 0, $noreg, killed renamable $eax :: (store 4 into %ir.6)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rax = MOV64rm %stack.1.secret.addr, 1, $noreg, 0, $noreg :: (dereferenceable load 8 from %ir.secret.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{MOV32mi killed renamable $rax, 4, killed renamable $rcx, 0, $noreg, 42 :: (store 4 into %ir.arrayidx3)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rcx = MOVSX64rm32 %stack.3.ret_val, 1, $noreg, 0, $noreg :: (dereferenceable load 4 from %ir.ret_val)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $rax = MOV64rm %stack.0.untrusted_user_ptr.addr, 1, $noreg, 0, $noreg :: (dereferenceable load 8 from %ir.untrusted_user_ptr.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[color = red, style = "dashed"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $eax = MOV32rm killed renamable $rax, 1, $noreg, 0, $noreg :: (load 4 from %ir.9)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,color = blue,label="{ARGS}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 0];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{MOV64mr %stack.0.untrusted_user_ptr.addr, 1, $noreg, 0, $noreg, killed renamable $rdi :: (store 8 into %ir.untrusted_user_ptr.addr)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 0];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{JMP_1 %bb.5\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{JMP_1 %bb.1\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 1];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{renamable $eax = MOV32rm %stack.3.ret_val, 1, $noreg, 0, $noreg :: (dereferenceable load 4 from %ir.ret_val)\n}"];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} -> Node0x{{[0-9a-f]+}}[label = 0];
+; CHECK-NEXT: Node0x{{[0-9a-f]+}} [shape=record,label="{RET 0, $eax\n}"];
+; CHECK-NEXT: }
+
+; Function Attrs: nounwind
+declare void @llvm.x86.sse2.lfence() #1
+
+attributes #0 = { "target-features"="+lvi-cfi"
+                  "target-features"="+lvi-load-hardening" }
+attributes #1 = { nounwind }


        


More information about the llvm-branch-commits mailing list