Index: sanitizer_common/sanitizer_stackdepot.h
===================================================================
--- sanitizer_common/sanitizer_stackdepot.h
+++ sanitizer_common/sanitizer_stackdepot.h
@@ -20,19 +20,163 @@
 
 // StackDepot efficiently stores huge amounts of stack traces.
 
-// Maps stack trace to an unique id.
-u32 StackDepotPut(const uptr *stack, uptr size);
-// Retrieves a stored stack trace by the id.
-const uptr *StackDepotGet(u32 id, uptr *size);
-
 struct StackDepotStats {
   uptr n_uniq_ids;
   uptr mapped;
 };
 
-StackDepotStats *StackDepotGetStats();
+struct StackDepotDesc {
+  const uptr *stack;
+  uptr size;
+  u32 hash() const {
+    // murmur2
+    const u32 m = 0x5bd1e995;
+    const u32 seed = 0x9747b28c;
+    const u32 r = 24;
+    u32 h = seed ^ (size * sizeof(uptr));
+    for (uptr i = 0; i < size; i++) {
+      u32 k = stack[i];
+      k *= m;
+      k ^= k >> r;
+      k *= m;
+      h *= m;
+      h ^= k;
+    }
+    h ^= h >> 13;
+    h *= m;
+    h ^= h >> 15;
+    return h;
+  }
+  bool is_valid() { return size > 0 && stack; }
+};
+
+struct StackDepotNode {
+  StackDepotNode *link;
+  u32 id;
+  u32 hash_bits : 12;
+  u32 use_count : 20;
+  static const u32 MAX_USE_COUNT = 1 << 18;
+  uptr size;
+  uptr stack[1];  // [size]
+  typedef StackDepotDesc args_type;
+  bool eq(u32 hash, const args_type &args) const {
+    if ((hash >> 20) != hash_bits || args.size != size) return false;
+    uptr i = 0;
+    for (; i < size; i++) {
+      if (stack[i] != args.stack[i]) return false;
+    }
+    return true;
+  }
+  static uptr storage_size(const args_type &args) {
+    return sizeof(StackDepotNode) + (args.size - 1) * sizeof(uptr);
+  }
+  void store(const args_type &args, u32 hash) {
+    hash_bits = hash >> 20;
+    size = args.size;
+    internal_memcpy(stack, args.stack, size * sizeof(uptr));
+  }
+  args_type load() const {
+    args_type ret = {&stack[0], size};
+    return ret;
+  }
+  struct Handle {
+    StackDepotNode *node_;
+    Handle() : node_(0) {}
+    explicit Handle(StackDepotNode *node) : node_(node) {}
+    bool valid() { return node_; }
+    u32 id() { return node_->id; }
+    int inc_use_count() {
+      if (node_->use_count >= MAX_USE_COUNT) node_->use_count++;
+      return node_->use_count;
+    }
+    uptr size() { return node_->size; }
+    uptr *stack() { return &node_->stack[0]; }
+  };
+  Handle get_handle() { return Handle(this); }
+};
+
+struct ChainedOriginDepotDesc {
+  u32 here_id;
+  u32 prev_id;
+  u32 hash() const { return 0; }
+  bool is_valid() { return true; }
+};
+
+struct ChainedOriginDepotNode {
+  StackDepotNode *link;
+  u32 id;
+  u32 here_id;
+  u32 prev_id;
+  typedef ChainedOriginDepotDesc args_type;
+  bool eq(u32 hash, const args_type &args) const {
+    return here_id == args.here_id && prev_id == args.prev_id;
+  }
+  static uptr storage_size(const args_type &args) {
+    return sizeof(ChainedOriginDepotNode);
+  }
+  void store(const args_type &args, u32 other_hash) {
+    here_id = args.here_id;
+    prev_id = args.prev_id;
+  }
+  args_type load() const {
+    args_type ret = {here_id, prev_id};
+    return ret;
+  }
+  struct Handle {
+    ChainedOriginDepotNode *node_;
+    Handle() : node_(0) {}
+    explicit Handle(ChainedOriginDepotNode *node) : node_(node) {}
+    bool valid() { return node_; }
+    u32 id() { return node_->id; }
+    int here_id() { return node_->here_id; }
+    int prev_id() { return node_->prev_id; }
+  };
+  Handle get_handle() { return Handle(this); }
+};
+
+template<class Node>
+class StackDepot {
+ public:
+  typedef typename Node::args_type args_type;
+  typedef typename Node::Handle handle_type;
+  // Maps stack trace to an unique id.
+  handle_type Put(args_type args);
+  // Retrieves a stored stack trace by the id.
+  args_type Get(u32 id);
+
+
+  StackDepotStats *GetStats() { return &stats; }
+
+ private:
+  Node *tryallocDesc(uptr memsz);
+  Node *allocDesc(uptr size);
+  static Node *find(Node *s, args_type args, u32 hash);
+  static Node *lock(atomic_uintptr_t *p);
+  static void unlock(atomic_uintptr_t *p, Node *s);
+
+  static const int kTabSize = 1024 * 1024;  // Hash table size.
+  static const int kPartBits = 8;
+  static const int kPartShift = sizeof(u32) * 8 - kPartBits - 1;
+  static const int kPartCount =
+      1 << kPartBits;  // Number of subparts in the table.
+  static const int kPartSize = kTabSize / kPartCount;
+  static const int kMaxId = 1 << kPartShift;
+
+  StaticSpinMutex mtx;  // Protects alloc of new blocks for region allocator.
+  atomic_uintptr_t region_pos;  // Region allocator for Node's.
+  atomic_uintptr_t region_end;
+  atomic_uintptr_t tab[kTabSize];   // Hash table of Node's.
+  atomic_uint32_t seq[kPartCount];  // Unique id generators.
+
+  StackDepotStats stats;
 
-struct StackDesc;
+  friend class StackDepotReverseMap;
+};
+
+StackDepotStats *StackDepotGetStats();
+u32 StackDepotPut(const uptr *stack, uptr size);
+// Retrieves a stored stack trace by the id.
+const uptr *StackDepotGet(u32 id, uptr *size);
 
 // Instantiating this class creates a snapshot of StackDepot which can be
 // efficiently queried with StackDepotGet(). You can use it concurrently with
@@ -46,7 +190,7 @@
  private:
   struct IdDescPair {
     u32 id;
-    StackDesc *desc;
+    StackDepotNode *desc;
 
     static bool IdComparator(const IdDescPair &a, const IdDescPair &b);
   };
@@ -57,6 +201,139 @@
   StackDepotReverseMap(const StackDepotReverseMap&);
   void operator=(const StackDepotReverseMap&);
 };
+
+
+template<class Node>
+Node *StackDepot<Node>::tryallocDesc(uptr memsz) {
+  // Optimisic lock-free allocation, essentially try to bump the region ptr.
+  for (;;) {
+    uptr cmp = atomic_load(&region_pos, memory_order_acquire);
+    uptr end = atomic_load(&region_end, memory_order_acquire);
+    if (cmp == 0 || cmp + memsz > end)
+      return 0;
+    if (atomic_compare_exchange_weak(
+        &region_pos, &cmp, cmp + memsz,
+        memory_order_acquire))
+      return (StackDepotNode*)cmp;
+  }
+}
+
+template<class Node>
+Node *StackDepot<Node>::allocDesc(uptr memsz) {
+  // First, try to allocate optimisitically.
+  StackDepotNode *s = tryallocDesc(memsz);
+  if (s)
+    return s;
+  // If failed, lock, retry and alloc new superblock.
+  SpinMutexLock l(&mtx);
+  for (;;) {
+    s = tryallocDesc(memsz);
+    if (s)
+      return s;
+    atomic_store(&region_pos, 0, memory_order_relaxed);
+    uptr allocsz = 64 * 1024;
+    if (allocsz < memsz)
+      allocsz = memsz;
+    uptr mem = (uptr)MmapOrDie(allocsz, "stack depot");
+    stats.mapped += allocsz;
+    atomic_store(&region_end, mem + allocsz, memory_order_release);
+    atomic_store(&region_pos, mem, memory_order_release);
+  }
+}
+
+template<class Node>
+Node *StackDepot<Node>::find(Node *s, args_type args, u32 hash) {
+  // Searches linked list s for the stack, returns its id.
+  for (; s; s = s->link) {
+    if (s->eq(hash, args)) {
+      return s;
+    }
+  }
+  return 0;
+}
+
+template<class Node>
+Node *StackDepot<Node>::lock(atomic_uintptr_t *p) {
+  // Uses the pointer lsb as mutex.
+  for (int i = 0;; i++) {
+    uptr cmp = atomic_load(p, memory_order_relaxed);
+    if ((cmp & 1) == 0
+        && atomic_compare_exchange_weak(p, &cmp, cmp | 1,
+                                        memory_order_acquire))
+      return (Node*)cmp;
+    if (i < 10)
+      proc_yield(10);
+    else
+      internal_sched_yield();
+  }
+}
+
+template<class Node>
+void StackDepot<Node>::unlock(atomic_uintptr_t *p, Node *s) {
+  DCHECK_EQ((uptr)s & 1, 0);
+  atomic_store(p, (uptr)s, memory_order_release);
+}
+
+template<class Node>
+typename StackDepot<Node>::handle_type StackDepot<Node>::Put(args_type args) {
+  if (!args.is_valid())
+    return handle_type();
+  uptr h = args.hash();
+  atomic_uintptr_t *p = &tab[h % kTabSize];
+  uptr v = atomic_load(p, memory_order_consume);
+  Node *s = (Node*)(v & ~1);
+  // First, try to find the existing stack.
+  Node *node = find(s, args, h);
+  if (node)
+    return node->get_handle();
+  // If failed, lock, retry and insert new.
+  Node *s2 = lock(p);
+  if (s2 != s) {
+    node = find(s2, args, h);
+    if (node) {
+      unlock(p, s2);
+      return node->get_handle();
+    }
+  }
+  uptr part = (h % kTabSize) / kPartSize;
+  u32 id = atomic_fetch_add(&seq[part], 1, memory_order_relaxed) + 1;
+  stats.n_uniq_ids++;
+  CHECK_LT(id, kMaxId);
+  id |= part << kPartShift;
+  CHECK_NE(id, 0);
+  CHECK_EQ(id & (1u << 31), 0);
+  uptr memsz = Node::storage_size(args);
+  s = allocDesc(memsz);
+  s->id = id;
+  s->store(args, h);
+  s->link = s2;
+  unlock(p, s);
+  return s->get_handle();
+}
+
+template<class Node>
+typename StackDepot<Node>::args_type StackDepot<Node>::Get(u32 id) {
+  if (id == 0) {
+    return args_type();
+  }
+  CHECK_EQ(id & (1u << 31), 0);
+  // High kPartBits contain part id, so we need to scan at most kPartSize lists.
+  uptr part = id >> kPartShift;
+  for (int i = 0; i != kPartSize; i++) {
+    uptr idx = part * kPartSize + i;
+    CHECK_LT(idx, kTabSize);
+    atomic_uintptr_t *p = &tab[idx];
+    uptr v = atomic_load(p, memory_order_consume);
+    Node *s = (Node*)(v & ~1);
+    for (; s; s = s->link) {
+      if (s->id == id)  {
+        return s->load();
+      }
+    }
+  }
+  return args_type();
+}
+
 }  // namespace __sanitizer
 
 #endif  // SANITIZER_STACKDEPOT_H
Index: sanitizer_common/sanitizer_stackdepot.cc
===================================================================
--- sanitizer_common/sanitizer_stackdepot.cc
+++ sanitizer_common/sanitizer_stackdepot.cc
@@ -19,186 +19,23 @@
 
 namespace __sanitizer {
 
-const int kTabSize = 1024 * 1024;  // Hash table size.
-const int kPartBits = 8;
-const int kPartShift = sizeof(u32) * 8 - kPartBits - 1;
-const int kPartCount = 1 << kPartBits;  // Number of subparts in the table.
-const int kPartSize = kTabSize / kPartCount;
-const int kMaxId = 1 << kPartShift;
-
-struct StackDesc {
-  StackDesc *link;
-  u32 id;
-  u32 hash;
-  uptr size;
-  uptr stack[1];  // [size]
-};
-
-static struct {
-  StaticSpinMutex mtx;  // Protects alloc of new blocks for region allocator.
-  atomic_uintptr_t region_pos;  // Region allocator for StackDesc's.
-  atomic_uintptr_t region_end;
-  atomic_uintptr_t tab[kTabSize];  // Hash table of StackDesc's.
-  atomic_uint32_t seq[kPartCount];  // Unique id generators.
-} depot;
-
-static StackDepotStats stats;
+static StackDepot<StackDepotNode> theDepot;
+static StackDepot<ChainedOriginDepotNode> chainedOriginDepot;
 
 StackDepotStats *StackDepotGetStats() {
-  return &stats;
-}
-
-static u32 hash(const uptr *stack, uptr size) {
-  // murmur2
-  const u32 m = 0x5bd1e995;
-  const u32 seed = 0x9747b28c;
-  const u32 r = 24;
-  u32 h = seed ^ (size * sizeof(uptr));
-  for (uptr i = 0; i < size; i++) {
-    u32 k = stack[i];
-    k *= m;
-    k ^= k >> r;
-    k *= m;
-    h *= m;
-    h ^= k;
-  }
-  h ^= h >> 13;
-  h *= m;
-  h ^= h >> 15;
-  return h;
-}
-
-static StackDesc *tryallocDesc(uptr memsz) {
-  // Optimisic lock-free allocation, essentially try to bump the region ptr.
-  for (;;) {
-    uptr cmp = atomic_load(&depot.region_pos, memory_order_acquire);
-    uptr end = atomic_load(&depot.region_end, memory_order_acquire);
-    if (cmp == 0 || cmp + memsz > end)
-      return 0;
-    if (atomic_compare_exchange_weak(
-        &depot.region_pos, &cmp, cmp + memsz,
-        memory_order_acquire))
-      return (StackDesc*)cmp;
-  }
-}
-
-static StackDesc *allocDesc(uptr size) {
-  // First, try to allocate optimisitically.
-  uptr memsz = sizeof(StackDesc) + (size - 1) * sizeof(uptr);
-  StackDesc *s = tryallocDesc(memsz);
-  if (s)
-    return s;
-  // If failed, lock, retry and alloc new superblock.
-  SpinMutexLock l(&depot.mtx);
-  for (;;) {
-    s = tryallocDesc(memsz);
-    if (s)
-      return s;
-    atomic_store(&depot.region_pos, 0, memory_order_relaxed);
-    uptr allocsz = 64 * 1024;
-    if (allocsz < memsz)
-      allocsz = memsz;
-    uptr mem = (uptr)MmapOrDie(allocsz, "stack depot");
-    stats.mapped += allocsz;
-    atomic_store(&depot.region_end, mem + allocsz, memory_order_release);
-    atomic_store(&depot.region_pos, mem, memory_order_release);
-  }
-}
-
-static u32 find(StackDesc *s, const uptr *stack, uptr size, u32 hash) {
-  // Searches linked list s for the stack, returns its id.
-  for (; s; s = s->link) {
-    if (s->hash == hash && s->size == size) {
-      uptr i = 0;
-      for (; i < size; i++) {
-        if (stack[i] != s->stack[i])
-          break;
-      }
-      if (i == size)
-        return s->id;
-    }
-  }
-  return 0;
-}
-
-static StackDesc *lock(atomic_uintptr_t *p) {
-  // Uses the pointer lsb as mutex.
-  for (int i = 0;; i++) {
-    uptr cmp = atomic_load(p, memory_order_relaxed);
-    if ((cmp & 1) == 0
-        && atomic_compare_exchange_weak(p, &cmp, cmp | 1,
-                                        memory_order_acquire))
-      return (StackDesc*)cmp;
-    if (i < 10)
-      proc_yield(10);
-    else
-      internal_sched_yield();
-  }
-}
-
-static void unlock(atomic_uintptr_t *p, StackDesc *s) {
-  DCHECK_EQ((uptr)s & 1, 0);
-  atomic_store(p, (uptr)s, memory_order_release);
+  return theDepot.GetStats();
 }
 
 u32 StackDepotPut(const uptr *stack, uptr size) {
-  if (stack == 0 || size == 0)
-    return 0;
-  uptr h = hash(stack, size);
-  atomic_uintptr_t *p = &depot.tab[h % kTabSize];
-  uptr v = atomic_load(p, memory_order_consume);
-  StackDesc *s = (StackDesc*)(v & ~1);
-  // First, try to find the existing stack.
-  u32 id = find(s, stack, size, h);
-  if (id)
-    return id;
-  // If failed, lock, retry and insert new.
-  StackDesc *s2 = lock(p);
-  if (s2 != s) {
-    id = find(s2, stack, size, h);
-    if (id) {
-      unlock(p, s2);
-      return id;
-    }
-  }
-  uptr part = (h % kTabSize) / kPartSize;
-  id = atomic_fetch_add(&depot.seq[part], 1, memory_order_relaxed) + 1;
-  stats.n_uniq_ids++;
-  CHECK_LT(id, kMaxId);
-  id |= part << kPartShift;
-  CHECK_NE(id, 0);
-  CHECK_EQ(id & (1u << 31), 0);
-  s = allocDesc(size);
-  s->id = id;
-  s->hash = h;
-  s->size = size;
-  internal_memcpy(s->stack, stack, size * sizeof(uptr));
-  s->link = s2;
-  unlock(p, s);
-  return id;
+  StackDepotDesc desc = {stack, size};
+  StackDepotNode::Handle h = theDepot.Put(desc);
+  return h.valid() ? h.id() : 0;
 }
 
 const uptr *StackDepotGet(u32 id, uptr *size) {
-  if (id == 0)
-    return 0;
-  CHECK_EQ(id & (1u << 31), 0);
-  // High kPartBits contain part id, so we need to scan at most kPartSize lists.
-  uptr part = id >> kPartShift;
-  for (int i = 0; i != kPartSize; i++) {
-    uptr idx = part * kPartSize + i;
-    CHECK_LT(idx, kTabSize);
-    atomic_uintptr_t *p = &depot.tab[idx];
-    uptr v = atomic_load(p, memory_order_consume);
-    StackDesc *s = (StackDesc*)(v & ~1);
-    for (; s; s = s->link) {
-      if (s->id == id) {
-        *size = s->size;
-        return s->stack;
-      }
-    }
-  }
-  *size = 0;
-  return 0;
+  StackDepotDesc desc = theDepot.Get(id);
+  *size = desc.size;
+  return desc.stack;
 }
 
 bool StackDepotReverseMap::IdDescPair::IdComparator(
@@ -209,10 +46,10 @@
 
 StackDepotReverseMap::StackDepotReverseMap()
     : map_(StackDepotGetStats()->n_uniq_ids + 100) {
-  for (int idx = 0; idx < kTabSize; idx++) {
-    atomic_uintptr_t *p = &depot.tab[idx];
+  for (int idx = 0; idx < StackDepot<StackDepotNode>::kTabSize; idx++) {
+    atomic_uintptr_t *p = &theDepot.tab[idx];
     uptr v = atomic_load(p, memory_order_consume);
-    StackDesc *s = (StackDesc*)(v & ~1);
+    StackDepotNode *s = (StackDepotNode*)(v & ~1);
     for (; s; s = s->link) {
       IdDescPair pair = {s->id, s};
       map_.push_back(pair);
@@ -230,7 +67,7 @@
     *size = 0;
     return 0;
   }
-  StackDesc *desc = map_[idx].desc;
+  StackDepotNode *desc = map_[idx].desc;
   *size = desc->size;
   return desc->stack;
 }