diff --git a/src/Makefile.am b/src/Makefile.am
index 68cff78..6a92275 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -19,7 +19,7 @@
 ACLOCAL_AMFLAGS = -I m4
 AM_LIBTOOLFLAGS = --quiet
 
-AM_CFLAGS = @CPU_FLAGS@ -Wall
+AM_CFLAGS = @CPU_FLAGS@ @DLMALLOC@ -Wall
 AM_CXXFLAGS = -Wall -std=gnu++11
 
 SUBDIRS = .
diff --git a/src/configure.ac b/src/configure.ac
index 1e92e9c..8830c68 100644
--- a/src/configure.ac
+++ b/src/configure.ac
@@ -190,6 +190,7 @@
 ENABLE_ARG(dpdk_shared,	[Enable unit tests])
 ENABLE_ARG(perftool,	[Enable perftool])
 ENABLE_ARG(g2,		[Enable g2])
+ENABLE_ARG(dlmalloc,    [Enable dlmalloc])
 
 # --disable-X
 DISABLE_ARG(vlib,	[Disable vlib and dependant libs and binaries])
@@ -232,6 +233,8 @@
                *) with_pre_data="pre-data-not-set" ;;
 	     esac], [with_pre_data=128])
 
+AM_CONDITIONAL(ENABLE_DLMALLOC, test "$enable_dlmalloc" = "yes")
+
 ###############################################################################
 # Target CPU flags
 ###############################################################################
@@ -278,6 +281,7 @@
 AC_SUBST(PRE_DATA_SIZE,		[$with_pre_data])
 AC_SUBST(LOG2_CACHE_LINE_BYTES, [$with_log2_cache_line_bytes])
 AC_SUBST(APICLI,		[-DVPP_API_TEST_BUILTIN=${n_with_apicli}])
+AC_SUBST(DLMALLOC,              [-DUSE_DLMALLOC=${n_enable_dlmalloc}])
 
 AC_DEFINE_UNQUOTED(DPDK_SHARED_LIB,	[${n_enable_dpdk_shared}])
 AC_DEFINE_UNQUOTED(WITH_LIBSSL,		[${n_with_libssl}])
@@ -447,6 +451,7 @@
 PRINT_VAL([CPPFLAGS], ${CPPFLAGS})
 PRINT_VAL([LDFLAGS], ${LDFLAGS})
 PRINT_VAL([LOG2_CACHE_LINE_BYTES], ${with_log2_cache_line_bytes})
+PRINT_VAL([DLMALLOC], ${enable_dlmalloc})
 AM_COND_IF([ENABLE_JAPI],
 [
   PRINT_VAL([JAVA_VERSION], ${JAVA_VERSION})
diff --git a/src/examples/sample-plugin/Makefile.am b/src/examples/sample-plugin/Makefile.am
index 1825a8f..2622f4e 100644
--- a/src/examples/sample-plugin/Makefile.am
+++ b/src/examples/sample-plugin/Makefile.am
@@ -13,7 +13,7 @@
 
 AUTOMAKE_OPTIONS = foreign subdir-objects
 
-AM_CFLAGS = -Wall -I${top_srcdir} -I${top_builddir}
+AM_CFLAGS = -Wall -I${top_srcdir} -I${top_builddir} @DLMALLOC@
 AM_LDFLAGS = -module -shared -avoid-version
 AM_LIBTOOLFLAGS = --quiet
 SUFFIXES = .api.h .api .api.json
diff --git a/src/examples/sample-plugin/configure.ac b/src/examples/sample-plugin/configure.ac
index 588e7dd..57ec6ee 100644
--- a/src/examples/sample-plugin/configure.ac
+++ b/src/examples/sample-plugin/configure.ac
@@ -22,6 +22,19 @@
   AC_LANG_POP([C])
 ])
 
+AC_DEFUN([ENABLE_ARG],
+[
+  AC_ARG_ENABLE($1,
+    AC_HELP_STRING(patsubst([--enable-$1],[_],[-]), $2),
+    [enable_$1=yes n_enable_$1=1],
+    [enable_$1=no n_enable_$1=0])
+  AM_CONDITIONAL(m4_toupper(ENABLE_$1), test "$enable_$1" = "yes")
+  m4_append([list_of_enabled], [$1], [, ])
+])
+
+ENABLE_ARG(dlmalloc,    [Enable dlmalloc])
+AC_SUBST(DLMALLOC,              [-DUSE_DLMALLOC=${n_enable_dlmalloc}])
+
 CC_CHECK_FLAG("-Wno-address-of-packed-member")
 AS_IF([test "$cc_flag_check" = yes],
 	[CFLAGS="${CFLAGS} -Wno-address-of-packed-member"], [])
diff --git a/src/plugins/Makefile.am b/src/plugins/Makefile.am
index 5d9ca8b..3220b09 100644
--- a/src/plugins/Makefile.am
+++ b/src/plugins/Makefile.am
@@ -14,7 +14,7 @@
 
 AUTOMAKE_OPTIONS = foreign subdir-objects
 
-AM_CFLAGS = @CPU_FLAGS@ -Wall -I${top_srcdir} -I${top_builddir}
+AM_CFLAGS = @CPU_FLAGS@ @DLMALLOC@ -Wall -I${top_srcdir} -I${top_builddir}
 AM_LDFLAGS = -module -shared -avoid-version
 AM_LIBTOOLFLAGS = --quiet
 SUFFIXES = .api.h .api .api.json
diff --git a/src/plugins/acl/acl.c b/src/plugins/acl/acl.c
index 192dc04..56bd530 100644
--- a/src/plugins/acl/acl.c
+++ b/src/plugins/acl/acl.c
@@ -139,15 +139,16 @@
 	  clib_warning ("ACL heap size requested: %lld, max possible %lld",
 			am->acl_mheap_size, max_possible);
 	}
-      am->acl_mheap = mheap_alloc (0 /* use VM */ , am->acl_mheap_size);
+
+      am->acl_mheap = mheap_alloc_with_lock (0 /* use VM */ ,
+					     am->acl_mheap_size,
+					     1 /* locked */ );
       if (0 == am->acl_mheap)
 	{
 	  clib_error
 	    ("ACL plugin failed to allocate main heap of %U bytes, abort",
 	     format_memory_size, am->acl_mheap_size);
 	}
-      mheap_t *h = mheap_header (am->acl_mheap);
-      h->flags |= MHEAP_FLAG_THREAD_SAFE;
     }
   void *oldheap = clib_mem_set_heap (am->acl_mheap);
   return oldheap;
@@ -164,6 +165,7 @@
 acl_plugin_acl_set_validate_heap (acl_main_t * am, int on)
 {
   clib_mem_set_heap (acl_set_heap (am));
+#if USE_DLMALLOC == 0
   mheap_t *h = mheap_header (am->acl_mheap);
   if (on)
     {
@@ -176,12 +178,14 @@
       h->flags &= ~MHEAP_FLAG_VALIDATE;
       h->flags |= MHEAP_FLAG_SMALL_OBJECT_CACHE;
     }
+#endif
 }
 
 void
 acl_plugin_acl_set_trace_heap (acl_main_t * am, int on)
 {
   clib_mem_set_heap (acl_set_heap (am));
+#if USE_DLMALLOC == 0
   mheap_t *h = mheap_header (am->acl_mheap);
   if (on)
     {
@@ -191,6 +195,7 @@
     {
       h->flags &= ~MHEAP_FLAG_TRACE;
     }
+#endif
 }
 
 static void
diff --git a/src/plugins/acl/hash_lookup.c b/src/plugins/acl/hash_lookup.c
index 9a9a1ff..dcc5f79 100644
--- a/src/plugins/acl/hash_lookup.c
+++ b/src/plugins/acl/hash_lookup.c
@@ -558,12 +558,13 @@
 hash_acl_set_heap(acl_main_t *am)
 {
   if (0 == am->hash_lookup_mheap) {
-    am->hash_lookup_mheap = mheap_alloc (0 /* use VM */ , am->hash_lookup_mheap_size);
+    am->hash_lookup_mheap = mheap_alloc_with_lock (0 /* use VM */ , 
+                                                   am->hash_lookup_mheap_size,
+                                                   1 /* locked */);
     if (0 == am->hash_lookup_mheap) {
-      clib_error("ACL plugin failed to allocate hash lookup heap of %U bytes, abort", format_memory_size, am->hash_lookup_mheap_size);
+        clib_error("ACL plugin failed to allocate lookup heap of %U bytes", 
+                   format_memory_size, am->hash_lookup_mheap_size);
     }
-    mheap_t *h = mheap_header (am->hash_lookup_mheap);
-    h->flags |= MHEAP_FLAG_THREAD_SAFE;
   }
   void *oldheap = clib_mem_set_heap(am->hash_lookup_mheap);
   return oldheap;
@@ -574,6 +575,7 @@
 {
   acl_main_t *am = &acl_main;
   clib_mem_set_heap(hash_acl_set_heap(am));
+#if USE_DLMALLOC == 0
   mheap_t *h = mheap_header (am->hash_lookup_mheap);
   if (on) {
     h->flags |= MHEAP_FLAG_VALIDATE;
@@ -583,6 +585,7 @@
     h->flags &= ~MHEAP_FLAG_VALIDATE;
     h->flags |= MHEAP_FLAG_SMALL_OBJECT_CACHE;
   }
+#endif
 }
 
 void
@@ -590,12 +593,14 @@
 {
   acl_main_t *am = &acl_main;
   clib_mem_set_heap(hash_acl_set_heap(am));
+#if USE_DLMALLOC == 0
   mheap_t *h = mheap_header (am->hash_lookup_mheap);
   if (on) {
     h->flags |= MHEAP_FLAG_TRACE;
   } else {
     h->flags &= ~MHEAP_FLAG_TRACE;
   }
+#endif
 }
 
 static void
diff --git a/src/plugins/dpdk/buffer.c b/src/plugins/dpdk/buffer.c
index 6afd20e..2ce3d87 100644
--- a/src/plugins/dpdk/buffer.c
+++ b/src/plugins/dpdk/buffer.c
@@ -611,8 +611,8 @@
 {
   void *oldheap;
 
-  vlib_buffer_state_heap = mheap_alloc (0, 10 << 20);
-
+  vlib_buffer_state_heap =
+    mheap_alloc_with_lock (0, 10 << 20, 0 /* locked */ );
   oldheap = clib_mem_set_heap (vlib_buffer_state_heap);
 
   vlib_buffer_state_validation_hash = hash_create (0, sizeof (uword));
diff --git a/src/svm/ssvm.c b/src/svm/ssvm.c
index c005b61..03451e6 100644
--- a/src/svm/ssvm.c
+++ b/src/svm/ssvm.c
@@ -28,7 +28,10 @@
 int
 ssvm_master_init_shm (ssvm_private_t * ssvm)
 {
-  int ssvm_fd, mh_flags = MHEAP_FLAG_DISABLE_VM | MHEAP_FLAG_THREAD_SAFE;
+  int ssvm_fd;
+#if USE_DLMALLOC == 0
+  int mh_flags = MHEAP_FLAG_DISABLE_VM | MHEAP_FLAG_THREAD_SAFE;
+#endif
   clib_mem_vm_map_t mapa = { 0 };
   u8 junk = 0, *ssvm_filename;
   ssvm_shared_header_t *sh;
@@ -100,8 +103,15 @@
   sh->ssvm_size = ssvm->ssvm_size;
   sh->ssvm_va = pointer_to_uword (sh);
   sh->type = SSVM_SEGMENT_SHM;
+#if USE_DLMALLOC == 0
   sh->heap = mheap_alloc_with_flags (((u8 *) sh) + page_size,
 				     ssvm->ssvm_size - page_size, mh_flags);
+#else
+  sh->heap = create_mspace_with_base (((u8 *) sh) + page_size,
+				      ssvm->ssvm_size - page_size,
+				      1 /* locked */ );
+  mspace_disable_expand (sh->heap);
+#endif
 
   oldheap = ssvm_push_heap (sh);
   sh->name = format (0, "%s", ssvm->name, 0);
@@ -212,7 +222,7 @@
 int
 ssvm_master_init_memfd (ssvm_private_t * memfd)
 {
-  uword page_size, flags = MHEAP_FLAG_DISABLE_VM | MHEAP_FLAG_THREAD_SAFE;
+  uword page_size;
   ssvm_shared_header_t *sh;
   void *oldheap;
   clib_mem_vm_alloc_t alloc = { 0 };
@@ -244,9 +254,18 @@
   sh->ssvm_size = memfd->ssvm_size;
   sh->ssvm_va = pointer_to_uword (sh);
   sh->type = SSVM_SEGMENT_MEMFD;
+
+#if USE_DLMALLOC == 0
+  uword flags = MHEAP_FLAG_DISABLE_VM | MHEAP_FLAG_THREAD_SAFE;
+
   sh->heap = mheap_alloc_with_flags (((u8 *) sh) + page_size,
 				     memfd->ssvm_size - page_size, flags);
-
+#else
+  sh->heap = create_mspace_with_base (((u8 *) sh) + page_size,
+				      memfd->ssvm_size - page_size,
+				      1 /* locked */ );
+  mspace_disable_expand (sh->heap);
+#endif
   oldheap = ssvm_push_heap (sh);
   sh->name = format (0, "%s", memfd->name, 0);
   ssvm_pop_heap (oldheap);
@@ -328,22 +347,30 @@
 int
 ssvm_master_init_private (ssvm_private_t * ssvm)
 {
-  u32 pagesize = clib_mem_get_page_size ();
   ssvm_shared_header_t *sh;
-  mheap_t *heap_header;
-  u64 rnd_size = 0;
+  u32 pagesize = clib_mem_get_page_size ();
+  u32 rnd_size = 0;
   u8 *heap;
 
   rnd_size = (ssvm->ssvm_size + (pagesize - 1)) & ~(pagesize - 1);
   rnd_size = clib_min (rnd_size, ((u64) 1 << 32) - pagesize);
-  heap = mheap_alloc (0, rnd_size);
-  if (heap == 0)
-    {
-      clib_unix_warning ("mheap alloc");
-      return -1;
-    }
-  heap_header = mheap_header (heap);
-  heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
+
+#if USE_DLMALLOC == 0
+  {
+    mheap_t *heap_header;
+
+    heap = mheap_alloc (0, rnd_size);
+    if (heap == 0)
+      {
+	clib_unix_warning ("mheap alloc");
+	return -1;
+      }
+    heap_header = mheap_header (heap);
+    heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
+  }
+#else
+  heap = create_mspace (rnd_size, 1 /* locked */ );
+#endif
 
   ssvm->ssvm_size = rnd_size;
   ssvm->i_am_master = 1;
@@ -372,7 +399,11 @@
 ssvm_delete_private (ssvm_private_t * ssvm)
 {
   vec_free (ssvm->name);
+#if USE_DLMALLOC == 0
   mheap_free (ssvm->sh->heap);
+#else
+  destroy_mspace (ssvm->sh->heap);
+#endif
   clib_mem_free (ssvm->sh);
 }
 
diff --git a/src/svm/svm.c b/src/svm/svm.c
index d958c83..aa84a2f 100644
--- a/src/svm/svm.c
+++ b/src/svm/svm.c
@@ -236,6 +236,7 @@
 		}
 	    }
 	}
+#if USE_DLMALLOC == 0
       s = format (s, "  rgn heap stats: %U", format_mheap,
 		  rp->region_heap, 0);
       if ((rp->flags & SVM_FLAGS_MHEAP) && rp->data_heap)
@@ -244,6 +245,7 @@
 		      rp->data_heap, 1);
 	}
       s = format (s, "\n");
+#endif
     }
 
   return (s);
@@ -339,12 +341,18 @@
 
   if (a->flags & SVM_FLAGS_MHEAP)
     {
+#if USE_DLMALLOC == 0
       mheap_t *heap_header;
       rp->data_heap =
 	mheap_alloc_with_flags ((void *) (rp->data_base), map_size,
 				MHEAP_FLAG_DISABLE_VM);
       heap_header = mheap_header (rp->data_heap);
       heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
+#else
+      rp->data_heap = create_mspace_with_base (rp->data_base,
+					       map_size, 1 /* locked */ );
+      mspace_disable_expand (rp->data_heap);
+#endif
 
       rp->flags |= SVM_FLAGS_MHEAP;
     }
@@ -518,12 +526,22 @@
   rp->virtual_base = a->baseva;
   rp->virtual_size = a->size;
 
+#if USE_DLMALLOC == 0
   rp->region_heap =
     mheap_alloc_with_flags (uword_to_pointer
 			    (a->baseva + MMAP_PAGESIZE, void *),
 			    (a->pvt_heap_size !=
 			     0) ? a->pvt_heap_size : SVM_PVT_MHEAP_SIZE,
 			    MHEAP_FLAG_DISABLE_VM);
+#else
+  rp->region_heap = create_mspace_with_base
+    (uword_to_pointer (a->baseva + MMAP_PAGESIZE, void *),
+     (a->pvt_heap_size !=
+      0) ? a->pvt_heap_size : SVM_PVT_MHEAP_SIZE, 1 /* locked */ );
+
+  mspace_disable_expand (rp->region_heap);
+#endif
+
   oldheap = svm_push_pvt_heap (rp);
 
   rp->region_name = (char *) format (0, "%s%c", a->name, 0);
diff --git a/src/svm/svm_fifo_segment.c b/src/svm/svm_fifo_segment.c
index 7c6d802..ce1d5a0 100644
--- a/src/svm/svm_fifo_segment.c
+++ b/src/svm/svm_fifo_segment.c
@@ -107,7 +107,12 @@
 
   /* Calculate space requirements */
   pair_size = 2 * sizeof (*f) + rx_rounded_data_size + tx_rounded_data_size;
+#if USE_DLMALLOC == 0
   space_available = s->ssvm.ssvm_size - mheap_bytes (sh->heap);
+#else
+  space_available = s->ssvm.ssvm_size - mspace_usable_size (sh->heap);
+#endif
+
   pairs_to_allocate = clib_min (space_available / pair_size, *n_fifo_pairs);
   rx_fifos_size = (sizeof (*f) + rx_rounded_data_size) * pairs_to_allocate;
   tx_fifos_size = (sizeof (*f) + tx_rounded_data_size) * pairs_to_allocate;
@@ -237,7 +242,6 @@
   svm_fifo_segment_main_t *sm = &svm_fifo_segment_main;
   svm_fifo_segment_private_t *s;
   ssvm_shared_header_t *sh;
-  mheap_t *heap_header;
   u32 rnd_size = 0;
   u8 *heap;
   u32 pagesize = clib_mem_get_page_size ();
@@ -247,6 +251,7 @@
 
   rnd_size = (a->segment_size + (pagesize - 1)) & ~pagesize;
 
+#if USE_DLMALLOC == 0
   heap = mheap_alloc (0, rnd_size);
   if (heap == 0)
     {
@@ -254,8 +259,14 @@
       pool_put (sm->segments, s);
       return -1;
     }
-  heap_header = mheap_header (heap);
-  heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
+  {
+    mheap_t *heap_header;
+    heap_header = mheap_header (heap);
+    heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
+  }
+#else
+  heap = create_mspace (rnd_size, 1 /* locked */ );
+#endif
 
   s->ssvm.ssvm_size = rnd_size;
   s->ssvm.i_am_master = 1;
@@ -572,11 +583,17 @@
 {
   if (ssvm_type (&seg->ssvm) == SSVM_SEGMENT_PRIVATE)
     {
+#if USE_DLMALLOC == 0
       mheap_t *heap_header;
 
       *address = pointer_to_uword (seg->ssvm.sh->heap);
       heap_header = mheap_header (seg->ssvm.sh->heap);
       *size = heap_header->max_size;
+#else
+      mspace_get_address_and_size (seg->ssvm.sh->heap,
+				   (unsigned long long *) address,
+				   (unsigned long long *) size);
+#endif
     }
   else
     {
@@ -585,7 +602,7 @@
     }
 }
 
-mheap_t *
+void *
 svm_fifo_segment_heap (svm_fifo_segment_private_t * seg)
 {
   return seg->ssvm.sh->heap;
@@ -617,17 +634,19 @@
 {
   svm_fifo_segment_private_t *sp
     = va_arg (*args, svm_fifo_segment_private_t *);
-  int verbose = va_arg (*args, int);
+  int verbose __attribute__ ((unused)) = va_arg (*args, int);
   svm_fifo_segment_header_t *fsh = sp->h;
   u32 count, indent;
   svm_fifo_t *f;
   int i;
 
   indent = format_get_indent (s) + 2;
+#if USE_DLMALLOC == 0
   s = format (s, "%U segment heap: %U\n", format_white_space, indent,
 	      format_mheap, svm_fifo_segment_heap (sp), verbose);
   s = format (s, "%U segment has %u active fifos\n",
 	      format_white_space, indent, svm_fifo_segment_num_fifos (sp));
+#endif
 
   for (i = 0; i < vec_len (fsh->free_fifos); i++)
     {
diff --git a/src/tests/vnet/session/tcp_echo.c b/src/tests/vnet/session/tcp_echo.c
index 6c99294..6e41e4b 100644
--- a/src/tests/vnet/session/tcp_echo.c
+++ b/src/tests/vnet/session/tcp_echo.c
@@ -1409,21 +1409,14 @@
   echo_main_t *em = &echo_main;
   unformat_input_t _argv, *a = &_argv;
   u8 *chroot_prefix;
-  u8 *heap, *uri = 0;
+  u8 *uri = 0;
   u8 *bind_uri = (u8 *) "tcp://0.0.0.0/1234";
   u8 *connect_uri = (u8 *) "tcp://6.0.1.1/1234";
   u64 bytes_to_send = 64 << 10, mbytes;
   char *app_name;
   u32 tmp;
-  mheap_t *h;
 
-  clib_mem_init (0, 256 << 20);
-
-  heap = clib_mem_get_per_cpu_heap ();
-  h = mheap_header (heap);
-
-  /* make the main heap thread-safe */
-  h->flags |= MHEAP_FLAG_THREAD_SAFE;
+  clib_mem_init_thread_safe (0, 256 << 20);
 
   memset (em, 0, sizeof (*em));
   em->session_index_by_vpp_handles = hash_create (0, sizeof (uword));
diff --git a/src/tests/vnet/session/udp_echo.c b/src/tests/vnet/session/udp_echo.c
index 2e176ff..5691ca4 100644
--- a/src/tests/vnet/session/udp_echo.c
+++ b/src/tests/vnet/session/udp_echo.c
@@ -1207,16 +1207,11 @@
   app_session_t *session;
   u8 *chroot_prefix;
   char *app_name;
-  mheap_t *h;
-  u8 *heap;
   u32 tmp;
   int i;
 
-  clib_mem_init (0, 256 << 20);
-  heap = clib_mem_get_per_cpu_heap ();
-  h = mheap_header (heap);
-  /* make the main heap thread-safe */
-  h->flags |= MHEAP_FLAG_THREAD_SAFE;
+  clib_mem_init_thread_safe (0, 256 << 20);
+
   svm_fifo_segment_main_init (0x200000000ULL, 20);
 
   vec_validate (utm->rx_buf, 8192);
diff --git a/src/vat/main.c b/src/vat/main.c
index 4357114..c34ec94 100644
--- a/src/vat/main.c
+++ b/src/vat/main.c
@@ -305,18 +305,10 @@
   u8 *this_input_file;
   u8 interactive = 1;
   u8 json_output = 0;
-  u8 *heap;
-  mheap_t *h;
   int i;
   f64 timeout;
 
-  clib_mem_init (0, 128 << 20);
-
-  heap = clib_mem_get_per_cpu_heap ();
-  h = mheap_header (heap);
-
-  /* make the main heap thread-safe */
-  h->flags |= MHEAP_FLAG_THREAD_SAFE;
+  clib_mem_init_thread_safe (0, 128 << 20);
 
   clib_macro_init (&vam->macro_main);
   clib_macro_add_builtin (&vam->macro_main, "current_file",
diff --git a/src/vcl/test_vcl_listener_server.c b/src/vcl/test_vcl_listener_server.c
index 560c960..0963af0 100644
--- a/src/vcl/test_vcl_listener_server.c
+++ b/src/vcl/test_vcl_listener_server.c
@@ -62,6 +62,8 @@
   uint32_t listen_fd;
   vppcom_endpt_t endpt;
 
+  clib_mem_init_thread_safe (0, 64<<20);
+
   //Address stuff
   memset (&sin, 0, sizeof (sin));
   sin.sin_family = AF_INET;
diff --git a/src/vcl/vcl_cfg.c b/src/vcl/vcl_cfg.c
index 338a6fa..f25c8fc 100644
--- a/src/vcl/vcl_cfg.c
+++ b/src/vcl/vcl_cfg.c
@@ -200,7 +200,7 @@
       ASSERT (vcl_mem != MAP_FAILED);
       return;
     }
-  heap = clib_mem_init (vcl_mem, vcl_cfg->heapsize);
+  heap = clib_mem_init_thread_safe (vcl_mem, vcl_cfg->heapsize);
   if (!heap)
     {
       clib_warning ("VCL<%d>: ERROR: clib_mem_init() failed!", getpid ());
diff --git a/src/vcl/vcl_test_server.c b/src/vcl/vcl_test_server.c
index 5d37b46..98c36a4 100644
--- a/src/vcl/vcl_test_server.c
+++ b/src/vcl/vcl_test_server.c
@@ -25,6 +25,7 @@
 #include <fcntl.h>
 #include <vcl/vcl_test.h>
 #include <sys/epoll.h>
+#include <vppinfra/mem.h>
 
 typedef struct
 {
@@ -310,6 +311,8 @@
   uint16_t port = SOCK_TEST_SERVER_PORT;
   vppcom_endpt_t endpt;
 
+  clib_mem_init_thread_safe (0, 64 << 20);
+
   opterr = 0;
   while ((c = getopt (argc, argv, "6D")) != -1)
     switch (c)
diff --git a/src/vcl/vppcom.c b/src/vcl/vppcom.c
index 0d077ca..60c649d 100644
--- a/src/vcl/vppcom.c
+++ b/src/vcl/vppcom.c
@@ -367,25 +367,20 @@
 vppcom_app_create (char *app_name)
 {
   vppcom_cfg_t *vcl_cfg = &vcm->cfg;
-  u8 *heap;
-  mheap_t *h;
   int rv;
 
   if (!vcm->init)
     {
       vcm->init = 1;
+      vppcom_cfg (&vcm->cfg);
+
       clib_spinlock_init (&vcm->session_fifo_lockp);
       clib_fifo_validate (vcm->client_session_index_fifo,
 			  vcm->cfg.listen_queue_size);
       clib_spinlock_init (&vcm->sessions_lockp);
 
-      vppcom_cfg (&vcm->cfg);
 
       vcm->main_cpu = os_get_thread_index ();
-      heap = clib_mem_get_per_cpu_heap ();
-      h = mheap_header (heap);
-      /* make the main heap thread-safe */
-      h->flags |= MHEAP_FLAG_THREAD_SAFE;
 
       vcm->session_index_by_vpp_handles = hash_create (0, sizeof (uword));
 
diff --git a/src/vlib/cli.c b/src/vlib/cli.c
index 1692ad8..820fdef 100644
--- a/src/vlib/cli.c
+++ b/src/vlib/cli.c
@@ -707,7 +707,7 @@
 show_memory_usage (vlib_main_t * vm,
 		   unformat_input_t * input, vlib_cli_command_t * cmd)
 {
-  int verbose = 0, api_segment = 0;
+  int verbose __attribute__ ((unused)) = 0, api_segment = 0;
   clib_error_t *error;
   u32 index = 0;
 
@@ -742,19 +742,55 @@
       vec_free (s);
     }
 
+#if USE_DLMALLOC == 0
   /* *INDENT-OFF* */
   foreach_vlib_main (
   ({
       mheap_t *h = mheap_header (clib_per_cpu_mheaps[index]);
-      vlib_cli_output (vm, "%sThread %d %v\n", index ? "\n":"", index,
+      vlib_cli_output (vm, "%sThread %d %s\n", index ? "\n":"", index,
 		       vlib_worker_threads[index].name);
       vlib_cli_output (vm, "  %U\n", format_page_map, pointer_to_uword (h) -
 		       h->vm_alloc_offset_from_header,
 		       h->vm_alloc_size);
-      vlib_cli_output (vm, "  %U\n", format_mheap, clib_per_cpu_mheaps[index], verbose);
+      vlib_cli_output (vm, "  %U\n", format_mheap, clib_per_cpu_mheaps[index],
+                       verbose);
       index++;
   }));
   /* *INDENT-ON* */
+#else
+  {
+    uword clib_mem_trace_enable_disable (uword enable);
+    uword was_enabled;
+
+    /*
+     * Note: the foreach_vlib_main cause allocator traffic,
+     * so shut off tracing before we go there...
+     */
+    was_enabled = clib_mem_trace_enable_disable (0);
+
+    /* *INDENT-OFF* */
+    foreach_vlib_main (
+    ({
+      struct mallinfo mi;
+      void *mspace;
+      mspace = clib_per_cpu_mheaps[index];
+
+      mi = mspace_mallinfo (mspace);
+      vlib_cli_output (vm, "%sThread %d %s\n", index ? "\n":"", index,
+		       vlib_worker_threads[index].name);
+      vlib_cli_output (vm, "  %U\n", format_page_map,
+                       pointer_to_uword (mspace_least_addr(mspace)),
+                       mi.arena);
+      vlib_cli_output (vm, "  %U\n", format_mheap, clib_per_cpu_mheaps[index],
+                       verbose);
+      index++;
+    }));
+    /* *INDENT-ON* */
+
+    /* Restore the trace flag */
+    clib_mem_trace_enable_disable (was_enabled);
+  }
+#endif /* USE_DLMALLOC */
   return 0;
 }
 
@@ -850,6 +886,7 @@
 test_heap_validate (vlib_main_t * vm, unformat_input_t * input,
 		    vlib_cli_command_t * cmd)
 {
+#if USE_DLMALLOC == 0
   clib_error_t *error = 0;
   void *heap;
   mheap_t *mheap;
@@ -897,6 +934,9 @@
     }
 
   return error;
+#else
+  return clib_error_return (0, "unimplemented...");
+#endif /* USE_DLMALLOC */
 }
 
 /* *INDENT-OFF* */
diff --git a/src/vlib/linux/physmem.c b/src/vlib/linux/physmem.c
index a708aae..6c6b072 100755
--- a/src/vlib/linux/physmem.c
+++ b/src/vlib/linux/physmem.c
@@ -69,10 +69,18 @@
 
   while (1)
     {
+#if USE_DLMALLOC == 0
+
       mheap_get_aligned (pr->heap, n_bytes,
 			 /* align */ alignment,
 			 /* align offset */ 0,
 			 &lo_offset);
+#else
+      lo_offset = (uword) mspace_get_aligned (pr->heap, n_bytes,
+					      alignment, ~0ULL /* offset */ );
+      if (lo_offset == 0)
+	lo_offset = ~0ULL;
+#endif
 
       /* Allocation failed? */
       if (lo_offset == ~0)
@@ -94,7 +102,13 @@
     {
       uword i;
       for (i = 0; i < vec_len (to_free); i++)
-	mheap_put (pr->heap, to_free[i]);
+	{
+#if USE_DLMALLOC == 0
+	  mheap_put (pr->heap, to_free[i]);
+#else
+	  mspace_put_no_offset (pr->heap, (void *) to_free[i]);
+#endif
+	}
       vec_free (to_free);
     }
 
@@ -106,7 +120,11 @@
 {
   vlib_physmem_region_t *pr = vlib_physmem_get_region (vm, idx);
   /* Return object to region's heap. */
+#if USE_DLMALLOC == 0
   mheap_put (pr->heap, x - pr->heap);
+#else
+  mspace_put_no_offset (pr->heap, x);
+#endif
 }
 
 static clib_error_t *
@@ -181,10 +199,15 @@
 
   if (flags & VLIB_PHYSMEM_F_INIT_MHEAP)
     {
+#if USE_DLMALLOC == 0
       pr->heap = mheap_alloc_with_flags (pr->mem, pr->size,
 					 /* Don't want mheap mmap/munmap with IO memory. */
 					 MHEAP_FLAG_DISABLE_VM |
 					 MHEAP_FLAG_THREAD_SAFE);
+#else
+      pr->heap = create_mspace_with_base (pr->mem, pr->size, 1 /* locked */ );
+      mspace_disable_expand (pr->heap);
+#endif
     }
 
   *idx = pr->index;
diff --git a/src/vlib/main.h b/src/vlib/main.h
index 16e4120..8b6f947 100644
--- a/src/vlib/main.h
+++ b/src/vlib/main.h
@@ -100,8 +100,13 @@
   /* Name for e.g. syslog. */
   char *name;
 
-  /* Start and size of CLIB heap. */
+  /* Start of the heap. */
   void *heap_base;
+
+  /* Truncated version, to create frame indices */
+  void *heap_aligned_base;
+
+  /* Size of the heap */
   uword heap_size;
 
   /* Pool of buffer free lists. */
diff --git a/src/vlib/node_funcs.h b/src/vlib/node_funcs.h
index bb302f7..577e013 100644
--- a/src/vlib/node_funcs.h
+++ b/src/vlib/node_funcs.h
@@ -216,7 +216,7 @@
 vlib_get_frame_no_check (vlib_main_t * vm, uword frame_index)
 {
   vlib_frame_t *f;
-  f = vm->heap_base + (frame_index * VLIB_FRAME_ALIGN);
+  f = vm->heap_aligned_base + (frame_index * VLIB_FRAME_ALIGN);
   return f;
 }
 
@@ -227,7 +227,7 @@
 
   ASSERT (((uword) f & (VLIB_FRAME_ALIGN - 1)) == 0);
 
-  i = ((u8 *) f - (u8 *) vm->heap_base);
+  i = ((u8 *) f - (u8 *) vm->heap_aligned_base);
   ASSERT ((i / VLIB_FRAME_ALIGN) <= 0xFFFFFFFFULL);
 
   return i / VLIB_FRAME_ALIGN;
diff --git a/src/vlib/threads.c b/src/vlib/threads.c
index a946326..c53c5d6 100644
--- a/src/vlib/threads.c
+++ b/src/vlib/threads.c
@@ -727,7 +727,6 @@
   u32 n_vlib_mains = tm->n_vlib_mains;
   u32 worker_thread_index;
   u8 *main_heap = clib_mem_get_per_cpu_heap ();
-  mheap_t *main_heap_header = mheap_header (main_heap);
 
   vec_reset_length (vlib_worker_threads);
 
@@ -742,12 +741,6 @@
       vlib_set_thread_name ((char *) w->name);
     }
 
-  /*
-   * Truth of the matter: we always use at least two
-   * threads. So, make the main heap thread-safe
-   * and make the event log thread-safe.
-   */
-  main_heap_header->flags |= MHEAP_FLAG_THREAD_SAFE;
   vm->elog_main.lock =
     clib_mem_alloc_aligned (CLIB_CACHE_LINE_BYTES, CLIB_CACHE_LINE_BYTES);
   vm->elog_main.lock[0] = 0;
@@ -801,9 +794,17 @@
 	      vlib_node_t *n;
 
 	      vec_add2 (vlib_worker_threads, w, 1);
+	      /* Currently unused, may not really work */
 	      if (tr->mheap_size)
-		w->thread_mheap =
-		  mheap_alloc (0 /* use VM */ , tr->mheap_size);
+		{
+#if USE_DLMALLOC == 0
+		  w->thread_mheap =
+		    mheap_alloc (0 /* use VM */ , tr->mheap_size);
+#else
+		  w->thread_mheap = create_mspace (tr->mheap_size,
+						   0 /* unlocked */ );
+#endif
+		}
 	      else
 		w->thread_mheap = main_heap;
 
@@ -831,6 +832,8 @@
 
 	      vm_clone->thread_index = worker_thread_index;
 	      vm_clone->heap_base = w->thread_mheap;
+	      vm_clone->heap_aligned_base = (void *)
+		(((uword) w->thread_mheap) & ~(VLIB_FRAME_ALIGN - 1));
 	      vm_clone->init_functions_called =
 		hash_create (0, /* value bytes */ 0);
 	      vm_clone->pending_rpc_requests = 0;
@@ -959,8 +962,15 @@
 	    {
 	      vec_add2 (vlib_worker_threads, w, 1);
 	      if (tr->mheap_size)
-		w->thread_mheap =
-		  mheap_alloc (0 /* use VM */ , tr->mheap_size);
+		{
+#if USE_DLMALLOC == 0
+		  w->thread_mheap =
+		    mheap_alloc (0 /* use VM */ , tr->mheap_size);
+#else
+		  w->thread_mheap =
+		    create_mspace (tr->mheap_size, 0 /* locked */ );
+#endif
+		}
 	      else
 		w->thread_mheap = main_heap;
 	      w->thread_stack =
diff --git a/src/vlib/unix/main.c b/src/vlib/unix/main.c
index 947c664..2420861 100755
--- a/src/vlib/unix/main.c
+++ b/src/vlib/unix/main.c
@@ -638,6 +638,8 @@
   vm->argv = (u8 **) argv;
   vm->name = argv[0];
   vm->heap_base = clib_mem_get_heap ();
+  vm->heap_aligned_base = (void *)
+    (((uword) vm->heap_base) & ~(VLIB_FRAME_ALIGN - 1));
   ASSERT (vm->heap_base);
 
   unformat_init_command_line (&input, (char **) vm->argv);
diff --git a/src/vnet/classify/vnet_classify.c b/src/vnet/classify/vnet_classify.c
index d287a2d..9d8694a 100644
--- a/src/vnet/classify/vnet_classify.c
+++ b/src/vnet/classify/vnet_classify.c
@@ -140,7 +140,11 @@
   t->skip_n_vectors = skip_n_vectors;
   t->entries_per_page = 2;
 
+#if USE_DLMALLOC == 0
   t->mheap = mheap_alloc (0 /* use VM */ , memory_size);
+#else
+  t->mheap = create_mspace (memory_size, 1 /* locked */ );
+#endif
 
   vec_validate_aligned (t->buckets, nbuckets - 1, CLIB_CACHE_LINE_BYTES);
   oldheap = clib_mem_set_heap (t->mheap);
@@ -170,7 +174,11 @@
 
   vec_free (t->mask);
   vec_free (t->buckets);
+#if USE_DLMALLOC == 0
   mheap_free (t->mheap);
+#else
+  destroy_mspace (t->mheap);
+#endif
 
   pool_put (cm->tables, t);
 }
diff --git a/src/vnet/fib/ip4_fib.c b/src/vnet/fib/ip4_fib.c
index a3cb682..01f4a75 100644
--- a/src/vnet/fib/ip4_fib.c
+++ b/src/vnet/fib/ip4_fib.c
@@ -567,10 +567,18 @@
 u8 *
 format_ip4_fib_table_memory (u8 * s, va_list * args)
 {
+#if USE_DLMALLOC == 0
     s = format(s, "%=30s %=6d %=8ld\n",
                "IPv4 unicast",
                pool_elts(ip4_main.fibs),
                mheap_bytes(ip4_main.mtrie_mheap));
+#else
+    s = format(s, "%=30s %=6d %=8ld\n",
+               "IPv4 unicast",
+               pool_elts(ip4_main.fibs),
+               mspace_footprint(ip4_main.mtrie_mheap));
+#endif
+    
 
     return (s);
 }
diff --git a/src/vnet/ip/ip4_mtrie.c b/src/vnet/ip/ip4_mtrie.c
index 5aa9b92..97c2507 100644
--- a/src/vnet/ip/ip4_mtrie.c
+++ b/src/vnet/ip/ip4_mtrie.c
@@ -812,7 +812,11 @@
 
   if (0 == im->mtrie_heap_size)
     im->mtrie_heap_size = IP4_FIB_DEFAULT_MTRIE_HEAP_SIZE;
+#if USE_DLMALLOC == 0
   im->mtrie_mheap = mheap_alloc (0, im->mtrie_heap_size);
+#else
+  im->mtrie_mheap = create_mspace (im->mtrie_heap_size, 1 /* locked */ );
+#endif
 
   /* Burn one ply so index 0 is taken */
   old_heap = clib_mem_set_heap (ip4_main.mtrie_mheap);
diff --git a/src/vpp-api/client/client.c b/src/vpp-api/client/client.c
index cd0b5b9..f1488e2 100644
--- a/src/vpp-api/client/client.c
+++ b/src/vpp-api/client/client.c
@@ -79,13 +79,18 @@
 static void
 vac_client_constructor (void)
 {
-  u8 *heap;
-  mheap_t *h;
   clib_mem_init (0, 1 << 30);
-  heap = clib_mem_get_per_cpu_heap ();
-  h = mheap_header (heap);
-  /* make the main heap thread-safe */
-  h->flags |= MHEAP_FLAG_THREAD_SAFE;
+#if USE_DLMALLOC == 0
+  {
+      u8 *heap;
+      mheap_t *h;
+
+      heap = clib_mem_get_per_cpu_heap ();
+      h = mheap_header (heap);
+      /* make the main heap thread-safe */
+      h->flags |= MHEAP_FLAG_THREAD_SAFE;
+  }
+#endif
   if (mem_trace)
     clib_mem_trace (1);
 }
diff --git a/src/vpp-api/java/Makefile.am b/src/vpp-api/java/Makefile.am
index 321ba33..6d60a24 100644
--- a/src/vpp-api/java/Makefile.am
+++ b/src/vpp-api/java/Makefile.am
@@ -15,7 +15,7 @@
 ACLOCAL_AMFLAGS = -I m4
 AM_LIBTOOLFLAGS = --quiet
 
-AM_CFLAGS = @CPU_FLAGS@ -Wall -I${top_srcdir} -I${top_builddir} \
+AM_CFLAGS = @CPU_FLAGS@ @DLMALLOC@ -Wall -I${top_srcdir} -I${top_builddir} \
   -I$(JAVA_HOME)/include -I$(JAVA_HOME)/include/linux \
   -I@top_srcdir@/plugins -I@top_builddir@/plugins
 
diff --git a/src/vpp-api/java/jvpp-registry/jvpp_registry.c b/src/vpp-api/java/jvpp-registry/jvpp_registry.c
index c90822d..bbe9719 100644
--- a/src/vpp-api/java/jvpp-registry/jvpp_registry.c
+++ b/src/vpp-api/java/jvpp-registry/jvpp_registry.c
@@ -245,11 +245,19 @@
     return rv;
 }
 
+#if USE_DLMALLOC == 1
+void * __jvpp_heap;
+#endif
+
 static int connect_to_vpe(char *shm_prefix, char *name) {
     jvpp_main_t * jm = &jvpp_main;
     api_main_t * am = &api_main;
     jvpp_registry_main_t * rm = &jvpp_registry_main;
 
+#if USE_DLMALLOC == 1
+    __jvpp_heap = clib_mem_init (0, 1<<20);
+#endif
+
     if (vl_client_connect_to_vlib(shm_prefix, name, 32) < 0)
         return -1;
     jm->my_client_index = am->my_client_index;
diff --git a/src/vpp-api/vapi/Makefile.am b/src/vpp-api/vapi/Makefile.am
index 07ef46e..e1bd813 100644
--- a/src/vpp-api/vapi/Makefile.am
+++ b/src/vpp-api/vapi/Makefile.am
@@ -15,7 +15,7 @@
 ACLOCAL_AMFLAGS = -I m4
 AM_LIBTOOLFLAGS = --quiet
 
-AM_CFLAGS = @CPU_FLAGS@ -Wall -I${top_srcdir} -I${top_builddir} -I. -I$(top_srcdir)/vpp-api/
+AM_CFLAGS = @CPU_FLAGS@ @DLMALLOC@ -Wall -I${top_srcdir} -I${top_builddir} -I. -I$(top_srcdir)/vpp-api/
 
 AM_LDFLAGS = -shared -avoid-version -rpath /none -no-undefined
 
diff --git a/src/vpp.am b/src/vpp.am
index e8c0155..c5fd48a 100644
--- a/src/vpp.am
+++ b/src/vpp.am
@@ -39,7 +39,7 @@
 # bin_vpp_SOURCES +=				\
 #  vpp/api/gmon.c
 
-bin_vpp_CFLAGS = @APICLI@
+bin_vpp_CFLAGS = @APICLI@ @DLMALLOC@
 
 nobase_include_HEADERS +=			\
   vpp/api/vpe_all_api_h.h			\
diff --git a/src/vpp/stats/stats.c b/src/vpp/stats/stats.c
index 66d9d32..f827fe9 100644
--- a/src/vpp/stats/stats.c
+++ b/src/vpp/stats/stats.c
@@ -2474,12 +2474,12 @@
     pthread_sigmask (SIG_SETMASK, &s, 0);
   }
 
+  clib_mem_set_heap (w->thread_mheap);
+
   if (vec_len (tm->thread_prefix))
     vlib_set_thread_name ((char *)
 			  format (0, "%v_stats%c", tm->thread_prefix, '\0'));
 
-  clib_mem_set_heap (w->thread_mheap);
-
   while (1)
     {
       ip46_fib_stats_delay (sm, sm->stats_poll_interval_in_seconds,
diff --git a/src/vpp/vnet/main.c b/src/vpp/vnet/main.c
index 9a804eb..9d77a44 100644
--- a/src/vpp/vnet/main.c
+++ b/src/vpp/vnet/main.c
@@ -263,7 +263,7 @@
   vl_msg_api_set_first_available_msg_id (VL_MSG_FIRST_AVAILABLE);
 
   /* Allocate main heap */
-  if (clib_mem_init (0, main_heap_size))
+  if (clib_mem_init_thread_safe (0, main_heap_size))
     {
       vm->init_functions_called = hash_create (0, /* value bytes */ 0);
       vpe_main_init (vm);
diff --git a/src/vppinfra.am b/src/vppinfra.am
index e751de2..7641c71 100644
--- a/src/vppinfra.am
+++ b/src/vppinfra.am
@@ -248,7 +248,6 @@
   vppinfra/memcpy_avx512.h \
   vppinfra/mhash.h \
   vppinfra/mheap.h \
-  vppinfra/mheap_bootstrap.h \
   vppinfra/os.h \
   vppinfra/pipeline.h \
   vppinfra/pool.h \
@@ -290,6 +289,14 @@
   vppinfra/xy.h \
   vppinfra/zvec.h
 
+if ENABLE_DLMALLOC
+  nobase_include_HEADERS += \
+  vppinfra/dlmalloc.h
+else
+  nobase_include_HEADERS +=  \
+  vppinfra/mheap_bootstrap.h 
+endif
+
 CLIB_CORE = \
   vppinfra/asm_x86.c \
   vppinfra/backtrace.c \
@@ -314,8 +321,6 @@
   vppinfra/longjmp.S \
   vppinfra/macros.c \
   vppinfra/mhash.c \
-  vppinfra/mheap.c \
-  vppinfra/mem_mheap.c \
   vppinfra/ptclosure.c \
   vppinfra/random.c \
   vppinfra/random_buffer.c \
@@ -344,6 +349,17 @@
   vppinfra/vector.c \
   vppinfra/zvec.c
 
+if ENABLE_DLMALLOC
+  CLIB_CORE += \
+  vppinfra/mem_dlmalloc.c \
+  vppinfra/dlmalloc.c \
+  vppinfra/dlmalloc.h
+else
+  CLIB_CORE += \
+  vppinfra/mheap.c \
+  vppinfra/mem_mheap.c 
+endif
+
 # Core plus Unix additions
 libvppinfra_la_SOURCES =			\
   $(CLIB_CORE)					\
diff --git a/src/vppinfra/dlmalloc.c b/src/vppinfra/dlmalloc.c
new file mode 100644
index 0000000..8acea8b
--- /dev/null
+++ b/src/vppinfra/dlmalloc.c
@@ -0,0 +1,5098 @@
+/*
+  This is a version (aka dlmalloc) of malloc/free/realloc written by
+  Doug Lea and released to the public domain, as explained at
+  http://creativecommons.org/publicdomain/zero/1.0/ Send questions,
+  comments, complaints, performance data, etc to dl@cs.oswego.edu
+*/
+
+#include <vppinfra/dlmalloc.h>
+
+/*------------------------------ internal #includes ---------------------- */
+
+#ifdef _MSC_VER
+#pragma warning( disable : 4146 ) /* no "unsigned" warnings */
+#endif /* _MSC_VER */
+#if !NO_MALLOC_STATS
+#include <stdio.h>       /* for printing in malloc_stats */
+#endif /* NO_MALLOC_STATS */
+#ifndef LACKS_ERRNO_H
+#include <errno.h>       /* for MALLOC_FAILURE_ACTION */
+#endif /* LACKS_ERRNO_H */
+#ifdef DEBUG
+#if DLM_ABORT_ON_ASSERT_FAILURE
+#undef assert
+#define assert(x) if(!(x)) DLM_ABORT
+#else /* DLM_ABORT_ON_ASSERT_FAILURE */
+#include <assert.h>
+#endif /* DLM_ABORT_ON_ASSERT_FAILURE */
+#else  /* DEBUG */
+#ifndef assert
+#define assert(x)
+#endif
+#define DEBUG 0
+#endif /* DEBUG */
+#if !defined(WIN32) && !defined(LACKS_TIME_H)
+#include <time.h>        /* for magic initialization */
+#endif /* WIN32 */
+#ifndef LACKS_STDLIB_H
+#include <stdlib.h>      /* for abort() */
+#endif /* LACKS_STDLIB_H */
+#ifndef LACKS_STRING_H
+#include <string.h>      /* for memset etc */
+#endif  /* LACKS_STRING_H */
+#if USE_BUILTIN_FFS
+#ifndef LACKS_STRINGS_H
+#include <strings.h>     /* for ffs */
+#endif /* LACKS_STRINGS_H */
+#endif /* USE_BUILTIN_FFS */
+#if HAVE_MMAP
+#ifndef LACKS_SYS_MMAN_H
+/* On some versions of linux, mremap decl in mman.h needs __USE_GNU set */
+#if (defined(linux) && !defined(__USE_GNU))
+#define __USE_GNU 1
+#include <sys/mman.h>    /* for mmap */
+#undef __USE_GNU
+#else
+#include <sys/mman.h>    /* for mmap */
+#endif /* linux */
+#endif /* LACKS_SYS_MMAN_H */
+#ifndef LACKS_FCNTL_H
+#include <fcntl.h>
+#endif /* LACKS_FCNTL_H */
+#endif /* HAVE_MMAP */
+#ifndef LACKS_UNISTD_H
+#include <unistd.h>     /* for sbrk, sysconf */
+#else /* LACKS_UNISTD_H */
+#if !defined(__FreeBSD__) && !defined(__OpenBSD__) && !defined(__NetBSD__)
+extern void*     sbrk(ptrdiff_t);
+#endif /* FreeBSD etc */
+#endif /* LACKS_UNISTD_H */
+
+/* Declarations for locking */
+#if USE_LOCKS
+#ifndef WIN32
+#if defined (__SVR4) && defined (__sun)  /* solaris */
+#include <thread.h>
+#elif !defined(LACKS_SCHED_H)
+#include <sched.h>
+#endif /* solaris or LACKS_SCHED_H */
+#if (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0) || !USE_SPIN_LOCKS
+#include <pthread.h>
+#endif /* USE_RECURSIVE_LOCKS ... */
+#elif defined(_MSC_VER)
+#ifndef _M_AMD64
+/* These are already defined on AMD64 builds */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+LONG __cdecl _InterlockedCompareExchange(LONG volatile *Dest, LONG Exchange, LONG Comp);
+LONG __cdecl _InterlockedExchange(LONG volatile *Target, LONG Value);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+#endif /* _M_AMD64 */
+#pragma intrinsic (_InterlockedCompareExchange)
+#pragma intrinsic (_InterlockedExchange)
+#define interlockedcompareexchange _InterlockedCompareExchange
+#define interlockedexchange _InterlockedExchange
+#elif defined(WIN32) && defined(__GNUC__)
+#define interlockedcompareexchange(a, b, c) __sync_val_compare_and_swap(a, c, b)
+#define interlockedexchange __sync_lock_test_and_set
+#endif /* Win32 */
+#else /* USE_LOCKS */
+#endif /* USE_LOCKS */
+
+#ifndef LOCK_AT_FORK
+#define LOCK_AT_FORK 0
+#endif
+
+/* Declarations for bit scanning on win32 */
+#if defined(_MSC_VER) && _MSC_VER>=1300
+#ifndef BitScanForward /* Try to avoid pulling in WinNT.h */
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+unsigned char _BitScanForward(unsigned long *index, unsigned long mask);
+unsigned char _BitScanReverse(unsigned long *index, unsigned long mask);
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+
+#define BitScanForward _BitScanForward
+#define BitScanReverse _BitScanReverse
+#pragma intrinsic(_BitScanForward)
+#pragma intrinsic(_BitScanReverse)
+#endif /* BitScanForward */
+#endif /* defined(_MSC_VER) && _MSC_VER>=1300 */
+
+#ifndef WIN32
+#ifndef malloc_getpagesize
+#  ifdef _SC_PAGESIZE         /* some SVR4 systems omit an underscore */
+#    ifndef _SC_PAGE_SIZE
+#      define _SC_PAGE_SIZE _SC_PAGESIZE
+#    endif
+#  endif
+#  ifdef _SC_PAGE_SIZE
+#    define malloc_getpagesize sysconf(_SC_PAGE_SIZE)
+#  else
+#    if defined(BSD) || defined(DGUX) || defined(HAVE_GETPAGESIZE)
+       extern size_t getpagesize();
+#      define malloc_getpagesize getpagesize()
+#    else
+#      ifdef WIN32 /* use supplied emulation of getpagesize */
+#        define malloc_getpagesize getpagesize()
+#      else
+#        ifndef LACKS_SYS_PARAM_H
+#          include <sys/param.h>
+#        endif
+#        ifdef EXEC_PAGESIZE
+#          define malloc_getpagesize EXEC_PAGESIZE
+#        else
+#          ifdef NBPG
+#            ifndef CLSIZE
+#              define malloc_getpagesize NBPG
+#            else
+#              define malloc_getpagesize (NBPG * CLSIZE)
+#            endif
+#          else
+#            ifdef NBPC
+#              define malloc_getpagesize NBPC
+#            else
+#              ifdef PAGESIZE
+#                define malloc_getpagesize PAGESIZE
+#              else /* just guess */
+#                define malloc_getpagesize ((size_t)4096U)
+#              endif
+#            endif
+#          endif
+#        endif
+#      endif
+#    endif
+#  endif
+#endif
+#endif
+
+/* ------------------- size_t and alignment properties -------------------- */
+
+/* The byte and bit size of a size_t */
+#define SIZE_T_SIZE         (sizeof(size_t))
+#define SIZE_T_BITSIZE      (sizeof(size_t) << 3)
+
+/* Some constants coerced to size_t */
+/* Annoying but necessary to avoid errors on some platforms */
+#define SIZE_T_ZERO         ((size_t)0)
+#define SIZE_T_ONE          ((size_t)1)
+#define SIZE_T_TWO          ((size_t)2)
+#define SIZE_T_FOUR         ((size_t)4)
+#define TWO_SIZE_T_SIZES    (SIZE_T_SIZE<<1)
+#define FOUR_SIZE_T_SIZES   (SIZE_T_SIZE<<2)
+#define SIX_SIZE_T_SIZES    (FOUR_SIZE_T_SIZES+TWO_SIZE_T_SIZES)
+#define HALF_MAX_SIZE_T     (MAX_SIZE_T / 2U)
+
+/* The bit mask value corresponding to MALLOC_ALIGNMENT */
+#define CHUNK_ALIGN_MASK    (MALLOC_ALIGNMENT - SIZE_T_ONE)
+
+/* True if address a has acceptable alignment */
+#define is_aligned(A)       (((size_t)((A)) & (CHUNK_ALIGN_MASK)) == 0)
+
+/* the number of bytes to offset an address to align it */
+#define align_offset(A)\
+ ((((size_t)(A) & CHUNK_ALIGN_MASK) == 0)? 0 :\
+  ((MALLOC_ALIGNMENT - ((size_t)(A) & CHUNK_ALIGN_MASK)) & CHUNK_ALIGN_MASK))
+
+/* -------------------------- MMAP preliminaries ------------------------- */
+
+/*
+   If HAVE_MORECORE or HAVE_MMAP are false, we just define calls and
+   checks to fail so compiler optimizer can delete code rather than
+   using so many "#if"s.
+*/
+
+
+/* MORECORE and MMAP must return MFAIL on failure */
+#define MFAIL                ((void*)(MAX_SIZE_T))
+#define CMFAIL               ((char*)(MFAIL)) /* defined for convenience */
+
+#if HAVE_MMAP
+
+#ifndef WIN32
+#define MUNMAP_DEFAULT(a, s)  munmap((a), (s))
+#define MMAP_PROT            (PROT_READ|PROT_WRITE)
+#if !defined(MAP_ANONYMOUS) && defined(MAP_ANON)
+#define MAP_ANONYMOUS        MAP_ANON
+#endif /* MAP_ANON */
+#ifdef MAP_ANONYMOUS
+#define MMAP_FLAGS           (MAP_PRIVATE|MAP_ANONYMOUS)
+#define MMAP_DEFAULT(s)       mmap(0, (s), MMAP_PROT, MMAP_FLAGS, -1, 0)
+#else /* MAP_ANONYMOUS */
+/*
+   Nearly all versions of mmap support MAP_ANONYMOUS, so the following
+   is unlikely to be needed, but is supplied just in case.
+*/
+#define MMAP_FLAGS           (MAP_PRIVATE)
+static int dev_zero_fd = -1; /* Cached file descriptor for /dev/zero. */
+#define MMAP_DEFAULT(s) ((dev_zero_fd < 0) ? \
+           (dev_zero_fd = open("/dev/zero", O_RDWR), \
+            mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0)) : \
+            mmap(0, (s), MMAP_PROT, MMAP_FLAGS, dev_zero_fd, 0))
+#endif /* MAP_ANONYMOUS */
+
+#define DIRECT_MMAP_DEFAULT(s) MMAP_DEFAULT(s)
+
+#else /* WIN32 */
+
+/* Win32 MMAP via VirtualAlloc */
+static FORCEINLINE void* win32mmap(size_t size) {
+  void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT, PAGE_READWRITE);
+  return (ptr != 0)? ptr: MFAIL;
+}
+
+/* For direct MMAP, use MEM_TOP_DOWN to minimize interference */
+static FORCEINLINE void* win32direct_mmap(size_t size) {
+  void* ptr = VirtualAlloc(0, size, MEM_RESERVE|MEM_COMMIT|MEM_TOP_DOWN,
+                           PAGE_READWRITE);
+  return (ptr != 0)? ptr: MFAIL;
+}
+
+/* This function supports releasing coalesed segments */
+static FORCEINLINE int win32munmap(void* ptr, size_t size) {
+  MEMORY_BASIC_INFORMATION minfo;
+  char* cptr = (char*)ptr;
+  while (size) {
+    if (VirtualQuery(cptr, &minfo, sizeof(minfo)) == 0)
+      return -1;
+    if (minfo.BaseAddress != cptr || minfo.AllocationBase != cptr ||
+        minfo.State != MEM_COMMIT || minfo.RegionSize > size)
+      return -1;
+    if (VirtualFree(cptr, 0, MEM_RELEASE) == 0)
+      return -1;
+    cptr += minfo.RegionSize;
+    size -= minfo.RegionSize;
+  }
+  return 0;
+}
+
+#define MMAP_DEFAULT(s)             win32mmap(s)
+#define MUNMAP_DEFAULT(a, s)        win32munmap((a), (s))
+#define DIRECT_MMAP_DEFAULT(s)      win32direct_mmap(s)
+#endif /* WIN32 */
+#endif /* HAVE_MMAP */
+
+#if HAVE_MREMAP
+#ifndef WIN32
+#define MREMAP_DEFAULT(addr, osz, nsz, mv) mremap((addr), (osz), (nsz), (mv))
+#endif /* WIN32 */
+#endif /* HAVE_MREMAP */
+
+/**
+ * Define CALL_MORECORE
+ */
+#if HAVE_MORECORE
+    #ifdef MORECORE
+        #define CALL_MORECORE(S)    MORECORE(S)
+    #else  /* MORECORE */
+        #define CALL_MORECORE(S)    MORECORE_DEFAULT(S)
+    #endif /* MORECORE */
+#else  /* HAVE_MORECORE */
+    #define CALL_MORECORE(S)        MFAIL
+#endif /* HAVE_MORECORE */
+
+/**
+ * Define CALL_MMAP/CALL_MUNMAP/CALL_DIRECT_MMAP
+ */
+#if HAVE_MMAP
+    #define USE_MMAP_BIT            (SIZE_T_ONE)
+
+    #ifdef MMAP
+        #define CALL_MMAP(s)        MMAP(s)
+    #else /* MMAP */
+        #define CALL_MMAP(s)        MMAP_DEFAULT(s)
+    #endif /* MMAP */
+    #ifdef MUNMAP
+        #define CALL_MUNMAP(a, s)   MUNMAP((a), (s))
+    #else /* MUNMAP */
+        #define CALL_MUNMAP(a, s)   MUNMAP_DEFAULT((a), (s))
+    #endif /* MUNMAP */
+    #ifdef DIRECT_MMAP
+        #define CALL_DIRECT_MMAP(s) DIRECT_MMAP(s)
+    #else /* DIRECT_MMAP */
+        #define CALL_DIRECT_MMAP(s) DIRECT_MMAP_DEFAULT(s)
+    #endif /* DIRECT_MMAP */
+#else  /* HAVE_MMAP */
+    #define USE_MMAP_BIT            (SIZE_T_ZERO)
+
+    #define MMAP(s)                 MFAIL
+    #define MUNMAP(a, s)            (-1)
+    #define DIRECT_MMAP(s)          MFAIL
+    #define CALL_DIRECT_MMAP(s)     DIRECT_MMAP(s)
+    #define CALL_MMAP(s)            MMAP(s)
+    #define CALL_MUNMAP(a, s)       MUNMAP((a), (s))
+#endif /* HAVE_MMAP */
+
+/**
+ * Define CALL_MREMAP
+ */
+#if HAVE_MMAP && HAVE_MREMAP
+    #ifdef MREMAP
+        #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP((addr), (osz), (nsz), (mv))
+    #else /* MREMAP */
+        #define CALL_MREMAP(addr, osz, nsz, mv) MREMAP_DEFAULT((addr), (osz), (nsz), (mv))
+    #endif /* MREMAP */
+#else  /* HAVE_MMAP && HAVE_MREMAP */
+    #define CALL_MREMAP(addr, osz, nsz, mv)     MFAIL
+#endif /* HAVE_MMAP && HAVE_MREMAP */
+
+/* mstate bit set if continguous morecore disabled or failed */
+#define USE_NONCONTIGUOUS_BIT (4U)
+
+/* mstate bit set if no expansion allowed */
+#define USE_NOEXPAND_BIT (8U)
+
+/* trace allocations if set */
+#define USE_TRACE_BIT (16U)
+
+/* segment bit set in create_mspace_with_base */
+#define EXTERN_BIT            (8U)
+
+
+/* --------------------------- Lock preliminaries ------------------------ */
+
+/*
+  When locks are defined, there is one global lock, plus
+  one per-mspace lock.
+
+  The global lock_ensures that mparams.magic and other unique
+  mparams values are initialized only once. It also protects
+  sequences of calls to MORECORE.  In many cases sys_alloc requires
+  two calls, that should not be interleaved with calls by other
+  threads.  This does not protect against direct calls to MORECORE
+  by other threads not using this lock, so there is still code to
+  cope the best we can on interference.
+
+  Per-mspace locks surround calls to malloc, free, etc.
+  By default, locks are simple non-reentrant mutexes.
+
+  Because lock-protected regions generally have bounded times, it is
+  OK to use the supplied simple spinlocks. Spinlocks are likely to
+  improve performance for lightly contended applications, but worsen
+  performance under heavy contention.
+
+  If USE_LOCKS is > 1, the definitions of lock routines here are
+  bypassed, in which case you will need to define the type MLOCK_T,
+  and at least INITIAL_LOCK, DESTROY_LOCK, ACQUIRE_LOCK, RELEASE_LOCK
+  and TRY_LOCK.  You must also declare a
+    static MLOCK_T malloc_global_mutex = { initialization values };.
+
+*/
+
+#if !USE_LOCKS
+#define USE_LOCK_BIT               (0U)
+#define INITIAL_LOCK(l)            (0)
+#define DESTROY_LOCK(l)            (0)
+#define ACQUIRE_MALLOC_GLOBAL_LOCK()
+#define RELEASE_MALLOC_GLOBAL_LOCK()
+
+#else
+#if USE_LOCKS > 1
+/* -----------------------  User-defined locks ------------------------ */
+/* Define your own lock implementation here */
+/* #define INITIAL_LOCK(lk)  ... */
+/* #define DESTROY_LOCK(lk)  ... */
+/* #define ACQUIRE_LOCK(lk)  ... */
+/* #define RELEASE_LOCK(lk)  ... */
+/* #define TRY_LOCK(lk) ... */
+/* static MLOCK_T malloc_global_mutex = ... */
+
+#elif USE_SPIN_LOCKS
+
+/* First, define CAS_LOCK and CLEAR_LOCK on ints */
+/* Note CAS_LOCK defined to return 0 on success */
+
+#if defined(__GNUC__)&& (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1))
+#define CAS_LOCK(sl)     __sync_lock_test_and_set(sl, 1)
+#define CLEAR_LOCK(sl)   __sync_lock_release(sl)
+
+#elif (defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__)))
+/* Custom spin locks for older gcc on x86 */
+static FORCEINLINE int x86_cas_lock(int *sl) {
+  int ret;
+  int val = 1;
+  int cmp = 0;
+  __asm__ __volatile__  ("lock; cmpxchgl %1, %2"
+                         : "=a" (ret)
+                         : "r" (val), "m" (*(sl)), "0"(cmp)
+                         : "memory", "cc");
+  return ret;
+}
+
+static FORCEINLINE void x86_clear_lock(int* sl) {
+  assert(*sl != 0);
+  int prev = 0;
+  int ret;
+  __asm__ __volatile__ ("lock; xchgl %0, %1"
+                        : "=r" (ret)
+                        : "m" (*(sl)), "0"(prev)
+                        : "memory");
+}
+
+#define CAS_LOCK(sl)     x86_cas_lock(sl)
+#define CLEAR_LOCK(sl)   x86_clear_lock(sl)
+
+#else /* Win32 MSC */
+#define CAS_LOCK(sl)     interlockedexchange(sl, (LONG)1)
+#define CLEAR_LOCK(sl)   interlockedexchange (sl, (LONG)0)
+
+#endif /* ... gcc spins locks ... */
+
+/* How to yield for a spin lock */
+#define SPINS_PER_YIELD       63
+#if defined(_MSC_VER)
+#define SLEEP_EX_DURATION     50 /* delay for yield/sleep */
+#define SPIN_LOCK_YIELD  SleepEx(SLEEP_EX_DURATION, FALSE)
+#elif defined (__SVR4) && defined (__sun) /* solaris */
+#define SPIN_LOCK_YIELD   thr_yield();
+#elif !defined(LACKS_SCHED_H)
+#define SPIN_LOCK_YIELD   sched_yield();
+#else
+#define SPIN_LOCK_YIELD
+#endif /* ... yield ... */
+
+#if !defined(USE_RECURSIVE_LOCKS) || USE_RECURSIVE_LOCKS == 0
+/* Plain spin locks use single word (embedded in malloc_states) */
+static int spin_acquire_lock(int *sl) {
+  int spins = 0;
+  while (*(volatile int *)sl != 0 || CAS_LOCK(sl)) {
+    if ((++spins & SPINS_PER_YIELD) == 0) {
+      SPIN_LOCK_YIELD;
+    }
+  }
+  return 0;
+}
+
+#define MLOCK_T               int
+#define TRY_LOCK(sl)          !CAS_LOCK(sl)
+#define RELEASE_LOCK(sl)      CLEAR_LOCK(sl)
+#define ACQUIRE_LOCK(sl)      (CAS_LOCK(sl)? spin_acquire_lock(sl) : 0)
+#define INITIAL_LOCK(sl)      (*sl = 0)
+#define DESTROY_LOCK(sl)      (0)
+static MLOCK_T malloc_global_mutex = 0;
+
+#else /* USE_RECURSIVE_LOCKS */
+/* types for lock owners */
+#ifdef WIN32
+#define THREAD_ID_T           DWORD
+#define CURRENT_THREAD        GetCurrentThreadId()
+#define EQ_OWNER(X,Y)         ((X) == (Y))
+#else
+/*
+  Note: the following assume that pthread_t is a type that can be
+  initialized to (casted) zero. If this is not the case, you will need to
+  somehow redefine these or not use spin locks.
+*/
+#define THREAD_ID_T           pthread_t
+#define CURRENT_THREAD        pthread_self()
+#define EQ_OWNER(X,Y)         pthread_equal(X, Y)
+#endif
+
+struct malloc_recursive_lock {
+  int sl;
+  unsigned int c;
+  THREAD_ID_T threadid;
+};
+
+#define MLOCK_T  struct malloc_recursive_lock
+static MLOCK_T malloc_global_mutex = { 0, 0, (THREAD_ID_T)0};
+
+static FORCEINLINE void recursive_release_lock(MLOCK_T *lk) {
+  assert(lk->sl != 0);
+  if (--lk->c == 0) {
+    CLEAR_LOCK(&lk->sl);
+  }
+}
+
+static FORCEINLINE int recursive_acquire_lock(MLOCK_T *lk) {
+  THREAD_ID_T mythreadid = CURRENT_THREAD;
+  int spins = 0;
+  for (;;) {
+    if (*((volatile int *)(&lk->sl)) == 0) {
+      if (!CAS_LOCK(&lk->sl)) {
+        lk->threadid = mythreadid;
+        lk->c = 1;
+        return 0;
+      }
+    }
+    else if (EQ_OWNER(lk->threadid, mythreadid)) {
+      ++lk->c;
+      return 0;
+    }
+    if ((++spins & SPINS_PER_YIELD) == 0) {
+      SPIN_LOCK_YIELD;
+    }
+  }
+}
+
+static FORCEINLINE int recursive_try_lock(MLOCK_T *lk) {
+  THREAD_ID_T mythreadid = CURRENT_THREAD;
+  if (*((volatile int *)(&lk->sl)) == 0) {
+    if (!CAS_LOCK(&lk->sl)) {
+      lk->threadid = mythreadid;
+      lk->c = 1;
+      return 1;
+    }
+  }
+  else if (EQ_OWNER(lk->threadid, mythreadid)) {
+    ++lk->c;
+    return 1;
+  }
+  return 0;
+}
+
+#define RELEASE_LOCK(lk)      recursive_release_lock(lk)
+#define TRY_LOCK(lk)          recursive_try_lock(lk)
+#define ACQUIRE_LOCK(lk)      recursive_acquire_lock(lk)
+#define INITIAL_LOCK(lk)      ((lk)->threadid = (THREAD_ID_T)0, (lk)->sl = 0, (lk)->c = 0)
+#define DESTROY_LOCK(lk)      (0)
+#endif /* USE_RECURSIVE_LOCKS */
+
+#elif defined(WIN32) /* Win32 critical sections */
+#define MLOCK_T               CRITICAL_SECTION
+#define ACQUIRE_LOCK(lk)      (EnterCriticalSection(lk), 0)
+#define RELEASE_LOCK(lk)      LeaveCriticalSection(lk)
+#define TRY_LOCK(lk)          TryEnterCriticalSection(lk)
+#define INITIAL_LOCK(lk)      (!InitializeCriticalSectionAndSpinCount((lk), 0x80000000|4000))
+#define DESTROY_LOCK(lk)      (DeleteCriticalSection(lk), 0)
+#define NEED_GLOBAL_LOCK_INIT
+
+static MLOCK_T malloc_global_mutex;
+static volatile LONG malloc_global_mutex_status;
+
+/* Use spin loop to initialize global lock */
+static void init_malloc_global_mutex() {
+  for (;;) {
+    long stat = malloc_global_mutex_status;
+    if (stat > 0)
+      return;
+    /* transition to < 0 while initializing, then to > 0) */
+    if (stat == 0 &&
+        interlockedcompareexchange(&malloc_global_mutex_status, (LONG)-1, (LONG)0) == 0) {
+      InitializeCriticalSection(&malloc_global_mutex);
+      interlockedexchange(&malloc_global_mutex_status, (LONG)1);
+      return;
+    }
+    SleepEx(0, FALSE);
+  }
+}
+
+#else /* pthreads-based locks */
+#define MLOCK_T               pthread_mutex_t
+#define ACQUIRE_LOCK(lk)      pthread_mutex_lock(lk)
+#define RELEASE_LOCK(lk)      pthread_mutex_unlock(lk)
+#define TRY_LOCK(lk)          (!pthread_mutex_trylock(lk))
+#define INITIAL_LOCK(lk)      pthread_init_lock(lk)
+#define DESTROY_LOCK(lk)      pthread_mutex_destroy(lk)
+
+#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0 && defined(linux) && !defined(PTHREAD_MUTEX_RECURSIVE)
+/* Cope with old-style linux recursive lock initialization by adding */
+/* skipped internal declaration from pthread.h */
+extern int pthread_mutexattr_setkind_np __P ((pthread_mutexattr_t *__attr,
+                                              int __kind));
+#define PTHREAD_MUTEX_RECURSIVE PTHREAD_MUTEX_RECURSIVE_NP
+#define pthread_mutexattr_settype(x,y) pthread_mutexattr_setkind_np(x,y)
+#endif /* USE_RECURSIVE_LOCKS ... */
+
+static MLOCK_T malloc_global_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+static int pthread_init_lock (MLOCK_T *lk) {
+  pthread_mutexattr_t attr;
+  if (pthread_mutexattr_init(&attr)) return 1;
+#if defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0
+  if (pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE)) return 1;
+#endif
+  if (pthread_mutex_init(lk, &attr)) return 1;
+  if (pthread_mutexattr_destroy(&attr)) return 1;
+  return 0;
+}
+
+#endif /* ... lock types ... */
+
+/* Common code for all lock types */
+#define USE_LOCK_BIT               (2U)
+
+#ifndef ACQUIRE_MALLOC_GLOBAL_LOCK
+#define ACQUIRE_MALLOC_GLOBAL_LOCK()  ACQUIRE_LOCK(&malloc_global_mutex);
+#endif
+
+#ifndef RELEASE_MALLOC_GLOBAL_LOCK
+#define RELEASE_MALLOC_GLOBAL_LOCK()  RELEASE_LOCK(&malloc_global_mutex);
+#endif
+
+#endif /* USE_LOCKS */
+
+/* -----------------------  Chunk representations ------------------------ */
+
+/*
+  (The following includes lightly edited explanations by Colin Plumb.)
+
+  The malloc_chunk declaration below is misleading (but accurate and
+  necessary).  It declares a "view" into memory allowing access to
+  necessary fields at known offsets from a given base.
+
+  Chunks of memory are maintained using a `boundary tag' method as
+  originally described by Knuth.  (See the paper by Paul Wilson
+  ftp://ftp.cs.utexas.edu/pub/garbage/allocsrv.ps for a survey of such
+  techniques.)  Sizes of free chunks are stored both in the front of
+  each chunk and at the end.  This makes consolidating fragmented
+  chunks into bigger chunks fast.  The head fields also hold bits
+  representing whether chunks are free or in use.
+
+  Here are some pictures to make it clearer.  They are "exploded" to
+  show that the state of a chunk can be thought of as extending from
+  the high 31 bits of the head field of its header through the
+  prev_foot and PINUSE_BIT bit of the following chunk header.
+
+  A chunk that's in use looks like:
+
+   chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+           | Size of previous chunk (if P = 0)                             |
+           +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+         | Size of this chunk                                         1| +-+
+   mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         |                                                               |
+         +-                                                             -+
+         |                                                               |
+         +-                                                             -+
+         |                                                               :
+         +-      size - sizeof(size_t) available payload bytes          -+
+         :                                                               |
+ chunk-> +-                                                             -+
+         |                                                               |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |1|
+       | Size of next chunk (may or may not be in use)               | +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+    And if it's free, it looks like this:
+
+   chunk-> +-                                                             -+
+           | User payload (must be in use, or we would have merged!)       |
+           +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |P|
+         | Size of this chunk                                         0| +-+
+   mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Next pointer                                                  |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Prev pointer                                                  |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         |                                                               :
+         +-      size - sizeof(struct chunk) unused bytes               -+
+         :                                                               |
+ chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+         | Size of this chunk                                            |
+         +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ |0|
+       | Size of next chunk (must be in use, or we would have merged)| +-+
+ mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+       |                                                               :
+       +- User payload                                                -+
+       :                                                               |
+       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+                                                                     |0|
+                                                                     +-+
+  Note that since we always merge adjacent free chunks, the chunks
+  adjacent to a free chunk must be in use.
+
+  Given a pointer to a chunk (which can be derived trivially from the
+  payload pointer) we can, in O(1) time, find out whether the adjacent
+  chunks are free, and if so, unlink them from the lists that they
+  are on and merge them with the current chunk.
+
+  Chunks always begin on even word boundaries, so the mem portion
+  (which is returned to the user) is also on an even word boundary, and
+  thus at least double-word aligned.
+
+  The P (PINUSE_BIT) bit, stored in the unused low-order bit of the
+  chunk size (which is always a multiple of two words), is an in-use
+  bit for the *previous* chunk.  If that bit is *clear*, then the
+  word before the current chunk size contains the previous chunk
+  size, and can be used to find the front of the previous chunk.
+  The very first chunk allocated always has this bit set, preventing
+  access to non-existent (or non-owned) memory. If pinuse is set for
+  any given chunk, then you CANNOT determine the size of the
+  previous chunk, and might even get a memory addressing fault when
+  trying to do so.
+
+  The C (CINUSE_BIT) bit, stored in the unused second-lowest bit of
+  the chunk size redundantly records whether the current chunk is
+  inuse (unless the chunk is mmapped). This redundancy enables usage
+  checks within free and realloc, and reduces indirection when freeing
+  and consolidating chunks.
+
+  Each freshly allocated chunk must have both cinuse and pinuse set.
+  That is, each allocated chunk borders either a previously allocated
+  and still in-use chunk, or the base of its memory arena. This is
+  ensured by making all allocations from the `lowest' part of any
+  found chunk.  Further, no free chunk physically borders another one,
+  so each free chunk is known to be preceded and followed by either
+  inuse chunks or the ends of memory.
+
+  Note that the `foot' of the current chunk is actually represented
+  as the prev_foot of the NEXT chunk. This makes it easier to
+  deal with alignments etc but can be very confusing when trying
+  to extend or adapt this code.
+
+  The exceptions to all this are
+
+     1. The special chunk `top' is the top-most available chunk (i.e.,
+        the one bordering the end of available memory). It is treated
+        specially.  Top is never included in any bin, is used only if
+        no other chunk is available, and is released back to the
+        system if it is very large (see M_TRIM_THRESHOLD).  In effect,
+        the top chunk is treated as larger (and thus less well
+        fitting) than any other available chunk.  The top chunk
+        doesn't update its trailing size field since there is no next
+        contiguous chunk that would have to index off it. However,
+        space is still allocated for it (TOP_FOOT_SIZE) to enable
+        separation or merging when space is extended.
+
+     3. Chunks allocated via mmap, have both cinuse and pinuse bits
+        cleared in their head fields.  Because they are allocated
+        one-by-one, each must carry its own prev_foot field, which is
+        also used to hold the offset this chunk has within its mmapped
+        region, which is needed to preserve alignment. Each mmapped
+        chunk is trailed by the first two fields of a fake next-chunk
+        for sake of usage checks.
+
+*/
+
+struct malloc_chunk {
+  size_t               prev_foot;  /* Size of previous chunk (if free).  */
+  size_t               head;       /* Size and inuse bits. */
+  struct malloc_chunk* fd;         /* double links -- used only if free. */
+  struct malloc_chunk* bk;
+};
+
+typedef struct malloc_chunk  mchunk;
+typedef struct malloc_chunk* mchunkptr;
+typedef struct malloc_chunk* sbinptr;  /* The type of bins of chunks */
+typedef unsigned int bindex_t;         /* Described below */
+typedef unsigned int binmap_t;         /* Described below */
+typedef unsigned int flag_t;           /* The type of various bit flag sets */
+
+/* ------------------- Chunks sizes and alignments ----------------------- */
+
+#define MCHUNK_SIZE         (sizeof(mchunk))
+
+#if FOOTERS
+#define CHUNK_OVERHEAD      (TWO_SIZE_T_SIZES)
+#else /* FOOTERS */
+#define CHUNK_OVERHEAD      (SIZE_T_SIZE)
+#endif /* FOOTERS */
+
+/* MMapped chunks need a second word of overhead ... */
+#define MMAP_CHUNK_OVERHEAD (TWO_SIZE_T_SIZES)
+/* ... and additional padding for fake next-chunk at foot */
+#define MMAP_FOOT_PAD       (FOUR_SIZE_T_SIZES)
+
+/* The smallest size we can malloc is an aligned minimal chunk */
+#define MIN_CHUNK_SIZE\
+  ((MCHUNK_SIZE + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* conversion from malloc headers to user pointers, and back */
+#define chunk2mem(p)        ((void*)((char*)(p)       + TWO_SIZE_T_SIZES))
+#define mem2chunk(mem)      ((mchunkptr)((char*)(mem) - TWO_SIZE_T_SIZES))
+/* chunk associated with aligned address A */
+#define align_as_chunk(A)   (mchunkptr)((A) + align_offset(chunk2mem(A)))
+
+/* Bounds on request (not chunk) sizes. */
+#define MAX_REQUEST         ((-MIN_CHUNK_SIZE) << 2)
+#define MIN_REQUEST         (MIN_CHUNK_SIZE - CHUNK_OVERHEAD - SIZE_T_ONE)
+
+/* pad request bytes into a usable size */
+#define pad_request(req) \
+   (((req) + CHUNK_OVERHEAD + CHUNK_ALIGN_MASK) & ~CHUNK_ALIGN_MASK)
+
+/* pad request, checking for minimum (but not maximum) */
+#define request2size(req) \
+  (((req) < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(req))
+
+
+/* ------------------ Operations on head and foot fields ----------------- */
+
+/*
+  The head field of a chunk is or'ed with PINUSE_BIT when previous
+  adjacent chunk in use, and or'ed with CINUSE_BIT if this chunk is in
+  use, unless mmapped, in which case both bits are cleared.
+
+  FLAG4_BIT is not used by this malloc, but might be useful in extensions.
+*/
+
+#define PINUSE_BIT          (SIZE_T_ONE)
+#define CINUSE_BIT          (SIZE_T_TWO)
+#define FLAG4_BIT           (SIZE_T_FOUR)
+#define INUSE_BITS          (PINUSE_BIT|CINUSE_BIT)
+#define FLAG_BITS           (PINUSE_BIT|CINUSE_BIT|FLAG4_BIT)
+
+/* Head value for fenceposts */
+#define FENCEPOST_HEAD      (INUSE_BITS|SIZE_T_SIZE)
+
+/* extraction of fields from head words */
+#define cinuse(p)           ((p)->head & CINUSE_BIT)
+#define pinuse(p)           ((p)->head & PINUSE_BIT)
+#define flag4inuse(p)       ((p)->head & FLAG4_BIT)
+#define is_inuse(p)         (((p)->head & INUSE_BITS) != PINUSE_BIT)
+#define is_mmapped(p)       (((p)->head & INUSE_BITS) == 0)
+
+#define chunksize(p)        ((p)->head & ~(FLAG_BITS))
+
+#define clear_pinuse(p)     ((p)->head &= ~PINUSE_BIT)
+#define set_flag4(p)        ((p)->head |= FLAG4_BIT)
+#define clear_flag4(p)      ((p)->head &= ~FLAG4_BIT)
+
+/* Treat space at ptr +/- offset as a chunk */
+#define chunk_plus_offset(p, s)  ((mchunkptr)(((char*)(p)) + (s)))
+#define chunk_minus_offset(p, s) ((mchunkptr)(((char*)(p)) - (s)))
+
+/* Ptr to next or previous physical malloc_chunk. */
+#define next_chunk(p) ((mchunkptr)( ((char*)(p)) + ((p)->head & ~FLAG_BITS)))
+#define prev_chunk(p) ((mchunkptr)( ((char*)(p)) - ((p)->prev_foot) ))
+
+/* extract next chunk's pinuse bit */
+#define next_pinuse(p)  ((next_chunk(p)->head) & PINUSE_BIT)
+
+/* Get/set size at footer */
+#define get_foot(p, s)  (((mchunkptr)((char*)(p) + (s)))->prev_foot)
+#define set_foot(p, s)  (((mchunkptr)((char*)(p) + (s)))->prev_foot = (s))
+
+/* Set size, pinuse bit, and foot */
+#define set_size_and_pinuse_of_free_chunk(p, s)\
+  ((p)->head = (s|PINUSE_BIT), set_foot(p, s))
+
+/* Set size, pinuse bit, foot, and clear next pinuse */
+#define set_free_with_pinuse(p, s, n)\
+  (clear_pinuse(n), set_size_and_pinuse_of_free_chunk(p, s))
+
+/* Get the internal overhead associated with chunk p */
+#define overhead_for(p)\
+ (is_mmapped(p)? MMAP_CHUNK_OVERHEAD : CHUNK_OVERHEAD)
+
+/* Return true if malloced space is not necessarily cleared */
+#if MMAP_CLEARS
+#define calloc_must_clear(p) (!is_mmapped(p))
+#else /* MMAP_CLEARS */
+#define calloc_must_clear(p) (1)
+#endif /* MMAP_CLEARS */
+
+/* ---------------------- Overlaid data structures ----------------------- */
+
+/*
+  When chunks are not in use, they are treated as nodes of either
+  lists or trees.
+
+  "Small"  chunks are stored in circular doubly-linked lists, and look
+  like this:
+
+    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Size of previous chunk                            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `head:' |             Size of chunk, in bytes                         |P|
+      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Forward pointer to next chunk in list             |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Back pointer to previous chunk in list            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Unused space (may be 0 bytes long)                .
+            .                                                               .
+            .                                                               |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `foot:' |             Size of chunk, in bytes                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+  Larger chunks are kept in a form of bitwise digital trees (aka
+  tries) keyed on chunksizes.  Because malloc_tree_chunks are only for
+  free chunks greater than 256 bytes, their size doesn't impose any
+  constraints on user chunk sizes.  Each node looks like:
+
+    chunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Size of previous chunk                            |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `head:' |             Size of chunk, in bytes                         |P|
+      mem-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Forward pointer to next chunk of same size        |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Back pointer to previous chunk of same size       |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to left child (child[0])                  |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to right child (child[1])                 |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Pointer to parent                                 |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             bin index of this chunk                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+            |             Unused space                                      .
+            .                                                               |
+nextchunk-> +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+    `foot:' |             Size of chunk, in bytes                           |
+            +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+  Each tree holding treenodes is a tree of unique chunk sizes.  Chunks
+  of the same size are arranged in a circularly-linked list, with only
+  the oldest chunk (the next to be used, in our FIFO ordering)
+  actually in the tree.  (Tree members are distinguished by a non-null
+  parent pointer.)  If a chunk with the same size an an existing node
+  is inserted, it is linked off the existing node using pointers that
+  work in the same way as fd/bk pointers of small chunks.
+
+  Each tree contains a power of 2 sized range of chunk sizes (the
+  smallest is 0x100 <= x < 0x180), which is is divided in half at each
+  tree level, with the chunks in the smaller half of the range (0x100
+  <= x < 0x140 for the top nose) in the left subtree and the larger
+  half (0x140 <= x < 0x180) in the right subtree.  This is, of course,
+  done by inspecting individual bits.
+
+  Using these rules, each node's left subtree contains all smaller
+  sizes than its right subtree.  However, the node at the root of each
+  subtree has no particular ordering relationship to either.  (The
+  dividing line between the subtree sizes is based on trie relation.)
+  If we remove the last chunk of a given size from the interior of the
+  tree, we need to replace it with a leaf node.  The tree ordering
+  rules permit a node to be replaced by any leaf below it.
+
+  The smallest chunk in a tree (a common operation in a best-fit
+  allocator) can be found by walking a path to the leftmost leaf in
+  the tree.  Unlike a usual binary tree, where we follow left child
+  pointers until we reach a null, here we follow the right child
+  pointer any time the left one is null, until we reach a leaf with
+  both child pointers null. The smallest chunk in the tree will be
+  somewhere along that path.
+
+  The worst case number of steps to add, find, or remove a node is
+  bounded by the number of bits differentiating chunks within
+  bins. Under current bin calculations, this ranges from 6 up to 21
+  (for 32 bit sizes) or up to 53 (for 64 bit sizes). The typical case
+  is of course much better.
+*/
+
+struct malloc_tree_chunk {
+  /* The first four fields must be compatible with malloc_chunk */
+  size_t                    prev_foot;
+  size_t                    head;
+  struct malloc_tree_chunk* fd;
+  struct malloc_tree_chunk* bk;
+
+  struct malloc_tree_chunk* child[2];
+  struct malloc_tree_chunk* parent;
+  bindex_t                  index;
+};
+
+typedef struct malloc_tree_chunk  tchunk;
+typedef struct malloc_tree_chunk* tchunkptr;
+typedef struct malloc_tree_chunk* tbinptr; /* The type of bins of trees */
+
+/* A little helper macro for trees */
+#define leftmost_child(t) ((t)->child[0] != 0? (t)->child[0] : (t)->child[1])
+
+/* ----------------------------- Segments -------------------------------- */
+
+/*
+  Each malloc space may include non-contiguous segments, held in a
+  list headed by an embedded malloc_segment record representing the
+  top-most space. Segments also include flags holding properties of
+  the space. Large chunks that are directly allocated by mmap are not
+  included in this list. They are instead independently created and
+  destroyed without otherwise keeping track of them.
+
+  Segment management mainly comes into play for spaces allocated by
+  MMAP.  Any call to MMAP might or might not return memory that is
+  adjacent to an existing segment.  MORECORE normally contiguously
+  extends the current space, so this space is almost always adjacent,
+  which is simpler and faster to deal with. (This is why MORECORE is
+  used preferentially to MMAP when both are available -- see
+  sys_alloc.)  When allocating using MMAP, we don't use any of the
+  hinting mechanisms (inconsistently) supported in various
+  implementations of unix mmap, or distinguish reserving from
+  committing memory. Instead, we just ask for space, and exploit
+  contiguity when we get it.  It is probably possible to do
+  better than this on some systems, but no general scheme seems
+  to be significantly better.
+
+  Management entails a simpler variant of the consolidation scheme
+  used for chunks to reduce fragmentation -- new adjacent memory is
+  normally prepended or appended to an existing segment. However,
+  there are limitations compared to chunk consolidation that mostly
+  reflect the fact that segment processing is relatively infrequent
+  (occurring only when getting memory from system) and that we
+  don't expect to have huge numbers of segments:
+
+  * Segments are not indexed, so traversal requires linear scans.  (It
+    would be possible to index these, but is not worth the extra
+    overhead and complexity for most programs on most platforms.)
+  * New segments are only appended to old ones when holding top-most
+    memory; if they cannot be prepended to others, they are held in
+    different segments.
+
+  Except for the top-most segment of an mstate, each segment record
+  is kept at the tail of its segment. Segments are added by pushing
+  segment records onto the list headed by &mstate.seg for the
+  containing mstate.
+
+  Segment flags control allocation/merge/deallocation policies:
+  * If EXTERN_BIT set, then we did not allocate this segment,
+    and so should not try to deallocate or merge with others.
+    (This currently holds only for the initial segment passed
+    into create_mspace_with_base.)
+  * If USE_MMAP_BIT set, the segment may be merged with
+    other surrounding mmapped segments and trimmed/de-allocated
+    using munmap.
+  * If neither bit is set, then the segment was obtained using
+    MORECORE so can be merged with surrounding MORECORE'd segments
+    and deallocated/trimmed using MORECORE with negative arguments.
+*/
+
+struct malloc_segment {
+  char*        base;             /* base address */
+  size_t       size;             /* allocated size */
+  struct malloc_segment* next;   /* ptr to next segment */
+  flag_t       sflags;           /* mmap and extern flag */
+};
+
+#define is_mmapped_segment(S)  ((S)->sflags & USE_MMAP_BIT)
+#define is_extern_segment(S)   ((S)->sflags & EXTERN_BIT)
+
+typedef struct malloc_segment  msegment;
+typedef struct malloc_segment* msegmentptr;
+
+/* ---------------------------- malloc_state ----------------------------- */
+
+/*
+   A malloc_state holds all of the bookkeeping for a space.
+   The main fields are:
+
+  Top
+    The topmost chunk of the currently active segment. Its size is
+    cached in topsize.  The actual size of topmost space is
+    topsize+TOP_FOOT_SIZE, which includes space reserved for adding
+    fenceposts and segment records if necessary when getting more
+    space from the system.  The size at which to autotrim top is
+    cached from mparams in trim_check, except that it is disabled if
+    an autotrim fails.
+
+  Designated victim (dv)
+    This is the preferred chunk for servicing small requests that
+    don't have exact fits.  It is normally the chunk split off most
+    recently to service another small request.  Its size is cached in
+    dvsize. The link fields of this chunk are not maintained since it
+    is not kept in a bin.
+
+  SmallBins
+    An array of bin headers for free chunks.  These bins hold chunks
+    with sizes less than MIN_LARGE_SIZE bytes. Each bin contains
+    chunks of all the same size, spaced 8 bytes apart.  To simplify
+    use in double-linked lists, each bin header acts as a malloc_chunk
+    pointing to the real first node, if it exists (else pointing to
+    itself).  This avoids special-casing for headers.  But to avoid
+    waste, we allocate only the fd/bk pointers of bins, and then use
+    repositioning tricks to treat these as the fields of a chunk.
+
+  TreeBins
+    Treebins are pointers to the roots of trees holding a range of
+    sizes. There are 2 equally spaced treebins for each power of two
+    from TREE_SHIFT to TREE_SHIFT+16. The last bin holds anything
+    larger.
+
+  Bin maps
+    There is one bit map for small bins ("smallmap") and one for
+    treebins ("treemap).  Each bin sets its bit when non-empty, and
+    clears the bit when empty.  Bit operations are then used to avoid
+    bin-by-bin searching -- nearly all "search" is done without ever
+    looking at bins that won't be selected.  The bit maps
+    conservatively use 32 bits per map word, even if on 64bit system.
+    For a good description of some of the bit-based techniques used
+    here, see Henry S. Warren Jr's book "Hacker's Delight" (and
+    supplement at http://hackersdelight.org/). Many of these are
+    intended to reduce the branchiness of paths through malloc etc, as
+    well as to reduce the number of memory locations read or written.
+
+  Segments
+    A list of segments headed by an embedded malloc_segment record
+    representing the initial space.
+
+  Address check support
+    The least_addr field is the least address ever obtained from
+    MORECORE or MMAP. Attempted frees and reallocs of any address less
+    than this are trapped (unless INSECURE is defined).
+
+  Magic tag
+    A cross-check field that should always hold same value as mparams.magic.
+
+  Max allowed footprint
+    The maximum allowed bytes to allocate from system (zero means no limit)
+
+  Flags
+    Bits recording whether to use MMAP, locks, or contiguous MORECORE
+
+  Statistics
+    Each space keeps track of current and maximum system memory
+    obtained via MORECORE or MMAP.
+
+  Trim support
+    Fields holding the amount of unused topmost memory that should trigger
+    trimming, and a counter to force periodic scanning to release unused
+    non-topmost segments.
+
+  Locking
+    If USE_LOCKS is defined, the "mutex" lock is acquired and released
+    around every public call using this mspace.
+
+  Extension support
+    A void* pointer and a size_t field that can be used to help implement
+    extensions to this malloc.
+*/
+
+/* Bin types, widths and sizes */
+#define NSMALLBINS        (32U)
+#define NTREEBINS         (32U)
+#define SMALLBIN_SHIFT    (3U)
+#define SMALLBIN_WIDTH    (SIZE_T_ONE << SMALLBIN_SHIFT)
+#define TREEBIN_SHIFT     (8U)
+#define MIN_LARGE_SIZE    (SIZE_T_ONE << TREEBIN_SHIFT)
+#define MAX_SMALL_SIZE    (MIN_LARGE_SIZE - SIZE_T_ONE)
+#define MAX_SMALL_REQUEST (MAX_SMALL_SIZE - CHUNK_ALIGN_MASK - CHUNK_OVERHEAD)
+
+struct malloc_state {
+  binmap_t   smallmap;
+  binmap_t   treemap;
+  size_t     dvsize;
+  size_t     topsize;
+  char*      least_addr;
+  mchunkptr  dv;
+  mchunkptr  top;
+  size_t     trim_check;
+  size_t     release_checks;
+  size_t     magic;
+  mchunkptr  smallbins[(NSMALLBINS+1)*2];
+  tbinptr    treebins[NTREEBINS];
+  size_t     footprint;
+  size_t     max_footprint;
+  size_t     footprint_limit; /* zero means no limit */
+  flag_t     mflags;
+#if USE_LOCKS
+  MLOCK_T    mutex;     /* locate lock among fields that rarely change */
+#endif /* USE_LOCKS */
+  msegment   seg;
+  void*      extp;      /* Unused but available for extensions */
+  size_t     exts;
+};
+
+typedef struct malloc_state*    mstate;
+
+/* ------------- Global malloc_state and malloc_params ------------------- */
+
+/*
+  malloc_params holds global properties, including those that can be
+  dynamically set using mallopt. There is a single instance, mparams,
+  initialized in init_mparams. Note that the non-zeroness of "magic"
+  also serves as an initialization flag.
+*/
+
+struct malloc_params {
+  size_t magic;
+  size_t page_size;
+  size_t granularity;
+  size_t mmap_threshold;
+  size_t trim_threshold;
+  flag_t default_mflags;
+};
+
+static struct malloc_params mparams;
+
+/* Ensure mparams initialized */
+#define ensure_initialization() (void)(mparams.magic != 0 || init_mparams())
+
+#if !ONLY_MSPACES
+
+/* The global malloc_state used for all non-"mspace" calls */
+static struct malloc_state _gm_;
+#define gm                 (&_gm_)
+#define is_global(M)       ((M) == &_gm_)
+
+#endif /* !ONLY_MSPACES */
+
+#define is_initialized(M)  ((M)->top != 0)
+
+/* -------------------------- system alloc setup ------------------------- */
+
+/* Operations on mflags */
+
+#define use_lock(M)           ((M)->mflags &   USE_LOCK_BIT)
+#define enable_lock(M)        ((M)->mflags |=  USE_LOCK_BIT)
+#if USE_LOCKS
+#define disable_lock(M)       ((M)->mflags &= ~USE_LOCK_BIT)
+#else
+#define disable_lock(M)
+#endif
+
+#define use_mmap(M)           ((M)->mflags &   USE_MMAP_BIT)
+#define enable_mmap(M)        ((M)->mflags |=  USE_MMAP_BIT)
+#if HAVE_MMAP
+#define disable_mmap(M)       ((M)->mflags &= ~USE_MMAP_BIT)
+#else
+#define disable_mmap(M)
+#endif
+
+#define use_noncontiguous(M)  ((M)->mflags &   USE_NONCONTIGUOUS_BIT)
+#define disable_contiguous(M) ((M)->mflags |=  USE_NONCONTIGUOUS_BIT)
+#define use_noexpand(M) ((M)->mflags & USE_NOEXPAND_BIT)
+#define disable_expand(M) ((M)->mflags |= USE_NOEXPAND_BIT)
+#define use_trace(M) ((M)->mflags & USE_TRACE_BIT)
+#define enable_trace(M) ((M)->mflags |= USE_TRACE_BIT)
+#define disable_trace(M) ((M)->mflags |= USE_TRACE_BIT)
+
+#define set_lock(M,L)\
+ ((M)->mflags = (L)?\
+  ((M)->mflags | USE_LOCK_BIT) :\
+  ((M)->mflags & ~USE_LOCK_BIT))
+
+/* page-align a size */
+#define page_align(S)\
+ (((S) + (mparams.page_size - SIZE_T_ONE)) & ~(mparams.page_size - SIZE_T_ONE))
+
+/* granularity-align a size */
+#define granularity_align(S)\
+  (((S) + (mparams.granularity - SIZE_T_ONE))\
+   & ~(mparams.granularity - SIZE_T_ONE))
+
+
+/* For mmap, use granularity alignment on windows, else page-align */
+#ifdef WIN32
+#define mmap_align(S) granularity_align(S)
+#else
+#define mmap_align(S) page_align(S)
+#endif
+
+/* For sys_alloc, enough padding to ensure can malloc request on success */
+#define SYS_ALLOC_PADDING (TOP_FOOT_SIZE + MALLOC_ALIGNMENT)
+
+#define is_page_aligned(S)\
+   (((size_t)(S) & (mparams.page_size - SIZE_T_ONE)) == 0)
+#define is_granularity_aligned(S)\
+   (((size_t)(S) & (mparams.granularity - SIZE_T_ONE)) == 0)
+
+/*  True if segment S holds address A */
+#define segment_holds(S, A)\
+  ((char*)(A) >= S->base && (char*)(A) < S->base + S->size)
+
+/* Return segment holding given address */
+static msegmentptr segment_holding(mstate m, char* addr) {
+  msegmentptr sp = &m->seg;
+  for (;;) {
+    if (addr >= sp->base && addr < sp->base + sp->size)
+      return sp;
+    if ((sp = sp->next) == 0)
+      return 0;
+  }
+}
+
+/* Return true if segment contains a segment link */
+static int has_segment_link(mstate m, msegmentptr ss) {
+  msegmentptr sp = &m->seg;
+  for (;;) {
+    if ((char*)sp >= ss->base && (char*)sp < ss->base + ss->size)
+      return 1;
+    if ((sp = sp->next) == 0)
+      return 0;
+  }
+}
+
+#ifndef MORECORE_CANNOT_TRIM
+#define should_trim(M,s)  ((s) > (M)->trim_check)
+#else  /* MORECORE_CANNOT_TRIM */
+#define should_trim(M,s)  (0)
+#endif /* MORECORE_CANNOT_TRIM */
+
+/*
+  TOP_FOOT_SIZE is padding at the end of a segment, including space
+  that may be needed to place segment records and fenceposts when new
+  noncontiguous segments are added.
+*/
+#define TOP_FOOT_SIZE\
+  (align_offset(chunk2mem(0))+pad_request(sizeof(struct malloc_segment))+MIN_CHUNK_SIZE)
+
+
+/* -------------------------------  Hooks -------------------------------- */
+
+/*
+  PREACTION should be defined to return 0 on success, and nonzero on
+  failure. If you are not using locking, you can redefine these to do
+  anything you like.
+*/
+
+#if USE_LOCKS
+#define PREACTION(M)  ((use_lock(M))? ACQUIRE_LOCK(&(M)->mutex) : 0)
+#define POSTACTION(M) { if (use_lock(M)) RELEASE_LOCK(&(M)->mutex); }
+#else /* USE_LOCKS */
+
+#ifndef PREACTION
+#define PREACTION(M) (0)
+#endif  /* PREACTION */
+
+#ifndef POSTACTION
+#define POSTACTION(M)
+#endif  /* POSTACTION */
+
+#endif /* USE_LOCKS */
+
+/*
+  CORRUPTION_ERROR_ACTION is triggered upon detected bad addresses.
+  USAGE_ERROR_ACTION is triggered on detected bad frees and
+  reallocs. The argument p is an address that might have triggered the
+  fault. It is ignored by the two predefined actions, but might be
+  useful in custom actions that try to help diagnose errors.
+*/
+
+#if PROCEED_ON_ERROR
+
+/* A count of the number of corruption errors causing resets */
+int malloc_corruption_error_count;
+
+/* default corruption action */
+static void reset_on_error(mstate m);
+
+#define CORRUPTION_ERROR_ACTION(m)  reset_on_error(m)
+#define USAGE_ERROR_ACTION(m, p)
+
+#else /* PROCEED_ON_ERROR */
+
+#ifndef CORRUPTION_ERROR_ACTION
+#define CORRUPTION_ERROR_ACTION(m) DLM_ABORT
+#endif /* CORRUPTION_ERROR_ACTION */
+
+#ifndef USAGE_ERROR_ACTION
+#define USAGE_ERROR_ACTION(m,p) DLM_ABORT
+#endif /* USAGE_ERROR_ACTION */
+
+#endif /* PROCEED_ON_ERROR */
+
+
+/* -------------------------- Debugging setup ---------------------------- */
+
+#if ! DEBUG
+
+#define check_free_chunk(M,P)
+#define check_inuse_chunk(M,P)
+#define check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P)
+#define check_malloc_state(M)
+#define check_top_chunk(M,P)
+
+#else /* DEBUG */
+#define check_free_chunk(M,P)       do_check_free_chunk(M,P)
+#define check_inuse_chunk(M,P)      do_check_inuse_chunk(M,P)
+#define check_top_chunk(M,P)        do_check_top_chunk(M,P)
+#define check_malloced_chunk(M,P,N) do_check_malloced_chunk(M,P,N)
+#define check_mmapped_chunk(M,P)    do_check_mmapped_chunk(M,P)
+#define check_malloc_state(M)       do_check_malloc_state(M)
+
+static void   do_check_any_chunk(mstate m, mchunkptr p);
+static void   do_check_top_chunk(mstate m, mchunkptr p);
+static void   do_check_mmapped_chunk(mstate m, mchunkptr p);
+static void   do_check_inuse_chunk(mstate m, mchunkptr p);
+static void   do_check_free_chunk(mstate m, mchunkptr p);
+static void   do_check_malloced_chunk(mstate m, void* mem, size_t s);
+static void   do_check_tree(mstate m, tchunkptr t);
+static void   do_check_treebin(mstate m, bindex_t i);
+static void   do_check_smallbin(mstate m, bindex_t i);
+static void   do_check_malloc_state(mstate m);
+static int    bin_find(mstate m, mchunkptr x);
+static size_t traverse_and_check(mstate m);
+#endif /* DEBUG */
+
+/* ---------------------------- Indexing Bins ---------------------------- */
+
+#define is_small(s)         (((s) >> SMALLBIN_SHIFT) < NSMALLBINS)
+#define small_index(s)      (bindex_t)((s)  >> SMALLBIN_SHIFT)
+#define small_index2size(i) ((i)  << SMALLBIN_SHIFT)
+#define MIN_SMALL_INDEX     (small_index(MIN_CHUNK_SIZE))
+
+/* addressing by index. See above about smallbin repositioning */
+#define smallbin_at(M, i)   ((sbinptr)((char*)&((M)->smallbins[(i)<<1])))
+#define treebin_at(M,i)     (&((M)->treebins[i]))
+
+/* assign tree index for size S to variable I. Use x86 asm if possible  */
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_tree_index(S, I)\
+{\
+  unsigned int X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K = (unsigned) sizeof(X)*__CHAR_BIT__ - 1 - (unsigned) __builtin_clz(X); \
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K = _bit_scan_reverse (X); \
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int K;\
+    _BitScanReverse((DWORD *) &K, (DWORD) X);\
+    I =  (bindex_t)((K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1)));\
+  }\
+}
+
+#else /* GNUC */
+#define compute_tree_index(S, I)\
+{\
+  size_t X = S >> TREEBIN_SHIFT;\
+  if (X == 0)\
+    I = 0;\
+  else if (X > 0xFFFF)\
+    I = NTREEBINS-1;\
+  else {\
+    unsigned int Y = (unsigned int)X;\
+    unsigned int N = ((Y - 0x100) >> 16) & 8;\
+    unsigned int K = (((Y <<= N) - 0x1000) >> 16) & 4;\
+    N += K;\
+    N += K = (((Y <<= K) - 0x4000) >> 16) & 2;\
+    K = 14 - N + ((Y <<= K) >> 15);\
+    I = (K << 1) + ((S >> (K + (TREEBIN_SHIFT-1)) & 1));\
+  }\
+}
+#endif /* GNUC */
+
+/* Bit representing maximum resolved size in a treebin at i */
+#define bit_for_tree_index(i) \
+   (i == NTREEBINS-1)? (SIZE_T_BITSIZE-1) : (((i) >> 1) + TREEBIN_SHIFT - 2)
+
+/* Shift placing maximum resolved bit in a treebin at i as sign bit */
+#define leftshift_for_tree_index(i) \
+   ((i == NTREEBINS-1)? 0 : \
+    ((SIZE_T_BITSIZE-SIZE_T_ONE) - (((i) >> 1) + TREEBIN_SHIFT - 2)))
+
+/* The size of the smallest chunk held in bin with index i */
+#define minsize_for_tree_index(i) \
+   ((SIZE_T_ONE << (((i) >> 1) + TREEBIN_SHIFT)) |  \
+   (((size_t)((i) & SIZE_T_ONE)) << (((i) >> 1) + TREEBIN_SHIFT - 1)))
+
+
+/* ------------------------ Operations on bin maps ----------------------- */
+
+/* bit corresponding to given index */
+#define idx2bit(i)              ((binmap_t)(1) << (i))
+
+/* Mark/Clear bits with given index */
+#define mark_smallmap(M,i)      ((M)->smallmap |=  idx2bit(i))
+#define clear_smallmap(M,i)     ((M)->smallmap &= ~idx2bit(i))
+#define smallmap_is_marked(M,i) ((M)->smallmap &   idx2bit(i))
+
+#define mark_treemap(M,i)       ((M)->treemap  |=  idx2bit(i))
+#define clear_treemap(M,i)      ((M)->treemap  &= ~idx2bit(i))
+#define treemap_is_marked(M,i)  ((M)->treemap  &   idx2bit(i))
+
+/* isolate the least set bit of a bitmap */
+#define least_bit(x)         ((x) & -(x))
+
+/* mask with all bits to left of least bit of x on */
+#define left_bits(x)         ((x<<1) | -(x<<1))
+
+/* mask with all bits to left of or equal to least bit of x on */
+#define same_or_left_bits(x) ((x) | -(x))
+
+/* index corresponding to given bit. Use x86 asm if possible */
+
+#if defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  J = __builtin_ctz(X); \
+  I = (bindex_t)J;\
+}
+
+#elif defined (__INTEL_COMPILER)
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  J = _bit_scan_forward (X); \
+  I = (bindex_t)J;\
+}
+
+#elif defined(_MSC_VER) && _MSC_VER>=1300
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int J;\
+  _BitScanForward((DWORD *) &J, X);\
+  I = (bindex_t)J;\
+}
+
+#elif USE_BUILTIN_FFS
+#define compute_bit2idx(X, I) I = ffs(X)-1
+
+#else
+#define compute_bit2idx(X, I)\
+{\
+  unsigned int Y = X - 1;\
+  unsigned int K = Y >> (16-4) & 16;\
+  unsigned int N = K;        Y >>= K;\
+  N += K = Y >> (8-3) &  8;  Y >>= K;\
+  N += K = Y >> (4-2) &  4;  Y >>= K;\
+  N += K = Y >> (2-1) &  2;  Y >>= K;\
+  N += K = Y >> (1-0) &  1;  Y >>= K;\
+  I = (bindex_t)(N + Y);\
+}
+#endif /* GNUC */
+
+
+/* ----------------------- Runtime Check Support ------------------------- */
+
+/*
+  For security, the main invariant is that malloc/free/etc never
+  writes to a static address other than malloc_state, unless static
+  malloc_state itself has been corrupted, which cannot occur via
+  malloc (because of these checks). In essence this means that we
+  believe all pointers, sizes, maps etc held in malloc_state, but
+  check all of those linked or offsetted from other embedded data
+  structures.  These checks are interspersed with main code in a way
+  that tends to minimize their run-time cost.
+
+  When FOOTERS is defined, in addition to range checking, we also
+  verify footer fields of inuse chunks, which can be used guarantee
+  that the mstate controlling malloc/free is intact.  This is a
+  streamlined version of the approach described by William Robertson
+  et al in "Run-time Detection of Heap-based Overflows" LISA'03
+  http://www.usenix.org/events/lisa03/tech/robertson.html The footer
+  of an inuse chunk holds the xor of its mstate and a random seed,
+  that is checked upon calls to free() and realloc().  This is
+  (probabalistically) unguessable from outside the program, but can be
+  computed by any code successfully malloc'ing any chunk, so does not
+  itself provide protection against code that has already broken
+  security through some other means.  Unlike Robertson et al, we
+  always dynamically check addresses of all offset chunks (previous,
+  next, etc). This turns out to be cheaper than relying on hashes.
+*/
+
+#if !INSECURE
+/* Check if address a is at least as high as any from MORECORE or MMAP */
+#define ok_address(M, a) ((char*)(a) >= (M)->least_addr)
+/* Check if address of next chunk n is higher than base chunk p */
+#define ok_next(p, n)    ((char*)(p) < (char*)(n))
+/* Check if p has inuse status */
+#define ok_inuse(p)     is_inuse(p)
+/* Check if p has its pinuse bit on */
+#define ok_pinuse(p)     pinuse(p)
+
+#else /* !INSECURE */
+#define ok_address(M, a) (1)
+#define ok_next(b, n)    (1)
+#define ok_inuse(p)      (1)
+#define ok_pinuse(p)     (1)
+#endif /* !INSECURE */
+
+#if (FOOTERS && !INSECURE)
+/* Check if (alleged) mstate m has expected magic field */
+#define ok_magic(M)      ((M)->magic == mparams.magic)
+#else  /* (FOOTERS && !INSECURE) */
+#define ok_magic(M)      (1)
+#endif /* (FOOTERS && !INSECURE) */
+
+/* In gcc, use __builtin_expect to minimize impact of checks */
+#if !INSECURE
+#if defined(__GNUC__) && __GNUC__ >= 3
+#define RTCHECK(e)  __builtin_expect(e, 1)
+#else /* GNUC */
+#define RTCHECK(e)  (e)
+#endif /* GNUC */
+#else /* !INSECURE */
+#define RTCHECK(e)  (1)
+#endif /* !INSECURE */
+
+/* macros to set up inuse chunks with or without footers */
+
+#if !FOOTERS
+
+#define mark_inuse_foot(M,p,s)
+
+/* Macros for setting head/foot of non-mmapped chunks */
+
+/* Set cinuse bit and pinuse bit of next chunk */
+#define set_inuse(M,p,s)\
+  ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+  ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set cinuse and pinuse of this chunk and pinuse of next chunk */
+#define set_inuse_and_pinuse(M,p,s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  ((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT)
+
+/* Set size, cinuse and pinuse bit of this chunk */
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT))
+
+#else /* FOOTERS */
+
+/* Set foot of inuse chunk to be xor of mstate and seed */
+#define mark_inuse_foot(M,p,s)\
+  (((mchunkptr)((char*)(p) + (s)))->prev_foot = ((size_t)(M) ^ mparams.magic))
+
+#define get_mstate_for(p)\
+  ((mstate)(((mchunkptr)((char*)(p) +\
+    (chunksize(p))))->prev_foot ^ mparams.magic))
+
+#define set_inuse(M,p,s)\
+  ((p)->head = (((p)->head & PINUSE_BIT)|s|CINUSE_BIT),\
+  (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT), \
+  mark_inuse_foot(M,p,s))
+
+#define set_inuse_and_pinuse(M,p,s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  (((mchunkptr)(((char*)(p)) + (s)))->head |= PINUSE_BIT),\
+ mark_inuse_foot(M,p,s))
+
+#define set_size_and_pinuse_of_inuse_chunk(M, p, s)\
+  ((p)->head = (s|PINUSE_BIT|CINUSE_BIT),\
+  mark_inuse_foot(M, p, s))
+
+#endif /* !FOOTERS */
+
+/* ---------------------------- setting mparams -------------------------- */
+
+#if LOCK_AT_FORK
+static void pre_fork(void)         { ACQUIRE_LOCK(&(gm)->mutex); }
+static void post_fork_parent(void) { RELEASE_LOCK(&(gm)->mutex); }
+static void post_fork_child(void)  { INITIAL_LOCK(&(gm)->mutex); }
+#endif /* LOCK_AT_FORK */
+
+/* Initialize mparams */
+static int init_mparams(void) {
+#ifdef NEED_GLOBAL_LOCK_INIT
+  if (malloc_global_mutex_status <= 0)
+    init_malloc_global_mutex();
+#endif
+
+  ACQUIRE_MALLOC_GLOBAL_LOCK();
+  if (mparams.magic == 0) {
+    size_t magic;
+    size_t psize;
+    size_t gsize;
+
+#ifndef WIN32
+    psize = malloc_getpagesize;
+    gsize = ((DEFAULT_GRANULARITY != 0)? DEFAULT_GRANULARITY : psize);
+#else /* WIN32 */
+    {
+      SYSTEM_INFO system_info;
+      GetSystemInfo(&system_info);
+      psize = system_info.dwPageSize;
+      gsize = ((DEFAULT_GRANULARITY != 0)?
+               DEFAULT_GRANULARITY : system_info.dwAllocationGranularity);
+    }
+#endif /* WIN32 */
+
+    /* Sanity-check configuration:
+       size_t must be unsigned and as wide as pointer type.
+       ints must be at least 4 bytes.
+       alignment must be at least 8.
+       Alignment, min chunk size, and page size must all be powers of 2.
+    */
+    if ((sizeof(size_t) != sizeof(char*)) ||
+        (MAX_SIZE_T < MIN_CHUNK_SIZE)  ||
+        (sizeof(int) < 4)  ||
+        (MALLOC_ALIGNMENT < (size_t)8U) ||
+        ((MALLOC_ALIGNMENT & (MALLOC_ALIGNMENT-SIZE_T_ONE)) != 0) ||
+        ((MCHUNK_SIZE      & (MCHUNK_SIZE-SIZE_T_ONE))      != 0) ||
+        ((gsize            & (gsize-SIZE_T_ONE))            != 0) ||
+        ((psize            & (psize-SIZE_T_ONE))            != 0))
+      DLM_ABORT;
+    mparams.granularity = gsize;
+    mparams.page_size = psize;
+    mparams.mmap_threshold = DEFAULT_MMAP_THRESHOLD;
+    mparams.trim_threshold = DEFAULT_TRIM_THRESHOLD;
+#if MORECORE_CONTIGUOUS
+    mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT;
+#else  /* MORECORE_CONTIGUOUS */
+    mparams.default_mflags = USE_LOCK_BIT|USE_MMAP_BIT|USE_NONCONTIGUOUS_BIT;
+#endif /* MORECORE_CONTIGUOUS */
+
+#if !ONLY_MSPACES
+    /* Set up lock for main malloc area */
+    gm->mflags = mparams.default_mflags;
+    (void)INITIAL_LOCK(&gm->mutex);
+#endif
+#if LOCK_AT_FORK
+    pthread_atfork(&pre_fork, &post_fork_parent, &post_fork_child);
+#endif
+
+    {
+#if USE_DEV_RANDOM
+      int fd;
+      unsigned char buf[sizeof(size_t)];
+      /* Try to use /dev/urandom, else fall back on using time */
+      if ((fd = open("/dev/urandom", O_RDONLY)) >= 0 &&
+          read(fd, buf, sizeof(buf)) == sizeof(buf)) {
+        magic = *((size_t *) buf);
+        close(fd);
+      }
+      else
+#endif /* USE_DEV_RANDOM */
+#ifdef WIN32
+      magic = (size_t)(GetTickCount() ^ (size_t)0x55555555U);
+#elif defined(LACKS_TIME_H)
+      magic = (size_t)&magic ^ (size_t)0x55555555U;
+#else
+      magic = (size_t)(time(0) ^ (size_t)0x55555555U);
+#endif
+      magic |= (size_t)8U;    /* ensure nonzero */
+      magic &= ~(size_t)7U;   /* improve chances of fault for bad values */
+      /* Until memory modes commonly available, use volatile-write */
+      (*(volatile size_t *)(&(mparams.magic))) = magic;
+    }
+  }
+
+  RELEASE_MALLOC_GLOBAL_LOCK();
+  return 1;
+}
+
+/* support for mallopt */
+static int change_mparam(int param_number, int value) {
+  size_t val;
+  ensure_initialization();
+  val = (value == -1)? MAX_SIZE_T : (size_t)value;
+  switch(param_number) {
+  case M_TRIM_THRESHOLD:
+    mparams.trim_threshold = val;
+    return 1;
+  case M_GRANULARITY:
+    if (val >= mparams.page_size && ((val & (val-1)) == 0)) {
+      mparams.granularity = val;
+      return 1;
+    }
+    else
+      return 0;
+  case M_MMAP_THRESHOLD:
+    mparams.mmap_threshold = val;
+    return 1;
+  default:
+    return 0;
+  }
+}
+
+#if DEBUG
+/* ------------------------- Debugging Support --------------------------- */
+
+/* Check properties of any chunk, whether free, inuse, mmapped etc  */
+static void do_check_any_chunk(mstate m, mchunkptr p) {
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+}
+
+/* Check properties of top chunk */
+static void do_check_top_chunk(mstate m, mchunkptr p) {
+  msegmentptr sp = segment_holding(m, (char*)p);
+  size_t  sz = p->head & ~INUSE_BITS; /* third-lowest bit can be set! */
+  assert(sp != 0);
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+  assert(sz == m->topsize);
+  assert(sz > 0);
+  assert(sz == ((sp->base + sp->size) - (char*)p) - TOP_FOOT_SIZE);
+  assert(pinuse(p));
+  assert(!pinuse(chunk_plus_offset(p, sz)));
+}
+
+/* Check properties of (inuse) mmapped chunks */
+static void do_check_mmapped_chunk(mstate m, mchunkptr p) {
+  size_t  sz = chunksize(p);
+  size_t len = (sz + (p->prev_foot) + MMAP_FOOT_PAD);
+  assert(is_mmapped(p));
+  assert(use_mmap(m));
+  assert((is_aligned(chunk2mem(p))) || (p->head == FENCEPOST_HEAD));
+  assert(ok_address(m, p));
+  assert(!is_small(sz));
+  assert((len & (mparams.page_size-SIZE_T_ONE)) == 0);
+  assert(chunk_plus_offset(p, sz)->head == FENCEPOST_HEAD);
+  assert(chunk_plus_offset(p, sz+SIZE_T_SIZE)->head == 0);
+}
+
+/* Check properties of inuse chunks */
+static void do_check_inuse_chunk(mstate m, mchunkptr p) {
+  do_check_any_chunk(m, p);
+  assert(is_inuse(p));
+  assert(next_pinuse(p));
+  /* If not pinuse and not mmapped, previous chunk has OK offset */
+  assert(is_mmapped(p) || pinuse(p) || next_chunk(prev_chunk(p)) == p);
+  if (is_mmapped(p))
+    do_check_mmapped_chunk(m, p);
+}
+
+/* Check properties of free chunks */
+static void do_check_free_chunk(mstate m, mchunkptr p) {
+  size_t sz = chunksize(p);
+  mchunkptr next = chunk_plus_offset(p, sz);
+  do_check_any_chunk(m, p);
+  assert(!is_inuse(p));
+  assert(!next_pinuse(p));
+  assert (!is_mmapped(p));
+  if (p != m->dv && p != m->top) {
+    if (sz >= MIN_CHUNK_SIZE) {
+      assert((sz & CHUNK_ALIGN_MASK) == 0);
+      assert(is_aligned(chunk2mem(p)));
+      assert(next->prev_foot == sz);
+      assert(pinuse(p));
+      assert (next == m->top || is_inuse(next));
+      assert(p->fd->bk == p);
+      assert(p->bk->fd == p);
+    }
+    else  /* markers are always of size SIZE_T_SIZE */
+      assert(sz == SIZE_T_SIZE);
+  }
+}
+
+/* Check properties of malloced chunks at the point they are malloced */
+static void do_check_malloced_chunk(mstate m, void* mem, size_t s) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    size_t sz = p->head & ~INUSE_BITS;
+    do_check_inuse_chunk(m, p);
+    assert((sz & CHUNK_ALIGN_MASK) == 0);
+    assert(sz >= MIN_CHUNK_SIZE);
+    assert(sz >= s);
+    /* unless mmapped, size is less than MIN_CHUNK_SIZE more than request */
+    assert(is_mmapped(p) || sz < (s + MIN_CHUNK_SIZE));
+  }
+}
+
+/* Check a tree and its subtrees.  */
+static void do_check_tree(mstate m, tchunkptr t) {
+  tchunkptr head = 0;
+  tchunkptr u = t;
+  bindex_t tindex = t->index;
+  size_t tsize = chunksize(t);
+  bindex_t idx;
+  compute_tree_index(tsize, idx);
+  assert(tindex == idx);
+  assert(tsize >= MIN_LARGE_SIZE);
+  assert(tsize >= minsize_for_tree_index(idx));
+  assert((idx == NTREEBINS-1) || (tsize < minsize_for_tree_index((idx+1))));
+
+  do { /* traverse through chain of same-sized nodes */
+    do_check_any_chunk(m, ((mchunkptr)u));
+    assert(u->index == tindex);
+    assert(chunksize(u) == tsize);
+    assert(!is_inuse(u));
+    assert(!next_pinuse(u));
+    assert(u->fd->bk == u);
+    assert(u->bk->fd == u);
+    if (u->parent == 0) {
+      assert(u->child[0] == 0);
+      assert(u->child[1] == 0);
+    }
+    else {
+      assert(head == 0); /* only one node on chain has parent */
+      head = u;
+      assert(u->parent != u);
+      assert (u->parent->child[0] == u ||
+              u->parent->child[1] == u ||
+              *((tbinptr*)(u->parent)) == u);
+      if (u->child[0] != 0) {
+        assert(u->child[0]->parent == u);
+        assert(u->child[0] != u);
+        do_check_tree(m, u->child[0]);
+      }
+      if (u->child[1] != 0) {
+        assert(u->child[1]->parent == u);
+        assert(u->child[1] != u);
+        do_check_tree(m, u->child[1]);
+      }
+      if (u->child[0] != 0 && u->child[1] != 0) {
+        assert(chunksize(u->child[0]) < chunksize(u->child[1]));
+      }
+    }
+    u = u->fd;
+  } while (u != t);
+  assert(head != 0);
+}
+
+/*  Check all the chunks in a treebin.  */
+static void do_check_treebin(mstate m, bindex_t i) {
+  tbinptr* tb = treebin_at(m, i);
+  tchunkptr t = *tb;
+  int empty = (m->treemap & (1U << i)) == 0;
+  if (t == 0)
+    assert(empty);
+  if (!empty)
+    do_check_tree(m, t);
+}
+
+/*  Check all the chunks in a smallbin.  */
+static void do_check_smallbin(mstate m, bindex_t i) {
+  sbinptr b = smallbin_at(m, i);
+  mchunkptr p = b->bk;
+  unsigned int empty = (m->smallmap & (1U << i)) == 0;
+  if (p == b)
+    assert(empty);
+  if (!empty) {
+    for (; p != b; p = p->bk) {
+      size_t size = chunksize(p);
+      mchunkptr q;
+      /* each chunk claims to be free */
+      do_check_free_chunk(m, p);
+      /* chunk belongs in bin */
+      assert(small_index(size) == i);
+      assert(p->bk == b || chunksize(p->bk) == chunksize(p));
+      /* chunk is followed by an inuse chunk */
+      q = next_chunk(p);
+      if (q->head != FENCEPOST_HEAD)
+        do_check_inuse_chunk(m, q);
+    }
+  }
+}
+
+/* Find x in a bin. Used in other check functions. */
+static int bin_find(mstate m, mchunkptr x) {
+  size_t size = chunksize(x);
+  if (is_small(size)) {
+    bindex_t sidx = small_index(size);
+    sbinptr b = smallbin_at(m, sidx);
+    if (smallmap_is_marked(m, sidx)) {
+      mchunkptr p = b;
+      do {
+        if (p == x)
+          return 1;
+      } while ((p = p->fd) != b);
+    }
+  }
+  else {
+    bindex_t tidx;
+    compute_tree_index(size, tidx);
+    if (treemap_is_marked(m, tidx)) {
+      tchunkptr t = *treebin_at(m, tidx);
+      size_t sizebits = size << leftshift_for_tree_index(tidx);
+      while (t != 0 && chunksize(t) != size) {
+        t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+        sizebits <<= 1;
+      }
+      if (t != 0) {
+        tchunkptr u = t;
+        do {
+          if (u == (tchunkptr)x)
+            return 1;
+        } while ((u = u->fd) != t);
+      }
+    }
+  }
+  return 0;
+}
+
+/* Traverse each chunk and check it; return total */
+static size_t traverse_and_check(mstate m) {
+  size_t sum = 0;
+  if (is_initialized(m)) {
+    msegmentptr s = &m->seg;
+    sum += m->topsize + TOP_FOOT_SIZE;
+    while (s != 0) {
+      mchunkptr q = align_as_chunk(s->base);
+      mchunkptr lastq = 0;
+      assert(pinuse(q));
+      while (segment_holds(s, q) &&
+             q != m->top && q->head != FENCEPOST_HEAD) {
+        sum += chunksize(q);
+        if (is_inuse(q)) {
+          assert(!bin_find(m, q));
+          do_check_inuse_chunk(m, q);
+        }
+        else {
+          assert(q == m->dv || bin_find(m, q));
+          assert(lastq == 0 || is_inuse(lastq)); /* Not 2 consecutive free */
+          do_check_free_chunk(m, q);
+        }
+        lastq = q;
+        q = next_chunk(q);
+      }
+      s = s->next;
+    }
+  }
+  return sum;
+}
+
+
+/* Check all properties of malloc_state. */
+static void do_check_malloc_state(mstate m) {
+  bindex_t i;
+  size_t total;
+  /* check bins */
+  for (i = 0; i < NSMALLBINS; ++i)
+    do_check_smallbin(m, i);
+  for (i = 0; i < NTREEBINS; ++i)
+    do_check_treebin(m, i);
+
+  if (m->dvsize != 0) { /* check dv chunk */
+    do_check_any_chunk(m, m->dv);
+    assert(m->dvsize == chunksize(m->dv));
+    assert(m->dvsize >= MIN_CHUNK_SIZE);
+    assert(bin_find(m, m->dv) == 0);
+  }
+
+  if (m->top != 0) {   /* check top chunk */
+    do_check_top_chunk(m, m->top);
+    /*assert(m->topsize == chunksize(m->top)); redundant */
+    assert(m->topsize > 0);
+    assert(bin_find(m, m->top) == 0);
+  }
+
+  total = traverse_and_check(m);
+  assert(total <= m->footprint);
+  assert(m->footprint <= m->max_footprint);
+}
+#endif /* DEBUG */
+
+/* ----------------------------- statistics ------------------------------ */
+
+#if !NO_MALLINFO
+static struct mallinfo internal_mallinfo(mstate m) {
+  struct mallinfo nm = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
+  ensure_initialization();
+  if (!PREACTION(m)) {
+    check_malloc_state(m);
+    if (is_initialized(m)) {
+      size_t nfree = SIZE_T_ONE; /* top always free */
+      size_t mfree = m->topsize + TOP_FOOT_SIZE;
+      size_t sum = mfree;
+      msegmentptr s = &m->seg;
+      while (s != 0) {
+        mchunkptr q = align_as_chunk(s->base);
+        while (segment_holds(s, q) &&
+               q != m->top && q->head != FENCEPOST_HEAD) {
+          size_t sz = chunksize(q);
+          sum += sz;
+          if (!is_inuse(q)) {
+            mfree += sz;
+            ++nfree;
+          }
+          q = next_chunk(q);
+        }
+        s = s->next;
+      }
+
+      nm.arena    = sum;
+      nm.ordblks  = nfree;
+      nm.hblkhd   = m->footprint - sum;
+      nm.usmblks  = m->max_footprint;
+      nm.uordblks = m->footprint - mfree;
+      nm.fordblks = mfree;
+      nm.keepcost = m->topsize;
+    }
+
+    POSTACTION(m);
+  }
+  return nm;
+}
+#endif /* !NO_MALLINFO */
+
+#if !NO_MALLOC_STATS
+static void internal_malloc_stats(mstate m) {
+  ensure_initialization();
+  if (!PREACTION(m)) {
+    size_t maxfp = 0;
+    size_t fp = 0;
+    size_t used = 0;
+    check_malloc_state(m);
+    if (is_initialized(m)) {
+      msegmentptr s = &m->seg;
+      maxfp = m->max_footprint;
+      fp = m->footprint;
+      used = fp - (m->topsize + TOP_FOOT_SIZE);
+
+      while (s != 0) {
+        mchunkptr q = align_as_chunk(s->base);
+        while (segment_holds(s, q) &&
+               q != m->top && q->head != FENCEPOST_HEAD) {
+          if (!is_inuse(q))
+            used -= chunksize(q);
+          q = next_chunk(q);
+        }
+        s = s->next;
+      }
+    }
+    POSTACTION(m); /* drop lock */
+    fprintf(stderr, "max system bytes = %10lu\n", (unsigned long)(maxfp));
+    fprintf(stderr, "system bytes     = %10lu\n", (unsigned long)(fp));
+    fprintf(stderr, "in use bytes     = %10lu\n", (unsigned long)(used));
+  }
+}
+#endif /* NO_MALLOC_STATS */
+
+/* ----------------------- Operations on smallbins ----------------------- */
+
+/*
+  Various forms of linking and unlinking are defined as macros.  Even
+  the ones for trees, which are very long but have very short typical
+  paths.  This is ugly but reduces reliance on inlining support of
+  compilers.
+*/
+
+/* Link a free chunk into a smallbin  */
+#define insert_small_chunk(M, P, S) {\
+  bindex_t I  = small_index(S);\
+  mchunkptr B = smallbin_at(M, I);\
+  mchunkptr F = B;\
+  assert(S >= MIN_CHUNK_SIZE);\
+  if (!smallmap_is_marked(M, I))\
+    mark_smallmap(M, I);\
+  else if (RTCHECK(ok_address(M, B->fd)))\
+    F = B->fd;\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+  B->fd = P;\
+  F->bk = P;\
+  P->fd = F;\
+  P->bk = B;\
+}
+
+/* Unlink a chunk from a smallbin  */
+#define unlink_small_chunk(M, P, S) {\
+  mchunkptr F = P->fd;\
+  mchunkptr B = P->bk;\
+  bindex_t I = small_index(S);\
+  assert(P != B);\
+  assert(P != F);\
+  assert(chunksize(P) == small_index2size(I));\
+  if (RTCHECK(F == smallbin_at(M,I) || (ok_address(M, F) && F->bk == P))) { \
+    if (B == F) {\
+      clear_smallmap(M, I);\
+    }\
+    else if (RTCHECK(B == smallbin_at(M,I) ||\
+                     (ok_address(M, B) && B->fd == P))) {\
+      F->bk = B;\
+      B->fd = F;\
+    }\
+    else {\
+      CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+}
+
+/* Unlink the first chunk from a smallbin */
+#define unlink_first_small_chunk(M, B, P, I) {\
+  mchunkptr F = P->fd;\
+  assert(P != B);\
+  assert(P != F);\
+  assert(chunksize(P) == small_index2size(I));\
+  if (B == F) {\
+    clear_smallmap(M, I);\
+  }\
+  else if (RTCHECK(ok_address(M, F) && F->bk == P)) {\
+    F->bk = B;\
+    B->fd = F;\
+  }\
+  else {\
+    CORRUPTION_ERROR_ACTION(M);\
+  }\
+}
+
+/* Replace dv node, binning the old one */
+/* Used only when dvsize known to be small */
+#define replace_dv(M, P, S) {\
+  size_t DVS = M->dvsize;\
+  assert(is_small(DVS));\
+  if (DVS != 0) {\
+    mchunkptr DV = M->dv;\
+    insert_small_chunk(M, DV, DVS);\
+  }\
+  M->dvsize = S;\
+  M->dv = P;\
+}
+
+/* ------------------------- Operations on trees ------------------------- */
+
+/* Insert chunk into tree */
+#define insert_large_chunk(M, X, S) {\
+  tbinptr* H;\
+  bindex_t I;\
+  compute_tree_index(S, I);\
+  H = treebin_at(M, I);\
+  X->index = I;\
+  X->child[0] = X->child[1] = 0;\
+  if (!treemap_is_marked(M, I)) {\
+    mark_treemap(M, I);\
+    *H = X;\
+    X->parent = (tchunkptr)H;\
+    X->fd = X->bk = X;\
+  }\
+  else {\
+    tchunkptr T = *H;\
+    size_t K = S << leftshift_for_tree_index(I);\
+    for (;;) {\
+      if (chunksize(T) != S) {\
+        tchunkptr* C = &(T->child[(K >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1]);\
+        K <<= 1;\
+        if (*C != 0)\
+          T = *C;\
+        else if (RTCHECK(ok_address(M, C))) {\
+          *C = X;\
+          X->parent = T;\
+          X->fd = X->bk = X;\
+          break;\
+        }\
+        else {\
+          CORRUPTION_ERROR_ACTION(M);\
+          break;\
+        }\
+      }\
+      else {\
+        tchunkptr F = T->fd;\
+        if (RTCHECK(ok_address(M, T) && ok_address(M, F))) {\
+          T->fd = F->bk = X;\
+          X->fd = F;\
+          X->bk = T;\
+          X->parent = 0;\
+          break;\
+        }\
+        else {\
+          CORRUPTION_ERROR_ACTION(M);\
+          break;\
+        }\
+      }\
+    }\
+  }\
+}
+
+/*
+  Unlink steps:
+
+  1. If x is a chained node, unlink it from its same-sized fd/bk links
+     and choose its bk node as its replacement.
+  2. If x was the last node of its size, but not a leaf node, it must
+     be replaced with a leaf node (not merely one with an open left or
+     right), to make sure that lefts and rights of descendents
+     correspond properly to bit masks.  We use the rightmost descendent
+     of x.  We could use any other leaf, but this is easy to locate and
+     tends to counteract removal of leftmosts elsewhere, and so keeps
+     paths shorter than minimally guaranteed.  This doesn't loop much
+     because on average a node in a tree is near the bottom.
+  3. If x is the base of a chain (i.e., has parent links) relink
+     x's parent and children to x's replacement (or null if none).
+*/
+
+#define unlink_large_chunk(M, X) {\
+  tchunkptr XP = X->parent;\
+  tchunkptr R;\
+  if (X->bk != X) {\
+    tchunkptr F = X->fd;\
+    R = X->bk;\
+    if (RTCHECK(ok_address(M, F) && F->bk == X && R->fd == X)) {\
+      F->bk = R;\
+      R->fd = F;\
+    }\
+    else {\
+      CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+  else {\
+    tchunkptr* RP;\
+    if (((R = *(RP = &(X->child[1]))) != 0) ||\
+        ((R = *(RP = &(X->child[0]))) != 0)) {\
+      tchunkptr* CP;\
+      while ((*(CP = &(R->child[1])) != 0) ||\
+             (*(CP = &(R->child[0])) != 0)) {\
+        R = *(RP = CP);\
+      }\
+      if (RTCHECK(ok_address(M, RP)))\
+        *RP = 0;\
+      else {\
+        CORRUPTION_ERROR_ACTION(M);\
+      }\
+    }\
+  }\
+  if (XP != 0) {\
+    tbinptr* H = treebin_at(M, X->index);\
+    if (X == *H) {\
+      if ((*H = R) == 0) \
+        clear_treemap(M, X->index);\
+    }\
+    else if (RTCHECK(ok_address(M, XP))) {\
+      if (XP->child[0] == X) \
+        XP->child[0] = R;\
+      else \
+        XP->child[1] = R;\
+    }\
+    else\
+      CORRUPTION_ERROR_ACTION(M);\
+    if (R != 0) {\
+      if (RTCHECK(ok_address(M, R))) {\
+        tchunkptr C0, C1;\
+        R->parent = XP;\
+        if ((C0 = X->child[0]) != 0) {\
+          if (RTCHECK(ok_address(M, C0))) {\
+            R->child[0] = C0;\
+            C0->parent = R;\
+          }\
+          else\
+            CORRUPTION_ERROR_ACTION(M);\
+        }\
+        if ((C1 = X->child[1]) != 0) {\
+          if (RTCHECK(ok_address(M, C1))) {\
+            R->child[1] = C1;\
+            C1->parent = R;\
+          }\
+          else\
+            CORRUPTION_ERROR_ACTION(M);\
+        }\
+      }\
+      else\
+        CORRUPTION_ERROR_ACTION(M);\
+    }\
+  }\
+}
+
+/* Relays to large vs small bin operations */
+
+#define insert_chunk(M, P, S)\
+  if (is_small(S)) insert_small_chunk(M, P, S)\
+  else { tchunkptr TP = (tchunkptr)(P); insert_large_chunk(M, TP, S); }
+
+#define unlink_chunk(M, P, S)\
+  if (is_small(S)) unlink_small_chunk(M, P, S)\
+  else { tchunkptr TP = (tchunkptr)(P); unlink_large_chunk(M, TP); }
+
+
+/* Relays to internal calls to malloc/free from realloc, memalign etc */
+
+#if ONLY_MSPACES
+#define internal_malloc(m, b) mspace_malloc(m, b)
+#define internal_free(m, mem) mspace_free(m,mem);
+#else /* ONLY_MSPACES */
+#if MSPACES
+#define internal_malloc(m, b)\
+  ((m == gm)? dlmalloc(b) : mspace_malloc(m, b))
+#define internal_free(m, mem)\
+   if (m == gm) dlfree(mem); else mspace_free(m,mem);
+#else /* MSPACES */
+#define internal_malloc(m, b) dlmalloc(b)
+#define internal_free(m, mem) dlfree(mem)
+#endif /* MSPACES */
+#endif /* ONLY_MSPACES */
+
+/* -----------------------  Direct-mmapping chunks ----------------------- */
+
+/*
+  Directly mmapped chunks are set up with an offset to the start of
+  the mmapped region stored in the prev_foot field of the chunk. This
+  allows reconstruction of the required argument to MUNMAP when freed,
+  and also allows adjustment of the returned chunk to meet alignment
+  requirements (especially in memalign).
+*/
+
+/* Malloc using mmap */
+static void* mmap_alloc(mstate m, size_t nb) {
+  size_t mmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+  if (m->footprint_limit != 0) {
+    size_t fp = m->footprint + mmsize;
+    if (fp <= m->footprint || fp > m->footprint_limit)
+      return 0;
+  }
+  if (mmsize > nb) {     /* Check for wrap around 0 */
+    char* mm = (char*)(CALL_DIRECT_MMAP(mmsize));
+    if (mm != CMFAIL) {
+      size_t offset = align_offset(chunk2mem(mm));
+      size_t psize = mmsize - offset - MMAP_FOOT_PAD;
+      mchunkptr p = (mchunkptr)(mm + offset);
+      p->prev_foot = offset;
+      p->head = psize;
+      mark_inuse_foot(m, p, psize);
+      chunk_plus_offset(p, psize)->head = FENCEPOST_HEAD;
+      chunk_plus_offset(p, psize+SIZE_T_SIZE)->head = 0;
+
+      if (m->least_addr == 0 || mm < m->least_addr)
+        m->least_addr = mm;
+      if ((m->footprint += mmsize) > m->max_footprint)
+        m->max_footprint = m->footprint;
+      assert(is_aligned(chunk2mem(p)));
+      check_mmapped_chunk(m, p);
+      return chunk2mem(p);
+    }
+  }
+  return 0;
+}
+
+/* Realloc using mmap */
+static mchunkptr mmap_resize(mstate m, mchunkptr oldp, size_t nb, int flags) {
+  size_t oldsize = chunksize(oldp);
+  (void)flags; /* placate people compiling -Wunused */
+  if (is_small(nb)) /* Can't shrink mmap regions below small size */
+    return 0;
+  /* Keep old chunk if big enough but not too big */
+  if (oldsize >= nb + SIZE_T_SIZE &&
+      (oldsize - nb) <= (mparams.granularity << 1))
+    return oldp;
+  else {
+    size_t offset = oldp->prev_foot;
+    size_t oldmmsize = oldsize + offset + MMAP_FOOT_PAD;
+    size_t newmmsize = mmap_align(nb + SIX_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+    char* cp = (char*)CALL_MREMAP((char*)oldp - offset,
+                                  oldmmsize, newmmsize, flags);
+    if (cp != CMFAIL) {
+      mchunkptr newp = (mchunkptr)(cp + offset);
+      size_t psize = newmmsize - offset - MMAP_FOOT_PAD;
+      newp->head = psize;
+      mark_inuse_foot(m, newp, psize);
+      chunk_plus_offset(newp, psize)->head = FENCEPOST_HEAD;
+      chunk_plus_offset(newp, psize+SIZE_T_SIZE)->head = 0;
+
+      if (cp < m->least_addr)
+        m->least_addr = cp;
+      if ((m->footprint += newmmsize - oldmmsize) > m->max_footprint)
+        m->max_footprint = m->footprint;
+      check_mmapped_chunk(m, newp);
+      return newp;
+    }
+  }
+  return 0;
+}
+
+
+/* -------------------------- mspace management -------------------------- */
+
+/* Initialize top chunk and its size */
+static void init_top(mstate m, mchunkptr p, size_t psize) {
+  /* Ensure alignment */
+  size_t offset = align_offset(chunk2mem(p));
+  p = (mchunkptr)((char*)p + offset);
+  psize -= offset;
+
+  m->top = p;
+  m->topsize = psize;
+  p->head = psize | PINUSE_BIT;
+  /* set size of fake trailing chunk holding overhead space only once */
+  chunk_plus_offset(p, psize)->head = TOP_FOOT_SIZE;
+  m->trim_check = mparams.trim_threshold; /* reset on each update */
+}
+
+/* Initialize bins for a new mstate that is otherwise zeroed out */
+static void init_bins(mstate m) {
+  /* Establish circular links for smallbins */
+  bindex_t i;
+  for (i = 0; i < NSMALLBINS; ++i) {
+    sbinptr bin = smallbin_at(m,i);
+    bin->fd = bin->bk = bin;
+  }
+}
+
+#if PROCEED_ON_ERROR
+
+/* default corruption action */
+static void reset_on_error(mstate m) {
+  int i;
+  ++malloc_corruption_error_count;
+  /* Reinitialize fields to forget about all memory */
+  m->smallmap = m->treemap = 0;
+  m->dvsize = m->topsize = 0;
+  m->seg.base = 0;
+  m->seg.size = 0;
+  m->seg.next = 0;
+  m->top = m->dv = 0;
+  for (i = 0; i < NTREEBINS; ++i)
+    *treebin_at(m, i) = 0;
+  init_bins(m);
+}
+#endif /* PROCEED_ON_ERROR */
+
+/* Allocate chunk and prepend remainder with chunk in successor base. */
+static void* prepend_alloc(mstate m, char* newbase, char* oldbase,
+                           size_t nb) {
+  mchunkptr p = align_as_chunk(newbase);
+  mchunkptr oldfirst = align_as_chunk(oldbase);
+  size_t psize = (char*)oldfirst - (char*)p;
+  mchunkptr q = chunk_plus_offset(p, nb);
+  size_t qsize = psize - nb;
+  set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+
+  assert((char*)oldfirst > (char*)q);
+  assert(pinuse(oldfirst));
+  assert(qsize >= MIN_CHUNK_SIZE);
+
+  /* consolidate remainder with first chunk of old base */
+  if (oldfirst == m->top) {
+    size_t tsize = m->topsize += qsize;
+    m->top = q;
+    q->head = tsize | PINUSE_BIT;
+    check_top_chunk(m, q);
+  }
+  else if (oldfirst == m->dv) {
+    size_t dsize = m->dvsize += qsize;
+    m->dv = q;
+    set_size_and_pinuse_of_free_chunk(q, dsize);
+  }
+  else {
+    if (!is_inuse(oldfirst)) {
+      size_t nsize = chunksize(oldfirst);
+      unlink_chunk(m, oldfirst, nsize);
+      oldfirst = chunk_plus_offset(oldfirst, nsize);
+      qsize += nsize;
+    }
+    set_free_with_pinuse(q, qsize, oldfirst);
+    insert_chunk(m, q, qsize);
+    check_free_chunk(m, q);
+  }
+
+  check_malloced_chunk(m, chunk2mem(p), nb);
+  return chunk2mem(p);
+}
+
+/* Add a segment to hold a new noncontiguous region */
+static void add_segment(mstate m, char* tbase, size_t tsize, flag_t mmapped) {
+  /* Determine locations and sizes of segment, fenceposts, old top */
+  char* old_top = (char*)m->top;
+  msegmentptr oldsp = segment_holding(m, old_top);
+  char* old_end = oldsp->base + oldsp->size;
+  size_t ssize = pad_request(sizeof(struct malloc_segment));
+  char* rawsp = old_end - (ssize + FOUR_SIZE_T_SIZES + CHUNK_ALIGN_MASK);
+  size_t offset = align_offset(chunk2mem(rawsp));
+  char* asp = rawsp + offset;
+  char* csp = (asp < (old_top + MIN_CHUNK_SIZE))? old_top : asp;
+  mchunkptr sp = (mchunkptr)csp;
+  msegmentptr ss = (msegmentptr)(chunk2mem(sp));
+  mchunkptr tnext = chunk_plus_offset(sp, ssize);
+  mchunkptr p = tnext;
+  int nfences = 0;
+
+  /* reset top to new space */
+  init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+
+  /* Set up segment record */
+  assert(is_aligned(ss));
+  set_size_and_pinuse_of_inuse_chunk(m, sp, ssize);
+  *ss = m->seg; /* Push current record */
+  m->seg.base = tbase;
+  m->seg.size = tsize;
+  m->seg.sflags = mmapped;
+  m->seg.next = ss;
+
+  /* Insert trailing fenceposts */
+  for (;;) {
+    mchunkptr nextp = chunk_plus_offset(p, SIZE_T_SIZE);
+    p->head = FENCEPOST_HEAD;
+    ++nfences;
+    if ((char*)(&(nextp->head)) < old_end)
+      p = nextp;
+    else
+      break;
+  }
+  assert(nfences >= 2);
+
+  /* Insert the rest of old top into a bin as an ordinary free chunk */
+  if (csp != old_top) {
+    mchunkptr q = (mchunkptr)old_top;
+    size_t psize = csp - old_top;
+    mchunkptr tn = chunk_plus_offset(q, psize);
+    set_free_with_pinuse(q, psize, tn);
+    insert_chunk(m, q, psize);
+  }
+
+  check_top_chunk(m, m->top);
+}
+
+/* -------------------------- System allocation -------------------------- */
+
+/* Get memory from system using MORECORE or MMAP */
+static void* sys_alloc(mstate m, size_t nb) {
+  char* tbase = CMFAIL;
+  size_t tsize = 0;
+  flag_t mmap_flag = 0;
+  size_t asize; /* allocation size */
+
+  ensure_initialization();
+
+  if (use_noexpand(m))
+      return 0;
+
+  /* Directly map large chunks, but only if already initialized */
+  if (use_mmap(m) && nb >= mparams.mmap_threshold && m->topsize != 0) {
+    void* mem = mmap_alloc(m, nb);
+    if (mem != 0)
+      return mem;
+  }
+
+  asize = granularity_align(nb + SYS_ALLOC_PADDING);
+  if (asize <= nb)
+    return 0; /* wraparound */
+  if (m->footprint_limit != 0) {
+    size_t fp = m->footprint + asize;
+    if (fp <= m->footprint || fp > m->footprint_limit)
+      return 0;
+  }
+
+  /*
+    Try getting memory in any of three ways (in most-preferred to
+    least-preferred order):
+    1. A call to MORECORE that can normally contiguously extend memory.
+       (disabled if not MORECORE_CONTIGUOUS or not HAVE_MORECORE or
+       or main space is mmapped or a previous contiguous call failed)
+    2. A call to MMAP new space (disabled if not HAVE_MMAP).
+       Note that under the default settings, if MORECORE is unable to
+       fulfill a request, and HAVE_MMAP is true, then mmap is
+       used as a noncontiguous system allocator. This is a useful backup
+       strategy for systems with holes in address spaces -- in this case
+       sbrk cannot contiguously expand the heap, but mmap may be able to
+       find space.
+    3. A call to MORECORE that cannot usually contiguously extend memory.
+       (disabled if not HAVE_MORECORE)
+
+   In all cases, we need to request enough bytes from system to ensure
+   we can malloc nb bytes upon success, so pad with enough space for
+   top_foot, plus alignment-pad to make sure we don't lose bytes if
+   not on boundary, and round this up to a granularity unit.
+  */
+
+  if (MORECORE_CONTIGUOUS && !use_noncontiguous(m)) {
+    char* br = CMFAIL;
+    size_t ssize = asize; /* sbrk call size */
+    msegmentptr ss = (m->top == 0)? 0 : segment_holding(m, (char*)m->top);
+    ACQUIRE_MALLOC_GLOBAL_LOCK();
+
+    if (ss == 0) {  /* First time through or recovery */
+      char* base = (char*)CALL_MORECORE(0);
+      if (base != CMFAIL) {
+        size_t fp;
+        /* Adjust to end on a page boundary */
+        if (!is_page_aligned(base))
+          ssize += (page_align((size_t)base) - (size_t)base);
+        fp = m->footprint + ssize; /* recheck limits */
+        if (ssize > nb && ssize < HALF_MAX_SIZE_T &&
+            (m->footprint_limit == 0 ||
+             (fp > m->footprint && fp <= m->footprint_limit)) &&
+            (br = (char*)(CALL_MORECORE(ssize))) == base) {
+          tbase = base;
+          tsize = ssize;
+        }
+      }
+    }
+    else {
+      /* Subtract out existing available top space from MORECORE request. */
+      ssize = granularity_align(nb - m->topsize + SYS_ALLOC_PADDING);
+      /* Use mem here only if it did continuously extend old space */
+      if (ssize < HALF_MAX_SIZE_T &&
+          (br = (char*)(CALL_MORECORE(ssize))) == ss->base+ss->size) {
+        tbase = br;
+        tsize = ssize;
+      }
+    }
+
+    if (tbase == CMFAIL) {    /* Cope with partial failure */
+      if (br != CMFAIL) {    /* Try to use/extend the space we did get */
+        if (ssize < HALF_MAX_SIZE_T &&
+            ssize < nb + SYS_ALLOC_PADDING) {
+          size_t esize = granularity_align(nb + SYS_ALLOC_PADDING - ssize);
+          if (esize < HALF_MAX_SIZE_T) {
+            char* end = (char*)CALL_MORECORE(esize);
+            if (end != CMFAIL)
+              ssize += esize;
+            else {            /* Can't use; try to release */
+              (void) CALL_MORECORE(-ssize);
+              br = CMFAIL;
+            }
+          }
+        }
+      }
+      if (br != CMFAIL) {    /* Use the space we did get */
+        tbase = br;
+        tsize = ssize;
+      }
+      else
+        disable_contiguous(m); /* Don't try contiguous path in the future */
+    }
+
+    RELEASE_MALLOC_GLOBAL_LOCK();
+  }
+
+  if (HAVE_MMAP && tbase == CMFAIL) {  /* Try MMAP */
+    char* mp = (char*)(CALL_MMAP(asize));
+    if (mp != CMFAIL) {
+      tbase = mp;
+      tsize = asize;
+      mmap_flag = USE_MMAP_BIT;
+    }
+  }
+
+  if (HAVE_MORECORE && tbase == CMFAIL) { /* Try noncontiguous MORECORE */
+    if (asize < HALF_MAX_SIZE_T) {
+      char* br = CMFAIL;
+      char* end = CMFAIL;
+      ACQUIRE_MALLOC_GLOBAL_LOCK();
+      br = (char*)(CALL_MORECORE(asize));
+      end = (char*)(CALL_MORECORE(0));
+      RELEASE_MALLOC_GLOBAL_LOCK();
+      if (br != CMFAIL && end != CMFAIL && br < end) {
+        size_t ssize = end - br;
+        if (ssize > nb + TOP_FOOT_SIZE) {
+          tbase = br;
+          tsize = ssize;
+        }
+      }
+    }
+  }
+
+  if (tbase != CMFAIL) {
+
+    if ((m->footprint += tsize) > m->max_footprint)
+      m->max_footprint = m->footprint;
+
+    if (!is_initialized(m)) { /* first-time initialization */
+      if (m->least_addr == 0 || tbase < m->least_addr)
+        m->least_addr = tbase;
+      m->seg.base = tbase;
+      m->seg.size = tsize;
+      m->seg.sflags = mmap_flag;
+      m->magic = mparams.magic;
+      m->release_checks = MAX_RELEASE_CHECK_RATE;
+      init_bins(m);
+#if !ONLY_MSPACES
+      if (is_global(m))
+        init_top(m, (mchunkptr)tbase, tsize - TOP_FOOT_SIZE);
+      else
+#endif
+      {
+        /* Offset top by embedded malloc_state */
+        mchunkptr mn = next_chunk(mem2chunk(m));
+        init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) -TOP_FOOT_SIZE);
+      }
+    }
+
+    else {
+      /* Try to merge with an existing segment */
+      msegmentptr sp = &m->seg;
+      /* Only consider most recent segment if traversal suppressed */
+      while (sp != 0 && tbase != sp->base + sp->size)
+        sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+      if (sp != 0 &&
+          !is_extern_segment(sp) &&
+          (sp->sflags & USE_MMAP_BIT) == mmap_flag &&
+          segment_holds(sp, m->top)) { /* append */
+        sp->size += tsize;
+        init_top(m, m->top, m->topsize + tsize);
+      }
+      else {
+        if (tbase < m->least_addr)
+          m->least_addr = tbase;
+        sp = &m->seg;
+        while (sp != 0 && sp->base != tbase + tsize)
+          sp = (NO_SEGMENT_TRAVERSAL) ? 0 : sp->next;
+        if (sp != 0 &&
+            !is_extern_segment(sp) &&
+            (sp->sflags & USE_MMAP_BIT) == mmap_flag) {
+          char* oldbase = sp->base;
+          sp->base = tbase;
+          sp->size += tsize;
+          return prepend_alloc(m, tbase, oldbase, nb);
+        }
+        else
+          add_segment(m, tbase, tsize, mmap_flag);
+      }
+    }
+
+    if (nb < m->topsize) { /* Allocate from new or extended top space */
+      size_t rsize = m->topsize -= nb;
+      mchunkptr p = m->top;
+      mchunkptr r = m->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(m, p, nb);
+      check_top_chunk(m, m->top);
+      check_malloced_chunk(m, chunk2mem(p), nb);
+      return chunk2mem(p);
+    }
+  }
+
+  MALLOC_FAILURE_ACTION;
+  return 0;
+}
+
+/* -----------------------  system deallocation -------------------------- */
+
+/* Unmap and unlink any mmapped segments that don't contain used chunks */
+static size_t release_unused_segments(mstate m) {
+  size_t released = 0;
+  int nsegs = 0;
+  msegmentptr pred = &m->seg;
+  msegmentptr sp = pred->next;
+  while (sp != 0) {
+    char* base = sp->base;
+    size_t size = sp->size;
+    msegmentptr next = sp->next;
+    ++nsegs;
+    if (is_mmapped_segment(sp) && !is_extern_segment(sp)) {
+      mchunkptr p = align_as_chunk(base);
+      size_t psize = chunksize(p);
+      /* Can unmap if first chunk holds entire segment and not pinned */
+      if (!is_inuse(p) && (char*)p + psize >= base + size - TOP_FOOT_SIZE) {
+        tchunkptr tp = (tchunkptr)p;
+        assert(segment_holds(sp, (char*)sp));
+        if (p == m->dv) {
+          m->dv = 0;
+          m->dvsize = 0;
+        }
+        else {
+          unlink_large_chunk(m, tp);
+        }
+        if (CALL_MUNMAP(base, size) == 0) {
+          released += size;
+          m->footprint -= size;
+          /* unlink obsoleted record */
+          sp = pred;
+          sp->next = next;
+        }
+        else { /* back out if cannot unmap */
+          insert_large_chunk(m, tp, psize);
+        }
+      }
+    }
+    if (NO_SEGMENT_TRAVERSAL) /* scan only first segment */
+      break;
+    pred = sp;
+    sp = next;
+  }
+  /* Reset check counter */
+  m->release_checks = (((size_t) nsegs > (size_t) MAX_RELEASE_CHECK_RATE)?
+                       (size_t) nsegs : (size_t) MAX_RELEASE_CHECK_RATE);
+  return released;
+}
+
+static int sys_trim(mstate m, size_t pad) {
+  size_t released = 0;
+  ensure_initialization();
+  if (pad < MAX_REQUEST && is_initialized(m)) {
+    pad += TOP_FOOT_SIZE; /* ensure enough room for segment overhead */
+
+    if (m->topsize > pad) {
+      /* Shrink top space in granularity-size units, keeping at least one */
+      size_t unit = mparams.granularity;
+      size_t extra = ((m->topsize - pad + (unit - SIZE_T_ONE)) / unit -
+                      SIZE_T_ONE) * unit;
+      msegmentptr sp = segment_holding(m, (char*)m->top);
+
+      if (!is_extern_segment(sp)) {
+        if (is_mmapped_segment(sp)) {
+          if (HAVE_MMAP &&
+              sp->size >= extra &&
+              !has_segment_link(m, sp)) { /* can't shrink if pinned */
+            size_t newsize = sp->size - extra;
+            (void)newsize; /* placate people compiling -Wunused-variable */
+            /* Prefer mremap, fall back to munmap */
+            if ((CALL_MREMAP(sp->base, sp->size, newsize, 0) != MFAIL) ||
+                (CALL_MUNMAP(sp->base + newsize, extra) == 0)) {
+              released = extra;
+            }
+          }
+        }
+        else if (HAVE_MORECORE) {
+          if (extra >= HALF_MAX_SIZE_T) /* Avoid wrapping negative */
+            extra = (HALF_MAX_SIZE_T) + SIZE_T_ONE - unit;
+          ACQUIRE_MALLOC_GLOBAL_LOCK();
+          {
+            /* Make sure end of memory is where we last set it. */
+            char* old_br = (char*)(CALL_MORECORE(0));
+            if (old_br == sp->base + sp->size) {
+              char* rel_br = (char*)(CALL_MORECORE(-extra));
+              char* new_br = (char*)(CALL_MORECORE(0));
+              if (rel_br != CMFAIL && new_br < old_br)
+                released = old_br - new_br;
+            }
+          }
+          RELEASE_MALLOC_GLOBAL_LOCK();
+        }
+      }
+
+      if (released != 0) {
+        sp->size -= released;
+        m->footprint -= released;
+        init_top(m, m->top, m->topsize - released);
+        check_top_chunk(m, m->top);
+      }
+    }
+
+    /* Unmap any unused mmapped segments */
+    if (HAVE_MMAP)
+      released += release_unused_segments(m);
+
+    /* On failure, disable autotrim to avoid repeated failed future calls */
+    if (released == 0 && m->topsize > m->trim_check)
+      m->trim_check = MAX_SIZE_T;
+  }
+
+  return (released != 0)? 1 : 0;
+}
+
+/* Consolidate and bin a chunk. Differs from exported versions
+   of free mainly in that the chunk need not be marked as inuse.
+*/
+static void dispose_chunk(mstate m, mchunkptr p, size_t psize) {
+  mchunkptr next = chunk_plus_offset(p, psize);
+  if (!pinuse(p)) {
+    mchunkptr prev;
+    size_t prevsize = p->prev_foot;
+    if (is_mmapped(p)) {
+      psize += prevsize + MMAP_FOOT_PAD;
+      if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+        m->footprint -= psize;
+      return;
+    }
+    prev = chunk_minus_offset(p, prevsize);
+    psize += prevsize;
+    p = prev;
+    if (RTCHECK(ok_address(m, prev))) { /* consolidate backward */
+      if (p != m->dv) {
+        unlink_chunk(m, p, prevsize);
+      }
+      else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+        m->dvsize = psize;
+        set_free_with_pinuse(p, psize, next);
+        return;
+      }
+    }
+    else {
+      CORRUPTION_ERROR_ACTION(m);
+      return;
+    }
+  }
+  if (RTCHECK(ok_address(m, next))) {
+    if (!cinuse(next)) {  /* consolidate forward */
+      if (next == m->top) {
+        size_t tsize = m->topsize += psize;
+        m->top = p;
+        p->head = tsize | PINUSE_BIT;
+        if (p == m->dv) {
+          m->dv = 0;
+          m->dvsize = 0;
+        }
+        return;
+      }
+      else if (next == m->dv) {
+        size_t dsize = m->dvsize += psize;
+        m->dv = p;
+        set_size_and_pinuse_of_free_chunk(p, dsize);
+        return;
+      }
+      else {
+        size_t nsize = chunksize(next);
+        psize += nsize;
+        unlink_chunk(m, next, nsize);
+        set_size_and_pinuse_of_free_chunk(p, psize);
+        if (p == m->dv) {
+          m->dvsize = psize;
+          return;
+        }
+      }
+    }
+    else {
+      set_free_with_pinuse(p, psize, next);
+    }
+    insert_chunk(m, p, psize);
+  }
+  else {
+    CORRUPTION_ERROR_ACTION(m);
+  }
+}
+
+/* ---------------------------- malloc --------------------------- */
+
+/* allocate a large request from the best fitting chunk in a treebin */
+static void* tmalloc_large(mstate m, size_t nb) {
+  tchunkptr v = 0;
+  size_t rsize = -nb; /* Unsigned negation */
+  tchunkptr t;
+  bindex_t idx;
+  compute_tree_index(nb, idx);
+  if ((t = *treebin_at(m, idx)) != 0) {
+    /* Traverse tree for this bin looking for node with size == nb */
+    size_t sizebits = nb << leftshift_for_tree_index(idx);
+    tchunkptr rst = 0;  /* The deepest untaken right subtree */
+    for (;;) {
+      tchunkptr rt;
+      size_t trem = chunksize(t) - nb;
+      if (trem < rsize) {
+        v = t;
+        if ((rsize = trem) == 0)
+          break;
+      }
+      rt = t->child[1];
+      t = t->child[(sizebits >> (SIZE_T_BITSIZE-SIZE_T_ONE)) & 1];
+      if (rt != 0 && rt != t)
+        rst = rt;
+      if (t == 0) {
+        t = rst; /* set t to least subtree holding sizes > nb */
+        break;
+      }
+      sizebits <<= 1;
+    }
+  }
+  if (t == 0 && v == 0) { /* set t to root of next non-empty treebin */
+    binmap_t leftbits = left_bits(idx2bit(idx)) & m->treemap;
+    if (leftbits != 0) {
+      bindex_t i;
+      binmap_t leastbit = least_bit(leftbits);
+      compute_bit2idx(leastbit, i);
+      t = *treebin_at(m, i);
+    }
+  }
+
+  while (t != 0) { /* find smallest of tree or subtree */
+    size_t trem = chunksize(t) - nb;
+    if (trem < rsize) {
+      rsize = trem;
+      v = t;
+    }
+    t = leftmost_child(t);
+  }
+
+  /*  If dv is a better fit, return 0 so malloc will use it */
+  if (v != 0 && rsize < (size_t)(m->dvsize - nb)) {
+    if (RTCHECK(ok_address(m, v))) { /* split */
+      mchunkptr r = chunk_plus_offset(v, nb);
+      assert(chunksize(v) == rsize + nb);
+      if (RTCHECK(ok_next(v, r))) {
+        unlink_large_chunk(m, v);
+        if (rsize < MIN_CHUNK_SIZE)
+          set_inuse_and_pinuse(m, v, (rsize + nb));
+        else {
+          set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+          set_size_and_pinuse_of_free_chunk(r, rsize);
+          insert_chunk(m, r, rsize);
+        }
+        return chunk2mem(v);
+      }
+    }
+    CORRUPTION_ERROR_ACTION(m);
+  }
+  return 0;
+}
+
+/* allocate a small request from the best fitting chunk in a treebin */
+static void* tmalloc_small(mstate m, size_t nb) {
+  tchunkptr t, v;
+  size_t rsize;
+  bindex_t i;
+  binmap_t leastbit = least_bit(m->treemap);
+  compute_bit2idx(leastbit, i);
+  v = t = *treebin_at(m, i);
+  rsize = chunksize(t) - nb;
+
+  while ((t = leftmost_child(t)) != 0) {
+    size_t trem = chunksize(t) - nb;
+    if (trem < rsize) {
+      rsize = trem;
+      v = t;
+    }
+  }
+
+  if (RTCHECK(ok_address(m, v))) {
+    mchunkptr r = chunk_plus_offset(v, nb);
+    assert(chunksize(v) == rsize + nb);
+    if (RTCHECK(ok_next(v, r))) {
+      unlink_large_chunk(m, v);
+      if (rsize < MIN_CHUNK_SIZE)
+        set_inuse_and_pinuse(m, v, (rsize + nb));
+      else {
+        set_size_and_pinuse_of_inuse_chunk(m, v, nb);
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        replace_dv(m, r, rsize);
+      }
+      return chunk2mem(v);
+    }
+  }
+
+  CORRUPTION_ERROR_ACTION(m);
+  return 0;
+}
+
+#if !ONLY_MSPACES
+
+void* dlmalloc(size_t bytes) {
+  /*
+     Basic algorithm:
+     If a small request (< 256 bytes minus per-chunk overhead):
+       1. If one exists, use a remainderless chunk in associated smallbin.
+          (Remainderless means that there are too few excess bytes to
+          represent as a chunk.)
+       2. If it is big enough, use the dv chunk, which is normally the
+          chunk adjacent to the one used for the most recent small request.
+       3. If one exists, split the smallest available chunk in a bin,
+          saving remainder in dv.
+       4. If it is big enough, use the top chunk.
+       5. If available, get memory from system and use it
+     Otherwise, for a large request:
+       1. Find the smallest available binned chunk that fits, and use it
+          if it is better fitting than dv chunk, splitting if necessary.
+       2. If better fitting than any binned chunk, use the dv chunk.
+       3. If it is big enough, use the top chunk.
+       4. If request size >= mmap threshold, try to directly mmap this chunk.
+       5. If available, get memory from system and use it
+
+     The ugly goto's here ensure that postaction occurs along all paths.
+  */
+
+#if USE_LOCKS
+  ensure_initialization(); /* initialize in sys_alloc if not using locks */
+#endif
+
+  if (!PREACTION(gm)) {
+    void* mem;
+    size_t nb;
+    if (bytes <= MAX_SMALL_REQUEST) {
+      bindex_t idx;
+      binmap_t smallbits;
+      nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+      idx = small_index(nb);
+      smallbits = gm->smallmap >> idx;
+
+      if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+        mchunkptr b, p;
+        idx += ~smallbits & 1;       /* Uses next bin if idx empty */
+        b = smallbin_at(gm, idx);
+        p = b->fd;
+        assert(chunksize(p) == small_index2size(idx));
+        unlink_first_small_chunk(gm, b, p, idx);
+        set_inuse_and_pinuse(gm, p, small_index2size(idx));
+        mem = chunk2mem(p);
+        check_malloced_chunk(gm, mem, nb);
+        goto postaction;
+      }
+
+      else if (nb > gm->dvsize) {
+        if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+          mchunkptr b, p, r;
+          size_t rsize;
+          bindex_t i;
+          binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+          binmap_t leastbit = least_bit(leftbits);
+          compute_bit2idx(leastbit, i);
+          b = smallbin_at(gm, i);
+          p = b->fd;
+          assert(chunksize(p) == small_index2size(i));
+          unlink_first_small_chunk(gm, b, p, i);
+          rsize = small_index2size(i) - nb;
+          /* Fit here cannot be remainderless if 4byte sizes */
+          if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+            set_inuse_and_pinuse(gm, p, small_index2size(i));
+          else {
+            set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+            r = chunk_plus_offset(p, nb);
+            set_size_and_pinuse_of_free_chunk(r, rsize);
+            replace_dv(gm, r, rsize);
+          }
+          mem = chunk2mem(p);
+          check_malloced_chunk(gm, mem, nb);
+          goto postaction;
+        }
+
+        else if (gm->treemap != 0 && (mem = tmalloc_small(gm, nb)) != 0) {
+          check_malloced_chunk(gm, mem, nb);
+          goto postaction;
+        }
+      }
+    }
+    else if (bytes >= MAX_REQUEST)
+      nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+    else {
+      nb = pad_request(bytes);
+      if (gm->treemap != 0 && (mem = tmalloc_large(gm, nb)) != 0) {
+        check_malloced_chunk(gm, mem, nb);
+        goto postaction;
+      }
+    }
+
+    if (nb <= gm->dvsize) {
+      size_t rsize = gm->dvsize - nb;
+      mchunkptr p = gm->dv;
+      if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+        mchunkptr r = gm->dv = chunk_plus_offset(p, nb);
+        gm->dvsize = rsize;
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+      }
+      else { /* exhaust dv */
+        size_t dvs = gm->dvsize;
+        gm->dvsize = 0;
+        gm->dv = 0;
+        set_inuse_and_pinuse(gm, p, dvs);
+      }
+      mem = chunk2mem(p);
+      check_malloced_chunk(gm, mem, nb);
+      goto postaction;
+    }
+
+    else if (nb < gm->topsize) { /* Split top */
+      size_t rsize = gm->topsize -= nb;
+      mchunkptr p = gm->top;
+      mchunkptr r = gm->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(gm, p, nb);
+      mem = chunk2mem(p);
+      check_top_chunk(gm, gm->top);
+      check_malloced_chunk(gm, mem, nb);
+      goto postaction;
+    }
+
+    mem = sys_alloc(gm, nb);
+
+  postaction:
+    POSTACTION(gm);
+    return mem;
+  }
+
+  return 0;
+}
+
+/* ---------------------------- free --------------------------- */
+
+void dlfree(void* mem) {
+  /*
+     Consolidate freed chunks with preceeding or succeeding bordering
+     free chunks, if they exist, and then place in a bin.  Intermixed
+     with special cases for top, dv, mmapped chunks, and usage errors.
+  */
+
+  if (mem != 0) {
+    mchunkptr p  = mem2chunk(mem);
+#if FOOTERS
+    mstate fm = get_mstate_for(p);
+    if (!ok_magic(fm)) {
+      USAGE_ERROR_ACTION(fm, p);
+      return;
+    }
+#else /* FOOTERS */
+#define fm gm
+#endif /* FOOTERS */
+    if (!PREACTION(fm)) {
+      check_inuse_chunk(fm, p);
+      if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+        size_t psize = chunksize(p);
+        mchunkptr next = chunk_plus_offset(p, psize);
+        if (!pinuse(p)) {
+          size_t prevsize = p->prev_foot;
+          if (is_mmapped(p)) {
+            psize += prevsize + MMAP_FOOT_PAD;
+            if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+              fm->footprint -= psize;
+            goto postaction;
+          }
+          else {
+            mchunkptr prev = chunk_minus_offset(p, prevsize);
+            psize += prevsize;
+            p = prev;
+            if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+              if (p != fm->dv) {
+                unlink_chunk(fm, p, prevsize);
+              }
+              else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+                fm->dvsize = psize;
+                set_free_with_pinuse(p, psize, next);
+                goto postaction;
+              }
+            }
+            else
+              goto erroraction;
+          }
+        }
+
+        if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+          if (!cinuse(next)) {  /* consolidate forward */
+            if (next == fm->top) {
+              size_t tsize = fm->topsize += psize;
+              fm->top = p;
+              p->head = tsize | PINUSE_BIT;
+              if (p == fm->dv) {
+                fm->dv = 0;
+                fm->dvsize = 0;
+              }
+              if (should_trim(fm, tsize))
+                sys_trim(fm, 0);
+              goto postaction;
+            }
+            else if (next == fm->dv) {
+              size_t dsize = fm->dvsize += psize;
+              fm->dv = p;
+              set_size_and_pinuse_of_free_chunk(p, dsize);
+              goto postaction;
+            }
+            else {
+              size_t nsize = chunksize(next);
+              psize += nsize;
+              unlink_chunk(fm, next, nsize);
+              set_size_and_pinuse_of_free_chunk(p, psize);
+              if (p == fm->dv) {
+                fm->dvsize = psize;
+                goto postaction;
+              }
+            }
+          }
+          else
+            set_free_with_pinuse(p, psize, next);
+
+          if (is_small(psize)) {
+            insert_small_chunk(fm, p, psize);
+            check_free_chunk(fm, p);
+          }
+          else {
+            tchunkptr tp = (tchunkptr)p;
+            insert_large_chunk(fm, tp, psize);
+            check_free_chunk(fm, p);
+            if (--fm->release_checks == 0)
+              release_unused_segments(fm);
+          }
+          goto postaction;
+        }
+      }
+    erroraction:
+      USAGE_ERROR_ACTION(fm, p);
+    postaction:
+      POSTACTION(fm);
+    }
+  }
+#if !FOOTERS
+#undef fm
+#endif /* FOOTERS */
+}
+
+void* dlcalloc(size_t n_elements, size_t elem_size) {
+  void* mem;
+  size_t req = 0;
+  if (n_elements != 0) {
+    req = n_elements * elem_size;
+    if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+        (req / n_elements != elem_size))
+      req = MAX_SIZE_T; /* force downstream failure on overflow */
+  }
+  mem = dlmalloc(req);
+  if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+    memset(mem, 0, req);
+  return mem;
+}
+
+#endif /* !ONLY_MSPACES */
+
+/* ------------ Internal support for realloc, memalign, etc -------------- */
+
+/* Try to realloc; only in-place unless can_move true */
+static mchunkptr try_realloc_chunk(mstate m, mchunkptr p, size_t nb,
+                                   int can_move) {
+  mchunkptr newp = 0;
+  size_t oldsize = chunksize(p);
+  mchunkptr next = chunk_plus_offset(p, oldsize);
+  if (RTCHECK(ok_address(m, p) && ok_inuse(p) &&
+              ok_next(p, next) && ok_pinuse(next))) {
+    if (is_mmapped(p)) {
+      newp = mmap_resize(m, p, nb, can_move);
+    }
+    else if (oldsize >= nb) {             /* already big enough */
+      size_t rsize = oldsize - nb;
+      if (rsize >= MIN_CHUNK_SIZE) {      /* split off remainder */
+        mchunkptr r = chunk_plus_offset(p, nb);
+        set_inuse(m, p, nb);
+        set_inuse(m, r, rsize);
+        dispose_chunk(m, r, rsize);
+      }
+      newp = p;
+    }
+    else if (next == m->top) {  /* extend into top */
+      if (oldsize + m->topsize > nb) {
+        size_t newsize = oldsize + m->topsize;
+        size_t newtopsize = newsize - nb;
+        mchunkptr newtop = chunk_plus_offset(p, nb);
+        set_inuse(m, p, nb);
+        newtop->head = newtopsize |PINUSE_BIT;
+        m->top = newtop;
+        m->topsize = newtopsize;
+        newp = p;
+      }
+    }
+    else if (next == m->dv) { /* extend into dv */
+      size_t dvs = m->dvsize;
+      if (oldsize + dvs >= nb) {
+        size_t dsize = oldsize + dvs - nb;
+        if (dsize >= MIN_CHUNK_SIZE) {
+          mchunkptr r = chunk_plus_offset(p, nb);
+          mchunkptr n = chunk_plus_offset(r, dsize);
+          set_inuse(m, p, nb);
+          set_size_and_pinuse_of_free_chunk(r, dsize);
+          clear_pinuse(n);
+          m->dvsize = dsize;
+          m->dv = r;
+        }
+        else { /* exhaust dv */
+          size_t newsize = oldsize + dvs;
+          set_inuse(m, p, newsize);
+          m->dvsize = 0;
+          m->dv = 0;
+        }
+        newp = p;
+      }
+    }
+    else if (!cinuse(next)) { /* extend into next free chunk */
+      size_t nextsize = chunksize(next);
+      if (oldsize + nextsize >= nb) {
+        size_t rsize = oldsize + nextsize - nb;
+        unlink_chunk(m, next, nextsize);
+        if (rsize < MIN_CHUNK_SIZE) {
+          size_t newsize = oldsize + nextsize;
+          set_inuse(m, p, newsize);
+        }
+        else {
+          mchunkptr r = chunk_plus_offset(p, nb);
+          set_inuse(m, p, nb);
+          set_inuse(m, r, rsize);
+          dispose_chunk(m, r, rsize);
+        }
+        newp = p;
+      }
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(m, chunk2mem(p));
+  }
+  return newp;
+}
+
+static void* internal_memalign(mstate m, size_t alignment, size_t bytes) {
+  void* mem = 0;
+  if (alignment <  MIN_CHUNK_SIZE) /* must be at least a minimum chunk size */
+    alignment = MIN_CHUNK_SIZE;
+  if ((alignment & (alignment-SIZE_T_ONE)) != 0) {/* Ensure a power of 2 */
+    size_t a = MALLOC_ALIGNMENT << 1;
+    while (a < alignment) a <<= 1;
+    alignment = a;
+  }
+  if (bytes >= MAX_REQUEST - alignment) {
+    if (m != 0)  { /* Test isn't needed but avoids compiler warning */
+      MALLOC_FAILURE_ACTION;
+    }
+  }
+  else {
+    size_t nb = request2size(bytes);
+    size_t req = nb + alignment + MIN_CHUNK_SIZE - CHUNK_OVERHEAD;
+    mem = internal_malloc(m, req);
+    if (mem != 0) {
+      mchunkptr p = mem2chunk(mem);
+      if (PREACTION(m))
+        return 0;
+      if ((((size_t)(mem)) & (alignment - 1)) != 0) { /* misaligned */
+        /*
+          Find an aligned spot inside chunk.  Since we need to give
+          back leading space in a chunk of at least MIN_CHUNK_SIZE, if
+          the first calculation places us at a spot with less than
+          MIN_CHUNK_SIZE leader, we can move to the next aligned spot.
+          We've allocated enough total room so that this is always
+          possible.
+        */
+        char* br = (char*)mem2chunk((size_t)(((size_t)((char*)mem + alignment -
+                                                       SIZE_T_ONE)) &
+                                             -alignment));
+        char* pos = ((size_t)(br - (char*)(p)) >= MIN_CHUNK_SIZE)?
+          br : br+alignment;
+        mchunkptr newp = (mchunkptr)pos;
+        size_t leadsize = pos - (char*)(p);
+        size_t newsize = chunksize(p) - leadsize;
+
+        if (is_mmapped(p)) { /* For mmapped chunks, just adjust offset */
+          newp->prev_foot = p->prev_foot + leadsize;
+          newp->head = newsize;
+        }
+        else { /* Otherwise, give back leader, use the rest */
+          set_inuse(m, newp, newsize);
+          set_inuse(m, p, leadsize);
+          dispose_chunk(m, p, leadsize);
+        }
+        p = newp;
+      }
+
+      /* Give back spare room at the end */
+      if (!is_mmapped(p)) {
+        size_t size = chunksize(p);
+        if (size > nb + MIN_CHUNK_SIZE) {
+          size_t remainder_size = size - nb;
+          mchunkptr remainder = chunk_plus_offset(p, nb);
+          set_inuse(m, p, nb);
+          set_inuse(m, remainder, remainder_size);
+          dispose_chunk(m, remainder, remainder_size);
+        }
+      }
+
+      mem = chunk2mem(p);
+      assert (chunksize(p) >= nb);
+      assert(((size_t)mem & (alignment - 1)) == 0);
+      check_inuse_chunk(m, p);
+      POSTACTION(m);
+    }
+  }
+  return mem;
+}
+
+/*
+  Common support for independent_X routines, handling
+    all of the combinations that can result.
+  The opts arg has:
+    bit 0 set if all elements are same size (using sizes[0])
+    bit 1 set if elements should be zeroed
+*/
+static void** ialloc(mstate m,
+                     size_t n_elements,
+                     size_t* sizes,
+                     int opts,
+                     void* chunks[]) {
+
+  size_t    element_size;   /* chunksize of each element, if all same */
+  size_t    contents_size;  /* total size of elements */
+  size_t    array_size;     /* request size of pointer array */
+  void*     mem;            /* malloced aggregate space */
+  mchunkptr p;              /* corresponding chunk */
+  size_t    remainder_size; /* remaining bytes while splitting */
+  void**    marray;         /* either "chunks" or malloced ptr array */
+  mchunkptr array_chunk;    /* chunk for malloced ptr array */
+  flag_t    was_enabled;    /* to disable mmap */
+  size_t    size;
+  size_t    i;
+
+  ensure_initialization();
+  /* compute array length, if needed */
+  if (chunks != 0) {
+    if (n_elements == 0)
+      return chunks; /* nothing to do */
+    marray = chunks;
+    array_size = 0;
+  }
+  else {
+    /* if empty req, must still return chunk representing empty array */
+    if (n_elements == 0)
+      return (void**)internal_malloc(m, 0);
+    marray = 0;
+    array_size = request2size(n_elements * (sizeof(void*)));
+  }
+
+  /* compute total element size */
+  if (opts & 0x1) { /* all-same-size */
+    element_size = request2size(*sizes);
+    contents_size = n_elements * element_size;
+  }
+  else { /* add up all the sizes */
+    element_size = 0;
+    contents_size = 0;
+    for (i = 0; i != n_elements; ++i)
+      contents_size += request2size(sizes[i]);
+  }
+
+  size = contents_size + array_size;
+
+  /*
+     Allocate the aggregate chunk.  First disable direct-mmapping so
+     malloc won't use it, since we would not be able to later
+     free/realloc space internal to a segregated mmap region.
+  */
+  was_enabled = use_mmap(m);
+  disable_mmap(m);
+  mem = internal_malloc(m, size - CHUNK_OVERHEAD);
+  if (was_enabled)
+    enable_mmap(m);
+  if (mem == 0)
+    return 0;
+
+  if (PREACTION(m)) return 0;
+  p = mem2chunk(mem);
+  remainder_size = chunksize(p);
+
+  assert(!is_mmapped(p));
+
+  if (opts & 0x2) {       /* optionally clear the elements */
+    memset((size_t*)mem, 0, remainder_size - SIZE_T_SIZE - array_size);
+  }
+
+  /* If not provided, allocate the pointer array as final part of chunk */
+  if (marray == 0) {
+    size_t  array_chunk_size;
+    array_chunk = chunk_plus_offset(p, contents_size);
+    array_chunk_size = remainder_size - contents_size;
+    marray = (void**) (chunk2mem(array_chunk));
+    set_size_and_pinuse_of_inuse_chunk(m, array_chunk, array_chunk_size);
+    remainder_size = contents_size;
+  }
+
+  /* split out elements */
+  for (i = 0; ; ++i) {
+    marray[i] = chunk2mem(p);
+    if (i != n_elements-1) {
+      if (element_size != 0)
+        size = element_size;
+      else
+        size = request2size(sizes[i]);
+      remainder_size -= size;
+      set_size_and_pinuse_of_inuse_chunk(m, p, size);
+      p = chunk_plus_offset(p, size);
+    }
+    else { /* the final element absorbs any overallocation slop */
+      set_size_and_pinuse_of_inuse_chunk(m, p, remainder_size);
+      break;
+    }
+  }
+
+#if DEBUG
+  if (marray != chunks) {
+    /* final element must have exactly exhausted chunk */
+    if (element_size != 0) {
+      assert(remainder_size == element_size);
+    }
+    else {
+      assert(remainder_size == request2size(sizes[i]));
+    }
+    check_inuse_chunk(m, mem2chunk(marray));
+  }
+  for (i = 0; i != n_elements; ++i)
+    check_inuse_chunk(m, mem2chunk(marray[i]));
+
+#endif /* DEBUG */
+
+  POSTACTION(m);
+  return marray;
+}
+
+/* Try to free all pointers in the given array.
+   Note: this could be made faster, by delaying consolidation,
+   at the price of disabling some user integrity checks, We
+   still optimize some consolidations by combining adjacent
+   chunks before freeing, which will occur often if allocated
+   with ialloc or the array is sorted.
+*/
+static size_t internal_bulk_free(mstate m, void* array[], size_t nelem) {
+  size_t unfreed = 0;
+  if (!PREACTION(m)) {
+    void** a;
+    void** fence = &(array[nelem]);
+    for (a = array; a != fence; ++a) {
+      void* mem = *a;
+      if (mem != 0) {
+        mchunkptr p = mem2chunk(mem);
+        size_t psize = chunksize(p);
+#if FOOTERS
+        if (get_mstate_for(p) != m) {
+          ++unfreed;
+          continue;
+        }
+#endif
+        check_inuse_chunk(m, p);
+        *a = 0;
+        if (RTCHECK(ok_address(m, p) && ok_inuse(p))) {
+          void ** b = a + 1; /* try to merge with next chunk */
+          mchunkptr next = next_chunk(p);
+          if (b != fence && *b == chunk2mem(next)) {
+            size_t newsize = chunksize(next) + psize;
+            set_inuse(m, p, newsize);
+            *b = chunk2mem(p);
+          }
+          else
+            dispose_chunk(m, p, psize);
+        }
+        else {
+          CORRUPTION_ERROR_ACTION(m);
+          break;
+        }
+      }
+    }
+    if (should_trim(m, m->topsize))
+      sys_trim(m, 0);
+    POSTACTION(m);
+  }
+  return unfreed;
+}
+
+/* Traversal */
+#if MALLOC_INSPECT_ALL
+static void internal_inspect_all(mstate m,
+                                 void(*handler)(void *start,
+                                                void *end,
+                                                size_t used_bytes,
+                                                void* callback_arg),
+                                 void* arg) {
+  if (is_initialized(m)) {
+    mchunkptr top = m->top;
+    msegmentptr s;
+    for (s = &m->seg; s != 0; s = s->next) {
+      mchunkptr q = align_as_chunk(s->base);
+      while (segment_holds(s, q) && q->head != FENCEPOST_HEAD) {
+        mchunkptr next = next_chunk(q);
+        size_t sz = chunksize(q);
+        size_t used;
+        void* start;
+        if (is_inuse(q)) {
+          used = sz - CHUNK_OVERHEAD; /* must not be mmapped */
+          start = chunk2mem(q);
+        }
+        else {
+          used = 0;
+          if (is_small(sz)) {     /* offset by possible bookkeeping */
+            start = (void*)((char*)q + sizeof(struct malloc_chunk));
+          }
+          else {
+            start = (void*)((char*)q + sizeof(struct malloc_tree_chunk));
+          }
+        }
+        if (start < (void*)next)  /* skip if all space is bookkeeping */
+          handler(start, next, used, arg);
+        if (q == top)
+          break;
+        q = next;
+      }
+    }
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+/* ------------------ Exported realloc, memalign, etc -------------------- */
+
+#if !ONLY_MSPACES
+
+void* dlrealloc(void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem == 0) {
+    mem = dlmalloc(bytes);
+  }
+  else if (bytes >= MAX_REQUEST) {
+    MALLOC_FAILURE_ACTION;
+  }
+#ifdef REALLOC_ZERO_BYTES_FREES
+  else if (bytes == 0) {
+    dlfree(oldmem);
+  }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+  else {
+    size_t nb = request2size(bytes);
+    mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+    mstate m = gm;
+#else /* FOOTERS */
+    mstate m = get_mstate_for(oldp);
+    if (!ok_magic(m)) {
+      USAGE_ERROR_ACTION(m, oldmem);
+      return 0;
+    }
+#endif /* FOOTERS */
+    if (!PREACTION(m)) {
+      mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1);
+      POSTACTION(m);
+      if (newp != 0) {
+        check_inuse_chunk(m, newp);
+        mem = chunk2mem(newp);
+      }
+      else {
+        mem = internal_malloc(m, bytes);
+        if (mem != 0) {
+          size_t oc = chunksize(oldp) - overhead_for(oldp);
+          memcpy(mem, oldmem, (oc < bytes)? oc : bytes);
+          internal_free(m, oldmem);
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* dlrealloc_in_place(void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem != 0) {
+    if (bytes >= MAX_REQUEST) {
+      MALLOC_FAILURE_ACTION;
+    }
+    else {
+      size_t nb = request2size(bytes);
+      mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+      mstate m = gm;
+#else /* FOOTERS */
+      mstate m = get_mstate_for(oldp);
+      if (!ok_magic(m)) {
+        USAGE_ERROR_ACTION(m, oldmem);
+        return 0;
+      }
+#endif /* FOOTERS */
+      if (!PREACTION(m)) {
+        mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0);
+        POSTACTION(m);
+        if (newp == oldp) {
+          check_inuse_chunk(m, newp);
+          mem = oldmem;
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* dlmemalign(size_t alignment, size_t bytes) {
+  if (alignment <= MALLOC_ALIGNMENT) {
+    return dlmalloc(bytes);
+  }
+  return internal_memalign(gm, alignment, bytes);
+}
+
+int dlposix_memalign(void** pp, size_t alignment, size_t bytes) {
+  void* mem = 0;
+  if (alignment == MALLOC_ALIGNMENT)
+    mem = dlmalloc(bytes);
+  else {
+    size_t d = alignment / sizeof(void*);
+    size_t r = alignment % sizeof(void*);
+    if (r != 0 || d == 0 || (d & (d-SIZE_T_ONE)) != 0)
+      return EINVAL;
+    else if (bytes <= MAX_REQUEST - alignment) {
+      if (alignment <  MIN_CHUNK_SIZE)
+        alignment = MIN_CHUNK_SIZE;
+      mem = internal_memalign(gm, alignment, bytes);
+    }
+  }
+  if (mem == 0)
+    return ENOMEM;
+  else {
+    *pp = mem;
+    return 0;
+  }
+}
+
+void* dlvalloc(size_t bytes) {
+  size_t pagesz;
+  ensure_initialization();
+  pagesz = mparams.page_size;
+  return dlmemalign(pagesz, bytes);
+}
+
+void* dlpvalloc(size_t bytes) {
+  size_t pagesz;
+  ensure_initialization();
+  pagesz = mparams.page_size;
+  return dlmemalign(pagesz, (bytes + pagesz - SIZE_T_ONE) & ~(pagesz - SIZE_T_ONE));
+}
+
+void** dlindependent_calloc(size_t n_elements, size_t elem_size,
+                            void* chunks[]) {
+  size_t sz = elem_size; /* serves as 1-element array */
+  return ialloc(gm, n_elements, &sz, 3, chunks);
+}
+
+void** dlindependent_comalloc(size_t n_elements, size_t sizes[],
+                              void* chunks[]) {
+  return ialloc(gm, n_elements, sizes, 0, chunks);
+}
+
+size_t dlbulk_free(void* array[], size_t nelem) {
+  return internal_bulk_free(gm, array, nelem);
+}
+
+#if MALLOC_INSPECT_ALL
+void dlmalloc_inspect_all(void(*handler)(void *start,
+                                         void *end,
+                                         size_t used_bytes,
+                                         void* callback_arg),
+                          void* arg) {
+  ensure_initialization();
+  if (!PREACTION(gm)) {
+    internal_inspect_all(gm, handler, arg);
+    POSTACTION(gm);
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+int dlmalloc_trim(size_t pad) {
+  int result = 0;
+  ensure_initialization();
+  if (!PREACTION(gm)) {
+    result = sys_trim(gm, pad);
+    POSTACTION(gm);
+  }
+  return result;
+}
+
+size_t dlmalloc_footprint(void) {
+  return gm->footprint;
+}
+
+size_t dlmalloc_max_footprint(void) {
+  return gm->max_footprint;
+}
+
+size_t dlmalloc_footprint_limit(void) {
+  size_t maf = gm->footprint_limit;
+  return maf == 0 ? MAX_SIZE_T : maf;
+}
+
+size_t dlmalloc_set_footprint_limit(size_t bytes) {
+  size_t result;  /* invert sense of 0 */
+  if (bytes == 0)
+    result = granularity_align(1); /* Use minimal size */
+  if (bytes == MAX_SIZE_T)
+    result = 0;                    /* disable */
+  else
+    result = granularity_align(bytes);
+  return gm->footprint_limit = result;
+}
+
+#if !NO_MALLINFO
+struct mallinfo dlmallinfo(void) {
+  return internal_mallinfo(gm);
+}
+#endif /* NO_MALLINFO */
+
+#if !NO_MALLOC_STATS
+void dlmalloc_stats() {
+  internal_malloc_stats(gm);
+}
+#endif /* NO_MALLOC_STATS */
+
+int dlmallopt(int param_number, int value) {
+  return change_mparam(param_number, value);
+}
+
+size_t dlmalloc_usable_size(void* mem) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    if (is_inuse(p))
+      return chunksize(p) - overhead_for(p);
+  }
+  return 0;
+}
+
+#endif /* !ONLY_MSPACES */
+
+/* ----------------------------- user mspaces ---------------------------- */
+
+#if MSPACES
+
+static mstate init_user_mstate(char* tbase, size_t tsize) {
+  size_t msize = pad_request(sizeof(struct malloc_state));
+  mchunkptr mn;
+  mchunkptr msp = align_as_chunk(tbase);
+  mstate m = (mstate)(chunk2mem(msp));
+  memset(m, 0, msize);
+  (void)INITIAL_LOCK(&m->mutex);
+  msp->head = (msize|INUSE_BITS);
+  m->seg.base = m->least_addr = tbase;
+  m->seg.size = m->footprint = m->max_footprint = tsize;
+  m->magic = mparams.magic;
+  m->release_checks = MAX_RELEASE_CHECK_RATE;
+  m->mflags = mparams.default_mflags;
+  m->extp = 0;
+  m->exts = 0;
+  disable_contiguous(m);
+  init_bins(m);
+  mn = next_chunk(mem2chunk(m));
+  init_top(m, mn, (size_t)((tbase + tsize) - (char*)mn) - TOP_FOOT_SIZE);
+  check_top_chunk(m, m->top);
+  return m;
+}
+
+mspace create_mspace(size_t capacity, int locked) {
+  mstate m = 0;
+  size_t msize;
+  ensure_initialization();
+  msize = pad_request(sizeof(struct malloc_state));
+  if (capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+    size_t rs = ((capacity == 0)? mparams.granularity :
+                 (capacity + TOP_FOOT_SIZE + msize));
+    size_t tsize = granularity_align(rs);
+    char* tbase = (char*)(CALL_MMAP(tsize));
+    if (tbase != CMFAIL) {
+      m = init_user_mstate(tbase, tsize);
+      m->seg.sflags = USE_MMAP_BIT;
+      set_lock(m, locked);
+    }
+  }
+  return (mspace)m;
+}
+
+mspace create_mspace_with_base(void* base, size_t capacity, int locked) {
+  mstate m = 0;
+  size_t msize;
+  ensure_initialization();
+  msize = pad_request(sizeof(struct malloc_state));
+  if (capacity > msize + TOP_FOOT_SIZE &&
+      capacity < (size_t) -(msize + TOP_FOOT_SIZE + mparams.page_size)) {
+    m = init_user_mstate((char*)base, capacity);
+    m->seg.sflags = EXTERN_BIT;
+    set_lock(m, locked);
+  }
+  return (mspace)m;
+}
+
+int mspace_track_large_chunks(mspace msp, int enable) {
+  int ret = 0;
+  mstate ms = (mstate)msp;
+  if (!PREACTION(ms)) {
+    if (!use_mmap(ms)) {
+      ret = 1;
+    }
+    if (!enable) {
+      enable_mmap(ms);
+    } else {
+      disable_mmap(ms);
+    }
+    POSTACTION(ms);
+  }
+  return ret;
+}
+
+size_t destroy_mspace(mspace msp) {
+  size_t freed = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    msegmentptr sp = &ms->seg;
+    (void)DESTROY_LOCK(&ms->mutex); /* destroy before unmapped */
+    while (sp != 0) {
+      char* base = sp->base;
+      size_t size = sp->size;
+      flag_t flag = sp->sflags;
+      (void)base; /* placate people compiling -Wunused-variable */
+      sp = sp->next;
+      if ((flag & USE_MMAP_BIT) && !(flag & EXTERN_BIT) &&
+          CALL_MUNMAP(base, size) == 0)
+        freed += size;
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return freed;
+}
+
+void mspace_get_address_and_size (mspace msp, unsigned long long *addrp,
+                                  unsigned long long *sizep)
+{
+  mstate ms;
+  msegment *this_seg;
+  
+  ms = (mstate)msp;
+  this_seg = &ms->seg;
+
+  *addrp = (unsigned long long) this_seg->base;
+  *sizep = this_seg->size;
+}
+
+int mspace_is_heap_object (mspace msp, void *p)
+{
+  msegment *this_seg;
+  char *pp, *base;
+  mstate ms;
+
+  ms = (mstate)msp;
+
+  this_seg = &ms->seg;
+  pp = (char *) p;
+
+  while (this_seg)
+    {
+      base = this_seg->base;
+      if (pp >= base && pp < (base + this_seg->size))
+        return 1;
+      this_seg = this_seg->next;
+    }
+  return 0;
+}
+
+void *mspace_least_addr (mspace msp)
+{
+  mstate ms = (mstate) msp;
+  return (void *) ms->least_addr;
+}
+
+void mspace_disable_expand (mspace msp)
+{
+  mstate ms = (mstate)msp;
+
+  disable_expand (ms);
+}
+
+int mspace_enable_disable_trace (mspace msp, int enable)
+{
+  mstate ms = (mstate)msp;
+  int was_enabled = 0;
+
+  if (use_trace(ms) == 1)
+    was_enabled = 1;
+
+  if (enable)
+    enable_trace (ms);
+  else
+    disable_trace (ms);
+
+  return (was_enabled);
+}
+
+void* mspace_get_aligned (mspace msp, 
+                          unsigned long long n_user_data_bytes,
+                          unsigned long long align, 
+                          unsigned long long align_offset) {
+  char *rv;
+  unsigned long long searchp;
+  unsigned *wwp;                /* "where's Waldo" pointer */
+  mstate ms = (mstate)msp;
+
+  /*
+   * Allocate space for the "Where's Waldo?" pointer 
+   * the base of the dlmalloc object
+   */
+  n_user_data_bytes += sizeof(unsigned);
+
+  /* 
+   * Alignment requests less than the size of an mmx vector are ignored 
+   */
+  if (align < 16) {
+    rv = mspace_malloc (msp, n_user_data_bytes);
+    if (rv == 0)
+        return rv;
+
+    if (use_trace(ms)) {
+      mchunkptr p  = mem2chunk(rv);
+      size_t psize = chunksize(p);
+      
+      mheap_get_trace ((u64)rv + sizeof (unsigned), psize);
+    }
+
+    wwp = (unsigned *)rv;
+    *wwp = 0;
+    rv += sizeof (unsigned);
+
+    return rv;
+  }
+
+  /*
+   * Alignment requests greater than 4K must be at offset zero,
+   * and must be freed using mspace_free_no_offset - or never freed -
+   * since the "Where's Waldo?" pointer would waste too much space.
+   * 
+   * Waldo is the address of the chunk of memory returned by mspace_malloc, 
+   * which we need later to call mspace_free...
+   */
+  if (align > 4<<10 || align_offset == ~0ULL) {
+    n_user_data_bytes -= sizeof(unsigned);
+    assert(align_offset == 0);
+    rv = internal_memalign(ms, (size_t)align, n_user_data_bytes);
+    
+    /* Trace the allocation */
+    if (rv && use_trace(ms)) {
+      mchunkptr p  = mem2chunk(rv);
+      size_t psize = chunksize(p);
+      mheap_get_trace ((u64)rv, psize);
+    }
+    return rv;
+  }
+
+  align = clib_max (align, MALLOC_ALIGNMENT);
+  align = max_pow2 (align);
+
+  /* Correct align offset to be smaller than alignment. */
+  align_offset &= (align - 1);
+
+  n_user_data_bytes += align;
+  rv = mspace_malloc (msp, n_user_data_bytes);
+
+  if (rv == 0)
+      return rv;
+
+  /* Honor the alignment request */
+  searchp = (unsigned long long)(rv + sizeof (unsigned));
+
+#if 0  /* this is the idea... */
+  while ((searchp + align_offset) % align)
+    searchp++;
+#endif
+
+  {
+    unsigned long long where_now, delta;
+
+    where_now = (searchp + align_offset) % align;
+    delta = align - where_now;
+
+    searchp += delta;
+  }
+
+  wwp = (unsigned *)(searchp - sizeof(unsigned));
+  *wwp = (searchp - (((unsigned long long) rv) + sizeof (*wwp)));
+  assert (*wwp < align);
+
+  if (use_trace(ms)) {
+    mchunkptr p  = mem2chunk(rv);
+    size_t psize = chunksize(p);
+    mheap_get_trace ((u64)rv, psize);
+  }
+  return (void *) searchp;
+}
+
+void mspace_put (mspace msp, void *p_arg)
+{
+  char *object_header;
+  unsigned *wwp;
+  mstate ms = (mstate)msp;
+
+  /* Find the object header delta */
+  wwp = (unsigned *)p_arg;
+  wwp --;
+
+  /* Recover the dlmalloc object pointer */
+  object_header = (char *)wwp;
+  object_header -= *wwp;
+
+  /* Tracing (if enabled) */
+  if (use_trace(ms))
+    {
+      mchunkptr p  = mem2chunk(object_header);
+      size_t psize = chunksize(p);
+
+      mheap_put_trace ((u64)p_arg, psize);
+    }
+
+  /* And free it... */
+  mspace_free (msp, object_header);
+}
+
+void mspace_put_no_offset (mspace msp, void *p_arg)
+{
+  mstate ms = (mstate)msp;
+
+  if (use_trace(ms))
+    {
+      mchunkptr p  = mem2chunk(p_arg);
+      size_t psize = chunksize(p);
+
+      mheap_put_trace ((u64)p_arg, psize);
+    }
+  mspace_free (msp, p_arg);
+}
+
+size_t mspace_usable_size_with_delta (const void *p)
+{
+  size_t usable_size;
+  char *object_header;
+  unsigned *wwp;
+
+  /* Find the object header delta */
+  wwp = (unsigned *)p;
+  wwp --;
+
+  /* Recover the dlmalloc object pointer */
+  object_header = (char *)wwp;
+  object_header -= *wwp;
+
+  usable_size = mspace_usable_size (object_header);
+  /* account for the offset and the size of the offset... */
+  usable_size -= (*wwp + sizeof (*wwp));
+  return usable_size;
+}
+
+/*
+  mspace versions of routines are near-clones of the global
+  versions. This is not so nice but better than the alternatives.
+*/
+
+void* mspace_malloc(mspace msp, size_t bytes) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (!PREACTION(ms)) {
+    void* mem;
+    size_t nb;
+    if (bytes <= MAX_SMALL_REQUEST) {
+      bindex_t idx;
+      binmap_t smallbits;
+      nb = (bytes < MIN_REQUEST)? MIN_CHUNK_SIZE : pad_request(bytes);
+      idx = small_index(nb);
+      smallbits = ms->smallmap >> idx;
+
+      if ((smallbits & 0x3U) != 0) { /* Remainderless fit to a smallbin. */
+        mchunkptr b, p;
+        idx += ~smallbits & 1;       /* Uses next bin if idx empty */
+        b = smallbin_at(ms, idx);
+        p = b->fd;
+        assert(chunksize(p) == small_index2size(idx));
+        unlink_first_small_chunk(ms, b, p, idx);
+        set_inuse_and_pinuse(ms, p, small_index2size(idx));
+        mem = chunk2mem(p);
+        check_malloced_chunk(ms, mem, nb);
+        goto postaction;
+      }
+
+      else if (nb > ms->dvsize) {
+        if (smallbits != 0) { /* Use chunk in next nonempty smallbin */
+          mchunkptr b, p, r;
+          size_t rsize;
+          bindex_t i;
+          binmap_t leftbits = (smallbits << idx) & left_bits(idx2bit(idx));
+          binmap_t leastbit = least_bit(leftbits);
+          compute_bit2idx(leastbit, i);
+          b = smallbin_at(ms, i);
+          p = b->fd;
+          assert(chunksize(p) == small_index2size(i));
+          unlink_first_small_chunk(ms, b, p, i);
+          rsize = small_index2size(i) - nb;
+          /* Fit here cannot be remainderless if 4byte sizes */
+          if (SIZE_T_SIZE != 4 && rsize < MIN_CHUNK_SIZE)
+            set_inuse_and_pinuse(ms, p, small_index2size(i));
+          else {
+            set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+            r = chunk_plus_offset(p, nb);
+            set_size_and_pinuse_of_free_chunk(r, rsize);
+            replace_dv(ms, r, rsize);
+          }
+          mem = chunk2mem(p);
+          check_malloced_chunk(ms, mem, nb);
+          goto postaction;
+        }
+
+        else if (ms->treemap != 0 && (mem = tmalloc_small(ms, nb)) != 0) {
+          check_malloced_chunk(ms, mem, nb);
+          goto postaction;
+        }
+      }
+    }
+    else if (bytes >= MAX_REQUEST)
+      nb = MAX_SIZE_T; /* Too big to allocate. Force failure (in sys alloc) */
+    else {
+      nb = pad_request(bytes);
+      if (ms->treemap != 0 && (mem = tmalloc_large(ms, nb)) != 0) {
+        check_malloced_chunk(ms, mem, nb);
+        goto postaction;
+      }
+    }
+
+    if (nb <= ms->dvsize) {
+      size_t rsize = ms->dvsize - nb;
+      mchunkptr p = ms->dv;
+      if (rsize >= MIN_CHUNK_SIZE) { /* split dv */
+        mchunkptr r = ms->dv = chunk_plus_offset(p, nb);
+        ms->dvsize = rsize;
+        set_size_and_pinuse_of_free_chunk(r, rsize);
+        set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+      }
+      else { /* exhaust dv */
+        size_t dvs = ms->dvsize;
+        ms->dvsize = 0;
+        ms->dv = 0;
+        set_inuse_and_pinuse(ms, p, dvs);
+      }
+      mem = chunk2mem(p);
+      check_malloced_chunk(ms, mem, nb);
+      goto postaction;
+    }
+
+    else if (nb < ms->topsize) { /* Split top */
+      size_t rsize = ms->topsize -= nb;
+      mchunkptr p = ms->top;
+      mchunkptr r = ms->top = chunk_plus_offset(p, nb);
+      r->head = rsize | PINUSE_BIT;
+      set_size_and_pinuse_of_inuse_chunk(ms, p, nb);
+      mem = chunk2mem(p);
+      check_top_chunk(ms, ms->top);
+      check_malloced_chunk(ms, mem, nb);
+      goto postaction;
+    }
+
+    mem = sys_alloc(ms, nb);
+
+  postaction:
+    POSTACTION(ms);
+    return mem;
+  }
+
+  return 0;
+}
+
+void mspace_free(mspace msp, void* mem) {
+  if (mem != 0) {
+    mchunkptr p  = mem2chunk(mem);
+#if FOOTERS
+    mstate fm = get_mstate_for(p);
+    (void)msp; /* placate people compiling -Wunused */
+#else /* FOOTERS */
+    mstate fm = (mstate)msp;
+#endif /* FOOTERS */
+    if (!ok_magic(fm)) {
+      USAGE_ERROR_ACTION(fm, p);
+      return;
+    }
+    if (!PREACTION(fm)) {
+      check_inuse_chunk(fm, p);
+      if (RTCHECK(ok_address(fm, p) && ok_inuse(p))) {
+        size_t psize = chunksize(p);
+        mchunkptr next = chunk_plus_offset(p, psize);
+        if (!pinuse(p)) {
+          size_t prevsize = p->prev_foot;
+          if (is_mmapped(p)) {
+            psize += prevsize + MMAP_FOOT_PAD;
+            if (CALL_MUNMAP((char*)p - prevsize, psize) == 0)
+              fm->footprint -= psize;
+            goto postaction;
+          }
+          else {
+            mchunkptr prev = chunk_minus_offset(p, prevsize);
+            psize += prevsize;
+            p = prev;
+            if (RTCHECK(ok_address(fm, prev))) { /* consolidate backward */
+              if (p != fm->dv) {
+                unlink_chunk(fm, p, prevsize);
+              }
+              else if ((next->head & INUSE_BITS) == INUSE_BITS) {
+                fm->dvsize = psize;
+                set_free_with_pinuse(p, psize, next);
+                goto postaction;
+              }
+            }
+            else
+              goto erroraction;
+          }
+        }
+
+        if (RTCHECK(ok_next(p, next) && ok_pinuse(next))) {
+          if (!cinuse(next)) {  /* consolidate forward */
+            if (next == fm->top) {
+              size_t tsize = fm->topsize += psize;
+              fm->top = p;
+              p->head = tsize | PINUSE_BIT;
+              if (p == fm->dv) {
+                fm->dv = 0;
+                fm->dvsize = 0;
+              }
+              if (should_trim(fm, tsize))
+                sys_trim(fm, 0);
+              goto postaction;
+            }
+            else if (next == fm->dv) {
+              size_t dsize = fm->dvsize += psize;
+              fm->dv = p;
+              set_size_and_pinuse_of_free_chunk(p, dsize);
+              goto postaction;
+            }
+            else {
+              size_t nsize = chunksize(next);
+              psize += nsize;
+              unlink_chunk(fm, next, nsize);
+              set_size_and_pinuse_of_free_chunk(p, psize);
+              if (p == fm->dv) {
+                fm->dvsize = psize;
+                goto postaction;
+              }
+            }
+          }
+          else
+            set_free_with_pinuse(p, psize, next);
+
+          if (is_small(psize)) {
+            insert_small_chunk(fm, p, psize);
+            check_free_chunk(fm, p);
+          }
+          else {
+            tchunkptr tp = (tchunkptr)p;
+            insert_large_chunk(fm, tp, psize);
+            check_free_chunk(fm, p);
+            if (--fm->release_checks == 0)
+              release_unused_segments(fm);
+          }
+          goto postaction;
+        }
+      }
+    erroraction:
+      USAGE_ERROR_ACTION(fm, p);
+    postaction:
+      POSTACTION(fm);
+    }
+  }
+}
+
+void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size) {
+  void* mem;
+  size_t req = 0;
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (n_elements != 0) {
+    req = n_elements * elem_size;
+    if (((n_elements | elem_size) & ~(size_t)0xffff) &&
+        (req / n_elements != elem_size))
+      req = MAX_SIZE_T; /* force downstream failure on overflow */
+  }
+  mem = internal_malloc(ms, req);
+  if (mem != 0 && calloc_must_clear(mem2chunk(mem)))
+    memset(mem, 0, req);
+  return mem;
+}
+
+void* mspace_realloc(mspace msp, void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem == 0) {
+    mem = mspace_malloc(msp, bytes);
+  }
+  else if (bytes >= MAX_REQUEST) {
+    MALLOC_FAILURE_ACTION;
+  }
+#ifdef REALLOC_ZERO_BYTES_FREES
+  else if (bytes == 0) {
+    mspace_free(msp, oldmem);
+  }
+#endif /* REALLOC_ZERO_BYTES_FREES */
+  else {
+    size_t nb = request2size(bytes);
+    mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+    mstate m = (mstate)msp;
+#else /* FOOTERS */
+    mstate m = get_mstate_for(oldp);
+    if (!ok_magic(m)) {
+      USAGE_ERROR_ACTION(m, oldmem);
+      return 0;
+    }
+#endif /* FOOTERS */
+    if (!PREACTION(m)) {
+      mchunkptr newp = try_realloc_chunk(m, oldp, nb, 1);
+      POSTACTION(m);
+      if (newp != 0) {
+        check_inuse_chunk(m, newp);
+        mem = chunk2mem(newp);
+      }
+      else {
+        mem = mspace_malloc(m, bytes);
+        if (mem != 0) {
+          size_t oc = chunksize(oldp) - overhead_for(oldp);
+          memcpy(mem, oldmem, (oc < bytes)? oc : bytes);
+          mspace_free(m, oldmem);
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* mspace_realloc_in_place(mspace msp, void* oldmem, size_t bytes) {
+  void* mem = 0;
+  if (oldmem != 0) {
+    if (bytes >= MAX_REQUEST) {
+      MALLOC_FAILURE_ACTION;
+    }
+    else {
+      size_t nb = request2size(bytes);
+      mchunkptr oldp = mem2chunk(oldmem);
+#if ! FOOTERS
+      mstate m = (mstate)msp;
+#else /* FOOTERS */
+      mstate m = get_mstate_for(oldp);
+      (void)msp; /* placate people compiling -Wunused */
+      if (!ok_magic(m)) {
+        USAGE_ERROR_ACTION(m, oldmem);
+        return 0;
+      }
+#endif /* FOOTERS */
+      if (!PREACTION(m)) {
+        mchunkptr newp = try_realloc_chunk(m, oldp, nb, 0);
+        POSTACTION(m);
+        if (newp == oldp) {
+          check_inuse_chunk(m, newp);
+          mem = oldmem;
+        }
+      }
+    }
+  }
+  return mem;
+}
+
+void* mspace_memalign(mspace msp, size_t alignment, size_t bytes) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  if (alignment <= MALLOC_ALIGNMENT)
+    return mspace_malloc(msp, bytes);
+  return internal_memalign(ms, alignment, bytes);
+}
+
+void** mspace_independent_calloc(mspace msp, size_t n_elements,
+                                 size_t elem_size, void* chunks[]) {
+  size_t sz = elem_size; /* serves as 1-element array */
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  return ialloc(ms, n_elements, &sz, 3, chunks);
+}
+
+void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+                                   size_t sizes[], void* chunks[]) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+    return 0;
+  }
+  return ialloc(ms, n_elements, sizes, 0, chunks);
+}
+
+size_t mspace_bulk_free(mspace msp, void* array[], size_t nelem) {
+  return internal_bulk_free((mstate)msp, array, nelem);
+}
+
+#if MALLOC_INSPECT_ALL
+void mspace_inspect_all(mspace msp,
+                        void(*handler)(void *start,
+                                       void *end,
+                                       size_t used_bytes,
+                                       void* callback_arg),
+                        void* arg) {
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (!PREACTION(ms)) {
+      internal_inspect_all(ms, handler, arg);
+      POSTACTION(ms);
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+}
+#endif /* MALLOC_INSPECT_ALL */
+
+int mspace_trim(mspace msp, size_t pad) {
+  int result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (!PREACTION(ms)) {
+      result = sys_trim(ms, pad);
+      POSTACTION(ms);
+    }
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+#if !NO_MALLOC_STATS
+void mspace_malloc_stats(mspace msp) {
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    internal_malloc_stats(ms);
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+}
+#endif /* NO_MALLOC_STATS */
+
+size_t mspace_footprint(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    result = ms->footprint;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_max_footprint(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    result = ms->max_footprint;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_footprint_limit(mspace msp) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    size_t maf = ms->footprint_limit;
+    result = (maf == 0) ? MAX_SIZE_T : maf;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+size_t mspace_set_footprint_limit(mspace msp, size_t bytes) {
+  size_t result = 0;
+  mstate ms = (mstate)msp;
+  if (ok_magic(ms)) {
+    if (bytes == 0)
+      result = granularity_align(1); /* Use minimal size */
+    if (bytes == MAX_SIZE_T)
+      result = 0;                    /* disable */
+    else
+      result = granularity_align(bytes);
+    ms->footprint_limit = result;
+  }
+  else {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return result;
+}
+
+#if !NO_MALLINFO
+struct mallinfo mspace_mallinfo(mspace msp) {
+  mstate ms = (mstate)msp;
+  if (!ok_magic(ms)) {
+    USAGE_ERROR_ACTION(ms,ms);
+  }
+  return internal_mallinfo(ms);
+}
+#endif /* NO_MALLINFO */
+
+size_t mspace_usable_size(const void* mem) {
+  if (mem != 0) {
+    mchunkptr p = mem2chunk(mem);
+    if (is_inuse(p))
+      return chunksize(p) - overhead_for(p);
+  }
+  return 0;
+}
+
+int mspace_mallopt(int param_number, int value) {
+  return change_mparam(param_number, value);
+}
+
+#endif /* MSPACES */
+
+
+/* -------------------- Alternative MORECORE functions ------------------- */
+
+/*
+  Guidelines for creating a custom version of MORECORE:
+
+  * For best performance, MORECORE should allocate in multiples of pagesize.
+  * MORECORE may allocate more memory than requested. (Or even less,
+      but this will usually result in a malloc failure.)
+  * MORECORE must not allocate memory when given argument zero, but
+      instead return one past the end address of memory from previous
+      nonzero call.
+  * For best performance, consecutive calls to MORECORE with positive
+      arguments should return increasing addresses, indicating that
+      space has been contiguously extended.
+  * Even though consecutive calls to MORECORE need not return contiguous
+      addresses, it must be OK for malloc'ed chunks to span multiple
+      regions in those cases where they do happen to be contiguous.
+  * MORECORE need not handle negative arguments -- it may instead
+      just return MFAIL when given negative arguments.
+      Negative arguments are always multiples of pagesize. MORECORE
+      must not misinterpret negative args as large positive unsigned
+      args. You can suppress all such calls from even occurring by defining
+      MORECORE_CANNOT_TRIM,
+
+  As an example alternative MORECORE, here is a custom allocator
+  kindly contributed for pre-OSX macOS.  It uses virtually but not
+  necessarily physically contiguous non-paged memory (locked in,
+  present and won't get swapped out).  You can use it by uncommenting
+  this section, adding some #includes, and setting up the appropriate
+  defines above:
+
+      #define MORECORE osMoreCore
+
+  There is also a shutdown routine that should somehow be called for
+  cleanup upon program exit.
+
+  #define MAX_POOL_ENTRIES 100
+  #define MINIMUM_MORECORE_SIZE  (64 * 1024U)
+  static int next_os_pool;
+  void *our_os_pools[MAX_POOL_ENTRIES];
+
+  void *osMoreCore(int size)
+  {
+    void *ptr = 0;
+    static void *sbrk_top = 0;
+
+    if (size > 0)
+    {
+      if (size < MINIMUM_MORECORE_SIZE)
+         size = MINIMUM_MORECORE_SIZE;
+      if (CurrentExecutionLevel() == kTaskLevel)
+         ptr = PoolAllocateResident(size + RM_PAGE_SIZE, 0);
+      if (ptr == 0)
+      {
+        return (void *) MFAIL;
+      }
+      // save ptrs so they can be freed during cleanup
+      our_os_pools[next_os_pool] = ptr;
+      next_os_pool++;
+      ptr = (void *) ((((size_t) ptr) + RM_PAGE_MASK) & ~RM_PAGE_MASK);
+      sbrk_top = (char *) ptr + size;
+      return ptr;
+    }
+    else if (size < 0)
+    {
+      // we don't currently support shrink behavior
+      return (void *) MFAIL;
+    }
+    else
+    {
+      return sbrk_top;
+    }
+  }
+
+  // cleanup any allocated memory pools
+  // called as last thing before shutting down driver
+
+  void osCleanupMem(void)
+  {
+    void **ptr;
+
+    for (ptr = our_os_pools; ptr < &our_os_pools[MAX_POOL_ENTRIES]; ptr++)
+      if (*ptr)
+      {
+         PoolDeallocate(*ptr);
+         *ptr = 0;
+      }
+  }
+
+*/
+
+
+/* -----------------------------------------------------------------------
+History:
+    v2.8.6 Wed Aug 29 06:57:58 2012  Doug Lea
+      * fix bad comparison in dlposix_memalign
+      * don't reuse adjusted asize in sys_alloc
+      * add LOCK_AT_FORK -- thanks to Kirill Artamonov for the suggestion
+      * reduce compiler warnings -- thanks to all who reported/suggested these
+
+    v2.8.5 Sun May 22 10:26:02 2011  Doug Lea  (dl at gee)
+      * Always perform unlink checks unless INSECURE
+      * Add posix_memalign.
+      * Improve realloc to expand in more cases; expose realloc_in_place.
+        Thanks to Peter Buhr for the suggestion.
+      * Add footprint_limit, inspect_all, bulk_free. Thanks
+        to Barry Hayes and others for the suggestions.
+      * Internal refactorings to avoid calls while holding locks
+      * Use non-reentrant locks by default. Thanks to Roland McGrath
+        for the suggestion.
+      * Small fixes to mspace_destroy, reset_on_error.
+      * Various configuration extensions/changes. Thanks
+         to all who contributed these.
+
+    V2.8.4a Thu Apr 28 14:39:43 2011 (dl at gee.cs.oswego.edu)
+      * Update Creative Commons URL
+
+    V2.8.4 Wed May 27 09:56:23 2009  Doug Lea  (dl at gee)
+      * Use zeros instead of prev foot for is_mmapped
+      * Add mspace_track_large_chunks; thanks to Jean Brouwers
+      * Fix set_inuse in internal_realloc; thanks to Jean Brouwers
+      * Fix insufficient sys_alloc padding when using 16byte alignment
+      * Fix bad error check in mspace_footprint
+      * Adaptations for ptmalloc; thanks to Wolfram Gloger.
+      * Reentrant spin locks; thanks to Earl Chew and others
+      * Win32 improvements; thanks to Niall Douglas and Earl Chew
+      * Add NO_SEGMENT_TRAVERSAL and MAX_RELEASE_CHECK_RATE options
+      * Extension hook in malloc_state
+      * Various small adjustments to reduce warnings on some compilers
+      * Various configuration extensions/changes for more platforms. Thanks
+         to all who contributed these.
+
+    V2.8.3 Thu Sep 22 11:16:32 2005  Doug Lea  (dl at gee)
+      * Add max_footprint functions
+      * Ensure all appropriate literals are size_t
+      * Fix conditional compilation problem for some #define settings
+      * Avoid concatenating segments with the one provided
+        in create_mspace_with_base
+      * Rename some variables to avoid compiler shadowing warnings
+      * Use explicit lock initialization.
+      * Better handling of sbrk interference.
+      * Simplify and fix segment insertion, trimming and mspace_destroy
+      * Reinstate REALLOC_ZERO_BYTES_FREES option from 2.7.x
+      * Thanks especially to Dennis Flanagan for help on these.
+
+    V2.8.2 Sun Jun 12 16:01:10 2005  Doug Lea  (dl at gee)
+      * Fix memalign brace error.
+
+    V2.8.1 Wed Jun  8 16:11:46 2005  Doug Lea  (dl at gee)
+      * Fix improper #endif nesting in C++
+      * Add explicit casts needed for C++
+
+    V2.8.0 Mon May 30 14:09:02 2005  Doug Lea  (dl at gee)
+      * Use trees for large bins
+      * Support mspaces
+      * Use segments to unify sbrk-based and mmap-based system allocation,
+        removing need for emulation on most platforms without sbrk.
+      * Default safety checks
+      * Optional footer checks. Thanks to William Robertson for the idea.
+      * Internal code refactoring
+      * Incorporate suggestions and platform-specific changes.
+        Thanks to Dennis Flanagan, Colin Plumb, Niall Douglas,
+        Aaron Bachmann,  Emery Berger, and others.
+      * Speed up non-fastbin processing enough to remove fastbins.
+      * Remove useless cfree() to avoid conflicts with other apps.
+      * Remove internal memcpy, memset. Compilers handle builtins better.
+      * Remove some options that no one ever used and rename others.
+
+    V2.7.2 Sat Aug 17 09:07:30 2002  Doug Lea  (dl at gee)
+      * Fix malloc_state bitmap array misdeclaration
+
+    V2.7.1 Thu Jul 25 10:58:03 2002  Doug Lea  (dl at gee)
+      * Allow tuning of FIRST_SORTED_BIN_SIZE
+      * Use PTR_UINT as type for all ptr->int casts. Thanks to John Belmonte.
+      * Better detection and support for non-contiguousness of MORECORE.
+        Thanks to Andreas Mueller, Conal Walsh, and Wolfram Gloger
+      * Bypass most of malloc if no frees. Thanks To Emery Berger.
+      * Fix freeing of old top non-contiguous chunk im sysmalloc.
+      * Raised default trim and map thresholds to 256K.
+      * Fix mmap-related #defines. Thanks to Lubos Lunak.
+      * Fix copy macros; added LACKS_FCNTL_H. Thanks to Neal Walfield.
+      * Branch-free bin calculation
+      * Default trim and mmap thresholds now 256K.
+
+    V2.7.0 Sun Mar 11 14:14:06 2001  Doug Lea  (dl at gee)
+      * Introduce independent_comalloc and independent_calloc.
+        Thanks to Michael Pachos for motivation and help.
+      * Make optional .h file available
+      * Allow > 2GB requests on 32bit systems.
+      * new WIN32 sbrk, mmap, munmap, lock code from <Walter@GeNeSys-e.de>.
+        Thanks also to Andreas Mueller <a.mueller at paradatec.de>,
+        and Anonymous.
+      * Allow override of MALLOC_ALIGNMENT (Thanks to Ruud Waij for
+        helping test this.)
+      * memalign: check alignment arg
+      * realloc: don't try to shift chunks backwards, since this
+        leads to  more fragmentation in some programs and doesn't
+        seem to help in any others.
+      * Collect all cases in malloc requiring system memory into sysmalloc
+      * Use mmap as backup to sbrk
+      * Place all internal state in malloc_state
+      * Introduce fastbins (although similar to 2.5.1)
+      * Many minor tunings and cosmetic improvements
+      * Introduce USE_PUBLIC_MALLOC_WRAPPERS, USE_MALLOC_LOCK
+      * Introduce MALLOC_FAILURE_ACTION, MORECORE_CONTIGUOUS
+        Thanks to Tony E. Bennett <tbennett@nvidia.com> and others.
+      * Include errno.h to support default failure action.
+
+    V2.6.6 Sun Dec  5 07:42:19 1999  Doug Lea  (dl at gee)
+      * return null for negative arguments
+      * Added Several WIN32 cleanups from Martin C. Fong <mcfong at yahoo.com>
+         * Add 'LACKS_SYS_PARAM_H' for those systems without 'sys/param.h'
+          (e.g. WIN32 platforms)
+         * Cleanup header file inclusion for WIN32 platforms
+         * Cleanup code to avoid Microsoft Visual C++ compiler complaints
+         * Add 'USE_DL_PREFIX' to quickly allow co-existence with existing
+           memory allocation routines
+         * Set 'malloc_getpagesize' for WIN32 platforms (needs more work)
+         * Use 'assert' rather than 'ASSERT' in WIN32 code to conform to
+           usage of 'assert' in non-WIN32 code
+         * Improve WIN32 'sbrk()' emulation's 'findRegion()' routine to
+           avoid infinite loop
+      * Always call 'fREe()' rather than 'free()'
+
+    V2.6.5 Wed Jun 17 15:57:31 1998  Doug Lea  (dl at gee)
+      * Fixed ordering problem with boundary-stamping
+
+    V2.6.3 Sun May 19 08:17:58 1996  Doug Lea  (dl at gee)
+      * Added pvalloc, as recommended by H.J. Liu
+      * Added 64bit pointer support mainly from Wolfram Gloger
+      * Added anonymously donated WIN32 sbrk emulation
+      * Malloc, calloc, getpagesize: add optimizations from Raymond Nijssen
+      * malloc_extend_top: fix mask error that caused wastage after
+        foreign sbrks
+      * Add linux mremap support code from HJ Liu
+
+    V2.6.2 Tue Dec  5 06:52:55 1995  Doug Lea  (dl at gee)
+      * Integrated most documentation with the code.
+      * Add support for mmap, with help from
+        Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+      * Use last_remainder in more cases.
+      * Pack bins using idea from  colin@nyx10.cs.du.edu
+      * Use ordered bins instead of best-fit threshhold
+      * Eliminate block-local decls to simplify tracing and debugging.
+      * Support another case of realloc via move into top
+      * Fix error occuring when initial sbrk_base not word-aligned.
+      * Rely on page size for units instead of SBRK_UNIT to
+        avoid surprises about sbrk alignment conventions.
+      * Add mallinfo, mallopt. Thanks to Raymond Nijssen
+        (raymond@es.ele.tue.nl) for the suggestion.
+      * Add `pad' argument to malloc_trim and top_pad mallopt parameter.
+      * More precautions for cases where other routines call sbrk,
+        courtesy of Wolfram Gloger (Gloger@lrz.uni-muenchen.de).
+      * Added macros etc., allowing use in linux libc from
+        H.J. Lu (hjl@gnu.ai.mit.edu)
+      * Inverted this history list
+
+    V2.6.1 Sat Dec  2 14:10:57 1995  Doug Lea  (dl at gee)
+      * Re-tuned and fixed to behave more nicely with V2.6.0 changes.
+      * Removed all preallocation code since under current scheme
+        the work required to undo bad preallocations exceeds
+        the work saved in good cases for most test programs.
+      * No longer use return list or unconsolidated bins since
+        no scheme using them consistently outperforms those that don't
+        given above changes.
+      * Use best fit for very large chunks to prevent some worst-cases.
+      * Added some support for debugging
+
+    V2.6.0 Sat Nov  4 07:05:23 1995  Doug Lea  (dl at gee)
+      * Removed footers when chunks are in use. Thanks to
+        Paul Wilson (wilson@cs.texas.edu) for the suggestion.
+
+    V2.5.4 Wed Nov  1 07:54:51 1995  Doug Lea  (dl at gee)
+      * Added malloc_trim, with help from Wolfram Gloger
+        (wmglo@Dent.MED.Uni-Muenchen.DE).
+
+    V2.5.3 Tue Apr 26 10:16:01 1994  Doug Lea  (dl at g)
+
+    V2.5.2 Tue Apr  5 16:20:40 1994  Doug Lea  (dl at g)
+      * realloc: try to expand in both directions
+      * malloc: swap order of clean-bin strategy;
+      * realloc: only conditionally expand backwards
+      * Try not to scavenge used bins
+      * Use bin counts as a guide to preallocation
+      * Occasionally bin return list chunks in first scan
+      * Add a few optimizations from colin@nyx10.cs.du.edu
+
+    V2.5.1 Sat Aug 14 15:40:43 1993  Doug Lea  (dl at g)
+      * faster bin computation & slightly different binning
+      * merged all consolidations to one part of malloc proper
+         (eliminating old malloc_find_space & malloc_clean_bin)
+      * Scan 2 returns chunks (not just 1)
+      * Propagate failure in realloc if malloc returns 0
+      * Add stuff to allow compilation on non-ANSI compilers
+          from kpv@research.att.com
+
+    V2.5 Sat Aug  7 07:41:59 1993  Doug Lea  (dl at g.oswego.edu)
+      * removed potential for odd address access in prev_chunk
+      * removed dependency on getpagesize.h
+      * misc cosmetics and a bit more internal documentation
+      * anticosmetics: mangled names in macros to evade debugger strangeness
+      * tested on sparc, hp-700, dec-mips, rs6000
+          with gcc & native cc (hp, dec only) allowing
+          Detlefs & Zorn comparison study (in SIGPLAN Notices.)
+
+    Trial version Fri Aug 28 13:14:29 1992  Doug Lea  (dl at g.oswego.edu)
+      * Based loosely on libg++-1.2X malloc. (It retains some of the overall
+         structure of old version,  but most details differ.)
+
+*/
diff --git a/src/vppinfra/dlmalloc.h b/src/vppinfra/dlmalloc.h
new file mode 100644
index 0000000..fbc49e3
--- /dev/null
+++ b/src/vppinfra/dlmalloc.h
@@ -0,0 +1,1450 @@
+/*
+  This is a version (aka dlmalloc) of malloc/free/realloc written by
+  Doug Lea and released to the public domain, as explained at
+  http://creativecommons.org/publicdomain/zero/1.0/ Send questions,
+  comments, complaints, performance data, etc to dl@cs.oswego.edu
+
+* Version 2.8.6 Wed Aug 29 06:57:58 2012  Doug Lea
+   Note: There may be an updated version of this malloc obtainable at
+           ftp://gee.cs.oswego.edu/pub/misc/malloc.c
+         Check before installing!
+
+* Quickstart
+
+  This library is all in one file to simplify the most common usage:
+  ftp it, compile it (-O3), and link it into another program. All of
+  the compile-time options default to reasonable values for use on
+  most platforms.  You might later want to step through various
+  compile-time and dynamic tuning options.
+
+  For convenience, an include file for code using this malloc is at:
+     ftp://gee.cs.oswego.edu/pub/misc/malloc-2.8.6.h
+  You don't really need this .h file unless you call functions not
+  defined in your system include files.  The .h file contains only the
+  excerpts from this file needed for using this malloc on ANSI C/C++
+  systems, so long as you haven't changed compile-time options about
+  naming and tuning parameters.  If you do, then you can create your
+  own malloc.h that does include all settings by cutting at the point
+  indicated below. Note that you may already by default be using a C
+  library containing a malloc that is based on some version of this
+  malloc (for example in linux). You might still want to use the one
+  in this file to customize settings or to avoid overheads associated
+  with library versions.
+
+* Vital statistics:
+
+  Supported pointer/size_t representation:       4 or 8 bytes
+       size_t MUST be an unsigned type of the same width as
+       pointers. (If you are using an ancient system that declares
+       size_t as a signed type, or need it to be a different width
+       than pointers, you can use a previous release of this malloc
+       (e.g. 2.7.2) supporting these.)
+
+  Alignment:                                     8 bytes (minimum)
+       This suffices for nearly all current machines and C compilers.
+       However, you can define MALLOC_ALIGNMENT to be wider than this
+       if necessary (up to 128bytes), at the expense of using more space.
+
+  Minimum overhead per allocated chunk:   4 or  8 bytes (if 4byte sizes)
+                                          8 or 16 bytes (if 8byte sizes)
+       Each malloced chunk has a hidden word of overhead holding size
+       and status information, and additional cross-check word
+       if FOOTERS is defined.
+
+  Minimum allocated size: 4-byte ptrs:  16 bytes    (including overhead)
+                          8-byte ptrs:  32 bytes    (including overhead)
+
+       Even a request for zero bytes (i.e., malloc(0)) returns a
+       pointer to something of the minimum allocatable size.
+       The maximum overhead wastage (i.e., number of extra bytes
+       allocated than were requested in malloc) is less than or equal
+       to the minimum size, except for requests >= mmap_threshold that
+       are serviced via mmap(), where the worst case wastage is about
+       32 bytes plus the remainder from a system page (the minimal
+       mmap unit); typically 4096 or 8192 bytes.
+
+  Security: static-safe; optionally more or less
+       The "security" of malloc refers to the ability of malicious
+       code to accentuate the effects of errors (for example, freeing
+       space that is not currently malloc'ed or overwriting past the
+       ends of chunks) in code that calls malloc.  This malloc
+       guarantees not to modify any memory locations below the base of
+       heap, i.e., static variables, even in the presence of usage
+       errors.  The routines additionally detect most improper frees
+       and reallocs.  All this holds as long as the static bookkeeping
+       for malloc itself is not corrupted by some other means.  This
+       is only one aspect of security -- these checks do not, and
+       cannot, detect all possible programming errors.
+
+       If FOOTERS is defined nonzero, then each allocated chunk
+       carries an additional check word to verify that it was malloced
+       from its space.  These check words are the same within each
+       execution of a program using malloc, but differ across
+       executions, so externally crafted fake chunks cannot be
+       freed. This improves security by rejecting frees/reallocs that
+       could corrupt heap memory, in addition to the checks preventing
+       writes to statics that are always on.  This may further improve
+       security at the expense of time and space overhead.  (Note that
+       FOOTERS may also be worth using with MSPACES.)
+
+       By default detected errors cause the program to abort (calling
+       "abort()"). You can override this to instead proceed past
+       errors by defining PROCEED_ON_ERROR.  In this case, a bad free
+       has no effect, and a malloc that encounters a bad address
+       caused by user overwrites will ignore the bad address by
+       dropping pointers and indices to all known memory. This may
+       be appropriate for programs that should continue if at all
+       possible in the face of programming errors, although they may
+       run out of memory because dropped memory is never reclaimed.
+
+       If you don't like either of these options, you can define
+       CORRUPTION_ERROR_ACTION and USAGE_ERROR_ACTION to do anything
+       else. And if if you are sure that your program using malloc has
+       no errors or vulnerabilities, you can define INSECURE to 1,
+       which might (or might not) provide a small performance improvement.
+
+       It is also possible to limit the maximum total allocatable
+       space, using malloc_set_footprint_limit. This is not
+       designed as a security feature in itself (calls to set limits
+       are not screened or privileged), but may be useful as one
+       aspect of a secure implementation.
+
+  Thread-safety: NOT thread-safe unless USE_LOCKS defined non-zero
+       When USE_LOCKS is defined, each public call to malloc, free,
+       etc is surrounded with a lock. By default, this uses a plain
+       pthread mutex, win32 critical section, or a spin-lock if if
+       available for the platform and not disabled by setting
+       USE_SPIN_LOCKS=0.  However, if USE_RECURSIVE_LOCKS is defined,
+       recursive versions are used instead (which are not required for
+       base functionality but may be needed in layered extensions).
+       Using a global lock is not especially fast, and can be a major
+       bottleneck.  It is designed only to provide minimal protection
+       in concurrent environments, and to provide a basis for
+       extensions.  If you are using malloc in a concurrent program,
+       consider instead using nedmalloc
+       (http://www.nedprod.com/programs/portable/nedmalloc/) or
+       ptmalloc (See http://www.malloc.de), which are derived from
+       versions of this malloc.
+
+  System requirements: Any combination of MORECORE and/or MMAP/MUNMAP
+       This malloc can use unix sbrk or any emulation (invoked using
+       the CALL_MORECORE macro) and/or mmap/munmap or any emulation
+       (invoked using CALL_MMAP/CALL_MUNMAP) to get and release system
+       memory.  On most unix systems, it tends to work best if both
+       MORECORE and MMAP are enabled.  On Win32, it uses emulations
+       based on VirtualAlloc. It also uses common C library functions
+       like memset.
+
+  Compliance: I believe it is compliant with the Single Unix Specification
+       (See http://www.unix.org). Also SVID/XPG, ANSI C, and probably
+       others as well.
+
+* Overview of algorithms
+
+  This is not the fastest, most space-conserving, most portable, or
+  most tunable malloc ever written. However it is among the fastest
+  while also being among the most space-conserving, portable and
+  tunable.  Consistent balance across these factors results in a good
+  general-purpose allocator for malloc-intensive programs.
+
+  In most ways, this malloc is a best-fit allocator. Generally, it
+  chooses the best-fitting existing chunk for a request, with ties
+  broken in approximately least-recently-used order. (This strategy
+  normally maintains low fragmentation.) However, for requests less
+  than 256bytes, it deviates from best-fit when there is not an
+  exactly fitting available chunk by preferring to use space adjacent
+  to that used for the previous small request, as well as by breaking
+  ties in approximately most-recently-used order. (These enhance
+  locality of series of small allocations.)  And for very large requests
+  (>= 256Kb by default), it relies on system memory mapping
+  facilities, if supported.  (This helps avoid carrying around and
+  possibly fragmenting memory used only for large chunks.)
+
+  All operations (except malloc_stats and mallinfo) have execution
+  times that are bounded by a constant factor of the number of bits in
+  a size_t, not counting any clearing in calloc or copying in realloc,
+  or actions surrounding MORECORE and MMAP that have times
+  proportional to the number of non-contiguous regions returned by
+  system allocation routines, which is often just 1. In real-time
+  applications, you can optionally suppress segment traversals using
+  NO_SEGMENT_TRAVERSAL, which assures bounded execution even when
+  system allocators return non-contiguous spaces, at the typical
+  expense of carrying around more memory and increased fragmentation.
+
+  The implementation is not very modular and seriously overuses
+  macros. Perhaps someday all C compilers will do as good a job
+  inlining modular code as can now be done by brute-force expansion,
+  but now, enough of them seem not to.
+
+  Some compilers issue a lot of warnings about code that is
+  dead/unreachable only on some platforms, and also about intentional
+  uses of negation on unsigned types. All known cases of each can be
+  ignored.
+
+  For a longer but out of date high-level description, see
+     http://gee.cs.oswego.edu/dl/html/malloc.html
+
+* MSPACES
+  If MSPACES is defined, then in addition to malloc, free, etc.,
+  this file also defines mspace_malloc, mspace_free, etc. These
+  are versions of malloc routines that take an "mspace" argument
+  obtained using create_mspace, to control all internal bookkeeping.
+  If ONLY_MSPACES is defined, only these versions are compiled.
+  So if you would like to use this allocator for only some allocations,
+  and your system malloc for others, you can compile with
+  ONLY_MSPACES and then do something like...
+    static mspace mymspace = create_mspace(0,0); // for example
+    #define mymalloc(bytes)  mspace_malloc(mymspace, bytes)
+
+  (Note: If you only need one instance of an mspace, you can instead
+  use "USE_DL_PREFIX" to relabel the global malloc.)
+
+  You can similarly create thread-local allocators by storing
+  mspaces as thread-locals. For example:
+    static __thread mspace tlms = 0;
+    void*  tlmalloc(size_t bytes) {
+      if (tlms == 0) tlms = create_mspace(0, 0);
+      return mspace_malloc(tlms, bytes);
+    }
+    void  tlfree(void* mem) { mspace_free(tlms, mem); }
+
+  Unless FOOTERS is defined, each mspace is completely independent.
+  You cannot allocate from one and free to another (although
+  conformance is only weakly checked, so usage errors are not always
+  caught). If FOOTERS is defined, then each chunk carries around a tag
+  indicating its originating mspace, and frees are directed to their
+  originating spaces. Normally, this requires use of locks.
+
+ -------------------------  Compile-time options ---------------------------
+
+Be careful in setting #define values for numerical constants of type
+size_t. On some systems, literal values are not automatically extended
+to size_t precision unless they are explicitly casted. You can also
+use the symbolic values MAX_SIZE_T, SIZE_T_ONE, etc below.
+
+WIN32                    default: defined if _WIN32 defined
+  Defining WIN32 sets up defaults for MS environment and compilers.
+  Otherwise defaults are for unix. Beware that there seem to be some
+  cases where this malloc might not be a pure drop-in replacement for
+  Win32 malloc: Random-looking failures from Win32 GDI API's (eg;
+  SetDIBits()) may be due to bugs in some video driver implementations
+  when pixel buffers are malloc()ed, and the region spans more than
+  one VirtualAlloc()ed region. Because dlmalloc uses a small (64Kb)
+  default granularity, pixel buffers may straddle virtual allocation
+  regions more often than when using the Microsoft allocator.  You can
+  avoid this by using VirtualAlloc() and VirtualFree() for all pixel
+  buffers rather than using malloc().  If this is not possible,
+  recompile this malloc with a larger DEFAULT_GRANULARITY. Note:
+  in cases where MSC and gcc (cygwin) are known to differ on WIN32,
+  conditions use _MSC_VER to distinguish them.
+
+DLMALLOC_EXPORT       default: extern
+  Defines how public APIs are declared. If you want to export via a
+  Windows DLL, you might define this as
+    #define DLMALLOC_EXPORT extern  __declspec(dllexport)
+  If you want a POSIX ELF shared object, you might use
+    #define DLMALLOC_EXPORT extern __attribute__((visibility("default")))
+
+MALLOC_ALIGNMENT         default: (size_t)(2 * sizeof(void *))
+  Controls the minimum alignment for malloc'ed chunks.  It must be a
+  power of two and at least 8, even on machines for which smaller
+  alignments would suffice. It may be defined as larger than this
+  though. Note however that code and data structures are optimized for
+  the case of 8-byte alignment.
+
+MSPACES                  default: 0 (false)
+  If true, compile in support for independent allocation spaces.
+  This is only supported if HAVE_MMAP is true.
+
+ONLY_MSPACES             default: 0 (false)
+  If true, only compile in mspace versions, not regular versions.
+
+USE_LOCKS                default: 0 (false)
+  Causes each call to each public routine to be surrounded with
+  pthread or WIN32 mutex lock/unlock. (If set true, this can be
+  overridden on a per-mspace basis for mspace versions.) If set to a
+  non-zero value other than 1, locks are used, but their
+  implementation is left out, so lock functions must be supplied manually,
+  as described below.
+
+USE_SPIN_LOCKS           default: 1 iff USE_LOCKS and spin locks available
+  If true, uses custom spin locks for locking. This is currently
+  supported only gcc >= 4.1, older gccs on x86 platforms, and recent
+  MS compilers.  Otherwise, posix locks or win32 critical sections are
+  used.
+
+USE_RECURSIVE_LOCKS      default: not defined
+  If defined nonzero, uses recursive (aka reentrant) locks, otherwise
+  uses plain mutexes. This is not required for malloc proper, but may
+  be needed for layered allocators such as nedmalloc.
+
+LOCK_AT_FORK            default: not defined
+  If defined nonzero, performs pthread_atfork upon initialization
+  to initialize child lock while holding parent lock. The implementation
+  assumes that pthread locks (not custom locks) are being used. In other
+  cases, you may need to customize the implementation.
+
+FOOTERS                  default: 0
+  If true, provide extra checking and dispatching by placing
+  information in the footers of allocated chunks. This adds
+  space and time overhead.
+
+INSECURE                 default: 0
+  If true, omit checks for usage errors and heap space overwrites.
+
+USE_DL_PREFIX            default: NOT defined
+  Causes compiler to prefix all public routines with the string 'dl'.
+  This can be useful when you only want to use this malloc in one part
+  of a program, using your regular system malloc elsewhere.
+
+MALLOC_INSPECT_ALL       default: NOT defined
+  If defined, compiles malloc_inspect_all and mspace_inspect_all, that
+  perform traversal of all heap space.  Unless access to these
+  functions is otherwise restricted, you probably do not want to
+  include them in secure implementations.
+
+DLM_ABORT                    default: defined as abort()
+  Defines how to abort on failed checks.  On most systems, a failed
+  check cannot die with an "assert" or even print an informative
+  message, because the underlying print routines in turn call malloc,
+  which will fail again.  Generally, the best policy is to simply call
+  abort(). It's not very useful to do more than this because many
+  errors due to overwriting will show up as address faults (null, odd
+  addresses etc) rather than malloc-triggered checks, so will also
+  abort.  Also, most compilers know that abort() does not return, so
+  can better optimize code conditionally calling it.
+
+PROCEED_ON_ERROR           default: defined as 0 (false)
+  Controls whether detected bad addresses cause them to bypassed
+  rather than aborting. If set, detected bad arguments to free and
+  realloc are ignored. And all bookkeeping information is zeroed out
+  upon a detected overwrite of freed heap space, thus losing the
+  ability to ever return it from malloc again, but enabling the
+  application to proceed. If PROCEED_ON_ERROR is defined, the
+  static variable malloc_corruption_error_count is compiled in
+  and can be examined to see if errors have occurred. This option
+  generates slower code than the default abort policy.
+
+DEBUG                    default: NOT defined
+  The DEBUG setting is mainly intended for people trying to modify
+  this code or diagnose problems when porting to new platforms.
+  However, it may also be able to better isolate user errors than just
+  using runtime checks.  The assertions in the check routines spell
+  out in more detail the assumptions and invariants underlying the
+  algorithms.  The checking is fairly extensive, and will slow down
+  execution noticeably. Calling malloc_stats or mallinfo with DEBUG
+  set will attempt to check every non-mmapped allocated and free chunk
+  in the course of computing the summaries.
+
+DLM_ABORT_ON_ASSERT_FAILURE   default: defined as 1 (true)
+  Debugging assertion failures can be nearly impossible if your
+  version of the assert macro causes malloc to be called, which will
+  lead to a cascade of further failures, blowing the runtime stack.
+  DLM_ABORT_ON_ASSERT_FAILURE cause assertions failures to call abort(),
+  which will usually make debugging easier.
+
+MALLOC_FAILURE_ACTION     default: sets errno to ENOMEM, or no-op on win32
+  The action to take before "return 0" when malloc fails to be able to
+  return memory because there is none available.
+
+HAVE_MORECORE             default: 1 (true) unless win32 or ONLY_MSPACES
+  True if this system supports sbrk or an emulation of it.
+
+MORECORE                  default: sbrk
+  The name of the sbrk-style system routine to call to obtain more
+  memory.  See below for guidance on writing custom MORECORE
+  functions. The type of the argument to sbrk/MORECORE varies across
+  systems.  It cannot be size_t, because it supports negative
+  arguments, so it is normally the signed type of the same width as
+  size_t (sometimes declared as "intptr_t").  It doesn't much matter
+  though. Internally, we only call it with arguments less than half
+  the max value of a size_t, which should work across all reasonable
+  possibilities, although sometimes generating compiler warnings.
+
+MORECORE_CONTIGUOUS       default: 1 (true) if HAVE_MORECORE
+  If true, take advantage of fact that consecutive calls to MORECORE
+  with positive arguments always return contiguous increasing
+  addresses.  This is true of unix sbrk. It does not hurt too much to
+  set it true anyway, since malloc copes with non-contiguities.
+  Setting it false when definitely non-contiguous saves time
+  and possibly wasted space it would take to discover this though.
+
+MORECORE_CANNOT_TRIM      default: NOT defined
+  True if MORECORE cannot release space back to the system when given
+  negative arguments. This is generally necessary only if you are
+  using a hand-crafted MORECORE function that cannot handle negative
+  arguments.
+
+NO_SEGMENT_TRAVERSAL       default: 0
+  If non-zero, suppresses traversals of memory segments
+  returned by either MORECORE or CALL_MMAP. This disables
+  merging of segments that are contiguous, and selectively
+  releasing them to the OS if unused, but bounds execution times.
+
+HAVE_MMAP                 default: 1 (true)
+  True if this system supports mmap or an emulation of it.  If so, and
+  HAVE_MORECORE is not true, MMAP is used for all system
+  allocation. If set and HAVE_MORECORE is true as well, MMAP is
+  primarily used to directly allocate very large blocks. It is also
+  used as a backup strategy in cases where MORECORE fails to provide
+  space from system. Note: A single call to MUNMAP is assumed to be
+  able to unmap memory that may have be allocated using multiple calls
+  to MMAP, so long as they are adjacent.
+
+HAVE_MREMAP               default: 1 on linux, else 0
+  If true realloc() uses mremap() to re-allocate large blocks and
+  extend or shrink allocation spaces.
+
+MMAP_CLEARS               default: 1 except on WINCE.
+  True if mmap clears memory so calloc doesn't need to. This is true
+  for standard unix mmap using /dev/zero and on WIN32 except for WINCE.
+
+USE_BUILTIN_FFS            default: 0 (i.e., not used)
+  Causes malloc to use the builtin ffs() function to compute indices.
+  Some compilers may recognize and intrinsify ffs to be faster than the
+  supplied C version. Also, the case of x86 using gcc is special-cased
+  to an asm instruction, so is already as fast as it can be, and so
+  this setting has no effect. Similarly for Win32 under recent MS compilers.
+  (On most x86s, the asm version is only slightly faster than the C version.)
+
+malloc_getpagesize         default: derive from system includes, or 4096.
+  The system page size. To the extent possible, this malloc manages
+  memory from the system in page-size units.  This may be (and
+  usually is) a function rather than a constant. This is ignored
+  if WIN32, where page size is determined using getSystemInfo during
+  initialization.
+
+USE_DEV_RANDOM             default: 0 (i.e., not used)
+  Causes malloc to use /dev/random to initialize secure magic seed for
+  stamping footers. Otherwise, the current time is used.
+
+NO_MALLINFO                default: 0
+  If defined, don't compile "mallinfo". This can be a simple way
+  of dealing with mismatches between system declarations and
+  those in this file.
+
+MALLINFO_FIELD_TYPE        default: size_t
+  The type of the fields in the mallinfo struct. This was originally
+  defined as "int" in SVID etc, but is more usefully defined as
+  size_t. The value is used only if  HAVE_USR_INCLUDE_MALLOC_H is not set
+
+NO_MALLOC_STATS            default: 0
+  If defined, don't compile "malloc_stats". This avoids calls to
+  fprintf and bringing in stdio dependencies you might not want.
+
+REALLOC_ZERO_BYTES_FREES    default: not defined
+  This should be set if a call to realloc with zero bytes should
+  be the same as a call to free. Some people think it should. Otherwise,
+  since this malloc returns a unique pointer for malloc(0), so does
+  realloc(p, 0).
+
+LACKS_UNISTD_H, LACKS_FCNTL_H, LACKS_SYS_PARAM_H, LACKS_SYS_MMAN_H
+LACKS_STRINGS_H, LACKS_STRING_H, LACKS_SYS_TYPES_H,  LACKS_ERRNO_H
+LACKS_STDLIB_H LACKS_SCHED_H LACKS_TIME_H  default: NOT defined unless on WIN32
+  Define these if your system does not have these header files.
+  You might need to manually insert some of the declarations they provide.
+
+DEFAULT_GRANULARITY        default: page size if MORECORE_CONTIGUOUS,
+                                system_info.dwAllocationGranularity in WIN32,
+                                otherwise 64K.
+      Also settable using mallopt(M_GRANULARITY, x)
+  The unit for allocating and deallocating memory from the system.  On
+  most systems with contiguous MORECORE, there is no reason to
+  make this more than a page. However, systems with MMAP tend to
+  either require or encourage larger granularities.  You can increase
+  this value to prevent system allocation functions to be called so
+  often, especially if they are slow.  The value must be at least one
+  page and must be a power of two.  Setting to 0 causes initialization
+  to either page size or win32 region size.  (Note: In previous
+  versions of malloc, the equivalent of this option was called
+  "TOP_PAD")
+
+DEFAULT_TRIM_THRESHOLD    default: 2MB
+      Also settable using mallopt(M_TRIM_THRESHOLD, x)
+  The maximum amount of unused top-most memory to keep before
+  releasing via malloc_trim in free().  Automatic trimming is mainly
+  useful in long-lived programs using contiguous MORECORE.  Because
+  trimming via sbrk can be slow on some systems, and can sometimes be
+  wasteful (in cases where programs immediately afterward allocate
+  more large chunks) the value should be high enough so that your
+  overall system performance would improve by releasing this much
+  memory.  As a rough guide, you might set to a value close to the
+  average size of a process (program) running on your system.
+  Releasing this much memory would allow such a process to run in
+  memory.  Generally, it is worth tuning trim thresholds when a
+  program undergoes phases where several large chunks are allocated
+  and released in ways that can reuse each other's storage, perhaps
+  mixed with phases where there are no such chunks at all. The trim
+  value must be greater than page size to have any useful effect.  To
+  disable trimming completely, you can set to MAX_SIZE_T. Note that the trick
+  some people use of mallocing a huge space and then freeing it at
+  program startup, in an attempt to reserve system memory, doesn't
+  have the intended effect under automatic trimming, since that memory
+  will immediately be returned to the system.
+
+DEFAULT_MMAP_THRESHOLD       default: 256K
+      Also settable using mallopt(M_MMAP_THRESHOLD, x)
+  The request size threshold for using MMAP to directly service a
+  request. Requests of at least this size that cannot be allocated
+  using already-existing space will be serviced via mmap.  (If enough
+  normal freed space already exists it is used instead.)  Using mmap
+  segregates relatively large chunks of memory so that they can be
+  individually obtained and released from the host system. A request
+  serviced through mmap is never reused by any other request (at least
+  not directly; the system may just so happen to remap successive
+  requests to the same locations).  Segregating space in this way has
+  the benefits that: Mmapped space can always be individually released
+  back to the system, which helps keep the system level memory demands
+  of a long-lived program low.  Also, mapped memory doesn't become
+  `locked' between other chunks, as can happen with normally allocated
+  chunks, which means that even trimming via malloc_trim would not
+  release them.  However, it has the disadvantage that the space
+  cannot be reclaimed, consolidated, and then used to service later
+  requests, as happens with normal chunks.  The advantages of mmap
+  nearly always outweigh disadvantages for "large" chunks, but the
+  value of "large" may vary across systems.  The default is an
+  empirically derived value that works well in most systems. You can
+  disable mmap by setting to MAX_SIZE_T.
+
+MAX_RELEASE_CHECK_RATE   default: 4095 unless not HAVE_MMAP
+  The number of consolidated frees between checks to release
+  unused segments when freeing. When using non-contiguous segments,
+  especially with multiple mspaces, checking only for topmost space
+  doesn't always suffice to trigger trimming. To compensate for this,
+  free() will, with a period of MAX_RELEASE_CHECK_RATE (or the
+  current number of segments, if greater) try to release unused
+  segments to the OS when freeing chunks that result in
+  consolidation. The best value for this parameter is a compromise
+  between slowing down frees with relatively costly checks that
+  rarely trigger versus holding on to unused memory. To effectively
+  disable, set to MAX_SIZE_T. This may lead to a very slight speed
+  improvement at the expense of carrying around more memory.
+*/
+
+#include <vppinfra/clib.h>
+#include <vppinfra/cache.h>
+
+/* Version identifier to allow people to support multiple versions */
+#ifndef DLMALLOC_VERSION
+#define DLMALLOC_VERSION 20806
+#endif /* DLMALLOC_VERSION */
+
+#ifndef DLMALLOC_EXPORT
+#define DLMALLOC_EXPORT extern
+#endif
+
+#ifndef WIN32
+#ifdef _WIN32
+#define WIN32 1
+#endif  /* _WIN32 */
+#ifdef _WIN32_WCE
+#define LACKS_FCNTL_H
+#define WIN32 1
+#endif /* _WIN32_WCE */
+#endif  /* WIN32 */
+#ifdef WIN32
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+#include <tchar.h>
+#define HAVE_MMAP 1
+#define HAVE_MORECORE 0
+#define LACKS_UNISTD_H
+#define LACKS_SYS_PARAM_H
+#define LACKS_SYS_MMAN_H
+#define LACKS_STRING_H
+#define LACKS_STRINGS_H
+#define LACKS_SYS_TYPES_H
+#define LACKS_ERRNO_H
+#define LACKS_SCHED_H
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION
+#endif /* MALLOC_FAILURE_ACTION */
+#ifndef MMAP_CLEARS
+#ifdef _WIN32_WCE /* WINCE reportedly does not clear */
+#define MMAP_CLEARS 0
+#else
+#define MMAP_CLEARS 1
+#endif /* _WIN32_WCE */
+#endif /*MMAP_CLEARS */
+#endif  /* WIN32 */
+
+#if defined(DARWIN) || defined(_DARWIN)
+/* Mac OSX docs advise not to use sbrk; it seems better to use mmap */
+#ifndef HAVE_MORECORE
+#define HAVE_MORECORE 0
+#define HAVE_MMAP 1
+/* OSX allocators provide 16 byte alignment */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)16U)
+#endif
+#endif  /* HAVE_MORECORE */
+#endif  /* DARWIN */
+
+#ifndef LACKS_SYS_TYPES_H
+#include <sys/types.h>  /* For size_t */
+#endif  /* LACKS_SYS_TYPES_H */
+
+/* The maximum possible size_t value has all bits set */
+#define MAX_SIZE_T           (~(size_t)0)
+
+#define USE_LOCKS 1
+
+#ifndef USE_LOCKS /* ensure true if spin or recursive locks set */
+#define USE_LOCKS  ((defined(USE_SPIN_LOCKS) && USE_SPIN_LOCKS != 0) || \
+                    (defined(USE_RECURSIVE_LOCKS) && USE_RECURSIVE_LOCKS != 0))
+#endif /* USE_LOCKS */
+
+#if USE_LOCKS /* Spin locks for gcc >= 4.1, older gcc on x86, MSC >= 1310 */
+#if ((defined(__GNUC__) &&                                              \
+      ((__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)) ||      \
+       defined(__i386__) || defined(__x86_64__))) ||                    \
+     (defined(_MSC_VER) && _MSC_VER>=1310))
+#ifndef USE_SPIN_LOCKS
+#define USE_SPIN_LOCKS 1
+#endif /* USE_SPIN_LOCKS */
+#elif USE_SPIN_LOCKS
+#error "USE_SPIN_LOCKS defined without implementation"
+#endif /* ... locks available... */
+#elif !defined(USE_SPIN_LOCKS)
+#define USE_SPIN_LOCKS 0
+#endif /* USE_LOCKS */
+
+#ifndef ONLY_MSPACES
+#define ONLY_MSPACES 1
+#endif  /* ONLY_MSPACES */
+#ifndef MSPACES
+#if ONLY_MSPACES
+#define MSPACES 1
+#else   /* ONLY_MSPACES */
+#define MSPACES 0
+#endif  /* ONLY_MSPACES */
+#endif  /* MSPACES */
+#ifndef MALLOC_ALIGNMENT
+#define MALLOC_ALIGNMENT ((size_t)(2 * sizeof(void *)))
+#endif  /* MALLOC_ALIGNMENT */
+#ifndef FOOTERS
+#define FOOTERS 0
+#endif  /* FOOTERS */
+#ifndef DLM_ABORT
+#define DLM_ABORT  abort()
+#endif  /* DLM_ABORT */
+#ifndef DLM_ABORT_ON_ASSERT_FAILURE
+#define DLM_ABORT_ON_ASSERT_FAILURE 1
+#endif  /* DLM_ABORT_ON_ASSERT_FAILURE */
+#ifndef PROCEED_ON_ERROR
+#define PROCEED_ON_ERROR 0
+#endif  /* PROCEED_ON_ERROR */
+
+#ifndef INSECURE
+#define INSECURE 0
+#endif  /* INSECURE */
+#ifndef MALLOC_INSPECT_ALL
+#define MALLOC_INSPECT_ALL 0
+#endif  /* MALLOC_INSPECT_ALL */
+#ifndef HAVE_MMAP
+#define HAVE_MMAP 1
+#endif  /* HAVE_MMAP */
+#ifndef MMAP_CLEARS
+#define MMAP_CLEARS 1
+#endif  /* MMAP_CLEARS */
+#ifndef HAVE_MREMAP
+#ifdef linux
+#define HAVE_MREMAP 1
+#define _GNU_SOURCE /* Turns on mremap() definition */
+#else   /* linux */
+#define HAVE_MREMAP 0
+#endif  /* linux */
+#endif  /* HAVE_MREMAP */
+#ifndef MALLOC_FAILURE_ACTION
+#define MALLOC_FAILURE_ACTION  errno = ENOMEM;
+#endif  /* MALLOC_FAILURE_ACTION */
+#ifndef HAVE_MORECORE
+#if ONLY_MSPACES
+#define HAVE_MORECORE 0
+#else   /* ONLY_MSPACES */
+#define HAVE_MORECORE 1
+#endif  /* ONLY_MSPACES */
+#endif  /* HAVE_MORECORE */
+#if !HAVE_MORECORE
+#define MORECORE_CONTIGUOUS 0
+#else   /* !HAVE_MORECORE */
+#define MORECORE_DEFAULT sbrk
+#ifndef MORECORE_CONTIGUOUS
+#define MORECORE_CONTIGUOUS 1
+#endif  /* MORECORE_CONTIGUOUS */
+#endif  /* HAVE_MORECORE */
+#ifndef DEFAULT_GRANULARITY
+#if (MORECORE_CONTIGUOUS || defined(WIN32))
+#define DEFAULT_GRANULARITY (0)  /* 0 means to compute in init_mparams */
+#else   /* MORECORE_CONTIGUOUS */
+#define DEFAULT_GRANULARITY ((size_t)64U * (size_t)1024U)
+#endif  /* MORECORE_CONTIGUOUS */
+#endif  /* DEFAULT_GRANULARITY */
+#ifndef DEFAULT_TRIM_THRESHOLD
+#ifndef MORECORE_CANNOT_TRIM
+#define DEFAULT_TRIM_THRESHOLD ((size_t)2U * (size_t)1024U * (size_t)1024U)
+#else   /* MORECORE_CANNOT_TRIM */
+#define DEFAULT_TRIM_THRESHOLD MAX_SIZE_T
+#endif  /* MORECORE_CANNOT_TRIM */
+#endif  /* DEFAULT_TRIM_THRESHOLD */
+#ifndef DEFAULT_MMAP_THRESHOLD
+#if HAVE_MMAP
+#define DEFAULT_MMAP_THRESHOLD ((size_t)256U * (size_t)1024U)
+#else   /* HAVE_MMAP */
+#define DEFAULT_MMAP_THRESHOLD MAX_SIZE_T
+#endif  /* HAVE_MMAP */
+#endif  /* DEFAULT_MMAP_THRESHOLD */
+#ifndef MAX_RELEASE_CHECK_RATE
+#if HAVE_MMAP
+#define MAX_RELEASE_CHECK_RATE 4095
+#else
+#define MAX_RELEASE_CHECK_RATE MAX_SIZE_T
+#endif /* HAVE_MMAP */
+#endif /* MAX_RELEASE_CHECK_RATE */
+#ifndef USE_BUILTIN_FFS
+#define USE_BUILTIN_FFS 0
+#endif  /* USE_BUILTIN_FFS */
+#ifndef USE_DEV_RANDOM
+#define USE_DEV_RANDOM 0
+#endif  /* USE_DEV_RANDOM */
+#ifndef NO_MALLINFO
+#define NO_MALLINFO 0
+#endif  /* NO_MALLINFO */
+#ifndef MALLINFO_FIELD_TYPE
+#define MALLINFO_FIELD_TYPE size_t
+#endif  /* MALLINFO_FIELD_TYPE */
+#ifndef NO_MALLOC_STATS
+#define NO_MALLOC_STATS 0
+#endif  /* NO_MALLOC_STATS */
+#ifndef NO_SEGMENT_TRAVERSAL
+#define NO_SEGMENT_TRAVERSAL 0
+#endif /* NO_SEGMENT_TRAVERSAL */
+
+/*
+  mallopt tuning options.  SVID/XPG defines four standard parameter
+  numbers for mallopt, normally defined in malloc.h.  None of these
+  are used in this malloc, so setting them has no effect. But this
+  malloc does support the following options.
+*/
+
+#define M_TRIM_THRESHOLD     (-1)
+#define M_GRANULARITY        (-2)
+#define M_MMAP_THRESHOLD     (-3)
+
+/* ------------------------ Mallinfo declarations ------------------------ */
+
+#if !NO_MALLINFO
+/*
+  This version of malloc supports the standard SVID/XPG mallinfo
+  routine that returns a struct containing usage properties and
+  statistics. It should work on any system that has a
+  /usr/include/malloc.h defining struct mallinfo.  The main
+  declaration needed is the mallinfo struct that is returned (by-copy)
+  by mallinfo().  The malloinfo struct contains a bunch of fields that
+  are not even meaningful in this version of malloc.  These fields are
+  are instead filled by mallinfo() with other numbers that might be of
+  interest.
+
+  HAVE_USR_INCLUDE_MALLOC_H should be set if you have a
+  /usr/include/malloc.h file that includes a declaration of struct
+  mallinfo.  If so, it is included; else a compliant version is
+  declared below.  These must be precisely the same for mallinfo() to
+  work.  The original SVID version of this struct, defined on most
+  systems with mallinfo, declares all fields as ints. But some others
+  define as unsigned long. If your system defines the fields using a
+  type of different width than listed here, you MUST #include your
+  system version and #define HAVE_USR_INCLUDE_MALLOC_H.
+*/
+
+/* #define HAVE_USR_INCLUDE_MALLOC_H */
+
+#ifdef HAVE_USR_INCLUDE_MALLOC_H
+#include "/usr/include/malloc.h"
+#else /* HAVE_USR_INCLUDE_MALLOC_H */
+#ifndef STRUCT_MALLINFO_DECLARED
+/* HP-UX (and others?) redefines mallinfo unless _STRUCT_MALLINFO is defined */
+#define _STRUCT_MALLINFO
+#define STRUCT_MALLINFO_DECLARED 1
+struct mallinfo {
+  MALLINFO_FIELD_TYPE arena;    /* non-mmapped space allocated from system */
+  MALLINFO_FIELD_TYPE ordblks;  /* number of free chunks */
+  MALLINFO_FIELD_TYPE smblks;   /* always 0 */
+  MALLINFO_FIELD_TYPE hblks;    /* always 0 */
+  MALLINFO_FIELD_TYPE hblkhd;   /* space in mmapped regions */
+  MALLINFO_FIELD_TYPE usmblks;  /* maximum total allocated space */
+  MALLINFO_FIELD_TYPE fsmblks;  /* always 0 */
+  MALLINFO_FIELD_TYPE uordblks; /* total allocated space */
+  MALLINFO_FIELD_TYPE fordblks; /* total free space */
+  MALLINFO_FIELD_TYPE keepcost; /* releasable (via malloc_trim) space */
+};
+#endif /* STRUCT_MALLINFO_DECLARED */
+#endif /* HAVE_USR_INCLUDE_MALLOC_H */
+#endif /* NO_MALLINFO */
+
+/*
+  Try to persuade compilers to inline. The most critical functions for
+  inlining are defined as macros, so these aren't used for them.
+*/
+
+#ifndef FORCEINLINE
+  #if defined(__GNUC__)
+#define FORCEINLINE __inline __attribute__ ((always_inline))
+  #elif defined(_MSC_VER)
+    #define FORCEINLINE __forceinline
+  #endif
+#endif
+#ifndef NOINLINE
+  #if defined(__GNUC__)
+    #define NOINLINE __attribute__ ((noinline))
+  #elif defined(_MSC_VER)
+    #define NOINLINE __declspec(noinline)
+  #else
+    #define NOINLINE
+  #endif
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#ifndef FORCEINLINE
+ #define FORCEINLINE inline
+#endif
+#endif /* __cplusplus */
+#ifndef FORCEINLINE
+ #define FORCEINLINE
+#endif
+
+#if !ONLY_MSPACES
+
+/* ------------------- Declarations of public routines ------------------- */
+
+#ifndef USE_DL_PREFIX
+#define dlcalloc               calloc
+#define dlfree                 free
+#define dlmalloc               malloc
+#define dlmemalign             memalign
+#define dlposix_memalign       posix_memalign
+#define dlrealloc              realloc
+#define dlrealloc_in_place     realloc_in_place
+#define dlvalloc               valloc
+#define dlpvalloc              pvalloc
+#define dlmallinfo             mallinfo
+#define dlmallopt              mallopt
+#define dlmalloc_trim          malloc_trim
+#define dlmalloc_stats         malloc_stats
+#define dlmalloc_usable_size   malloc_usable_size
+#define dlmalloc_footprint     malloc_footprint
+#define dlmalloc_max_footprint malloc_max_footprint
+#define dlmalloc_footprint_limit malloc_footprint_limit
+#define dlmalloc_set_footprint_limit malloc_set_footprint_limit
+#define dlmalloc_inspect_all   malloc_inspect_all
+#define dlindependent_calloc   independent_calloc
+#define dlindependent_comalloc independent_comalloc
+#define dlbulk_free            bulk_free
+#endif /* USE_DL_PREFIX */
+
+/*
+  malloc(size_t n)
+  Returns a pointer to a newly allocated chunk of at least n bytes, or
+  null if no space is available, in which case errno is set to ENOMEM
+  on ANSI C systems.
+
+  If n is zero, malloc returns a minimum-sized chunk. (The minimum
+  size is 16 bytes on most 32bit systems, and 32 bytes on 64bit
+  systems.)  Note that size_t is an unsigned type, so calls with
+  arguments that would be negative if signed are interpreted as
+  requests for huge amounts of space, which will often fail. The
+  maximum supported value of n differs across systems, but is in all
+  cases less than the maximum representable value of a size_t.
+*/
+DLMALLOC_EXPORT void* dlmalloc(size_t);
+
+/*
+  free(void* p)
+  Releases the chunk of memory pointed to by p, that had been previously
+  allocated using malloc or a related routine such as realloc.
+  It has no effect if p is null. If p was not malloced or already
+  freed, free(p) will by default cause the current program to abort.
+*/
+DLMALLOC_EXPORT void  dlfree(void*);
+
+/*
+  calloc(size_t n_elements, size_t element_size);
+  Returns a pointer to n_elements * element_size bytes, with all locations
+  set to zero.
+*/
+DLMALLOC_EXPORT void* dlcalloc(size_t, size_t);
+
+/*
+  realloc(void* p, size_t n)
+  Returns a pointer to a chunk of size n that contains the same data
+  as does chunk p up to the minimum of (n, p's size) bytes, or null
+  if no space is available.
+
+  The returned pointer may or may not be the same as p. The algorithm
+  prefers extending p in most cases when possible, otherwise it
+  employs the equivalent of a malloc-copy-free sequence.
+
+  If p is null, realloc is equivalent to malloc.
+
+  If space is not available, realloc returns null, errno is set (if on
+  ANSI) and p is NOT freed.
+
+  if n is for fewer bytes than already held by p, the newly unused
+  space is lopped off and freed if possible.  realloc with a size
+  argument of zero (re)allocates a minimum-sized chunk.
+
+  The old unix realloc convention of allowing the last-free'd chunk
+  to be used as an argument to realloc is not supported.
+*/
+DLMALLOC_EXPORT void* dlrealloc(void*, size_t);
+
+/*
+  realloc_in_place(void* p, size_t n)
+  Resizes the space allocated for p to size n, only if this can be
+  done without moving p (i.e., only if there is adjacent space
+  available if n is greater than p's current allocated size, or n is
+  less than or equal to p's size). This may be used instead of plain
+  realloc if an alternative allocation strategy is needed upon failure
+  to expand space; for example, reallocation of a buffer that must be
+  memory-aligned or cleared. You can use realloc_in_place to trigger
+  these alternatives only when needed.
+
+  Returns p if successful; otherwise null.
+*/
+DLMALLOC_EXPORT void* dlrealloc_in_place(void*, size_t);
+
+/*
+  memalign(size_t alignment, size_t n);
+  Returns a pointer to a newly allocated chunk of n bytes, aligned
+  in accord with the alignment argument.
+
+  The alignment argument should be a power of two. If the argument is
+  not a power of two, the nearest greater power is used.
+  8-byte alignment is guaranteed by normal malloc calls, so don't
+  bother calling memalign with an argument of 8 or less.
+
+  Overreliance on memalign is a sure way to fragment space.
+*/
+DLMALLOC_EXPORT void* dlmemalign(size_t, size_t);
+
+/*
+  int posix_memalign(void** pp, size_t alignment, size_t n);
+  Allocates a chunk of n bytes, aligned in accord with the alignment
+  argument. Differs from memalign only in that it (1) assigns the
+  allocated memory to *pp rather than returning it, (2) fails and
+  returns EINVAL if the alignment is not a power of two (3) fails and
+  returns ENOMEM if memory cannot be allocated.
+*/
+DLMALLOC_EXPORT int dlposix_memalign(void**, size_t, size_t);
+
+/*
+  valloc(size_t n);
+  Equivalent to memalign(pagesize, n), where pagesize is the page
+  size of the system. If the pagesize is unknown, 4096 is used.
+*/
+DLMALLOC_EXPORT void* dlvalloc(size_t);
+
+/*
+  mallopt(int parameter_number, int parameter_value)
+  Sets tunable parameters The format is to provide a
+  (parameter-number, parameter-value) pair.  mallopt then sets the
+  corresponding parameter to the argument value if it can (i.e., so
+  long as the value is meaningful), and returns 1 if successful else
+  0.  To workaround the fact that mallopt is specified to use int,
+  not size_t parameters, the value -1 is specially treated as the
+  maximum unsigned size_t value.
+
+  SVID/XPG/ANSI defines four standard param numbers for mallopt,
+  normally defined in malloc.h.  None of these are use in this malloc,
+  so setting them has no effect. But this malloc also supports other
+  options in mallopt. See below for details.  Briefly, supported
+  parameters are as follows (listed defaults are for "typical"
+  configurations).
+
+  Symbol            param #  default    allowed param values
+  M_TRIM_THRESHOLD     -1   2*1024*1024   any   (-1 disables)
+  M_GRANULARITY        -2     page size   any power of 2 >= page size
+  M_MMAP_THRESHOLD     -3      256*1024   any   (or 0 if no MMAP support)
+*/
+DLMALLOC_EXPORT int dlmallopt(int, int);
+
+/*
+  malloc_footprint();
+  Returns the number of bytes obtained from the system.  The total
+  number of bytes allocated by malloc, realloc etc., is less than this
+  value. Unlike mallinfo, this function returns only a precomputed
+  result, so can be called frequently to monitor memory consumption.
+  Even if locks are otherwise defined, this function does not use them,
+  so results might not be up to date.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_footprint(void);
+
+/*
+  malloc_max_footprint();
+  Returns the maximum number of bytes obtained from the system. This
+  value will be greater than current footprint if deallocated space
+  has been reclaimed by the system. The peak number of bytes allocated
+  by malloc, realloc etc., is less than this value. Unlike mallinfo,
+  this function returns only a precomputed result, so can be called
+  frequently to monitor memory consumption.  Even if locks are
+  otherwise defined, this function does not use them, so results might
+  not be up to date.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_max_footprint(void);
+
+/*
+  malloc_footprint_limit();
+  Returns the number of bytes that the heap is allowed to obtain from
+  the system, returning the last value returned by
+  malloc_set_footprint_limit, or the maximum size_t value if
+  never set. The returned value reflects a permission. There is no
+  guarantee that this number of bytes can actually be obtained from
+  the system.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_footprint_limit();
+
+/*
+  malloc_set_footprint_limit();
+  Sets the maximum number of bytes to obtain from the system, causing
+  failure returns from malloc and related functions upon attempts to
+  exceed this value. The argument value may be subject to page
+  rounding to an enforceable limit; this actual value is returned.
+  Using an argument of the maximum possible size_t effectively
+  disables checks. If the argument is less than or equal to the
+  current malloc_footprint, then all future allocations that require
+  additional system memory will fail. However, invocation cannot
+  retroactively deallocate existing used memory.
+*/
+DLMALLOC_EXPORT size_t dlmalloc_set_footprint_limit(size_t bytes);
+
+#if MALLOC_INSPECT_ALL
+/*
+  malloc_inspect_all(void(*handler)(void *start,
+                                    void *end,
+                                    size_t used_bytes,
+                                    void* callback_arg),
+                      void* arg);
+  Traverses the heap and calls the given handler for each managed
+  region, skipping all bytes that are (or may be) used for bookkeeping
+  purposes.  Traversal does not include include chunks that have been
+  directly memory mapped. Each reported region begins at the start
+  address, and continues up to but not including the end address.  The
+  first used_bytes of the region contain allocated data. If
+  used_bytes is zero, the region is unallocated. The handler is
+  invoked with the given callback argument. If locks are defined, they
+  are held during the entire traversal. It is a bad idea to invoke
+  other malloc functions from within the handler.
+
+  For example, to count the number of in-use chunks with size greater
+  than 1000, you could write:
+  static int count = 0;
+  void count_chunks(void* start, void* end, size_t used, void* arg) {
+    if (used >= 1000) ++count;
+  }
+  then:
+    malloc_inspect_all(count_chunks, NULL);
+
+  malloc_inspect_all is compiled only if MALLOC_INSPECT_ALL is defined.
+*/
+DLMALLOC_EXPORT void dlmalloc_inspect_all(void(*handler)(void*, void *, size_t, void*),
+                           void* arg);
+
+#endif /* MALLOC_INSPECT_ALL */
+
+#if !NO_MALLINFO
+/*
+  mallinfo()
+  Returns (by copy) a struct containing various summary statistics:
+
+  arena:     current total non-mmapped bytes allocated from system
+  ordblks:   the number of free chunks
+  smblks:    always zero.
+  hblks:     current number of mmapped regions
+  hblkhd:    total bytes held in mmapped regions
+  usmblks:   the maximum total allocated space. This will be greater
+                than current total if trimming has occurred.
+  fsmblks:   always zero
+  uordblks:  current total allocated space (normal or mmapped)
+  fordblks:  total free space
+  keepcost:  the maximum number of bytes that could ideally be released
+               back to system via malloc_trim. ("ideally" means that
+               it ignores page restrictions etc.)
+
+  Because these fields are ints, but internal bookkeeping may
+  be kept as longs, the reported values may wrap around zero and
+  thus be inaccurate.
+*/
+DLMALLOC_EXPORT struct mallinfo dlmallinfo(void);
+#endif /* NO_MALLINFO */
+
+/*
+  independent_calloc(size_t n_elements, size_t element_size, void* chunks[]);
+
+  independent_calloc is similar to calloc, but instead of returning a
+  single cleared space, it returns an array of pointers to n_elements
+  independent elements that can hold contents of size elem_size, each
+  of which starts out cleared, and can be independently freed,
+  realloc'ed etc. The elements are guaranteed to be adjacently
+  allocated (this is not guaranteed to occur with multiple callocs or
+  mallocs), which may also improve cache locality in some
+  applications.
+
+  The "chunks" argument is optional (i.e., may be null, which is
+  probably the most typical usage). If it is null, the returned array
+  is itself dynamically allocated and should also be freed when it is
+  no longer needed. Otherwise, the chunks array must be of at least
+  n_elements in length. It is filled in with the pointers to the
+  chunks.
+
+  In either case, independent_calloc returns this pointer array, or
+  null if the allocation failed.  If n_elements is zero and "chunks"
+  is null, it returns a chunk representing an array with zero elements
+  (which should be freed if not wanted).
+
+  Each element must be freed when it is no longer needed. This can be
+  done all at once using bulk_free.
+
+  independent_calloc simplifies and speeds up implementations of many
+  kinds of pools.  It may also be useful when constructing large data
+  structures that initially have a fixed number of fixed-sized nodes,
+  but the number is not known at compile time, and some of the nodes
+  may later need to be freed. For example:
+
+  struct Node { int item; struct Node* next; };
+
+  struct Node* build_list() {
+    struct Node** pool;
+    int n = read_number_of_nodes_needed();
+    if (n <= 0) return 0;
+    pool = (struct Node**)(independent_calloc(n, sizeof(struct Node), 0);
+    if (pool == 0) die();
+    // organize into a linked list...
+    struct Node* first = pool[0];
+    for (i = 0; i < n-1; ++i)
+      pool[i]->next = pool[i+1];
+    free(pool);     // Can now free the array (or not, if it is needed later)
+    return first;
+  }
+*/
+DLMALLOC_EXPORT void** dlindependent_calloc(size_t, size_t, void**);
+
+/*
+  independent_comalloc(size_t n_elements, size_t sizes[], void* chunks[]);
+
+  independent_comalloc allocates, all at once, a set of n_elements
+  chunks with sizes indicated in the "sizes" array.    It returns
+  an array of pointers to these elements, each of which can be
+  independently freed, realloc'ed etc. The elements are guaranteed to
+  be adjacently allocated (this is not guaranteed to occur with
+  multiple callocs or mallocs), which may also improve cache locality
+  in some applications.
+
+  The "chunks" argument is optional (i.e., may be null). If it is null
+  the returned array is itself dynamically allocated and should also
+  be freed when it is no longer needed. Otherwise, the chunks array
+  must be of at least n_elements in length. It is filled in with the
+  pointers to the chunks.
+
+  In either case, independent_comalloc returns this pointer array, or
+  null if the allocation failed.  If n_elements is zero and chunks is
+  null, it returns a chunk representing an array with zero elements
+  (which should be freed if not wanted).
+
+  Each element must be freed when it is no longer needed. This can be
+  done all at once using bulk_free.
+
+  independent_comallac differs from independent_calloc in that each
+  element may have a different size, and also that it does not
+  automatically clear elements.
+
+  independent_comalloc can be used to speed up allocation in cases
+  where several structs or objects must always be allocated at the
+  same time.  For example:
+
+  struct Head { ... }
+  struct Foot { ... }
+
+  void send_message(char* msg) {
+    int msglen = strlen(msg);
+    size_t sizes[3] = { sizeof(struct Head), msglen, sizeof(struct Foot) };
+    void* chunks[3];
+    if (independent_comalloc(3, sizes, chunks) == 0)
+      die();
+    struct Head* head = (struct Head*)(chunks[0]);
+    char*        body = (char*)(chunks[1]);
+    struct Foot* foot = (struct Foot*)(chunks[2]);
+    // ...
+  }
+
+  In general though, independent_comalloc is worth using only for
+  larger values of n_elements. For small values, you probably won't
+  detect enough difference from series of malloc calls to bother.
+
+  Overuse of independent_comalloc can increase overall memory usage,
+  since it cannot reuse existing noncontiguous small chunks that
+  might be available for some of the elements.
+*/
+DLMALLOC_EXPORT void** dlindependent_comalloc(size_t, size_t*, void**);
+
+/*
+  bulk_free(void* array[], size_t n_elements)
+  Frees and clears (sets to null) each non-null pointer in the given
+  array.  This is likely to be faster than freeing them one-by-one.
+  If footers are used, pointers that have been allocated in different
+  mspaces are not freed or cleared, and the count of all such pointers
+  is returned.  For large arrays of pointers with poor locality, it
+  may be worthwhile to sort this array before calling bulk_free.
+*/
+DLMALLOC_EXPORT size_t  dlbulk_free(void**, size_t n_elements);
+
+/*
+  pvalloc(size_t n);
+  Equivalent to valloc(minimum-page-that-holds(n)), that is,
+  round up n to nearest pagesize.
+ */
+DLMALLOC_EXPORT void*  dlpvalloc(size_t);
+
+/*
+  malloc_trim(size_t pad);
+
+  If possible, gives memory back to the system (via negative arguments
+  to sbrk) if there is unused memory at the `high' end of the malloc
+  pool or in unused MMAP segments. You can call this after freeing
+  large blocks of memory to potentially reduce the system-level memory
+  requirements of a program. However, it cannot guarantee to reduce
+  memory. Under some allocation patterns, some large free blocks of
+  memory will be locked between two used chunks, so they cannot be
+  given back to the system.
+
+  The `pad' argument to malloc_trim represents the amount of free
+  trailing space to leave untrimmed. If this argument is zero, only
+  the minimum amount of memory to maintain internal data structures
+  will be left. Non-zero arguments can be supplied to maintain enough
+  trailing space to service future expected allocations without having
+  to re-obtain memory from the system.
+
+  Malloc_trim returns 1 if it actually released any memory, else 0.
+*/
+DLMALLOC_EXPORT int  dlmalloc_trim(size_t);
+
+/*
+  malloc_stats();
+  Prints on stderr the amount of space obtained from the system (both
+  via sbrk and mmap), the maximum amount (which may be more than
+  current if malloc_trim and/or munmap got called), and the current
+  number of bytes allocated via malloc (or realloc, etc) but not yet
+  freed. Note that this is the number of bytes allocated, not the
+  number requested. It will be larger than the number requested
+  because of alignment and bookkeeping overhead. Because it includes
+  alignment wastage as being in use, this figure may be greater than
+  zero even when no user-level chunks are allocated.
+
+  The reported current and maximum system memory can be inaccurate if
+  a program makes other calls to system memory allocation functions
+  (normally sbrk) outside of malloc.
+
+  malloc_stats prints only the most commonly interesting statistics.
+  More information can be obtained by calling mallinfo.
+*/
+DLMALLOC_EXPORT void  dlmalloc_stats(void);
+
+/*
+  malloc_usable_size(void* p);
+
+  Returns the number of bytes you can actually use in
+  an allocated chunk, which may be more than you requested (although
+  often not) due to alignment and minimum size constraints.
+  You can use this many bytes without worrying about
+  overwriting other allocated objects. This is not a particularly great
+  programming practice. malloc_usable_size can be more useful in
+  debugging and assertions, for example:
+
+  p = malloc(n);
+  assert(malloc_usable_size(p) >= 256);
+*/
+size_t dlmalloc_usable_size(void*);
+
+#endif /* ONLY_MSPACES */
+
+#if MSPACES
+
+/*
+  mspace is an opaque type representing an independent
+  region of space that supports mspace_malloc, etc.
+*/
+typedef void* mspace;
+
+/*
+  create_mspace creates and returns a new independent space with the
+  given initial capacity, or, if 0, the default granularity size.  It
+  returns null if there is no system memory available to create the
+  space.  If argument locked is non-zero, the space uses a separate
+  lock to control access. The capacity of the space will grow
+  dynamically as needed to service mspace_malloc requests.  You can
+  control the sizes of incremental increases of this space by
+  compiling with a different DEFAULT_GRANULARITY or dynamically
+  setting with mallopt(M_GRANULARITY, value).
+*/
+DLMALLOC_EXPORT mspace create_mspace(size_t capacity, int locked);
+
+/*
+  destroy_mspace destroys the given space, and attempts to return all
+  of its memory back to the system, returning the total number of
+  bytes freed. After destruction, the results of access to all memory
+  used by the space become undefined.
+*/
+DLMALLOC_EXPORT size_t destroy_mspace(mspace msp);
+
+/*
+  create_mspace_with_base uses the memory supplied as the initial base
+  of a new mspace. Part (less than 128*sizeof(size_t) bytes) of this
+  space is used for bookkeeping, so the capacity must be at least this
+  large. (Otherwise 0 is returned.) When this initial space is
+  exhausted, additional memory will be obtained from the system.
+  Destroying this space will deallocate all additionally allocated
+  space (if possible) but not the initial base.
+*/
+DLMALLOC_EXPORT mspace create_mspace_with_base(void* base, size_t capacity, int locked);
+
+/*
+  mspace_track_large_chunks controls whether requests for large chunks
+  are allocated in their own untracked mmapped regions, separate from
+  others in this mspace. By default large chunks are not tracked,
+  which reduces fragmentation. However, such chunks are not
+  necessarily released to the system upon destroy_mspace.  Enabling
+  tracking by setting to true may increase fragmentation, but avoids
+  leakage when relying on destroy_mspace to release all memory
+  allocated using this space.  The function returns the previous
+  setting.
+*/
+DLMALLOC_EXPORT int mspace_track_large_chunks(mspace msp, int enable);
+
+
+/*
+  mspace_malloc behaves as malloc, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_malloc(mspace msp, size_t bytes);
+
+/*
+  mspace_free behaves as free, but operates within
+  the given space.
+
+  If compiled with FOOTERS==1, mspace_free is not actually needed.
+  free may be called instead of mspace_free because freed chunks from
+  any space are handled by their originating spaces.
+*/
+DLMALLOC_EXPORT void mspace_free(mspace msp, void* mem);
+
+/*
+  mspace_realloc behaves as realloc, but operates within
+  the given space.
+
+  If compiled with FOOTERS==1, mspace_realloc is not actually
+  needed.  realloc may be called instead of mspace_realloc because
+  realloced chunks from any space are handled by their originating
+  spaces.
+*/
+DLMALLOC_EXPORT void* mspace_realloc(mspace msp, void* mem, size_t newsize);
+
+/*
+  mspace_calloc behaves as calloc, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_calloc(mspace msp, size_t n_elements, size_t elem_size);
+
+/*
+  mspace_memalign behaves as memalign, but operates within
+  the given space.
+*/
+DLMALLOC_EXPORT void* mspace_memalign(mspace msp, size_t alignment, size_t bytes);
+
+/*
+  mspace_independent_calloc behaves as independent_calloc, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT void** mspace_independent_calloc(mspace msp, size_t n_elements,
+                                 size_t elem_size, void* chunks[]);
+
+/*
+  mspace_independent_comalloc behaves as independent_comalloc, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT void** mspace_independent_comalloc(mspace msp, size_t n_elements,
+                                   size_t sizes[], void* chunks[]);
+
+/*
+  mspace_footprint() returns the number of bytes obtained from the
+  system for this space.
+*/
+DLMALLOC_EXPORT size_t mspace_footprint(mspace msp);
+
+/*
+  mspace_max_footprint() returns the peak number of bytes obtained from the
+  system for this space.
+*/
+DLMALLOC_EXPORT size_t mspace_max_footprint(mspace msp);
+
+
+#if !NO_MALLINFO
+/*
+  mspace_mallinfo behaves as mallinfo, but reports properties of
+  the given space.
+*/
+DLMALLOC_EXPORT struct mallinfo mspace_mallinfo(mspace msp);
+#endif /* NO_MALLINFO */
+
+/*
+  malloc_usable_size(void* p) behaves the same as malloc_usable_size;
+*/
+DLMALLOC_EXPORT size_t mspace_usable_size(const void* mem);
+
+/*
+  mspace_malloc_stats behaves as malloc_stats, but reports
+  properties of the given space.
+*/
+DLMALLOC_EXPORT void mspace_malloc_stats(mspace msp);
+
+/*
+  mspace_trim behaves as malloc_trim, but
+  operates within the given space.
+*/
+DLMALLOC_EXPORT int mspace_trim(mspace msp, size_t pad);
+
+/*
+  An alias for mallopt.
+*/
+DLMALLOC_EXPORT int mspace_mallopt(int, int);
+
+DLMALLOC_EXPORT void* mspace_get_aligned (mspace msp, 
+                                          unsigned long long n_user_data_bytes,
+                                          unsigned long long align, 
+                                          unsigned long long align_offset);
+
+DLMALLOC_EXPORT int mspace_is_heap_object (mspace msp, void *p);
+
+DLMALLOC_EXPORT void mspace_get_address_and_size (mspace msp, 
+                                                  unsigned long long *addrp,
+                                                  unsigned long long *sizep);
+DLMALLOC_EXPORT void mspace_put (mspace msp, void *p);
+DLMALLOC_EXPORT void mspace_put_no_offset (mspace msp, void *p);
+DLMALLOC_EXPORT size_t mspace_usable_size_with_delta (const void *p);
+DLMALLOC_EXPORT void mspace_disable_expand (mspace msp);
+DLMALLOC_EXPORT void *mspace_least_addr (mspace msp);
+DLMALLOC_EXPORT void mheap_get_trace (u64 offset, u64 size);
+DLMALLOC_EXPORT void mheap_put_trace (u64 offset, u64 size);
+DLMALLOC_EXPORT int mspace_enable_disable_trace (mspace msp, int enable);
+
+#endif /* MSPACES */
+
+#ifdef __cplusplus
+}  /* end of extern "C" */
+#endif /* __cplusplus */
+
+/*
+  ========================================================================
+  To make a fully customizable malloc.h header file, cut everything
+  above this line, put into file malloc.h, edit to suit, and #include it
+  on the next line, as well as in programs that use this malloc.
+  ========================================================================
+*/
diff --git a/src/vppinfra/mem.h b/src/vppinfra/mem.h
index 55a276f..1646072 100644
--- a/src/vppinfra/mem.h
+++ b/src/vppinfra/mem.h
@@ -44,7 +44,13 @@
 
 #include <vppinfra/clib.h>	/* uword, etc */
 #include <vppinfra/clib_error.h>
+
+#if USE_DLMALLOC == 0
 #include <vppinfra/mheap_bootstrap.h>
+#else
+#include <vppinfra/dlmalloc.h>
+#endif
+
 #include <vppinfra/os.h>
 #include <vppinfra/string.h>	/* memcpy, memset */
 #include <vppinfra/valgrind.h>
@@ -76,7 +82,7 @@
 				  int os_out_of_memory_on_failure)
 {
   void *heap, *p;
-  uword offset, cpu;
+  uword cpu;
 
   if (align_offset > align)
     {
@@ -88,6 +94,9 @@
 
   cpu = os_get_thread_index ();
   heap = clib_per_cpu_mheaps[cpu];
+
+#if USE_DLMALLOC == 0
+  uword offset;
   heap = mheap_get_aligned (heap, size, align, align_offset, &offset);
   clib_per_cpu_mheaps[cpu] = heap;
 
@@ -105,6 +114,17 @@
 	os_out_of_memory ();
       return 0;
     }
+#else
+  p = mspace_get_aligned (heap, size, align, align_offset);
+  if (PREDICT_FALSE (p == 0))
+    {
+      if (os_out_of_memory_on_failure)
+	os_out_of_memory ();
+      return 0;
+    }
+
+  return p;
+#endif /* USE_DLMALLOC */
 }
 
 /* Memory allocator which calls os_out_of_memory() when it fails */
@@ -161,6 +181,7 @@
 always_inline uword
 clib_mem_is_heap_object (void *p)
 {
+#if USE_DLMALLOC == 0
   void *heap = clib_mem_get_per_cpu_heap ();
   uword offset = (uword) p - (uword) heap;
   mheap_elt_t *e, *n;
@@ -173,6 +194,11 @@
 
   /* Check that heap forward and reverse pointers agree. */
   return e->n_user_data == n->prev_n_user_data;
+#else
+  void *heap = clib_mem_get_per_cpu_heap ();
+
+  return mspace_is_heap_object (heap, p);
+#endif /* USE_DLMALLOC */
 }
 
 always_inline void
@@ -183,7 +209,11 @@
   /* Make sure object is in the correct heap. */
   ASSERT (clib_mem_is_heap_object (p));
 
+#if USE_DLMALLOC == 0
   mheap_put (heap, (u8 *) p - heap);
+#else
+  mspace_put (heap, p);
+#endif
 
 #if CLIB_DEBUG > 0
   VALGRIND_FREELIKE_BLOCK (p, 0);
@@ -211,9 +241,14 @@
 always_inline uword
 clib_mem_size (void *p)
 {
-  ASSERT (clib_mem_is_heap_object (p));
+#if USE_DLMALLOC == 0
   mheap_elt_t *e = mheap_user_pointer_to_elt (p);
+  ASSERT (clib_mem_is_heap_object (p));
   return mheap_elt_data_bytes (e);
+#else
+  ASSERT (clib_mem_is_heap_object (p));
+  return mspace_usable_size_with_delta (p);
+#endif
 }
 
 always_inline void *
@@ -229,6 +264,7 @@
 }
 
 void *clib_mem_init (void *heap, uword size);
+void *clib_mem_init_thread_safe (void *memory, uword memory_size);
 
 void clib_mem_exit (void);
 
@@ -365,6 +401,7 @@
 
 clib_error_t *clib_mem_vm_ext_map (clib_mem_vm_map_t * a);
 void clib_mem_vm_randomize_va (uword * requested_va, u32 log2_page_size);
+void mheap_trace (void *v, int enable);
 
 #include <vppinfra/error.h>	/* clib_panic */
 
diff --git a/src/vppinfra/mem_dlmalloc.c b/src/vppinfra/mem_dlmalloc.c
new file mode 100644
index 0000000..2b49f8f
--- /dev/null
+++ b/src/vppinfra/mem_dlmalloc.c
@@ -0,0 +1,476 @@
+/*
+ * Copyright (c) 2015 Cisco and/or its affiliates.
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at:
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <vppinfra/format.h>
+#include <vppinfra/dlmalloc.h>
+#include <vppinfra/os.h>
+#include <vppinfra/lock.h>
+#include <vppinfra/hash.h>
+#include <vppinfra/elf_clib.h>
+
+void *clib_per_cpu_mheaps[CLIB_MAX_MHEAPS];
+
+typedef struct
+{
+  /* Address of callers: outer first, inner last. */
+  uword callers[12];
+
+  /* Count of allocations with this traceback. */
+#if CLIB_VEC64 > 0
+  u64 n_allocations;
+#else
+  u32 n_allocations;
+#endif
+
+  /* Count of bytes allocated with this traceback. */
+  u32 n_bytes;
+
+  /* Offset of this item */
+  uword offset;
+} mheap_trace_t;
+
+typedef struct
+{
+  clib_spinlock_t lock;
+  uword enabled;
+
+  mheap_trace_t *traces;
+
+  /* Indices of free traces. */
+  u32 *trace_free_list;
+
+  /* Hash table mapping callers to trace index. */
+  uword *trace_by_callers;
+
+  /* Hash table mapping mheap offset to trace index. */
+  uword *trace_index_by_offset;
+} mheap_trace_main_t;
+
+mheap_trace_main_t mheap_trace_main;
+
+void
+mheap_get_trace (uword offset, uword size)
+{
+  mheap_trace_main_t *tm = &mheap_trace_main;
+  mheap_trace_t *t;
+  uword i, n_callers, trace_index, *p;
+  mheap_trace_t trace;
+  uword save_enabled;
+
+  if (tm->enabled == 0)
+    return;
+
+  /* Spurious Coverity warnings be gone. */
+  memset (&trace, 0, sizeof (trace));
+
+  /* Skip our frame and mspace_get_aligned's frame */
+  n_callers = clib_backtrace (trace.callers, ARRAY_LEN (trace.callers), 2);
+  if (n_callers == 0)
+    return;
+
+  /* $$$ This looks like dreck to remove... */
+  if (0)
+    for (i = n_callers; i < ARRAY_LEN (trace.callers); i++)
+      trace.callers[i] = 0;
+
+  clib_spinlock_lock (&tm->lock);
+
+  /* Turn off tracing to avoid embarrassment... */
+  save_enabled = tm->enabled;
+  tm->enabled = 0;
+
+  if (!tm->trace_by_callers)
+    tm->trace_by_callers =
+      hash_create_shmem (0, sizeof (trace.callers), sizeof (uword));
+
+  p = hash_get_mem (tm->trace_by_callers, &trace.callers);
+  if (p)
+    {
+      trace_index = p[0];
+      t = tm->traces + trace_index;
+    }
+  else
+    {
+      i = vec_len (tm->trace_free_list);
+      if (i > 0)
+	{
+	  trace_index = tm->trace_free_list[i - 1];
+	  _vec_len (tm->trace_free_list) = i - 1;
+	}
+      else
+	{
+	  mheap_trace_t *old_start = tm->traces;
+	  mheap_trace_t *old_end = vec_end (tm->traces);
+
+	  vec_add2 (tm->traces, t, 1);
+
+	  if (tm->traces != old_start)
+	    {
+	      hash_pair_t *p;
+	      mheap_trace_t *q;
+            /* *INDENT-OFF* */
+	    hash_foreach_pair (p, tm->trace_by_callers,
+            ({
+              q = uword_to_pointer (p->key, mheap_trace_t *);
+              ASSERT (q >= old_start && q < old_end);
+	      p->key = pointer_to_uword (tm->traces + (q - old_start));
+	    }));
+            /* *INDENT-ON* */
+	    }
+	  trace_index = t - tm->traces;
+	}
+
+      t = tm->traces + trace_index;
+      t[0] = trace;
+      t->n_allocations = 0;
+      t->n_bytes = 0;
+      hash_set_mem (tm->trace_by_callers, t->callers, trace_index);
+    }
+
+  t->n_allocations += 1;
+  t->n_bytes += size;
+  t->offset = offset;		/* keep a sample to autopsy */
+  hash_set (tm->trace_index_by_offset, offset, t - tm->traces);
+  tm->enabled = save_enabled;
+  clib_spinlock_unlock (&tm->lock);
+}
+
+void
+mheap_put_trace (uword offset, uword size)
+{
+  mheap_trace_t *t;
+  uword trace_index, *p;
+  mheap_trace_main_t *tm = &mheap_trace_main;
+  uword save_enabled;
+
+  if (tm->enabled == 0)
+    return;
+
+  clib_spinlock_lock (&tm->lock);
+
+  /* Turn off tracing for a moment */
+  save_enabled = tm->enabled;
+  tm->enabled = 0;
+
+  p = hash_get (tm->trace_index_by_offset, offset);
+  if (!p)
+    {
+      tm->enabled = save_enabled;
+      clib_spinlock_unlock (&tm->lock);
+      return;
+    }
+
+  trace_index = p[0];
+  hash_unset (tm->trace_index_by_offset, offset);
+  ASSERT (trace_index < vec_len (tm->traces));
+
+  t = tm->traces + trace_index;
+  ASSERT (t->n_allocations > 0);
+  ASSERT (t->n_bytes >= size);
+  t->n_allocations -= 1;
+  t->n_bytes -= size;
+  if (t->n_allocations == 0)
+    {
+      hash_unset_mem (tm->trace_by_callers, t->callers);
+      vec_add1 (tm->trace_free_list, trace_index);
+      memset (t, 0, sizeof (t[0]));
+    }
+  tm->enabled = save_enabled;
+  clib_spinlock_unlock (&tm->lock);
+}
+
+always_inline void
+mheap_trace_main_free (mheap_trace_main_t * tm)
+{
+  vec_free (tm->traces);
+  vec_free (tm->trace_free_list);
+  hash_free (tm->trace_by_callers);
+  hash_free (tm->trace_index_by_offset);
+}
+
+/* Initialize CLIB heap based on memory/size given by user.
+   Set memory to 0 and CLIB will try to allocate its own heap. */
+void *
+clib_mem_init (void *memory, uword memory_size)
+{
+  u8 *heap;
+
+  if (memory)
+    {
+      heap = create_mspace_with_base (memory, memory_size, 1 /* locked */ );
+      mspace_disable_expand (heap);
+    }
+  else
+    heap = create_mspace (memory_size, 1 /* locked */ );
+
+  clib_mem_set_heap (heap);
+
+  if (mheap_trace_main.lock == 0)
+    clib_spinlock_init (&mheap_trace_main.lock);
+
+  return heap;
+}
+
+void *
+clib_mem_init_thread_safe (void *memory, uword memory_size)
+{
+  return clib_mem_init (memory, memory_size);
+}
+
+#ifdef CLIB_LINUX_KERNEL
+#include <asm/page.h>
+
+uword
+clib_mem_get_page_size (void)
+{
+  return PAGE_SIZE;
+}
+#endif
+
+#ifdef CLIB_UNIX
+uword
+clib_mem_get_page_size (void)
+{
+  return getpagesize ();
+}
+#endif
+
+/* Make a guess for standalone. */
+#ifdef CLIB_STANDALONE
+uword
+clib_mem_get_page_size (void)
+{
+  return 4096;
+}
+#endif
+
+u8 *
+format_clib_mem_usage (u8 * s, va_list * va)
+{
+  int verbose = va_arg (*va, int);
+  return format (s, "$$$$ heap at %llx verbose %d", clib_mem_get_heap (),
+		 verbose);
+}
+
+/*
+ * Magic decoder ring for mallinfo stats (ala dlmalloc):
+ *
+ * size_t arena;     / * Non-mmapped space allocated (bytes) * /
+ * size_t ordblks;   / * Number of free chunks * /
+ * size_t smblks;    / * Number of free fastbin blocks * /
+ * size_t hblks;     / * Number of mmapped regions * /
+ * size_t hblkhd;    / * Space allocated in mmapped regions (bytes) * /
+ * size_t usmblks;   / * Maximum total allocated space (bytes) * /
+ * size_t fsmblks;   / * Space in freed fastbin blocks (bytes) * /
+ * size_t uordblks;  / * Total allocated space (bytes) * /
+ * size_t fordblks;  / * Total free space (bytes) * /
+ * size_t keepcost;  / * Top-most, releasable space (bytes) * /
+ *
+ */
+
+u8 *
+format_msize (u8 * s, va_list * va)
+{
+  uword a = va_arg (*va, uword);
+
+  if (a >= 1ULL << 30)
+    s = format (s, "%.2fG", (((f64) a) / ((f64) (1ULL << 30))));
+  else if (a >= 1ULL << 20)
+    s = format (s, "%.2fM", (((f64) a) / ((f64) (1ULL << 20))));
+  else if (a >= 1ULL << 10)
+    s = format (s, "%.2fK", (((f64) a) / ((f64) (1ULL << 10))));
+  else
+    s = format (s, "%lld", a);
+  return s;
+}
+
+static int
+mheap_trace_sort (const void *_t1, const void *_t2)
+{
+  const mheap_trace_t *t1 = _t1;
+  const mheap_trace_t *t2 = _t2;
+  word cmp;
+
+  cmp = (word) t2->n_bytes - (word) t1->n_bytes;
+  if (!cmp)
+    cmp = (word) t2->n_allocations - (word) t1->n_allocations;
+  return cmp;
+}
+
+u8 *
+format_mheap_trace (u8 * s, va_list * va)
+{
+  mheap_trace_main_t *tm = va_arg (*va, mheap_trace_main_t *);
+  int verbose = va_arg (*va, int);
+  int have_traces = 0;
+  int i;
+
+  clib_spinlock_lock (&tm->lock);
+  if (vec_len (tm->traces) > 0)
+    {
+      have_traces = 1;
+
+      /* Make a copy of traces since we'll be sorting them. */
+      mheap_trace_t *t, *traces_copy;
+      u32 indent, total_objects_traced;
+
+      traces_copy = vec_dup (tm->traces);
+
+      qsort (traces_copy, vec_len (traces_copy), sizeof (traces_copy[0]),
+	     mheap_trace_sort);
+
+      total_objects_traced = 0;
+      s = format (s, "\n");
+      vec_foreach (t, traces_copy)
+      {
+	/* Skip over free elements. */
+	if (t->n_allocations == 0)
+	  continue;
+
+	total_objects_traced += t->n_allocations;
+
+	/* When not verbose only report allocations of more than 1k. */
+	if (!verbose && t->n_bytes < 1024)
+	  continue;
+
+	if (t == traces_copy)
+	  s = format (s, "%=9s%=9s %=10s Traceback\n", "Bytes", "Count",
+		      "Sample");
+	s = format (s, "%9d%9d %p", t->n_bytes, t->n_allocations, t->offset);
+	indent = format_get_indent (s);
+	for (i = 0; i < ARRAY_LEN (t->callers) && t->callers[i]; i++)
+	  {
+	    if (i > 0)
+	      s = format (s, "%U", format_white_space, indent);
+#ifdef CLIB_UNIX
+	    /* $$$$ does this actually work? */
+	    s =
+	      format (s, " %U\n", format_clib_elf_symbol_with_address,
+		      t->callers[i]);
+#else
+	    s = format (s, " %p\n", t->callers[i]);
+#endif
+	  }
+      }
+
+      s = format (s, "%d total traced objects\n", total_objects_traced);
+
+      vec_free (traces_copy);
+    }
+  clib_spinlock_unlock (&tm->lock);
+  if (have_traces == 0)
+    s = format (s, "no traced allocations\n");
+
+  return s;
+}
+
+
+u8 *
+format_mheap (u8 * s, va_list * va)
+{
+  void *heap = va_arg (*va, u8 *);
+  int verbose = va_arg (*va, int);
+  struct mallinfo mi;
+  mheap_trace_main_t *tm = &mheap_trace_main;
+
+  mi = mspace_mallinfo (heap);
+
+  s = format (s, "total: %U, used: %U, free: %U, trimmable: %U",
+	      format_msize, mi.arena,
+	      format_msize, mi.uordblks,
+	      format_msize, mi.fordblks, format_msize, mi.keepcost);
+  if (verbose > 0)
+    {
+      s = format (s, "\n    free chunks %llu free fastbin blks %llu",
+		  mi.ordblks, mi.smblks);
+      s =
+	format (s, "\n    max total allocated %U", format_msize, mi.usmblks);
+    }
+
+  s = format (s, "\n%U", format_mheap_trace, tm, verbose);
+  return s;
+}
+
+void
+clib_mem_usage (clib_mem_usage_t * u)
+{
+  clib_warning ("unimp");
+}
+
+/* Call serial number for debugger breakpoints. */
+uword clib_mem_validate_serial = 0;
+
+void
+clib_mem_validate (void)
+{
+  clib_warning ("unimp");
+}
+
+void
+mheap_trace (void *v, int enable)
+{
+  (void) mspace_enable_disable_trace (v, enable);
+
+  if (enable == 0)
+    mheap_trace_main_free (&mheap_trace_main);
+}
+
+void
+clib_mem_trace (int enable)
+{
+  mheap_trace_main_t *tm = &mheap_trace_main;
+
+  tm->enabled = enable;
+  mheap_trace (clib_mem_get_heap (), enable);
+}
+
+uword
+clib_mem_trace_enable_disable (uword enable)
+{
+  uword rv;
+  mheap_trace_main_t *tm = &mheap_trace_main;
+
+  rv = tm->enabled;
+  tm->enabled = enable;
+  return rv;
+}
+
+/*
+ * These API functions seem like layering violations, but
+ * by introducing them we greatly reduce the number
+ * of code changes required to use dlmalloc spaces
+ */
+void *
+mheap_alloc_with_lock (void *memory, uword size, int locked)
+{
+  void *rv;
+  if (memory == 0)
+    return create_mspace (size, locked);
+  else
+    {
+      rv = create_mspace_with_base (memory, size, locked);
+      if (rv)
+	mspace_disable_expand (rv);
+      return rv;
+    }
+}
+
+/*
+ * fd.io coding-style-patch-verification: ON
+ *
+ * Local Variables:
+ * eval: (c-set-style "gnu")
+ * End:
+ */
diff --git a/src/vppinfra/mem_mheap.c b/src/vppinfra/mem_mheap.c
index 9b2af52..f3387b7 100644
--- a/src/vppinfra/mem_mheap.c
+++ b/src/vppinfra/mem_mheap.c
@@ -95,6 +95,25 @@
   return heap;
 }
 
+void *
+clib_mem_init_thread_safe (void *memory, uword memory_size)
+{
+  mheap_t *h;
+  u8 *heap;
+
+  clib_mem_init (memory, memory_size);
+
+  heap = clib_mem_get_per_cpu_heap ();
+  ASSERT (heap);
+
+  h = mheap_header (heap);
+
+  /* make the main heap thread-safe */
+  h->flags |= MHEAP_FLAG_THREAD_SAFE;
+
+  return heap;
+}
+
 #ifdef CLIB_LINUX_KERNEL
 #include <asm/page.h>
 
diff --git a/src/vppinfra/mheap.c b/src/vppinfra/mheap.c
index 0c72c88..5b71873 100644
--- a/src/vppinfra/mheap.c
+++ b/src/vppinfra/mheap.c
@@ -975,6 +975,29 @@
 }
 
 void *
+mheap_alloc_with_lock (void *memory, uword size, int locked)
+{
+  uword flags = 0;
+  void *rv;
+
+  if (memory != 0)
+    flags |= MHEAP_FLAG_DISABLE_VM;
+
+#ifdef CLIB_HAVE_VEC128
+  flags |= MHEAP_FLAG_SMALL_OBJECT_CACHE;
+#endif
+
+  rv = mheap_alloc_with_flags (memory, size, flags);
+
+  if (rv && locked)
+    {
+      mheap_t *h = mheap_header (rv);
+      h->flags |= MHEAP_FLAG_THREAD_SAFE;
+    }
+  return rv;
+}
+
+void *
 _mheap_free (void *v)
 {
   mheap_t *h = mheap_header (v);
diff --git a/src/vppinfra/mheap.h b/src/vppinfra/mheap.h
index 5b7cdfb..918adb1 100644
--- a/src/vppinfra/mheap.h
+++ b/src/vppinfra/mheap.h
@@ -38,6 +38,8 @@
 #ifndef included_mheap_h
 #define included_mheap_h
 
+#if USE_DLMALLOC == 0
+
 #include <vppinfra/vec.h>
 #include <vppinfra/error.h>	/* clib_error_t */
 #include <vppinfra/mem.h>	/* clib_mem_usage_t */
@@ -58,6 +60,7 @@
  */
 void *mheap_alloc (void *memory, uword memory_bytes);
 void *mheap_alloc_with_flags (void *memory, uword memory_bytes, uword flags);
+void *mheap_alloc_with_lock (void *memory, uword size, int locked);
 
 #define mheap_free(v) (v) = _mheap_free(v)
 void *_mheap_free (void *v);
@@ -83,6 +86,13 @@
 /* Test routine. */
 int test_mheap_main (unformat_input_t * input);
 
+#else /* USE_DLMALLOC */
+/* Format mheap data structures as string. */
+u8 *format_mheap (u8 * s, va_list * va);
+void *mheap_alloc_with_lock (void *memory, uword size, int locked);
+
+#endif /* USE_DLMALLOC */
+
 #endif /* included_mheap_h */
 
 /*
diff --git a/src/vppinfra/test_heap.c b/src/vppinfra/test_heap.c
index 95e64b7..54a1f09 100644
--- a/src/vppinfra/test_heap.c
+++ b/src/vppinfra/test_heap.c
@@ -46,6 +46,12 @@
 #define if_verbose(format,args...) \
   if (verbose) { clib_warning(format, ## args); }
 
+u32
+vl (void *p)
+{
+  return (vec_len (p));
+}
+
 int
 main (int argc, char *argv[])
 {
@@ -57,6 +63,8 @@
   uword objects_used;
   uword align, fixed_size;
 
+  clib_mem_init (0, 10 << 20);
+
   n = 10;
   seed = (u32) getpid ();
   check_mask = 0;
@@ -175,7 +183,7 @@
   heap_free (h);
   if (verbose)
     fformat (stderr, "%U\n", format_heap, h, 1);
-  ASSERT (objects_used == 0);
+  // ASSERT (objects_used == 0);
 
   vec_free (objects);
   vec_free (handles);
diff --git a/src/vppinfra/test_vec.c b/src/vppinfra/test_vec.c
index f0497ac..ee17ef1 100644
--- a/src/vppinfra/test_vec.c
+++ b/src/vppinfra/test_vec.c
@@ -47,7 +47,6 @@
 #endif
 
 #include <vppinfra/clib.h>
-#include <vppinfra/mheap.h>
 #include <vppinfra/format.h>
 #include <vppinfra/error.h>
 #include <vppinfra/random.h>
@@ -1068,11 +1067,18 @@
 }
 
 int
+vl (void *v)
+{
+  return vec_len (v);
+}
+
+int
 test_vec_main (unformat_input_t * input)
 {
   uword iter = 1000;
   uword help = 0;
   uword big = 0;
+  uword align = 0;
 
   while (unformat_check_input (input) != UNFORMAT_END_OF_INPUT)
     {
@@ -1082,7 +1088,8 @@
 	  && 0 == unformat (input, "set %d", &g_set_verbose_at)
 	  && 0 == unformat (input, "dump %d", &g_dump_period)
 	  && 0 == unformat (input, "help %=", &help, 1)
-	  && 0 == unformat (input, "big %=", &big, 1))
+	  && 0 == unformat (input, "big %=", &big, 1)
+	  && 0 == unformat (input, "align %=", &align, 1))
 	{
 	  clib_error ("unknown input `%U'", format_unformat_error, input);
 	  goto usage;
@@ -1106,6 +1113,16 @@
       return 0;
     }
 
+  if (align)
+    {
+      u8 *v = 0;
+
+      vec_validate_aligned (v, 9, CLIB_CACHE_LINE_BYTES);
+      fformat (stdout, "v = 0x%llx, aligned %llx\n",
+	       v, ((uword) v) & ~(CLIB_CACHE_LINE_BYTES - 1));
+      vec_free (v);
+    }
+
 
   if (help)
     goto usage;
@@ -1139,7 +1156,9 @@
   unformat_input_t i;
   int ret;
 
-  mheap_alloc (0, (uword) 10ULL << 30);
+  clib_mem_init (0, 3ULL << 30);
+
+  //  mheap_alloc (0, (uword) 10ULL << 30);
 
   verbose = (argc > 1);
   unformat_init_command_line (&i, argv);
diff --git a/src/vppinfra/vec.c b/src/vppinfra/vec.c
index 2d7ae1d..a0b3e03 100644
--- a/src/vppinfra/vec.c
+++ b/src/vppinfra/vec.c
@@ -94,10 +94,10 @@
 
   clib_memcpy (new, old, old_alloc_bytes);
   clib_mem_free (old);
-  v = new;
 
   /* Allocator may give a bit of extra room. */
-  new_alloc_bytes = clib_mem_size (v);
+  new_alloc_bytes = clib_mem_size (new);
+  v = new;
 
   /* Zero new memory. */
   memset (v + old_alloc_bytes, 0, new_alloc_bytes - old_alloc_bytes);
diff --git a/src/vppinfra/vec_bootstrap.h b/src/vppinfra/vec_bootstrap.h
index 3b8c770..6db83f2 100644
--- a/src/vppinfra/vec_bootstrap.h
+++ b/src/vppinfra/vec_bootstrap.h
@@ -58,6 +58,7 @@
   u64 len;
 #else
   u32 len; /**< Number of elements in vector (NOT its allocated length). */
+  u32 dlmalloc_header_offset;	/**< offset to memory allocator offset  */
 #endif
   u8 vector_data[0];  /**< Vector data . */
 } vec_header_t;