Library Jemalloc updated to 5.0.1 (#721)

121 files changed, 28813 insertions, 8884 deletions

diff --git a/modules/worldengine/deps/PackageList.txt b/modules/worldengine/deps/PackageList.txt
index 1727e4ea35..30fcb8dbab 100644
--- a/modules/worldengine/deps/PackageList.txt
+++ b/modules/worldengine/deps/PackageList.txt
@@ -14,7 +14,7 @@ G3D (a commercial-grade C++ 3D engine available as Open Source (BSD License)
 
 jemalloc (a general-purpose scalable concurrent malloc-implementation)
   http://www.canonware.com/jemalloc/
-  Version: 3.5.1
+  Version: 5.0.1
   
 libMPQ (a library for reading MPQ files)
   https://libmpq.org/
diff --git a/modules/worldengine/deps/jemalloc/CMakeLists.txt b/modules/worldengine/deps/jemalloc/CMakeLists.txt
index fe976cb6ca..712051ca34 100644
--- a/modules/worldengine/deps/jemalloc/CMakeLists.txt
+++ b/modules/worldengine/deps/jemalloc/CMakeLists.txt
@@ -1,4 +1,4 @@
-# Copyright (C)
+# Copyright (C) 2008-2017 TrinityCore <http://www.trinitycore.org/>
 #
 # This file is free software; as a special exception the author gives
 # unlimited permission to copy and/or distribute it, with or without
@@ -8,47 +8,56 @@
 # WITHOUT ANY WARRANTY, to the extent permitted by law; without even the
 # implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 
-# We need to generate the jemalloc_def.h header based on platform-specific settings
-if (PLATFORM EQUAL 32)
-  set(JEM_SIZEDEF 2)
-  set(JEM_TLSMODEL)
-else()
-  set(JEM_SIZEDEF 3)
-  set(JEM_TLSMODEL "__attribute__\(\(tls_model\(\"initial-exec\"\)\)\)")
-endif()
+  # We need to generate the jemalloc_def.h header based on platform-specific settings
+  if (PLATFORM EQUAL 32)
+    set(JEM_SIZEDEF 2)
+    set(JEM_TLSMODEL)
+	set(JEM_VADDRBITS 32)
+  else()
+    set(JEM_SIZEDEF 3)
+    set(JEM_TLSMODEL "__attribute__\(\(tls_model\(\"initial-exec\"\)\)\)")
+	set(JEM_VADDRBITS 48)
+  endif()
 
-# Create the header, so we can use it
-configure_file(
-  "${CMAKE_SOURCE_DIR}/modules/worldengine/deps/jemalloc/jemalloc_defs.h.in.cmake"
-  "${BUILDDIR}/jemalloc_defs.h"
-  @ONLY
-)
+  # Create the header, so we can use it
+  configure_file(
+    "${CMAKE_SOURCE_DIR}/modules/worldengine/deps/jemalloc/jemalloc_internal_defs.h.in.cmake"
+    "${BUILDDIR}/jemalloc_internal_defs.h"
+    @ONLY
+  )
 
-# Done, let's continue
-set(jemalloc_STAT_SRC
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/arena.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/atomic.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/base.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/bitmap.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/chunk.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/chunk_dss.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/chunk_mmap.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/ckh.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/ctl.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/extent.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/hash.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/huge.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/jemalloc.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/mb.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/mutex.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/prof.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/quarantine.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/rtree.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/stats.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/tcache.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/tsd.c
-  ${CMAKE_CURRENT_SOURCE_DIR}/src/util.c
-)
+  # Done, let's continue
+  set(jemalloc_STAT_SRC
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/arena.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/background_thread.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/base.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/bitmap.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/ckh.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/ctl.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/extent.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/extent_dss.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/extent_mmap.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/hash.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/hooks.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/jemalloc.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/jemalloc_cpp.cpp
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/large.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/malloc_io.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/mutex.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/mutex_pool.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/nstime.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/pages.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/prng.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/prof.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/rtree.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/spin.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/stats.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/sz.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/tcache.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/ticker.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/tsd.c
+    ${CMAKE_CURRENT_SOURCE_DIR}/src/witness.c
+  )
 
 include_directories(
   ${BUILDDIR}/
@@ -58,3 +67,12 @@ include_directories(
 add_definitions(-D_GNU_SOURCE -D_REENTRANT)
 
 add_library(jemalloc STATIC ${jemalloc_STAT_SRC})
+
+target_link_libraries(jemalloc
+    PUBLIC
+	  ${CMAKE_DL_LIBS})
+      
+set_target_properties(jemalloc
+    PROPERTIES
+      FOLDER
+        "deps")
diff --git a/modules/worldengine/deps/jemalloc/COPYING b/modules/worldengine/deps/jemalloc/COPYING
index bdda0feb9e..e308632a81 100644
--- a/modules/worldengine/deps/jemalloc/COPYING
+++ b/modules/worldengine/deps/jemalloc/COPYING
@@ -1,10 +1,10 @@
 Unless otherwise specified, files in the jemalloc source distribution are
 subject to the following license:
 --------------------------------------------------------------------------------
-Copyright (C) 2002-2014 Jason Evans <jasone@canonware.com>.
+Copyright (C) 2002-2017 Jason Evans <jasone@canonware.com>.
 All rights reserved.
 Copyright (C) 2007-2012 Mozilla Foundation.  All rights reserved.
-Copyright (C) 2009-2014 Facebook, Inc.  All rights reserved.
+Copyright (C) 2009-2017 Facebook, Inc.  All rights reserved.
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:
diff --git a/modules/worldengine/deps/jemalloc/ChangeLog b/modules/worldengine/deps/jemalloc/ChangeLog
index d56ee999e6..ee1b7ead39 100644
--- a/modules/worldengine/deps/jemalloc/ChangeLog
+++ b/modules/worldengine/deps/jemalloc/ChangeLog
@@ -1,10 +1,727 @@
 Following are change highlights associated with official releases.  Important
-bug fixes are all mentioned, but internal enhancements are omitted here for
-brevity (even though they are more fun to write about).  Much more detail can be
-found in the git revision history:
+bug fixes are all mentioned, but some internal enhancements are omitted here for
+brevity.  Much more detail can be found in the git revision history:
 
     https://github.com/jemalloc/jemalloc
 
+* 5.0.1 (July 1, 2017)
+
+  This bugfix release fixes several issues, most of which are obscure enough
+  that typical applications are not impacted.
+
+  Bug fixes:
+  - Update decay->nunpurged before purging, in order to avoid potential update
+    races and subsequent incorrect purging volume.  (@interwq)
+  - Only abort on dlsym(3) error if the failure impacts an enabled feature (lazy
+    locking and/or background threads).  This mitigates an initialization
+    failure bug for which we still do not have a clear reproduction test case.
+    (@interwq)
+  - Modify tsd management so that it neither crashes nor leaks if a thread's
+    only allocation activity is to call free() after TLS destructors have been
+    executed.  This behavior was observed when operating with GNU libc, and is
+    unlikely to be an issue with other libc implementations.  (@interwq)
+  - Mask signals during background thread creation.  This prevents signals from
+    being inadvertently delivered to background threads.  (@jasone,
+    @davidgoldblatt, @interwq)
+  - Avoid inactivity checks within background threads, in order to prevent
+    recursive mutex acquisition.  (@interwq)
+  - Fix extent_grow_retained() to use the specified hooks when the
+    arena.<i>.extent_hooks mallctl is used to override the default hooks.
+    (@interwq)
+  - Add missing reentrancy support for custom extent hooks which allocate.
+    (@interwq)
+  - Post-fork(2), re-initialize the list of tcaches associated with each arena
+    to contain no tcaches except the forking thread's.  (@interwq)
+  - Add missing post-fork(2) mutex reinitialization for extent_grow_mtx.  This
+    fixes potential deadlocks after fork(2).  (@interwq)
+  - Enforce minimum autoconf version (currently 2.68), since 2.63 is known to
+    generate corrupt configure scripts.  (@jasone)
+  - Ensure that the configured page size (--with-lg-page) is no larger than the
+    configured huge page size (--with-lg-hugepage).  (@jasone)
+
+* 5.0.0 (June 13, 2017)
+
+  Unlike all previous jemalloc releases, this release does not use naturally
+  aligned "chunks" for virtual memory management, and instead uses page-aligned
+  "extents".  This change has few externally visible effects, but the internal
+  impacts are... extensive.  Many other internal changes combine to make this
+  the most cohesively designed version of jemalloc so far, with ample
+  opportunity for further enhancements.
+
+  Continuous integration is now an integral aspect of development thanks to the
+  efforts of @davidtgoldblatt, and the dev branch tends to remain reasonably
+  stable on the tested platforms (Linux, FreeBSD, macOS, and Windows).  As a
+  side effect the official release frequency may decrease over time.
+
+  New features:
+  - Implement optional per-CPU arena support; threads choose which arena to use
+    based on current CPU rather than on fixed thread-->arena associations.
+    (@interwq)
+  - Implement two-phase decay of unused dirty pages.  Pages transition from
+    dirty-->muzzy-->clean, where the first phase transition relies on
+    madvise(... MADV_FREE) semantics, and the second phase transition discards
+    pages such that they are replaced with demand-zeroed pages on next access.
+    (@jasone)
+  - Increase decay time resolution from seconds to milliseconds.  (@jasone)
+  - Implement opt-in per CPU background threads, and use them for asynchronous
+    decay-driven unused dirty page purging.  (@interwq)
+  - Add mutex profiling, which collects a variety of statistics useful for
+    diagnosing overhead/contention issues.  (@interwq)
+  - Add C++ new/delete operator bindings.  (@djwatson)
+  - Support manually created arena destruction, such that all data and metadata
+    are discarded.  Add MALLCTL_ARENAS_DESTROYED for accessing merged stats
+    associated with destroyed arenas.  (@jasone)
+  - Add MALLCTL_ARENAS_ALL as a fixed index for use in accessing
+    merged/destroyed arena statistics via mallctl.  (@jasone)
+  - Add opt.abort_conf to optionally abort if invalid configuration options are
+    detected during initialization.  (@interwq)
+  - Add opt.stats_print_opts, so that e.g. JSON output can be selected for the
+    stats dumped during exit if opt.stats_print is true.  (@jasone)
+  - Add --with-version=VERSION for use when embedding jemalloc into another
+    project's git repository.  (@jasone)
+  - Add --disable-thp to support cross compiling.  (@jasone)
+  - Add --with-lg-hugepage to support cross compiling.  (@jasone)
+  - Add mallctl interfaces (various authors):
+    + background_thread
+    + opt.abort_conf
+    + opt.retain
+    + opt.percpu_arena
+    + opt.background_thread
+    + opt.{dirty,muzzy}_decay_ms
+    + opt.stats_print_opts
+    + arena.<i>.initialized
+    + arena.<i>.destroy
+    + arena.<i>.{dirty,muzzy}_decay_ms
+    + arena.<i>.extent_hooks
+    + arenas.{dirty,muzzy}_decay_ms
+    + arenas.bin.<i>.slab_size
+    + arenas.nlextents
+    + arenas.lextent.<i>.size
+    + arenas.create
+    + stats.background_thread.{num_threads,num_runs,run_interval}
+    + stats.mutexes.{ctl,background_thread,prof,reset}.
+      {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
+      num_owner_switch}
+    + stats.arenas.<i>.{dirty,muzzy}_decay_ms
+    + stats.arenas.<i>.uptime
+    + stats.arenas.<i>.{pmuzzy,base,internal,resident}
+    + stats.arenas.<i>.{dirty,muzzy}_{npurge,nmadvise,purged}
+    + stats.arenas.<i>.bins.<j>.{nslabs,reslabs,curslabs}
+    + stats.arenas.<i>.bins.<j>.mutex.
+      {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
+      num_owner_switch}
+    + stats.arenas.<i>.lextents.<j>.{nmalloc,ndalloc,nrequests,curlextents}
+    + stats.arenas.i.mutexes.{large,extent_avail,extents_dirty,extents_muzzy,
+      extents_retained,decay_dirty,decay_muzzy,base,tcache_list}.
+      {num_ops,num_spin_acq,num_wait,max_wait_time,total_wait_time,max_num_thds,
+      num_owner_switch}
+
+  Portability improvements:
+  - Improve reentrant allocation support, such that deadlock is less likely if
+    e.g. a system library call in turn allocates memory.  (@davidtgoldblatt,
+    @interwq)
+  - Support static linking of jemalloc with glibc.  (@djwatson)
+
+  Optimizations and refactors:
+  - Organize virtual memory as "extents" of virtual memory pages, rather than as
+    naturally aligned "chunks", and store all metadata in arbitrarily distant
+    locations.  This reduces virtual memory external fragmentation, and will
+    interact better with huge pages (not yet explicitly supported).  (@jasone)
+  - Fold large and huge size classes together; only small and large size classes
+    remain.  (@jasone)
+  - Unify the allocation paths, and merge most fast-path branching decisions.
+    (@davidtgoldblatt, @interwq)
+  - Embed per thread automatic tcache into thread-specific data, which reduces
+    conditional branches and dereferences.  Also reorganize tcache to increase
+    fast-path data locality.  (@interwq)
+  - Rewrite atomics to closely model the C11 API, convert various
+    synchronization from mutex-based to atomic, and use the explicit memory
+    ordering control to resolve various hypothetical races without increasing
+    synchronization overhead.  (@davidtgoldblatt)
+  - Extensively optimize rtree via various methods:
+    + Add multiple layers of rtree lookup caching, since rtree lookups are now
+      part of fast-path deallocation.  (@interwq)
+    + Determine rtree layout at compile time.  (@jasone)
+    + Make the tree shallower for common configurations.  (@jasone)
+    + Embed the root node in the top-level rtree data structure, thus avoiding
+      one level of indirection.  (@jasone)
+    + Further specialize leaf elements as compared to internal node elements,
+      and directly embed extent metadata needed for fast-path deallocation.
+      (@jasone)
+    + Ignore leading always-zero address bits (architecture-specific).
+      (@jasone)
+  - Reorganize headers (ongoing work) to make them hermetic, and disentangle
+    various module dependencies.  (@davidtgoldblatt)
+  - Convert various internal data structures such as size class metadata from
+    boot-time-initialized to compile-time-initialized.  Propagate resulting data
+    structure simplifications, such as making arena metadata fixed-size.
+    (@jasone)
+  - Simplify size class lookups when constrained to size classes that are
+    multiples of the page size.  This speeds lookups, but the primary benefit is
+    complexity reduction in code that was the source of numerous regressions.
+    (@jasone)
+  - Lock individual extents when possible for localized extent operations,
+    rather than relying on a top-level arena lock.  (@davidtgoldblatt, @jasone)
+  - Use first fit layout policy instead of best fit, in order to improve
+    packing.  (@jasone)
+  - If munmap(2) is not in use, use an exponential series to grow each arena's
+    virtual memory, so that the number of disjoint virtual memory mappings
+    remains low.  (@jasone)
+  - Implement per arena base allocators, so that arenas never share any virtual
+    memory pages.  (@jasone)
+  - Automatically generate private symbol name mangling macros.  (@jasone)
+
+  Incompatible changes:
+  - Replace chunk hooks with an expanded/normalized set of extent hooks.
+    (@jasone)
+  - Remove ratio-based purging.  (@jasone)
+  - Remove --disable-tcache.  (@jasone)
+  - Remove --disable-tls.  (@jasone)
+  - Remove --enable-ivsalloc.  (@jasone)
+  - Remove --with-lg-size-class-group.  (@jasone)
+  - Remove --with-lg-tiny-min.  (@jasone)
+  - Remove --disable-cc-silence.  (@jasone)
+  - Remove --enable-code-coverage.  (@jasone)
+  - Remove --disable-munmap (replaced by opt.retain).  (@jasone)
+  - Remove Valgrind support.  (@jasone)
+  - Remove quarantine support.  (@jasone)
+  - Remove redzone support.  (@jasone)
+  - Remove mallctl interfaces (various authors):
+    + config.munmap
+    + config.tcache
+    + config.tls
+    + config.valgrind
+    + opt.lg_chunk
+    + opt.purge
+    + opt.lg_dirty_mult
+    + opt.decay_time
+    + opt.quarantine
+    + opt.redzone
+    + opt.thp
+    + arena.<i>.lg_dirty_mult
+    + arena.<i>.decay_time
+    + arena.<i>.chunk_hooks
+    + arenas.initialized
+    + arenas.lg_dirty_mult
+    + arenas.decay_time
+    + arenas.bin.<i>.run_size
+    + arenas.nlruns
+    + arenas.lrun.<i>.size
+    + arenas.nhchunks
+    + arenas.hchunk.<i>.size
+    + arenas.extend
+    + stats.cactive
+    + stats.arenas.<i>.lg_dirty_mult
+    + stats.arenas.<i>.decay_time
+    + stats.arenas.<i>.metadata.{mapped,allocated}
+    + stats.arenas.<i>.{npurge,nmadvise,purged}
+    + stats.arenas.<i>.huge.{allocated,nmalloc,ndalloc,nrequests}
+    + stats.arenas.<i>.bins.<j>.{nruns,reruns,curruns}
+    + stats.arenas.<i>.lruns.<j>.{nmalloc,ndalloc,nrequests,curruns}
+    + stats.arenas.<i>.hchunks.<j>.{nmalloc,ndalloc,nrequests,curhchunks}
+
+  Bug fixes:
+  - Improve interval-based profile dump triggering to dump only one profile when
+    a single allocation's size exceeds the interval.  (@jasone)
+  - Use prefixed function names (as controlled by --with-jemalloc-prefix) when
+    pruning backtrace frames in jeprof.  (@jasone)
+
+* 4.5.0 (February 28, 2017)
+
+  This is the first release to benefit from much broader continuous integration
+  testing, thanks to @davidtgoldblatt.  Had we had this testing infrastructure
+  in place for prior releases, it would have caught all of the most serious
+  regressions fixed by this release.
+
+  New features:
+  - Add --disable-thp and the opt.thp mallctl to provide opt-out mechanisms for
+    transparent huge page integration.  (@jasone)
+  - Update zone allocator integration to work with macOS 10.12.  (@glandium)
+  - Restructure *CFLAGS configuration, so that CFLAGS behaves typically, and
+    EXTRA_CFLAGS provides a way to specify e.g. -Werror during building, but not
+    during configuration.  (@jasone, @ronawho)
+
+  Bug fixes:
+  - Fix DSS (sbrk(2)-based) allocation.  This regression was first released in
+    4.3.0.  (@jasone)
+  - Handle race in per size class utilization computation.  This functionality
+    was first released in 4.0.0.  (@interwq)
+  - Fix lock order reversal during gdump.  (@jasone)
+  - Fix/refactor tcache synchronization.  This regression was first released in
+    4.0.0.  (@jasone)
+  - Fix various JSON-formatted malloc_stats_print() bugs.  This functionality
+    was first released in 4.3.0.  (@jasone)
+  - Fix huge-aligned allocation.  This regression was first released in 4.4.0.
+    (@jasone)
+  - When transparent huge page integration is enabled, detect what state pages
+    start in according to the kernel's current operating mode, and only convert
+    arena chunks to non-huge during purging if that is not their initial state.
+    This functionality was first released in 4.4.0.  (@jasone)
+  - Fix lg_chunk clamping for the --enable-cache-oblivious --disable-fill case.
+    This regression was first released in 4.0.0.  (@jasone, @428desmo)
+  - Properly detect sparc64 when building for Linux.  (@glaubitz)
+
+* 4.4.0 (December 3, 2016)
+
+  New features:
+  - Add configure support for *-*-linux-android.  (@cferris1000, @jasone)
+  - Add the --disable-syscall configure option, for use on systems that place
+    security-motivated limitations on syscall(2).  (@jasone)
+  - Add support for Debian GNU/kFreeBSD.  (@thesam)
+
+  Optimizations:
+  - Add extent serial numbers and use them where appropriate as a sort key that
+    is higher priority than address, so that the allocation policy prefers older
+    extents.  This tends to improve locality (decrease fragmentation) when
+    memory grows downward.  (@jasone)
+  - Refactor madvise(2) configuration so that MADV_FREE is detected and utilized
+    on Linux 4.5 and newer.  (@jasone)
+  - Mark partially purged arena chunks as non-huge-page.  This improves
+    interaction with Linux's transparent huge page functionality.  (@jasone)
+
+  Bug fixes:
+  - Fix size class computations for edge conditions involving extremely large
+    allocations.  This regression was first released in 4.0.0.  (@jasone,
+    @ingvarha)
+  - Remove overly restrictive assertions related to the cactive statistic.  This
+    regression was first released in 4.1.0.  (@jasone)
+  - Implement a more reliable detection scheme for os_unfair_lock on macOS.
+    (@jszakmeister)
+
+* 4.3.1 (November 7, 2016)
+
+  Bug fixes:
+  - Fix a severe virtual memory leak.  This regression was first released in
+    4.3.0.  (@interwq, @jasone)
+  - Refactor atomic and prng APIs to restore support for 32-bit platforms that
+    use pre-C11 toolchains, e.g. FreeBSD's mips.  (@jasone)
+
+* 4.3.0 (November 4, 2016)
+
+  This is the first release that passes the test suite for multiple Windows
+  configurations, thanks in large part to @glandium setting up continuous
+  integration via AppVeyor (and Travis CI for Linux and OS X).
+
+  New features:
+  - Add "J" (JSON) support to malloc_stats_print().  (@jasone)
+  - Add Cray compiler support.  (@ronawho)
+
+  Optimizations:
+  - Add/use adaptive spinning for bootstrapping and radix tree node
+    initialization.  (@jasone)
+
+  Bug fixes:
+  - Fix large allocation to search starting in the optimal size class heap,
+    which can substantially reduce virtual memory churn and fragmentation.  This
+    regression was first released in 4.0.0.  (@mjp41, @jasone)
+  - Fix stats.arenas.<i>.nthreads accounting.  (@interwq)
+  - Fix and simplify decay-based purging.  (@jasone)
+  - Make DSS (sbrk(2)-related) operations lockless, which resolves potential
+    deadlocks during thread exit.  (@jasone)
+  - Fix over-sized allocation of radix tree leaf nodes.  (@mjp41, @ogaun,
+    @jasone)
+  - Fix over-sized allocation of arena_t (plus associated stats) data
+    structures.  (@jasone, @interwq)
+  - Fix EXTRA_CFLAGS to not affect configuration.  (@jasone)
+  - Fix a Valgrind integration bug.  (@ronawho)
+  - Disallow 0x5a junk filling when running in Valgrind.  (@jasone)
+  - Fix a file descriptor leak on Linux.  This regression was first released in
+    4.2.0.  (@vsarunas, @jasone)
+  - Fix static linking of jemalloc with glibc.  (@djwatson)
+  - Use syscall(2) rather than {open,read,close}(2) during boot on Linux.  This
+    works around other libraries' system call wrappers performing reentrant
+    allocation.  (@kspinka, @Whissi, @jasone)
+  - Fix OS X default zone replacement to work with OS X 10.12.  (@glandium,
+    @jasone)
+  - Fix cached memory management to avoid needless commit/decommit operations
+    during purging, which resolves permanent virtual memory map fragmentation
+    issues on Windows.  (@mjp41, @jasone)
+  - Fix TSD fetches to avoid (recursive) allocation.  This is relevant to
+    non-TLS and Windows configurations.  (@jasone)
+  - Fix malloc_conf overriding to work on Windows.  (@jasone)
+  - Forcibly disable lazy-lock on Windows (was forcibly *enabled*).  (@jasone)
+
+* 4.2.1 (June 8, 2016)
+
+  Bug fixes:
+  - Fix bootstrapping issues for configurations that require allocation during
+    tsd initialization (e.g. --disable-tls).  (@cferris1000, @jasone)
+  - Fix gettimeofday() version of nstime_update().  (@ronawho)
+  - Fix Valgrind regressions in calloc() and chunk_alloc_wrapper().  (@ronawho)
+  - Fix potential VM map fragmentation regression.  (@jasone)
+  - Fix opt_zero-triggered in-place huge reallocation zeroing.  (@jasone)
+  - Fix heap profiling context leaks in reallocation edge cases.  (@jasone)
+
+* 4.2.0 (May 12, 2016)
+
+  New features:
+  - Add the arena.<i>.reset mallctl, which makes it possible to discard all of
+    an arena's allocations in a single operation.  (@jasone)
+  - Add the stats.retained and stats.arenas.<i>.retained statistics.  (@jasone)
+  - Add the --with-version configure option.  (@jasone)
+  - Support --with-lg-page values larger than actual page size.  (@jasone)
+
+  Optimizations:
+  - Use pairing heaps rather than red-black trees for various hot data
+    structures.  (@djwatson, @jasone)
+  - Streamline fast paths of rtree operations.  (@jasone)
+  - Optimize the fast paths of calloc() and [m,d,sd]allocx().  (@jasone)
+  - Decommit unused virtual memory if the OS does not overcommit.  (@jasone)
+  - Specify MAP_NORESERVE on Linux if [heuristic] overcommit is active, in order
+    to avoid unfortunate interactions during fork(2).  (@jasone)
+
+  Bug fixes:
+  - Fix chunk accounting related to triggering gdump profiles.  (@jasone)
+  - Link against librt for clock_gettime(2) if glibc < 2.17.  (@jasone)
+  - Scale leak report summary according to sampling probability.  (@jasone)
+
+* 4.1.1 (May 3, 2016)
+
+  This bugfix release resolves a variety of mostly minor issues, though the
+  bitmap fix is critical for 64-bit Windows.
+
+  Bug fixes:
+  - Fix the linear scan version of bitmap_sfu() to shift by the proper amount
+    even when sizeof(long) is not the same as sizeof(void *), as on 64-bit
+    Windows.  (@jasone)
+  - Fix hashing functions to avoid unaligned memory accesses (and resulting
+    crashes).  This is relevant at least to some ARM-based platforms.
+    (@rkmisra)
+  - Fix fork()-related lock rank ordering reversals.  These reversals were
+    unlikely to cause deadlocks in practice except when heap profiling was
+    enabled and active.  (@jasone)
+  - Fix various chunk leaks in OOM code paths.  (@jasone)
+  - Fix malloc_stats_print() to print opt.narenas correctly.  (@jasone)
+  - Fix MSVC-specific build/test issues.  (@rustyx, @yuslepukhin)
+  - Fix a variety of test failures that were due to test fragility rather than
+    core bugs.  (@jasone)
+
+* 4.1.0 (February 28, 2016)
+
+  This release is primarily about optimizations, but it also incorporates a lot
+  of portability-motivated refactoring and enhancements.  Many people worked on
+  this release, to an extent that even with the omission here of minor changes
+  (see git revision history), and of the people who reported and diagnosed
+  issues, so much of the work was contributed that starting with this release,
+  changes are annotated with author credits to help reflect the collaborative
+  effort involved.
+
+  New features:
+  - Implement decay-based unused dirty page purging, a major optimization with
+    mallctl API impact.  This is an alternative to the existing ratio-based
+    unused dirty page purging, and is intended to eventually become the sole
+    purging mechanism.  New mallctls:
+    + opt.purge
+    + opt.decay_time
+    + arena.<i>.decay
+    + arena.<i>.decay_time
+    + arenas.decay_time
+    + stats.arenas.<i>.decay_time
+    (@jasone, @cevans87)
+  - Add --with-malloc-conf, which makes it possible to embed a default
+    options string during configuration.  This was motivated by the desire to
+    specify --with-malloc-conf=purge:decay , since the default must remain
+    purge:ratio until the 5.0.0 release.  (@jasone)
+  - Add MS Visual Studio 2015 support.  (@rustyx, @yuslepukhin)
+  - Make *allocx() size class overflow behavior defined.  The maximum
+    size class is now less than PTRDIFF_MAX to protect applications against
+    numerical overflow, and all allocation functions are guaranteed to indicate
+    errors rather than potentially crashing if the request size exceeds the
+    maximum size class.  (@jasone)
+  - jeprof:
+    + Add raw heap profile support.  (@jasone)
+    + Add --retain and --exclude for backtrace symbol filtering.  (@jasone)
+
+  Optimizations:
+  - Optimize the fast path to combine various bootstrapping and configuration
+    checks and execute more streamlined code in the common case.  (@interwq)
+  - Use linear scan for small bitmaps (used for small object tracking).  In
+    addition to speeding up bitmap operations on 64-bit systems, this reduces
+    allocator metadata overhead by approximately 0.2%.  (@djwatson)
+  - Separate arena_avail trees, which substantially speeds up run tree
+    operations.  (@djwatson)
+  - Use memoization (boot-time-computed table) for run quantization.  Separate
+    arena_avail trees reduced the importance of this optimization.  (@jasone)
+  - Attempt mmap-based in-place huge reallocation.  This can dramatically speed
+    up incremental huge reallocation.  (@jasone)
+
+  Incompatible changes:
+  - Make opt.narenas unsigned rather than size_t.  (@jasone)
+
+  Bug fixes:
+  - Fix stats.cactive accounting regression.  (@rustyx, @jasone)
+  - Handle unaligned keys in hash().  This caused problems for some ARM systems.
+    (@jasone, @cferris1000)
+  - Refactor arenas array.  In addition to fixing a fork-related deadlock, this
+    makes arena lookups faster and simpler.  (@jasone)
+  - Move retained memory allocation out of the default chunk allocation
+    function, to a location that gets executed even if the application installs
+    a custom chunk allocation function.  This resolves a virtual memory leak.
+    (@buchgr)
+  - Fix a potential tsd cleanup leak.  (@cferris1000, @jasone)
+  - Fix run quantization.  In practice this bug had no impact unless
+    applications requested memory with alignment exceeding one page.
+    (@jasone, @djwatson)
+  - Fix LinuxThreads-specific bootstrapping deadlock.  (Cosmin Paraschiv)
+  - jeprof:
+    + Don't discard curl options if timeout is not defined.  (@djwatson)
+    + Detect failed profile fetches.  (@djwatson)
+  - Fix stats.arenas.<i>.{dss,lg_dirty_mult,decay_time,pactive,pdirty} for
+    --disable-stats case.  (@jasone)
+
+* 4.0.4 (October 24, 2015)
+
+  This bugfix release fixes another xallocx() regression.  No other regressions
+  have come to light in over a month, so this is likely a good starting point
+  for people who prefer to wait for "dot one" releases with all the major issues
+  shaken out.
+
+  Bug fixes:
+  - Fix xallocx(..., MALLOCX_ZERO to zero the last full trailing page of large
+    allocations that have been randomly assigned an offset of 0 when
+    --enable-cache-oblivious configure option is enabled.
+
+* 4.0.3 (September 24, 2015)
+
+  This bugfix release continues the trend of xallocx() and heap profiling fixes.
+
+  Bug fixes:
+  - Fix xallocx(..., MALLOCX_ZERO) to zero all trailing bytes of large
+    allocations when --enable-cache-oblivious configure option is enabled.
+  - Fix xallocx(..., MALLOCX_ZERO) to zero trailing bytes of huge allocations
+    when resizing from/to a size class that is not a multiple of the chunk size.
+  - Fix prof_tctx_dump_iter() to filter out nodes that were created after heap
+    profile dumping started.
+  - Work around a potentially bad thread-specific data initialization
+    interaction with NPTL (glibc's pthreads implementation).
+
+* 4.0.2 (September 21, 2015)
+
+  This bugfix release addresses a few bugs specific to heap profiling.
+
+  Bug fixes:
+  - Fix ixallocx_prof_sample() to never modify nor create sampled small
+    allocations.  xallocx() is in general incapable of moving small allocations,
+    so this fix removes buggy code without loss of generality.
+  - Fix irallocx_prof_sample() to always allocate large regions, even when
+    alignment is non-zero.
+  - Fix prof_alloc_rollback() to read tdata from thread-specific data rather
+    than dereferencing a potentially invalid tctx.
+
+* 4.0.1 (September 15, 2015)
+
+  This is a bugfix release that is somewhat high risk due to the amount of
+  refactoring required to address deep xallocx() problems.  As a side effect of
+  these fixes, xallocx() now tries harder to partially fulfill requests for
+  optional extra space.  Note that a couple of minor heap profiling
+  optimizations are included, but these are better thought of as performance
+  fixes that were integral to disovering most of the other bugs.
+
+  Optimizations:
+  - Avoid a chunk metadata read in arena_prof_tctx_set(), since it is in the
+    fast path when heap profiling is enabled.  Additionally, split a special
+    case out into arena_prof_tctx_reset(), which also avoids chunk metadata
+    reads.
+  - Optimize irallocx_prof() to optimistically update the sampler state.  The
+    prior implementation appears to have been a holdover from when
+    rallocx()/xallocx() functionality was combined as rallocm().
+
+  Bug fixes:
+  - Fix TLS configuration such that it is enabled by default for platforms on
+    which it works correctly.
+  - Fix arenas_cache_cleanup() and arena_get_hard() to handle
+    allocation/deallocation within the application's thread-specific data
+    cleanup functions even after arenas_cache is torn down.
+  - Fix xallocx() bugs related to size+extra exceeding HUGE_MAXCLASS.
+  - Fix chunk purge hook calls for in-place huge shrinking reallocation to
+    specify the old chunk size rather than the new chunk size.  This bug caused
+    no correctness issues for the default chunk purge function, but was
+    visible to custom functions set via the "arena.<i>.chunk_hooks" mallctl.
+  - Fix heap profiling bugs:
+    + Fix heap profiling to distinguish among otherwise identical sample sites
+      with interposed resets (triggered via the "prof.reset" mallctl).  This bug
+      could cause data structure corruption that would most likely result in a
+      segfault.
+    + Fix irealloc_prof() to prof_alloc_rollback() on OOM.
+    + Make one call to prof_active_get_unlocked() per allocation event, and use
+      the result throughout the relevant functions that handle an allocation
+      event.  Also add a missing check in prof_realloc().  These fixes protect
+      allocation events against concurrent prof_active changes.
+    + Fix ixallocx_prof() to pass usize_max and zero to ixallocx_prof_sample()
+      in the correct order.
+    + Fix prof_realloc() to call prof_free_sampled_object() after calling
+      prof_malloc_sample_object().  Prior to this fix, if tctx and old_tctx were
+      the same, the tctx could have been prematurely destroyed.
+  - Fix portability bugs:
+    + Don't bitshift by negative amounts when encoding/decoding run sizes in
+      chunk header maps.  This affected systems with page sizes greater than 8
+      KiB.
+    + Rename index_t to szind_t to avoid an existing type on Solaris.
+    + Add JEMALLOC_CXX_THROW to the memalign() function prototype, in order to
+      match glibc and avoid compilation errors when including both
+      jemalloc/jemalloc.h and malloc.h in C++ code.
+    + Don't assume that /bin/sh is appropriate when running size_classes.sh
+      during configuration.
+    + Consider __sparcv9 a synonym for __sparc64__ when defining LG_QUANTUM.
+    + Link tests to librt if it contains clock_gettime(2).
+
+* 4.0.0 (August 17, 2015)
+
+  This version contains many speed and space optimizations, both minor and
+  major.  The major themes are generalization, unification, and simplification.
+  Although many of these optimizations cause no visible behavior change, their
+  cumulative effect is substantial.
+
+  New features:
+  - Normalize size class spacing to be consistent across the complete size
+    range.  By default there are four size classes per size doubling, but this
+    is now configurable via the --with-lg-size-class-group option.  Also add the
+    --with-lg-page, --with-lg-page-sizes, --with-lg-quantum, and
+    --with-lg-tiny-min options, which can be used to tweak page and size class
+    settings.  Impacts:
+    + Worst case performance for incrementally growing/shrinking reallocation
+      is improved because there are far fewer size classes, and therefore
+      copying happens less often.
+    + Internal fragmentation is limited to 20% for all but the smallest size
+      classes (those less than four times the quantum).  (1B + 4 KiB)
+      and (1B + 4 MiB) previously suffered nearly 50% internal fragmentation.
+    + Chunk fragmentation tends to be lower because there are fewer distinct run
+      sizes to pack.
+  - Add support for explicit tcaches.  The "tcache.create", "tcache.flush", and
+    "tcache.destroy" mallctls control tcache lifetime and flushing, and the
+    MALLOCX_TCACHE(tc) and MALLOCX_TCACHE_NONE flags to the *allocx() API
+    control which tcache is used for each operation.
+  - Implement per thread heap profiling, as well as the ability to
+    enable/disable heap profiling on a per thread basis.  Add the "prof.reset",
+    "prof.lg_sample", "thread.prof.name", "thread.prof.active",
+    "opt.prof_thread_active_init", "prof.thread_active_init", and
+    "thread.prof.active" mallctls.
+  - Add support for per arena application-specified chunk allocators, configured
+    via the "arena.<i>.chunk_hooks" mallctl.
+  - Refactor huge allocation to be managed by arenas, so that arenas now
+    function as general purpose independent allocators.  This is important in
+    the context of user-specified chunk allocators, aside from the scalability
+    benefits.  Related new statistics:
+    + The "stats.arenas.<i>.huge.allocated", "stats.arenas.<i>.huge.nmalloc",
+      "stats.arenas.<i>.huge.ndalloc", and "stats.arenas.<i>.huge.nrequests"
+      mallctls provide high level per arena huge allocation statistics.
+    + The "arenas.nhchunks", "arenas.hchunk.<i>.size",
+      "stats.arenas.<i>.hchunks.<j>.nmalloc",
+      "stats.arenas.<i>.hchunks.<j>.ndalloc",
+      "stats.arenas.<i>.hchunks.<j>.nrequests", and
+      "stats.arenas.<i>.hchunks.<j>.curhchunks" mallctls provide per size class
+      statistics.
+  - Add the 'util' column to malloc_stats_print() output, which reports the
+    proportion of available regions that are currently in use for each small
+    size class.
+  - Add "alloc" and "free" modes for for junk filling (see the "opt.junk"
+    mallctl), so that it is possible to separately enable junk filling for
+    allocation versus deallocation.
+  - Add the jemalloc-config script, which provides information about how
+    jemalloc was configured, and how to integrate it into application builds.
+  - Add metadata statistics, which are accessible via the "stats.metadata",
+    "stats.arenas.<i>.metadata.mapped", and
+    "stats.arenas.<i>.metadata.allocated" mallctls.
+  - Add the "stats.resident" mallctl, which reports the upper limit of
+    physically resident memory mapped by the allocator.
+  - Add per arena control over unused dirty page purging, via the
+    "arenas.lg_dirty_mult", "arena.<i>.lg_dirty_mult", and
+    "stats.arenas.<i>.lg_dirty_mult" mallctls.
+  - Add the "prof.gdump" mallctl, which makes it possible to toggle the gdump
+    feature on/off during program execution.
+  - Add sdallocx(), which implements sized deallocation.  The primary
+    optimization over dallocx() is the removal of a metadata read, which often
+    suffers an L1 cache miss.
+  - Add missing header includes in jemalloc/jemalloc.h, so that applications
+    only have to #include <jemalloc/jemalloc.h>.
+  - Add support for additional platforms:
+    + Bitrig
+    + Cygwin
+    + DragonFlyBSD
+    + iOS
+    + OpenBSD
+    + OpenRISC/or1k
+
+  Optimizations:
+  - Maintain dirty runs in per arena LRUs rather than in per arena trees of
+    dirty-run-containing chunks.  In practice this change significantly reduces
+    dirty page purging volume.
+  - Integrate whole chunks into the unused dirty page purging machinery.  This
+    reduces the cost of repeated huge allocation/deallocation, because it
+    effectively introduces a cache of chunks.
+  - Split the arena chunk map into two separate arrays, in order to increase
+    cache locality for the frequently accessed bits.
+  - Move small run metadata out of runs, into arena chunk headers.  This reduces
+    run fragmentation, smaller runs reduce external fragmentation for small size
+    classes, and packed (less uniformly aligned) metadata layout improves CPU
+    cache set distribution.
+  - Randomly distribute large allocation base pointer alignment relative to page
+    boundaries in order to more uniformly utilize CPU cache sets.  This can be
+    disabled via the --disable-cache-oblivious configure option, and queried via
+    the "config.cache_oblivious" mallctl.
+  - Micro-optimize the fast paths for the public API functions.
+  - Refactor thread-specific data to reside in a single structure.  This assures
+    that only a single TLS read is necessary per call into the public API.
+  - Implement in-place huge allocation growing and shrinking.
+  - Refactor rtree (radix tree for chunk lookups) to be lock-free, and make
+    additional optimizations that reduce maximum lookup depth to one or two
+    levels.  This resolves what was a concurrency bottleneck for per arena huge
+    allocation, because a global data structure is critical for determining
+    which arenas own which huge allocations.
+
+  Incompatible changes:
+  - Replace --enable-cc-silence with --disable-cc-silence to suppress spurious
+    warnings by default.
+  - Assure that the constness of malloc_usable_size()'s return type matches that
+    of the system implementation.
+  - Change the heap profile dump format to support per thread heap profiling,
+    rename pprof to jeprof, and enhance it with the --thread=<n> option.  As a
+    result, the bundled jeprof must now be used rather than the upstream
+    (gperftools) pprof.
+  - Disable "opt.prof_final" by default, in order to avoid atexit(3), which can
+    internally deadlock on some platforms.
+  - Change the "arenas.nlruns" mallctl type from size_t to unsigned.
+  - Replace the "stats.arenas.<i>.bins.<j>.allocated" mallctl with
+    "stats.arenas.<i>.bins.<j>.curregs".
+  - Ignore MALLOC_CONF in set{uid,gid,cap} binaries.
+  - Ignore MALLOCX_ARENA(a) in dallocx(), in favor of using the
+    MALLOCX_TCACHE(tc) and MALLOCX_TCACHE_NONE flags to control tcache usage.
+
+  Removed features:
+  - Remove the *allocm() API, which is superseded by the *allocx() API.
+  - Remove the --enable-dss options, and make dss non-optional on all platforms
+    which support sbrk(2).
+  - Remove the "arenas.purge" mallctl, which was obsoleted by the
+    "arena.<i>.purge" mallctl in 3.1.0.
+  - Remove the unnecessary "opt.valgrind" mallctl; jemalloc automatically
+    detects whether it is running inside Valgrind.
+  - Remove the "stats.huge.allocated", "stats.huge.nmalloc", and
+    "stats.huge.ndalloc" mallctls.
+  - Remove the --enable-mremap option.
+  - Remove the "stats.chunks.current", "stats.chunks.total", and
+    "stats.chunks.high" mallctls.
+
+  Bug fixes:
+  - Fix the cactive statistic to decrease (rather than increase) when active
+    memory decreases.  This regression was first released in 3.5.0.
+  - Fix OOM handling in memalign() and valloc().  A variant of this bug existed
+    in all releases since 2.0.0, which introduced these functions.
+  - Fix an OOM-related regression in arena_tcache_fill_small(), which could
+    cause cache corruption on OOM.  This regression was present in all releases
+    from 2.2.0 through 3.6.0.
+  - Fix size class overflow handling for malloc(), posix_memalign(), memalign(),
+    calloc(), and realloc() when profiling is enabled.
+  - Fix the "arena.<i>.dss" mallctl to return an error if "primary" or
+    "secondary" precedence is specified, but sbrk(2) is not supported.
+  - Fix fallback lg_floor() implementations to handle extremely large inputs.
+  - Ensure the default purgeable zone is after the default zone on OS X.
+  - Fix latent bugs in atomic_*().
+  - Fix the "arena.<i>.dss" mallctl to handle read-only calls.
+  - Fix tls_model configuration to enable the initial-exec model when possible.
+  - Mark malloc_conf as a weak symbol so that the application can override it.
+  - Correctly detect glibc's adaptive pthread mutexes.
+  - Fix the --without-export configure option.
+
 * 3.6.0 (March 31, 2014)
 
   This version contains a critical bug fix for a regression present in 3.5.0 and
@@ -21,7 +738,7 @@ found in the git revision history:
     backtracing to be reliable.
   - Use dss allocation precedence for huge allocations as well as small/large
     allocations.
-  - Fix test assertion failure message formatting.  This bug did not manifect on
+  - Fix test assertion failure message formatting.  This bug did not manifest on
     x86_64 systems because of implementation subtleties in va_list.
   - Fix inconsequential test failures for hash and SFMT code.
 
@@ -516,7 +1233,7 @@ found in the git revision history:
   - Make it possible for the application to manually flush a thread's cache, via
     the "tcache.flush" mallctl.
   - Base maximum dirty page count on proportion of active memory.
-  - Compute various addtional run-time statistics, including per size class
+  - Compute various additional run-time statistics, including per size class
     statistics for large objects.
   - Expose malloc_stats_print(), which can be called repeatedly by the
     application.
diff --git a/modules/worldengine/deps/jemalloc/README b/modules/worldengine/deps/jemalloc/README
index 9b268f4228..3a6e0d2725 100644
--- a/modules/worldengine/deps/jemalloc/README
+++ b/modules/worldengine/deps/jemalloc/README
@@ -3,12 +3,12 @@ fragmentation avoidance and scalable concurrency support.  jemalloc first came
 into use as the FreeBSD libc allocator in 2005, and since then it has found its
 way into numerous applications that rely on its predictable behavior.  In 2010
 jemalloc development efforts broadened to include developer support features
-such as heap profiling, Valgrind integration, and extensive monitoring/tuning
-hooks.  Modern jemalloc releases continue to be integrated back into FreeBSD,
-and therefore versatility remains critical.  Ongoing development efforts trend
-toward making jemalloc among the best allocators for a broad range of demanding
-applications, and eliminating/mitigating weaknesses that have practical
-repercussions for real world applications.
+such as heap profiling and extensive monitoring/tuning hooks.  Modern jemalloc
+releases continue to be integrated back into FreeBSD, and therefore versatility
+remains critical.  Ongoing development efforts trend toward making jemalloc
+among the best allocators for a broad range of demanding applications, and
+eliminating/mitigating weaknesses that have practical repercussions for real
+world applications.
 
 The COPYING file contains copyright and licensing information.
 
@@ -17,4 +17,4 @@ jemalloc.
 
 The ChangeLog file contains a brief summary of changes for each release.
 
-URL: http://www.canonware.com/jemalloc/
+URL: http://jemalloc.net/
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_externs.h
new file mode 100644
index 0000000000..af16d15885
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_externs.h
@@ -0,0 +1,97 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_EXTERNS_H
+#define JEMALLOC_INTERNAL_ARENA_EXTERNS_H
+
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/pages.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/stats.h"
+
+extern ssize_t opt_dirty_decay_ms;
+extern ssize_t opt_muzzy_decay_ms;
+
+extern const arena_bin_info_t arena_bin_info[NBINS];
+
+extern percpu_arena_mode_t opt_percpu_arena;
+extern const char *percpu_arena_mode_names[];
+
+extern const uint64_t h_steps[SMOOTHSTEP_NSTEPS];
+extern malloc_mutex_t arenas_lock;
+
+void arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    szind_t szind, uint64_t nrequests);
+void arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    size_t size);
+void arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena,
+    unsigned *nthreads, const char **dss, ssize_t *dirty_decay_ms,
+    ssize_t *muzzy_decay_ms, size_t *nactive, size_t *ndirty, size_t *nmuzzy);
+void arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms,
+    size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats,
+    malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats);
+void arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent);
+#ifdef JEMALLOC_JET
+size_t arena_slab_regind(extent_t *slab, szind_t binind, const void *ptr);
+#endif
+extent_t *arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena,
+    size_t usize, size_t alignment, bool *zero);
+void arena_extent_dalloc_large_prep(tsdn_t *tsdn, arena_t *arena,
+    extent_t *extent);
+void arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena,
+    extent_t *extent, size_t oldsize);
+void arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena,
+    extent_t *extent, size_t oldsize);
+ssize_t arena_dirty_decay_ms_get(arena_t *arena);
+bool arena_dirty_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms);
+ssize_t arena_muzzy_decay_ms_get(arena_t *arena);
+bool arena_muzzy_decay_ms_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_ms);
+void arena_decay(tsdn_t *tsdn, arena_t *arena, bool is_background_thread,
+    bool all);
+void arena_reset(tsd_t *tsd, arena_t *arena);
+void arena_destroy(tsd_t *tsd, arena_t *arena);
+void arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache,
+    tcache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes);
+void arena_alloc_junk_small(void *ptr, const arena_bin_info_t *bin_info,
+    bool zero);
+
+typedef void (arena_dalloc_junk_small_t)(void *, const arena_bin_info_t *);
+extern arena_dalloc_junk_small_t *JET_MUTABLE arena_dalloc_junk_small;
+
+void *arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size,
+    szind_t ind, bool zero);
+void *arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, bool zero, tcache_t *tcache);
+void arena_prof_promote(tsdn_t *tsdn, const void *ptr, size_t usize);
+void arena_dalloc_promoted(tsdn_t *tsdn, void *ptr, tcache_t *tcache,
+    bool slow_path);
+void arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena,
+    extent_t *extent, void *ptr);
+void arena_dalloc_small(tsdn_t *tsdn, void *ptr);
+bool arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size,
+    size_t extra, bool zero);
+void *arena_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t oldsize,
+    size_t size, size_t alignment, bool zero, tcache_t *tcache);
+dss_prec_t arena_dss_prec_get(arena_t *arena);
+bool arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec);
+ssize_t arena_dirty_decay_ms_default_get(void);
+bool arena_dirty_decay_ms_default_set(ssize_t decay_ms);
+ssize_t arena_muzzy_decay_ms_default_get(void);
+bool arena_muzzy_decay_ms_default_set(ssize_t decay_ms);
+unsigned arena_nthreads_get(arena_t *arena, bool internal);
+void arena_nthreads_inc(arena_t *arena, bool internal);
+void arena_nthreads_dec(arena_t *arena, bool internal);
+size_t arena_extent_sn_next(arena_t *arena);
+arena_t *arena_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks);
+void arena_boot(void);
+void arena_prefork0(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork1(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork2(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork3(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork4(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork5(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork6(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork7(tsdn_t *tsdn, arena_t *arena);
+void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena);
+void arena_postfork_child(tsdn_t *tsdn, arena_t *arena);
+
+#endif /* JEMALLOC_INTERNAL_ARENA_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_a.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_a.h
new file mode 100644
index 0000000000..da5877060a
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_a.h
@@ -0,0 +1,57 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_INLINES_A_H
+#define JEMALLOC_INTERNAL_ARENA_INLINES_A_H
+
+static inline unsigned
+arena_ind_get(const arena_t *arena) {
+	return base_ind_get(arena->base);
+}
+
+static inline void
+arena_internal_add(arena_t *arena, size_t size) {
+	atomic_fetch_add_zu(&arena->stats.internal, size, ATOMIC_RELAXED);
+}
+
+static inline void
+arena_internal_sub(arena_t *arena, size_t size) {
+	atomic_fetch_sub_zu(&arena->stats.internal, size, ATOMIC_RELAXED);
+}
+
+static inline size_t
+arena_internal_get(arena_t *arena) {
+	return atomic_load_zu(&arena->stats.internal, ATOMIC_RELAXED);
+}
+
+static inline bool
+arena_prof_accum(tsdn_t *tsdn, arena_t *arena, uint64_t accumbytes) {
+	cassert(config_prof);
+
+	if (likely(prof_interval == 0)) {
+		return false;
+	}
+
+	return prof_accum_add(tsdn, &arena->prof_accum, accumbytes);
+}
+
+static inline void
+percpu_arena_update(tsd_t *tsd, unsigned cpu) {
+	assert(have_percpu_arena);
+	arena_t *oldarena = tsd_arena_get(tsd);
+	assert(oldarena != NULL);
+	unsigned oldind = arena_ind_get(oldarena);
+
+	if (oldind != cpu) {
+		unsigned newind = cpu;
+		arena_t *newarena = arena_get(tsd_tsdn(tsd), newind, true);
+		assert(newarena != NULL);
+
+		/* Set new arena/tcache associations. */
+		arena_migrate(tsd, oldind, newind);
+		tcache_t *tcache = tcache_get(tsd);
+		if (tcache != NULL) {
+			tcache_arena_reassociate(tsd_tsdn(tsd), tcache,
+			    newarena);
+		}
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_ARENA_INLINES_A_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_b.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_b.h
new file mode 100644
index 0000000000..003abe116f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_inlines_b.h
@@ -0,0 +1,361 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_INLINES_B_H
+#define JEMALLOC_INTERNAL_ARENA_INLINES_B_H
+
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/sz.h"
+#include "jemalloc/internal/ticker.h"
+
+static inline szind_t
+arena_bin_index(arena_t *arena, arena_bin_t *bin) {
+	szind_t binind = (szind_t)(bin - arena->bins);
+	assert(binind < NBINS);
+	return binind;
+}
+
+JEMALLOC_ALWAYS_INLINE prof_tctx_t *
+arena_prof_tctx_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	/* Static check. */
+	if (alloc_ctx == NULL) {
+		const extent_t *extent = iealloc(tsdn, ptr);
+		if (unlikely(!extent_slab_get(extent))) {
+			return large_prof_tctx_get(tsdn, extent);
+		}
+	} else {
+		if (unlikely(!alloc_ctx->slab)) {
+			return large_prof_tctx_get(tsdn, iealloc(tsdn, ptr));
+		}
+	}
+	return (prof_tctx_t *)(uintptr_t)1U;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_prof_tctx_set(tsdn_t *tsdn, const void *ptr, size_t usize,
+    alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	/* Static check. */
+	if (alloc_ctx == NULL) {
+		extent_t *extent = iealloc(tsdn, ptr);
+		if (unlikely(!extent_slab_get(extent))) {
+			large_prof_tctx_set(tsdn, extent, tctx);
+		}
+	} else {
+		if (unlikely(!alloc_ctx->slab)) {
+			large_prof_tctx_set(tsdn, iealloc(tsdn, ptr), tctx);
+		}
+	}
+}
+
+static inline void
+arena_prof_tctx_reset(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	extent_t *extent = iealloc(tsdn, ptr);
+	assert(!extent_slab_get(extent));
+
+	large_prof_tctx_reset(tsdn, extent);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_decay_ticks(tsdn_t *tsdn, arena_t *arena, unsigned nticks) {
+	tsd_t *tsd;
+	ticker_t *decay_ticker;
+
+	if (unlikely(tsdn_null(tsdn))) {
+		return;
+	}
+	tsd = tsdn_tsd(tsdn);
+	decay_ticker = decay_ticker_get(tsd, arena_ind_get(arena));
+	if (unlikely(decay_ticker == NULL)) {
+		return;
+	}
+	if (unlikely(ticker_ticks(decay_ticker, nticks))) {
+		arena_decay(tsdn, arena, false, false);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_decay_tick(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_assert_not_owner(tsdn, &arena->decay_dirty.mtx);
+	malloc_mutex_assert_not_owner(tsdn, &arena->decay_muzzy.mtx);
+
+	arena_decay_ticks(tsdn, arena, 1);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+arena_malloc(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind, bool zero,
+    tcache_t *tcache, bool slow_path) {
+	assert(!tsdn_null(tsdn) || tcache == NULL);
+	assert(size != 0);
+
+	if (likely(tcache != NULL)) {
+		if (likely(size <= SMALL_MAXCLASS)) {
+			return tcache_alloc_small(tsdn_tsd(tsdn), arena,
+			    tcache, size, ind, zero, slow_path);
+		}
+		if (likely(size <= tcache_maxclass)) {
+			return tcache_alloc_large(tsdn_tsd(tsdn), arena,
+			    tcache, size, ind, zero, slow_path);
+		}
+		/* (size > tcache_maxclass) case falls through. */
+		assert(size > tcache_maxclass);
+	}
+
+	return arena_malloc_hard(tsdn, arena, size, ind, zero);
+}
+
+JEMALLOC_ALWAYS_INLINE arena_t *
+arena_aalloc(tsdn_t *tsdn, const void *ptr) {
+	return extent_arena_get(iealloc(tsdn, ptr));
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+arena_salloc(tsdn_t *tsdn, const void *ptr) {
+	assert(ptr != NULL);
+
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	szind_t szind = rtree_szind_read(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true);
+	assert(szind != NSIZES);
+
+	return sz_index2size(szind);
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+arena_vsalloc(tsdn_t *tsdn, const void *ptr) {
+	/*
+	 * Return 0 if ptr is not within an extent managed by jemalloc.  This
+	 * function has two extra costs relative to isalloc():
+	 * - The rtree calls cannot claim to be dependent lookups, which induces
+	 *   rtree lookup load dependencies.
+	 * - The lookup may fail, so there is an extra branch to check for
+	 *   failure.
+	 */
+
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	extent_t *extent;
+	szind_t szind;
+	if (rtree_extent_szind_read(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, false, &extent, &szind)) {
+		return 0;
+	}
+
+	if (extent == NULL) {
+		return 0;
+	}
+	assert(extent_state_get(extent) == extent_state_active);
+	/* Only slab members should be looked up via interior pointers. */
+	assert(extent_addr_get(extent) == ptr || extent_slab_get(extent));
+
+	assert(szind != NSIZES);
+
+	return sz_index2size(szind);
+}
+
+static inline void
+arena_dalloc_no_tcache(tsdn_t *tsdn, void *ptr) {
+	assert(ptr != NULL);
+
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	szind_t szind;
+	bool slab;
+	rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr,
+	    true, &szind, &slab);
+
+	if (config_debug) {
+		extent_t *extent = rtree_extent_read(tsdn, &extents_rtree,
+		    rtree_ctx, (uintptr_t)ptr, true);
+		assert(szind == extent_szind_get(extent));
+		assert(szind < NSIZES);
+		assert(slab == extent_slab_get(extent));
+	}
+
+	if (likely(slab)) {
+		/* Small allocation. */
+		arena_dalloc_small(tsdn, ptr);
+	} else {
+		extent_t *extent = iealloc(tsdn, ptr);
+		large_dalloc(tsdn, extent);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_dalloc(tsdn_t *tsdn, void *ptr, tcache_t *tcache,
+    alloc_ctx_t *alloc_ctx, bool slow_path) {
+	assert(!tsdn_null(tsdn) || tcache == NULL);
+	assert(ptr != NULL);
+
+	if (unlikely(tcache == NULL)) {
+		arena_dalloc_no_tcache(tsdn, ptr);
+		return;
+	}
+
+	szind_t szind;
+	bool slab;
+	rtree_ctx_t *rtree_ctx;
+	if (alloc_ctx != NULL) {
+		szind = alloc_ctx->szind;
+		slab = alloc_ctx->slab;
+		assert(szind != NSIZES);
+	} else {
+		rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
+		rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &szind, &slab);
+	}
+
+	if (config_debug) {
+		rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
+		extent_t *extent = rtree_extent_read(tsdn, &extents_rtree,
+		    rtree_ctx, (uintptr_t)ptr, true);
+		assert(szind == extent_szind_get(extent));
+		assert(szind < NSIZES);
+		assert(slab == extent_slab_get(extent));
+	}
+
+	if (likely(slab)) {
+		/* Small allocation. */
+		tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind,
+		    slow_path);
+	} else {
+		if (szind < nhbins) {
+			if (config_prof && unlikely(szind < NBINS)) {
+				arena_dalloc_promoted(tsdn, ptr, tcache,
+				    slow_path);
+			} else {
+				tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr,
+				    szind, slow_path);
+			}
+		} else {
+			extent_t *extent = iealloc(tsdn, ptr);
+			large_dalloc(tsdn, extent);
+		}
+	}
+}
+
+static inline void
+arena_sdalloc_no_tcache(tsdn_t *tsdn, void *ptr, size_t size) {
+	assert(ptr != NULL);
+	assert(size <= LARGE_MAXCLASS);
+
+	szind_t szind;
+	bool slab;
+	if (!config_prof || !opt_prof) {
+		/*
+		 * There is no risk of being confused by a promoted sampled
+		 * object, so base szind and slab on the given size.
+		 */
+		szind = sz_size2index(size);
+		slab = (szind < NBINS);
+	}
+
+	if ((config_prof && opt_prof) || config_debug) {
+		rtree_ctx_t rtree_ctx_fallback;
+		rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
+		    &rtree_ctx_fallback);
+
+		rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &szind, &slab);
+
+		assert(szind == sz_size2index(size));
+		assert((config_prof && opt_prof) || slab == (szind < NBINS));
+
+		if (config_debug) {
+			extent_t *extent = rtree_extent_read(tsdn,
+			    &extents_rtree, rtree_ctx, (uintptr_t)ptr, true);
+			assert(szind == extent_szind_get(extent));
+			assert(slab == extent_slab_get(extent));
+		}
+	}
+
+	if (likely(slab)) {
+		/* Small allocation. */
+		arena_dalloc_small(tsdn, ptr);
+	} else {
+		extent_t *extent = iealloc(tsdn, ptr);
+		large_dalloc(tsdn, extent);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_sdalloc(tsdn_t *tsdn, void *ptr, size_t size, tcache_t *tcache,
+    alloc_ctx_t *alloc_ctx, bool slow_path) {
+	assert(!tsdn_null(tsdn) || tcache == NULL);
+	assert(ptr != NULL);
+	assert(size <= LARGE_MAXCLASS);
+
+	if (unlikely(tcache == NULL)) {
+		arena_sdalloc_no_tcache(tsdn, ptr, size);
+		return;
+	}
+
+	szind_t szind;
+	bool slab;
+	UNUSED alloc_ctx_t local_ctx;
+	if (config_prof && opt_prof) {
+		if (alloc_ctx == NULL) {
+			/* Uncommon case and should be a static check. */
+			rtree_ctx_t rtree_ctx_fallback;
+			rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
+			    &rtree_ctx_fallback);
+			rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
+			    (uintptr_t)ptr, true, &local_ctx.szind,
+			    &local_ctx.slab);
+			assert(local_ctx.szind == sz_size2index(size));
+			alloc_ctx = &local_ctx;
+		}
+		slab = alloc_ctx->slab;
+		szind = alloc_ctx->szind;
+	} else {
+		/*
+		 * There is no risk of being confused by a promoted sampled
+		 * object, so base szind and slab on the given size.
+		 */
+		szind = sz_size2index(size);
+		slab = (szind < NBINS);
+	}
+
+	if (config_debug) {
+		rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsdn_tsd(tsdn));
+		rtree_szind_slab_read(tsdn, &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &szind, &slab);
+		extent_t *extent = rtree_extent_read(tsdn,
+		    &extents_rtree, rtree_ctx, (uintptr_t)ptr, true);
+		assert(szind == extent_szind_get(extent));
+		assert(slab == extent_slab_get(extent));
+	}
+
+	if (likely(slab)) {
+		/* Small allocation. */
+		tcache_dalloc_small(tsdn_tsd(tsdn), tcache, ptr, szind,
+		    slow_path);
+	} else {
+		if (szind < nhbins) {
+			if (config_prof && unlikely(szind < NBINS)) {
+				arena_dalloc_promoted(tsdn, ptr, tcache,
+				    slow_path);
+			} else {
+				tcache_dalloc_large(tsdn_tsd(tsdn),
+				    tcache, ptr, szind, slow_path);
+			}
+		} else {
+			extent_t *extent = iealloc(tsdn, ptr);
+			large_dalloc(tsdn, extent);
+		}
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_ARENA_INLINES_B_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_a.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_a.h
new file mode 100644
index 0000000000..46aa77c884
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_a.h
@@ -0,0 +1,11 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H
+#define JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H
+
+#include "jemalloc/internal/bitmap.h"
+
+struct arena_slab_data_s {
+	/* Per region allocated/deallocated bitmap. */
+	bitmap_t	bitmap[BITMAP_GROUPS_MAX];
+};
+
+#endif /* JEMALLOC_INTERNAL_ARENA_STRUCTS_A_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_b.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_b.h
new file mode 100644
index 0000000000..d1fffec193
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_structs_b.h
@@ -0,0 +1,284 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H
+#define JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/bitmap.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/nstime.h"
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/smoothstep.h"
+#include "jemalloc/internal/stats.h"
+#include "jemalloc/internal/ticker.h"
+
+/*
+ * Read-only information associated with each element of arena_t's bins array
+ * is stored separately, partly to reduce memory usage (only one copy, rather
+ * than one per arena), but mainly to avoid false cacheline sharing.
+ *
+ * Each slab has the following layout:
+ *
+ *   /--------------------\
+ *   | region 0           |
+ *   |--------------------|
+ *   | region 1           |
+ *   |--------------------|
+ *   | ...                |
+ *   | ...                |
+ *   | ...                |
+ *   |--------------------|
+ *   | region nregs-1     |
+ *   \--------------------/
+ */
+struct arena_bin_info_s {
+	/* Size of regions in a slab for this bin's size class. */
+	size_t			reg_size;
+
+	/* Total size of a slab for this bin's size class. */
+	size_t			slab_size;
+
+	/* Total number of regions in a slab for this bin's size class. */
+	uint32_t		nregs;
+
+	/*
+	 * Metadata used to manipulate bitmaps for slabs associated with this
+	 * bin.
+	 */
+	bitmap_info_t		bitmap_info;
+};
+
+struct arena_decay_s {
+	/* Synchronizes all non-atomic fields. */
+	malloc_mutex_t		mtx;
+	/*
+	 * True if a thread is currently purging the extents associated with
+	 * this decay structure.
+	 */
+	bool			purging;
+	/*
+	 * Approximate time in milliseconds from the creation of a set of unused
+	 * dirty pages until an equivalent set of unused dirty pages is purged
+	 * and/or reused.
+	 */
+	atomic_zd_t		time_ms;
+	/* time / SMOOTHSTEP_NSTEPS. */
+	nstime_t		interval;
+	/*
+	 * Time at which the current decay interval logically started.  We do
+	 * not actually advance to a new epoch until sometime after it starts
+	 * because of scheduling and computation delays, and it is even possible
+	 * to completely skip epochs.  In all cases, during epoch advancement we
+	 * merge all relevant activity into the most recently recorded epoch.
+	 */
+	nstime_t		epoch;
+	/* Deadline randomness generator. */
+	uint64_t		jitter_state;
+	/*
+	 * Deadline for current epoch.  This is the sum of interval and per
+	 * epoch jitter which is a uniform random variable in [0..interval).
+	 * Epochs always advance by precise multiples of interval, but we
+	 * randomize the deadline to reduce the likelihood of arenas purging in
+	 * lockstep.
+	 */
+	nstime_t		deadline;
+	/*
+	 * Number of unpurged pages at beginning of current epoch.  During epoch
+	 * advancement we use the delta between arena->decay_*.nunpurged and
+	 * extents_npages_get(&arena->extents_*) to determine how many dirty
+	 * pages, if any, were generated.
+	 */
+	size_t			nunpurged;
+	/*
+	 * Trailing log of how many unused dirty pages were generated during
+	 * each of the past SMOOTHSTEP_NSTEPS decay epochs, where the last
+	 * element is the most recent epoch.  Corresponding epoch times are
+	 * relative to epoch.
+	 */
+	size_t			backlog[SMOOTHSTEP_NSTEPS];
+
+	/*
+	 * Pointer to associated stats.  These stats are embedded directly in
+	 * the arena's stats due to how stats structures are shared between the
+	 * arena and ctl code.
+	 *
+	 * Synchronization: Same as associated arena's stats field. */
+	decay_stats_t		*stats;
+	/* Peak number of pages in associated extents.  Used for debug only. */
+	uint64_t		ceil_npages;
+};
+
+struct arena_bin_s {
+	/* All operations on arena_bin_t fields require lock ownership. */
+	malloc_mutex_t		lock;
+
+	/*
+	 * Current slab being used to service allocations of this bin's size
+	 * class.  slabcur is independent of slabs_{nonfull,full}; whenever
+	 * slabcur is reassigned, the previous slab must be deallocated or
+	 * inserted into slabs_{nonfull,full}.
+	 */
+	extent_t		*slabcur;
+
+	/*
+	 * Heap of non-full slabs.  This heap is used to assure that new
+	 * allocations come from the non-full slab that is oldest/lowest in
+	 * memory.
+	 */
+	extent_heap_t		slabs_nonfull;
+
+	/* List used to track full slabs. */
+	extent_list_t		slabs_full;
+
+	/* Bin statistics. */
+	malloc_bin_stats_t	stats;
+};
+
+struct arena_s {
+	/*
+	 * Number of threads currently assigned to this arena.  Each thread has
+	 * two distinct assignments, one for application-serving allocation, and
+	 * the other for internal metadata allocation.  Internal metadata must
+	 * not be allocated from arenas explicitly created via the arenas.create
+	 * mallctl, because the arena.<i>.reset mallctl indiscriminately
+	 * discards all allocations for the affected arena.
+	 *
+	 *   0: Application allocation.
+	 *   1: Internal metadata allocation.
+	 *
+	 * Synchronization: atomic.
+	 */
+	atomic_u_t		nthreads[2];
+
+	/*
+	 * When percpu_arena is enabled, to amortize the cost of reading /
+	 * updating the current CPU id, track the most recent thread accessing
+	 * this arena, and only read CPU if there is a mismatch.
+	 */
+	tsdn_t		*last_thd;
+
+	/* Synchronization: internal. */
+	arena_stats_t		stats;
+
+	/*
+	 * List of tcaches for extant threads associated with this arena.
+	 * Stats from these are merged incrementally, and at exit if
+	 * opt_stats_print is enabled.
+	 *
+	 * Synchronization: tcache_ql_mtx.
+	 */
+	ql_head(tcache_t)	tcache_ql;
+	malloc_mutex_t		tcache_ql_mtx;
+
+	/* Synchronization: internal. */
+	prof_accum_t		prof_accum;
+	uint64_t		prof_accumbytes;
+
+	/*
+	 * PRNG state for cache index randomization of large allocation base
+	 * pointers.
+	 *
+	 * Synchronization: atomic.
+	 */
+	atomic_zu_t		offset_state;
+
+	/*
+	 * Extent serial number generator state.
+	 *
+	 * Synchronization: atomic.
+	 */
+	atomic_zu_t		extent_sn_next;
+
+	/*
+	 * Represents a dss_prec_t, but atomically.
+	 *
+	 * Synchronization: atomic.
+	 */
+	atomic_u_t		dss_prec;
+
+	/*
+	 * Number of pages in active extents.
+	 *
+	 * Synchronization: atomic.
+	 */
+	atomic_zu_t		nactive;
+
+	/*
+	 * Extant large allocations.
+	 *
+	 * Synchronization: large_mtx.
+	 */
+	extent_list_t		large;
+	/* Synchronizes all large allocation/update/deallocation. */
+	malloc_mutex_t		large_mtx;
+
+	/*
+	 * Collections of extents that were previously allocated.  These are
+	 * used when allocating extents, in an attempt to re-use address space.
+	 *
+	 * Synchronization: internal.
+	 */
+	extents_t		extents_dirty;
+	extents_t		extents_muzzy;
+	extents_t		extents_retained;
+
+	/*
+	 * Decay-based purging state, responsible for scheduling extent state
+	 * transitions.
+	 *
+	 * Synchronization: internal.
+	 */
+	arena_decay_t		decay_dirty; /* dirty --> muzzy */
+	arena_decay_t		decay_muzzy; /* muzzy --> retained */
+
+	/*
+	 * Next extent size class in a growing series to use when satisfying a
+	 * request via the extent hooks (only if opt_retain).  This limits the
+	 * number of disjoint virtual memory ranges so that extent merging can
+	 * be effective even if multiple arenas' extent allocation requests are
+	 * highly interleaved.
+	 *
+	 * Synchronization: extent_grow_mtx
+	 */
+	pszind_t		extent_grow_next;
+	malloc_mutex_t		extent_grow_mtx;
+
+	/*
+	 * Available extent structures that were allocated via
+	 * base_alloc_extent().
+	 *
+	 * Synchronization: extent_avail_mtx.
+	 */
+	extent_tree_t		extent_avail;
+	malloc_mutex_t		extent_avail_mtx;
+
+	/*
+	 * bins is used to store heaps of free regions.
+	 *
+	 * Synchronization: internal.
+	 */
+	arena_bin_t		bins[NBINS];
+
+	/*
+	 * Base allocator, from which arena metadata are allocated.
+	 *
+	 * Synchronization: internal.
+	 */
+	base_t			*base;
+	/* Used to determine uptime.  Read-only after initialization. */
+	nstime_t		create_time;
+};
+
+/* Used in conjunction with tsd for fast arena-related context lookup. */
+struct arena_tdata_s {
+	ticker_t		decay_ticker;
+};
+
+/* Used to pass rtree lookup context down the path. */
+struct alloc_ctx_s {
+	szind_t szind;
+	bool slab;
+};
+
+#endif /* JEMALLOC_INTERNAL_ARENA_STRUCTS_B_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_types.h
new file mode 100644
index 0000000000..a691bd811e
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/arena_types.h
@@ -0,0 +1,45 @@
+#ifndef JEMALLOC_INTERNAL_ARENA_TYPES_H
+#define JEMALLOC_INTERNAL_ARENA_TYPES_H
+
+/* Maximum number of regions in one slab. */
+#define LG_SLAB_MAXREGS		(LG_PAGE - LG_TINY_MIN)
+#define SLAB_MAXREGS		(1U << LG_SLAB_MAXREGS)
+
+/* Default decay times in milliseconds. */
+#define DIRTY_DECAY_MS_DEFAULT	ZD(10 * 1000)
+#define MUZZY_DECAY_MS_DEFAULT	ZD(10 * 1000)
+/* Number of event ticks between time checks. */
+#define DECAY_NTICKS_PER_UPDATE	1000
+
+typedef struct arena_slab_data_s arena_slab_data_t;
+typedef struct arena_bin_info_s arena_bin_info_t;
+typedef struct arena_decay_s arena_decay_t;
+typedef struct arena_bin_s arena_bin_t;
+typedef struct arena_s arena_t;
+typedef struct arena_tdata_s arena_tdata_t;
+typedef struct alloc_ctx_s alloc_ctx_t;
+
+typedef enum {
+	percpu_arena_mode_names_base   = 0, /* Used for options processing. */
+
+	/*
+	 * *_uninit are used only during bootstrapping, and must correspond
+	 * to initialized variant plus percpu_arena_mode_enabled_base.
+	 */
+	percpu_arena_uninit            = 0,
+	per_phycpu_arena_uninit        = 1,
+
+	/* All non-disabled modes must come after percpu_arena_disabled. */
+	percpu_arena_disabled          = 2,
+
+	percpu_arena_mode_names_limit  = 3, /* Used for options processing. */
+	percpu_arena_mode_enabled_base = 3,
+
+	percpu_arena                   = 3,
+	per_phycpu_arena               = 4  /* Hyper threads share arena. */
+} percpu_arena_mode_t;
+
+#define PERCPU_ARENA_ENABLED(m)	((m) >= percpu_arena_mode_enabled_base)
+#define PERCPU_ARENA_DEFAULT	percpu_arena_disabled
+
+#endif /* JEMALLOC_INTERNAL_ARENA_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/assert.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/assert.h
new file mode 100644
index 0000000000..be4d45b321
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/assert.h
@@ -0,0 +1,56 @@
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/util.h"
+
+/*
+ * Define a custom assert() in order to reduce the chances of deadlock during
+ * assertion failure.
+ */
+#ifndef assert
+#define assert(e) do {							\
+	if (unlikely(config_debug && !(e))) {				\
+		malloc_printf(						\
+		    "<jemalloc>: %s:%d: Failed assertion: \"%s\"\n",	\
+		    __FILE__, __LINE__, #e);				\
+		abort();						\
+	}								\
+} while (0)
+#endif
+
+#ifndef not_reached
+#define not_reached() do {						\
+	if (config_debug) {						\
+		malloc_printf(						\
+		    "<jemalloc>: %s:%d: Unreachable code reached\n",	\
+		    __FILE__, __LINE__);				\
+		abort();						\
+	}								\
+	unreachable();							\
+} while (0)
+#endif
+
+#ifndef not_implemented
+#define not_implemented() do {						\
+	if (config_debug) {						\
+		malloc_printf("<jemalloc>: %s:%d: Not implemented\n",	\
+		    __FILE__, __LINE__);				\
+		abort();						\
+	}								\
+} while (0)
+#endif
+
+#ifndef assert_not_implemented
+#define assert_not_implemented(e) do {					\
+	if (unlikely(config_debug && !(e))) {				\
+		not_implemented();					\
+	}								\
+} while (0)
+#endif
+
+/* Use to assert a particular configuration, e.g., cassert(config_debug). */
+#ifndef cassert
+#define cassert(c) do {							\
+	if (unlikely(!(c))) {						\
+		not_reached();						\
+	}								\
+} while (0)
+#endif
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic.h
index 11a7b47fe0..adadb1a3ac 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic.h
@@ -1,304 +1,77 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
-
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-#define	atomic_read_uint64(p)	atomic_add_uint64(p, 0)
-#define	atomic_read_uint32(p)	atomic_add_uint32(p, 0)
-#define	atomic_read_z(p)	atomic_add_z(p, 0)
-#define	atomic_read_u(p)	atomic_add_u(p, 0)
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-#ifndef JEMALLOC_ENABLE_INLINE
-uint64_t	atomic_add_uint64(uint64_t *p, uint64_t x);
-uint64_t	atomic_sub_uint64(uint64_t *p, uint64_t x);
-uint32_t	atomic_add_uint32(uint32_t *p, uint32_t x);
-uint32_t	atomic_sub_uint32(uint32_t *p, uint32_t x);
-size_t	atomic_add_z(size_t *p, size_t x);
-size_t	atomic_sub_z(size_t *p, size_t x);
-unsigned	atomic_add_u(unsigned *p, unsigned x);
-unsigned	atomic_sub_u(unsigned *p, unsigned x);
+#ifndef JEMALLOC_INTERNAL_ATOMIC_H
+#define JEMALLOC_INTERNAL_ATOMIC_H
+
+#define ATOMIC_INLINE static inline
+
+#if defined(JEMALLOC_GCC_ATOMIC_ATOMICS)
+#  include "jemalloc/internal/atomic_gcc_atomic.h"
+#elif defined(JEMALLOC_GCC_SYNC_ATOMICS)
+#  include "jemalloc/internal/atomic_gcc_sync.h"
+#elif defined(_MSC_VER)
+#  include "jemalloc/internal/atomic_msvc.h"
+#elif defined(JEMALLOC_C11_ATOMICS)
+#  include "jemalloc/internal/atomic_c11.h"
+#else
+#  error "Don't have atomics implemented on this platform."
 #endif
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_ATOMIC_C_))
-/******************************************************************************/
-/* 64-bit operations. */
+/*
+ * This header gives more or less a backport of C11 atomics. The user can write
+ * JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_sizeof_type); to generate
+ * counterparts of the C11 atomic functions for type, as so:
+ *   JEMALLOC_GENERATE_ATOMICS(int *, pi, 3);
+ * and then write things like:
+ *   int *some_ptr;
+ *   atomic_pi_t atomic_ptr_to_int;
+ *   atomic_store_pi(&atomic_ptr_to_int, some_ptr, ATOMIC_RELAXED);
+ *   int *prev_value = atomic_exchange_pi(&ptr_to_int, NULL, ATOMIC_ACQ_REL);
+ *   assert(some_ptr == prev_value);
+ * and expect things to work in the obvious way.
+ *
+ * Also included (with naming differences to avoid conflicts with the standard
+ * library):
+ *   atomic_fence(atomic_memory_order_t) (mimics C11's atomic_thread_fence).
+ *   ATOMIC_INIT (mimics C11's ATOMIC_VAR_INIT).
+ */
+
+/*
+ * Pure convenience, so that we don't have to type "atomic_memory_order_"
+ * quite so often.
+ */
+#define ATOMIC_RELAXED atomic_memory_order_relaxed
+#define ATOMIC_ACQUIRE atomic_memory_order_acquire
+#define ATOMIC_RELEASE atomic_memory_order_release
+#define ATOMIC_ACQ_REL atomic_memory_order_acq_rel
+#define ATOMIC_SEQ_CST atomic_memory_order_seq_cst
+
+/*
+ * Not all platforms have 64-bit atomics.  If we do, this #define exposes that
+ * fact.
+ */
 #if (LG_SIZEOF_PTR == 3 || LG_SIZEOF_INT == 3)
-#  ifdef __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (__sync_add_and_fetch(p, x));
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (__sync_sub_and_fetch(p, x));
-}
-#elif (defined(_MSC_VER))
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (InterlockedExchangeAdd64(p, x));
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (InterlockedExchangeAdd64(p, -((int64_t)x)));
-}
-#elif (defined(JEMALLOC_OSATOMIC))
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (OSAtomicAdd64((int64_t)x, (int64_t *)p));
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (OSAtomicAdd64(-((int64_t)x), (int64_t *)p));
-}
-#  elif (defined(__amd64__) || defined(__x86_64__))
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	asm volatile (
-	    "lock; xaddq %0, %1;"
-	    : "+r" (x), "=m" (*p) /* Outputs. */
-	    : "m" (*p) /* Inputs. */
-	    );
-
-	return (x);
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	x = (uint64_t)(-(int64_t)x);
-	asm volatile (
-	    "lock; xaddq %0, %1;"
-	    : "+r" (x), "=m" (*p) /* Outputs. */
-	    : "m" (*p) /* Inputs. */
-	    );
-
-	return (x);
-}
-#  elif (defined(JEMALLOC_ATOMIC9))
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	/*
-	 * atomic_fetchadd_64() doesn't exist, but we only ever use this
-	 * function on LP64 systems, so atomic_fetchadd_long() will do.
-	 */
-	assert(sizeof(uint64_t) == sizeof(unsigned long));
-
-	return (atomic_fetchadd_long(p, (unsigned long)x) + x);
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	assert(sizeof(uint64_t) == sizeof(unsigned long));
-
-	return (atomic_fetchadd_long(p, (unsigned long)(-(long)x)) - x);
-}
-#  elif (defined(JE_FORCE_SYNC_COMPARE_AND_SWAP_8))
-JEMALLOC_INLINE uint64_t
-atomic_add_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (__sync_add_and_fetch(p, x));
-}
-
-JEMALLOC_INLINE uint64_t
-atomic_sub_uint64(uint64_t *p, uint64_t x)
-{
-
-	return (__sync_sub_and_fetch(p, x));
-}
-#  else
-#    error "Missing implementation for 64-bit atomic operations"
-#  endif
+#  define JEMALLOC_ATOMIC_U64
 #endif
 
-/******************************************************************************/
-/* 32-bit operations. */
-#ifdef __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
+JEMALLOC_GENERATE_ATOMICS(void *, p, LG_SIZEOF_PTR)
 
-	return (__sync_add_and_fetch(p, x));
-}
+/*
+ * There's no actual guarantee that sizeof(bool) == 1, but it's true on the only
+ * platform that actually needs to know the size, MSVC.
+ */
+JEMALLOC_GENERATE_ATOMICS(bool, b, 0)
 
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
+JEMALLOC_GENERATE_INT_ATOMICS(unsigned, u, LG_SIZEOF_INT)
 
-	return (__sync_sub_and_fetch(p, x));
-}
-#elif (defined(_MSC_VER))
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
+JEMALLOC_GENERATE_INT_ATOMICS(size_t, zu, LG_SIZEOF_PTR)
 
-	return (InterlockedExchangeAdd(p, x));
-}
+JEMALLOC_GENERATE_INT_ATOMICS(ssize_t, zd, LG_SIZEOF_PTR)
 
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
+JEMALLOC_GENERATE_INT_ATOMICS(uint32_t, u32, 2)
 
-	return (InterlockedExchangeAdd(p, -((int32_t)x)));
-}
-#elif (defined(JEMALLOC_OSATOMIC))
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (OSAtomicAdd32((int32_t)x, (int32_t *)p));
-}
-
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (OSAtomicAdd32(-((int32_t)x), (int32_t *)p));
-}
-#elif (defined(__i386__) || defined(__amd64__) || defined(__x86_64__))
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
-
-	asm volatile (
-	    "lock; xaddl %0, %1;"
-	    : "+r" (x), "=m" (*p) /* Outputs. */
-	    : "m" (*p) /* Inputs. */
-	    );
-
-	return (x);
-}
-
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
-
-	x = (uint32_t)(-(int32_t)x);
-	asm volatile (
-	    "lock; xaddl %0, %1;"
-	    : "+r" (x), "=m" (*p) /* Outputs. */
-	    : "m" (*p) /* Inputs. */
-	    );
-
-	return (x);
-}
-#elif (defined(JEMALLOC_ATOMIC9))
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (atomic_fetchadd_32(p, x) + x);
-}
-
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (atomic_fetchadd_32(p, (uint32_t)(-(int32_t)x)) - x);
-}
-#elif (defined(JE_FORCE_SYNC_COMPARE_AND_SWAP_4))
-JEMALLOC_INLINE uint32_t
-atomic_add_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (__sync_add_and_fetch(p, x));
-}
-
-JEMALLOC_INLINE uint32_t
-atomic_sub_uint32(uint32_t *p, uint32_t x)
-{
-
-	return (__sync_sub_and_fetch(p, x));
-}
-#else
-#  error "Missing implementation for 32-bit atomic operations"
-#endif
-
-/******************************************************************************/
-/* size_t operations. */
-JEMALLOC_INLINE size_t
-atomic_add_z(size_t *p, size_t x)
-{
-
-#if (LG_SIZEOF_PTR == 3)
-	return ((size_t)atomic_add_uint64((uint64_t *)p, (uint64_t)x));
-#elif (LG_SIZEOF_PTR == 2)
-	return ((size_t)atomic_add_uint32((uint32_t *)p, (uint32_t)x));
-#endif
-}
-
-JEMALLOC_INLINE size_t
-atomic_sub_z(size_t *p, size_t x)
-{
-
-#if (LG_SIZEOF_PTR == 3)
-	return ((size_t)atomic_add_uint64((uint64_t *)p,
-	    (uint64_t)-((int64_t)x)));
-#elif (LG_SIZEOF_PTR == 2)
-	return ((size_t)atomic_add_uint32((uint32_t *)p,
-	    (uint32_t)-((int32_t)x)));
+#ifdef JEMALLOC_ATOMIC_U64
+JEMALLOC_GENERATE_INT_ATOMICS(uint64_t, u64, 3)
 #endif
-}
 
-/******************************************************************************/
-/* unsigned operations. */
-JEMALLOC_INLINE unsigned
-atomic_add_u(unsigned *p, unsigned x)
-{
-
-#if (LG_SIZEOF_INT == 3)
-	return ((unsigned)atomic_add_uint64((uint64_t *)p, (uint64_t)x));
-#elif (LG_SIZEOF_INT == 2)
-	return ((unsigned)atomic_add_uint32((uint32_t *)p, (uint32_t)x));
-#endif
-}
-
-JEMALLOC_INLINE unsigned
-atomic_sub_u(unsigned *p, unsigned x)
-{
-
-#if (LG_SIZEOF_INT == 3)
-	return ((unsigned)atomic_add_uint64((uint64_t *)p,
-	    (uint64_t)-((int64_t)x)));
-#elif (LG_SIZEOF_INT == 2)
-	return ((unsigned)atomic_add_uint32((uint32_t *)p,
-	    (uint32_t)-((int32_t)x)));
-#endif
-}
-/******************************************************************************/
-#endif
+#undef ATOMIC_INLINE
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_ATOMIC_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_c11.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_c11.h
new file mode 100644
index 0000000000..a5f9313a61
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_c11.h
@@ -0,0 +1,97 @@
+#ifndef JEMALLOC_INTERNAL_ATOMIC_C11_H
+#define JEMALLOC_INTERNAL_ATOMIC_C11_H
+
+#include <stdatomic.h>
+
+#define ATOMIC_INIT(...) ATOMIC_VAR_INIT(__VA_ARGS__)
+
+#define atomic_memory_order_t memory_order
+#define atomic_memory_order_relaxed memory_order_relaxed
+#define atomic_memory_order_acquire memory_order_acquire
+#define atomic_memory_order_release memory_order_release
+#define atomic_memory_order_acq_rel memory_order_acq_rel
+#define atomic_memory_order_seq_cst memory_order_seq_cst
+
+#define atomic_fence atomic_thread_fence
+
+#define JEMALLOC_GENERATE_ATOMICS(type, short_type,			\
+    /* unused */ lg_size)						\
+typedef _Atomic(type) atomic_##short_type##_t;				\
+									\
+ATOMIC_INLINE type							\
+atomic_load_##short_type(const atomic_##short_type##_t *a,		\
+    atomic_memory_order_t mo) {						\
+	/*								\
+	 * A strict interpretation of the C standard prevents		\
+	 * atomic_load from taking a const argument, but it's		\
+	 * convenient for our purposes. This cast is a workaround.	\
+	 */								\
+	atomic_##short_type##_t* a_nonconst =				\
+	    (atomic_##short_type##_t*)a;				\
+	return atomic_load_explicit(a_nonconst, mo);			\
+}									\
+									\
+ATOMIC_INLINE void							\
+atomic_store_##short_type(atomic_##short_type##_t *a,			\
+    type val, atomic_memory_order_t mo) {				\
+	atomic_store_explicit(a, val, mo);				\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_exchange_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return atomic_exchange_explicit(a, val, mo);			\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	return atomic_compare_exchange_weak_explicit(a, expected,	\
+	    desired, success_mo, failure_mo);				\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	return atomic_compare_exchange_strong_explicit(a, expected,	\
+	    desired, success_mo, failure_mo);				\
+}
+
+/*
+ * Integral types have some special operations available that non-integral ones
+ * lack.
+ */
+#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, 		\
+    /* unused */ lg_size)						\
+JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size)	\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_add_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return atomic_fetch_add_explicit(a, val, mo);			\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_sub_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return atomic_fetch_sub_explicit(a, val, mo);			\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_and_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return atomic_fetch_and_explicit(a, val, mo);			\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_or_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return atomic_fetch_or_explicit(a, val, mo);			\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_xor_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return atomic_fetch_xor_explicit(a, val, mo);			\
+}
+
+#endif /* JEMALLOC_INTERNAL_ATOMIC_C11_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h
new file mode 100644
index 0000000000..6b73a14f81
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_atomic.h
@@ -0,0 +1,127 @@
+#ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H
+#define JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H
+
+#include "jemalloc/internal/assert.h"
+
+#define ATOMIC_INIT(...) {__VA_ARGS__}
+
+typedef enum {
+	atomic_memory_order_relaxed,
+	atomic_memory_order_acquire,
+	atomic_memory_order_release,
+	atomic_memory_order_acq_rel,
+	atomic_memory_order_seq_cst
+} atomic_memory_order_t;
+
+ATOMIC_INLINE int
+atomic_enum_to_builtin(atomic_memory_order_t mo) {
+	switch (mo) {
+	case atomic_memory_order_relaxed:
+		return __ATOMIC_RELAXED;
+	case atomic_memory_order_acquire:
+		return __ATOMIC_ACQUIRE;
+	case atomic_memory_order_release:
+		return __ATOMIC_RELEASE;
+	case atomic_memory_order_acq_rel:
+		return __ATOMIC_ACQ_REL;
+	case atomic_memory_order_seq_cst:
+		return __ATOMIC_SEQ_CST;
+	}
+	/* Can't happen; the switch is exhaustive. */
+	not_reached();
+}
+
+ATOMIC_INLINE void
+atomic_fence(atomic_memory_order_t mo) {
+	__atomic_thread_fence(atomic_enum_to_builtin(mo));
+}
+
+#define JEMALLOC_GENERATE_ATOMICS(type, short_type,			\
+    /* unused */ lg_size)						\
+typedef struct {							\
+	type repr;							\
+} atomic_##short_type##_t;						\
+									\
+ATOMIC_INLINE type							\
+atomic_load_##short_type(const atomic_##short_type##_t *a,		\
+    atomic_memory_order_t mo) {						\
+	type result;							\
+	__atomic_load(&a->repr, &result, atomic_enum_to_builtin(mo));	\
+	return result;							\
+}									\
+									\
+ATOMIC_INLINE void							\
+atomic_store_##short_type(atomic_##short_type##_t *a, type val,		\
+    atomic_memory_order_t mo) {						\
+	__atomic_store(&a->repr, &val, atomic_enum_to_builtin(mo));	\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_exchange_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	type result;							\
+	__atomic_exchange(&a->repr, &val, &result,			\
+	    atomic_enum_to_builtin(mo));				\
+	return result;							\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	return __atomic_compare_exchange(&a->repr, expected, &desired,	\
+	    true, atomic_enum_to_builtin(success_mo),			\
+	    atomic_enum_to_builtin(failure_mo));			\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	return __atomic_compare_exchange(&a->repr, expected, &desired,	\
+	    false,							\
+	    atomic_enum_to_builtin(success_mo),				\
+	    atomic_enum_to_builtin(failure_mo));			\
+}
+
+
+#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type,			\
+    /* unused */ lg_size)						\
+JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size)	\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __atomic_fetch_add(&a->repr, val,			\
+	    atomic_enum_to_builtin(mo));				\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __atomic_fetch_sub(&a->repr, val,			\
+	    atomic_enum_to_builtin(mo));				\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __atomic_fetch_and(&a->repr, val,			\
+	    atomic_enum_to_builtin(mo));				\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __atomic_fetch_or(&a->repr, val,				\
+	    atomic_enum_to_builtin(mo));				\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __atomic_fetch_xor(&a->repr, val,			\
+	    atomic_enum_to_builtin(mo));				\
+}
+
+#endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_ATOMIC_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h
new file mode 100644
index 0000000000..30846e4d27
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_gcc_sync.h
@@ -0,0 +1,191 @@
+#ifndef JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H
+#define JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H
+
+#define ATOMIC_INIT(...) {__VA_ARGS__}
+
+typedef enum {
+	atomic_memory_order_relaxed,
+	atomic_memory_order_acquire,
+	atomic_memory_order_release,
+	atomic_memory_order_acq_rel,
+	atomic_memory_order_seq_cst
+} atomic_memory_order_t;
+
+ATOMIC_INLINE void
+atomic_fence(atomic_memory_order_t mo) {
+	/* Easy cases first: no barrier, and full barrier. */
+	if (mo == atomic_memory_order_relaxed) {
+		asm volatile("" ::: "memory");
+		return;
+	}
+	if (mo == atomic_memory_order_seq_cst) {
+		asm volatile("" ::: "memory");
+		__sync_synchronize();
+		asm volatile("" ::: "memory");
+		return;
+	}
+	asm volatile("" ::: "memory");
+#  if defined(__i386__) || defined(__x86_64__)
+	/* This is implicit on x86. */
+#  elif defined(__ppc__)
+	asm volatile("lwsync");
+#  elif defined(__sparc__) && defined(__arch64__)
+	if (mo == atomic_memory_order_acquire) {
+		asm volatile("membar #LoadLoad | #LoadStore");
+	} else if (mo == atomic_memory_order_release) {
+		asm volatile("membar #LoadStore | #StoreStore");
+	} else {
+		asm volatile("membar #LoadLoad | #LoadStore | #StoreStore");
+	}
+#  else
+	__sync_synchronize();
+#  endif
+	asm volatile("" ::: "memory");
+}
+
+/*
+ * A correct implementation of seq_cst loads and stores on weakly ordered
+ * architectures could do either of the following:
+ *   1. store() is weak-fence -> store -> strong fence, load() is load ->
+ *      strong-fence.
+ *   2. store() is strong-fence -> store, load() is strong-fence -> load ->
+ *      weak-fence.
+ * The tricky thing is, load() and store() above can be the load or store
+ * portions of a gcc __sync builtin, so we have to follow GCC's lead, which
+ * means going with strategy 2.
+ * On strongly ordered architectures, the natural strategy is to stick a strong
+ * fence after seq_cst stores, and have naked loads.  So we want the strong
+ * fences in different places on different architectures.
+ * atomic_pre_sc_load_fence and atomic_post_sc_store_fence allow us to
+ * accomplish this.
+ */
+
+ATOMIC_INLINE void
+atomic_pre_sc_load_fence() {
+#  if defined(__i386__) || defined(__x86_64__) ||			\
+    (defined(__sparc__) && defined(__arch64__))
+	atomic_fence(atomic_memory_order_relaxed);
+#  else
+	atomic_fence(atomic_memory_order_seq_cst);
+#  endif
+}
+
+ATOMIC_INLINE void
+atomic_post_sc_store_fence() {
+#  if defined(__i386__) || defined(__x86_64__) ||			\
+    (defined(__sparc__) && defined(__arch64__))
+	atomic_fence(atomic_memory_order_seq_cst);
+#  else
+	atomic_fence(atomic_memory_order_relaxed);
+#  endif
+
+}
+
+#define JEMALLOC_GENERATE_ATOMICS(type, short_type,			\
+    /* unused */ lg_size)						\
+typedef struct {							\
+	type volatile repr;						\
+} atomic_##short_type##_t;						\
+									\
+ATOMIC_INLINE type							\
+atomic_load_##short_type(const atomic_##short_type##_t *a,		\
+    atomic_memory_order_t mo) {						\
+	if (mo == atomic_memory_order_seq_cst) {			\
+		atomic_pre_sc_load_fence();				\
+	}								\
+	type result = a->repr;						\
+	if (mo != atomic_memory_order_relaxed) {			\
+		atomic_fence(atomic_memory_order_acquire);		\
+	}								\
+	return result;							\
+}									\
+									\
+ATOMIC_INLINE void							\
+atomic_store_##short_type(atomic_##short_type##_t *a,			\
+    type val, atomic_memory_order_t mo) {				\
+	if (mo != atomic_memory_order_relaxed) {			\
+		atomic_fence(atomic_memory_order_release);		\
+	}								\
+	a->repr = val;							\
+	if (mo == atomic_memory_order_seq_cst) {			\
+		atomic_post_sc_store_fence();				\
+	}								\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_exchange_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	/*								\
+	 * Because of FreeBSD, we care about gcc 4.2, which doesn't have\
+	 * an atomic exchange builtin.  We fake it with a CAS loop.	\
+	 */								\
+	while (true) {							\
+		type old = a->repr;					\
+		if (__sync_bool_compare_and_swap(&a->repr, old, val)) {	\
+			return old;					\
+		}							\
+	}								\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	type prev = __sync_val_compare_and_swap(&a->repr, *expected,	\
+	    desired);							\
+	if (prev == *expected) {					\
+		return true;						\
+	} else {							\
+		*expected = prev;					\
+		return false;						\
+	}								\
+}									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	type prev = __sync_val_compare_and_swap(&a->repr, *expected,	\
+	    desired);							\
+	if (prev == *expected) {					\
+		return true;						\
+	} else {							\
+		*expected = prev;					\
+		return false;						\
+	}								\
+}
+
+#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type,			\
+    /* unused */ lg_size)						\
+JEMALLOC_GENERATE_ATOMICS(type, short_type, /* unused */ lg_size)	\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_add_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __sync_fetch_and_add(&a->repr, val);			\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_sub_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __sync_fetch_and_sub(&a->repr, val);			\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_and_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __sync_fetch_and_and(&a->repr, val);			\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_or_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __sync_fetch_and_or(&a->repr, val);			\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_xor_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return __sync_fetch_and_xor(&a->repr, val);			\
+}
+
+#endif /* JEMALLOC_INTERNAL_ATOMIC_GCC_SYNC_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_msvc.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_msvc.h
new file mode 100644
index 0000000000..67057ce508
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/atomic_msvc.h
@@ -0,0 +1,158 @@
+#ifndef JEMALLOC_INTERNAL_ATOMIC_MSVC_H
+#define JEMALLOC_INTERNAL_ATOMIC_MSVC_H
+
+#define ATOMIC_INIT(...) {__VA_ARGS__}
+
+typedef enum {
+	atomic_memory_order_relaxed,
+	atomic_memory_order_acquire,
+	atomic_memory_order_release,
+	atomic_memory_order_acq_rel,
+	atomic_memory_order_seq_cst
+} atomic_memory_order_t;
+
+typedef char atomic_repr_0_t;
+typedef short atomic_repr_1_t;
+typedef long atomic_repr_2_t;
+typedef __int64 atomic_repr_3_t;
+
+ATOMIC_INLINE void
+atomic_fence(atomic_memory_order_t mo) {
+	_ReadWriteBarrier();
+#  if defined(_M_ARM) || defined(_M_ARM64)
+	/* ARM needs a barrier for everything but relaxed. */
+	if (mo != atomic_memory_order_relaxed) {
+		MemoryBarrier();
+	}
+#  elif defined(_M_IX86) || defined (_M_X64)
+	/* x86 needs a barrier only for seq_cst. */
+	if (mo == atomic_memory_order_seq_cst) {
+		MemoryBarrier();
+	}
+#  else
+#  error "Don't know how to create atomics for this platform for MSVC."
+#  endif
+	_ReadWriteBarrier();
+}
+
+#define ATOMIC_INTERLOCKED_REPR(lg_size) atomic_repr_ ## lg_size ## _t
+
+#define ATOMIC_CONCAT(a, b) ATOMIC_RAW_CONCAT(a, b)
+#define ATOMIC_RAW_CONCAT(a, b) a ## b
+
+#define ATOMIC_INTERLOCKED_NAME(base_name, lg_size) ATOMIC_CONCAT(	\
+    base_name, ATOMIC_INTERLOCKED_SUFFIX(lg_size))
+
+#define ATOMIC_INTERLOCKED_SUFFIX(lg_size)				\
+    ATOMIC_CONCAT(ATOMIC_INTERLOCKED_SUFFIX_, lg_size)
+
+#define ATOMIC_INTERLOCKED_SUFFIX_0 8
+#define ATOMIC_INTERLOCKED_SUFFIX_1 16
+#define ATOMIC_INTERLOCKED_SUFFIX_2
+#define ATOMIC_INTERLOCKED_SUFFIX_3 64
+
+#define JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_size)		\
+typedef struct {							\
+	ATOMIC_INTERLOCKED_REPR(lg_size) repr;				\
+} atomic_##short_type##_t;						\
+									\
+ATOMIC_INLINE type							\
+atomic_load_##short_type(const atomic_##short_type##_t *a,		\
+    atomic_memory_order_t mo) {						\
+	ATOMIC_INTERLOCKED_REPR(lg_size) ret = a->repr;			\
+	if (mo != atomic_memory_order_relaxed) {			\
+		atomic_fence(atomic_memory_order_acquire);		\
+	}								\
+	return (type) ret;						\
+}									\
+									\
+ATOMIC_INLINE void							\
+atomic_store_##short_type(atomic_##short_type##_t *a,			\
+    type val, atomic_memory_order_t mo) {				\
+	if (mo != atomic_memory_order_relaxed) {			\
+		atomic_fence(atomic_memory_order_release);		\
+	}								\
+	a->repr = (ATOMIC_INTERLOCKED_REPR(lg_size)) val;		\
+	if (mo == atomic_memory_order_seq_cst) {			\
+		atomic_fence(atomic_memory_order_seq_cst);		\
+	}								\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_exchange_##short_type(atomic_##short_type##_t *a, type val,	\
+    atomic_memory_order_t mo) {						\
+	return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedExchange,	\
+	    lg_size)(&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val);	\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_weak_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	ATOMIC_INTERLOCKED_REPR(lg_size) e =				\
+	    (ATOMIC_INTERLOCKED_REPR(lg_size))*expected;		\
+	ATOMIC_INTERLOCKED_REPR(lg_size) d =				\
+	    (ATOMIC_INTERLOCKED_REPR(lg_size))desired;			\
+	ATOMIC_INTERLOCKED_REPR(lg_size) old =				\
+	    ATOMIC_INTERLOCKED_NAME(_InterlockedCompareExchange, 	\
+		lg_size)(&a->repr, d, e);				\
+	if (old == e) {							\
+		return true;						\
+	} else {							\
+		*expected = (type)old;					\
+		return false;						\
+	}								\
+}									\
+									\
+ATOMIC_INLINE bool							\
+atomic_compare_exchange_strong_##short_type(atomic_##short_type##_t *a,	\
+    type *expected, type desired, atomic_memory_order_t success_mo,	\
+    atomic_memory_order_t failure_mo) {					\
+	/* We implement the weak version with strong semantics. */	\
+	return atomic_compare_exchange_weak_##short_type(a, expected,	\
+	    desired, success_mo, failure_mo);				\
+}
+
+
+#define JEMALLOC_GENERATE_INT_ATOMICS(type, short_type, lg_size)	\
+JEMALLOC_GENERATE_ATOMICS(type, short_type, lg_size)			\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_add_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedExchangeAdd,	\
+	    lg_size)(&a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val);	\
+}									\
+									\
+ATOMIC_INLINE type							\
+atomic_fetch_sub_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	/*								\
+	 * MSVC warns on negation of unsigned operands, but for us it	\
+	 * gives exactly the right semantics (MAX_TYPE + 1 - operand).	\
+	 */								\
+	__pragma(warning(push))						\
+	__pragma(warning(disable: 4146))				\
+	return atomic_fetch_add_##short_type(a, -val, mo);		\
+	__pragma(warning(pop))						\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_and_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedAnd, lg_size)(	\
+	    &a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val);		\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_or_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedOr, lg_size)(	\
+	    &a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val);		\
+}									\
+ATOMIC_INLINE type							\
+atomic_fetch_xor_##short_type(atomic_##short_type##_t *a,		\
+    type val, atomic_memory_order_t mo) {				\
+	return (type)ATOMIC_INTERLOCKED_NAME(_InterlockedXor, lg_size)(	\
+	    &a->repr, (ATOMIC_INTERLOCKED_REPR(lg_size))val);		\
+}
+
+#endif /* JEMALLOC_INTERNAL_ATOMIC_MSVC_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_externs.h
new file mode 100644
index 0000000000..8b4b8471a9
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_externs.h
@@ -0,0 +1,31 @@
+#ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H
+#define JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H
+
+extern bool opt_background_thread;
+extern malloc_mutex_t background_thread_lock;
+extern atomic_b_t background_thread_enabled_state;
+extern size_t n_background_threads;
+extern background_thread_info_t *background_thread_info;
+extern bool can_enable_background_thread;
+
+bool background_thread_create(tsd_t *tsd, unsigned arena_ind);
+bool background_threads_enable(tsd_t *tsd);
+bool background_threads_disable(tsd_t *tsd);
+void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena,
+    arena_decay_t *decay, size_t npages_new);
+void background_thread_prefork0(tsdn_t *tsdn);
+void background_thread_prefork1(tsdn_t *tsdn);
+void background_thread_postfork_parent(tsdn_t *tsdn);
+void background_thread_postfork_child(tsdn_t *tsdn);
+bool background_thread_stats_read(tsdn_t *tsdn,
+    background_thread_stats_t *stats);
+void background_thread_ctl_init(tsdn_t *tsdn);
+
+#ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER
+extern int pthread_create_wrapper(pthread_t *__restrict, const pthread_attr_t *,
+    void *(*)(void *), void *__restrict);
+#endif
+bool background_thread_boot0(void);
+bool background_thread_boot1(tsdn_t *tsdn);
+
+#endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_inlines.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_inlines.h
new file mode 100644
index 0000000000..ef50231e8d
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_inlines.h
@@ -0,0 +1,57 @@
+#ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H
+#define JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H
+
+JEMALLOC_ALWAYS_INLINE bool
+background_thread_enabled(void) {
+	return atomic_load_b(&background_thread_enabled_state, ATOMIC_RELAXED);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+background_thread_enabled_set(tsdn_t *tsdn, bool state) {
+	malloc_mutex_assert_owner(tsdn, &background_thread_lock);
+	atomic_store_b(&background_thread_enabled_state, state, ATOMIC_RELAXED);
+}
+
+JEMALLOC_ALWAYS_INLINE background_thread_info_t *
+arena_background_thread_info_get(arena_t *arena) {
+	unsigned arena_ind = arena_ind_get(arena);
+	return &background_thread_info[arena_ind % ncpus];
+}
+
+JEMALLOC_ALWAYS_INLINE uint64_t
+background_thread_wakeup_time_get(background_thread_info_t *info) {
+	uint64_t next_wakeup = nstime_ns(&info->next_wakeup);
+	assert(atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE) ==
+	    (next_wakeup == BACKGROUND_THREAD_INDEFINITE_SLEEP));
+	return next_wakeup;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+background_thread_wakeup_time_set(tsdn_t *tsdn, background_thread_info_t *info,
+    uint64_t wakeup_time) {
+	malloc_mutex_assert_owner(tsdn, &info->mtx);
+	atomic_store_b(&info->indefinite_sleep,
+	    wakeup_time == BACKGROUND_THREAD_INDEFINITE_SLEEP, ATOMIC_RELEASE);
+	nstime_init(&info->next_wakeup, wakeup_time);
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+background_thread_indefinite_sleep(background_thread_info_t *info) {
+	return atomic_load_b(&info->indefinite_sleep, ATOMIC_ACQUIRE);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+arena_background_thread_inactivity_check(tsdn_t *tsdn, arena_t *arena,
+    bool is_background_thread) {
+	if (!background_thread_enabled() || is_background_thread) {
+		return;
+	}
+	background_thread_info_t *info =
+	    arena_background_thread_info_get(arena);
+	if (background_thread_indefinite_sleep(info)) {
+		background_thread_interval_check(tsdn, arena,
+		    &arena->decay_dirty, 0);
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_INLINES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_structs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_structs.h
new file mode 100644
index 0000000000..e69a7d022b
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/background_thread_structs.h
@@ -0,0 +1,52 @@
+#ifndef JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H
+#define JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H
+
+/* This file really combines "structs" and "types", but only transitionally. */
+
+#if defined(JEMALLOC_BACKGROUND_THREAD) || defined(JEMALLOC_LAZY_LOCK)
+#  define JEMALLOC_PTHREAD_CREATE_WRAPPER
+#endif
+
+#define BACKGROUND_THREAD_INDEFINITE_SLEEP UINT64_MAX
+
+typedef enum {
+	background_thread_stopped,
+	background_thread_started,
+	/* Thread waits on the global lock when paused (for arena_reset). */
+	background_thread_paused,
+} background_thread_state_t;
+
+struct background_thread_info_s {
+#ifdef JEMALLOC_BACKGROUND_THREAD
+	/* Background thread is pthread specific. */
+	pthread_t		thread;
+	pthread_cond_t		cond;
+#endif
+	malloc_mutex_t		mtx;
+	background_thread_state_t	state;
+	/* When true, it means no wakeup scheduled. */
+	atomic_b_t		indefinite_sleep;
+	/* Next scheduled wakeup time (absolute time in ns). */
+	nstime_t		next_wakeup;
+	/*
+	 *  Since the last background thread run, newly added number of pages
+	 *  that need to be purged by the next wakeup.  This is adjusted on
+	 *  epoch advance, and is used to determine whether we should signal the
+	 *  background thread to wake up earlier.
+	 */
+	size_t			npages_to_purge_new;
+	/* Stats: total number of runs since started. */
+	uint64_t		tot_n_runs;
+	/* Stats: total sleep time since started. */
+	nstime_t		tot_sleep_time;
+};
+typedef struct background_thread_info_s background_thread_info_t;
+
+struct background_thread_stats_s {
+	size_t num_threads;
+	uint64_t num_runs;
+	nstime_t run_interval;
+};
+typedef struct background_thread_stats_s background_thread_stats_t;
+
+#endif /* JEMALLOC_INTERNAL_BACKGROUND_THREAD_STRUCTS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_externs.h
new file mode 100644
index 0000000000..a4fd5ac7d9
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_externs.h
@@ -0,0 +1,19 @@
+#ifndef JEMALLOC_INTERNAL_BASE_EXTERNS_H
+#define JEMALLOC_INTERNAL_BASE_EXTERNS_H
+
+base_t *b0get(void);
+base_t *base_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks);
+void base_delete(tsdn_t *tsdn, base_t *base);
+extent_hooks_t *base_extent_hooks_get(base_t *base);
+extent_hooks_t *base_extent_hooks_set(base_t *base,
+    extent_hooks_t *extent_hooks);
+void *base_alloc(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment);
+extent_t *base_alloc_extent(tsdn_t *tsdn, base_t *base);
+void base_stats_get(tsdn_t *tsdn, base_t *base, size_t *allocated,
+    size_t *resident, size_t *mapped);
+void base_prefork(tsdn_t *tsdn, base_t *base);
+void base_postfork_parent(tsdn_t *tsdn, base_t *base);
+void base_postfork_child(tsdn_t *tsdn, base_t *base);
+bool base_boot(tsdn_t *tsdn);
+
+#endif /* JEMALLOC_INTERNAL_BASE_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_inlines.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_inlines.h
new file mode 100644
index 0000000000..931560bfae
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_inlines.h
@@ -0,0 +1,9 @@
+#ifndef JEMALLOC_INTERNAL_BASE_INLINES_H
+#define JEMALLOC_INTERNAL_BASE_INLINES_H
+
+static inline unsigned
+base_ind_get(const base_t *base) {
+	return base->ind;
+}
+
+#endif /* JEMALLOC_INTERNAL_BASE_INLINES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_structs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_structs.h
new file mode 100644
index 0000000000..18e227bd5a
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_structs.h
@@ -0,0 +1,55 @@
+#ifndef JEMALLOC_INTERNAL_BASE_STRUCTS_H
+#define JEMALLOC_INTERNAL_BASE_STRUCTS_H
+
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/size_classes.h"
+
+/* Embedded at the beginning of every block of base-managed virtual memory. */
+struct base_block_s {
+	/* Total size of block's virtual memory mapping. */
+	size_t		size;
+
+	/* Next block in list of base's blocks. */
+	base_block_t	*next;
+
+	/* Tracks unused trailing space. */
+	extent_t	extent;
+};
+
+struct base_s {
+	/* Associated arena's index within the arenas array. */
+	unsigned	ind;
+
+	/*
+	 * User-configurable extent hook functions.  Points to an
+	 * extent_hooks_t.
+	 */
+	atomic_p_t	extent_hooks;
+
+	/* Protects base_alloc() and base_stats_get() operations. */
+	malloc_mutex_t	mtx;
+
+	/*
+	 * Most recent size class in the series of increasingly large base
+	 * extents.  Logarithmic spacing between subsequent allocations ensures
+	 * that the total number of distinct mappings remains small.
+	 */
+	pszind_t	pind_last;
+
+	/* Serial number generation state. */
+	size_t		extent_sn_next;
+
+	/* Chain of all blocks associated with base. */
+	base_block_t	*blocks;
+
+	/* Heap of extents that track unused trailing space within blocks. */
+	extent_heap_t	avail[NSIZES];
+
+	/* Stats, only maintained if config_stats. */
+	size_t		allocated;
+	size_t		resident;
+	size_t		mapped;
+};
+
+#endif /* JEMALLOC_INTERNAL_BASE_STRUCTS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_types.h
new file mode 100644
index 0000000000..be7ee82589
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/base_types.h
@@ -0,0 +1,7 @@
+#ifndef JEMALLOC_INTERNAL_BASE_TYPES_H
+#define JEMALLOC_INTERNAL_BASE_TYPES_H
+
+typedef struct base_block_s base_block_t;
+typedef struct base_s base_t;
+
+#endif /* JEMALLOC_INTERNAL_BASE_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bit_util.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bit_util.h
new file mode 100644
index 0000000000..8d078a8a35
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bit_util.h
@@ -0,0 +1,165 @@
+#ifndef JEMALLOC_INTERNAL_BIT_UTIL_H
+#define JEMALLOC_INTERNAL_BIT_UTIL_H
+
+#include "jemalloc/internal/assert.h"
+
+#define BIT_UTIL_INLINE static inline
+
+/* Sanity check. */
+#if !defined(JEMALLOC_INTERNAL_FFSLL) || !defined(JEMALLOC_INTERNAL_FFSL) \
+    || !defined(JEMALLOC_INTERNAL_FFS)
+#  error JEMALLOC_INTERNAL_FFS{,L,LL} should have been defined by configure
+#endif
+
+
+BIT_UTIL_INLINE unsigned
+ffs_llu(unsigned long long bitmap) {
+	return JEMALLOC_INTERNAL_FFSLL(bitmap);
+}
+
+BIT_UTIL_INLINE unsigned
+ffs_lu(unsigned long bitmap) {
+	return JEMALLOC_INTERNAL_FFSL(bitmap);
+}
+
+BIT_UTIL_INLINE unsigned
+ffs_u(unsigned bitmap) {
+	return JEMALLOC_INTERNAL_FFS(bitmap);
+}
+
+BIT_UTIL_INLINE unsigned
+ffs_zu(size_t bitmap) {
+#if LG_SIZEOF_PTR == LG_SIZEOF_INT
+	return ffs_u(bitmap);
+#elif LG_SIZEOF_PTR == LG_SIZEOF_LONG
+	return ffs_lu(bitmap);
+#elif LG_SIZEOF_PTR == LG_SIZEOF_LONG_LONG
+	return ffs_llu(bitmap);
+#else
+#error No implementation for size_t ffs()
+#endif
+}
+
+BIT_UTIL_INLINE unsigned
+ffs_u64(uint64_t bitmap) {
+#if LG_SIZEOF_LONG == 3
+	return ffs_lu(bitmap);
+#elif LG_SIZEOF_LONG_LONG == 3
+	return ffs_llu(bitmap);
+#else
+#error No implementation for 64-bit ffs()
+#endif
+}
+
+BIT_UTIL_INLINE unsigned
+ffs_u32(uint32_t bitmap) {
+#if LG_SIZEOF_INT == 2
+	return ffs_u(bitmap);
+#else
+#error No implementation for 32-bit ffs()
+#endif
+	return ffs_u(bitmap);
+}
+
+BIT_UTIL_INLINE uint64_t
+pow2_ceil_u64(uint64_t x) {
+	x--;
+	x |= x >> 1;
+	x |= x >> 2;
+	x |= x >> 4;
+	x |= x >> 8;
+	x |= x >> 16;
+	x |= x >> 32;
+	x++;
+	return x;
+}
+
+BIT_UTIL_INLINE uint32_t
+pow2_ceil_u32(uint32_t x) {
+	x--;
+	x |= x >> 1;
+	x |= x >> 2;
+	x |= x >> 4;
+	x |= x >> 8;
+	x |= x >> 16;
+	x++;
+	return x;
+}
+
+/* Compute the smallest power of 2 that is >= x. */
+BIT_UTIL_INLINE size_t
+pow2_ceil_zu(size_t x) {
+#if (LG_SIZEOF_PTR == 3)
+	return pow2_ceil_u64(x);
+#else
+	return pow2_ceil_u32(x);
+#endif
+}
+
+#if (defined(__i386__) || defined(__amd64__) || defined(__x86_64__))
+BIT_UTIL_INLINE unsigned
+lg_floor(size_t x) {
+	size_t ret;
+	assert(x != 0);
+
+	asm ("bsr %1, %0"
+	    : "=r"(ret) // Outputs.
+	    : "r"(x)    // Inputs.
+	    );
+	assert(ret < UINT_MAX);
+	return (unsigned)ret;
+}
+#elif (defined(_MSC_VER))
+BIT_UTIL_INLINE unsigned
+lg_floor(size_t x) {
+	unsigned long ret;
+
+	assert(x != 0);
+
+#if (LG_SIZEOF_PTR == 3)
+	_BitScanReverse64(&ret, x);
+#elif (LG_SIZEOF_PTR == 2)
+	_BitScanReverse(&ret, x);
+#else
+#  error "Unsupported type size for lg_floor()"
+#endif
+	assert(ret < UINT_MAX);
+	return (unsigned)ret;
+}
+#elif (defined(JEMALLOC_HAVE_BUILTIN_CLZ))
+BIT_UTIL_INLINE unsigned
+lg_floor(size_t x) {
+	assert(x != 0);
+
+#if (LG_SIZEOF_PTR == LG_SIZEOF_INT)
+	return ((8 << LG_SIZEOF_PTR) - 1) - __builtin_clz(x);
+#elif (LG_SIZEOF_PTR == LG_SIZEOF_LONG)
+	return ((8 << LG_SIZEOF_PTR) - 1) - __builtin_clzl(x);
+#else
+#  error "Unsupported type size for lg_floor()"
+#endif
+}
+#else
+BIT_UTIL_INLINE unsigned
+lg_floor(size_t x) {
+	assert(x != 0);
+
+	x |= (x >> 1);
+	x |= (x >> 2);
+	x |= (x >> 4);
+	x |= (x >> 8);
+	x |= (x >> 16);
+#if (LG_SIZEOF_PTR == 3)
+	x |= (x >> 32);
+#endif
+	if (x == SIZE_T_MAX) {
+		return (8 << LG_SIZEOF_PTR) - 1;
+	}
+	x++;
+	return ffs_zu(x) - 2;
+}
+#endif
+
+#undef BIT_UTIL_INLINE
+
+#endif /* JEMALLOC_INTERNAL_BIT_UTIL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bitmap.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bitmap.h
index 605ebac58c..ac990290a5 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bitmap.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/bitmap.h
@@ -1,37 +1,159 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_BITMAP_H
+#define JEMALLOC_INTERNAL_BITMAP_H
 
-/* Maximum bitmap bit count is 2^LG_BITMAP_MAXBITS. */
-#define	LG_BITMAP_MAXBITS	LG_RUN_MAXREGS
+#include "jemalloc/internal/arena_types.h"
+#include "jemalloc/internal/bit_util.h"
+#include "jemalloc/internal/size_classes.h"
 
-typedef struct bitmap_level_s bitmap_level_t;
-typedef struct bitmap_info_s bitmap_info_t;
 typedef unsigned long bitmap_t;
-#define	LG_SIZEOF_BITMAP	LG_SIZEOF_LONG
+#define LG_SIZEOF_BITMAP	LG_SIZEOF_LONG
+
+/* Maximum bitmap bit count is 2^LG_BITMAP_MAXBITS. */
+#if LG_SLAB_MAXREGS > LG_CEIL_NSIZES
+/* Maximum bitmap bit count is determined by maximum regions per slab. */
+#  define LG_BITMAP_MAXBITS	LG_SLAB_MAXREGS
+#else
+/* Maximum bitmap bit count is determined by number of extent size classes. */
+#  define LG_BITMAP_MAXBITS	LG_CEIL_NSIZES
+#endif
+#define BITMAP_MAXBITS		(ZU(1) << LG_BITMAP_MAXBITS)
 
 /* Number of bits per group. */
-#define	LG_BITMAP_GROUP_NBITS		(LG_SIZEOF_BITMAP + 3)
-#define	BITMAP_GROUP_NBITS		(ZU(1) << LG_BITMAP_GROUP_NBITS)
-#define	BITMAP_GROUP_NBITS_MASK		(BITMAP_GROUP_NBITS-1)
+#define LG_BITMAP_GROUP_NBITS		(LG_SIZEOF_BITMAP + 3)
+#define BITMAP_GROUP_NBITS		(1U << LG_BITMAP_GROUP_NBITS)
+#define BITMAP_GROUP_NBITS_MASK		(BITMAP_GROUP_NBITS-1)
+
+/*
+ * Do some analysis on how big the bitmap is before we use a tree.  For a brute
+ * force linear search, if we would have to call ffs_lu() more than 2^3 times,
+ * use a tree instead.
+ */
+#if LG_BITMAP_MAXBITS - LG_BITMAP_GROUP_NBITS > 3
+#  define BITMAP_USE_TREE
+#endif
+
+/* Number of groups required to store a given number of bits. */
+#define BITMAP_BITS2GROUPS(nbits)					\
+    (((nbits) + BITMAP_GROUP_NBITS_MASK) >> LG_BITMAP_GROUP_NBITS)
+
+/*
+ * Number of groups required at a particular level for a given number of bits.
+ */
+#define BITMAP_GROUPS_L0(nbits)						\
+    BITMAP_BITS2GROUPS(nbits)
+#define BITMAP_GROUPS_L1(nbits)						\
+    BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(nbits))
+#define BITMAP_GROUPS_L2(nbits)						\
+    BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS((nbits))))
+#define BITMAP_GROUPS_L3(nbits)						\
+    BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(		\
+	BITMAP_BITS2GROUPS((nbits)))))
+#define BITMAP_GROUPS_L4(nbits)						\
+    BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS(		\
+	BITMAP_BITS2GROUPS(BITMAP_BITS2GROUPS((nbits))))))
+
+/*
+ * Assuming the number of levels, number of groups required for a given number
+ * of bits.
+ */
+#define BITMAP_GROUPS_1_LEVEL(nbits)					\
+    BITMAP_GROUPS_L0(nbits)
+#define BITMAP_GROUPS_2_LEVEL(nbits)					\
+    (BITMAP_GROUPS_1_LEVEL(nbits) + BITMAP_GROUPS_L1(nbits))
+#define BITMAP_GROUPS_3_LEVEL(nbits)					\
+    (BITMAP_GROUPS_2_LEVEL(nbits) + BITMAP_GROUPS_L2(nbits))
+#define BITMAP_GROUPS_4_LEVEL(nbits)					\
+    (BITMAP_GROUPS_3_LEVEL(nbits) + BITMAP_GROUPS_L3(nbits))
+#define BITMAP_GROUPS_5_LEVEL(nbits)					\
+    (BITMAP_GROUPS_4_LEVEL(nbits) + BITMAP_GROUPS_L4(nbits))
+
+/*
+ * Maximum number of groups required to support LG_BITMAP_MAXBITS.
+ */
+#ifdef BITMAP_USE_TREE
 
-/* Maximum number of levels possible. */
-#define	BITMAP_MAX_LEVELS						\
-    (LG_BITMAP_MAXBITS / LG_SIZEOF_BITMAP)				\
-    + !!(LG_BITMAP_MAXBITS % LG_SIZEOF_BITMAP)
+#if LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS
+#  define BITMAP_GROUPS(nbits)	BITMAP_GROUPS_1_LEVEL(nbits)
+#  define BITMAP_GROUPS_MAX	BITMAP_GROUPS_1_LEVEL(BITMAP_MAXBITS)
+#elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 2
+#  define BITMAP_GROUPS(nbits)	BITMAP_GROUPS_2_LEVEL(nbits)
+#  define BITMAP_GROUPS_MAX	BITMAP_GROUPS_2_LEVEL(BITMAP_MAXBITS)
+#elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 3
+#  define BITMAP_GROUPS(nbits)	BITMAP_GROUPS_3_LEVEL(nbits)
+#  define BITMAP_GROUPS_MAX	BITMAP_GROUPS_3_LEVEL(BITMAP_MAXBITS)
+#elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 4
+#  define BITMAP_GROUPS(nbits)	BITMAP_GROUPS_4_LEVEL(nbits)
+#  define BITMAP_GROUPS_MAX	BITMAP_GROUPS_4_LEVEL(BITMAP_MAXBITS)
+#elif LG_BITMAP_MAXBITS <= LG_BITMAP_GROUP_NBITS * 5
+#  define BITMAP_GROUPS(nbits)	BITMAP_GROUPS_5_LEVEL(nbits)
+#  define BITMAP_GROUPS_MAX	BITMAP_GROUPS_5_LEVEL(BITMAP_MAXBITS)
+#else
+#  error "Unsupported bitmap size"
+#endif
+
+/*
+ * Maximum number of levels possible.  This could be statically computed based
+ * on LG_BITMAP_MAXBITS:
+ *
+ * #define BITMAP_MAX_LEVELS \
+ *     (LG_BITMAP_MAXBITS / LG_SIZEOF_BITMAP) \
+ *     + !!(LG_BITMAP_MAXBITS % LG_SIZEOF_BITMAP)
+ *
+ * However, that would not allow the generic BITMAP_INFO_INITIALIZER() macro, so
+ * instead hardcode BITMAP_MAX_LEVELS to the largest number supported by the
+ * various cascading macros.  The only additional cost this incurs is some
+ * unused trailing entries in bitmap_info_t structures; the bitmaps themselves
+ * are not impacted.
+ */
+#define BITMAP_MAX_LEVELS	5
+
+#define BITMAP_INFO_INITIALIZER(nbits) {				\
+	/* nbits. */							\
+	nbits,								\
+	/* nlevels. */							\
+	(BITMAP_GROUPS_L0(nbits) > BITMAP_GROUPS_L1(nbits)) +		\
+	    (BITMAP_GROUPS_L1(nbits) > BITMAP_GROUPS_L2(nbits)) +	\
+	    (BITMAP_GROUPS_L2(nbits) > BITMAP_GROUPS_L3(nbits)) +	\
+	    (BITMAP_GROUPS_L3(nbits) > BITMAP_GROUPS_L4(nbits)) + 1,	\
+	/* levels. */							\
+	{								\
+		{0},							\
+		{BITMAP_GROUPS_L0(nbits)},				\
+		{BITMAP_GROUPS_L1(nbits) + BITMAP_GROUPS_L0(nbits)},	\
+		{BITMAP_GROUPS_L2(nbits) + BITMAP_GROUPS_L1(nbits) +	\
+		    BITMAP_GROUPS_L0(nbits)},				\
+		{BITMAP_GROUPS_L3(nbits) + BITMAP_GROUPS_L2(nbits) +	\
+		    BITMAP_GROUPS_L1(nbits) + BITMAP_GROUPS_L0(nbits)},	\
+		{BITMAP_GROUPS_L4(nbits) + BITMAP_GROUPS_L3(nbits) +	\
+		     BITMAP_GROUPS_L2(nbits) + BITMAP_GROUPS_L1(nbits)	\
+		     + BITMAP_GROUPS_L0(nbits)}				\
+	}								\
+}
+
+#else /* BITMAP_USE_TREE */
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+#define BITMAP_GROUPS(nbits)	BITMAP_BITS2GROUPS(nbits)
+#define BITMAP_GROUPS_MAX	BITMAP_BITS2GROUPS(BITMAP_MAXBITS)
 
-struct bitmap_level_s {
+#define BITMAP_INFO_INITIALIZER(nbits) {				\
+	/* nbits. */							\
+	nbits,								\
+	/* ngroups. */							\
+	BITMAP_BITS2GROUPS(nbits)					\
+}
+
+#endif /* BITMAP_USE_TREE */
+
+typedef struct bitmap_level_s {
 	/* Offset of this level's groups within the array of groups. */
 	size_t group_offset;
-};
+} bitmap_level_t;
 
-struct bitmap_info_s {
+typedef struct bitmap_info_s {
 	/* Logical number of bits in bitmap (stored at bottom level). */
 	size_t nbits;
 
+#ifdef BITMAP_USE_TREE
 	/* Number of levels necessary for nbits. */
 	unsigned nlevels;
 
@@ -40,67 +162,62 @@ struct bitmap_info_s {
 	 * bottom to top (e.g. the bottom level is stored in levels[0]).
 	 */
 	bitmap_level_t levels[BITMAP_MAX_LEVELS+1];
-};
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-void	bitmap_info_init(bitmap_info_t *binfo, size_t nbits);
-size_t	bitmap_info_ngroups(const bitmap_info_t *binfo);
-size_t	bitmap_size(size_t nbits);
-void	bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo);
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-#ifndef JEMALLOC_ENABLE_INLINE
-bool	bitmap_full(bitmap_t *bitmap, const bitmap_info_t *binfo);
-bool	bitmap_get(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit);
-void	bitmap_set(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit);
-size_t	bitmap_sfu(bitmap_t *bitmap, const bitmap_info_t *binfo);
-void	bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit);
-#endif
+#else /* BITMAP_USE_TREE */
+	/* Number of groups necessary for nbits. */
+	size_t ngroups;
+#endif /* BITMAP_USE_TREE */
+} bitmap_info_t;
+
+void bitmap_info_init(bitmap_info_t *binfo, size_t nbits);
+void bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo, bool fill);
+size_t bitmap_size(const bitmap_info_t *binfo);
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_BITMAP_C_))
-JEMALLOC_INLINE bool
-bitmap_full(bitmap_t *bitmap, const bitmap_info_t *binfo)
-{
-	unsigned rgoff = binfo->levels[binfo->nlevels].group_offset - 1;
+static inline bool
+bitmap_full(bitmap_t *bitmap, const bitmap_info_t *binfo) {
+#ifdef BITMAP_USE_TREE
+	size_t rgoff = binfo->levels[binfo->nlevels].group_offset - 1;
 	bitmap_t rg = bitmap[rgoff];
 	/* The bitmap is full iff the root group is 0. */
 	return (rg == 0);
+#else
+	size_t i;
+
+	for (i = 0; i < binfo->ngroups; i++) {
+		if (bitmap[i] != 0) {
+			return false;
+		}
+	}
+	return true;
+#endif
 }
 
-JEMALLOC_INLINE bool
-bitmap_get(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
-{
+static inline bool
+bitmap_get(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) {
 	size_t goff;
 	bitmap_t g;
 
 	assert(bit < binfo->nbits);
 	goff = bit >> LG_BITMAP_GROUP_NBITS;
 	g = bitmap[goff];
-	return (!(g & (1LU << (bit & BITMAP_GROUP_NBITS_MASK))));
+	return !(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK)));
 }
 
-JEMALLOC_INLINE void
-bitmap_set(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
-{
+static inline void
+bitmap_set(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) {
 	size_t goff;
 	bitmap_t *gp;
 	bitmap_t g;
 
 	assert(bit < binfo->nbits);
-	assert(bitmap_get(bitmap, binfo, bit) == false);
+	assert(!bitmap_get(bitmap, binfo, bit));
 	goff = bit >> LG_BITMAP_GROUP_NBITS;
 	gp = &bitmap[goff];
 	g = *gp;
-	assert(g & (1LU << (bit & BITMAP_GROUP_NBITS_MASK)));
-	g ^= 1LU << (bit & BITMAP_GROUP_NBITS_MASK);
+	assert(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK)));
+	g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK);
 	*gp = g;
 	assert(bitmap_get(bitmap, binfo, bit));
+#ifdef BITMAP_USE_TREE
 	/* Propagate group state transitions up the tree. */
 	if (g == 0) {
 		unsigned i;
@@ -109,45 +226,113 @@ bitmap_set(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
 			goff = bit >> LG_BITMAP_GROUP_NBITS;
 			gp = &bitmap[binfo->levels[i].group_offset + goff];
 			g = *gp;
-			assert(g & (1LU << (bit & BITMAP_GROUP_NBITS_MASK)));
-			g ^= 1LU << (bit & BITMAP_GROUP_NBITS_MASK);
+			assert(g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK)));
+			g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK);
 			*gp = g;
-			if (g != 0)
+			if (g != 0) {
 				break;
+			}
 		}
 	}
+#endif
+}
+
+/* ffu: find first unset >= bit. */
+static inline size_t
+bitmap_ffu(const bitmap_t *bitmap, const bitmap_info_t *binfo, size_t min_bit) {
+	assert(min_bit < binfo->nbits);
+
+#ifdef BITMAP_USE_TREE
+	size_t bit = 0;
+	for (unsigned level = binfo->nlevels; level--;) {
+		size_t lg_bits_per_group = (LG_BITMAP_GROUP_NBITS * (level +
+		    1));
+		bitmap_t group = bitmap[binfo->levels[level].group_offset + (bit
+		    >> lg_bits_per_group)];
+		unsigned group_nmask = (unsigned)(((min_bit > bit) ? (min_bit -
+		    bit) : 0) >> (lg_bits_per_group - LG_BITMAP_GROUP_NBITS));
+		assert(group_nmask <= BITMAP_GROUP_NBITS);
+		bitmap_t group_mask = ~((1LU << group_nmask) - 1);
+		bitmap_t group_masked = group & group_mask;
+		if (group_masked == 0LU) {
+			if (group == 0LU) {
+				return binfo->nbits;
+			}
+			/*
+			 * min_bit was preceded by one or more unset bits in
+			 * this group, but there are no other unset bits in this
+			 * group.  Try again starting at the first bit of the
+			 * next sibling.  This will recurse at most once per
+			 * non-root level.
+			 */
+			size_t sib_base = bit + (ZU(1) << lg_bits_per_group);
+			assert(sib_base > min_bit);
+			assert(sib_base > bit);
+			if (sib_base >= binfo->nbits) {
+				return binfo->nbits;
+			}
+			return bitmap_ffu(bitmap, binfo, sib_base);
+		}
+		bit += ((size_t)(ffs_lu(group_masked) - 1)) <<
+		    (lg_bits_per_group - LG_BITMAP_GROUP_NBITS);
+	}
+	assert(bit >= min_bit);
+	assert(bit < binfo->nbits);
+	return bit;
+#else
+	size_t i = min_bit >> LG_BITMAP_GROUP_NBITS;
+	bitmap_t g = bitmap[i] & ~((1LU << (min_bit & BITMAP_GROUP_NBITS_MASK))
+	    - 1);
+	size_t bit;
+	do {
+		bit = ffs_lu(g);
+		if (bit != 0) {
+			return (i << LG_BITMAP_GROUP_NBITS) + (bit - 1);
+		}
+		i++;
+		g = bitmap[i];
+	} while (i < binfo->ngroups);
+	return binfo->nbits;
+#endif
 }
 
 /* sfu: set first unset. */
-JEMALLOC_INLINE size_t
-bitmap_sfu(bitmap_t *bitmap, const bitmap_info_t *binfo)
-{
+static inline size_t
+bitmap_sfu(bitmap_t *bitmap, const bitmap_info_t *binfo) {
 	size_t bit;
 	bitmap_t g;
 	unsigned i;
 
-	assert(bitmap_full(bitmap, binfo) == false);
+	assert(!bitmap_full(bitmap, binfo));
 
+#ifdef BITMAP_USE_TREE
 	i = binfo->nlevels - 1;
 	g = bitmap[binfo->levels[i].group_offset];
-	bit = ffsl(g) - 1;
+	bit = ffs_lu(g) - 1;
 	while (i > 0) {
 		i--;
 		g = bitmap[binfo->levels[i].group_offset + bit];
-		bit = (bit << LG_BITMAP_GROUP_NBITS) + (ffsl(g) - 1);
+		bit = (bit << LG_BITMAP_GROUP_NBITS) + (ffs_lu(g) - 1);
 	}
-
+#else
+	i = 0;
+	g = bitmap[0];
+	while ((bit = ffs_lu(g)) == 0) {
+		i++;
+		g = bitmap[i];
+	}
+	bit = (i << LG_BITMAP_GROUP_NBITS) + (bit - 1);
+#endif
 	bitmap_set(bitmap, binfo, bit);
-	return (bit);
+	return bit;
 }
 
-JEMALLOC_INLINE void
-bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
-{
+static inline void
+bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit) {
 	size_t goff;
 	bitmap_t *gp;
 	bitmap_t g;
-	bool propagate;
+	UNUSED bool propagate;
 
 	assert(bit < binfo->nbits);
 	assert(bitmap_get(bitmap, binfo, bit));
@@ -155,10 +340,11 @@ bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
 	gp = &bitmap[goff];
 	g = *gp;
 	propagate = (g == 0);
-	assert((g & (1LU << (bit & BITMAP_GROUP_NBITS_MASK))) == 0);
-	g ^= 1LU << (bit & BITMAP_GROUP_NBITS_MASK);
+	assert((g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK))) == 0);
+	g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK);
 	*gp = g;
-	assert(bitmap_get(bitmap, binfo, bit) == false);
+	assert(!bitmap_get(bitmap, binfo, bit));
+#ifdef BITMAP_USE_TREE
 	/* Propagate group state transitions up the tree. */
 	if (propagate) {
 		unsigned i;
@@ -168,17 +354,16 @@ bitmap_unset(bitmap_t *bitmap, const bitmap_info_t *binfo, size_t bit)
 			gp = &bitmap[binfo->levels[i].group_offset + goff];
 			g = *gp;
 			propagate = (g == 0);
-			assert((g & (1LU << (bit & BITMAP_GROUP_NBITS_MASK)))
+			assert((g & (ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK)))
 			    == 0);
-			g ^= 1LU << (bit & BITMAP_GROUP_NBITS_MASK);
+			g ^= ZU(1) << (bit & BITMAP_GROUP_NBITS_MASK);
 			*gp = g;
-			if (propagate == false)
+			if (!propagate) {
 				break;
+			}
 		}
 	}
+#endif /* BITMAP_USE_TREE */
 }
 
-#endif
-
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_BITMAP_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ckh.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ckh.h
index 58712a6a76..7b3850bc16 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ckh.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ckh.h
@@ -1,88 +1,101 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_CKH_H
+#define JEMALLOC_INTERNAL_CKH_H
 
-typedef struct ckh_s ckh_t;
-typedef struct ckhc_s ckhc_t;
+#include "jemalloc/internal/tsd.h"
 
-/* Typedefs to allow easy function pointer passing. */
-typedef void ckh_hash_t (const void *, size_t[2]);
-typedef bool ckh_keycomp_t (const void *, const void *);
+/* Cuckoo hashing implementation.  Skip to the end for the interface. */
+
+/******************************************************************************/
+/* INTERNAL DEFINITIONS -- IGNORE */
+/******************************************************************************/
 
 /* Maintain counters used to get an idea of performance. */
-/* #define	CKH_COUNT */
+/* #define CKH_COUNT */
 /* Print counter values in ckh_delete() (requires CKH_COUNT). */
-/* #define	CKH_VERBOSE */
+/* #define CKH_VERBOSE */
 
 /*
  * There are 2^LG_CKH_BUCKET_CELLS cells in each hash table bucket.  Try to fit
  * one bucket per L1 cache line.
  */
-#define	LG_CKH_BUCKET_CELLS (LG_CACHELINE - LG_SIZEOF_PTR - 1)
+#define LG_CKH_BUCKET_CELLS (LG_CACHELINE - LG_SIZEOF_PTR - 1)
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+/* Typedefs to allow easy function pointer passing. */
+typedef void ckh_hash_t (const void *, size_t[2]);
+typedef bool ckh_keycomp_t (const void *, const void *);
 
 /* Hash table cell. */
-struct ckhc_s {
-	const void	*key;
-	const void	*data;
-};
+typedef struct {
+	const void *key;
+	const void *data;
+} ckhc_t;
 
-struct ckh_s {
+/* The hash table itself. */
+typedef struct {
 #ifdef CKH_COUNT
 	/* Counters used to get an idea of performance. */
-	uint64_t	ngrows;
-	uint64_t	nshrinks;
-	uint64_t	nshrinkfails;
-	uint64_t	ninserts;
-	uint64_t	nrelocs;
+	uint64_t ngrows;
+	uint64_t nshrinks;
+	uint64_t nshrinkfails;
+	uint64_t ninserts;
+	uint64_t nrelocs;
 #endif
 
 	/* Used for pseudo-random number generation. */
-#define	CKH_A		1103515241
-#define	CKH_C		12347
-	uint32_t	prng_state;
+	uint64_t prng_state;
 
 	/* Total number of items. */
-	size_t		count;
+	size_t count;
 
 	/*
 	 * Minimum and current number of hash table buckets.  There are
 	 * 2^LG_CKH_BUCKET_CELLS cells per bucket.
 	 */
-	unsigned	lg_minbuckets;
-	unsigned	lg_curbuckets;
+	unsigned lg_minbuckets;
+	unsigned lg_curbuckets;
 
 	/* Hash and comparison functions. */
-	ckh_hash_t	*hash;
-	ckh_keycomp_t	*keycomp;
+	ckh_hash_t *hash;
+	ckh_keycomp_t *keycomp;
 
 	/* Hash table with 2^lg_curbuckets buckets. */
-	ckhc_t		*tab;
-};
+	ckhc_t *tab;
+} ckh_t;
 
-#endif /* JEMALLOC_H_STRUCTS */
 /******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
+/* BEGIN PUBLIC API */
+/******************************************************************************/
 
-bool	ckh_new(ckh_t *ckh, size_t minitems, ckh_hash_t *hash,
+/* Lifetime management.  Minitems is the initial capacity. */
+bool ckh_new(tsd_t *tsd, ckh_t *ckh, size_t minitems, ckh_hash_t *hash,
     ckh_keycomp_t *keycomp);
-void	ckh_delete(ckh_t *ckh);
-size_t	ckh_count(ckh_t *ckh);
-bool	ckh_iter(ckh_t *ckh, size_t *tabind, void **key, void **data);
-bool	ckh_insert(ckh_t *ckh, const void *key, const void *data);
-bool	ckh_remove(ckh_t *ckh, const void *searchkey, void **key,
+void ckh_delete(tsd_t *tsd, ckh_t *ckh);
+
+/* Get the number of elements in the set. */
+size_t ckh_count(ckh_t *ckh);
+
+/*
+ * To iterate over the elements in the table, initialize *tabind to 0 and call
+ * this function until it returns true.  Each call that returns false will
+ * update *key and *data to the next element in the table, assuming the pointers
+ * are non-NULL.
+ */
+bool ckh_iter(ckh_t *ckh, size_t *tabind, void **key, void **data);
+
+/*
+ * Basic hash table operations -- insert, removal, lookup.  For ckh_remove and
+ * ckh_search, key or data can be NULL.  The hash-table only stores pointers to
+ * the key and value, and doesn't do any lifetime management.
+ */
+bool ckh_insert(tsd_t *tsd, ckh_t *ckh, const void *key, const void *data);
+bool ckh_remove(tsd_t *tsd, ckh_t *ckh, const void *searchkey, void **key,
     void **data);
-bool	ckh_search(ckh_t *ckh, const void *seachkey, void **key, void **data);
-void	ckh_string_hash(const void *key, size_t r_hash[2]);
-bool	ckh_string_keycomp(const void *k1, const void *k2);
-void	ckh_pointer_hash(const void *key, size_t r_hash[2]);
-bool	ckh_pointer_keycomp(const void *k1, const void *k2);
+bool ckh_search(ckh_t *ckh, const void *searchkey, void **key, void **data);
 
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+/* Some useful hash and comparison functions for strings and pointers. */
+void ckh_string_hash(const void *key, size_t r_hash[2]);
+bool ckh_string_keycomp(const void *k1, const void *k2);
+void ckh_pointer_hash(const void *key, size_t r_hash[2]);
+bool ckh_pointer_keycomp(const void *k1, const void *k2);
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_CKH_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ctl.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ctl.h
index 0ffecc5f2a..a91c4cf556 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ctl.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ctl.h
@@ -1,87 +1,106 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
-
-typedef struct ctl_node_s ctl_node_t;
-typedef struct ctl_named_node_s ctl_named_node_t;
-typedef struct ctl_indexed_node_s ctl_indexed_node_t;
-typedef struct ctl_arena_stats_s ctl_arena_stats_t;
-typedef struct ctl_stats_s ctl_stats_t;
-
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
-
-struct ctl_node_s {
-	bool			named;
-};
-
-struct ctl_named_node_s {
-	struct ctl_node_s	node;
-	const char		*name;
+#ifndef JEMALLOC_INTERNAL_CTL_H
+#define JEMALLOC_INTERNAL_CTL_H
+
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/mutex_prof.h"
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/stats.h"
+
+/* Maximum ctl tree depth. */
+#define CTL_MAX_DEPTH	7
+
+typedef struct ctl_node_s {
+	bool named;
+} ctl_node_t;
+
+typedef struct ctl_named_node_s {
+	ctl_node_t node;
+	const char *name;
 	/* If (nchildren == 0), this is a terminal node. */
-	unsigned		nchildren;
-	const			ctl_node_t *children;
-	int			(*ctl)(const size_t *, size_t, void *, size_t *,
-	    void *, size_t);
-};
+	size_t nchildren;
+	const ctl_node_t *children;
+	int (*ctl)(tsd_t *, const size_t *, size_t, void *, size_t *, void *,
+	    size_t);
+} ctl_named_node_t;
 
-struct ctl_indexed_node_s {
-	struct ctl_node_s	node;
-	const ctl_named_node_t	*(*index)(const size_t *, size_t, size_t);
-};
+typedef struct ctl_indexed_node_s {
+	struct ctl_node_s node;
+	const ctl_named_node_t *(*index)(tsdn_t *, const size_t *, size_t,
+	    size_t);
+} ctl_indexed_node_t;
 
-struct ctl_arena_stats_s {
-	bool			initialized;
-	unsigned		nthreads;
-	const char		*dss;
-	size_t			pactive;
-	size_t			pdirty;
-	arena_stats_t		astats;
+typedef struct ctl_arena_stats_s {
+	arena_stats_t astats;
 
 	/* Aggregate stats for small size classes, based on bin stats. */
-	size_t			allocated_small;
-	uint64_t		nmalloc_small;
-	uint64_t		ndalloc_small;
-	uint64_t		nrequests_small;
-
-	malloc_bin_stats_t	bstats[NBINS];
-	malloc_large_stats_t	*lstats;	/* nlclasses elements. */
+	size_t allocated_small;
+	uint64_t nmalloc_small;
+	uint64_t ndalloc_small;
+	uint64_t nrequests_small;
+
+	malloc_bin_stats_t bstats[NBINS];
+	malloc_large_stats_t lstats[NSIZES - NBINS];
+} ctl_arena_stats_t;
+
+typedef struct ctl_stats_s {
+	size_t allocated;
+	size_t active;
+	size_t metadata;
+	size_t resident;
+	size_t mapped;
+	size_t retained;
+
+	background_thread_stats_t background_thread;
+	mutex_prof_data_t mutex_prof_data[mutex_prof_num_global_mutexes];
+} ctl_stats_t;
+
+typedef struct ctl_arena_s ctl_arena_t;
+struct ctl_arena_s {
+	unsigned arena_ind;
+	bool initialized;
+	ql_elm(ctl_arena_t) destroyed_link;
+
+	/* Basic stats, supported even if !config_stats. */
+	unsigned nthreads;
+	const char *dss;
+	ssize_t dirty_decay_ms;
+	ssize_t muzzy_decay_ms;
+	size_t pactive;
+	size_t pdirty;
+	size_t pmuzzy;
+
+	/* NULL if !config_stats. */
+	ctl_arena_stats_t *astats;
 };
 
-struct ctl_stats_s {
-	size_t			allocated;
-	size_t			active;
-	size_t			mapped;
-	struct {
-		size_t		current;	/* stats_chunks.curchunks */
-		uint64_t	total;		/* stats_chunks.nchunks */
-		size_t		high;		/* stats_chunks.highchunks */
-	} chunks;
-	struct {
-		size_t		allocated;	/* huge_allocated */
-		uint64_t	nmalloc;	/* huge_nmalloc */
-		uint64_t	ndalloc;	/* huge_ndalloc */
-	} huge;
-	unsigned		narenas;
-	ctl_arena_stats_t	*arenas;	/* (narenas + 1) elements. */
-};
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-int	ctl_byname(const char *name, void *oldp, size_t *oldlenp, void *newp,
-    size_t newlen);
-int	ctl_nametomib(const char *name, size_t *mibp, size_t *miblenp);
-
-int	ctl_bymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
+typedef struct ctl_arenas_s {
+	uint64_t epoch;
+	unsigned narenas;
+	ql_head(ctl_arena_t) destroyed;
+
+	/*
+	 * Element 0 corresponds to merged stats for extant arenas (accessed via
+	 * MALLCTL_ARENAS_ALL), element 1 corresponds to merged stats for
+	 * destroyed arenas (accessed via MALLCTL_ARENAS_DESTROYED), and the
+	 * remaining MALLOCX_ARENA_LIMIT elements correspond to arenas.
+	 */
+	ctl_arena_t *arenas[2 + MALLOCX_ARENA_LIMIT];
+} ctl_arenas_t;
+
+int ctl_byname(tsd_t *tsd, const char *name, void *oldp, size_t *oldlenp,
     void *newp, size_t newlen);
-bool	ctl_boot(void);
-void	ctl_prefork(void);
-void	ctl_postfork_parent(void);
-void	ctl_postfork_child(void);
+int ctl_nametomib(tsd_t *tsd, const char *name, size_t *mibp, size_t *miblenp);
 
-#define	xmallctl(name, oldp, oldlenp, newp, newlen) do {		\
+int ctl_bymib(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen);
+bool ctl_boot(void);
+void ctl_prefork(tsdn_t *tsdn);
+void ctl_postfork_parent(tsdn_t *tsdn);
+void ctl_postfork_child(tsdn_t *tsdn);
+
+#define xmallctl(name, oldp, oldlenp, newp, newlen) do {		\
 	if (je_mallctl(name, oldp, oldlenp, newp, newlen)		\
 	    != 0) {							\
 		malloc_printf(						\
@@ -91,7 +110,7 @@ void	ctl_postfork_child(void);
 	}								\
 } while (0)
 
-#define	xmallctlnametomib(name, mibp, miblenp) do {			\
+#define xmallctlnametomib(name, mibp, miblenp) do {			\
 	if (je_mallctlnametomib(name, mibp, miblenp) != 0) {		\
 		malloc_printf("<jemalloc>: Failure in "			\
 		    "xmallctlnametomib(\"%s\", ...)\n", name);		\
@@ -99,7 +118,7 @@ void	ctl_postfork_child(void);
 	}								\
 } while (0)
 
-#define	xmallctlbymib(mib, miblen, oldp, oldlenp, newp, newlen) do {	\
+#define xmallctlbymib(mib, miblen, oldp, oldlenp, newp, newlen) do {	\
 	if (je_mallctlbymib(mib, miblen, oldp, oldlenp, newp,		\
 	    newlen) != 0) {						\
 		malloc_write(						\
@@ -108,10 +127,4 @@ void	ctl_postfork_child(void);
 	}								\
 } while (0)
 
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
-
+#endif /* JEMALLOC_INTERNAL_CTL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_dss.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_dss.h
new file mode 100644
index 0000000000..e8f02ce2ad
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_dss.h
@@ -0,0 +1,26 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_DSS_H
+#define JEMALLOC_INTERNAL_EXTENT_DSS_H
+
+typedef enum {
+	dss_prec_disabled  = 0,
+	dss_prec_primary   = 1,
+	dss_prec_secondary = 2,
+
+	dss_prec_limit     = 3
+} dss_prec_t;
+#define DSS_PREC_DEFAULT dss_prec_secondary
+#define DSS_DEFAULT "secondary"
+
+extern const char *dss_prec_names[];
+
+extern const char *opt_dss;
+
+dss_prec_t extent_dss_prec_get(void);
+bool extent_dss_prec_set(dss_prec_t dss_prec);
+void *extent_alloc_dss(tsdn_t *tsdn, arena_t *arena, void *new_addr,
+    size_t size, size_t alignment, bool *zero, bool *commit);
+bool extent_in_dss(void *addr);
+bool extent_dss_mergeable(void *addr_a, void *addr_b);
+void extent_dss_boot(void);
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_DSS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_externs.h
new file mode 100644
index 0000000000..489a813c80
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_externs.h
@@ -0,0 +1,72 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_EXTERNS_H
+#define JEMALLOC_INTERNAL_EXTENT_EXTERNS_H
+
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/mutex_pool.h"
+#include "jemalloc/internal/ph.h"
+#include "jemalloc/internal/rb.h"
+#include "jemalloc/internal/rtree.h"
+
+extern rtree_t			extents_rtree;
+extern const extent_hooks_t	extent_hooks_default;
+extern mutex_pool_t		extent_mutex_pool;
+
+extent_t *extent_alloc(tsdn_t *tsdn, arena_t *arena);
+void extent_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent);
+
+extent_hooks_t *extent_hooks_get(arena_t *arena);
+extent_hooks_t *extent_hooks_set(tsd_t *tsd, arena_t *arena,
+    extent_hooks_t *extent_hooks);
+
+#ifdef JEMALLOC_JET
+size_t extent_size_quantize_floor(size_t size);
+size_t extent_size_quantize_ceil(size_t size);
+#endif
+
+rb_proto(, extent_avail_, extent_tree_t, extent_t)
+ph_proto(, extent_heap_, extent_heap_t, extent_t)
+
+bool extents_init(tsdn_t *tsdn, extents_t *extents, extent_state_t state,
+    bool delay_coalesce);
+extent_state_t extents_state_get(const extents_t *extents);
+size_t extents_npages_get(extents_t *extents);
+extent_t *extents_alloc(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr,
+    size_t size, size_t pad, size_t alignment, bool slab, szind_t szind,
+    bool *zero, bool *commit);
+void extents_dalloc(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent);
+extent_t *extents_evict(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, size_t npages_min);
+void extents_prefork(tsdn_t *tsdn, extents_t *extents);
+void extents_postfork_parent(tsdn_t *tsdn, extents_t *extents);
+void extents_postfork_child(tsdn_t *tsdn, extents_t *extents);
+extent_t *extent_alloc_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit);
+void extent_dalloc_gap(tsdn_t *tsdn, arena_t *arena, extent_t *extent);
+void extent_dalloc_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent);
+void extent_destroy_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent);
+bool extent_commit_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length);
+bool extent_decommit_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length);
+bool extent_purge_lazy_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length);
+bool extent_purge_forced_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length);
+extent_t *extent_split_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a,
+    szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b);
+bool extent_merge_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b);
+
+bool extent_boot(void);
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_inlines.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_inlines.h
new file mode 100644
index 0000000000..bb2bd699ed
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_inlines.h
@@ -0,0 +1,407 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_INLINES_H
+#define JEMALLOC_INTERNAL_EXTENT_INLINES_H
+
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/mutex_pool.h"
+#include "jemalloc/internal/pages.h"
+#include "jemalloc/internal/prng.h"
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/sz.h"
+
+static inline void
+extent_lock(tsdn_t *tsdn, extent_t *extent) {
+	assert(extent != NULL);
+	mutex_pool_lock(tsdn, &extent_mutex_pool, (uintptr_t)extent);
+}
+
+static inline void
+extent_unlock(tsdn_t *tsdn, extent_t *extent) {
+	assert(extent != NULL);
+	mutex_pool_unlock(tsdn, &extent_mutex_pool, (uintptr_t)extent);
+}
+
+static inline void
+extent_lock2(tsdn_t *tsdn, extent_t *extent1, extent_t *extent2) {
+	assert(extent1 != NULL && extent2 != NULL);
+	mutex_pool_lock2(tsdn, &extent_mutex_pool, (uintptr_t)extent1,
+	    (uintptr_t)extent2);
+}
+
+static inline void
+extent_unlock2(tsdn_t *tsdn, extent_t *extent1, extent_t *extent2) {
+	assert(extent1 != NULL && extent2 != NULL);
+	mutex_pool_unlock2(tsdn, &extent_mutex_pool, (uintptr_t)extent1,
+	    (uintptr_t)extent2);
+}
+
+static inline arena_t *
+extent_arena_get(const extent_t *extent) {
+	unsigned arena_ind = (unsigned)((extent->e_bits &
+	    EXTENT_BITS_ARENA_MASK) >> EXTENT_BITS_ARENA_SHIFT);
+	/*
+	 * The following check is omitted because we should never actually read
+	 * a NULL arena pointer.
+	 */
+	if (false && arena_ind >= MALLOCX_ARENA_LIMIT) {
+		return NULL;
+	}
+	assert(arena_ind < MALLOCX_ARENA_LIMIT);
+	return (arena_t *)atomic_load_p(&arenas[arena_ind], ATOMIC_ACQUIRE);
+}
+
+static inline szind_t
+extent_szind_get_maybe_invalid(const extent_t *extent) {
+	szind_t szind = (szind_t)((extent->e_bits & EXTENT_BITS_SZIND_MASK) >>
+	    EXTENT_BITS_SZIND_SHIFT);
+	assert(szind <= NSIZES);
+	return szind;
+}
+
+static inline szind_t
+extent_szind_get(const extent_t *extent) {
+	szind_t szind = extent_szind_get_maybe_invalid(extent);
+	assert(szind < NSIZES); /* Never call when "invalid". */
+	return szind;
+}
+
+static inline size_t
+extent_usize_get(const extent_t *extent) {
+	return sz_index2size(extent_szind_get(extent));
+}
+
+static inline size_t
+extent_sn_get(const extent_t *extent) {
+	return (size_t)((extent->e_bits & EXTENT_BITS_SN_MASK) >>
+	    EXTENT_BITS_SN_SHIFT);
+}
+
+static inline extent_state_t
+extent_state_get(const extent_t *extent) {
+	return (extent_state_t)((extent->e_bits & EXTENT_BITS_STATE_MASK) >>
+	    EXTENT_BITS_STATE_SHIFT);
+}
+
+static inline bool
+extent_zeroed_get(const extent_t *extent) {
+	return (bool)((extent->e_bits & EXTENT_BITS_ZEROED_MASK) >>
+	    EXTENT_BITS_ZEROED_SHIFT);
+}
+
+static inline bool
+extent_committed_get(const extent_t *extent) {
+	return (bool)((extent->e_bits & EXTENT_BITS_COMMITTED_MASK) >>
+	    EXTENT_BITS_COMMITTED_SHIFT);
+}
+
+static inline bool
+extent_slab_get(const extent_t *extent) {
+	return (bool)((extent->e_bits & EXTENT_BITS_SLAB_MASK) >>
+	    EXTENT_BITS_SLAB_SHIFT);
+}
+
+static inline unsigned
+extent_nfree_get(const extent_t *extent) {
+	assert(extent_slab_get(extent));
+	return (unsigned)((extent->e_bits & EXTENT_BITS_NFREE_MASK) >>
+	    EXTENT_BITS_NFREE_SHIFT);
+}
+
+static inline void *
+extent_base_get(const extent_t *extent) {
+	assert(extent->e_addr == PAGE_ADDR2BASE(extent->e_addr) ||
+	    !extent_slab_get(extent));
+	return PAGE_ADDR2BASE(extent->e_addr);
+}
+
+static inline void *
+extent_addr_get(const extent_t *extent) {
+	assert(extent->e_addr == PAGE_ADDR2BASE(extent->e_addr) ||
+	    !extent_slab_get(extent));
+	return extent->e_addr;
+}
+
+static inline size_t
+extent_size_get(const extent_t *extent) {
+	return (extent->e_size_esn & EXTENT_SIZE_MASK);
+}
+
+static inline size_t
+extent_esn_get(const extent_t *extent) {
+	return (extent->e_size_esn & EXTENT_ESN_MASK);
+}
+
+static inline size_t
+extent_bsize_get(const extent_t *extent) {
+	return extent->e_bsize;
+}
+
+static inline void *
+extent_before_get(const extent_t *extent) {
+	return (void *)((uintptr_t)extent_base_get(extent) - PAGE);
+}
+
+static inline void *
+extent_last_get(const extent_t *extent) {
+	return (void *)((uintptr_t)extent_base_get(extent) +
+	    extent_size_get(extent) - PAGE);
+}
+
+static inline void *
+extent_past_get(const extent_t *extent) {
+	return (void *)((uintptr_t)extent_base_get(extent) +
+	    extent_size_get(extent));
+}
+
+static inline arena_slab_data_t *
+extent_slab_data_get(extent_t *extent) {
+	assert(extent_slab_get(extent));
+	return &extent->e_slab_data;
+}
+
+static inline const arena_slab_data_t *
+extent_slab_data_get_const(const extent_t *extent) {
+	assert(extent_slab_get(extent));
+	return &extent->e_slab_data;
+}
+
+static inline prof_tctx_t *
+extent_prof_tctx_get(const extent_t *extent) {
+	return (prof_tctx_t *)atomic_load_p(&extent->e_prof_tctx,
+	    ATOMIC_ACQUIRE);
+}
+
+static inline void
+extent_arena_set(extent_t *extent, arena_t *arena) {
+	unsigned arena_ind = (arena != NULL) ? arena_ind_get(arena) : ((1U <<
+	    MALLOCX_ARENA_BITS) - 1);
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_ARENA_MASK) |
+	    ((uint64_t)arena_ind << EXTENT_BITS_ARENA_SHIFT);
+}
+
+static inline void
+extent_addr_set(extent_t *extent, void *addr) {
+	extent->e_addr = addr;
+}
+
+static inline void
+extent_addr_randomize(tsdn_t *tsdn, extent_t *extent, size_t alignment) {
+	assert(extent_base_get(extent) == extent_addr_get(extent));
+
+	if (alignment < PAGE) {
+		unsigned lg_range = LG_PAGE -
+		    lg_floor(CACHELINE_CEILING(alignment));
+		size_t r =
+		    prng_lg_range_zu(&extent_arena_get(extent)->offset_state,
+		    lg_range, true);
+		uintptr_t random_offset = ((uintptr_t)r) << (LG_PAGE -
+		    lg_range);
+		extent->e_addr = (void *)((uintptr_t)extent->e_addr +
+		    random_offset);
+		assert(ALIGNMENT_ADDR2BASE(extent->e_addr, alignment) ==
+		    extent->e_addr);
+	}
+}
+
+static inline void
+extent_size_set(extent_t *extent, size_t size) {
+	assert((size & ~EXTENT_SIZE_MASK) == 0);
+	extent->e_size_esn = size | (extent->e_size_esn & ~EXTENT_SIZE_MASK);
+}
+
+static inline void
+extent_esn_set(extent_t *extent, size_t esn) {
+	extent->e_size_esn = (extent->e_size_esn & ~EXTENT_ESN_MASK) | (esn &
+	    EXTENT_ESN_MASK);
+}
+
+static inline void
+extent_bsize_set(extent_t *extent, size_t bsize) {
+	extent->e_bsize = bsize;
+}
+
+static inline void
+extent_szind_set(extent_t *extent, szind_t szind) {
+	assert(szind <= NSIZES); /* NSIZES means "invalid". */
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SZIND_MASK) |
+	    ((uint64_t)szind << EXTENT_BITS_SZIND_SHIFT);
+}
+
+static inline void
+extent_nfree_set(extent_t *extent, unsigned nfree) {
+	assert(extent_slab_get(extent));
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_NFREE_MASK) |
+	    ((uint64_t)nfree << EXTENT_BITS_NFREE_SHIFT);
+}
+
+static inline void
+extent_nfree_inc(extent_t *extent) {
+	assert(extent_slab_get(extent));
+	extent->e_bits += ((uint64_t)1U << EXTENT_BITS_NFREE_SHIFT);
+}
+
+static inline void
+extent_nfree_dec(extent_t *extent) {
+	assert(extent_slab_get(extent));
+	extent->e_bits -= ((uint64_t)1U << EXTENT_BITS_NFREE_SHIFT);
+}
+
+static inline void
+extent_sn_set(extent_t *extent, size_t sn) {
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SN_MASK) |
+	    ((uint64_t)sn << EXTENT_BITS_SN_SHIFT);
+}
+
+static inline void
+extent_state_set(extent_t *extent, extent_state_t state) {
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_STATE_MASK) |
+	    ((uint64_t)state << EXTENT_BITS_STATE_SHIFT);
+}
+
+static inline void
+extent_zeroed_set(extent_t *extent, bool zeroed) {
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_ZEROED_MASK) |
+	    ((uint64_t)zeroed << EXTENT_BITS_ZEROED_SHIFT);
+}
+
+static inline void
+extent_committed_set(extent_t *extent, bool committed) {
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_COMMITTED_MASK) |
+	    ((uint64_t)committed << EXTENT_BITS_COMMITTED_SHIFT);
+}
+
+static inline void
+extent_slab_set(extent_t *extent, bool slab) {
+	extent->e_bits = (extent->e_bits & ~EXTENT_BITS_SLAB_MASK) |
+	    ((uint64_t)slab << EXTENT_BITS_SLAB_SHIFT);
+}
+
+static inline void
+extent_prof_tctx_set(extent_t *extent, prof_tctx_t *tctx) {
+	atomic_store_p(&extent->e_prof_tctx, tctx, ATOMIC_RELEASE);
+}
+
+static inline void
+extent_init(extent_t *extent, arena_t *arena, void *addr, size_t size,
+    bool slab, szind_t szind, size_t sn, extent_state_t state, bool zeroed,
+    bool committed) {
+	assert(addr == PAGE_ADDR2BASE(addr) || !slab);
+
+	extent_arena_set(extent, arena);
+	extent_addr_set(extent, addr);
+	extent_size_set(extent, size);
+	extent_slab_set(extent, slab);
+	extent_szind_set(extent, szind);
+	extent_sn_set(extent, sn);
+	extent_state_set(extent, state);
+	extent_zeroed_set(extent, zeroed);
+	extent_committed_set(extent, committed);
+	ql_elm_new(extent, ql_link);
+	if (config_prof) {
+		extent_prof_tctx_set(extent, NULL);
+	}
+}
+
+static inline void
+extent_binit(extent_t *extent, void *addr, size_t bsize, size_t sn) {
+	extent_arena_set(extent, NULL);
+	extent_addr_set(extent, addr);
+	extent_bsize_set(extent, bsize);
+	extent_slab_set(extent, false);
+	extent_szind_set(extent, NSIZES);
+	extent_sn_set(extent, sn);
+	extent_state_set(extent, extent_state_active);
+	extent_zeroed_set(extent, true);
+	extent_committed_set(extent, true);
+}
+
+static inline void
+extent_list_init(extent_list_t *list) {
+	ql_new(list);
+}
+
+static inline extent_t *
+extent_list_first(const extent_list_t *list) {
+	return ql_first(list);
+}
+
+static inline extent_t *
+extent_list_last(const extent_list_t *list) {
+	return ql_last(list, ql_link);
+}
+
+static inline void
+extent_list_append(extent_list_t *list, extent_t *extent) {
+	ql_tail_insert(list, extent, ql_link);
+}
+
+static inline void
+extent_list_replace(extent_list_t *list, extent_t *to_remove,
+    extent_t *to_insert) {
+	ql_after_insert(to_remove, to_insert, ql_link);
+	ql_remove(list, to_remove, ql_link);
+}
+
+static inline void
+extent_list_remove(extent_list_t *list, extent_t *extent) {
+	ql_remove(list, extent, ql_link);
+}
+
+static inline int
+extent_sn_comp(const extent_t *a, const extent_t *b) {
+	size_t a_sn = extent_sn_get(a);
+	size_t b_sn = extent_sn_get(b);
+
+	return (a_sn > b_sn) - (a_sn < b_sn);
+}
+
+static inline int
+extent_esn_comp(const extent_t *a, const extent_t *b) {
+	size_t a_esn = extent_esn_get(a);
+	size_t b_esn = extent_esn_get(b);
+
+	return (a_esn > b_esn) - (a_esn < b_esn);
+}
+
+static inline int
+extent_ad_comp(const extent_t *a, const extent_t *b) {
+	uintptr_t a_addr = (uintptr_t)extent_addr_get(a);
+	uintptr_t b_addr = (uintptr_t)extent_addr_get(b);
+
+	return (a_addr > b_addr) - (a_addr < b_addr);
+}
+
+static inline int
+extent_ead_comp(const extent_t *a, const extent_t *b) {
+	uintptr_t a_eaddr = (uintptr_t)a;
+	uintptr_t b_eaddr = (uintptr_t)b;
+
+	return (a_eaddr > b_eaddr) - (a_eaddr < b_eaddr);
+}
+
+static inline int
+extent_snad_comp(const extent_t *a, const extent_t *b) {
+	int ret;
+
+	ret = extent_sn_comp(a, b);
+	if (ret != 0) {
+		return ret;
+	}
+
+	ret = extent_ad_comp(a, b);
+	return ret;
+}
+
+static inline int
+extent_esnead_comp(const extent_t *a, const extent_t *b) {
+	int ret;
+
+	ret = extent_esn_comp(a, b);
+	if (ret != 0) {
+		return ret;
+	}
+
+	ret = extent_ead_comp(a, b);
+	return ret;
+}
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_INLINES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_mmap.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_mmap.h
new file mode 100644
index 0000000000..55f17ee487
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_mmap.h
@@ -0,0 +1,10 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_MMAP_EXTERNS_H
+#define JEMALLOC_INTERNAL_EXTENT_MMAP_EXTERNS_H
+
+extern bool opt_retain;
+
+void *extent_alloc_mmap(void *new_addr, size_t size, size_t alignment,
+    bool *zero, bool *commit);
+bool extent_dalloc_mmap(void *addr, size_t size);
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_MMAP_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_structs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_structs.h
new file mode 100644
index 0000000000..d297950345
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_structs.h
@@ -0,0 +1,199 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_STRUCTS_H
+#define JEMALLOC_INTERNAL_EXTENT_STRUCTS_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/bitmap.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/rb.h"
+#include "jemalloc/internal/ph.h"
+#include "jemalloc/internal/size_classes.h"
+
+typedef enum {
+	extent_state_active   = 0,
+	extent_state_dirty    = 1,
+	extent_state_muzzy    = 2,
+	extent_state_retained = 3
+} extent_state_t;
+
+/* Extent (span of pages).  Use accessor functions for e_* fields. */
+struct extent_s {
+	/*
+	 * Bitfield containing several fields:
+	 *
+	 * a: arena_ind
+	 * b: slab
+	 * c: committed
+	 * z: zeroed
+	 * t: state
+	 * i: szind
+	 * f: nfree
+	 * n: sn
+	 *
+	 * nnnnnnnn ... nnnnnfff fffffffi iiiiiiit tzcbaaaa aaaaaaaa
+	 *
+	 * arena_ind: Arena from which this extent came, or all 1 bits if
+	 *            unassociated.
+	 *
+	 * slab: The slab flag indicates whether the extent is used for a slab
+	 *       of small regions.  This helps differentiate small size classes,
+	 *       and it indicates whether interior pointers can be looked up via
+	 *       iealloc().
+	 *
+	 * committed: The committed flag indicates whether physical memory is
+	 *            committed to the extent, whether explicitly or implicitly
+	 *            as on a system that overcommits and satisfies physical
+	 *            memory needs on demand via soft page faults.
+	 *
+	 * zeroed: The zeroed flag is used by extent recycling code to track
+	 *         whether memory is zero-filled.
+	 *
+	 * state: The state flag is an extent_state_t.
+	 *
+	 * szind: The szind flag indicates usable size class index for
+	 *        allocations residing in this extent, regardless of whether the
+	 *        extent is a slab.  Extent size and usable size often differ
+	 *        even for non-slabs, either due to sz_large_pad or promotion of
+	 *        sampled small regions.
+	 *
+	 * nfree: Number of free regions in slab.
+	 *
+	 * sn: Serial number (potentially non-unique).
+	 *
+	 *     Serial numbers may wrap around if !opt_retain, but as long as
+	 *     comparison functions fall back on address comparison for equal
+	 *     serial numbers, stable (if imperfect) ordering is maintained.
+	 *
+	 *     Serial numbers may not be unique even in the absence of
+	 *     wrap-around, e.g. when splitting an extent and assigning the same
+	 *     serial number to both resulting adjacent extents.
+	 */
+	uint64_t		e_bits;
+#define EXTENT_BITS_ARENA_SHIFT		0
+#define EXTENT_BITS_ARENA_MASK \
+    (((uint64_t)(1U << MALLOCX_ARENA_BITS) - 1) << EXTENT_BITS_ARENA_SHIFT)
+
+#define EXTENT_BITS_SLAB_SHIFT		MALLOCX_ARENA_BITS
+#define EXTENT_BITS_SLAB_MASK \
+    ((uint64_t)0x1U << EXTENT_BITS_SLAB_SHIFT)
+
+#define EXTENT_BITS_COMMITTED_SHIFT	(MALLOCX_ARENA_BITS + 1)
+#define EXTENT_BITS_COMMITTED_MASK \
+    ((uint64_t)0x1U << EXTENT_BITS_COMMITTED_SHIFT)
+
+#define EXTENT_BITS_ZEROED_SHIFT	(MALLOCX_ARENA_BITS + 2)
+#define EXTENT_BITS_ZEROED_MASK \
+    ((uint64_t)0x1U << EXTENT_BITS_ZEROED_SHIFT)
+
+#define EXTENT_BITS_STATE_SHIFT		(MALLOCX_ARENA_BITS + 3)
+#define EXTENT_BITS_STATE_MASK \
+    ((uint64_t)0x3U << EXTENT_BITS_STATE_SHIFT)
+
+#define EXTENT_BITS_SZIND_SHIFT		(MALLOCX_ARENA_BITS + 5)
+#define EXTENT_BITS_SZIND_MASK \
+    (((uint64_t)(1U << LG_CEIL_NSIZES) - 1) << EXTENT_BITS_SZIND_SHIFT)
+
+#define EXTENT_BITS_NFREE_SHIFT \
+    (MALLOCX_ARENA_BITS + 5 + LG_CEIL_NSIZES)
+#define EXTENT_BITS_NFREE_MASK \
+    ((uint64_t)((1U << (LG_SLAB_MAXREGS + 1)) - 1) << EXTENT_BITS_NFREE_SHIFT)
+
+#define EXTENT_BITS_SN_SHIFT \
+    (MALLOCX_ARENA_BITS + 5 + LG_CEIL_NSIZES + (LG_SLAB_MAXREGS + 1))
+#define EXTENT_BITS_SN_MASK		(UINT64_MAX << EXTENT_BITS_SN_SHIFT)
+
+	/* Pointer to the extent that this structure is responsible for. */
+	void			*e_addr;
+
+	union {
+		/*
+		 * Extent size and serial number associated with the extent
+		 * structure (different than the serial number for the extent at
+		 * e_addr).
+		 *
+		 * ssssssss [...] ssssssss ssssnnnn nnnnnnnn
+		 */
+		size_t			e_size_esn;
+	#define EXTENT_SIZE_MASK	((size_t)~(PAGE-1))
+	#define EXTENT_ESN_MASK		((size_t)PAGE-1)
+		/* Base extent size, which may not be a multiple of PAGE. */
+		size_t			e_bsize;
+	};
+
+	union {
+		/*
+		 * List linkage, used by a variety of lists:
+		 * - arena_bin_t's slabs_full
+		 * - extents_t's LRU
+		 * - stashed dirty extents
+		 * - arena's large allocations
+		 */
+		ql_elm(extent_t)	ql_link;
+		/* Red-black tree linkage, used by arena's extent_avail. */
+		rb_node(extent_t)	rb_link;
+	};
+
+	/* Linkage for per size class sn/address-ordered heaps. */
+	phn(extent_t)		ph_link;
+
+	union {
+		/* Small region slab metadata. */
+		arena_slab_data_t	e_slab_data;
+
+		/*
+		 * Profile counters, used for large objects.  Points to a
+		 * prof_tctx_t.
+		 */
+		atomic_p_t		e_prof_tctx;
+	};
+};
+typedef ql_head(extent_t) extent_list_t;
+typedef rb_tree(extent_t) extent_tree_t;
+typedef ph(extent_t) extent_heap_t;
+
+/* Quantized collection of extents, with built-in LRU queue. */
+struct extents_s {
+	malloc_mutex_t		mtx;
+
+	/*
+	 * Quantized per size class heaps of extents.
+	 *
+	 * Synchronization: mtx.
+	 */
+	extent_heap_t		heaps[NPSIZES+1];
+
+	/*
+	 * Bitmap for which set bits correspond to non-empty heaps.
+	 *
+	 * Synchronization: mtx.
+	 */
+	bitmap_t		bitmap[BITMAP_GROUPS(NPSIZES+1)];
+
+	/*
+	 * LRU of all extents in heaps.
+	 *
+	 * Synchronization: mtx.
+	 */
+	extent_list_t		lru;
+
+	/*
+	 * Page sum for all extents in heaps.
+	 *
+	 * The synchronization here is a little tricky.  Modifications to npages
+	 * must hold mtx, but reads need not (though, a reader who sees npages
+	 * without holding the mutex can't assume anything about the rest of the
+	 * state of the extents_t).
+	 */
+	atomic_zu_t		npages;
+
+	/* All stored extents must be in the same state. */
+	extent_state_t		state;
+
+	/*
+	 * If true, delay coalescing until eviction; otherwise coalesce during
+	 * deallocation.
+	 */
+	bool			delay_coalesce;
+};
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_STRUCTS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_types.h
new file mode 100644
index 0000000000..b6905ce105
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/extent_types.h
@@ -0,0 +1,9 @@
+#ifndef JEMALLOC_INTERNAL_EXTENT_TYPES_H
+#define JEMALLOC_INTERNAL_EXTENT_TYPES_H
+
+typedef struct extent_s extent_t;
+typedef struct extents_s extents_t;
+
+#define EXTENT_HOOKS_INITIALIZER	NULL
+
+#endif /* JEMALLOC_INTERNAL_EXTENT_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hash.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hash.h
index c7183ede82..188296cf0e 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hash.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hash.h
@@ -1,92 +1,76 @@
+#ifndef JEMALLOC_INTERNAL_HASH_H
+#define JEMALLOC_INTERNAL_HASH_H
+
+#include "jemalloc/internal/assert.h"
+
 /*
  * The following hash function is based on MurmurHash3, placed into the public
- * domain by Austin Appleby.  See http://code.google.com/p/smhasher/ for
+ * domain by Austin Appleby.  See https://github.com/aappleby/smhasher for
  * details.
  */
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-#ifndef JEMALLOC_ENABLE_INLINE
-uint32_t	hash_x86_32(const void *key, int len, uint32_t seed);
-void	hash_x86_128(const void *key, const int len, uint32_t seed,
-    uint64_t r_out[2]);
-void	hash_x64_128(const void *key, const int len, const uint32_t seed,
-    uint64_t r_out[2]);
-void	hash(const void *key, size_t len, const uint32_t seed,
-    size_t r_hash[2]);
-#endif
-
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_HASH_C_))
 /******************************************************************************/
 /* Internal implementation. */
-JEMALLOC_INLINE uint32_t
-hash_rotl_32(uint32_t x, int8_t r)
-{
-
-	return (x << r) | (x >> (32 - r));
+static inline uint32_t
+hash_rotl_32(uint32_t x, int8_t r) {
+	return ((x << r) | (x >> (32 - r)));
 }
 
-JEMALLOC_INLINE uint64_t
-hash_rotl_64(uint64_t x, int8_t r)
-{
-	return (x << r) | (x >> (64 - r));
+static inline uint64_t
+hash_rotl_64(uint64_t x, int8_t r) {
+	return ((x << r) | (x >> (64 - r)));
 }
 
-JEMALLOC_INLINE uint32_t
-hash_get_block_32(const uint32_t *p, int i)
-{
+static inline uint32_t
+hash_get_block_32(const uint32_t *p, int i) {
+	/* Handle unaligned read. */
+	if (unlikely((uintptr_t)p & (sizeof(uint32_t)-1)) != 0) {
+		uint32_t ret;
 
-	return (p[i]);
+		memcpy(&ret, (uint8_t *)(p + i), sizeof(uint32_t));
+		return ret;
+	}
+
+	return p[i];
 }
 
-JEMALLOC_INLINE uint64_t
-hash_get_block_64(const uint64_t *p, int i)
-{
+static inline uint64_t
+hash_get_block_64(const uint64_t *p, int i) {
+	/* Handle unaligned read. */
+	if (unlikely((uintptr_t)p & (sizeof(uint64_t)-1)) != 0) {
+		uint64_t ret;
 
-	return (p[i]);
-}
+		memcpy(&ret, (uint8_t *)(p + i), sizeof(uint64_t));
+		return ret;
+	}
 
-JEMALLOC_INLINE uint32_t
-hash_fmix_32(uint32_t h)
-{
+	return p[i];
+}
 
+static inline uint32_t
+hash_fmix_32(uint32_t h) {
 	h ^= h >> 16;
 	h *= 0x85ebca6b;
 	h ^= h >> 13;
 	h *= 0xc2b2ae35;
 	h ^= h >> 16;
 
-	return (h);
+	return h;
 }
 
-JEMALLOC_INLINE uint64_t
-hash_fmix_64(uint64_t k)
-{
-
+static inline uint64_t
+hash_fmix_64(uint64_t k) {
 	k ^= k >> 33;
-	k *= QU(0xff51afd7ed558ccdLLU);
+	k *= KQU(0xff51afd7ed558ccd);
 	k ^= k >> 33;
-	k *= QU(0xc4ceb9fe1a85ec53LLU);
+	k *= KQU(0xc4ceb9fe1a85ec53);
 	k ^= k >> 33;
 
-	return (k);
+	return k;
 }
 
-JEMALLOC_INLINE uint32_t
-hash_x86_32(const void *key, int len, uint32_t seed)
-{
+static inline uint32_t
+hash_x86_32(const void *key, int len, uint32_t seed) {
 	const uint8_t *data = (const uint8_t *) key;
 	const int nblocks = len / 4;
 
@@ -132,13 +116,12 @@ hash_x86_32(const void *key, int len, uint32_t seed)
 
 	h1 = hash_fmix_32(h1);
 
-	return (h1);
+	return h1;
 }
 
-UNUSED JEMALLOC_INLINE void
+UNUSED static inline void
 hash_x86_128(const void *key, const int len, uint32_t seed,
-    uint64_t r_out[2])
-{
+    uint64_t r_out[2]) {
 	const uint8_t * data = (const uint8_t *) key;
 	const int nblocks = len / 16;
 
@@ -237,18 +220,17 @@ hash_x86_128(const void *key, const int len, uint32_t seed,
 	r_out[1] = (((uint64_t) h4) << 32) | h3;
 }
 
-UNUSED JEMALLOC_INLINE void
+UNUSED static inline void
 hash_x64_128(const void *key, const int len, const uint32_t seed,
-    uint64_t r_out[2])
-{
+    uint64_t r_out[2]) {
 	const uint8_t *data = (const uint8_t *) key;
 	const int nblocks = len / 16;
 
 	uint64_t h1 = seed;
 	uint64_t h2 = seed;
 
-	const uint64_t c1 = QU(0x87c37b91114253d5LLU);
-	const uint64_t c2 = QU(0x4cf5ad432745937fLLU);
+	const uint64_t c1 = KQU(0x87c37b91114253d5);
+	const uint64_t c2 = KQU(0x4cf5ad432745937f);
 
 	/* body */
 	{
@@ -317,19 +299,20 @@ hash_x64_128(const void *key, const int len, const uint32_t seed,
 
 /******************************************************************************/
 /* API. */
-JEMALLOC_INLINE void
-hash(const void *key, size_t len, const uint32_t seed, size_t r_hash[2])
-{
+static inline void
+hash(const void *key, size_t len, const uint32_t seed, size_t r_hash[2]) {
+	assert(len <= INT_MAX); /* Unfortunate implementation limitation. */
+
 #if (LG_SIZEOF_PTR == 3 && !defined(JEMALLOC_BIG_ENDIAN))
-	hash_x64_128(key, len, seed, (uint64_t *)r_hash);
+	hash_x64_128(key, (int)len, seed, (uint64_t *)r_hash);
 #else
-	uint64_t hashes[2];
-	hash_x86_128(key, len, seed, hashes);
-	r_hash[0] = (size_t)hashes[0];
-	r_hash[1] = (size_t)hashes[1];
+	{
+		uint64_t hashes[2];
+		hash_x86_128(key, (int)len, seed, hashes);
+		r_hash[0] = (size_t)hashes[0];
+		r_hash[1] = (size_t)hashes[1];
+	}
 #endif
 }
-#endif
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_HASH_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hooks.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hooks.h
new file mode 100644
index 0000000000..cd49afcb09
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/hooks.h
@@ -0,0 +1,19 @@
+#ifndef JEMALLOC_INTERNAL_HOOKS_H
+#define JEMALLOC_INTERNAL_HOOKS_H
+
+extern JEMALLOC_EXPORT void (*hooks_arena_new_hook)();
+extern JEMALLOC_EXPORT void (*hooks_libc_hook)();
+
+#define JEMALLOC_HOOK(fn, hook) ((void)(hook != NULL && (hook(), 0)), fn)
+
+#define open JEMALLOC_HOOK(open, hooks_libc_hook)
+#define read JEMALLOC_HOOK(read, hooks_libc_hook)
+#define write JEMALLOC_HOOK(write, hooks_libc_hook)
+#define readlink JEMALLOC_HOOK(readlink, hooks_libc_hook)
+#define close JEMALLOC_HOOK(close, hooks_libc_hook)
+#define creat JEMALLOC_HOOK(creat, hooks_libc_hook)
+#define secure_getenv JEMALLOC_HOOK(secure_getenv, hooks_libc_hook)
+/* Note that this is undef'd and re-define'd in src/prof.c. */
+#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, hooks_libc_hook)
+
+#endif /* JEMALLOC_INTERNAL_HOOKS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h
new file mode 100644
index 0000000000..8ae5ef48cd
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_decls.h
@@ -0,0 +1,82 @@
+#ifndef JEMALLOC_INTERNAL_DECLS_H
+#define JEMALLOC_INTERNAL_DECLS_H
+
+#include <math.h>
+#ifdef _WIN32
+#  include <windows.h>
+#  include "msvc_compat/windows_extra.h"
+
+#else
+#  include <sys/param.h>
+#  include <sys/mman.h>
+#  if !defined(__pnacl__) && !defined(__native_client__)
+#    include <sys/syscall.h>
+#    if !defined(SYS_write) && defined(__NR_write)
+#      define SYS_write __NR_write
+#    endif
+#    if defined(SYS_open) && defined(__aarch64__)
+       /* Android headers may define SYS_open to __NR_open even though
+        * __NR_open may not exist on AArch64 (superseded by __NR_openat). */
+#      undef SYS_open
+#    endif
+#    include <sys/uio.h>
+#  endif
+#  include <pthread.h>
+#  include <signal.h>
+#  ifdef JEMALLOC_OS_UNFAIR_LOCK
+#    include <os/lock.h>
+#  endif
+#  ifdef JEMALLOC_GLIBC_MALLOC_HOOK
+#    include <sched.h>
+#  endif
+#  include <errno.h>
+#  include <sys/time.h>
+#  include <time.h>
+#  ifdef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME
+#    include <mach/mach_time.h>
+#  endif
+#endif
+#include <sys/types.h>
+
+#include <limits.h>
+#ifndef SIZE_T_MAX
+#  define SIZE_T_MAX	SIZE_MAX
+#endif
+#ifndef SSIZE_MAX
+#  define SSIZE_MAX	((ssize_t)(SIZE_T_MAX >> 1))
+#endif
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <stddef.h>
+#ifndef offsetof
+#  define offsetof(type, member)	((size_t)&(((type *)NULL)->member))
+#endif
+#include <string.h>
+#include <strings.h>
+#include <ctype.h>
+#ifdef _MSC_VER
+#  include <io.h>
+typedef intptr_t ssize_t;
+#  define PATH_MAX 1024
+#  define STDERR_FILENO 2
+#  define __func__ __FUNCTION__
+#  ifdef JEMALLOC_HAS_RESTRICT
+#    define restrict __restrict
+#  endif
+/* Disable warnings about deprecated system functions. */
+#  pragma warning(disable: 4996)
+#if _MSC_VER < 1800
+static int
+isblank(int c) {
+	return (c == '\t' || c == ' ');
+}
+#endif
+#else
+#  include <unistd.h>
+#endif
+#include <fcntl.h>
+
+#endif /* JEMALLOC_INTERNAL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h
new file mode 100644
index 0000000000..e10fb275d4
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_externs.h
@@ -0,0 +1,53 @@
+#ifndef JEMALLOC_INTERNAL_EXTERNS_H
+#define JEMALLOC_INTERNAL_EXTERNS_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/tsd_types.h"
+
+/* TSD checks this to set thread local slow state accordingly. */
+extern bool malloc_slow;
+
+/* Run-time options. */
+extern bool opt_abort;
+extern bool opt_abort_conf;
+extern const char *opt_junk;
+extern bool opt_junk_alloc;
+extern bool opt_junk_free;
+extern bool opt_utrace;
+extern bool opt_xmalloc;
+extern bool opt_zero;
+extern unsigned opt_narenas;
+
+/* Number of CPUs. */
+extern unsigned ncpus;
+
+/* Number of arenas used for automatic multiplexing of threads and arenas. */
+extern unsigned narenas_auto;
+
+/*
+ * Arenas that are used to service external requests.  Not all elements of the
+ * arenas array are necessarily used; arenas are created lazily as needed.
+ */
+extern atomic_p_t arenas[];
+
+void *a0malloc(size_t size);
+void a0dalloc(void *ptr);
+void *bootstrap_malloc(size_t size);
+void *bootstrap_calloc(size_t num, size_t size);
+void bootstrap_free(void *ptr);
+void arena_set(unsigned ind, arena_t *arena);
+unsigned narenas_total_get(void);
+arena_t *arena_init(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks);
+arena_tdata_t *arena_tdata_get_hard(tsd_t *tsd, unsigned ind);
+arena_t *arena_choose_hard(tsd_t *tsd, bool internal);
+void arena_migrate(tsd_t *tsd, unsigned oldind, unsigned newind);
+void iarena_cleanup(tsd_t *tsd);
+void arena_cleanup(tsd_t *tsd);
+void arenas_tdata_cleanup(tsd_t *tsd);
+void jemalloc_prefork(void);
+void jemalloc_postfork_parent(void);
+void jemalloc_postfork_child(void);
+bool malloc_initialized(void);
+
+#endif /* JEMALLOC_INTERNAL_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_includes.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_includes.h
new file mode 100644
index 0000000000..437eaa4079
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_includes.h
@@ -0,0 +1,94 @@
+#ifndef JEMALLOC_INTERNAL_INCLUDES_H
+#define JEMALLOC_INTERNAL_INCLUDES_H
+
+/*
+ * jemalloc can conceptually be broken into components (arena, tcache, etc.),
+ * but there are circular dependencies that cannot be broken without
+ * substantial performance degradation.
+ *
+ * Historically, we dealt with this by each header into four sections (types,
+ * structs, externs, and inlines), and included each header file multiple times
+ * in this file, picking out the portion we want on each pass using the
+ * following #defines:
+ *   JEMALLOC_H_TYPES   : Preprocessor-defined constants and psuedo-opaque data
+ *                        types.
+ *   JEMALLOC_H_STRUCTS : Data structures.
+ *   JEMALLOC_H_EXTERNS : Extern data declarations and function prototypes.
+ *   JEMALLOC_H_INLINES : Inline functions.
+ *
+ * We're moving toward a world in which the dependencies are explicit; each file
+ * will #include the headers it depends on (rather than relying on them being
+ * implicitly available via this file including every header file in the
+ * project).
+ *
+ * We're now in an intermediate state: we've broken up the header files to avoid
+ * having to include each one multiple times, but have not yet moved the
+ * dependency information into the header files (i.e. we still rely on the
+ * ordering in this file to ensure all a header's dependencies are available in
+ * its translation unit).  Each component is now broken up into multiple header
+ * files, corresponding to the sections above (e.g. instead of "foo.h", we now
+ * have "foo_types.h", "foo_structs.h", "foo_externs.h", "foo_inlines.h").
+ *
+ * Those files which have been converted to explicitly include their
+ * inter-component dependencies are now in the initial HERMETIC HEADERS
+ * section.  All headers may still rely on jemalloc_preamble.h (which, by fiat,
+ * must be included first in every translation unit) for system headers and
+ * global jemalloc definitions, however.
+ */
+
+/******************************************************************************/
+/* TYPES */
+/******************************************************************************/
+
+#include "jemalloc/internal/extent_types.h"
+#include "jemalloc/internal/base_types.h"
+#include "jemalloc/internal/arena_types.h"
+#include "jemalloc/internal/tcache_types.h"
+#include "jemalloc/internal/prof_types.h"
+
+/******************************************************************************/
+/* STRUCTS */
+/******************************************************************************/
+
+#include "jemalloc/internal/arena_structs_a.h"
+#include "jemalloc/internal/extent_structs.h"
+#include "jemalloc/internal/base_structs.h"
+#include "jemalloc/internal/prof_structs.h"
+#include "jemalloc/internal/arena_structs_b.h"
+#include "jemalloc/internal/tcache_structs.h"
+#include "jemalloc/internal/background_thread_structs.h"
+
+/******************************************************************************/
+/* EXTERNS */
+/******************************************************************************/
+
+#include "jemalloc/internal/jemalloc_internal_externs.h"
+#include "jemalloc/internal/extent_externs.h"
+#include "jemalloc/internal/base_externs.h"
+#include "jemalloc/internal/arena_externs.h"
+#include "jemalloc/internal/large_externs.h"
+#include "jemalloc/internal/tcache_externs.h"
+#include "jemalloc/internal/prof_externs.h"
+#include "jemalloc/internal/background_thread_externs.h"
+
+/******************************************************************************/
+/* INLINES */
+/******************************************************************************/
+
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
+#include "jemalloc/internal/base_inlines.h"
+/*
+ * Include portions of arena code interleaved with tcache code in order to
+ * resolve circular dependencies.
+ */
+#include "jemalloc/internal/prof_inlines_a.h"
+#include "jemalloc/internal/arena_inlines_a.h"
+#include "jemalloc/internal/extent_inlines.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_b.h"
+#include "jemalloc/internal/tcache_inlines.h"
+#include "jemalloc/internal/arena_inlines_b.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_c.h"
+#include "jemalloc/internal/prof_inlines_b.h"
+#include "jemalloc/internal/background_thread_inlines.h"
+
+#endif /* JEMALLOC_INTERNAL_INCLUDES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h
new file mode 100644
index 0000000000..24ea416297
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_a.h
@@ -0,0 +1,171 @@
+#ifndef JEMALLOC_INTERNAL_INLINES_A_H
+#define JEMALLOC_INTERNAL_INLINES_A_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/bit_util.h"
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/ticker.h"
+
+JEMALLOC_ALWAYS_INLINE malloc_cpuid_t
+malloc_getcpu(void) {
+	assert(have_percpu_arena);
+#if defined(JEMALLOC_HAVE_SCHED_GETCPU)
+	return (malloc_cpuid_t)sched_getcpu();
+#else
+	not_reached();
+	return -1;
+#endif
+}
+
+/* Return the chosen arena index based on current cpu. */
+JEMALLOC_ALWAYS_INLINE unsigned
+percpu_arena_choose(void) {
+	assert(have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena));
+
+	malloc_cpuid_t cpuid = malloc_getcpu();
+	assert(cpuid >= 0);
+
+	unsigned arena_ind;
+	if ((opt_percpu_arena == percpu_arena) || ((unsigned)cpuid < ncpus /
+	    2)) {
+		arena_ind = cpuid;
+	} else {
+		assert(opt_percpu_arena == per_phycpu_arena);
+		/* Hyper threads on the same physical CPU share arena. */
+		arena_ind = cpuid - ncpus / 2;
+	}
+
+	return arena_ind;
+}
+
+/* Return the limit of percpu auto arena range, i.e. arenas[0...ind_limit). */
+JEMALLOC_ALWAYS_INLINE unsigned
+percpu_arena_ind_limit(percpu_arena_mode_t mode) {
+	assert(have_percpu_arena && PERCPU_ARENA_ENABLED(mode));
+	if (mode == per_phycpu_arena && ncpus > 1) {
+		if (ncpus % 2) {
+			/* This likely means a misconfig. */
+			return ncpus / 2 + 1;
+		}
+		return ncpus / 2;
+	} else {
+		return ncpus;
+	}
+}
+
+static inline arena_tdata_t *
+arena_tdata_get(tsd_t *tsd, unsigned ind, bool refresh_if_missing) {
+	arena_tdata_t *tdata;
+	arena_tdata_t *arenas_tdata = tsd_arenas_tdata_get(tsd);
+
+	if (unlikely(arenas_tdata == NULL)) {
+		/* arenas_tdata hasn't been initialized yet. */
+		return arena_tdata_get_hard(tsd, ind);
+	}
+	if (unlikely(ind >= tsd_narenas_tdata_get(tsd))) {
+		/*
+		 * ind is invalid, cache is old (too small), or tdata to be
+		 * initialized.
+		 */
+		return (refresh_if_missing ? arena_tdata_get_hard(tsd, ind) :
+		    NULL);
+	}
+
+	tdata = &arenas_tdata[ind];
+	if (likely(tdata != NULL) || !refresh_if_missing) {
+		return tdata;
+	}
+	return arena_tdata_get_hard(tsd, ind);
+}
+
+static inline arena_t *
+arena_get(tsdn_t *tsdn, unsigned ind, bool init_if_missing) {
+	arena_t *ret;
+
+	assert(ind < MALLOCX_ARENA_LIMIT);
+
+	ret = (arena_t *)atomic_load_p(&arenas[ind], ATOMIC_ACQUIRE);
+	if (unlikely(ret == NULL)) {
+		if (init_if_missing) {
+			ret = arena_init(tsdn, ind,
+			    (extent_hooks_t *)&extent_hooks_default);
+		}
+	}
+	return ret;
+}
+
+static inline ticker_t *
+decay_ticker_get(tsd_t *tsd, unsigned ind) {
+	arena_tdata_t *tdata;
+
+	tdata = arena_tdata_get(tsd, ind, true);
+	if (unlikely(tdata == NULL)) {
+		return NULL;
+	}
+	return &tdata->decay_ticker;
+}
+
+JEMALLOC_ALWAYS_INLINE tcache_bin_t *
+tcache_small_bin_get(tcache_t *tcache, szind_t binind) {
+	assert(binind < NBINS);
+	return &tcache->tbins_small[binind];
+}
+
+JEMALLOC_ALWAYS_INLINE tcache_bin_t *
+tcache_large_bin_get(tcache_t *tcache, szind_t binind) {
+	assert(binind >= NBINS &&binind < nhbins);
+	return &tcache->tbins_large[binind - NBINS];
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tcache_available(tsd_t *tsd) {
+	/*
+	 * Thread specific auto tcache might be unavailable if: 1) during tcache
+	 * initialization, or 2) disabled through thread.tcache.enabled mallctl
+	 * or config options.  This check covers all cases.
+	 */
+	if (likely(tsd_tcache_enabled_get(tsd))) {
+		/* Associated arena == NULL implies tcache init in progress. */
+		assert(tsd_tcachep_get(tsd)->arena == NULL ||
+		    tcache_small_bin_get(tsd_tcachep_get(tsd), 0)->avail !=
+		    NULL);
+		return true;
+	}
+
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE tcache_t *
+tcache_get(tsd_t *tsd) {
+	if (!tcache_available(tsd)) {
+		return NULL;
+	}
+
+	return tsd_tcachep_get(tsd);
+}
+
+static inline void
+pre_reentrancy(tsd_t *tsd, arena_t *arena) {
+	/* arena is the current context.  Reentry from a0 is not allowed. */
+	assert(arena != arena_get(tsd_tsdn(tsd), 0, false));
+
+	bool fast = tsd_fast(tsd);
+	++*tsd_reentrancy_levelp_get(tsd);
+	if (fast) {
+		/* Prepare slow path for reentrancy. */
+		tsd_slow_update(tsd);
+		assert(tsd->state == tsd_state_nominal_slow);
+	}
+}
+
+static inline void
+post_reentrancy(tsd_t *tsd) {
+	int8_t *reentrancy_level = tsd_reentrancy_levelp_get(tsd);
+	assert(*reentrancy_level > 0);
+	if (--*reentrancy_level == 0) {
+		tsd_slow_update(tsd);
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_INLINES_A_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h
new file mode 100644
index 0000000000..2e76e5d8f7
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_b.h
@@ -0,0 +1,86 @@
+#ifndef JEMALLOC_INTERNAL_INLINES_B_H
+#define JEMALLOC_INTERNAL_INLINES_B_H
+
+#include "jemalloc/internal/rtree.h"
+
+/* Choose an arena based on a per-thread value. */
+static inline arena_t *
+arena_choose_impl(tsd_t *tsd, arena_t *arena, bool internal) {
+	arena_t *ret;
+
+	if (arena != NULL) {
+		return arena;
+	}
+
+	/* During reentrancy, arena 0 is the safest bet. */
+	if (unlikely(tsd_reentrancy_level_get(tsd) > 0)) {
+		return arena_get(tsd_tsdn(tsd), 0, true);
+	}
+
+	ret = internal ? tsd_iarena_get(tsd) : tsd_arena_get(tsd);
+	if (unlikely(ret == NULL)) {
+		ret = arena_choose_hard(tsd, internal);
+		assert(ret);
+		if (tcache_available(tsd)) {
+			tcache_t *tcache = tcache_get(tsd);
+			if (tcache->arena != NULL) {
+				/* See comments in tcache_data_init().*/
+				assert(tcache->arena ==
+				    arena_get(tsd_tsdn(tsd), 0, false));
+				if (tcache->arena != ret) {
+					tcache_arena_reassociate(tsd_tsdn(tsd),
+					    tcache, ret);
+				}
+			} else {
+				tcache_arena_associate(tsd_tsdn(tsd), tcache,
+				    ret);
+			}
+		}
+	}
+
+	/*
+	 * Note that for percpu arena, if the current arena is outside of the
+	 * auto percpu arena range, (i.e. thread is assigned to a manually
+	 * managed arena), then percpu arena is skipped.
+	 */
+	if (have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena) &&
+	    !internal && (arena_ind_get(ret) <
+	    percpu_arena_ind_limit(opt_percpu_arena)) && (ret->last_thd !=
+	    tsd_tsdn(tsd))) {
+		unsigned ind = percpu_arena_choose();
+		if (arena_ind_get(ret) != ind) {
+			percpu_arena_update(tsd, ind);
+			ret = tsd_arena_get(tsd);
+		}
+		ret->last_thd = tsd_tsdn(tsd);
+	}
+
+	return ret;
+}
+
+static inline arena_t *
+arena_choose(tsd_t *tsd, arena_t *arena) {
+	return arena_choose_impl(tsd, arena, false);
+}
+
+static inline arena_t *
+arena_ichoose(tsd_t *tsd, arena_t *arena) {
+	return arena_choose_impl(tsd, arena, true);
+}
+
+static inline bool
+arena_is_auto(arena_t *arena) {
+	assert(narenas_auto > 0);
+	return (arena_ind_get(arena) < narenas_auto);
+}
+
+JEMALLOC_ALWAYS_INLINE extent_t *
+iealloc(tsdn_t *tsdn, const void *ptr) {
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	return rtree_extent_read(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true);
+}
+
+#endif /* JEMALLOC_INTERNAL_INLINES_B_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h
new file mode 100644
index 0000000000..7ffce6fb03
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_inlines_c.h
@@ -0,0 +1,197 @@
+#ifndef JEMALLOC_INTERNAL_INLINES_C_H
+#define JEMALLOC_INTERNAL_INLINES_C_H
+
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/sz.h"
+#include "jemalloc/internal/witness.h"
+
+JEMALLOC_ALWAYS_INLINE arena_t *
+iaalloc(tsdn_t *tsdn, const void *ptr) {
+	assert(ptr != NULL);
+
+	return arena_aalloc(tsdn, ptr);
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+isalloc(tsdn_t *tsdn, const void *ptr) {
+	assert(ptr != NULL);
+
+	return arena_salloc(tsdn, ptr);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+iallocztm(tsdn_t *tsdn, size_t size, szind_t ind, bool zero, tcache_t *tcache,
+    bool is_internal, arena_t *arena, bool slow_path) {
+	void *ret;
+
+	assert(size != 0);
+	assert(!is_internal || tcache == NULL);
+	assert(!is_internal || arena == NULL || arena_is_auto(arena));
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	ret = arena_malloc(tsdn, arena, size, ind, zero, tcache, slow_path);
+	if (config_stats && is_internal && likely(ret != NULL)) {
+		arena_internal_add(iaalloc(tsdn, ret), isalloc(tsdn, ret));
+	}
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+ialloc(tsd_t *tsd, size_t size, szind_t ind, bool zero, bool slow_path) {
+	return iallocztm(tsd_tsdn(tsd), size, ind, zero, tcache_get(tsd), false,
+	    NULL, slow_path);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+ipallocztm(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero,
+    tcache_t *tcache, bool is_internal, arena_t *arena) {
+	void *ret;
+
+	assert(usize != 0);
+	assert(usize == sz_sa2u(usize, alignment));
+	assert(!is_internal || tcache == NULL);
+	assert(!is_internal || arena == NULL || arena_is_auto(arena));
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	ret = arena_palloc(tsdn, arena, usize, alignment, zero, tcache);
+	assert(ALIGNMENT_ADDR2BASE(ret, alignment) == ret);
+	if (config_stats && is_internal && likely(ret != NULL)) {
+		arena_internal_add(iaalloc(tsdn, ret), isalloc(tsdn, ret));
+	}
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+ipalloct(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero,
+    tcache_t *tcache, arena_t *arena) {
+	return ipallocztm(tsdn, usize, alignment, zero, tcache, false, arena);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+ipalloc(tsd_t *tsd, size_t usize, size_t alignment, bool zero) {
+	return ipallocztm(tsd_tsdn(tsd), usize, alignment, zero,
+	    tcache_get(tsd), false, NULL);
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+ivsalloc(tsdn_t *tsdn, const void *ptr) {
+	return arena_vsalloc(tsdn, ptr);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+idalloctm(tsdn_t *tsdn, void *ptr, tcache_t *tcache, alloc_ctx_t *alloc_ctx,
+    bool is_internal, bool slow_path) {
+	assert(ptr != NULL);
+	assert(!is_internal || tcache == NULL);
+	assert(!is_internal || arena_is_auto(iaalloc(tsdn, ptr)));
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+	if (config_stats && is_internal) {
+		arena_internal_sub(iaalloc(tsdn, ptr), isalloc(tsdn, ptr));
+	}
+	if (!is_internal && tsd_reentrancy_level_get(tsdn_tsd(tsdn)) != 0) {
+		assert(tcache == NULL);
+	}
+	arena_dalloc(tsdn, ptr, tcache, alloc_ctx, slow_path);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+idalloc(tsd_t *tsd, void *ptr) {
+	idalloctm(tsd_tsdn(tsd), ptr, tcache_get(tsd), NULL, false, true);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+isdalloct(tsdn_t *tsdn, void *ptr, size_t size, tcache_t *tcache,
+    alloc_ctx_t *alloc_ctx, bool slow_path) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+	arena_sdalloc(tsdn, ptr, size, tcache, alloc_ctx, slow_path);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+iralloct_realign(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size,
+    size_t extra, size_t alignment, bool zero, tcache_t *tcache,
+    arena_t *arena) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+	void *p;
+	size_t usize, copysize;
+
+	usize = sz_sa2u(size + extra, alignment);
+	if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
+		return NULL;
+	}
+	p = ipalloct(tsdn, usize, alignment, zero, tcache, arena);
+	if (p == NULL) {
+		if (extra == 0) {
+			return NULL;
+		}
+		/* Try again, without extra this time. */
+		usize = sz_sa2u(size, alignment);
+		if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
+			return NULL;
+		}
+		p = ipalloct(tsdn, usize, alignment, zero, tcache, arena);
+		if (p == NULL) {
+			return NULL;
+		}
+	}
+	/*
+	 * Copy at most size bytes (not size+extra), since the caller has no
+	 * expectation that the extra bytes will be reliably preserved.
+	 */
+	copysize = (size < oldsize) ? size : oldsize;
+	memcpy(p, ptr, copysize);
+	isdalloct(tsdn, ptr, oldsize, tcache, NULL, true);
+	return p;
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+iralloct(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, size_t alignment,
+    bool zero, tcache_t *tcache, arena_t *arena) {
+	assert(ptr != NULL);
+	assert(size != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	if (alignment != 0 && ((uintptr_t)ptr & ((uintptr_t)alignment-1))
+	    != 0) {
+		/*
+		 * Existing object alignment is inadequate; allocate new space
+		 * and copy.
+		 */
+		return iralloct_realign(tsdn, ptr, oldsize, size, 0, alignment,
+		    zero, tcache, arena);
+	}
+
+	return arena_ralloc(tsdn, arena, ptr, oldsize, size, alignment, zero,
+	    tcache);
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+iralloc(tsd_t *tsd, void *ptr, size_t oldsize, size_t size, size_t alignment,
+    bool zero) {
+	return iralloct(tsd_tsdn(tsd), ptr, oldsize, size, alignment, zero,
+	    tcache_get(tsd), NULL);
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+ixalloc(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size, size_t extra,
+    size_t alignment, bool zero) {
+	assert(ptr != NULL);
+	assert(size != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	if (alignment != 0 && ((uintptr_t)ptr & ((uintptr_t)alignment-1))
+	    != 0) {
+		/* Existing object alignment is inadequate. */
+		return true;
+	}
+
+	return arena_ralloc_no_move(tsdn, ptr, oldsize, size, extra, zero);
+}
+
+#endif /* JEMALLOC_INTERNAL_INLINES_C_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h
new file mode 100644
index 0000000000..4571895ec3
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_macros.h
@@ -0,0 +1,40 @@
+#ifndef JEMALLOC_INTERNAL_MACROS_H
+#define JEMALLOC_INTERNAL_MACROS_H
+
+#ifdef JEMALLOC_DEBUG
+#  define JEMALLOC_ALWAYS_INLINE static inline
+#else
+#  define JEMALLOC_ALWAYS_INLINE JEMALLOC_ATTR(always_inline) static inline
+#endif
+#ifdef _MSC_VER
+#  define inline _inline
+#endif
+
+#define UNUSED JEMALLOC_ATTR(unused)
+
+#define ZU(z)	((size_t)z)
+#define ZD(z)	((ssize_t)z)
+#define QU(q)	((uint64_t)q)
+#define QD(q)	((int64_t)q)
+
+#define KZU(z)	ZU(z##ULL)
+#define KZD(z)	ZD(z##LL)
+#define KQU(q)	QU(q##ULL)
+#define KQD(q)	QI(q##LL)
+
+#ifndef __DECONST
+#  define	__DECONST(type, var)	((type)(uintptr_t)(const void *)(var))
+#endif
+
+#if !defined(JEMALLOC_HAS_RESTRICT) || defined(__cplusplus)
+#  define restrict
+#endif
+
+/* Various function pointers are statick and immutable except during testing. */
+#ifdef JEMALLOC_JET
+#  define JET_MUTABLE
+#else
+#  define JET_MUTABLE const
+#endif
+
+#endif /* JEMALLOC_INTERNAL_MACROS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h
new file mode 100644
index 0000000000..50f9d001d5
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_internal_types.h
@@ -0,0 +1,178 @@
+#ifndef JEMALLOC_INTERNAL_TYPES_H
+#define JEMALLOC_INTERNAL_TYPES_H
+
+/* Page size index type. */
+typedef unsigned pszind_t;
+
+/* Size class index type. */
+typedef unsigned szind_t;
+
+/* Processor / core id type. */
+typedef int malloc_cpuid_t;
+
+/*
+ * Flags bits:
+ *
+ * a: arena
+ * t: tcache
+ * 0: unused
+ * z: zero
+ * n: alignment
+ *
+ * aaaaaaaa aaaatttt tttttttt 0znnnnnn
+ */
+#define MALLOCX_ARENA_BITS	12
+#define MALLOCX_TCACHE_BITS	12
+#define MALLOCX_LG_ALIGN_BITS	6
+#define MALLOCX_ARENA_SHIFT	20
+#define MALLOCX_TCACHE_SHIFT	8
+#define MALLOCX_ARENA_MASK \
+    (((1 << MALLOCX_ARENA_BITS) - 1) << MALLOCX_ARENA_SHIFT)
+/* NB: Arena index bias decreases the maximum number of arenas by 1. */
+#define MALLOCX_ARENA_LIMIT	((1 << MALLOCX_ARENA_BITS) - 1)
+#define MALLOCX_TCACHE_MASK \
+    (((1 << MALLOCX_TCACHE_BITS) - 1) << MALLOCX_TCACHE_SHIFT)
+#define MALLOCX_TCACHE_MAX	((1 << MALLOCX_TCACHE_BITS) - 3)
+#define MALLOCX_LG_ALIGN_MASK	((1 << MALLOCX_LG_ALIGN_BITS) - 1)
+/* Use MALLOCX_ALIGN_GET() if alignment may not be specified in flags. */
+#define MALLOCX_ALIGN_GET_SPECIFIED(flags)				\
+    (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK))
+#define MALLOCX_ALIGN_GET(flags)					\
+    (MALLOCX_ALIGN_GET_SPECIFIED(flags) & (SIZE_T_MAX-1))
+#define MALLOCX_ZERO_GET(flags)						\
+    ((bool)(flags & MALLOCX_ZERO))
+
+#define MALLOCX_TCACHE_GET(flags)					\
+    (((unsigned)((flags & MALLOCX_TCACHE_MASK) >> MALLOCX_TCACHE_SHIFT)) - 2)
+#define MALLOCX_ARENA_GET(flags)					\
+    (((unsigned)(((unsigned)flags) >> MALLOCX_ARENA_SHIFT)) - 1)
+
+/* Smallest size class to support. */
+#define TINY_MIN		(1U << LG_TINY_MIN)
+
+/*
+ * Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
+ * classes).
+ */
+#ifndef LG_QUANTUM
+#  if (defined(__i386__) || defined(_M_IX86))
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __ia64__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __alpha__
+#    define LG_QUANTUM		4
+#  endif
+#  if (defined(__sparc64__) || defined(__sparcv9) || defined(__sparc_v9__))
+#    define LG_QUANTUM		4
+#  endif
+#  if (defined(__amd64__) || defined(__x86_64__) || defined(_M_X64))
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __arm__
+#    define LG_QUANTUM		3
+#  endif
+#  ifdef __aarch64__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __hppa__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __mips__
+#    define LG_QUANTUM		3
+#  endif
+#  ifdef __or1k__
+#    define LG_QUANTUM		3
+#  endif
+#  ifdef __powerpc__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __riscv__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __s390__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __SH4__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __tile__
+#    define LG_QUANTUM		4
+#  endif
+#  ifdef __le32__
+#    define LG_QUANTUM		4
+#  endif
+#  ifndef LG_QUANTUM
+#    error "Unknown minimum alignment for architecture; specify via "
+	 "--with-lg-quantum"
+#  endif
+#endif
+
+#define QUANTUM			((size_t)(1U << LG_QUANTUM))
+#define QUANTUM_MASK		(QUANTUM - 1)
+
+/* Return the smallest quantum multiple that is >= a. */
+#define QUANTUM_CEILING(a)						\
+	(((a) + QUANTUM_MASK) & ~QUANTUM_MASK)
+
+#define LONG			((size_t)(1U << LG_SIZEOF_LONG))
+#define LONG_MASK		(LONG - 1)
+
+/* Return the smallest long multiple that is >= a. */
+#define LONG_CEILING(a)							\
+	(((a) + LONG_MASK) & ~LONG_MASK)
+
+#define SIZEOF_PTR		(1U << LG_SIZEOF_PTR)
+#define PTR_MASK		(SIZEOF_PTR - 1)
+
+/* Return the smallest (void *) multiple that is >= a. */
+#define PTR_CEILING(a)							\
+	(((a) + PTR_MASK) & ~PTR_MASK)
+
+/*
+ * Maximum size of L1 cache line.  This is used to avoid cache line aliasing.
+ * In addition, this controls the spacing of cacheline-spaced size classes.
+ *
+ * CACHELINE cannot be based on LG_CACHELINE because __declspec(align()) can
+ * only handle raw constants.
+ */
+#define LG_CACHELINE		6
+#define CACHELINE		64
+#define CACHELINE_MASK		(CACHELINE - 1)
+
+/* Return the smallest cacheline multiple that is >= s. */
+#define CACHELINE_CEILING(s)						\
+	(((s) + CACHELINE_MASK) & ~CACHELINE_MASK)
+
+/* Return the nearest aligned address at or below a. */
+#define ALIGNMENT_ADDR2BASE(a, alignment)				\
+	((void *)((uintptr_t)(a) & ((~(alignment)) + 1)))
+
+/* Return the offset between a and the nearest aligned address at or below a. */
+#define ALIGNMENT_ADDR2OFFSET(a, alignment)				\
+	((size_t)((uintptr_t)(a) & (alignment - 1)))
+
+/* Return the smallest alignment multiple that is >= s. */
+#define ALIGNMENT_CEILING(s, alignment)					\
+	(((s) + (alignment - 1)) & ((~(alignment)) + 1))
+
+/* Declare a variable-length array. */
+#if __STDC_VERSION__ < 199901L
+#  ifdef _MSC_VER
+#    include <malloc.h>
+#    define alloca _alloca
+#  else
+#    ifdef JEMALLOC_HAS_ALLOCA_H
+#      include <alloca.h>
+#    else
+#      include <stdlib.h>
+#    endif
+#  endif
+#  define VARIABLE_ARRAY(type, name, count) \
+	type *name = alloca(sizeof(type) * (count))
+#else
+#  define VARIABLE_ARRAY(type, name, count) type name[(count)]
+#endif
+
+#endif /* JEMALLOC_INTERNAL_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h
new file mode 100644
index 0000000000..39045c857f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h
@@ -0,0 +1,179 @@
+#ifndef JEMALLOC_PREAMBLE_H
+#define JEMALLOC_PREAMBLE_H
+
+#include "jemalloc_internal_defs.h"
+#include "jemalloc/internal/jemalloc_internal_decls.h"
+
+#ifdef JEMALLOC_UTRACE
+#include <sys/ktrace.h>
+#endif
+
+#define JEMALLOC_NO_DEMANGLE
+#ifdef JEMALLOC_JET
+#  undef JEMALLOC_IS_MALLOC
+#  define JEMALLOC_N(n) jet_##n
+#  include "jemalloc/internal/public_namespace.h"
+#  define JEMALLOC_NO_RENAME
+#  include "../jemalloc.h"
+#  undef JEMALLOC_NO_RENAME
+#else
+#  define JEMALLOC_N(n) je_##n
+#  include "../jemalloc.h"
+#endif
+
+#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN))
+#include <libkern/OSAtomic.h>
+#endif
+
+#ifdef JEMALLOC_ZONE
+#include <mach/mach_error.h>
+#include <mach/mach_init.h>
+#include <mach/vm_map.h>
+#endif
+
+#include "jemalloc/internal/jemalloc_internal_macros.h"
+
+/*
+ * Note that the ordering matters here; the hook itself is name-mangled.  We
+ * want the inclusion of hooks to happen early, so that we hook as much as
+ * possible.
+ */
+#ifndef JEMALLOC_NO_PRIVATE_NAMESPACE
+#  ifndef JEMALLOC_JET
+#    include "jemalloc/internal/private_namespace.h"
+#  else
+#    include "jemalloc/internal/private_namespace_jet.h"
+#  endif
+#endif
+#include "jemalloc/internal/hooks.h"
+
+static const bool config_debug =
+#ifdef JEMALLOC_DEBUG
+    true
+#else
+    false
+#endif
+    ;
+static const bool have_dss =
+#ifdef JEMALLOC_DSS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_fill =
+#ifdef JEMALLOC_FILL
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_lazy_lock =
+#ifdef JEMALLOC_LAZY_LOCK
+    true
+#else
+    false
+#endif
+    ;
+static const char * const config_malloc_conf = JEMALLOC_CONFIG_MALLOC_CONF;
+static const bool config_prof =
+#ifdef JEMALLOC_PROF
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_prof_libgcc =
+#ifdef JEMALLOC_PROF_LIBGCC
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_prof_libunwind =
+#ifdef JEMALLOC_PROF_LIBUNWIND
+    true
+#else
+    false
+#endif
+    ;
+static const bool maps_coalesce =
+#ifdef JEMALLOC_MAPS_COALESCE
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_stats =
+#ifdef JEMALLOC_STATS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_thp =
+#ifdef JEMALLOC_THP
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_tls =
+#ifdef JEMALLOC_TLS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_utrace =
+#ifdef JEMALLOC_UTRACE
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_xmalloc =
+#ifdef JEMALLOC_XMALLOC
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_cache_oblivious =
+#ifdef JEMALLOC_CACHE_OBLIVIOUS
+    true
+#else
+    false
+#endif
+    ;
+#ifdef JEMALLOC_HAVE_SCHED_GETCPU
+/* Currently percpu_arena depends on sched_getcpu. */
+#define JEMALLOC_PERCPU_ARENA
+#endif
+static const bool have_percpu_arena =
+#ifdef JEMALLOC_PERCPU_ARENA
+    true
+#else
+    false
+#endif
+    ;
+/*
+ * Undocumented, and not recommended; the application should take full
+ * responsibility for tracking provenance.
+ */
+static const bool force_ivsalloc =
+#ifdef JEMALLOC_FORCE_IVSALLOC
+    true
+#else
+    false
+#endif
+    ;
+static const bool have_background_thread =
+#ifdef JEMALLOC_BACKGROUND_THREAD
+    true
+#else
+    false
+#endif
+    ;
+
+#endif /* JEMALLOC_PREAMBLE_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h.in b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h.in
new file mode 100644
index 0000000000..18539a0988
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/jemalloc_preamble.h.in
@@ -0,0 +1,179 @@
+#ifndef JEMALLOC_PREAMBLE_H
+#define JEMALLOC_PREAMBLE_H
+
+#include "jemalloc_internal_defs.h"
+#include "jemalloc/internal/jemalloc_internal_decls.h"
+
+#ifdef JEMALLOC_UTRACE
+#include <sys/ktrace.h>
+#endif
+
+#define JEMALLOC_NO_DEMANGLE
+#ifdef JEMALLOC_JET
+#  undef JEMALLOC_IS_MALLOC
+#  define JEMALLOC_N(n) jet_##n
+#  include "jemalloc/internal/public_namespace.h"
+#  define JEMALLOC_NO_RENAME
+#  include "../jemalloc@install_suffix@.h"
+#  undef JEMALLOC_NO_RENAME
+#else
+#  define JEMALLOC_N(n) @private_namespace@##n
+#  include "../jemalloc@install_suffix@.h"
+#endif
+
+#if (defined(JEMALLOC_OSATOMIC) || defined(JEMALLOC_OSSPIN))
+#include <libkern/OSAtomic.h>
+#endif
+
+#ifdef JEMALLOC_ZONE
+#include <mach/mach_error.h>
+#include <mach/mach_init.h>
+#include <mach/vm_map.h>
+#endif
+
+#include "jemalloc/internal/jemalloc_internal_macros.h"
+
+/*
+ * Note that the ordering matters here; the hook itself is name-mangled.  We
+ * want the inclusion of hooks to happen early, so that we hook as much as
+ * possible.
+ */
+#ifndef JEMALLOC_NO_PRIVATE_NAMESPACE
+#  ifndef JEMALLOC_JET
+#    include "jemalloc/internal/private_namespace.h"
+#  else
+#    include "jemalloc/internal/private_namespace_jet.h"
+#  endif
+#endif
+#include "jemalloc/internal/hooks.h"
+
+static const bool config_debug =
+#ifdef JEMALLOC_DEBUG
+    true
+#else
+    false
+#endif
+    ;
+static const bool have_dss =
+#ifdef JEMALLOC_DSS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_fill =
+#ifdef JEMALLOC_FILL
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_lazy_lock =
+#ifdef JEMALLOC_LAZY_LOCK
+    true
+#else
+    false
+#endif
+    ;
+static const char * const config_malloc_conf = JEMALLOC_CONFIG_MALLOC_CONF;
+static const bool config_prof =
+#ifdef JEMALLOC_PROF
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_prof_libgcc =
+#ifdef JEMALLOC_PROF_LIBGCC
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_prof_libunwind =
+#ifdef JEMALLOC_PROF_LIBUNWIND
+    true
+#else
+    false
+#endif
+    ;
+static const bool maps_coalesce =
+#ifdef JEMALLOC_MAPS_COALESCE
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_stats =
+#ifdef JEMALLOC_STATS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_thp =
+#ifdef JEMALLOC_THP
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_tls =
+#ifdef JEMALLOC_TLS
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_utrace =
+#ifdef JEMALLOC_UTRACE
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_xmalloc =
+#ifdef JEMALLOC_XMALLOC
+    true
+#else
+    false
+#endif
+    ;
+static const bool config_cache_oblivious =
+#ifdef JEMALLOC_CACHE_OBLIVIOUS
+    true
+#else
+    false
+#endif
+    ;
+#ifdef JEMALLOC_HAVE_SCHED_GETCPU
+/* Currently percpu_arena depends on sched_getcpu. */
+#define JEMALLOC_PERCPU_ARENA
+#endif
+static const bool have_percpu_arena =
+#ifdef JEMALLOC_PERCPU_ARENA
+    true
+#else
+    false
+#endif
+    ;
+/*
+ * Undocumented, and not recommended; the application should take full
+ * responsibility for tracking provenance.
+ */
+static const bool force_ivsalloc =
+#ifdef JEMALLOC_FORCE_IVSALLOC
+    true
+#else
+    false
+#endif
+    ;
+static const bool have_background_thread =
+#ifdef JEMALLOC_BACKGROUND_THREAD
+    true
+#else
+    false
+#endif
+    ;
+
+#endif /* JEMALLOC_PREAMBLE_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/large_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/large_externs.h
new file mode 100644
index 0000000000..3f36282cd4
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/large_externs.h
@@ -0,0 +1,26 @@
+#ifndef JEMALLOC_INTERNAL_LARGE_EXTERNS_H
+#define JEMALLOC_INTERNAL_LARGE_EXTERNS_H
+
+void *large_malloc(tsdn_t *tsdn, arena_t *arena, size_t usize, bool zero);
+void *large_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero);
+bool large_ralloc_no_move(tsdn_t *tsdn, extent_t *extent, size_t usize_min,
+    size_t usize_max, bool zero);
+void *large_ralloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t usize,
+    size_t alignment, bool zero, tcache_t *tcache);
+
+typedef void (large_dalloc_junk_t)(void *, size_t);
+extern large_dalloc_junk_t *JET_MUTABLE large_dalloc_junk;
+
+typedef void (large_dalloc_maybe_junk_t)(void *, size_t);
+extern large_dalloc_maybe_junk_t *JET_MUTABLE large_dalloc_maybe_junk;
+
+void large_dalloc_prep_junked_locked(tsdn_t *tsdn, extent_t *extent);
+void large_dalloc_finish(tsdn_t *tsdn, extent_t *extent);
+void large_dalloc(tsdn_t *tsdn, extent_t *extent);
+size_t large_salloc(tsdn_t *tsdn, const extent_t *extent);
+prof_tctx_t *large_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent);
+void large_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, prof_tctx_t *tctx);
+void large_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent);
+
+#endif /* JEMALLOC_INTERNAL_LARGE_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/malloc_io.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/malloc_io.h
new file mode 100644
index 0000000000..47ae58ec35
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/malloc_io.h
@@ -0,0 +1,62 @@
+#ifndef JEMALLOC_INTERNAL_MALLOC_IO_H
+#define JEMALLOC_INTERNAL_MALLOC_IO_H
+
+#ifdef _WIN32
+#  ifdef _WIN64
+#    define FMT64_PREFIX "ll"
+#    define FMTPTR_PREFIX "ll"
+#  else
+#    define FMT64_PREFIX "ll"
+#    define FMTPTR_PREFIX ""
+#  endif
+#  define FMTd32 "d"
+#  define FMTu32 "u"
+#  define FMTx32 "x"
+#  define FMTd64 FMT64_PREFIX "d"
+#  define FMTu64 FMT64_PREFIX "u"
+#  define FMTx64 FMT64_PREFIX "x"
+#  define FMTdPTR FMTPTR_PREFIX "d"
+#  define FMTuPTR FMTPTR_PREFIX "u"
+#  define FMTxPTR FMTPTR_PREFIX "x"
+#else
+#  include <inttypes.h>
+#  define FMTd32 PRId32
+#  define FMTu32 PRIu32
+#  define FMTx32 PRIx32
+#  define FMTd64 PRId64
+#  define FMTu64 PRIu64
+#  define FMTx64 PRIx64
+#  define FMTdPTR PRIdPTR
+#  define FMTuPTR PRIuPTR
+#  define FMTxPTR PRIxPTR
+#endif
+
+/* Size of stack-allocated buffer passed to buferror(). */
+#define BUFERROR_BUF		64
+
+/*
+ * Size of stack-allocated buffer used by malloc_{,v,vc}printf().  This must be
+ * large enough for all possible uses within jemalloc.
+ */
+#define MALLOC_PRINTF_BUFSIZE	4096
+
+int buferror(int err, char *buf, size_t buflen);
+uintmax_t malloc_strtoumax(const char *restrict nptr, char **restrict endptr,
+    int base);
+void malloc_write(const char *s);
+
+/*
+ * malloc_vsnprintf() supports a subset of snprintf(3) that avoids floating
+ * point math.
+ */
+size_t malloc_vsnprintf(char *str, size_t size, const char *format,
+    va_list ap);
+size_t malloc_snprintf(char *str, size_t size, const char *format, ...)
+    JEMALLOC_FORMAT_PRINTF(3, 4);
+void malloc_vcprintf(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *format, va_list ap);
+void malloc_cprintf(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *format, ...) JEMALLOC_FORMAT_PRINTF(3, 4);
+void malloc_printf(const char *format, ...) JEMALLOC_FORMAT_PRINTF(1, 2);
+
+#endif /* JEMALLOC_INTERNAL_MALLOC_IO_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex.h
index de44e1435a..6520c2512d 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex.h
@@ -1,45 +1,123 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_MUTEX_H
+#define JEMALLOC_INTERNAL_MUTEX_H
 
-typedef struct malloc_mutex_s malloc_mutex_t;
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/mutex_prof.h"
+#include "jemalloc/internal/tsd.h"
+#include "jemalloc/internal/witness.h"
+
+typedef enum {
+	/* Can only acquire one mutex of a given witness rank at a time. */
+	malloc_mutex_rank_exclusive,
+	/*
+	 * Can acquire multiple mutexes of the same witness rank, but in
+	 * address-ascending order only.
+	 */
+	malloc_mutex_address_ordered
+} malloc_mutex_lock_order_t;
 
+typedef struct malloc_mutex_s malloc_mutex_t;
+struct malloc_mutex_s {
+	union {
+		struct {
+			/*
+			 * prof_data is defined first to reduce cacheline
+			 * bouncing: the data is not touched by the mutex holder
+			 * during unlocking, while might be modified by
+			 * contenders.  Having it before the mutex itself could
+			 * avoid prefetching a modified cacheline (for the
+			 * unlocking thread).
+			 */
+			mutex_prof_data_t	prof_data;
 #ifdef _WIN32
-#  define MALLOC_MUTEX_INITIALIZER
+#  if _WIN32_WINNT >= 0x0600
+			SRWLOCK         	lock;
+#  else
+			CRITICAL_SECTION	lock;
+#  endif
+#elif (defined(JEMALLOC_OS_UNFAIR_LOCK))
+			os_unfair_lock		lock;
 #elif (defined(JEMALLOC_OSSPIN))
-#  define MALLOC_MUTEX_INITIALIZER {0}
+			OSSpinLock		lock;
 #elif (defined(JEMALLOC_MUTEX_INIT_CB))
-#  define MALLOC_MUTEX_INITIALIZER {PTHREAD_MUTEX_INITIALIZER, NULL}
+			pthread_mutex_t		lock;
+			malloc_mutex_t		*postponed_next;
 #else
-#  if (defined(PTHREAD_MUTEX_ADAPTIVE_NP) &&				\
-       defined(PTHREAD_ADAPTIVE_MUTEX_INITIALIZER_NP))
-#    define MALLOC_MUTEX_TYPE PTHREAD_MUTEX_ADAPTIVE_NP
-#    define MALLOC_MUTEX_INITIALIZER {PTHREAD_ADAPTIVE_MUTEX_INITIALIZER_NP}
+			pthread_mutex_t		lock;
+#endif
+		};
+		/*
+		 * We only touch witness when configured w/ debug.  However we
+		 * keep the field in a union when !debug so that we don't have
+		 * to pollute the code base with #ifdefs, while avoid paying the
+		 * memory cost.
+		 */
+#if !defined(JEMALLOC_DEBUG)
+		witness_t			witness;
+		malloc_mutex_lock_order_t	lock_order;
+#endif
+	};
+
+#if defined(JEMALLOC_DEBUG)
+	witness_t			witness;
+	malloc_mutex_lock_order_t	lock_order;
+#endif
+};
+
+/*
+ * Based on benchmark results, a fixed spin with this amount of retries works
+ * well for our critical sections.
+ */
+#define MALLOC_MUTEX_MAX_SPIN 250
+
+#ifdef _WIN32
+#  if _WIN32_WINNT >= 0x0600
+#    define MALLOC_MUTEX_LOCK(m)    AcquireSRWLockExclusive(&(m)->lock)
+#    define MALLOC_MUTEX_UNLOCK(m)  ReleaseSRWLockExclusive(&(m)->lock)
+#    define MALLOC_MUTEX_TRYLOCK(m) (!TryAcquireSRWLockExclusive(&(m)->lock))
 #  else
-#    define MALLOC_MUTEX_TYPE PTHREAD_MUTEX_DEFAULT
-#    define MALLOC_MUTEX_INITIALIZER {PTHREAD_MUTEX_INITIALIZER}
+#    define MALLOC_MUTEX_LOCK(m)    EnterCriticalSection(&(m)->lock)
+#    define MALLOC_MUTEX_UNLOCK(m)  LeaveCriticalSection(&(m)->lock)
+#    define MALLOC_MUTEX_TRYLOCK(m) (!TryEnterCriticalSection(&(m)->lock))
 #  endif
+#elif (defined(JEMALLOC_OS_UNFAIR_LOCK))
+#    define MALLOC_MUTEX_LOCK(m)    os_unfair_lock_lock(&(m)->lock)
+#    define MALLOC_MUTEX_UNLOCK(m)  os_unfair_lock_unlock(&(m)->lock)
+#    define MALLOC_MUTEX_TRYLOCK(m) (!os_unfair_lock_trylock(&(m)->lock))
+#elif (defined(JEMALLOC_OSSPIN))
+#    define MALLOC_MUTEX_LOCK(m)    OSSpinLockLock(&(m)->lock)
+#    define MALLOC_MUTEX_UNLOCK(m)  OSSpinLockUnlock(&(m)->lock)
+#    define MALLOC_MUTEX_TRYLOCK(m) (!OSSpinLockTry(&(m)->lock))
+#else
+#    define MALLOC_MUTEX_LOCK(m)    pthread_mutex_lock(&(m)->lock)
+#    define MALLOC_MUTEX_UNLOCK(m)  pthread_mutex_unlock(&(m)->lock)
+#    define MALLOC_MUTEX_TRYLOCK(m) (pthread_mutex_trylock(&(m)->lock) != 0)
 #endif
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+#define LOCK_PROF_DATA_INITIALIZER					\
+    {NSTIME_ZERO_INITIALIZER, NSTIME_ZERO_INITIALIZER, 0, 0, 0,		\
+	    ATOMIC_INIT(0), 0, NULL, 0}
 
-struct malloc_mutex_s {
 #ifdef _WIN32
-	CRITICAL_SECTION	lock;
+#  define MALLOC_MUTEX_INITIALIZER
+#elif (defined(JEMALLOC_OS_UNFAIR_LOCK))
+#  define MALLOC_MUTEX_INITIALIZER					\
+     {{{LOCK_PROF_DATA_INITIALIZER, OS_UNFAIR_LOCK_INIT}},		\
+      WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)}
 #elif (defined(JEMALLOC_OSSPIN))
-	OSSpinLock		lock;
+#  define MALLOC_MUTEX_INITIALIZER					\
+     {{{LOCK_PROF_DATA_INITIALIZER, 0}},				\
+      WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)}
 #elif (defined(JEMALLOC_MUTEX_INIT_CB))
-	pthread_mutex_t		lock;
-	malloc_mutex_t		*postponed_next;
+#  define MALLOC_MUTEX_INITIALIZER					\
+     {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER, NULL}},	\
+      WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)}
 #else
-	pthread_mutex_t		lock;
+#    define MALLOC_MUTEX_TYPE PTHREAD_MUTEX_DEFAULT
+#    define MALLOC_MUTEX_INITIALIZER					\
+       {{{LOCK_PROF_DATA_INITIALIZER, PTHREAD_MUTEX_INITIALIZER}},	\
+        WITNESS_INITIALIZER("mutex", WITNESS_RANK_OMIT)}
 #endif
-};
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
 
 #ifdef JEMALLOC_LAZY_LOCK
 extern bool isthreaded;
@@ -48,52 +126,123 @@ extern bool isthreaded;
 #  define isthreaded true
 #endif
 
-bool	malloc_mutex_init(malloc_mutex_t *mutex);
-void	malloc_mutex_prefork(malloc_mutex_t *mutex);
-void	malloc_mutex_postfork_parent(malloc_mutex_t *mutex);
-void	malloc_mutex_postfork_child(malloc_mutex_t *mutex);
-bool	mutex_boot(void);
+bool malloc_mutex_init(malloc_mutex_t *mutex, const char *name,
+    witness_rank_t rank, malloc_mutex_lock_order_t lock_order);
+void malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex);
+void malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex);
+void malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex);
+bool malloc_mutex_boot(void);
+void malloc_mutex_prof_data_reset(tsdn_t *tsdn, malloc_mutex_t *mutex);
 
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+void malloc_mutex_lock_slow(malloc_mutex_t *mutex);
 
-#ifndef JEMALLOC_ENABLE_INLINE
-void	malloc_mutex_lock(malloc_mutex_t *mutex);
-void	malloc_mutex_unlock(malloc_mutex_t *mutex);
-#endif
+static inline void
+malloc_mutex_lock_final(malloc_mutex_t *mutex) {
+	MALLOC_MUTEX_LOCK(mutex);
+}
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_MUTEX_C_))
-JEMALLOC_INLINE void
-malloc_mutex_lock(malloc_mutex_t *mutex)
-{
+static inline bool
+malloc_mutex_trylock_final(malloc_mutex_t *mutex) {
+	return MALLOC_MUTEX_TRYLOCK(mutex);
+}
 
+static inline void
+mutex_owner_stats_update(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	if (config_stats) {
+		mutex_prof_data_t *data = &mutex->prof_data;
+		data->n_lock_ops++;
+		if (data->prev_owner != tsdn) {
+			data->prev_owner = tsdn;
+			data->n_owner_switches++;
+		}
+	}
+}
+
+/* Trylock: return false if the lock is successfully acquired. */
+static inline bool
+malloc_mutex_trylock(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
 	if (isthreaded) {
-#ifdef _WIN32
-		EnterCriticalSection(&mutex->lock);
-#elif (defined(JEMALLOC_OSSPIN))
-		OSSpinLockLock(&mutex->lock);
-#else
-		pthread_mutex_lock(&mutex->lock);
-#endif
+		if (malloc_mutex_trylock_final(mutex)) {
+			return true;
+		}
+		mutex_owner_stats_update(tsdn, mutex);
 	}
+	witness_lock(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
+
+	return false;
 }
 
-JEMALLOC_INLINE void
-malloc_mutex_unlock(malloc_mutex_t *mutex)
-{
+/* Aggregate lock prof data. */
+static inline void
+malloc_mutex_prof_merge(mutex_prof_data_t *sum, mutex_prof_data_t *data) {
+	nstime_add(&sum->tot_wait_time, &data->tot_wait_time);
+	if (nstime_compare(&sum->max_wait_time, &data->max_wait_time) < 0) {
+		nstime_copy(&sum->max_wait_time, &data->max_wait_time);
+	}
+
+	sum->n_wait_times += data->n_wait_times;
+	sum->n_spin_acquired += data->n_spin_acquired;
+
+	if (sum->max_n_thds < data->max_n_thds) {
+		sum->max_n_thds = data->max_n_thds;
+	}
+	uint32_t cur_n_waiting_thds = atomic_load_u32(&sum->n_waiting_thds,
+	    ATOMIC_RELAXED);
+	uint32_t new_n_waiting_thds = cur_n_waiting_thds + atomic_load_u32(
+	    &data->n_waiting_thds, ATOMIC_RELAXED);
+	atomic_store_u32(&sum->n_waiting_thds, new_n_waiting_thds,
+	    ATOMIC_RELAXED);
+	sum->n_owner_switches += data->n_owner_switches;
+	sum->n_lock_ops += data->n_lock_ops;
+}
 
+static inline void
+malloc_mutex_lock(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
 	if (isthreaded) {
-#ifdef _WIN32
-		LeaveCriticalSection(&mutex->lock);
-#elif (defined(JEMALLOC_OSSPIN))
-		OSSpinLockUnlock(&mutex->lock);
-#else
-		pthread_mutex_unlock(&mutex->lock);
-#endif
+		if (malloc_mutex_trylock_final(mutex)) {
+			malloc_mutex_lock_slow(mutex);
+		}
+		mutex_owner_stats_update(tsdn, mutex);
 	}
+	witness_lock(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
+}
+
+static inline void
+malloc_mutex_unlock(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	witness_unlock(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
+	if (isthreaded) {
+		MALLOC_MUTEX_UNLOCK(mutex);
+	}
+}
+
+static inline void
+malloc_mutex_assert_owner(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	witness_assert_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
+}
+
+static inline void
+malloc_mutex_assert_not_owner(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	witness_assert_not_owner(tsdn_witness_tsdp_get(tsdn), &mutex->witness);
+}
+
+/* Copy the prof data from mutex for processing. */
+static inline void
+malloc_mutex_prof_read(tsdn_t *tsdn, mutex_prof_data_t *data,
+    malloc_mutex_t *mutex) {
+	mutex_prof_data_t *source = &mutex->prof_data;
+	/* Can only read holding the mutex. */
+	malloc_mutex_assert_owner(tsdn, mutex);
+
+	/*
+	 * Not *really* allowed (we shouldn't be doing non-atomic loads of
+	 * atomic data), but the mutex protection makes this safe, and writing
+	 * a member-for-member copy is tedious for this situation.
+	 */
+	*data = *source;
+	/* n_wait_thds is not reported (modified w/o locking). */
+	atomic_store_u32(&data->n_waiting_thds, 0, ATOMIC_RELAXED);
 }
-#endif
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_MUTEX_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_pool.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_pool.h
new file mode 100644
index 0000000000..726cece90b
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_pool.h
@@ -0,0 +1,94 @@
+#ifndef JEMALLOC_INTERNAL_MUTEX_POOL_H
+#define JEMALLOC_INTERNAL_MUTEX_POOL_H
+
+#include "jemalloc/internal/hash.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/witness.h"
+
+/* We do mod reductions by this value, so it should be kept a power of 2. */
+#define MUTEX_POOL_SIZE 256
+
+typedef struct mutex_pool_s mutex_pool_t;
+struct mutex_pool_s {
+	malloc_mutex_t mutexes[MUTEX_POOL_SIZE];
+};
+
+bool mutex_pool_init(mutex_pool_t *pool, const char *name, witness_rank_t rank);
+
+/* Internal helper - not meant to be called outside this module. */
+static inline malloc_mutex_t *
+mutex_pool_mutex(mutex_pool_t *pool, uintptr_t key) {
+	size_t hash_result[2];
+	hash(&key, sizeof(key), 0xd50dcc1b, hash_result);
+	return &pool->mutexes[hash_result[0] % MUTEX_POOL_SIZE];
+}
+
+static inline void
+mutex_pool_assert_not_held(tsdn_t *tsdn, mutex_pool_t *pool) {
+	for (int i = 0; i < MUTEX_POOL_SIZE; i++) {
+		malloc_mutex_assert_not_owner(tsdn, &pool->mutexes[i]);
+	}
+}
+
+/*
+ * Note that a mutex pool doesn't work exactly the way an embdedded mutex would.
+ * You're not allowed to acquire mutexes in the pool one at a time.  You have to
+ * acquire all the mutexes you'll need in a single function call, and then
+ * release them all in a single function call.
+ */
+
+static inline void
+mutex_pool_lock(tsdn_t *tsdn, mutex_pool_t *pool, uintptr_t key) {
+	mutex_pool_assert_not_held(tsdn, pool);
+
+	malloc_mutex_t *mutex = mutex_pool_mutex(pool, key);
+	malloc_mutex_lock(tsdn, mutex);
+}
+
+static inline void
+mutex_pool_unlock(tsdn_t *tsdn, mutex_pool_t *pool, uintptr_t key) {
+	malloc_mutex_t *mutex = mutex_pool_mutex(pool, key);
+	malloc_mutex_unlock(tsdn, mutex);
+
+	mutex_pool_assert_not_held(tsdn, pool);
+}
+
+static inline void
+mutex_pool_lock2(tsdn_t *tsdn, mutex_pool_t *pool, uintptr_t key1,
+    uintptr_t key2) {
+	mutex_pool_assert_not_held(tsdn, pool);
+
+	malloc_mutex_t *mutex1 = mutex_pool_mutex(pool, key1);
+	malloc_mutex_t *mutex2 = mutex_pool_mutex(pool, key2);
+	if ((uintptr_t)mutex1 < (uintptr_t)mutex2) {
+		malloc_mutex_lock(tsdn, mutex1);
+		malloc_mutex_lock(tsdn, mutex2);
+	} else if ((uintptr_t)mutex1 == (uintptr_t)mutex2) {
+		malloc_mutex_lock(tsdn, mutex1);
+	} else {
+		malloc_mutex_lock(tsdn, mutex2);
+		malloc_mutex_lock(tsdn, mutex1);
+	}
+}
+
+static inline void
+mutex_pool_unlock2(tsdn_t *tsdn, mutex_pool_t *pool, uintptr_t key1,
+    uintptr_t key2) {
+	malloc_mutex_t *mutex1 = mutex_pool_mutex(pool, key1);
+	malloc_mutex_t *mutex2 = mutex_pool_mutex(pool, key2);
+	if (mutex1 == mutex2) {
+		malloc_mutex_unlock(tsdn, mutex1);
+	} else {
+		malloc_mutex_unlock(tsdn, mutex1);
+		malloc_mutex_unlock(tsdn, mutex2);
+	}
+
+	mutex_pool_assert_not_held(tsdn, pool);
+}
+
+static inline void
+mutex_pool_assert_owner(tsdn_t *tsdn, mutex_pool_t *pool, uintptr_t key) {
+	malloc_mutex_assert_owner(tsdn, mutex_pool_mutex(pool, key));
+}
+
+#endif /* JEMALLOC_INTERNAL_MUTEX_POOL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_prof.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_prof.h
new file mode 100644
index 0000000000..3358bcf535
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/mutex_prof.h
@@ -0,0 +1,86 @@
+#ifndef JEMALLOC_INTERNAL_MUTEX_PROF_H
+#define JEMALLOC_INTERNAL_MUTEX_PROF_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/nstime.h"
+#include "jemalloc/internal/tsd_types.h"
+
+#define MUTEX_PROF_GLOBAL_MUTEXES					\
+    OP(background_thread)						\
+    OP(ctl)								\
+    OP(prof)
+
+typedef enum {
+#define OP(mtx) global_prof_mutex_##mtx,
+	MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+	mutex_prof_num_global_mutexes
+} mutex_prof_global_ind_t;
+
+#define MUTEX_PROF_ARENA_MUTEXES					\
+    OP(large)								\
+    OP(extent_avail)							\
+    OP(extents_dirty)							\
+    OP(extents_muzzy)							\
+    OP(extents_retained)						\
+    OP(decay_dirty)							\
+    OP(decay_muzzy)							\
+    OP(base)								\
+    OP(tcache_list)
+
+typedef enum {
+#define OP(mtx) arena_prof_mutex_##mtx,
+	MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+	mutex_prof_num_arena_mutexes
+} mutex_prof_arena_ind_t;
+
+#define MUTEX_PROF_COUNTERS						\
+    OP(num_ops, uint64_t)						\
+    OP(num_wait, uint64_t)						\
+    OP(num_spin_acq, uint64_t)						\
+    OP(num_owner_switch, uint64_t)					\
+    OP(total_wait_time, uint64_t)					\
+    OP(max_wait_time, uint64_t)						\
+    OP(max_num_thds, uint32_t)
+
+typedef enum {
+#define OP(counter, type) mutex_counter_##counter,
+	MUTEX_PROF_COUNTERS
+#undef OP
+	mutex_prof_num_counters
+} mutex_prof_counter_ind_t;
+
+typedef struct {
+	/*
+	 * Counters touched on the slow path, i.e. when there is lock
+	 * contention.  We update them once we have the lock.
+	 */
+	/* Total time (in nano seconds) spent waiting on this mutex. */
+	nstime_t		tot_wait_time;
+	/* Max time (in nano seconds) spent on a single lock operation. */
+	nstime_t		max_wait_time;
+	/* # of times have to wait for this mutex (after spinning). */
+	uint64_t		n_wait_times;
+	/* # of times acquired the mutex through local spinning. */
+	uint64_t		n_spin_acquired;
+	/* Max # of threads waiting for the mutex at the same time. */
+	uint32_t		max_n_thds;
+	/* Current # of threads waiting on the lock.  Atomic synced. */
+	atomic_u32_t		n_waiting_thds;
+
+	/*
+	 * Data touched on the fast path.  These are modified right after we
+	 * grab the lock, so it's placed closest to the end (i.e. right before
+	 * the lock) so that we have a higher chance of them being on the same
+	 * cacheline.
+	 */
+	/* # of times the mutex holder is different than the previous one. */
+	uint64_t		n_owner_switches;
+	/* Previous mutex holder, to facilitate n_owner_switches. */
+	tsdn_t			*prev_owner;
+	/* # of lock() operations in total. */
+	uint64_t		n_lock_ops;
+} mutex_prof_data_t;
+
+#endif /* JEMALLOC_INTERNAL_MUTEX_PROF_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/nstime.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/nstime.h
new file mode 100644
index 0000000000..17c177c7f4
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/nstime.h
@@ -0,0 +1,34 @@
+#ifndef JEMALLOC_INTERNAL_NSTIME_H
+#define JEMALLOC_INTERNAL_NSTIME_H
+
+/* Maximum supported number of seconds (~584 years). */
+#define NSTIME_SEC_MAX KQU(18446744072)
+#define NSTIME_ZERO_INITIALIZER {0}
+
+typedef struct {
+	uint64_t ns;
+} nstime_t;
+
+void nstime_init(nstime_t *time, uint64_t ns);
+void nstime_init2(nstime_t *time, uint64_t sec, uint64_t nsec);
+uint64_t nstime_ns(const nstime_t *time);
+uint64_t nstime_sec(const nstime_t *time);
+uint64_t nstime_msec(const nstime_t *time);
+uint64_t nstime_nsec(const nstime_t *time);
+void nstime_copy(nstime_t *time, const nstime_t *source);
+int nstime_compare(const nstime_t *a, const nstime_t *b);
+void nstime_add(nstime_t *time, const nstime_t *addend);
+void nstime_iadd(nstime_t *time, uint64_t addend);
+void nstime_subtract(nstime_t *time, const nstime_t *subtrahend);
+void nstime_isubtract(nstime_t *time, uint64_t subtrahend);
+void nstime_imultiply(nstime_t *time, uint64_t multiplier);
+void nstime_idivide(nstime_t *time, uint64_t divisor);
+uint64_t nstime_divide(const nstime_t *time, const nstime_t *divisor);
+
+typedef bool (nstime_monotonic_t)(void);
+extern nstime_monotonic_t *JET_MUTABLE nstime_monotonic;
+
+typedef bool (nstime_update_t)(nstime_t *);
+extern nstime_update_t *JET_MUTABLE nstime_update;
+
+#endif /* JEMALLOC_INTERNAL_NSTIME_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/pages.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/pages.h
new file mode 100644
index 0000000000..28383b7f97
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/pages.h
@@ -0,0 +1,71 @@
+#ifndef JEMALLOC_INTERNAL_PAGES_EXTERNS_H
+#define JEMALLOC_INTERNAL_PAGES_EXTERNS_H
+
+/* Page size.  LG_PAGE is determined by the configure script. */
+#ifdef PAGE_MASK
+#  undef PAGE_MASK
+#endif
+#define PAGE		((size_t)(1U << LG_PAGE))
+#define PAGE_MASK	((size_t)(PAGE - 1))
+/* Return the page base address for the page containing address a. */
+#define PAGE_ADDR2BASE(a)						\
+	((void *)((uintptr_t)(a) & ~PAGE_MASK))
+/* Return the smallest pagesize multiple that is >= s. */
+#define PAGE_CEILING(s)							\
+	(((s) + PAGE_MASK) & ~PAGE_MASK)
+
+/* Huge page size.  LG_HUGEPAGE is determined by the configure script. */
+#define HUGEPAGE	((size_t)(1U << LG_HUGEPAGE))
+#define HUGEPAGE_MASK	((size_t)(HUGEPAGE - 1))
+/* Return the huge page base address for the huge page containing address a. */
+#define HUGEPAGE_ADDR2BASE(a)						\
+	((void *)((uintptr_t)(a) & ~HUGEPAGE_MASK))
+/* Return the smallest pagesize multiple that is >= s. */
+#define HUGEPAGE_CEILING(s)						\
+	(((s) + HUGEPAGE_MASK) & ~HUGEPAGE_MASK)
+
+/* PAGES_CAN_PURGE_LAZY is defined if lazy purging is supported. */
+#if defined(_WIN32) || defined(JEMALLOC_PURGE_MADVISE_FREE)
+#  define PAGES_CAN_PURGE_LAZY
+#endif
+/*
+ * PAGES_CAN_PURGE_FORCED is defined if forced purging is supported.
+ *
+ * The only supported way to hard-purge on Windows is to decommit and then
+ * re-commit, but doing so is racy, and if re-commit fails it's a pain to
+ * propagate the "poisoned" memory state.  Since we typically decommit as the
+ * next step after purging on Windows anyway, there's no point in adding such
+ * complexity.
+ */
+#if !defined(_WIN32) && ((defined(JEMALLOC_PURGE_MADVISE_DONTNEED) && \
+    defined(JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS)) || \
+    defined(JEMALLOC_MAPS_COALESCE))
+#  define PAGES_CAN_PURGE_FORCED
+#endif
+
+static const bool pages_can_purge_lazy =
+#ifdef PAGES_CAN_PURGE_LAZY
+    true
+#else
+    false
+#endif
+    ;
+static const bool pages_can_purge_forced =
+#ifdef PAGES_CAN_PURGE_FORCED
+    true
+#else
+    false
+#endif
+    ;
+
+void *pages_map(void *addr, size_t size, size_t alignment, bool *commit);
+void pages_unmap(void *addr, size_t size);
+bool pages_commit(void *addr, size_t size);
+bool pages_decommit(void *addr, size_t size);
+bool pages_purge_lazy(void *addr, size_t size);
+bool pages_purge_forced(void *addr, size_t size);
+bool pages_huge(void *addr, size_t size);
+bool pages_nohuge(void *addr, size_t size);
+bool pages_boot(void);
+
+#endif /* JEMALLOC_INTERNAL_PAGES_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ph.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ph.h
new file mode 100644
index 0000000000..84d6778a90
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ph.h
@@ -0,0 +1,391 @@
+/*
+ * A Pairing Heap implementation.
+ *
+ * "The Pairing Heap: A New Form of Self-Adjusting Heap"
+ * https://www.cs.cmu.edu/~sleator/papers/pairing-heaps.pdf
+ *
+ * With auxiliary twopass list, described in a follow on paper.
+ *
+ * "Pairing Heaps: Experiments and Analysis"
+ * http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.106.2988&rep=rep1&type=pdf
+ *
+ *******************************************************************************
+ */
+
+#ifndef PH_H_
+#define PH_H_
+
+/* Node structure. */
+#define phn(a_type)							\
+struct {								\
+	a_type	*phn_prev;						\
+	a_type	*phn_next;						\
+	a_type	*phn_lchild;						\
+}
+
+/* Root structure. */
+#define ph(a_type)							\
+struct {								\
+	a_type	*ph_root;						\
+}
+
+/* Internal utility macros. */
+#define phn_lchild_get(a_type, a_field, a_phn)				\
+	(a_phn->a_field.phn_lchild)
+#define phn_lchild_set(a_type, a_field, a_phn, a_lchild) do {		\
+	a_phn->a_field.phn_lchild = a_lchild;				\
+} while (0)
+
+#define phn_next_get(a_type, a_field, a_phn)				\
+	(a_phn->a_field.phn_next)
+#define phn_prev_set(a_type, a_field, a_phn, a_prev) do {		\
+	a_phn->a_field.phn_prev = a_prev;				\
+} while (0)
+
+#define phn_prev_get(a_type, a_field, a_phn)				\
+	(a_phn->a_field.phn_prev)
+#define phn_next_set(a_type, a_field, a_phn, a_next) do {		\
+	a_phn->a_field.phn_next = a_next;				\
+} while (0)
+
+#define phn_merge_ordered(a_type, a_field, a_phn0, a_phn1, a_cmp) do {	\
+	a_type *phn0child;						\
+									\
+	assert(a_phn0 != NULL);						\
+	assert(a_phn1 != NULL);						\
+	assert(a_cmp(a_phn0, a_phn1) <= 0);				\
+									\
+	phn_prev_set(a_type, a_field, a_phn1, a_phn0);			\
+	phn0child = phn_lchild_get(a_type, a_field, a_phn0);		\
+	phn_next_set(a_type, a_field, a_phn1, phn0child);		\
+	if (phn0child != NULL) {					\
+		phn_prev_set(a_type, a_field, phn0child, a_phn1);	\
+	}								\
+	phn_lchild_set(a_type, a_field, a_phn0, a_phn1);		\
+} while (0)
+
+#define phn_merge(a_type, a_field, a_phn0, a_phn1, a_cmp, r_phn) do {	\
+	if (a_phn0 == NULL) {						\
+		r_phn = a_phn1;						\
+	} else if (a_phn1 == NULL) {					\
+		r_phn = a_phn0;						\
+	} else if (a_cmp(a_phn0, a_phn1) < 0) {				\
+		phn_merge_ordered(a_type, a_field, a_phn0, a_phn1,	\
+		    a_cmp);						\
+		r_phn = a_phn0;						\
+	} else {							\
+		phn_merge_ordered(a_type, a_field, a_phn1, a_phn0,	\
+		    a_cmp);						\
+		r_phn = a_phn1;						\
+	}								\
+} while (0)
+
+#define ph_merge_siblings(a_type, a_field, a_phn, a_cmp, r_phn) do {	\
+	a_type *head = NULL;						\
+	a_type *tail = NULL;						\
+	a_type *phn0 = a_phn;						\
+	a_type *phn1 = phn_next_get(a_type, a_field, phn0);		\
+									\
+	/*								\
+	 * Multipass merge, wherein the first two elements of a FIFO	\
+	 * are repeatedly merged, and each result is appended to the	\
+	 * singly linked FIFO, until the FIFO contains only a single	\
+	 * element.  We start with a sibling list but no reference to	\
+	 * its tail, so we do a single pass over the sibling list to	\
+	 * populate the FIFO.						\
+	 */								\
+	if (phn1 != NULL) {						\
+		a_type *phnrest = phn_next_get(a_type, a_field, phn1);	\
+		if (phnrest != NULL) {					\
+			phn_prev_set(a_type, a_field, phnrest, NULL);	\
+		}							\
+		phn_prev_set(a_type, a_field, phn0, NULL);		\
+		phn_next_set(a_type, a_field, phn0, NULL);		\
+		phn_prev_set(a_type, a_field, phn1, NULL);		\
+		phn_next_set(a_type, a_field, phn1, NULL);		\
+		phn_merge(a_type, a_field, phn0, phn1, a_cmp, phn0);	\
+		head = tail = phn0;					\
+		phn0 = phnrest;						\
+		while (phn0 != NULL) {					\
+			phn1 = phn_next_get(a_type, a_field, phn0);	\
+			if (phn1 != NULL) {				\
+				phnrest = phn_next_get(a_type, a_field,	\
+				    phn1);				\
+				if (phnrest != NULL) {			\
+					phn_prev_set(a_type, a_field,	\
+					    phnrest, NULL);		\
+				}					\
+				phn_prev_set(a_type, a_field, phn0,	\
+				    NULL);				\
+				phn_next_set(a_type, a_field, phn0,	\
+				    NULL);				\
+				phn_prev_set(a_type, a_field, phn1,	\
+				    NULL);				\
+				phn_next_set(a_type, a_field, phn1,	\
+				    NULL);				\
+				phn_merge(a_type, a_field, phn0, phn1,	\
+				    a_cmp, phn0);			\
+				phn_next_set(a_type, a_field, tail,	\
+				    phn0);				\
+				tail = phn0;				\
+				phn0 = phnrest;				\
+			} else {					\
+				phn_next_set(a_type, a_field, tail,	\
+				    phn0);				\
+				tail = phn0;				\
+				phn0 = NULL;				\
+			}						\
+		}							\
+		phn0 = head;						\
+		phn1 = phn_next_get(a_type, a_field, phn0);		\
+		if (phn1 != NULL) {					\
+			while (true) {					\
+				head = phn_next_get(a_type, a_field,	\
+				    phn1);				\
+				assert(phn_prev_get(a_type, a_field,	\
+				    phn0) == NULL);			\
+				phn_next_set(a_type, a_field, phn0,	\
+				    NULL);				\
+				assert(phn_prev_get(a_type, a_field,	\
+				    phn1) == NULL);			\
+				phn_next_set(a_type, a_field, phn1,	\
+				    NULL);				\
+				phn_merge(a_type, a_field, phn0, phn1,	\
+				    a_cmp, phn0);			\
+				if (head == NULL) {			\
+					break;				\
+				}					\
+				phn_next_set(a_type, a_field, tail,	\
+				    phn0);				\
+				tail = phn0;				\
+				phn0 = head;				\
+				phn1 = phn_next_get(a_type, a_field,	\
+				    phn0);				\
+			}						\
+		}							\
+	}								\
+	r_phn = phn0;							\
+} while (0)
+
+#define ph_merge_aux(a_type, a_field, a_ph, a_cmp) do {			\
+	a_type *phn = phn_next_get(a_type, a_field, a_ph->ph_root);	\
+	if (phn != NULL) {						\
+		phn_prev_set(a_type, a_field, a_ph->ph_root, NULL);	\
+		phn_next_set(a_type, a_field, a_ph->ph_root, NULL);	\
+		phn_prev_set(a_type, a_field, phn, NULL);		\
+		ph_merge_siblings(a_type, a_field, phn, a_cmp, phn);	\
+		assert(phn_next_get(a_type, a_field, phn) == NULL);	\
+		phn_merge(a_type, a_field, a_ph->ph_root, phn, a_cmp,	\
+		    a_ph->ph_root);					\
+	}								\
+} while (0)
+
+#define ph_merge_children(a_type, a_field, a_phn, a_cmp, r_phn) do {	\
+	a_type *lchild = phn_lchild_get(a_type, a_field, a_phn);	\
+	if (lchild == NULL) {						\
+		r_phn = NULL;						\
+	} else {							\
+		ph_merge_siblings(a_type, a_field, lchild, a_cmp,	\
+		    r_phn);						\
+	}								\
+} while (0)
+
+/*
+ * The ph_proto() macro generates function prototypes that correspond to the
+ * functions generated by an equivalently parameterized call to ph_gen().
+ */
+#define ph_proto(a_attr, a_prefix, a_ph_type, a_type)			\
+a_attr void	a_prefix##new(a_ph_type *ph);				\
+a_attr bool	a_prefix##empty(a_ph_type *ph);				\
+a_attr a_type	*a_prefix##first(a_ph_type *ph);			\
+a_attr a_type	*a_prefix##any(a_ph_type *ph);				\
+a_attr void	a_prefix##insert(a_ph_type *ph, a_type *phn);		\
+a_attr a_type	*a_prefix##remove_first(a_ph_type *ph);			\
+a_attr a_type	*a_prefix##remove_any(a_ph_type *ph);			\
+a_attr void	a_prefix##remove(a_ph_type *ph, a_type *phn);
+
+/*
+ * The ph_gen() macro generates a type-specific pairing heap implementation,
+ * based on the above cpp macros.
+ */
+#define ph_gen(a_attr, a_prefix, a_ph_type, a_type, a_field, a_cmp)	\
+a_attr void								\
+a_prefix##new(a_ph_type *ph) {						\
+	memset(ph, 0, sizeof(ph(a_type)));				\
+}									\
+a_attr bool								\
+a_prefix##empty(a_ph_type *ph) {					\
+	return (ph->ph_root == NULL);					\
+}									\
+a_attr a_type *								\
+a_prefix##first(a_ph_type *ph) {					\
+	if (ph->ph_root == NULL) {					\
+		return NULL;						\
+	}								\
+	ph_merge_aux(a_type, a_field, ph, a_cmp);			\
+	return ph->ph_root;						\
+}									\
+a_attr a_type *								\
+a_prefix##any(a_ph_type *ph) {						\
+	if (ph->ph_root == NULL) {					\
+		return NULL;						\
+	}								\
+	a_type *aux = phn_next_get(a_type, a_field, ph->ph_root);	\
+	if (aux != NULL) {						\
+		return aux;						\
+	}								\
+	return ph->ph_root;						\
+}									\
+a_attr void								\
+a_prefix##insert(a_ph_type *ph, a_type *phn) {				\
+	memset(&phn->a_field, 0, sizeof(phn(a_type)));			\
+									\
+	/*								\
+	 * Treat the root as an aux list during insertion, and lazily	\
+	 * merge during a_prefix##remove_first().  For elements that	\
+	 * are inserted, then removed via a_prefix##remove() before the	\
+	 * aux list is ever processed, this makes insert/remove		\
+	 * constant-time, whereas eager merging would make insert	\
+	 * O(log n).							\
+	 */								\
+	if (ph->ph_root == NULL) {					\
+		ph->ph_root = phn;					\
+	} else {							\
+		phn_next_set(a_type, a_field, phn, phn_next_get(a_type,	\
+		    a_field, ph->ph_root));				\
+		if (phn_next_get(a_type, a_field, ph->ph_root) !=	\
+		    NULL) {						\
+			phn_prev_set(a_type, a_field,			\
+			    phn_next_get(a_type, a_field, ph->ph_root),	\
+			    phn);					\
+		}							\
+		phn_prev_set(a_type, a_field, phn, ph->ph_root);	\
+		phn_next_set(a_type, a_field, ph->ph_root, phn);	\
+	}								\
+}									\
+a_attr a_type *								\
+a_prefix##remove_first(a_ph_type *ph) {					\
+	a_type *ret;							\
+									\
+	if (ph->ph_root == NULL) {					\
+		return NULL;						\
+	}								\
+	ph_merge_aux(a_type, a_field, ph, a_cmp);			\
+									\
+	ret = ph->ph_root;						\
+									\
+	ph_merge_children(a_type, a_field, ph->ph_root, a_cmp,		\
+	    ph->ph_root);						\
+									\
+	return ret;							\
+}									\
+a_attr a_type *								\
+a_prefix##remove_any(a_ph_type *ph) {					\
+	/*								\
+	 * Remove the most recently inserted aux list element, or the	\
+	 * root if the aux list is empty.  This has the effect of	\
+	 * behaving as a LIFO (and insertion/removal is therefore	\
+	 * constant-time) if a_prefix##[remove_]first() are never	\
+	 * called.							\
+	 */								\
+	if (ph->ph_root == NULL) {					\
+		return NULL;						\
+	}								\
+	a_type *ret = phn_next_get(a_type, a_field, ph->ph_root);	\
+	if (ret != NULL) {						\
+		a_type *aux = phn_next_get(a_type, a_field, ret);	\
+		phn_next_set(a_type, a_field, ph->ph_root, aux);	\
+		if (aux != NULL) {					\
+			phn_prev_set(a_type, a_field, aux,		\
+			    ph->ph_root);				\
+		}							\
+		return ret;						\
+	}								\
+	ret = ph->ph_root;						\
+	ph_merge_children(a_type, a_field, ph->ph_root, a_cmp,		\
+	    ph->ph_root);						\
+	return ret;							\
+}									\
+a_attr void								\
+a_prefix##remove(a_ph_type *ph, a_type *phn) {				\
+	a_type *replace, *parent;					\
+									\
+	if (ph->ph_root == phn) {					\
+		/*							\
+		 * We can delete from aux list without merging it, but	\
+		 * we need to merge if we are dealing with the root	\
+		 * node and it has children.				\
+		 */							\
+		if (phn_lchild_get(a_type, a_field, phn) == NULL) {	\
+			ph->ph_root = phn_next_get(a_type, a_field,	\
+			    phn);					\
+			if (ph->ph_root != NULL) {			\
+				phn_prev_set(a_type, a_field,		\
+				    ph->ph_root, NULL);			\
+			}						\
+			return;						\
+		}							\
+		ph_merge_aux(a_type, a_field, ph, a_cmp);		\
+		if (ph->ph_root == phn) {				\
+			ph_merge_children(a_type, a_field, ph->ph_root,	\
+			    a_cmp, ph->ph_root);			\
+			return;						\
+		}							\
+	}								\
+									\
+	/* Get parent (if phn is leftmost child) before mutating. */	\
+	if ((parent = phn_prev_get(a_type, a_field, phn)) != NULL) {	\
+		if (phn_lchild_get(a_type, a_field, parent) != phn) {	\
+			parent = NULL;					\
+		}							\
+	}								\
+	/* Find a possible replacement node, and link to parent. */	\
+	ph_merge_children(a_type, a_field, phn, a_cmp, replace);	\
+	/* Set next/prev for sibling linked list. */			\
+	if (replace != NULL) {						\
+		if (parent != NULL) {					\
+			phn_prev_set(a_type, a_field, replace, parent);	\
+			phn_lchild_set(a_type, a_field, parent,		\
+			    replace);					\
+		} else {						\
+			phn_prev_set(a_type, a_field, replace,		\
+			    phn_prev_get(a_type, a_field, phn));	\
+			if (phn_prev_get(a_type, a_field, phn) !=	\
+			    NULL) {					\
+				phn_next_set(a_type, a_field,		\
+				    phn_prev_get(a_type, a_field, phn),	\
+				    replace);				\
+			}						\
+		}							\
+		phn_next_set(a_type, a_field, replace,			\
+		    phn_next_get(a_type, a_field, phn));		\
+		if (phn_next_get(a_type, a_field, phn) != NULL) {	\
+			phn_prev_set(a_type, a_field,			\
+			    phn_next_get(a_type, a_field, phn),		\
+			    replace);					\
+		}							\
+	} else {							\
+		if (parent != NULL) {					\
+			a_type *next = phn_next_get(a_type, a_field,	\
+			    phn);					\
+			phn_lchild_set(a_type, a_field, parent, next);	\
+			if (next != NULL) {				\
+				phn_prev_set(a_type, a_field, next,	\
+				    parent);				\
+			}						\
+		} else {						\
+			assert(phn_prev_get(a_type, a_field, phn) !=	\
+			    NULL);					\
+			phn_next_set(a_type, a_field,			\
+			    phn_prev_get(a_type, a_field, phn),		\
+			    phn_next_get(a_type, a_field, phn));	\
+		}							\
+		if (phn_next_get(a_type, a_field, phn) != NULL) {	\
+			phn_prev_set(a_type, a_field,			\
+			    phn_next_get(a_type, a_field, phn),		\
+			    phn_prev_get(a_type, a_field, phn));	\
+		}							\
+	}								\
+}
+
+#endif /* PH_H_ */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/private_namespace.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/private_namespace.h
index 35c3b0c6c7..7ebeeba826 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/private_namespace.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/private_namespace.h
@@ -1,147 +1,199 @@
-#define	a0calloc JEMALLOC_N(a0calloc)
-#define	a0free JEMALLOC_N(a0free)
+#define	a0dalloc JEMALLOC_N(a0dalloc)
+#define	a0get JEMALLOC_N(a0get)
 #define	a0malloc JEMALLOC_N(a0malloc)
+#define	arena_aalloc JEMALLOC_N(arena_aalloc)
 #define	arena_alloc_junk_small JEMALLOC_N(arena_alloc_junk_small)
+#define	arena_basic_stats_merge JEMALLOC_N(arena_basic_stats_merge)
 #define	arena_bin_index JEMALLOC_N(arena_bin_index)
 #define	arena_bin_info JEMALLOC_N(arena_bin_info)
+#define	arena_bitselm_get_const JEMALLOC_N(arena_bitselm_get_const)
+#define	arena_bitselm_get_mutable JEMALLOC_N(arena_bitselm_get_mutable)
 #define	arena_boot JEMALLOC_N(arena_boot)
+#define	arena_choose JEMALLOC_N(arena_choose)
+#define	arena_choose_hard JEMALLOC_N(arena_choose_hard)
+#define	arena_choose_impl JEMALLOC_N(arena_choose_impl)
+#define	arena_chunk_alloc_huge JEMALLOC_N(arena_chunk_alloc_huge)
+#define	arena_chunk_cache_maybe_insert JEMALLOC_N(arena_chunk_cache_maybe_insert)
+#define	arena_chunk_cache_maybe_remove JEMALLOC_N(arena_chunk_cache_maybe_remove)
+#define	arena_chunk_dalloc_huge JEMALLOC_N(arena_chunk_dalloc_huge)
+#define	arena_chunk_ralloc_huge_expand JEMALLOC_N(arena_chunk_ralloc_huge_expand)
+#define	arena_chunk_ralloc_huge_shrink JEMALLOC_N(arena_chunk_ralloc_huge_shrink)
+#define	arena_chunk_ralloc_huge_similar JEMALLOC_N(arena_chunk_ralloc_huge_similar)
+#define	arena_cleanup JEMALLOC_N(arena_cleanup)
 #define	arena_dalloc JEMALLOC_N(arena_dalloc)
 #define	arena_dalloc_bin JEMALLOC_N(arena_dalloc_bin)
-#define	arena_dalloc_bin_locked JEMALLOC_N(arena_dalloc_bin_locked)
+#define	arena_dalloc_bin_junked_locked JEMALLOC_N(arena_dalloc_bin_junked_locked)
 #define	arena_dalloc_junk_large JEMALLOC_N(arena_dalloc_junk_large)
 #define	arena_dalloc_junk_small JEMALLOC_N(arena_dalloc_junk_small)
 #define	arena_dalloc_large JEMALLOC_N(arena_dalloc_large)
-#define	arena_dalloc_large_locked JEMALLOC_N(arena_dalloc_large_locked)
+#define	arena_dalloc_large_junked_locked JEMALLOC_N(arena_dalloc_large_junked_locked)
 #define	arena_dalloc_small JEMALLOC_N(arena_dalloc_small)
+#define	arena_decay_tick JEMALLOC_N(arena_decay_tick)
+#define	arena_decay_ticks JEMALLOC_N(arena_decay_ticks)
+#define	arena_decay_time_default_get JEMALLOC_N(arena_decay_time_default_get)
+#define	arena_decay_time_default_set JEMALLOC_N(arena_decay_time_default_set)
+#define	arena_decay_time_get JEMALLOC_N(arena_decay_time_get)
+#define	arena_decay_time_set JEMALLOC_N(arena_decay_time_set)
 #define	arena_dss_prec_get JEMALLOC_N(arena_dss_prec_get)
 #define	arena_dss_prec_set JEMALLOC_N(arena_dss_prec_set)
+#define	arena_extent_sn_next JEMALLOC_N(arena_extent_sn_next)
+#define	arena_get JEMALLOC_N(arena_get)
+#define	arena_ichoose JEMALLOC_N(arena_ichoose)
+#define	arena_init JEMALLOC_N(arena_init)
+#define	arena_lg_dirty_mult_default_get JEMALLOC_N(arena_lg_dirty_mult_default_get)
+#define	arena_lg_dirty_mult_default_set JEMALLOC_N(arena_lg_dirty_mult_default_set)
+#define	arena_lg_dirty_mult_get JEMALLOC_N(arena_lg_dirty_mult_get)
+#define	arena_lg_dirty_mult_set JEMALLOC_N(arena_lg_dirty_mult_set)
 #define	arena_malloc JEMALLOC_N(arena_malloc)
+#define	arena_malloc_hard JEMALLOC_N(arena_malloc_hard)
 #define	arena_malloc_large JEMALLOC_N(arena_malloc_large)
-#define	arena_malloc_small JEMALLOC_N(arena_malloc_small)
 #define	arena_mapbits_allocated_get JEMALLOC_N(arena_mapbits_allocated_get)
 #define	arena_mapbits_binind_get JEMALLOC_N(arena_mapbits_binind_get)
+#define	arena_mapbits_decommitted_get JEMALLOC_N(arena_mapbits_decommitted_get)
 #define	arena_mapbits_dirty_get JEMALLOC_N(arena_mapbits_dirty_get)
 #define	arena_mapbits_get JEMALLOC_N(arena_mapbits_get)
+#define	arena_mapbits_internal_set JEMALLOC_N(arena_mapbits_internal_set)
 #define	arena_mapbits_large_binind_set JEMALLOC_N(arena_mapbits_large_binind_set)
 #define	arena_mapbits_large_get JEMALLOC_N(arena_mapbits_large_get)
 #define	arena_mapbits_large_set JEMALLOC_N(arena_mapbits_large_set)
 #define	arena_mapbits_large_size_get JEMALLOC_N(arena_mapbits_large_size_get)
+#define	arena_mapbits_size_decode JEMALLOC_N(arena_mapbits_size_decode)
+#define	arena_mapbits_size_encode JEMALLOC_N(arena_mapbits_size_encode)
 #define	arena_mapbits_small_runind_get JEMALLOC_N(arena_mapbits_small_runind_get)
 #define	arena_mapbits_small_set JEMALLOC_N(arena_mapbits_small_set)
 #define	arena_mapbits_unallocated_set JEMALLOC_N(arena_mapbits_unallocated_set)
 #define	arena_mapbits_unallocated_size_get JEMALLOC_N(arena_mapbits_unallocated_size_get)
 #define	arena_mapbits_unallocated_size_set JEMALLOC_N(arena_mapbits_unallocated_size_set)
 #define	arena_mapbits_unzeroed_get JEMALLOC_N(arena_mapbits_unzeroed_get)
-#define	arena_mapbits_unzeroed_set JEMALLOC_N(arena_mapbits_unzeroed_set)
-#define	arena_mapbitsp_get JEMALLOC_N(arena_mapbitsp_get)
+#define	arena_mapbitsp_get_const JEMALLOC_N(arena_mapbitsp_get_const)
+#define	arena_mapbitsp_get_mutable JEMALLOC_N(arena_mapbitsp_get_mutable)
 #define	arena_mapbitsp_read JEMALLOC_N(arena_mapbitsp_read)
 #define	arena_mapbitsp_write JEMALLOC_N(arena_mapbitsp_write)
-#define	arena_mapp_get JEMALLOC_N(arena_mapp_get)
-#define	arena_maxclass JEMALLOC_N(arena_maxclass)
+#define	arena_maxrun JEMALLOC_N(arena_maxrun)
+#define	arena_maybe_purge JEMALLOC_N(arena_maybe_purge)
+#define	arena_metadata_allocated_add JEMALLOC_N(arena_metadata_allocated_add)
+#define	arena_metadata_allocated_get JEMALLOC_N(arena_metadata_allocated_get)
+#define	arena_metadata_allocated_sub JEMALLOC_N(arena_metadata_allocated_sub)
+#define	arena_migrate JEMALLOC_N(arena_migrate)
+#define	arena_miscelm_get_const JEMALLOC_N(arena_miscelm_get_const)
+#define	arena_miscelm_get_mutable JEMALLOC_N(arena_miscelm_get_mutable)
+#define	arena_miscelm_to_pageind JEMALLOC_N(arena_miscelm_to_pageind)
+#define	arena_miscelm_to_rpages JEMALLOC_N(arena_miscelm_to_rpages)
 #define	arena_new JEMALLOC_N(arena_new)
+#define	arena_node_alloc JEMALLOC_N(arena_node_alloc)
+#define	arena_node_dalloc JEMALLOC_N(arena_node_dalloc)
+#define	arena_nthreads_dec JEMALLOC_N(arena_nthreads_dec)
+#define	arena_nthreads_get JEMALLOC_N(arena_nthreads_get)
+#define	arena_nthreads_inc JEMALLOC_N(arena_nthreads_inc)
 #define	arena_palloc JEMALLOC_N(arena_palloc)
 #define	arena_postfork_child JEMALLOC_N(arena_postfork_child)
 #define	arena_postfork_parent JEMALLOC_N(arena_postfork_parent)
-#define	arena_prefork JEMALLOC_N(arena_prefork)
+#define	arena_prefork0 JEMALLOC_N(arena_prefork0)
+#define	arena_prefork1 JEMALLOC_N(arena_prefork1)
+#define	arena_prefork2 JEMALLOC_N(arena_prefork2)
+#define	arena_prefork3 JEMALLOC_N(arena_prefork3)
 #define	arena_prof_accum JEMALLOC_N(arena_prof_accum)
 #define	arena_prof_accum_impl JEMALLOC_N(arena_prof_accum_impl)
 #define	arena_prof_accum_locked JEMALLOC_N(arena_prof_accum_locked)
-#define	arena_prof_ctx_get JEMALLOC_N(arena_prof_ctx_get)
-#define	arena_prof_ctx_set JEMALLOC_N(arena_prof_ctx_set)
 #define	arena_prof_promoted JEMALLOC_N(arena_prof_promoted)
+#define	arena_prof_tctx_get JEMALLOC_N(arena_prof_tctx_get)
+#define	arena_prof_tctx_reset JEMALLOC_N(arena_prof_tctx_reset)
+#define	arena_prof_tctx_set JEMALLOC_N(arena_prof_tctx_set)
 #define	arena_ptr_small_binind_get JEMALLOC_N(arena_ptr_small_binind_get)
-#define	arena_purge_all JEMALLOC_N(arena_purge_all)
+#define	arena_purge JEMALLOC_N(arena_purge)
 #define	arena_quarantine_junk_small JEMALLOC_N(arena_quarantine_junk_small)
 #define	arena_ralloc JEMALLOC_N(arena_ralloc)
 #define	arena_ralloc_junk_large JEMALLOC_N(arena_ralloc_junk_large)
 #define	arena_ralloc_no_move JEMALLOC_N(arena_ralloc_no_move)
+#define	arena_rd_to_miscelm JEMALLOC_N(arena_rd_to_miscelm)
 #define	arena_redzone_corruption JEMALLOC_N(arena_redzone_corruption)
+#define	arena_reset JEMALLOC_N(arena_reset)
 #define	arena_run_regind JEMALLOC_N(arena_run_regind)
+#define	arena_run_to_miscelm JEMALLOC_N(arena_run_to_miscelm)
 #define	arena_salloc JEMALLOC_N(arena_salloc)
+#define	arena_sdalloc JEMALLOC_N(arena_sdalloc)
 #define	arena_stats_merge JEMALLOC_N(arena_stats_merge)
 #define	arena_tcache_fill_small JEMALLOC_N(arena_tcache_fill_small)
+#define	arena_tdata_get JEMALLOC_N(arena_tdata_get)
+#define	arena_tdata_get_hard JEMALLOC_N(arena_tdata_get_hard)
 #define	arenas JEMALLOC_N(arenas)
-#define	arenas_booted JEMALLOC_N(arenas_booted)
-#define	arenas_cleanup JEMALLOC_N(arenas_cleanup)
-#define	arenas_extend JEMALLOC_N(arenas_extend)
-#define	arenas_initialized JEMALLOC_N(arenas_initialized)
-#define	arenas_lock JEMALLOC_N(arenas_lock)
-#define	arenas_tls JEMALLOC_N(arenas_tls)
-#define	arenas_tsd JEMALLOC_N(arenas_tsd)
-#define	arenas_tsd_boot JEMALLOC_N(arenas_tsd_boot)
-#define	arenas_tsd_cleanup_wrapper JEMALLOC_N(arenas_tsd_cleanup_wrapper)
-#define	arenas_tsd_get JEMALLOC_N(arenas_tsd_get)
-#define	arenas_tsd_get_wrapper JEMALLOC_N(arenas_tsd_get_wrapper)
-#define	arenas_tsd_init_head JEMALLOC_N(arenas_tsd_init_head)
-#define	arenas_tsd_set JEMALLOC_N(arenas_tsd_set)
+#define	arenas_tdata_bypass_cleanup JEMALLOC_N(arenas_tdata_bypass_cleanup)
+#define	arenas_tdata_cleanup JEMALLOC_N(arenas_tdata_cleanup)
+#define	atomic_add_p JEMALLOC_N(atomic_add_p)
 #define	atomic_add_u JEMALLOC_N(atomic_add_u)
 #define	atomic_add_uint32 JEMALLOC_N(atomic_add_uint32)
 #define	atomic_add_uint64 JEMALLOC_N(atomic_add_uint64)
 #define	atomic_add_z JEMALLOC_N(atomic_add_z)
+#define	atomic_cas_p JEMALLOC_N(atomic_cas_p)
+#define	atomic_cas_u JEMALLOC_N(atomic_cas_u)
+#define	atomic_cas_uint32 JEMALLOC_N(atomic_cas_uint32)
+#define	atomic_cas_uint64 JEMALLOC_N(atomic_cas_uint64)
+#define	atomic_cas_z JEMALLOC_N(atomic_cas_z)
+#define	atomic_sub_p JEMALLOC_N(atomic_sub_p)
 #define	atomic_sub_u JEMALLOC_N(atomic_sub_u)
 #define	atomic_sub_uint32 JEMALLOC_N(atomic_sub_uint32)
 #define	atomic_sub_uint64 JEMALLOC_N(atomic_sub_uint64)
 #define	atomic_sub_z JEMALLOC_N(atomic_sub_z)
+#define	atomic_write_p JEMALLOC_N(atomic_write_p)
+#define	atomic_write_u JEMALLOC_N(atomic_write_u)
+#define	atomic_write_uint32 JEMALLOC_N(atomic_write_uint32)
+#define	atomic_write_uint64 JEMALLOC_N(atomic_write_uint64)
+#define	atomic_write_z JEMALLOC_N(atomic_write_z)
 #define	base_alloc JEMALLOC_N(base_alloc)
 #define	base_boot JEMALLOC_N(base_boot)
-#define	base_calloc JEMALLOC_N(base_calloc)
-#define	base_node_alloc JEMALLOC_N(base_node_alloc)
-#define	base_node_dealloc JEMALLOC_N(base_node_dealloc)
 #define	base_postfork_child JEMALLOC_N(base_postfork_child)
 #define	base_postfork_parent JEMALLOC_N(base_postfork_parent)
 #define	base_prefork JEMALLOC_N(base_prefork)
+#define	base_stats_get JEMALLOC_N(base_stats_get)
 #define	bitmap_full JEMALLOC_N(bitmap_full)
 #define	bitmap_get JEMALLOC_N(bitmap_get)
 #define	bitmap_info_init JEMALLOC_N(bitmap_info_init)
-#define	bitmap_info_ngroups JEMALLOC_N(bitmap_info_ngroups)
 #define	bitmap_init JEMALLOC_N(bitmap_init)
 #define	bitmap_set JEMALLOC_N(bitmap_set)
 #define	bitmap_sfu JEMALLOC_N(bitmap_sfu)
 #define	bitmap_size JEMALLOC_N(bitmap_size)
 #define	bitmap_unset JEMALLOC_N(bitmap_unset)
+#define	bootstrap_calloc JEMALLOC_N(bootstrap_calloc)
+#define	bootstrap_free JEMALLOC_N(bootstrap_free)
+#define	bootstrap_malloc JEMALLOC_N(bootstrap_malloc)
 #define	bt_init JEMALLOC_N(bt_init)
 #define	buferror JEMALLOC_N(buferror)
-#define	choose_arena JEMALLOC_N(choose_arena)
-#define	choose_arena_hard JEMALLOC_N(choose_arena_hard)
-#define	chunk_alloc JEMALLOC_N(chunk_alloc)
+#define	chunk_alloc_base JEMALLOC_N(chunk_alloc_base)
+#define	chunk_alloc_cache JEMALLOC_N(chunk_alloc_cache)
 #define	chunk_alloc_dss JEMALLOC_N(chunk_alloc_dss)
 #define	chunk_alloc_mmap JEMALLOC_N(chunk_alloc_mmap)
+#define	chunk_alloc_wrapper JEMALLOC_N(chunk_alloc_wrapper)
 #define	chunk_boot JEMALLOC_N(chunk_boot)
-#define	chunk_dealloc JEMALLOC_N(chunk_dealloc)
-#define	chunk_dealloc_mmap JEMALLOC_N(chunk_dealloc_mmap)
+#define	chunk_dalloc_cache JEMALLOC_N(chunk_dalloc_cache)
+#define	chunk_dalloc_mmap JEMALLOC_N(chunk_dalloc_mmap)
+#define	chunk_dalloc_wrapper JEMALLOC_N(chunk_dalloc_wrapper)
+#define	chunk_deregister JEMALLOC_N(chunk_deregister)
 #define	chunk_dss_boot JEMALLOC_N(chunk_dss_boot)
-#define	chunk_dss_postfork_child JEMALLOC_N(chunk_dss_postfork_child)
-#define	chunk_dss_postfork_parent JEMALLOC_N(chunk_dss_postfork_parent)
+#define	chunk_dss_mergeable JEMALLOC_N(chunk_dss_mergeable)
 #define	chunk_dss_prec_get JEMALLOC_N(chunk_dss_prec_get)
 #define	chunk_dss_prec_set JEMALLOC_N(chunk_dss_prec_set)
-#define	chunk_dss_prefork JEMALLOC_N(chunk_dss_prefork)
+#define	chunk_hooks_default JEMALLOC_N(chunk_hooks_default)
+#define	chunk_hooks_get JEMALLOC_N(chunk_hooks_get)
+#define	chunk_hooks_set JEMALLOC_N(chunk_hooks_set)
 #define	chunk_in_dss JEMALLOC_N(chunk_in_dss)
+#define	chunk_lookup JEMALLOC_N(chunk_lookup)
 #define	chunk_npages JEMALLOC_N(chunk_npages)
-#define	chunk_postfork_child JEMALLOC_N(chunk_postfork_child)
-#define	chunk_postfork_parent JEMALLOC_N(chunk_postfork_parent)
-#define	chunk_prefork JEMALLOC_N(chunk_prefork)
-#define	chunk_unmap JEMALLOC_N(chunk_unmap)
-#define	chunks_mtx JEMALLOC_N(chunks_mtx)
+#define	chunk_purge_wrapper JEMALLOC_N(chunk_purge_wrapper)
+#define	chunk_register JEMALLOC_N(chunk_register)
 #define	chunks_rtree JEMALLOC_N(chunks_rtree)
 #define	chunksize JEMALLOC_N(chunksize)
 #define	chunksize_mask JEMALLOC_N(chunksize_mask)
-#define	ckh_bucket_search JEMALLOC_N(ckh_bucket_search)
 #define	ckh_count JEMALLOC_N(ckh_count)
 #define	ckh_delete JEMALLOC_N(ckh_delete)
-#define	ckh_evict_reloc_insert JEMALLOC_N(ckh_evict_reloc_insert)
 #define	ckh_insert JEMALLOC_N(ckh_insert)
-#define	ckh_isearch JEMALLOC_N(ckh_isearch)
 #define	ckh_iter JEMALLOC_N(ckh_iter)
 #define	ckh_new JEMALLOC_N(ckh_new)
 #define	ckh_pointer_hash JEMALLOC_N(ckh_pointer_hash)
 #define	ckh_pointer_keycomp JEMALLOC_N(ckh_pointer_keycomp)
-#define	ckh_rebuild JEMALLOC_N(ckh_rebuild)
 #define	ckh_remove JEMALLOC_N(ckh_remove)
 #define	ckh_search JEMALLOC_N(ckh_search)
 #define	ckh_string_hash JEMALLOC_N(ckh_string_hash)
 #define	ckh_string_keycomp JEMALLOC_N(ckh_string_keycomp)
-#define	ckh_try_bucket_insert JEMALLOC_N(ckh_try_bucket_insert)
-#define	ckh_try_insert JEMALLOC_N(ckh_try_insert)
 #define	ctl_boot JEMALLOC_N(ctl_boot)
 #define	ctl_bymib JEMALLOC_N(ctl_bymib)
 #define	ctl_byname JEMALLOC_N(ctl_byname)
@@ -149,7 +201,33 @@
 #define	ctl_postfork_child JEMALLOC_N(ctl_postfork_child)
 #define	ctl_postfork_parent JEMALLOC_N(ctl_postfork_parent)
 #define	ctl_prefork JEMALLOC_N(ctl_prefork)
+#define	decay_ticker_get JEMALLOC_N(decay_ticker_get)
 #define	dss_prec_names JEMALLOC_N(dss_prec_names)
+#define	extent_node_achunk_get JEMALLOC_N(extent_node_achunk_get)
+#define	extent_node_achunk_set JEMALLOC_N(extent_node_achunk_set)
+#define	extent_node_addr_get JEMALLOC_N(extent_node_addr_get)
+#define	extent_node_addr_set JEMALLOC_N(extent_node_addr_set)
+#define	extent_node_arena_get JEMALLOC_N(extent_node_arena_get)
+#define	extent_node_arena_set JEMALLOC_N(extent_node_arena_set)
+#define	extent_node_committed_get JEMALLOC_N(extent_node_committed_get)
+#define	extent_node_committed_set JEMALLOC_N(extent_node_committed_set)
+#define	extent_node_dirty_insert JEMALLOC_N(extent_node_dirty_insert)
+#define	extent_node_dirty_linkage_init JEMALLOC_N(extent_node_dirty_linkage_init)
+#define	extent_node_dirty_remove JEMALLOC_N(extent_node_dirty_remove)
+#define	extent_node_init JEMALLOC_N(extent_node_init)
+#define	extent_node_prof_tctx_get JEMALLOC_N(extent_node_prof_tctx_get)
+#define	extent_node_prof_tctx_set JEMALLOC_N(extent_node_prof_tctx_set)
+#define	extent_node_size_get JEMALLOC_N(extent_node_size_get)
+#define	extent_node_size_set JEMALLOC_N(extent_node_size_set)
+#define	extent_node_sn_get JEMALLOC_N(extent_node_sn_get)
+#define	extent_node_sn_set JEMALLOC_N(extent_node_sn_set)
+#define	extent_node_zeroed_get JEMALLOC_N(extent_node_zeroed_get)
+#define	extent_node_zeroed_set JEMALLOC_N(extent_node_zeroed_set)
+#define	extent_size_quantize_ceil JEMALLOC_N(extent_size_quantize_ceil)
+#define	extent_size_quantize_floor JEMALLOC_N(extent_size_quantize_floor)
+#define	extent_tree_ad_destroy JEMALLOC_N(extent_tree_ad_destroy)
+#define	extent_tree_ad_destroy_recurse JEMALLOC_N(extent_tree_ad_destroy_recurse)
+#define	extent_tree_ad_empty JEMALLOC_N(extent_tree_ad_empty)
 #define	extent_tree_ad_first JEMALLOC_N(extent_tree_ad_first)
 #define	extent_tree_ad_insert JEMALLOC_N(extent_tree_ad_insert)
 #define	extent_tree_ad_iter JEMALLOC_N(extent_tree_ad_iter)
@@ -166,22 +244,31 @@
 #define	extent_tree_ad_reverse_iter_recurse JEMALLOC_N(extent_tree_ad_reverse_iter_recurse)
 #define	extent_tree_ad_reverse_iter_start JEMALLOC_N(extent_tree_ad_reverse_iter_start)
 #define	extent_tree_ad_search JEMALLOC_N(extent_tree_ad_search)
-#define	extent_tree_szad_first JEMALLOC_N(extent_tree_szad_first)
-#define	extent_tree_szad_insert JEMALLOC_N(extent_tree_szad_insert)
-#define	extent_tree_szad_iter JEMALLOC_N(extent_tree_szad_iter)
-#define	extent_tree_szad_iter_recurse JEMALLOC_N(extent_tree_szad_iter_recurse)
-#define	extent_tree_szad_iter_start JEMALLOC_N(extent_tree_szad_iter_start)
-#define	extent_tree_szad_last JEMALLOC_N(extent_tree_szad_last)
-#define	extent_tree_szad_new JEMALLOC_N(extent_tree_szad_new)
-#define	extent_tree_szad_next JEMALLOC_N(extent_tree_szad_next)
-#define	extent_tree_szad_nsearch JEMALLOC_N(extent_tree_szad_nsearch)
-#define	extent_tree_szad_prev JEMALLOC_N(extent_tree_szad_prev)
-#define	extent_tree_szad_psearch JEMALLOC_N(extent_tree_szad_psearch)
-#define	extent_tree_szad_remove JEMALLOC_N(extent_tree_szad_remove)
-#define	extent_tree_szad_reverse_iter JEMALLOC_N(extent_tree_szad_reverse_iter)
-#define	extent_tree_szad_reverse_iter_recurse JEMALLOC_N(extent_tree_szad_reverse_iter_recurse)
-#define	extent_tree_szad_reverse_iter_start JEMALLOC_N(extent_tree_szad_reverse_iter_start)
-#define	extent_tree_szad_search JEMALLOC_N(extent_tree_szad_search)
+#define	extent_tree_szsnad_destroy JEMALLOC_N(extent_tree_szsnad_destroy)
+#define	extent_tree_szsnad_destroy_recurse JEMALLOC_N(extent_tree_szsnad_destroy_recurse)
+#define	extent_tree_szsnad_empty JEMALLOC_N(extent_tree_szsnad_empty)
+#define	extent_tree_szsnad_first JEMALLOC_N(extent_tree_szsnad_first)
+#define	extent_tree_szsnad_insert JEMALLOC_N(extent_tree_szsnad_insert)
+#define	extent_tree_szsnad_iter JEMALLOC_N(extent_tree_szsnad_iter)
+#define	extent_tree_szsnad_iter_recurse JEMALLOC_N(extent_tree_szsnad_iter_recurse)
+#define	extent_tree_szsnad_iter_start JEMALLOC_N(extent_tree_szsnad_iter_start)
+#define	extent_tree_szsnad_last JEMALLOC_N(extent_tree_szsnad_last)
+#define	extent_tree_szsnad_new JEMALLOC_N(extent_tree_szsnad_new)
+#define	extent_tree_szsnad_next JEMALLOC_N(extent_tree_szsnad_next)
+#define	extent_tree_szsnad_nsearch JEMALLOC_N(extent_tree_szsnad_nsearch)
+#define	extent_tree_szsnad_prev JEMALLOC_N(extent_tree_szsnad_prev)
+#define	extent_tree_szsnad_psearch JEMALLOC_N(extent_tree_szsnad_psearch)
+#define	extent_tree_szsnad_remove JEMALLOC_N(extent_tree_szsnad_remove)
+#define	extent_tree_szsnad_reverse_iter JEMALLOC_N(extent_tree_szsnad_reverse_iter)
+#define	extent_tree_szsnad_reverse_iter_recurse JEMALLOC_N(extent_tree_szsnad_reverse_iter_recurse)
+#define	extent_tree_szsnad_reverse_iter_start JEMALLOC_N(extent_tree_szsnad_reverse_iter_start)
+#define	extent_tree_szsnad_search JEMALLOC_N(extent_tree_szsnad_search)
+#define	ffs_llu JEMALLOC_N(ffs_llu)
+#define	ffs_lu JEMALLOC_N(ffs_lu)
+#define	ffs_u JEMALLOC_N(ffs_u)
+#define	ffs_u32 JEMALLOC_N(ffs_u32)
+#define	ffs_u64 JEMALLOC_N(ffs_u64)
+#define	ffs_zu JEMALLOC_N(ffs_zu)
 #define	get_errno JEMALLOC_N(get_errno)
 #define	hash JEMALLOC_N(hash)
 #define	hash_fmix_32 JEMALLOC_N(hash_fmix_32)
@@ -193,46 +280,51 @@
 #define	hash_x64_128 JEMALLOC_N(hash_x64_128)
 #define	hash_x86_128 JEMALLOC_N(hash_x86_128)
 #define	hash_x86_32 JEMALLOC_N(hash_x86_32)
-#define	huge_allocated JEMALLOC_N(huge_allocated)
-#define	huge_boot JEMALLOC_N(huge_boot)
+#define	huge_aalloc JEMALLOC_N(huge_aalloc)
 #define	huge_dalloc JEMALLOC_N(huge_dalloc)
 #define	huge_dalloc_junk JEMALLOC_N(huge_dalloc_junk)
-#define	huge_dss_prec_get JEMALLOC_N(huge_dss_prec_get)
 #define	huge_malloc JEMALLOC_N(huge_malloc)
-#define	huge_mtx JEMALLOC_N(huge_mtx)
-#define	huge_ndalloc JEMALLOC_N(huge_ndalloc)
-#define	huge_nmalloc JEMALLOC_N(huge_nmalloc)
 #define	huge_palloc JEMALLOC_N(huge_palloc)
-#define	huge_postfork_child JEMALLOC_N(huge_postfork_child)
-#define	huge_postfork_parent JEMALLOC_N(huge_postfork_parent)
-#define	huge_prefork JEMALLOC_N(huge_prefork)
-#define	huge_prof_ctx_get JEMALLOC_N(huge_prof_ctx_get)
-#define	huge_prof_ctx_set JEMALLOC_N(huge_prof_ctx_set)
+#define	huge_prof_tctx_get JEMALLOC_N(huge_prof_tctx_get)
+#define	huge_prof_tctx_reset JEMALLOC_N(huge_prof_tctx_reset)
+#define	huge_prof_tctx_set JEMALLOC_N(huge_prof_tctx_set)
 #define	huge_ralloc JEMALLOC_N(huge_ralloc)
 #define	huge_ralloc_no_move JEMALLOC_N(huge_ralloc_no_move)
 #define	huge_salloc JEMALLOC_N(huge_salloc)
-#define	iallocm JEMALLOC_N(iallocm)
-#define	icalloc JEMALLOC_N(icalloc)
-#define	icalloct JEMALLOC_N(icalloct)
+#define	iaalloc JEMALLOC_N(iaalloc)
+#define	ialloc JEMALLOC_N(ialloc)
+#define	iallocztm JEMALLOC_N(iallocztm)
+#define	iarena_cleanup JEMALLOC_N(iarena_cleanup)
 #define	idalloc JEMALLOC_N(idalloc)
-#define	idalloct JEMALLOC_N(idalloct)
-#define	imalloc JEMALLOC_N(imalloc)
-#define	imalloct JEMALLOC_N(imalloct)
+#define	idalloctm JEMALLOC_N(idalloctm)
+#define	in_valgrind JEMALLOC_N(in_valgrind)
+#define	index2size JEMALLOC_N(index2size)
+#define	index2size_compute JEMALLOC_N(index2size_compute)
+#define	index2size_lookup JEMALLOC_N(index2size_lookup)
+#define	index2size_tab JEMALLOC_N(index2size_tab)
 #define	ipalloc JEMALLOC_N(ipalloc)
 #define	ipalloct JEMALLOC_N(ipalloct)
+#define	ipallocztm JEMALLOC_N(ipallocztm)
 #define	iqalloc JEMALLOC_N(iqalloc)
-#define	iqalloct JEMALLOC_N(iqalloct)
 #define	iralloc JEMALLOC_N(iralloc)
 #define	iralloct JEMALLOC_N(iralloct)
 #define	iralloct_realign JEMALLOC_N(iralloct_realign)
 #define	isalloc JEMALLOC_N(isalloc)
+#define	isdalloct JEMALLOC_N(isdalloct)
+#define	isqalloc JEMALLOC_N(isqalloc)
 #define	isthreaded JEMALLOC_N(isthreaded)
 #define	ivsalloc JEMALLOC_N(ivsalloc)
 #define	ixalloc JEMALLOC_N(ixalloc)
 #define	jemalloc_postfork_child JEMALLOC_N(jemalloc_postfork_child)
 #define	jemalloc_postfork_parent JEMALLOC_N(jemalloc_postfork_parent)
 #define	jemalloc_prefork JEMALLOC_N(jemalloc_prefork)
+#define	large_maxclass JEMALLOC_N(large_maxclass)
+#define	lg_floor JEMALLOC_N(lg_floor)
+#define	lg_prof_sample JEMALLOC_N(lg_prof_sample)
 #define	malloc_cprintf JEMALLOC_N(malloc_cprintf)
+#define	malloc_mutex_assert_not_owner JEMALLOC_N(malloc_mutex_assert_not_owner)
+#define	malloc_mutex_assert_owner JEMALLOC_N(malloc_mutex_assert_owner)
+#define	malloc_mutex_boot JEMALLOC_N(malloc_mutex_boot)
 #define	malloc_mutex_init JEMALLOC_N(malloc_mutex_init)
 #define	malloc_mutex_lock JEMALLOC_N(malloc_mutex_lock)
 #define	malloc_mutex_postfork_child JEMALLOC_N(malloc_mutex_postfork_child)
@@ -242,7 +334,8 @@
 #define	malloc_printf JEMALLOC_N(malloc_printf)
 #define	malloc_snprintf JEMALLOC_N(malloc_snprintf)
 #define	malloc_strtoumax JEMALLOC_N(malloc_strtoumax)
-#define	malloc_tsd_boot JEMALLOC_N(malloc_tsd_boot)
+#define	malloc_tsd_boot0 JEMALLOC_N(malloc_tsd_boot0)
+#define	malloc_tsd_boot1 JEMALLOC_N(malloc_tsd_boot1)
 #define	malloc_tsd_cleanup_register JEMALLOC_N(malloc_tsd_cleanup_register)
 #define	malloc_tsd_dalloc JEMALLOC_N(malloc_tsd_dalloc)
 #define	malloc_tsd_malloc JEMALLOC_N(malloc_tsd_malloc)
@@ -251,16 +344,35 @@
 #define	malloc_vsnprintf JEMALLOC_N(malloc_vsnprintf)
 #define	malloc_write JEMALLOC_N(malloc_write)
 #define	map_bias JEMALLOC_N(map_bias)
+#define	map_misc_offset JEMALLOC_N(map_misc_offset)
 #define	mb_write JEMALLOC_N(mb_write)
-#define	mutex_boot JEMALLOC_N(mutex_boot)
 #define	narenas_auto JEMALLOC_N(narenas_auto)
-#define	narenas_total JEMALLOC_N(narenas_total)
+#define	narenas_tdata_cleanup JEMALLOC_N(narenas_tdata_cleanup)
 #define	narenas_total_get JEMALLOC_N(narenas_total_get)
 #define	ncpus JEMALLOC_N(ncpus)
 #define	nhbins JEMALLOC_N(nhbins)
+#define	nhclasses JEMALLOC_N(nhclasses)
+#define	nlclasses JEMALLOC_N(nlclasses)
+#define	nstime_add JEMALLOC_N(nstime_add)
+#define	nstime_compare JEMALLOC_N(nstime_compare)
+#define	nstime_copy JEMALLOC_N(nstime_copy)
+#define	nstime_divide JEMALLOC_N(nstime_divide)
+#define	nstime_idivide JEMALLOC_N(nstime_idivide)
+#define	nstime_imultiply JEMALLOC_N(nstime_imultiply)
+#define	nstime_init JEMALLOC_N(nstime_init)
+#define	nstime_init2 JEMALLOC_N(nstime_init2)
+#define	nstime_monotonic JEMALLOC_N(nstime_monotonic)
+#define	nstime_ns JEMALLOC_N(nstime_ns)
+#define	nstime_nsec JEMALLOC_N(nstime_nsec)
+#define	nstime_sec JEMALLOC_N(nstime_sec)
+#define	nstime_subtract JEMALLOC_N(nstime_subtract)
+#define	nstime_update JEMALLOC_N(nstime_update)
 #define	opt_abort JEMALLOC_N(opt_abort)
+#define	opt_decay_time JEMALLOC_N(opt_decay_time)
 #define	opt_dss JEMALLOC_N(opt_dss)
 #define	opt_junk JEMALLOC_N(opt_junk)
+#define	opt_junk_alloc JEMALLOC_N(opt_junk_alloc)
+#define	opt_junk_free JEMALLOC_N(opt_junk_free)
 #define	opt_lg_chunk JEMALLOC_N(opt_lg_chunk)
 #define	opt_lg_dirty_mult JEMALLOC_N(opt_lg_dirty_mult)
 #define	opt_lg_prof_interval JEMALLOC_N(opt_lg_prof_interval)
@@ -274,140 +386,254 @@
 #define	opt_prof_gdump JEMALLOC_N(opt_prof_gdump)
 #define	opt_prof_leak JEMALLOC_N(opt_prof_leak)
 #define	opt_prof_prefix JEMALLOC_N(opt_prof_prefix)
+#define	opt_prof_thread_active_init JEMALLOC_N(opt_prof_thread_active_init)
+#define	opt_purge JEMALLOC_N(opt_purge)
 #define	opt_quarantine JEMALLOC_N(opt_quarantine)
 #define	opt_redzone JEMALLOC_N(opt_redzone)
 #define	opt_stats_print JEMALLOC_N(opt_stats_print)
 #define	opt_tcache JEMALLOC_N(opt_tcache)
+#define	opt_thp JEMALLOC_N(opt_thp)
 #define	opt_utrace JEMALLOC_N(opt_utrace)
-#define	opt_valgrind JEMALLOC_N(opt_valgrind)
 #define	opt_xmalloc JEMALLOC_N(opt_xmalloc)
 #define	opt_zero JEMALLOC_N(opt_zero)
 #define	p2rz JEMALLOC_N(p2rz)
+#define	pages_boot JEMALLOC_N(pages_boot)
+#define	pages_commit JEMALLOC_N(pages_commit)
+#define	pages_decommit JEMALLOC_N(pages_decommit)
+#define	pages_huge JEMALLOC_N(pages_huge)
+#define	pages_map JEMALLOC_N(pages_map)
+#define	pages_nohuge JEMALLOC_N(pages_nohuge)
 #define	pages_purge JEMALLOC_N(pages_purge)
-#define	pow2_ceil JEMALLOC_N(pow2_ceil)
+#define	pages_trim JEMALLOC_N(pages_trim)
+#define	pages_unmap JEMALLOC_N(pages_unmap)
+#define	pind2sz JEMALLOC_N(pind2sz)
+#define	pind2sz_compute JEMALLOC_N(pind2sz_compute)
+#define	pind2sz_lookup JEMALLOC_N(pind2sz_lookup)
+#define	pind2sz_tab JEMALLOC_N(pind2sz_tab)
+#define	pow2_ceil_u32 JEMALLOC_N(pow2_ceil_u32)
+#define	pow2_ceil_u64 JEMALLOC_N(pow2_ceil_u64)
+#define	pow2_ceil_zu JEMALLOC_N(pow2_ceil_zu)
+#define	prng_lg_range_u32 JEMALLOC_N(prng_lg_range_u32)
+#define	prng_lg_range_u64 JEMALLOC_N(prng_lg_range_u64)
+#define	prng_lg_range_zu JEMALLOC_N(prng_lg_range_zu)
+#define	prng_range_u32 JEMALLOC_N(prng_range_u32)
+#define	prng_range_u64 JEMALLOC_N(prng_range_u64)
+#define	prng_range_zu JEMALLOC_N(prng_range_zu)
+#define	prng_state_next_u32 JEMALLOC_N(prng_state_next_u32)
+#define	prng_state_next_u64 JEMALLOC_N(prng_state_next_u64)
+#define	prng_state_next_zu JEMALLOC_N(prng_state_next_zu)
+#define	prof_active JEMALLOC_N(prof_active)
+#define	prof_active_get JEMALLOC_N(prof_active_get)
+#define	prof_active_get_unlocked JEMALLOC_N(prof_active_get_unlocked)
+#define	prof_active_set JEMALLOC_N(prof_active_set)
+#define	prof_alloc_prep JEMALLOC_N(prof_alloc_prep)
+#define	prof_alloc_rollback JEMALLOC_N(prof_alloc_rollback)
 #define	prof_backtrace JEMALLOC_N(prof_backtrace)
 #define	prof_boot0 JEMALLOC_N(prof_boot0)
 #define	prof_boot1 JEMALLOC_N(prof_boot1)
 #define	prof_boot2 JEMALLOC_N(prof_boot2)
 #define	prof_bt_count JEMALLOC_N(prof_bt_count)
-#define	prof_ctx_get JEMALLOC_N(prof_ctx_get)
-#define	prof_ctx_set JEMALLOC_N(prof_ctx_set)
+#define	prof_dump_header JEMALLOC_N(prof_dump_header)
 #define	prof_dump_open JEMALLOC_N(prof_dump_open)
 #define	prof_free JEMALLOC_N(prof_free)
+#define	prof_free_sampled_object JEMALLOC_N(prof_free_sampled_object)
 #define	prof_gdump JEMALLOC_N(prof_gdump)
+#define	prof_gdump_get JEMALLOC_N(prof_gdump_get)
+#define	prof_gdump_get_unlocked JEMALLOC_N(prof_gdump_get_unlocked)
+#define	prof_gdump_set JEMALLOC_N(prof_gdump_set)
+#define	prof_gdump_val JEMALLOC_N(prof_gdump_val)
 #define	prof_idump JEMALLOC_N(prof_idump)
 #define	prof_interval JEMALLOC_N(prof_interval)
 #define	prof_lookup JEMALLOC_N(prof_lookup)
 #define	prof_malloc JEMALLOC_N(prof_malloc)
+#define	prof_malloc_sample_object JEMALLOC_N(prof_malloc_sample_object)
 #define	prof_mdump JEMALLOC_N(prof_mdump)
 #define	prof_postfork_child JEMALLOC_N(prof_postfork_child)
 #define	prof_postfork_parent JEMALLOC_N(prof_postfork_parent)
-#define	prof_prefork JEMALLOC_N(prof_prefork)
-#define	prof_promote JEMALLOC_N(prof_promote)
+#define	prof_prefork0 JEMALLOC_N(prof_prefork0)
+#define	prof_prefork1 JEMALLOC_N(prof_prefork1)
 #define	prof_realloc JEMALLOC_N(prof_realloc)
+#define	prof_reset JEMALLOC_N(prof_reset)
 #define	prof_sample_accum_update JEMALLOC_N(prof_sample_accum_update)
 #define	prof_sample_threshold_update JEMALLOC_N(prof_sample_threshold_update)
-#define	prof_tdata_booted JEMALLOC_N(prof_tdata_booted)
+#define	prof_tctx_get JEMALLOC_N(prof_tctx_get)
+#define	prof_tctx_reset JEMALLOC_N(prof_tctx_reset)
+#define	prof_tctx_set JEMALLOC_N(prof_tctx_set)
 #define	prof_tdata_cleanup JEMALLOC_N(prof_tdata_cleanup)
+#define	prof_tdata_count JEMALLOC_N(prof_tdata_count)
 #define	prof_tdata_get JEMALLOC_N(prof_tdata_get)
 #define	prof_tdata_init JEMALLOC_N(prof_tdata_init)
-#define	prof_tdata_initialized JEMALLOC_N(prof_tdata_initialized)
-#define	prof_tdata_tls JEMALLOC_N(prof_tdata_tls)
-#define	prof_tdata_tsd JEMALLOC_N(prof_tdata_tsd)
-#define	prof_tdata_tsd_boot JEMALLOC_N(prof_tdata_tsd_boot)
-#define	prof_tdata_tsd_cleanup_wrapper JEMALLOC_N(prof_tdata_tsd_cleanup_wrapper)
-#define	prof_tdata_tsd_get JEMALLOC_N(prof_tdata_tsd_get)
-#define	prof_tdata_tsd_get_wrapper JEMALLOC_N(prof_tdata_tsd_get_wrapper)
-#define	prof_tdata_tsd_init_head JEMALLOC_N(prof_tdata_tsd_init_head)
-#define	prof_tdata_tsd_set JEMALLOC_N(prof_tdata_tsd_set)
+#define	prof_tdata_reinit JEMALLOC_N(prof_tdata_reinit)
+#define	prof_thread_active_get JEMALLOC_N(prof_thread_active_get)
+#define	prof_thread_active_init_get JEMALLOC_N(prof_thread_active_init_get)
+#define	prof_thread_active_init_set JEMALLOC_N(prof_thread_active_init_set)
+#define	prof_thread_active_set JEMALLOC_N(prof_thread_active_set)
+#define	prof_thread_name_get JEMALLOC_N(prof_thread_name_get)
+#define	prof_thread_name_set JEMALLOC_N(prof_thread_name_set)
+#define	psz2ind JEMALLOC_N(psz2ind)
+#define	psz2u JEMALLOC_N(psz2u)
+#define	purge_mode_names JEMALLOC_N(purge_mode_names)
 #define	quarantine JEMALLOC_N(quarantine)
 #define	quarantine_alloc_hook JEMALLOC_N(quarantine_alloc_hook)
-#define	quarantine_boot JEMALLOC_N(quarantine_boot)
-#define	quarantine_booted JEMALLOC_N(quarantine_booted)
+#define	quarantine_alloc_hook_work JEMALLOC_N(quarantine_alloc_hook_work)
 #define	quarantine_cleanup JEMALLOC_N(quarantine_cleanup)
-#define	quarantine_init JEMALLOC_N(quarantine_init)
-#define	quarantine_tls JEMALLOC_N(quarantine_tls)
-#define	quarantine_tsd JEMALLOC_N(quarantine_tsd)
-#define	quarantine_tsd_boot JEMALLOC_N(quarantine_tsd_boot)
-#define	quarantine_tsd_cleanup_wrapper JEMALLOC_N(quarantine_tsd_cleanup_wrapper)
-#define	quarantine_tsd_get JEMALLOC_N(quarantine_tsd_get)
-#define	quarantine_tsd_get_wrapper JEMALLOC_N(quarantine_tsd_get_wrapper)
-#define	quarantine_tsd_init_head JEMALLOC_N(quarantine_tsd_init_head)
-#define	quarantine_tsd_set JEMALLOC_N(quarantine_tsd_set)
-#define	register_zone JEMALLOC_N(register_zone)
+#define	rtree_child_read JEMALLOC_N(rtree_child_read)
+#define	rtree_child_read_hard JEMALLOC_N(rtree_child_read_hard)
+#define	rtree_child_tryread JEMALLOC_N(rtree_child_tryread)
 #define	rtree_delete JEMALLOC_N(rtree_delete)
 #define	rtree_get JEMALLOC_N(rtree_get)
-#define	rtree_get_locked JEMALLOC_N(rtree_get_locked)
 #define	rtree_new JEMALLOC_N(rtree_new)
-#define	rtree_postfork_child JEMALLOC_N(rtree_postfork_child)
-#define	rtree_postfork_parent JEMALLOC_N(rtree_postfork_parent)
-#define	rtree_prefork JEMALLOC_N(rtree_prefork)
+#define	rtree_node_valid JEMALLOC_N(rtree_node_valid)
 #define	rtree_set JEMALLOC_N(rtree_set)
+#define	rtree_start_level JEMALLOC_N(rtree_start_level)
+#define	rtree_subkey JEMALLOC_N(rtree_subkey)
+#define	rtree_subtree_read JEMALLOC_N(rtree_subtree_read)
+#define	rtree_subtree_read_hard JEMALLOC_N(rtree_subtree_read_hard)
+#define	rtree_subtree_tryread JEMALLOC_N(rtree_subtree_tryread)
+#define	rtree_val_read JEMALLOC_N(rtree_val_read)
+#define	rtree_val_write JEMALLOC_N(rtree_val_write)
+#define	run_quantize_ceil JEMALLOC_N(run_quantize_ceil)
+#define	run_quantize_floor JEMALLOC_N(run_quantize_floor)
 #define	s2u JEMALLOC_N(s2u)
+#define	s2u_compute JEMALLOC_N(s2u_compute)
+#define	s2u_lookup JEMALLOC_N(s2u_lookup)
 #define	sa2u JEMALLOC_N(sa2u)
 #define	set_errno JEMALLOC_N(set_errno)
-#define	small_size2bin JEMALLOC_N(small_size2bin)
+#define	size2index JEMALLOC_N(size2index)
+#define	size2index_compute JEMALLOC_N(size2index_compute)
+#define	size2index_lookup JEMALLOC_N(size2index_lookup)
+#define	size2index_tab JEMALLOC_N(size2index_tab)
+#define	spin_adaptive JEMALLOC_N(spin_adaptive)
+#define	spin_init JEMALLOC_N(spin_init)
 #define	stats_cactive JEMALLOC_N(stats_cactive)
 #define	stats_cactive_add JEMALLOC_N(stats_cactive_add)
 #define	stats_cactive_get JEMALLOC_N(stats_cactive_get)
 #define	stats_cactive_sub JEMALLOC_N(stats_cactive_sub)
-#define	stats_chunks JEMALLOC_N(stats_chunks)
 #define	stats_print JEMALLOC_N(stats_print)
 #define	tcache_alloc_easy JEMALLOC_N(tcache_alloc_easy)
 #define	tcache_alloc_large JEMALLOC_N(tcache_alloc_large)
 #define	tcache_alloc_small JEMALLOC_N(tcache_alloc_small)
 #define	tcache_alloc_small_hard JEMALLOC_N(tcache_alloc_small_hard)
-#define	tcache_arena_associate JEMALLOC_N(tcache_arena_associate)
-#define	tcache_arena_dissociate JEMALLOC_N(tcache_arena_dissociate)
+#define	tcache_arena_reassociate JEMALLOC_N(tcache_arena_reassociate)
 #define	tcache_bin_flush_large JEMALLOC_N(tcache_bin_flush_large)
 #define	tcache_bin_flush_small JEMALLOC_N(tcache_bin_flush_small)
 #define	tcache_bin_info JEMALLOC_N(tcache_bin_info)
-#define	tcache_boot0 JEMALLOC_N(tcache_boot0)
-#define	tcache_boot1 JEMALLOC_N(tcache_boot1)
-#define	tcache_booted JEMALLOC_N(tcache_booted)
+#define	tcache_boot JEMALLOC_N(tcache_boot)
+#define	tcache_cleanup JEMALLOC_N(tcache_cleanup)
 #define	tcache_create JEMALLOC_N(tcache_create)
 #define	tcache_dalloc_large JEMALLOC_N(tcache_dalloc_large)
 #define	tcache_dalloc_small JEMALLOC_N(tcache_dalloc_small)
-#define	tcache_destroy JEMALLOC_N(tcache_destroy)
-#define	tcache_enabled_booted JEMALLOC_N(tcache_enabled_booted)
+#define	tcache_enabled_cleanup JEMALLOC_N(tcache_enabled_cleanup)
 #define	tcache_enabled_get JEMALLOC_N(tcache_enabled_get)
-#define	tcache_enabled_initialized JEMALLOC_N(tcache_enabled_initialized)
 #define	tcache_enabled_set JEMALLOC_N(tcache_enabled_set)
-#define	tcache_enabled_tls JEMALLOC_N(tcache_enabled_tls)
-#define	tcache_enabled_tsd JEMALLOC_N(tcache_enabled_tsd)
-#define	tcache_enabled_tsd_boot JEMALLOC_N(tcache_enabled_tsd_boot)
-#define	tcache_enabled_tsd_cleanup_wrapper JEMALLOC_N(tcache_enabled_tsd_cleanup_wrapper)
-#define	tcache_enabled_tsd_get JEMALLOC_N(tcache_enabled_tsd_get)
-#define	tcache_enabled_tsd_get_wrapper JEMALLOC_N(tcache_enabled_tsd_get_wrapper)
-#define	tcache_enabled_tsd_init_head JEMALLOC_N(tcache_enabled_tsd_init_head)
-#define	tcache_enabled_tsd_set JEMALLOC_N(tcache_enabled_tsd_set)
 #define	tcache_event JEMALLOC_N(tcache_event)
 #define	tcache_event_hard JEMALLOC_N(tcache_event_hard)
 #define	tcache_flush JEMALLOC_N(tcache_flush)
 #define	tcache_get JEMALLOC_N(tcache_get)
-#define	tcache_initialized JEMALLOC_N(tcache_initialized)
+#define	tcache_get_hard JEMALLOC_N(tcache_get_hard)
 #define	tcache_maxclass JEMALLOC_N(tcache_maxclass)
+#define	tcache_postfork_child JEMALLOC_N(tcache_postfork_child)
+#define	tcache_postfork_parent JEMALLOC_N(tcache_postfork_parent)
+#define	tcache_prefork JEMALLOC_N(tcache_prefork)
 #define	tcache_salloc JEMALLOC_N(tcache_salloc)
 #define	tcache_stats_merge JEMALLOC_N(tcache_stats_merge)
-#define	tcache_thread_cleanup JEMALLOC_N(tcache_thread_cleanup)
-#define	tcache_tls JEMALLOC_N(tcache_tls)
-#define	tcache_tsd JEMALLOC_N(tcache_tsd)
-#define	tcache_tsd_boot JEMALLOC_N(tcache_tsd_boot)
-#define	tcache_tsd_cleanup_wrapper JEMALLOC_N(tcache_tsd_cleanup_wrapper)
-#define	tcache_tsd_get JEMALLOC_N(tcache_tsd_get)
-#define	tcache_tsd_get_wrapper JEMALLOC_N(tcache_tsd_get_wrapper)
-#define	tcache_tsd_init_head JEMALLOC_N(tcache_tsd_init_head)
-#define	tcache_tsd_set JEMALLOC_N(tcache_tsd_set)
-#define	thread_allocated_booted JEMALLOC_N(thread_allocated_booted)
-#define	thread_allocated_initialized JEMALLOC_N(thread_allocated_initialized)
-#define	thread_allocated_tls JEMALLOC_N(thread_allocated_tls)
-#define	thread_allocated_tsd JEMALLOC_N(thread_allocated_tsd)
-#define	thread_allocated_tsd_boot JEMALLOC_N(thread_allocated_tsd_boot)
-#define	thread_allocated_tsd_cleanup_wrapper JEMALLOC_N(thread_allocated_tsd_cleanup_wrapper)
-#define	thread_allocated_tsd_get JEMALLOC_N(thread_allocated_tsd_get)
-#define	thread_allocated_tsd_get_wrapper JEMALLOC_N(thread_allocated_tsd_get_wrapper)
-#define	thread_allocated_tsd_init_head JEMALLOC_N(thread_allocated_tsd_init_head)
-#define	thread_allocated_tsd_set JEMALLOC_N(thread_allocated_tsd_set)
+#define	tcaches JEMALLOC_N(tcaches)
+#define	tcaches_create JEMALLOC_N(tcaches_create)
+#define	tcaches_destroy JEMALLOC_N(tcaches_destroy)
+#define	tcaches_flush JEMALLOC_N(tcaches_flush)
+#define	tcaches_get JEMALLOC_N(tcaches_get)
+#define	thread_allocated_cleanup JEMALLOC_N(thread_allocated_cleanup)
+#define	thread_deallocated_cleanup JEMALLOC_N(thread_deallocated_cleanup)
+#define	ticker_copy JEMALLOC_N(ticker_copy)
+#define	ticker_init JEMALLOC_N(ticker_init)
+#define	ticker_read JEMALLOC_N(ticker_read)
+#define	ticker_tick JEMALLOC_N(ticker_tick)
+#define	ticker_ticks JEMALLOC_N(ticker_ticks)
+#define	tsd_arena_get JEMALLOC_N(tsd_arena_get)
+#define	tsd_arena_set JEMALLOC_N(tsd_arena_set)
+#define	tsd_arenap_get JEMALLOC_N(tsd_arenap_get)
+#define	tsd_arenas_tdata_bypass_get JEMALLOC_N(tsd_arenas_tdata_bypass_get)
+#define	tsd_arenas_tdata_bypass_set JEMALLOC_N(tsd_arenas_tdata_bypass_set)
+#define	tsd_arenas_tdata_bypassp_get JEMALLOC_N(tsd_arenas_tdata_bypassp_get)
+#define	tsd_arenas_tdata_get JEMALLOC_N(tsd_arenas_tdata_get)
+#define	tsd_arenas_tdata_set JEMALLOC_N(tsd_arenas_tdata_set)
+#define	tsd_arenas_tdatap_get JEMALLOC_N(tsd_arenas_tdatap_get)
+#define	tsd_boot JEMALLOC_N(tsd_boot)
+#define	tsd_boot0 JEMALLOC_N(tsd_boot0)
+#define	tsd_boot1 JEMALLOC_N(tsd_boot1)
+#define	tsd_booted JEMALLOC_N(tsd_booted)
+#define	tsd_booted_get JEMALLOC_N(tsd_booted_get)
+#define	tsd_cleanup JEMALLOC_N(tsd_cleanup)
+#define	tsd_cleanup_wrapper JEMALLOC_N(tsd_cleanup_wrapper)
+#define	tsd_fetch JEMALLOC_N(tsd_fetch)
+#define	tsd_fetch_impl JEMALLOC_N(tsd_fetch_impl)
+#define	tsd_get JEMALLOC_N(tsd_get)
+#define	tsd_get_allocates JEMALLOC_N(tsd_get_allocates)
+#define	tsd_iarena_get JEMALLOC_N(tsd_iarena_get)
+#define	tsd_iarena_set JEMALLOC_N(tsd_iarena_set)
+#define	tsd_iarenap_get JEMALLOC_N(tsd_iarenap_get)
+#define	tsd_initialized JEMALLOC_N(tsd_initialized)
 #define	tsd_init_check_recursion JEMALLOC_N(tsd_init_check_recursion)
 #define	tsd_init_finish JEMALLOC_N(tsd_init_finish)
+#define	tsd_init_head JEMALLOC_N(tsd_init_head)
+#define	tsd_narenas_tdata_get JEMALLOC_N(tsd_narenas_tdata_get)
+#define	tsd_narenas_tdata_set JEMALLOC_N(tsd_narenas_tdata_set)
+#define	tsd_narenas_tdatap_get JEMALLOC_N(tsd_narenas_tdatap_get)
+#define	tsd_wrapper_get JEMALLOC_N(tsd_wrapper_get)
+#define	tsd_wrapper_set JEMALLOC_N(tsd_wrapper_set)
+#define	tsd_nominal JEMALLOC_N(tsd_nominal)
+#define	tsd_prof_tdata_get JEMALLOC_N(tsd_prof_tdata_get)
+#define	tsd_prof_tdata_set JEMALLOC_N(tsd_prof_tdata_set)
+#define	tsd_prof_tdatap_get JEMALLOC_N(tsd_prof_tdatap_get)
+#define	tsd_quarantine_get JEMALLOC_N(tsd_quarantine_get)
+#define	tsd_quarantine_set JEMALLOC_N(tsd_quarantine_set)
+#define	tsd_quarantinep_get JEMALLOC_N(tsd_quarantinep_get)
+#define	tsd_set JEMALLOC_N(tsd_set)
+#define	tsd_tcache_enabled_get JEMALLOC_N(tsd_tcache_enabled_get)
+#define	tsd_tcache_enabled_set JEMALLOC_N(tsd_tcache_enabled_set)
+#define	tsd_tcache_enabledp_get JEMALLOC_N(tsd_tcache_enabledp_get)
+#define	tsd_tcache_get JEMALLOC_N(tsd_tcache_get)
+#define	tsd_tcache_set JEMALLOC_N(tsd_tcache_set)
+#define	tsd_tcachep_get JEMALLOC_N(tsd_tcachep_get)
+#define	tsd_thread_allocated_get JEMALLOC_N(tsd_thread_allocated_get)
+#define	tsd_thread_allocated_set JEMALLOC_N(tsd_thread_allocated_set)
+#define	tsd_thread_allocatedp_get JEMALLOC_N(tsd_thread_allocatedp_get)
+#define	tsd_thread_deallocated_get JEMALLOC_N(tsd_thread_deallocated_get)
+#define	tsd_thread_deallocated_set JEMALLOC_N(tsd_thread_deallocated_set)
+#define	tsd_thread_deallocatedp_get JEMALLOC_N(tsd_thread_deallocatedp_get)
+#define	tsd_tls JEMALLOC_N(tsd_tls)
+#define	tsd_tsd JEMALLOC_N(tsd_tsd)
+#define	tsd_tsdn JEMALLOC_N(tsd_tsdn)
+#define	tsd_witness_fork_get JEMALLOC_N(tsd_witness_fork_get)
+#define	tsd_witness_fork_set JEMALLOC_N(tsd_witness_fork_set)
+#define	tsd_witness_forkp_get JEMALLOC_N(tsd_witness_forkp_get)
+#define	tsd_witnesses_get JEMALLOC_N(tsd_witnesses_get)
+#define	tsd_witnesses_set JEMALLOC_N(tsd_witnesses_set)
+#define	tsd_witnessesp_get JEMALLOC_N(tsd_witnessesp_get)
+#define	tsdn_fetch JEMALLOC_N(tsdn_fetch)
+#define	tsdn_null JEMALLOC_N(tsdn_null)
+#define	tsdn_tsd JEMALLOC_N(tsdn_tsd)
 #define	u2rz JEMALLOC_N(u2rz)
+#define	valgrind_freelike_block JEMALLOC_N(valgrind_freelike_block)
+#define	valgrind_make_mem_defined JEMALLOC_N(valgrind_make_mem_defined)
+#define	valgrind_make_mem_noaccess JEMALLOC_N(valgrind_make_mem_noaccess)
+#define	valgrind_make_mem_undefined JEMALLOC_N(valgrind_make_mem_undefined)
+#define	witness_assert_depth JEMALLOC_N(witness_assert_depth)
+#define	witness_assert_depth_to_rank JEMALLOC_N(witness_assert_depth_to_rank)
+#define	witness_assert_lockless JEMALLOC_N(witness_assert_lockless)
+#define	witness_assert_not_owner JEMALLOC_N(witness_assert_not_owner)
+#define	witness_assert_owner JEMALLOC_N(witness_assert_owner)
+#define	witness_depth_error JEMALLOC_N(witness_depth_error)
+#define	witness_fork_cleanup JEMALLOC_N(witness_fork_cleanup)
+#define	witness_init JEMALLOC_N(witness_init)
+#define	witness_lock JEMALLOC_N(witness_lock)
+#define	witness_lock_error JEMALLOC_N(witness_lock_error)
+#define	witness_not_owner_error JEMALLOC_N(witness_not_owner_error)
+#define	witness_owner JEMALLOC_N(witness_owner)
+#define	witness_owner_error JEMALLOC_N(witness_owner_error)
+#define	witness_postfork_child JEMALLOC_N(witness_postfork_child)
+#define	witness_postfork_parent JEMALLOC_N(witness_postfork_parent)
+#define	witness_prefork JEMALLOC_N(witness_prefork)
+#define	witness_unlock JEMALLOC_N(witness_unlock)
+#define	witnesses_cleanup JEMALLOC_N(witnesses_cleanup)
+#define	zone_register JEMALLOC_N(zone_register)
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prng.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prng.h
index 7b2b06512f..15cc2d18fa 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prng.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prng.h
@@ -1,5 +1,8 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_PRNG_H
+#define JEMALLOC_INTERNAL_PRNG_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/bit_util.h"
 
 /*
  * Simple linear congruential pseudo-random number generator:
@@ -15,46 +18,168 @@
  * See Knuth's TAOCP 3rd Ed., Vol. 2, pg. 17 for details on these constraints.
  *
  * This choice of m has the disadvantage that the quality of the bits is
- * proportional to bit position.  For example. the lowest bit has a cycle of 2,
+ * proportional to bit position.  For example, the lowest bit has a cycle of 2,
  * the next has a cycle of 4, etc.  For this reason, we prefer to use the upper
  * bits.
- *
- * Macro parameters:
- *   uint32_t r          : Result.
- *   unsigned lg_range   : (0..32], number of least significant bits to return.
- *   uint32_t state      : Seed value.
- *   const uint32_t a, c : See above discussion.
  */
-#define	prng32(r, lg_range, state, a, c) do {				\
-	assert(lg_range > 0);						\
-	assert(lg_range <= 32);						\
-									\
-	r = (state * (a)) + (c);					\
-	state = r;							\
-	r >>= (32 - lg_range);						\
-} while (false)
-
-/* Same as prng32(), but 64 bits of pseudo-randomness, using uint64_t. */
-#define	prng64(r, lg_range, state, a, c) do {				\
-	assert(lg_range > 0);						\
-	assert(lg_range <= 64);						\
-									\
-	r = (state * (a)) + (c);					\
-	state = r;							\
-	r >>= (64 - lg_range);						\
-} while (false)
-
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
 
-#endif /* JEMALLOC_H_STRUCTS */
 /******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-#endif /* JEMALLOC_H_EXTERNS */
+/* INTERNAL DEFINITIONS -- IGNORE */
 /******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+#define PRNG_A_32	UINT32_C(1103515241)
+#define PRNG_C_32	UINT32_C(12347)
+
+#define PRNG_A_64	UINT64_C(6364136223846793005)
+#define PRNG_C_64	UINT64_C(1442695040888963407)
+
+JEMALLOC_ALWAYS_INLINE uint32_t
+prng_state_next_u32(uint32_t state) {
+	return (state * PRNG_A_32) + PRNG_C_32;
+}
+
+JEMALLOC_ALWAYS_INLINE uint64_t
+prng_state_next_u64(uint64_t state) {
+	return (state * PRNG_A_64) + PRNG_C_64;
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+prng_state_next_zu(size_t state) {
+#if LG_SIZEOF_PTR == 2
+	return (state * PRNG_A_32) + PRNG_C_32;
+#elif LG_SIZEOF_PTR == 3
+	return (state * PRNG_A_64) + PRNG_C_64;
+#else
+#error Unsupported pointer size
+#endif
+}
 
-#endif /* JEMALLOC_H_INLINES */
 /******************************************************************************/
+/* BEGIN PUBLIC API */
+/******************************************************************************/
+
+/*
+ * The prng_lg_range functions give a uniform int in the half-open range [0,
+ * 2**lg_range).  If atomic is true, they do so safely from multiple threads.
+ * Multithreaded 64-bit prngs aren't supported.
+ */
+
+JEMALLOC_ALWAYS_INLINE uint32_t
+prng_lg_range_u32(atomic_u32_t *state, unsigned lg_range, bool atomic) {
+	uint32_t ret, state0, state1;
+
+	assert(lg_range > 0);
+	assert(lg_range <= 32);
+
+	state0 = atomic_load_u32(state, ATOMIC_RELAXED);
+
+	if (atomic) {
+		do {
+			state1 = prng_state_next_u32(state0);
+		} while (!atomic_compare_exchange_weak_u32(state, &state0,
+		    state1, ATOMIC_RELAXED, ATOMIC_RELAXED));
+	} else {
+		state1 = prng_state_next_u32(state0);
+		atomic_store_u32(state, state1, ATOMIC_RELAXED);
+	}
+	ret = state1 >> (32 - lg_range);
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE uint64_t
+prng_lg_range_u64(uint64_t *state, unsigned lg_range) {
+	uint64_t ret, state1;
+
+	assert(lg_range > 0);
+	assert(lg_range <= 64);
+
+	state1 = prng_state_next_u64(*state);
+	*state = state1;
+	ret = state1 >> (64 - lg_range);
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+prng_lg_range_zu(atomic_zu_t *state, unsigned lg_range, bool atomic) {
+	size_t ret, state0, state1;
+
+	assert(lg_range > 0);
+	assert(lg_range <= ZU(1) << (3 + LG_SIZEOF_PTR));
+
+	state0 = atomic_load_zu(state, ATOMIC_RELAXED);
+
+	if (atomic) {
+		do {
+			state1 = prng_state_next_zu(state0);
+		} while (atomic_compare_exchange_weak_zu(state, &state0,
+		    state1, ATOMIC_RELAXED, ATOMIC_RELAXED));
+	} else {
+		state1 = prng_state_next_zu(state0);
+		atomic_store_zu(state, state1, ATOMIC_RELAXED);
+	}
+	ret = state1 >> ((ZU(1) << (3 + LG_SIZEOF_PTR)) - lg_range);
+
+	return ret;
+}
+
+/*
+ * The prng_range functions behave like the prng_lg_range, but return a result
+ * in [0, range) instead of [0, 2**lg_range).
+ */
+
+JEMALLOC_ALWAYS_INLINE uint32_t
+prng_range_u32(atomic_u32_t *state, uint32_t range, bool atomic) {
+	uint32_t ret;
+	unsigned lg_range;
+
+	assert(range > 1);
+
+	/* Compute the ceiling of lg(range). */
+	lg_range = ffs_u32(pow2_ceil_u32(range)) - 1;
+
+	/* Generate a result in [0..range) via repeated trial. */
+	do {
+		ret = prng_lg_range_u32(state, lg_range, atomic);
+	} while (ret >= range);
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE uint64_t
+prng_range_u64(uint64_t *state, uint64_t range) {
+	uint64_t ret;
+	unsigned lg_range;
+
+	assert(range > 1);
+
+	/* Compute the ceiling of lg(range). */
+	lg_range = ffs_u64(pow2_ceil_u64(range)) - 1;
+
+	/* Generate a result in [0..range) via repeated trial. */
+	do {
+		ret = prng_lg_range_u64(state, lg_range);
+	} while (ret >= range);
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+prng_range_zu(atomic_zu_t *state, size_t range, bool atomic) {
+	size_t ret;
+	unsigned lg_range;
+
+	assert(range > 1);
+
+	/* Compute the ceiling of lg(range). */
+	lg_range = ffs_u64(pow2_ceil_u64(range)) - 1;
+
+	/* Generate a result in [0..range) via repeated trial. */
+	do {
+		ret = prng_lg_range_zu(state, lg_range, atomic);
+	} while (ret >= range);
+
+	return ret;
+}
+
+#endif /* JEMALLOC_INTERNAL_PRNG_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_externs.h
new file mode 100644
index 0000000000..04348696f5
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_externs.h
@@ -0,0 +1,92 @@
+#ifndef JEMALLOC_INTERNAL_PROF_EXTERNS_H
+#define JEMALLOC_INTERNAL_PROF_EXTERNS_H
+
+#include "jemalloc/internal/mutex.h"
+
+extern malloc_mutex_t	bt2gctx_mtx;
+
+extern bool	opt_prof;
+extern bool	opt_prof_active;
+extern bool	opt_prof_thread_active_init;
+extern size_t	opt_lg_prof_sample;   /* Mean bytes between samples. */
+extern ssize_t	opt_lg_prof_interval; /* lg(prof_interval). */
+extern bool	opt_prof_gdump;       /* High-water memory dumping. */
+extern bool	opt_prof_final;       /* Final profile dumping. */
+extern bool	opt_prof_leak;        /* Dump leak summary at exit. */
+extern bool	opt_prof_accum;       /* Report cumulative bytes. */
+extern char	opt_prof_prefix[
+    /* Minimize memory bloat for non-prof builds. */
+#ifdef JEMALLOC_PROF
+    PATH_MAX +
+#endif
+    1];
+
+/* Accessed via prof_active_[gs]et{_unlocked,}(). */
+extern bool	prof_active;
+
+/* Accessed via prof_gdump_[gs]et{_unlocked,}(). */
+extern bool	prof_gdump_val;
+
+/*
+ * Profile dump interval, measured in bytes allocated.  Each arena triggers a
+ * profile dump when it reaches this threshold.  The effect is that the
+ * interval between profile dumps averages prof_interval, though the actual
+ * interval between dumps will tend to be sporadic, and the interval will be a
+ * maximum of approximately (prof_interval * narenas).
+ */
+extern uint64_t	prof_interval;
+
+/*
+ * Initialized as opt_lg_prof_sample, and potentially modified during profiling
+ * resets.
+ */
+extern size_t	lg_prof_sample;
+
+void prof_alloc_rollback(tsd_t *tsd, prof_tctx_t *tctx, bool updated);
+void prof_malloc_sample_object(tsdn_t *tsdn, const void *ptr, size_t usize,
+    prof_tctx_t *tctx);
+void prof_free_sampled_object(tsd_t *tsd, size_t usize, prof_tctx_t *tctx);
+void bt_init(prof_bt_t *bt, void **vec);
+void prof_backtrace(prof_bt_t *bt);
+prof_tctx_t *prof_lookup(tsd_t *tsd, prof_bt_t *bt);
+#ifdef JEMALLOC_JET
+size_t prof_tdata_count(void);
+size_t prof_bt_count(void);
+#endif
+typedef int (prof_dump_open_t)(bool, const char *);
+extern prof_dump_open_t *JET_MUTABLE prof_dump_open;
+
+typedef bool (prof_dump_header_t)(tsdn_t *, bool, const prof_cnt_t *);
+extern prof_dump_header_t *JET_MUTABLE prof_dump_header;
+#ifdef JEMALLOC_JET
+void prof_cnt_all(uint64_t *curobjs, uint64_t *curbytes, uint64_t *accumobjs,
+    uint64_t *accumbytes);
+#endif
+bool prof_accum_init(tsdn_t *tsdn, prof_accum_t *prof_accum);
+void prof_idump(tsdn_t *tsdn);
+bool prof_mdump(tsd_t *tsd, const char *filename);
+void prof_gdump(tsdn_t *tsdn);
+prof_tdata_t *prof_tdata_init(tsd_t *tsd);
+prof_tdata_t *prof_tdata_reinit(tsd_t *tsd, prof_tdata_t *tdata);
+void prof_reset(tsd_t *tsd, size_t lg_sample);
+void prof_tdata_cleanup(tsd_t *tsd);
+bool prof_active_get(tsdn_t *tsdn);
+bool prof_active_set(tsdn_t *tsdn, bool active);
+const char *prof_thread_name_get(tsd_t *tsd);
+int prof_thread_name_set(tsd_t *tsd, const char *thread_name);
+bool prof_thread_active_get(tsd_t *tsd);
+bool prof_thread_active_set(tsd_t *tsd, bool active);
+bool prof_thread_active_init_get(tsdn_t *tsdn);
+bool prof_thread_active_init_set(tsdn_t *tsdn, bool active_init);
+bool prof_gdump_get(tsdn_t *tsdn);
+bool prof_gdump_set(tsdn_t *tsdn, bool active);
+void prof_boot0(void);
+void prof_boot1(void);
+bool prof_boot2(tsd_t *tsd);
+void prof_prefork0(tsdn_t *tsdn);
+void prof_prefork1(tsdn_t *tsdn);
+void prof_postfork_parent(tsdn_t *tsdn);
+void prof_postfork_child(tsdn_t *tsdn);
+void prof_sample_threshold_update(prof_tdata_t *tdata);
+
+#endif /* JEMALLOC_INTERNAL_PROF_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_a.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_a.h
new file mode 100644
index 0000000000..eda6839ade
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_a.h
@@ -0,0 +1,72 @@
+#ifndef JEMALLOC_INTERNAL_PROF_INLINES_A_H
+#define JEMALLOC_INTERNAL_PROF_INLINES_A_H
+
+#include "jemalloc/internal/mutex.h"
+
+static inline bool
+prof_accum_add(tsdn_t *tsdn, prof_accum_t *prof_accum, uint64_t accumbytes) {
+	cassert(config_prof);
+
+	bool overflow;
+	uint64_t a0, a1;
+
+	/*
+	 * If the application allocates fast enough (and/or if idump is slow
+	 * enough), extreme overflow here (a1 >= prof_interval * 2) can cause
+	 * idump trigger coalescing.  This is an intentional mechanism that
+	 * avoids rate-limiting allocation.
+	 */
+#ifdef JEMALLOC_ATOMIC_U64
+	a0 = atomic_load_u64(&prof_accum->accumbytes, ATOMIC_RELAXED);
+	do {
+		a1 = a0 + accumbytes;
+		assert(a1 >= a0);
+		overflow = (a1 >= prof_interval);
+		if (overflow) {
+			a1 %= prof_interval;
+		}
+	} while (!atomic_compare_exchange_weak_u64(&prof_accum->accumbytes, &a0,
+	    a1, ATOMIC_RELAXED, ATOMIC_RELAXED));
+#else
+	malloc_mutex_lock(tsdn, &prof_accum->mtx);
+	a0 = prof_accum->accumbytes;
+	a1 = a0 + accumbytes;
+	overflow = (a1 >= prof_interval);
+	if (overflow) {
+		a1 %= prof_interval;
+	}
+	prof_accum->accumbytes = a1;
+	malloc_mutex_unlock(tsdn, &prof_accum->mtx);
+#endif
+	return overflow;
+}
+
+static inline void
+prof_accum_cancel(tsdn_t *tsdn, prof_accum_t *prof_accum, size_t usize) {
+	cassert(config_prof);
+
+	/*
+	 * Cancel out as much of the excessive prof_accumbytes increase as
+	 * possible without underflowing.  Interval-triggered dumps occur
+	 * slightly more often than intended as a result of incomplete
+	 * canceling.
+	 */
+	uint64_t a0, a1;
+#ifdef JEMALLOC_ATOMIC_U64
+	a0 = atomic_load_u64(&prof_accum->accumbytes, ATOMIC_RELAXED);
+	do {
+		a1 = (a0 >= LARGE_MINCLASS - usize) ?  a0 - (LARGE_MINCLASS -
+		    usize) : 0;
+	} while (!atomic_compare_exchange_weak_u64(&prof_accum->accumbytes, &a0,
+	    a1, ATOMIC_RELAXED, ATOMIC_RELAXED));
+#else
+	malloc_mutex_lock(tsdn, &prof_accum->mtx);
+	a0 = prof_accum->accumbytes;
+	a1 = (a0 >= LARGE_MINCLASS - usize) ?  a0 - (LARGE_MINCLASS - usize) :
+	    0;
+	prof_accum->accumbytes = a1;
+	malloc_mutex_unlock(tsdn, &prof_accum->mtx);
+#endif
+}
+
+#endif /* JEMALLOC_INTERNAL_PROF_INLINES_A_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_b.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_b.h
new file mode 100644
index 0000000000..d670cb7b8f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_inlines_b.h
@@ -0,0 +1,217 @@
+#ifndef JEMALLOC_INTERNAL_PROF_INLINES_B_H
+#define JEMALLOC_INTERNAL_PROF_INLINES_B_H
+
+#include "jemalloc/internal/sz.h"
+
+JEMALLOC_ALWAYS_INLINE bool
+prof_active_get_unlocked(void) {
+	/*
+	 * Even if opt_prof is true, sampling can be temporarily disabled by
+	 * setting prof_active to false.  No locking is used when reading
+	 * prof_active in the fast path, so there are no guarantees regarding
+	 * how long it will take for all threads to notice state changes.
+	 */
+	return prof_active;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+prof_gdump_get_unlocked(void) {
+	/*
+	 * No locking is used when reading prof_gdump_val in the fast path, so
+	 * there are no guarantees regarding how long it will take for all
+	 * threads to notice state changes.
+	 */
+	return prof_gdump_val;
+}
+
+JEMALLOC_ALWAYS_INLINE prof_tdata_t *
+prof_tdata_get(tsd_t *tsd, bool create) {
+	prof_tdata_t *tdata;
+
+	cassert(config_prof);
+
+	tdata = tsd_prof_tdata_get(tsd);
+	if (create) {
+		if (unlikely(tdata == NULL)) {
+			if (tsd_nominal(tsd)) {
+				tdata = prof_tdata_init(tsd);
+				tsd_prof_tdata_set(tsd, tdata);
+			}
+		} else if (unlikely(tdata->expired)) {
+			tdata = prof_tdata_reinit(tsd, tdata);
+			tsd_prof_tdata_set(tsd, tdata);
+		}
+		assert(tdata == NULL || tdata->attached);
+	}
+
+	return tdata;
+}
+
+JEMALLOC_ALWAYS_INLINE prof_tctx_t *
+prof_tctx_get(tsdn_t *tsdn, const void *ptr, alloc_ctx_t *alloc_ctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	return arena_prof_tctx_get(tsdn, ptr, alloc_ctx);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+prof_tctx_set(tsdn_t *tsdn, const void *ptr, size_t usize,
+    alloc_ctx_t *alloc_ctx, prof_tctx_t *tctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	arena_prof_tctx_set(tsdn, ptr, usize, alloc_ctx, tctx);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+prof_tctx_reset(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+
+	arena_prof_tctx_reset(tsdn, ptr, tctx);
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+prof_sample_accum_update(tsd_t *tsd, size_t usize, bool update,
+    prof_tdata_t **tdata_out) {
+	prof_tdata_t *tdata;
+
+	cassert(config_prof);
+
+	tdata = prof_tdata_get(tsd, true);
+	if (unlikely((uintptr_t)tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)) {
+		tdata = NULL;
+	}
+
+	if (tdata_out != NULL) {
+		*tdata_out = tdata;
+	}
+
+	if (unlikely(tdata == NULL)) {
+		return true;
+	}
+
+	if (likely(tdata->bytes_until_sample >= usize)) {
+		if (update) {
+			tdata->bytes_until_sample -= usize;
+		}
+		return true;
+	} else {
+		if (tsd_reentrancy_level_get(tsd) > 0) {
+			return true;
+		}
+		/* Compute new sample threshold. */
+		if (update) {
+			prof_sample_threshold_update(tdata);
+		}
+		return !tdata->active;
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE prof_tctx_t *
+prof_alloc_prep(tsd_t *tsd, size_t usize, bool prof_active, bool update) {
+	prof_tctx_t *ret;
+	prof_tdata_t *tdata;
+	prof_bt_t bt;
+
+	assert(usize == sz_s2u(usize));
+
+	if (!prof_active || likely(prof_sample_accum_update(tsd, usize, update,
+	    &tdata))) {
+		ret = (prof_tctx_t *)(uintptr_t)1U;
+	} else {
+		bt_init(&bt, tdata->vec);
+		prof_backtrace(&bt);
+		ret = prof_lookup(tsd, &bt);
+	}
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+prof_malloc(tsdn_t *tsdn, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx,
+    prof_tctx_t *tctx) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+	assert(usize == isalloc(tsdn, ptr));
+
+	if (unlikely((uintptr_t)tctx > (uintptr_t)1U)) {
+		prof_malloc_sample_object(tsdn, ptr, usize, tctx);
+	} else {
+		prof_tctx_set(tsdn, ptr, usize, alloc_ctx,
+		    (prof_tctx_t *)(uintptr_t)1U);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+prof_realloc(tsd_t *tsd, const void *ptr, size_t usize, prof_tctx_t *tctx,
+    bool prof_active, bool updated, const void *old_ptr, size_t old_usize,
+    prof_tctx_t *old_tctx) {
+	bool sampled, old_sampled, moved;
+
+	cassert(config_prof);
+	assert(ptr != NULL || (uintptr_t)tctx <= (uintptr_t)1U);
+
+	if (prof_active && !updated && ptr != NULL) {
+		assert(usize == isalloc(tsd_tsdn(tsd), ptr));
+		if (prof_sample_accum_update(tsd, usize, true, NULL)) {
+			/*
+			 * Don't sample.  The usize passed to prof_alloc_prep()
+			 * was larger than what actually got allocated, so a
+			 * backtrace was captured for this allocation, even
+			 * though its actual usize was insufficient to cross the
+			 * sample threshold.
+			 */
+			prof_alloc_rollback(tsd, tctx, true);
+			tctx = (prof_tctx_t *)(uintptr_t)1U;
+		}
+	}
+
+	sampled = ((uintptr_t)tctx > (uintptr_t)1U);
+	old_sampled = ((uintptr_t)old_tctx > (uintptr_t)1U);
+	moved = (ptr != old_ptr);
+
+	if (unlikely(sampled)) {
+		prof_malloc_sample_object(tsd_tsdn(tsd), ptr, usize, tctx);
+	} else if (moved) {
+		prof_tctx_set(tsd_tsdn(tsd), ptr, usize, NULL,
+		    (prof_tctx_t *)(uintptr_t)1U);
+	} else if (unlikely(old_sampled)) {
+		/*
+		 * prof_tctx_set() would work for the !moved case as well, but
+		 * prof_tctx_reset() is slightly cheaper, and the proper thing
+		 * to do here in the presence of explicit knowledge re: moved
+		 * state.
+		 */
+		prof_tctx_reset(tsd_tsdn(tsd), ptr, tctx);
+	} else {
+		assert((uintptr_t)prof_tctx_get(tsd_tsdn(tsd), ptr, NULL) ==
+		    (uintptr_t)1U);
+	}
+
+	/*
+	 * The prof_free_sampled_object() call must come after the
+	 * prof_malloc_sample_object() call, because tctx and old_tctx may be
+	 * the same, in which case reversing the call order could cause the tctx
+	 * to be prematurely destroyed as a side effect of momentarily zeroed
+	 * counters.
+	 */
+	if (unlikely(old_sampled)) {
+		prof_free_sampled_object(tsd, old_usize, old_tctx);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+prof_free(tsd_t *tsd, const void *ptr, size_t usize, alloc_ctx_t *alloc_ctx) {
+	prof_tctx_t *tctx = prof_tctx_get(tsd_tsdn(tsd), ptr, alloc_ctx);
+
+	cassert(config_prof);
+	assert(usize == isalloc(tsd_tsdn(tsd), ptr));
+
+	if (unlikely((uintptr_t)tctx > (uintptr_t)1U)) {
+		prof_free_sampled_object(tsd, usize, tctx);
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_PROF_INLINES_B_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_structs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_structs.h
new file mode 100644
index 0000000000..0d58ae1005
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_structs.h
@@ -0,0 +1,201 @@
+#ifndef JEMALLOC_INTERNAL_PROF_STRUCTS_H
+#define JEMALLOC_INTERNAL_PROF_STRUCTS_H
+
+#include "jemalloc/internal/ckh.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/prng.h"
+#include "jemalloc/internal/rb.h"
+
+struct prof_bt_s {
+	/* Backtrace, stored as len program counters. */
+	void		**vec;
+	unsigned	len;
+};
+
+#ifdef JEMALLOC_PROF_LIBGCC
+/* Data structure passed to libgcc _Unwind_Backtrace() callback functions. */
+typedef struct {
+	prof_bt_t	*bt;
+	unsigned	max;
+} prof_unwind_data_t;
+#endif
+
+struct prof_accum_s {
+#ifndef JEMALLOC_ATOMIC_U64
+	malloc_mutex_t	mtx;
+	uint64_t	accumbytes;
+#else
+	atomic_u64_t	accumbytes;
+#endif
+};
+
+struct prof_cnt_s {
+	/* Profiling counters. */
+	uint64_t	curobjs;
+	uint64_t	curbytes;
+	uint64_t	accumobjs;
+	uint64_t	accumbytes;
+};
+
+typedef enum {
+	prof_tctx_state_initializing,
+	prof_tctx_state_nominal,
+	prof_tctx_state_dumping,
+	prof_tctx_state_purgatory /* Dumper must finish destroying. */
+} prof_tctx_state_t;
+
+struct prof_tctx_s {
+	/* Thread data for thread that performed the allocation. */
+	prof_tdata_t		*tdata;
+
+	/*
+	 * Copy of tdata->thr_{uid,discrim}, necessary because tdata may be
+	 * defunct during teardown.
+	 */
+	uint64_t		thr_uid;
+	uint64_t		thr_discrim;
+
+	/* Profiling counters, protected by tdata->lock. */
+	prof_cnt_t		cnts;
+
+	/* Associated global context. */
+	prof_gctx_t		*gctx;
+
+	/*
+	 * UID that distinguishes multiple tctx's created by the same thread,
+	 * but coexisting in gctx->tctxs.  There are two ways that such
+	 * coexistence can occur:
+	 * - A dumper thread can cause a tctx to be retained in the purgatory
+	 *   state.
+	 * - Although a single "producer" thread must create all tctx's which
+	 *   share the same thr_uid, multiple "consumers" can each concurrently
+	 *   execute portions of prof_tctx_destroy().  prof_tctx_destroy() only
+	 *   gets called once each time cnts.cur{objs,bytes} drop to 0, but this
+	 *   threshold can be hit again before the first consumer finishes
+	 *   executing prof_tctx_destroy().
+	 */
+	uint64_t		tctx_uid;
+
+	/* Linkage into gctx's tctxs. */
+	rb_node(prof_tctx_t)	tctx_link;
+
+	/*
+	 * True during prof_alloc_prep()..prof_malloc_sample_object(), prevents
+	 * sample vs destroy race.
+	 */
+	bool			prepared;
+
+	/* Current dump-related state, protected by gctx->lock. */
+	prof_tctx_state_t	state;
+
+	/*
+	 * Copy of cnts snapshotted during early dump phase, protected by
+	 * dump_mtx.
+	 */
+	prof_cnt_t		dump_cnts;
+};
+typedef rb_tree(prof_tctx_t) prof_tctx_tree_t;
+
+struct prof_gctx_s {
+	/* Protects nlimbo, cnt_summed, and tctxs. */
+	malloc_mutex_t		*lock;
+
+	/*
+	 * Number of threads that currently cause this gctx to be in a state of
+	 * limbo due to one of:
+	 *   - Initializing this gctx.
+	 *   - Initializing per thread counters associated with this gctx.
+	 *   - Preparing to destroy this gctx.
+	 *   - Dumping a heap profile that includes this gctx.
+	 * nlimbo must be 1 (single destroyer) in order to safely destroy the
+	 * gctx.
+	 */
+	unsigned		nlimbo;
+
+	/*
+	 * Tree of profile counters, one for each thread that has allocated in
+	 * this context.
+	 */
+	prof_tctx_tree_t	tctxs;
+
+	/* Linkage for tree of contexts to be dumped. */
+	rb_node(prof_gctx_t)	dump_link;
+
+	/* Temporary storage for summation during dump. */
+	prof_cnt_t		cnt_summed;
+
+	/* Associated backtrace. */
+	prof_bt_t		bt;
+
+	/* Backtrace vector, variable size, referred to by bt. */
+	void			*vec[1];
+};
+typedef rb_tree(prof_gctx_t) prof_gctx_tree_t;
+
+struct prof_tdata_s {
+	malloc_mutex_t		*lock;
+
+	/* Monotonically increasing unique thread identifier. */
+	uint64_t		thr_uid;
+
+	/*
+	 * Monotonically increasing discriminator among tdata structures
+	 * associated with the same thr_uid.
+	 */
+	uint64_t		thr_discrim;
+
+	/* Included in heap profile dumps if non-NULL. */
+	char			*thread_name;
+
+	bool			attached;
+	bool			expired;
+
+	rb_node(prof_tdata_t)	tdata_link;
+
+	/*
+	 * Counter used to initialize prof_tctx_t's tctx_uid.  No locking is
+	 * necessary when incrementing this field, because only one thread ever
+	 * does so.
+	 */
+	uint64_t		tctx_uid_next;
+
+	/*
+	 * Hash of (prof_bt_t *)-->(prof_tctx_t *).  Each thread tracks
+	 * backtraces for which it has non-zero allocation/deallocation counters
+	 * associated with thread-specific prof_tctx_t objects.  Other threads
+	 * may write to prof_tctx_t contents when freeing associated objects.
+	 */
+	ckh_t			bt2tctx;
+
+	/* Sampling state. */
+	uint64_t		prng_state;
+	uint64_t		bytes_until_sample;
+
+	/* State used to avoid dumping while operating on prof internals. */
+	bool			enq;
+	bool			enq_idump;
+	bool			enq_gdump;
+
+	/*
+	 * Set to true during an early dump phase for tdata's which are
+	 * currently being dumped.  New threads' tdata's have this initialized
+	 * to false so that they aren't accidentally included in later dump
+	 * phases.
+	 */
+	bool			dumping;
+
+	/*
+	 * True if profiling is active for this tdata's thread
+	 * (thread.prof.active mallctl).
+	 */
+	bool			active;
+
+	/* Temporary storage for summation during dump. */
+	prof_cnt_t		cnt_summed;
+
+	/* Backtrace vector, used for calls to prof_backtrace(). */
+	void			*vec[PROF_BT_MAX];
+};
+typedef rb_tree(prof_tdata_t) prof_tdata_tree_t;
+
+#endif /* JEMALLOC_INTERNAL_PROF_STRUCTS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_types.h
new file mode 100644
index 0000000000..1eff995ecf
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/prof_types.h
@@ -0,0 +1,56 @@
+#ifndef JEMALLOC_INTERNAL_PROF_TYPES_H
+#define JEMALLOC_INTERNAL_PROF_TYPES_H
+
+typedef struct prof_bt_s prof_bt_t;
+typedef struct prof_accum_s prof_accum_t;
+typedef struct prof_cnt_s prof_cnt_t;
+typedef struct prof_tctx_s prof_tctx_t;
+typedef struct prof_gctx_s prof_gctx_t;
+typedef struct prof_tdata_s prof_tdata_t;
+
+/* Option defaults. */
+#ifdef JEMALLOC_PROF
+#  define PROF_PREFIX_DEFAULT		"jeprof"
+#else
+#  define PROF_PREFIX_DEFAULT		""
+#endif
+#define LG_PROF_SAMPLE_DEFAULT		19
+#define LG_PROF_INTERVAL_DEFAULT	-1
+
+/*
+ * Hard limit on stack backtrace depth.  The version of prof_backtrace() that
+ * is based on __builtin_return_address() necessarily has a hard-coded number
+ * of backtrace frame handlers, and should be kept in sync with this setting.
+ */
+#define PROF_BT_MAX			128
+
+/* Initial hash table size. */
+#define PROF_CKH_MINITEMS		64
+
+/* Size of memory buffer to use when writing dump files. */
+#define PROF_DUMP_BUFSIZE		65536
+
+/* Size of stack-allocated buffer used by prof_printf(). */
+#define PROF_PRINTF_BUFSIZE		128
+
+/*
+ * Number of mutexes shared among all gctx's.  No space is allocated for these
+ * unless profiling is enabled, so it's okay to over-provision.
+ */
+#define PROF_NCTX_LOCKS			1024
+
+/*
+ * Number of mutexes shared among all tdata's.  No space is allocated for these
+ * unless profiling is enabled, so it's okay to over-provision.
+ */
+#define PROF_NTDATA_LOCKS		256
+
+/*
+ * prof_tdata pointers close to NULL are used to encode state information that
+ * is used for cleaning up during thread shutdown.
+ */
+#define PROF_TDATA_STATE_REINCARNATED	((prof_tdata_t *)(uintptr_t)1)
+#define PROF_TDATA_STATE_PURGATORY	((prof_tdata_t *)(uintptr_t)2)
+#define PROF_TDATA_STATE_MAX		PROF_TDATA_STATE_PURGATORY
+
+#endif /* JEMALLOC_INTERNAL_PROF_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ql.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ql.h
index f70c5f6f39..8029040771 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ql.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ql.h
@@ -1,61 +1,64 @@
-/*
- * List definitions.
- */
-#define	ql_head(a_type)							\
+#ifndef JEMALLOC_INTERNAL_QL_H
+#define JEMALLOC_INTERNAL_QL_H
+
+#include "jemalloc/internal/qr.h"
+
+/* List definitions. */
+#define ql_head(a_type)							\
 struct {								\
 	a_type *qlh_first;						\
 }
 
-#define	ql_head_initializer(a_head) {NULL}
+#define ql_head_initializer(a_head) {NULL}
 
-#define	ql_elm(a_type)	qr(a_type)
+#define ql_elm(a_type)	qr(a_type)
 
 /* List functions. */
-#define	ql_new(a_head) do {						\
+#define ql_new(a_head) do {						\
 	(a_head)->qlh_first = NULL;					\
 } while (0)
 
-#define	ql_elm_new(a_elm, a_field) qr_new((a_elm), a_field)
+#define ql_elm_new(a_elm, a_field) qr_new((a_elm), a_field)
 
-#define	ql_first(a_head) ((a_head)->qlh_first)
+#define ql_first(a_head) ((a_head)->qlh_first)
 
-#define	ql_last(a_head, a_field)					\
+#define ql_last(a_head, a_field)					\
 	((ql_first(a_head) != NULL)					\
 	    ? qr_prev(ql_first(a_head), a_field) : NULL)
 
-#define	ql_next(a_head, a_elm, a_field)					\
+#define ql_next(a_head, a_elm, a_field)					\
 	((ql_last(a_head, a_field) != (a_elm))				\
 	    ? qr_next((a_elm), a_field)	: NULL)
 
-#define	ql_prev(a_head, a_elm, a_field)					\
+#define ql_prev(a_head, a_elm, a_field)					\
 	((ql_first(a_head) != (a_elm)) ? qr_prev((a_elm), a_field)	\
 				       : NULL)
 
-#define	ql_before_insert(a_head, a_qlelm, a_elm, a_field) do {		\
+#define ql_before_insert(a_head, a_qlelm, a_elm, a_field) do {		\
 	qr_before_insert((a_qlelm), (a_elm), a_field);			\
 	if (ql_first(a_head) == (a_qlelm)) {				\
 		ql_first(a_head) = (a_elm);				\
 	}								\
 } while (0)
 
-#define	ql_after_insert(a_qlelm, a_elm, a_field)			\
+#define ql_after_insert(a_qlelm, a_elm, a_field)			\
 	qr_after_insert((a_qlelm), (a_elm), a_field)
 
-#define	ql_head_insert(a_head, a_elm, a_field) do {			\
+#define ql_head_insert(a_head, a_elm, a_field) do {			\
 	if (ql_first(a_head) != NULL) {					\
 		qr_before_insert(ql_first(a_head), (a_elm), a_field);	\
 	}								\
 	ql_first(a_head) = (a_elm);					\
 } while (0)
 
-#define	ql_tail_insert(a_head, a_elm, a_field) do {			\
+#define ql_tail_insert(a_head, a_elm, a_field) do {			\
 	if (ql_first(a_head) != NULL) {					\
 		qr_before_insert(ql_first(a_head), (a_elm), a_field);	\
 	}								\
 	ql_first(a_head) = qr_next((a_elm), a_field);			\
 } while (0)
 
-#define	ql_remove(a_head, a_elm, a_field) do {				\
+#define ql_remove(a_head, a_elm, a_field) do {				\
 	if (ql_first(a_head) == (a_elm)) {				\
 		ql_first(a_head) = qr_next(ql_first(a_head), a_field);	\
 	}								\
@@ -66,18 +69,20 @@ struct {								\
 	}								\
 } while (0)
 
-#define	ql_head_remove(a_head, a_type, a_field) do {			\
+#define ql_head_remove(a_head, a_type, a_field) do {			\
 	a_type *t = ql_first(a_head);					\
 	ql_remove((a_head), t, a_field);				\
 } while (0)
 
-#define	ql_tail_remove(a_head, a_type, a_field) do {			\
+#define ql_tail_remove(a_head, a_type, a_field) do {			\
 	a_type *t = ql_last(a_head, a_field);				\
 	ql_remove((a_head), t, a_field);				\
 } while (0)
 
-#define	ql_foreach(a_var, a_head, a_field)				\
+#define ql_foreach(a_var, a_head, a_field)				\
 	qr_foreach((a_var), ql_first(a_head), a_field)
 
-#define	ql_reverse_foreach(a_var, a_head, a_field)			\
+#define ql_reverse_foreach(a_var, a_head, a_field)			\
 	qr_reverse_foreach((a_var), ql_first(a_head), a_field)
+
+#endif /* JEMALLOC_INTERNAL_QL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/qr.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/qr.h
index 602944b9b4..1e1056b386 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/qr.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/qr.h
@@ -1,38 +1,39 @@
+#ifndef JEMALLOC_INTERNAL_QR_H
+#define JEMALLOC_INTERNAL_QR_H
+
 /* Ring definitions. */
-#define	qr(a_type)							\
+#define qr(a_type)							\
 struct {								\
 	a_type	*qre_next;						\
 	a_type	*qre_prev;						\
 }
 
 /* Ring functions. */
-#define	qr_new(a_qr, a_field) do {					\
+#define qr_new(a_qr, a_field) do {					\
 	(a_qr)->a_field.qre_next = (a_qr);				\
 	(a_qr)->a_field.qre_prev = (a_qr);				\
 } while (0)
 
-#define	qr_next(a_qr, a_field) ((a_qr)->a_field.qre_next)
+#define qr_next(a_qr, a_field) ((a_qr)->a_field.qre_next)
 
-#define	qr_prev(a_qr, a_field) ((a_qr)->a_field.qre_prev)
+#define qr_prev(a_qr, a_field) ((a_qr)->a_field.qre_prev)
 
-#define	qr_before_insert(a_qrelm, a_qr, a_field) do {			\
+#define qr_before_insert(a_qrelm, a_qr, a_field) do {			\
 	(a_qr)->a_field.qre_prev = (a_qrelm)->a_field.qre_prev;		\
 	(a_qr)->a_field.qre_next = (a_qrelm);				\
 	(a_qr)->a_field.qre_prev->a_field.qre_next = (a_qr);		\
 	(a_qrelm)->a_field.qre_prev = (a_qr);				\
 } while (0)
 
-#define	qr_after_insert(a_qrelm, a_qr, a_field)				\
-    do									\
-    {									\
+#define qr_after_insert(a_qrelm, a_qr, a_field) do {			\
 	(a_qr)->a_field.qre_next = (a_qrelm)->a_field.qre_next;		\
 	(a_qr)->a_field.qre_prev = (a_qrelm);				\
 	(a_qr)->a_field.qre_next->a_field.qre_prev = (a_qr);		\
 	(a_qrelm)->a_field.qre_next = (a_qr);				\
-    } while (0)
+} while (0)
 
-#define	qr_meld(a_qr_a, a_qr_b, a_field) do {				\
-	void *t;							\
+#define qr_meld(a_qr_a, a_qr_b, a_type, a_field) do {			\
+	a_type *t;							\
 	(a_qr_a)->a_field.qre_prev->a_field.qre_next = (a_qr_b);	\
 	(a_qr_b)->a_field.qre_prev->a_field.qre_next = (a_qr_a);	\
 	t = (a_qr_a)->a_field.qre_prev;					\
@@ -40,12 +41,14 @@ struct {								\
 	(a_qr_b)->a_field.qre_prev = t;					\
 } while (0)
 
-/* qr_meld() and qr_split() are functionally equivalent, so there's no need to
- * have two copies of the code. */
-#define	qr_split(a_qr_a, a_qr_b, a_field)				\
-	qr_meld((a_qr_a), (a_qr_b), a_field)
+/*
+ * qr_meld() and qr_split() are functionally equivalent, so there's no need to
+ * have two copies of the code.
+ */
+#define qr_split(a_qr_a, a_qr_b, a_type, a_field)			\
+	qr_meld((a_qr_a), (a_qr_b), a_type, a_field)
 
-#define	qr_remove(a_qr, a_field) do {					\
+#define qr_remove(a_qr, a_field) do {					\
 	(a_qr)->a_field.qre_prev->a_field.qre_next			\
 	    = (a_qr)->a_field.qre_next;					\
 	(a_qr)->a_field.qre_next->a_field.qre_prev			\
@@ -54,14 +57,16 @@ struct {								\
 	(a_qr)->a_field.qre_prev = (a_qr);				\
 } while (0)
 
-#define	qr_foreach(var, a_qr, a_field)					\
+#define qr_foreach(var, a_qr, a_field)					\
 	for ((var) = (a_qr);						\
 	    (var) != NULL;						\
 	    (var) = (((var)->a_field.qre_next != (a_qr))		\
 	    ? (var)->a_field.qre_next : NULL))
 
-#define	qr_reverse_foreach(var, a_qr, a_field)				\
+#define qr_reverse_foreach(var, a_qr, a_field)				\
 	for ((var) = ((a_qr) != NULL) ? qr_prev(a_qr, a_field) : NULL;	\
 	    (var) != NULL;						\
 	    (var) = (((var) != (a_qr))					\
 	    ? (var)->a_field.qre_prev : NULL))
+
+#endif /* JEMALLOC_INTERNAL_QR_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rb.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rb.h
index 423802eb2d..47fa5ca99b 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rb.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rb.h
@@ -20,17 +20,21 @@
  */
 
 #ifndef RB_H_
-#define	RB_H_
+#define RB_H_
+
+#ifndef __PGI
+#define RB_COMPACT
+#endif
 
 #ifdef RB_COMPACT
 /* Node structure. */
-#define	rb_node(a_type)							\
+#define rb_node(a_type)							\
 struct {								\
     a_type *rbn_left;							\
     a_type *rbn_right_red;						\
 }
 #else
-#define	rb_node(a_type)							\
+#define rb_node(a_type)							\
 struct {								\
     a_type *rbn_left;							\
     a_type *rbn_right;							\
@@ -39,111 +43,116 @@ struct {								\
 #endif
 
 /* Root structure. */
-#define	rb_tree(a_type)							\
+#define rb_tree(a_type)							\
 struct {								\
     a_type *rbt_root;							\
-    a_type rbt_nil;							\
 }
 
 /* Left accessors. */
-#define	rbtn_left_get(a_type, a_field, a_node)				\
+#define rbtn_left_get(a_type, a_field, a_node)				\
     ((a_node)->a_field.rbn_left)
-#define	rbtn_left_set(a_type, a_field, a_node, a_left) do {		\
+#define rbtn_left_set(a_type, a_field, a_node, a_left) do {		\
     (a_node)->a_field.rbn_left = a_left;				\
 } while (0)
 
 #ifdef RB_COMPACT
 /* Right accessors. */
-#define	rbtn_right_get(a_type, a_field, a_node)				\
+#define rbtn_right_get(a_type, a_field, a_node)				\
     ((a_type *) (((intptr_t) (a_node)->a_field.rbn_right_red)		\
       & ((ssize_t)-2)))
-#define	rbtn_right_set(a_type, a_field, a_node, a_right) do {		\
+#define rbtn_right_set(a_type, a_field, a_node, a_right) do {		\
     (a_node)->a_field.rbn_right_red = (a_type *) (((uintptr_t) a_right)	\
       | (((uintptr_t) (a_node)->a_field.rbn_right_red) & ((size_t)1)));	\
 } while (0)
 
 /* Color accessors. */
-#define	rbtn_red_get(a_type, a_field, a_node)				\
+#define rbtn_red_get(a_type, a_field, a_node)				\
     ((bool) (((uintptr_t) (a_node)->a_field.rbn_right_red)		\
       & ((size_t)1)))
-#define	rbtn_color_set(a_type, a_field, a_node, a_red) do {		\
+#define rbtn_color_set(a_type, a_field, a_node, a_red) do {		\
     (a_node)->a_field.rbn_right_red = (a_type *) ((((intptr_t)		\
       (a_node)->a_field.rbn_right_red) & ((ssize_t)-2))			\
       | ((ssize_t)a_red));						\
 } while (0)
-#define	rbtn_red_set(a_type, a_field, a_node) do {			\
+#define rbtn_red_set(a_type, a_field, a_node) do {			\
     (a_node)->a_field.rbn_right_red = (a_type *) (((uintptr_t)		\
       (a_node)->a_field.rbn_right_red) | ((size_t)1));			\
 } while (0)
-#define	rbtn_black_set(a_type, a_field, a_node) do {			\
+#define rbtn_black_set(a_type, a_field, a_node) do {			\
     (a_node)->a_field.rbn_right_red = (a_type *) (((intptr_t)		\
       (a_node)->a_field.rbn_right_red) & ((ssize_t)-2));		\
 } while (0)
+
+/* Node initializer. */
+#define rbt_node_new(a_type, a_field, a_rbt, a_node) do {		\
+    /* Bookkeeping bit cannot be used by node pointer. */		\
+    assert(((uintptr_t)(a_node) & 0x1) == 0);				\
+    rbtn_left_set(a_type, a_field, (a_node), NULL);	\
+    rbtn_right_set(a_type, a_field, (a_node), NULL);	\
+    rbtn_red_set(a_type, a_field, (a_node));				\
+} while (0)
 #else
 /* Right accessors. */
-#define	rbtn_right_get(a_type, a_field, a_node)				\
+#define rbtn_right_get(a_type, a_field, a_node)				\
     ((a_node)->a_field.rbn_right)
-#define	rbtn_right_set(a_type, a_field, a_node, a_right) do {		\
+#define rbtn_right_set(a_type, a_field, a_node, a_right) do {		\
     (a_node)->a_field.rbn_right = a_right;				\
 } while (0)
 
 /* Color accessors. */
-#define	rbtn_red_get(a_type, a_field, a_node)				\
+#define rbtn_red_get(a_type, a_field, a_node)				\
     ((a_node)->a_field.rbn_red)
-#define	rbtn_color_set(a_type, a_field, a_node, a_red) do {		\
+#define rbtn_color_set(a_type, a_field, a_node, a_red) do {		\
     (a_node)->a_field.rbn_red = (a_red);				\
 } while (0)
-#define	rbtn_red_set(a_type, a_field, a_node) do {			\
+#define rbtn_red_set(a_type, a_field, a_node) do {			\
     (a_node)->a_field.rbn_red = true;					\
 } while (0)
-#define	rbtn_black_set(a_type, a_field, a_node) do {			\
+#define rbtn_black_set(a_type, a_field, a_node) do {			\
     (a_node)->a_field.rbn_red = false;					\
 } while (0)
-#endif
 
 /* Node initializer. */
-#define	rbt_node_new(a_type, a_field, a_rbt, a_node) do {		\
-    rbtn_left_set(a_type, a_field, (a_node), &(a_rbt)->rbt_nil);	\
-    rbtn_right_set(a_type, a_field, (a_node), &(a_rbt)->rbt_nil);	\
+#define rbt_node_new(a_type, a_field, a_rbt, a_node) do {		\
+    rbtn_left_set(a_type, a_field, (a_node), NULL);	\
+    rbtn_right_set(a_type, a_field, (a_node), NULL);	\
     rbtn_red_set(a_type, a_field, (a_node));				\
 } while (0)
+#endif
 
 /* Tree initializer. */
-#define	rb_new(a_type, a_field, a_rbt) do {				\
-    (a_rbt)->rbt_root = &(a_rbt)->rbt_nil;				\
-    rbt_node_new(a_type, a_field, a_rbt, &(a_rbt)->rbt_nil);		\
-    rbtn_black_set(a_type, a_field, &(a_rbt)->rbt_nil);			\
+#define rb_new(a_type, a_field, a_rbt) do {				\
+    (a_rbt)->rbt_root = NULL;						\
 } while (0)
 
 /* Internal utility macros. */
-#define	rbtn_first(a_type, a_field, a_rbt, a_root, r_node) do {		\
+#define rbtn_first(a_type, a_field, a_rbt, a_root, r_node) do {		\
     (r_node) = (a_root);						\
-    if ((r_node) != &(a_rbt)->rbt_nil) {				\
+    if ((r_node) != NULL) {						\
 	for (;								\
-	  rbtn_left_get(a_type, a_field, (r_node)) != &(a_rbt)->rbt_nil;\
+	  rbtn_left_get(a_type, a_field, (r_node)) != NULL;		\
 	  (r_node) = rbtn_left_get(a_type, a_field, (r_node))) {	\
 	}								\
     }									\
 } while (0)
 
-#define	rbtn_last(a_type, a_field, a_rbt, a_root, r_node) do {		\
+#define rbtn_last(a_type, a_field, a_rbt, a_root, r_node) do {		\
     (r_node) = (a_root);						\
-    if ((r_node) != &(a_rbt)->rbt_nil) {				\
-	for (; rbtn_right_get(a_type, a_field, (r_node)) !=		\
-	  &(a_rbt)->rbt_nil; (r_node) = rbtn_right_get(a_type, a_field,	\
-	  (r_node))) {							\
+    if ((r_node) != NULL) {						\
+	for (; rbtn_right_get(a_type, a_field, (r_node)) != NULL;	\
+	  (r_node) = rbtn_right_get(a_type, a_field, (r_node))) {	\
 	}								\
     }									\
 } while (0)
 
-#define	rbtn_rotate_left(a_type, a_field, a_node, r_node) do {		\
+#define rbtn_rotate_left(a_type, a_field, a_node, r_node) do {		\
     (r_node) = rbtn_right_get(a_type, a_field, (a_node));		\
     rbtn_right_set(a_type, a_field, (a_node),				\
       rbtn_left_get(a_type, a_field, (r_node)));			\
     rbtn_left_set(a_type, a_field, (r_node), (a_node));			\
 } while (0)
 
-#define	rbtn_rotate_right(a_type, a_field, a_node, r_node) do {		\
+#define rbtn_rotate_right(a_type, a_field, a_node, r_node) do {		\
     (r_node) = rbtn_left_get(a_type, a_field, (a_node));		\
     rbtn_left_set(a_type, a_field, (a_node),				\
       rbtn_right_get(a_type, a_field, (r_node)));			\
@@ -155,9 +164,11 @@ struct {								\
  * functions generated by an equivalently parameterized call to rb_gen().
  */
 
-#define	rb_proto(a_attr, a_prefix, a_rbt_type, a_type)			\
+#define rb_proto(a_attr, a_prefix, a_rbt_type, a_type)			\
 a_attr void								\
 a_prefix##new(a_rbt_type *rbtree);					\
+a_attr bool								\
+a_prefix##empty(a_rbt_type *rbtree);					\
 a_attr a_type *								\
 a_prefix##first(a_rbt_type *rbtree);					\
 a_attr a_type *								\
@@ -167,11 +178,11 @@ a_prefix##next(a_rbt_type *rbtree, a_type *node);			\
 a_attr a_type *								\
 a_prefix##prev(a_rbt_type *rbtree, a_type *node);			\
 a_attr a_type *								\
-a_prefix##search(a_rbt_type *rbtree, a_type *key);			\
+a_prefix##search(a_rbt_type *rbtree, const a_type *key);		\
 a_attr a_type *								\
-a_prefix##nsearch(a_rbt_type *rbtree, a_type *key);			\
+a_prefix##nsearch(a_rbt_type *rbtree, const a_type *key);		\
 a_attr a_type *								\
-a_prefix##psearch(a_rbt_type *rbtree, a_type *key);			\
+a_prefix##psearch(a_rbt_type *rbtree, const a_type *key);		\
 a_attr void								\
 a_prefix##insert(a_rbt_type *rbtree, a_type *node);			\
 a_attr void								\
@@ -181,7 +192,10 @@ a_prefix##iter(a_rbt_type *rbtree, a_type *start, a_type *(*cb)(	\
   a_rbt_type *, a_type *, void *), void *arg);				\
 a_attr a_type *								\
 a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
-  a_type *(*cb)(a_rbt_type *, a_type *, void *), void *arg);
+  a_type *(*cb)(a_rbt_type *, a_type *, void *), void *arg);		\
+a_attr void								\
+a_prefix##destroy(a_rbt_type *rbtree, void (*cb)(a_type *, void *),	\
+  void *arg);
 
 /*
  * The rb_gen() macro generates a type-specific red-black tree implementation,
@@ -198,7 +212,7 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
  *                 int (a_cmp *)(a_type *a_node, a_type *a_other);
  *                                       ^^^^^^
  *                                    or a_key
- *               Interpretation of comparision function return values:
+ *               Interpretation of comparison function return values:
  *                 -1 : a_node <  a_other
  *                  0 : a_node == a_other
  *                  1 : a_node >  a_other
@@ -224,6 +238,13 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
  *       Args:
  *         tree: Pointer to an uninitialized red-black tree object.
  *
+ *   static bool
+ *   ex_empty(ex_t *tree);
+ *       Description: Determine whether tree is empty.
+ *       Args:
+ *         tree: Pointer to an initialized red-black tree object.
+ *       Ret: True if tree is empty, false otherwise.
+ *
  *   static ex_node_t *
  *   ex_first(ex_t *tree);
  *   static ex_node_t *
@@ -245,7 +266,7 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
  *            last/first.
  *
  *   static ex_node_t *
- *   ex_search(ex_t *tree, ex_node_t *key);
+ *   ex_search(ex_t *tree, const ex_node_t *key);
  *       Description: Search for node that matches key.
  *       Args:
  *         tree: Pointer to an initialized red-black tree object.
@@ -253,9 +274,9 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
  *       Ret: Node in tree that matches key, or NULL if no match.
  *
  *   static ex_node_t *
- *   ex_nsearch(ex_t *tree, ex_node_t *key);
+ *   ex_nsearch(ex_t *tree, const ex_node_t *key);
  *   static ex_node_t *
- *   ex_psearch(ex_t *tree, ex_node_t *key);
+ *   ex_psearch(ex_t *tree, const ex_node_t *key);
  *       Description: Search for node that matches key.  If no match is found,
  *                    return what would be key's successor/predecessor, were
  *                    key in tree.
@@ -303,40 +324,52 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
  *         arg  : Opaque pointer passed to cb().
  *       Ret: NULL if iteration completed, or the non-NULL callback return value
  *            that caused termination of the iteration.
+ *
+ *   static void
+ *   ex_destroy(ex_t *tree, void (*cb)(ex_node_t *, void *), void *arg);
+ *       Description: Iterate over the tree with post-order traversal, remove
+ *                    each node, and run the callback if non-null.  This is
+ *                    used for destroying a tree without paying the cost to
+ *                    rebalance it.  The tree must not be otherwise altered
+ *                    during traversal.
+ *       Args:
+ *         tree: Pointer to an initialized red-black tree object.
+ *         cb  : Callback function, which, if non-null, is called for each node
+ *               during iteration.  There is no way to stop iteration once it
+ *               has begun.
+ *         arg : Opaque pointer passed to cb().
  */
-#define	rb_gen(a_attr, a_prefix, a_rbt_type, a_type, a_field, a_cmp)	\
+#define rb_gen(a_attr, a_prefix, a_rbt_type, a_type, a_field, a_cmp)	\
 a_attr void								\
 a_prefix##new(a_rbt_type *rbtree) {					\
     rb_new(a_type, a_field, rbtree);					\
 }									\
+a_attr bool								\
+a_prefix##empty(a_rbt_type *rbtree) {					\
+    return (rbtree->rbt_root == NULL);					\
+}									\
 a_attr a_type *								\
 a_prefix##first(a_rbt_type *rbtree) {					\
     a_type *ret;							\
     rbtn_first(a_type, a_field, rbtree, rbtree->rbt_root, ret);		\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = NULL;							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
 a_prefix##last(a_rbt_type *rbtree) {					\
     a_type *ret;							\
     rbtn_last(a_type, a_field, rbtree, rbtree->rbt_root, ret);		\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = NULL;							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
 a_prefix##next(a_rbt_type *rbtree, a_type *node) {			\
     a_type *ret;							\
-    if (rbtn_right_get(a_type, a_field, node) != &rbtree->rbt_nil) {	\
+    if (rbtn_right_get(a_type, a_field, node) != NULL) {		\
 	rbtn_first(a_type, a_field, rbtree, rbtn_right_get(a_type,	\
 	  a_field, node), ret);						\
     } else {								\
 	a_type *tnode = rbtree->rbt_root;				\
-	assert(tnode != &rbtree->rbt_nil);				\
-	ret = &rbtree->rbt_nil;						\
+	assert(tnode != NULL);						\
+	ret = NULL;							\
 	while (true) {							\
 	    int cmp = (a_cmp)(node, tnode);				\
 	    if (cmp < 0) {						\
@@ -347,24 +380,21 @@ a_prefix##next(a_rbt_type *rbtree, a_type *node) {			\
 	    } else {							\
 		break;							\
 	    }								\
-	    assert(tnode != &rbtree->rbt_nil);				\
+	    assert(tnode != NULL);					\
 	}								\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = (NULL);							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
 a_prefix##prev(a_rbt_type *rbtree, a_type *node) {			\
     a_type *ret;							\
-    if (rbtn_left_get(a_type, a_field, node) != &rbtree->rbt_nil) {	\
+    if (rbtn_left_get(a_type, a_field, node) != NULL) {			\
 	rbtn_last(a_type, a_field, rbtree, rbtn_left_get(a_type,	\
 	  a_field, node), ret);						\
     } else {								\
 	a_type *tnode = rbtree->rbt_root;				\
-	assert(tnode != &rbtree->rbt_nil);				\
-	ret = &rbtree->rbt_nil;						\
+	assert(tnode != NULL);						\
+	ret = NULL;							\
 	while (true) {							\
 	    int cmp = (a_cmp)(node, tnode);				\
 	    if (cmp < 0) {						\
@@ -375,20 +405,17 @@ a_prefix##prev(a_rbt_type *rbtree, a_type *node) {			\
 	    } else {							\
 		break;							\
 	    }								\
-	    assert(tnode != &rbtree->rbt_nil);				\
+	    assert(tnode != NULL);					\
 	}								\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = (NULL);							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
-a_prefix##search(a_rbt_type *rbtree, a_type *key) {			\
+a_prefix##search(a_rbt_type *rbtree, const a_type *key) {		\
     a_type *ret;							\
     int cmp;								\
     ret = rbtree->rbt_root;						\
-    while (ret != &rbtree->rbt_nil					\
+    while (ret != NULL							\
       && (cmp = (a_cmp)(key, ret)) != 0) {				\
 	if (cmp < 0) {							\
 	    ret = rbtn_left_get(a_type, a_field, ret);			\
@@ -396,17 +423,14 @@ a_prefix##search(a_rbt_type *rbtree, a_type *key) {			\
 	    ret = rbtn_right_get(a_type, a_field, ret);			\
 	}								\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = (NULL);							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
-a_prefix##nsearch(a_rbt_type *rbtree, a_type *key) {			\
+a_prefix##nsearch(a_rbt_type *rbtree, const a_type *key) {		\
     a_type *ret;							\
     a_type *tnode = rbtree->rbt_root;					\
-    ret = &rbtree->rbt_nil;						\
-    while (tnode != &rbtree->rbt_nil) {					\
+    ret = NULL;								\
+    while (tnode != NULL) {						\
 	int cmp = (a_cmp)(key, tnode);					\
 	if (cmp < 0) {							\
 	    ret = tnode;						\
@@ -418,17 +442,14 @@ a_prefix##nsearch(a_rbt_type *rbtree, a_type *key) {			\
 	    break;							\
 	}								\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = (NULL);							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
-a_prefix##psearch(a_rbt_type *rbtree, a_type *key) {			\
+a_prefix##psearch(a_rbt_type *rbtree, const a_type *key) {		\
     a_type *ret;							\
     a_type *tnode = rbtree->rbt_root;					\
-    ret = &rbtree->rbt_nil;						\
-    while (tnode != &rbtree->rbt_nil) {					\
+    ret = NULL;								\
+    while (tnode != NULL) {						\
 	int cmp = (a_cmp)(key, tnode);					\
 	if (cmp < 0) {							\
 	    tnode = rbtn_left_get(a_type, a_field, tnode);		\
@@ -440,10 +461,7 @@ a_prefix##psearch(a_rbt_type *rbtree, a_type *key) {			\
 	    break;							\
 	}								\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = (NULL);							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr void								\
 a_prefix##insert(a_rbt_type *rbtree, a_type *node) {			\
@@ -454,7 +472,7 @@ a_prefix##insert(a_rbt_type *rbtree, a_type *node) {			\
     rbt_node_new(a_type, a_field, rbtree, node);			\
     /* Wind. */								\
     path->node = rbtree->rbt_root;					\
-    for (pathp = path; pathp->node != &rbtree->rbt_nil; pathp++) {	\
+    for (pathp = path; pathp->node != NULL; pathp++) {			\
 	int cmp = pathp->cmp = a_cmp(node, pathp->node);		\
 	assert(cmp != 0);						\
 	if (cmp < 0) {							\
@@ -474,7 +492,8 @@ a_prefix##insert(a_rbt_type *rbtree, a_type *node) {			\
 	    rbtn_left_set(a_type, a_field, cnode, left);		\
 	    if (rbtn_red_get(a_type, a_field, left)) {			\
 		a_type *leftleft = rbtn_left_get(a_type, a_field, left);\
-		if (rbtn_red_get(a_type, a_field, leftleft)) {		\
+		if (leftleft != NULL && rbtn_red_get(a_type, a_field,	\
+		  leftleft)) {						\
 		    /* Fix up 4-node. */				\
 		    a_type *tnode;					\
 		    rbtn_black_set(a_type, a_field, leftleft);		\
@@ -489,7 +508,8 @@ a_prefix##insert(a_rbt_type *rbtree, a_type *node) {			\
 	    rbtn_right_set(a_type, a_field, cnode, right);		\
 	    if (rbtn_red_get(a_type, a_field, right)) {			\
 		a_type *left = rbtn_left_get(a_type, a_field, cnode);	\
-		if (rbtn_red_get(a_type, a_field, left)) {		\
+		if (left != NULL && rbtn_red_get(a_type, a_field,	\
+		  left)) {						\
 		    /* Split 4-node. */					\
 		    rbtn_black_set(a_type, a_field, left);		\
 		    rbtn_black_set(a_type, a_field, right);		\
@@ -522,7 +542,7 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
     /* Wind. */								\
     nodep = NULL; /* Silence compiler warning. */			\
     path->node = rbtree->rbt_root;					\
-    for (pathp = path; pathp->node != &rbtree->rbt_nil; pathp++) {	\
+    for (pathp = path; pathp->node != NULL; pathp++) {			\
 	int cmp = pathp->cmp = a_cmp(node, pathp->node);		\
 	if (cmp < 0) {							\
 	    pathp[1].node = rbtn_left_get(a_type, a_field,		\
@@ -534,8 +554,7 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 	        /* Find node's successor, in preparation for swap. */	\
 		pathp->cmp = 1;						\
 		nodep = pathp;						\
-		for (pathp++; pathp->node != &rbtree->rbt_nil;		\
-		  pathp++) {						\
+		for (pathp++; pathp->node != NULL; pathp++) {		\
 		    pathp->cmp = -1;					\
 		    pathp[1].node = rbtn_left_get(a_type, a_field,	\
 		      pathp->node);					\
@@ -577,10 +596,10 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 	}								\
     } else {								\
 	a_type *left = rbtn_left_get(a_type, a_field, node);		\
-	if (left != &rbtree->rbt_nil) {					\
+	if (left != NULL) {						\
 	    /* node has no successor, but it has a left child.        */\
 	    /* Splice node out, without losing the left child.        */\
-	    assert(rbtn_red_get(a_type, a_field, node) == false);	\
+	    assert(!rbtn_red_get(a_type, a_field, node));		\
 	    assert(rbtn_red_get(a_type, a_field, left));		\
 	    rbtn_black_set(a_type, a_field, left);			\
 	    if (pathp == path) {					\
@@ -597,34 +616,32 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 	    return;							\
 	} else if (pathp == path) {					\
 	    /* The tree only contained one node. */			\
-	    rbtree->rbt_root = &rbtree->rbt_nil;			\
+	    rbtree->rbt_root = NULL;					\
 	    return;							\
 	}								\
     }									\
     if (rbtn_red_get(a_type, a_field, pathp->node)) {			\
 	/* Prune red node, which requires no fixup. */			\
 	assert(pathp[-1].cmp < 0);					\
-	rbtn_left_set(a_type, a_field, pathp[-1].node,			\
-	  &rbtree->rbt_nil);						\
+	rbtn_left_set(a_type, a_field, pathp[-1].node, NULL);		\
 	return;								\
     }									\
     /* The node to be pruned is black, so unwind until balance is     */\
     /* restored.                                                      */\
-    pathp->node = &rbtree->rbt_nil;					\
+    pathp->node = NULL;							\
     for (pathp--; (uintptr_t)pathp >= (uintptr_t)path; pathp--) {	\
 	assert(pathp->cmp != 0);					\
 	if (pathp->cmp < 0) {						\
 	    rbtn_left_set(a_type, a_field, pathp->node,			\
 	      pathp[1].node);						\
-	    assert(rbtn_red_get(a_type, a_field, pathp[1].node)		\
-	      == false);						\
 	    if (rbtn_red_get(a_type, a_field, pathp->node)) {		\
 		a_type *right = rbtn_right_get(a_type, a_field,		\
 		  pathp->node);						\
 		a_type *rightleft = rbtn_left_get(a_type, a_field,	\
 		  right);						\
 		a_type *tnode;						\
-		if (rbtn_red_get(a_type, a_field, rightleft)) {		\
+		if (rightleft != NULL && rbtn_red_get(a_type, a_field,	\
+		  rightleft)) {						\
 		    /* In the following diagrams, ||, //, and \\      */\
 		    /* indicate the path to the removed node.         */\
 		    /*                                                */\
@@ -667,7 +684,8 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		  pathp->node);						\
 		a_type *rightleft = rbtn_left_get(a_type, a_field,	\
 		  right);						\
-		if (rbtn_red_get(a_type, a_field, rightleft)) {		\
+		if (rightleft != NULL && rbtn_red_get(a_type, a_field,	\
+		  rightleft)) {						\
 		    /*      ||                                        */\
 		    /*    pathp(b)                                    */\
 		    /*  //        \                                   */\
@@ -681,7 +699,7 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		    rbtn_rotate_left(a_type, a_field, pathp->node,	\
 		      tnode);						\
 		    /* Balance restored, but rotation modified        */\
-		    /* subree root, which may actually be the tree    */\
+		    /* subtree root, which may actually be the tree   */\
 		    /* root.                                          */\
 		    if (pathp == path) {				\
 			/* Set root. */					\
@@ -721,7 +739,8 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		  left);						\
 		a_type *leftrightleft = rbtn_left_get(a_type, a_field,	\
 		  leftright);						\
-		if (rbtn_red_get(a_type, a_field, leftrightleft)) {	\
+		if (leftrightleft != NULL && rbtn_red_get(a_type,	\
+		  a_field, leftrightleft)) {				\
 		    /*      ||                                        */\
 		    /*    pathp(b)                                    */\
 		    /*   /        \\                                  */\
@@ -747,7 +766,7 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		    /*   (b)                                          */\
 		    /*   /                                            */\
 		    /* (b)                                            */\
-		    assert(leftright != &rbtree->rbt_nil);		\
+		    assert(leftright != NULL);				\
 		    rbtn_red_set(a_type, a_field, leftright);		\
 		    rbtn_rotate_right(a_type, a_field, pathp->node,	\
 		      tnode);						\
@@ -770,7 +789,8 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		return;							\
 	    } else if (rbtn_red_get(a_type, a_field, pathp->node)) {	\
 		a_type *leftleft = rbtn_left_get(a_type, a_field, left);\
-		if (rbtn_red_get(a_type, a_field, leftleft)) {		\
+		if (leftleft != NULL && rbtn_red_get(a_type, a_field,	\
+		  leftleft)) {						\
 		    /*        ||                                      */\
 		    /*      pathp(r)                                  */\
 		    /*     /        \\                                */\
@@ -808,7 +828,8 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
 		}							\
 	    } else {							\
 		a_type *leftleft = rbtn_left_get(a_type, a_field, left);\
-		if (rbtn_red_get(a_type, a_field, leftleft)) {		\
+		if (leftleft != NULL && rbtn_red_get(a_type, a_field,	\
+		  leftleft)) {						\
 		    /*               ||                               */\
 		    /*             pathp(b)                           */\
 		    /*            /        \\                         */\
@@ -849,22 +870,22 @@ a_prefix##remove(a_rbt_type *rbtree, a_type *node) {			\
     }									\
     /* Set root. */							\
     rbtree->rbt_root = path->node;					\
-    assert(rbtn_red_get(a_type, a_field, rbtree->rbt_root) == false);	\
+    assert(!rbtn_red_get(a_type, a_field, rbtree->rbt_root));		\
 }									\
 a_attr a_type *								\
 a_prefix##iter_recurse(a_rbt_type *rbtree, a_type *node,		\
   a_type *(*cb)(a_rbt_type *, a_type *, void *), void *arg) {		\
-    if (node == &rbtree->rbt_nil) {					\
-	return (&rbtree->rbt_nil);					\
+    if (node == NULL) {							\
+	return NULL;							\
     } else {								\
 	a_type *ret;							\
 	if ((ret = a_prefix##iter_recurse(rbtree, rbtn_left_get(a_type,	\
-	  a_field, node), cb, arg)) != &rbtree->rbt_nil			\
-	  || (ret = cb(rbtree, node, arg)) != NULL) {			\
-	    return (ret);						\
+	  a_field, node), cb, arg)) != NULL || (ret = cb(rbtree, node,	\
+	  arg)) != NULL) {						\
+	    return ret;							\
 	}								\
-	return (a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
-	  a_field, node), cb, arg));					\
+	return a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
+	  a_field, node), cb, arg);					\
     }									\
 }									\
 a_attr a_type *								\
@@ -874,22 +895,22 @@ a_prefix##iter_start(a_rbt_type *rbtree, a_type *start, a_type *node,	\
     if (cmp < 0) {							\
 	a_type *ret;							\
 	if ((ret = a_prefix##iter_start(rbtree, start,			\
-	  rbtn_left_get(a_type, a_field, node), cb, arg)) !=		\
-	  &rbtree->rbt_nil || (ret = cb(rbtree, node, arg)) != NULL) {	\
-	    return (ret);						\
+	  rbtn_left_get(a_type, a_field, node), cb, arg)) != NULL ||	\
+	  (ret = cb(rbtree, node, arg)) != NULL) {			\
+	    return ret;							\
 	}								\
-	return (a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
-	  a_field, node), cb, arg));					\
+	return a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
+	  a_field, node), cb, arg);					\
     } else if (cmp > 0) {						\
-	return (a_prefix##iter_start(rbtree, start,			\
-	  rbtn_right_get(a_type, a_field, node), cb, arg));		\
+	return a_prefix##iter_start(rbtree, start,			\
+	  rbtn_right_get(a_type, a_field, node), cb, arg);		\
     } else {								\
 	a_type *ret;							\
 	if ((ret = cb(rbtree, node, arg)) != NULL) {			\
-	    return (ret);						\
+	    return ret;							\
 	}								\
-	return (a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
-	  a_field, node), cb, arg));					\
+	return a_prefix##iter_recurse(rbtree, rbtn_right_get(a_type,	\
+	  a_field, node), cb, arg);					\
     }									\
 }									\
 a_attr a_type *								\
@@ -902,25 +923,22 @@ a_prefix##iter(a_rbt_type *rbtree, a_type *start, a_type *(*cb)(	\
     } else {								\
 	ret = a_prefix##iter_recurse(rbtree, rbtree->rbt_root, cb, arg);\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = NULL;							\
-    }									\
-    return (ret);							\
+    return ret;								\
 }									\
 a_attr a_type *								\
 a_prefix##reverse_iter_recurse(a_rbt_type *rbtree, a_type *node,	\
   a_type *(*cb)(a_rbt_type *, a_type *, void *), void *arg) {		\
-    if (node == &rbtree->rbt_nil) {					\
-	return (&rbtree->rbt_nil);					\
+    if (node == NULL) {							\
+	return NULL;							\
     } else {								\
 	a_type *ret;							\
 	if ((ret = a_prefix##reverse_iter_recurse(rbtree,		\
-	  rbtn_right_get(a_type, a_field, node), cb, arg)) !=		\
-	  &rbtree->rbt_nil || (ret = cb(rbtree, node, arg)) != NULL) {	\
-	    return (ret);						\
+	  rbtn_right_get(a_type, a_field, node), cb, arg)) != NULL ||	\
+	  (ret = cb(rbtree, node, arg)) != NULL) {			\
+	    return ret;							\
 	}								\
-	return (a_prefix##reverse_iter_recurse(rbtree,			\
-	  rbtn_left_get(a_type, a_field, node), cb, arg));		\
+	return a_prefix##reverse_iter_recurse(rbtree,			\
+	  rbtn_left_get(a_type, a_field, node), cb, arg);		\
     }									\
 }									\
 a_attr a_type *								\
@@ -931,22 +949,22 @@ a_prefix##reverse_iter_start(a_rbt_type *rbtree, a_type *start,		\
     if (cmp > 0) {							\
 	a_type *ret;							\
 	if ((ret = a_prefix##reverse_iter_start(rbtree, start,		\
-	  rbtn_right_get(a_type, a_field, node), cb, arg)) !=		\
-	  &rbtree->rbt_nil || (ret = cb(rbtree, node, arg)) != NULL) {	\
-	    return (ret);						\
+	  rbtn_right_get(a_type, a_field, node), cb, arg)) != NULL ||	\
+	  (ret = cb(rbtree, node, arg)) != NULL) {			\
+	    return ret;							\
 	}								\
-	return (a_prefix##reverse_iter_recurse(rbtree,			\
-	  rbtn_left_get(a_type, a_field, node), cb, arg));		\
+	return a_prefix##reverse_iter_recurse(rbtree,			\
+	  rbtn_left_get(a_type, a_field, node), cb, arg);		\
     } else if (cmp < 0) {						\
-	return (a_prefix##reverse_iter_start(rbtree, start,		\
-	  rbtn_left_get(a_type, a_field, node), cb, arg));		\
+	return a_prefix##reverse_iter_start(rbtree, start,		\
+	  rbtn_left_get(a_type, a_field, node), cb, arg);		\
     } else {								\
 	a_type *ret;							\
 	if ((ret = cb(rbtree, node, arg)) != NULL) {			\
-	    return (ret);						\
+	    return ret;							\
 	}								\
-	return (a_prefix##reverse_iter_recurse(rbtree,			\
-	  rbtn_left_get(a_type, a_field, node), cb, arg));		\
+	return a_prefix##reverse_iter_recurse(rbtree,			\
+	  rbtn_left_get(a_type, a_field, node), cb, arg);		\
     }									\
 }									\
 a_attr a_type *								\
@@ -960,10 +978,29 @@ a_prefix##reverse_iter(a_rbt_type *rbtree, a_type *start,		\
 	ret = a_prefix##reverse_iter_recurse(rbtree, rbtree->rbt_root,	\
 	  cb, arg);							\
     }									\
-    if (ret == &rbtree->rbt_nil) {					\
-	ret = NULL;							\
+    return ret;								\
+}									\
+a_attr void								\
+a_prefix##destroy_recurse(a_rbt_type *rbtree, a_type *node, void (*cb)(	\
+  a_type *, void *), void *arg) {					\
+    if (node == NULL) {							\
+	return;								\
     }									\
-    return (ret);							\
+    a_prefix##destroy_recurse(rbtree, rbtn_left_get(a_type, a_field,	\
+      node), cb, arg);							\
+    rbtn_left_set(a_type, a_field, (node), NULL);			\
+    a_prefix##destroy_recurse(rbtree, rbtn_right_get(a_type, a_field,	\
+      node), cb, arg);							\
+    rbtn_right_set(a_type, a_field, (node), NULL);			\
+    if (cb) {								\
+	cb(node, arg);							\
+    }									\
+}									\
+a_attr void								\
+a_prefix##destroy(a_rbt_type *rbtree, void (*cb)(a_type *, void *),	\
+  void *arg) {								\
+    a_prefix##destroy_recurse(rbtree, rbtree->rbt_root, cb, arg);	\
+    rbtree->rbt_root = NULL;						\
 }
 
 #endif /* RB_H_ */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree.h
index bc74769f50..b5d4db3988 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree.h
@@ -1,172 +1,474 @@
+#ifndef JEMALLOC_INTERNAL_RTREE_H
+#define JEMALLOC_INTERNAL_RTREE_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree_tsd.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/tsd.h"
+
 /*
  * This radix tree implementation is tailored to the singular purpose of
- * tracking which chunks are currently owned by jemalloc.  This functionality
- * is mandatory for OS X, where jemalloc must be able to respond to object
- * ownership queries.
+ * associating metadata with extents that are currently owned by jemalloc.
  *
  *******************************************************************************
  */
-#ifdef JEMALLOC_H_TYPES
+
+/* Number of high insignificant bits. */
+#define RTREE_NHIB ((1U << (LG_SIZEOF_PTR+3)) - LG_VADDR)
+/* Number of low insigificant bits. */
+#define RTREE_NLIB LG_PAGE
+/* Number of significant bits. */
+#define RTREE_NSB (LG_VADDR - RTREE_NLIB)
+/* Number of levels in radix tree. */
+#if RTREE_NSB <= 10
+#  define RTREE_HEIGHT 1
+#elif RTREE_NSB <= 36
+#  define RTREE_HEIGHT 2
+#elif RTREE_NSB <= 52
+#  define RTREE_HEIGHT 3
+#else
+#  error Unsupported number of significant virtual address bits
+#endif
+/* Use compact leaf representation if virtual address encoding allows. */
+#if RTREE_NHIB >= LG_CEIL_NSIZES
+#  define RTREE_LEAF_COMPACT
+#endif
+
+/* Needed for initialization only. */
+#define RTREE_LEAFKEY_INVALID ((uintptr_t)1)
+
+typedef struct rtree_node_elm_s rtree_node_elm_t;
+struct rtree_node_elm_s {
+	atomic_p_t	child; /* (rtree_{node,leaf}_elm_t *) */
+};
+
+struct rtree_leaf_elm_s {
+#ifdef RTREE_LEAF_COMPACT
+	/*
+	 * Single pointer-width field containing all three leaf element fields.
+	 * For example, on a 64-bit x64 system with 48 significant virtual
+	 * memory address bits, the index, extent, and slab fields are packed as
+	 * such:
+	 *
+	 * x: index
+	 * e: extent
+	 * b: slab
+	 *
+	 *   00000000 xxxxxxxx eeeeeeee [...] eeeeeeee eeee000b
+	 */
+	atomic_p_t	le_bits;
+#else
+	atomic_p_t	le_extent; /* (extent_t *) */
+	atomic_u_t	le_szind; /* (szind_t) */
+	atomic_b_t	le_slab; /* (bool) */
+#endif
+};
+
+typedef struct rtree_level_s rtree_level_t;
+struct rtree_level_s {
+	/* Number of key bits distinguished by this level. */
+	unsigned		bits;
+	/*
+	 * Cumulative number of key bits distinguished by traversing to
+	 * corresponding tree level.
+	 */
+	unsigned		cumbits;
+};
 
 typedef struct rtree_s rtree_t;
+struct rtree_s {
+	malloc_mutex_t		init_lock;
+	/* Number of elements based on rtree_levels[0].bits. */
+#if RTREE_HEIGHT > 1
+	rtree_node_elm_t	root[1U << (RTREE_NSB/RTREE_HEIGHT)];
+#else
+	rtree_leaf_elm_t	root[1U << (RTREE_NSB/RTREE_HEIGHT)];
+#endif
+};
 
 /*
- * Size of each radix tree node (must be a power of 2).  This impacts tree
- * depth.
+ * Split the bits into one to three partitions depending on number of
+ * significant bits.  It the number of bits does not divide evenly into the
+ * number of levels, place one remainder bit per level starting at the leaf
+ * level.
  */
-#define	RTREE_NODESIZE (1U << 16)
+static const rtree_level_t rtree_levels[] = {
+#if RTREE_HEIGHT == 1
+	{RTREE_NSB, RTREE_NHIB + RTREE_NSB}
+#elif RTREE_HEIGHT == 2
+	{RTREE_NSB/2, RTREE_NHIB + RTREE_NSB/2},
+	{RTREE_NSB/2 + RTREE_NSB%2, RTREE_NHIB + RTREE_NSB}
+#elif RTREE_HEIGHT == 3
+	{RTREE_NSB/3, RTREE_NHIB + RTREE_NSB/3},
+	{RTREE_NSB/3 + RTREE_NSB%3/2,
+	    RTREE_NHIB + RTREE_NSB/3*2 + RTREE_NSB%3/2},
+	{RTREE_NSB/3 + RTREE_NSB%3 - RTREE_NSB%3/2, RTREE_NHIB + RTREE_NSB}
+#else
+#  error Unsupported rtree height
+#endif
+};
 
-typedef void *(rtree_alloc_t)(size_t);
-typedef void (rtree_dalloc_t)(void *);
+bool rtree_new(rtree_t *rtree, bool zeroed);
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+typedef rtree_node_elm_t *(rtree_node_alloc_t)(tsdn_t *, rtree_t *, size_t);
+extern rtree_node_alloc_t *JET_MUTABLE rtree_node_alloc;
 
-struct rtree_s {
-	rtree_alloc_t	*alloc;
-	rtree_dalloc_t	*dalloc;
-	malloc_mutex_t	mutex;
-	void		**root;
-	unsigned	height;
-	unsigned	level2bits[1]; /* Dynamically sized. */
-};
+typedef rtree_leaf_elm_t *(rtree_leaf_alloc_t)(tsdn_t *, rtree_t *, size_t);
+extern rtree_leaf_alloc_t *JET_MUTABLE rtree_leaf_alloc;
+
+typedef void (rtree_node_dalloc_t)(tsdn_t *, rtree_t *, rtree_node_elm_t *);
+extern rtree_node_dalloc_t *JET_MUTABLE rtree_node_dalloc;
+
+typedef void (rtree_leaf_dalloc_t)(tsdn_t *, rtree_t *, rtree_leaf_elm_t *);
+extern rtree_leaf_dalloc_t *JET_MUTABLE rtree_leaf_dalloc;
+#ifdef JEMALLOC_JET
+void rtree_delete(tsdn_t *tsdn, rtree_t *rtree);
+#endif
+rtree_leaf_elm_t *rtree_leaf_elm_lookup_hard(tsdn_t *tsdn, rtree_t *rtree,
+    rtree_ctx_t *rtree_ctx, uintptr_t key, bool dependent, bool init_missing);
+
+JEMALLOC_ALWAYS_INLINE uintptr_t
+rtree_leafkey(uintptr_t key) {
+	unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3);
+	unsigned cumbits = (rtree_levels[RTREE_HEIGHT-1].cumbits -
+	    rtree_levels[RTREE_HEIGHT-1].bits);
+	unsigned maskbits = ptrbits - cumbits;
+	uintptr_t mask = ~((ZU(1) << maskbits) - 1);
+	return (key & mask);
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+rtree_cache_direct_map(uintptr_t key) {
+	unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3);
+	unsigned cumbits = (rtree_levels[RTREE_HEIGHT-1].cumbits -
+	    rtree_levels[RTREE_HEIGHT-1].bits);
+	unsigned maskbits = ptrbits - cumbits;
+	return (size_t)((key >> maskbits) & (RTREE_CTX_NCACHE - 1));
+}
+
+JEMALLOC_ALWAYS_INLINE uintptr_t
+rtree_subkey(uintptr_t key, unsigned level) {
+	unsigned ptrbits = ZU(1) << (LG_SIZEOF_PTR+3);
+	unsigned cumbits = rtree_levels[level].cumbits;
+	unsigned shiftbits = ptrbits - cumbits;
+	unsigned maskbits = rtree_levels[level].bits;
+	uintptr_t mask = (ZU(1) << maskbits) - 1;
+	return ((key >> shiftbits) & mask);
+}
+
+/*
+ * Atomic getters.
+ *
+ * dependent: Reading a value on behalf of a pointer to a valid allocation
+ *            is guaranteed to be a clean read even without synchronization,
+ *            because the rtree update became visible in memory before the
+ *            pointer came into existence.
+ * !dependent: An arbitrary read, e.g. on behalf of ivsalloc(), may not be
+ *             dependent on a previous rtree write, which means a stale read
+ *             could result if synchronization were omitted here.
+ */
+#  ifdef RTREE_LEAF_COMPACT
+JEMALLOC_ALWAYS_INLINE uintptr_t
+rtree_leaf_elm_bits_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    bool dependent) {
+	return (uintptr_t)atomic_load_p(&elm->le_bits, dependent
+	    ? ATOMIC_RELAXED : ATOMIC_ACQUIRE);
+}
+
+JEMALLOC_ALWAYS_INLINE extent_t *
+rtree_leaf_elm_bits_extent_get(uintptr_t bits) {
+	/* Restore sign-extended high bits, mask slab bit. */
+	return (extent_t *)((uintptr_t)((intptr_t)(bits << RTREE_NHIB) >>
+	    RTREE_NHIB) & ~((uintptr_t)0x1));
+}
 
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
+JEMALLOC_ALWAYS_INLINE szind_t
+rtree_leaf_elm_bits_szind_get(uintptr_t bits) {
+	return (szind_t)(bits >> LG_VADDR);
+}
 
-rtree_t	*rtree_new(unsigned bits, rtree_alloc_t *alloc, rtree_dalloc_t *dalloc);
-void	rtree_delete(rtree_t *rtree);
-void	rtree_prefork(rtree_t *rtree);
-void	rtree_postfork_parent(rtree_t *rtree);
-void	rtree_postfork_child(rtree_t *rtree);
+JEMALLOC_ALWAYS_INLINE bool
+rtree_leaf_elm_bits_slab_get(uintptr_t bits) {
+	return (bool)(bits & (uintptr_t)0x1);
+}
 
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+#  endif
 
-#ifndef JEMALLOC_ENABLE_INLINE
-#ifdef JEMALLOC_DEBUG
-uint8_t rtree_get_locked(rtree_t *rtree, uintptr_t key);
+JEMALLOC_ALWAYS_INLINE extent_t *
+rtree_leaf_elm_extent_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    bool dependent) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent);
+	return rtree_leaf_elm_bits_extent_get(bits);
+#else
+	extent_t *extent = (extent_t *)atomic_load_p(&elm->le_extent, dependent
+	    ? ATOMIC_RELAXED : ATOMIC_ACQUIRE);
+	return extent;
 #endif
-uint8_t	rtree_get(rtree_t *rtree, uintptr_t key);
-bool	rtree_set(rtree_t *rtree, uintptr_t key, uint8_t val);
+}
+
+JEMALLOC_ALWAYS_INLINE szind_t
+rtree_leaf_elm_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    bool dependent) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent);
+	return rtree_leaf_elm_bits_szind_get(bits);
+#else
+	return (szind_t)atomic_load_u(&elm->le_szind, dependent ? ATOMIC_RELAXED
+	    : ATOMIC_ACQUIRE);
 #endif
+}
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_RTREE_C_))
-#define	RTREE_GET_GENERATE(f)						\
-/* The least significant bits of the key are ignored. */		\
-JEMALLOC_INLINE uint8_t							\
-f(rtree_t *rtree, uintptr_t key)					\
-{									\
-	uint8_t ret;							\
-	uintptr_t subkey;						\
-	unsigned i, lshift, height, bits;				\
-	void **node, **child;						\
-									\
-	RTREE_LOCK(&rtree->mutex);					\
-	for (i = lshift = 0, height = rtree->height, node = rtree->root;\
-	    i < height - 1;						\
-	    i++, lshift += bits, node = child) {			\
-		bits = rtree->level2bits[i];				\
-		subkey = (key << lshift) >> ((ZU(1) << (LG_SIZEOF_PTR +	\
-		    3)) - bits);					\
-		child = (void**)node[subkey];				\
-		if (child == NULL) {					\
-			RTREE_UNLOCK(&rtree->mutex);			\
-			return (0);					\
-		}							\
-	}								\
-									\
-	/*								\
-	 * node is a leaf, so it contains values rather than node	\
-	 * pointers.							\
-	 */								\
-	bits = rtree->level2bits[i];					\
-	subkey = (key << lshift) >> ((ZU(1) << (LG_SIZEOF_PTR+3)) -	\
-	    bits);							\
-	{								\
-		uint8_t *leaf = (uint8_t *)node;			\
-		ret = leaf[subkey];					\
-	}								\
-	RTREE_UNLOCK(&rtree->mutex);					\
-									\
-	RTREE_GET_VALIDATE						\
-	return (ret);							\
-}
-
-#ifdef JEMALLOC_DEBUG
-#  define RTREE_LOCK(l)		malloc_mutex_lock(l)
-#  define RTREE_UNLOCK(l)	malloc_mutex_unlock(l)
-#  define RTREE_GET_VALIDATE
-RTREE_GET_GENERATE(rtree_get_locked)
-#  undef RTREE_LOCK
-#  undef RTREE_UNLOCK
-#  undef RTREE_GET_VALIDATE
+JEMALLOC_ALWAYS_INLINE bool
+rtree_leaf_elm_slab_read(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    bool dependent) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, dependent);
+	return rtree_leaf_elm_bits_slab_get(bits);
+#else
+	return atomic_load_b(&elm->le_slab, dependent ? ATOMIC_RELAXED :
+	    ATOMIC_ACQUIRE);
 #endif
+}
 
-#define	RTREE_LOCK(l)
-#define	RTREE_UNLOCK(l)
-#ifdef JEMALLOC_DEBUG
-   /*
-    * Suppose that it were possible for a jemalloc-allocated chunk to be
-    * munmap()ped, followed by a different allocator in another thread re-using
-    * overlapping virtual memory, all without invalidating the cached rtree
-    * value.  The result would be a false positive (the rtree would claim that
-    * jemalloc owns memory that it had actually discarded).  This scenario
-    * seems impossible, but the following assertion is a prudent sanity check.
-    */
-#  define RTREE_GET_VALIDATE						\
-	assert(rtree_get_locked(rtree, key) == ret);
+static inline void
+rtree_leaf_elm_extent_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    extent_t *extent) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm, true);
+	uintptr_t bits = ((uintptr_t)rtree_leaf_elm_bits_szind_get(old_bits) <<
+	    LG_VADDR) | ((uintptr_t)extent & (((uintptr_t)0x1 << LG_VADDR) - 1))
+	    | ((uintptr_t)rtree_leaf_elm_bits_slab_get(old_bits));
+	atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE);
 #else
-#  define RTREE_GET_VALIDATE
+	atomic_store_p(&elm->le_extent, extent, ATOMIC_RELEASE);
 #endif
-RTREE_GET_GENERATE(rtree_get)
-#undef RTREE_LOCK
-#undef RTREE_UNLOCK
-#undef RTREE_GET_VALIDATE
-
-JEMALLOC_INLINE bool
-rtree_set(rtree_t *rtree, uintptr_t key, uint8_t val)
-{
-	uintptr_t subkey;
-	unsigned i, lshift, height, bits;
-	void **node, **child;
-
-	malloc_mutex_lock(&rtree->mutex);
-	for (i = lshift = 0, height = rtree->height, node = rtree->root;
-	    i < height - 1;
-	    i++, lshift += bits, node = child) {
-		bits = rtree->level2bits[i];
-		subkey = (key << lshift) >> ((ZU(1) << (LG_SIZEOF_PTR+3)) -
-		    bits);
-		child = (void**)node[subkey];
-		if (child == NULL) {
-			size_t size = ((i + 1 < height - 1) ? sizeof(void *)
-			    : (sizeof(uint8_t))) << rtree->level2bits[i+1];
-			child = (void**)rtree->alloc(size);
-			if (child == NULL) {
-				malloc_mutex_unlock(&rtree->mutex);
-				return (true);
-			}
-			memset(child, 0, size);
-			node[subkey] = child;
-		}
+}
+
+static inline void
+rtree_leaf_elm_szind_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    szind_t szind) {
+	assert(szind <= NSIZES);
+
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm,
+	    true);
+	uintptr_t bits = ((uintptr_t)szind << LG_VADDR) |
+	    ((uintptr_t)rtree_leaf_elm_bits_extent_get(old_bits) &
+	    (((uintptr_t)0x1 << LG_VADDR) - 1)) |
+	    ((uintptr_t)rtree_leaf_elm_bits_slab_get(old_bits));
+	atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE);
+#else
+	atomic_store_u(&elm->le_szind, szind, ATOMIC_RELEASE);
+#endif
+}
+
+static inline void
+rtree_leaf_elm_slab_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+     bool slab) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t old_bits = rtree_leaf_elm_bits_read(tsdn, rtree, elm,
+	    true);
+	uintptr_t bits = ((uintptr_t)rtree_leaf_elm_bits_szind_get(old_bits) <<
+	    LG_VADDR) | ((uintptr_t)rtree_leaf_elm_bits_extent_get(old_bits) &
+	    (((uintptr_t)0x1 << LG_VADDR) - 1)) | ((uintptr_t)slab);
+	atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE);
+#else
+	atomic_store_b(&elm->le_slab, slab, ATOMIC_RELEASE);
+#endif
+}
+
+static inline void
+rtree_leaf_elm_write(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *elm,
+    extent_t *extent, szind_t szind, bool slab) {
+#ifdef RTREE_LEAF_COMPACT
+	uintptr_t bits = ((uintptr_t)szind << LG_VADDR) |
+	    ((uintptr_t)extent & (((uintptr_t)0x1 << LG_VADDR) - 1)) |
+	    ((uintptr_t)slab);
+	atomic_store_p(&elm->le_bits, (void *)bits, ATOMIC_RELEASE);
+#else
+	rtree_leaf_elm_slab_write(tsdn, rtree, elm, slab);
+	rtree_leaf_elm_szind_write(tsdn, rtree, elm, szind);
+	/*
+	 * Write extent last, since the element is atomically considered valid
+	 * as soon as the extent field is non-NULL.
+	 */
+	rtree_leaf_elm_extent_write(tsdn, rtree, elm, extent);
+#endif
+}
+
+static inline void
+rtree_leaf_elm_szind_slab_update(tsdn_t *tsdn, rtree_t *rtree,
+    rtree_leaf_elm_t *elm, szind_t szind, bool slab) {
+	assert(!slab || szind < NBINS);
+
+	/*
+	 * The caller implicitly assures that it is the only writer to the szind
+	 * and slab fields, and that the extent field cannot currently change.
+	 */
+	rtree_leaf_elm_slab_write(tsdn, rtree, elm, slab);
+	rtree_leaf_elm_szind_write(tsdn, rtree, elm, szind);
+}
+
+JEMALLOC_ALWAYS_INLINE rtree_leaf_elm_t *
+rtree_leaf_elm_lookup(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent, bool init_missing) {
+	assert(key != 0);
+	assert(!dependent || !init_missing);
+
+	size_t slot = rtree_cache_direct_map(key);
+	uintptr_t leafkey = rtree_leafkey(key);
+	assert(leafkey != RTREE_LEAFKEY_INVALID);
+
+	/* Fast path: L1 direct mapped cache. */
+	if (likely(rtree_ctx->cache[slot].leafkey == leafkey)) {
+		rtree_leaf_elm_t *leaf = rtree_ctx->cache[slot].leaf;
+		assert(leaf != NULL);
+		uintptr_t subkey = rtree_subkey(key, RTREE_HEIGHT-1);
+		return &leaf[subkey];
 	}
+	/*
+	 * Search the L2 LRU cache.  On hit, swap the matching element into the
+	 * slot in L1 cache, and move the position in L2 up by 1.
+	 */
+#define RTREE_CACHE_CHECK_L2(i) do {					\
+	if (likely(rtree_ctx->l2_cache[i].leafkey == leafkey)) {	\
+		rtree_leaf_elm_t *leaf = rtree_ctx->l2_cache[i].leaf;	\
+		assert(leaf != NULL);					\
+		if (i > 0) {						\
+			/* Bubble up by one. */				\
+			rtree_ctx->l2_cache[i].leafkey =		\
+				rtree_ctx->l2_cache[i - 1].leafkey;	\
+			rtree_ctx->l2_cache[i].leaf =			\
+				rtree_ctx->l2_cache[i - 1].leaf;	\
+			rtree_ctx->l2_cache[i - 1].leafkey =		\
+			    rtree_ctx->cache[slot].leafkey;		\
+			rtree_ctx->l2_cache[i - 1].leaf =		\
+			    rtree_ctx->cache[slot].leaf;		\
+		} else {						\
+			rtree_ctx->l2_cache[0].leafkey =		\
+			    rtree_ctx->cache[slot].leafkey;		\
+			rtree_ctx->l2_cache[0].leaf =			\
+			    rtree_ctx->cache[slot].leaf;		\
+		}							\
+		rtree_ctx->cache[slot].leafkey = leafkey;		\
+		rtree_ctx->cache[slot].leaf = leaf;			\
+		uintptr_t subkey = rtree_subkey(key, RTREE_HEIGHT-1);	\
+		return &leaf[subkey];					\
+	}								\
+} while (0)
+	/* Check the first cache entry. */
+	RTREE_CACHE_CHECK_L2(0);
+	/* Search the remaining cache elements. */
+	for (unsigned i = 1; i < RTREE_CTX_NCACHE_L2; i++) {
+		RTREE_CACHE_CHECK_L2(i);
+	}
+#undef RTREE_CACHE_CHECK_L2
+
+	return rtree_leaf_elm_lookup_hard(tsdn, rtree, rtree_ctx, key,
+	    dependent, init_missing);
+}
+
+static inline bool
+rtree_write(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key,
+    extent_t *extent, szind_t szind, bool slab) {
+	/* Use rtree_clear() to set the extent to NULL. */
+	assert(extent != NULL);
 
-	/* node is a leaf, so it contains values rather than node pointers. */
-	bits = rtree->level2bits[i];
-	subkey = (key << lshift) >> ((ZU(1) << (LG_SIZEOF_PTR+3)) - bits);
-	{
-		uint8_t *leaf = (uint8_t *)node;
-		leaf[subkey] = val;
+	rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, rtree, rtree_ctx,
+	    key, false, true);
+	if (elm == NULL) {
+		return true;
 	}
-	malloc_mutex_unlock(&rtree->mutex);
 
-	return (false);
+	assert(rtree_leaf_elm_extent_read(tsdn, rtree, elm, false) == NULL);
+	rtree_leaf_elm_write(tsdn, rtree, elm, extent, szind, slab);
+
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE rtree_leaf_elm_t *
+rtree_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx, uintptr_t key,
+    bool dependent) {
+	rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, rtree, rtree_ctx,
+	    key, dependent, false);
+	if (!dependent && elm == NULL) {
+		return NULL;
+	}
+	assert(elm != NULL);
+	return elm;
+}
+
+JEMALLOC_ALWAYS_INLINE extent_t *
+rtree_extent_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent) {
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key,
+	    dependent);
+	if (!dependent && elm == NULL) {
+		return NULL;
+	}
+	return rtree_leaf_elm_extent_read(tsdn, rtree, elm, dependent);
+}
+
+JEMALLOC_ALWAYS_INLINE szind_t
+rtree_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent) {
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key,
+	    dependent);
+	if (!dependent && elm == NULL) {
+		return NSIZES;
+	}
+	return rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent);
+}
+
+/*
+ * rtree_slab_read() is intentionally omitted because slab is always read in
+ * conjunction with szind, which makes rtree_szind_slab_read() a better choice.
+ */
+
+JEMALLOC_ALWAYS_INLINE bool
+rtree_extent_szind_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent, extent_t **r_extent, szind_t *r_szind) {
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key,
+	    dependent);
+	if (!dependent && elm == NULL) {
+		return true;
+	}
+	*r_extent = rtree_leaf_elm_extent_read(tsdn, rtree, elm, dependent);
+	*r_szind = rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent);
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+rtree_szind_slab_read(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent, szind_t *r_szind, bool *r_slab) {
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key,
+	    dependent);
+	if (!dependent && elm == NULL) {
+		return true;
+	}
+	*r_szind = rtree_leaf_elm_szind_read(tsdn, rtree, elm, dependent);
+	*r_slab = rtree_leaf_elm_slab_read(tsdn, rtree, elm, dependent);
+	return false;
+}
+
+static inline void
+rtree_szind_slab_update(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, szind_t szind, bool slab) {
+	assert(!slab || szind < NBINS);
+
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, true);
+	rtree_leaf_elm_szind_slab_update(tsdn, rtree, elm, szind, slab);
+}
+
+static inline void
+rtree_clear(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key) {
+	rtree_leaf_elm_t *elm = rtree_read(tsdn, rtree, rtree_ctx, key, true);
+	assert(rtree_leaf_elm_extent_read(tsdn, rtree, elm, false) !=
+	    NULL);
+	rtree_leaf_elm_write(tsdn, rtree, elm, NULL, NSIZES, false);
 }
-#endif
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_RTREE_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree_tsd.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree_tsd.h
new file mode 100644
index 0000000000..3cdc862548
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/rtree_tsd.h
@@ -0,0 +1,50 @@
+#ifndef JEMALLOC_INTERNAL_RTREE_CTX_H
+#define JEMALLOC_INTERNAL_RTREE_CTX_H
+
+/*
+ * Number of leafkey/leaf pairs to cache in L1 and L2 level respectively.  Each
+ * entry supports an entire leaf, so the cache hit rate is typically high even
+ * with a small number of entries.  In rare cases extent activity will straddle
+ * the boundary between two leaf nodes.  Furthermore, an arena may use a
+ * combination of dss and mmap.  Note that as memory usage grows past the amount
+ * that this cache can directly cover, the cache will become less effective if
+ * locality of reference is low, but the consequence is merely cache misses
+ * while traversing the tree nodes.
+ *
+ * The L1 direct mapped cache offers consistent and low cost on cache hit.
+ * However collision could affect hit rate negatively.  This is resolved by
+ * combining with a L2 LRU cache, which requires linear search and re-ordering
+ * on access but suffers no collision.  Note that, the cache will itself suffer
+ * cache misses if made overly large, plus the cost of linear search in the LRU
+ * cache.
+ */
+#define RTREE_CTX_LG_NCACHE 4
+#define RTREE_CTX_NCACHE (1 << RTREE_CTX_LG_NCACHE)
+#define RTREE_CTX_NCACHE_L2 8
+
+/*
+ * Zero initializer required for tsd initialization only.  Proper initialization
+ * done via rtree_ctx_data_init().
+ */
+#define RTREE_CTX_ZERO_INITIALIZER {{{0}}}
+
+
+typedef struct rtree_leaf_elm_s rtree_leaf_elm_t;
+
+typedef struct rtree_ctx_cache_elm_s rtree_ctx_cache_elm_t;
+struct rtree_ctx_cache_elm_s {
+	uintptr_t		leafkey;
+	rtree_leaf_elm_t	*leaf;
+};
+
+typedef struct rtree_ctx_s rtree_ctx_t;
+struct rtree_ctx_s {
+	/* Direct mapped cache. */
+	rtree_ctx_cache_elm_t	cache[RTREE_CTX_NCACHE];
+	/* L2 LRU cache. */
+	rtree_ctx_cache_elm_t	l2_cache[RTREE_CTX_NCACHE_L2];
+};
+
+void rtree_ctx_data_init(rtree_ctx_t *ctx);
+
+#endif /* JEMALLOC_INTERNAL_RTREE_CTX_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/size_classes.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/size_classes.h
index 821102e5c1..0b7d3cd369 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/size_classes.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/size_classes.h
@@ -1,690 +1,1416 @@
-/* This file was automatically generated by size_classes.sh. */
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 12)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	8,	24)					\
-    SIZE_CLASS(3,	8,	32)					\
-    SIZE_CLASS(4,	8,	40)					\
-    SIZE_CLASS(5,	8,	48)					\
-    SIZE_CLASS(6,	8,	56)					\
-    SIZE_CLASS(7,	8,	64)					\
-    SIZE_CLASS(8,	16,	80)					\
-    SIZE_CLASS(9,	16,	96)					\
-    SIZE_CLASS(10,	16,	112)					\
-    SIZE_CLASS(11,	16,	128)					\
-    SIZE_CLASS(12,	32,	160)					\
-    SIZE_CLASS(13,	32,	192)					\
-    SIZE_CLASS(14,	32,	224)					\
-    SIZE_CLASS(15,	32,	256)					\
-    SIZE_CLASS(16,	64,	320)					\
-    SIZE_CLASS(17,	64,	384)					\
-    SIZE_CLASS(18,	64,	448)					\
-    SIZE_CLASS(19,	64,	512)					\
-    SIZE_CLASS(20,	128,	640)					\
-    SIZE_CLASS(21,	128,	768)					\
-    SIZE_CLASS(22,	128,	896)					\
-    SIZE_CLASS(23,	128,	1024)					\
-    SIZE_CLASS(24,	256,	1280)					\
-    SIZE_CLASS(25,	256,	1536)					\
-    SIZE_CLASS(26,	256,	1792)					\
-    SIZE_CLASS(27,	256,	2048)					\
-    SIZE_CLASS(28,	512,	2560)					\
-    SIZE_CLASS(29,	512,	3072)					\
-    SIZE_CLASS(30,	512,	3584)					\
-
-#define	NBINS		31
-#define	SMALL_MAXCLASS	3584
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 13)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	8,	24)					\
-    SIZE_CLASS(3,	8,	32)					\
-    SIZE_CLASS(4,	8,	40)					\
-    SIZE_CLASS(5,	8,	48)					\
-    SIZE_CLASS(6,	8,	56)					\
-    SIZE_CLASS(7,	8,	64)					\
-    SIZE_CLASS(8,	16,	80)					\
-    SIZE_CLASS(9,	16,	96)					\
-    SIZE_CLASS(10,	16,	112)					\
-    SIZE_CLASS(11,	16,	128)					\
-    SIZE_CLASS(12,	32,	160)					\
-    SIZE_CLASS(13,	32,	192)					\
-    SIZE_CLASS(14,	32,	224)					\
-    SIZE_CLASS(15,	32,	256)					\
-    SIZE_CLASS(16,	64,	320)					\
-    SIZE_CLASS(17,	64,	384)					\
-    SIZE_CLASS(18,	64,	448)					\
-    SIZE_CLASS(19,	64,	512)					\
-    SIZE_CLASS(20,	128,	640)					\
-    SIZE_CLASS(21,	128,	768)					\
-    SIZE_CLASS(22,	128,	896)					\
-    SIZE_CLASS(23,	128,	1024)					\
-    SIZE_CLASS(24,	256,	1280)					\
-    SIZE_CLASS(25,	256,	1536)					\
-    SIZE_CLASS(26,	256,	1792)					\
-    SIZE_CLASS(27,	256,	2048)					\
-    SIZE_CLASS(28,	512,	2560)					\
-    SIZE_CLASS(29,	512,	3072)					\
-    SIZE_CLASS(30,	512,	3584)					\
-    SIZE_CLASS(31,	512,	4096)					\
-    SIZE_CLASS(32,	1024,	5120)					\
-    SIZE_CLASS(33,	1024,	6144)					\
-    SIZE_CLASS(34,	1024,	7168)					\
-
-#define	NBINS		35
-#define	SMALL_MAXCLASS	7168
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 14)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	8,	24)					\
-    SIZE_CLASS(3,	8,	32)					\
-    SIZE_CLASS(4,	8,	40)					\
-    SIZE_CLASS(5,	8,	48)					\
-    SIZE_CLASS(6,	8,	56)					\
-    SIZE_CLASS(7,	8,	64)					\
-    SIZE_CLASS(8,	16,	80)					\
-    SIZE_CLASS(9,	16,	96)					\
-    SIZE_CLASS(10,	16,	112)					\
-    SIZE_CLASS(11,	16,	128)					\
-    SIZE_CLASS(12,	32,	160)					\
-    SIZE_CLASS(13,	32,	192)					\
-    SIZE_CLASS(14,	32,	224)					\
-    SIZE_CLASS(15,	32,	256)					\
-    SIZE_CLASS(16,	64,	320)					\
-    SIZE_CLASS(17,	64,	384)					\
-    SIZE_CLASS(18,	64,	448)					\
-    SIZE_CLASS(19,	64,	512)					\
-    SIZE_CLASS(20,	128,	640)					\
-    SIZE_CLASS(21,	128,	768)					\
-    SIZE_CLASS(22,	128,	896)					\
-    SIZE_CLASS(23,	128,	1024)					\
-    SIZE_CLASS(24,	256,	1280)					\
-    SIZE_CLASS(25,	256,	1536)					\
-    SIZE_CLASS(26,	256,	1792)					\
-    SIZE_CLASS(27,	256,	2048)					\
-    SIZE_CLASS(28,	512,	2560)					\
-    SIZE_CLASS(29,	512,	3072)					\
-    SIZE_CLASS(30,	512,	3584)					\
-    SIZE_CLASS(31,	512,	4096)					\
-    SIZE_CLASS(32,	1024,	5120)					\
-    SIZE_CLASS(33,	1024,	6144)					\
-    SIZE_CLASS(34,	1024,	7168)					\
-    SIZE_CLASS(35,	1024,	8192)					\
-    SIZE_CLASS(36,	2048,	10240)					\
-    SIZE_CLASS(37,	2048,	12288)					\
-    SIZE_CLASS(38,	2048,	14336)					\
-
-#define	NBINS		39
-#define	SMALL_MAXCLASS	14336
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 15)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	8,	24)					\
-    SIZE_CLASS(3,	8,	32)					\
-    SIZE_CLASS(4,	8,	40)					\
-    SIZE_CLASS(5,	8,	48)					\
-    SIZE_CLASS(6,	8,	56)					\
-    SIZE_CLASS(7,	8,	64)					\
-    SIZE_CLASS(8,	16,	80)					\
-    SIZE_CLASS(9,	16,	96)					\
-    SIZE_CLASS(10,	16,	112)					\
-    SIZE_CLASS(11,	16,	128)					\
-    SIZE_CLASS(12,	32,	160)					\
-    SIZE_CLASS(13,	32,	192)					\
-    SIZE_CLASS(14,	32,	224)					\
-    SIZE_CLASS(15,	32,	256)					\
-    SIZE_CLASS(16,	64,	320)					\
-    SIZE_CLASS(17,	64,	384)					\
-    SIZE_CLASS(18,	64,	448)					\
-    SIZE_CLASS(19,	64,	512)					\
-    SIZE_CLASS(20,	128,	640)					\
-    SIZE_CLASS(21,	128,	768)					\
-    SIZE_CLASS(22,	128,	896)					\
-    SIZE_CLASS(23,	128,	1024)					\
-    SIZE_CLASS(24,	256,	1280)					\
-    SIZE_CLASS(25,	256,	1536)					\
-    SIZE_CLASS(26,	256,	1792)					\
-    SIZE_CLASS(27,	256,	2048)					\
-    SIZE_CLASS(28,	512,	2560)					\
-    SIZE_CLASS(29,	512,	3072)					\
-    SIZE_CLASS(30,	512,	3584)					\
-    SIZE_CLASS(31,	512,	4096)					\
-    SIZE_CLASS(32,	1024,	5120)					\
-    SIZE_CLASS(33,	1024,	6144)					\
-    SIZE_CLASS(34,	1024,	7168)					\
-    SIZE_CLASS(35,	1024,	8192)					\
-    SIZE_CLASS(36,	2048,	10240)					\
-    SIZE_CLASS(37,	2048,	12288)					\
-    SIZE_CLASS(38,	2048,	14336)					\
-    SIZE_CLASS(39,	2048,	16384)					\
-    SIZE_CLASS(40,	4096,	20480)					\
-    SIZE_CLASS(41,	4096,	24576)					\
-    SIZE_CLASS(42,	4096,	28672)					\
-
-#define	NBINS		43
-#define	SMALL_MAXCLASS	28672
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 16)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	8,	24)					\
-    SIZE_CLASS(3,	8,	32)					\
-    SIZE_CLASS(4,	8,	40)					\
-    SIZE_CLASS(5,	8,	48)					\
-    SIZE_CLASS(6,	8,	56)					\
-    SIZE_CLASS(7,	8,	64)					\
-    SIZE_CLASS(8,	16,	80)					\
-    SIZE_CLASS(9,	16,	96)					\
-    SIZE_CLASS(10,	16,	112)					\
-    SIZE_CLASS(11,	16,	128)					\
-    SIZE_CLASS(12,	32,	160)					\
-    SIZE_CLASS(13,	32,	192)					\
-    SIZE_CLASS(14,	32,	224)					\
-    SIZE_CLASS(15,	32,	256)					\
-    SIZE_CLASS(16,	64,	320)					\
-    SIZE_CLASS(17,	64,	384)					\
-    SIZE_CLASS(18,	64,	448)					\
-    SIZE_CLASS(19,	64,	512)					\
-    SIZE_CLASS(20,	128,	640)					\
-    SIZE_CLASS(21,	128,	768)					\
-    SIZE_CLASS(22,	128,	896)					\
-    SIZE_CLASS(23,	128,	1024)					\
-    SIZE_CLASS(24,	256,	1280)					\
-    SIZE_CLASS(25,	256,	1536)					\
-    SIZE_CLASS(26,	256,	1792)					\
-    SIZE_CLASS(27,	256,	2048)					\
-    SIZE_CLASS(28,	512,	2560)					\
-    SIZE_CLASS(29,	512,	3072)					\
-    SIZE_CLASS(30,	512,	3584)					\
-    SIZE_CLASS(31,	512,	4096)					\
-    SIZE_CLASS(32,	1024,	5120)					\
-    SIZE_CLASS(33,	1024,	6144)					\
-    SIZE_CLASS(34,	1024,	7168)					\
-    SIZE_CLASS(35,	1024,	8192)					\
-    SIZE_CLASS(36,	2048,	10240)					\
-    SIZE_CLASS(37,	2048,	12288)					\
-    SIZE_CLASS(38,	2048,	14336)					\
-    SIZE_CLASS(39,	2048,	16384)					\
-    SIZE_CLASS(40,	4096,	20480)					\
-    SIZE_CLASS(41,	4096,	24576)					\
-    SIZE_CLASS(42,	4096,	28672)					\
-    SIZE_CLASS(43,	4096,	32768)					\
-    SIZE_CLASS(44,	8192,	40960)					\
-    SIZE_CLASS(45,	8192,	49152)					\
-    SIZE_CLASS(46,	8192,	57344)					\
-
-#define	NBINS		47
-#define	SMALL_MAXCLASS	57344
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 12)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	16,	32)					\
-    SIZE_CLASS(3,	16,	48)					\
-    SIZE_CLASS(4,	16,	64)					\
-    SIZE_CLASS(5,	16,	80)					\
-    SIZE_CLASS(6,	16,	96)					\
-    SIZE_CLASS(7,	16,	112)					\
-    SIZE_CLASS(8,	16,	128)					\
-    SIZE_CLASS(9,	32,	160)					\
-    SIZE_CLASS(10,	32,	192)					\
-    SIZE_CLASS(11,	32,	224)					\
-    SIZE_CLASS(12,	32,	256)					\
-    SIZE_CLASS(13,	64,	320)					\
-    SIZE_CLASS(14,	64,	384)					\
-    SIZE_CLASS(15,	64,	448)					\
-    SIZE_CLASS(16,	64,	512)					\
-    SIZE_CLASS(17,	128,	640)					\
-    SIZE_CLASS(18,	128,	768)					\
-    SIZE_CLASS(19,	128,	896)					\
-    SIZE_CLASS(20,	128,	1024)					\
-    SIZE_CLASS(21,	256,	1280)					\
-    SIZE_CLASS(22,	256,	1536)					\
-    SIZE_CLASS(23,	256,	1792)					\
-    SIZE_CLASS(24,	256,	2048)					\
-    SIZE_CLASS(25,	512,	2560)					\
-    SIZE_CLASS(26,	512,	3072)					\
-    SIZE_CLASS(27,	512,	3584)					\
+#ifndef JEMALLOC_INTERNAL_SIZE_CLASSES_H
+#define JEMALLOC_INTERNAL_SIZE_CLASSES_H
 
-#define	NBINS		28
-#define	SMALL_MAXCLASS	3584
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 13)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	16,	32)					\
-    SIZE_CLASS(3,	16,	48)					\
-    SIZE_CLASS(4,	16,	64)					\
-    SIZE_CLASS(5,	16,	80)					\
-    SIZE_CLASS(6,	16,	96)					\
-    SIZE_CLASS(7,	16,	112)					\
-    SIZE_CLASS(8,	16,	128)					\
-    SIZE_CLASS(9,	32,	160)					\
-    SIZE_CLASS(10,	32,	192)					\
-    SIZE_CLASS(11,	32,	224)					\
-    SIZE_CLASS(12,	32,	256)					\
-    SIZE_CLASS(13,	64,	320)					\
-    SIZE_CLASS(14,	64,	384)					\
-    SIZE_CLASS(15,	64,	448)					\
-    SIZE_CLASS(16,	64,	512)					\
-    SIZE_CLASS(17,	128,	640)					\
-    SIZE_CLASS(18,	128,	768)					\
-    SIZE_CLASS(19,	128,	896)					\
-    SIZE_CLASS(20,	128,	1024)					\
-    SIZE_CLASS(21,	256,	1280)					\
-    SIZE_CLASS(22,	256,	1536)					\
-    SIZE_CLASS(23,	256,	1792)					\
-    SIZE_CLASS(24,	256,	2048)					\
-    SIZE_CLASS(25,	512,	2560)					\
-    SIZE_CLASS(26,	512,	3072)					\
-    SIZE_CLASS(27,	512,	3584)					\
-    SIZE_CLASS(28,	512,	4096)					\
-    SIZE_CLASS(29,	1024,	5120)					\
-    SIZE_CLASS(30,	1024,	6144)					\
-    SIZE_CLASS(31,	1024,	7168)					\
-
-#define	NBINS		32
-#define	SMALL_MAXCLASS	7168
-#endif
-
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 14)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	16,	32)					\
-    SIZE_CLASS(3,	16,	48)					\
-    SIZE_CLASS(4,	16,	64)					\
-    SIZE_CLASS(5,	16,	80)					\
-    SIZE_CLASS(6,	16,	96)					\
-    SIZE_CLASS(7,	16,	112)					\
-    SIZE_CLASS(8,	16,	128)					\
-    SIZE_CLASS(9,	32,	160)					\
-    SIZE_CLASS(10,	32,	192)					\
-    SIZE_CLASS(11,	32,	224)					\
-    SIZE_CLASS(12,	32,	256)					\
-    SIZE_CLASS(13,	64,	320)					\
-    SIZE_CLASS(14,	64,	384)					\
-    SIZE_CLASS(15,	64,	448)					\
-    SIZE_CLASS(16,	64,	512)					\
-    SIZE_CLASS(17,	128,	640)					\
-    SIZE_CLASS(18,	128,	768)					\
-    SIZE_CLASS(19,	128,	896)					\
-    SIZE_CLASS(20,	128,	1024)					\
-    SIZE_CLASS(21,	256,	1280)					\
-    SIZE_CLASS(22,	256,	1536)					\
-    SIZE_CLASS(23,	256,	1792)					\
-    SIZE_CLASS(24,	256,	2048)					\
-    SIZE_CLASS(25,	512,	2560)					\
-    SIZE_CLASS(26,	512,	3072)					\
-    SIZE_CLASS(27,	512,	3584)					\
-    SIZE_CLASS(28,	512,	4096)					\
-    SIZE_CLASS(29,	1024,	5120)					\
-    SIZE_CLASS(30,	1024,	6144)					\
-    SIZE_CLASS(31,	1024,	7168)					\
-    SIZE_CLASS(32,	1024,	8192)					\
-    SIZE_CLASS(33,	2048,	10240)					\
-    SIZE_CLASS(34,	2048,	12288)					\
-    SIZE_CLASS(35,	2048,	14336)					\
+/* This file was automatically generated by size_classes.sh. */
 
-#define	NBINS		36
-#define	SMALL_MAXCLASS	14336
-#endif
+#include "jemalloc/internal/jemalloc_internal_types.h"
 
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 15)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	16,	32)					\
-    SIZE_CLASS(3,	16,	48)					\
-    SIZE_CLASS(4,	16,	64)					\
-    SIZE_CLASS(5,	16,	80)					\
-    SIZE_CLASS(6,	16,	96)					\
-    SIZE_CLASS(7,	16,	112)					\
-    SIZE_CLASS(8,	16,	128)					\
-    SIZE_CLASS(9,	32,	160)					\
-    SIZE_CLASS(10,	32,	192)					\
-    SIZE_CLASS(11,	32,	224)					\
-    SIZE_CLASS(12,	32,	256)					\
-    SIZE_CLASS(13,	64,	320)					\
-    SIZE_CLASS(14,	64,	384)					\
-    SIZE_CLASS(15,	64,	448)					\
-    SIZE_CLASS(16,	64,	512)					\
-    SIZE_CLASS(17,	128,	640)					\
-    SIZE_CLASS(18,	128,	768)					\
-    SIZE_CLASS(19,	128,	896)					\
-    SIZE_CLASS(20,	128,	1024)					\
-    SIZE_CLASS(21,	256,	1280)					\
-    SIZE_CLASS(22,	256,	1536)					\
-    SIZE_CLASS(23,	256,	1792)					\
-    SIZE_CLASS(24,	256,	2048)					\
-    SIZE_CLASS(25,	512,	2560)					\
-    SIZE_CLASS(26,	512,	3072)					\
-    SIZE_CLASS(27,	512,	3584)					\
-    SIZE_CLASS(28,	512,	4096)					\
-    SIZE_CLASS(29,	1024,	5120)					\
-    SIZE_CLASS(30,	1024,	6144)					\
-    SIZE_CLASS(31,	1024,	7168)					\
-    SIZE_CLASS(32,	1024,	8192)					\
-    SIZE_CLASS(33,	2048,	10240)					\
-    SIZE_CLASS(34,	2048,	12288)					\
-    SIZE_CLASS(35,	2048,	14336)					\
-    SIZE_CLASS(36,	2048,	16384)					\
-    SIZE_CLASS(37,	4096,	20480)					\
-    SIZE_CLASS(38,	4096,	24576)					\
-    SIZE_CLASS(39,	4096,	28672)					\
+/*
+ * This header file defines:
+ *
+ *   LG_SIZE_CLASS_GROUP: Lg of size class count for each size doubling.
+ *   LG_TINY_MIN: Lg of minimum size class to support.
+ *   SIZE_CLASSES: Complete table of SC(index, lg_grp, lg_delta, ndelta, psz,
+ *                 bin, pgs, lg_delta_lookup) tuples.
+ *     index: Size class index.
+ *     lg_grp: Lg group base size (no deltas added).
+ *     lg_delta: Lg delta to previous size class.
+ *     ndelta: Delta multiplier.  size == 1<<lg_grp + ndelta<<lg_delta
+ *     psz: 'yes' if a multiple of the page size, 'no' otherwise.
+ *     bin: 'yes' if a small bin size class, 'no' otherwise.
+ *     pgs: Slab page count if a small bin size class, 0 otherwise.
+ *     lg_delta_lookup: Same as lg_delta if a lookup table size class, 'no'
+ *                      otherwise.
+ *   NTBINS: Number of tiny bins.
+ *   NLBINS: Number of bins supported by the lookup table.
+ *   NBINS: Number of small size class bins.
+ *   NSIZES: Number of size classes.
+ *   LG_CEIL_NSIZES: Number of bits required to store NSIZES.
+ *   NPSIZES: Number of size classes that are a multiple of (1U << LG_PAGE).
+ *   LG_TINY_MAXCLASS: Lg of maximum tiny size class.
+ *   LOOKUP_MAXCLASS: Maximum size class included in lookup table.
+ *   SMALL_MAXCLASS: Maximum small size class.
+ *   LG_LARGE_MINCLASS: Lg of minimum large size class.
+ *   LARGE_MAXCLASS: Maximum (large) size class.
+ */
 
-#define	NBINS		40
-#define	SMALL_MAXCLASS	28672
-#endif
+#define LG_SIZE_CLASS_GROUP	2
+#define LG_TINY_MIN		3
 
-#if (LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 16)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	8,	8)					\
-    SIZE_CLASS(1,	8,	16)					\
-    SIZE_CLASS(2,	16,	32)					\
-    SIZE_CLASS(3,	16,	48)					\
-    SIZE_CLASS(4,	16,	64)					\
-    SIZE_CLASS(5,	16,	80)					\
-    SIZE_CLASS(6,	16,	96)					\
-    SIZE_CLASS(7,	16,	112)					\
-    SIZE_CLASS(8,	16,	128)					\
-    SIZE_CLASS(9,	32,	160)					\
-    SIZE_CLASS(10,	32,	192)					\
-    SIZE_CLASS(11,	32,	224)					\
-    SIZE_CLASS(12,	32,	256)					\
-    SIZE_CLASS(13,	64,	320)					\
-    SIZE_CLASS(14,	64,	384)					\
-    SIZE_CLASS(15,	64,	448)					\
-    SIZE_CLASS(16,	64,	512)					\
-    SIZE_CLASS(17,	128,	640)					\
-    SIZE_CLASS(18,	128,	768)					\
-    SIZE_CLASS(19,	128,	896)					\
-    SIZE_CLASS(20,	128,	1024)					\
-    SIZE_CLASS(21,	256,	1280)					\
-    SIZE_CLASS(22,	256,	1536)					\
-    SIZE_CLASS(23,	256,	1792)					\
-    SIZE_CLASS(24,	256,	2048)					\
-    SIZE_CLASS(25,	512,	2560)					\
-    SIZE_CLASS(26,	512,	3072)					\
-    SIZE_CLASS(27,	512,	3584)					\
-    SIZE_CLASS(28,	512,	4096)					\
-    SIZE_CLASS(29,	1024,	5120)					\
-    SIZE_CLASS(30,	1024,	6144)					\
-    SIZE_CLASS(31,	1024,	7168)					\
-    SIZE_CLASS(32,	1024,	8192)					\
-    SIZE_CLASS(33,	2048,	10240)					\
-    SIZE_CLASS(34,	2048,	12288)					\
-    SIZE_CLASS(35,	2048,	14336)					\
-    SIZE_CLASS(36,	2048,	16384)					\
-    SIZE_CLASS(37,	4096,	20480)					\
-    SIZE_CLASS(38,	4096,	24576)					\
-    SIZE_CLASS(39,	4096,	28672)					\
-    SIZE_CLASS(40,	4096,	32768)					\
-    SIZE_CLASS(41,	8192,	40960)					\
-    SIZE_CLASS(42,	8192,	49152)					\
-    SIZE_CLASS(43,	8192,	57344)					\
+#if (LG_SIZEOF_PTR == 2 && LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      3,        3,      0,  no, yes,   1,  3) \
+    SC(  1,      3,        3,      1,  no, yes,   1,  3) \
+    SC(  2,      3,        3,      2,  no, yes,   3,  3) \
+    SC(  3,      3,        3,      3,  no, yes,   1,  3) \
+                                                         \
+    SC(  4,      5,        3,      1,  no, yes,   5,  3) \
+    SC(  5,      5,        3,      2,  no, yes,   3,  3) \
+    SC(  6,      5,        3,      3,  no, yes,   7,  3) \
+    SC(  7,      5,        3,      4,  no, yes,   1,  3) \
+                                                         \
+    SC(  8,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  9,      6,        4,      2,  no, yes,   3,  4) \
+    SC( 10,      6,        4,      3,  no, yes,   7,  4) \
+    SC( 11,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC( 12,      7,        5,      1,  no, yes,   5,  5) \
+    SC( 13,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 14,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 15,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 16,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 17,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 18,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 19,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 20,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 21,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 22,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 23,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 24,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 25,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 26,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 27,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 28,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 29,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 30,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 31,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 32,     12,       10,      1,  no, yes,   5, no) \
+    SC( 33,     12,       10,      2,  no, yes,   3, no) \
+    SC( 34,     12,       10,      3,  no, yes,   7, no) \
+    SC( 35,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 36,     13,       11,      1,  no, yes,   5, no) \
+    SC( 37,     13,       11,      2, yes, yes,   3, no) \
+    SC( 38,     13,       11,      3,  no, yes,   7, no) \
+    SC( 39,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 40,     14,       12,      1, yes,  no,   0, no) \
+    SC( 41,     14,       12,      2, yes,  no,   0, no) \
+    SC( 42,     14,       12,      3, yes,  no,   0, no) \
+    SC( 43,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 44,     15,       13,      1, yes,  no,   0, no) \
+    SC( 45,     15,       13,      2, yes,  no,   0, no) \
+    SC( 46,     15,       13,      3, yes,  no,   0, no) \
+    SC( 47,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 48,     16,       14,      1, yes,  no,   0, no) \
+    SC( 49,     16,       14,      2, yes,  no,   0, no) \
+    SC( 50,     16,       14,      3, yes,  no,   0, no) \
+    SC( 51,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 52,     17,       15,      1, yes,  no,   0, no) \
+    SC( 53,     17,       15,      2, yes,  no,   0, no) \
+    SC( 54,     17,       15,      3, yes,  no,   0, no) \
+    SC( 55,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 56,     18,       16,      1, yes,  no,   0, no) \
+    SC( 57,     18,       16,      2, yes,  no,   0, no) \
+    SC( 58,     18,       16,      3, yes,  no,   0, no) \
+    SC( 59,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 60,     19,       17,      1, yes,  no,   0, no) \
+    SC( 61,     19,       17,      2, yes,  no,   0, no) \
+    SC( 62,     19,       17,      3, yes,  no,   0, no) \
+    SC( 63,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 64,     20,       18,      1, yes,  no,   0, no) \
+    SC( 65,     20,       18,      2, yes,  no,   0, no) \
+    SC( 66,     20,       18,      3, yes,  no,   0, no) \
+    SC( 67,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 68,     21,       19,      1, yes,  no,   0, no) \
+    SC( 69,     21,       19,      2, yes,  no,   0, no) \
+    SC( 70,     21,       19,      3, yes,  no,   0, no) \
+    SC( 71,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 72,     22,       20,      1, yes,  no,   0, no) \
+    SC( 73,     22,       20,      2, yes,  no,   0, no) \
+    SC( 74,     22,       20,      3, yes,  no,   0, no) \
+    SC( 75,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 76,     23,       21,      1, yes,  no,   0, no) \
+    SC( 77,     23,       21,      2, yes,  no,   0, no) \
+    SC( 78,     23,       21,      3, yes,  no,   0, no) \
+    SC( 79,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 80,     24,       22,      1, yes,  no,   0, no) \
+    SC( 81,     24,       22,      2, yes,  no,   0, no) \
+    SC( 82,     24,       22,      3, yes,  no,   0, no) \
+    SC( 83,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 84,     25,       23,      1, yes,  no,   0, no) \
+    SC( 85,     25,       23,      2, yes,  no,   0, no) \
+    SC( 86,     25,       23,      3, yes,  no,   0, no) \
+    SC( 87,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 88,     26,       24,      1, yes,  no,   0, no) \
+    SC( 89,     26,       24,      2, yes,  no,   0, no) \
+    SC( 90,     26,       24,      3, yes,  no,   0, no) \
+    SC( 91,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 92,     27,       25,      1, yes,  no,   0, no) \
+    SC( 93,     27,       25,      2, yes,  no,   0, no) \
+    SC( 94,     27,       25,      3, yes,  no,   0, no) \
+    SC( 95,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 96,     28,       26,      1, yes,  no,   0, no) \
+    SC( 97,     28,       26,      2, yes,  no,   0, no) \
+    SC( 98,     28,       26,      3, yes,  no,   0, no) \
+    SC( 99,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC(100,     29,       27,      1, yes,  no,   0, no) \
+    SC(101,     29,       27,      2, yes,  no,   0, no) \
+    SC(102,     29,       27,      3, yes,  no,   0, no) \
+    SC(103,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(104,     30,       28,      1, yes,  no,   0, no) \
+    SC(105,     30,       28,      2, yes,  no,   0, no) \
+    SC(106,     30,       28,      3, yes,  no,   0, no) \
 
-#define	NBINS		44
-#define	SMALL_MAXCLASS	57344
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			0
+#define NLBINS			32
+#define NBINS			39
+#define NSIZES			107
+#define LG_CEIL_NSIZES		7
+#define NPSIZES			71
+#define LG_TINY_MAXCLASS	"NA"
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 30) + (((size_t)3) << 28))
 #endif
 
-#if (LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 12)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	16,	16)					\
-    SIZE_CLASS(1,	16,	32)					\
-    SIZE_CLASS(2,	16,	48)					\
-    SIZE_CLASS(3,	16,	64)					\
-    SIZE_CLASS(4,	16,	80)					\
-    SIZE_CLASS(5,	16,	96)					\
-    SIZE_CLASS(6,	16,	112)					\
-    SIZE_CLASS(7,	16,	128)					\
-    SIZE_CLASS(8,	32,	160)					\
-    SIZE_CLASS(9,	32,	192)					\
-    SIZE_CLASS(10,	32,	224)					\
-    SIZE_CLASS(11,	32,	256)					\
-    SIZE_CLASS(12,	64,	320)					\
-    SIZE_CLASS(13,	64,	384)					\
-    SIZE_CLASS(14,	64,	448)					\
-    SIZE_CLASS(15,	64,	512)					\
-    SIZE_CLASS(16,	128,	640)					\
-    SIZE_CLASS(17,	128,	768)					\
-    SIZE_CLASS(18,	128,	896)					\
-    SIZE_CLASS(19,	128,	1024)					\
-    SIZE_CLASS(20,	256,	1280)					\
-    SIZE_CLASS(21,	256,	1536)					\
-    SIZE_CLASS(22,	256,	1792)					\
-    SIZE_CLASS(23,	256,	2048)					\
-    SIZE_CLASS(24,	512,	2560)					\
-    SIZE_CLASS(25,	512,	3072)					\
-    SIZE_CLASS(26,	512,	3584)					\
+#if (LG_SIZEOF_PTR == 2 && LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      3,        3,      0,  no, yes,   1,  3) \
+                                                         \
+    SC(  1,      3,        3,      1,  no, yes,   1,  3) \
+    SC(  2,      4,        4,      1,  no, yes,   1,  4) \
+    SC(  3,      4,        4,      2,  no, yes,   3,  4) \
+    SC(  4,      4,        4,      3,  no, yes,   1,  4) \
+                                                         \
+    SC(  5,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  6,      6,        4,      2,  no, yes,   3,  4) \
+    SC(  7,      6,        4,      3,  no, yes,   7,  4) \
+    SC(  8,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC(  9,      7,        5,      1,  no, yes,   5,  5) \
+    SC( 10,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 11,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 12,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 13,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 14,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 15,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 16,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 17,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 18,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 19,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 20,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 21,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 22,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 23,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 24,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 25,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 26,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 27,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 28,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 29,     12,       10,      1,  no, yes,   5, no) \
+    SC( 30,     12,       10,      2,  no, yes,   3, no) \
+    SC( 31,     12,       10,      3,  no, yes,   7, no) \
+    SC( 32,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 33,     13,       11,      1,  no, yes,   5, no) \
+    SC( 34,     13,       11,      2, yes, yes,   3, no) \
+    SC( 35,     13,       11,      3,  no, yes,   7, no) \
+    SC( 36,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 37,     14,       12,      1, yes,  no,   0, no) \
+    SC( 38,     14,       12,      2, yes,  no,   0, no) \
+    SC( 39,     14,       12,      3, yes,  no,   0, no) \
+    SC( 40,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 41,     15,       13,      1, yes,  no,   0, no) \
+    SC( 42,     15,       13,      2, yes,  no,   0, no) \
+    SC( 43,     15,       13,      3, yes,  no,   0, no) \
+    SC( 44,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 45,     16,       14,      1, yes,  no,   0, no) \
+    SC( 46,     16,       14,      2, yes,  no,   0, no) \
+    SC( 47,     16,       14,      3, yes,  no,   0, no) \
+    SC( 48,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 49,     17,       15,      1, yes,  no,   0, no) \
+    SC( 50,     17,       15,      2, yes,  no,   0, no) \
+    SC( 51,     17,       15,      3, yes,  no,   0, no) \
+    SC( 52,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 53,     18,       16,      1, yes,  no,   0, no) \
+    SC( 54,     18,       16,      2, yes,  no,   0, no) \
+    SC( 55,     18,       16,      3, yes,  no,   0, no) \
+    SC( 56,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 57,     19,       17,      1, yes,  no,   0, no) \
+    SC( 58,     19,       17,      2, yes,  no,   0, no) \
+    SC( 59,     19,       17,      3, yes,  no,   0, no) \
+    SC( 60,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 61,     20,       18,      1, yes,  no,   0, no) \
+    SC( 62,     20,       18,      2, yes,  no,   0, no) \
+    SC( 63,     20,       18,      3, yes,  no,   0, no) \
+    SC( 64,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 65,     21,       19,      1, yes,  no,   0, no) \
+    SC( 66,     21,       19,      2, yes,  no,   0, no) \
+    SC( 67,     21,       19,      3, yes,  no,   0, no) \
+    SC( 68,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 69,     22,       20,      1, yes,  no,   0, no) \
+    SC( 70,     22,       20,      2, yes,  no,   0, no) \
+    SC( 71,     22,       20,      3, yes,  no,   0, no) \
+    SC( 72,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 73,     23,       21,      1, yes,  no,   0, no) \
+    SC( 74,     23,       21,      2, yes,  no,   0, no) \
+    SC( 75,     23,       21,      3, yes,  no,   0, no) \
+    SC( 76,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 77,     24,       22,      1, yes,  no,   0, no) \
+    SC( 78,     24,       22,      2, yes,  no,   0, no) \
+    SC( 79,     24,       22,      3, yes,  no,   0, no) \
+    SC( 80,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 81,     25,       23,      1, yes,  no,   0, no) \
+    SC( 82,     25,       23,      2, yes,  no,   0, no) \
+    SC( 83,     25,       23,      3, yes,  no,   0, no) \
+    SC( 84,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 85,     26,       24,      1, yes,  no,   0, no) \
+    SC( 86,     26,       24,      2, yes,  no,   0, no) \
+    SC( 87,     26,       24,      3, yes,  no,   0, no) \
+    SC( 88,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 89,     27,       25,      1, yes,  no,   0, no) \
+    SC( 90,     27,       25,      2, yes,  no,   0, no) \
+    SC( 91,     27,       25,      3, yes,  no,   0, no) \
+    SC( 92,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 93,     28,       26,      1, yes,  no,   0, no) \
+    SC( 94,     28,       26,      2, yes,  no,   0, no) \
+    SC( 95,     28,       26,      3, yes,  no,   0, no) \
+    SC( 96,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 97,     29,       27,      1, yes,  no,   0, no) \
+    SC( 98,     29,       27,      2, yes,  no,   0, no) \
+    SC( 99,     29,       27,      3, yes,  no,   0, no) \
+    SC(100,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(101,     30,       28,      1, yes,  no,   0, no) \
+    SC(102,     30,       28,      2, yes,  no,   0, no) \
+    SC(103,     30,       28,      3, yes,  no,   0, no) \
 
-#define	NBINS		27
-#define	SMALL_MAXCLASS	3584
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			1
+#define NLBINS			29
+#define NBINS			36
+#define NSIZES			104
+#define LG_CEIL_NSIZES		7
+#define NPSIZES			71
+#define LG_TINY_MAXCLASS	3
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 30) + (((size_t)3) << 28))
 #endif
 
-#if (LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 13)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	16,	16)					\
-    SIZE_CLASS(1,	16,	32)					\
-    SIZE_CLASS(2,	16,	48)					\
-    SIZE_CLASS(3,	16,	64)					\
-    SIZE_CLASS(4,	16,	80)					\
-    SIZE_CLASS(5,	16,	96)					\
-    SIZE_CLASS(6,	16,	112)					\
-    SIZE_CLASS(7,	16,	128)					\
-    SIZE_CLASS(8,	32,	160)					\
-    SIZE_CLASS(9,	32,	192)					\
-    SIZE_CLASS(10,	32,	224)					\
-    SIZE_CLASS(11,	32,	256)					\
-    SIZE_CLASS(12,	64,	320)					\
-    SIZE_CLASS(13,	64,	384)					\
-    SIZE_CLASS(14,	64,	448)					\
-    SIZE_CLASS(15,	64,	512)					\
-    SIZE_CLASS(16,	128,	640)					\
-    SIZE_CLASS(17,	128,	768)					\
-    SIZE_CLASS(18,	128,	896)					\
-    SIZE_CLASS(19,	128,	1024)					\
-    SIZE_CLASS(20,	256,	1280)					\
-    SIZE_CLASS(21,	256,	1536)					\
-    SIZE_CLASS(22,	256,	1792)					\
-    SIZE_CLASS(23,	256,	2048)					\
-    SIZE_CLASS(24,	512,	2560)					\
-    SIZE_CLASS(25,	512,	3072)					\
-    SIZE_CLASS(26,	512,	3584)					\
-    SIZE_CLASS(27,	512,	4096)					\
-    SIZE_CLASS(28,	1024,	5120)					\
-    SIZE_CLASS(29,	1024,	6144)					\
-    SIZE_CLASS(30,	1024,	7168)					\
+#if (LG_SIZEOF_PTR == 2 && LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      4,        4,      0,  no, yes,   1,  4) \
+    SC(  1,      4,        4,      1,  no, yes,   1,  4) \
+    SC(  2,      4,        4,      2,  no, yes,   3,  4) \
+    SC(  3,      4,        4,      3,  no, yes,   1,  4) \
+                                                         \
+    SC(  4,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  5,      6,        4,      2,  no, yes,   3,  4) \
+    SC(  6,      6,        4,      3,  no, yes,   7,  4) \
+    SC(  7,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC(  8,      7,        5,      1,  no, yes,   5,  5) \
+    SC(  9,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 10,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 11,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 12,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 13,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 14,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 15,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 16,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 17,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 18,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 19,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 20,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 21,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 22,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 23,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 24,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 25,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 26,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 27,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 28,     12,       10,      1,  no, yes,   5, no) \
+    SC( 29,     12,       10,      2,  no, yes,   3, no) \
+    SC( 30,     12,       10,      3,  no, yes,   7, no) \
+    SC( 31,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 32,     13,       11,      1,  no, yes,   5, no) \
+    SC( 33,     13,       11,      2, yes, yes,   3, no) \
+    SC( 34,     13,       11,      3,  no, yes,   7, no) \
+    SC( 35,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 36,     14,       12,      1, yes,  no,   0, no) \
+    SC( 37,     14,       12,      2, yes,  no,   0, no) \
+    SC( 38,     14,       12,      3, yes,  no,   0, no) \
+    SC( 39,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 40,     15,       13,      1, yes,  no,   0, no) \
+    SC( 41,     15,       13,      2, yes,  no,   0, no) \
+    SC( 42,     15,       13,      3, yes,  no,   0, no) \
+    SC( 43,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 44,     16,       14,      1, yes,  no,   0, no) \
+    SC( 45,     16,       14,      2, yes,  no,   0, no) \
+    SC( 46,     16,       14,      3, yes,  no,   0, no) \
+    SC( 47,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 48,     17,       15,      1, yes,  no,   0, no) \
+    SC( 49,     17,       15,      2, yes,  no,   0, no) \
+    SC( 50,     17,       15,      3, yes,  no,   0, no) \
+    SC( 51,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 52,     18,       16,      1, yes,  no,   0, no) \
+    SC( 53,     18,       16,      2, yes,  no,   0, no) \
+    SC( 54,     18,       16,      3, yes,  no,   0, no) \
+    SC( 55,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 56,     19,       17,      1, yes,  no,   0, no) \
+    SC( 57,     19,       17,      2, yes,  no,   0, no) \
+    SC( 58,     19,       17,      3, yes,  no,   0, no) \
+    SC( 59,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 60,     20,       18,      1, yes,  no,   0, no) \
+    SC( 61,     20,       18,      2, yes,  no,   0, no) \
+    SC( 62,     20,       18,      3, yes,  no,   0, no) \
+    SC( 63,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 64,     21,       19,      1, yes,  no,   0, no) \
+    SC( 65,     21,       19,      2, yes,  no,   0, no) \
+    SC( 66,     21,       19,      3, yes,  no,   0, no) \
+    SC( 67,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 68,     22,       20,      1, yes,  no,   0, no) \
+    SC( 69,     22,       20,      2, yes,  no,   0, no) \
+    SC( 70,     22,       20,      3, yes,  no,   0, no) \
+    SC( 71,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 72,     23,       21,      1, yes,  no,   0, no) \
+    SC( 73,     23,       21,      2, yes,  no,   0, no) \
+    SC( 74,     23,       21,      3, yes,  no,   0, no) \
+    SC( 75,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 76,     24,       22,      1, yes,  no,   0, no) \
+    SC( 77,     24,       22,      2, yes,  no,   0, no) \
+    SC( 78,     24,       22,      3, yes,  no,   0, no) \
+    SC( 79,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 80,     25,       23,      1, yes,  no,   0, no) \
+    SC( 81,     25,       23,      2, yes,  no,   0, no) \
+    SC( 82,     25,       23,      3, yes,  no,   0, no) \
+    SC( 83,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 84,     26,       24,      1, yes,  no,   0, no) \
+    SC( 85,     26,       24,      2, yes,  no,   0, no) \
+    SC( 86,     26,       24,      3, yes,  no,   0, no) \
+    SC( 87,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 88,     27,       25,      1, yes,  no,   0, no) \
+    SC( 89,     27,       25,      2, yes,  no,   0, no) \
+    SC( 90,     27,       25,      3, yes,  no,   0, no) \
+    SC( 91,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 92,     28,       26,      1, yes,  no,   0, no) \
+    SC( 93,     28,       26,      2, yes,  no,   0, no) \
+    SC( 94,     28,       26,      3, yes,  no,   0, no) \
+    SC( 95,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 96,     29,       27,      1, yes,  no,   0, no) \
+    SC( 97,     29,       27,      2, yes,  no,   0, no) \
+    SC( 98,     29,       27,      3, yes,  no,   0, no) \
+    SC( 99,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(100,     30,       28,      1, yes,  no,   0, no) \
+    SC(101,     30,       28,      2, yes,  no,   0, no) \
+    SC(102,     30,       28,      3, yes,  no,   0, no) \
 
-#define	NBINS		31
-#define	SMALL_MAXCLASS	7168
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			0
+#define NLBINS			28
+#define NBINS			35
+#define NSIZES			103
+#define LG_CEIL_NSIZES		7
+#define NPSIZES			71
+#define LG_TINY_MAXCLASS	"NA"
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 30) + (((size_t)3) << 28))
 #endif
 
-#if (LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 14)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	16,	16)					\
-    SIZE_CLASS(1,	16,	32)					\
-    SIZE_CLASS(2,	16,	48)					\
-    SIZE_CLASS(3,	16,	64)					\
-    SIZE_CLASS(4,	16,	80)					\
-    SIZE_CLASS(5,	16,	96)					\
-    SIZE_CLASS(6,	16,	112)					\
-    SIZE_CLASS(7,	16,	128)					\
-    SIZE_CLASS(8,	32,	160)					\
-    SIZE_CLASS(9,	32,	192)					\
-    SIZE_CLASS(10,	32,	224)					\
-    SIZE_CLASS(11,	32,	256)					\
-    SIZE_CLASS(12,	64,	320)					\
-    SIZE_CLASS(13,	64,	384)					\
-    SIZE_CLASS(14,	64,	448)					\
-    SIZE_CLASS(15,	64,	512)					\
-    SIZE_CLASS(16,	128,	640)					\
-    SIZE_CLASS(17,	128,	768)					\
-    SIZE_CLASS(18,	128,	896)					\
-    SIZE_CLASS(19,	128,	1024)					\
-    SIZE_CLASS(20,	256,	1280)					\
-    SIZE_CLASS(21,	256,	1536)					\
-    SIZE_CLASS(22,	256,	1792)					\
-    SIZE_CLASS(23,	256,	2048)					\
-    SIZE_CLASS(24,	512,	2560)					\
-    SIZE_CLASS(25,	512,	3072)					\
-    SIZE_CLASS(26,	512,	3584)					\
-    SIZE_CLASS(27,	512,	4096)					\
-    SIZE_CLASS(28,	1024,	5120)					\
-    SIZE_CLASS(29,	1024,	6144)					\
-    SIZE_CLASS(30,	1024,	7168)					\
-    SIZE_CLASS(31,	1024,	8192)					\
-    SIZE_CLASS(32,	2048,	10240)					\
-    SIZE_CLASS(33,	2048,	12288)					\
-    SIZE_CLASS(34,	2048,	14336)					\
+#if (LG_SIZEOF_PTR == 3 && LG_TINY_MIN == 3 && LG_QUANTUM == 3 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      3,        3,      0,  no, yes,   1,  3) \
+    SC(  1,      3,        3,      1,  no, yes,   1,  3) \
+    SC(  2,      3,        3,      2,  no, yes,   3,  3) \
+    SC(  3,      3,        3,      3,  no, yes,   1,  3) \
+                                                         \
+    SC(  4,      5,        3,      1,  no, yes,   5,  3) \
+    SC(  5,      5,        3,      2,  no, yes,   3,  3) \
+    SC(  6,      5,        3,      3,  no, yes,   7,  3) \
+    SC(  7,      5,        3,      4,  no, yes,   1,  3) \
+                                                         \
+    SC(  8,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  9,      6,        4,      2,  no, yes,   3,  4) \
+    SC( 10,      6,        4,      3,  no, yes,   7,  4) \
+    SC( 11,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC( 12,      7,        5,      1,  no, yes,   5,  5) \
+    SC( 13,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 14,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 15,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 16,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 17,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 18,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 19,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 20,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 21,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 22,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 23,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 24,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 25,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 26,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 27,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 28,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 29,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 30,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 31,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 32,     12,       10,      1,  no, yes,   5, no) \
+    SC( 33,     12,       10,      2,  no, yes,   3, no) \
+    SC( 34,     12,       10,      3,  no, yes,   7, no) \
+    SC( 35,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 36,     13,       11,      1,  no, yes,   5, no) \
+    SC( 37,     13,       11,      2, yes, yes,   3, no) \
+    SC( 38,     13,       11,      3,  no, yes,   7, no) \
+    SC( 39,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 40,     14,       12,      1, yes,  no,   0, no) \
+    SC( 41,     14,       12,      2, yes,  no,   0, no) \
+    SC( 42,     14,       12,      3, yes,  no,   0, no) \
+    SC( 43,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 44,     15,       13,      1, yes,  no,   0, no) \
+    SC( 45,     15,       13,      2, yes,  no,   0, no) \
+    SC( 46,     15,       13,      3, yes,  no,   0, no) \
+    SC( 47,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 48,     16,       14,      1, yes,  no,   0, no) \
+    SC( 49,     16,       14,      2, yes,  no,   0, no) \
+    SC( 50,     16,       14,      3, yes,  no,   0, no) \
+    SC( 51,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 52,     17,       15,      1, yes,  no,   0, no) \
+    SC( 53,     17,       15,      2, yes,  no,   0, no) \
+    SC( 54,     17,       15,      3, yes,  no,   0, no) \
+    SC( 55,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 56,     18,       16,      1, yes,  no,   0, no) \
+    SC( 57,     18,       16,      2, yes,  no,   0, no) \
+    SC( 58,     18,       16,      3, yes,  no,   0, no) \
+    SC( 59,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 60,     19,       17,      1, yes,  no,   0, no) \
+    SC( 61,     19,       17,      2, yes,  no,   0, no) \
+    SC( 62,     19,       17,      3, yes,  no,   0, no) \
+    SC( 63,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 64,     20,       18,      1, yes,  no,   0, no) \
+    SC( 65,     20,       18,      2, yes,  no,   0, no) \
+    SC( 66,     20,       18,      3, yes,  no,   0, no) \
+    SC( 67,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 68,     21,       19,      1, yes,  no,   0, no) \
+    SC( 69,     21,       19,      2, yes,  no,   0, no) \
+    SC( 70,     21,       19,      3, yes,  no,   0, no) \
+    SC( 71,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 72,     22,       20,      1, yes,  no,   0, no) \
+    SC( 73,     22,       20,      2, yes,  no,   0, no) \
+    SC( 74,     22,       20,      3, yes,  no,   0, no) \
+    SC( 75,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 76,     23,       21,      1, yes,  no,   0, no) \
+    SC( 77,     23,       21,      2, yes,  no,   0, no) \
+    SC( 78,     23,       21,      3, yes,  no,   0, no) \
+    SC( 79,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 80,     24,       22,      1, yes,  no,   0, no) \
+    SC( 81,     24,       22,      2, yes,  no,   0, no) \
+    SC( 82,     24,       22,      3, yes,  no,   0, no) \
+    SC( 83,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 84,     25,       23,      1, yes,  no,   0, no) \
+    SC( 85,     25,       23,      2, yes,  no,   0, no) \
+    SC( 86,     25,       23,      3, yes,  no,   0, no) \
+    SC( 87,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 88,     26,       24,      1, yes,  no,   0, no) \
+    SC( 89,     26,       24,      2, yes,  no,   0, no) \
+    SC( 90,     26,       24,      3, yes,  no,   0, no) \
+    SC( 91,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 92,     27,       25,      1, yes,  no,   0, no) \
+    SC( 93,     27,       25,      2, yes,  no,   0, no) \
+    SC( 94,     27,       25,      3, yes,  no,   0, no) \
+    SC( 95,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 96,     28,       26,      1, yes,  no,   0, no) \
+    SC( 97,     28,       26,      2, yes,  no,   0, no) \
+    SC( 98,     28,       26,      3, yes,  no,   0, no) \
+    SC( 99,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC(100,     29,       27,      1, yes,  no,   0, no) \
+    SC(101,     29,       27,      2, yes,  no,   0, no) \
+    SC(102,     29,       27,      3, yes,  no,   0, no) \
+    SC(103,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(104,     30,       28,      1, yes,  no,   0, no) \
+    SC(105,     30,       28,      2, yes,  no,   0, no) \
+    SC(106,     30,       28,      3, yes,  no,   0, no) \
+    SC(107,     30,       28,      4, yes,  no,   0, no) \
+                                                         \
+    SC(108,     31,       29,      1, yes,  no,   0, no) \
+    SC(109,     31,       29,      2, yes,  no,   0, no) \
+    SC(110,     31,       29,      3, yes,  no,   0, no) \
+    SC(111,     31,       29,      4, yes,  no,   0, no) \
+                                                         \
+    SC(112,     32,       30,      1, yes,  no,   0, no) \
+    SC(113,     32,       30,      2, yes,  no,   0, no) \
+    SC(114,     32,       30,      3, yes,  no,   0, no) \
+    SC(115,     32,       30,      4, yes,  no,   0, no) \
+                                                         \
+    SC(116,     33,       31,      1, yes,  no,   0, no) \
+    SC(117,     33,       31,      2, yes,  no,   0, no) \
+    SC(118,     33,       31,      3, yes,  no,   0, no) \
+    SC(119,     33,       31,      4, yes,  no,   0, no) \
+                                                         \
+    SC(120,     34,       32,      1, yes,  no,   0, no) \
+    SC(121,     34,       32,      2, yes,  no,   0, no) \
+    SC(122,     34,       32,      3, yes,  no,   0, no) \
+    SC(123,     34,       32,      4, yes,  no,   0, no) \
+                                                         \
+    SC(124,     35,       33,      1, yes,  no,   0, no) \
+    SC(125,     35,       33,      2, yes,  no,   0, no) \
+    SC(126,     35,       33,      3, yes,  no,   0, no) \
+    SC(127,     35,       33,      4, yes,  no,   0, no) \
+                                                         \
+    SC(128,     36,       34,      1, yes,  no,   0, no) \
+    SC(129,     36,       34,      2, yes,  no,   0, no) \
+    SC(130,     36,       34,      3, yes,  no,   0, no) \
+    SC(131,     36,       34,      4, yes,  no,   0, no) \
+                                                         \
+    SC(132,     37,       35,      1, yes,  no,   0, no) \
+    SC(133,     37,       35,      2, yes,  no,   0, no) \
+    SC(134,     37,       35,      3, yes,  no,   0, no) \
+    SC(135,     37,       35,      4, yes,  no,   0, no) \
+                                                         \
+    SC(136,     38,       36,      1, yes,  no,   0, no) \
+    SC(137,     38,       36,      2, yes,  no,   0, no) \
+    SC(138,     38,       36,      3, yes,  no,   0, no) \
+    SC(139,     38,       36,      4, yes,  no,   0, no) \
+                                                         \
+    SC(140,     39,       37,      1, yes,  no,   0, no) \
+    SC(141,     39,       37,      2, yes,  no,   0, no) \
+    SC(142,     39,       37,      3, yes,  no,   0, no) \
+    SC(143,     39,       37,      4, yes,  no,   0, no) \
+                                                         \
+    SC(144,     40,       38,      1, yes,  no,   0, no) \
+    SC(145,     40,       38,      2, yes,  no,   0, no) \
+    SC(146,     40,       38,      3, yes,  no,   0, no) \
+    SC(147,     40,       38,      4, yes,  no,   0, no) \
+                                                         \
+    SC(148,     41,       39,      1, yes,  no,   0, no) \
+    SC(149,     41,       39,      2, yes,  no,   0, no) \
+    SC(150,     41,       39,      3, yes,  no,   0, no) \
+    SC(151,     41,       39,      4, yes,  no,   0, no) \
+                                                         \
+    SC(152,     42,       40,      1, yes,  no,   0, no) \
+    SC(153,     42,       40,      2, yes,  no,   0, no) \
+    SC(154,     42,       40,      3, yes,  no,   0, no) \
+    SC(155,     42,       40,      4, yes,  no,   0, no) \
+                                                         \
+    SC(156,     43,       41,      1, yes,  no,   0, no) \
+    SC(157,     43,       41,      2, yes,  no,   0, no) \
+    SC(158,     43,       41,      3, yes,  no,   0, no) \
+    SC(159,     43,       41,      4, yes,  no,   0, no) \
+                                                         \
+    SC(160,     44,       42,      1, yes,  no,   0, no) \
+    SC(161,     44,       42,      2, yes,  no,   0, no) \
+    SC(162,     44,       42,      3, yes,  no,   0, no) \
+    SC(163,     44,       42,      4, yes,  no,   0, no) \
+                                                         \
+    SC(164,     45,       43,      1, yes,  no,   0, no) \
+    SC(165,     45,       43,      2, yes,  no,   0, no) \
+    SC(166,     45,       43,      3, yes,  no,   0, no) \
+    SC(167,     45,       43,      4, yes,  no,   0, no) \
+                                                         \
+    SC(168,     46,       44,      1, yes,  no,   0, no) \
+    SC(169,     46,       44,      2, yes,  no,   0, no) \
+    SC(170,     46,       44,      3, yes,  no,   0, no) \
+    SC(171,     46,       44,      4, yes,  no,   0, no) \
+                                                         \
+    SC(172,     47,       45,      1, yes,  no,   0, no) \
+    SC(173,     47,       45,      2, yes,  no,   0, no) \
+    SC(174,     47,       45,      3, yes,  no,   0, no) \
+    SC(175,     47,       45,      4, yes,  no,   0, no) \
+                                                         \
+    SC(176,     48,       46,      1, yes,  no,   0, no) \
+    SC(177,     48,       46,      2, yes,  no,   0, no) \
+    SC(178,     48,       46,      3, yes,  no,   0, no) \
+    SC(179,     48,       46,      4, yes,  no,   0, no) \
+                                                         \
+    SC(180,     49,       47,      1, yes,  no,   0, no) \
+    SC(181,     49,       47,      2, yes,  no,   0, no) \
+    SC(182,     49,       47,      3, yes,  no,   0, no) \
+    SC(183,     49,       47,      4, yes,  no,   0, no) \
+                                                         \
+    SC(184,     50,       48,      1, yes,  no,   0, no) \
+    SC(185,     50,       48,      2, yes,  no,   0, no) \
+    SC(186,     50,       48,      3, yes,  no,   0, no) \
+    SC(187,     50,       48,      4, yes,  no,   0, no) \
+                                                         \
+    SC(188,     51,       49,      1, yes,  no,   0, no) \
+    SC(189,     51,       49,      2, yes,  no,   0, no) \
+    SC(190,     51,       49,      3, yes,  no,   0, no) \
+    SC(191,     51,       49,      4, yes,  no,   0, no) \
+                                                         \
+    SC(192,     52,       50,      1, yes,  no,   0, no) \
+    SC(193,     52,       50,      2, yes,  no,   0, no) \
+    SC(194,     52,       50,      3, yes,  no,   0, no) \
+    SC(195,     52,       50,      4, yes,  no,   0, no) \
+                                                         \
+    SC(196,     53,       51,      1, yes,  no,   0, no) \
+    SC(197,     53,       51,      2, yes,  no,   0, no) \
+    SC(198,     53,       51,      3, yes,  no,   0, no) \
+    SC(199,     53,       51,      4, yes,  no,   0, no) \
+                                                         \
+    SC(200,     54,       52,      1, yes,  no,   0, no) \
+    SC(201,     54,       52,      2, yes,  no,   0, no) \
+    SC(202,     54,       52,      3, yes,  no,   0, no) \
+    SC(203,     54,       52,      4, yes,  no,   0, no) \
+                                                         \
+    SC(204,     55,       53,      1, yes,  no,   0, no) \
+    SC(205,     55,       53,      2, yes,  no,   0, no) \
+    SC(206,     55,       53,      3, yes,  no,   0, no) \
+    SC(207,     55,       53,      4, yes,  no,   0, no) \
+                                                         \
+    SC(208,     56,       54,      1, yes,  no,   0, no) \
+    SC(209,     56,       54,      2, yes,  no,   0, no) \
+    SC(210,     56,       54,      3, yes,  no,   0, no) \
+    SC(211,     56,       54,      4, yes,  no,   0, no) \
+                                                         \
+    SC(212,     57,       55,      1, yes,  no,   0, no) \
+    SC(213,     57,       55,      2, yes,  no,   0, no) \
+    SC(214,     57,       55,      3, yes,  no,   0, no) \
+    SC(215,     57,       55,      4, yes,  no,   0, no) \
+                                                         \
+    SC(216,     58,       56,      1, yes,  no,   0, no) \
+    SC(217,     58,       56,      2, yes,  no,   0, no) \
+    SC(218,     58,       56,      3, yes,  no,   0, no) \
+    SC(219,     58,       56,      4, yes,  no,   0, no) \
+                                                         \
+    SC(220,     59,       57,      1, yes,  no,   0, no) \
+    SC(221,     59,       57,      2, yes,  no,   0, no) \
+    SC(222,     59,       57,      3, yes,  no,   0, no) \
+    SC(223,     59,       57,      4, yes,  no,   0, no) \
+                                                         \
+    SC(224,     60,       58,      1, yes,  no,   0, no) \
+    SC(225,     60,       58,      2, yes,  no,   0, no) \
+    SC(226,     60,       58,      3, yes,  no,   0, no) \
+    SC(227,     60,       58,      4, yes,  no,   0, no) \
+                                                         \
+    SC(228,     61,       59,      1, yes,  no,   0, no) \
+    SC(229,     61,       59,      2, yes,  no,   0, no) \
+    SC(230,     61,       59,      3, yes,  no,   0, no) \
+    SC(231,     61,       59,      4, yes,  no,   0, no) \
+                                                         \
+    SC(232,     62,       60,      1, yes,  no,   0, no) \
+    SC(233,     62,       60,      2, yes,  no,   0, no) \
+    SC(234,     62,       60,      3, yes,  no,   0, no) \
 
-#define	NBINS		35
-#define	SMALL_MAXCLASS	14336
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			0
+#define NLBINS			32
+#define NBINS			39
+#define NSIZES			235
+#define LG_CEIL_NSIZES		8
+#define NPSIZES			199
+#define LG_TINY_MAXCLASS	"NA"
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 62) + (((size_t)3) << 60))
 #endif
 
-#if (LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 15)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	16,	16)					\
-    SIZE_CLASS(1,	16,	32)					\
-    SIZE_CLASS(2,	16,	48)					\
-    SIZE_CLASS(3,	16,	64)					\
-    SIZE_CLASS(4,	16,	80)					\
-    SIZE_CLASS(5,	16,	96)					\
-    SIZE_CLASS(6,	16,	112)					\
-    SIZE_CLASS(7,	16,	128)					\
-    SIZE_CLASS(8,	32,	160)					\
-    SIZE_CLASS(9,	32,	192)					\
-    SIZE_CLASS(10,	32,	224)					\
-    SIZE_CLASS(11,	32,	256)					\
-    SIZE_CLASS(12,	64,	320)					\
-    SIZE_CLASS(13,	64,	384)					\
-    SIZE_CLASS(14,	64,	448)					\
-    SIZE_CLASS(15,	64,	512)					\
-    SIZE_CLASS(16,	128,	640)					\
-    SIZE_CLASS(17,	128,	768)					\
-    SIZE_CLASS(18,	128,	896)					\
-    SIZE_CLASS(19,	128,	1024)					\
-    SIZE_CLASS(20,	256,	1280)					\
-    SIZE_CLASS(21,	256,	1536)					\
-    SIZE_CLASS(22,	256,	1792)					\
-    SIZE_CLASS(23,	256,	2048)					\
-    SIZE_CLASS(24,	512,	2560)					\
-    SIZE_CLASS(25,	512,	3072)					\
-    SIZE_CLASS(26,	512,	3584)					\
-    SIZE_CLASS(27,	512,	4096)					\
-    SIZE_CLASS(28,	1024,	5120)					\
-    SIZE_CLASS(29,	1024,	6144)					\
-    SIZE_CLASS(30,	1024,	7168)					\
-    SIZE_CLASS(31,	1024,	8192)					\
-    SIZE_CLASS(32,	2048,	10240)					\
-    SIZE_CLASS(33,	2048,	12288)					\
-    SIZE_CLASS(34,	2048,	14336)					\
-    SIZE_CLASS(35,	2048,	16384)					\
-    SIZE_CLASS(36,	4096,	20480)					\
-    SIZE_CLASS(37,	4096,	24576)					\
-    SIZE_CLASS(38,	4096,	28672)					\
+#if (LG_SIZEOF_PTR == 3 && LG_TINY_MIN == 3 && LG_QUANTUM == 4 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      3,        3,      0,  no, yes,   1,  3) \
+                                                         \
+    SC(  1,      3,        3,      1,  no, yes,   1,  3) \
+    SC(  2,      4,        4,      1,  no, yes,   1,  4) \
+    SC(  3,      4,        4,      2,  no, yes,   3,  4) \
+    SC(  4,      4,        4,      3,  no, yes,   1,  4) \
+                                                         \
+    SC(  5,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  6,      6,        4,      2,  no, yes,   3,  4) \
+    SC(  7,      6,        4,      3,  no, yes,   7,  4) \
+    SC(  8,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC(  9,      7,        5,      1,  no, yes,   5,  5) \
+    SC( 10,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 11,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 12,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 13,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 14,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 15,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 16,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 17,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 18,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 19,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 20,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 21,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 22,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 23,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 24,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 25,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 26,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 27,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 28,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 29,     12,       10,      1,  no, yes,   5, no) \
+    SC( 30,     12,       10,      2,  no, yes,   3, no) \
+    SC( 31,     12,       10,      3,  no, yes,   7, no) \
+    SC( 32,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 33,     13,       11,      1,  no, yes,   5, no) \
+    SC( 34,     13,       11,      2, yes, yes,   3, no) \
+    SC( 35,     13,       11,      3,  no, yes,   7, no) \
+    SC( 36,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 37,     14,       12,      1, yes,  no,   0, no) \
+    SC( 38,     14,       12,      2, yes,  no,   0, no) \
+    SC( 39,     14,       12,      3, yes,  no,   0, no) \
+    SC( 40,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 41,     15,       13,      1, yes,  no,   0, no) \
+    SC( 42,     15,       13,      2, yes,  no,   0, no) \
+    SC( 43,     15,       13,      3, yes,  no,   0, no) \
+    SC( 44,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 45,     16,       14,      1, yes,  no,   0, no) \
+    SC( 46,     16,       14,      2, yes,  no,   0, no) \
+    SC( 47,     16,       14,      3, yes,  no,   0, no) \
+    SC( 48,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 49,     17,       15,      1, yes,  no,   0, no) \
+    SC( 50,     17,       15,      2, yes,  no,   0, no) \
+    SC( 51,     17,       15,      3, yes,  no,   0, no) \
+    SC( 52,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 53,     18,       16,      1, yes,  no,   0, no) \
+    SC( 54,     18,       16,      2, yes,  no,   0, no) \
+    SC( 55,     18,       16,      3, yes,  no,   0, no) \
+    SC( 56,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 57,     19,       17,      1, yes,  no,   0, no) \
+    SC( 58,     19,       17,      2, yes,  no,   0, no) \
+    SC( 59,     19,       17,      3, yes,  no,   0, no) \
+    SC( 60,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 61,     20,       18,      1, yes,  no,   0, no) \
+    SC( 62,     20,       18,      2, yes,  no,   0, no) \
+    SC( 63,     20,       18,      3, yes,  no,   0, no) \
+    SC( 64,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 65,     21,       19,      1, yes,  no,   0, no) \
+    SC( 66,     21,       19,      2, yes,  no,   0, no) \
+    SC( 67,     21,       19,      3, yes,  no,   0, no) \
+    SC( 68,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 69,     22,       20,      1, yes,  no,   0, no) \
+    SC( 70,     22,       20,      2, yes,  no,   0, no) \
+    SC( 71,     22,       20,      3, yes,  no,   0, no) \
+    SC( 72,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 73,     23,       21,      1, yes,  no,   0, no) \
+    SC( 74,     23,       21,      2, yes,  no,   0, no) \
+    SC( 75,     23,       21,      3, yes,  no,   0, no) \
+    SC( 76,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 77,     24,       22,      1, yes,  no,   0, no) \
+    SC( 78,     24,       22,      2, yes,  no,   0, no) \
+    SC( 79,     24,       22,      3, yes,  no,   0, no) \
+    SC( 80,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 81,     25,       23,      1, yes,  no,   0, no) \
+    SC( 82,     25,       23,      2, yes,  no,   0, no) \
+    SC( 83,     25,       23,      3, yes,  no,   0, no) \
+    SC( 84,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 85,     26,       24,      1, yes,  no,   0, no) \
+    SC( 86,     26,       24,      2, yes,  no,   0, no) \
+    SC( 87,     26,       24,      3, yes,  no,   0, no) \
+    SC( 88,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 89,     27,       25,      1, yes,  no,   0, no) \
+    SC( 90,     27,       25,      2, yes,  no,   0, no) \
+    SC( 91,     27,       25,      3, yes,  no,   0, no) \
+    SC( 92,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 93,     28,       26,      1, yes,  no,   0, no) \
+    SC( 94,     28,       26,      2, yes,  no,   0, no) \
+    SC( 95,     28,       26,      3, yes,  no,   0, no) \
+    SC( 96,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 97,     29,       27,      1, yes,  no,   0, no) \
+    SC( 98,     29,       27,      2, yes,  no,   0, no) \
+    SC( 99,     29,       27,      3, yes,  no,   0, no) \
+    SC(100,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(101,     30,       28,      1, yes,  no,   0, no) \
+    SC(102,     30,       28,      2, yes,  no,   0, no) \
+    SC(103,     30,       28,      3, yes,  no,   0, no) \
+    SC(104,     30,       28,      4, yes,  no,   0, no) \
+                                                         \
+    SC(105,     31,       29,      1, yes,  no,   0, no) \
+    SC(106,     31,       29,      2, yes,  no,   0, no) \
+    SC(107,     31,       29,      3, yes,  no,   0, no) \
+    SC(108,     31,       29,      4, yes,  no,   0, no) \
+                                                         \
+    SC(109,     32,       30,      1, yes,  no,   0, no) \
+    SC(110,     32,       30,      2, yes,  no,   0, no) \
+    SC(111,     32,       30,      3, yes,  no,   0, no) \
+    SC(112,     32,       30,      4, yes,  no,   0, no) \
+                                                         \
+    SC(113,     33,       31,      1, yes,  no,   0, no) \
+    SC(114,     33,       31,      2, yes,  no,   0, no) \
+    SC(115,     33,       31,      3, yes,  no,   0, no) \
+    SC(116,     33,       31,      4, yes,  no,   0, no) \
+                                                         \
+    SC(117,     34,       32,      1, yes,  no,   0, no) \
+    SC(118,     34,       32,      2, yes,  no,   0, no) \
+    SC(119,     34,       32,      3, yes,  no,   0, no) \
+    SC(120,     34,       32,      4, yes,  no,   0, no) \
+                                                         \
+    SC(121,     35,       33,      1, yes,  no,   0, no) \
+    SC(122,     35,       33,      2, yes,  no,   0, no) \
+    SC(123,     35,       33,      3, yes,  no,   0, no) \
+    SC(124,     35,       33,      4, yes,  no,   0, no) \
+                                                         \
+    SC(125,     36,       34,      1, yes,  no,   0, no) \
+    SC(126,     36,       34,      2, yes,  no,   0, no) \
+    SC(127,     36,       34,      3, yes,  no,   0, no) \
+    SC(128,     36,       34,      4, yes,  no,   0, no) \
+                                                         \
+    SC(129,     37,       35,      1, yes,  no,   0, no) \
+    SC(130,     37,       35,      2, yes,  no,   0, no) \
+    SC(131,     37,       35,      3, yes,  no,   0, no) \
+    SC(132,     37,       35,      4, yes,  no,   0, no) \
+                                                         \
+    SC(133,     38,       36,      1, yes,  no,   0, no) \
+    SC(134,     38,       36,      2, yes,  no,   0, no) \
+    SC(135,     38,       36,      3, yes,  no,   0, no) \
+    SC(136,     38,       36,      4, yes,  no,   0, no) \
+                                                         \
+    SC(137,     39,       37,      1, yes,  no,   0, no) \
+    SC(138,     39,       37,      2, yes,  no,   0, no) \
+    SC(139,     39,       37,      3, yes,  no,   0, no) \
+    SC(140,     39,       37,      4, yes,  no,   0, no) \
+                                                         \
+    SC(141,     40,       38,      1, yes,  no,   0, no) \
+    SC(142,     40,       38,      2, yes,  no,   0, no) \
+    SC(143,     40,       38,      3, yes,  no,   0, no) \
+    SC(144,     40,       38,      4, yes,  no,   0, no) \
+                                                         \
+    SC(145,     41,       39,      1, yes,  no,   0, no) \
+    SC(146,     41,       39,      2, yes,  no,   0, no) \
+    SC(147,     41,       39,      3, yes,  no,   0, no) \
+    SC(148,     41,       39,      4, yes,  no,   0, no) \
+                                                         \
+    SC(149,     42,       40,      1, yes,  no,   0, no) \
+    SC(150,     42,       40,      2, yes,  no,   0, no) \
+    SC(151,     42,       40,      3, yes,  no,   0, no) \
+    SC(152,     42,       40,      4, yes,  no,   0, no) \
+                                                         \
+    SC(153,     43,       41,      1, yes,  no,   0, no) \
+    SC(154,     43,       41,      2, yes,  no,   0, no) \
+    SC(155,     43,       41,      3, yes,  no,   0, no) \
+    SC(156,     43,       41,      4, yes,  no,   0, no) \
+                                                         \
+    SC(157,     44,       42,      1, yes,  no,   0, no) \
+    SC(158,     44,       42,      2, yes,  no,   0, no) \
+    SC(159,     44,       42,      3, yes,  no,   0, no) \
+    SC(160,     44,       42,      4, yes,  no,   0, no) \
+                                                         \
+    SC(161,     45,       43,      1, yes,  no,   0, no) \
+    SC(162,     45,       43,      2, yes,  no,   0, no) \
+    SC(163,     45,       43,      3, yes,  no,   0, no) \
+    SC(164,     45,       43,      4, yes,  no,   0, no) \
+                                                         \
+    SC(165,     46,       44,      1, yes,  no,   0, no) \
+    SC(166,     46,       44,      2, yes,  no,   0, no) \
+    SC(167,     46,       44,      3, yes,  no,   0, no) \
+    SC(168,     46,       44,      4, yes,  no,   0, no) \
+                                                         \
+    SC(169,     47,       45,      1, yes,  no,   0, no) \
+    SC(170,     47,       45,      2, yes,  no,   0, no) \
+    SC(171,     47,       45,      3, yes,  no,   0, no) \
+    SC(172,     47,       45,      4, yes,  no,   0, no) \
+                                                         \
+    SC(173,     48,       46,      1, yes,  no,   0, no) \
+    SC(174,     48,       46,      2, yes,  no,   0, no) \
+    SC(175,     48,       46,      3, yes,  no,   0, no) \
+    SC(176,     48,       46,      4, yes,  no,   0, no) \
+                                                         \
+    SC(177,     49,       47,      1, yes,  no,   0, no) \
+    SC(178,     49,       47,      2, yes,  no,   0, no) \
+    SC(179,     49,       47,      3, yes,  no,   0, no) \
+    SC(180,     49,       47,      4, yes,  no,   0, no) \
+                                                         \
+    SC(181,     50,       48,      1, yes,  no,   0, no) \
+    SC(182,     50,       48,      2, yes,  no,   0, no) \
+    SC(183,     50,       48,      3, yes,  no,   0, no) \
+    SC(184,     50,       48,      4, yes,  no,   0, no) \
+                                                         \
+    SC(185,     51,       49,      1, yes,  no,   0, no) \
+    SC(186,     51,       49,      2, yes,  no,   0, no) \
+    SC(187,     51,       49,      3, yes,  no,   0, no) \
+    SC(188,     51,       49,      4, yes,  no,   0, no) \
+                                                         \
+    SC(189,     52,       50,      1, yes,  no,   0, no) \
+    SC(190,     52,       50,      2, yes,  no,   0, no) \
+    SC(191,     52,       50,      3, yes,  no,   0, no) \
+    SC(192,     52,       50,      4, yes,  no,   0, no) \
+                                                         \
+    SC(193,     53,       51,      1, yes,  no,   0, no) \
+    SC(194,     53,       51,      2, yes,  no,   0, no) \
+    SC(195,     53,       51,      3, yes,  no,   0, no) \
+    SC(196,     53,       51,      4, yes,  no,   0, no) \
+                                                         \
+    SC(197,     54,       52,      1, yes,  no,   0, no) \
+    SC(198,     54,       52,      2, yes,  no,   0, no) \
+    SC(199,     54,       52,      3, yes,  no,   0, no) \
+    SC(200,     54,       52,      4, yes,  no,   0, no) \
+                                                         \
+    SC(201,     55,       53,      1, yes,  no,   0, no) \
+    SC(202,     55,       53,      2, yes,  no,   0, no) \
+    SC(203,     55,       53,      3, yes,  no,   0, no) \
+    SC(204,     55,       53,      4, yes,  no,   0, no) \
+                                                         \
+    SC(205,     56,       54,      1, yes,  no,   0, no) \
+    SC(206,     56,       54,      2, yes,  no,   0, no) \
+    SC(207,     56,       54,      3, yes,  no,   0, no) \
+    SC(208,     56,       54,      4, yes,  no,   0, no) \
+                                                         \
+    SC(209,     57,       55,      1, yes,  no,   0, no) \
+    SC(210,     57,       55,      2, yes,  no,   0, no) \
+    SC(211,     57,       55,      3, yes,  no,   0, no) \
+    SC(212,     57,       55,      4, yes,  no,   0, no) \
+                                                         \
+    SC(213,     58,       56,      1, yes,  no,   0, no) \
+    SC(214,     58,       56,      2, yes,  no,   0, no) \
+    SC(215,     58,       56,      3, yes,  no,   0, no) \
+    SC(216,     58,       56,      4, yes,  no,   0, no) \
+                                                         \
+    SC(217,     59,       57,      1, yes,  no,   0, no) \
+    SC(218,     59,       57,      2, yes,  no,   0, no) \
+    SC(219,     59,       57,      3, yes,  no,   0, no) \
+    SC(220,     59,       57,      4, yes,  no,   0, no) \
+                                                         \
+    SC(221,     60,       58,      1, yes,  no,   0, no) \
+    SC(222,     60,       58,      2, yes,  no,   0, no) \
+    SC(223,     60,       58,      3, yes,  no,   0, no) \
+    SC(224,     60,       58,      4, yes,  no,   0, no) \
+                                                         \
+    SC(225,     61,       59,      1, yes,  no,   0, no) \
+    SC(226,     61,       59,      2, yes,  no,   0, no) \
+    SC(227,     61,       59,      3, yes,  no,   0, no) \
+    SC(228,     61,       59,      4, yes,  no,   0, no) \
+                                                         \
+    SC(229,     62,       60,      1, yes,  no,   0, no) \
+    SC(230,     62,       60,      2, yes,  no,   0, no) \
+    SC(231,     62,       60,      3, yes,  no,   0, no) \
 
-#define	NBINS		39
-#define	SMALL_MAXCLASS	28672
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			1
+#define NLBINS			29
+#define NBINS			36
+#define NSIZES			232
+#define LG_CEIL_NSIZES		8
+#define NPSIZES			199
+#define LG_TINY_MAXCLASS	3
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 62) + (((size_t)3) << 60))
 #endif
 
-#if (LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 16)
-#define	SIZE_CLASSES_DEFINED
-/*  SIZE_CLASS(bin,	delta,	sz) */
-#define	SIZE_CLASSES							\
-    SIZE_CLASS(0,	16,	16)					\
-    SIZE_CLASS(1,	16,	32)					\
-    SIZE_CLASS(2,	16,	48)					\
-    SIZE_CLASS(3,	16,	64)					\
-    SIZE_CLASS(4,	16,	80)					\
-    SIZE_CLASS(5,	16,	96)					\
-    SIZE_CLASS(6,	16,	112)					\
-    SIZE_CLASS(7,	16,	128)					\
-    SIZE_CLASS(8,	32,	160)					\
-    SIZE_CLASS(9,	32,	192)					\
-    SIZE_CLASS(10,	32,	224)					\
-    SIZE_CLASS(11,	32,	256)					\
-    SIZE_CLASS(12,	64,	320)					\
-    SIZE_CLASS(13,	64,	384)					\
-    SIZE_CLASS(14,	64,	448)					\
-    SIZE_CLASS(15,	64,	512)					\
-    SIZE_CLASS(16,	128,	640)					\
-    SIZE_CLASS(17,	128,	768)					\
-    SIZE_CLASS(18,	128,	896)					\
-    SIZE_CLASS(19,	128,	1024)					\
-    SIZE_CLASS(20,	256,	1280)					\
-    SIZE_CLASS(21,	256,	1536)					\
-    SIZE_CLASS(22,	256,	1792)					\
-    SIZE_CLASS(23,	256,	2048)					\
-    SIZE_CLASS(24,	512,	2560)					\
-    SIZE_CLASS(25,	512,	3072)					\
-    SIZE_CLASS(26,	512,	3584)					\
-    SIZE_CLASS(27,	512,	4096)					\
-    SIZE_CLASS(28,	1024,	5120)					\
-    SIZE_CLASS(29,	1024,	6144)					\
-    SIZE_CLASS(30,	1024,	7168)					\
-    SIZE_CLASS(31,	1024,	8192)					\
-    SIZE_CLASS(32,	2048,	10240)					\
-    SIZE_CLASS(33,	2048,	12288)					\
-    SIZE_CLASS(34,	2048,	14336)					\
-    SIZE_CLASS(35,	2048,	16384)					\
-    SIZE_CLASS(36,	4096,	20480)					\
-    SIZE_CLASS(37,	4096,	24576)					\
-    SIZE_CLASS(38,	4096,	28672)					\
-    SIZE_CLASS(39,	4096,	32768)					\
-    SIZE_CLASS(40,	8192,	40960)					\
-    SIZE_CLASS(41,	8192,	49152)					\
-    SIZE_CLASS(42,	8192,	57344)					\
+#if (LG_SIZEOF_PTR == 3 && LG_TINY_MIN == 4 && LG_QUANTUM == 4 && LG_PAGE == 12)
+#define SIZE_CLASSES \
+  /* index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup */ \
+    SC(  0,      4,        4,      0,  no, yes,   1,  4) \
+    SC(  1,      4,        4,      1,  no, yes,   1,  4) \
+    SC(  2,      4,        4,      2,  no, yes,   3,  4) \
+    SC(  3,      4,        4,      3,  no, yes,   1,  4) \
+                                                         \
+    SC(  4,      6,        4,      1,  no, yes,   5,  4) \
+    SC(  5,      6,        4,      2,  no, yes,   3,  4) \
+    SC(  6,      6,        4,      3,  no, yes,   7,  4) \
+    SC(  7,      6,        4,      4,  no, yes,   1,  4) \
+                                                         \
+    SC(  8,      7,        5,      1,  no, yes,   5,  5) \
+    SC(  9,      7,        5,      2,  no, yes,   3,  5) \
+    SC( 10,      7,        5,      3,  no, yes,   7,  5) \
+    SC( 11,      7,        5,      4,  no, yes,   1,  5) \
+                                                         \
+    SC( 12,      8,        6,      1,  no, yes,   5,  6) \
+    SC( 13,      8,        6,      2,  no, yes,   3,  6) \
+    SC( 14,      8,        6,      3,  no, yes,   7,  6) \
+    SC( 15,      8,        6,      4,  no, yes,   1,  6) \
+                                                         \
+    SC( 16,      9,        7,      1,  no, yes,   5,  7) \
+    SC( 17,      9,        7,      2,  no, yes,   3,  7) \
+    SC( 18,      9,        7,      3,  no, yes,   7,  7) \
+    SC( 19,      9,        7,      4,  no, yes,   1,  7) \
+                                                         \
+    SC( 20,     10,        8,      1,  no, yes,   5,  8) \
+    SC( 21,     10,        8,      2,  no, yes,   3,  8) \
+    SC( 22,     10,        8,      3,  no, yes,   7,  8) \
+    SC( 23,     10,        8,      4,  no, yes,   1,  8) \
+                                                         \
+    SC( 24,     11,        9,      1,  no, yes,   5,  9) \
+    SC( 25,     11,        9,      2,  no, yes,   3,  9) \
+    SC( 26,     11,        9,      3,  no, yes,   7,  9) \
+    SC( 27,     11,        9,      4, yes, yes,   1,  9) \
+                                                         \
+    SC( 28,     12,       10,      1,  no, yes,   5, no) \
+    SC( 29,     12,       10,      2,  no, yes,   3, no) \
+    SC( 30,     12,       10,      3,  no, yes,   7, no) \
+    SC( 31,     12,       10,      4, yes, yes,   2, no) \
+                                                         \
+    SC( 32,     13,       11,      1,  no, yes,   5, no) \
+    SC( 33,     13,       11,      2, yes, yes,   3, no) \
+    SC( 34,     13,       11,      3,  no, yes,   7, no) \
+    SC( 35,     13,       11,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 36,     14,       12,      1, yes,  no,   0, no) \
+    SC( 37,     14,       12,      2, yes,  no,   0, no) \
+    SC( 38,     14,       12,      3, yes,  no,   0, no) \
+    SC( 39,     14,       12,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 40,     15,       13,      1, yes,  no,   0, no) \
+    SC( 41,     15,       13,      2, yes,  no,   0, no) \
+    SC( 42,     15,       13,      3, yes,  no,   0, no) \
+    SC( 43,     15,       13,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 44,     16,       14,      1, yes,  no,   0, no) \
+    SC( 45,     16,       14,      2, yes,  no,   0, no) \
+    SC( 46,     16,       14,      3, yes,  no,   0, no) \
+    SC( 47,     16,       14,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 48,     17,       15,      1, yes,  no,   0, no) \
+    SC( 49,     17,       15,      2, yes,  no,   0, no) \
+    SC( 50,     17,       15,      3, yes,  no,   0, no) \
+    SC( 51,     17,       15,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 52,     18,       16,      1, yes,  no,   0, no) \
+    SC( 53,     18,       16,      2, yes,  no,   0, no) \
+    SC( 54,     18,       16,      3, yes,  no,   0, no) \
+    SC( 55,     18,       16,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 56,     19,       17,      1, yes,  no,   0, no) \
+    SC( 57,     19,       17,      2, yes,  no,   0, no) \
+    SC( 58,     19,       17,      3, yes,  no,   0, no) \
+    SC( 59,     19,       17,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 60,     20,       18,      1, yes,  no,   0, no) \
+    SC( 61,     20,       18,      2, yes,  no,   0, no) \
+    SC( 62,     20,       18,      3, yes,  no,   0, no) \
+    SC( 63,     20,       18,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 64,     21,       19,      1, yes,  no,   0, no) \
+    SC( 65,     21,       19,      2, yes,  no,   0, no) \
+    SC( 66,     21,       19,      3, yes,  no,   0, no) \
+    SC( 67,     21,       19,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 68,     22,       20,      1, yes,  no,   0, no) \
+    SC( 69,     22,       20,      2, yes,  no,   0, no) \
+    SC( 70,     22,       20,      3, yes,  no,   0, no) \
+    SC( 71,     22,       20,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 72,     23,       21,      1, yes,  no,   0, no) \
+    SC( 73,     23,       21,      2, yes,  no,   0, no) \
+    SC( 74,     23,       21,      3, yes,  no,   0, no) \
+    SC( 75,     23,       21,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 76,     24,       22,      1, yes,  no,   0, no) \
+    SC( 77,     24,       22,      2, yes,  no,   0, no) \
+    SC( 78,     24,       22,      3, yes,  no,   0, no) \
+    SC( 79,     24,       22,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 80,     25,       23,      1, yes,  no,   0, no) \
+    SC( 81,     25,       23,      2, yes,  no,   0, no) \
+    SC( 82,     25,       23,      3, yes,  no,   0, no) \
+    SC( 83,     25,       23,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 84,     26,       24,      1, yes,  no,   0, no) \
+    SC( 85,     26,       24,      2, yes,  no,   0, no) \
+    SC( 86,     26,       24,      3, yes,  no,   0, no) \
+    SC( 87,     26,       24,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 88,     27,       25,      1, yes,  no,   0, no) \
+    SC( 89,     27,       25,      2, yes,  no,   0, no) \
+    SC( 90,     27,       25,      3, yes,  no,   0, no) \
+    SC( 91,     27,       25,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 92,     28,       26,      1, yes,  no,   0, no) \
+    SC( 93,     28,       26,      2, yes,  no,   0, no) \
+    SC( 94,     28,       26,      3, yes,  no,   0, no) \
+    SC( 95,     28,       26,      4, yes,  no,   0, no) \
+                                                         \
+    SC( 96,     29,       27,      1, yes,  no,   0, no) \
+    SC( 97,     29,       27,      2, yes,  no,   0, no) \
+    SC( 98,     29,       27,      3, yes,  no,   0, no) \
+    SC( 99,     29,       27,      4, yes,  no,   0, no) \
+                                                         \
+    SC(100,     30,       28,      1, yes,  no,   0, no) \
+    SC(101,     30,       28,      2, yes,  no,   0, no) \
+    SC(102,     30,       28,      3, yes,  no,   0, no) \
+    SC(103,     30,       28,      4, yes,  no,   0, no) \
+                                                         \
+    SC(104,     31,       29,      1, yes,  no,   0, no) \
+    SC(105,     31,       29,      2, yes,  no,   0, no) \
+    SC(106,     31,       29,      3, yes,  no,   0, no) \
+    SC(107,     31,       29,      4, yes,  no,   0, no) \
+                                                         \
+    SC(108,     32,       30,      1, yes,  no,   0, no) \
+    SC(109,     32,       30,      2, yes,  no,   0, no) \
+    SC(110,     32,       30,      3, yes,  no,   0, no) \
+    SC(111,     32,       30,      4, yes,  no,   0, no) \
+                                                         \
+    SC(112,     33,       31,      1, yes,  no,   0, no) \
+    SC(113,     33,       31,      2, yes,  no,   0, no) \
+    SC(114,     33,       31,      3, yes,  no,   0, no) \
+    SC(115,     33,       31,      4, yes,  no,   0, no) \
+                                                         \
+    SC(116,     34,       32,      1, yes,  no,   0, no) \
+    SC(117,     34,       32,      2, yes,  no,   0, no) \
+    SC(118,     34,       32,      3, yes,  no,   0, no) \
+    SC(119,     34,       32,      4, yes,  no,   0, no) \
+                                                         \
+    SC(120,     35,       33,      1, yes,  no,   0, no) \
+    SC(121,     35,       33,      2, yes,  no,   0, no) \
+    SC(122,     35,       33,      3, yes,  no,   0, no) \
+    SC(123,     35,       33,      4, yes,  no,   0, no) \
+                                                         \
+    SC(124,     36,       34,      1, yes,  no,   0, no) \
+    SC(125,     36,       34,      2, yes,  no,   0, no) \
+    SC(126,     36,       34,      3, yes,  no,   0, no) \
+    SC(127,     36,       34,      4, yes,  no,   0, no) \
+                                                         \
+    SC(128,     37,       35,      1, yes,  no,   0, no) \
+    SC(129,     37,       35,      2, yes,  no,   0, no) \
+    SC(130,     37,       35,      3, yes,  no,   0, no) \
+    SC(131,     37,       35,      4, yes,  no,   0, no) \
+                                                         \
+    SC(132,     38,       36,      1, yes,  no,   0, no) \
+    SC(133,     38,       36,      2, yes,  no,   0, no) \
+    SC(134,     38,       36,      3, yes,  no,   0, no) \
+    SC(135,     38,       36,      4, yes,  no,   0, no) \
+                                                         \
+    SC(136,     39,       37,      1, yes,  no,   0, no) \
+    SC(137,     39,       37,      2, yes,  no,   0, no) \
+    SC(138,     39,       37,      3, yes,  no,   0, no) \
+    SC(139,     39,       37,      4, yes,  no,   0, no) \
+                                                         \
+    SC(140,     40,       38,      1, yes,  no,   0, no) \
+    SC(141,     40,       38,      2, yes,  no,   0, no) \
+    SC(142,     40,       38,      3, yes,  no,   0, no) \
+    SC(143,     40,       38,      4, yes,  no,   0, no) \
+                                                         \
+    SC(144,     41,       39,      1, yes,  no,   0, no) \
+    SC(145,     41,       39,      2, yes,  no,   0, no) \
+    SC(146,     41,       39,      3, yes,  no,   0, no) \
+    SC(147,     41,       39,      4, yes,  no,   0, no) \
+                                                         \
+    SC(148,     42,       40,      1, yes,  no,   0, no) \
+    SC(149,     42,       40,      2, yes,  no,   0, no) \
+    SC(150,     42,       40,      3, yes,  no,   0, no) \
+    SC(151,     42,       40,      4, yes,  no,   0, no) \
+                                                         \
+    SC(152,     43,       41,      1, yes,  no,   0, no) \
+    SC(153,     43,       41,      2, yes,  no,   0, no) \
+    SC(154,     43,       41,      3, yes,  no,   0, no) \
+    SC(155,     43,       41,      4, yes,  no,   0, no) \
+                                                         \
+    SC(156,     44,       42,      1, yes,  no,   0, no) \
+    SC(157,     44,       42,      2, yes,  no,   0, no) \
+    SC(158,     44,       42,      3, yes,  no,   0, no) \
+    SC(159,     44,       42,      4, yes,  no,   0, no) \
+                                                         \
+    SC(160,     45,       43,      1, yes,  no,   0, no) \
+    SC(161,     45,       43,      2, yes,  no,   0, no) \
+    SC(162,     45,       43,      3, yes,  no,   0, no) \
+    SC(163,     45,       43,      4, yes,  no,   0, no) \
+                                                         \
+    SC(164,     46,       44,      1, yes,  no,   0, no) \
+    SC(165,     46,       44,      2, yes,  no,   0, no) \
+    SC(166,     46,       44,      3, yes,  no,   0, no) \
+    SC(167,     46,       44,      4, yes,  no,   0, no) \
+                                                         \
+    SC(168,     47,       45,      1, yes,  no,   0, no) \
+    SC(169,     47,       45,      2, yes,  no,   0, no) \
+    SC(170,     47,       45,      3, yes,  no,   0, no) \
+    SC(171,     47,       45,      4, yes,  no,   0, no) \
+                                                         \
+    SC(172,     48,       46,      1, yes,  no,   0, no) \
+    SC(173,     48,       46,      2, yes,  no,   0, no) \
+    SC(174,     48,       46,      3, yes,  no,   0, no) \
+    SC(175,     48,       46,      4, yes,  no,   0, no) \
+                                                         \
+    SC(176,     49,       47,      1, yes,  no,   0, no) \
+    SC(177,     49,       47,      2, yes,  no,   0, no) \
+    SC(178,     49,       47,      3, yes,  no,   0, no) \
+    SC(179,     49,       47,      4, yes,  no,   0, no) \
+                                                         \
+    SC(180,     50,       48,      1, yes,  no,   0, no) \
+    SC(181,     50,       48,      2, yes,  no,   0, no) \
+    SC(182,     50,       48,      3, yes,  no,   0, no) \
+    SC(183,     50,       48,      4, yes,  no,   0, no) \
+                                                         \
+    SC(184,     51,       49,      1, yes,  no,   0, no) \
+    SC(185,     51,       49,      2, yes,  no,   0, no) \
+    SC(186,     51,       49,      3, yes,  no,   0, no) \
+    SC(187,     51,       49,      4, yes,  no,   0, no) \
+                                                         \
+    SC(188,     52,       50,      1, yes,  no,   0, no) \
+    SC(189,     52,       50,      2, yes,  no,   0, no) \
+    SC(190,     52,       50,      3, yes,  no,   0, no) \
+    SC(191,     52,       50,      4, yes,  no,   0, no) \
+                                                         \
+    SC(192,     53,       51,      1, yes,  no,   0, no) \
+    SC(193,     53,       51,      2, yes,  no,   0, no) \
+    SC(194,     53,       51,      3, yes,  no,   0, no) \
+    SC(195,     53,       51,      4, yes,  no,   0, no) \
+                                                         \
+    SC(196,     54,       52,      1, yes,  no,   0, no) \
+    SC(197,     54,       52,      2, yes,  no,   0, no) \
+    SC(198,     54,       52,      3, yes,  no,   0, no) \
+    SC(199,     54,       52,      4, yes,  no,   0, no) \
+                                                         \
+    SC(200,     55,       53,      1, yes,  no,   0, no) \
+    SC(201,     55,       53,      2, yes,  no,   0, no) \
+    SC(202,     55,       53,      3, yes,  no,   0, no) \
+    SC(203,     55,       53,      4, yes,  no,   0, no) \
+                                                         \
+    SC(204,     56,       54,      1, yes,  no,   0, no) \
+    SC(205,     56,       54,      2, yes,  no,   0, no) \
+    SC(206,     56,       54,      3, yes,  no,   0, no) \
+    SC(207,     56,       54,      4, yes,  no,   0, no) \
+                                                         \
+    SC(208,     57,       55,      1, yes,  no,   0, no) \
+    SC(209,     57,       55,      2, yes,  no,   0, no) \
+    SC(210,     57,       55,      3, yes,  no,   0, no) \
+    SC(211,     57,       55,      4, yes,  no,   0, no) \
+                                                         \
+    SC(212,     58,       56,      1, yes,  no,   0, no) \
+    SC(213,     58,       56,      2, yes,  no,   0, no) \
+    SC(214,     58,       56,      3, yes,  no,   0, no) \
+    SC(215,     58,       56,      4, yes,  no,   0, no) \
+                                                         \
+    SC(216,     59,       57,      1, yes,  no,   0, no) \
+    SC(217,     59,       57,      2, yes,  no,   0, no) \
+    SC(218,     59,       57,      3, yes,  no,   0, no) \
+    SC(219,     59,       57,      4, yes,  no,   0, no) \
+                                                         \
+    SC(220,     60,       58,      1, yes,  no,   0, no) \
+    SC(221,     60,       58,      2, yes,  no,   0, no) \
+    SC(222,     60,       58,      3, yes,  no,   0, no) \
+    SC(223,     60,       58,      4, yes,  no,   0, no) \
+                                                         \
+    SC(224,     61,       59,      1, yes,  no,   0, no) \
+    SC(225,     61,       59,      2, yes,  no,   0, no) \
+    SC(226,     61,       59,      3, yes,  no,   0, no) \
+    SC(227,     61,       59,      4, yes,  no,   0, no) \
+                                                         \
+    SC(228,     62,       60,      1, yes,  no,   0, no) \
+    SC(229,     62,       60,      2, yes,  no,   0, no) \
+    SC(230,     62,       60,      3, yes,  no,   0, no) \
 
-#define	NBINS		43
-#define	SMALL_MAXCLASS	57344
+#define SIZE_CLASSES_DEFINED
+#define NTBINS			0
+#define NLBINS			28
+#define NBINS			35
+#define NSIZES			231
+#define LG_CEIL_NSIZES		8
+#define NPSIZES			199
+#define LG_TINY_MAXCLASS	"NA"
+#define LOOKUP_MAXCLASS		((((size_t)1) << 11) + (((size_t)4) << 9))
+#define SMALL_MAXCLASS		((((size_t)1) << 13) + (((size_t)3) << 11))
+#define LG_LARGE_MINCLASS	14
+#define LARGE_MINCLASS		(ZU(1) << LG_LARGE_MINCLASS)
+#define LARGE_MAXCLASS		((((size_t)1) << 62) + (((size_t)3) << 60))
 #endif
 
 #ifndef SIZE_CLASSES_DEFINED
@@ -692,30 +1418,11 @@
 #endif
 #undef SIZE_CLASSES_DEFINED
 /*
- * The small_size2bin lookup table uses uint8_t to encode each bin index, so we
- * cannot support more than 256 small size classes.  Further constrain NBINS to
- * 255 to support prof_promote, since all small size classes, plus a "not
- * small" size class must be stored in 8 bits of arena_chunk_map_t's bits
- * field.
+ * The size2index_tab lookup table uses uint8_t to encode each bin index, so we
+ * cannot support more than 256 small size classes.
  */
-#if (NBINS > 255)
+#if (NBINS > 256)
 #  error "Too many small size classes"
 #endif
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
-
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_SIZE_CLASSES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/smoothstep.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/smoothstep.h
new file mode 100644
index 0000000000..2e14430f5f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/smoothstep.h
@@ -0,0 +1,232 @@
+#ifndef JEMALLOC_INTERNAL_SMOOTHSTEP_H
+#define JEMALLOC_INTERNAL_SMOOTHSTEP_H
+
+/*
+ * This file was generated by the following command:
+ *   sh smoothstep.sh smoother 200 24 3 15
+ */
+/******************************************************************************/
+
+/*
+ * This header defines a precomputed table based on the smoothstep family of
+ * sigmoidal curves (https://en.wikipedia.org/wiki/Smoothstep) that grow from 0
+ * to 1 in 0 <= x <= 1.  The table is stored as integer fixed point values so
+ * that floating point math can be avoided.
+ *
+ *                      3     2
+ *   smoothstep(x) = -2x  + 3x
+ *
+ *                       5      4      3
+ *   smootherstep(x) = 6x  - 15x  + 10x
+ *
+ *                          7      6      5      4
+ *   smootheststep(x) = -20x  + 70x  - 84x  + 35x
+ */
+
+#define SMOOTHSTEP_VARIANT	"smoother"
+#define SMOOTHSTEP_NSTEPS	200
+#define SMOOTHSTEP_BFP		24
+#define SMOOTHSTEP \
+ /* STEP(step, h,                            x,     y) */ \
+    STEP(   1, UINT64_C(0x0000000000000014), 0.005, 0.000001240643750) \
+    STEP(   2, UINT64_C(0x00000000000000a5), 0.010, 0.000009850600000) \
+    STEP(   3, UINT64_C(0x0000000000000229), 0.015, 0.000032995181250) \
+    STEP(   4, UINT64_C(0x0000000000000516), 0.020, 0.000077619200000) \
+    STEP(   5, UINT64_C(0x00000000000009dc), 0.025, 0.000150449218750) \
+    STEP(   6, UINT64_C(0x00000000000010e8), 0.030, 0.000257995800000) \
+    STEP(   7, UINT64_C(0x0000000000001aa4), 0.035, 0.000406555756250) \
+    STEP(   8, UINT64_C(0x0000000000002777), 0.040, 0.000602214400000) \
+    STEP(   9, UINT64_C(0x00000000000037c2), 0.045, 0.000850847793750) \
+    STEP(  10, UINT64_C(0x0000000000004be6), 0.050, 0.001158125000000) \
+    STEP(  11, UINT64_C(0x000000000000643c), 0.055, 0.001529510331250) \
+    STEP(  12, UINT64_C(0x000000000000811f), 0.060, 0.001970265600000) \
+    STEP(  13, UINT64_C(0x000000000000a2e2), 0.065, 0.002485452368750) \
+    STEP(  14, UINT64_C(0x000000000000c9d8), 0.070, 0.003079934200000) \
+    STEP(  15, UINT64_C(0x000000000000f64f), 0.075, 0.003758378906250) \
+    STEP(  16, UINT64_C(0x0000000000012891), 0.080, 0.004525260800000) \
+    STEP(  17, UINT64_C(0x00000000000160e7), 0.085, 0.005384862943750) \
+    STEP(  18, UINT64_C(0x0000000000019f95), 0.090, 0.006341279400000) \
+    STEP(  19, UINT64_C(0x000000000001e4dc), 0.095, 0.007398417481250) \
+    STEP(  20, UINT64_C(0x00000000000230fc), 0.100, 0.008560000000000) \
+    STEP(  21, UINT64_C(0x0000000000028430), 0.105, 0.009829567518750) \
+    STEP(  22, UINT64_C(0x000000000002deb0), 0.110, 0.011210480600000) \
+    STEP(  23, UINT64_C(0x00000000000340b1), 0.115, 0.012705922056250) \
+    STEP(  24, UINT64_C(0x000000000003aa67), 0.120, 0.014318899200000) \
+    STEP(  25, UINT64_C(0x0000000000041c00), 0.125, 0.016052246093750) \
+    STEP(  26, UINT64_C(0x00000000000495a8), 0.130, 0.017908625800000) \
+    STEP(  27, UINT64_C(0x000000000005178b), 0.135, 0.019890532631250) \
+    STEP(  28, UINT64_C(0x000000000005a1cf), 0.140, 0.022000294400000) \
+    STEP(  29, UINT64_C(0x0000000000063498), 0.145, 0.024240074668750) \
+    STEP(  30, UINT64_C(0x000000000006d009), 0.150, 0.026611875000000) \
+    STEP(  31, UINT64_C(0x000000000007743f), 0.155, 0.029117537206250) \
+    STEP(  32, UINT64_C(0x0000000000082157), 0.160, 0.031758745600000) \
+    STEP(  33, UINT64_C(0x000000000008d76b), 0.165, 0.034537029243750) \
+    STEP(  34, UINT64_C(0x0000000000099691), 0.170, 0.037453764200000) \
+    STEP(  35, UINT64_C(0x00000000000a5edf), 0.175, 0.040510175781250) \
+    STEP(  36, UINT64_C(0x00000000000b3067), 0.180, 0.043707340800000) \
+    STEP(  37, UINT64_C(0x00000000000c0b38), 0.185, 0.047046189818750) \
+    STEP(  38, UINT64_C(0x00000000000cef5e), 0.190, 0.050527509400000) \
+    STEP(  39, UINT64_C(0x00000000000ddce6), 0.195, 0.054151944356250) \
+    STEP(  40, UINT64_C(0x00000000000ed3d8), 0.200, 0.057920000000000) \
+    STEP(  41, UINT64_C(0x00000000000fd439), 0.205, 0.061832044393750) \
+    STEP(  42, UINT64_C(0x000000000010de0e), 0.210, 0.065888310600000) \
+    STEP(  43, UINT64_C(0x000000000011f158), 0.215, 0.070088898931250) \
+    STEP(  44, UINT64_C(0x0000000000130e17), 0.220, 0.074433779200000) \
+    STEP(  45, UINT64_C(0x0000000000143448), 0.225, 0.078922792968750) \
+    STEP(  46, UINT64_C(0x00000000001563e7), 0.230, 0.083555655800000) \
+    STEP(  47, UINT64_C(0x0000000000169cec), 0.235, 0.088331959506250) \
+    STEP(  48, UINT64_C(0x000000000017df4f), 0.240, 0.093251174400000) \
+    STEP(  49, UINT64_C(0x0000000000192b04), 0.245, 0.098312651543750) \
+    STEP(  50, UINT64_C(0x00000000001a8000), 0.250, 0.103515625000000) \
+    STEP(  51, UINT64_C(0x00000000001bde32), 0.255, 0.108859214081250) \
+    STEP(  52, UINT64_C(0x00000000001d458b), 0.260, 0.114342425600000) \
+    STEP(  53, UINT64_C(0x00000000001eb5f8), 0.265, 0.119964156118750) \
+    STEP(  54, UINT64_C(0x0000000000202f65), 0.270, 0.125723194200000) \
+    STEP(  55, UINT64_C(0x000000000021b1bb), 0.275, 0.131618222656250) \
+    STEP(  56, UINT64_C(0x0000000000233ce3), 0.280, 0.137647820800000) \
+    STEP(  57, UINT64_C(0x000000000024d0c3), 0.285, 0.143810466693750) \
+    STEP(  58, UINT64_C(0x0000000000266d40), 0.290, 0.150104539400000) \
+    STEP(  59, UINT64_C(0x000000000028123d), 0.295, 0.156528321231250) \
+    STEP(  60, UINT64_C(0x000000000029bf9c), 0.300, 0.163080000000000) \
+    STEP(  61, UINT64_C(0x00000000002b753d), 0.305, 0.169757671268750) \
+    STEP(  62, UINT64_C(0x00000000002d32fe), 0.310, 0.176559340600000) \
+    STEP(  63, UINT64_C(0x00000000002ef8bc), 0.315, 0.183482925806250) \
+    STEP(  64, UINT64_C(0x000000000030c654), 0.320, 0.190526259200000) \
+    STEP(  65, UINT64_C(0x0000000000329b9f), 0.325, 0.197687089843750) \
+    STEP(  66, UINT64_C(0x0000000000347875), 0.330, 0.204963085800000) \
+    STEP(  67, UINT64_C(0x0000000000365cb0), 0.335, 0.212351836381250) \
+    STEP(  68, UINT64_C(0x0000000000384825), 0.340, 0.219850854400000) \
+    STEP(  69, UINT64_C(0x00000000003a3aa8), 0.345, 0.227457578418750) \
+    STEP(  70, UINT64_C(0x00000000003c340f), 0.350, 0.235169375000000) \
+    STEP(  71, UINT64_C(0x00000000003e342b), 0.355, 0.242983540956250) \
+    STEP(  72, UINT64_C(0x0000000000403ace), 0.360, 0.250897305600000) \
+    STEP(  73, UINT64_C(0x00000000004247c8), 0.365, 0.258907832993750) \
+    STEP(  74, UINT64_C(0x0000000000445ae9), 0.370, 0.267012224200000) \
+    STEP(  75, UINT64_C(0x0000000000467400), 0.375, 0.275207519531250) \
+    STEP(  76, UINT64_C(0x00000000004892d8), 0.380, 0.283490700800000) \
+    STEP(  77, UINT64_C(0x00000000004ab740), 0.385, 0.291858693568750) \
+    STEP(  78, UINT64_C(0x00000000004ce102), 0.390, 0.300308369400000) \
+    STEP(  79, UINT64_C(0x00000000004f0fe9), 0.395, 0.308836548106250) \
+    STEP(  80, UINT64_C(0x00000000005143bf), 0.400, 0.317440000000000) \
+    STEP(  81, UINT64_C(0x0000000000537c4d), 0.405, 0.326115448143750) \
+    STEP(  82, UINT64_C(0x000000000055b95b), 0.410, 0.334859570600000) \
+    STEP(  83, UINT64_C(0x000000000057fab1), 0.415, 0.343669002681250) \
+    STEP(  84, UINT64_C(0x00000000005a4015), 0.420, 0.352540339200000) \
+    STEP(  85, UINT64_C(0x00000000005c894e), 0.425, 0.361470136718750) \
+    STEP(  86, UINT64_C(0x00000000005ed622), 0.430, 0.370454915800000) \
+    STEP(  87, UINT64_C(0x0000000000612655), 0.435, 0.379491163256250) \
+    STEP(  88, UINT64_C(0x00000000006379ac), 0.440, 0.388575334400000) \
+    STEP(  89, UINT64_C(0x000000000065cfeb), 0.445, 0.397703855293750) \
+    STEP(  90, UINT64_C(0x00000000006828d6), 0.450, 0.406873125000000) \
+    STEP(  91, UINT64_C(0x00000000006a842f), 0.455, 0.416079517831250) \
+    STEP(  92, UINT64_C(0x00000000006ce1bb), 0.460, 0.425319385600000) \
+    STEP(  93, UINT64_C(0x00000000006f413a), 0.465, 0.434589059868750) \
+    STEP(  94, UINT64_C(0x000000000071a270), 0.470, 0.443884854200000) \
+    STEP(  95, UINT64_C(0x000000000074051d), 0.475, 0.453203066406250) \
+    STEP(  96, UINT64_C(0x0000000000766905), 0.480, 0.462539980800000) \
+    STEP(  97, UINT64_C(0x000000000078cde7), 0.485, 0.471891870443750) \
+    STEP(  98, UINT64_C(0x00000000007b3387), 0.490, 0.481254999400000) \
+    STEP(  99, UINT64_C(0x00000000007d99a4), 0.495, 0.490625624981250) \
+    STEP( 100, UINT64_C(0x0000000000800000), 0.500, 0.500000000000000) \
+    STEP( 101, UINT64_C(0x000000000082665b), 0.505, 0.509374375018750) \
+    STEP( 102, UINT64_C(0x000000000084cc78), 0.510, 0.518745000600000) \
+    STEP( 103, UINT64_C(0x0000000000873218), 0.515, 0.528108129556250) \
+    STEP( 104, UINT64_C(0x00000000008996fa), 0.520, 0.537460019200000) \
+    STEP( 105, UINT64_C(0x00000000008bfae2), 0.525, 0.546796933593750) \
+    STEP( 106, UINT64_C(0x00000000008e5d8f), 0.530, 0.556115145800000) \
+    STEP( 107, UINT64_C(0x000000000090bec5), 0.535, 0.565410940131250) \
+    STEP( 108, UINT64_C(0x0000000000931e44), 0.540, 0.574680614400000) \
+    STEP( 109, UINT64_C(0x0000000000957bd0), 0.545, 0.583920482168750) \
+    STEP( 110, UINT64_C(0x000000000097d729), 0.550, 0.593126875000000) \
+    STEP( 111, UINT64_C(0x00000000009a3014), 0.555, 0.602296144706250) \
+    STEP( 112, UINT64_C(0x00000000009c8653), 0.560, 0.611424665600000) \
+    STEP( 113, UINT64_C(0x00000000009ed9aa), 0.565, 0.620508836743750) \
+    STEP( 114, UINT64_C(0x0000000000a129dd), 0.570, 0.629545084200000) \
+    STEP( 115, UINT64_C(0x0000000000a376b1), 0.575, 0.638529863281250) \
+    STEP( 116, UINT64_C(0x0000000000a5bfea), 0.580, 0.647459660800000) \
+    STEP( 117, UINT64_C(0x0000000000a8054e), 0.585, 0.656330997318750) \
+    STEP( 118, UINT64_C(0x0000000000aa46a4), 0.590, 0.665140429400000) \
+    STEP( 119, UINT64_C(0x0000000000ac83b2), 0.595, 0.673884551856250) \
+    STEP( 120, UINT64_C(0x0000000000aebc40), 0.600, 0.682560000000000) \
+    STEP( 121, UINT64_C(0x0000000000b0f016), 0.605, 0.691163451893750) \
+    STEP( 122, UINT64_C(0x0000000000b31efd), 0.610, 0.699691630600000) \
+    STEP( 123, UINT64_C(0x0000000000b548bf), 0.615, 0.708141306431250) \
+    STEP( 124, UINT64_C(0x0000000000b76d27), 0.620, 0.716509299200000) \
+    STEP( 125, UINT64_C(0x0000000000b98c00), 0.625, 0.724792480468750) \
+    STEP( 126, UINT64_C(0x0000000000bba516), 0.630, 0.732987775800000) \
+    STEP( 127, UINT64_C(0x0000000000bdb837), 0.635, 0.741092167006250) \
+    STEP( 128, UINT64_C(0x0000000000bfc531), 0.640, 0.749102694400000) \
+    STEP( 129, UINT64_C(0x0000000000c1cbd4), 0.645, 0.757016459043750) \
+    STEP( 130, UINT64_C(0x0000000000c3cbf0), 0.650, 0.764830625000000) \
+    STEP( 131, UINT64_C(0x0000000000c5c557), 0.655, 0.772542421581250) \
+    STEP( 132, UINT64_C(0x0000000000c7b7da), 0.660, 0.780149145600000) \
+    STEP( 133, UINT64_C(0x0000000000c9a34f), 0.665, 0.787648163618750) \
+    STEP( 134, UINT64_C(0x0000000000cb878a), 0.670, 0.795036914200000) \
+    STEP( 135, UINT64_C(0x0000000000cd6460), 0.675, 0.802312910156250) \
+    STEP( 136, UINT64_C(0x0000000000cf39ab), 0.680, 0.809473740800000) \
+    STEP( 137, UINT64_C(0x0000000000d10743), 0.685, 0.816517074193750) \
+    STEP( 138, UINT64_C(0x0000000000d2cd01), 0.690, 0.823440659400000) \
+    STEP( 139, UINT64_C(0x0000000000d48ac2), 0.695, 0.830242328731250) \
+    STEP( 140, UINT64_C(0x0000000000d64063), 0.700, 0.836920000000000) \
+    STEP( 141, UINT64_C(0x0000000000d7edc2), 0.705, 0.843471678768750) \
+    STEP( 142, UINT64_C(0x0000000000d992bf), 0.710, 0.849895460600000) \
+    STEP( 143, UINT64_C(0x0000000000db2f3c), 0.715, 0.856189533306250) \
+    STEP( 144, UINT64_C(0x0000000000dcc31c), 0.720, 0.862352179200000) \
+    STEP( 145, UINT64_C(0x0000000000de4e44), 0.725, 0.868381777343750) \
+    STEP( 146, UINT64_C(0x0000000000dfd09a), 0.730, 0.874276805800000) \
+    STEP( 147, UINT64_C(0x0000000000e14a07), 0.735, 0.880035843881250) \
+    STEP( 148, UINT64_C(0x0000000000e2ba74), 0.740, 0.885657574400000) \
+    STEP( 149, UINT64_C(0x0000000000e421cd), 0.745, 0.891140785918750) \
+    STEP( 150, UINT64_C(0x0000000000e58000), 0.750, 0.896484375000000) \
+    STEP( 151, UINT64_C(0x0000000000e6d4fb), 0.755, 0.901687348456250) \
+    STEP( 152, UINT64_C(0x0000000000e820b0), 0.760, 0.906748825600000) \
+    STEP( 153, UINT64_C(0x0000000000e96313), 0.765, 0.911668040493750) \
+    STEP( 154, UINT64_C(0x0000000000ea9c18), 0.770, 0.916444344200000) \
+    STEP( 155, UINT64_C(0x0000000000ebcbb7), 0.775, 0.921077207031250) \
+    STEP( 156, UINT64_C(0x0000000000ecf1e8), 0.780, 0.925566220800000) \
+    STEP( 157, UINT64_C(0x0000000000ee0ea7), 0.785, 0.929911101068750) \
+    STEP( 158, UINT64_C(0x0000000000ef21f1), 0.790, 0.934111689400000) \
+    STEP( 159, UINT64_C(0x0000000000f02bc6), 0.795, 0.938167955606250) \
+    STEP( 160, UINT64_C(0x0000000000f12c27), 0.800, 0.942080000000000) \
+    STEP( 161, UINT64_C(0x0000000000f22319), 0.805, 0.945848055643750) \
+    STEP( 162, UINT64_C(0x0000000000f310a1), 0.810, 0.949472490600000) \
+    STEP( 163, UINT64_C(0x0000000000f3f4c7), 0.815, 0.952953810181250) \
+    STEP( 164, UINT64_C(0x0000000000f4cf98), 0.820, 0.956292659200000) \
+    STEP( 165, UINT64_C(0x0000000000f5a120), 0.825, 0.959489824218750) \
+    STEP( 166, UINT64_C(0x0000000000f6696e), 0.830, 0.962546235800000) \
+    STEP( 167, UINT64_C(0x0000000000f72894), 0.835, 0.965462970756250) \
+    STEP( 168, UINT64_C(0x0000000000f7dea8), 0.840, 0.968241254400000) \
+    STEP( 169, UINT64_C(0x0000000000f88bc0), 0.845, 0.970882462793750) \
+    STEP( 170, UINT64_C(0x0000000000f92ff6), 0.850, 0.973388125000000) \
+    STEP( 171, UINT64_C(0x0000000000f9cb67), 0.855, 0.975759925331250) \
+    STEP( 172, UINT64_C(0x0000000000fa5e30), 0.860, 0.977999705600000) \
+    STEP( 173, UINT64_C(0x0000000000fae874), 0.865, 0.980109467368750) \
+    STEP( 174, UINT64_C(0x0000000000fb6a57), 0.870, 0.982091374200000) \
+    STEP( 175, UINT64_C(0x0000000000fbe400), 0.875, 0.983947753906250) \
+    STEP( 176, UINT64_C(0x0000000000fc5598), 0.880, 0.985681100800000) \
+    STEP( 177, UINT64_C(0x0000000000fcbf4e), 0.885, 0.987294077943750) \
+    STEP( 178, UINT64_C(0x0000000000fd214f), 0.890, 0.988789519400000) \
+    STEP( 179, UINT64_C(0x0000000000fd7bcf), 0.895, 0.990170432481250) \
+    STEP( 180, UINT64_C(0x0000000000fdcf03), 0.900, 0.991440000000000) \
+    STEP( 181, UINT64_C(0x0000000000fe1b23), 0.905, 0.992601582518750) \
+    STEP( 182, UINT64_C(0x0000000000fe606a), 0.910, 0.993658720600000) \
+    STEP( 183, UINT64_C(0x0000000000fe9f18), 0.915, 0.994615137056250) \
+    STEP( 184, UINT64_C(0x0000000000fed76e), 0.920, 0.995474739200000) \
+    STEP( 185, UINT64_C(0x0000000000ff09b0), 0.925, 0.996241621093750) \
+    STEP( 186, UINT64_C(0x0000000000ff3627), 0.930, 0.996920065800000) \
+    STEP( 187, UINT64_C(0x0000000000ff5d1d), 0.935, 0.997514547631250) \
+    STEP( 188, UINT64_C(0x0000000000ff7ee0), 0.940, 0.998029734400000) \
+    STEP( 189, UINT64_C(0x0000000000ff9bc3), 0.945, 0.998470489668750) \
+    STEP( 190, UINT64_C(0x0000000000ffb419), 0.950, 0.998841875000000) \
+    STEP( 191, UINT64_C(0x0000000000ffc83d), 0.955, 0.999149152206250) \
+    STEP( 192, UINT64_C(0x0000000000ffd888), 0.960, 0.999397785600000) \
+    STEP( 193, UINT64_C(0x0000000000ffe55b), 0.965, 0.999593444243750) \
+    STEP( 194, UINT64_C(0x0000000000ffef17), 0.970, 0.999742004200000) \
+    STEP( 195, UINT64_C(0x0000000000fff623), 0.975, 0.999849550781250) \
+    STEP( 196, UINT64_C(0x0000000000fffae9), 0.980, 0.999922380800000) \
+    STEP( 197, UINT64_C(0x0000000000fffdd6), 0.985, 0.999967004818750) \
+    STEP( 198, UINT64_C(0x0000000000ffff5a), 0.990, 0.999990149400000) \
+    STEP( 199, UINT64_C(0x0000000000ffffeb), 0.995, 0.999998759356250) \
+    STEP( 200, UINT64_C(0x0000000001000000), 1.000, 1.000000000000000) \
+
+#endif /* JEMALLOC_INTERNAL_SMOOTHSTEP_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/spin.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/spin.h
new file mode 100644
index 0000000000..e2afc98cfd
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/spin.h
@@ -0,0 +1,36 @@
+#ifndef JEMALLOC_INTERNAL_SPIN_H
+#define JEMALLOC_INTERNAL_SPIN_H
+
+#ifdef JEMALLOC_SPIN_C_
+#  define SPIN_INLINE extern inline
+#else
+#  define SPIN_INLINE inline
+#endif
+
+#define SPIN_INITIALIZER {0U}
+
+typedef struct {
+	unsigned iteration;
+} spin_t;
+
+SPIN_INLINE void
+spin_adaptive(spin_t *spin) {
+	volatile uint32_t i;
+
+	if (spin->iteration < 5) {
+		for (i = 0; i < (1U << spin->iteration); i++) {
+			CPU_SPINWAIT;
+		}
+		spin->iteration++;
+	} else {
+#ifdef _WIN32
+		SwitchToThread();
+#else
+		sched_yield();
+#endif
+	}
+}
+
+#undef SPIN_INLINE
+
+#endif /* JEMALLOC_INTERNAL_SPIN_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats.h
index 27f68e3681..1198779ab9 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats.h
@@ -1,31 +1,51 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
-
-typedef struct tcache_bin_stats_s tcache_bin_stats_t;
-typedef struct malloc_bin_stats_s malloc_bin_stats_t;
-typedef struct malloc_large_stats_s malloc_large_stats_t;
-typedef struct arena_stats_s arena_stats_t;
-typedef struct chunk_stats_s chunk_stats_t;
+#ifndef JEMALLOC_INTERNAL_STATS_H
+#define JEMALLOC_INTERNAL_STATS_H
+
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/mutex_prof.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/stats_tsd.h"
+
+/*  OPTION(opt,		var_name,	default,	set_value_to) */
+#define STATS_PRINT_OPTIONS						\
+    OPTION('J',		json,		false,		true)		\
+    OPTION('g',		general,	true,		false)		\
+    OPTION('m',		merged,		config_stats,	false)		\
+    OPTION('d',		destroyed,	config_stats,	false)		\
+    OPTION('a',		unmerged,	config_stats,	false)		\
+    OPTION('b',		bins,		true,		false)		\
+    OPTION('l',		large,		true,		false)		\
+    OPTION('x',		mutex,		true,		false)
+
+enum {
+#define OPTION(o, v, d, s) stats_print_option_num_##v,
+    STATS_PRINT_OPTIONS
+#undef OPTION
+    stats_print_tot_num_options
+};
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+/* Options for stats_print. */
+extern bool opt_stats_print;
+extern char opt_stats_print_opts[stats_print_tot_num_options+1];
 
-struct tcache_bin_stats_s {
-	/*
-	 * Number of allocation requests that corresponded to the size of this
-	 * bin.
-	 */
-	uint64_t	nrequests;
-};
+/* Implements je_malloc_stats_print. */
+void stats_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *opts);
 
-struct malloc_bin_stats_s {
-	/*
-	 * Current number of bytes allocated, including objects currently
-	 * cached by tcache.
-	 */
-	size_t		allocated;
+/*
+ * In those architectures that support 64-bit atomics, we use atomic updates for
+ * our 64-bit values.  Otherwise, we use a plain uint64_t and synchronize
+ * externally.
+ */
+#ifdef JEMALLOC_ATOMIC_U64
+typedef atomic_u64_t arena_stats_u64_t;
+#else
+/* Must hold the arena stats mutex while reading atomically. */
+typedef uint64_t arena_stats_u64_t;
+#endif
 
+typedef struct malloc_bin_stats_s {
 	/*
 	 * Total number of allocation/deallocation requests served directly by
 	 * the bin.  Note that tcache may allocate an object, then recycle it
@@ -42,132 +62,103 @@ struct malloc_bin_stats_s {
 	 */
 	uint64_t	nrequests;
 
+	/*
+	 * Current number of regions of this size class, including regions
+	 * currently cached by tcache.
+	 */
+	size_t		curregs;
+
 	/* Number of tcache fills from this bin. */
 	uint64_t	nfills;
 
 	/* Number of tcache flushes to this bin. */
 	uint64_t	nflushes;
 
-	/* Total number of runs created for this bin's size class. */
-	uint64_t	nruns;
+	/* Total number of slabs created for this bin's size class. */
+	uint64_t	nslabs;
 
 	/*
-	 * Total number of runs reused by extracting them from the runs tree for
-	 * this bin's size class.
+	 * Total number of slabs reused by extracting them from the slabs heap
+	 * for this bin's size class.
 	 */
-	uint64_t	reruns;
+	uint64_t	reslabs;
 
-	/* Current number of runs in this bin. */
-	size_t		curruns;
-};
+	/* Current number of slabs in this bin. */
+	size_t		curslabs;
 
-struct malloc_large_stats_s {
+	mutex_prof_data_t mutex_data;
+} malloc_bin_stats_t;
+
+typedef struct malloc_large_stats_s {
 	/*
 	 * Total number of allocation/deallocation requests served directly by
-	 * the arena.  Note that tcache may allocate an object, then recycle it
-	 * many times, resulting many increments to nrequests, but only one
-	 * each to nmalloc and ndalloc.
+	 * the arena.
 	 */
-	uint64_t	nmalloc;
-	uint64_t	ndalloc;
+	arena_stats_u64_t	nmalloc;
+	arena_stats_u64_t	ndalloc;
 
 	/*
 	 * Number of allocation requests that correspond to this size class.
 	 * This includes requests served by tcache, though tcache only
 	 * periodically merges into this counter.
 	 */
-	uint64_t	nrequests;
-
-	/* Current number of runs of this size class. */
-	size_t		curruns;
-};
-
-struct arena_stats_s {
-	/* Number of bytes currently mapped. */
-	size_t		mapped;
-
-	/*
-	 * Total number of purge sweeps, total number of madvise calls made,
-	 * and total pages purged in order to keep dirty unused memory under
-	 * control.
-	 */
-	uint64_t	npurge;
-	uint64_t	nmadvise;
-	uint64_t	purged;
-
-	/* Per-size-category statistics. */
-	size_t		allocated_large;
-	uint64_t	nmalloc_large;
-	uint64_t	ndalloc_large;
-	uint64_t	nrequests_large;
-
-	/*
-	 * One element for each possible size class, including sizes that
-	 * overlap with bin size classes.  This is necessary because ipalloc()
-	 * sometimes has to use such large objects in order to assure proper
-	 * alignment.
-	 */
-	malloc_large_stats_t	*lstats;
-};
-
-struct chunk_stats_s {
-	/* Number of chunks that were allocated. */
-	uint64_t	nchunks;
+	arena_stats_u64_t	nrequests; /* Partially derived. */
+
+	/* Current number of allocations of this size class. */
+	size_t		curlextents; /* Derived. */
+} malloc_large_stats_t;
+
+typedef struct decay_stats_s {
+	/* Total number of purge sweeps. */
+	arena_stats_u64_t	npurge;
+	/* Total number of madvise calls made. */
+	arena_stats_u64_t	nmadvise;
+	/* Total number of pages purged. */
+	arena_stats_u64_t	purged;
+} decay_stats_t;
+
+/*
+ * Arena stats.  Note that fields marked "derived" are not directly maintained
+ * within the arena code; rather their values are derived during stats merge
+ * requests.
+ */
+typedef struct arena_stats_s {
+#ifndef JEMALLOC_ATOMIC_U64
+	malloc_mutex_t		mtx;
+#endif
 
-	/* High-water mark for number of chunks allocated. */
-	size_t		highchunks;
+	/* Number of bytes currently mapped, excluding retained memory. */
+	atomic_zu_t		mapped; /* Partially derived. */
 
 	/*
-	 * Current number of chunks allocated.  This value isn't maintained for
-	 * any other purpose, so keep track of it in order to be able to set
-	 * highchunks.
+	 * Number of unused virtual memory bytes currently retained.  Retained
+	 * bytes are technically mapped (though always decommitted or purged),
+	 * but they are excluded from the mapped statistic (above).
 	 */
-	size_t		curchunks;
-};
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-extern bool	opt_stats_print;
-
-extern size_t	stats_cactive;
+	atomic_zu_t		retained; /* Derived. */
 
-void	stats_print(void (*write)(void *, const char *), void *cbopaque,
-    const char *opts);
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+	decay_stats_t		decay_dirty;
+	decay_stats_t		decay_muzzy;
 
-#ifndef JEMALLOC_ENABLE_INLINE
-size_t	stats_cactive_get(void);
-void	stats_cactive_add(size_t size);
-void	stats_cactive_sub(size_t size);
-#endif
+	atomic_zu_t		base; /* Derived. */
+	atomic_zu_t		internal;
+	atomic_zu_t		resident; /* Derived. */
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_STATS_C_))
-JEMALLOC_INLINE size_t
-stats_cactive_get(void)
-{
+	atomic_zu_t		allocated_large; /* Derived. */
+	arena_stats_u64_t	nmalloc_large; /* Derived. */
+	arena_stats_u64_t	ndalloc_large; /* Derived. */
+	arena_stats_u64_t	nrequests_large; /* Derived. */
 
-	return (atomic_read_z(&stats_cactive));
-}
+	/* Number of bytes cached in tcache associated with this arena. */
+	atomic_zu_t		tcache_bytes; /* Derived. */
 
-JEMALLOC_INLINE void
-stats_cactive_add(size_t size)
-{
+	mutex_prof_data_t mutex_prof_data[mutex_prof_num_arena_mutexes];
 
-	atomic_add_z(&stats_cactive, size);
-}
+	/* One element for each large size class. */
+	malloc_large_stats_t	lstats[NSIZES - NBINS];
 
-JEMALLOC_INLINE void
-stats_cactive_sub(size_t size)
-{
-
-	atomic_sub_z(&stats_cactive, size);
-}
-#endif
+	/* Arena uptime. */
+	nstime_t		uptime;
+} arena_stats_t;
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_STATS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats_tsd.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats_tsd.h
new file mode 100644
index 0000000000..d0c3bbe494
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/stats_tsd.h
@@ -0,0 +1,12 @@
+#ifndef JEMALLOC_INTERNAL_STATS_TSD_H
+#define JEMALLOC_INTERNAL_STATS_TSD_H
+
+typedef struct tcache_bin_stats_s {
+	/*
+	 * Number of allocation requests that corresponded to the size of this
+	 * bin.
+	 */
+	uint64_t	nrequests;
+} tcache_bin_stats_t;
+
+#endif /* JEMALLOC_INTERNAL_STATS_TSD_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/sz.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/sz.h
new file mode 100644
index 0000000000..7f640d55ad
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/sz.h
@@ -0,0 +1,317 @@
+#ifndef JEMALLOC_INTERNAL_SIZE_H
+#define JEMALLOC_INTERNAL_SIZE_H
+
+#include "jemalloc/internal/bit_util.h"
+#include "jemalloc/internal/pages.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/util.h"
+
+/*
+ * sz module: Size computations.
+ *
+ * Some abbreviations used here:
+ *   p: Page
+ *   ind: Index
+ *   s, sz: Size
+ *   u: Usable size
+ *   a: Aligned
+ *
+ * These are not always used completely consistently, but should be enough to
+ * interpret function names.  E.g. sz_psz2ind converts page size to page size
+ * index; sz_sa2u converts a (size, alignment) allocation request to the usable
+ * size that would result from such an allocation.
+ */
+
+/*
+ * sz_pind2sz_tab encodes the same information as could be computed by
+ * sz_pind2sz_compute().
+ */
+extern size_t const sz_pind2sz_tab[NPSIZES+1];
+/*
+ * sz_index2size_tab encodes the same information as could be computed (at
+ * unacceptable cost in some code paths) by sz_index2size_compute().
+ */
+extern size_t const sz_index2size_tab[NSIZES];
+/*
+ * sz_size2index_tab is a compact lookup table that rounds request sizes up to
+ * size classes.  In order to reduce cache footprint, the table is compressed,
+ * and all accesses are via sz_size2index().
+ */
+extern uint8_t const sz_size2index_tab[];
+
+static const size_t sz_large_pad =
+#ifdef JEMALLOC_CACHE_OBLIVIOUS
+    PAGE
+#else
+    0
+#endif
+    ;
+
+JEMALLOC_ALWAYS_INLINE pszind_t
+sz_psz2ind(size_t psz) {
+	if (unlikely(psz > LARGE_MAXCLASS)) {
+		return NPSIZES;
+	}
+	{
+		pszind_t x = lg_floor((psz<<1)-1);
+		pszind_t shift = (x < LG_SIZE_CLASS_GROUP + LG_PAGE) ? 0 : x -
+		    (LG_SIZE_CLASS_GROUP + LG_PAGE);
+		pszind_t grp = shift << LG_SIZE_CLASS_GROUP;
+
+		pszind_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_PAGE + 1) ?
+		    LG_PAGE : x - LG_SIZE_CLASS_GROUP - 1;
+
+		size_t delta_inverse_mask = ZD(-1) << lg_delta;
+		pszind_t mod = ((((psz-1) & delta_inverse_mask) >> lg_delta)) &
+		    ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1);
+
+		pszind_t ind = grp + mod;
+		return ind;
+	}
+}
+
+static inline size_t
+sz_pind2sz_compute(pszind_t pind) {
+	if (unlikely(pind == NPSIZES)) {
+		return LARGE_MAXCLASS + PAGE;
+	}
+	{
+		size_t grp = pind >> LG_SIZE_CLASS_GROUP;
+		size_t mod = pind & ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1);
+
+		size_t grp_size_mask = ~((!!grp)-1);
+		size_t grp_size = ((ZU(1) << (LG_PAGE +
+		    (LG_SIZE_CLASS_GROUP-1))) << grp) & grp_size_mask;
+
+		size_t shift = (grp == 0) ? 1 : grp;
+		size_t lg_delta = shift + (LG_PAGE-1);
+		size_t mod_size = (mod+1) << lg_delta;
+
+		size_t sz = grp_size + mod_size;
+		return sz;
+	}
+}
+
+static inline size_t
+sz_pind2sz_lookup(pszind_t pind) {
+	size_t ret = (size_t)sz_pind2sz_tab[pind];
+	assert(ret == sz_pind2sz_compute(pind));
+	return ret;
+}
+
+static inline size_t
+sz_pind2sz(pszind_t pind) {
+	assert(pind < NPSIZES+1);
+	return sz_pind2sz_lookup(pind);
+}
+
+static inline size_t
+sz_psz2u(size_t psz) {
+	if (unlikely(psz > LARGE_MAXCLASS)) {
+		return LARGE_MAXCLASS + PAGE;
+	}
+	{
+		size_t x = lg_floor((psz<<1)-1);
+		size_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_PAGE + 1) ?
+		    LG_PAGE : x - LG_SIZE_CLASS_GROUP - 1;
+		size_t delta = ZU(1) << lg_delta;
+		size_t delta_mask = delta - 1;
+		size_t usize = (psz + delta_mask) & ~delta_mask;
+		return usize;
+	}
+}
+
+static inline szind_t
+sz_size2index_compute(size_t size) {
+	if (unlikely(size > LARGE_MAXCLASS)) {
+		return NSIZES;
+	}
+#if (NTBINS != 0)
+	if (size <= (ZU(1) << LG_TINY_MAXCLASS)) {
+		szind_t lg_tmin = LG_TINY_MAXCLASS - NTBINS + 1;
+		szind_t lg_ceil = lg_floor(pow2_ceil_zu(size));
+		return (lg_ceil < lg_tmin ? 0 : lg_ceil - lg_tmin);
+	}
+#endif
+	{
+		szind_t x = lg_floor((size<<1)-1);
+		szind_t shift = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM) ? 0 :
+		    x - (LG_SIZE_CLASS_GROUP + LG_QUANTUM);
+		szind_t grp = shift << LG_SIZE_CLASS_GROUP;
+
+		szind_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM + 1)
+		    ? LG_QUANTUM : x - LG_SIZE_CLASS_GROUP - 1;
+
+		size_t delta_inverse_mask = ZD(-1) << lg_delta;
+		szind_t mod = ((((size-1) & delta_inverse_mask) >> lg_delta)) &
+		    ((ZU(1) << LG_SIZE_CLASS_GROUP) - 1);
+
+		szind_t index = NTBINS + grp + mod;
+		return index;
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE szind_t
+sz_size2index_lookup(size_t size) {
+	assert(size <= LOOKUP_MAXCLASS);
+	{
+		szind_t ret = (sz_size2index_tab[(size-1) >> LG_TINY_MIN]);
+		assert(ret == sz_size2index_compute(size));
+		return ret;
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE szind_t
+sz_size2index(size_t size) {
+	assert(size > 0);
+	if (likely(size <= LOOKUP_MAXCLASS)) {
+		return sz_size2index_lookup(size);
+	}
+	return sz_size2index_compute(size);
+}
+
+static inline size_t
+sz_index2size_compute(szind_t index) {
+#if (NTBINS > 0)
+	if (index < NTBINS) {
+		return (ZU(1) << (LG_TINY_MAXCLASS - NTBINS + 1 + index));
+	}
+#endif
+	{
+		size_t reduced_index = index - NTBINS;
+		size_t grp = reduced_index >> LG_SIZE_CLASS_GROUP;
+		size_t mod = reduced_index & ((ZU(1) << LG_SIZE_CLASS_GROUP) -
+		    1);
+
+		size_t grp_size_mask = ~((!!grp)-1);
+		size_t grp_size = ((ZU(1) << (LG_QUANTUM +
+		    (LG_SIZE_CLASS_GROUP-1))) << grp) & grp_size_mask;
+
+		size_t shift = (grp == 0) ? 1 : grp;
+		size_t lg_delta = shift + (LG_QUANTUM-1);
+		size_t mod_size = (mod+1) << lg_delta;
+
+		size_t usize = grp_size + mod_size;
+		return usize;
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+sz_index2size_lookup(szind_t index) {
+	size_t ret = (size_t)sz_index2size_tab[index];
+	assert(ret == sz_index2size_compute(index));
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+sz_index2size(szind_t index) {
+	assert(index < NSIZES);
+	return sz_index2size_lookup(index);
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+sz_s2u_compute(size_t size) {
+	if (unlikely(size > LARGE_MAXCLASS)) {
+		return 0;
+	}
+#if (NTBINS > 0)
+	if (size <= (ZU(1) << LG_TINY_MAXCLASS)) {
+		size_t lg_tmin = LG_TINY_MAXCLASS - NTBINS + 1;
+		size_t lg_ceil = lg_floor(pow2_ceil_zu(size));
+		return (lg_ceil < lg_tmin ? (ZU(1) << lg_tmin) :
+		    (ZU(1) << lg_ceil));
+	}
+#endif
+	{
+		size_t x = lg_floor((size<<1)-1);
+		size_t lg_delta = (x < LG_SIZE_CLASS_GROUP + LG_QUANTUM + 1)
+		    ?  LG_QUANTUM : x - LG_SIZE_CLASS_GROUP - 1;
+		size_t delta = ZU(1) << lg_delta;
+		size_t delta_mask = delta - 1;
+		size_t usize = (size + delta_mask) & ~delta_mask;
+		return usize;
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+sz_s2u_lookup(size_t size) {
+	size_t ret = sz_index2size_lookup(sz_size2index_lookup(size));
+
+	assert(ret == sz_s2u_compute(size));
+	return ret;
+}
+
+/*
+ * Compute usable size that would result from allocating an object with the
+ * specified size.
+ */
+JEMALLOC_ALWAYS_INLINE size_t
+sz_s2u(size_t size) {
+	assert(size > 0);
+	if (likely(size <= LOOKUP_MAXCLASS)) {
+		return sz_s2u_lookup(size);
+	}
+	return sz_s2u_compute(size);
+}
+
+/*
+ * Compute usable size that would result from allocating an object with the
+ * specified size and alignment.
+ */
+JEMALLOC_ALWAYS_INLINE size_t
+sz_sa2u(size_t size, size_t alignment) {
+	size_t usize;
+
+	assert(alignment != 0 && ((alignment - 1) & alignment) == 0);
+
+	/* Try for a small size class. */
+	if (size <= SMALL_MAXCLASS && alignment < PAGE) {
+		/*
+		 * Round size up to the nearest multiple of alignment.
+		 *
+		 * This done, we can take advantage of the fact that for each
+		 * small size class, every object is aligned at the smallest
+		 * power of two that is non-zero in the base two representation
+		 * of the size.  For example:
+		 *
+		 *   Size |   Base 2 | Minimum alignment
+		 *   -----+----------+------------------
+		 *     96 |  1100000 |  32
+		 *    144 | 10100000 |  32
+		 *    192 | 11000000 |  64
+		 */
+		usize = sz_s2u(ALIGNMENT_CEILING(size, alignment));
+		if (usize < LARGE_MINCLASS) {
+			return usize;
+		}
+	}
+
+	/* Large size class.  Beware of overflow. */
+
+	if (unlikely(alignment > LARGE_MAXCLASS)) {
+		return 0;
+	}
+
+	/* Make sure result is a large size class. */
+	if (size <= LARGE_MINCLASS) {
+		usize = LARGE_MINCLASS;
+	} else {
+		usize = sz_s2u(size);
+		if (usize < size) {
+			/* size_t overflow. */
+			return 0;
+		}
+	}
+
+	/*
+	 * Calculate the multi-page mapping that large_palloc() would need in
+	 * order to guarantee the alignment.
+	 */
+	if (usize + sz_large_pad + PAGE_CEILING(alignment) - PAGE < usize) {
+		/* size_t overflow. */
+		return 0;
+	}
+	return usize;
+}
+
+#endif /* JEMALLOC_INTERNAL_SIZE_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_externs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_externs.h
new file mode 100644
index 0000000000..db3e9c7d5d
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_externs.h
@@ -0,0 +1,55 @@
+#ifndef JEMALLOC_INTERNAL_TCACHE_EXTERNS_H
+#define JEMALLOC_INTERNAL_TCACHE_EXTERNS_H
+
+#include "jemalloc/internal/size_classes.h"
+
+extern bool	opt_tcache;
+extern ssize_t	opt_lg_tcache_max;
+
+extern tcache_bin_info_t	*tcache_bin_info;
+
+/*
+ * Number of tcache bins.  There are NBINS small-object bins, plus 0 or more
+ * large-object bins.
+ */
+extern unsigned	nhbins;
+
+/* Maximum cached size class. */
+extern size_t	tcache_maxclass;
+
+/*
+ * Explicit tcaches, managed via the tcache.{create,flush,destroy} mallctls and
+ * usable via the MALLOCX_TCACHE() flag.  The automatic per thread tcaches are
+ * completely disjoint from this data structure.  tcaches starts off as a sparse
+ * array, so it has no physical memory footprint until individual pages are
+ * touched.  This allows the entire array to be allocated the first time an
+ * explicit tcache is created without a disproportionate impact on memory usage.
+ */
+extern tcaches_t	*tcaches;
+
+size_t	tcache_salloc(tsdn_t *tsdn, const void *ptr);
+void	tcache_event_hard(tsd_t *tsd, tcache_t *tcache);
+void	*tcache_alloc_small_hard(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache,
+    tcache_bin_t *tbin, szind_t binind, bool *tcache_success);
+void	tcache_bin_flush_small(tsd_t *tsd, tcache_t *tcache, tcache_bin_t *tbin,
+    szind_t binind, unsigned rem);
+void	tcache_bin_flush_large(tsd_t *tsd, tcache_bin_t *tbin, szind_t binind,
+    unsigned rem, tcache_t *tcache);
+void	tcache_arena_reassociate(tsdn_t *tsdn, tcache_t *tcache,
+    arena_t *arena);
+tcache_t *tcache_create_explicit(tsd_t *tsd);
+void	tcache_cleanup(tsd_t *tsd);
+void	tcache_stats_merge(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena);
+bool	tcaches_create(tsd_t *tsd, unsigned *r_ind);
+void	tcaches_flush(tsd_t *tsd, unsigned ind);
+void	tcaches_destroy(tsd_t *tsd, unsigned ind);
+bool	tcache_boot(tsdn_t *tsdn);
+void tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena);
+void tcache_prefork(tsdn_t *tsdn);
+void tcache_postfork_parent(tsdn_t *tsdn);
+void tcache_postfork_child(tsdn_t *tsdn);
+void tcache_flush(tsd_t *tsd);
+bool tsd_tcache_data_init(tsd_t *tsd);
+bool tsd_tcache_enabled_data_init(tsd_t *tsd);
+
+#endif /* JEMALLOC_INTERNAL_TCACHE_EXTERNS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_inlines.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_inlines.h
new file mode 100644
index 0000000000..c55bcd2723
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_inlines.h
@@ -0,0 +1,250 @@
+#ifndef JEMALLOC_INTERNAL_TCACHE_INLINES_H
+#define JEMALLOC_INTERNAL_TCACHE_INLINES_H
+
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/sz.h"
+#include "jemalloc/internal/ticker.h"
+#include "jemalloc/internal/util.h"
+
+static inline bool
+tcache_enabled_get(tsd_t *tsd) {
+	return tsd_tcache_enabled_get(tsd);
+}
+
+static inline void
+tcache_enabled_set(tsd_t *tsd, bool enabled) {
+	bool was_enabled = tsd_tcache_enabled_get(tsd);
+
+	if (!was_enabled && enabled) {
+		tsd_tcache_data_init(tsd);
+	} else if (was_enabled && !enabled) {
+		tcache_cleanup(tsd);
+	}
+	/* Commit the state last.  Above calls check current state. */
+	tsd_tcache_enabled_set(tsd, enabled);
+	tsd_slow_update(tsd);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tcache_event(tsd_t *tsd, tcache_t *tcache) {
+	if (TCACHE_GC_INCR == 0) {
+		return;
+	}
+
+	if (unlikely(ticker_tick(&tcache->gc_ticker))) {
+		tcache_event_hard(tsd, tcache);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+tcache_alloc_easy(tcache_bin_t *tbin, bool *tcache_success) {
+	void *ret;
+
+	if (unlikely(tbin->ncached == 0)) {
+		tbin->low_water = -1;
+		*tcache_success = false;
+		return NULL;
+	}
+	/*
+	 * tcache_success (instead of ret) should be checked upon the return of
+	 * this function.  We avoid checking (ret == NULL) because there is
+	 * never a null stored on the avail stack (which is unknown to the
+	 * compiler), and eagerly checking ret would cause pipeline stall
+	 * (waiting for the cacheline).
+	 */
+	*tcache_success = true;
+	ret = *(tbin->avail - tbin->ncached);
+	tbin->ncached--;
+
+	if (unlikely((low_water_t)tbin->ncached < tbin->low_water)) {
+		tbin->low_water = tbin->ncached;
+	}
+
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+tcache_alloc_small(tsd_t *tsd, arena_t *arena, tcache_t *tcache, size_t size,
+    szind_t binind, bool zero, bool slow_path) {
+	void *ret;
+	tcache_bin_t *tbin;
+	bool tcache_success;
+	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
+
+	assert(binind < NBINS);
+	tbin = tcache_small_bin_get(tcache, binind);
+	ret = tcache_alloc_easy(tbin, &tcache_success);
+	assert(tcache_success == (ret != NULL));
+	if (unlikely(!tcache_success)) {
+		bool tcache_hard_success;
+		arena = arena_choose(tsd, arena);
+		if (unlikely(arena == NULL)) {
+			return NULL;
+		}
+
+		ret = tcache_alloc_small_hard(tsd_tsdn(tsd), arena, tcache,
+		    tbin, binind, &tcache_hard_success);
+		if (tcache_hard_success == false) {
+			return NULL;
+		}
+	}
+
+	assert(ret);
+	/*
+	 * Only compute usize if required.  The checks in the following if
+	 * statement are all static.
+	 */
+	if (config_prof || (slow_path && config_fill) || unlikely(zero)) {
+		usize = sz_index2size(binind);
+		assert(tcache_salloc(tsd_tsdn(tsd), ret) == usize);
+	}
+
+	if (likely(!zero)) {
+		if (slow_path && config_fill) {
+			if (unlikely(opt_junk_alloc)) {
+				arena_alloc_junk_small(ret,
+				    &arena_bin_info[binind], false);
+			} else if (unlikely(opt_zero)) {
+				memset(ret, 0, usize);
+			}
+		}
+	} else {
+		if (slow_path && config_fill && unlikely(opt_junk_alloc)) {
+			arena_alloc_junk_small(ret, &arena_bin_info[binind],
+			    true);
+		}
+		memset(ret, 0, usize);
+	}
+
+	if (config_stats) {
+		tbin->tstats.nrequests++;
+	}
+	if (config_prof) {
+		tcache->prof_accumbytes += usize;
+	}
+	tcache_event(tsd, tcache);
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void *
+tcache_alloc_large(tsd_t *tsd, arena_t *arena, tcache_t *tcache, size_t size,
+    szind_t binind, bool zero, bool slow_path) {
+	void *ret;
+	tcache_bin_t *tbin;
+	bool tcache_success;
+
+	assert(binind >= NBINS &&binind < nhbins);
+	tbin = tcache_large_bin_get(tcache, binind);
+	ret = tcache_alloc_easy(tbin, &tcache_success);
+	assert(tcache_success == (ret != NULL));
+	if (unlikely(!tcache_success)) {
+		/*
+		 * Only allocate one large object at a time, because it's quite
+		 * expensive to create one and not use it.
+		 */
+		arena = arena_choose(tsd, arena);
+		if (unlikely(arena == NULL)) {
+			return NULL;
+		}
+
+		ret = large_malloc(tsd_tsdn(tsd), arena, sz_s2u(size), zero);
+		if (ret == NULL) {
+			return NULL;
+		}
+	} else {
+		size_t usize JEMALLOC_CC_SILENCE_INIT(0);
+
+		/* Only compute usize on demand */
+		if (config_prof || (slow_path && config_fill) ||
+		    unlikely(zero)) {
+			usize = sz_index2size(binind);
+			assert(usize <= tcache_maxclass);
+		}
+
+		if (likely(!zero)) {
+			if (slow_path && config_fill) {
+				if (unlikely(opt_junk_alloc)) {
+					memset(ret, JEMALLOC_ALLOC_JUNK,
+					    usize);
+				} else if (unlikely(opt_zero)) {
+					memset(ret, 0, usize);
+				}
+			}
+		} else {
+			memset(ret, 0, usize);
+		}
+
+		if (config_stats) {
+			tbin->tstats.nrequests++;
+		}
+		if (config_prof) {
+			tcache->prof_accumbytes += usize;
+		}
+	}
+
+	tcache_event(tsd, tcache);
+	return ret;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tcache_dalloc_small(tsd_t *tsd, tcache_t *tcache, void *ptr, szind_t binind,
+    bool slow_path) {
+	tcache_bin_t *tbin;
+	tcache_bin_info_t *tbin_info;
+
+	assert(tcache_salloc(tsd_tsdn(tsd), ptr) <= SMALL_MAXCLASS);
+
+	if (slow_path && config_fill && unlikely(opt_junk_free)) {
+		arena_dalloc_junk_small(ptr, &arena_bin_info[binind]);
+	}
+
+	tbin = tcache_small_bin_get(tcache, binind);
+	tbin_info = &tcache_bin_info[binind];
+	if (unlikely(tbin->ncached == tbin_info->ncached_max)) {
+		tcache_bin_flush_small(tsd, tcache, tbin, binind,
+		    (tbin_info->ncached_max >> 1));
+	}
+	assert(tbin->ncached < tbin_info->ncached_max);
+	tbin->ncached++;
+	*(tbin->avail - tbin->ncached) = ptr;
+
+	tcache_event(tsd, tcache);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tcache_dalloc_large(tsd_t *tsd, tcache_t *tcache, void *ptr, szind_t binind,
+    bool slow_path) {
+	tcache_bin_t *tbin;
+	tcache_bin_info_t *tbin_info;
+
+	assert(tcache_salloc(tsd_tsdn(tsd), ptr) > SMALL_MAXCLASS);
+	assert(tcache_salloc(tsd_tsdn(tsd), ptr) <= tcache_maxclass);
+
+	if (slow_path && config_fill && unlikely(opt_junk_free)) {
+		large_dalloc_junk(ptr, sz_index2size(binind));
+	}
+
+	tbin = tcache_large_bin_get(tcache, binind);
+	tbin_info = &tcache_bin_info[binind];
+	if (unlikely(tbin->ncached == tbin_info->ncached_max)) {
+		tcache_bin_flush_large(tsd, tbin, binind,
+		    (tbin_info->ncached_max >> 1), tcache);
+	}
+	assert(tbin->ncached < tbin_info->ncached_max);
+	tbin->ncached++;
+	*(tbin->avail - tbin->ncached) = ptr;
+
+	tcache_event(tsd, tcache);
+}
+
+JEMALLOC_ALWAYS_INLINE tcache_t *
+tcaches_get(tsd_t *tsd, unsigned ind) {
+	tcaches_t *elm = &tcaches[ind];
+	if (unlikely(elm->tcache == NULL)) {
+		elm->tcache = tcache_create_explicit(tsd);
+	}
+	return elm->tcache;
+}
+
+#endif /* JEMALLOC_INTERNAL_TCACHE_INLINES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_structs.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_structs.h
new file mode 100644
index 0000000000..7eb516fb6b
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_structs.h
@@ -0,0 +1,64 @@
+#ifndef JEMALLOC_INTERNAL_TCACHE_STRUCTS_H
+#define JEMALLOC_INTERNAL_TCACHE_STRUCTS_H
+
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/stats_tsd.h"
+#include "jemalloc/internal/ticker.h"
+
+/*
+ * Read-only information associated with each element of tcache_t's tbins array
+ * is stored separately, mainly to reduce memory usage.
+ */
+struct tcache_bin_info_s {
+	unsigned	ncached_max;	/* Upper limit on ncached. */
+};
+
+struct tcache_bin_s {
+	low_water_t	low_water;	/* Min # cached since last GC. */
+	uint32_t	ncached;	/* # of cached objects. */
+	/*
+	 * ncached and stats are both modified frequently.  Let's keep them
+	 * close so that they have a higher chance of being on the same
+	 * cacheline, thus less write-backs.
+	 */
+	tcache_bin_stats_t tstats;
+	/*
+	 * To make use of adjacent cacheline prefetch, the items in the avail
+	 * stack goes to higher address for newer allocations.  avail points
+	 * just above the available space, which means that
+	 * avail[-ncached, ... -1] are available items and the lowest item will
+	 * be allocated first.
+	 */
+	void		**avail;	/* Stack of available objects. */
+};
+
+struct tcache_s {
+	/* Data accessed frequently first: prof, ticker and small bins. */
+	uint64_t	prof_accumbytes;/* Cleared after arena_prof_accum(). */
+	ticker_t	gc_ticker;	/* Drives incremental GC. */
+	/*
+	 * The pointer stacks associated with tbins follow as a contiguous
+	 * array.  During tcache initialization, the avail pointer in each
+	 * element of tbins is initialized to point to the proper offset within
+	 * this array.
+	 */
+	tcache_bin_t	tbins_small[NBINS];
+	/* Data accessed less often below. */
+	ql_elm(tcache_t) link;		/* Used for aggregating stats. */
+	arena_t		*arena;		/* Associated arena. */
+	szind_t		next_gc_bin;	/* Next bin to GC. */
+	/* For small bins, fill (ncached_max >> lg_fill_div). */
+	uint8_t		lg_fill_div[NBINS];
+	tcache_bin_t	tbins_large[NSIZES-NBINS];
+};
+
+/* Linkage for list of available (previously used) explicit tcache IDs. */
+struct tcaches_s {
+	union {
+		tcache_t	*tcache;
+		tcaches_t	*next;
+	};
+};
+
+#endif /* JEMALLOC_INTERNAL_TCACHE_STRUCTS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_types.h
new file mode 100644
index 0000000000..1155d62cb4
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tcache_types.h
@@ -0,0 +1,61 @@
+#ifndef JEMALLOC_INTERNAL_TCACHE_TYPES_H
+#define JEMALLOC_INTERNAL_TCACHE_TYPES_H
+
+#include "jemalloc/internal/size_classes.h"
+
+typedef struct tcache_bin_info_s tcache_bin_info_t;
+typedef struct tcache_bin_s tcache_bin_t;
+typedef struct tcache_s tcache_t;
+typedef struct tcaches_s tcaches_t;
+
+/* ncached is cast to this type for comparison. */
+typedef int32_t low_water_t;
+
+/*
+ * tcache pointers close to NULL are used to encode state information that is
+ * used for two purposes: preventing thread caching on a per thread basis and
+ * cleaning up during thread shutdown.
+ */
+#define TCACHE_STATE_DISABLED		((tcache_t *)(uintptr_t)1)
+#define TCACHE_STATE_REINCARNATED	((tcache_t *)(uintptr_t)2)
+#define TCACHE_STATE_PURGATORY		((tcache_t *)(uintptr_t)3)
+#define TCACHE_STATE_MAX		TCACHE_STATE_PURGATORY
+
+/*
+ * Absolute minimum number of cache slots for each small bin.
+ */
+#define TCACHE_NSLOTS_SMALL_MIN		20
+
+/*
+ * Absolute maximum number of cache slots for each small bin in the thread
+ * cache.  This is an additional constraint beyond that imposed as: twice the
+ * number of regions per slab for this size class.
+ *
+ * This constant must be an even number.
+ */
+#define TCACHE_NSLOTS_SMALL_MAX		200
+
+/* Number of cache slots for large size classes. */
+#define TCACHE_NSLOTS_LARGE		20
+
+/* (1U << opt_lg_tcache_max) is used to compute tcache_maxclass. */
+#define LG_TCACHE_MAXCLASS_DEFAULT	15
+
+/*
+ * TCACHE_GC_SWEEP is the approximate number of allocation events between
+ * full GC sweeps.  Integer rounding may cause the actual number to be
+ * slightly higher, since GC is performed incrementally.
+ */
+#define TCACHE_GC_SWEEP			8192
+
+/* Number of tcache allocation/deallocation events between incremental GCs. */
+#define TCACHE_GC_INCR							\
+    ((TCACHE_GC_SWEEP / NBINS) + ((TCACHE_GC_SWEEP / NBINS == 0) ? 0 : 1))
+
+/* Used in TSD static initializer only. Real init in tcache_data_init(). */
+#define TCACHE_ZERO_INITIALIZER {0}
+
+/* Used in TSD static initializer only. Will be initialized to opt_tcache. */
+#define TCACHE_ENABLED_ZERO_INITIALIZER false
+
+#endif /* JEMALLOC_INTERNAL_TCACHE_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ticker.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ticker.h
new file mode 100644
index 0000000000..572b96459c
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/ticker.h
@@ -0,0 +1,50 @@
+#ifndef JEMALLOC_INTERNAL_TICKER_H
+#define JEMALLOC_INTERNAL_TICKER_H
+
+#include "jemalloc/internal/util.h"
+
+/**
+ * A ticker makes it easy to count-down events until some limit.  You
+ * ticker_init the ticker to trigger every nticks events.  You then notify it
+ * that an event has occurred with calls to ticker_tick (or that nticks events
+ * have occurred with a call to ticker_ticks), which will return true (and reset
+ * the counter) if the countdown hit zero.
+ */
+
+typedef struct {
+	int32_t tick;
+	int32_t nticks;
+} ticker_t;
+
+static inline void
+ticker_init(ticker_t *ticker, int32_t nticks) {
+	ticker->tick = nticks;
+	ticker->nticks = nticks;
+}
+
+static inline void
+ticker_copy(ticker_t *ticker, const ticker_t *other) {
+	*ticker = *other;
+}
+
+static inline int32_t
+ticker_read(const ticker_t *ticker) {
+	return ticker->tick;
+}
+
+static inline bool
+ticker_ticks(ticker_t *ticker, int32_t nticks) {
+	if (unlikely(ticker->tick < nticks)) {
+		ticker->tick = ticker->nticks;
+		return true;
+	}
+	ticker->tick -= nticks;
+	return(false);
+}
+
+static inline bool
+ticker_tick(ticker_t *ticker) {
+	return ticker_ticks(ticker, 1);
+}
+
+#endif /* JEMALLOC_INTERNAL_TICKER_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd.h
index 9fb4a23ec6..155a2ec6c4 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd.h
@@ -1,434 +1,324 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_TSD_H
+#define JEMALLOC_INTERNAL_TSD_H
 
-/* Maximum number of malloc_tsd users with cleanup functions. */
-#define	MALLOC_TSD_CLEANUPS_MAX	8
+#include "jemalloc/internal/arena_types.h"
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/jemalloc_internal_externs.h"
+#include "jemalloc/internal/prof_types.h"
+#include "jemalloc/internal/ql.h"
+#include "jemalloc/internal/rtree_tsd.h"
+#include "jemalloc/internal/tcache_types.h"
+#include "jemalloc/internal/tcache_structs.h"
+#include "jemalloc/internal/util.h"
+#include "jemalloc/internal/witness.h"
 
-typedef bool (*malloc_tsd_cleanup_t)(void);
-
-#if (!defined(JEMALLOC_MALLOC_THREAD_CLEANUP) && !defined(JEMALLOC_TLS) && \
-    !defined(_WIN32))
-typedef struct tsd_init_block_s tsd_init_block_t;
-typedef struct tsd_init_head_s tsd_init_head_t;
+/*
+ * Thread-Specific-Data layout
+ * --- data accessed on tcache fast path: state, rtree_ctx, stats, prof ---
+ * s: state
+ * e: tcache_enabled
+ * m: thread_allocated (config_stats)
+ * f: thread_deallocated (config_stats)
+ * p: prof_tdata (config_prof)
+ * c: rtree_ctx (rtree cache accessed on deallocation)
+ * t: tcache
+ * --- data not accessed on tcache fast path: arena-related fields ---
+ * d: arenas_tdata_bypass
+ * r: reentrancy_level
+ * x: narenas_tdata
+ * i: iarena
+ * a: arena
+ * o: arenas_tdata
+ * Loading TSD data is on the critical path of basically all malloc operations.
+ * In particular, tcache and rtree_ctx rely on hot CPU cache to be effective.
+ * Use a compact layout to reduce cache footprint.
+ * +--- 64-bit and 64B cacheline; 1B each letter; First byte on the left. ---+
+ * |----------------------------  1st cacheline  ----------------------------|
+ * | sedrxxxx mmmmmmmm ffffffff pppppppp [c * 32  ........ ........ .......] |
+ * |----------------------------  2nd cacheline  ----------------------------|
+ * | [c * 64  ........ ........ ........ ........ ........ ........ .......] |
+ * |----------------------------  3nd cacheline  ----------------------------|
+ * | [c * 32  ........ ........ .......] iiiiiiii aaaaaaaa oooooooo [t...... |
+ * +-------------------------------------------------------------------------+
+ * Note: the entire tcache is embedded into TSD and spans multiple cachelines.
+ *
+ * The last 3 members (i, a and o) before tcache isn't really needed on tcache
+ * fast path.  However we have a number of unused tcache bins and witnesses
+ * (never touched unless config_debug) at the end of tcache, so we place them
+ * there to avoid breaking the cachelines and possibly paging in an extra page.
+ */
+#ifdef JEMALLOC_JET
+typedef void (*test_callback_t)(int *);
+#  define MALLOC_TSD_TEST_DATA_INIT 0x72b65c10
+#  define MALLOC_TEST_TSD \
+    O(test_data,		int,			int)		\
+    O(test_callback,		test_callback_t,	int)
+#  define MALLOC_TEST_TSD_INITIALIZER , MALLOC_TSD_TEST_DATA_INIT, NULL
+#else
+#  define MALLOC_TEST_TSD
+#  define MALLOC_TEST_TSD_INITIALIZER
 #endif
 
+/*  O(name,			type,			nullable type */
+#define MALLOC_TSD							\
+    O(tcache_enabled,		bool,			bool)		\
+    O(arenas_tdata_bypass,	bool,			bool)		\
+    O(reentrancy_level,		int8_t,			int8_t)		\
+    O(narenas_tdata,		uint32_t,		uint32_t)	\
+    O(thread_allocated,		uint64_t,		uint64_t)	\
+    O(thread_deallocated,	uint64_t,		uint64_t)	\
+    O(prof_tdata,		prof_tdata_t *,		prof_tdata_t *)	\
+    O(rtree_ctx,		rtree_ctx_t,		rtree_ctx_t)	\
+    O(iarena,			arena_t *,		arena_t *)	\
+    O(arena,			arena_t *,		arena_t *)	\
+    O(arenas_tdata,		arena_tdata_t *,	arena_tdata_t *)\
+    O(tcache,			tcache_t,		tcache_t)	\
+    O(witness_tsd,              witness_tsd_t,		witness_tsdn_t)	\
+    MALLOC_TEST_TSD
+
+#define TSD_INITIALIZER {						\
+    tsd_state_uninitialized,						\
+    TCACHE_ENABLED_ZERO_INITIALIZER,					\
+    false,								\
+    0,									\
+    0,									\
+    0,									\
+    0,									\
+    NULL,								\
+    RTREE_CTX_ZERO_INITIALIZER,						\
+    NULL,								\
+    NULL,								\
+    NULL,								\
+    TCACHE_ZERO_INITIALIZER,						\
+    WITNESS_TSD_INITIALIZER						\
+    MALLOC_TEST_TSD_INITIALIZER						\
+}
+
+enum {
+	tsd_state_nominal = 0, /* Common case --> jnz. */
+	tsd_state_nominal_slow = 1, /* Initialized but on slow path. */
+	/* the above 2 nominal states should be lower values. */
+	tsd_state_nominal_max = 1, /* used for comparison only. */
+	tsd_state_minimal_initialized = 2,
+	tsd_state_purgatory = 3,
+	tsd_state_reincarnated = 4,
+	tsd_state_uninitialized = 5
+};
+
+/* Manually limit tsd_state_t to a single byte. */
+typedef uint8_t tsd_state_t;
+
+/* The actual tsd. */
+struct tsd_s {
+	/*
+	 * The contents should be treated as totally opaque outside the tsd
+	 * module.  Access any thread-local state through the getters and
+	 * setters below.
+	 */
+	tsd_state_t	state;
+#define O(n, t, nt)							\
+	t use_a_getter_or_setter_instead_##n;
+MALLOC_TSD
+#undef O
+};
+
 /*
- * TLS/TSD-agnostic macro-based implementation of thread-specific data.  There
- * are four macros that support (at least) three use cases: file-private,
- * library-private, and library-private inlined.  Following is an example
- * library-private tsd variable:
- *
- * In example.h:
- *   typedef struct {
- *           int x;
- *           int y;
- *   } example_t;
- *   #define EX_INITIALIZER JEMALLOC_CONCAT({0, 0})
- *   malloc_tsd_protos(, example, example_t *)
- *   malloc_tsd_externs(example, example_t *)
- * In example.c:
- *   malloc_tsd_data(, example, example_t *, EX_INITIALIZER)
- *   malloc_tsd_funcs(, example, example_t *, EX_INITIALIZER,
- *       example_tsd_cleanup)
- *
- * The result is a set of generated functions, e.g.:
- *
- *   bool example_tsd_boot(void) {...}
- *   example_t **example_tsd_get() {...}
- *   void example_tsd_set(example_t **val) {...}
- *
- * Note that all of the functions deal in terms of (a_type *) rather than
- * (a_type)  so that it is possible to support non-pointer types (unlike
- * pthreads TSD).  example_tsd_cleanup() is passed an (a_type *) pointer that is
- * cast to (void *).  This means that the cleanup function needs to cast *and*
- * dereference the function argument, e.g.:
- *
- *   void
- *   example_tsd_cleanup(void *arg)
- *   {
- *           example_t *example = *(example_t **)arg;
- *
- *           [...]
- *           if ([want the cleanup function to be called again]) {
- *                   example_tsd_set(&example);
- *           }
- *   }
- *
- * If example_tsd_set() is called within example_tsd_cleanup(), it will be
- * called again.  This is similar to how pthreads TSD destruction works, except
- * that pthreads only calls the cleanup function again if the value was set to
- * non-NULL.
+ * Wrapper around tsd_t that makes it possible to avoid implicit conversion
+ * between tsd_t and tsdn_t, where tsdn_t is "nullable" and has to be
+ * explicitly converted to tsd_t, which is non-nullable.
  */
+struct tsdn_s {
+	tsd_t tsd;
+};
+#define TSDN_NULL ((tsdn_t *)0)
+JEMALLOC_ALWAYS_INLINE tsdn_t *
+tsd_tsdn(tsd_t *tsd) {
+	return (tsdn_t *)tsd;
+}
 
-/* malloc_tsd_protos(). */
-#define	malloc_tsd_protos(a_attr, a_name, a_type)			\
-a_attr bool								\
-a_name##_tsd_boot(void);						\
-a_attr a_type *								\
-a_name##_tsd_get(void);							\
-a_attr void								\
-a_name##_tsd_set(a_type *val);
+JEMALLOC_ALWAYS_INLINE bool
+tsdn_null(const tsdn_t *tsdn) {
+	return tsdn == NULL;
+}
 
-/* malloc_tsd_externs(). */
-#ifdef JEMALLOC_MALLOC_THREAD_CLEANUP
-#define	malloc_tsd_externs(a_name, a_type)				\
-extern __thread a_type	a_name##_tls;					\
-extern __thread bool	a_name##_initialized;				\
-extern bool		a_name##_booted;
-#elif (defined(JEMALLOC_TLS))
-#define	malloc_tsd_externs(a_name, a_type)				\
-extern __thread a_type	a_name##_tls;					\
-extern pthread_key_t	a_name##_tsd;					\
-extern bool		a_name##_booted;
-#elif (defined(_WIN32))
-#define	malloc_tsd_externs(a_name, a_type)				\
-extern DWORD		a_name##_tsd;					\
-extern bool		a_name##_booted;
-#else
-#define	malloc_tsd_externs(a_name, a_type)				\
-extern pthread_key_t	a_name##_tsd;					\
-extern tsd_init_head_t	a_name##_tsd_init_head;				\
-extern bool		a_name##_booted;
-#endif
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsdn_tsd(tsdn_t *tsdn) {
+	assert(!tsdn_null(tsdn));
+
+	return &tsdn->tsd;
+}
+
+void *malloc_tsd_malloc(size_t size);
+void malloc_tsd_dalloc(void *wrapper);
+void malloc_tsd_cleanup_register(bool (*f)(void));
+tsd_t *malloc_tsd_boot0(void);
+void malloc_tsd_boot1(void);
+void tsd_cleanup(void *arg);
+tsd_t *tsd_fetch_slow(tsd_t *tsd, bool internal);
+void tsd_slow_update(tsd_t *tsd);
 
-/* malloc_tsd_data(). */
+/*
+ * We put the platform-specific data declarations and inlines into their own
+ * header files to avoid cluttering this file.  They define tsd_boot0,
+ * tsd_boot1, tsd_boot, tsd_booted_get, tsd_get_allocates, tsd_get, and tsd_set.
+ */
 #ifdef JEMALLOC_MALLOC_THREAD_CLEANUP
-#define	malloc_tsd_data(a_attr, a_name, a_type, a_initializer)		\
-a_attr __thread a_type JEMALLOC_TLS_MODEL				\
-    a_name##_tls = a_initializer;					\
-a_attr __thread bool JEMALLOC_TLS_MODEL					\
-    a_name##_initialized = false;					\
-a_attr bool		a_name##_booted = false;
+#include "jemalloc/internal/tsd_malloc_thread_cleanup.h"
 #elif (defined(JEMALLOC_TLS))
-#define	malloc_tsd_data(a_attr, a_name, a_type, a_initializer)		\
-a_attr __thread a_type JEMALLOC_TLS_MODEL				\
-    a_name##_tls = a_initializer;					\
-a_attr pthread_key_t	a_name##_tsd;					\
-a_attr bool		a_name##_booted = false;
+#include "jemalloc/internal/tsd_tls.h"
 #elif (defined(_WIN32))
-#define	malloc_tsd_data(a_attr, a_name, a_type, a_initializer)		\
-a_attr DWORD		a_name##_tsd;					\
-a_attr bool		a_name##_booted = false;
+#include "jemalloc/internal/tsd_win.h"
 #else
-#define	malloc_tsd_data(a_attr, a_name, a_type, a_initializer)		\
-a_attr pthread_key_t	a_name##_tsd;					\
-a_attr tsd_init_head_t	a_name##_tsd_init_head = {			\
-	ql_head_initializer(blocks),					\
-	MALLOC_MUTEX_INITIALIZER					\
-};									\
-a_attr bool		a_name##_booted = false;
+#include "jemalloc/internal/tsd_generic.h"
 #endif
 
-/* malloc_tsd_funcs(). */
-#ifdef JEMALLOC_MALLOC_THREAD_CLEANUP
-#define	malloc_tsd_funcs(a_attr, a_name, a_type, a_initializer,		\
-    a_cleanup)								\
-/* Initialization/cleanup. */						\
-a_attr bool								\
-a_name##_tsd_cleanup_wrapper(void)					\
-{									\
-									\
-	if (a_name##_initialized) {					\
-		a_name##_initialized = false;				\
-		a_cleanup(&a_name##_tls);				\
-	}								\
-	return (a_name##_initialized);					\
-}									\
-a_attr bool								\
-a_name##_tsd_boot(void)							\
-{									\
-									\
-	if (a_cleanup != malloc_tsd_no_cleanup) {			\
-		malloc_tsd_cleanup_register(				\
-		    &a_name##_tsd_cleanup_wrapper);			\
-	}								\
-	a_name##_booted = true;						\
-	return (false);							\
-}									\
-/* Get/set. */								\
-a_attr a_type *								\
-a_name##_tsd_get(void)							\
-{									\
-									\
-	assert(a_name##_booted);					\
-	return (&a_name##_tls);						\
-}									\
-a_attr void								\
-a_name##_tsd_set(a_type *val)						\
-{									\
-									\
-	assert(a_name##_booted);					\
-	a_name##_tls = (*val);						\
-	if (a_cleanup != malloc_tsd_no_cleanup)				\
-		a_name##_initialized = true;				\
+/*
+ * tsd_foop_get_unsafe(tsd) returns a pointer to the thread-local instance of
+ * foo.  This omits some safety checks, and so can be used during tsd
+ * initialization and cleanup.
+ */
+#define O(n, t, nt)							\
+JEMALLOC_ALWAYS_INLINE t *						\
+tsd_##n##p_get_unsafe(tsd_t *tsd) {					\
+	return &tsd->use_a_getter_or_setter_instead_##n;		\
 }
-#elif (defined(JEMALLOC_TLS))
-#define	malloc_tsd_funcs(a_attr, a_name, a_type, a_initializer,		\
-    a_cleanup)								\
-/* Initialization/cleanup. */						\
-a_attr bool								\
-a_name##_tsd_boot(void)							\
-{									\
-									\
-	if (a_cleanup != malloc_tsd_no_cleanup) {			\
-		if (pthread_key_create(&a_name##_tsd, a_cleanup) != 0)	\
-			return (true);					\
-	}								\
-	a_name##_booted = true;						\
-	return (false);							\
-}									\
-/* Get/set. */								\
-a_attr a_type *								\
-a_name##_tsd_get(void)							\
-{									\
-									\
-	assert(a_name##_booted);					\
-	return (&a_name##_tls);						\
-}									\
-a_attr void								\
-a_name##_tsd_set(a_type *val)						\
-{									\
-									\
-	assert(a_name##_booted);					\
-	a_name##_tls = (*val);						\
-	if (a_cleanup != malloc_tsd_no_cleanup) {			\
-		if (pthread_setspecific(a_name##_tsd,			\
-		    (void *)(&a_name##_tls))) {				\
-			malloc_write("<jemalloc>: Error"		\
-			    " setting TSD for "#a_name"\n");		\
-			if (opt_abort)					\
-				abort();				\
-		}							\
-	}								\
+MALLOC_TSD
+#undef O
+
+/* tsd_foop_get(tsd) returns a pointer to the thread-local instance of foo. */
+#define O(n, t, nt)							\
+JEMALLOC_ALWAYS_INLINE t *						\
+tsd_##n##p_get(tsd_t *tsd) {						\
+	assert(tsd->state == tsd_state_nominal ||			\
+	    tsd->state == tsd_state_nominal_slow ||			\
+	    tsd->state == tsd_state_reincarnated ||			\
+	    tsd->state == tsd_state_minimal_initialized);		\
+	return tsd_##n##p_get_unsafe(tsd);				\
 }
-#elif (defined(_WIN32))
-#define	malloc_tsd_funcs(a_attr, a_name, a_type, a_initializer,		\
-    a_cleanup)								\
-/* Data structure. */							\
-typedef struct {							\
-	bool	initialized;						\
-	a_type	val;							\
-} a_name##_tsd_wrapper_t;						\
-/* Initialization/cleanup. */						\
-a_attr bool								\
-a_name##_tsd_cleanup_wrapper(void)					\
-{									\
-	a_name##_tsd_wrapper_t *wrapper;				\
-									\
-	wrapper = (a_name##_tsd_wrapper_t *) TlsGetValue(a_name##_tsd);	\
-	if (wrapper == NULL)						\
-		return (false);						\
-	if (a_cleanup != malloc_tsd_no_cleanup &&			\
-	    wrapper->initialized) {					\
-		a_type val = wrapper->val;				\
-		a_type tsd_static_data = a_initializer;			\
-		wrapper->initialized = false;				\
-		wrapper->val = tsd_static_data;				\
-		a_cleanup(&val);					\
-		if (wrapper->initialized) {				\
-			/* Trigger another cleanup round. */		\
-			return (true);					\
-		}							\
-	}								\
-	malloc_tsd_dalloc(wrapper);					\
-	return (false);							\
-}									\
-a_attr bool								\
-a_name##_tsd_boot(void)							\
-{									\
-									\
-	a_name##_tsd = TlsAlloc();					\
-	if (a_name##_tsd == TLS_OUT_OF_INDEXES)				\
-		return (true);						\
-	if (a_cleanup != malloc_tsd_no_cleanup) {			\
-		malloc_tsd_cleanup_register(				\
-		    &a_name##_tsd_cleanup_wrapper);			\
-	}								\
-	a_name##_booted = true;						\
-	return (false);							\
-}									\
-/* Get/set. */								\
-a_attr a_name##_tsd_wrapper_t *						\
-a_name##_tsd_get_wrapper(void)						\
-{									\
-	a_name##_tsd_wrapper_t *wrapper = (a_name##_tsd_wrapper_t *)	\
-	    TlsGetValue(a_name##_tsd);					\
-									\
-	if (wrapper == NULL) {						\
-		wrapper = (a_name##_tsd_wrapper_t *)			\
-		    malloc_tsd_malloc(sizeof(a_name##_tsd_wrapper_t));	\
-		if (wrapper == NULL) {					\
-			malloc_write("<jemalloc>: Error allocating"	\
-			    " TSD for "#a_name"\n");			\
-			abort();					\
-		} else {						\
-			static a_type tsd_static_data = a_initializer;	\
-			wrapper->initialized = false;			\
-			wrapper->val = tsd_static_data;			\
-		}							\
-		if (!TlsSetValue(a_name##_tsd, (void *)wrapper)) {	\
-			malloc_write("<jemalloc>: Error setting"	\
-			    " TSD for "#a_name"\n");			\
-			abort();					\
-		}							\
+MALLOC_TSD
+#undef O
+
+/*
+ * tsdn_foop_get(tsdn) returns either the thread-local instance of foo (if tsdn
+ * isn't NULL), or NULL (if tsdn is NULL), cast to the nullable pointer type.
+ */
+#define O(n, t, nt)							\
+JEMALLOC_ALWAYS_INLINE nt *						\
+tsdn_##n##p_get(tsdn_t *tsdn) {						\
+	if (tsdn_null(tsdn)) {						\
+		return NULL;						\
 	}								\
-	return (wrapper);						\
-}									\
-a_attr a_type *								\
-a_name##_tsd_get(void)							\
-{									\
-	a_name##_tsd_wrapper_t *wrapper;				\
-									\
-	assert(a_name##_booted);					\
-	wrapper = a_name##_tsd_get_wrapper();				\
-	return (&wrapper->val);						\
-}									\
-a_attr void								\
-a_name##_tsd_set(a_type *val)						\
-{									\
-	a_name##_tsd_wrapper_t *wrapper;				\
-									\
-	assert(a_name##_booted);					\
-	wrapper = a_name##_tsd_get_wrapper();				\
-	wrapper->val = *(val);						\
-	if (a_cleanup != malloc_tsd_no_cleanup)				\
-		wrapper->initialized = true;				\
+	tsd_t *tsd = tsdn_tsd(tsdn);					\
+	return (nt *)tsd_##n##p_get(tsd);				\
 }
-#else
-#define	malloc_tsd_funcs(a_attr, a_name, a_type, a_initializer,		\
-    a_cleanup)								\
-/* Data structure. */							\
-typedef struct {							\
-	bool	initialized;						\
-	a_type	val;							\
-} a_name##_tsd_wrapper_t;						\
-/* Initialization/cleanup. */						\
-a_attr void								\
-a_name##_tsd_cleanup_wrapper(void *arg)					\
-{									\
-	a_name##_tsd_wrapper_t *wrapper = (a_name##_tsd_wrapper_t *)arg;\
-									\
-	if (a_cleanup != malloc_tsd_no_cleanup &&			\
-	    wrapper->initialized) {					\
-		wrapper->initialized = false;				\
-		a_cleanup(&wrapper->val);				\
-		if (wrapper->initialized) {				\
-			/* Trigger another cleanup round. */		\
-			if (pthread_setspecific(a_name##_tsd,		\
-			    (void *)wrapper)) {				\
-				malloc_write("<jemalloc>: Error"	\
-				    " setting TSD for "#a_name"\n");	\
-				if (opt_abort)				\
-					abort();			\
-			}						\
-			return;						\
-		}							\
-	}								\
-	malloc_tsd_dalloc(wrapper);					\
-}									\
-a_attr bool								\
-a_name##_tsd_boot(void)							\
-{									\
-									\
-	if (pthread_key_create(&a_name##_tsd,				\
-	    a_name##_tsd_cleanup_wrapper) != 0)				\
-		return (true);						\
-	a_name##_booted = true;						\
-	return (false);							\
-}									\
-/* Get/set. */								\
-a_attr a_name##_tsd_wrapper_t *						\
-a_name##_tsd_get_wrapper(void)						\
-{									\
-	a_name##_tsd_wrapper_t *wrapper = (a_name##_tsd_wrapper_t *)	\
-	    pthread_getspecific(a_name##_tsd);				\
-									\
-	if (wrapper == NULL) {						\
-		tsd_init_block_t block;					\
-		wrapper = tsd_init_check_recursion(			\
-		    &a_name##_tsd_init_head, &block);			\
-		if (wrapper)						\
-		    return (wrapper);					\
-		wrapper = (a_name##_tsd_wrapper_t *)			\
-		    malloc_tsd_malloc(sizeof(a_name##_tsd_wrapper_t));	\
-		block.data = wrapper;					\
-		if (wrapper == NULL) {					\
-			malloc_write("<jemalloc>: Error allocating"	\
-			    " TSD for "#a_name"\n");			\
-			abort();					\
-		} else {						\
-			static a_type tsd_static_data = a_initializer;	\
-			wrapper->initialized = false;			\
-			wrapper->val = tsd_static_data;			\
-		}							\
-		if (pthread_setspecific(a_name##_tsd,			\
-		    (void *)wrapper)) {					\
-			malloc_write("<jemalloc>: Error setting"	\
-			    " TSD for "#a_name"\n");			\
-			abort();					\
-		}							\
-		tsd_init_finish(&a_name##_tsd_init_head, &block);	\
-	}								\
-	return (wrapper);						\
-}									\
-a_attr a_type *								\
-a_name##_tsd_get(void)							\
-{									\
-	a_name##_tsd_wrapper_t *wrapper;				\
-									\
-	assert(a_name##_booted);					\
-	wrapper = a_name##_tsd_get_wrapper();				\
-	return (&wrapper->val);						\
-}									\
-a_attr void								\
-a_name##_tsd_set(a_type *val)						\
-{									\
-	a_name##_tsd_wrapper_t *wrapper;				\
-									\
-	assert(a_name##_booted);					\
-	wrapper = a_name##_tsd_get_wrapper();				\
-	wrapper->val = *(val);						\
-	if (a_cleanup != malloc_tsd_no_cleanup)				\
-		wrapper->initialized = true;				\
+MALLOC_TSD
+#undef O
+
+/* tsd_foo_get(tsd) returns the value of the thread-local instance of foo. */
+#define O(n, t, nt)							\
+JEMALLOC_ALWAYS_INLINE t						\
+tsd_##n##_get(tsd_t *tsd) {						\
+	return *tsd_##n##p_get(tsd);					\
 }
-#endif
+MALLOC_TSD
+#undef O
 
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
+/* tsd_foo_set(tsd, val) updates the thread-local instance of foo to be val. */
+#define O(n, t, nt)							\
+JEMALLOC_ALWAYS_INLINE void						\
+tsd_##n##_set(tsd_t *tsd, t val) {					\
+	assert(tsd->state != tsd_state_reincarnated &&			\
+	    tsd->state != tsd_state_minimal_initialized);		\
+	*tsd_##n##p_get(tsd) = val;					\
+}
+MALLOC_TSD
+#undef O
 
-#if (!defined(JEMALLOC_MALLOC_THREAD_CLEANUP) && !defined(JEMALLOC_TLS) && \
-    !defined(_WIN32))
-struct tsd_init_block_s {
-	ql_elm(tsd_init_block_t)	link;
-	pthread_t			thread;
-	void				*data;
-};
-struct tsd_init_head_s {
-	ql_head(tsd_init_block_t)	blocks;
-	malloc_mutex_t			lock;
-};
-#endif
+JEMALLOC_ALWAYS_INLINE void
+tsd_assert_fast(tsd_t *tsd) {
+	assert(!malloc_slow && tsd_tcache_enabled_get(tsd) &&
+	    tsd_reentrancy_level_get(tsd) == 0);
+}
 
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-void	*malloc_tsd_malloc(size_t size);
-void	malloc_tsd_dalloc(void *wrapper);
-void	malloc_tsd_no_cleanup(void *);
-void	malloc_tsd_cleanup_register(bool (*f)(void));
-void	malloc_tsd_boot(void);
-#if (!defined(JEMALLOC_MALLOC_THREAD_CLEANUP) && !defined(JEMALLOC_TLS) && \
-    !defined(_WIN32))
-void	*tsd_init_check_recursion(tsd_init_head_t *head,
-    tsd_init_block_t *block);
-void	tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block);
-#endif
+JEMALLOC_ALWAYS_INLINE bool
+tsd_fast(tsd_t *tsd) {
+	bool fast = (tsd->state == tsd_state_nominal);
+	if (fast) {
+		tsd_assert_fast(tsd);
+	}
+
+	return fast;
+}
 
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_fetch_impl(bool init, bool minimal) {
+	tsd_t *tsd = tsd_get(init);
+
+	if (!init && tsd_get_allocates() && tsd == NULL) {
+		return NULL;
+	}
+	assert(tsd != NULL);
+
+	if (unlikely(tsd->state != tsd_state_nominal)) {
+		return tsd_fetch_slow(tsd, minimal);
+	}
+	assert(tsd_fast(tsd));
+	tsd_assert_fast(tsd);
+
+	return tsd;
+}
+
+/* Get a minimal TSD that requires no cleanup.  See comments in free(). */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_fetch_min(void) {
+	return tsd_fetch_impl(true, true);
+}
+
+/* For internal background threads use only. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_internal_fetch(void) {
+	tsd_t *tsd = tsd_fetch_min();
+	/* Use reincarnated state to prevent full initialization. */
+	tsd->state = tsd_state_reincarnated;
+
+	return tsd;
+}
+
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_fetch(void) {
+	return tsd_fetch_impl(true, false);
+}
+
+static inline bool
+tsd_nominal(tsd_t *tsd) {
+	return (tsd->state <= tsd_state_nominal_max);
+}
+
+JEMALLOC_ALWAYS_INLINE tsdn_t *
+tsdn_fetch(void) {
+	if (!tsd_booted_get()) {
+		return NULL;
+	}
+
+	return tsd_tsdn(tsd_fetch_impl(false, false));
+}
+
+JEMALLOC_ALWAYS_INLINE rtree_ctx_t *
+tsd_rtree_ctx(tsd_t *tsd) {
+	return tsd_rtree_ctxp_get(tsd);
+}
+
+JEMALLOC_ALWAYS_INLINE rtree_ctx_t *
+tsdn_rtree_ctx(tsdn_t *tsdn, rtree_ctx_t *fallback) {
+	/*
+	 * If tsd cannot be accessed, initialize the fallback rtree_ctx and
+	 * return a pointer to it.
+	 */
+	if (unlikely(tsdn_null(tsdn))) {
+		rtree_ctx_data_init(fallback);
+		return fallback;
+	}
+	return tsd_rtree_ctx(tsdn_tsd(tsdn));
+}
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#endif /* JEMALLOC_INTERNAL_TSD_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_generic.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_generic.h
new file mode 100644
index 0000000000..1e52ef767f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_generic.h
@@ -0,0 +1,157 @@
+#ifdef JEMALLOC_INTERNAL_TSD_GENERIC_H
+#error This file should be included only once, by tsd.h.
+#endif
+#define JEMALLOC_INTERNAL_TSD_GENERIC_H
+
+typedef struct tsd_init_block_s tsd_init_block_t;
+struct tsd_init_block_s {
+	ql_elm(tsd_init_block_t) link;
+	pthread_t thread;
+	void *data;
+};
+
+/* Defined in tsd.c, to allow the mutex headers to have tsd dependencies. */
+typedef struct tsd_init_head_s tsd_init_head_t;
+
+typedef struct {
+	bool initialized;
+	tsd_t val;
+} tsd_wrapper_t;
+
+void *tsd_init_check_recursion(tsd_init_head_t *head,
+    tsd_init_block_t *block);
+void tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block);
+
+extern pthread_key_t tsd_tsd;
+extern tsd_init_head_t tsd_init_head;
+extern tsd_wrapper_t tsd_boot_wrapper;
+extern bool tsd_booted;
+
+/* Initialization/cleanup. */
+JEMALLOC_ALWAYS_INLINE void
+tsd_cleanup_wrapper(void *arg) {
+	tsd_wrapper_t *wrapper = (tsd_wrapper_t *)arg;
+
+	if (wrapper->initialized) {
+		wrapper->initialized = false;
+		tsd_cleanup(&wrapper->val);
+		if (wrapper->initialized) {
+			/* Trigger another cleanup round. */
+			if (pthread_setspecific(tsd_tsd, (void *)wrapper) != 0)
+			{
+				malloc_write("<jemalloc>: Error setting TSD\n");
+				if (opt_abort) {
+					abort();
+				}
+			}
+			return;
+		}
+	}
+	malloc_tsd_dalloc(wrapper);
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_wrapper_set(tsd_wrapper_t *wrapper) {
+	if (pthread_setspecific(tsd_tsd, (void *)wrapper) != 0) {
+		malloc_write("<jemalloc>: Error setting TSD\n");
+		abort();
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE tsd_wrapper_t *
+tsd_wrapper_get(bool init) {
+	tsd_wrapper_t *wrapper = (tsd_wrapper_t *)pthread_getspecific(tsd_tsd);
+
+	if (init && unlikely(wrapper == NULL)) {
+		tsd_init_block_t block;
+		wrapper = (tsd_wrapper_t *)
+		    tsd_init_check_recursion(&tsd_init_head, &block);
+		if (wrapper) {
+			return wrapper;
+		}
+		wrapper = (tsd_wrapper_t *)
+		    malloc_tsd_malloc(sizeof(tsd_wrapper_t));
+		block.data = (void *)wrapper;
+		if (wrapper == NULL) {
+			malloc_write("<jemalloc>: Error allocating TSD\n");
+			abort();
+		} else {
+			wrapper->initialized = false;
+			tsd_t initializer = TSD_INITIALIZER;
+			wrapper->val = initializer;
+		}
+		tsd_wrapper_set(wrapper);
+		tsd_init_finish(&tsd_init_head, &block);
+	}
+	return wrapper;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot0(void) {
+	if (pthread_key_create(&tsd_tsd, tsd_cleanup_wrapper) != 0) {
+		return true;
+	}
+	tsd_wrapper_set(&tsd_boot_wrapper);
+	tsd_booted = true;
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_boot1(void) {
+	tsd_wrapper_t *wrapper;
+	wrapper = (tsd_wrapper_t *)malloc_tsd_malloc(sizeof(tsd_wrapper_t));
+	if (wrapper == NULL) {
+		malloc_write("<jemalloc>: Error allocating TSD\n");
+		abort();
+	}
+	tsd_boot_wrapper.initialized = false;
+	tsd_cleanup(&tsd_boot_wrapper.val);
+	wrapper->initialized = false;
+	tsd_t initializer = TSD_INITIALIZER;
+	wrapper->val = initializer;
+	tsd_wrapper_set(wrapper);
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot(void) {
+	if (tsd_boot0()) {
+		return true;
+	}
+	tsd_boot1();
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_booted_get(void) {
+	return tsd_booted;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_get_allocates(void) {
+	return true;
+}
+
+/* Get/set. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_get(bool init) {
+	tsd_wrapper_t *wrapper;
+
+	assert(tsd_booted);
+	wrapper = tsd_wrapper_get(init);
+	if (tsd_get_allocates() && !init && wrapper == NULL) {
+		return NULL;
+	}
+	return &wrapper->val;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_set(tsd_t *val) {
+	tsd_wrapper_t *wrapper;
+
+	assert(tsd_booted);
+	wrapper = tsd_wrapper_get(true);
+	if (likely(&wrapper->val != val)) {
+		wrapper->val = *(val);
+	}
+	wrapper->initialized = true;
+}
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h
new file mode 100644
index 0000000000..beb467a67e
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_malloc_thread_cleanup.h
@@ -0,0 +1,60 @@
+#ifdef JEMALLOC_INTERNAL_TSD_MALLOC_THREAD_CLEANUP_H
+#error This file should be included only once, by tsd.h.
+#endif
+#define JEMALLOC_INTERNAL_TSD_MALLOC_THREAD_CLEANUP_H
+
+extern __thread tsd_t tsd_tls;
+extern __thread bool tsd_initialized;
+extern bool tsd_booted;
+
+/* Initialization/cleanup. */
+JEMALLOC_ALWAYS_INLINE bool
+tsd_cleanup_wrapper(void) {
+	if (tsd_initialized) {
+		tsd_initialized = false;
+		tsd_cleanup(&tsd_tls);
+	}
+	return tsd_initialized;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot0(void) {
+	malloc_tsd_cleanup_register(&tsd_cleanup_wrapper);
+	tsd_booted = true;
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_boot1(void) {
+	/* Do nothing. */
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot(void) {
+	return tsd_boot0();
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_booted_get(void) {
+	return tsd_booted;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_get_allocates(void) {
+	return false;
+}
+
+/* Get/set. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_get(bool init) {
+	assert(tsd_booted);
+	return &tsd_tls;
+}
+JEMALLOC_ALWAYS_INLINE void
+tsd_set(tsd_t *val) {
+	assert(tsd_booted);
+	if (likely(&tsd_tls != val)) {
+		tsd_tls = (*val);
+	}
+	tsd_initialized = true;
+}
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_tls.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_tls.h
new file mode 100644
index 0000000000..757aaa0eef
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_tls.h
@@ -0,0 +1,59 @@
+#ifdef JEMALLOC_INTERNAL_TSD_TLS_H
+#error This file should be included only once, by tsd.h.
+#endif
+#define JEMALLOC_INTERNAL_TSD_TLS_H
+
+extern __thread tsd_t tsd_tls;
+extern pthread_key_t tsd_tsd;
+extern bool tsd_booted;
+
+/* Initialization/cleanup. */
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot0(void) {
+	if (pthread_key_create(&tsd_tsd, &tsd_cleanup) != 0) {
+		return true;
+	}
+	tsd_booted = true;
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_boot1(void) {
+	/* Do nothing. */
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot(void) {
+	return tsd_boot0();
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_booted_get(void) {
+	return tsd_booted;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_get_allocates(void) {
+	return false;
+}
+
+/* Get/set. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_get(bool init) {
+	assert(tsd_booted);
+	return &tsd_tls;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_set(tsd_t *val) {
+	assert(tsd_booted);
+	if (likely(&tsd_tls != val)) {
+		tsd_tls = (*val);
+	}
+	if (pthread_setspecific(tsd_tsd, (void *)(&tsd_tls)) != 0) {
+		malloc_write("<jemalloc>: Error setting tsd.\n");
+		if (opt_abort) {
+			abort();
+		}
+	}
+}
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_types.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_types.h
new file mode 100644
index 0000000000..6200af61f3
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_types.h
@@ -0,0 +1,10 @@
+#ifndef JEMALLOC_INTERNAL_TSD_TYPES_H
+#define JEMALLOC_INTERNAL_TSD_TYPES_H
+
+#define MALLOC_TSD_CLEANUPS_MAX	2
+
+typedef struct tsd_s tsd_t;
+typedef struct tsdn_s tsdn_t;
+typedef bool (*malloc_tsd_cleanup_t)(void);
+
+#endif /* JEMALLOC_INTERNAL_TSD_TYPES_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_win.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_win.h
new file mode 100644
index 0000000000..cf30d18e3c
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/tsd_win.h
@@ -0,0 +1,139 @@
+#ifdef JEMALLOC_INTERNAL_TSD_WIN_H
+#error This file should be included only once, by tsd.h.
+#endif
+#define JEMALLOC_INTERNAL_TSD_WIN_H
+
+typedef struct {
+	bool initialized;
+	tsd_t val;
+} tsd_wrapper_t;
+
+extern DWORD tsd_tsd;
+extern tsd_wrapper_t tsd_boot_wrapper;
+extern bool tsd_booted;
+
+/* Initialization/cleanup. */
+JEMALLOC_ALWAYS_INLINE bool
+tsd_cleanup_wrapper(void) {
+	DWORD error = GetLastError();
+	tsd_wrapper_t *wrapper = (tsd_wrapper_t *)TlsGetValue(tsd_tsd);
+	SetLastError(error);
+
+	if (wrapper == NULL) {
+		return false;
+	}
+
+	if (wrapper->initialized) {
+		wrapper->initialized = false;
+		tsd_cleanup(&wrapper->val);
+		if (wrapper->initialized) {
+			/* Trigger another cleanup round. */
+			return true;
+		}
+	}
+	malloc_tsd_dalloc(wrapper);
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_wrapper_set(tsd_wrapper_t *wrapper) {
+	if (!TlsSetValue(tsd_tsd, (void *)wrapper)) {
+		malloc_write("<jemalloc>: Error setting TSD\n");
+		abort();
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE tsd_wrapper_t *
+tsd_wrapper_get(bool init) {
+	DWORD error = GetLastError();
+	tsd_wrapper_t *wrapper = (tsd_wrapper_t *) TlsGetValue(tsd_tsd);
+	SetLastError(error);
+
+	if (init && unlikely(wrapper == NULL)) {
+		wrapper = (tsd_wrapper_t *)
+		    malloc_tsd_malloc(sizeof(tsd_wrapper_t));
+		if (wrapper == NULL) {
+			malloc_write("<jemalloc>: Error allocating TSD\n");
+			abort();
+		} else {
+			wrapper->initialized = false;
+			/* MSVC is finicky about aggregate initialization. */
+			tsd_t tsd_initializer = TSD_INITIALIZER;
+			wrapper->val = tsd_initializer;
+		}
+		tsd_wrapper_set(wrapper);
+	}
+	return wrapper;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot0(void) {
+	tsd_tsd = TlsAlloc();
+	if (tsd_tsd == TLS_OUT_OF_INDEXES) {
+		return true;
+	}
+	malloc_tsd_cleanup_register(&tsd_cleanup_wrapper);
+	tsd_wrapper_set(&tsd_boot_wrapper);
+	tsd_booted = true;
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_boot1(void) {
+	tsd_wrapper_t *wrapper;
+	wrapper = (tsd_wrapper_t *)
+	    malloc_tsd_malloc(sizeof(tsd_wrapper_t));
+	if (wrapper == NULL) {
+		malloc_write("<jemalloc>: Error allocating TSD\n");
+		abort();
+	}
+	tsd_boot_wrapper.initialized = false;
+	tsd_cleanup(&tsd_boot_wrapper.val);
+	wrapper->initialized = false;
+	tsd_t initializer = TSD_INITIALIZER;
+	wrapper->val = initializer;
+	tsd_wrapper_set(wrapper);
+}
+JEMALLOC_ALWAYS_INLINE bool
+tsd_boot(void) {
+	if (tsd_boot0()) {
+		return true;
+	}
+	tsd_boot1();
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_booted_get(void) {
+	return tsd_booted;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+tsd_get_allocates(void) {
+	return true;
+}
+
+/* Get/set. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_get(bool init) {
+	tsd_wrapper_t *wrapper;
+
+	assert(tsd_booted);
+	wrapper = tsd_wrapper_get(init);
+	if (tsd_get_allocates() && !init && wrapper == NULL) {
+		return NULL;
+	}
+	return &wrapper->val;
+}
+
+JEMALLOC_ALWAYS_INLINE void
+tsd_set(tsd_t *val) {
+	tsd_wrapper_t *wrapper;
+
+	assert(tsd_booted);
+	wrapper = tsd_wrapper_get(true);
+	if (likely(&wrapper->val != val)) {
+		wrapper->val = *(val);
+	}
+	wrapper->initialized = true;
+}
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/util.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/util.h
index 6b938f7468..304cb545af 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/util.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/util.h
@@ -1,143 +1,50 @@
-/******************************************************************************/
-#ifdef JEMALLOC_H_TYPES
+#ifndef JEMALLOC_INTERNAL_UTIL_H
+#define JEMALLOC_INTERNAL_UTIL_H
 
-/* Size of stack-allocated buffer passed to buferror(). */
-#define	BUFERROR_BUF		64
+#define UTIL_INLINE static inline
 
-/*
- * Size of stack-allocated buffer used by malloc_{,v,vc}printf().  This must be
- * large enough for all possible uses within jemalloc.
- */
-#define	MALLOC_PRINTF_BUFSIZE	4096
+/* Junk fill patterns. */
+#ifndef JEMALLOC_ALLOC_JUNK
+#  define JEMALLOC_ALLOC_JUNK	((uint8_t)0xa5)
+#endif
+#ifndef JEMALLOC_FREE_JUNK
+#  define JEMALLOC_FREE_JUNK	((uint8_t)0x5a)
+#endif
 
 /*
  * Wrap a cpp argument that contains commas such that it isn't broken up into
  * multiple arguments.
  */
-#define	JEMALLOC_ARG_CONCAT(...) __VA_ARGS__
+#define JEMALLOC_ARG_CONCAT(...) __VA_ARGS__
+
+/* cpp macro definition stringification. */
+#define STRINGIFY_HELPER(x) #x
+#define STRINGIFY(x) STRINGIFY_HELPER(x)
 
 /*
  * Silence compiler warnings due to uninitialized values.  This is used
  * wherever the compiler fails to recognize that the variable is never used
  * uninitialized.
  */
-#ifdef JEMALLOC_CC_SILENCE
-#  define JEMALLOC_CC_SILENCE_INIT(v) = v
-#else
-#  define JEMALLOC_CC_SILENCE_INIT(v)
-#endif
-
-/*
- * Define a custom assert() in order to reduce the chances of deadlock during
- * assertion failure.
- */
-#ifndef assert
-#define	assert(e) do {							\
-	if (config_debug && !(e)) {					\
-		malloc_printf(						\
-		    "<jemalloc>: %s:%d: Failed assertion: \"%s\"\n",	\
-		    __FILE__, __LINE__, #e);				\
-		abort();						\
-	}								\
-} while (0)
-#endif
-
-#ifndef not_reached
-#define	not_reached() do {						\
-	if (config_debug) {						\
-		malloc_printf(						\
-		    "<jemalloc>: %s:%d: Unreachable code reached\n",	\
-		    __FILE__, __LINE__);				\
-		abort();						\
-	}								\
-} while (0)
-#endif
-
-#ifndef not_implemented
-#define	not_implemented() do {						\
-	if (config_debug) {						\
-		malloc_printf("<jemalloc>: %s:%d: Not implemented\n",	\
-		    __FILE__, __LINE__);				\
-		abort();						\
-	}								\
-} while (0)
-#endif
+#define JEMALLOC_CC_SILENCE_INIT(v) = v
 
-#ifndef assert_not_implemented
-#define	assert_not_implemented(e) do {					\
-	if (config_debug && !(e))					\
-		not_implemented();					\
-} while (0)
-#endif
-
-/* Use to assert a particular configuration, e.g., cassert(config_debug). */
-#define	cassert(c) do {							\
-	if ((c) == false)						\
-		not_reached();						\
-} while (0)
-
-#endif /* JEMALLOC_H_TYPES */
-/******************************************************************************/
-#ifdef JEMALLOC_H_STRUCTS
-
-#endif /* JEMALLOC_H_STRUCTS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_EXTERNS
-
-int	buferror(int err, char *buf, size_t buflen);
-uintmax_t	malloc_strtoumax(const char *restrict nptr,
-    char **restrict endptr, int base);
-void	malloc_write(const char *s);
-
-/*
- * malloc_vsnprintf() supports a subset of snprintf(3) that avoids floating
- * point math.
- */
-int	malloc_vsnprintf(char *str, size_t size, const char *format,
-    va_list ap);
-int	malloc_snprintf(char *str, size_t size, const char *format, ...)
-    JEMALLOC_ATTR(format(printf, 3, 4));
-void	malloc_vcprintf(void (*write_cb)(void *, const char *), void *cbopaque,
-    const char *format, va_list ap);
-void malloc_cprintf(void (*write)(void *, const char *), void *cbopaque,
-    const char *format, ...) JEMALLOC_ATTR(format(printf, 3, 4));
-void	malloc_printf(const char *format, ...)
-    JEMALLOC_ATTR(format(printf, 1, 2));
-
-#endif /* JEMALLOC_H_EXTERNS */
-/******************************************************************************/
-#ifdef JEMALLOC_H_INLINES
-
-#ifndef JEMALLOC_ENABLE_INLINE
-size_t	pow2_ceil(size_t x);
-void	set_errno(int errnum);
-int	get_errno(void);
+#ifdef __GNUC__
+#  define likely(x)   __builtin_expect(!!(x), 1)
+#  define unlikely(x) __builtin_expect(!!(x), 0)
+#else
+#  define likely(x)   !!(x)
+#  define unlikely(x) !!(x)
 #endif
 
-#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_UTIL_C_))
-/* Compute the smallest power of 2 that is >= x. */
-JEMALLOC_INLINE size_t
-pow2_ceil(size_t x)
-{
-
-	x--;
-	x |= x >> 1;
-	x |= x >> 2;
-	x |= x >> 4;
-	x |= x >> 8;
-	x |= x >> 16;
-#if (LG_SIZEOF_PTR == 3)
-	x |= x >> 32;
+#if !defined(JEMALLOC_INTERNAL_UNREACHABLE)
+#  error JEMALLOC_INTERNAL_UNREACHABLE should have been defined by configure
 #endif
-	x++;
-	return (x);
-}
 
-/* Sets error code */
-JEMALLOC_INLINE void
-set_errno(int errnum)
-{
+#define unreachable() JEMALLOC_INTERNAL_UNREACHABLE()
 
+/* Set error code. */
+UTIL_INLINE void
+set_errno(int errnum) {
 #ifdef _WIN32
 	SetLastError(errnum);
 #else
@@ -145,18 +52,16 @@ set_errno(int errnum)
 #endif
 }
 
-/* Get last error code */
-JEMALLOC_INLINE int
-get_errno(void)
-{
-
+/* Get last error code. */
+UTIL_INLINE int
+get_errno(void) {
 #ifdef _WIN32
-	return (GetLastError());
+	return GetLastError();
 #else
-	return (errno);
+	return errno;
 #endif
 }
-#endif
 
-#endif /* JEMALLOC_H_INLINES */
-/******************************************************************************/
+#undef UTIL_INLINE
+
+#endif /* JEMALLOC_INTERNAL_UTIL_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/internal/witness.h b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/witness.h
new file mode 100644
index 0000000000..33be666107
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/internal/witness.h
@@ -0,0 +1,346 @@
+#ifndef JEMALLOC_INTERNAL_WITNESS_H
+#define JEMALLOC_INTERNAL_WITNESS_H
+
+#include "jemalloc/internal/ql.h"
+
+/******************************************************************************/
+/* LOCK RANKS */
+/******************************************************************************/
+
+/*
+ * Witnesses with rank WITNESS_RANK_OMIT are completely ignored by the witness
+ * machinery.
+ */
+
+#define WITNESS_RANK_OMIT		0U
+
+#define WITNESS_RANK_MIN		1U
+
+#define WITNESS_RANK_INIT		1U
+#define WITNESS_RANK_CTL		1U
+#define WITNESS_RANK_TCACHES		2U
+#define WITNESS_RANK_ARENAS		3U
+
+#define WITNESS_RANK_BACKGROUND_THREAD_GLOBAL	4U
+
+#define WITNESS_RANK_PROF_DUMP		5U
+#define WITNESS_RANK_PROF_BT2GCTX	6U
+#define WITNESS_RANK_PROF_TDATAS	7U
+#define WITNESS_RANK_PROF_TDATA		8U
+#define WITNESS_RANK_PROF_GCTX		9U
+
+#define WITNESS_RANK_BACKGROUND_THREAD	10U
+
+/*
+ * Used as an argument to witness_assert_depth_to_rank() in order to validate
+ * depth excluding non-core locks with lower ranks.  Since the rank argument to
+ * witness_assert_depth_to_rank() is inclusive rather than exclusive, this
+ * definition can have the same value as the minimally ranked core lock.
+ */
+#define WITNESS_RANK_CORE		11U
+
+#define WITNESS_RANK_DECAY		11U
+#define WITNESS_RANK_TCACHE_QL		12U
+#define WITNESS_RANK_EXTENT_GROW	13U
+#define WITNESS_RANK_EXTENTS		14U
+#define WITNESS_RANK_EXTENT_AVAIL	15U
+
+#define WITNESS_RANK_EXTENT_POOL	16U
+#define WITNESS_RANK_RTREE		17U
+#define WITNESS_RANK_BASE		18U
+#define WITNESS_RANK_ARENA_LARGE	19U
+
+#define WITNESS_RANK_LEAF		0xffffffffU
+#define WITNESS_RANK_ARENA_BIN		WITNESS_RANK_LEAF
+#define WITNESS_RANK_ARENA_STATS	WITNESS_RANK_LEAF
+#define WITNESS_RANK_DSS		WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_ACTIVE	WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_ACCUM		WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_DUMP_SEQ	WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_GDUMP		WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_NEXT_THR_UID	WITNESS_RANK_LEAF
+#define WITNESS_RANK_PROF_THREAD_ACTIVE_INIT	WITNESS_RANK_LEAF
+
+/******************************************************************************/
+/* PER-WITNESS DATA */
+/******************************************************************************/
+#if defined(JEMALLOC_DEBUG)
+#  define WITNESS_INITIALIZER(name, rank) {name, rank, NULL, NULL, {NULL, NULL}}
+#else
+#  define WITNESS_INITIALIZER(name, rank)
+#endif
+
+typedef struct witness_s witness_t;
+typedef unsigned witness_rank_t;
+typedef ql_head(witness_t) witness_list_t;
+typedef int witness_comp_t (const witness_t *, void *, const witness_t *,
+    void *);
+
+struct witness_s {
+	/* Name, used for printing lock order reversal messages. */
+	const char		*name;
+
+	/*
+	 * Witness rank, where 0 is lowest and UINT_MAX is highest.  Witnesses
+	 * must be acquired in order of increasing rank.
+	 */
+	witness_rank_t		rank;
+
+	/*
+	 * If two witnesses are of equal rank and they have the samp comp
+	 * function pointer, it is called as a last attempt to differentiate
+	 * between witnesses of equal rank.
+	 */
+	witness_comp_t		*comp;
+
+	/* Opaque data, passed to comp(). */
+	void			*opaque;
+
+	/* Linkage for thread's currently owned locks. */
+	ql_elm(witness_t)	link;
+};
+
+/******************************************************************************/
+/* PER-THREAD DATA */
+/******************************************************************************/
+typedef struct witness_tsd_s witness_tsd_t;
+struct witness_tsd_s {
+	witness_list_t witnesses;
+	bool forking;
+};
+
+#define WITNESS_TSD_INITIALIZER { ql_head_initializer(witnesses), false }
+#define WITNESS_TSDN_NULL ((witness_tsdn_t *)0)
+
+/******************************************************************************/
+/* (PER-THREAD) NULLABILITY HELPERS */
+/******************************************************************************/
+typedef struct witness_tsdn_s witness_tsdn_t;
+struct witness_tsdn_s {
+	witness_tsd_t witness_tsd;
+};
+
+JEMALLOC_ALWAYS_INLINE witness_tsdn_t *
+witness_tsd_tsdn(witness_tsd_t *witness_tsd) {
+	return (witness_tsdn_t *)witness_tsd;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+witness_tsdn_null(witness_tsdn_t *witness_tsdn) {
+	return witness_tsdn == NULL;
+}
+
+JEMALLOC_ALWAYS_INLINE witness_tsd_t *
+witness_tsdn_tsd(witness_tsdn_t *witness_tsdn) {
+	assert(!witness_tsdn_null(witness_tsdn));
+	return &witness_tsdn->witness_tsd;
+}
+
+/******************************************************************************/
+/* API */
+/******************************************************************************/
+void witness_init(witness_t *witness, const char *name, witness_rank_t rank,
+    witness_comp_t *comp, void *opaque);
+
+typedef void (witness_lock_error_t)(const witness_list_t *, const witness_t *);
+extern witness_lock_error_t *JET_MUTABLE witness_lock_error;
+
+typedef void (witness_owner_error_t)(const witness_t *);
+extern witness_owner_error_t *JET_MUTABLE witness_owner_error;
+
+typedef void (witness_not_owner_error_t)(const witness_t *);
+extern witness_not_owner_error_t *JET_MUTABLE witness_not_owner_error;
+
+typedef void (witness_depth_error_t)(const witness_list_t *,
+    witness_rank_t rank_inclusive, unsigned depth);
+extern witness_depth_error_t *JET_MUTABLE witness_depth_error;
+
+void witnesses_cleanup(witness_tsd_t *witness_tsd);
+void witness_prefork(witness_tsd_t *witness_tsd);
+void witness_postfork_parent(witness_tsd_t *witness_tsd);
+void witness_postfork_child(witness_tsd_t *witness_tsd);
+
+/* Helper, not intended for direct use. */
+static inline bool
+witness_owner(witness_tsd_t *witness_tsd, const witness_t *witness) {
+	witness_list_t *witnesses;
+	witness_t *w;
+
+	cassert(config_debug);
+
+	witnesses = &witness_tsd->witnesses;
+	ql_foreach(w, witnesses, link) {
+		if (w == witness) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static inline void
+witness_assert_owner(witness_tsdn_t *witness_tsdn, const witness_t *witness) {
+	witness_tsd_t *witness_tsd;
+
+	if (!config_debug) {
+		return;
+	}
+
+	if (witness_tsdn_null(witness_tsdn)) {
+		return;
+	}
+	witness_tsd = witness_tsdn_tsd(witness_tsdn);
+	if (witness->rank == WITNESS_RANK_OMIT) {
+		return;
+	}
+
+	if (witness_owner(witness_tsd, witness)) {
+		return;
+	}
+	witness_owner_error(witness);
+}
+
+static inline void
+witness_assert_not_owner(witness_tsdn_t *witness_tsdn,
+    const witness_t *witness) {
+	witness_tsd_t *witness_tsd;
+	witness_list_t *witnesses;
+	witness_t *w;
+
+	if (!config_debug) {
+		return;
+	}
+
+	if (witness_tsdn_null(witness_tsdn)) {
+		return;
+	}
+	witness_tsd = witness_tsdn_tsd(witness_tsdn);
+	if (witness->rank == WITNESS_RANK_OMIT) {
+		return;
+	}
+
+	witnesses = &witness_tsd->witnesses;
+	ql_foreach(w, witnesses, link) {
+		if (w == witness) {
+			witness_not_owner_error(witness);
+		}
+	}
+}
+
+static inline void
+witness_assert_depth_to_rank(witness_tsdn_t *witness_tsdn,
+    witness_rank_t rank_inclusive, unsigned depth) {
+	witness_tsd_t *witness_tsd;
+	unsigned d;
+	witness_list_t *witnesses;
+	witness_t *w;
+
+	if (!config_debug) {
+		return;
+	}
+
+	if (witness_tsdn_null(witness_tsdn)) {
+		return;
+	}
+	witness_tsd = witness_tsdn_tsd(witness_tsdn);
+
+	d = 0;
+	witnesses = &witness_tsd->witnesses;
+	w = ql_last(witnesses, link);
+	if (w != NULL) {
+		ql_reverse_foreach(w, witnesses, link) {
+			if (w->rank < rank_inclusive) {
+				break;
+			}
+			d++;
+		}
+	}
+	if (d != depth) {
+		witness_depth_error(witnesses, rank_inclusive, depth);
+	}
+}
+
+static inline void
+witness_assert_depth(witness_tsdn_t *witness_tsdn, unsigned depth) {
+	witness_assert_depth_to_rank(witness_tsdn, WITNESS_RANK_MIN, depth);
+}
+
+static inline void
+witness_assert_lockless(witness_tsdn_t *witness_tsdn) {
+	witness_assert_depth(witness_tsdn, 0);
+}
+
+static inline void
+witness_lock(witness_tsdn_t *witness_tsdn, witness_t *witness) {
+	witness_tsd_t *witness_tsd;
+	witness_list_t *witnesses;
+	witness_t *w;
+
+	if (!config_debug) {
+		return;
+	}
+
+	if (witness_tsdn_null(witness_tsdn)) {
+		return;
+	}
+	witness_tsd = witness_tsdn_tsd(witness_tsdn);
+	if (witness->rank == WITNESS_RANK_OMIT) {
+		return;
+	}
+
+	witness_assert_not_owner(witness_tsdn, witness);
+
+	witnesses = &witness_tsd->witnesses;
+	w = ql_last(witnesses, link);
+	if (w == NULL) {
+		/* No other locks; do nothing. */
+	} else if (witness_tsd->forking && w->rank <= witness->rank) {
+		/* Forking, and relaxed ranking satisfied. */
+	} else if (w->rank > witness->rank) {
+		/* Not forking, rank order reversal. */
+		witness_lock_error(witnesses, witness);
+	} else if (w->rank == witness->rank && (w->comp == NULL || w->comp !=
+	    witness->comp || w->comp(w, w->opaque, witness, witness->opaque) >
+	    0)) {
+		/*
+		 * Missing/incompatible comparison function, or comparison
+		 * function indicates rank order reversal.
+		 */
+		witness_lock_error(witnesses, witness);
+	}
+
+	ql_elm_new(witness, link);
+	ql_tail_insert(witnesses, witness, link);
+}
+
+static inline void
+witness_unlock(witness_tsdn_t *witness_tsdn, witness_t *witness) {
+	witness_tsd_t *witness_tsd;
+	witness_list_t *witnesses;
+
+	if (!config_debug) {
+		return;
+	}
+
+	if (witness_tsdn_null(witness_tsdn)) {
+		return;
+	}
+	witness_tsd = witness_tsdn_tsd(witness_tsdn);
+	if (witness->rank == WITNESS_RANK_OMIT) {
+		return;
+	}
+
+	/*
+	 * Check whether owner before removal, rather than relying on
+	 * witness_assert_owner() to abort, so that unit tests can test this
+	 * function's failure mode without causing undefined behavior.
+	 */
+	if (witness_owner(witness_tsd, witness)) {
+		witnesses = &witness_tsd->witnesses;
+		ql_remove(witnesses, witness, link);
+	} else {
+		witness_assert_owner(witness_tsdn, witness);
+	}
+}
+
+#endif /* JEMALLOC_INTERNAL_WITNESS_H */
diff --git a/modules/worldengine/deps/jemalloc/include/jemalloc/jemalloc.h b/modules/worldengine/deps/jemalloc/include/jemalloc/jemalloc.h
index b8ea851e52..6ffe5c71b3 100644
--- a/modules/worldengine/deps/jemalloc/include/jemalloc/jemalloc.h
+++ b/modules/worldengine/deps/jemalloc/include/jemalloc/jemalloc.h
@@ -1,45 +1,203 @@
 #ifndef JEMALLOC_H_
-#define	JEMALLOC_H_
+#define JEMALLOC_H_
 #ifdef __cplusplus
 extern "C" {
 #endif
 
+/* Defined if __attribute__((...)) syntax is supported. */
+#define JEMALLOC_HAVE_ATTR
+
+/* Defined if alloc_size attribute is supported. */
+#define JEMALLOC_HAVE_ATTR_ALLOC_SIZE
+
+/* Defined if format(gnu_printf, ...) attribute is supported. */
+#define JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF
+
+/* Defined if format(printf, ...) attribute is supported. */
+#define JEMALLOC_HAVE_ATTR_FORMAT_PRINTF
+
+/*
+ * Define overrides for non-standard allocator-related functions if they are
+ * present on the system.
+ */
+#define JEMALLOC_OVERRIDE_MEMALIGN
+#define JEMALLOC_OVERRIDE_VALLOC
+
+/*
+ * At least Linux omits the "const" in:
+ *
+ *   size_t malloc_usable_size(const void *ptr);
+ *
+ * Match the operating system's prototype.
+ */
+#define JEMALLOC_USABLE_SIZE_CONST
+
+/*
+ * If defined, specify throw() for the public function prototypes when compiling
+ * with C++.  The only justification for this is to match the prototypes that
+ * glibc defines.
+ */
+#define JEMALLOC_USE_CXX_THROW
+
+#ifdef _MSC_VER
+#  ifdef _WIN64
+#    define LG_SIZEOF_PTR_WIN 3
+#  else
+#    define LG_SIZEOF_PTR_WIN 2
+#  endif
+#endif
+
+/*
+ * Name mangling for public symbols is controlled by --with-mangling and
+ * --with-jemalloc-prefix.  With default settings the je_ prefix is stripped by
+ * these macro definitions.
+ */
+#ifndef JEMALLOC_NO_RENAME
+#  define je_aligned_alloc aligned_alloc
+#  define je_calloc calloc
+#  define je_dallocx dallocx
+#  define je_free free
+#  define je_mallctl mallctl
+#  define je_mallctlbymib mallctlbymib
+#  define je_mallctlnametomib mallctlnametomib
+#  define je_malloc malloc
+#  define je_malloc_conf malloc_conf
+#  define je_malloc_message malloc_message
+#  define je_malloc_stats_print malloc_stats_print
+#  define je_malloc_usable_size malloc_usable_size
+#  define je_mallocx mallocx
+#  define je_nallocx nallocx
+#  define je_posix_memalign posix_memalign
+#  define je_rallocx rallocx
+#  define je_realloc realloc
+#  define je_sallocx sallocx
+#  define je_sdallocx sdallocx
+#  define je_xallocx xallocx
+#  define je_memalign memalign
+#  define je_valloc valloc
+#endif
+
+#include <stdlib.h>
+#include <stdbool.h>
+#include <stdint.h>
 #include <limits.h>
 #include <strings.h>
 
-#define	JEMALLOC_VERSION "3.6.0-0-g46c0af68bd248b04df75e4f92d5fb804c3d75340"
-#define	JEMALLOC_VERSION_MAJOR 3
-#define	JEMALLOC_VERSION_MINOR 6
-#define	JEMALLOC_VERSION_BUGFIX 0
-#define	JEMALLOC_VERSION_NREV 0
-#define	JEMALLOC_VERSION_GID "46c0af68bd248b04df75e4f92d5fb804c3d75340"
+#define JEMALLOC_VERSION "5.0.1-0-g896ed3a8b3f41998d4fb4d625d30ac63ef2d51fb"
+#define JEMALLOC_VERSION_MAJOR 5
+#define JEMALLOC_VERSION_MINOR 0
+#define JEMALLOC_VERSION_BUGFIX 1
+#define JEMALLOC_VERSION_NREV 0
+#define JEMALLOC_VERSION_GID "896ed3a8b3f41998d4fb4d625d30ac63ef2d51fb"
+
+#define MALLOCX_LG_ALIGN(la)	((int)(la))
+#if LG_SIZEOF_PTR == 2
+#  define MALLOCX_ALIGN(a)	((int)(ffs((int)(a))-1))
+#else
+#  define MALLOCX_ALIGN(a)						\
+     ((int)(((size_t)(a) < (size_t)INT_MAX) ? ffs((int)(a))-1 :	\
+     ffs((int)(((size_t)(a))>>32))+31))
+#endif
+#define MALLOCX_ZERO	((int)0x40)
+/*
+ * Bias tcache index bits so that 0 encodes "automatic tcache management", and 1
+ * encodes MALLOCX_TCACHE_NONE.
+ */
+#define MALLOCX_TCACHE(tc)	((int)(((tc)+2) << 8))
+#define MALLOCX_TCACHE_NONE	MALLOCX_TCACHE(-1)
+/*
+ * Bias arena index bits so that 0 encodes "use an automatically chosen arena".
+ */
+#define MALLOCX_ARENA(a)	((((int)(a))+1) << 20)
+
+/*
+ * Use as arena index in "arena.<i>.{purge,decay,dss}" and
+ * "stats.arenas.<i>.*" mallctl interfaces to select all arenas.  This
+ * definition is intentionally specified in raw decimal format to support
+ * cpp-based string concatenation, e.g.
+ *
+ *   #define STRINGIFY_HELPER(x) #x
+ *   #define STRINGIFY(x) STRINGIFY_HELPER(x)
+ *
+ *   mallctl("arena." STRINGIFY(MALLCTL_ARENAS_ALL) ".purge", NULL, NULL, NULL,
+ *       0);
+ */
+#define MALLCTL_ARENAS_ALL	4096
+/*
+ * Use as arena index in "stats.arenas.<i>.*" mallctl interfaces to select
+ * destroyed arenas.
+ */
+#define MALLCTL_ARENAS_DESTROYED	4097
 
-#  define MALLOCX_LG_ALIGN(la)	(la)
-#  if LG_SIZEOF_PTR == 2
-#    define MALLOCX_ALIGN(a)	(ffs(a)-1)
+#if defined(__cplusplus) && defined(JEMALLOC_USE_CXX_THROW)
+#  define JEMALLOC_CXX_THROW throw()
+#else
+#  define JEMALLOC_CXX_THROW
+#endif
+
+#if defined(_MSC_VER)
+#  define JEMALLOC_ATTR(s)
+#  define JEMALLOC_ALIGNED(s) __declspec(align(s))
+#  define JEMALLOC_ALLOC_SIZE(s)
+#  define JEMALLOC_ALLOC_SIZE2(s1, s2)
+#  ifndef JEMALLOC_EXPORT
+#    ifdef DLLEXPORT
+#      define JEMALLOC_EXPORT __declspec(dllexport)
+#    else
+#      define JEMALLOC_EXPORT __declspec(dllimport)
+#    endif
+#  endif
+#  define JEMALLOC_FORMAT_PRINTF(s, i)
+#  define JEMALLOC_NOINLINE __declspec(noinline)
+#  ifdef __cplusplus
+#    define JEMALLOC_NOTHROW __declspec(nothrow)
+#  else
+#    define JEMALLOC_NOTHROW
+#  endif
+#  define JEMALLOC_SECTION(s) __declspec(allocate(s))
+#  define JEMALLOC_RESTRICT_RETURN __declspec(restrict)
+#  if _MSC_VER >= 1900 && !defined(__EDG__)
+#    define JEMALLOC_ALLOCATOR __declspec(allocator)
+#  else
+#    define JEMALLOC_ALLOCATOR
+#  endif
+#elif defined(JEMALLOC_HAVE_ATTR)
+#  define JEMALLOC_ATTR(s) __attribute__((s))
+#  define JEMALLOC_ALIGNED(s) JEMALLOC_ATTR(aligned(s))
+#  ifdef JEMALLOC_HAVE_ATTR_ALLOC_SIZE
+#    define JEMALLOC_ALLOC_SIZE(s) JEMALLOC_ATTR(alloc_size(s))
+#    define JEMALLOC_ALLOC_SIZE2(s1, s2) JEMALLOC_ATTR(alloc_size(s1, s2))
 #  else
-#    define MALLOCX_ALIGN(a)						\
-	 ((a < (size_t)INT_MAX) ? ffs(a)-1 : ffs(a>>32)+31)
+#    define JEMALLOC_ALLOC_SIZE(s)
+#    define JEMALLOC_ALLOC_SIZE2(s1, s2)
+#  endif
+#  ifndef JEMALLOC_EXPORT
+#    define JEMALLOC_EXPORT JEMALLOC_ATTR(visibility("default"))
 #  endif
-#  define MALLOCX_ZERO	((int)0x40)
-/* Bias arena index bits so that 0 encodes "MALLOCX_ARENA() unspecified". */
-#  define MALLOCX_ARENA(a)	((int)(((a)+1) << 8))
-
-#ifdef JEMALLOC_EXPERIMENTAL
-#  define ALLOCM_LG_ALIGN(la)	(la)
-#  if LG_SIZEOF_PTR == 2
-#    define ALLOCM_ALIGN(a)	(ffs(a)-1)
+#  ifdef JEMALLOC_HAVE_ATTR_FORMAT_GNU_PRINTF
+#    define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(gnu_printf, s, i))
+#  elif defined(JEMALLOC_HAVE_ATTR_FORMAT_PRINTF)
+#    define JEMALLOC_FORMAT_PRINTF(s, i) JEMALLOC_ATTR(format(printf, s, i))
 #  else
-#    define ALLOCM_ALIGN(a)						\
-	 ((a < (size_t)INT_MAX) ? ffs(a)-1 : ffs(a>>32)+31)
+#    define JEMALLOC_FORMAT_PRINTF(s, i)
 #  endif
-#  define ALLOCM_ZERO	((int)0x40)
-#  define ALLOCM_NO_MOVE	((int)0x80)
-/* Bias arena index bits so that 0 encodes "ALLOCM_ARENA() unspecified". */
-#  define ALLOCM_ARENA(a)	((int)(((a)+1) << 8))
-#  define ALLOCM_SUCCESS	0
-#  define ALLOCM_ERR_OOM	1
-#  define ALLOCM_ERR_NOT_MOVED	2
+#  define JEMALLOC_NOINLINE JEMALLOC_ATTR(noinline)
+#  define JEMALLOC_NOTHROW JEMALLOC_ATTR(nothrow)
+#  define JEMALLOC_SECTION(s) JEMALLOC_ATTR(section(s))
+#  define JEMALLOC_RESTRICT_RETURN
+#  define JEMALLOC_ALLOCATOR
+#else
+#  define JEMALLOC_ATTR(s)
+#  define JEMALLOC_ALIGNED(s)
+#  define JEMALLOC_ALLOC_SIZE(s)
+#  define JEMALLOC_ALLOC_SIZE2(s1, s2)
+#  define JEMALLOC_EXPORT
+#  define JEMALLOC_FORMAT_PRINTF(s, i)
+#  define JEMALLOC_NOINLINE
+#  define JEMALLOC_NOTHROW
+#  define JEMALLOC_SECTION(s)
+#  define JEMALLOC_RESTRICT_RETURN
+#  define JEMALLOC_ALLOCATOR
 #endif
 
 /*
@@ -51,55 +209,141 @@ extern JEMALLOC_EXPORT const char	*je_malloc_conf;
 extern JEMALLOC_EXPORT void		(*je_malloc_message)(void *cbopaque,
     const char *s);
 
-JEMALLOC_EXPORT void	*je_malloc(size_t size) JEMALLOC_ATTR(malloc);
-JEMALLOC_EXPORT void	*je_calloc(size_t num, size_t size)
-    JEMALLOC_ATTR(malloc);
-JEMALLOC_EXPORT int	je_posix_memalign(void **memptr, size_t alignment,
-    size_t size) JEMALLOC_ATTR(nonnull(1));
-JEMALLOC_EXPORT void	*je_aligned_alloc(size_t alignment, size_t size)
-    JEMALLOC_ATTR(malloc);
-JEMALLOC_EXPORT void	*je_realloc(void *ptr, size_t size);
-JEMALLOC_EXPORT void	je_free(void *ptr);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_malloc(size_t size)
+    JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_calloc(size_t num, size_t size)
+    JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2);
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW	je_posix_memalign(void **memptr,
+    size_t alignment, size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(nonnull(1));
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_aligned_alloc(size_t alignment,
+    size_t size) JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc)
+    JEMALLOC_ALLOC_SIZE(2);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_realloc(void *ptr, size_t size)
+    JEMALLOC_CXX_THROW JEMALLOC_ALLOC_SIZE(2);
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW	je_free(void *ptr)
+    JEMALLOC_CXX_THROW;
 
-JEMALLOC_EXPORT void	*je_mallocx(size_t size, int flags);
-JEMALLOC_EXPORT void	*je_rallocx(void *ptr, size_t size, int flags);
-JEMALLOC_EXPORT size_t	je_xallocx(void *ptr, size_t size, size_t extra,
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_mallocx(size_t size, int flags)
+    JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_rallocx(void *ptr, size_t size,
+    int flags) JEMALLOC_ALLOC_SIZE(2);
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW	je_xallocx(void *ptr, size_t size,
+    size_t extra, int flags);
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW	je_sallocx(const void *ptr,
+    int flags) JEMALLOC_ATTR(pure);
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW	je_dallocx(void *ptr, int flags);
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW	je_sdallocx(void *ptr, size_t size,
     int flags);
-JEMALLOC_EXPORT size_t	je_sallocx(const void *ptr, int flags);
-JEMALLOC_EXPORT void	je_dallocx(void *ptr, int flags);
-JEMALLOC_EXPORT size_t	je_nallocx(size_t size, int flags);
-
-JEMALLOC_EXPORT int	je_mallctl(const char *name, void *oldp,
-    size_t *oldlenp, void *newp, size_t newlen);
-JEMALLOC_EXPORT int	je_mallctlnametomib(const char *name, size_t *mibp,
-    size_t *miblenp);
-JEMALLOC_EXPORT int	je_mallctlbymib(const size_t *mib, size_t miblen,
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW	je_nallocx(size_t size, int flags)
+    JEMALLOC_ATTR(pure);
+
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW	je_mallctl(const char *name,
     void *oldp, size_t *oldlenp, void *newp, size_t newlen);
-JEMALLOC_EXPORT void	je_malloc_stats_print(void (*write_cb)(void *,
-    const char *), void *je_cbopaque, const char *opts);
-JEMALLOC_EXPORT size_t	je_malloc_usable_size(
-    JEMALLOC_USABLE_SIZE_CONST void *ptr);
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW	je_mallctlnametomib(const char *name,
+    size_t *mibp, size_t *miblenp);
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW	je_mallctlbymib(const size_t *mib,
+    size_t miblen, void *oldp, size_t *oldlenp, void *newp, size_t newlen);
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW	je_malloc_stats_print(
+    void (*write_cb)(void *, const char *), void *je_cbopaque,
+    const char *opts);
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW	je_malloc_usable_size(
+    JEMALLOC_USABLE_SIZE_CONST void *ptr) JEMALLOC_CXX_THROW;
 
 #ifdef JEMALLOC_OVERRIDE_MEMALIGN
-JEMALLOC_EXPORT void *	je_memalign(size_t alignment, size_t size)
-    JEMALLOC_ATTR(malloc);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_memalign(size_t alignment, size_t size)
+    JEMALLOC_CXX_THROW JEMALLOC_ATTR(malloc);
 #endif
 
 #ifdef JEMALLOC_OVERRIDE_VALLOC
-JEMALLOC_EXPORT void *	je_valloc(size_t size) JEMALLOC_ATTR(malloc);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+    void JEMALLOC_NOTHROW	*je_valloc(size_t size) JEMALLOC_CXX_THROW
+    JEMALLOC_ATTR(malloc);
 #endif
 
-#ifdef JEMALLOC_EXPERIMENTAL
-JEMALLOC_EXPORT int	je_allocm(void **ptr, size_t *rsize, size_t size,
-    int flags) JEMALLOC_ATTR(nonnull(1));
-JEMALLOC_EXPORT int	je_rallocm(void **ptr, size_t *rsize, size_t size,
-    size_t extra, int flags) JEMALLOC_ATTR(nonnull(1));
-JEMALLOC_EXPORT int	je_sallocm(const void *ptr, size_t *rsize, int flags)
-    JEMALLOC_ATTR(nonnull(1));
-JEMALLOC_EXPORT int	je_dallocm(void *ptr, int flags)
-    JEMALLOC_ATTR(nonnull(1));
-JEMALLOC_EXPORT int	je_nallocm(size_t *rsize, size_t size, int flags);
-#endif
+typedef struct extent_hooks_s extent_hooks_t;
+
+/*
+ * void *
+ * extent_alloc(extent_hooks_t *extent_hooks, void *new_addr, size_t size,
+ *     size_t alignment, bool *zero, bool *commit, unsigned arena_ind);
+ */
+typedef void *(extent_alloc_t)(extent_hooks_t *, void *, size_t, size_t, bool *,
+    bool *, unsigned);
+
+/*
+ * bool
+ * extent_dalloc(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     bool committed, unsigned arena_ind);
+ */
+typedef bool (extent_dalloc_t)(extent_hooks_t *, void *, size_t, bool,
+    unsigned);
+
+/*
+ * void
+ * extent_destroy(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     bool committed, unsigned arena_ind);
+ */
+typedef void (extent_destroy_t)(extent_hooks_t *, void *, size_t, bool,
+    unsigned);
+
+/*
+ * bool
+ * extent_commit(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     size_t offset, size_t length, unsigned arena_ind);
+ */
+typedef bool (extent_commit_t)(extent_hooks_t *, void *, size_t, size_t, size_t,
+    unsigned);
+
+/*
+ * bool
+ * extent_decommit(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     size_t offset, size_t length, unsigned arena_ind);
+ */
+typedef bool (extent_decommit_t)(extent_hooks_t *, void *, size_t, size_t,
+    size_t, unsigned);
+
+/*
+ * bool
+ * extent_purge(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     size_t offset, size_t length, unsigned arena_ind);
+ */
+typedef bool (extent_purge_t)(extent_hooks_t *, void *, size_t, size_t, size_t,
+    unsigned);
+
+/*
+ * bool
+ * extent_split(extent_hooks_t *extent_hooks, void *addr, size_t size,
+ *     size_t size_a, size_t size_b, bool committed, unsigned arena_ind);
+ */
+typedef bool (extent_split_t)(extent_hooks_t *, void *, size_t, size_t, size_t,
+    bool, unsigned);
+
+/*
+ * bool
+ * extent_merge(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a,
+ *     void *addr_b, size_t size_b, bool committed, unsigned arena_ind);
+ */
+typedef bool (extent_merge_t)(extent_hooks_t *, void *, size_t, void *, size_t,
+    bool, unsigned);
+
+struct extent_hooks_s {
+	extent_alloc_t		*alloc;
+	extent_dalloc_t		*dalloc;
+	extent_destroy_t	*destroy;
+	extent_commit_t		*commit;
+	extent_decommit_t	*decommit;
+	extent_purge_t		*purge_lazy;
+	extent_purge_t		*purge_forced;
+	extent_split_t		*split;
+	extent_merge_t		*merge;
+};
 
 /*
  * By default application code must explicitly refer to mangled symbol names,
@@ -112,32 +356,28 @@ JEMALLOC_EXPORT int	je_nallocm(size_t *rsize, size_t size, int flags);
 #  ifndef JEMALLOC_NO_DEMANGLE
 #    define JEMALLOC_NO_DEMANGLE
 #  endif
-#  define malloc_conf je_malloc_conf
-#  define malloc_message je_malloc_message
-#  define malloc je_malloc
-#  define calloc je_calloc
-#  define posix_memalign je_posix_memalign
 #  define aligned_alloc je_aligned_alloc
-#  define realloc je_realloc
-#  define free je_free
-#  define mallocx je_mallocx
-#  define rallocx je_rallocx
-#  define xallocx je_xallocx
-#  define sallocx je_sallocx
+#  define calloc je_calloc
 #  define dallocx je_dallocx
-#  define nallocx je_nallocx
+#  define free je_free
 #  define mallctl je_mallctl
-#  define mallctlnametomib je_mallctlnametomib
 #  define mallctlbymib je_mallctlbymib
+#  define mallctlnametomib je_mallctlnametomib
+#  define malloc je_malloc
+#  define malloc_conf je_malloc_conf
+#  define malloc_message je_malloc_message
 #  define malloc_stats_print je_malloc_stats_print
 #  define malloc_usable_size je_malloc_usable_size
+#  define mallocx je_mallocx
+#  define nallocx je_nallocx
+#  define posix_memalign je_posix_memalign
+#  define rallocx je_rallocx
+#  define realloc je_realloc
+#  define sallocx je_sallocx
+#  define sdallocx je_sdallocx
+#  define xallocx je_xallocx
 #  define memalign je_memalign
 #  define valloc je_valloc
-#  define allocm je_allocm
-#  define dallocm je_dallocm
-#  define nallocm je_nallocm
-#  define rallocm je_rallocm
-#  define sallocm je_sallocm
 #endif
 
 /*
@@ -148,35 +388,31 @@ JEMALLOC_EXPORT int	je_nallocm(size_t *rsize, size_t size, int flags);
  * and/or --with-jemalloc-prefix.
  */
 #ifndef JEMALLOC_NO_DEMANGLE
-#  undef je_malloc_conf
-#  undef je_malloc_message
-#  undef je_malloc
-#  undef je_calloc
-#  undef je_posix_memalign
 #  undef je_aligned_alloc
-#  undef je_realloc
-#  undef je_free
-#  undef je_mallocx
-#  undef je_rallocx
-#  undef je_xallocx
-#  undef je_sallocx
+#  undef je_calloc
 #  undef je_dallocx
-#  undef je_nallocx
+#  undef je_free
 #  undef je_mallctl
-#  undef je_mallctlnametomib
 #  undef je_mallctlbymib
+#  undef je_mallctlnametomib
+#  undef je_malloc
+#  undef je_malloc_conf
+#  undef je_malloc_message
 #  undef je_malloc_stats_print
 #  undef je_malloc_usable_size
+#  undef je_mallocx
+#  undef je_nallocx
+#  undef je_posix_memalign
+#  undef je_rallocx
+#  undef je_realloc
+#  undef je_sallocx
+#  undef je_sdallocx
+#  undef je_xallocx
 #  undef je_memalign
 #  undef je_valloc
-#  undef je_allocm
-#  undef je_dallocm
-#  undef je_nallocm
-#  undef je_rallocm
-#  undef je_sallocm
 #endif
 
 #ifdef __cplusplus
-};
+}
 #endif
 #endif /* JEMALLOC_H_ */
diff --git a/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdbool.h b/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdbool.h
new file mode 100644
index 0000000000..d92160ebc7
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdbool.h
@@ -0,0 +1,20 @@
+#ifndef stdbool_h
+#define stdbool_h
+
+#include <wtypes.h>
+
+/* MSVC doesn't define _Bool or bool in C, but does have BOOL */
+/* Note this doesn't pass autoconf's test because (bool) 0.5 != true */
+/* Clang-cl uses MSVC headers, so needs msvc_compat, but has _Bool as
+ * a built-in type. */
+#ifndef __clang__
+typedef BOOL _Bool;
+#endif
+
+#define bool _Bool
+#define true 1
+#define false 0
+
+#define __bool_true_false_are_defined 1
+
+#endif /* stdbool_h */
diff --git a/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdint.h b/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdint.h
new file mode 100644
index 0000000000..d02608a597
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/msvc_compat/C99/stdint.h
@@ -0,0 +1,247 @@
+// ISO C9x  compliant stdint.h for Microsoft Visual Studio
+// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124 
+// 
+//  Copyright (c) 2006-2008 Alexander Chemeris
+// 
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are met:
+// 
+//   1. Redistributions of source code must retain the above copyright notice,
+//      this list of conditions and the following disclaimer.
+// 
+//   2. Redistributions in binary form must reproduce the above copyright
+//      notice, this list of conditions and the following disclaimer in the
+//      documentation and/or other materials provided with the distribution.
+// 
+//   3. The name of the author may be used to endorse or promote products
+//      derived from this software without specific prior written permission.
+// 
+// THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
+// WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
+// EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
+// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, 
+// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+// 
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef _MSC_VER // [
+#error "Use this header only with Microsoft Visual C++ compilers!"
+#endif // _MSC_VER ]
+
+#ifndef _MSC_STDINT_H_ // [
+#define _MSC_STDINT_H_
+
+#if _MSC_VER > 1000
+#pragma once
+#endif
+
+#include <limits.h>
+
+// For Visual Studio 6 in C++ mode and for many Visual Studio versions when
+// compiling for ARM we should wrap <wchar.h> include with 'extern "C++" {}'
+// or compiler give many errors like this:
+//   error C2733: second C linkage of overloaded function 'wmemchr' not allowed
+#ifdef __cplusplus
+extern "C" {
+#endif
+#  include <wchar.h>
+#ifdef __cplusplus
+}
+#endif
+
+// Define _W64 macros to mark types changing their size, like intptr_t.
+#ifndef _W64
+#  if !defined(__midl) && (defined(_X86_) || defined(_M_IX86)) && _MSC_VER >= 1300
+#     define _W64 __w64
+#  else
+#     define _W64
+#  endif
+#endif
+
+
+// 7.18.1 Integer types
+
+// 7.18.1.1 Exact-width integer types
+
+// Visual Studio 6 and Embedded Visual C++ 4 doesn't
+// realize that, e.g. char has the same size as __int8
+// so we give up on __intX for them.
+#if (_MSC_VER < 1300)
+   typedef signed char       int8_t;
+   typedef signed short      int16_t;
+   typedef signed int        int32_t;
+   typedef unsigned char     uint8_t;
+   typedef unsigned short    uint16_t;
+   typedef unsigned int      uint32_t;
+#else
+   typedef signed __int8     int8_t;
+   typedef signed __int16    int16_t;
+   typedef signed __int32    int32_t;
+   typedef unsigned __int8   uint8_t;
+   typedef unsigned __int16  uint16_t;
+   typedef unsigned __int32  uint32_t;
+#endif
+typedef signed __int64       int64_t;
+typedef unsigned __int64     uint64_t;
+
+
+// 7.18.1.2 Minimum-width integer types
+typedef int8_t    int_least8_t;
+typedef int16_t   int_least16_t;
+typedef int32_t   int_least32_t;
+typedef int64_t   int_least64_t;
+typedef uint8_t   uint_least8_t;
+typedef uint16_t  uint_least16_t;
+typedef uint32_t  uint_least32_t;
+typedef uint64_t  uint_least64_t;
+
+// 7.18.1.3 Fastest minimum-width integer types
+typedef int8_t    int_fast8_t;
+typedef int16_t   int_fast16_t;
+typedef int32_t   int_fast32_t;
+typedef int64_t   int_fast64_t;
+typedef uint8_t   uint_fast8_t;
+typedef uint16_t  uint_fast16_t;
+typedef uint32_t  uint_fast32_t;
+typedef uint64_t  uint_fast64_t;
+
+// 7.18.1.4 Integer types capable of holding object pointers
+#ifdef _WIN64 // [
+   typedef signed __int64    intptr_t;
+   typedef unsigned __int64  uintptr_t;
+#else // _WIN64 ][
+   typedef _W64 signed int   intptr_t;
+   typedef _W64 unsigned int uintptr_t;
+#endif // _WIN64 ]
+
+// 7.18.1.5 Greatest-width integer types
+typedef int64_t   intmax_t;
+typedef uint64_t  uintmax_t;
+
+
+// 7.18.2 Limits of specified-width integer types
+
+#if !defined(__cplusplus) || defined(__STDC_LIMIT_MACROS) // [   See footnote 220 at page 257 and footnote 221 at page 259
+
+// 7.18.2.1 Limits of exact-width integer types
+#define INT8_MIN     ((int8_t)_I8_MIN)
+#define INT8_MAX     _I8_MAX
+#define INT16_MIN    ((int16_t)_I16_MIN)
+#define INT16_MAX    _I16_MAX
+#define INT32_MIN    ((int32_t)_I32_MIN)
+#define INT32_MAX    _I32_MAX
+#define INT64_MIN    ((int64_t)_I64_MIN)
+#define INT64_MAX    _I64_MAX
+#define UINT8_MAX    _UI8_MAX
+#define UINT16_MAX   _UI16_MAX
+#define UINT32_MAX   _UI32_MAX
+#define UINT64_MAX   _UI64_MAX
+
+// 7.18.2.2 Limits of minimum-width integer types
+#define INT_LEAST8_MIN    INT8_MIN
+#define INT_LEAST8_MAX    INT8_MAX
+#define INT_LEAST16_MIN   INT16_MIN
+#define INT_LEAST16_MAX   INT16_MAX
+#define INT_LEAST32_MIN   INT32_MIN
+#define INT_LEAST32_MAX   INT32_MAX
+#define INT_LEAST64_MIN   INT64_MIN
+#define INT_LEAST64_MAX   INT64_MAX
+#define UINT_LEAST8_MAX   UINT8_MAX
+#define UINT_LEAST16_MAX  UINT16_MAX
+#define UINT_LEAST32_MAX  UINT32_MAX
+#define UINT_LEAST64_MAX  UINT64_MAX
+
+// 7.18.2.3 Limits of fastest minimum-width integer types
+#define INT_FAST8_MIN    INT8_MIN
+#define INT_FAST8_MAX    INT8_MAX
+#define INT_FAST16_MIN   INT16_MIN
+#define INT_FAST16_MAX   INT16_MAX
+#define INT_FAST32_MIN   INT32_MIN
+#define INT_FAST32_MAX   INT32_MAX
+#define INT_FAST64_MIN   INT64_MIN
+#define INT_FAST64_MAX   INT64_MAX
+#define UINT_FAST8_MAX   UINT8_MAX
+#define UINT_FAST16_MAX  UINT16_MAX
+#define UINT_FAST32_MAX  UINT32_MAX
+#define UINT_FAST64_MAX  UINT64_MAX
+
+// 7.18.2.4 Limits of integer types capable of holding object pointers
+#ifdef _WIN64 // [
+#  define INTPTR_MIN   INT64_MIN
+#  define INTPTR_MAX   INT64_MAX
+#  define UINTPTR_MAX  UINT64_MAX
+#else // _WIN64 ][
+#  define INTPTR_MIN   INT32_MIN
+#  define INTPTR_MAX   INT32_MAX
+#  define UINTPTR_MAX  UINT32_MAX
+#endif // _WIN64 ]
+
+// 7.18.2.5 Limits of greatest-width integer types
+#define INTMAX_MIN   INT64_MIN
+#define INTMAX_MAX   INT64_MAX
+#define UINTMAX_MAX  UINT64_MAX
+
+// 7.18.3 Limits of other integer types
+
+#ifdef _WIN64 // [
+#  define PTRDIFF_MIN  _I64_MIN
+#  define PTRDIFF_MAX  _I64_MAX
+#else  // _WIN64 ][
+#  define PTRDIFF_MIN  _I32_MIN
+#  define PTRDIFF_MAX  _I32_MAX
+#endif  // _WIN64 ]
+
+#define SIG_ATOMIC_MIN  INT_MIN
+#define SIG_ATOMIC_MAX  INT_MAX
+
+#ifndef SIZE_MAX // [
+#  ifdef _WIN64 // [
+#     define SIZE_MAX  _UI64_MAX
+#  else // _WIN64 ][
+#     define SIZE_MAX  _UI32_MAX
+#  endif // _WIN64 ]
+#endif // SIZE_MAX ]
+
+// WCHAR_MIN and WCHAR_MAX are also defined in <wchar.h>
+#ifndef WCHAR_MIN // [
+#  define WCHAR_MIN  0
+#endif  // WCHAR_MIN ]
+#ifndef WCHAR_MAX // [
+#  define WCHAR_MAX  _UI16_MAX
+#endif  // WCHAR_MAX ]
+
+#define WINT_MIN  0
+#define WINT_MAX  _UI16_MAX
+
+#endif // __STDC_LIMIT_MACROS ]
+
+
+// 7.18.4 Limits of other integer types
+
+#if !defined(__cplusplus) || defined(__STDC_CONSTANT_MACROS) // [   See footnote 224 at page 260
+
+// 7.18.4.1 Macros for minimum-width integer constants
+
+#define INT8_C(val)  val##i8
+#define INT16_C(val) val##i16
+#define INT32_C(val) val##i32
+#define INT64_C(val) val##i64
+
+#define UINT8_C(val)  val##ui8
+#define UINT16_C(val) val##ui16
+#define UINT32_C(val) val##ui32
+#define UINT64_C(val) val##ui64
+
+// 7.18.4.2 Macros for greatest-width integer constants
+#define INTMAX_C   INT64_C
+#define UINTMAX_C  UINT64_C
+
+#endif // __STDC_CONSTANT_MACROS ]
+
+
+#endif // _MSC_STDINT_H_ ]
diff --git a/modules/worldengine/deps/jemalloc/include/msvc_compat/strings.h b/modules/worldengine/deps/jemalloc/include/msvc_compat/strings.h
index c84975b6b8..996f256ce8 100644
--- a/modules/worldengine/deps/jemalloc/include/msvc_compat/strings.h
+++ b/modules/worldengine/deps/jemalloc/include/msvc_compat/strings.h
@@ -3,21 +3,56 @@
 
 /* MSVC doesn't define ffs/ffsl. This dummy strings.h header is provided
  * for both */
-#include <intrin.h>
-#pragma intrinsic(_BitScanForward)
-static __forceinline int ffsl(long x)
-{
+#ifdef _MSC_VER
+#  include <intrin.h>
+#  pragma intrinsic(_BitScanForward)
+static __forceinline int ffsl(long x) {
 	unsigned long i;
 
-	if (_BitScanForward(&i, x))
-		return (i + 1);
-	return (0);
+	if (_BitScanForward(&i, x)) {
+		return i + 1;
+	}
+	return 0;
 }
 
-static __forceinline int ffs(int x)
-{
+static __forceinline int ffs(int x) {
+	return ffsl(x);
+}
+
+#  ifdef  _M_X64
+#    pragma intrinsic(_BitScanForward64)
+#  endif
+
+static __forceinline int ffsll(unsigned __int64 x) {
+	unsigned long i;
+#ifdef  _M_X64
+	if (_BitScanForward64(&i, x)) {
+		return i + 1;
+	}
+	return 0;
+#else
+// Fallback for 32-bit build where 64-bit version not available
+// assuming little endian
+	union {
+		unsigned __int64 ll;
+		unsigned   long l[2];
+	} s;
 
-	return (ffsl(x));
+	s.ll = x;
+
+	if (_BitScanForward(&i, s.l[0])) {
+		return i + 1;
+	} else if(_BitScanForward(&i, s.l[1])) {
+		return i + 33;
+	}
+	return 0;
+#endif
 }
 
+#else
+#  define ffsll(x) __builtin_ffsll(x)
+#  define ffsl(x) __builtin_ffsl(x)
+#  define ffs(x) __builtin_ffs(x)
 #endif
+
+#endif /* strings_h */
diff --git a/modules/worldengine/deps/jemalloc/include/msvc_compat/windows_extra.h b/modules/worldengine/deps/jemalloc/include/msvc_compat/windows_extra.h
new file mode 100644
index 0000000000..a6ebb9306f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/include/msvc_compat/windows_extra.h
@@ -0,0 +1,6 @@
+#ifndef MSVC_COMPAT_WINDOWS_EXTRA_H
+#define MSVC_COMPAT_WINDOWS_EXTRA_H
+
+#include <errno.h>
+
+#endif /* MSVC_COMPAT_WINDOWS_EXTRA_H */
diff --git a/modules/worldengine/deps/jemalloc/jemalloc_internal_defs.h.in.cmake b/modules/worldengine/deps/jemalloc/jemalloc_internal_defs.h.in.cmake
new file mode 100644
index 0000000000..214435283d
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/jemalloc_internal_defs.h.in.cmake
@@ -0,0 +1,343 @@
+/* include/jemalloc/internal/jemalloc_internal_defs.h.  Generated from jemalloc_internal_defs.h.in by configure.  */
+#ifndef JEMALLOC_INTERNAL_DEFS_H_
+#define JEMALLOC_INTERNAL_DEFS_H_
+/*
+ * If JEMALLOC_PREFIX is defined via --with-jemalloc-prefix, it will cause all
+ * public APIs to be prefixed.  This makes it possible, with some care, to use
+ * multiple allocators simultaneously.
+ */
+/* #undef JEMALLOC_PREFIX */
+/* #undef JEMALLOC_CPREFIX */
+
+/*
+ * Define overrides for non-standard allocator-related functions if they are
+ * present on the system.
+ */
+#define JEMALLOC_OVERRIDE___LIBC_CALLOC 
+#define JEMALLOC_OVERRIDE___LIBC_FREE 
+#define JEMALLOC_OVERRIDE___LIBC_MALLOC 
+#define JEMALLOC_OVERRIDE___LIBC_MEMALIGN 
+#define JEMALLOC_OVERRIDE___LIBC_REALLOC 
+#define JEMALLOC_OVERRIDE___LIBC_VALLOC 
+/* #undef JEMALLOC_OVERRIDE___POSIX_MEMALIGN */
+
+/*
+ * JEMALLOC_PRIVATE_NAMESPACE is used as a prefix for all library-private APIs.
+ * For shared libraries, symbol visibility mechanisms prevent these symbols
+ * from being exported, but for static libraries, naming collisions are a real
+ * possibility.
+ */
+#define JEMALLOC_PRIVATE_NAMESPACE je_
+
+/*
+ * Hyper-threaded CPUs may need a special instruction inside spin loops in
+ * order to yield to another virtual CPU.
+ */
+#define CPU_SPINWAIT __asm__ volatile("pause")
+
+/*
+ * Number of significant bits in virtual addresses.  This may be less than the
+ * total number of bits in a pointer, e.g. on x64, for which the uppermost 16
+ * bits are the same as bit 47.
+ */
+#define LG_VADDR @JEM_VADDRBITS@
+
+/* Defined if C11 atomics are available. */
+#define JEMALLOC_C11_ATOMICS 1
+
+/* Defined if GCC __atomic atomics are available. */
+#define JEMALLOC_GCC_ATOMIC_ATOMICS 1
+
+/* Defined if GCC __sync atomics are available. */
+#define JEMALLOC_GCC_SYNC_ATOMICS 1
+
+/*
+ * Defined if __sync_add_and_fetch(uint32_t *, uint32_t) and
+ * __sync_sub_and_fetch(uint32_t *, uint32_t) are available, despite
+ * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_4 not being defined (which means the
+ * functions are defined in libgcc instead of being inlines).
+ */
+/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_4 */
+
+/*
+ * Defined if __sync_add_and_fetch(uint64_t *, uint64_t) and
+ * __sync_sub_and_fetch(uint64_t *, uint64_t) are available, despite
+ * __GCC_HAVE_SYNC_COMPARE_AND_SWAP_8 not being defined (which means the
+ * functions are defined in libgcc instead of being inlines).
+ */
+/* #undef JE_FORCE_SYNC_COMPARE_AND_SWAP_8 */
+
+/*
+ * Defined if __builtin_clz() and __builtin_clzl() are available.
+ */
+#define JEMALLOC_HAVE_BUILTIN_CLZ 
+
+/*
+ * Defined if os_unfair_lock_*() functions are available, as provided by Darwin.
+ */
+/* #undef JEMALLOC_OS_UNFAIR_LOCK */
+
+/*
+ * Defined if OSSpin*() functions are available, as provided by Darwin, and
+ * documented in the spinlock(3) manual page.
+ */
+/* #undef JEMALLOC_OSSPIN */
+
+/* Defined if syscall(2) is usable. */
+#define JEMALLOC_USE_SYSCALL 
+
+/*
+ * Defined if secure_getenv(3) is available.
+ */
+#define JEMALLOC_HAVE_SECURE_GETENV 
+
+/*
+ * Defined if issetugid(2) is available.
+ */
+/* #undef JEMALLOC_HAVE_ISSETUGID */
+
+/* Defined if pthread_atfork(3) is available. */
+#define JEMALLOC_HAVE_PTHREAD_ATFORK 
+
+/* Defined if pthread_setname_np(3) is available. */
+#define JEMALLOC_HAVE_PTHREAD_SETNAME_NP 
+
+/*
+ * Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
+ */
+#define JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE 1
+
+/*
+ * Defined if clock_gettime(CLOCK_MONOTONIC, ...) is available.
+ */
+#define JEMALLOC_HAVE_CLOCK_MONOTONIC 1
+
+/*
+ * Defined if mach_absolute_time() is available.
+ */
+/* #undef JEMALLOC_HAVE_MACH_ABSOLUTE_TIME */
+
+/*
+ * Defined if _malloc_thread_cleanup() exists.  At least in the case of
+ * FreeBSD, pthread_key_create() allocates, which if used during malloc
+ * bootstrapping will cause recursion into the pthreads library.  Therefore, if
+ * _malloc_thread_cleanup() exists, use it as the basis for thread cleanup in
+ * malloc_tsd.
+ */
+/* #undef JEMALLOC_MALLOC_THREAD_CLEANUP */
+
+/*
+ * Defined if threaded initialization is known to be safe on this platform.
+ * Among other things, it must be possible to initialize a mutex without
+ * triggering allocation in order for threaded allocation to be safe.
+ */
+#define JEMALLOC_THREADED_INIT 
+
+/*
+ * Defined if the pthreads implementation defines
+ * _pthread_mutex_init_calloc_cb(), in which case the function is used in order
+ * to avoid recursive allocation during mutex initialization.
+ */
+/* #undef JEMALLOC_MUTEX_INIT_CB */
+
+/* Non-empty if the tls_model attribute is supported. */
+#define JEMALLOC_TLS_MODEL @JEM_TLSMODEL@
+
+/*
+ * JEMALLOC_DEBUG enables assertions and other sanity checks, and disables
+ * inline functions.
+ */
+/* #undef JEMALLOC_DEBUG */
+
+/* JEMALLOC_STATS enables statistics calculation. */
+/* #undef JEMALLOC_STATS */
+
+/* JEMALLOC_PROF enables allocation profiling. */
+/* #undef JEMALLOC_PROF */
+
+/* Use libunwind for profile backtracing if defined. */
+/* #undef JEMALLOC_PROF_LIBUNWIND */
+
+/* Use libgcc for profile backtracing if defined. */
+/* #undef JEMALLOC_PROF_LIBGCC */
+
+/* Use gcc intrinsics for profile backtracing if defined. */
+/* #undef JEMALLOC_PROF_GCC */
+
+/*
+ * JEMALLOC_DSS enables use of sbrk(2) to allocate extents from the data storage
+ * segment (DSS).
+ */
+#define JEMALLOC_DSS 
+
+/* Support memory filling (junk/zero). */
+#define JEMALLOC_FILL 
+
+/* Support utrace(2)-based tracing. */
+/* #undef JEMALLOC_UTRACE */
+
+/* Support optional abort() on OOM. */
+/* #undef JEMALLOC_XMALLOC */
+
+/* Support lazy locking (avoid locking unless a second thread is launched). */
+/* #undef JEMALLOC_LAZY_LOCK */
+
+/*
+ * Minimum allocation alignment is 2^LG_QUANTUM bytes (ignoring tiny size
+ * classes).
+ */
+/* #undef LG_QUANTUM */
+
+/* One page is 2^LG_PAGE bytes. */
+#define LG_PAGE 12
+
+/*
+ * One huge page is 2^LG_HUGEPAGE bytes.  Note that this is defined even if the
+ * system does not explicitly support huge pages; system calls that require
+ * explicit huge page support are separately configured.
+ */
+#define LG_HUGEPAGE 21
+
+/*
+ * If defined, adjacent virtual memory mappings with identical attributes
+ * automatically coalesce, and they fragment when changes are made to subranges.
+ * This is the normal order of things for mmap()/munmap(), but on Windows
+ * VirtualAlloc()/VirtualFree() operations must be precisely matched, i.e.
+ * mappings do *not* coalesce/fragment.
+ */
+#define JEMALLOC_MAPS_COALESCE 
+
+/*
+ * If defined, retain memory for later reuse by default rather than using e.g.
+ * munmap() to unmap freed extents.  This is enabled on 64-bit Linux because
+ * common sequences of mmap()/munmap() calls will cause virtual memory map
+ * holes.
+ */
+#define JEMALLOC_RETAIN 
+
+/* TLS is used to map arenas and magazine caches to threads. */
+#define JEMALLOC_TLS 
+
+/*
+ * Used to mark unreachable code to quiet "end of non-void" compiler warnings.
+ * Don't use this directly; instead use unreachable() from util.h
+ */
+#define JEMALLOC_INTERNAL_UNREACHABLE __builtin_unreachable
+
+/*
+ * ffs*() functions to use for bitmapping.  Don't use these directly; instead,
+ * use ffs_*() from util.h.
+ */
+#define JEMALLOC_INTERNAL_FFSLL __builtin_ffsll
+#define JEMALLOC_INTERNAL_FFSL __builtin_ffsl
+#define JEMALLOC_INTERNAL_FFS __builtin_ffs
+
+/*
+ * If defined, explicitly attempt to more uniformly distribute large allocation
+ * pointer alignments across all cache indices.
+ */
+#define JEMALLOC_CACHE_OBLIVIOUS 
+
+/*
+ * Darwin (OS X) uses zones to work around Mach-O symbol override shortcomings.
+ */
+/* #undef JEMALLOC_ZONE */
+
+/*
+ * Methods for determining whether the OS overcommits.
+ * JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY: Linux's
+ *                                         /proc/sys/vm.overcommit_memory file.
+ * JEMALLOC_SYSCTL_VM_OVERCOMMIT: FreeBSD's vm.overcommit sysctl.
+ */
+/* #undef JEMALLOC_SYSCTL_VM_OVERCOMMIT */
+#define JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY 
+
+/* Defined if madvise(2) is available. */
+#define JEMALLOC_HAVE_MADVISE 
+
+/*
+ * Methods for purging unused pages differ between operating systems.
+ *
+ *   madvise(..., MADV_FREE) : This marks pages as being unused, such that they
+ *                             will be discarded rather than swapped out.
+ *   madvise(..., MADV_DONTNEED) : If JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS is
+ *                                 defined, this immediately discards pages,
+ *                                 such that new pages will be demand-zeroed if
+ *                                 the address region is later touched;
+ *                                 otherwise this behaves similarly to
+ *                                 MADV_FREE, though typically with higher
+ *                                 system overhead.
+ */
+#define JEMALLOC_PURGE_MADVISE_FREE 
+#define JEMALLOC_PURGE_MADVISE_DONTNEED 
+#define JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS 1
+
+/*
+ * Defined if transparent huge pages (THPs) are supported via the
+ * MADV_[NO]HUGEPAGE arguments to madvise(2), and THP support is enabled.
+ */
+#define JEMALLOC_THP 
+
+/* Define if operating system has alloca.h header. */
+#define JEMALLOC_HAS_ALLOCA_H 1
+
+/* C99 restrict keyword supported. */
+#define JEMALLOC_HAS_RESTRICT 1
+
+/* For use by hash code. */
+/* #undef JEMALLOC_BIG_ENDIAN */
+
+/* sizeof(int) == 2^LG_SIZEOF_INT. */
+#define LG_SIZEOF_INT 2
+
+/* sizeof(long) == 2^LG_SIZEOF_LONG. */
+#define LG_SIZEOF_LONG @JEM_SIZEDEF@
+
+/* sizeof(long long) == 2^LG_SIZEOF_LONG_LONG. */
+#define LG_SIZEOF_LONG_LONG 3
+
+/* sizeof(intmax_t) == 2^LG_SIZEOF_INTMAX_T. */
+#define LG_SIZEOF_INTMAX_T 3
+
+/* glibc malloc hooks (__malloc_hook, __realloc_hook, __free_hook). */
+#define JEMALLOC_GLIBC_MALLOC_HOOK 
+
+/* glibc memalign hook. */
+#define JEMALLOC_GLIBC_MEMALIGN_HOOK 
+
+/* pthread support */
+#define JEMALLOC_HAVE_PTHREAD 
+
+/* dlsym() support */
+#define JEMALLOC_HAVE_DLSYM 
+
+/* Adaptive mutex support in pthreads. */
+#define JEMALLOC_HAVE_PTHREAD_MUTEX_ADAPTIVE_NP 
+
+/* GNU specific sched_getcpu support */
+#define JEMALLOC_HAVE_SCHED_GETCPU 
+
+/* GNU specific sched_setaffinity support */
+#define JEMALLOC_HAVE_SCHED_SETAFFINITY 
+
+/*
+ * If defined, all the features necessary for background threads are present.
+ */
+#define JEMALLOC_BACKGROUND_THREAD 1
+
+/*
+ * If defined, jemalloc symbols are not exported (doesn't work when
+ * JEMALLOC_PREFIX is not defined).
+ */
+/* #undef JEMALLOC_EXPORT */
+
+/* config.malloc_conf options string. */
+#define JEMALLOC_CONFIG_MALLOC_CONF ""
+
+/* If defined, jemalloc takes the malloc/free/etc. symbol names. */
+#define JEMALLOC_IS_MALLOC 1
+
+/* sizeof(void *) == 2^LG_SIZEOF_PTR. */
+#define LG_SIZEOF_PTR @JEM_SIZEDEF@
+
+#endif /* JEMALLOC_INTERNAL_DEFS_H_ */
diff --git a/modules/worldengine/deps/jemalloc/src/arena.c b/modules/worldengine/deps/jemalloc/src/arena.c
index dad707b63d..632fce5233 100644
--- a/modules/worldengine/deps/jemalloc/src/arena.c
+++ b/modules/worldengine/deps/jemalloc/src/arena.c
@@ -1,40 +1,57 @@
-#define	JEMALLOC_ARENA_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_ARENA_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/util.h"
 
 /******************************************************************************/
 /* Data. */
 
-ssize_t		opt_lg_dirty_mult = LG_DIRTY_MULT_DEFAULT;
-arena_bin_info_t	arena_bin_info[NBINS];
-
-JEMALLOC_ALIGNED(CACHELINE)
-const uint8_t	small_size2bin[] = {
-#define	S2B_8(i)	i,
-#define	S2B_16(i)	S2B_8(i) S2B_8(i)
-#define	S2B_32(i)	S2B_16(i) S2B_16(i)
-#define	S2B_64(i)	S2B_32(i) S2B_32(i)
-#define	S2B_128(i)	S2B_64(i) S2B_64(i)
-#define	S2B_256(i)	S2B_128(i) S2B_128(i)
-#define	S2B_512(i)	S2B_256(i) S2B_256(i)
-#define	S2B_1024(i)	S2B_512(i) S2B_512(i)
-#define	S2B_2048(i)	S2B_1024(i) S2B_1024(i)
-#define	S2B_4096(i)	S2B_2048(i) S2B_2048(i)
-#define	S2B_8192(i)	S2B_4096(i) S2B_4096(i)
-#define	SIZE_CLASS(bin, delta, size)					\
-	S2B_##delta(bin)
+/*
+ * Define names for both unininitialized and initialized phases, so that
+ * options and mallctl processing are straightforward.
+ */
+const char *percpu_arena_mode_names[] = {
+	"percpu",
+	"phycpu",
+	"disabled",
+	"percpu",
+	"phycpu"
+};
+percpu_arena_mode_t opt_percpu_arena = PERCPU_ARENA_DEFAULT;
+
+ssize_t opt_dirty_decay_ms = DIRTY_DECAY_MS_DEFAULT;
+ssize_t opt_muzzy_decay_ms = MUZZY_DECAY_MS_DEFAULT;
+
+static atomic_zd_t dirty_decay_ms_default;
+static atomic_zd_t muzzy_decay_ms_default;
+
+const arena_bin_info_t arena_bin_info[NBINS] = {
+#define BIN_INFO_bin_yes(reg_size, slab_size, nregs)			\
+	{reg_size, slab_size, nregs, BITMAP_INFO_INITIALIZER(nregs)},
+#define BIN_INFO_bin_no(reg_size, slab_size, nregs)
+#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs,		\
+    lg_delta_lookup)							\
+	BIN_INFO_bin_##bin((1U<<lg_grp) + (ndelta<<lg_delta),		\
+	    (pgs << LG_PAGE), (pgs << LG_PAGE) / ((1U<<lg_grp) +	\
+	    (ndelta<<lg_delta)))
 	SIZE_CLASSES
-#undef S2B_8
-#undef S2B_16
-#undef S2B_32
-#undef S2B_64
-#undef S2B_128
-#undef S2B_256
-#undef S2B_512
-#undef S2B_1024
-#undef S2B_2048
-#undef S2B_4096
-#undef S2B_8192
-#undef SIZE_CLASS
+#undef BIN_INFO_bin_yes
+#undef BIN_INFO_bin_no
+#undef SC
+};
+
+const uint64_t h_steps[SMOOTHSTEP_NSTEPS] = {
+#define STEP(step, h, x, y)			\
+		h,
+		SMOOTHSTEP
+#undef STEP
 };
 
 /******************************************************************************/
@@ -43,2535 +60,2120 @@ const uint8_t	small_size2bin[] = {
  * definition.
  */
 
-static void	arena_purge(arena_t *arena, bool all);
-static void	arena_run_dalloc(arena_t *arena, arena_run_t *run, bool dirty,
-    bool cleaned);
-static void	arena_dalloc_bin_run(arena_t *arena, arena_chunk_t *chunk,
-    arena_run_t *run, arena_bin_t *bin);
-static void	arena_bin_lower_run(arena_t *arena, arena_chunk_t *chunk,
-    arena_run_t *run, arena_bin_t *bin);
+static void arena_decay_to_limit(tsdn_t *tsdn, arena_t *arena,
+    arena_decay_t *decay, extents_t *extents, bool all, size_t npages_limit,
+    bool is_background_thread);
+static bool arena_decay_dirty(tsdn_t *tsdn, arena_t *arena,
+    bool is_background_thread, bool all);
+static void arena_dalloc_bin_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab,
+    arena_bin_t *bin);
+static void arena_bin_lower_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab,
+    arena_bin_t *bin);
 
 /******************************************************************************/
 
-static inline int
-arena_run_comp(arena_chunk_map_t *a, arena_chunk_map_t *b)
-{
-	uintptr_t a_mapelm = (uintptr_t)a;
-	uintptr_t b_mapelm = (uintptr_t)b;
-
-	assert(a != NULL);
-	assert(b != NULL);
-
-	return ((a_mapelm > b_mapelm) - (a_mapelm < b_mapelm));
-}
-
-/* Generate red-black tree functions. */
-rb_gen(static UNUSED, arena_run_tree_, arena_run_tree_t, arena_chunk_map_t,
-    u.rb_link, arena_run_comp)
-
-static inline int
-arena_avail_comp(arena_chunk_map_t *a, arena_chunk_map_t *b)
-{
-	int ret;
-	size_t a_size = a->bits & ~PAGE_MASK;
-	size_t b_size = b->bits & ~PAGE_MASK;
-
-	ret = (a_size > b_size) - (a_size < b_size);
-	if (ret == 0) {
-		uintptr_t a_mapelm, b_mapelm;
-
-		if ((a->bits & CHUNK_MAP_KEY) != CHUNK_MAP_KEY)
-			a_mapelm = (uintptr_t)a;
-		else {
-			/*
-			 * Treat keys as though they are lower than anything
-			 * else.
-			 */
-			a_mapelm = 0;
+static bool
+arena_stats_init(tsdn_t *tsdn, arena_stats_t *arena_stats) {
+	if (config_debug) {
+		for (size_t i = 0; i < sizeof(arena_stats_t); i++) {
+			assert(((char *)arena_stats)[i] == 0);
 		}
-		b_mapelm = (uintptr_t)b;
-
-		ret = (a_mapelm > b_mapelm) - (a_mapelm < b_mapelm);
 	}
-
-	return (ret);
+#ifndef JEMALLOC_ATOMIC_U64
+	if (malloc_mutex_init(&arena_stats->mtx, "arena_stats",
+	    WITNESS_RANK_ARENA_STATS, malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+#endif
+	/* Memory is zeroed, so there is no need to clear stats. */
+	return false;
 }
 
-/* Generate red-black tree functions. */
-rb_gen(static UNUSED, arena_avail_tree_, arena_avail_tree_t, arena_chunk_map_t,
-    u.rb_link, arena_avail_comp)
-
-static inline int
-arena_chunk_dirty_comp(arena_chunk_t *a, arena_chunk_t *b)
-{
-
-	assert(a != NULL);
-	assert(b != NULL);
-
-	/*
-	 * Short-circuit for self comparison.  The following comparison code
-	 * would come to the same result, but at the cost of executing the slow
-	 * path.
-	 */
-	if (a == b)
-		return (0);
-
-	/*
-	 * Order such that chunks with higher fragmentation are "less than"
-	 * those with lower fragmentation -- purging order is from "least" to
-	 * "greatest".  Fragmentation is measured as:
-	 *
-	 *     mean current avail run size
-	 *   --------------------------------
-	 *   mean defragmented avail run size
-	 *
-	 *            navail
-	 *         -----------
-	 *         nruns_avail           nruns_avail-nruns_adjac
-	 * = ========================= = -----------------------
-	 *            navail                  nruns_avail
-	 *    -----------------------
-	 *    nruns_avail-nruns_adjac
-	 *
-	 * The following code multiplies away the denominator prior to
-	 * comparison, in order to avoid division.
-	 *
-	 */
-	{
-		size_t a_val = (a->nruns_avail - a->nruns_adjac) *
-		    b->nruns_avail;
-		size_t b_val = (b->nruns_avail - b->nruns_adjac) *
-		    a->nruns_avail;
+static void
+arena_stats_lock(tsdn_t *tsdn, arena_stats_t *arena_stats) {
+#ifndef JEMALLOC_ATOMIC_U64
+	malloc_mutex_lock(tsdn, &arena_stats->mtx);
+#endif
+}
 
-		if (a_val < b_val)
-			return (1);
-		if (a_val > b_val)
-			return (-1);
-	}
-	/*
-	 * Break ties by chunk address.  For fragmented chunks, report lower
-	 * addresses as "lower", so that fragmentation reduction happens first
-	 * at lower addresses.  However, use the opposite ordering for
-	 * unfragmented chunks, in order to increase the chances of
-	 * re-allocating dirty runs.
-	 */
-	{
-		uintptr_t a_chunk = (uintptr_t)a;
-		uintptr_t b_chunk = (uintptr_t)b;
-		int ret = ((a_chunk > b_chunk) - (a_chunk < b_chunk));
-		if (a->nruns_adjac == 0) {
-			assert(b->nruns_adjac == 0);
-			ret = -ret;
-		}
-		return (ret);
-	}
+static void
+arena_stats_unlock(tsdn_t *tsdn, arena_stats_t *arena_stats) {
+#ifndef JEMALLOC_ATOMIC_U64
+	malloc_mutex_unlock(tsdn, &arena_stats->mtx);
+#endif
 }
 
-/* Generate red-black tree functions. */
-rb_gen(static UNUSED, arena_chunk_dirty_, arena_chunk_tree_t, arena_chunk_t,
-    dirty_link, arena_chunk_dirty_comp)
+static uint64_t
+arena_stats_read_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    arena_stats_u64_t *p) {
+#ifdef JEMALLOC_ATOMIC_U64
+	return atomic_load_u64(p, ATOMIC_RELAXED);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	return *p;
+#endif
+}
 
-static inline bool
-arena_avail_adjac_pred(arena_chunk_t *chunk, size_t pageind)
-{
-	bool ret;
+static void
+arena_stats_add_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    arena_stats_u64_t *p, uint64_t x) {
+#ifdef JEMALLOC_ATOMIC_U64
+	atomic_fetch_add_u64(p, x, ATOMIC_RELAXED);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	*p += x;
+#endif
+}
 
-	if (pageind-1 < map_bias)
-		ret = false;
-	else {
-		ret = (arena_mapbits_allocated_get(chunk, pageind-1) == 0);
-		assert(ret == false || arena_mapbits_dirty_get(chunk,
-		    pageind-1) != arena_mapbits_dirty_get(chunk, pageind));
-	}
-	return (ret);
+UNUSED static void
+arena_stats_sub_u64(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    arena_stats_u64_t *p, uint64_t x) {
+#ifdef JEMALLOC_ATOMIC_U64
+	UNUSED uint64_t r = atomic_fetch_sub_u64(p, x, ATOMIC_RELAXED);
+	assert(r - x <= r);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	*p -= x;
+	assert(*p + x >= *p);
+#endif
 }
 
-static inline bool
-arena_avail_adjac_succ(arena_chunk_t *chunk, size_t pageind, size_t npages)
-{
-	bool ret;
+/*
+ * Non-atomically sets *dst += src.  *dst needs external synchronization.
+ * This lets us avoid the cost of a fetch_add when its unnecessary (note that
+ * the types here are atomic).
+ */
+static void
+arena_stats_accum_u64(arena_stats_u64_t *dst, uint64_t src) {
+#ifdef JEMALLOC_ATOMIC_U64
+	uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED);
+	atomic_store_u64(dst, src + cur_dst, ATOMIC_RELAXED);
+#else
+	*dst += src;
+#endif
+}
 
-	if (pageind+npages == chunk_npages)
-		ret = false;
-	else {
-		assert(pageind+npages < chunk_npages);
-		ret = (arena_mapbits_allocated_get(chunk, pageind+npages) == 0);
-		assert(ret == false || arena_mapbits_dirty_get(chunk, pageind)
-		    != arena_mapbits_dirty_get(chunk, pageind+npages));
-	}
-	return (ret);
+static size_t
+arena_stats_read_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p) {
+#ifdef JEMALLOC_ATOMIC_U64
+	return atomic_load_zu(p, ATOMIC_RELAXED);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	return atomic_load_zu(p, ATOMIC_RELAXED);
+#endif
 }
 
-static inline bool
-arena_avail_adjac(arena_chunk_t *chunk, size_t pageind, size_t npages)
-{
+static void
+arena_stats_add_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p,
+    size_t x) {
+#ifdef JEMALLOC_ATOMIC_U64
+	atomic_fetch_add_zu(p, x, ATOMIC_RELAXED);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	size_t cur = atomic_load_zu(p, ATOMIC_RELAXED);
+	atomic_store_zu(p, cur + x, ATOMIC_RELAXED);
+#endif
+}
 
-	return (arena_avail_adjac_pred(chunk, pageind) ||
-	    arena_avail_adjac_succ(chunk, pageind, npages));
+static void
+arena_stats_sub_zu(tsdn_t *tsdn, arena_stats_t *arena_stats, atomic_zu_t *p,
+    size_t x) {
+#ifdef JEMALLOC_ATOMIC_U64
+	UNUSED size_t r = atomic_fetch_sub_zu(p, x, ATOMIC_RELAXED);
+	assert(r - x <= r);
+#else
+	malloc_mutex_assert_owner(tsdn, &arena_stats->mtx);
+	size_t cur = atomic_load_zu(p, ATOMIC_RELAXED);
+	atomic_store_zu(p, cur - x, ATOMIC_RELAXED);
+#endif
 }
 
+/* Like the _u64 variant, needs an externally synchronized *dst. */
 static void
-arena_avail_insert(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
-    size_t npages, bool maybe_adjac_pred, bool maybe_adjac_succ)
-{
+arena_stats_accum_zu(atomic_zu_t *dst, size_t src) {
+	size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED);
+	atomic_store_zu(dst, src + cur_dst, ATOMIC_RELAXED);
+}
 
-	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
-	    LG_PAGE));
+void
+arena_stats_large_nrequests_add(tsdn_t *tsdn, arena_stats_t *arena_stats,
+    szind_t szind, uint64_t nrequests) {
+	arena_stats_lock(tsdn, arena_stats);
+	arena_stats_add_u64(tsdn, arena_stats, &arena_stats->lstats[szind -
+	    NBINS].nrequests, nrequests);
+	arena_stats_unlock(tsdn, arena_stats);
+}
 
-	/*
-	 * chunks_dirty is keyed by nruns_{avail,adjac}, so the chunk must be
-	 * removed and reinserted even if the run to be inserted is clean.
-	 */
-	if (chunk->ndirty != 0)
-		arena_chunk_dirty_remove(&arena->chunks_dirty, chunk);
+void
+arena_stats_mapped_add(tsdn_t *tsdn, arena_stats_t *arena_stats, size_t size) {
+	arena_stats_lock(tsdn, arena_stats);
+	arena_stats_add_zu(tsdn, arena_stats, &arena_stats->mapped, size);
+	arena_stats_unlock(tsdn, arena_stats);
+}
 
-	if (maybe_adjac_pred && arena_avail_adjac_pred(chunk, pageind))
-		chunk->nruns_adjac++;
-	if (maybe_adjac_succ && arena_avail_adjac_succ(chunk, pageind, npages))
-		chunk->nruns_adjac++;
-	chunk->nruns_avail++;
-	assert(chunk->nruns_avail > chunk->nruns_adjac);
+void
+arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms,
+    size_t *nactive, size_t *ndirty, size_t *nmuzzy) {
+	*nthreads += arena_nthreads_get(arena, false);
+	*dss = dss_prec_names[arena_dss_prec_get(arena)];
+	*dirty_decay_ms = arena_dirty_decay_ms_get(arena);
+	*muzzy_decay_ms = arena_muzzy_decay_ms_get(arena);
+	*nactive += atomic_load_zu(&arena->nactive, ATOMIC_RELAXED);
+	*ndirty += extents_npages_get(&arena->extents_dirty);
+	*nmuzzy += extents_npages_get(&arena->extents_muzzy);
+}
 
-	if (arena_mapbits_dirty_get(chunk, pageind) != 0) {
-		arena->ndirty += npages;
-		chunk->ndirty += npages;
+void
+arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *dirty_decay_ms, ssize_t *muzzy_decay_ms,
+    size_t *nactive, size_t *ndirty, size_t *nmuzzy, arena_stats_t *astats,
+    malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats) {
+	cassert(config_stats);
+
+	arena_basic_stats_merge(tsdn, arena, nthreads, dss, dirty_decay_ms,
+	    muzzy_decay_ms, nactive, ndirty, nmuzzy);
+
+	size_t base_allocated, base_resident, base_mapped;
+	base_stats_get(tsdn, arena->base, &base_allocated, &base_resident,
+	    &base_mapped);
+
+	arena_stats_lock(tsdn, &arena->stats);
+
+	arena_stats_accum_zu(&astats->mapped, base_mapped
+	    + arena_stats_read_zu(tsdn, &arena->stats, &arena->stats.mapped));
+	arena_stats_accum_zu(&astats->retained,
+	    extents_npages_get(&arena->extents_retained) << LG_PAGE);
+
+	arena_stats_accum_u64(&astats->decay_dirty.npurge,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_dirty.npurge));
+	arena_stats_accum_u64(&astats->decay_dirty.nmadvise,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_dirty.nmadvise));
+	arena_stats_accum_u64(&astats->decay_dirty.purged,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_dirty.purged));
+
+	arena_stats_accum_u64(&astats->decay_muzzy.npurge,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_muzzy.npurge));
+	arena_stats_accum_u64(&astats->decay_muzzy.nmadvise,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_muzzy.nmadvise));
+	arena_stats_accum_u64(&astats->decay_muzzy.purged,
+	    arena_stats_read_u64(tsdn, &arena->stats,
+	    &arena->stats.decay_muzzy.purged));
+
+	arena_stats_accum_zu(&astats->base, base_allocated);
+	arena_stats_accum_zu(&astats->internal, arena_internal_get(arena));
+	arena_stats_accum_zu(&astats->resident, base_resident +
+	    (((atomic_load_zu(&arena->nactive, ATOMIC_RELAXED) +
+	    extents_npages_get(&arena->extents_dirty) +
+	    extents_npages_get(&arena->extents_muzzy)) << LG_PAGE)));
+
+	for (szind_t i = 0; i < NSIZES - NBINS; i++) {
+		uint64_t nmalloc = arena_stats_read_u64(tsdn, &arena->stats,
+		    &arena->stats.lstats[i].nmalloc);
+		arena_stats_accum_u64(&lstats[i].nmalloc, nmalloc);
+		arena_stats_accum_u64(&astats->nmalloc_large, nmalloc);
+
+		uint64_t ndalloc = arena_stats_read_u64(tsdn, &arena->stats,
+		    &arena->stats.lstats[i].ndalloc);
+		arena_stats_accum_u64(&lstats[i].ndalloc, ndalloc);
+		arena_stats_accum_u64(&astats->ndalloc_large, ndalloc);
+
+		uint64_t nrequests = arena_stats_read_u64(tsdn, &arena->stats,
+		    &arena->stats.lstats[i].nrequests);
+		arena_stats_accum_u64(&lstats[i].nrequests,
+		    nmalloc + nrequests);
+		arena_stats_accum_u64(&astats->nrequests_large,
+		    nmalloc + nrequests);
+
+		assert(nmalloc >= ndalloc);
+		assert(nmalloc - ndalloc <= SIZE_T_MAX);
+		size_t curlextents = (size_t)(nmalloc - ndalloc);
+		lstats[i].curlextents += curlextents;
+		arena_stats_accum_zu(&astats->allocated_large,
+		    curlextents * sz_index2size(NBINS + i));
+	}
+
+	arena_stats_unlock(tsdn, &arena->stats);
+
+	/* tcache_bytes counts currently cached bytes. */
+	atomic_store_zu(&astats->tcache_bytes, 0, ATOMIC_RELAXED);
+	malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx);
+	tcache_t *tcache;
+	ql_foreach(tcache, &arena->tcache_ql, link) {
+		szind_t i = 0;
+		for (; i < NBINS; i++) {
+			tcache_bin_t *tbin = tcache_small_bin_get(tcache, i);
+			arena_stats_accum_zu(&astats->tcache_bytes,
+			    tbin->ncached * sz_index2size(i));
+		}
+		for (; i < nhbins; i++) {
+			tcache_bin_t *tbin = tcache_large_bin_get(tcache, i);
+			arena_stats_accum_zu(&astats->tcache_bytes,
+			    tbin->ncached * sz_index2size(i));
+		}
 	}
-	if (chunk->ndirty != 0)
-		arena_chunk_dirty_insert(&arena->chunks_dirty, chunk);
+	malloc_mutex_prof_read(tsdn,
+	    &astats->mutex_prof_data[arena_prof_mutex_tcache_list],
+	    &arena->tcache_ql_mtx);
+	malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx);
+
+#define READ_ARENA_MUTEX_PROF_DATA(mtx, ind)				\
+    malloc_mutex_lock(tsdn, &arena->mtx);				\
+    malloc_mutex_prof_read(tsdn, &astats->mutex_prof_data[ind],		\
+        &arena->mtx);							\
+    malloc_mutex_unlock(tsdn, &arena->mtx);
+
+	/* Gather per arena mutex profiling data. */
+	READ_ARENA_MUTEX_PROF_DATA(large_mtx, arena_prof_mutex_large);
+	READ_ARENA_MUTEX_PROF_DATA(extent_avail_mtx,
+	    arena_prof_mutex_extent_avail)
+	READ_ARENA_MUTEX_PROF_DATA(extents_dirty.mtx,
+	    arena_prof_mutex_extents_dirty)
+	READ_ARENA_MUTEX_PROF_DATA(extents_muzzy.mtx,
+	    arena_prof_mutex_extents_muzzy)
+	READ_ARENA_MUTEX_PROF_DATA(extents_retained.mtx,
+	    arena_prof_mutex_extents_retained)
+	READ_ARENA_MUTEX_PROF_DATA(decay_dirty.mtx,
+	    arena_prof_mutex_decay_dirty)
+	READ_ARENA_MUTEX_PROF_DATA(decay_muzzy.mtx,
+	    arena_prof_mutex_decay_muzzy)
+	READ_ARENA_MUTEX_PROF_DATA(base->mtx,
+	    arena_prof_mutex_base)
+#undef READ_ARENA_MUTEX_PROF_DATA
+
+	nstime_copy(&astats->uptime, &arena->create_time);
+	nstime_update(&astats->uptime);
+	nstime_subtract(&astats->uptime, &arena->create_time);
+
+	for (szind_t i = 0; i < NBINS; i++) {
+		arena_bin_t *bin = &arena->bins[i];
 
-	arena_avail_tree_insert(&arena->runs_avail, arena_mapp_get(chunk,
-	    pageind));
+		malloc_mutex_lock(tsdn, &bin->lock);
+		malloc_mutex_prof_read(tsdn, &bstats[i].mutex_data, &bin->lock);
+		bstats[i].nmalloc += bin->stats.nmalloc;
+		bstats[i].ndalloc += bin->stats.ndalloc;
+		bstats[i].nrequests += bin->stats.nrequests;
+		bstats[i].curregs += bin->stats.curregs;
+		bstats[i].nfills += bin->stats.nfills;
+		bstats[i].nflushes += bin->stats.nflushes;
+		bstats[i].nslabs += bin->stats.nslabs;
+		bstats[i].reslabs += bin->stats.reslabs;
+		bstats[i].curslabs += bin->stats.curslabs;
+		malloc_mutex_unlock(tsdn, &bin->lock);
+	}
 }
 
-static void
-arena_avail_remove(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
-    size_t npages, bool maybe_adjac_pred, bool maybe_adjac_succ)
-{
-
-	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
-	    LG_PAGE));
-
-	/*
-	 * chunks_dirty is keyed by nruns_{avail,adjac}, so the chunk must be
-	 * removed and reinserted even if the run to be removed is clean.
-	 */
-	if (chunk->ndirty != 0)
-		arena_chunk_dirty_remove(&arena->chunks_dirty, chunk);
-
-	if (maybe_adjac_pred && arena_avail_adjac_pred(chunk, pageind))
-		chunk->nruns_adjac--;
-	if (maybe_adjac_succ && arena_avail_adjac_succ(chunk, pageind, npages))
-		chunk->nruns_adjac--;
-	chunk->nruns_avail--;
-	assert(chunk->nruns_avail > chunk->nruns_adjac || (chunk->nruns_avail
-	    == 0 && chunk->nruns_adjac == 0));
-
-	if (arena_mapbits_dirty_get(chunk, pageind) != 0) {
-		arena->ndirty -= npages;
-		chunk->ndirty -= npages;
+void
+arena_extents_dirty_dalloc(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extents_dalloc(tsdn, arena, r_extent_hooks, &arena->extents_dirty,
+	    extent);
+	if (arena_dirty_decay_ms_get(arena) == 0) {
+		arena_decay_dirty(tsdn, arena, false, true);
+	} else {
+		arena_background_thread_inactivity_check(tsdn, arena, false);
 	}
-	if (chunk->ndirty != 0)
-		arena_chunk_dirty_insert(&arena->chunks_dirty, chunk);
-
-	arena_avail_tree_remove(&arena->runs_avail, arena_mapp_get(chunk,
-	    pageind));
 }
 
-static inline void *
-arena_run_reg_alloc(arena_run_t *run, arena_bin_info_t *bin_info)
-{
+static void *
+arena_slab_reg_alloc(tsdn_t *tsdn, extent_t *slab,
+    const arena_bin_info_t *bin_info) {
 	void *ret;
-	unsigned regind;
-	bitmap_t *bitmap = (bitmap_t *)((uintptr_t)run +
-	    (uintptr_t)bin_info->bitmap_offset);
-
-	assert(run->nfree > 0);
-	assert(bitmap_full(bitmap, &bin_info->bitmap_info) == false);
-
-	regind = bitmap_sfu(bitmap, &bin_info->bitmap_info);
-	ret = (void *)((uintptr_t)run + (uintptr_t)bin_info->reg0_offset +
-	    (uintptr_t)(bin_info->reg_interval * regind));
-	run->nfree--;
-	if (regind == run->nextind)
-		run->nextind++;
-	assert(regind < run->nextind);
-	return (ret);
-}
-
-static inline void
-arena_run_reg_dalloc(arena_run_t *run, void *ptr)
-{
-	arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-	size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
-	size_t mapbits = arena_mapbits_get(chunk, pageind);
-	size_t binind = arena_ptr_small_binind_get(ptr, mapbits);
-	arena_bin_info_t *bin_info = &arena_bin_info[binind];
-	unsigned regind = arena_run_regind(run, bin_info, ptr);
-	bitmap_t *bitmap = (bitmap_t *)((uintptr_t)run +
-	    (uintptr_t)bin_info->bitmap_offset);
-
-	assert(run->nfree < bin_info->nregs);
-	/* Freeing an interior pointer can cause assertion failure. */
-	assert(((uintptr_t)ptr - ((uintptr_t)run +
-	    (uintptr_t)bin_info->reg0_offset)) %
-	    (uintptr_t)bin_info->reg_interval == 0);
-	assert((uintptr_t)ptr >= (uintptr_t)run +
-	    (uintptr_t)bin_info->reg0_offset);
-	/* Freeing an unallocated pointer can cause assertion failure. */
-	assert(bitmap_get(bitmap, &bin_info->bitmap_info, regind));
+	arena_slab_data_t *slab_data = extent_slab_data_get(slab);
+	size_t regind;
+
+	assert(extent_nfree_get(slab) > 0);
+	assert(!bitmap_full(slab_data->bitmap, &bin_info->bitmap_info));
 
-	bitmap_unset(bitmap, &bin_info->bitmap_info, regind);
-	run->nfree++;
+	regind = bitmap_sfu(slab_data->bitmap, &bin_info->bitmap_info);
+	ret = (void *)((uintptr_t)extent_addr_get(slab) +
+	    (uintptr_t)(bin_info->reg_size * regind));
+	extent_nfree_dec(slab);
+	return ret;
 }
 
-static inline void
-arena_run_zero(arena_chunk_t *chunk, size_t run_ind, size_t npages)
-{
+#ifndef JEMALLOC_JET
+static
+#endif
+size_t
+arena_slab_regind(extent_t *slab, szind_t binind, const void *ptr) {
+	size_t diff, regind;
 
-	VALGRIND_MAKE_MEM_UNDEFINED((void *)((uintptr_t)chunk + (run_ind <<
-	    LG_PAGE)), (npages << LG_PAGE));
-	memset((void *)((uintptr_t)chunk + (run_ind << LG_PAGE)), 0,
-	    (npages << LG_PAGE));
-}
+	/* Freeing a pointer outside the slab can cause assertion failure. */
+	assert((uintptr_t)ptr >= (uintptr_t)extent_addr_get(slab));
+	assert((uintptr_t)ptr < (uintptr_t)extent_past_get(slab));
+	/* Freeing an interior pointer can cause assertion failure. */
+	assert(((uintptr_t)ptr - (uintptr_t)extent_addr_get(slab)) %
+	    (uintptr_t)arena_bin_info[binind].reg_size == 0);
+
+	/* Avoid doing division with a variable divisor. */
+	diff = (size_t)((uintptr_t)ptr - (uintptr_t)extent_addr_get(slab));
+	switch (binind) {
+#define REGIND_bin_yes(index, reg_size)					\
+	case index:							\
+		regind = diff / (reg_size);				\
+		assert(diff == regind * (reg_size));			\
+		break;
+#define REGIND_bin_no(index, reg_size)
+#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs,		\
+    lg_delta_lookup)							\
+	REGIND_bin_##bin(index, (1U<<lg_grp) + (ndelta<<lg_delta))
+	SIZE_CLASSES
+#undef REGIND_bin_yes
+#undef REGIND_bin_no
+#undef SC
+	default: not_reached();
+	}
 
-static inline void
-arena_run_page_mark_zeroed(arena_chunk_t *chunk, size_t run_ind)
-{
+	assert(regind < arena_bin_info[binind].nregs);
 
-	VALGRIND_MAKE_MEM_DEFINED((void *)((uintptr_t)chunk + (run_ind <<
-	    LG_PAGE)), PAGE);
+	return regind;
 }
 
-static inline void
-arena_run_page_validate_zeroed(arena_chunk_t *chunk, size_t run_ind)
-{
-	size_t i;
-	UNUSED size_t *p = (size_t *)((uintptr_t)chunk + (run_ind << LG_PAGE));
+static void
+arena_slab_reg_dalloc(tsdn_t *tsdn, extent_t *slab,
+    arena_slab_data_t *slab_data, void *ptr) {
+	szind_t binind = extent_szind_get(slab);
+	const arena_bin_info_t *bin_info = &arena_bin_info[binind];
+	size_t regind = arena_slab_regind(slab, binind, ptr);
+
+	assert(extent_nfree_get(slab) < bin_info->nregs);
+	/* Freeing an unallocated pointer can cause assertion failure. */
+	assert(bitmap_get(slab_data->bitmap, &bin_info->bitmap_info, regind));
 
-	arena_run_page_mark_zeroed(chunk, run_ind);
-	for (i = 0; i < PAGE / sizeof(size_t); i++)
-		assert(p[i] == 0);
+	bitmap_unset(slab_data->bitmap, &bin_info->bitmap_info, regind);
+	extent_nfree_inc(slab);
 }
 
 static void
-arena_cactive_update(arena_t *arena, size_t add_pages, size_t sub_pages)
-{
+arena_nactive_add(arena_t *arena, size_t add_pages) {
+	atomic_fetch_add_zu(&arena->nactive, add_pages, ATOMIC_RELAXED);
+}
 
-	if (config_stats) {
-		ssize_t cactive_diff = CHUNK_CEILING((arena->nactive +
-		    add_pages) << LG_PAGE) - CHUNK_CEILING((arena->nactive -
-		    sub_pages) << LG_PAGE);
-		if (cactive_diff != 0)
-			stats_cactive_add(cactive_diff);
-	}
+static void
+arena_nactive_sub(arena_t *arena, size_t sub_pages) {
+	assert(atomic_load_zu(&arena->nactive, ATOMIC_RELAXED) >= sub_pages);
+	atomic_fetch_sub_zu(&arena->nactive, sub_pages, ATOMIC_RELAXED);
 }
 
 static void
-arena_run_split_remove(arena_t *arena, arena_chunk_t *chunk, size_t run_ind,
-    size_t flag_dirty, size_t need_pages)
-{
-	size_t total_pages, rem_pages;
-
-	total_pages = arena_mapbits_unallocated_size_get(chunk, run_ind) >>
-	    LG_PAGE;
-	assert(arena_mapbits_dirty_get(chunk, run_ind+total_pages-1) ==
-	    flag_dirty);
-	assert(need_pages <= total_pages);
-	rem_pages = total_pages - need_pages;
-
-	arena_avail_remove(arena, chunk, run_ind, total_pages, true, true);
-	arena_cactive_update(arena, need_pages, 0);
-	arena->nactive += need_pages;
-
-	/* Keep track of trailing unused pages for later use. */
-	if (rem_pages > 0) {
-		if (flag_dirty != 0) {
-			arena_mapbits_unallocated_set(chunk,
-			    run_ind+need_pages, (rem_pages << LG_PAGE),
-			    flag_dirty);
-			arena_mapbits_unallocated_set(chunk,
-			    run_ind+total_pages-1, (rem_pages << LG_PAGE),
-			    flag_dirty);
-		} else {
-			arena_mapbits_unallocated_set(chunk, run_ind+need_pages,
-			    (rem_pages << LG_PAGE),
-			    arena_mapbits_unzeroed_get(chunk,
-			    run_ind+need_pages));
-			arena_mapbits_unallocated_set(chunk,
-			    run_ind+total_pages-1, (rem_pages << LG_PAGE),
-			    arena_mapbits_unzeroed_get(chunk,
-			    run_ind+total_pages-1));
-		}
-		arena_avail_insert(arena, chunk, run_ind+need_pages, rem_pages,
-		    false, true);
+arena_large_malloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t usize) {
+	szind_t index, hindex;
+
+	cassert(config_stats);
+
+	if (usize < LARGE_MINCLASS) {
+		usize = LARGE_MINCLASS;
 	}
+	index = sz_size2index(usize);
+	hindex = (index >= NBINS) ? index - NBINS : 0;
+
+	arena_stats_add_u64(tsdn, &arena->stats,
+	    &arena->stats.lstats[hindex].nmalloc, 1);
 }
 
 static void
-arena_run_split_large_helper(arena_t *arena, arena_run_t *run, size_t size,
-    bool remove, bool zero)
-{
-	arena_chunk_t *chunk;
-	size_t flag_dirty, run_ind, need_pages, i;
+arena_large_dalloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t usize) {
+	szind_t index, hindex;
 
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-	run_ind = (unsigned)(((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE);
-	flag_dirty = arena_mapbits_dirty_get(chunk, run_ind);
-	need_pages = (size >> LG_PAGE);
-	assert(need_pages > 0);
+	cassert(config_stats);
 
-	if (remove) {
-		arena_run_split_remove(arena, chunk, run_ind, flag_dirty,
-		    need_pages);
+	if (usize < LARGE_MINCLASS) {
+		usize = LARGE_MINCLASS;
 	}
+	index = sz_size2index(usize);
+	hindex = (index >= NBINS) ? index - NBINS : 0;
 
-	if (zero) {
-		if (flag_dirty == 0) {
+	arena_stats_add_u64(tsdn, &arena->stats,
+	    &arena->stats.lstats[hindex].ndalloc, 1);
+}
+
+static void
+arena_large_ralloc_stats_update(tsdn_t *tsdn, arena_t *arena, size_t oldusize,
+    size_t usize) {
+	arena_large_dalloc_stats_update(tsdn, arena, oldusize);
+	arena_large_malloc_stats_update(tsdn, arena, usize);
+}
+
+extent_t *
+arena_extent_alloc_large(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, bool *zero) {
+	extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER;
+
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	szind_t szind = sz_size2index(usize);
+	size_t mapped_add;
+	bool commit = true;
+	extent_t *extent = extents_alloc(tsdn, arena, &extent_hooks,
+	    &arena->extents_dirty, NULL, usize, sz_large_pad, alignment, false,
+	    szind, zero, &commit);
+	if (extent == NULL) {
+		extent = extents_alloc(tsdn, arena, &extent_hooks,
+		    &arena->extents_muzzy, NULL, usize, sz_large_pad, alignment,
+		    false, szind, zero, &commit);
+	}
+	size_t size = usize + sz_large_pad;
+	if (extent == NULL) {
+		extent = extent_alloc_wrapper(tsdn, arena, &extent_hooks, NULL,
+		    usize, sz_large_pad, alignment, false, szind, zero,
+		    &commit);
+		if (config_stats) {
 			/*
-			 * The run is clean, so some pages may be zeroed (i.e.
-			 * never before touched).
+			 * extent may be NULL on OOM, but in that case
+			 * mapped_add isn't used below, so there's no need to
+			 * conditionlly set it to 0 here.
 			 */
-			for (i = 0; i < need_pages; i++) {
-				if (arena_mapbits_unzeroed_get(chunk, run_ind+i)
-				    != 0)
-					arena_run_zero(chunk, run_ind+i, 1);
-				else if (config_debug) {
-					arena_run_page_validate_zeroed(chunk,
-					    run_ind+i);
-				} else {
-					arena_run_page_mark_zeroed(chunk,
-					    run_ind+i);
-				}
+			mapped_add = size;
+		}
+	} else if (config_stats) {
+		mapped_add = 0;
+	}
+
+	if (extent != NULL) {
+		if (config_stats) {
+			arena_stats_lock(tsdn, &arena->stats);
+			arena_large_malloc_stats_update(tsdn, arena, usize);
+			if (mapped_add != 0) {
+				arena_stats_add_zu(tsdn, &arena->stats,
+				    &arena->stats.mapped, mapped_add);
 			}
-		} else {
-			/* The run is dirty, so all pages must be zeroed. */
-			arena_run_zero(chunk, run_ind, need_pages);
+			arena_stats_unlock(tsdn, &arena->stats);
 		}
-	} else {
-		VALGRIND_MAKE_MEM_UNDEFINED((void *)((uintptr_t)chunk +
-		    (run_ind << LG_PAGE)), (need_pages << LG_PAGE));
+		arena_nactive_add(arena, size >> LG_PAGE);
 	}
 
-	/*
-	 * Set the last element first, in case the run only contains one page
-	 * (i.e. both statements set the same element).
-	 */
-	arena_mapbits_large_set(chunk, run_ind+need_pages-1, 0, flag_dirty);
-	arena_mapbits_large_set(chunk, run_ind, size, flag_dirty);
+	return extent;
 }
 
-static void
-arena_run_split_large(arena_t *arena, arena_run_t *run, size_t size, bool zero)
-{
-
-	arena_run_split_large_helper(arena, run, size, true, zero);
+void
+arena_extent_dalloc_large_prep(tsdn_t *tsdn, arena_t *arena, extent_t *extent) {
+	if (config_stats) {
+		arena_stats_lock(tsdn, &arena->stats);
+		arena_large_dalloc_stats_update(tsdn, arena,
+		    extent_usize_get(extent));
+		arena_stats_unlock(tsdn, &arena->stats);
+	}
+	arena_nactive_sub(arena, extent_size_get(extent) >> LG_PAGE);
 }
 
-static void
-arena_run_init_large(arena_t *arena, arena_run_t *run, size_t size, bool zero)
-{
+void
+arena_extent_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena, extent_t *extent,
+    size_t oldusize) {
+	size_t usize = extent_usize_get(extent);
+	size_t udiff = oldusize - usize;
 
-	arena_run_split_large_helper(arena, run, size, false, zero);
+	if (config_stats) {
+		arena_stats_lock(tsdn, &arena->stats);
+		arena_large_ralloc_stats_update(tsdn, arena, oldusize, usize);
+		arena_stats_unlock(tsdn, &arena->stats);
+	}
+	arena_nactive_sub(arena, udiff >> LG_PAGE);
 }
 
-static void
-arena_run_split_small(arena_t *arena, arena_run_t *run, size_t size,
-    size_t binind)
-{
-	arena_chunk_t *chunk;
-	size_t flag_dirty, run_ind, need_pages, i;
+void
+arena_extent_ralloc_large_expand(tsdn_t *tsdn, arena_t *arena, extent_t *extent,
+    size_t oldusize) {
+	size_t usize = extent_usize_get(extent);
+	size_t udiff = usize - oldusize;
 
-	assert(binind != BININD_INVALID);
+	if (config_stats) {
+		arena_stats_lock(tsdn, &arena->stats);
+		arena_large_ralloc_stats_update(tsdn, arena, oldusize, usize);
+		arena_stats_unlock(tsdn, &arena->stats);
+	}
+	arena_nactive_add(arena, udiff >> LG_PAGE);
+}
 
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-	run_ind = (unsigned)(((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE);
-	flag_dirty = arena_mapbits_dirty_get(chunk, run_ind);
-	need_pages = (size >> LG_PAGE);
-	assert(need_pages > 0);
+static ssize_t
+arena_decay_ms_read(arena_decay_t *decay) {
+	return atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED);
+}
 
-	arena_run_split_remove(arena, chunk, run_ind, flag_dirty, need_pages);
+static void
+arena_decay_ms_write(arena_decay_t *decay, ssize_t decay_ms) {
+	atomic_store_zd(&decay->time_ms, decay_ms, ATOMIC_RELAXED);
+}
 
+static void
+arena_decay_deadline_init(arena_decay_t *decay) {
 	/*
-	 * Propagate the dirty and unzeroed flags to the allocated small run,
-	 * so that arena_dalloc_bin_run() has the ability to conditionally trim
-	 * clean pages.
-	 */
-	arena_mapbits_small_set(chunk, run_ind, 0, binind, flag_dirty);
-	/*
-	 * The first page will always be dirtied during small run
-	 * initialization, so a validation failure here would not actually
-	 * cause an observable failure.
+	 * Generate a new deadline that is uniformly random within the next
+	 * epoch after the current one.
 	 */
-	if (config_debug && flag_dirty == 0 && arena_mapbits_unzeroed_get(chunk,
-	    run_ind) == 0)
-		arena_run_page_validate_zeroed(chunk, run_ind);
-	for (i = 1; i < need_pages - 1; i++) {
-		arena_mapbits_small_set(chunk, run_ind+i, i, binind, 0);
-		if (config_debug && flag_dirty == 0 &&
-		    arena_mapbits_unzeroed_get(chunk, run_ind+i) == 0)
-			arena_run_page_validate_zeroed(chunk, run_ind+i);
-	}
-	arena_mapbits_small_set(chunk, run_ind+need_pages-1, need_pages-1,
-	    binind, flag_dirty);
-	if (config_debug && flag_dirty == 0 && arena_mapbits_unzeroed_get(chunk,
-	    run_ind+need_pages-1) == 0)
-		arena_run_page_validate_zeroed(chunk, run_ind+need_pages-1);
-	VALGRIND_MAKE_MEM_UNDEFINED((void *)((uintptr_t)chunk +
-	    (run_ind << LG_PAGE)), (need_pages << LG_PAGE));
-}
-
-static arena_chunk_t *
-arena_chunk_init_spare(arena_t *arena)
-{
-	arena_chunk_t *chunk;
-
-	assert(arena->spare != NULL);
-
-	chunk = arena->spare;
-	arena->spare = NULL;
-
-	assert(arena_mapbits_allocated_get(chunk, map_bias) == 0);
-	assert(arena_mapbits_allocated_get(chunk, chunk_npages-1) == 0);
-	assert(arena_mapbits_unallocated_size_get(chunk, map_bias) ==
-	    arena_maxclass);
-	assert(arena_mapbits_unallocated_size_get(chunk, chunk_npages-1) ==
-	    arena_maxclass);
-	assert(arena_mapbits_dirty_get(chunk, map_bias) ==
-	    arena_mapbits_dirty_get(chunk, chunk_npages-1));
-
-	return (chunk);
-}
-
-static arena_chunk_t *
-arena_chunk_init_hard(arena_t *arena)
-{
-	arena_chunk_t *chunk;
-	bool zero;
-	size_t unzeroed, i;
-
-	assert(arena->spare == NULL);
-
-	zero = false;
-	malloc_mutex_unlock(&arena->lock);
-	chunk = (arena_chunk_t *)chunk_alloc(chunksize, chunksize, false,
-	    &zero, arena->dss_prec);
-	malloc_mutex_lock(&arena->lock);
-	if (chunk == NULL)
-		return (NULL);
-	if (config_stats)
-		arena->stats.mapped += chunksize;
+	nstime_copy(&decay->deadline, &decay->epoch);
+	nstime_add(&decay->deadline, &decay->interval);
+	if (arena_decay_ms_read(decay) > 0) {
+		nstime_t jitter;
 
-	chunk->arena = arena;
+		nstime_init(&jitter, prng_range_u64(&decay->jitter_state,
+		    nstime_ns(&decay->interval)));
+		nstime_add(&decay->deadline, &jitter);
+	}
+}
 
-	/*
-	 * Claim that no pages are in use, since the header is merely overhead.
-	 */
-	chunk->ndirty = 0;
+static bool
+arena_decay_deadline_reached(const arena_decay_t *decay, const nstime_t *time) {
+	return (nstime_compare(&decay->deadline, time) <= 0);
+}
 
-	chunk->nruns_avail = 0;
-	chunk->nruns_adjac = 0;
+static size_t
+arena_decay_backlog_npages_limit(const arena_decay_t *decay) {
+	uint64_t sum;
+	size_t npages_limit_backlog;
+	unsigned i;
 
 	/*
-	 * Initialize the map to contain one maximal free untouched run.  Mark
-	 * the pages as zeroed iff chunk_alloc() returned a zeroed chunk.
-	 */
-	unzeroed = zero ? 0 : CHUNK_MAP_UNZEROED;
-	arena_mapbits_unallocated_set(chunk, map_bias, arena_maxclass,
-	    unzeroed);
-	/*
-	 * There is no need to initialize the internal page map entries unless
-	 * the chunk is not zeroed.
+	 * For each element of decay_backlog, multiply by the corresponding
+	 * fixed-point smoothstep decay factor.  Sum the products, then divide
+	 * to round down to the nearest whole number of pages.
 	 */
-	if (zero == false) {
-		VALGRIND_MAKE_MEM_UNDEFINED((void *)arena_mapp_get(chunk,
-		    map_bias+1), (size_t)((uintptr_t) arena_mapp_get(chunk,
-		    chunk_npages-1) - (uintptr_t)arena_mapp_get(chunk,
-		    map_bias+1)));
-		for (i = map_bias+1; i < chunk_npages-1; i++)
-			arena_mapbits_unzeroed_set(chunk, i, unzeroed);
-	} else {
-		VALGRIND_MAKE_MEM_DEFINED((void *)arena_mapp_get(chunk,
-		    map_bias+1), (size_t)((uintptr_t) arena_mapp_get(chunk,
-		    chunk_npages-1) - (uintptr_t)arena_mapp_get(chunk,
-		    map_bias+1)));
-		if (config_debug) {
-			for (i = map_bias+1; i < chunk_npages-1; i++) {
-				assert(arena_mapbits_unzeroed_get(chunk, i) ==
-				    unzeroed);
-			}
-		}
+	sum = 0;
+	for (i = 0; i < SMOOTHSTEP_NSTEPS; i++) {
+		sum += decay->backlog[i] * h_steps[i];
 	}
-	arena_mapbits_unallocated_set(chunk, chunk_npages-1, arena_maxclass,
-	    unzeroed);
+	npages_limit_backlog = (size_t)(sum >> SMOOTHSTEP_BFP);
 
-	return (chunk);
+	return npages_limit_backlog;
 }
 
-static arena_chunk_t *
-arena_chunk_alloc(arena_t *arena)
-{
-	arena_chunk_t *chunk;
+static void
+arena_decay_backlog_update_last(arena_decay_t *decay, size_t current_npages) {
+	size_t npages_delta = (current_npages > decay->nunpurged) ?
+	    current_npages - decay->nunpurged : 0;
+	decay->backlog[SMOOTHSTEP_NSTEPS-1] = npages_delta;
 
-	if (arena->spare != NULL)
-		chunk = arena_chunk_init_spare(arena);
-	else {
-		chunk = arena_chunk_init_hard(arena);
-		if (chunk == NULL)
-			return (NULL);
+	if (config_debug) {
+		if (current_npages > decay->ceil_npages) {
+			decay->ceil_npages = current_npages;
+		}
+		size_t npages_limit = arena_decay_backlog_npages_limit(decay);
+		assert(decay->ceil_npages >= npages_limit);
+		if (decay->ceil_npages > npages_limit) {
+			decay->ceil_npages = npages_limit;
+		}
 	}
-
-	/* Insert the run into the runs_avail tree. */
-	arena_avail_insert(arena, chunk, map_bias, chunk_npages-map_bias,
-	    false, false);
-
-	return (chunk);
 }
 
 static void
-arena_chunk_dealloc(arena_t *arena, arena_chunk_t *chunk)
-{
-	assert(arena_mapbits_allocated_get(chunk, map_bias) == 0);
-	assert(arena_mapbits_allocated_get(chunk, chunk_npages-1) == 0);
-	assert(arena_mapbits_unallocated_size_get(chunk, map_bias) ==
-	    arena_maxclass);
-	assert(arena_mapbits_unallocated_size_get(chunk, chunk_npages-1) ==
-	    arena_maxclass);
-	assert(arena_mapbits_dirty_get(chunk, map_bias) ==
-	    arena_mapbits_dirty_get(chunk, chunk_npages-1));
+arena_decay_backlog_update(arena_decay_t *decay, uint64_t nadvance_u64,
+    size_t current_npages) {
+	if (nadvance_u64 >= SMOOTHSTEP_NSTEPS) {
+		memset(decay->backlog, 0, (SMOOTHSTEP_NSTEPS-1) *
+		    sizeof(size_t));
+	} else {
+		size_t nadvance_z = (size_t)nadvance_u64;
 
-	/*
-	 * Remove run from the runs_avail tree, so that the arena does not use
-	 * it.
-	 */
-	arena_avail_remove(arena, chunk, map_bias, chunk_npages-map_bias,
-	    false, false);
+		assert((uint64_t)nadvance_z == nadvance_u64);
 
-	if (arena->spare != NULL) {
-		arena_chunk_t *spare = arena->spare;
+		memmove(decay->backlog, &decay->backlog[nadvance_z],
+		    (SMOOTHSTEP_NSTEPS - nadvance_z) * sizeof(size_t));
+		if (nadvance_z > 1) {
+			memset(&decay->backlog[SMOOTHSTEP_NSTEPS -
+			    nadvance_z], 0, (nadvance_z-1) * sizeof(size_t));
+		}
+	}
 
-		arena->spare = chunk;
-		malloc_mutex_unlock(&arena->lock);
-		chunk_dealloc((void *)spare, chunksize, true);
-		malloc_mutex_lock(&arena->lock);
-		if (config_stats)
-			arena->stats.mapped -= chunksize;
-	} else
-		arena->spare = chunk;
+	arena_decay_backlog_update_last(decay, current_npages);
 }
 
-static arena_run_t *
-arena_run_alloc_large_helper(arena_t *arena, size_t size, bool zero)
-{
-	arena_run_t *run;
-	arena_chunk_map_t *mapelm, key;
-
-	key.bits = size | CHUNK_MAP_KEY;
-	mapelm = arena_avail_tree_nsearch(&arena->runs_avail, &key);
-	if (mapelm != NULL) {
-		arena_chunk_t *run_chunk = CHUNK_ADDR2BASE(mapelm);
-		size_t pageind = (((uintptr_t)mapelm -
-		    (uintptr_t)run_chunk->map) / sizeof(arena_chunk_map_t))
-		    + map_bias;
-
-		run = (arena_run_t *)((uintptr_t)run_chunk + (pageind <<
-		    LG_PAGE));
-		arena_run_split_large(arena, run, size, zero);
-		return (run);
+static void
+arena_decay_try_purge(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, size_t current_npages, size_t npages_limit,
+    bool is_background_thread) {
+	if (current_npages > npages_limit) {
+		arena_decay_to_limit(tsdn, arena, decay, extents, false,
+		    npages_limit, is_background_thread);
 	}
-
-	return (NULL);
 }
 
-static arena_run_t *
-arena_run_alloc_large(arena_t *arena, size_t size, bool zero)
-{
-	arena_chunk_t *chunk;
-	arena_run_t *run;
+static void
+arena_decay_epoch_advance_helper(arena_decay_t *decay, const nstime_t *time,
+    size_t current_npages) {
+	assert(arena_decay_deadline_reached(decay, time));
 
-	assert(size <= arena_maxclass);
-	assert((size & PAGE_MASK) == 0);
+	nstime_t delta;
+	nstime_copy(&delta, time);
+	nstime_subtract(&delta, &decay->epoch);
 
-	/* Search the arena's chunks for the lowest best fit. */
-	run = arena_run_alloc_large_helper(arena, size, zero);
-	if (run != NULL)
-		return (run);
+	uint64_t nadvance_u64 = nstime_divide(&delta, &decay->interval);
+	assert(nadvance_u64 > 0);
 
-	/*
-	 * No usable runs.  Create a new chunk from which to allocate the run.
-	 */
-	chunk = arena_chunk_alloc(arena);
-	if (chunk != NULL) {
-		run = (arena_run_t *)((uintptr_t)chunk + (map_bias << LG_PAGE));
-		arena_run_split_large(arena, run, size, zero);
-		return (run);
-	}
+	/* Add nadvance_u64 decay intervals to epoch. */
+	nstime_copy(&delta, &decay->interval);
+	nstime_imultiply(&delta, nadvance_u64);
+	nstime_add(&decay->epoch, &delta);
 
-	/*
-	 * arena_chunk_alloc() failed, but another thread may have made
-	 * sufficient memory available while this one dropped arena->lock in
-	 * arena_chunk_alloc(), so search one more time.
-	 */
-	return (arena_run_alloc_large_helper(arena, size, zero));
+	/* Set a new deadline. */
+	arena_decay_deadline_init(decay);
+
+	/* Update the backlog. */
+	arena_decay_backlog_update(decay, nadvance_u64, current_npages);
 }
 
-static arena_run_t *
-arena_run_alloc_small_helper(arena_t *arena, size_t size, size_t binind)
-{
-	arena_run_t *run;
-	arena_chunk_map_t *mapelm, key;
+static void
+arena_decay_epoch_advance(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, const nstime_t *time, bool is_background_thread) {
+	size_t current_npages = extents_npages_get(extents);
+	arena_decay_epoch_advance_helper(decay, time, current_npages);
 
-	key.bits = size | CHUNK_MAP_KEY;
-	mapelm = arena_avail_tree_nsearch(&arena->runs_avail, &key);
-	if (mapelm != NULL) {
-		arena_chunk_t *run_chunk = CHUNK_ADDR2BASE(mapelm);
-		size_t pageind = (((uintptr_t)mapelm -
-		    (uintptr_t)run_chunk->map) / sizeof(arena_chunk_map_t))
-		    + map_bias;
+	size_t npages_limit = arena_decay_backlog_npages_limit(decay);
+	/* We may unlock decay->mtx when try_purge(). Finish logging first. */
+	decay->nunpurged = (npages_limit > current_npages) ? npages_limit :
+	    current_npages;
 
-		run = (arena_run_t *)((uintptr_t)run_chunk + (pageind <<
-		    LG_PAGE));
-		arena_run_split_small(arena, run, size, binind);
-		return (run);
+	if (!background_thread_enabled() || is_background_thread) {
+		arena_decay_try_purge(tsdn, arena, decay, extents,
+		    current_npages, npages_limit, is_background_thread);
 	}
-
-	return (NULL);
 }
 
-static arena_run_t *
-arena_run_alloc_small(arena_t *arena, size_t size, size_t binind)
-{
-	arena_chunk_t *chunk;
-	arena_run_t *run;
-
-	assert(size <= arena_maxclass);
-	assert((size & PAGE_MASK) == 0);
-	assert(binind != BININD_INVALID);
+static void
+arena_decay_reinit(arena_decay_t *decay, extents_t *extents, ssize_t decay_ms) {
+	arena_decay_ms_write(decay, decay_ms);
+	if (decay_ms > 0) {
+		nstime_init(&decay->interval, (uint64_t)decay_ms *
+		    KQU(1000000));
+		nstime_idivide(&decay->interval, SMOOTHSTEP_NSTEPS);
+	}
 
-	/* Search the arena's chunks for the lowest best fit. */
-	run = arena_run_alloc_small_helper(arena, size, binind);
-	if (run != NULL)
-		return (run);
+	nstime_init(&decay->epoch, 0);
+	nstime_update(&decay->epoch);
+	decay->jitter_state = (uint64_t)(uintptr_t)decay;
+	arena_decay_deadline_init(decay);
+	decay->nunpurged = 0;
+	memset(decay->backlog, 0, SMOOTHSTEP_NSTEPS * sizeof(size_t));
+}
 
-	/*
-	 * No usable runs.  Create a new chunk from which to allocate the run.
-	 */
-	chunk = arena_chunk_alloc(arena);
-	if (chunk != NULL) {
-		run = (arena_run_t *)((uintptr_t)chunk + (map_bias << LG_PAGE));
-		arena_run_split_small(arena, run, size, binind);
-		return (run);
+static bool
+arena_decay_init(arena_decay_t *decay, extents_t *extents, ssize_t decay_ms,
+    decay_stats_t *stats) {
+	if (config_debug) {
+		for (size_t i = 0; i < sizeof(arena_decay_t); i++) {
+			assert(((char *)decay)[i] == 0);
+		}
+		decay->ceil_npages = 0;
+	}
+	if (malloc_mutex_init(&decay->mtx, "decay", WITNESS_RANK_DECAY,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+	decay->purging = false;
+	arena_decay_reinit(decay, extents, decay_ms);
+	/* Memory is zeroed, so there is no need to clear stats. */
+	if (config_stats) {
+		decay->stats = stats;
 	}
+	return false;
+}
 
-	/*
-	 * arena_chunk_alloc() failed, but another thread may have made
-	 * sufficient memory available while this one dropped arena->lock in
-	 * arena_chunk_alloc(), so search one more time.
-	 */
-	return (arena_run_alloc_small_helper(arena, size, binind));
+static bool
+arena_decay_ms_valid(ssize_t decay_ms) {
+	if (decay_ms < -1) {
+		return false;
+	}
+	if (decay_ms == -1 || (uint64_t)decay_ms <= NSTIME_SEC_MAX *
+	    KQU(1000)) {
+		return true;
+	}
+	return false;
 }
 
-static inline void
-arena_maybe_purge(arena_t *arena)
-{
-	size_t npurgeable, threshold;
+static bool
+arena_maybe_decay(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, bool is_background_thread) {
+	malloc_mutex_assert_owner(tsdn, &decay->mtx);
+
+	/* Purge all or nothing if the option is disabled. */
+	ssize_t decay_ms = arena_decay_ms_read(decay);
+	if (decay_ms <= 0) {
+		if (decay_ms == 0) {
+			arena_decay_to_limit(tsdn, arena, decay, extents, false,
+			    0, is_background_thread);
+		}
+		return false;
+	}
+
+	nstime_t time;
+	nstime_init(&time, 0);
+	nstime_update(&time);
+	if (unlikely(!nstime_monotonic() && nstime_compare(&decay->epoch, &time)
+	    > 0)) {
+		/*
+		 * Time went backwards.  Move the epoch back in time and
+		 * generate a new deadline, with the expectation that time
+		 * typically flows forward for long enough periods of time that
+		 * epochs complete.  Unfortunately, this strategy is susceptible
+		 * to clock jitter triggering premature epoch advances, but
+		 * clock jitter estimation and compensation isn't feasible here
+		 * because calls into this code are event-driven.
+		 */
+		nstime_copy(&decay->epoch, &time);
+		arena_decay_deadline_init(decay);
+	} else {
+		/* Verify that time does not go backwards. */
+		assert(nstime_compare(&decay->epoch, &time) <= 0);
+	}
 
-	/* Don't purge if the option is disabled. */
-	if (opt_lg_dirty_mult < 0)
-		return;
-	/* Don't purge if all dirty pages are already being purged. */
-	if (arena->ndirty <= arena->npurgatory)
-		return;
-	npurgeable = arena->ndirty - arena->npurgatory;
-	threshold = (arena->nactive >> opt_lg_dirty_mult);
 	/*
-	 * Don't purge unless the number of purgeable pages exceeds the
-	 * threshold.
+	 * If the deadline has been reached, advance to the current epoch and
+	 * purge to the new limit if necessary.  Note that dirty pages created
+	 * during the current epoch are not subject to purge until a future
+	 * epoch, so as a result purging only happens during epoch advances, or
+	 * being triggered by background threads (scheduled event).
 	 */
-	if (npurgeable <= threshold)
-		return;
+	bool advance_epoch = arena_decay_deadline_reached(decay, &time);
+	if (advance_epoch) {
+		arena_decay_epoch_advance(tsdn, arena, decay, extents, &time,
+		    is_background_thread);
+	} else if (is_background_thread) {
+		arena_decay_try_purge(tsdn, arena, decay, extents,
+		    extents_npages_get(extents),
+		    arena_decay_backlog_npages_limit(decay),
+		    is_background_thread);
+	}
 
-	arena_purge(arena, false);
+	return advance_epoch;
 }
 
-static arena_chunk_t *
-chunks_dirty_iter_cb(arena_chunk_tree_t *tree, arena_chunk_t *chunk, void *arg)
-{
-       size_t *ndirty = (size_t *)arg;
+static ssize_t
+arena_decay_ms_get(arena_decay_t *decay) {
+	return arena_decay_ms_read(decay);
+}
 
-       assert(chunk->ndirty != 0);
-       *ndirty += chunk->ndirty;
-       return (NULL);
+ssize_t
+arena_dirty_decay_ms_get(arena_t *arena) {
+	return arena_decay_ms_get(&arena->decay_dirty);
 }
 
-static size_t
-arena_compute_npurgatory(arena_t *arena, bool all)
-{
-	size_t npurgatory, npurgeable;
+ssize_t
+arena_muzzy_decay_ms_get(arena_t *arena) {
+	return arena_decay_ms_get(&arena->decay_muzzy);
+}
 
+static bool
+arena_decay_ms_set(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, ssize_t decay_ms) {
+	if (!arena_decay_ms_valid(decay_ms)) {
+		return true;
+	}
+
+	malloc_mutex_lock(tsdn, &decay->mtx);
 	/*
-	 * Compute the minimum number of pages that this thread should try to
-	 * purge.
+	 * Restart decay backlog from scratch, which may cause many dirty pages
+	 * to be immediately purged.  It would conceptually be possible to map
+	 * the old backlog onto the new backlog, but there is no justification
+	 * for such complexity since decay_ms changes are intended to be
+	 * infrequent, either between the {-1, 0, >0} states, or a one-time
+	 * arbitrary change during initial arena configuration.
 	 */
-	npurgeable = arena->ndirty - arena->npurgatory;
+	arena_decay_reinit(decay, extents, decay_ms);
+	arena_maybe_decay(tsdn, arena, decay, extents, false);
+	malloc_mutex_unlock(tsdn, &decay->mtx);
 
-	if (all == false) {
-		size_t threshold = (arena->nactive >> opt_lg_dirty_mult);
+	return false;
+}
 
-		npurgatory = npurgeable - threshold;
-	} else
-		npurgatory = npurgeable;
+bool
+arena_dirty_decay_ms_set(tsdn_t *tsdn, arena_t *arena,
+    ssize_t decay_ms) {
+	return arena_decay_ms_set(tsdn, arena, &arena->decay_dirty,
+	    &arena->extents_dirty, decay_ms);
+}
 
-	return (npurgatory);
+bool
+arena_muzzy_decay_ms_set(tsdn_t *tsdn, arena_t *arena,
+    ssize_t decay_ms) {
+	return arena_decay_ms_set(tsdn, arena, &arena->decay_muzzy,
+	    &arena->extents_muzzy, decay_ms);
 }
 
-static void
-arena_chunk_stash_dirty(arena_t *arena, arena_chunk_t *chunk, bool all,
-    arena_chunk_mapelms_t *mapelms)
-{
-	size_t pageind, npages;
+static size_t
+arena_stash_decayed(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, size_t npages_limit,
+    extent_list_t *decay_extents) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
 
-	/*
-	 * Temporarily allocate free dirty runs within chunk.  If all is false,
-	 * only operate on dirty runs that are fragments; otherwise operate on
-	 * all dirty runs.
-	 */
-	for (pageind = map_bias; pageind < chunk_npages; pageind += npages) {
-		arena_chunk_map_t *mapelm = arena_mapp_get(chunk, pageind);
-		if (arena_mapbits_allocated_get(chunk, pageind) == 0) {
-			size_t run_size =
-			    arena_mapbits_unallocated_size_get(chunk, pageind);
-
-			npages = run_size >> LG_PAGE;
-			assert(pageind + npages <= chunk_npages);
-			assert(arena_mapbits_dirty_get(chunk, pageind) ==
-			    arena_mapbits_dirty_get(chunk, pageind+npages-1));
-
-			if (arena_mapbits_dirty_get(chunk, pageind) != 0 &&
-			    (all || arena_avail_adjac(chunk, pageind,
-			    npages))) {
-				arena_run_t *run = (arena_run_t *)((uintptr_t)
-				    chunk + (uintptr_t)(pageind << LG_PAGE));
-
-				arena_run_split_large(arena, run, run_size,
-				    false);
-				/* Append to list for later processing. */
-				ql_elm_new(mapelm, u.ql_link);
-				ql_tail_insert(mapelms, mapelm, u.ql_link);
-			}
-		} else {
-			/* Skip run. */
-			if (arena_mapbits_large_get(chunk, pageind) != 0) {
-				npages = arena_mapbits_large_size_get(chunk,
-				    pageind) >> LG_PAGE;
-			} else {
-				size_t binind;
-				arena_bin_info_t *bin_info;
-				arena_run_t *run = (arena_run_t *)((uintptr_t)
-				    chunk + (uintptr_t)(pageind << LG_PAGE));
-
-				assert(arena_mapbits_small_runind_get(chunk,
-				    pageind) == 0);
-				binind = arena_bin_index(arena, run->bin);
-				bin_info = &arena_bin_info[binind];
-				npages = bin_info->run_size >> LG_PAGE;
-			}
-		}
+	/* Stash extents according to npages_limit. */
+	size_t nstashed = 0;
+	extent_t *extent;
+	while ((extent = extents_evict(tsdn, arena, r_extent_hooks, extents,
+	    npages_limit)) != NULL) {
+		extent_list_append(decay_extents, extent);
+		nstashed += extent_size_get(extent) >> LG_PAGE;
 	}
-	assert(pageind == chunk_npages);
-	assert(chunk->ndirty == 0 || all == false);
-	assert(chunk->nruns_adjac == 0);
+	return nstashed;
 }
 
 static size_t
-arena_chunk_purge_stashed(arena_t *arena, arena_chunk_t *chunk,
-    arena_chunk_mapelms_t *mapelms)
-{
-	size_t npurged, pageind, npages, nmadvise;
-	arena_chunk_map_t *mapelm;
-
-	malloc_mutex_unlock(&arena->lock);
-	if (config_stats)
+arena_decay_stashed(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, arena_decay_t *decay, extents_t *extents,
+    bool all, extent_list_t *decay_extents, bool is_background_thread) {
+	UNUSED size_t nmadvise, nunmapped;
+	size_t npurged;
+
+	if (config_stats) {
 		nmadvise = 0;
+		nunmapped = 0;
+	}
 	npurged = 0;
-	ql_foreach(mapelm, mapelms, u.ql_link) {
-		bool unzeroed;
-		size_t flag_unzeroed, i;
-
-		pageind = (((uintptr_t)mapelm - (uintptr_t)chunk->map) /
-		    sizeof(arena_chunk_map_t)) + map_bias;
-		npages = arena_mapbits_large_size_get(chunk, pageind) >>
-		    LG_PAGE;
-		assert(pageind + npages <= chunk_npages);
-		unzeroed = pages_purge((void *)((uintptr_t)chunk + (pageind <<
-		    LG_PAGE)), (npages << LG_PAGE));
-		flag_unzeroed = unzeroed ? CHUNK_MAP_UNZEROED : 0;
-		/*
-		 * Set the unzeroed flag for all pages, now that pages_purge()
-		 * has returned whether the pages were zeroed as a side effect
-		 * of purging.  This chunk map modification is safe even though
-		 * the arena mutex isn't currently owned by this thread,
-		 * because the run is marked as allocated, thus protecting it
-		 * from being modified by any other thread.  As long as these
-		 * writes don't perturb the first and last elements'
-		 * CHUNK_MAP_ALLOCATED bits, behavior is well defined.
-		 */
-		for (i = 0; i < npages; i++) {
-			arena_mapbits_unzeroed_set(chunk, pageind+i,
-			    flag_unzeroed);
+
+	ssize_t muzzy_decay_ms = arena_muzzy_decay_ms_get(arena);
+	for (extent_t *extent = extent_list_first(decay_extents); extent !=
+	    NULL; extent = extent_list_first(decay_extents)) {
+		if (config_stats) {
+			nmadvise++;
 		}
+		size_t npages = extent_size_get(extent) >> LG_PAGE;
 		npurged += npages;
-		if (config_stats)
-			nmadvise++;
+		extent_list_remove(decay_extents, extent);
+		switch (extents_state_get(extents)) {
+		case extent_state_active:
+			not_reached();
+		case extent_state_dirty:
+			if (!all && muzzy_decay_ms != 0 &&
+			    !extent_purge_lazy_wrapper(tsdn, arena,
+			    r_extent_hooks, extent, 0,
+			    extent_size_get(extent))) {
+				extents_dalloc(tsdn, arena, r_extent_hooks,
+				    &arena->extents_muzzy, extent);
+				arena_background_thread_inactivity_check(tsdn,
+				    arena, is_background_thread);
+				break;
+			}
+			/* Fall through. */
+		case extent_state_muzzy:
+			extent_dalloc_wrapper(tsdn, arena, r_extent_hooks,
+			    extent);
+			if (config_stats) {
+				nunmapped += npages;
+			}
+			break;
+		case extent_state_retained:
+		default:
+			not_reached();
+		}
 	}
-	malloc_mutex_lock(&arena->lock);
-	if (config_stats)
-		arena->stats.nmadvise += nmadvise;
 
-	return (npurged);
+	if (config_stats) {
+		arena_stats_lock(tsdn, &arena->stats);
+		arena_stats_add_u64(tsdn, &arena->stats, &decay->stats->npurge,
+		    1);
+		arena_stats_add_u64(tsdn, &arena->stats,
+		    &decay->stats->nmadvise, nmadvise);
+		arena_stats_add_u64(tsdn, &arena->stats, &decay->stats->purged,
+		    npurged);
+		arena_stats_sub_zu(tsdn, &arena->stats, &arena->stats.mapped,
+		    nunmapped << LG_PAGE);
+		arena_stats_unlock(tsdn, &arena->stats);
+	}
+
+	return npurged;
 }
 
+/*
+ * npages_limit: Decay as many dirty extents as possible without violating the
+ * invariant: (extents_npages_get(extents) >= npages_limit)
+ */
 static void
-arena_chunk_unstash_purged(arena_t *arena, arena_chunk_t *chunk,
-    arena_chunk_mapelms_t *mapelms)
-{
-	arena_chunk_map_t *mapelm;
-	size_t pageind;
-
-	/* Deallocate runs. */
-	for (mapelm = ql_first(mapelms); mapelm != NULL;
-	    mapelm = ql_first(mapelms)) {
-		arena_run_t *run;
-
-		pageind = (((uintptr_t)mapelm - (uintptr_t)chunk->map) /
-		    sizeof(arena_chunk_map_t)) + map_bias;
-		run = (arena_run_t *)((uintptr_t)chunk + (uintptr_t)(pageind <<
-		    LG_PAGE));
-		ql_remove(mapelms, mapelm, u.ql_link);
-		arena_run_dalloc(arena, run, false, true);
+arena_decay_to_limit(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, bool all, size_t npages_limit,
+    bool is_background_thread) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 1);
+	malloc_mutex_assert_owner(tsdn, &decay->mtx);
+
+	if (decay->purging) {
+		return;
 	}
-}
+	decay->purging = true;
+	malloc_mutex_unlock(tsdn, &decay->mtx);
 
-static inline size_t
-arena_chunk_purge(arena_t *arena, arena_chunk_t *chunk, bool all)
-{
-	size_t npurged;
-	arena_chunk_mapelms_t mapelms;
+	extent_hooks_t *extent_hooks = extent_hooks_get(arena);
 
-	ql_new(&mapelms);
+	extent_list_t decay_extents;
+	extent_list_init(&decay_extents);
 
-	/*
-	 * If chunk is the spare, temporarily re-allocate it, 1) so that its
-	 * run is reinserted into runs_avail, and 2) so that it cannot be
-	 * completely discarded by another thread while arena->lock is dropped
-	 * by this thread.  Note that the arena_run_dalloc() call will
-	 * implicitly deallocate the chunk, so no explicit action is required
-	 * in this function to deallocate the chunk.
-	 *
-	 * Note that once a chunk contains dirty pages, it cannot again contain
-	 * a single run unless 1) it is a dirty run, or 2) this function purges
-	 * dirty pages and causes the transition to a single clean run.  Thus
-	 * (chunk == arena->spare) is possible, but it is not possible for
-	 * this function to be called on the spare unless it contains a dirty
-	 * run.
-	 */
-	if (chunk == arena->spare) {
-		assert(arena_mapbits_dirty_get(chunk, map_bias) != 0);
-		assert(arena_mapbits_dirty_get(chunk, chunk_npages-1) != 0);
-
-		arena_chunk_alloc(arena);
+	size_t npurge = arena_stash_decayed(tsdn, arena, &extent_hooks, extents,
+	    npages_limit, &decay_extents);
+	if (npurge != 0) {
+		UNUSED size_t npurged = arena_decay_stashed(tsdn, arena,
+		    &extent_hooks, decay, extents, all, &decay_extents,
+		    is_background_thread);
+		assert(npurged == npurge);
 	}
 
-	if (config_stats)
-		arena->stats.purged += chunk->ndirty;
-
-	/*
-	 * Operate on all dirty runs if there is no clean/dirty run
-	 * fragmentation.
-	 */
-	if (chunk->nruns_adjac == 0)
-		all = true;
-
-	arena_chunk_stash_dirty(arena, chunk, all, &mapelms);
-	npurged = arena_chunk_purge_stashed(arena, chunk, &mapelms);
-	arena_chunk_unstash_purged(arena, chunk, &mapelms);
-
-	return (npurged);
+	malloc_mutex_lock(tsdn, &decay->mtx);
+	decay->purging = false;
 }
 
-static void
-arena_purge(arena_t *arena, bool all)
-{
-	arena_chunk_t *chunk;
-	size_t npurgatory;
-	if (config_debug) {
-		size_t ndirty = 0;
+static bool
+arena_decay_impl(tsdn_t *tsdn, arena_t *arena, arena_decay_t *decay,
+    extents_t *extents, bool is_background_thread, bool all) {
+	if (all) {
+		malloc_mutex_lock(tsdn, &decay->mtx);
+		arena_decay_to_limit(tsdn, arena, decay, extents, all, 0,
+		    is_background_thread);
+		malloc_mutex_unlock(tsdn, &decay->mtx);
 
-		arena_chunk_dirty_iter(&arena->chunks_dirty, NULL,
-		    chunks_dirty_iter_cb, (void *)&ndirty);
-		assert(ndirty == arena->ndirty);
+		return false;
 	}
-	assert(arena->ndirty > arena->npurgatory || all);
-	assert((arena->nactive >> opt_lg_dirty_mult) < (arena->ndirty -
-	    arena->npurgatory) || all);
 
-	if (config_stats)
-		arena->stats.npurge++;
+	if (malloc_mutex_trylock(tsdn, &decay->mtx)) {
+		/* No need to wait if another thread is in progress. */
+		return true;
+	}
 
-	/*
-	 * Add the minimum number of pages this thread should try to purge to
-	 * arena->npurgatory.  This will keep multiple threads from racing to
-	 * reduce ndirty below the threshold.
-	 */
-	npurgatory = arena_compute_npurgatory(arena, all);
-	arena->npurgatory += npurgatory;
+	bool epoch_advanced = arena_maybe_decay(tsdn, arena, decay, extents,
+	    is_background_thread);
+	size_t npages_new;
+	if (epoch_advanced) {
+		/* Backlog is updated on epoch advance. */
+		npages_new = decay->backlog[SMOOTHSTEP_NSTEPS-1];
+	}
+	malloc_mutex_unlock(tsdn, &decay->mtx);
 
-	while (npurgatory > 0) {
-		size_t npurgeable, npurged, nunpurged;
+	if (have_background_thread && background_thread_enabled() &&
+	    epoch_advanced && !is_background_thread) {
+		background_thread_interval_check(tsdn, arena, decay, npages_new);
+	}
 
-		/* Get next chunk with dirty pages. */
-		chunk = arena_chunk_dirty_first(&arena->chunks_dirty);
-		if (chunk == NULL) {
-			/*
-			 * This thread was unable to purge as many pages as
-			 * originally intended, due to races with other threads
-			 * that either did some of the purging work, or re-used
-			 * dirty pages.
-			 */
-			arena->npurgatory -= npurgatory;
-			return;
-		}
-		npurgeable = chunk->ndirty;
-		assert(npurgeable != 0);
+	return false;
+}
 
-		if (npurgeable > npurgatory && chunk->nruns_adjac == 0) {
-			/*
-			 * This thread will purge all the dirty pages in chunk,
-			 * so set npurgatory to reflect this thread's intent to
-			 * purge the pages.  This tends to reduce the chances
-			 * of the following scenario:
-			 *
-			 * 1) This thread sets arena->npurgatory such that
-			 *    (arena->ndirty - arena->npurgatory) is at the
-			 *    threshold.
-			 * 2) This thread drops arena->lock.
-			 * 3) Another thread causes one or more pages to be
-			 *    dirtied, and immediately determines that it must
-			 *    purge dirty pages.
-			 *
-			 * If this scenario *does* play out, that's okay,
-			 * because all of the purging work being done really
-			 * needs to happen.
-			 */
-			arena->npurgatory += npurgeable - npurgatory;
-			npurgatory = npurgeable;
-		}
+static bool
+arena_decay_dirty(tsdn_t *tsdn, arena_t *arena, bool is_background_thread,
+    bool all) {
+	return arena_decay_impl(tsdn, arena, &arena->decay_dirty,
+	    &arena->extents_dirty, is_background_thread, all);
+}
 
-		/*
-		 * Keep track of how many pages are purgeable, versus how many
-		 * actually get purged, and adjust counters accordingly.
-		 */
-		arena->npurgatory -= npurgeable;
-		npurgatory -= npurgeable;
-		npurged = arena_chunk_purge(arena, chunk, all);
-		nunpurged = npurgeable - npurged;
-		arena->npurgatory += nunpurged;
-		npurgatory += nunpurged;
-	}
+static bool
+arena_decay_muzzy(tsdn_t *tsdn, arena_t *arena, bool is_background_thread,
+    bool all) {
+	return arena_decay_impl(tsdn, arena, &arena->decay_muzzy,
+	    &arena->extents_muzzy, is_background_thread, all);
 }
 
 void
-arena_purge_all(arena_t *arena)
-{
-
-	malloc_mutex_lock(&arena->lock);
-	arena_purge(arena, true);
-	malloc_mutex_unlock(&arena->lock);
+arena_decay(tsdn_t *tsdn, arena_t *arena, bool is_background_thread, bool all) {
+	if (arena_decay_dirty(tsdn, arena, is_background_thread, all)) {
+		return;
+	}
+	arena_decay_muzzy(tsdn, arena, is_background_thread, all);
 }
 
 static void
-arena_run_coalesce(arena_t *arena, arena_chunk_t *chunk, size_t *p_size,
-    size_t *p_run_ind, size_t *p_run_pages, size_t flag_dirty)
-{
-	size_t size = *p_size;
-	size_t run_ind = *p_run_ind;
-	size_t run_pages = *p_run_pages;
-
-	/* Try to coalesce forward. */
-	if (run_ind + run_pages < chunk_npages &&
-	    arena_mapbits_allocated_get(chunk, run_ind+run_pages) == 0 &&
-	    arena_mapbits_dirty_get(chunk, run_ind+run_pages) == flag_dirty) {
-		size_t nrun_size = arena_mapbits_unallocated_size_get(chunk,
-		    run_ind+run_pages);
-		size_t nrun_pages = nrun_size >> LG_PAGE;
-
-		/*
-		 * Remove successor from runs_avail; the coalesced run is
-		 * inserted later.
-		 */
-		assert(arena_mapbits_unallocated_size_get(chunk,
-		    run_ind+run_pages+nrun_pages-1) == nrun_size);
-		assert(arena_mapbits_dirty_get(chunk,
-		    run_ind+run_pages+nrun_pages-1) == flag_dirty);
-		arena_avail_remove(arena, chunk, run_ind+run_pages, nrun_pages,
-		    false, true);
+arena_slab_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *slab) {
+	arena_nactive_sub(arena, extent_size_get(slab) >> LG_PAGE);
 
-		size += nrun_size;
-		run_pages += nrun_pages;
-
-		arena_mapbits_unallocated_size_set(chunk, run_ind, size);
-		arena_mapbits_unallocated_size_set(chunk, run_ind+run_pages-1,
-		    size);
-	}
-
-	/* Try to coalesce backward. */
-	if (run_ind > map_bias && arena_mapbits_allocated_get(chunk,
-	    run_ind-1) == 0 && arena_mapbits_dirty_get(chunk, run_ind-1) ==
-	    flag_dirty) {
-		size_t prun_size = arena_mapbits_unallocated_size_get(chunk,
-		    run_ind-1);
-		size_t prun_pages = prun_size >> LG_PAGE;
-
-		run_ind -= prun_pages;
+	extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER;
+	arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, slab);
+}
 
-		/*
-		 * Remove predecessor from runs_avail; the coalesced run is
-		 * inserted later.
-		 */
-		assert(arena_mapbits_unallocated_size_get(chunk, run_ind) ==
-		    prun_size);
-		assert(arena_mapbits_dirty_get(chunk, run_ind) == flag_dirty);
-		arena_avail_remove(arena, chunk, run_ind, prun_pages, true,
-		    false);
+static void
+arena_bin_slabs_nonfull_insert(arena_bin_t *bin, extent_t *slab) {
+	assert(extent_nfree_get(slab) > 0);
+	extent_heap_insert(&bin->slabs_nonfull, slab);
+}
 
-		size += prun_size;
-		run_pages += prun_pages;
+static void
+arena_bin_slabs_nonfull_remove(arena_bin_t *bin, extent_t *slab) {
+	extent_heap_remove(&bin->slabs_nonfull, slab);
+}
 
-		arena_mapbits_unallocated_size_set(chunk, run_ind, size);
-		arena_mapbits_unallocated_size_set(chunk, run_ind+run_pages-1,
-		    size);
+static extent_t *
+arena_bin_slabs_nonfull_tryget(arena_bin_t *bin) {
+	extent_t *slab = extent_heap_remove_first(&bin->slabs_nonfull);
+	if (slab == NULL) {
+		return NULL;
 	}
-
-	*p_size = size;
-	*p_run_ind = run_ind;
-	*p_run_pages = run_pages;
+	if (config_stats) {
+		bin->stats.reslabs++;
+	}
+	return slab;
 }
 
 static void
-arena_run_dalloc(arena_t *arena, arena_run_t *run, bool dirty, bool cleaned)
-{
-	arena_chunk_t *chunk;
-	size_t size, run_ind, run_pages, flag_dirty;
-
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-	run_ind = (size_t)(((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE);
-	assert(run_ind >= map_bias);
-	assert(run_ind < chunk_npages);
-	if (arena_mapbits_large_get(chunk, run_ind) != 0) {
-		size = arena_mapbits_large_size_get(chunk, run_ind);
-		assert(size == PAGE ||
-		    arena_mapbits_large_size_get(chunk,
-		    run_ind+(size>>LG_PAGE)-1) == 0);
-	} else {
-		size_t binind = arena_bin_index(arena, run->bin);
-		arena_bin_info_t *bin_info = &arena_bin_info[binind];
-		size = bin_info->run_size;
-	}
-	run_pages = (size >> LG_PAGE);
-	arena_cactive_update(arena, 0, run_pages);
-	arena->nactive -= run_pages;
-
+arena_bin_slabs_full_insert(arena_t *arena, arena_bin_t *bin, extent_t *slab) {
+	assert(extent_nfree_get(slab) == 0);
 	/*
-	 * The run is dirty if the caller claims to have dirtied it, as well as
-	 * if it was already dirty before being allocated and the caller
-	 * doesn't claim to have cleaned it.
+	 *  Tracking extents is required by arena_reset, which is not allowed
+	 *  for auto arenas.  Bypass this step to avoid touching the extent
+	 *  linkage (often results in cache misses) for auto arenas.
 	 */
-	assert(arena_mapbits_dirty_get(chunk, run_ind) ==
-	    arena_mapbits_dirty_get(chunk, run_ind+run_pages-1));
-	if (cleaned == false && arena_mapbits_dirty_get(chunk, run_ind) != 0)
-		dirty = true;
-	flag_dirty = dirty ? CHUNK_MAP_DIRTY : 0;
-
-	/* Mark pages as unallocated in the chunk map. */
-	if (dirty) {
-		arena_mapbits_unallocated_set(chunk, run_ind, size,
-		    CHUNK_MAP_DIRTY);
-		arena_mapbits_unallocated_set(chunk, run_ind+run_pages-1, size,
-		    CHUNK_MAP_DIRTY);
-	} else {
-		arena_mapbits_unallocated_set(chunk, run_ind, size,
-		    arena_mapbits_unzeroed_get(chunk, run_ind));
-		arena_mapbits_unallocated_set(chunk, run_ind+run_pages-1, size,
-		    arena_mapbits_unzeroed_get(chunk, run_ind+run_pages-1));
+	if (arena_is_auto(arena)) {
+		return;
 	}
+	extent_list_append(&bin->slabs_full, slab);
+}
 
-	arena_run_coalesce(arena, chunk, &size, &run_ind, &run_pages,
-	    flag_dirty);
-
-	/* Insert into runs_avail, now that coalescing is complete. */
-	assert(arena_mapbits_unallocated_size_get(chunk, run_ind) ==
-	    arena_mapbits_unallocated_size_get(chunk, run_ind+run_pages-1));
-	assert(arena_mapbits_dirty_get(chunk, run_ind) ==
-	    arena_mapbits_dirty_get(chunk, run_ind+run_pages-1));
-	arena_avail_insert(arena, chunk, run_ind, run_pages, true, true);
-
-	/* Deallocate chunk if it is now completely unused. */
-	if (size == arena_maxclass) {
-		assert(run_ind == map_bias);
-		assert(run_pages == (arena_maxclass >> LG_PAGE));
-		arena_chunk_dealloc(arena, chunk);
+static void
+arena_bin_slabs_full_remove(arena_t *arena, arena_bin_t *bin, extent_t *slab) {
+	if (arena_is_auto(arena)) {
+		return;
 	}
+	extent_list_remove(&bin->slabs_full, slab);
+}
 
+void
+arena_reset(tsd_t *tsd, arena_t *arena) {
 	/*
-	 * It is okay to do dirty page processing here even if the chunk was
-	 * deallocated above, since in that case it is the spare.  Waiting
-	 * until after possible chunk deallocation to do dirty processing
-	 * allows for an old spare to be fully deallocated, thus decreasing the
-	 * chances of spuriously crossing the dirty page purging threshold.
+	 * Locking in this function is unintuitive.  The caller guarantees that
+	 * no concurrent operations are happening in this arena, but there are
+	 * still reasons that some locking is necessary:
+	 *
+	 * - Some of the functions in the transitive closure of calls assume
+	 *   appropriate locks are held, and in some cases these locks are
+	 *   temporarily dropped to avoid lock order reversal or deadlock due to
+	 *   reentry.
+	 * - mallctl("epoch", ...) may concurrently refresh stats.  While
+	 *   strictly speaking this is a "concurrent operation", disallowing
+	 *   stats refreshes would impose an inconvenient burden.
 	 */
-	if (dirty)
-		arena_maybe_purge(arena);
-}
 
-static void
-arena_run_trim_head(arena_t *arena, arena_chunk_t *chunk, arena_run_t *run,
-    size_t oldsize, size_t newsize)
-{
-	size_t pageind = ((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE;
-	size_t head_npages = (oldsize - newsize) >> LG_PAGE;
-	size_t flag_dirty = arena_mapbits_dirty_get(chunk, pageind);
+	/* Large allocations. */
+	malloc_mutex_lock(tsd_tsdn(tsd), &arena->large_mtx);
 
-	assert(oldsize > newsize);
+	for (extent_t *extent = extent_list_first(&arena->large); extent !=
+	    NULL; extent = extent_list_first(&arena->large)) {
+		void *ptr = extent_base_get(extent);
+		size_t usize;
 
-	/*
-	 * Update the chunk map so that arena_run_dalloc() can treat the
-	 * leading run as separately allocated.  Set the last element of each
-	 * run first, in case of single-page runs.
-	 */
-	assert(arena_mapbits_large_size_get(chunk, pageind) == oldsize);
-	arena_mapbits_large_set(chunk, pageind+head_npages-1, 0, flag_dirty);
-	arena_mapbits_large_set(chunk, pageind, oldsize-newsize, flag_dirty);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &arena->large_mtx);
+		alloc_ctx_t alloc_ctx;
+		rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+		rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+		assert(alloc_ctx.szind != NSIZES);
 
-	if (config_debug) {
-		UNUSED size_t tail_npages = newsize >> LG_PAGE;
-		assert(arena_mapbits_large_size_get(chunk,
-		    pageind+head_npages+tail_npages-1) == 0);
-		assert(arena_mapbits_dirty_get(chunk,
-		    pageind+head_npages+tail_npages-1) == flag_dirty);
+		if (config_stats || (config_prof && opt_prof)) {
+			usize = sz_index2size(alloc_ctx.szind);
+			assert(usize == isalloc(tsd_tsdn(tsd), ptr));
+		}
+		/* Remove large allocation from prof sample set. */
+		if (config_prof && opt_prof) {
+			prof_free(tsd, ptr, usize, &alloc_ctx);
+		}
+		large_dalloc(tsd_tsdn(tsd), extent);
+		malloc_mutex_lock(tsd_tsdn(tsd), &arena->large_mtx);
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), &arena->large_mtx);
+
+	/* Bins. */
+	for (unsigned i = 0; i < NBINS; i++) {
+		extent_t *slab;
+		arena_bin_t *bin = &arena->bins[i];
+		malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		if (bin->slabcur != NULL) {
+			slab = bin->slabcur;
+			bin->slabcur = NULL;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+			arena_slab_dalloc(tsd_tsdn(tsd), arena, slab);
+			malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		}
+		while ((slab = extent_heap_remove_first(&bin->slabs_nonfull)) !=
+		    NULL) {
+			malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+			arena_slab_dalloc(tsd_tsdn(tsd), arena, slab);
+			malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		}
+		for (slab = extent_list_first(&bin->slabs_full); slab != NULL;
+		    slab = extent_list_first(&bin->slabs_full)) {
+			arena_bin_slabs_full_remove(arena, bin, slab);
+			malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+			arena_slab_dalloc(tsd_tsdn(tsd), arena, slab);
+			malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		}
+		if (config_stats) {
+			bin->stats.curregs = 0;
+			bin->stats.curslabs = 0;
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
 	}
-	arena_mapbits_large_set(chunk, pageind+head_npages, newsize,
-	    flag_dirty);
 
-	arena_run_dalloc(arena, run, false, false);
+	atomic_store_zu(&arena->nactive, 0, ATOMIC_RELAXED);
 }
 
 static void
-arena_run_trim_tail(arena_t *arena, arena_chunk_t *chunk, arena_run_t *run,
-    size_t oldsize, size_t newsize, bool dirty)
-{
-	size_t pageind = ((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE;
-	size_t head_npages = newsize >> LG_PAGE;
-	size_t flag_dirty = arena_mapbits_dirty_get(chunk, pageind);
-
-	assert(oldsize > newsize);
-
+arena_destroy_retained(tsdn_t *tsdn, arena_t *arena) {
 	/*
-	 * Update the chunk map so that arena_run_dalloc() can treat the
-	 * trailing run as separately allocated.  Set the last element of each
-	 * run first, in case of single-page runs.
+	 * Iterate over the retained extents and destroy them.  This gives the
+	 * extent allocator underlying the extent hooks an opportunity to unmap
+	 * all retained memory without having to keep its own metadata
+	 * structures.  In practice, virtual memory for dss-allocated extents is
+	 * leaked here, so best practice is to avoid dss for arenas to be
+	 * destroyed, or provide custom extent hooks that track retained
+	 * dss-based extents for later reuse.
 	 */
-	assert(arena_mapbits_large_size_get(chunk, pageind) == oldsize);
-	arena_mapbits_large_set(chunk, pageind+head_npages-1, 0, flag_dirty);
-	arena_mapbits_large_set(chunk, pageind, newsize, flag_dirty);
-
-	if (config_debug) {
-		UNUSED size_t tail_npages = (oldsize - newsize) >> LG_PAGE;
-		assert(arena_mapbits_large_size_get(chunk,
-		    pageind+head_npages+tail_npages-1) == 0);
-		assert(arena_mapbits_dirty_get(chunk,
-		    pageind+head_npages+tail_npages-1) == flag_dirty);
+	extent_hooks_t *extent_hooks = extent_hooks_get(arena);
+	extent_t *extent;
+	while ((extent = extents_evict(tsdn, arena, &extent_hooks,
+	    &arena->extents_retained, 0)) != NULL) {
+		extent_destroy_wrapper(tsdn, arena, &extent_hooks, extent);
 	}
-	arena_mapbits_large_set(chunk, pageind+head_npages, oldsize-newsize,
-	    flag_dirty);
-
-	arena_run_dalloc(arena, (arena_run_t *)((uintptr_t)run + newsize),
-	    dirty, false);
 }
 
-static arena_run_t *
-arena_bin_runs_first(arena_bin_t *bin)
-{
-	arena_chunk_map_t *mapelm = arena_run_tree_first(&bin->runs);
-	if (mapelm != NULL) {
-		arena_chunk_t *chunk;
-		size_t pageind;
-		arena_run_t *run;
-
-		chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(mapelm);
-		pageind = ((((uintptr_t)mapelm - (uintptr_t)chunk->map) /
-		    sizeof(arena_chunk_map_t))) + map_bias;
-		run = (arena_run_t *)((uintptr_t)chunk + (uintptr_t)((pageind -
-		    arena_mapbits_small_runind_get(chunk, pageind)) <<
-		    LG_PAGE));
-		return (run);
-	}
+void
+arena_destroy(tsd_t *tsd, arena_t *arena) {
+	assert(base_ind_get(arena->base) >= narenas_auto);
+	assert(arena_nthreads_get(arena, false) == 0);
+	assert(arena_nthreads_get(arena, true) == 0);
 
-	return (NULL);
-}
+	/*
+	 * No allocations have occurred since arena_reset() was called.
+	 * Furthermore, the caller (arena_i_destroy_ctl()) purged all cached
+	 * extents, so only retained extents may remain.
+	 */
+	assert(extents_npages_get(&arena->extents_dirty) == 0);
+	assert(extents_npages_get(&arena->extents_muzzy) == 0);
 
-static void
-arena_bin_runs_insert(arena_bin_t *bin, arena_run_t *run)
-{
-	arena_chunk_t *chunk = CHUNK_ADDR2BASE(run);
-	size_t pageind = ((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE;
-	arena_chunk_map_t *mapelm = arena_mapp_get(chunk, pageind);
+	/* Deallocate retained memory. */
+	arena_destroy_retained(tsd_tsdn(tsd), arena);
 
-	assert(arena_run_tree_search(&bin->runs, mapelm) == NULL);
+	/*
+	 * Remove the arena pointer from the arenas array.  We rely on the fact
+	 * that there is no way for the application to get a dirty read from the
+	 * arenas array unless there is an inherent race in the application
+	 * involving access of an arena being concurrently destroyed.  The
+	 * application must synchronize knowledge of the arena's validity, so as
+	 * long as we use an atomic write to update the arenas array, the
+	 * application will get a clean read any time after it synchronizes
+	 * knowledge that the arena is no longer valid.
+	 */
+	arena_set(base_ind_get(arena->base), NULL);
 
-	arena_run_tree_insert(&bin->runs, mapelm);
+	/*
+	 * Destroy the base allocator, which manages all metadata ever mapped by
+	 * this arena.
+	 */
+	base_delete(tsd_tsdn(tsd), arena->base);
 }
 
-static void
-arena_bin_runs_remove(arena_bin_t *bin, arena_run_t *run)
-{
-	arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-	size_t pageind = ((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE;
-	arena_chunk_map_t *mapelm = arena_mapp_get(chunk, pageind);
+static extent_t *
+arena_slab_alloc_hard(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, const arena_bin_info_t *bin_info,
+    szind_t szind) {
+	extent_t *slab;
+	bool zero, commit;
 
-	assert(arena_run_tree_search(&bin->runs, mapelm) != NULL);
-
-	arena_run_tree_remove(&bin->runs, mapelm);
-}
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
 
-static arena_run_t *
-arena_bin_nonfull_run_tryget(arena_bin_t *bin)
-{
-	arena_run_t *run = arena_bin_runs_first(bin);
-	if (run != NULL) {
-		arena_bin_runs_remove(bin, run);
-		if (config_stats)
-			bin->stats.reruns++;
+	zero = false;
+	commit = true;
+	slab = extent_alloc_wrapper(tsdn, arena, r_extent_hooks, NULL,
+	    bin_info->slab_size, 0, PAGE, true, szind, &zero, &commit);
+
+	if (config_stats && slab != NULL) {
+		arena_stats_mapped_add(tsdn, &arena->stats,
+		    bin_info->slab_size);
+	}
+
+	return slab;
+}
+
+static extent_t *
+arena_slab_alloc(tsdn_t *tsdn, arena_t *arena, szind_t binind,
+    const arena_bin_info_t *bin_info) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER;
+	szind_t szind = sz_size2index(bin_info->reg_size);
+	bool zero = false;
+	bool commit = true;
+	extent_t *slab = extents_alloc(tsdn, arena, &extent_hooks,
+	    &arena->extents_dirty, NULL, bin_info->slab_size, 0, PAGE, true,
+	    binind, &zero, &commit);
+	if (slab == NULL) {
+		slab = extents_alloc(tsdn, arena, &extent_hooks,
+		    &arena->extents_muzzy, NULL, bin_info->slab_size, 0, PAGE,
+		    true, binind, &zero, &commit);
+	}
+	if (slab == NULL) {
+		slab = arena_slab_alloc_hard(tsdn, arena, &extent_hooks,
+		    bin_info, szind);
+		if (slab == NULL) {
+			return NULL;
+		}
 	}
-	return (run);
+	assert(extent_slab_get(slab));
+
+	/* Initialize slab internals. */
+	arena_slab_data_t *slab_data = extent_slab_data_get(slab);
+	extent_nfree_set(slab, bin_info->nregs);
+	bitmap_init(slab_data->bitmap, &bin_info->bitmap_info, false);
+
+	arena_nactive_add(arena, extent_size_get(slab) >> LG_PAGE);
+
+	return slab;
 }
 
-static arena_run_t *
-arena_bin_nonfull_run_get(arena_t *arena, arena_bin_t *bin)
-{
-	arena_run_t *run;
-	size_t binind;
-	arena_bin_info_t *bin_info;
+static extent_t *
+arena_bin_nonfull_slab_get(tsdn_t *tsdn, arena_t *arena, arena_bin_t *bin,
+    szind_t binind) {
+	extent_t *slab;
+	const arena_bin_info_t *bin_info;
 
-	/* Look for a usable run. */
-	run = arena_bin_nonfull_run_tryget(bin);
-	if (run != NULL)
-		return (run);
-	/* No existing runs have any space available. */
+	/* Look for a usable slab. */
+	slab = arena_bin_slabs_nonfull_tryget(bin);
+	if (slab != NULL) {
+		return slab;
+	}
+	/* No existing slabs have any space available. */
 
-	binind = arena_bin_index(arena, bin);
 	bin_info = &arena_bin_info[binind];
 
-	/* Allocate a new run. */
-	malloc_mutex_unlock(&bin->lock);
+	/* Allocate a new slab. */
+	malloc_mutex_unlock(tsdn, &bin->lock);
 	/******************************/
-	malloc_mutex_lock(&arena->lock);
-	run = arena_run_alloc_small(arena, bin_info->run_size, binind);
-	if (run != NULL) {
-		bitmap_t *bitmap = (bitmap_t *)((uintptr_t)run +
-		    (uintptr_t)bin_info->bitmap_offset);
-
-		/* Initialize run internals. */
-		run->bin = bin;
-		run->nextind = 0;
-		run->nfree = bin_info->nregs;
-		bitmap_init(bitmap, &bin_info->bitmap_info);
-	}
-	malloc_mutex_unlock(&arena->lock);
+	slab = arena_slab_alloc(tsdn, arena, binind, bin_info);
 	/********************************/
-	malloc_mutex_lock(&bin->lock);
-	if (run != NULL) {
+	malloc_mutex_lock(tsdn, &bin->lock);
+	if (slab != NULL) {
 		if (config_stats) {
-			bin->stats.nruns++;
-			bin->stats.curruns++;
+			bin->stats.nslabs++;
+			bin->stats.curslabs++;
 		}
-		return (run);
+		return slab;
 	}
 
 	/*
-	 * arena_run_alloc_small() failed, but another thread may have made
+	 * arena_slab_alloc() failed, but another thread may have made
 	 * sufficient memory available while this one dropped bin->lock above,
 	 * so search one more time.
 	 */
-	run = arena_bin_nonfull_run_tryget(bin);
-	if (run != NULL)
-		return (run);
+	slab = arena_bin_slabs_nonfull_tryget(bin);
+	if (slab != NULL) {
+		return slab;
+	}
 
-	return (NULL);
+	return NULL;
 }
 
-/* Re-fill bin->runcur, then call arena_run_reg_alloc(). */
+/* Re-fill bin->slabcur, then call arena_slab_reg_alloc(). */
 static void *
-arena_bin_malloc_hard(arena_t *arena, arena_bin_t *bin)
-{
-	void *ret;
-	size_t binind;
-	arena_bin_info_t *bin_info;
-	arena_run_t *run;
+arena_bin_malloc_hard(tsdn_t *tsdn, arena_t *arena, arena_bin_t *bin,
+    szind_t binind) {
+	const arena_bin_info_t *bin_info;
+	extent_t *slab;
 
-	binind = arena_bin_index(arena, bin);
 	bin_info = &arena_bin_info[binind];
-	bin->runcur = NULL;
-	run = arena_bin_nonfull_run_get(arena, bin);
-	if (bin->runcur != NULL && bin->runcur->nfree > 0) {
+	if (!arena_is_auto(arena) && bin->slabcur != NULL) {
+		arena_bin_slabs_full_insert(arena, bin, bin->slabcur);
+		bin->slabcur = NULL;
+	}
+	slab = arena_bin_nonfull_slab_get(tsdn, arena, bin, binind);
+	if (bin->slabcur != NULL) {
 		/*
-		 * Another thread updated runcur while this one ran without the
-		 * bin lock in arena_bin_nonfull_run_get().
+		 * Another thread updated slabcur while this one ran without the
+		 * bin lock in arena_bin_nonfull_slab_get().
 		 */
-		assert(bin->runcur->nfree > 0);
-		ret = arena_run_reg_alloc(bin->runcur, bin_info);
-		if (run != NULL) {
-			arena_chunk_t *chunk;
-
-			/*
-			 * arena_run_alloc_small() may have allocated run, or
-			 * it may have pulled run from the bin's run tree.
-			 * Therefore it is unsafe to make any assumptions about
-			 * how run has previously been used, and
-			 * arena_bin_lower_run() must be called, as if a region
-			 * were just deallocated from the run.
-			 */
-			chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
-			if (run->nfree == bin_info->nregs)
-				arena_dalloc_bin_run(arena, chunk, run, bin);
-			else
-				arena_bin_lower_run(arena, chunk, run, bin);
+		if (extent_nfree_get(bin->slabcur) > 0) {
+			void *ret = arena_slab_reg_alloc(tsdn, bin->slabcur,
+			    bin_info);
+			if (slab != NULL) {
+				/*
+				 * arena_slab_alloc() may have allocated slab,
+				 * or it may have been pulled from
+				 * slabs_nonfull.  Therefore it is unsafe to
+				 * make any assumptions about how slab has
+				 * previously been used, and
+				 * arena_bin_lower_slab() must be called, as if
+				 * a region were just deallocated from the slab.
+				 */
+				if (extent_nfree_get(slab) == bin_info->nregs) {
+					arena_dalloc_bin_slab(tsdn, arena, slab,
+					    bin);
+				} else {
+					arena_bin_lower_slab(tsdn, arena, slab,
+					    bin);
+				}
+			}
+			return ret;
 		}
-		return (ret);
-	}
 
-	if (run == NULL)
-		return (NULL);
+		arena_bin_slabs_full_insert(arena, bin, bin->slabcur);
+		bin->slabcur = NULL;
+	}
 
-	bin->runcur = run;
+	if (slab == NULL) {
+		return NULL;
+	}
+	bin->slabcur = slab;
 
-	assert(bin->runcur->nfree > 0);
+	assert(extent_nfree_get(bin->slabcur) > 0);
 
-	return (arena_run_reg_alloc(bin->runcur, bin_info));
+	return arena_slab_reg_alloc(tsdn, slab, bin_info);
 }
 
 void
-arena_tcache_fill_small(arena_t *arena, tcache_bin_t *tbin, size_t binind,
-    uint64_t prof_accumbytes)
-{
+arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache,
+    tcache_bin_t *tbin, szind_t binind, uint64_t prof_accumbytes) {
 	unsigned i, nfill;
 	arena_bin_t *bin;
-	arena_run_t *run;
-	void *ptr;
 
 	assert(tbin->ncached == 0);
 
-	if (config_prof && arena_prof_accum(arena, prof_accumbytes))
-		prof_idump();
+	if (config_prof && arena_prof_accum(tsdn, arena, prof_accumbytes)) {
+		prof_idump(tsdn);
+	}
 	bin = &arena->bins[binind];
-	malloc_mutex_lock(&bin->lock);
+	malloc_mutex_lock(tsdn, &bin->lock);
 	for (i = 0, nfill = (tcache_bin_info[binind].ncached_max >>
-	    tbin->lg_fill_div); i < nfill; i++) {
-		if ((run = bin->runcur) != NULL && run->nfree > 0)
-			ptr = arena_run_reg_alloc(run, &arena_bin_info[binind]);
-		else
-			ptr = arena_bin_malloc_hard(arena, bin);
-		if (ptr == NULL)
+	    tcache->lg_fill_div[binind]); i < nfill; i++) {
+		extent_t *slab;
+		void *ptr;
+		if ((slab = bin->slabcur) != NULL && extent_nfree_get(slab) >
+		    0) {
+			ptr = arena_slab_reg_alloc(tsdn, slab,
+			    &arena_bin_info[binind]);
+		} else {
+			ptr = arena_bin_malloc_hard(tsdn, arena, bin, binind);
+		}
+		if (ptr == NULL) {
+			/*
+			 * OOM.  tbin->avail isn't yet filled down to its first
+			 * element, so the successful allocations (if any) must
+			 * be moved just before tbin->avail before bailing out.
+			 */
+			if (i > 0) {
+				memmove(tbin->avail - i, tbin->avail - nfill,
+				    i * sizeof(void *));
+			}
 			break;
-		if (config_fill && opt_junk) {
+		}
+		if (config_fill && unlikely(opt_junk_alloc)) {
 			arena_alloc_junk_small(ptr, &arena_bin_info[binind],
 			    true);
 		}
 		/* Insert such that low regions get used first. */
-		tbin->avail[nfill - 1 - i] = ptr;
+		*(tbin->avail - nfill + i) = ptr;
 	}
 	if (config_stats) {
-		bin->stats.allocated += i * arena_bin_info[binind].reg_size;
 		bin->stats.nmalloc += i;
 		bin->stats.nrequests += tbin->tstats.nrequests;
+		bin->stats.curregs += i;
 		bin->stats.nfills++;
 		tbin->tstats.nrequests = 0;
 	}
-	malloc_mutex_unlock(&bin->lock);
+	malloc_mutex_unlock(tsdn, &bin->lock);
 	tbin->ncached = i;
+	arena_decay_tick(tsdn, arena);
 }
 
 void
-arena_alloc_junk_small(void *ptr, arena_bin_info_t *bin_info, bool zero)
-{
-
-	if (zero) {
-		size_t redzone_size = bin_info->redzone_size;
-		memset((void *)((uintptr_t)ptr - redzone_size), 0xa5,
-		    redzone_size);
-		memset((void *)((uintptr_t)ptr + bin_info->reg_size), 0xa5,
-		    redzone_size);
-	} else {
-		memset((void *)((uintptr_t)ptr - bin_info->redzone_size), 0xa5,
-		    bin_info->reg_interval);
+arena_alloc_junk_small(void *ptr, const arena_bin_info_t *bin_info, bool zero) {
+	if (!zero) {
+		memset(ptr, JEMALLOC_ALLOC_JUNK, bin_info->reg_size);
 	}
 }
 
-#ifdef JEMALLOC_JET
-#undef arena_redzone_corruption
-#define	arena_redzone_corruption JEMALLOC_N(arena_redzone_corruption_impl)
-#endif
-static void
-arena_redzone_corruption(void *ptr, size_t usize, bool after,
-    size_t offset, uint8_t byte)
-{
-
-	malloc_printf("<jemalloc>: Corrupt redzone %zu byte%s %s %p "
-	    "(size %zu), byte=%#x\n", offset, (offset == 1) ? "" : "s",
-	    after ? "after" : "before", ptr, usize, byte);
-}
-#ifdef JEMALLOC_JET
-#undef arena_redzone_corruption
-#define	arena_redzone_corruption JEMALLOC_N(arena_redzone_corruption)
-arena_redzone_corruption_t *arena_redzone_corruption =
-    JEMALLOC_N(arena_redzone_corruption_impl);
-#endif
-
 static void
-arena_redzones_validate(void *ptr, arena_bin_info_t *bin_info, bool reset)
-{
-	size_t size = bin_info->reg_size;
-	size_t redzone_size = bin_info->redzone_size;
-	size_t i;
-	bool error = false;
-
-	for (i = 1; i <= redzone_size; i++) {
-		uint8_t *byte = (uint8_t *)((uintptr_t)ptr - i);
-		if (*byte != 0xa5) {
-			error = true;
-			arena_redzone_corruption(ptr, size, false, i, *byte);
-			if (reset)
-				*byte = 0xa5;
-		}
-	}
-	for (i = 0; i < redzone_size; i++) {
-		uint8_t *byte = (uint8_t *)((uintptr_t)ptr + size + i);
-		if (*byte != 0xa5) {
-			error = true;
-			arena_redzone_corruption(ptr, size, true, i, *byte);
-			if (reset)
-				*byte = 0xa5;
-		}
-	}
-	if (opt_abort && error)
-		abort();
+arena_dalloc_junk_small_impl(void *ptr, const arena_bin_info_t *bin_info) {
+	memset(ptr, JEMALLOC_FREE_JUNK, bin_info->reg_size);
 }
+arena_dalloc_junk_small_t *JET_MUTABLE arena_dalloc_junk_small =
+    arena_dalloc_junk_small_impl;
 
-#ifdef JEMALLOC_JET
-#undef arena_dalloc_junk_small
-#define	arena_dalloc_junk_small JEMALLOC_N(arena_dalloc_junk_small_impl)
-#endif
-void
-arena_dalloc_junk_small(void *ptr, arena_bin_info_t *bin_info)
-{
-	size_t redzone_size = bin_info->redzone_size;
-
-	arena_redzones_validate(ptr, bin_info, false);
-	memset((void *)((uintptr_t)ptr - redzone_size), 0x5a,
-	    bin_info->reg_interval);
-}
-#ifdef JEMALLOC_JET
-#undef arena_dalloc_junk_small
-#define	arena_dalloc_junk_small JEMALLOC_N(arena_dalloc_junk_small)
-arena_dalloc_junk_small_t *arena_dalloc_junk_small =
-    JEMALLOC_N(arena_dalloc_junk_small_impl);
-#endif
-
-void
-arena_quarantine_junk_small(void *ptr, size_t usize)
-{
-	size_t binind;
-	arena_bin_info_t *bin_info;
-	cassert(config_fill);
-	assert(opt_junk);
-	assert(opt_quarantine);
-	assert(usize <= SMALL_MAXCLASS);
-
-	binind = SMALL_SIZE2BIN(usize);
-	bin_info = &arena_bin_info[binind];
-	arena_redzones_validate(ptr, bin_info, true);
-}
-
-void *
-arena_malloc_small(arena_t *arena, size_t size, bool zero)
-{
+static void *
+arena_malloc_small(tsdn_t *tsdn, arena_t *arena, szind_t binind, bool zero) {
 	void *ret;
 	arena_bin_t *bin;
-	arena_run_t *run;
-	size_t binind;
+	size_t usize;
+	extent_t *slab;
 
-	binind = SMALL_SIZE2BIN(size);
 	assert(binind < NBINS);
 	bin = &arena->bins[binind];
-	size = arena_bin_info[binind].reg_size;
+	usize = sz_index2size(binind);
 
-	malloc_mutex_lock(&bin->lock);
-	if ((run = bin->runcur) != NULL && run->nfree > 0)
-		ret = arena_run_reg_alloc(run, &arena_bin_info[binind]);
-	else
-		ret = arena_bin_malloc_hard(arena, bin);
+	malloc_mutex_lock(tsdn, &bin->lock);
+	if ((slab = bin->slabcur) != NULL && extent_nfree_get(slab) > 0) {
+		ret = arena_slab_reg_alloc(tsdn, slab, &arena_bin_info[binind]);
+	} else {
+		ret = arena_bin_malloc_hard(tsdn, arena, bin, binind);
+	}
 
 	if (ret == NULL) {
-		malloc_mutex_unlock(&bin->lock);
-		return (NULL);
+		malloc_mutex_unlock(tsdn, &bin->lock);
+		return NULL;
 	}
 
 	if (config_stats) {
-		bin->stats.allocated += size;
 		bin->stats.nmalloc++;
 		bin->stats.nrequests++;
+		bin->stats.curregs++;
+	}
+	malloc_mutex_unlock(tsdn, &bin->lock);
+	if (config_prof && arena_prof_accum(tsdn, arena, usize)) {
+		prof_idump(tsdn);
 	}
-	malloc_mutex_unlock(&bin->lock);
-	if (config_prof && isthreaded == false && arena_prof_accum(arena, size))
-		prof_idump();
 
-	if (zero == false) {
+	if (!zero) {
 		if (config_fill) {
-			if (opt_junk) {
+			if (unlikely(opt_junk_alloc)) {
 				arena_alloc_junk_small(ret,
 				    &arena_bin_info[binind], false);
-			} else if (opt_zero)
-				memset(ret, 0, size);
+			} else if (unlikely(opt_zero)) {
+				memset(ret, 0, usize);
+			}
 		}
-		VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
 	} else {
-		if (config_fill && opt_junk) {
+		if (config_fill && unlikely(opt_junk_alloc)) {
 			arena_alloc_junk_small(ret, &arena_bin_info[binind],
 			    true);
 		}
-		VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
-		memset(ret, 0, size);
+		memset(ret, 0, usize);
 	}
 
-	return (ret);
+	arena_decay_tick(tsdn, arena);
+	return ret;
 }
 
 void *
-arena_malloc_large(arena_t *arena, size_t size, bool zero)
-{
-	void *ret;
-	UNUSED bool idump;
+arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind,
+    bool zero) {
+	assert(!tsdn_null(tsdn) || arena != NULL);
 
-	/* Large allocation. */
-	size = PAGE_CEILING(size);
-	malloc_mutex_lock(&arena->lock);
-	ret = (void *)arena_run_alloc_large(arena, size, zero);
-	if (ret == NULL) {
-		malloc_mutex_unlock(&arena->lock);
-		return (NULL);
+	if (likely(!tsdn_null(tsdn))) {
+		arena = arena_choose(tsdn_tsd(tsdn), arena);
 	}
-	if (config_stats) {
-		arena->stats.nmalloc_large++;
-		arena->stats.nrequests_large++;
-		arena->stats.allocated_large += size;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nmalloc++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nrequests++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].curruns++;
-	}
-	if (config_prof)
-		idump = arena_prof_accum_locked(arena, size);
-	malloc_mutex_unlock(&arena->lock);
-	if (config_prof && idump)
-		prof_idump();
-
-	if (zero == false) {
-		if (config_fill) {
-			if (opt_junk)
-				memset(ret, 0xa5, size);
-			else if (opt_zero)
-				memset(ret, 0, size);
-		}
+	if (unlikely(arena == NULL)) {
+		return NULL;
 	}
 
-	return (ret);
+	if (likely(size <= SMALL_MAXCLASS)) {
+		return arena_malloc_small(tsdn, arena, ind, zero);
+	}
+	return large_malloc(tsdn, arena, sz_index2size(ind), zero);
 }
 
-/* Only handles large allocations that require more than page alignment. */
 void *
-arena_palloc(arena_t *arena, size_t size, size_t alignment, bool zero)
-{
+arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero, tcache_t *tcache) {
 	void *ret;
-	size_t alloc_size, leadsize, trailsize;
-	arena_run_t *run;
-	arena_chunk_t *chunk;
 
-	assert((size & PAGE_MASK) == 0);
+	if (usize <= SMALL_MAXCLASS && (alignment < PAGE || (alignment == PAGE
+	    && (usize & PAGE_MASK) == 0))) {
+		/* Small; alignment doesn't require special slab placement. */
+		ret = arena_malloc(tsdn, arena, usize, sz_size2index(usize),
+		    zero, tcache, true);
+	} else {
+		if (likely(alignment <= CACHELINE)) {
+			ret = large_malloc(tsdn, arena, usize, zero);
+		} else {
+			ret = large_palloc(tsdn, arena, usize, alignment, zero);
+		}
+	}
+	return ret;
+}
 
-	alignment = PAGE_CEILING(alignment);
-	alloc_size = size + alignment - PAGE;
+void
+arena_prof_promote(tsdn_t *tsdn, const void *ptr, size_t usize) {
+	cassert(config_prof);
+	assert(ptr != NULL);
+	assert(isalloc(tsdn, ptr) == LARGE_MINCLASS);
+	assert(usize <= SMALL_MAXCLASS);
 
-	malloc_mutex_lock(&arena->lock);
-	run = arena_run_alloc_large(arena, alloc_size, false);
-	if (run == NULL) {
-		malloc_mutex_unlock(&arena->lock);
-		return (NULL);
-	}
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
 
-	leadsize = ALIGNMENT_CEILING((uintptr_t)run, alignment) -
-	    (uintptr_t)run;
-	assert(alloc_size >= leadsize + size);
-	trailsize = alloc_size - leadsize - size;
-	ret = (void *)((uintptr_t)run + leadsize);
-	if (leadsize != 0) {
-		arena_run_trim_head(arena, chunk, run, alloc_size, alloc_size -
-		    leadsize);
-	}
-	if (trailsize != 0) {
-		arena_run_trim_tail(arena, chunk, ret, size + trailsize, size,
-		    false);
-	}
-	arena_run_init_large(arena, (arena_run_t *)ret, size, zero);
+	extent_t *extent = rtree_extent_read(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true);
+	arena_t *arena = extent_arena_get(extent);
 
-	if (config_stats) {
-		arena->stats.nmalloc_large++;
-		arena->stats.nrequests_large++;
-		arena->stats.allocated_large += size;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nmalloc++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nrequests++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].curruns++;
-	}
-	malloc_mutex_unlock(&arena->lock);
+	szind_t szind = sz_size2index(usize);
+	extent_szind_set(extent, szind);
+	rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr,
+	    szind, false);
 
-	if (config_fill && zero == false) {
-		if (opt_junk)
-			memset(ret, 0xa5, size);
-		else if (opt_zero)
-			memset(ret, 0, size);
-	}
-	return (ret);
-}
+	prof_accum_cancel(tsdn, &arena->prof_accum, usize);
 
-void
-arena_prof_promoted(const void *ptr, size_t size)
-{
-	arena_chunk_t *chunk;
-	size_t pageind, binind;
+	assert(isalloc(tsdn, ptr) == usize);
+}
 
+static size_t
+arena_prof_demote(tsdn_t *tsdn, extent_t *extent, const void *ptr) {
 	cassert(config_prof);
 	assert(ptr != NULL);
-	assert(CHUNK_ADDR2BASE(ptr) != ptr);
-	assert(isalloc(ptr, false) == PAGE);
-	assert(isalloc(ptr, true) == PAGE);
-	assert(size <= SMALL_MAXCLASS);
-
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-	pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
-	binind = SMALL_SIZE2BIN(size);
-	assert(binind < NBINS);
-	arena_mapbits_large_binind_set(chunk, pageind, binind);
 
-	assert(isalloc(ptr, false) == PAGE);
-	assert(isalloc(ptr, true) == size);
+	extent_szind_set(extent, NBINS);
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx, (uintptr_t)ptr,
+	    NBINS, false);
+
+	assert(isalloc(tsdn, ptr) == LARGE_MINCLASS);
+
+	return LARGE_MINCLASS;
+}
+
+void
+arena_dalloc_promoted(tsdn_t *tsdn, void *ptr, tcache_t *tcache,
+    bool slow_path) {
+	cassert(config_prof);
+	assert(opt_prof);
+
+	extent_t *extent = iealloc(tsdn, ptr);
+	size_t usize = arena_prof_demote(tsdn, extent, ptr);
+	if (usize <= tcache_maxclass) {
+		tcache_dalloc_large(tsdn_tsd(tsdn), tcache, ptr,
+		    sz_size2index(usize), slow_path);
+	} else {
+		large_dalloc(tsdn, extent);
+	}
 }
 
 static void
-arena_dissociate_bin_run(arena_chunk_t *chunk, arena_run_t *run,
-    arena_bin_t *bin)
-{
-
-	/* Dissociate run from bin. */
-	if (run == bin->runcur)
-		bin->runcur = NULL;
-	else {
-		size_t binind = arena_bin_index(chunk->arena, bin);
-		arena_bin_info_t *bin_info = &arena_bin_info[binind];
-
-		if (bin_info->nregs != 1) {
-			/*
-			 * This block's conditional is necessary because if the
-			 * run only contains one region, then it never gets
-			 * inserted into the non-full runs tree.
-			 */
-			arena_bin_runs_remove(bin, run);
+arena_dissociate_bin_slab(arena_t *arena, extent_t *slab, arena_bin_t *bin) {
+	/* Dissociate slab from bin. */
+	if (slab == bin->slabcur) {
+		bin->slabcur = NULL;
+	} else {
+		szind_t binind = extent_szind_get(slab);
+		const arena_bin_info_t *bin_info = &arena_bin_info[binind];
+
+		/*
+		 * The following block's conditional is necessary because if the
+		 * slab only contains one region, then it never gets inserted
+		 * into the non-full slabs heap.
+		 */
+		if (bin_info->nregs == 1) {
+			arena_bin_slabs_full_remove(arena, bin, slab);
+		} else {
+			arena_bin_slabs_nonfull_remove(bin, slab);
 		}
 	}
 }
 
 static void
-arena_dalloc_bin_run(arena_t *arena, arena_chunk_t *chunk, arena_run_t *run,
-    arena_bin_t *bin)
-{
-	size_t binind;
-	arena_bin_info_t *bin_info;
-	size_t npages, run_ind, past;
-
-	assert(run != bin->runcur);
-	assert(arena_run_tree_search(&bin->runs,
-	    arena_mapp_get(chunk, ((uintptr_t)run-(uintptr_t)chunk)>>LG_PAGE))
-	    == NULL);
-
-	binind = arena_bin_index(chunk->arena, run->bin);
-	bin_info = &arena_bin_info[binind];
+arena_dalloc_bin_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab,
+    arena_bin_t *bin) {
+	assert(slab != bin->slabcur);
 
-	malloc_mutex_unlock(&bin->lock);
+	malloc_mutex_unlock(tsdn, &bin->lock);
 	/******************************/
-	npages = bin_info->run_size >> LG_PAGE;
-	run_ind = (size_t)(((uintptr_t)run - (uintptr_t)chunk) >> LG_PAGE);
-	past = (size_t)(PAGE_CEILING((uintptr_t)run +
-	    (uintptr_t)bin_info->reg0_offset + (uintptr_t)(run->nextind *
-	    bin_info->reg_interval - bin_info->redzone_size) -
-	    (uintptr_t)chunk) >> LG_PAGE);
-	malloc_mutex_lock(&arena->lock);
-
-	/*
-	 * If the run was originally clean, and some pages were never touched,
-	 * trim the clean pages before deallocating the dirty portion of the
-	 * run.
-	 */
-	assert(arena_mapbits_dirty_get(chunk, run_ind) ==
-	    arena_mapbits_dirty_get(chunk, run_ind+npages-1));
-	if (arena_mapbits_dirty_get(chunk, run_ind) == 0 && past - run_ind <
-	    npages) {
-		/* Trim clean pages.  Convert to large run beforehand. */
-		assert(npages > 0);
-		arena_mapbits_large_set(chunk, run_ind, bin_info->run_size, 0);
-		arena_mapbits_large_set(chunk, run_ind+npages-1, 0, 0);
-		arena_run_trim_tail(arena, chunk, run, (npages << LG_PAGE),
-		    ((past - run_ind) << LG_PAGE), false);
-		/* npages = past - run_ind; */
-	}
-	arena_run_dalloc(arena, run, true, false);
-	malloc_mutex_unlock(&arena->lock);
+	arena_slab_dalloc(tsdn, arena, slab);
 	/****************************/
-	malloc_mutex_lock(&bin->lock);
-	if (config_stats)
-		bin->stats.curruns--;
+	malloc_mutex_lock(tsdn, &bin->lock);
+	if (config_stats) {
+		bin->stats.curslabs--;
+	}
 }
 
 static void
-arena_bin_lower_run(arena_t *arena, arena_chunk_t *chunk, arena_run_t *run,
-    arena_bin_t *bin)
-{
+arena_bin_lower_slab(tsdn_t *tsdn, arena_t *arena, extent_t *slab,
+    arena_bin_t *bin) {
+	assert(extent_nfree_get(slab) > 0);
 
 	/*
-	 * Make sure that if bin->runcur is non-NULL, it refers to the lowest
-	 * non-full run.  It is okay to NULL runcur out rather than proactively
-	 * keeping it pointing at the lowest non-full run.
+	 * Make sure that if bin->slabcur is non-NULL, it refers to the
+	 * oldest/lowest non-full slab.  It is okay to NULL slabcur out rather
+	 * than proactively keeping it pointing at the oldest/lowest non-full
+	 * slab.
 	 */
-	if ((uintptr_t)run < (uintptr_t)bin->runcur) {
-		/* Switch runcur. */
-		if (bin->runcur->nfree > 0)
-			arena_bin_runs_insert(bin, bin->runcur);
-		bin->runcur = run;
-		if (config_stats)
-			bin->stats.reruns++;
-	} else
-		arena_bin_runs_insert(bin, run);
+	if (bin->slabcur != NULL && extent_snad_comp(bin->slabcur, slab) > 0) {
+		/* Switch slabcur. */
+		if (extent_nfree_get(bin->slabcur) > 0) {
+			arena_bin_slabs_nonfull_insert(bin, bin->slabcur);
+		} else {
+			arena_bin_slabs_full_insert(arena, bin, bin->slabcur);
+		}
+		bin->slabcur = slab;
+		if (config_stats) {
+			bin->stats.reslabs++;
+		}
+	} else {
+		arena_bin_slabs_nonfull_insert(bin, slab);
+	}
 }
 
-void
-arena_dalloc_bin_locked(arena_t *arena, arena_chunk_t *chunk, void *ptr,
-    arena_chunk_map_t *mapelm)
-{
-	size_t pageind;
-	arena_run_t *run;
-	arena_bin_t *bin;
-	arena_bin_info_t *bin_info;
-	size_t size, binind;
-
-	pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
-	run = (arena_run_t *)((uintptr_t)chunk + (uintptr_t)((pageind -
-	    arena_mapbits_small_runind_get(chunk, pageind)) << LG_PAGE));
-	bin = run->bin;
-	binind = arena_ptr_small_binind_get(ptr, mapelm->bits);
-	bin_info = &arena_bin_info[binind];
-	if (config_fill || config_stats)
-		size = bin_info->reg_size;
-
-	if (config_fill && opt_junk)
+static void
+arena_dalloc_bin_locked_impl(tsdn_t *tsdn, arena_t *arena, extent_t *slab,
+    void *ptr, bool junked) {
+	arena_slab_data_t *slab_data = extent_slab_data_get(slab);
+	szind_t binind = extent_szind_get(slab);
+	arena_bin_t *bin = &arena->bins[binind];
+	const arena_bin_info_t *bin_info = &arena_bin_info[binind];
+
+	if (!junked && config_fill && unlikely(opt_junk_free)) {
 		arena_dalloc_junk_small(ptr, bin_info);
+	}
 
-	arena_run_reg_dalloc(run, ptr);
-	if (run->nfree == bin_info->nregs) {
-		arena_dissociate_bin_run(chunk, run, bin);
-		arena_dalloc_bin_run(arena, chunk, run, bin);
-	} else if (run->nfree == 1 && run != bin->runcur)
-		arena_bin_lower_run(arena, chunk, run, bin);
+	arena_slab_reg_dalloc(tsdn, slab, slab_data, ptr);
+	unsigned nfree = extent_nfree_get(slab);
+	if (nfree == bin_info->nregs) {
+		arena_dissociate_bin_slab(arena, slab, bin);
+		arena_dalloc_bin_slab(tsdn, arena, slab, bin);
+	} else if (nfree == 1 && slab != bin->slabcur) {
+		arena_bin_slabs_full_remove(arena, bin, slab);
+		arena_bin_lower_slab(tsdn, arena, slab, bin);
+	}
 
 	if (config_stats) {
-		bin->stats.allocated -= size;
 		bin->stats.ndalloc++;
+		bin->stats.curregs--;
 	}
 }
 
 void
-arena_dalloc_bin(arena_t *arena, arena_chunk_t *chunk, void *ptr,
-    size_t pageind, arena_chunk_map_t *mapelm)
-{
-	arena_run_t *run;
-	arena_bin_t *bin;
-
-	run = (arena_run_t *)((uintptr_t)chunk + (uintptr_t)((pageind -
-	    arena_mapbits_small_runind_get(chunk, pageind)) << LG_PAGE));
-	bin = run->bin;
-	malloc_mutex_lock(&bin->lock);
-	arena_dalloc_bin_locked(arena, chunk, ptr, mapelm);
-	malloc_mutex_unlock(&bin->lock);
-}
-
-void
-arena_dalloc_small(arena_t *arena, arena_chunk_t *chunk, void *ptr,
-    size_t pageind)
-{
-	arena_chunk_map_t *mapelm;
-
-	if (config_debug) {
-		/* arena_ptr_small_binind_get() does extra sanity checking. */
-		assert(arena_ptr_small_binind_get(ptr, arena_mapbits_get(chunk,
-		    pageind)) != BININD_INVALID);
-	}
-	mapelm = arena_mapp_get(chunk, pageind);
-	arena_dalloc_bin(arena, chunk, ptr, pageind, mapelm);
+arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena, extent_t *extent,
+    void *ptr) {
+	arena_dalloc_bin_locked_impl(tsdn, arena, extent, ptr, true);
 }
 
-#ifdef JEMALLOC_JET
-#undef arena_dalloc_junk_large
-#define	arena_dalloc_junk_large JEMALLOC_N(arena_dalloc_junk_large_impl)
-#endif
 static void
-arena_dalloc_junk_large(void *ptr, size_t usize)
-{
-
-	if (config_fill && opt_junk)
-		memset(ptr, 0x5a, usize);
-}
-#ifdef JEMALLOC_JET
-#undef arena_dalloc_junk_large
-#define	arena_dalloc_junk_large JEMALLOC_N(arena_dalloc_junk_large)
-arena_dalloc_junk_large_t *arena_dalloc_junk_large =
-    JEMALLOC_N(arena_dalloc_junk_large_impl);
-#endif
-
-void
-arena_dalloc_large_locked(arena_t *arena, arena_chunk_t *chunk, void *ptr)
-{
+arena_dalloc_bin(tsdn_t *tsdn, arena_t *arena, extent_t *extent, void *ptr) {
+	szind_t binind = extent_szind_get(extent);
+	arena_bin_t *bin = &arena->bins[binind];
 
-	if (config_fill || config_stats) {
-		size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
-		size_t usize = arena_mapbits_large_size_get(chunk, pageind);
-
-		arena_dalloc_junk_large(ptr, usize);
-		if (config_stats) {
-			arena->stats.ndalloc_large++;
-			arena->stats.allocated_large -= usize;
-			arena->stats.lstats[(usize >> LG_PAGE) - 1].ndalloc++;
-			arena->stats.lstats[(usize >> LG_PAGE) - 1].curruns--;
-		}
-	}
-
-	arena_run_dalloc(arena, (arena_run_t *)ptr, true, false);
+	malloc_mutex_lock(tsdn, &bin->lock);
+	arena_dalloc_bin_locked_impl(tsdn, arena, extent, ptr, false);
+	malloc_mutex_unlock(tsdn, &bin->lock);
 }
 
 void
-arena_dalloc_large(arena_t *arena, arena_chunk_t *chunk, void *ptr)
-{
+arena_dalloc_small(tsdn_t *tsdn, void *ptr) {
+	extent_t *extent = iealloc(tsdn, ptr);
+	arena_t *arena = extent_arena_get(extent);
 
-	malloc_mutex_lock(&arena->lock);
-	arena_dalloc_large_locked(arena, chunk, ptr);
-	malloc_mutex_unlock(&arena->lock);
+	arena_dalloc_bin(tsdn, arena, extent, ptr);
+	arena_decay_tick(tsdn, arena);
 }
 
-static void
-arena_ralloc_large_shrink(arena_t *arena, arena_chunk_t *chunk, void *ptr,
-    size_t oldsize, size_t size)
-{
-
-	assert(size < oldsize);
-
-	/*
-	 * Shrink the run, and make trailing pages available for other
-	 * allocations.
-	 */
-	malloc_mutex_lock(&arena->lock);
-	arena_run_trim_tail(arena, chunk, (arena_run_t *)ptr, oldsize, size,
-	    true);
-	if (config_stats) {
-		arena->stats.ndalloc_large++;
-		arena->stats.allocated_large -= oldsize;
-		arena->stats.lstats[(oldsize >> LG_PAGE) - 1].ndalloc++;
-		arena->stats.lstats[(oldsize >> LG_PAGE) - 1].curruns--;
+bool
+arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size,
+    size_t extra, bool zero) {
+	/* Calls with non-zero extra had to clamp extra. */
+	assert(extra == 0 || size + extra <= LARGE_MAXCLASS);
 
-		arena->stats.nmalloc_large++;
-		arena->stats.nrequests_large++;
-		arena->stats.allocated_large += size;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nmalloc++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].nrequests++;
-		arena->stats.lstats[(size >> LG_PAGE) - 1].curruns++;
+	if (unlikely(size > LARGE_MAXCLASS)) {
+		return true;
 	}
-	malloc_mutex_unlock(&arena->lock);
-}
 
-static bool
-arena_ralloc_large_grow(arena_t *arena, arena_chunk_t *chunk, void *ptr,
-    size_t oldsize, size_t size, size_t extra, bool zero)
-{
-	size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
-	size_t npages = oldsize >> LG_PAGE;
-	size_t followsize;
-
-	assert(oldsize == arena_mapbits_large_size_get(chunk, pageind));
-
-	/* Try to extend the run. */
-	assert(size + extra > oldsize);
-	malloc_mutex_lock(&arena->lock);
-	if (pageind + npages < chunk_npages &&
-	    arena_mapbits_allocated_get(chunk, pageind+npages) == 0 &&
-	    (followsize = arena_mapbits_unallocated_size_get(chunk,
-	    pageind+npages)) >= size - oldsize) {
+	extent_t *extent = iealloc(tsdn, ptr);
+	size_t usize_min = sz_s2u(size);
+	size_t usize_max = sz_s2u(size + extra);
+	if (likely(oldsize <= SMALL_MAXCLASS && usize_min <= SMALL_MAXCLASS)) {
 		/*
-		 * The next run is available and sufficiently large.  Split the
-		 * following run, then merge the first part with the existing
-		 * allocation.
+		 * Avoid moving the allocation if the size class can be left the
+		 * same.
 		 */
-		size_t flag_dirty;
-		size_t splitsize = (oldsize + followsize <= size + extra)
-		    ? followsize : size + extra - oldsize;
-		arena_run_split_large(arena, (arena_run_t *)((uintptr_t)chunk +
-		    ((pageind+npages) << LG_PAGE)), splitsize, zero);
-
-		size = oldsize + splitsize;
-		npages = size >> LG_PAGE;
-
-		/*
-		 * Mark the extended run as dirty if either portion of the run
-		 * was dirty before allocation.  This is rather pedantic,
-		 * because there's not actually any sequence of events that
-		 * could cause the resulting run to be passed to
-		 * arena_run_dalloc() with the dirty argument set to false
-		 * (which is when dirty flag consistency would really matter).
-		 */
-		flag_dirty = arena_mapbits_dirty_get(chunk, pageind) |
-		    arena_mapbits_dirty_get(chunk, pageind+npages-1);
-		arena_mapbits_large_set(chunk, pageind, size, flag_dirty);
-		arena_mapbits_large_set(chunk, pageind+npages-1, 0, flag_dirty);
-
-		if (config_stats) {
-			arena->stats.ndalloc_large++;
-			arena->stats.allocated_large -= oldsize;
-			arena->stats.lstats[(oldsize >> LG_PAGE) - 1].ndalloc++;
-			arena->stats.lstats[(oldsize >> LG_PAGE) - 1].curruns--;
-
-			arena->stats.nmalloc_large++;
-			arena->stats.nrequests_large++;
-			arena->stats.allocated_large += size;
-			arena->stats.lstats[(size >> LG_PAGE) - 1].nmalloc++;
-			arena->stats.lstats[(size >> LG_PAGE) - 1].nrequests++;
-			arena->stats.lstats[(size >> LG_PAGE) - 1].curruns++;
+		assert(arena_bin_info[sz_size2index(oldsize)].reg_size ==
+		    oldsize);
+		if ((usize_max > SMALL_MAXCLASS || sz_size2index(usize_max) !=
+		    sz_size2index(oldsize)) && (size > oldsize || usize_max <
+		    oldsize)) {
+			return true;
 		}
-		malloc_mutex_unlock(&arena->lock);
-		return (false);
+
+		arena_decay_tick(tsdn, extent_arena_get(extent));
+		return false;
+	} else if (oldsize >= LARGE_MINCLASS && usize_max >= LARGE_MINCLASS) {
+		return large_ralloc_no_move(tsdn, extent, usize_min, usize_max,
+		    zero);
 	}
-	malloc_mutex_unlock(&arena->lock);
 
-	return (true);
+	return true;
 }
 
-#ifdef JEMALLOC_JET
-#undef arena_ralloc_junk_large
-#define	arena_ralloc_junk_large JEMALLOC_N(arena_ralloc_junk_large_impl)
-#endif
-static void
-arena_ralloc_junk_large(void *ptr, size_t old_usize, size_t usize)
-{
-
-	if (config_fill && opt_junk) {
-		memset((void *)((uintptr_t)ptr + usize), 0x5a,
-		    old_usize - usize);
+static void *
+arena_ralloc_move_helper(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, bool zero, tcache_t *tcache) {
+	if (alignment == 0) {
+		return arena_malloc(tsdn, arena, usize, sz_size2index(usize),
+		    zero, tcache, true);
 	}
-}
-#ifdef JEMALLOC_JET
-#undef arena_ralloc_junk_large
-#define	arena_ralloc_junk_large JEMALLOC_N(arena_ralloc_junk_large)
-arena_ralloc_junk_large_t *arena_ralloc_junk_large =
-    JEMALLOC_N(arena_ralloc_junk_large_impl);
-#endif
-
-/*
- * Try to resize a large allocation, in order to avoid copying.  This will
- * always fail if growing an object, and the following run is already in use.
- */
-static bool
-arena_ralloc_large(void *ptr, size_t oldsize, size_t size, size_t extra,
-    bool zero)
-{
-	size_t psize;
-
-	psize = PAGE_CEILING(size + extra);
-	if (psize == oldsize) {
-		/* Same size class. */
-		return (false);
-	} else {
-		arena_chunk_t *chunk;
-		arena_t *arena;
-
-		chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-		arena = chunk->arena;
-
-		if (psize < oldsize) {
-			/* Fill before shrinking in order avoid a race. */
-			arena_ralloc_junk_large(ptr, oldsize, psize);
-			arena_ralloc_large_shrink(arena, chunk, ptr, oldsize,
-			    psize);
-			return (false);
-		} else {
-			bool ret = arena_ralloc_large_grow(arena, chunk, ptr,
-			    oldsize, PAGE_CEILING(size),
-			    psize - PAGE_CEILING(size), zero);
-			if (config_fill && ret == false && zero == false) {
-				if (opt_junk) {
-					memset((void *)((uintptr_t)ptr +
-					    oldsize), 0xa5, isalloc(ptr,
-					    config_prof) - oldsize);
-				} else if (opt_zero) {
-					memset((void *)((uintptr_t)ptr +
-					    oldsize), 0, isalloc(ptr,
-					    config_prof) - oldsize);
-				}
-			}
-			return (ret);
-		}
+	usize = sz_sa2u(usize, alignment);
+	if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
+		return NULL;
 	}
+	return ipalloct(tsdn, usize, alignment, zero, tcache, arena);
 }
 
-bool
-arena_ralloc_no_move(void *ptr, size_t oldsize, size_t size, size_t extra,
-    bool zero)
-{
+void *
+arena_ralloc(tsdn_t *tsdn, arena_t *arena, void *ptr, size_t oldsize,
+    size_t size, size_t alignment, bool zero, tcache_t *tcache) {
+	size_t usize = sz_s2u(size);
+	if (unlikely(usize == 0 || size > LARGE_MAXCLASS)) {
+		return NULL;
+	}
 
-	/*
-	 * Avoid moving the allocation if the size class can be left the same.
-	 */
-	if (oldsize <= arena_maxclass) {
-		if (oldsize <= SMALL_MAXCLASS) {
-			assert(arena_bin_info[SMALL_SIZE2BIN(oldsize)].reg_size
-			    == oldsize);
-			if ((size + extra <= SMALL_MAXCLASS &&
-			    SMALL_SIZE2BIN(size + extra) ==
-			    SMALL_SIZE2BIN(oldsize)) || (size <= oldsize &&
-			    size + extra >= oldsize))
-				return (false);
-		} else {
-			assert(size <= arena_maxclass);
-			if (size + extra > SMALL_MAXCLASS) {
-				if (arena_ralloc_large(ptr, oldsize, size,
-				    extra, zero) == false)
-					return (false);
-			}
+	if (likely(usize <= SMALL_MAXCLASS)) {
+		/* Try to avoid moving the allocation. */
+		if (!arena_ralloc_no_move(tsdn, ptr, oldsize, usize, 0, zero)) {
+			return ptr;
 		}
 	}
 
-	/* Reallocation would require a move. */
-	return (true);
-}
-
-void *
-arena_ralloc(arena_t *arena, void *ptr, size_t oldsize, size_t size,
-    size_t extra, size_t alignment, bool zero, bool try_tcache_alloc,
-    bool try_tcache_dalloc)
-{
-	void *ret;
-	size_t copysize;
-
-	/* Try to avoid moving the allocation. */
-	if (arena_ralloc_no_move(ptr, oldsize, size, extra, zero) == false)
-		return (ptr);
+	if (oldsize >= LARGE_MINCLASS && usize >= LARGE_MINCLASS) {
+		return large_ralloc(tsdn, arena, iealloc(tsdn, ptr), usize,
+		    alignment, zero, tcache);
+	}
 
 	/*
 	 * size and oldsize are different enough that we need to move the
-	 * object.  In that case, fall back to allocating new space and
-	 * copying.
+	 * object.  In that case, fall back to allocating new space and copying.
 	 */
-	if (alignment != 0) {
-		size_t usize = sa2u(size + extra, alignment);
-		if (usize == 0)
-			return (NULL);
-		ret = ipalloct(usize, alignment, zero, try_tcache_alloc, arena);
-	} else
-		ret = arena_malloc(arena, size + extra, zero, try_tcache_alloc);
-
+	void *ret = arena_ralloc_move_helper(tsdn, arena, usize, alignment,
+	    zero, tcache);
 	if (ret == NULL) {
-		if (extra == 0)
-			return (NULL);
-		/* Try again, this time without extra. */
-		if (alignment != 0) {
-			size_t usize = sa2u(size, alignment);
-			if (usize == 0)
-				return (NULL);
-			ret = ipalloct(usize, alignment, zero, try_tcache_alloc,
-			    arena);
-		} else
-			ret = arena_malloc(arena, size, zero, try_tcache_alloc);
-
-		if (ret == NULL)
-			return (NULL);
+		return NULL;
 	}
 
-	/* Junk/zero-filling were already done by ipalloc()/arena_malloc(). */
-
 	/*
-	 * Copy at most size bytes (not size+extra), since the caller has no
-	 * expectation that the extra bytes will be reliably preserved.
+	 * Junk/zero-filling were already done by
+	 * ipalloc()/arena_malloc().
 	 */
-	copysize = (size < oldsize) ? size : oldsize;
-	VALGRIND_MAKE_MEM_UNDEFINED(ret, copysize);
+
+	size_t copysize = (usize < oldsize) ? usize : oldsize;
 	memcpy(ret, ptr, copysize);
-	iqalloct(ptr, try_tcache_dalloc);
-	return (ret);
+	isdalloct(tsdn, ptr, oldsize, tcache, NULL, true);
+	return ret;
 }
 
 dss_prec_t
-arena_dss_prec_get(arena_t *arena)
-{
-	dss_prec_t ret;
+arena_dss_prec_get(arena_t *arena) {
+	return (dss_prec_t)atomic_load_u(&arena->dss_prec, ATOMIC_ACQUIRE);
+}
 
-	malloc_mutex_lock(&arena->lock);
-	ret = arena->dss_prec;
-	malloc_mutex_unlock(&arena->lock);
-	return (ret);
+bool
+arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec) {
+	if (!have_dss) {
+		return (dss_prec != dss_prec_disabled);
+	}
+	atomic_store_u(&arena->dss_prec, (unsigned)dss_prec, ATOMIC_RELEASE);
+	return false;
 }
 
-void
-arena_dss_prec_set(arena_t *arena, dss_prec_t dss_prec)
-{
+ssize_t
+arena_dirty_decay_ms_default_get(void) {
+	return atomic_load_zd(&dirty_decay_ms_default, ATOMIC_RELAXED);
+}
 
-	malloc_mutex_lock(&arena->lock);
-	arena->dss_prec = dss_prec;
-	malloc_mutex_unlock(&arena->lock);
+bool
+arena_dirty_decay_ms_default_set(ssize_t decay_ms) {
+	if (!arena_decay_ms_valid(decay_ms)) {
+		return true;
+	}
+	atomic_store_zd(&dirty_decay_ms_default, decay_ms, ATOMIC_RELAXED);
+	return false;
 }
 
-void
-arena_stats_merge(arena_t *arena, const char **dss, size_t *nactive,
-    size_t *ndirty, arena_stats_t *astats, malloc_bin_stats_t *bstats,
-    malloc_large_stats_t *lstats)
-{
-	unsigned i;
+ssize_t
+arena_muzzy_decay_ms_default_get(void) {
+	return atomic_load_zd(&muzzy_decay_ms_default, ATOMIC_RELAXED);
+}
 
-	malloc_mutex_lock(&arena->lock);
-	*dss = dss_prec_names[arena->dss_prec];
-	*nactive += arena->nactive;
-	*ndirty += arena->ndirty;
+bool
+arena_muzzy_decay_ms_default_set(ssize_t decay_ms) {
+	if (!arena_decay_ms_valid(decay_ms)) {
+		return true;
+	}
+	atomic_store_zd(&muzzy_decay_ms_default, decay_ms, ATOMIC_RELAXED);
+	return false;
+}
 
-	astats->mapped += arena->stats.mapped;
-	astats->npurge += arena->stats.npurge;
-	astats->nmadvise += arena->stats.nmadvise;
-	astats->purged += arena->stats.purged;
-	astats->allocated_large += arena->stats.allocated_large;
-	astats->nmalloc_large += arena->stats.nmalloc_large;
-	astats->ndalloc_large += arena->stats.ndalloc_large;
-	astats->nrequests_large += arena->stats.nrequests_large;
+unsigned
+arena_nthreads_get(arena_t *arena, bool internal) {
+	return atomic_load_u(&arena->nthreads[internal], ATOMIC_RELAXED);
+}
 
-	for (i = 0; i < nlclasses; i++) {
-		lstats[i].nmalloc += arena->stats.lstats[i].nmalloc;
-		lstats[i].ndalloc += arena->stats.lstats[i].ndalloc;
-		lstats[i].nrequests += arena->stats.lstats[i].nrequests;
-		lstats[i].curruns += arena->stats.lstats[i].curruns;
-	}
-	malloc_mutex_unlock(&arena->lock);
+void
+arena_nthreads_inc(arena_t *arena, bool internal) {
+	atomic_fetch_add_u(&arena->nthreads[internal], 1, ATOMIC_RELAXED);
+}
 
-	for (i = 0; i < NBINS; i++) {
-		arena_bin_t *bin = &arena->bins[i];
+void
+arena_nthreads_dec(arena_t *arena, bool internal) {
+	atomic_fetch_sub_u(&arena->nthreads[internal], 1, ATOMIC_RELAXED);
+}
 
-		malloc_mutex_lock(&bin->lock);
-		bstats[i].allocated += bin->stats.allocated;
-		bstats[i].nmalloc += bin->stats.nmalloc;
-		bstats[i].ndalloc += bin->stats.ndalloc;
-		bstats[i].nrequests += bin->stats.nrequests;
-		if (config_tcache) {
-			bstats[i].nfills += bin->stats.nfills;
-			bstats[i].nflushes += bin->stats.nflushes;
-		}
-		bstats[i].nruns += bin->stats.nruns;
-		bstats[i].reruns += bin->stats.reruns;
-		bstats[i].curruns += bin->stats.curruns;
-		malloc_mutex_unlock(&bin->lock);
-	}
+size_t
+arena_extent_sn_next(arena_t *arena) {
+	return atomic_fetch_add_zu(&arena->extent_sn_next, 1, ATOMIC_RELAXED);
 }
 
-bool
-arena_new(arena_t *arena, unsigned ind)
-{
+arena_t *
+arena_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) {
+	arena_t *arena;
+	base_t *base;
 	unsigned i;
-	arena_bin_t *bin;
 
-	arena->ind = ind;
-	arena->nthreads = 0;
+	if (ind == 0) {
+		base = b0get();
+	} else {
+		base = base_new(tsdn, ind, extent_hooks);
+		if (base == NULL) {
+			return NULL;
+		}
+	}
+
+	arena = (arena_t *)base_alloc(tsdn, base, sizeof(arena_t), CACHELINE);
+	if (arena == NULL) {
+		goto label_error;
+	}
 
-	if (malloc_mutex_init(&arena->lock))
-		return (true);
+	atomic_store_u(&arena->nthreads[0], 0, ATOMIC_RELAXED);
+	atomic_store_u(&arena->nthreads[1], 0, ATOMIC_RELAXED);
+	arena->last_thd = NULL;
 
 	if (config_stats) {
-		memset(&arena->stats, 0, sizeof(arena_stats_t));
-		arena->stats.lstats =
-		    (malloc_large_stats_t *)base_alloc(nlclasses *
-		    sizeof(malloc_large_stats_t));
-		if (arena->stats.lstats == NULL)
-			return (true);
-		memset(arena->stats.lstats, 0, nlclasses *
-		    sizeof(malloc_large_stats_t));
-		if (config_tcache)
-			ql_new(&arena->tcache_ql);
+		if (arena_stats_init(tsdn, &arena->stats)) {
+			goto label_error;
+		}
+
+		ql_new(&arena->tcache_ql);
+		if (malloc_mutex_init(&arena->tcache_ql_mtx, "tcache_ql",
+		    WITNESS_RANK_TCACHE_QL, malloc_mutex_rank_exclusive)) {
+			goto label_error;
+		}
 	}
 
-	if (config_prof)
-		arena->prof_accumbytes = 0;
+	if (config_prof) {
+		if (prof_accum_init(tsdn, &arena->prof_accum)) {
+			goto label_error;
+		}
+	}
 
-	arena->dss_prec = chunk_dss_prec_get();
+	if (config_cache_oblivious) {
+		/*
+		 * A nondeterministic seed based on the address of arena reduces
+		 * the likelihood of lockstep non-uniform cache index
+		 * utilization among identical concurrent processes, but at the
+		 * cost of test repeatability.  For debug builds, instead use a
+		 * deterministic seed.
+		 */
+		atomic_store_zu(&arena->offset_state, config_debug ? ind :
+		    (size_t)(uintptr_t)arena, ATOMIC_RELAXED);
+	}
 
-	/* Initialize chunks. */
-	arena_chunk_dirty_new(&arena->chunks_dirty);
-	arena->spare = NULL;
+	atomic_store_zu(&arena->extent_sn_next, 0, ATOMIC_RELAXED);
 
-	arena->nactive = 0;
-	arena->ndirty = 0;
-	arena->npurgatory = 0;
+	atomic_store_u(&arena->dss_prec, (unsigned)extent_dss_prec_get(),
+	    ATOMIC_RELAXED);
 
-	arena_avail_tree_new(&arena->runs_avail);
+	atomic_store_zu(&arena->nactive, 0, ATOMIC_RELAXED);
 
-	/* Initialize bins. */
-	for (i = 0; i < NBINS; i++) {
-		bin = &arena->bins[i];
-		if (malloc_mutex_init(&bin->lock))
-			return (true);
-		bin->runcur = NULL;
-		arena_run_tree_new(&bin->runs);
-		if (config_stats)
-			memset(&bin->stats, 0, sizeof(malloc_bin_stats_t));
+	extent_list_init(&arena->large);
+	if (malloc_mutex_init(&arena->large_mtx, "arena_large",
+	    WITNESS_RANK_ARENA_LARGE, malloc_mutex_rank_exclusive)) {
+		goto label_error;
 	}
 
-	return (false);
-}
-
-/*
- * Calculate bin_info->run_size such that it meets the following constraints:
- *
- *   *) bin_info->run_size >= min_run_size
- *   *) bin_info->run_size <= arena_maxclass
- *   *) run header overhead <= RUN_MAX_OVRHD (or header overhead relaxed).
- *   *) bin_info->nregs <= RUN_MAXREGS
- *
- * bin_info->nregs, bin_info->bitmap_offset, and bin_info->reg0_offset are also
- * calculated here, since these settings are all interdependent.
- */
-static size_t
-bin_info_run_size_calc(arena_bin_info_t *bin_info, size_t min_run_size)
-{
-	size_t pad_size;
-	size_t try_run_size, good_run_size;
-	uint32_t try_nregs, good_nregs;
-	uint32_t try_hdr_size, good_hdr_size;
-	uint32_t try_bitmap_offset, good_bitmap_offset;
-	uint32_t try_ctx0_offset, good_ctx0_offset;
-	uint32_t try_redzone0_offset, good_redzone0_offset;
-
-	assert(min_run_size >= PAGE);
-	assert(min_run_size <= arena_maxclass);
-
 	/*
-	 * Determine redzone size based on minimum alignment and minimum
-	 * redzone size.  Add padding to the end of the run if it is needed to
-	 * align the regions.  The padding allows each redzone to be half the
-	 * minimum alignment; without the padding, each redzone would have to
-	 * be twice as large in order to maintain alignment.
+	 * Delay coalescing for dirty extents despite the disruptive effect on
+	 * memory layout for best-fit extent allocation, since cached extents
+	 * are likely to be reused soon after deallocation, and the cost of
+	 * merging/splitting extents is non-trivial.
 	 */
-	if (config_fill && opt_redzone) {
-		size_t align_min = ZU(1) << (ffs(bin_info->reg_size) - 1);
-		if (align_min <= REDZONE_MINSIZE) {
-			bin_info->redzone_size = REDZONE_MINSIZE;
-			pad_size = 0;
-		} else {
-			bin_info->redzone_size = align_min >> 1;
-			pad_size = bin_info->redzone_size;
-		}
-	} else {
-		bin_info->redzone_size = 0;
-		pad_size = 0;
+	if (extents_init(tsdn, &arena->extents_dirty, extent_state_dirty,
+	    true)) {
+		goto label_error;
 	}
-	bin_info->reg_interval = bin_info->reg_size +
-	    (bin_info->redzone_size << 1);
-
 	/*
-	 * Calculate known-valid settings before entering the run_size
-	 * expansion loop, so that the first part of the loop always copies
-	 * valid settings.
-	 *
-	 * The do..while loop iteratively reduces the number of regions until
-	 * the run header and the regions no longer overlap.  A closed formula
-	 * would be quite messy, since there is an interdependency between the
-	 * header's mask length and the number of regions.
+	 * Coalesce muzzy extents immediately, because operations on them are in
+	 * the critical path much less often than for dirty extents.
 	 */
-	try_run_size = min_run_size;
-	try_nregs = ((try_run_size - sizeof(arena_run_t)) /
-	    bin_info->reg_interval)
-	    + 1; /* Counter-act try_nregs-- in loop. */
-	if (try_nregs > RUN_MAXREGS) {
-		try_nregs = RUN_MAXREGS
-		    + 1; /* Counter-act try_nregs-- in loop. */
-	}
-	do {
-		try_nregs--;
-		try_hdr_size = sizeof(arena_run_t);
-		/* Pad to a long boundary. */
-		try_hdr_size = LONG_CEILING(try_hdr_size);
-		try_bitmap_offset = try_hdr_size;
-		/* Add space for bitmap. */
-		try_hdr_size += bitmap_size(try_nregs);
-		if (config_prof && opt_prof && prof_promote == false) {
-			/* Pad to a quantum boundary. */
-			try_hdr_size = QUANTUM_CEILING(try_hdr_size);
-			try_ctx0_offset = try_hdr_size;
-			/* Add space for one (prof_ctx_t *) per region. */
-			try_hdr_size += try_nregs * sizeof(prof_ctx_t *);
-		} else
-			try_ctx0_offset = 0;
-		try_redzone0_offset = try_run_size - (try_nregs *
-		    bin_info->reg_interval) - pad_size;
-	} while (try_hdr_size > try_redzone0_offset);
-
-	/* run_size expansion loop. */
-	do {
-		/*
-		 * Copy valid settings before trying more aggressive settings.
-		 */
-		good_run_size = try_run_size;
-		good_nregs = try_nregs;
-		good_hdr_size = try_hdr_size;
-		good_bitmap_offset = try_bitmap_offset;
-		good_ctx0_offset = try_ctx0_offset;
-		good_redzone0_offset = try_redzone0_offset;
-
-		/* Try more aggressive settings. */
-		try_run_size += PAGE;
-		try_nregs = ((try_run_size - sizeof(arena_run_t) - pad_size) /
-		    bin_info->reg_interval)
-		    + 1; /* Counter-act try_nregs-- in loop. */
-		if (try_nregs > RUN_MAXREGS) {
-			try_nregs = RUN_MAXREGS
-			    + 1; /* Counter-act try_nregs-- in loop. */
+	if (extents_init(tsdn, &arena->extents_muzzy, extent_state_muzzy,
+	    false)) {
+		goto label_error;
+	}
+	/*
+	 * Coalesce retained extents immediately, in part because they will
+	 * never be evicted (and therefore there's no opportunity for delayed
+	 * coalescing), but also because operations on retained extents are not
+	 * in the critical path.
+	 */
+	if (extents_init(tsdn, &arena->extents_retained, extent_state_retained,
+	    false)) {
+		goto label_error;
+	}
+
+	if (arena_decay_init(&arena->decay_dirty, &arena->extents_dirty,
+	    arena_dirty_decay_ms_default_get(), &arena->stats.decay_dirty)) {
+		goto label_error;
+	}
+	if (arena_decay_init(&arena->decay_muzzy, &arena->extents_muzzy,
+	    arena_muzzy_decay_ms_default_get(), &arena->stats.decay_muzzy)) {
+		goto label_error;
+	}
+
+	arena->extent_grow_next = sz_psz2ind(HUGEPAGE);
+	if (malloc_mutex_init(&arena->extent_grow_mtx, "extent_grow",
+	    WITNESS_RANK_EXTENT_GROW, malloc_mutex_rank_exclusive)) {
+		goto label_error;
+	}
+
+	extent_avail_new(&arena->extent_avail);
+	if (malloc_mutex_init(&arena->extent_avail_mtx, "extent_avail",
+	    WITNESS_RANK_EXTENT_AVAIL, malloc_mutex_rank_exclusive)) {
+		goto label_error;
+	}
+
+	/* Initialize bins. */
+	for (i = 0; i < NBINS; i++) {
+		arena_bin_t *bin = &arena->bins[i];
+		if (malloc_mutex_init(&bin->lock, "arena_bin",
+		    WITNESS_RANK_ARENA_BIN, malloc_mutex_rank_exclusive)) {
+			goto label_error;
 		}
-		do {
-			try_nregs--;
-			try_hdr_size = sizeof(arena_run_t);
-			/* Pad to a long boundary. */
-			try_hdr_size = LONG_CEILING(try_hdr_size);
-			try_bitmap_offset = try_hdr_size;
-			/* Add space for bitmap. */
-			try_hdr_size += bitmap_size(try_nregs);
-			if (config_prof && opt_prof && prof_promote == false) {
-				/* Pad to a quantum boundary. */
-				try_hdr_size = QUANTUM_CEILING(try_hdr_size);
-				try_ctx0_offset = try_hdr_size;
-				/*
-				 * Add space for one (prof_ctx_t *) per region.
-				 */
-				try_hdr_size += try_nregs *
-				    sizeof(prof_ctx_t *);
-			}
-			try_redzone0_offset = try_run_size - (try_nregs *
-			    bin_info->reg_interval) - pad_size;
-		} while (try_hdr_size > try_redzone0_offset);
-	} while (try_run_size <= arena_maxclass
-	    && RUN_MAX_OVRHD * (bin_info->reg_interval << 3) >
-	    RUN_MAX_OVRHD_RELAX
-	    && (try_redzone0_offset << RUN_BFP) > RUN_MAX_OVRHD * try_run_size
-	    && try_nregs < RUN_MAXREGS);
+		bin->slabcur = NULL;
+		extent_heap_new(&bin->slabs_nonfull);
+		extent_list_init(&bin->slabs_full);
+		if (config_stats) {
+			memset(&bin->stats, 0, sizeof(malloc_bin_stats_t));
+		}
+	}
 
-	assert(good_hdr_size <= good_redzone0_offset);
+	arena->base = base;
+	/* Set arena before creating background threads. */
+	arena_set(ind, arena);
 
-	/* Copy final settings. */
-	bin_info->run_size = good_run_size;
-	bin_info->nregs = good_nregs;
-	bin_info->bitmap_offset = good_bitmap_offset;
-	bin_info->ctx0_offset = good_ctx0_offset;
-	bin_info->reg0_offset = good_redzone0_offset + bin_info->redzone_size;
+	nstime_init(&arena->create_time, 0);
+	nstime_update(&arena->create_time);
 
-	assert(bin_info->reg0_offset - bin_info->redzone_size + (bin_info->nregs
-	    * bin_info->reg_interval) + pad_size == bin_info->run_size);
+	/* We don't support reentrancy for arena 0 bootstrapping. */
+	if (ind != 0) {
+		/*
+		 * If we're here, then arena 0 already exists, so bootstrapping
+		 * is done enough that we should have tsd.
+		 */
+		assert(!tsdn_null(tsdn));
+		pre_reentrancy(tsdn_tsd(tsdn), arena);
+		if (hooks_arena_new_hook) {
+			hooks_arena_new_hook();
+		}
+		post_reentrancy(tsdn_tsd(tsdn));
+	}
 
-	return (good_run_size);
+	return arena;
+label_error:
+	if (ind != 0) {
+		base_delete(tsdn, base);
+	}
+	return NULL;
 }
 
-static void
-bin_info_init(void)
-{
-	arena_bin_info_t *bin_info;
-	size_t prev_run_size = PAGE;
-
-#define	SIZE_CLASS(bin, delta, size)					\
-	bin_info = &arena_bin_info[bin];				\
-	bin_info->reg_size = size;					\
-	prev_run_size = bin_info_run_size_calc(bin_info, prev_run_size);\
-	bitmap_info_init(&bin_info->bitmap_info, bin_info->nregs);
-	SIZE_CLASSES
-#undef SIZE_CLASS
+void
+arena_boot(void) {
+	arena_dirty_decay_ms_default_set(opt_dirty_decay_ms);
+	arena_muzzy_decay_ms_default_set(opt_muzzy_decay_ms);
 }
 
 void
-arena_boot(void)
-{
-	size_t header_size;
-	unsigned i;
+arena_prefork0(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_prefork(tsdn, &arena->decay_dirty.mtx);
+	malloc_mutex_prefork(tsdn, &arena->decay_muzzy.mtx);
+}
 
-	/*
-	 * Compute the header size such that it is large enough to contain the
-	 * page map.  The page map is biased to omit entries for the header
-	 * itself, so some iteration is necessary to compute the map bias.
-	 *
-	 * 1) Compute safe header_size and map_bias values that include enough
-	 *    space for an unbiased page map.
-	 * 2) Refine map_bias based on (1) to omit the header pages in the page
-	 *    map.  The resulting map_bias may be one too small.
-	 * 3) Refine map_bias based on (2).  The result will be >= the result
-	 *    from (2), and will always be correct.
-	 */
-	map_bias = 0;
-	for (i = 0; i < 3; i++) {
-		header_size = offsetof(arena_chunk_t, map) +
-		    (sizeof(arena_chunk_map_t) * (chunk_npages-map_bias));
-		map_bias = (header_size >> LG_PAGE) + ((header_size & PAGE_MASK)
-		    != 0);
+void
+arena_prefork1(tsdn_t *tsdn, arena_t *arena) {
+	if (config_stats) {
+		malloc_mutex_prefork(tsdn, &arena->tcache_ql_mtx);
 	}
-	assert(map_bias > 0);
+}
 
-	arena_maxclass = chunksize - (map_bias << LG_PAGE);
+void
+arena_prefork2(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_prefork(tsdn, &arena->extent_grow_mtx);
+}
 
-	bin_info_init();
+void
+arena_prefork3(tsdn_t *tsdn, arena_t *arena) {
+	extents_prefork(tsdn, &arena->extents_dirty);
+	extents_prefork(tsdn, &arena->extents_muzzy);
+	extents_prefork(tsdn, &arena->extents_retained);
 }
 
 void
-arena_prefork(arena_t *arena)
-{
-	unsigned i;
+arena_prefork4(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_prefork(tsdn, &arena->extent_avail_mtx);
+}
 
-	malloc_mutex_prefork(&arena->lock);
-	for (i = 0; i < NBINS; i++)
-		malloc_mutex_prefork(&arena->bins[i].lock);
+void
+arena_prefork5(tsdn_t *tsdn, arena_t *arena) {
+	base_prefork(tsdn, arena->base);
+}
+
+void
+arena_prefork6(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_prefork(tsdn, &arena->large_mtx);
+}
+
+void
+arena_prefork7(tsdn_t *tsdn, arena_t *arena) {
+	for (unsigned i = 0; i < NBINS; i++) {
+		malloc_mutex_prefork(tsdn, &arena->bins[i].lock);
+	}
 }
 
 void
-arena_postfork_parent(arena_t *arena)
-{
+arena_postfork_parent(tsdn_t *tsdn, arena_t *arena) {
 	unsigned i;
 
-	for (i = 0; i < NBINS; i++)
-		malloc_mutex_postfork_parent(&arena->bins[i].lock);
-	malloc_mutex_postfork_parent(&arena->lock);
+	for (i = 0; i < NBINS; i++) {
+		malloc_mutex_postfork_parent(tsdn, &arena->bins[i].lock);
+	}
+	malloc_mutex_postfork_parent(tsdn, &arena->large_mtx);
+	base_postfork_parent(tsdn, arena->base);
+	malloc_mutex_postfork_parent(tsdn, &arena->extent_avail_mtx);
+	extents_postfork_parent(tsdn, &arena->extents_dirty);
+	extents_postfork_parent(tsdn, &arena->extents_muzzy);
+	extents_postfork_parent(tsdn, &arena->extents_retained);
+	malloc_mutex_postfork_parent(tsdn, &arena->extent_grow_mtx);
+	malloc_mutex_postfork_parent(tsdn, &arena->decay_dirty.mtx);
+	malloc_mutex_postfork_parent(tsdn, &arena->decay_muzzy.mtx);
+	if (config_stats) {
+		malloc_mutex_postfork_parent(tsdn, &arena->tcache_ql_mtx);
+	}
 }
 
 void
-arena_postfork_child(arena_t *arena)
-{
+arena_postfork_child(tsdn_t *tsdn, arena_t *arena) {
 	unsigned i;
 
-	for (i = 0; i < NBINS; i++)
-		malloc_mutex_postfork_child(&arena->bins[i].lock);
-	malloc_mutex_postfork_child(&arena->lock);
+	atomic_store_u(&arena->nthreads[0], 0, ATOMIC_RELAXED);
+	atomic_store_u(&arena->nthreads[1], 0, ATOMIC_RELAXED);
+	if (tsd_arena_get(tsdn_tsd(tsdn)) == arena) {
+		arena_nthreads_inc(arena, false);
+	}
+	if (tsd_iarena_get(tsdn_tsd(tsdn)) == arena) {
+		arena_nthreads_inc(arena, true);
+	}
+	if (config_stats) {
+		ql_new(&arena->tcache_ql);
+		tcache_t *tcache = tcache_get(tsdn_tsd(tsdn));
+		if (tcache != NULL && tcache->arena == arena) {
+			ql_elm_new(tcache, link);
+			ql_tail_insert(&arena->tcache_ql, tcache, link);
+		}
+	}
+
+	for (i = 0; i < NBINS; i++) {
+		malloc_mutex_postfork_child(tsdn, &arena->bins[i].lock);
+	}
+	malloc_mutex_postfork_child(tsdn, &arena->large_mtx);
+	base_postfork_child(tsdn, arena->base);
+	malloc_mutex_postfork_child(tsdn, &arena->extent_avail_mtx);
+	extents_postfork_child(tsdn, &arena->extents_dirty);
+	extents_postfork_child(tsdn, &arena->extents_muzzy);
+	extents_postfork_child(tsdn, &arena->extents_retained);
+	malloc_mutex_postfork_child(tsdn, &arena->extent_grow_mtx);
+	malloc_mutex_postfork_child(tsdn, &arena->decay_dirty.mtx);
+	malloc_mutex_postfork_child(tsdn, &arena->decay_muzzy.mtx);
+	if (config_stats) {
+		malloc_mutex_postfork_child(tsdn, &arena->tcache_ql_mtx);
+	}
 }
diff --git a/modules/worldengine/deps/jemalloc/src/background_thread.c b/modules/worldengine/deps/jemalloc/src/background_thread.c
new file mode 100644
index 0000000000..eb30eb5b42
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/background_thread.c
@@ -0,0 +1,880 @@
+#define JEMALLOC_BACKGROUND_THREAD_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+
+/******************************************************************************/
+/* Data. */
+
+/* This option should be opt-in only. */
+#define BACKGROUND_THREAD_DEFAULT false
+/* Read-only after initialization. */
+bool opt_background_thread = BACKGROUND_THREAD_DEFAULT;
+
+/* Used for thread creation, termination and stats. */
+malloc_mutex_t background_thread_lock;
+/* Indicates global state.  Atomic because decay reads this w/o locking. */
+atomic_b_t background_thread_enabled_state;
+size_t n_background_threads;
+/* Thread info per-index. */
+background_thread_info_t *background_thread_info;
+
+/* False if no necessary runtime support. */
+bool can_enable_background_thread;
+
+/******************************************************************************/
+
+#ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER
+#include <dlfcn.h>
+
+static int (*pthread_create_fptr)(pthread_t *__restrict, const pthread_attr_t *,
+    void *(*)(void *), void *__restrict);
+static pthread_once_t once_control = PTHREAD_ONCE_INIT;
+
+static void
+pthread_create_wrapper_once(void) {
+#ifdef JEMALLOC_LAZY_LOCK
+	isthreaded = true;
+#endif
+}
+
+int
+pthread_create_wrapper(pthread_t *__restrict thread, const pthread_attr_t *attr,
+    void *(*start_routine)(void *), void *__restrict arg) {
+	pthread_once(&once_control, pthread_create_wrapper_once);
+
+	return pthread_create_fptr(thread, attr, start_routine, arg);
+}
+#endif /* JEMALLOC_PTHREAD_CREATE_WRAPPER */
+
+#ifndef JEMALLOC_BACKGROUND_THREAD
+#define NOT_REACHED { not_reached(); }
+bool background_thread_create(tsd_t *tsd, unsigned arena_ind) NOT_REACHED
+bool background_threads_enable(tsd_t *tsd) NOT_REACHED
+bool background_threads_disable(tsd_t *tsd) NOT_REACHED
+void background_thread_interval_check(tsdn_t *tsdn, arena_t *arena,
+    arena_decay_t *decay, size_t npages_new) NOT_REACHED
+void background_thread_prefork0(tsdn_t *tsdn) NOT_REACHED
+void background_thread_prefork1(tsdn_t *tsdn) NOT_REACHED
+void background_thread_postfork_parent(tsdn_t *tsdn) NOT_REACHED
+void background_thread_postfork_child(tsdn_t *tsdn) NOT_REACHED
+bool background_thread_stats_read(tsdn_t *tsdn,
+    background_thread_stats_t *stats) NOT_REACHED
+void background_thread_ctl_init(tsdn_t *tsdn) NOT_REACHED
+#undef NOT_REACHED
+#else
+
+static bool background_thread_enabled_at_fork;
+
+static void
+background_thread_info_init(tsdn_t *tsdn, background_thread_info_t *info) {
+	background_thread_wakeup_time_set(tsdn, info, 0);
+	info->npages_to_purge_new = 0;
+	if (config_stats) {
+		info->tot_n_runs = 0;
+		nstime_init(&info->tot_sleep_time, 0);
+	}
+}
+
+static inline bool
+set_current_thread_affinity(UNUSED int cpu) {
+#if defined(JEMALLOC_HAVE_SCHED_SETAFFINITY)
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpu, &cpuset);
+	int ret = sched_setaffinity(0, sizeof(cpu_set_t), &cpuset);
+
+	return (ret != 0);
+#else
+	return false;
+#endif
+}
+
+/* Threshold for determining when to wake up the background thread. */
+#define BACKGROUND_THREAD_NPAGES_THRESHOLD UINT64_C(1024)
+#define BILLION UINT64_C(1000000000)
+/* Minimal sleep interval 100 ms. */
+#define BACKGROUND_THREAD_MIN_INTERVAL_NS (BILLION / 10)
+
+static inline size_t
+decay_npurge_after_interval(arena_decay_t *decay, size_t interval) {
+	size_t i;
+	uint64_t sum = 0;
+	for (i = 0; i < interval; i++) {
+		sum += decay->backlog[i] * h_steps[i];
+	}
+	for (; i < SMOOTHSTEP_NSTEPS; i++) {
+		sum += decay->backlog[i] * (h_steps[i] - h_steps[i - interval]);
+	}
+
+	return (size_t)(sum >> SMOOTHSTEP_BFP);
+}
+
+static uint64_t
+arena_decay_compute_purge_interval_impl(tsdn_t *tsdn, arena_decay_t *decay,
+    extents_t *extents) {
+	if (malloc_mutex_trylock(tsdn, &decay->mtx)) {
+		/* Use minimal interval if decay is contended. */
+		return BACKGROUND_THREAD_MIN_INTERVAL_NS;
+	}
+
+	uint64_t interval;
+	ssize_t decay_time = atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED);
+	if (decay_time <= 0) {
+		/* Purging is eagerly done or disabled currently. */
+		interval = BACKGROUND_THREAD_INDEFINITE_SLEEP;
+		goto label_done;
+	}
+
+	uint64_t decay_interval_ns = nstime_ns(&decay->interval);
+	assert(decay_interval_ns > 0);
+	size_t npages = extents_npages_get(extents);
+	if (npages == 0) {
+		unsigned i;
+		for (i = 0; i < SMOOTHSTEP_NSTEPS; i++) {
+			if (decay->backlog[i] > 0) {
+				break;
+			}
+		}
+		if (i == SMOOTHSTEP_NSTEPS) {
+			/* No dirty pages recorded.  Sleep indefinitely. */
+			interval = BACKGROUND_THREAD_INDEFINITE_SLEEP;
+			goto label_done;
+		}
+	}
+	if (npages <= BACKGROUND_THREAD_NPAGES_THRESHOLD) {
+		/* Use max interval. */
+		interval = decay_interval_ns * SMOOTHSTEP_NSTEPS;
+		goto label_done;
+	}
+
+	size_t lb = BACKGROUND_THREAD_MIN_INTERVAL_NS / decay_interval_ns;
+	size_t ub = SMOOTHSTEP_NSTEPS;
+	/* Minimal 2 intervals to ensure reaching next epoch deadline. */
+	lb = (lb < 2) ? 2 : lb;
+	if ((decay_interval_ns * ub <= BACKGROUND_THREAD_MIN_INTERVAL_NS) ||
+	    (lb + 2 > ub)) {
+		interval = BACKGROUND_THREAD_MIN_INTERVAL_NS;
+		goto label_done;
+	}
+
+	assert(lb + 2 <= ub);
+	size_t npurge_lb, npurge_ub;
+	npurge_lb = decay_npurge_after_interval(decay, lb);
+	if (npurge_lb > BACKGROUND_THREAD_NPAGES_THRESHOLD) {
+		interval = decay_interval_ns * lb;
+		goto label_done;
+	}
+	npurge_ub = decay_npurge_after_interval(decay, ub);
+	if (npurge_ub < BACKGROUND_THREAD_NPAGES_THRESHOLD) {
+		interval = decay_interval_ns * ub;
+		goto label_done;
+	}
+
+	unsigned n_search = 0;
+	size_t target, npurge;
+	while ((npurge_lb + BACKGROUND_THREAD_NPAGES_THRESHOLD < npurge_ub)
+	    && (lb + 2 < ub)) {
+		target = (lb + ub) / 2;
+		npurge = decay_npurge_after_interval(decay, target);
+		if (npurge > BACKGROUND_THREAD_NPAGES_THRESHOLD) {
+			ub = target;
+			npurge_ub = npurge;
+		} else {
+			lb = target;
+			npurge_lb = npurge;
+		}
+		assert(n_search++ < lg_floor(SMOOTHSTEP_NSTEPS) + 1);
+	}
+	interval = decay_interval_ns * (ub + lb) / 2;
+label_done:
+	interval = (interval < BACKGROUND_THREAD_MIN_INTERVAL_NS) ?
+	    BACKGROUND_THREAD_MIN_INTERVAL_NS : interval;
+	malloc_mutex_unlock(tsdn, &decay->mtx);
+
+	return interval;
+}
+
+/* Compute purge interval for background threads. */
+static uint64_t
+arena_decay_compute_purge_interval(tsdn_t *tsdn, arena_t *arena) {
+	uint64_t i1, i2;
+	i1 = arena_decay_compute_purge_interval_impl(tsdn, &arena->decay_dirty,
+	    &arena->extents_dirty);
+	if (i1 == BACKGROUND_THREAD_MIN_INTERVAL_NS) {
+		return i1;
+	}
+	i2 = arena_decay_compute_purge_interval_impl(tsdn, &arena->decay_muzzy,
+	    &arena->extents_muzzy);
+
+	return i1 < i2 ? i1 : i2;
+}
+
+static void
+background_thread_sleep(tsdn_t *tsdn, background_thread_info_t *info,
+    uint64_t interval) {
+	if (config_stats) {
+		info->tot_n_runs++;
+	}
+	info->npages_to_purge_new = 0;
+
+	struct timeval tv;
+	/* Specific clock required by timedwait. */
+	gettimeofday(&tv, NULL);
+	nstime_t before_sleep;
+	nstime_init2(&before_sleep, tv.tv_sec, tv.tv_usec * 1000);
+
+	int ret;
+	if (interval == BACKGROUND_THREAD_INDEFINITE_SLEEP) {
+		assert(background_thread_indefinite_sleep(info));
+		ret = pthread_cond_wait(&info->cond, &info->mtx.lock);
+		assert(ret == 0);
+	} else {
+		assert(interval >= BACKGROUND_THREAD_MIN_INTERVAL_NS &&
+		    interval <= BACKGROUND_THREAD_INDEFINITE_SLEEP);
+		/* We need malloc clock (can be different from tv). */
+		nstime_t next_wakeup;
+		nstime_init(&next_wakeup, 0);
+		nstime_update(&next_wakeup);
+		nstime_iadd(&next_wakeup, interval);
+		assert(nstime_ns(&next_wakeup) <
+		    BACKGROUND_THREAD_INDEFINITE_SLEEP);
+		background_thread_wakeup_time_set(tsdn, info,
+		    nstime_ns(&next_wakeup));
+
+		nstime_t ts_wakeup;
+		nstime_copy(&ts_wakeup, &before_sleep);
+		nstime_iadd(&ts_wakeup, interval);
+		struct timespec ts;
+		ts.tv_sec = (size_t)nstime_sec(&ts_wakeup);
+		ts.tv_nsec = (size_t)nstime_nsec(&ts_wakeup);
+
+		assert(!background_thread_indefinite_sleep(info));
+		ret = pthread_cond_timedwait(&info->cond, &info->mtx.lock, &ts);
+		assert(ret == ETIMEDOUT || ret == 0);
+		background_thread_wakeup_time_set(tsdn, info,
+		    BACKGROUND_THREAD_INDEFINITE_SLEEP);
+	}
+	if (config_stats) {
+		gettimeofday(&tv, NULL);
+		nstime_t after_sleep;
+		nstime_init2(&after_sleep, tv.tv_sec, tv.tv_usec * 1000);
+		if (nstime_compare(&after_sleep, &before_sleep) > 0) {
+			nstime_subtract(&after_sleep, &before_sleep);
+			nstime_add(&info->tot_sleep_time, &after_sleep);
+		}
+	}
+}
+
+static bool
+background_thread_pause_check(tsdn_t *tsdn, background_thread_info_t *info) {
+	if (unlikely(info->state == background_thread_paused)) {
+		malloc_mutex_unlock(tsdn, &info->mtx);
+		/* Wait on global lock to update status. */
+		malloc_mutex_lock(tsdn, &background_thread_lock);
+		malloc_mutex_unlock(tsdn, &background_thread_lock);
+		malloc_mutex_lock(tsdn, &info->mtx);
+		return true;
+	}
+
+	return false;
+}
+
+static inline void
+background_work_sleep_once(tsdn_t *tsdn, background_thread_info_t *info, unsigned ind) {
+	uint64_t min_interval = BACKGROUND_THREAD_INDEFINITE_SLEEP;
+	unsigned narenas = narenas_total_get();
+
+	for (unsigned i = ind; i < narenas; i += ncpus) {
+		arena_t *arena = arena_get(tsdn, i, false);
+		if (!arena) {
+			continue;
+		}
+		arena_decay(tsdn, arena, true, false);
+		if (min_interval == BACKGROUND_THREAD_MIN_INTERVAL_NS) {
+			/* Min interval will be used. */
+			continue;
+		}
+		uint64_t interval = arena_decay_compute_purge_interval(tsdn,
+		    arena);
+		assert(interval >= BACKGROUND_THREAD_MIN_INTERVAL_NS);
+		if (min_interval > interval) {
+			min_interval = interval;
+		}
+	}
+	background_thread_sleep(tsdn, info, min_interval);
+}
+
+static bool
+background_threads_disable_single(tsd_t *tsd, background_thread_info_t *info) {
+	if (info == &background_thread_info[0]) {
+		malloc_mutex_assert_owner(tsd_tsdn(tsd),
+		    &background_thread_lock);
+	} else {
+		malloc_mutex_assert_not_owner(tsd_tsdn(tsd),
+		    &background_thread_lock);
+	}
+
+	pre_reentrancy(tsd, NULL);
+	malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+	bool has_thread;
+	assert(info->state != background_thread_paused);
+	if (info->state == background_thread_started) {
+		has_thread = true;
+		info->state = background_thread_stopped;
+		pthread_cond_signal(&info->cond);
+	} else {
+		has_thread = false;
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+
+	if (!has_thread) {
+		post_reentrancy(tsd);
+		return false;
+	}
+	void *ret;
+	if (pthread_join(info->thread, &ret)) {
+		post_reentrancy(tsd);
+		return true;
+	}
+	assert(ret == NULL);
+	n_background_threads--;
+	post_reentrancy(tsd);
+
+	return false;
+}
+
+static void *background_thread_entry(void *ind_arg);
+
+static int
+background_thread_create_signals_masked(pthread_t *thread,
+    const pthread_attr_t *attr, void *(*start_routine)(void *), void *arg) {
+	/*
+	 * Mask signals during thread creation so that the thread inherits
+	 * an empty signal set.
+	 */
+	sigset_t set;
+	sigfillset(&set);
+	sigset_t oldset;
+	int mask_err = pthread_sigmask(SIG_SETMASK, &set, &oldset);
+	if (mask_err != 0) {
+		return mask_err;
+	}
+	int create_err = pthread_create_wrapper(thread, attr, start_routine,
+	    arg);
+	/*
+	 * Restore the signal mask.  Failure to restore the signal mask here
+	 * changes program behavior.
+	 */
+	int restore_err = pthread_sigmask(SIG_SETMASK, &oldset, NULL);
+	if (restore_err != 0) {
+		malloc_printf("<jemalloc>: background thread creation "
+		    "failed (%d), and signal mask restoration failed "
+		    "(%d)\n", create_err, restore_err);
+		if (opt_abort) {
+			abort();
+		}
+	}
+	return create_err;
+}
+
+static void
+check_background_thread_creation(tsd_t *tsd, unsigned *n_created,
+    bool *created_threads) {
+	if (likely(*n_created == n_background_threads)) {
+		return;
+	}
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_info[0].mtx);
+label_restart:
+	malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock);
+	for (unsigned i = 1; i < ncpus; i++) {
+		if (created_threads[i]) {
+			continue;
+		}
+		background_thread_info_t *info = &background_thread_info[i];
+		malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+		assert(info->state != background_thread_paused);
+		bool create = (info->state == background_thread_started);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+		if (!create) {
+			continue;
+		}
+
+		/*
+		 * To avoid deadlock with prefork handlers (which waits for the
+		 * mutex held here), unlock before calling pthread_create().
+		 */
+		malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock);
+
+		pre_reentrancy(tsd, NULL);
+		int err = background_thread_create_signals_masked(&info->thread,
+		    NULL, background_thread_entry, (void *)(uintptr_t)i);
+		post_reentrancy(tsd);
+
+		if (err == 0) {
+			(*n_created)++;
+			created_threads[i] = true;
+		} else {
+			malloc_printf("<jemalloc>: background thread "
+			    "creation failed (%d)\n", err);
+			if (opt_abort) {
+				abort();
+			}
+		}
+		/* Restart since we unlocked. */
+		goto label_restart;
+	}
+	malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_info[0].mtx);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock);
+}
+
+static void
+background_thread0_work(tsd_t *tsd) {
+	/* Thread0 is also responsible for launching / terminating threads. */
+	VARIABLE_ARRAY(bool, created_threads, ncpus);
+	unsigned i;
+	for (i = 1; i < ncpus; i++) {
+		created_threads[i] = false;
+	}
+	/* Start working, and create more threads when asked. */
+	unsigned n_created = 1;
+	while (background_thread_info[0].state != background_thread_stopped) {
+		if (background_thread_pause_check(tsd_tsdn(tsd),
+		    &background_thread_info[0])) {
+			continue;
+		}
+		check_background_thread_creation(tsd, &n_created,
+		    (bool *)&created_threads);
+		background_work_sleep_once(tsd_tsdn(tsd),
+		    &background_thread_info[0], 0);
+	}
+
+	/*
+	 * Shut down other threads at exit.  Note that the ctl thread is holding
+	 * the global background_thread mutex (and is waiting) for us.
+	 */
+	assert(!background_thread_enabled());
+	for (i = 1; i < ncpus; i++) {
+		background_thread_info_t *info = &background_thread_info[i];
+		assert(info->state != background_thread_paused);
+		if (created_threads[i]) {
+			background_threads_disable_single(tsd, info);
+		} else {
+			malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+			/* Clear in case the thread wasn't created. */
+			info->state = background_thread_stopped;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+		}
+	}
+	background_thread_info[0].state = background_thread_stopped;
+	assert(n_background_threads == 1);
+}
+
+static void
+background_work(tsd_t *tsd, unsigned ind) {
+	background_thread_info_t *info = &background_thread_info[ind];
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+	background_thread_wakeup_time_set(tsd_tsdn(tsd), info,
+	    BACKGROUND_THREAD_INDEFINITE_SLEEP);
+	if (ind == 0) {
+		background_thread0_work(tsd);
+	} else {
+		while (info->state != background_thread_stopped) {
+			if (background_thread_pause_check(tsd_tsdn(tsd),
+			    info)) {
+				continue;
+			}
+			background_work_sleep_once(tsd_tsdn(tsd), info, ind);
+		}
+	}
+	assert(info->state == background_thread_stopped);
+	background_thread_wakeup_time_set(tsd_tsdn(tsd), info, 0);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+}
+
+static void *
+background_thread_entry(void *ind_arg) {
+	unsigned thread_ind = (unsigned)(uintptr_t)ind_arg;
+	assert(thread_ind < ncpus);
+#ifdef JEMALLOC_HAVE_PTHREAD_SETNAME_NP
+	pthread_setname_np(pthread_self(), "jemalloc_bg_thd");
+#endif
+	if (opt_percpu_arena != percpu_arena_disabled) {
+		set_current_thread_affinity((int)thread_ind);
+	}
+	/*
+	 * Start periodic background work.  We use internal tsd which avoids
+	 * side effects, for example triggering new arena creation (which in
+	 * turn triggers another background thread creation).
+	 */
+	background_work(tsd_internal_fetch(), thread_ind);
+	assert(pthread_equal(pthread_self(),
+	    background_thread_info[thread_ind].thread));
+
+	return NULL;
+}
+
+static void
+background_thread_init(tsd_t *tsd, background_thread_info_t *info) {
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock);
+	info->state = background_thread_started;
+	background_thread_info_init(tsd_tsdn(tsd), info);
+	n_background_threads++;
+}
+
+/* Create a new background thread if needed. */
+bool
+background_thread_create(tsd_t *tsd, unsigned arena_ind) {
+	assert(have_background_thread);
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock);
+
+	/* We create at most NCPUs threads. */
+	size_t thread_ind = arena_ind % ncpus;
+	background_thread_info_t *info = &background_thread_info[thread_ind];
+
+	bool need_new_thread;
+	malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+	need_new_thread = background_thread_enabled() &&
+	    (info->state == background_thread_stopped);
+	if (need_new_thread) {
+		background_thread_init(tsd, info);
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+	if (!need_new_thread) {
+		return false;
+	}
+	if (arena_ind != 0) {
+		/* Threads are created asynchronously by Thread 0. */
+		background_thread_info_t *t0 = &background_thread_info[0];
+		malloc_mutex_lock(tsd_tsdn(tsd), &t0->mtx);
+		assert(t0->state == background_thread_started);
+		pthread_cond_signal(&t0->cond);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &t0->mtx);
+
+		return false;
+	}
+
+	pre_reentrancy(tsd, NULL);
+	/*
+	 * To avoid complications (besides reentrancy), create internal
+	 * background threads with the underlying pthread_create.
+	 */
+	int err = background_thread_create_signals_masked(&info->thread, NULL,
+	    background_thread_entry, (void *)thread_ind);
+	post_reentrancy(tsd);
+
+	if (err != 0) {
+		malloc_printf("<jemalloc>: arena 0 background thread creation "
+		    "failed (%d)\n", err);
+		malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+		info->state = background_thread_stopped;
+		n_background_threads--;
+		malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+
+		return true;
+	}
+
+	return false;
+}
+
+bool
+background_threads_enable(tsd_t *tsd) {
+	assert(n_background_threads == 0);
+	assert(background_thread_enabled());
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock);
+
+	VARIABLE_ARRAY(bool, marked, ncpus);
+	unsigned i, nmarked;
+	for (i = 0; i < ncpus; i++) {
+		marked[i] = false;
+	}
+	nmarked = 0;
+	/* Mark the threads we need to create for thread 0. */
+	unsigned n = narenas_total_get();
+	for (i = 1; i < n; i++) {
+		if (marked[i % ncpus] ||
+		    arena_get(tsd_tsdn(tsd), i, false) == NULL) {
+			continue;
+		}
+		background_thread_info_t *info = &background_thread_info[i];
+		malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+		assert(info->state == background_thread_stopped);
+		background_thread_init(tsd, info);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+		marked[i % ncpus] = true;
+		if (++nmarked == ncpus) {
+			break;
+		}
+	}
+
+	return background_thread_create(tsd, 0);
+}
+
+bool
+background_threads_disable(tsd_t *tsd) {
+	assert(!background_thread_enabled());
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &background_thread_lock);
+
+	/* Thread 0 will be responsible for terminating other threads. */
+	if (background_threads_disable_single(tsd,
+	    &background_thread_info[0])) {
+		return true;
+	}
+	assert(n_background_threads == 0);
+
+	return false;
+}
+
+/* Check if we need to signal the background thread early. */
+void
+background_thread_interval_check(tsdn_t *tsdn, arena_t *arena,
+    arena_decay_t *decay, size_t npages_new) {
+	background_thread_info_t *info = arena_background_thread_info_get(
+	    arena);
+	if (malloc_mutex_trylock(tsdn, &info->mtx)) {
+		/*
+		 * Background thread may hold the mutex for a long period of
+		 * time.  We'd like to avoid the variance on application
+		 * threads.  So keep this non-blocking, and leave the work to a
+		 * future epoch.
+		 */
+		return;
+	}
+
+	if (info->state != background_thread_started) {
+		goto label_done;
+	}
+	if (malloc_mutex_trylock(tsdn, &decay->mtx)) {
+		goto label_done;
+	}
+
+	ssize_t decay_time = atomic_load_zd(&decay->time_ms, ATOMIC_RELAXED);
+	if (decay_time <= 0) {
+		/* Purging is eagerly done or disabled currently. */
+		goto label_done_unlock2;
+	}
+	uint64_t decay_interval_ns = nstime_ns(&decay->interval);
+	assert(decay_interval_ns > 0);
+
+	nstime_t diff;
+	nstime_init(&diff, background_thread_wakeup_time_get(info));
+	if (nstime_compare(&diff, &decay->epoch) <= 0) {
+		goto label_done_unlock2;
+	}
+	nstime_subtract(&diff, &decay->epoch);
+	if (nstime_ns(&diff) < BACKGROUND_THREAD_MIN_INTERVAL_NS) {
+		goto label_done_unlock2;
+	}
+
+	if (npages_new > 0) {
+		size_t n_epoch = (size_t)(nstime_ns(&diff) / decay_interval_ns);
+		/*
+		 * Compute how many new pages we would need to purge by the next
+		 * wakeup, which is used to determine if we should signal the
+		 * background thread.
+		 */
+		uint64_t npurge_new;
+		if (n_epoch >= SMOOTHSTEP_NSTEPS) {
+			npurge_new = npages_new;
+		} else {
+			uint64_t h_steps_max = h_steps[SMOOTHSTEP_NSTEPS - 1];
+			assert(h_steps_max >=
+			    h_steps[SMOOTHSTEP_NSTEPS - 1 - n_epoch]);
+			npurge_new = npages_new * (h_steps_max -
+			    h_steps[SMOOTHSTEP_NSTEPS - 1 - n_epoch]);
+			npurge_new >>= SMOOTHSTEP_BFP;
+		}
+		info->npages_to_purge_new += npurge_new;
+	}
+
+	bool should_signal;
+	if (info->npages_to_purge_new > BACKGROUND_THREAD_NPAGES_THRESHOLD) {
+		should_signal = true;
+	} else if (unlikely(background_thread_indefinite_sleep(info)) &&
+	    (extents_npages_get(&arena->extents_dirty) > 0 ||
+	    extents_npages_get(&arena->extents_muzzy) > 0 ||
+	    info->npages_to_purge_new > 0)) {
+		should_signal = true;
+	} else {
+		should_signal = false;
+	}
+
+	if (should_signal) {
+		info->npages_to_purge_new = 0;
+		pthread_cond_signal(&info->cond);
+	}
+label_done_unlock2:
+	malloc_mutex_unlock(tsdn, &decay->mtx);
+label_done:
+	malloc_mutex_unlock(tsdn, &info->mtx);
+}
+
+void
+background_thread_prefork0(tsdn_t *tsdn) {
+	malloc_mutex_prefork(tsdn, &background_thread_lock);
+	background_thread_enabled_at_fork = background_thread_enabled();
+}
+
+void
+background_thread_prefork1(tsdn_t *tsdn) {
+	for (unsigned i = 0; i < ncpus; i++) {
+		malloc_mutex_prefork(tsdn, &background_thread_info[i].mtx);
+	}
+}
+
+void
+background_thread_postfork_parent(tsdn_t *tsdn) {
+	for (unsigned i = 0; i < ncpus; i++) {
+		malloc_mutex_postfork_parent(tsdn,
+		    &background_thread_info[i].mtx);
+	}
+	malloc_mutex_postfork_parent(tsdn, &background_thread_lock);
+}
+
+void
+background_thread_postfork_child(tsdn_t *tsdn) {
+	for (unsigned i = 0; i < ncpus; i++) {
+		malloc_mutex_postfork_child(tsdn,
+		    &background_thread_info[i].mtx);
+	}
+	malloc_mutex_postfork_child(tsdn, &background_thread_lock);
+	if (!background_thread_enabled_at_fork) {
+		return;
+	}
+
+	/* Clear background_thread state (reset to disabled for child). */
+	malloc_mutex_lock(tsdn, &background_thread_lock);
+	n_background_threads = 0;
+	background_thread_enabled_set(tsdn, false);
+	for (unsigned i = 0; i < ncpus; i++) {
+		background_thread_info_t *info = &background_thread_info[i];
+		malloc_mutex_lock(tsdn, &info->mtx);
+		info->state = background_thread_stopped;
+		int ret = pthread_cond_init(&info->cond, NULL);
+		assert(ret == 0);
+		background_thread_info_init(tsdn, info);
+		malloc_mutex_unlock(tsdn, &info->mtx);
+	}
+	malloc_mutex_unlock(tsdn, &background_thread_lock);
+}
+
+bool
+background_thread_stats_read(tsdn_t *tsdn, background_thread_stats_t *stats) {
+	assert(config_stats);
+	malloc_mutex_lock(tsdn, &background_thread_lock);
+	if (!background_thread_enabled()) {
+		malloc_mutex_unlock(tsdn, &background_thread_lock);
+		return true;
+	}
+
+	stats->num_threads = n_background_threads;
+	uint64_t num_runs = 0;
+	nstime_init(&stats->run_interval, 0);
+	for (unsigned i = 0; i < ncpus; i++) {
+		background_thread_info_t *info = &background_thread_info[i];
+		malloc_mutex_lock(tsdn, &info->mtx);
+		if (info->state != background_thread_stopped) {
+			num_runs += info->tot_n_runs;
+			nstime_add(&stats->run_interval, &info->tot_sleep_time);
+		}
+		malloc_mutex_unlock(tsdn, &info->mtx);
+	}
+	stats->num_runs = num_runs;
+	if (num_runs > 0) {
+		nstime_idivide(&stats->run_interval, num_runs);
+	}
+	malloc_mutex_unlock(tsdn, &background_thread_lock);
+
+	return false;
+}
+
+#undef BACKGROUND_THREAD_NPAGES_THRESHOLD
+#undef BILLION
+#undef BACKGROUND_THREAD_MIN_INTERVAL_NS
+
+/*
+ * When lazy lock is enabled, we need to make sure setting isthreaded before
+ * taking any background_thread locks.  This is called early in ctl (instead of
+ * wait for the pthread_create calls to trigger) because the mutex is required
+ * before creating background threads.
+ */
+void
+background_thread_ctl_init(tsdn_t *tsdn) {
+	malloc_mutex_assert_not_owner(tsdn, &background_thread_lock);
+#ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER
+	pthread_once(&once_control, pthread_create_wrapper_once);
+#endif
+}
+
+#endif /* defined(JEMALLOC_BACKGROUND_THREAD) */
+
+bool
+background_thread_boot0(void) {
+	if (!have_background_thread && opt_background_thread) {
+		malloc_printf("<jemalloc>: option background_thread currently "
+		    "supports pthread only\n");
+		return true;
+	}
+
+#ifdef JEMALLOC_PTHREAD_CREATE_WRAPPER
+	pthread_create_fptr = dlsym(RTLD_NEXT, "pthread_create");
+	if (pthread_create_fptr == NULL) {
+		can_enable_background_thread = false;
+		if (config_lazy_lock || opt_background_thread) {
+			malloc_write("<jemalloc>: Error in dlsym(RTLD_NEXT, "
+			    "\"pthread_create\")\n");
+			abort();
+		}
+	} else {
+		can_enable_background_thread = true;
+	}
+#endif
+	return false;
+}
+
+bool
+background_thread_boot1(tsdn_t *tsdn) {
+#ifdef JEMALLOC_BACKGROUND_THREAD
+	assert(have_background_thread);
+	assert(narenas_total_get() > 0);
+
+	background_thread_enabled_set(tsdn, opt_background_thread);
+	if (malloc_mutex_init(&background_thread_lock,
+	    "background_thread_global",
+	    WITNESS_RANK_BACKGROUND_THREAD_GLOBAL,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+	if (opt_background_thread) {
+		background_thread_ctl_init(tsdn);
+	}
+
+	background_thread_info = (background_thread_info_t *)base_alloc(tsdn,
+	    b0get(), ncpus * sizeof(background_thread_info_t), CACHELINE);
+	if (background_thread_info == NULL) {
+		return true;
+	}
+
+	for (unsigned i = 0; i < ncpus; i++) {
+		background_thread_info_t *info = &background_thread_info[i];
+		/* Thread mutex is rank_inclusive because of thread0. */
+		if (malloc_mutex_init(&info->mtx, "background_thread",
+		    WITNESS_RANK_BACKGROUND_THREAD,
+		    malloc_mutex_address_ordered)) {
+			return true;
+		}
+		if (pthread_cond_init(&info->cond, NULL)) {
+			return true;
+		}
+		malloc_mutex_lock(tsdn, &info->mtx);
+		info->state = background_thread_stopped;
+		background_thread_info_init(tsdn, info);
+		malloc_mutex_unlock(tsdn, &info->mtx);
+	}
+#endif
+
+	return false;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/base.c b/modules/worldengine/deps/jemalloc/src/base.c
index 4e62e8fa91..97078b134d 100644
--- a/modules/worldengine/deps/jemalloc/src/base.c
+++ b/modules/worldengine/deps/jemalloc/src/base.c
@@ -1,142 +1,402 @@
-#define	JEMALLOC_BASE_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_BASE_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/sz.h"
 
 /******************************************************************************/
 /* Data. */
 
-static malloc_mutex_t	base_mtx;
-
-/*
- * Current pages that are being used for internal memory allocations.  These
- * pages are carved up in cacheline-size quanta, so that there is no chance of
- * false cache line sharing.
- */
-static void		*base_pages;
-static void		*base_next_addr;
-static void		*base_past_addr; /* Addr immediately past base_pages. */
-static extent_node_t	*base_nodes;
+static base_t	*b0;
 
 /******************************************************************************/
-/* Function prototypes for non-inline static functions. */
 
-static bool	base_pages_alloc(size_t minsize);
+static void *
+base_map(tsdn_t *tsdn, extent_hooks_t *extent_hooks, unsigned ind, size_t size) {
+	void *addr;
+	bool zero = true;
+	bool commit = true;
 
-/******************************************************************************/
+	assert(size == HUGEPAGE_CEILING(size));
+
+	if (extent_hooks == &extent_hooks_default) {
+		addr = extent_alloc_mmap(NULL, size, PAGE, &zero, &commit);
+	} else {
+		/* No arena context as we are creating new arenas. */
+		tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn);
+		pre_reentrancy(tsd, NULL);
+		addr = extent_hooks->alloc(extent_hooks, NULL, size, PAGE,
+		    &zero, &commit, ind);
+		post_reentrancy(tsd);
+	}
+
+	return addr;
+}
+
+static void
+base_unmap(tsdn_t *tsdn, extent_hooks_t *extent_hooks, unsigned ind, void *addr,
+    size_t size) {
+	/*
+	 * Cascade through dalloc, decommit, purge_forced, and purge_lazy,
+	 * stopping at first success.  This cascade is performed for consistency
+	 * with the cascade in extent_dalloc_wrapper() because an application's
+	 * custom hooks may not support e.g. dalloc.  This function is only ever
+	 * called as a side effect of arena destruction, so although it might
+	 * seem pointless to do anything besides dalloc here, the application
+	 * may in fact want the end state of all associated virtual memory to be
+	 * in some consistent-but-allocated state.
+	 */
+	if (extent_hooks == &extent_hooks_default) {
+		if (!extent_dalloc_mmap(addr, size)) {
+			return;
+		}
+		if (!pages_decommit(addr, size)) {
+			return;
+		}
+		if (!pages_purge_forced(addr, size)) {
+			return;
+		}
+		if (!pages_purge_lazy(addr, size)) {
+			return;
+		}
+		/* Nothing worked.  This should never happen. */
+		not_reached();
+	} else {
+		tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn);
+		pre_reentrancy(tsd, NULL);
+		if (extent_hooks->dalloc != NULL &&
+		    !extent_hooks->dalloc(extent_hooks, addr, size, true,
+		    ind)) {
+			goto label_done;
+		}
+		if (extent_hooks->decommit != NULL &&
+		    !extent_hooks->decommit(extent_hooks, addr, size, 0, size,
+		    ind)) {
+			goto label_done;
+		}
+		if (extent_hooks->purge_forced != NULL &&
+		    !extent_hooks->purge_forced(extent_hooks, addr, size, 0,
+		    size, ind)) {
+			goto label_done;
+		}
+		if (extent_hooks->purge_lazy != NULL &&
+		    !extent_hooks->purge_lazy(extent_hooks, addr, size, 0, size,
+		    ind)) {
+			goto label_done;
+		}
+		/* Nothing worked.  That's the application's problem. */
+	label_done:
+		post_reentrancy(tsd);
+		return;
+	}
+}
 
-static bool
-base_pages_alloc(size_t minsize)
-{
-	size_t csize;
-	bool zero;
+static void
+base_extent_init(size_t *extent_sn_next, extent_t *extent, void *addr,
+    size_t size) {
+	size_t sn;
 
-	assert(minsize != 0);
-	csize = CHUNK_CEILING(minsize);
-	zero = false;
-	base_pages = chunk_alloc(csize, chunksize, true, &zero,
-	    chunk_dss_prec_get());
-	if (base_pages == NULL)
-		return (true);
-	base_next_addr = base_pages;
-	base_past_addr = (void *)((uintptr_t)base_pages + csize);
+	sn = *extent_sn_next;
+	(*extent_sn_next)++;
 
-	return (false);
+	extent_binit(extent, addr, size, sn);
 }
 
-void *
-base_alloc(size_t size)
-{
+static void *
+base_extent_bump_alloc_helper(extent_t *extent, size_t *gap_size, size_t size,
+    size_t alignment) {
 	void *ret;
-	size_t csize;
 
-	/* Round size up to nearest multiple of the cacheline size. */
-	csize = CACHELINE_CEILING(size);
+	assert(alignment == ALIGNMENT_CEILING(alignment, QUANTUM));
+	assert(size == ALIGNMENT_CEILING(size, alignment));
 
-	malloc_mutex_lock(&base_mtx);
-	/* Make sure there's enough space for the allocation. */
-	if ((uintptr_t)base_next_addr + csize > (uintptr_t)base_past_addr) {
-		if (base_pages_alloc(csize)) {
-			malloc_mutex_unlock(&base_mtx);
-			return (NULL);
-		}
+	*gap_size = ALIGNMENT_CEILING((uintptr_t)extent_addr_get(extent),
+	    alignment) - (uintptr_t)extent_addr_get(extent);
+	ret = (void *)((uintptr_t)extent_addr_get(extent) + *gap_size);
+	assert(extent_bsize_get(extent) >= *gap_size + size);
+	extent_binit(extent, (void *)((uintptr_t)extent_addr_get(extent) +
+	    *gap_size + size), extent_bsize_get(extent) - *gap_size - size,
+	    extent_sn_get(extent));
+	return ret;
+}
+
+static void
+base_extent_bump_alloc_post(tsdn_t *tsdn, base_t *base, extent_t *extent,
+    size_t gap_size, void *addr, size_t size) {
+	if (extent_bsize_get(extent) > 0) {
+		/*
+		 * Compute the index for the largest size class that does not
+		 * exceed extent's size.
+		 */
+		szind_t index_floor =
+		    sz_size2index(extent_bsize_get(extent) + 1) - 1;
+		extent_heap_insert(&base->avail[index_floor], extent);
 	}
-	/* Allocate. */
-	ret = base_next_addr;
-	base_next_addr = (void *)((uintptr_t)base_next_addr + csize);
-	malloc_mutex_unlock(&base_mtx);
-	VALGRIND_MAKE_MEM_UNDEFINED(ret, csize);
 
-	return (ret);
+	if (config_stats) {
+		base->allocated += size;
+		/*
+		 * Add one PAGE to base_resident for every page boundary that is
+		 * crossed by the new allocation.
+		 */
+		base->resident += PAGE_CEILING((uintptr_t)addr + size) -
+		    PAGE_CEILING((uintptr_t)addr - gap_size);
+		assert(base->allocated <= base->resident);
+		assert(base->resident <= base->mapped);
+	}
 }
 
-void *
-base_calloc(size_t number, size_t size)
-{
-	void *ret = base_alloc(number * size);
+static void *
+base_extent_bump_alloc(tsdn_t *tsdn, base_t *base, extent_t *extent,
+    size_t size, size_t alignment) {
+	void *ret;
+	size_t gap_size;
+
+	ret = base_extent_bump_alloc_helper(extent, &gap_size, size, alignment);
+	base_extent_bump_alloc_post(tsdn, base, extent, gap_size, ret, size);
+	return ret;
+}
+
+/*
+ * Allocate a block of virtual memory that is large enough to start with a
+ * base_block_t header, followed by an object of specified size and alignment.
+ * On success a pointer to the initialized base_block_t header is returned.
+ */
+static base_block_t *
+base_block_alloc(tsdn_t *tsdn, extent_hooks_t *extent_hooks, unsigned ind,
+    pszind_t *pind_last, size_t *extent_sn_next, size_t size,
+    size_t alignment) {
+	alignment = ALIGNMENT_CEILING(alignment, QUANTUM);
+	size_t usize = ALIGNMENT_CEILING(size, alignment);
+	size_t header_size = sizeof(base_block_t);
+	size_t gap_size = ALIGNMENT_CEILING(header_size, alignment) -
+	    header_size;
+	/*
+	 * Create increasingly larger blocks in order to limit the total number
+	 * of disjoint virtual memory ranges.  Choose the next size in the page
+	 * size class series (skipping size classes that are not a multiple of
+	 * HUGEPAGE), or a size large enough to satisfy the requested size and
+	 * alignment, whichever is larger.
+	 */
+	size_t min_block_size = HUGEPAGE_CEILING(sz_psz2u(header_size + gap_size
+	    + usize));
+	pszind_t pind_next = (*pind_last + 1 < NPSIZES) ? *pind_last + 1 :
+	    *pind_last;
+	size_t next_block_size = HUGEPAGE_CEILING(sz_pind2sz(pind_next));
+	size_t block_size = (min_block_size > next_block_size) ? min_block_size
+	    : next_block_size;
+	base_block_t *block = (base_block_t *)base_map(tsdn, extent_hooks, ind,
+	    block_size);
+	if (block == NULL) {
+		return NULL;
+	}
+	*pind_last = sz_psz2ind(block_size);
+	block->size = block_size;
+	block->next = NULL;
+	assert(block_size >= header_size);
+	base_extent_init(extent_sn_next, &block->extent,
+	    (void *)((uintptr_t)block + header_size), block_size - header_size);
+	return block;
+}
 
-	if (ret != NULL)
-		memset(ret, 0, number * size);
+/*
+ * Allocate an extent that is at least as large as specified size, with
+ * specified alignment.
+ */
+static extent_t *
+base_extent_alloc(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment) {
+	malloc_mutex_assert_owner(tsdn, &base->mtx);
 
-	return (ret);
+	extent_hooks_t *extent_hooks = base_extent_hooks_get(base);
+	/*
+	 * Drop mutex during base_block_alloc(), because an extent hook will be
+	 * called.
+	 */
+	malloc_mutex_unlock(tsdn, &base->mtx);
+	base_block_t *block = base_block_alloc(tsdn, extent_hooks,
+	    base_ind_get(base), &base->pind_last, &base->extent_sn_next, size,
+	    alignment);
+	malloc_mutex_lock(tsdn, &base->mtx);
+	if (block == NULL) {
+		return NULL;
+	}
+	block->next = base->blocks;
+	base->blocks = block;
+	if (config_stats) {
+		base->allocated += sizeof(base_block_t);
+		base->resident += PAGE_CEILING(sizeof(base_block_t));
+		base->mapped += block->size;
+		assert(base->allocated <= base->resident);
+		assert(base->resident <= base->mapped);
+	}
+	return &block->extent;
 }
 
-extent_node_t *
-base_node_alloc(void)
-{
-	extent_node_t *ret;
+base_t *
+b0get(void) {
+	return b0;
+}
 
-	malloc_mutex_lock(&base_mtx);
-	if (base_nodes != NULL) {
-		ret = base_nodes;
-		base_nodes = *(extent_node_t **)ret;
-		malloc_mutex_unlock(&base_mtx);
-		VALGRIND_MAKE_MEM_UNDEFINED(ret, sizeof(extent_node_t));
-	} else {
-		malloc_mutex_unlock(&base_mtx);
-		ret = (extent_node_t *)base_alloc(sizeof(extent_node_t));
+base_t *
+base_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) {
+	pszind_t pind_last = 0;
+	size_t extent_sn_next = 0;
+	base_block_t *block = base_block_alloc(tsdn, extent_hooks, ind,
+	    &pind_last, &extent_sn_next, sizeof(base_t), QUANTUM);
+	if (block == NULL) {
+		return NULL;
 	}
 
-	return (ret);
+	size_t gap_size;
+	size_t base_alignment = CACHELINE;
+	size_t base_size = ALIGNMENT_CEILING(sizeof(base_t), base_alignment);
+	base_t *base = (base_t *)base_extent_bump_alloc_helper(&block->extent,
+	    &gap_size, base_size, base_alignment);
+	base->ind = ind;
+	atomic_store_p(&base->extent_hooks, extent_hooks, ATOMIC_RELAXED);
+	if (malloc_mutex_init(&base->mtx, "base", WITNESS_RANK_BASE,
+	    malloc_mutex_rank_exclusive)) {
+		base_unmap(tsdn, extent_hooks, ind, block, block->size);
+		return NULL;
+	}
+	base->pind_last = pind_last;
+	base->extent_sn_next = extent_sn_next;
+	base->blocks = block;
+	for (szind_t i = 0; i < NSIZES; i++) {
+		extent_heap_new(&base->avail[i]);
+	}
+	if (config_stats) {
+		base->allocated = sizeof(base_block_t);
+		base->resident = PAGE_CEILING(sizeof(base_block_t));
+		base->mapped = block->size;
+		assert(base->allocated <= base->resident);
+		assert(base->resident <= base->mapped);
+	}
+	base_extent_bump_alloc_post(tsdn, base, &block->extent, gap_size, base,
+	    base_size);
+
+	return base;
 }
 
 void
-base_node_dealloc(extent_node_t *node)
-{
+base_delete(tsdn_t *tsdn, base_t *base) {
+	extent_hooks_t *extent_hooks = base_extent_hooks_get(base);
+	base_block_t *next = base->blocks;
+	do {
+		base_block_t *block = next;
+		next = block->next;
+		base_unmap(tsdn, extent_hooks, base_ind_get(base), block,
+		    block->size);
+	} while (next != NULL);
+}
 
-	VALGRIND_MAKE_MEM_UNDEFINED(node, sizeof(extent_node_t));
-	malloc_mutex_lock(&base_mtx);
-	*(extent_node_t **)node = base_nodes;
-	base_nodes = node;
-	malloc_mutex_unlock(&base_mtx);
+extent_hooks_t *
+base_extent_hooks_get(base_t *base) {
+	return (extent_hooks_t *)atomic_load_p(&base->extent_hooks,
+	    ATOMIC_ACQUIRE);
 }
 
-bool
-base_boot(void)
-{
+extent_hooks_t *
+base_extent_hooks_set(base_t *base, extent_hooks_t *extent_hooks) {
+	extent_hooks_t *old_extent_hooks = base_extent_hooks_get(base);
+	atomic_store_p(&base->extent_hooks, extent_hooks, ATOMIC_RELEASE);
+	return old_extent_hooks;
+}
+
+static void *
+base_alloc_impl(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment,
+    size_t *esn) {
+	alignment = QUANTUM_CEILING(alignment);
+	size_t usize = ALIGNMENT_CEILING(size, alignment);
+	size_t asize = usize + alignment - QUANTUM;
+
+	extent_t *extent = NULL;
+	malloc_mutex_lock(tsdn, &base->mtx);
+	for (szind_t i = sz_size2index(asize); i < NSIZES; i++) {
+		extent = extent_heap_remove_first(&base->avail[i]);
+		if (extent != NULL) {
+			/* Use existing space. */
+			break;
+		}
+	}
+	if (extent == NULL) {
+		/* Try to allocate more space. */
+		extent = base_extent_alloc(tsdn, base, usize, alignment);
+	}
+	void *ret;
+	if (extent == NULL) {
+		ret = NULL;
+		goto label_return;
+	}
 
-	base_nodes = NULL;
-	if (malloc_mutex_init(&base_mtx))
-		return (true);
+	ret = base_extent_bump_alloc(tsdn, base, extent, usize, alignment);
+	if (esn != NULL) {
+		*esn = extent_sn_get(extent);
+	}
+label_return:
+	malloc_mutex_unlock(tsdn, &base->mtx);
+	return ret;
+}
 
-	return (false);
+/*
+ * base_alloc() returns zeroed memory, which is always demand-zeroed for the
+ * auto arenas, in order to make multi-page sparse data structures such as radix
+ * tree nodes efficient with respect to physical memory usage.  Upon success a
+ * pointer to at least size bytes with specified alignment is returned.  Note
+ * that size is rounded up to the nearest multiple of alignment to avoid false
+ * sharing.
+ */
+void *
+base_alloc(tsdn_t *tsdn, base_t *base, size_t size, size_t alignment) {
+	return base_alloc_impl(tsdn, base, size, alignment, NULL);
+}
+
+extent_t *
+base_alloc_extent(tsdn_t *tsdn, base_t *base) {
+	size_t esn;
+	extent_t *extent = base_alloc_impl(tsdn, base, sizeof(extent_t),
+	    CACHELINE, &esn);
+	if (extent == NULL) {
+		return NULL;
+	}
+	extent_esn_set(extent, esn);
+	return extent;
 }
 
 void
-base_prefork(void)
-{
+base_stats_get(tsdn_t *tsdn, base_t *base, size_t *allocated, size_t *resident,
+    size_t *mapped) {
+	cassert(config_stats);
 
-	malloc_mutex_prefork(&base_mtx);
+	malloc_mutex_lock(tsdn, &base->mtx);
+	assert(base->allocated <= base->resident);
+	assert(base->resident <= base->mapped);
+	*allocated = base->allocated;
+	*resident = base->resident;
+	*mapped = base->mapped;
+	malloc_mutex_unlock(tsdn, &base->mtx);
 }
 
 void
-base_postfork_parent(void)
-{
+base_prefork(tsdn_t *tsdn, base_t *base) {
+	malloc_mutex_prefork(tsdn, &base->mtx);
+}
 
-	malloc_mutex_postfork_parent(&base_mtx);
+void
+base_postfork_parent(tsdn_t *tsdn, base_t *base) {
+	malloc_mutex_postfork_parent(tsdn, &base->mtx);
 }
 
 void
-base_postfork_child(void)
-{
+base_postfork_child(tsdn_t *tsdn, base_t *base) {
+	malloc_mutex_postfork_child(tsdn, &base->mtx);
+}
 
-	malloc_mutex_postfork_child(&base_mtx);
+bool
+base_boot(tsdn_t *tsdn) {
+	b0 = base_new(tsdn, 0, (extent_hooks_t *)&extent_hooks_default);
+	return (b0 == NULL);
 }
diff --git a/modules/worldengine/deps/jemalloc/src/bitmap.c b/modules/worldengine/deps/jemalloc/src/bitmap.c
index e2bd907d55..468b3178eb 100644
--- a/modules/worldengine/deps/jemalloc/src/bitmap.c
+++ b/modules/worldengine/deps/jemalloc/src/bitmap.c
@@ -1,24 +1,15 @@
-#define	JEMALLOC_BITMAP_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_BITMAP_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
 
-/******************************************************************************/
-/* Function prototypes for non-inline static functions. */
-
-static size_t	bits2groups(size_t nbits);
+#include "jemalloc/internal/assert.h"
 
 /******************************************************************************/
 
-static size_t
-bits2groups(size_t nbits)
-{
-
-	return ((nbits >> LG_BITMAP_GROUP_NBITS) +
-	    !!(nbits & BITMAP_GROUP_NBITS_MASK));
-}
+#ifdef BITMAP_USE_TREE
 
 void
-bitmap_info_init(bitmap_info_t *binfo, size_t nbits)
-{
+bitmap_info_init(bitmap_info_t *binfo, size_t nbits) {
 	unsigned i;
 	size_t group_count;
 
@@ -31,60 +22,100 @@ bitmap_info_init(bitmap_info_t *binfo, size_t nbits)
 	 * that requires only one group.
 	 */
 	binfo->levels[0].group_offset = 0;
-	group_count = bits2groups(nbits);
+	group_count = BITMAP_BITS2GROUPS(nbits);
 	for (i = 1; group_count > 1; i++) {
 		assert(i < BITMAP_MAX_LEVELS);
 		binfo->levels[i].group_offset = binfo->levels[i-1].group_offset
 		    + group_count;
-		group_count = bits2groups(group_count);
+		group_count = BITMAP_BITS2GROUPS(group_count);
 	}
 	binfo->levels[i].group_offset = binfo->levels[i-1].group_offset
 	    + group_count;
+	assert(binfo->levels[i].group_offset <= BITMAP_GROUPS_MAX);
 	binfo->nlevels = i;
 	binfo->nbits = nbits;
 }
 
-size_t
-bitmap_info_ngroups(const bitmap_info_t *binfo)
-{
-
-	return (binfo->levels[binfo->nlevels].group_offset << LG_SIZEOF_BITMAP);
-}
-
-size_t
-bitmap_size(size_t nbits)
-{
-	bitmap_info_t binfo;
-
-	bitmap_info_init(&binfo, nbits);
-	return (bitmap_info_ngroups(&binfo));
+static size_t
+bitmap_info_ngroups(const bitmap_info_t *binfo) {
+	return binfo->levels[binfo->nlevels].group_offset;
 }
 
 void
-bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo)
-{
+bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo, bool fill) {
 	size_t extra;
 	unsigned i;
 
 	/*
 	 * Bits are actually inverted with regard to the external bitmap
-	 * interface, so the bitmap starts out with all 1 bits, except for
-	 * trailing unused bits (if any).  Note that each group uses bit 0 to
-	 * correspond to the first logical bit in the group, so extra bits
-	 * are the most significant bits of the last group.
+	 * interface.
+	 */
+
+	if (fill) {
+		/* The "filled" bitmap starts out with all 0 bits. */
+		memset(bitmap, 0, bitmap_size(binfo));
+		return;
+	}
+
+	/*
+	 * The "empty" bitmap starts out with all 1 bits, except for trailing
+	 * unused bits (if any).  Note that each group uses bit 0 to correspond
+	 * to the first logical bit in the group, so extra bits are the most
+	 * significant bits of the last group.
 	 */
-	memset(bitmap, 0xffU, binfo->levels[binfo->nlevels].group_offset <<
-	    LG_SIZEOF_BITMAP);
+	memset(bitmap, 0xffU, bitmap_size(binfo));
 	extra = (BITMAP_GROUP_NBITS - (binfo->nbits & BITMAP_GROUP_NBITS_MASK))
 	    & BITMAP_GROUP_NBITS_MASK;
-	if (extra != 0)
+	if (extra != 0) {
 		bitmap[binfo->levels[1].group_offset - 1] >>= extra;
+	}
 	for (i = 1; i < binfo->nlevels; i++) {
 		size_t group_count = binfo->levels[i].group_offset -
 		    binfo->levels[i-1].group_offset;
 		extra = (BITMAP_GROUP_NBITS - (group_count &
 		    BITMAP_GROUP_NBITS_MASK)) & BITMAP_GROUP_NBITS_MASK;
-		if (extra != 0)
+		if (extra != 0) {
 			bitmap[binfo->levels[i+1].group_offset - 1] >>= extra;
+		}
 	}
 }
+
+#else /* BITMAP_USE_TREE */
+
+void
+bitmap_info_init(bitmap_info_t *binfo, size_t nbits) {
+	assert(nbits > 0);
+	assert(nbits <= (ZU(1) << LG_BITMAP_MAXBITS));
+
+	binfo->ngroups = BITMAP_BITS2GROUPS(nbits);
+	binfo->nbits = nbits;
+}
+
+static size_t
+bitmap_info_ngroups(const bitmap_info_t *binfo) {
+	return binfo->ngroups;
+}
+
+void
+bitmap_init(bitmap_t *bitmap, const bitmap_info_t *binfo, bool fill) {
+	size_t extra;
+
+	if (fill) {
+		memset(bitmap, 0, bitmap_size(binfo));
+		return;
+	}
+
+	memset(bitmap, 0xffU, bitmap_size(binfo));
+	extra = (BITMAP_GROUP_NBITS - (binfo->nbits & BITMAP_GROUP_NBITS_MASK))
+	    & BITMAP_GROUP_NBITS_MASK;
+	if (extra != 0) {
+		bitmap[binfo->ngroups - 1] >>= extra;
+	}
+}
+
+#endif /* BITMAP_USE_TREE */
+
+size_t
+bitmap_size(const bitmap_info_t *binfo) {
+	return (bitmap_info_ngroups(binfo) << LG_SIZEOF_BITMAP);
+}
diff --git a/modules/worldengine/deps/jemalloc/src/ckh.c b/modules/worldengine/deps/jemalloc/src/ckh.c
index 04c5296619..e95e0a3ed5 100644
--- a/modules/worldengine/deps/jemalloc/src/ckh.c
+++ b/modules/worldengine/deps/jemalloc/src/ckh.c
@@ -34,14 +34,24 @@
  * respectively.
  *
  ******************************************************************************/
-#define	JEMALLOC_CKH_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_CKH_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+
+#include "jemalloc/internal/ckh.h"
+
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/hash.h"
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/prng.h"
+#include "jemalloc/internal/util.h"
 
 /******************************************************************************/
 /* Function prototypes for non-inline static functions. */
 
-static bool	ckh_grow(ckh_t *ckh);
-static void	ckh_shrink(ckh_t *ckh);
+static bool	ckh_grow(tsd_t *tsd, ckh_t *ckh);
+static void	ckh_shrink(tsd_t *tsd, ckh_t *ckh);
 
 /******************************************************************************/
 
@@ -49,27 +59,26 @@ static void	ckh_shrink(ckh_t *ckh);
  * Search bucket for key and return the cell number if found; SIZE_T_MAX
  * otherwise.
  */
-JEMALLOC_INLINE_C size_t
-ckh_bucket_search(ckh_t *ckh, size_t bucket, const void *key)
-{
+static size_t
+ckh_bucket_search(ckh_t *ckh, size_t bucket, const void *key) {
 	ckhc_t *cell;
 	unsigned i;
 
 	for (i = 0; i < (ZU(1) << LG_CKH_BUCKET_CELLS); i++) {
 		cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) + i];
-		if (cell->key != NULL && ckh->keycomp(key, cell->key))
-			return ((bucket << LG_CKH_BUCKET_CELLS) + i);
+		if (cell->key != NULL && ckh->keycomp(key, cell->key)) {
+			return (bucket << LG_CKH_BUCKET_CELLS) + i;
+		}
 	}
 
-	return (SIZE_T_MAX);
+	return SIZE_T_MAX;
 }
 
 /*
  * Search table for key and return cell number if found; SIZE_T_MAX otherwise.
  */
-JEMALLOC_INLINE_C size_t
-ckh_isearch(ckh_t *ckh, const void *key)
-{
+static size_t
+ckh_isearch(ckh_t *ckh, const void *key) {
 	size_t hashes[2], bucket, cell;
 
 	assert(ckh != NULL);
@@ -79,19 +88,19 @@ ckh_isearch(ckh_t *ckh, const void *key)
 	/* Search primary bucket. */
 	bucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1);
 	cell = ckh_bucket_search(ckh, bucket, key);
-	if (cell != SIZE_T_MAX)
-		return (cell);
+	if (cell != SIZE_T_MAX) {
+		return cell;
+	}
 
 	/* Search secondary bucket. */
 	bucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1);
 	cell = ckh_bucket_search(ckh, bucket, key);
-	return (cell);
+	return cell;
 }
 
-JEMALLOC_INLINE_C bool
+static bool
 ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key,
-    const void *data)
-{
+    const void *data) {
 	ckhc_t *cell;
 	unsigned offset, i;
 
@@ -99,7 +108,8 @@ ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key,
 	 * Cycle through the cells in the bucket, starting at a random position.
 	 * The randomness avoids worst-case search overhead as buckets fill up.
 	 */
-	prng32(offset, LG_CKH_BUCKET_CELLS, ckh->prng_state, CKH_A, CKH_C);
+	offset = (unsigned)prng_lg_range_u64(&ckh->prng_state,
+	    LG_CKH_BUCKET_CELLS);
 	for (i = 0; i < (ZU(1) << LG_CKH_BUCKET_CELLS); i++) {
 		cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) +
 		    ((i + offset) & ((ZU(1) << LG_CKH_BUCKET_CELLS) - 1))];
@@ -107,11 +117,11 @@ ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key,
 			cell->key = key;
 			cell->data = data;
 			ckh->count++;
-			return (false);
+			return false;
 		}
 	}
 
-	return (true);
+	return true;
 }
 
 /*
@@ -120,10 +130,9 @@ ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key,
  * eviction/relocation procedure until either success or detection of an
  * eviction/relocation bucket cycle.
  */
-JEMALLOC_INLINE_C bool
+static bool
 ckh_evict_reloc_insert(ckh_t *ckh, size_t argbucket, void const **argkey,
-    void const **argdata)
-{
+    void const **argdata) {
 	const void *key, *data, *tkey, *tdata;
 	ckhc_t *cell;
 	size_t hashes[2], bucket, tbucket;
@@ -141,7 +150,8 @@ ckh_evict_reloc_insert(ckh_t *ckh, size_t argbucket, void const **argkey,
 		 * were an item for which both hashes indicated the same
 		 * bucket.
 		 */
-		prng32(i, LG_CKH_BUCKET_CELLS, ckh->prng_state, CKH_A, CKH_C);
+		i = (unsigned)prng_lg_range_u64(&ckh->prng_state,
+		    LG_CKH_BUCKET_CELLS);
 		cell = &ckh->tab[(bucket << LG_CKH_BUCKET_CELLS) + i];
 		assert(cell->key != NULL);
 
@@ -181,18 +191,18 @@ ckh_evict_reloc_insert(ckh_t *ckh, size_t argbucket, void const **argkey,
 		if (tbucket == argbucket) {
 			*argkey = key;
 			*argdata = data;
-			return (true);
+			return true;
 		}
 
 		bucket = tbucket;
-		if (ckh_try_bucket_insert(ckh, bucket, key, data) == false)
-			return (false);
+		if (!ckh_try_bucket_insert(ckh, bucket, key, data)) {
+			return false;
+		}
 	}
 }
 
-JEMALLOC_INLINE_C bool
-ckh_try_insert(ckh_t *ckh, void const**argkey, void const**argdata)
-{
+static bool
+ckh_try_insert(ckh_t *ckh, void const**argkey, void const**argdata) {
 	size_t hashes[2], bucket;
 	const void *key = *argkey;
 	const void *data = *argdata;
@@ -201,27 +211,28 @@ ckh_try_insert(ckh_t *ckh, void const**argkey, void const**argdata)
 
 	/* Try to insert in primary bucket. */
 	bucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1);
-	if (ckh_try_bucket_insert(ckh, bucket, key, data) == false)
-		return (false);
+	if (!ckh_try_bucket_insert(ckh, bucket, key, data)) {
+		return false;
+	}
 
 	/* Try to insert in secondary bucket. */
 	bucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1);
-	if (ckh_try_bucket_insert(ckh, bucket, key, data) == false)
-		return (false);
+	if (!ckh_try_bucket_insert(ckh, bucket, key, data)) {
+		return false;
+	}
 
 	/*
 	 * Try to find a place for this item via iterative eviction/relocation.
 	 */
-	return (ckh_evict_reloc_insert(ckh, bucket, argkey, argdata));
+	return ckh_evict_reloc_insert(ckh, bucket, argkey, argdata);
 }
 
 /*
  * Try to rebuild the hash table from scratch by inserting all items from the
  * old table into the new.
  */
-JEMALLOC_INLINE_C bool
-ckh_rebuild(ckh_t *ckh, ckhc_t *aTab)
-{
+static bool
+ckh_rebuild(ckh_t *ckh, ckhc_t *aTab) {
 	size_t count, i, nins;
 	const void *key, *data;
 
@@ -233,22 +244,20 @@ ckh_rebuild(ckh_t *ckh, ckhc_t *aTab)
 			data = aTab[i].data;
 			if (ckh_try_insert(ckh, &key, &data)) {
 				ckh->count = count;
-				return (true);
+				return true;
 			}
 			nins++;
 		}
 	}
 
-	return (false);
+	return false;
 }
 
 static bool
-ckh_grow(ckh_t *ckh)
-{
+ckh_grow(tsd_t *tsd, ckh_t *ckh) {
 	bool ret;
 	ckhc_t *tab, *ttab;
-	size_t lg_curcells;
-	unsigned lg_prevbuckets;
+	unsigned lg_prevbuckets, lg_curcells;
 
 #ifdef CKH_COUNT
 	ckh->ngrows++;
@@ -265,12 +274,13 @@ ckh_grow(ckh_t *ckh)
 		size_t usize;
 
 		lg_curcells++;
-		usize = sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
-		if (usize == 0) {
+		usize = sz_sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
+		if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
 			ret = true;
 			goto label_return;
 		}
-		tab = (ckhc_t *)ipalloc(usize, CACHELINE, true);
+		tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE,
+		    true, NULL, true, arena_ichoose(tsd, NULL));
 		if (tab == NULL) {
 			ret = true;
 			goto label_return;
@@ -281,28 +291,27 @@ ckh_grow(ckh_t *ckh)
 		tab = ttab;
 		ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS;
 
-		if (ckh_rebuild(ckh, tab) == false) {
-			idalloc(tab);
+		if (!ckh_rebuild(ckh, tab)) {
+			idalloctm(tsd_tsdn(tsd), tab, NULL, NULL, true, true);
 			break;
 		}
 
 		/* Rebuilding failed, so back out partially rebuilt table. */
-		idalloc(ckh->tab);
+		idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true);
 		ckh->tab = tab;
 		ckh->lg_curbuckets = lg_prevbuckets;
 	}
 
 	ret = false;
 label_return:
-	return (ret);
+	return ret;
 }
 
 static void
-ckh_shrink(ckh_t *ckh)
-{
+ckh_shrink(tsd_t *tsd, ckh_t *ckh) {
 	ckhc_t *tab, *ttab;
-	size_t lg_curcells, usize;
-	unsigned lg_prevbuckets;
+	size_t usize;
+	unsigned lg_prevbuckets, lg_curcells;
 
 	/*
 	 * It is possible (though unlikely, given well behaved hashes) that the
@@ -310,10 +319,12 @@ ckh_shrink(ckh_t *ckh)
 	 */
 	lg_prevbuckets = ckh->lg_curbuckets;
 	lg_curcells = ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS - 1;
-	usize = sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
-	if (usize == 0)
+	usize = sz_sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
+	if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
 		return;
-	tab = (ckhc_t *)ipalloc(usize, CACHELINE, true);
+	}
+	tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE, true, NULL,
+	    true, arena_ichoose(tsd, NULL));
 	if (tab == NULL) {
 		/*
 		 * An OOM error isn't worth propagating, since it doesn't
@@ -327,8 +338,8 @@ ckh_shrink(ckh_t *ckh)
 	tab = ttab;
 	ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS;
 
-	if (ckh_rebuild(ckh, tab) == false) {
-		idalloc(tab);
+	if (!ckh_rebuild(ckh, tab)) {
+		idalloctm(tsd_tsdn(tsd), tab, NULL, NULL, true, true);
 #ifdef CKH_COUNT
 		ckh->nshrinks++;
 #endif
@@ -336,7 +347,7 @@ ckh_shrink(ckh_t *ckh)
 	}
 
 	/* Rebuilding failed, so back out partially rebuilt table. */
-	idalloc(ckh->tab);
+	idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true);
 	ckh->tab = tab;
 	ckh->lg_curbuckets = lg_prevbuckets;
 #ifdef CKH_COUNT
@@ -345,8 +356,8 @@ ckh_shrink(ckh_t *ckh)
 }
 
 bool
-ckh_new(ckh_t *ckh, size_t minitems, ckh_hash_t *hash, ckh_keycomp_t *keycomp)
-{
+ckh_new(tsd_t *tsd, ckh_t *ckh, size_t minitems, ckh_hash_t *hash,
+    ckh_keycomp_t *keycomp) {
 	bool ret;
 	size_t mincells, usize;
 	unsigned lg_mincells;
@@ -366,29 +377,31 @@ ckh_new(ckh_t *ckh, size_t minitems, ckh_hash_t *hash, ckh_keycomp_t *keycomp)
 	ckh->count = 0;
 
 	/*
-	 * Find the minimum power of 2 that is large enough to fit aBaseCount
+	 * Find the minimum power of 2 that is large enough to fit minitems
 	 * entries.  We are using (2+,2) cuckoo hashing, which has an expected
 	 * maximum load factor of at least ~0.86, so 0.75 is a conservative load
-	 * factor that will typically allow 2^aLgMinItems to fit without ever
+	 * factor that will typically allow mincells items to fit without ever
 	 * growing the table.
 	 */
 	assert(LG_CKH_BUCKET_CELLS > 0);
 	mincells = ((minitems + (3 - (minitems % 3))) / 3) << 2;
 	for (lg_mincells = LG_CKH_BUCKET_CELLS;
 	    (ZU(1) << lg_mincells) < mincells;
-	    lg_mincells++)
-		; /* Do nothing. */
+	    lg_mincells++) {
+		/* Do nothing. */
+	}
 	ckh->lg_minbuckets = lg_mincells - LG_CKH_BUCKET_CELLS;
 	ckh->lg_curbuckets = lg_mincells - LG_CKH_BUCKET_CELLS;
 	ckh->hash = hash;
 	ckh->keycomp = keycomp;
 
-	usize = sa2u(sizeof(ckhc_t) << lg_mincells, CACHELINE);
-	if (usize == 0) {
+	usize = sz_sa2u(sizeof(ckhc_t) << lg_mincells, CACHELINE);
+	if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
 		ret = true;
 		goto label_return;
 	}
-	ckh->tab = (ckhc_t *)ipalloc(usize, CACHELINE, true);
+	ckh->tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE, true,
+	    NULL, true, arena_ichoose(tsd, NULL));
 	if (ckh->tab == NULL) {
 		ret = true;
 		goto label_return;
@@ -396,20 +409,18 @@ ckh_new(ckh_t *ckh, size_t minitems, ckh_hash_t *hash, ckh_keycomp_t *keycomp)
 
 	ret = false;
 label_return:
-	return (ret);
+	return ret;
 }
 
 void
-ckh_delete(ckh_t *ckh)
-{
-
+ckh_delete(tsd_t *tsd, ckh_t *ckh) {
 	assert(ckh != NULL);
 
 #ifdef CKH_VERBOSE
 	malloc_printf(
-	    "%s(%p): ngrows: %"PRIu64", nshrinks: %"PRIu64","
-	    " nshrinkfails: %"PRIu64", ninserts: %"PRIu64","
-	    " nrelocs: %"PRIu64"\n", __func__, ckh,
+	    "%s(%p): ngrows: %"FMTu64", nshrinks: %"FMTu64","
+	    " nshrinkfails: %"FMTu64", ninserts: %"FMTu64","
+	    " nrelocs: %"FMTu64"\n", __func__, ckh,
 	    (unsigned long long)ckh->ngrows,
 	    (unsigned long long)ckh->nshrinks,
 	    (unsigned long long)ckh->nshrinkfails,
@@ -417,43 +428,42 @@ ckh_delete(ckh_t *ckh)
 	    (unsigned long long)ckh->nrelocs);
 #endif
 
-	idalloc(ckh->tab);
-	if (config_debug)
-		memset(ckh, 0x5a, sizeof(ckh_t));
+	idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, NULL, true, true);
+	if (config_debug) {
+		memset(ckh, JEMALLOC_FREE_JUNK, sizeof(ckh_t));
+	}
 }
 
 size_t
-ckh_count(ckh_t *ckh)
-{
-
+ckh_count(ckh_t *ckh) {
 	assert(ckh != NULL);
 
-	return (ckh->count);
+	return ckh->count;
 }
 
 bool
-ckh_iter(ckh_t *ckh, size_t *tabind, void **key, void **data)
-{
+ckh_iter(ckh_t *ckh, size_t *tabind, void **key, void **data) {
 	size_t i, ncells;
 
 	for (i = *tabind, ncells = (ZU(1) << (ckh->lg_curbuckets +
 	    LG_CKH_BUCKET_CELLS)); i < ncells; i++) {
 		if (ckh->tab[i].key != NULL) {
-			if (key != NULL)
+			if (key != NULL) {
 				*key = (void *)ckh->tab[i].key;
-			if (data != NULL)
+			}
+			if (data != NULL) {
 				*data = (void *)ckh->tab[i].data;
+			}
 			*tabind = i + 1;
-			return (false);
+			return false;
 		}
 	}
 
-	return (true);
+	return true;
 }
 
 bool
-ckh_insert(ckh_t *ckh, const void *key, const void *data)
-{
+ckh_insert(tsd_t *tsd, ckh_t *ckh, const void *key, const void *data) {
 	bool ret;
 
 	assert(ckh != NULL);
@@ -464,7 +474,7 @@ ckh_insert(ckh_t *ckh, const void *key, const void *data)
 #endif
 
 	while (ckh_try_insert(ckh, &key, &data)) {
-		if (ckh_grow(ckh)) {
+		if (ckh_grow(tsd, ckh)) {
 			ret = true;
 			goto label_return;
 		}
@@ -472,22 +482,24 @@ ckh_insert(ckh_t *ckh, const void *key, const void *data)
 
 	ret = false;
 label_return:
-	return (ret);
+	return ret;
 }
 
 bool
-ckh_remove(ckh_t *ckh, const void *searchkey, void **key, void **data)
-{
+ckh_remove(tsd_t *tsd, ckh_t *ckh, const void *searchkey, void **key,
+    void **data) {
 	size_t cell;
 
 	assert(ckh != NULL);
 
 	cell = ckh_isearch(ckh, searchkey);
 	if (cell != SIZE_T_MAX) {
-		if (key != NULL)
+		if (key != NULL) {
 			*key = (void *)ckh->tab[cell].key;
-		if (data != NULL)
+		}
+		if (data != NULL) {
 			*data = (void *)ckh->tab[cell].data;
+		}
 		ckh->tab[cell].key = NULL;
 		ckh->tab[cell].data = NULL; /* Not necessary. */
 
@@ -497,54 +509,50 @@ ckh_remove(ckh_t *ckh, const void *searchkey, void **key, void **data)
 		    + LG_CKH_BUCKET_CELLS - 2)) && ckh->lg_curbuckets
 		    > ckh->lg_minbuckets) {
 			/* Ignore error due to OOM. */
-			ckh_shrink(ckh);
+			ckh_shrink(tsd, ckh);
 		}
 
-		return (false);
+		return false;
 	}
 
-	return (true);
+	return true;
 }
 
 bool
-ckh_search(ckh_t *ckh, const void *searchkey, void **key, void **data)
-{
+ckh_search(ckh_t *ckh, const void *searchkey, void **key, void **data) {
 	size_t cell;
 
 	assert(ckh != NULL);
 
 	cell = ckh_isearch(ckh, searchkey);
 	if (cell != SIZE_T_MAX) {
-		if (key != NULL)
+		if (key != NULL) {
 			*key = (void *)ckh->tab[cell].key;
-		if (data != NULL)
+		}
+		if (data != NULL) {
 			*data = (void *)ckh->tab[cell].data;
-		return (false);
+		}
+		return false;
 	}
 
-	return (true);
+	return true;
 }
 
 void
-ckh_string_hash(const void *key, size_t r_hash[2])
-{
-
+ckh_string_hash(const void *key, size_t r_hash[2]) {
 	hash(key, strlen((const char *)key), 0x94122f33U, r_hash);
 }
 
 bool
-ckh_string_keycomp(const void *k1, const void *k2)
-{
-
-    assert(k1 != NULL);
-    assert(k2 != NULL);
+ckh_string_keycomp(const void *k1, const void *k2) {
+	assert(k1 != NULL);
+	assert(k2 != NULL);
 
-    return (strcmp((char *)k1, (char *)k2) ? false : true);
+	return !strcmp((char *)k1, (char *)k2);
 }
 
 void
-ckh_pointer_hash(const void *key, size_t r_hash[2])
-{
+ckh_pointer_hash(const void *key, size_t r_hash[2]) {
 	union {
 		const void	*v;
 		size_t		i;
@@ -556,8 +564,6 @@ ckh_pointer_hash(const void *key, size_t r_hash[2])
 }
 
 bool
-ckh_pointer_keycomp(const void *k1, const void *k2)
-{
-
-	return ((k1 == k2) ? true : false);
+ckh_pointer_keycomp(const void *k1, const void *k2) {
+	return (k1 == k2);
 }
diff --git a/modules/worldengine/deps/jemalloc/src/ctl.c b/modules/worldengine/deps/jemalloc/src/ctl.c
index cc2c5aef57..36bc8fb5b7 100644
--- a/modules/worldengine/deps/jemalloc/src/ctl.c
+++ b/modules/worldengine/deps/jemalloc/src/ctl.c
@@ -1,146 +1,146 @@
-#define	JEMALLOC_CTL_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_CTL_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/ctl.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/nstime.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/util.h"
 
 /******************************************************************************/
 /* Data. */
 
 /*
  * ctl_mtx protects the following:
- * - ctl_stats.*
- * - opt_prof_active
+ * - ctl_stats->*
  */
 static malloc_mutex_t	ctl_mtx;
 static bool		ctl_initialized;
-static uint64_t		ctl_epoch;
-static ctl_stats_t	ctl_stats;
+static ctl_stats_t	*ctl_stats;
+static ctl_arenas_t	*ctl_arenas;
 
 /******************************************************************************/
 /* Helpers for named and indexed nodes. */
 
-static inline const ctl_named_node_t *
-ctl_named_node(const ctl_node_t *node)
-{
-
+static const ctl_named_node_t *
+ctl_named_node(const ctl_node_t *node) {
 	return ((node->named) ? (const ctl_named_node_t *)node : NULL);
 }
 
-static inline const ctl_named_node_t *
-ctl_named_children(const ctl_named_node_t *node, int index)
-{
+static const ctl_named_node_t *
+ctl_named_children(const ctl_named_node_t *node, size_t index) {
 	const ctl_named_node_t *children = ctl_named_node(node->children);
 
 	return (children ? &children[index] : NULL);
 }
 
-static inline const ctl_indexed_node_t *
-ctl_indexed_node(const ctl_node_t *node)
-{
-
-	return ((node->named == false) ? (const ctl_indexed_node_t *)node :
-	    NULL);
+static const ctl_indexed_node_t *
+ctl_indexed_node(const ctl_node_t *node) {
+	return (!node->named ? (const ctl_indexed_node_t *)node : NULL);
 }
 
 /******************************************************************************/
 /* Function prototypes for non-inline static functions. */
 
-#define	CTL_PROTO(n)							\
-static int	n##_ctl(const size_t *mib, size_t miblen, void *oldp,	\
-    size_t *oldlenp, void *newp, size_t newlen);
-
-#define	INDEX_PROTO(n)							\
-static const ctl_named_node_t	*n##_index(const size_t *mib,		\
-    size_t miblen, size_t i);
-
-static bool	ctl_arena_init(ctl_arena_stats_t *astats);
-static void	ctl_arena_clear(ctl_arena_stats_t *astats);
-static void	ctl_arena_stats_amerge(ctl_arena_stats_t *cstats,
-    arena_t *arena);
-static void	ctl_arena_stats_smerge(ctl_arena_stats_t *sstats,
-    ctl_arena_stats_t *astats);
-static void	ctl_arena_refresh(arena_t *arena, unsigned i);
-static bool	ctl_grow(void);
-static void	ctl_refresh(void);
-static bool	ctl_init(void);
-static int	ctl_lookup(const char *name, ctl_node_t const **nodesp,
-    size_t *mibp, size_t *depthp);
+#define CTL_PROTO(n)							\
+static int	n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,	\
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen);
+
+#define INDEX_PROTO(n)							\
+static const ctl_named_node_t	*n##_index(tsdn_t *tsdn,		\
+    const size_t *mib, size_t miblen, size_t i);
 
 CTL_PROTO(version)
 CTL_PROTO(epoch)
+CTL_PROTO(background_thread)
 CTL_PROTO(thread_tcache_enabled)
 CTL_PROTO(thread_tcache_flush)
+CTL_PROTO(thread_prof_name)
+CTL_PROTO(thread_prof_active)
 CTL_PROTO(thread_arena)
 CTL_PROTO(thread_allocated)
 CTL_PROTO(thread_allocatedp)
 CTL_PROTO(thread_deallocated)
 CTL_PROTO(thread_deallocatedp)
+CTL_PROTO(config_cache_oblivious)
 CTL_PROTO(config_debug)
-CTL_PROTO(config_dss)
 CTL_PROTO(config_fill)
 CTL_PROTO(config_lazy_lock)
-CTL_PROTO(config_mremap)
-CTL_PROTO(config_munmap)
+CTL_PROTO(config_malloc_conf)
 CTL_PROTO(config_prof)
 CTL_PROTO(config_prof_libgcc)
 CTL_PROTO(config_prof_libunwind)
 CTL_PROTO(config_stats)
-CTL_PROTO(config_tcache)
-CTL_PROTO(config_tls)
+CTL_PROTO(config_thp)
 CTL_PROTO(config_utrace)
-CTL_PROTO(config_valgrind)
 CTL_PROTO(config_xmalloc)
 CTL_PROTO(opt_abort)
+CTL_PROTO(opt_abort_conf)
+CTL_PROTO(opt_retain)
 CTL_PROTO(opt_dss)
-CTL_PROTO(opt_lg_chunk)
 CTL_PROTO(opt_narenas)
-CTL_PROTO(opt_lg_dirty_mult)
+CTL_PROTO(opt_percpu_arena)
+CTL_PROTO(opt_background_thread)
+CTL_PROTO(opt_dirty_decay_ms)
+CTL_PROTO(opt_muzzy_decay_ms)
 CTL_PROTO(opt_stats_print)
+CTL_PROTO(opt_stats_print_opts)
 CTL_PROTO(opt_junk)
 CTL_PROTO(opt_zero)
-CTL_PROTO(opt_quarantine)
-CTL_PROTO(opt_redzone)
 CTL_PROTO(opt_utrace)
-CTL_PROTO(opt_valgrind)
 CTL_PROTO(opt_xmalloc)
 CTL_PROTO(opt_tcache)
 CTL_PROTO(opt_lg_tcache_max)
 CTL_PROTO(opt_prof)
 CTL_PROTO(opt_prof_prefix)
 CTL_PROTO(opt_prof_active)
+CTL_PROTO(opt_prof_thread_active_init)
 CTL_PROTO(opt_lg_prof_sample)
 CTL_PROTO(opt_lg_prof_interval)
 CTL_PROTO(opt_prof_gdump)
 CTL_PROTO(opt_prof_final)
 CTL_PROTO(opt_prof_leak)
 CTL_PROTO(opt_prof_accum)
+CTL_PROTO(tcache_create)
+CTL_PROTO(tcache_flush)
+CTL_PROTO(tcache_destroy)
+CTL_PROTO(arena_i_initialized)
+CTL_PROTO(arena_i_decay)
 CTL_PROTO(arena_i_purge)
-static void	arena_purge(unsigned arena_ind);
+CTL_PROTO(arena_i_reset)
+CTL_PROTO(arena_i_destroy)
 CTL_PROTO(arena_i_dss)
+CTL_PROTO(arena_i_dirty_decay_ms)
+CTL_PROTO(arena_i_muzzy_decay_ms)
+CTL_PROTO(arena_i_extent_hooks)
 INDEX_PROTO(arena_i)
 CTL_PROTO(arenas_bin_i_size)
 CTL_PROTO(arenas_bin_i_nregs)
-CTL_PROTO(arenas_bin_i_run_size)
+CTL_PROTO(arenas_bin_i_slab_size)
 INDEX_PROTO(arenas_bin_i)
-CTL_PROTO(arenas_lrun_i_size)
-INDEX_PROTO(arenas_lrun_i)
+CTL_PROTO(arenas_lextent_i_size)
+INDEX_PROTO(arenas_lextent_i)
 CTL_PROTO(arenas_narenas)
-CTL_PROTO(arenas_initialized)
+CTL_PROTO(arenas_dirty_decay_ms)
+CTL_PROTO(arenas_muzzy_decay_ms)
 CTL_PROTO(arenas_quantum)
 CTL_PROTO(arenas_page)
 CTL_PROTO(arenas_tcache_max)
 CTL_PROTO(arenas_nbins)
 CTL_PROTO(arenas_nhbins)
-CTL_PROTO(arenas_nlruns)
-CTL_PROTO(arenas_purge)
-CTL_PROTO(arenas_extend)
+CTL_PROTO(arenas_nlextents)
+CTL_PROTO(arenas_create)
+CTL_PROTO(prof_thread_active_init)
 CTL_PROTO(prof_active)
 CTL_PROTO(prof_dump)
+CTL_PROTO(prof_gdump)
+CTL_PROTO(prof_reset)
 CTL_PROTO(prof_interval)
-CTL_PROTO(stats_chunks_current)
-CTL_PROTO(stats_chunks_total)
-CTL_PROTO(stats_chunks_high)
-CTL_PROTO(stats_huge_allocated)
-CTL_PROTO(stats_huge_nmalloc)
-CTL_PROTO(stats_huge_ndalloc)
+CTL_PROTO(lg_prof_sample)
 CTL_PROTO(stats_arenas_i_small_allocated)
 CTL_PROTO(stats_arenas_i_small_nmalloc)
 CTL_PROTO(stats_arenas_i_small_ndalloc)
@@ -149,119 +149,177 @@ CTL_PROTO(stats_arenas_i_large_allocated)
 CTL_PROTO(stats_arenas_i_large_nmalloc)
 CTL_PROTO(stats_arenas_i_large_ndalloc)
 CTL_PROTO(stats_arenas_i_large_nrequests)
-CTL_PROTO(stats_arenas_i_bins_j_allocated)
 CTL_PROTO(stats_arenas_i_bins_j_nmalloc)
 CTL_PROTO(stats_arenas_i_bins_j_ndalloc)
 CTL_PROTO(stats_arenas_i_bins_j_nrequests)
+CTL_PROTO(stats_arenas_i_bins_j_curregs)
 CTL_PROTO(stats_arenas_i_bins_j_nfills)
 CTL_PROTO(stats_arenas_i_bins_j_nflushes)
-CTL_PROTO(stats_arenas_i_bins_j_nruns)
-CTL_PROTO(stats_arenas_i_bins_j_nreruns)
-CTL_PROTO(stats_arenas_i_bins_j_curruns)
+CTL_PROTO(stats_arenas_i_bins_j_nslabs)
+CTL_PROTO(stats_arenas_i_bins_j_nreslabs)
+CTL_PROTO(stats_arenas_i_bins_j_curslabs)
 INDEX_PROTO(stats_arenas_i_bins_j)
-CTL_PROTO(stats_arenas_i_lruns_j_nmalloc)
-CTL_PROTO(stats_arenas_i_lruns_j_ndalloc)
-CTL_PROTO(stats_arenas_i_lruns_j_nrequests)
-CTL_PROTO(stats_arenas_i_lruns_j_curruns)
-INDEX_PROTO(stats_arenas_i_lruns_j)
+CTL_PROTO(stats_arenas_i_lextents_j_nmalloc)
+CTL_PROTO(stats_arenas_i_lextents_j_ndalloc)
+CTL_PROTO(stats_arenas_i_lextents_j_nrequests)
+CTL_PROTO(stats_arenas_i_lextents_j_curlextents)
+INDEX_PROTO(stats_arenas_i_lextents_j)
 CTL_PROTO(stats_arenas_i_nthreads)
+CTL_PROTO(stats_arenas_i_uptime)
 CTL_PROTO(stats_arenas_i_dss)
+CTL_PROTO(stats_arenas_i_dirty_decay_ms)
+CTL_PROTO(stats_arenas_i_muzzy_decay_ms)
 CTL_PROTO(stats_arenas_i_pactive)
 CTL_PROTO(stats_arenas_i_pdirty)
+CTL_PROTO(stats_arenas_i_pmuzzy)
 CTL_PROTO(stats_arenas_i_mapped)
-CTL_PROTO(stats_arenas_i_npurge)
-CTL_PROTO(stats_arenas_i_nmadvise)
-CTL_PROTO(stats_arenas_i_purged)
+CTL_PROTO(stats_arenas_i_retained)
+CTL_PROTO(stats_arenas_i_dirty_npurge)
+CTL_PROTO(stats_arenas_i_dirty_nmadvise)
+CTL_PROTO(stats_arenas_i_dirty_purged)
+CTL_PROTO(stats_arenas_i_muzzy_npurge)
+CTL_PROTO(stats_arenas_i_muzzy_nmadvise)
+CTL_PROTO(stats_arenas_i_muzzy_purged)
+CTL_PROTO(stats_arenas_i_base)
+CTL_PROTO(stats_arenas_i_internal)
+CTL_PROTO(stats_arenas_i_tcache_bytes)
+CTL_PROTO(stats_arenas_i_resident)
 INDEX_PROTO(stats_arenas_i)
-CTL_PROTO(stats_cactive)
 CTL_PROTO(stats_allocated)
 CTL_PROTO(stats_active)
+CTL_PROTO(stats_background_thread_num_threads)
+CTL_PROTO(stats_background_thread_num_runs)
+CTL_PROTO(stats_background_thread_run_interval)
+CTL_PROTO(stats_metadata)
+CTL_PROTO(stats_resident)
 CTL_PROTO(stats_mapped)
+CTL_PROTO(stats_retained)
+
+#define MUTEX_STATS_CTL_PROTO_GEN(n)					\
+CTL_PROTO(stats_##n##_num_ops)						\
+CTL_PROTO(stats_##n##_num_wait)						\
+CTL_PROTO(stats_##n##_num_spin_acq)					\
+CTL_PROTO(stats_##n##_num_owner_switch)					\
+CTL_PROTO(stats_##n##_total_wait_time)					\
+CTL_PROTO(stats_##n##_max_wait_time)					\
+CTL_PROTO(stats_##n##_max_num_thds)
+
+/* Global mutexes. */
+#define OP(mtx) MUTEX_STATS_CTL_PROTO_GEN(mutexes_##mtx)
+MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+
+/* Per arena mutexes. */
+#define OP(mtx) MUTEX_STATS_CTL_PROTO_GEN(arenas_i_mutexes_##mtx)
+MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+
+/* Arena bin mutexes. */
+MUTEX_STATS_CTL_PROTO_GEN(arenas_i_bins_j_mutex)
+#undef MUTEX_STATS_CTL_PROTO_GEN
+
+CTL_PROTO(stats_mutexes_reset)
 
 /******************************************************************************/
 /* mallctl tree. */
 
-/* Maximum tree depth. */
-#define	CTL_MAX_DEPTH	6
-
-#define	NAME(n)	{true},	n
-#define	CHILD(t, c)							\
+#define NAME(n)	{true},	n
+#define CHILD(t, c)							\
 	sizeof(c##_node) / sizeof(ctl_##t##_node_t),			\
 	(ctl_node_t *)c##_node,						\
 	NULL
-#define	CTL(c)	0, NULL, c##_ctl
+#define CTL(c)	0, NULL, c##_ctl
 
 /*
  * Only handles internal indexed nodes, since there are currently no external
  * ones.
  */
-#define	INDEX(i)	{false},	i##_index
+#define INDEX(i)	{false},	i##_index
 
-static const ctl_named_node_t	tcache_node[] = {
+static const ctl_named_node_t	thread_tcache_node[] = {
 	{NAME("enabled"),	CTL(thread_tcache_enabled)},
 	{NAME("flush"),		CTL(thread_tcache_flush)}
 };
 
+static const ctl_named_node_t	thread_prof_node[] = {
+	{NAME("name"),		CTL(thread_prof_name)},
+	{NAME("active"),	CTL(thread_prof_active)}
+};
+
 static const ctl_named_node_t	thread_node[] = {
 	{NAME("arena"),		CTL(thread_arena)},
 	{NAME("allocated"),	CTL(thread_allocated)},
 	{NAME("allocatedp"),	CTL(thread_allocatedp)},
 	{NAME("deallocated"),	CTL(thread_deallocated)},
 	{NAME("deallocatedp"),	CTL(thread_deallocatedp)},
-	{NAME("tcache"),	CHILD(named, tcache)}
+	{NAME("tcache"),	CHILD(named, thread_tcache)},
+	{NAME("prof"),		CHILD(named, thread_prof)}
 };
 
 static const ctl_named_node_t	config_node[] = {
-	{NAME("debug"),			CTL(config_debug)},
-	{NAME("dss"),			CTL(config_dss)},
-	{NAME("fill"),			CTL(config_fill)},
-	{NAME("lazy_lock"),		CTL(config_lazy_lock)},
-	{NAME("mremap"),		CTL(config_mremap)},
-	{NAME("munmap"),		CTL(config_munmap)},
-	{NAME("prof"),			CTL(config_prof)},
-	{NAME("prof_libgcc"),		CTL(config_prof_libgcc)},
-	{NAME("prof_libunwind"),	CTL(config_prof_libunwind)},
-	{NAME("stats"),			CTL(config_stats)},
-	{NAME("tcache"),		CTL(config_tcache)},
-	{NAME("tls"),			CTL(config_tls)},
-	{NAME("utrace"),		CTL(config_utrace)},
-	{NAME("valgrind"),		CTL(config_valgrind)},
-	{NAME("xmalloc"),		CTL(config_xmalloc)}
+	{NAME("cache_oblivious"), CTL(config_cache_oblivious)},
+	{NAME("debug"),		CTL(config_debug)},
+	{NAME("fill"),		CTL(config_fill)},
+	{NAME("lazy_lock"),	CTL(config_lazy_lock)},
+	{NAME("malloc_conf"),	CTL(config_malloc_conf)},
+	{NAME("prof"),		CTL(config_prof)},
+	{NAME("prof_libgcc"),	CTL(config_prof_libgcc)},
+	{NAME("prof_libunwind"), CTL(config_prof_libunwind)},
+	{NAME("stats"),		CTL(config_stats)},
+	{NAME("thp"),		CTL(config_thp)},
+	{NAME("utrace"),	CTL(config_utrace)},
+	{NAME("xmalloc"),	CTL(config_xmalloc)}
 };
 
 static const ctl_named_node_t opt_node[] = {
-	{NAME("abort"),			CTL(opt_abort)},
-	{NAME("dss"),			CTL(opt_dss)},
-	{NAME("lg_chunk"),		CTL(opt_lg_chunk)},
-	{NAME("narenas"),		CTL(opt_narenas)},
-	{NAME("lg_dirty_mult"),		CTL(opt_lg_dirty_mult)},
-	{NAME("stats_print"),		CTL(opt_stats_print)},
-	{NAME("junk"),			CTL(opt_junk)},
-	{NAME("zero"),			CTL(opt_zero)},
-	{NAME("quarantine"),		CTL(opt_quarantine)},
-	{NAME("redzone"),		CTL(opt_redzone)},
-	{NAME("utrace"),		CTL(opt_utrace)},
-	{NAME("valgrind"),		CTL(opt_valgrind)},
-	{NAME("xmalloc"),		CTL(opt_xmalloc)},
-	{NAME("tcache"),		CTL(opt_tcache)},
-	{NAME("lg_tcache_max"),		CTL(opt_lg_tcache_max)},
-	{NAME("prof"),			CTL(opt_prof)},
-	{NAME("prof_prefix"),		CTL(opt_prof_prefix)},
-	{NAME("prof_active"),		CTL(opt_prof_active)},
-	{NAME("lg_prof_sample"),	CTL(opt_lg_prof_sample)},
-	{NAME("lg_prof_interval"),	CTL(opt_lg_prof_interval)},
-	{NAME("prof_gdump"),		CTL(opt_prof_gdump)},
-	{NAME("prof_final"),		CTL(opt_prof_final)},
-	{NAME("prof_leak"),		CTL(opt_prof_leak)},
-	{NAME("prof_accum"),		CTL(opt_prof_accum)}
+	{NAME("abort"),		CTL(opt_abort)},
+	{NAME("abort_conf"),	CTL(opt_abort_conf)},
+	{NAME("retain"),	CTL(opt_retain)},
+	{NAME("dss"),		CTL(opt_dss)},
+	{NAME("narenas"),	CTL(opt_narenas)},
+	{NAME("percpu_arena"),	CTL(opt_percpu_arena)},
+	{NAME("background_thread"),	CTL(opt_background_thread)},
+	{NAME("dirty_decay_ms"), CTL(opt_dirty_decay_ms)},
+	{NAME("muzzy_decay_ms"), CTL(opt_muzzy_decay_ms)},
+	{NAME("stats_print"),	CTL(opt_stats_print)},
+	{NAME("stats_print_opts"),	CTL(opt_stats_print_opts)},
+	{NAME("junk"),		CTL(opt_junk)},
+	{NAME("zero"),		CTL(opt_zero)},
+	{NAME("utrace"),	CTL(opt_utrace)},
+	{NAME("xmalloc"),	CTL(opt_xmalloc)},
+	{NAME("tcache"),	CTL(opt_tcache)},
+	{NAME("lg_tcache_max"),	CTL(opt_lg_tcache_max)},
+	{NAME("prof"),		CTL(opt_prof)},
+	{NAME("prof_prefix"),	CTL(opt_prof_prefix)},
+	{NAME("prof_active"),	CTL(opt_prof_active)},
+	{NAME("prof_thread_active_init"), CTL(opt_prof_thread_active_init)},
+	{NAME("lg_prof_sample"), CTL(opt_lg_prof_sample)},
+	{NAME("lg_prof_interval"), CTL(opt_lg_prof_interval)},
+	{NAME("prof_gdump"),	CTL(opt_prof_gdump)},
+	{NAME("prof_final"),	CTL(opt_prof_final)},
+	{NAME("prof_leak"),	CTL(opt_prof_leak)},
+	{NAME("prof_accum"),	CTL(opt_prof_accum)}
+};
+
+static const ctl_named_node_t	tcache_node[] = {
+	{NAME("create"),	CTL(tcache_create)},
+	{NAME("flush"),		CTL(tcache_flush)},
+	{NAME("destroy"),	CTL(tcache_destroy)}
 };
 
 static const ctl_named_node_t arena_i_node[] = {
-	{NAME("purge"),			CTL(arena_i_purge)},
-	{NAME("dss"),			CTL(arena_i_dss)}
+	{NAME("initialized"),	CTL(arena_i_initialized)},
+	{NAME("decay"),		CTL(arena_i_decay)},
+	{NAME("purge"),		CTL(arena_i_purge)},
+	{NAME("reset"),		CTL(arena_i_reset)},
+	{NAME("destroy"),	CTL(arena_i_destroy)},
+	{NAME("dss"),		CTL(arena_i_dss)},
+	{NAME("dirty_decay_ms"), CTL(arena_i_dirty_decay_ms)},
+	{NAME("muzzy_decay_ms"), CTL(arena_i_muzzy_decay_ms)},
+	{NAME("extent_hooks"),	CTL(arena_i_extent_hooks)}
 };
 static const ctl_named_node_t super_arena_i_node[] = {
-	{NAME(""),			CHILD(named, arena_i)}
+	{NAME(""),		CHILD(named, arena_i)}
 };
 
 static const ctl_indexed_node_t arena_node[] = {
@@ -269,147 +327,208 @@ static const ctl_indexed_node_t arena_node[] = {
 };
 
 static const ctl_named_node_t arenas_bin_i_node[] = {
-	{NAME("size"),			CTL(arenas_bin_i_size)},
-	{NAME("nregs"),			CTL(arenas_bin_i_nregs)},
-	{NAME("run_size"),		CTL(arenas_bin_i_run_size)}
+	{NAME("size"),		CTL(arenas_bin_i_size)},
+	{NAME("nregs"),		CTL(arenas_bin_i_nregs)},
+	{NAME("slab_size"),	CTL(arenas_bin_i_slab_size)}
 };
 static const ctl_named_node_t super_arenas_bin_i_node[] = {
-	{NAME(""),			CHILD(named, arenas_bin_i)}
+	{NAME(""),		CHILD(named, arenas_bin_i)}
 };
 
 static const ctl_indexed_node_t arenas_bin_node[] = {
 	{INDEX(arenas_bin_i)}
 };
 
-static const ctl_named_node_t arenas_lrun_i_node[] = {
-	{NAME("size"),			CTL(arenas_lrun_i_size)}
+static const ctl_named_node_t arenas_lextent_i_node[] = {
+	{NAME("size"),		CTL(arenas_lextent_i_size)}
 };
-static const ctl_named_node_t super_arenas_lrun_i_node[] = {
-	{NAME(""),			CHILD(named, arenas_lrun_i)}
+static const ctl_named_node_t super_arenas_lextent_i_node[] = {
+	{NAME(""),		CHILD(named, arenas_lextent_i)}
 };
 
-static const ctl_indexed_node_t arenas_lrun_node[] = {
-	{INDEX(arenas_lrun_i)}
+static const ctl_indexed_node_t arenas_lextent_node[] = {
+	{INDEX(arenas_lextent_i)}
 };
 
 static const ctl_named_node_t arenas_node[] = {
-	{NAME("narenas"),		CTL(arenas_narenas)},
-	{NAME("initialized"),		CTL(arenas_initialized)},
-	{NAME("quantum"),		CTL(arenas_quantum)},
-	{NAME("page"),			CTL(arenas_page)},
-	{NAME("tcache_max"),		CTL(arenas_tcache_max)},
-	{NAME("nbins"),			CTL(arenas_nbins)},
-	{NAME("nhbins"),		CTL(arenas_nhbins)},
-	{NAME("bin"),			CHILD(indexed, arenas_bin)},
-	{NAME("nlruns"),		CTL(arenas_nlruns)},
-	{NAME("lrun"),			CHILD(indexed, arenas_lrun)},
-	{NAME("purge"),			CTL(arenas_purge)},
-	{NAME("extend"),		CTL(arenas_extend)}
+	{NAME("narenas"),	CTL(arenas_narenas)},
+	{NAME("dirty_decay_ms"), CTL(arenas_dirty_decay_ms)},
+	{NAME("muzzy_decay_ms"), CTL(arenas_muzzy_decay_ms)},
+	{NAME("quantum"),	CTL(arenas_quantum)},
+	{NAME("page"),		CTL(arenas_page)},
+	{NAME("tcache_max"),	CTL(arenas_tcache_max)},
+	{NAME("nbins"),		CTL(arenas_nbins)},
+	{NAME("nhbins"),	CTL(arenas_nhbins)},
+	{NAME("bin"),		CHILD(indexed, arenas_bin)},
+	{NAME("nlextents"),	CTL(arenas_nlextents)},
+	{NAME("lextent"),	CHILD(indexed, arenas_lextent)},
+	{NAME("create"),	CTL(arenas_create)}
 };
 
 static const ctl_named_node_t	prof_node[] = {
+	{NAME("thread_active_init"), CTL(prof_thread_active_init)},
 	{NAME("active"),	CTL(prof_active)},
 	{NAME("dump"),		CTL(prof_dump)},
-	{NAME("interval"),	CTL(prof_interval)}
+	{NAME("gdump"),		CTL(prof_gdump)},
+	{NAME("reset"),		CTL(prof_reset)},
+	{NAME("interval"),	CTL(prof_interval)},
+	{NAME("lg_sample"),	CTL(lg_prof_sample)}
 };
 
-static const ctl_named_node_t stats_chunks_node[] = {
-	{NAME("current"),		CTL(stats_chunks_current)},
-	{NAME("total"),			CTL(stats_chunks_total)},
-	{NAME("high"),			CTL(stats_chunks_high)}
+static const ctl_named_node_t stats_arenas_i_small_node[] = {
+	{NAME("allocated"),	CTL(stats_arenas_i_small_allocated)},
+	{NAME("nmalloc"),	CTL(stats_arenas_i_small_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_small_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_small_nrequests)}
 };
 
-static const ctl_named_node_t stats_huge_node[] = {
-	{NAME("allocated"),		CTL(stats_huge_allocated)},
-	{NAME("nmalloc"),		CTL(stats_huge_nmalloc)},
-	{NAME("ndalloc"),		CTL(stats_huge_ndalloc)}
+static const ctl_named_node_t stats_arenas_i_large_node[] = {
+	{NAME("allocated"),	CTL(stats_arenas_i_large_allocated)},
+	{NAME("nmalloc"),	CTL(stats_arenas_i_large_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_large_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_large_nrequests)}
 };
 
-static const ctl_named_node_t stats_arenas_i_small_node[] = {
-	{NAME("allocated"),		CTL(stats_arenas_i_small_allocated)},
-	{NAME("nmalloc"),		CTL(stats_arenas_i_small_nmalloc)},
-	{NAME("ndalloc"),		CTL(stats_arenas_i_small_ndalloc)},
-	{NAME("nrequests"),		CTL(stats_arenas_i_small_nrequests)}
+#define MUTEX_PROF_DATA_NODE(prefix)					\
+static const ctl_named_node_t stats_##prefix##_node[] = {		\
+	{NAME("num_ops"),						\
+	 CTL(stats_##prefix##_num_ops)},				\
+	{NAME("num_wait"),						\
+	 CTL(stats_##prefix##_num_wait)},				\
+	{NAME("num_spin_acq"),						\
+	 CTL(stats_##prefix##_num_spin_acq)},				\
+	{NAME("num_owner_switch"),					\
+	 CTL(stats_##prefix##_num_owner_switch)},			\
+	{NAME("total_wait_time"),					\
+	 CTL(stats_##prefix##_total_wait_time)},			\
+	{NAME("max_wait_time"),						\
+	 CTL(stats_##prefix##_max_wait_time)},				\
+	{NAME("max_num_thds"),						\
+	 CTL(stats_##prefix##_max_num_thds)}				\
+	/* Note that # of current waiting thread not provided. */	\
 };
 
-static const ctl_named_node_t stats_arenas_i_large_node[] = {
-	{NAME("allocated"),		CTL(stats_arenas_i_large_allocated)},
-	{NAME("nmalloc"),		CTL(stats_arenas_i_large_nmalloc)},
-	{NAME("ndalloc"),		CTL(stats_arenas_i_large_ndalloc)},
-	{NAME("nrequests"),		CTL(stats_arenas_i_large_nrequests)}
-};
+MUTEX_PROF_DATA_NODE(arenas_i_bins_j_mutex)
 
 static const ctl_named_node_t stats_arenas_i_bins_j_node[] = {
-	{NAME("allocated"),		CTL(stats_arenas_i_bins_j_allocated)},
-	{NAME("nmalloc"),		CTL(stats_arenas_i_bins_j_nmalloc)},
-	{NAME("ndalloc"),		CTL(stats_arenas_i_bins_j_ndalloc)},
-	{NAME("nrequests"),		CTL(stats_arenas_i_bins_j_nrequests)},
-	{NAME("nfills"),		CTL(stats_arenas_i_bins_j_nfills)},
-	{NAME("nflushes"),		CTL(stats_arenas_i_bins_j_nflushes)},
-	{NAME("nruns"),			CTL(stats_arenas_i_bins_j_nruns)},
-	{NAME("nreruns"),		CTL(stats_arenas_i_bins_j_nreruns)},
-	{NAME("curruns"),		CTL(stats_arenas_i_bins_j_curruns)}
+	{NAME("nmalloc"),	CTL(stats_arenas_i_bins_j_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_bins_j_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_bins_j_nrequests)},
+	{NAME("curregs"),	CTL(stats_arenas_i_bins_j_curregs)},
+	{NAME("nfills"),	CTL(stats_arenas_i_bins_j_nfills)},
+	{NAME("nflushes"),	CTL(stats_arenas_i_bins_j_nflushes)},
+	{NAME("nslabs"),	CTL(stats_arenas_i_bins_j_nslabs)},
+	{NAME("nreslabs"),	CTL(stats_arenas_i_bins_j_nreslabs)},
+	{NAME("curslabs"),	CTL(stats_arenas_i_bins_j_curslabs)},
+	{NAME("mutex"),		CHILD(named, stats_arenas_i_bins_j_mutex)}
 };
+
 static const ctl_named_node_t super_stats_arenas_i_bins_j_node[] = {
-	{NAME(""),			CHILD(named, stats_arenas_i_bins_j)}
+	{NAME(""),		CHILD(named, stats_arenas_i_bins_j)}
 };
 
 static const ctl_indexed_node_t stats_arenas_i_bins_node[] = {
 	{INDEX(stats_arenas_i_bins_j)}
 };
 
-static const ctl_named_node_t stats_arenas_i_lruns_j_node[] = {
-	{NAME("nmalloc"),		CTL(stats_arenas_i_lruns_j_nmalloc)},
-	{NAME("ndalloc"),		CTL(stats_arenas_i_lruns_j_ndalloc)},
-	{NAME("nrequests"),		CTL(stats_arenas_i_lruns_j_nrequests)},
-	{NAME("curruns"),		CTL(stats_arenas_i_lruns_j_curruns)}
+static const ctl_named_node_t stats_arenas_i_lextents_j_node[] = {
+	{NAME("nmalloc"),	CTL(stats_arenas_i_lextents_j_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_lextents_j_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_lextents_j_nrequests)},
+	{NAME("curlextents"),	CTL(stats_arenas_i_lextents_j_curlextents)}
 };
-static const ctl_named_node_t super_stats_arenas_i_lruns_j_node[] = {
-	{NAME(""),			CHILD(named, stats_arenas_i_lruns_j)}
+static const ctl_named_node_t super_stats_arenas_i_lextents_j_node[] = {
+	{NAME(""),		CHILD(named, stats_arenas_i_lextents_j)}
 };
 
-static const ctl_indexed_node_t stats_arenas_i_lruns_node[] = {
-	{INDEX(stats_arenas_i_lruns_j)}
+static const ctl_indexed_node_t stats_arenas_i_lextents_node[] = {
+	{INDEX(stats_arenas_i_lextents_j)}
+};
+
+#define OP(mtx)  MUTEX_PROF_DATA_NODE(arenas_i_mutexes_##mtx)
+MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+
+static const ctl_named_node_t stats_arenas_i_mutexes_node[] = {
+#define OP(mtx) {NAME(#mtx), CHILD(named, stats_arenas_i_mutexes_##mtx)},
+MUTEX_PROF_ARENA_MUTEXES
+#undef OP
 };
 
 static const ctl_named_node_t stats_arenas_i_node[] = {
-	{NAME("nthreads"),		CTL(stats_arenas_i_nthreads)},
-	{NAME("dss"),			CTL(stats_arenas_i_dss)},
-	{NAME("pactive"),		CTL(stats_arenas_i_pactive)},
-	{NAME("pdirty"),		CTL(stats_arenas_i_pdirty)},
-	{NAME("mapped"),		CTL(stats_arenas_i_mapped)},
-	{NAME("npurge"),		CTL(stats_arenas_i_npurge)},
-	{NAME("nmadvise"),		CTL(stats_arenas_i_nmadvise)},
-	{NAME("purged"),		CTL(stats_arenas_i_purged)},
-	{NAME("small"),			CHILD(named, stats_arenas_i_small)},
-	{NAME("large"),			CHILD(named, stats_arenas_i_large)},
-	{NAME("bins"),			CHILD(indexed, stats_arenas_i_bins)},
-	{NAME("lruns"),			CHILD(indexed, stats_arenas_i_lruns)}
+	{NAME("nthreads"),	CTL(stats_arenas_i_nthreads)},
+	{NAME("uptime"),	CTL(stats_arenas_i_uptime)},
+	{NAME("dss"),		CTL(stats_arenas_i_dss)},
+	{NAME("dirty_decay_ms"), CTL(stats_arenas_i_dirty_decay_ms)},
+	{NAME("muzzy_decay_ms"), CTL(stats_arenas_i_muzzy_decay_ms)},
+	{NAME("pactive"),	CTL(stats_arenas_i_pactive)},
+	{NAME("pdirty"),	CTL(stats_arenas_i_pdirty)},
+	{NAME("pmuzzy"),	CTL(stats_arenas_i_pmuzzy)},
+	{NAME("mapped"),	CTL(stats_arenas_i_mapped)},
+	{NAME("retained"),	CTL(stats_arenas_i_retained)},
+	{NAME("dirty_npurge"),	CTL(stats_arenas_i_dirty_npurge)},
+	{NAME("dirty_nmadvise"), CTL(stats_arenas_i_dirty_nmadvise)},
+	{NAME("dirty_purged"),	CTL(stats_arenas_i_dirty_purged)},
+	{NAME("muzzy_npurge"),	CTL(stats_arenas_i_muzzy_npurge)},
+	{NAME("muzzy_nmadvise"), CTL(stats_arenas_i_muzzy_nmadvise)},
+	{NAME("muzzy_purged"),	CTL(stats_arenas_i_muzzy_purged)},
+	{NAME("base"),		CTL(stats_arenas_i_base)},
+	{NAME("internal"),	CTL(stats_arenas_i_internal)},
+	{NAME("tcache_bytes"),	CTL(stats_arenas_i_tcache_bytes)},
+	{NAME("resident"),	CTL(stats_arenas_i_resident)},
+	{NAME("small"),		CHILD(named, stats_arenas_i_small)},
+	{NAME("large"),		CHILD(named, stats_arenas_i_large)},
+	{NAME("bins"),		CHILD(indexed, stats_arenas_i_bins)},
+	{NAME("lextents"),	CHILD(indexed, stats_arenas_i_lextents)},
+	{NAME("mutexes"),	CHILD(named, stats_arenas_i_mutexes)}
 };
 static const ctl_named_node_t super_stats_arenas_i_node[] = {
-	{NAME(""),			CHILD(named, stats_arenas_i)}
+	{NAME(""),		CHILD(named, stats_arenas_i)}
 };
 
 static const ctl_indexed_node_t stats_arenas_node[] = {
 	{INDEX(stats_arenas_i)}
 };
 
+static const ctl_named_node_t stats_background_thread_node[] = {
+	{NAME("num_threads"),	CTL(stats_background_thread_num_threads)},
+	{NAME("num_runs"),	CTL(stats_background_thread_num_runs)},
+	{NAME("run_interval"),	CTL(stats_background_thread_run_interval)}
+};
+
+#define OP(mtx) MUTEX_PROF_DATA_NODE(mutexes_##mtx)
+MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+
+static const ctl_named_node_t stats_mutexes_node[] = {
+#define OP(mtx) {NAME(#mtx), CHILD(named, stats_mutexes_##mtx)},
+MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+	{NAME("reset"),		CTL(stats_mutexes_reset)}
+};
+#undef MUTEX_PROF_DATA_NODE
+
 static const ctl_named_node_t stats_node[] = {
-	{NAME("cactive"),		CTL(stats_cactive)},
-	{NAME("allocated"),		CTL(stats_allocated)},
-	{NAME("active"),		CTL(stats_active)},
-	{NAME("mapped"),		CTL(stats_mapped)},
-	{NAME("chunks"),		CHILD(named, stats_chunks)},
-	{NAME("huge"),			CHILD(named, stats_huge)},
-	{NAME("arenas"),		CHILD(indexed, stats_arenas)}
+	{NAME("allocated"),	CTL(stats_allocated)},
+	{NAME("active"),	CTL(stats_active)},
+	{NAME("metadata"),	CTL(stats_metadata)},
+	{NAME("resident"),	CTL(stats_resident)},
+	{NAME("mapped"),	CTL(stats_mapped)},
+	{NAME("retained"),	CTL(stats_retained)},
+	{NAME("background_thread"),
+	 CHILD(named, stats_background_thread)},
+	{NAME("mutexes"),	CHILD(named, stats_mutexes)},
+	{NAME("arenas"),	CHILD(indexed, stats_arenas)}
 };
 
 static const ctl_named_node_t	root_node[] = {
 	{NAME("version"),	CTL(version)},
 	{NAME("epoch"),		CTL(epoch)},
+	{NAME("background_thread"),	CTL(background_thread)},
 	{NAME("thread"),	CHILD(named, thread)},
 	{NAME("config"),	CHILD(named, config)},
 	{NAME("opt"),		CHILD(named, opt)},
+	{NAME("tcache"),	CHILD(named, tcache)},
 	{NAME("arena"),		CHILD(indexed, arena)},
 	{NAME("arenas"),	CHILD(named, arenas)},
 	{NAME("prof"),		CHILD(named, prof)},
@@ -426,303 +545,514 @@ static const ctl_named_node_t super_root_node[] = {
 
 /******************************************************************************/
 
-static bool
-ctl_arena_init(ctl_arena_stats_t *astats)
-{
+/*
+ * Sets *dst + *src non-atomically.  This is safe, since everything is
+ * synchronized by the ctl mutex.
+ */
+static void
+accum_arena_stats_u64(arena_stats_u64_t *dst, arena_stats_u64_t *src) {
+#ifdef JEMALLOC_ATOMIC_U64
+	uint64_t cur_dst = atomic_load_u64(dst, ATOMIC_RELAXED);
+	uint64_t cur_src = atomic_load_u64(src, ATOMIC_RELAXED);
+	atomic_store_u64(dst, cur_dst + cur_src, ATOMIC_RELAXED);
+#else
+	*dst += *src;
+#endif
+}
 
-	if (astats->lstats == NULL) {
-		astats->lstats = (malloc_large_stats_t *)base_alloc(nlclasses *
-		    sizeof(malloc_large_stats_t));
-		if (astats->lstats == NULL)
-			return (true);
+/* Likewise: with ctl mutex synchronization, reading is simple. */
+static uint64_t
+arena_stats_read_u64(arena_stats_u64_t *p) {
+#ifdef JEMALLOC_ATOMIC_U64
+	return atomic_load_u64(p, ATOMIC_RELAXED);
+#else
+	return *p;
+#endif
+}
+
+static void accum_atomic_zu(atomic_zu_t *dst, atomic_zu_t *src) {
+	size_t cur_dst = atomic_load_zu(dst, ATOMIC_RELAXED);
+	size_t cur_src = atomic_load_zu(src, ATOMIC_RELAXED);
+	atomic_store_zu(dst, cur_dst + cur_src, ATOMIC_RELAXED);
+}
+
+/******************************************************************************/
+
+static unsigned
+arenas_i2a_impl(size_t i, bool compat, bool validate) {
+	unsigned a;
+
+	switch (i) {
+	case MALLCTL_ARENAS_ALL:
+		a = 0;
+		break;
+	case MALLCTL_ARENAS_DESTROYED:
+		a = 1;
+		break;
+	default:
+		if (compat && i == ctl_arenas->narenas) {
+			/*
+			 * Provide deprecated backward compatibility for
+			 * accessing the merged stats at index narenas rather
+			 * than via MALLCTL_ARENAS_ALL.  This is scheduled for
+			 * removal in 6.0.0.
+			 */
+			a = 0;
+		} else if (validate && i >= ctl_arenas->narenas) {
+			a = UINT_MAX;
+		} else {
+			/*
+			 * This function should never be called for an index
+			 * more than one past the range of indices that have
+			 * initialized ctl data.
+			 */
+			assert(i < ctl_arenas->narenas || (!validate && i ==
+			    ctl_arenas->narenas));
+			a = (unsigned)i + 2;
+		}
+		break;
 	}
 
-	return (false);
+	return a;
 }
 
-static void
-ctl_arena_clear(ctl_arena_stats_t *astats)
-{
+static unsigned
+arenas_i2a(size_t i) {
+	return arenas_i2a_impl(i, true, false);
+}
+
+static ctl_arena_t *
+arenas_i_impl(tsd_t *tsd, size_t i, bool compat, bool init) {
+	ctl_arena_t *ret;
 
-	astats->dss = dss_prec_names[dss_prec_limit];
-	astats->pactive = 0;
-	astats->pdirty = 0;
+	assert(!compat || !init);
+
+	ret = ctl_arenas->arenas[arenas_i2a_impl(i, compat, false)];
+	if (init && ret == NULL) {
+		if (config_stats) {
+			struct container_s {
+				ctl_arena_t		ctl_arena;
+				ctl_arena_stats_t	astats;
+			};
+			struct container_s *cont =
+			    (struct container_s *)base_alloc(tsd_tsdn(tsd),
+			    b0get(), sizeof(struct container_s), QUANTUM);
+			if (cont == NULL) {
+				return NULL;
+			}
+			ret = &cont->ctl_arena;
+			ret->astats = &cont->astats;
+		} else {
+			ret = (ctl_arena_t *)base_alloc(tsd_tsdn(tsd), b0get(),
+			    sizeof(ctl_arena_t), QUANTUM);
+			if (ret == NULL) {
+				return NULL;
+			}
+		}
+		ret->arena_ind = (unsigned)i;
+		ctl_arenas->arenas[arenas_i2a_impl(i, compat, false)] = ret;
+	}
+
+	assert(ret == NULL || arenas_i2a(ret->arena_ind) == arenas_i2a(i));
+	return ret;
+}
+
+static ctl_arena_t *
+arenas_i(size_t i) {
+	ctl_arena_t *ret = arenas_i_impl(tsd_fetch(), i, true, false);
+	assert(ret != NULL);
+	return ret;
+}
+
+static void
+ctl_arena_clear(ctl_arena_t *ctl_arena) {
+	ctl_arena->nthreads = 0;
+	ctl_arena->dss = dss_prec_names[dss_prec_limit];
+	ctl_arena->dirty_decay_ms = -1;
+	ctl_arena->muzzy_decay_ms = -1;
+	ctl_arena->pactive = 0;
+	ctl_arena->pdirty = 0;
+	ctl_arena->pmuzzy = 0;
 	if (config_stats) {
-		memset(&astats->astats, 0, sizeof(arena_stats_t));
-		astats->allocated_small = 0;
-		astats->nmalloc_small = 0;
-		astats->ndalloc_small = 0;
-		astats->nrequests_small = 0;
-		memset(astats->bstats, 0, NBINS * sizeof(malloc_bin_stats_t));
-		memset(astats->lstats, 0, nlclasses *
+		memset(&ctl_arena->astats->astats, 0, sizeof(arena_stats_t));
+		ctl_arena->astats->allocated_small = 0;
+		ctl_arena->astats->nmalloc_small = 0;
+		ctl_arena->astats->ndalloc_small = 0;
+		ctl_arena->astats->nrequests_small = 0;
+		memset(ctl_arena->astats->bstats, 0, NBINS *
+		    sizeof(malloc_bin_stats_t));
+		memset(ctl_arena->astats->lstats, 0, (NSIZES - NBINS) *
 		    sizeof(malloc_large_stats_t));
 	}
 }
 
 static void
-ctl_arena_stats_amerge(ctl_arena_stats_t *cstats, arena_t *arena)
-{
+ctl_arena_stats_amerge(tsdn_t *tsdn, ctl_arena_t *ctl_arena, arena_t *arena) {
 	unsigned i;
 
-	arena_stats_merge(arena, &cstats->dss, &cstats->pactive,
-	    &cstats->pdirty, &cstats->astats, cstats->bstats, cstats->lstats);
-
-	for (i = 0; i < NBINS; i++) {
-		cstats->allocated_small += cstats->bstats[i].allocated;
-		cstats->nmalloc_small += cstats->bstats[i].nmalloc;
-		cstats->ndalloc_small += cstats->bstats[i].ndalloc;
-		cstats->nrequests_small += cstats->bstats[i].nrequests;
+	if (config_stats) {
+		arena_stats_merge(tsdn, arena, &ctl_arena->nthreads,
+		    &ctl_arena->dss, &ctl_arena->dirty_decay_ms,
+		    &ctl_arena->muzzy_decay_ms, &ctl_arena->pactive,
+		    &ctl_arena->pdirty, &ctl_arena->pmuzzy,
+		    &ctl_arena->astats->astats, ctl_arena->astats->bstats,
+		    ctl_arena->astats->lstats);
+
+		for (i = 0; i < NBINS; i++) {
+			ctl_arena->astats->allocated_small +=
+			    ctl_arena->astats->bstats[i].curregs *
+			    sz_index2size(i);
+			ctl_arena->astats->nmalloc_small +=
+			    ctl_arena->astats->bstats[i].nmalloc;
+			ctl_arena->astats->ndalloc_small +=
+			    ctl_arena->astats->bstats[i].ndalloc;
+			ctl_arena->astats->nrequests_small +=
+			    ctl_arena->astats->bstats[i].nrequests;
+		}
+	} else {
+		arena_basic_stats_merge(tsdn, arena, &ctl_arena->nthreads,
+		    &ctl_arena->dss, &ctl_arena->dirty_decay_ms,
+		    &ctl_arena->muzzy_decay_ms, &ctl_arena->pactive,
+		    &ctl_arena->pdirty, &ctl_arena->pmuzzy);
 	}
 }
 
 static void
-ctl_arena_stats_smerge(ctl_arena_stats_t *sstats, ctl_arena_stats_t *astats)
-{
+ctl_arena_stats_sdmerge(ctl_arena_t *ctl_sdarena, ctl_arena_t *ctl_arena,
+    bool destroyed) {
 	unsigned i;
 
-	sstats->pactive += astats->pactive;
-	sstats->pdirty += astats->pdirty;
-
-	sstats->astats.mapped += astats->astats.mapped;
-	sstats->astats.npurge += astats->astats.npurge;
-	sstats->astats.nmadvise += astats->astats.nmadvise;
-	sstats->astats.purged += astats->astats.purged;
-
-	sstats->allocated_small += astats->allocated_small;
-	sstats->nmalloc_small += astats->nmalloc_small;
-	sstats->ndalloc_small += astats->ndalloc_small;
-	sstats->nrequests_small += astats->nrequests_small;
-
-	sstats->astats.allocated_large += astats->astats.allocated_large;
-	sstats->astats.nmalloc_large += astats->astats.nmalloc_large;
-	sstats->astats.ndalloc_large += astats->astats.ndalloc_large;
-	sstats->astats.nrequests_large += astats->astats.nrequests_large;
-
-	for (i = 0; i < nlclasses; i++) {
-		sstats->lstats[i].nmalloc += astats->lstats[i].nmalloc;
-		sstats->lstats[i].ndalloc += astats->lstats[i].ndalloc;
-		sstats->lstats[i].nrequests += astats->lstats[i].nrequests;
-		sstats->lstats[i].curruns += astats->lstats[i].curruns;
-	}
-
-	for (i = 0; i < NBINS; i++) {
-		sstats->bstats[i].allocated += astats->bstats[i].allocated;
-		sstats->bstats[i].nmalloc += astats->bstats[i].nmalloc;
-		sstats->bstats[i].ndalloc += astats->bstats[i].ndalloc;
-		sstats->bstats[i].nrequests += astats->bstats[i].nrequests;
-		if (config_tcache) {
-			sstats->bstats[i].nfills += astats->bstats[i].nfills;
-			sstats->bstats[i].nflushes +=
+	if (!destroyed) {
+		ctl_sdarena->nthreads += ctl_arena->nthreads;
+		ctl_sdarena->pactive += ctl_arena->pactive;
+		ctl_sdarena->pdirty += ctl_arena->pdirty;
+		ctl_sdarena->pmuzzy += ctl_arena->pmuzzy;
+	} else {
+		assert(ctl_arena->nthreads == 0);
+		assert(ctl_arena->pactive == 0);
+		assert(ctl_arena->pdirty == 0);
+		assert(ctl_arena->pmuzzy == 0);
+	}
+
+	if (config_stats) {
+		ctl_arena_stats_t *sdstats = ctl_sdarena->astats;
+		ctl_arena_stats_t *astats = ctl_arena->astats;
+
+		if (!destroyed) {
+			accum_atomic_zu(&sdstats->astats.mapped,
+			    &astats->astats.mapped);
+			accum_atomic_zu(&sdstats->astats.retained,
+			    &astats->astats.retained);
+		}
+
+		accum_arena_stats_u64(&sdstats->astats.decay_dirty.npurge,
+		    &astats->astats.decay_dirty.npurge);
+		accum_arena_stats_u64(&sdstats->astats.decay_dirty.nmadvise,
+		    &astats->astats.decay_dirty.nmadvise);
+		accum_arena_stats_u64(&sdstats->astats.decay_dirty.purged,
+		    &astats->astats.decay_dirty.purged);
+
+		accum_arena_stats_u64(&sdstats->astats.decay_muzzy.npurge,
+		    &astats->astats.decay_muzzy.npurge);
+		accum_arena_stats_u64(&sdstats->astats.decay_muzzy.nmadvise,
+		    &astats->astats.decay_muzzy.nmadvise);
+		accum_arena_stats_u64(&sdstats->astats.decay_muzzy.purged,
+		    &astats->astats.decay_muzzy.purged);
+
+#define OP(mtx) malloc_mutex_prof_merge(				\
+		    &(sdstats->astats.mutex_prof_data[			\
+		        arena_prof_mutex_##mtx]),			\
+		    &(astats->astats.mutex_prof_data[			\
+		        arena_prof_mutex_##mtx]));
+MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+		if (!destroyed) {
+			accum_atomic_zu(&sdstats->astats.base,
+			    &astats->astats.base);
+			accum_atomic_zu(&sdstats->astats.internal,
+			    &astats->astats.internal);
+			accum_atomic_zu(&sdstats->astats.resident,
+			    &astats->astats.resident);
+		} else {
+			assert(atomic_load_zu(
+			    &astats->astats.internal, ATOMIC_RELAXED) == 0);
+		}
+
+		if (!destroyed) {
+			sdstats->allocated_small += astats->allocated_small;
+		} else {
+			assert(astats->allocated_small == 0);
+		}
+		sdstats->nmalloc_small += astats->nmalloc_small;
+		sdstats->ndalloc_small += astats->ndalloc_small;
+		sdstats->nrequests_small += astats->nrequests_small;
+
+		if (!destroyed) {
+			accum_atomic_zu(&sdstats->astats.allocated_large,
+			    &astats->astats.allocated_large);
+		} else {
+			assert(atomic_load_zu(&astats->astats.allocated_large,
+			    ATOMIC_RELAXED) == 0);
+		}
+		accum_arena_stats_u64(&sdstats->astats.nmalloc_large,
+		    &astats->astats.nmalloc_large);
+		accum_arena_stats_u64(&sdstats->astats.ndalloc_large,
+		    &astats->astats.ndalloc_large);
+		accum_arena_stats_u64(&sdstats->astats.nrequests_large,
+		    &astats->astats.nrequests_large);
+
+		accum_atomic_zu(&sdstats->astats.tcache_bytes,
+		    &astats->astats.tcache_bytes);
+
+		if (ctl_arena->arena_ind == 0) {
+			sdstats->astats.uptime = astats->astats.uptime;
+		}
+
+		for (i = 0; i < NBINS; i++) {
+			sdstats->bstats[i].nmalloc += astats->bstats[i].nmalloc;
+			sdstats->bstats[i].ndalloc += astats->bstats[i].ndalloc;
+			sdstats->bstats[i].nrequests +=
+			    astats->bstats[i].nrequests;
+			if (!destroyed) {
+				sdstats->bstats[i].curregs +=
+				    astats->bstats[i].curregs;
+			} else {
+				assert(astats->bstats[i].curregs == 0);
+			}
+			sdstats->bstats[i].nfills += astats->bstats[i].nfills;
+			sdstats->bstats[i].nflushes +=
 			    astats->bstats[i].nflushes;
+			sdstats->bstats[i].nslabs += astats->bstats[i].nslabs;
+			sdstats->bstats[i].reslabs += astats->bstats[i].reslabs;
+			if (!destroyed) {
+				sdstats->bstats[i].curslabs +=
+				    astats->bstats[i].curslabs;
+			} else {
+				assert(astats->bstats[i].curslabs == 0);
+			}
+			malloc_mutex_prof_merge(&sdstats->bstats[i].mutex_data,
+			    &astats->bstats[i].mutex_data);
+		}
+
+		for (i = 0; i < NSIZES - NBINS; i++) {
+			accum_arena_stats_u64(&sdstats->lstats[i].nmalloc,
+			    &astats->lstats[i].nmalloc);
+			accum_arena_stats_u64(&sdstats->lstats[i].ndalloc,
+			    &astats->lstats[i].ndalloc);
+			accum_arena_stats_u64(&sdstats->lstats[i].nrequests,
+			    &astats->lstats[i].nrequests);
+			if (!destroyed) {
+				sdstats->lstats[i].curlextents +=
+				    astats->lstats[i].curlextents;
+			} else {
+				assert(astats->lstats[i].curlextents == 0);
+			}
 		}
-		sstats->bstats[i].nruns += astats->bstats[i].nruns;
-		sstats->bstats[i].reruns += astats->bstats[i].reruns;
-		sstats->bstats[i].curruns += astats->bstats[i].curruns;
 	}
 }
 
 static void
-ctl_arena_refresh(arena_t *arena, unsigned i)
-{
-	ctl_arena_stats_t *astats = &ctl_stats.arenas[i];
-	ctl_arena_stats_t *sstats = &ctl_stats.arenas[ctl_stats.narenas];
+ctl_arena_refresh(tsdn_t *tsdn, arena_t *arena, ctl_arena_t *ctl_sdarena,
+    unsigned i, bool destroyed) {
+	ctl_arena_t *ctl_arena = arenas_i(i);
+
+	ctl_arena_clear(ctl_arena);
+	ctl_arena_stats_amerge(tsdn, ctl_arena, arena);
+	/* Merge into sum stats as well. */
+	ctl_arena_stats_sdmerge(ctl_sdarena, ctl_arena, destroyed);
+}
 
-	ctl_arena_clear(astats);
+static unsigned
+ctl_arena_init(tsd_t *tsd, extent_hooks_t *extent_hooks) {
+	unsigned arena_ind;
+	ctl_arena_t *ctl_arena;
 
-	sstats->nthreads += astats->nthreads;
-	if (config_stats) {
-		ctl_arena_stats_amerge(astats, arena);
-		/* Merge into sum stats as well. */
-		ctl_arena_stats_smerge(sstats, astats);
+	if ((ctl_arena = ql_last(&ctl_arenas->destroyed, destroyed_link)) !=
+	    NULL) {
+		ql_remove(&ctl_arenas->destroyed, ctl_arena, destroyed_link);
+		arena_ind = ctl_arena->arena_ind;
 	} else {
-		astats->pactive += arena->nactive;
-		astats->pdirty += arena->ndirty;
-		/* Merge into sum stats as well. */
-		sstats->pactive += arena->nactive;
-		sstats->pdirty += arena->ndirty;
+		arena_ind = ctl_arenas->narenas;
 	}
-}
 
-static bool
-ctl_grow(void)
-{
-	ctl_arena_stats_t *astats;
-	arena_t **tarenas;
-
-	/* Allocate extended arena stats and arenas arrays. */
-	astats = (ctl_arena_stats_t *)imalloc((ctl_stats.narenas + 2) *
-	    sizeof(ctl_arena_stats_t));
-	if (astats == NULL)
-		return (true);
-	tarenas = (arena_t **)imalloc((ctl_stats.narenas + 1) *
-	    sizeof(arena_t *));
-	if (tarenas == NULL) {
-		idalloc(astats);
-		return (true);
-	}
-
-	/* Initialize the new astats element. */
-	memcpy(astats, ctl_stats.arenas, (ctl_stats.narenas + 1) *
-	    sizeof(ctl_arena_stats_t));
-	memset(&astats[ctl_stats.narenas + 1], 0, sizeof(ctl_arena_stats_t));
-	if (ctl_arena_init(&astats[ctl_stats.narenas + 1])) {
-		idalloc(tarenas);
-		idalloc(astats);
-		return (true);
-	}
-	/* Swap merged stats to their new location. */
-	{
-		ctl_arena_stats_t tstats;
-		memcpy(&tstats, &astats[ctl_stats.narenas],
-		    sizeof(ctl_arena_stats_t));
-		memcpy(&astats[ctl_stats.narenas],
-		    &astats[ctl_stats.narenas + 1], sizeof(ctl_arena_stats_t));
-		memcpy(&astats[ctl_stats.narenas + 1], &tstats,
-		    sizeof(ctl_arena_stats_t));
-	}
-	/* Initialize the new arenas element. */
-	tarenas[ctl_stats.narenas] = NULL;
-	{
-		arena_t **arenas_old = arenas;
-		/*
-		 * Swap extended arenas array into place.  Although ctl_mtx
-		 * protects this function from other threads extending the
-		 * array, it does not protect from other threads mutating it
-		 * (i.e. initializing arenas and setting array elements to
-		 * point to them).  Therefore, array copying must happen under
-		 * the protection of arenas_lock.
-		 */
-		malloc_mutex_lock(&arenas_lock);
-		arenas = tarenas;
-		memcpy(arenas, arenas_old, ctl_stats.narenas *
-		    sizeof(arena_t *));
-		narenas_total++;
-		arenas_extend(narenas_total - 1);
-		malloc_mutex_unlock(&arenas_lock);
-		/*
-		 * Deallocate arenas_old only if it came from imalloc() (not
-		 * base_alloc()).
-		 */
-		if (ctl_stats.narenas != narenas_auto)
-			idalloc(arenas_old);
+	/* Trigger stats allocation. */
+	if (arenas_i_impl(tsd, arena_ind, false, true) == NULL) {
+		return UINT_MAX;
 	}
-	ctl_stats.arenas = astats;
-	ctl_stats.narenas++;
 
-	return (false);
-}
+	/* Initialize new arena. */
+	if (arena_init(tsd_tsdn(tsd), arena_ind, extent_hooks) == NULL) {
+		return UINT_MAX;
+	}
 
-static void
-ctl_refresh(void)
-{
-	unsigned i;
-	VARIABLE_ARRAY(arena_t *, tarenas, ctl_stats.narenas);
+	if (arena_ind == ctl_arenas->narenas) {
+		ctl_arenas->narenas++;
+	}
 
-	if (config_stats) {
-		malloc_mutex_lock(&chunks_mtx);
-		ctl_stats.chunks.current = stats_chunks.curchunks;
-		ctl_stats.chunks.total = stats_chunks.nchunks;
-		ctl_stats.chunks.high = stats_chunks.highchunks;
-		malloc_mutex_unlock(&chunks_mtx);
+	return arena_ind;
+}
 
-		malloc_mutex_lock(&huge_mtx);
-		ctl_stats.huge.allocated = huge_allocated;
-		ctl_stats.huge.nmalloc = huge_nmalloc;
-		ctl_stats.huge.ndalloc = huge_ndalloc;
-		malloc_mutex_unlock(&huge_mtx);
+static void
+ctl_background_thread_stats_read(tsdn_t *tsdn) {
+	background_thread_stats_t *stats = &ctl_stats->background_thread;
+	if (!have_background_thread ||
+	    background_thread_stats_read(tsdn, stats)) {
+		memset(stats, 0, sizeof(background_thread_stats_t));
+		nstime_init(&stats->run_interval, 0);
 	}
+}
+
+static void
+ctl_refresh(tsdn_t *tsdn) {
+	unsigned i;
+	ctl_arena_t *ctl_sarena = arenas_i(MALLCTL_ARENAS_ALL);
+	VARIABLE_ARRAY(arena_t *, tarenas, ctl_arenas->narenas);
 
 	/*
 	 * Clear sum stats, since they will be merged into by
 	 * ctl_arena_refresh().
 	 */
-	ctl_stats.arenas[ctl_stats.narenas].nthreads = 0;
-	ctl_arena_clear(&ctl_stats.arenas[ctl_stats.narenas]);
-
-	malloc_mutex_lock(&arenas_lock);
-	memcpy(tarenas, arenas, sizeof(arena_t *) * ctl_stats.narenas);
-	for (i = 0; i < ctl_stats.narenas; i++) {
-		if (arenas[i] != NULL)
-			ctl_stats.arenas[i].nthreads = arenas[i]->nthreads;
-		else
-			ctl_stats.arenas[i].nthreads = 0;
-	}
-	malloc_mutex_unlock(&arenas_lock);
-	for (i = 0; i < ctl_stats.narenas; i++) {
+	ctl_arena_clear(ctl_sarena);
+
+	for (i = 0; i < ctl_arenas->narenas; i++) {
+		tarenas[i] = arena_get(tsdn, i, false);
+	}
+
+	for (i = 0; i < ctl_arenas->narenas; i++) {
+		ctl_arena_t *ctl_arena = arenas_i(i);
 		bool initialized = (tarenas[i] != NULL);
 
-		ctl_stats.arenas[i].initialized = initialized;
-		if (initialized)
-			ctl_arena_refresh(tarenas[i], i);
+		ctl_arena->initialized = initialized;
+		if (initialized) {
+			ctl_arena_refresh(tsdn, tarenas[i], ctl_sarena, i,
+			    false);
+		}
 	}
 
 	if (config_stats) {
-		ctl_stats.allocated =
-		    ctl_stats.arenas[ctl_stats.narenas].allocated_small
-		    + ctl_stats.arenas[ctl_stats.narenas].astats.allocated_large
-		    + ctl_stats.huge.allocated;
-		ctl_stats.active =
-		    (ctl_stats.arenas[ctl_stats.narenas].pactive << LG_PAGE)
-		    + ctl_stats.huge.allocated;
-		ctl_stats.mapped = (ctl_stats.chunks.current << opt_lg_chunk);
+		ctl_stats->allocated = ctl_sarena->astats->allocated_small +
+		    atomic_load_zu(&ctl_sarena->astats->astats.allocated_large,
+			ATOMIC_RELAXED);
+		ctl_stats->active = (ctl_sarena->pactive << LG_PAGE);
+		ctl_stats->metadata = atomic_load_zu(
+		    &ctl_sarena->astats->astats.base, ATOMIC_RELAXED) +
+		    atomic_load_zu(&ctl_sarena->astats->astats.internal,
+			ATOMIC_RELAXED);
+		ctl_stats->resident = atomic_load_zu(
+		    &ctl_sarena->astats->astats.resident, ATOMIC_RELAXED);
+		ctl_stats->mapped = atomic_load_zu(
+		    &ctl_sarena->astats->astats.mapped, ATOMIC_RELAXED);
+		ctl_stats->retained = atomic_load_zu(
+		    &ctl_sarena->astats->astats.retained, ATOMIC_RELAXED);
+
+		ctl_background_thread_stats_read(tsdn);
+
+#define READ_GLOBAL_MUTEX_PROF_DATA(i, mtx)				\
+    malloc_mutex_lock(tsdn, &mtx);					\
+    malloc_mutex_prof_read(tsdn, &ctl_stats->mutex_prof_data[i], &mtx);	\
+    malloc_mutex_unlock(tsdn, &mtx);
+
+		if (config_prof && opt_prof) {
+			READ_GLOBAL_MUTEX_PROF_DATA(global_prof_mutex_prof,
+			    bt2gctx_mtx);
+		}
+		if (have_background_thread) {
+			READ_GLOBAL_MUTEX_PROF_DATA(
+			    global_prof_mutex_background_thread,
+			    background_thread_lock);
+		} else {
+			memset(&ctl_stats->mutex_prof_data[
+			    global_prof_mutex_background_thread], 0,
+			    sizeof(mutex_prof_data_t));
+		}
+		/* We own ctl mutex already. */
+		malloc_mutex_prof_read(tsdn,
+		    &ctl_stats->mutex_prof_data[global_prof_mutex_ctl],
+		    &ctl_mtx);
+#undef READ_GLOBAL_MUTEX_PROF_DATA
 	}
-
-	ctl_epoch++;
+	ctl_arenas->epoch++;
 }
 
 static bool
-ctl_init(void)
-{
+ctl_init(tsd_t *tsd) {
 	bool ret;
+	tsdn_t *tsdn = tsd_tsdn(tsd);
+
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	if (!ctl_initialized) {
+		ctl_arena_t *ctl_sarena, *ctl_darena;
+		unsigned i;
 
-	malloc_mutex_lock(&ctl_mtx);
-	if (ctl_initialized == false) {
 		/*
-		 * Allocate space for one extra arena stats element, which
-		 * contains summed stats across all arenas.
+		 * Allocate demand-zeroed space for pointers to the full
+		 * range of supported arena indices.
 		 */
-		assert(narenas_auto == narenas_total_get());
-		ctl_stats.narenas = narenas_auto;
-		ctl_stats.arenas = (ctl_arena_stats_t *)base_alloc(
-		    (ctl_stats.narenas + 1) * sizeof(ctl_arena_stats_t));
-		if (ctl_stats.arenas == NULL) {
+		if (ctl_arenas == NULL) {
+			ctl_arenas = (ctl_arenas_t *)base_alloc(tsdn,
+			    b0get(), sizeof(ctl_arenas_t), QUANTUM);
+			if (ctl_arenas == NULL) {
+				ret = true;
+				goto label_return;
+			}
+		}
+
+		if (config_stats && ctl_stats == NULL) {
+			ctl_stats = (ctl_stats_t *)base_alloc(tsdn, b0get(),
+			    sizeof(ctl_stats_t), QUANTUM);
+			if (ctl_stats == NULL) {
+				ret = true;
+				goto label_return;
+			}
+		}
+
+		/*
+		 * Allocate space for the current full range of arenas
+		 * here rather than doing it lazily elsewhere, in order
+		 * to limit when OOM-caused errors can occur.
+		 */
+		if ((ctl_sarena = arenas_i_impl(tsd, MALLCTL_ARENAS_ALL, false,
+		    true)) == NULL) {
 			ret = true;
 			goto label_return;
 		}
-		memset(ctl_stats.arenas, 0, (ctl_stats.narenas + 1) *
-		    sizeof(ctl_arena_stats_t));
+		ctl_sarena->initialized = true;
 
+		if ((ctl_darena = arenas_i_impl(tsd, MALLCTL_ARENAS_DESTROYED,
+		    false, true)) == NULL) {
+			ret = true;
+			goto label_return;
+		}
+		ctl_arena_clear(ctl_darena);
 		/*
-		 * Initialize all stats structures, regardless of whether they
-		 * ever get used.  Lazy initialization would allow errors to
-		 * cause inconsistent state to be viewable by the application.
+		 * Don't toggle ctl_darena to initialized until an arena is
+		 * actually destroyed, so that arena.<i>.initialized can be used
+		 * to query whether the stats are relevant.
 		 */
-		if (config_stats) {
-			unsigned i;
-			for (i = 0; i <= ctl_stats.narenas; i++) {
-				if (ctl_arena_init(&ctl_stats.arenas[i])) {
-					ret = true;
-					goto label_return;
-				}
+
+		ctl_arenas->narenas = narenas_total_get();
+		for (i = 0; i < ctl_arenas->narenas; i++) {
+			if (arenas_i_impl(tsd, i, false, true) == NULL) {
+				ret = true;
+				goto label_return;
 			}
 		}
-		ctl_stats.arenas[ctl_stats.narenas].initialized = true;
 
-		ctl_epoch = 0;
-		ctl_refresh();
+		ql_new(&ctl_arenas->destroyed);
+		ctl_refresh(tsdn);
+
 		ctl_initialized = true;
 	}
 
 	ret = false;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return ret;
 }
 
 static int
-ctl_lookup(const char *name, ctl_node_t const **nodesp, size_t *mibp,
-    size_t *depthp)
-{
+ctl_lookup(tsdn_t *tsdn, const char *name, ctl_node_t const **nodesp,
+    size_t *mibp, size_t *depthp) {
 	int ret;
 	const char *elm, *tdot, *dot;
 	size_t elen, i, j;
@@ -750,9 +1080,10 @@ ctl_lookup(const char *name, ctl_node_t const **nodesp, size_t *mibp,
 				if (strlen(child->name) == elen &&
 				    strncmp(elm, child->name, elen) == 0) {
 					node = child;
-					if (nodesp != NULL)
+					if (nodesp != NULL) {
 						nodesp[i] =
 						    (const ctl_node_t *)node;
+					}
 					mibp[i] = j;
 					break;
 				}
@@ -773,14 +1104,15 @@ ctl_lookup(const char *name, ctl_node_t const **nodesp, size_t *mibp,
 			}
 
 			inode = ctl_indexed_node(node->children);
-			node = inode->index(mibp, *depthp, (size_t)index);
+			node = inode->index(tsdn, mibp, *depthp, (size_t)index);
 			if (node == NULL) {
 				ret = ENOENT;
 				goto label_return;
 			}
 
-			if (nodesp != NULL)
+			if (nodesp != NULL) {
 				nodesp[i] = (const ctl_node_t *)node;
+			}
 			mibp[i] = (size_t)index;
 		}
 
@@ -813,33 +1145,33 @@ ctl_lookup(const char *name, ctl_node_t const **nodesp, size_t *mibp,
 
 	ret = 0;
 label_return:
-	return (ret);
+	return ret;
 }
 
 int
-ctl_byname(const char *name, void *oldp, size_t *oldlenp, void *newp,
-    size_t newlen)
-{
+ctl_byname(tsd_t *tsd, const char *name, void *oldp, size_t *oldlenp,
+    void *newp, size_t newlen) {
 	int ret;
 	size_t depth;
 	ctl_node_t const *nodes[CTL_MAX_DEPTH];
 	size_t mib[CTL_MAX_DEPTH];
 	const ctl_named_node_t *node;
 
-	if (ctl_initialized == false && ctl_init()) {
+	if (!ctl_initialized && ctl_init(tsd)) {
 		ret = EAGAIN;
 		goto label_return;
 	}
 
 	depth = CTL_MAX_DEPTH;
-	ret = ctl_lookup(name, nodes, mib, &depth);
-	if (ret != 0)
+	ret = ctl_lookup(tsd_tsdn(tsd), name, nodes, mib, &depth);
+	if (ret != 0) {
 		goto label_return;
+	}
 
 	node = ctl_named_node(nodes[depth-1]);
-	if (node != NULL && node->ctl)
-		ret = node->ctl(mib, depth, oldp, oldlenp, newp, newlen);
-	else {
+	if (node != NULL && node->ctl) {
+		ret = node->ctl(tsd, mib, depth, oldp, oldlenp, newp, newlen);
+	} else {
 		/* The name refers to a partial path through the ctl tree. */
 		ret = ENOENT;
 	}
@@ -849,29 +1181,27 @@ label_return:
 }
 
 int
-ctl_nametomib(const char *name, size_t *mibp, size_t *miblenp)
-{
+ctl_nametomib(tsd_t *tsd, const char *name, size_t *mibp, size_t *miblenp) {
 	int ret;
 
-	if (ctl_initialized == false && ctl_init()) {
+	if (!ctl_initialized && ctl_init(tsd)) {
 		ret = EAGAIN;
 		goto label_return;
 	}
 
-	ret = ctl_lookup(name, NULL, mibp, miblenp);
+	ret = ctl_lookup(tsd_tsdn(tsd), name, NULL, mibp, miblenp);
 label_return:
 	return(ret);
 }
 
 int
-ctl_bymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+ctl_bymib(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	const ctl_named_node_t *node;
 	size_t i;
 
-	if (ctl_initialized == false && ctl_init()) {
+	if (!ctl_initialized && ctl_init(tsd)) {
 		ret = EAGAIN;
 		goto label_return;
 	}
@@ -893,7 +1223,7 @@ ctl_bymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
 
 			/* Indexed element. */
 			inode = ctl_indexed_node(node->children);
-			node = inode->index(mib, miblen, mib[i]);
+			node = inode->index(tsd_tsdn(tsd), mib, miblen, mib[i]);
 			if (node == NULL) {
 				ret = ENOENT;
 				goto label_return;
@@ -902,9 +1232,9 @@ ctl_bymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
 	}
 
 	/* Call the ctl function. */
-	if (node && node->ctl)
-		ret = node->ctl(mib, miblen, oldp, oldlenp, newp, newlen);
-	else {
+	if (node && node->ctl) {
+		ret = node->ctl(tsd, mib, miblen, oldp, oldlenp, newp, newlen);
+	} else {
 		/* Partial MIB. */
 		ret = ENOENT;
 	}
@@ -914,56 +1244,58 @@ label_return:
 }
 
 bool
-ctl_boot(void)
-{
-
-	if (malloc_mutex_init(&ctl_mtx))
-		return (true);
+ctl_boot(void) {
+	if (malloc_mutex_init(&ctl_mtx, "ctl", WITNESS_RANK_CTL,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
 
 	ctl_initialized = false;
 
-	return (false);
+	return false;
 }
 
 void
-ctl_prefork(void)
-{
-
-	malloc_mutex_prefork(&ctl_mtx);
+ctl_prefork(tsdn_t *tsdn) {
+	malloc_mutex_prefork(tsdn, &ctl_mtx);
 }
 
 void
-ctl_postfork_parent(void)
-{
-
-	malloc_mutex_postfork_parent(&ctl_mtx);
+ctl_postfork_parent(tsdn_t *tsdn) {
+	malloc_mutex_postfork_parent(tsdn, &ctl_mtx);
 }
 
 void
-ctl_postfork_child(void)
-{
-
-	malloc_mutex_postfork_child(&ctl_mtx);
+ctl_postfork_child(tsdn_t *tsdn) {
+	malloc_mutex_postfork_child(tsdn, &ctl_mtx);
 }
 
 /******************************************************************************/
 /* *_ctl() functions. */
 
-#define	READONLY()	do {						\
+#define READONLY()	do {						\
 	if (newp != NULL || newlen != 0) {				\
 		ret = EPERM;						\
 		goto label_return;					\
 	}								\
 } while (0)
 
-#define	WRITEONLY()	do {						\
+#define WRITEONLY()	do {						\
 	if (oldp != NULL || oldlenp != NULL) {				\
 		ret = EPERM;						\
 		goto label_return;					\
 	}								\
 } while (0)
 
-#define	READ(v, t)	do {						\
+#define READ_XOR_WRITE()	do {					\
+	if ((oldp != NULL && oldlenp != NULL) && (newp != NULL ||	\
+	    newlen != 0)) {						\
+		ret = EPERM;						\
+		goto label_return;					\
+	}								\
+} while (0)
+
+#define READ(v, t)	do {						\
 	if (oldp != NULL && oldlenp != NULL) {				\
 		if (*oldlenp != sizeof(t)) {				\
 			size_t	copylen = (sizeof(t) <= *oldlenp)	\
@@ -971,12 +1303,12 @@ ctl_postfork_child(void)
 			memcpy(oldp, (void *)&(v), copylen);		\
 			ret = EINVAL;					\
 			goto label_return;				\
-		} else							\
-			*(t *)oldp = (v);				\
+		}							\
+		*(t *)oldp = (v);					\
 	}								\
 } while (0)
 
-#define	WRITE(v, t)	do {						\
+#define WRITE(v, t)	do {						\
 	if (newp != NULL) {						\
 		if (newlen != sizeof(t)) {				\
 			ret = EINVAL;					\
@@ -986,101 +1318,109 @@ ctl_postfork_child(void)
 	}								\
 } while (0)
 
+#define MIB_UNSIGNED(v, i) do {						\
+	if (mib[i] > UINT_MAX) {					\
+		ret = EFAULT;						\
+		goto label_return;					\
+	}								\
+	v = (unsigned)mib[i];						\
+} while (0)
+
 /*
  * There's a lot of code duplication in the following macros due to limitations
  * in how nested cpp macros are expanded.
  */
-#define	CTL_RO_CLGEN(c, l, n, v, t)					\
+#define CTL_RO_CLGEN(c, l, n, v, t)					\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
 	t oldval;							\
 									\
-	if ((c) == false)						\
-		return (ENOENT);					\
-	if (l)								\
-		malloc_mutex_lock(&ctl_mtx);				\
+	if (!(c)) {							\
+		return ENOENT;						\
+	}								\
+	if (l) {							\
+		malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);		\
+	}								\
 	READONLY();							\
 	oldval = (v);							\
 	READ(oldval, t);						\
 									\
 	ret = 0;							\
 label_return:								\
-	if (l)								\
-		malloc_mutex_unlock(&ctl_mtx);				\
-	return (ret);							\
+	if (l) {							\
+		malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);		\
+	}								\
+	return ret;							\
 }
 
-#define	CTL_RO_CGEN(c, n, v, t)						\
+#define CTL_RO_CGEN(c, n, v, t)						\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
 	t oldval;							\
 									\
-	if ((c) == false)						\
-		return (ENOENT);					\
-	malloc_mutex_lock(&ctl_mtx);					\
+	if (!(c)) {							\
+		return ENOENT;						\
+	}								\
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);			\
 	READONLY();							\
 	oldval = (v);							\
 	READ(oldval, t);						\
 									\
 	ret = 0;							\
 label_return:								\
-	malloc_mutex_unlock(&ctl_mtx);					\
-	return (ret);							\
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);			\
+	return ret;							\
 }
 
-#define	CTL_RO_GEN(n, v, t)						\
+#define CTL_RO_GEN(n, v, t)						\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
 	t oldval;							\
 									\
-	malloc_mutex_lock(&ctl_mtx);					\
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);			\
 	READONLY();							\
 	oldval = (v);							\
 	READ(oldval, t);						\
 									\
 	ret = 0;							\
 label_return:								\
-	malloc_mutex_unlock(&ctl_mtx);					\
-	return (ret);							\
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);			\
+	return ret;							\
 }
 
 /*
  * ctl_mtx is not acquired, under the assumption that no pertinent data will
  * mutate during the call.
  */
-#define	CTL_RO_NL_CGEN(c, n, v, t)					\
+#define CTL_RO_NL_CGEN(c, n, v, t)					\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
 	t oldval;							\
 									\
-	if ((c) == false)						\
-		return (ENOENT);					\
+	if (!(c)) {							\
+		return ENOENT;						\
+	}								\
 	READONLY();							\
 	oldval = (v);							\
 	READ(oldval, t);						\
 									\
 	ret = 0;							\
 label_return:								\
-	return (ret);							\
+	return ret;							\
 }
 
-#define	CTL_RO_NL_GEN(n, v, t)						\
+#define CTL_RO_NL_GEN(n, v, t)						\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
 	t oldval;							\
 									\
@@ -1090,24 +1430,42 @@ n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
 									\
 	ret = 0;							\
 label_return:								\
-	return (ret);							\
+	return ret;							\
 }
 
-#define	CTL_RO_BOOL_CONFIG_GEN(n)					\
+#define CTL_TSD_RO_NL_CGEN(c, n, m, t)					\
 static int								\
-n##_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,	\
-    void *newp, size_t newlen)						\
-{									\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
 	int ret;							\
-	bool oldval;							\
+	t oldval;							\
+									\
+	if (!(c)) {							\
+		return ENOENT;						\
+	}								\
+	READONLY();							\
+	oldval = (m(tsd));						\
+	READ(oldval, t);						\
+									\
+	ret = 0;							\
+label_return:								\
+	return ret;							\
+}
+
+#define CTL_RO_CONFIG_GEN(n, t)						\
+static int								\
+n##_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,	\
+    size_t *oldlenp, void *newp, size_t newlen) {			\
+	int ret;							\
+	t oldval;							\
 									\
 	READONLY();							\
 	oldval = n;							\
-	READ(oldval, bool);						\
+	READ(oldval, t);						\
 									\
 	ret = 0;							\
 label_return:								\
-	return (ret);							\
+	return ret;							\
 }
 
 /******************************************************************************/
@@ -1115,62 +1473,122 @@ label_return:								\
 CTL_RO_NL_GEN(version, JEMALLOC_VERSION, const char *)
 
 static int
-epoch_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+epoch_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	UNUSED uint64_t newval;
 
-	malloc_mutex_lock(&ctl_mtx);
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
 	WRITE(newval, uint64_t);
-	if (newp != NULL)
-		ctl_refresh();
-	READ(ctl_epoch, uint64_t);
+	if (newp != NULL) {
+		ctl_refresh(tsd_tsdn(tsd));
+	}
+	READ(ctl_arenas->epoch, uint64_t);
 
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return ret;
+}
+
+static int
+background_thread_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	bool oldval;
+
+	if (!have_background_thread) {
+		return ENOENT;
+	}
+	background_thread_ctl_init(tsd_tsdn(tsd));
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock);
+	if (newp == NULL) {
+		oldval = background_thread_enabled();
+		READ(oldval, bool);
+	} else {
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		oldval = background_thread_enabled();
+		READ(oldval, bool);
+
+		bool newval = *(bool *)newp;
+		if (newval == oldval) {
+			ret = 0;
+			goto label_return;
+		}
+
+		background_thread_enabled_set(tsd_tsdn(tsd), newval);
+		if (newval) {
+			if (!can_enable_background_thread) {
+				malloc_printf("<jemalloc>: Error in dlsym("
+			            "RTLD_NEXT, \"pthread_create\"). Cannot "
+				    "enable background_thread\n");
+				ret = EFAULT;
+				goto label_return;
+			}
+			if (background_threads_enable(tsd)) {
+				ret = EFAULT;
+				goto label_return;
+			}
+		} else {
+			if (background_threads_disable(tsd)) {
+				ret = EFAULT;
+				goto label_return;
+			}
+		}
+	}
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+
+	return ret;
 }
 
 /******************************************************************************/
 
-CTL_RO_BOOL_CONFIG_GEN(config_debug)
-CTL_RO_BOOL_CONFIG_GEN(config_dss)
-CTL_RO_BOOL_CONFIG_GEN(config_fill)
-CTL_RO_BOOL_CONFIG_GEN(config_lazy_lock)
-CTL_RO_BOOL_CONFIG_GEN(config_mremap)
-CTL_RO_BOOL_CONFIG_GEN(config_munmap)
-CTL_RO_BOOL_CONFIG_GEN(config_prof)
-CTL_RO_BOOL_CONFIG_GEN(config_prof_libgcc)
-CTL_RO_BOOL_CONFIG_GEN(config_prof_libunwind)
-CTL_RO_BOOL_CONFIG_GEN(config_stats)
-CTL_RO_BOOL_CONFIG_GEN(config_tcache)
-CTL_RO_BOOL_CONFIG_GEN(config_tls)
-CTL_RO_BOOL_CONFIG_GEN(config_utrace)
-CTL_RO_BOOL_CONFIG_GEN(config_valgrind)
-CTL_RO_BOOL_CONFIG_GEN(config_xmalloc)
+CTL_RO_CONFIG_GEN(config_cache_oblivious, bool)
+CTL_RO_CONFIG_GEN(config_debug, bool)
+CTL_RO_CONFIG_GEN(config_fill, bool)
+CTL_RO_CONFIG_GEN(config_lazy_lock, bool)
+CTL_RO_CONFIG_GEN(config_malloc_conf, const char *)
+CTL_RO_CONFIG_GEN(config_prof, bool)
+CTL_RO_CONFIG_GEN(config_prof_libgcc, bool)
+CTL_RO_CONFIG_GEN(config_prof_libunwind, bool)
+CTL_RO_CONFIG_GEN(config_stats, bool)
+CTL_RO_CONFIG_GEN(config_thp, bool)
+CTL_RO_CONFIG_GEN(config_utrace, bool)
+CTL_RO_CONFIG_GEN(config_xmalloc, bool)
 
 /******************************************************************************/
 
 CTL_RO_NL_GEN(opt_abort, opt_abort, bool)
+CTL_RO_NL_GEN(opt_abort_conf, opt_abort_conf, bool)
+CTL_RO_NL_GEN(opt_retain, opt_retain, bool)
 CTL_RO_NL_GEN(opt_dss, opt_dss, const char *)
-CTL_RO_NL_GEN(opt_lg_chunk, opt_lg_chunk, size_t)
-CTL_RO_NL_GEN(opt_narenas, opt_narenas, size_t)
-CTL_RO_NL_GEN(opt_lg_dirty_mult, opt_lg_dirty_mult, ssize_t)
+CTL_RO_NL_GEN(opt_narenas, opt_narenas, unsigned)
+CTL_RO_NL_GEN(opt_percpu_arena, percpu_arena_mode_names[opt_percpu_arena],
+    const char *)
+CTL_RO_NL_GEN(opt_background_thread, opt_background_thread, bool)
+CTL_RO_NL_GEN(opt_dirty_decay_ms, opt_dirty_decay_ms, ssize_t)
+CTL_RO_NL_GEN(opt_muzzy_decay_ms, opt_muzzy_decay_ms, ssize_t)
 CTL_RO_NL_GEN(opt_stats_print, opt_stats_print, bool)
-CTL_RO_NL_CGEN(config_fill, opt_junk, opt_junk, bool)
-CTL_RO_NL_CGEN(config_fill, opt_quarantine, opt_quarantine, size_t)
-CTL_RO_NL_CGEN(config_fill, opt_redzone, opt_redzone, bool)
+CTL_RO_NL_GEN(opt_stats_print_opts, opt_stats_print_opts, const char *)
+CTL_RO_NL_CGEN(config_fill, opt_junk, opt_junk, const char *)
 CTL_RO_NL_CGEN(config_fill, opt_zero, opt_zero, bool)
 CTL_RO_NL_CGEN(config_utrace, opt_utrace, opt_utrace, bool)
-CTL_RO_NL_CGEN(config_valgrind, opt_valgrind, opt_valgrind, bool)
 CTL_RO_NL_CGEN(config_xmalloc, opt_xmalloc, opt_xmalloc, bool)
-CTL_RO_NL_CGEN(config_tcache, opt_tcache, opt_tcache, bool)
-CTL_RO_NL_CGEN(config_tcache, opt_lg_tcache_max, opt_lg_tcache_max, ssize_t)
+CTL_RO_NL_GEN(opt_tcache, opt_tcache, bool)
+CTL_RO_NL_GEN(opt_lg_tcache_max, opt_lg_tcache_max, ssize_t)
 CTL_RO_NL_CGEN(config_prof, opt_prof, opt_prof, bool)
 CTL_RO_NL_CGEN(config_prof, opt_prof_prefix, opt_prof_prefix, const char *)
-CTL_RO_CGEN(config_prof, opt_prof_active, opt_prof_active, bool) /* Mutable. */
+CTL_RO_NL_CGEN(config_prof, opt_prof_active, opt_prof_active, bool)
+CTL_RO_NL_CGEN(config_prof, opt_prof_thread_active_init,
+    opt_prof_thread_active_init, bool)
 CTL_RO_NL_CGEN(config_prof, opt_lg_prof_sample, opt_lg_prof_sample, size_t)
 CTL_RO_NL_CGEN(config_prof, opt_prof_accum, opt_prof_accum, bool)
 CTL_RO_NL_CGEN(config_prof, opt_lg_prof_interval, opt_lg_prof_interval, ssize_t)
@@ -1181,504 +1599,1100 @@ CTL_RO_NL_CGEN(config_prof, opt_prof_leak, opt_prof_leak, bool)
 /******************************************************************************/
 
 static int
-thread_arena_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+thread_arena_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
+	arena_t *oldarena;
 	unsigned newind, oldind;
 
-	malloc_mutex_lock(&ctl_mtx);
-	newind = oldind = choose_arena(NULL)->ind;
+	oldarena = arena_choose(tsd, NULL);
+	if (oldarena == NULL) {
+		return EAGAIN;
+	}
+	newind = oldind = arena_ind_get(oldarena);
 	WRITE(newind, unsigned);
 	READ(oldind, unsigned);
+
 	if (newind != oldind) {
-		arena_t *arena;
+		arena_t *newarena;
 
-		if (newind >= ctl_stats.narenas) {
+		if (newind >= narenas_total_get()) {
 			/* New arena index is out of range. */
 			ret = EFAULT;
 			goto label_return;
 		}
 
+		if (have_percpu_arena &&
+		    PERCPU_ARENA_ENABLED(opt_percpu_arena)) {
+			if (newind < percpu_arena_ind_limit(opt_percpu_arena)) {
+				/*
+				 * If perCPU arena is enabled, thread_arena
+				 * control is not allowed for the auto arena
+				 * range.
+				 */
+				ret = EPERM;
+				goto label_return;
+			}
+		}
+
 		/* Initialize arena if necessary. */
-		malloc_mutex_lock(&arenas_lock);
-		if ((arena = arenas[newind]) == NULL && (arena =
-		    arenas_extend(newind)) == NULL) {
-			malloc_mutex_unlock(&arenas_lock);
+		newarena = arena_get(tsd_tsdn(tsd), newind, true);
+		if (newarena == NULL) {
 			ret = EAGAIN;
 			goto label_return;
 		}
-		assert(arena == arenas[newind]);
-		arenas[oldind]->nthreads--;
-		arenas[newind]->nthreads++;
-		malloc_mutex_unlock(&arenas_lock);
-
-		/* Set new arena association. */
-		if (config_tcache) {
-			tcache_t *tcache;
-			if ((uintptr_t)(tcache = *tcache_tsd_get()) >
-			    (uintptr_t)TCACHE_STATE_MAX) {
-				tcache_arena_dissociate(tcache);
-				tcache_arena_associate(tcache, arena);
-			}
+		/* Set new arena/tcache associations. */
+		arena_migrate(tsd, oldind, newind);
+		if (tcache_available(tsd)) {
+			tcache_arena_reassociate(tsd_tsdn(tsd),
+			    tsd_tcachep_get(tsd), newarena);
 		}
-		arenas_tsd_set(&arena);
 	}
 
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	return ret;
 }
 
-CTL_RO_NL_CGEN(config_stats, thread_allocated,
-    thread_allocated_tsd_get()->allocated, uint64_t)
-CTL_RO_NL_CGEN(config_stats, thread_allocatedp,
-    &thread_allocated_tsd_get()->allocated, uint64_t *)
-CTL_RO_NL_CGEN(config_stats, thread_deallocated,
-    thread_allocated_tsd_get()->deallocated, uint64_t)
-CTL_RO_NL_CGEN(config_stats, thread_deallocatedp,
-    &thread_allocated_tsd_get()->deallocated, uint64_t *)
+CTL_TSD_RO_NL_CGEN(config_stats, thread_allocated, tsd_thread_allocated_get,
+    uint64_t)
+CTL_TSD_RO_NL_CGEN(config_stats, thread_allocatedp, tsd_thread_allocatedp_get,
+    uint64_t *)
+CTL_TSD_RO_NL_CGEN(config_stats, thread_deallocated, tsd_thread_deallocated_get,
+    uint64_t)
+CTL_TSD_RO_NL_CGEN(config_stats, thread_deallocatedp,
+    tsd_thread_deallocatedp_get, uint64_t *)
 
 static int
-thread_tcache_enabled_ctl(const size_t *mib, size_t miblen, void *oldp,
-    size_t *oldlenp, void *newp, size_t newlen)
-{
+thread_tcache_enabled_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	bool oldval;
 
-	if (config_tcache == false)
-		return (ENOENT);
-
-	oldval = tcache_enabled_get();
+	oldval = tcache_enabled_get(tsd);
 	if (newp != NULL) {
 		if (newlen != sizeof(bool)) {
 			ret = EINVAL;
 			goto label_return;
 		}
-		tcache_enabled_set(*(bool *)newp);
+		tcache_enabled_set(tsd, *(bool *)newp);
 	}
 	READ(oldval, bool);
 
 	ret = 0;
 label_return:
-	return (ret);
+	return ret;
+}
+
+static int
+thread_tcache_flush_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+
+	if (!tcache_available(tsd)) {
+		ret = EFAULT;
+		goto label_return;
+	}
+
+	READONLY();
+	WRITEONLY();
+
+	tcache_flush(tsd);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static int
+thread_prof_name_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+
+	if (!config_prof) {
+		return ENOENT;
+	}
+
+	READ_XOR_WRITE();
+
+	if (newp != NULL) {
+		if (newlen != sizeof(const char *)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+
+		if ((ret = prof_thread_name_set(tsd, *(const char **)newp)) !=
+		    0) {
+			goto label_return;
+		}
+	} else {
+		const char *oldname = prof_thread_name_get(tsd);
+		READ(oldname, const char *);
+	}
+
+	ret = 0;
+label_return:
+	return ret;
 }
 
 static int
-thread_tcache_flush_ctl(const size_t *mib, size_t miblen, void *oldp,
-    size_t *oldlenp, void *newp, size_t newlen)
-{
+thread_prof_active_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
+	bool oldval;
 
-	if (config_tcache == false)
-		return (ENOENT);
+	if (!config_prof) {
+		return ENOENT;
+	}
+
+	oldval = prof_thread_active_get(tsd);
+	if (newp != NULL) {
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (prof_thread_active_set(tsd, *(bool *)newp)) {
+			ret = EAGAIN;
+			goto label_return;
+		}
+	}
+	READ(oldval, bool);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+/******************************************************************************/
+
+static int
+tcache_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned tcache_ind;
 
 	READONLY();
+	if (tcaches_create(tsd, &tcache_ind)) {
+		ret = EFAULT;
+		goto label_return;
+	}
+	READ(tcache_ind, unsigned);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static int
+tcache_flush_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned tcache_ind;
+
 	WRITEONLY();
+	tcache_ind = UINT_MAX;
+	WRITE(tcache_ind, unsigned);
+	if (tcache_ind == UINT_MAX) {
+		ret = EFAULT;
+		goto label_return;
+	}
+	tcaches_flush(tsd, tcache_ind);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static int
+tcache_destroy_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned tcache_ind;
 
-	tcache_flush();
+	WRITEONLY();
+	tcache_ind = UINT_MAX;
+	WRITE(tcache_ind, unsigned);
+	if (tcache_ind == UINT_MAX) {
+		ret = EFAULT;
+		goto label_return;
+	}
+	tcaches_destroy(tsd, tcache_ind);
 
 	ret = 0;
 label_return:
-	return (ret);
+	return ret;
 }
 
 /******************************************************************************/
 
-/* ctl_mutex must be held during execution of this function. */
+static int
+arena_i_initialized_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	tsdn_t *tsdn = tsd_tsdn(tsd);
+	unsigned arena_ind;
+	bool initialized;
+
+	READONLY();
+	MIB_UNSIGNED(arena_ind, 1);
+
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	initialized = arenas_i(arena_ind)->initialized;
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+
+	READ(initialized, bool);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
 static void
-arena_purge(unsigned arena_ind)
-{
-	VARIABLE_ARRAY(arena_t *, tarenas, ctl_stats.narenas);
+arena_i_decay(tsdn_t *tsdn, unsigned arena_ind, bool all) {
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	{
+		unsigned narenas = ctl_arenas->narenas;
 
-	malloc_mutex_lock(&arenas_lock);
-	memcpy(tarenas, arenas, sizeof(arena_t *) * ctl_stats.narenas);
-	malloc_mutex_unlock(&arenas_lock);
+		/*
+		 * Access via index narenas is deprecated, and scheduled for
+		 * removal in 6.0.0.
+		 */
+		if (arena_ind == MALLCTL_ARENAS_ALL || arena_ind == narenas) {
+			unsigned i;
+			VARIABLE_ARRAY(arena_t *, tarenas, narenas);
 
-	if (arena_ind == ctl_stats.narenas) {
-		unsigned i;
-		for (i = 0; i < ctl_stats.narenas; i++) {
-			if (tarenas[i] != NULL)
-				arena_purge_all(tarenas[i]);
+			for (i = 0; i < narenas; i++) {
+				tarenas[i] = arena_get(tsdn, i, false);
+			}
+
+			/*
+			 * No further need to hold ctl_mtx, since narenas and
+			 * tarenas contain everything needed below.
+			 */
+			malloc_mutex_unlock(tsdn, &ctl_mtx);
+
+			for (i = 0; i < narenas; i++) {
+				if (tarenas[i] != NULL) {
+					arena_decay(tsdn, tarenas[i], false,
+					    all);
+				}
+			}
+		} else {
+			arena_t *tarena;
+
+			assert(arena_ind < narenas);
+
+			tarena = arena_get(tsdn, arena_ind, false);
+
+			/* No further need to hold ctl_mtx. */
+			malloc_mutex_unlock(tsdn, &ctl_mtx);
+
+			if (tarena != NULL) {
+				arena_decay(tsdn, tarena, false, all);
+			}
 		}
-	} else {
-		assert(arena_ind < ctl_stats.narenas);
-		if (tarenas[arena_ind] != NULL)
-			arena_purge_all(tarenas[arena_ind]);
 	}
 }
 
 static int
-arena_i_purge_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+arena_i_decay_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
+	unsigned arena_ind;
 
 	READONLY();
 	WRITEONLY();
-	malloc_mutex_lock(&ctl_mtx);
-	arena_purge(mib[1]);
-	malloc_mutex_unlock(&ctl_mtx);
+	MIB_UNSIGNED(arena_ind, 1);
+	arena_i_decay(tsd_tsdn(tsd), arena_ind, false);
 
 	ret = 0;
 label_return:
-	return (ret);
+	return ret;
 }
 
 static int
-arena_i_dss_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
-	int ret, i;
-	bool match, err;
-	const char *dss;
-	unsigned arena_ind = mib[1];
+arena_i_purge_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned arena_ind;
+
+	READONLY();
+	WRITEONLY();
+	MIB_UNSIGNED(arena_ind, 1);
+	arena_i_decay(tsd_tsdn(tsd), arena_ind, true);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static int
+arena_i_reset_destroy_helper(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen, unsigned *arena_ind,
+    arena_t **arena) {
+	int ret;
+
+	READONLY();
+	WRITEONLY();
+	MIB_UNSIGNED(*arena_ind, 1);
+
+	*arena = arena_get(tsd_tsdn(tsd), *arena_ind, false);
+	if (*arena == NULL || arena_is_auto(*arena)) {
+		ret = EFAULT;
+		goto label_return;
+	}
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static void
+arena_reset_prepare_background_thread(tsd_t *tsd, unsigned arena_ind) {
+	/* Temporarily disable the background thread during arena reset. */
+	if (have_background_thread) {
+		malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock);
+		if (background_thread_enabled()) {
+			unsigned ind = arena_ind % ncpus;
+			background_thread_info_t *info =
+			    &background_thread_info[ind];
+			assert(info->state == background_thread_started);
+			malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+			info->state = background_thread_paused;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+		}
+	}
+}
+
+static void
+arena_reset_finish_background_thread(tsd_t *tsd, unsigned arena_ind) {
+	if (have_background_thread) {
+		if (background_thread_enabled()) {
+			unsigned ind = arena_ind % ncpus;
+			background_thread_info_t *info =
+			    &background_thread_info[ind];
+			assert(info->state == background_thread_paused);
+			malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+			info->state = background_thread_started;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock);
+	}
+}
+
+static int
+arena_i_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned arena_ind;
+	arena_t *arena;
+
+	ret = arena_i_reset_destroy_helper(tsd, mib, miblen, oldp, oldlenp,
+	    newp, newlen, &arena_ind, &arena);
+	if (ret != 0) {
+		return ret;
+	}
+
+	arena_reset_prepare_background_thread(tsd, arena_ind);
+	arena_reset(tsd, arena);
+	arena_reset_finish_background_thread(tsd, arena_ind);
+
+	return ret;
+}
+
+static int
+arena_i_destroy_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned arena_ind;
+	arena_t *arena;
+	ctl_arena_t *ctl_darena, *ctl_arena;
+
+	ret = arena_i_reset_destroy_helper(tsd, mib, miblen, oldp, oldlenp,
+	    newp, newlen, &arena_ind, &arena);
+	if (ret != 0) {
+		goto label_return;
+	}
+
+	if (arena_nthreads_get(arena, false) != 0 || arena_nthreads_get(arena,
+	    true) != 0) {
+		ret = EFAULT;
+		goto label_return;
+	}
+
+	arena_reset_prepare_background_thread(tsd, arena_ind);
+	/* Merge stats after resetting and purging arena. */
+	arena_reset(tsd, arena);
+	arena_decay(tsd_tsdn(tsd), arena, false, true);
+	ctl_darena = arenas_i(MALLCTL_ARENAS_DESTROYED);
+	ctl_darena->initialized = true;
+	ctl_arena_refresh(tsd_tsdn(tsd), arena, ctl_darena, arena_ind, true);
+	/* Destroy arena. */
+	arena_destroy(tsd, arena);
+	ctl_arena = arenas_i(arena_ind);
+	ctl_arena->initialized = false;
+	/* Record arena index for later recycling via arenas.create. */
+	ql_elm_new(ctl_arena, destroyed_link);
+	ql_tail_insert(&ctl_arenas->destroyed, ctl_arena, destroyed_link);
+	arena_reset_finish_background_thread(tsd, arena_ind);
+
+	assert(ret == 0);
+label_return:
+	return ret;
+}
+
+static int
+arena_i_dss_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	const char *dss = NULL;
+	unsigned arena_ind;
 	dss_prec_t dss_prec_old = dss_prec_limit;
 	dss_prec_t dss_prec = dss_prec_limit;
 
-	malloc_mutex_lock(&ctl_mtx);
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
 	WRITE(dss, const char *);
-	match = false;
-	for (i = 0; i < dss_prec_limit; i++) {
-		if (strcmp(dss_prec_names[i], dss) == 0) {
-			dss_prec = i;
-			match = true;
-			break;
+	MIB_UNSIGNED(arena_ind, 1);
+	if (dss != NULL) {
+		int i;
+		bool match = false;
+
+		for (i = 0; i < dss_prec_limit; i++) {
+			if (strcmp(dss_prec_names[i], dss) == 0) {
+				dss_prec = i;
+				match = true;
+				break;
+			}
+		}
+
+		if (!match) {
+			ret = EINVAL;
+			goto label_return;
 		}
-	}
-	if (match == false) {
-		ret = EINVAL;
-		goto label_return;
 	}
 
-	if (arena_ind < ctl_stats.narenas) {
-		arena_t *arena = arenas[arena_ind];
-		if (arena != NULL) {
-			dss_prec_old = arena_dss_prec_get(arena);
-			arena_dss_prec_set(arena, dss_prec);
-			err = false;
-		} else
-			err = true;
+	/*
+	 * Access via index narenas is deprecated, and scheduled for removal in
+	 * 6.0.0.
+	 */
+	if (arena_ind == MALLCTL_ARENAS_ALL || arena_ind ==
+	    ctl_arenas->narenas) {
+		if (dss_prec != dss_prec_limit &&
+		    extent_dss_prec_set(dss_prec)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+		dss_prec_old = extent_dss_prec_get();
 	} else {
-		dss_prec_old = chunk_dss_prec_get();
-		err = chunk_dss_prec_set(dss_prec);
+		arena_t *arena = arena_get(tsd_tsdn(tsd), arena_ind, false);
+		if (arena == NULL || (dss_prec != dss_prec_limit &&
+		    arena_dss_prec_set(arena, dss_prec))) {
+			ret = EFAULT;
+			goto label_return;
+		}
+		dss_prec_old = arena_dss_prec_get(arena);
 	}
+
 	dss = dss_prec_names[dss_prec_old];
 	READ(dss, const char *);
-	if (err) {
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return ret;
+}
+
+static int
+arena_i_decay_ms_ctl_impl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen, bool dirty) {
+	int ret;
+	unsigned arena_ind;
+	arena_t *arena;
+
+	MIB_UNSIGNED(arena_ind, 1);
+	arena = arena_get(tsd_tsdn(tsd), arena_ind, false);
+	if (arena == NULL) {
 		ret = EFAULT;
 		goto label_return;
 	}
 
+	if (oldp != NULL && oldlenp != NULL) {
+		size_t oldval = dirty ? arena_dirty_decay_ms_get(arena) :
+		    arena_muzzy_decay_ms_get(arena);
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (dirty ? arena_dirty_decay_ms_set(tsd_tsdn(tsd), arena,
+		    *(ssize_t *)newp) : arena_muzzy_decay_ms_set(tsd_tsdn(tsd),
+		    arena, *(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+	}
+
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	return ret;
 }
 
-static const ctl_named_node_t *
-arena_i_index(const size_t *mib, size_t miblen, size_t i)
-{
-	const ctl_named_node_t * ret;
+static int
+arena_i_dirty_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	return arena_i_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp,
+	    newlen, true);
+}
 
-	malloc_mutex_lock(&ctl_mtx);
-	if (i > ctl_stats.narenas) {
-		ret = NULL;
+static int
+arena_i_muzzy_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	return arena_i_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp,
+	    newlen, false);
+}
+
+static int
+arena_i_extent_hooks_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	unsigned arena_ind;
+	arena_t *arena;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	MIB_UNSIGNED(arena_ind, 1);
+	if (arena_ind < narenas_total_get() && (arena =
+	    arena_get(tsd_tsdn(tsd), arena_ind, false)) != NULL) {
+		if (newp != NULL) {
+			extent_hooks_t *old_extent_hooks;
+			extent_hooks_t *new_extent_hooks
+			    JEMALLOC_CC_SILENCE_INIT(NULL);
+			WRITE(new_extent_hooks, extent_hooks_t *);
+			old_extent_hooks = extent_hooks_set(tsd, arena,
+			    new_extent_hooks);
+			READ(old_extent_hooks, extent_hooks_t *);
+		} else {
+			extent_hooks_t *old_extent_hooks =
+			    extent_hooks_get(arena);
+			READ(old_extent_hooks, extent_hooks_t *);
+		}
+	} else {
+		ret = EFAULT;
 		goto label_return;
 	}
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return ret;
+}
+
+static const ctl_named_node_t *
+arena_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) {
+	const ctl_named_node_t *ret;
+
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	switch (i) {
+	case MALLCTL_ARENAS_ALL:
+	case MALLCTL_ARENAS_DESTROYED:
+		break;
+	default:
+		if (i > ctl_arenas->narenas) {
+			ret = NULL;
+			goto label_return;
+		}
+		break;
+	}
 
 	ret = super_arena_i_node;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return ret;
 }
 
 /******************************************************************************/
 
 static int
-arenas_narenas_ctl(const size_t *mib, size_t miblen, void *oldp,
-    size_t *oldlenp, void *newp, size_t newlen)
-{
+arenas_narenas_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	unsigned narenas;
 
-	malloc_mutex_lock(&ctl_mtx);
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
 	READONLY();
 	if (*oldlenp != sizeof(unsigned)) {
 		ret = EINVAL;
 		goto label_return;
 	}
-	narenas = ctl_stats.narenas;
+	narenas = ctl_arenas->narenas;
 	READ(narenas, unsigned);
 
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return ret;
 }
 
 static int
-arenas_initialized_ctl(const size_t *mib, size_t miblen, void *oldp,
-    size_t *oldlenp, void *newp, size_t newlen)
-{
+arenas_decay_ms_ctl_impl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen, bool dirty) {
 	int ret;
-	unsigned nread, i;
 
-	malloc_mutex_lock(&ctl_mtx);
-	READONLY();
-	if (*oldlenp != ctl_stats.narenas * sizeof(bool)) {
-		ret = EINVAL;
-		nread = (*oldlenp < ctl_stats.narenas * sizeof(bool))
-		    ? (*oldlenp / sizeof(bool)) : ctl_stats.narenas;
-	} else {
-		ret = 0;
-		nread = ctl_stats.narenas;
+	if (oldp != NULL && oldlenp != NULL) {
+		size_t oldval = (dirty ? arena_dirty_decay_ms_default_get() :
+		    arena_muzzy_decay_ms_default_get());
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (dirty ?  arena_dirty_decay_ms_default_set(*(ssize_t *)newp)
+		    : arena_muzzy_decay_ms_default_set(*(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
 	}
 
-	for (i = 0; i < nread; i++)
-		((bool *)oldp)[i] = ctl_stats.arenas[i].initialized;
-
+	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	return ret;
+}
+
+static int
+arenas_dirty_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	return arenas_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp,
+	    newlen, true);
+}
+
+static int
+arenas_muzzy_decay_ms_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	return arenas_decay_ms_ctl_impl(tsd, mib, miblen, oldp, oldlenp, newp,
+	    newlen, false);
 }
 
 CTL_RO_NL_GEN(arenas_quantum, QUANTUM, size_t)
 CTL_RO_NL_GEN(arenas_page, PAGE, size_t)
-CTL_RO_NL_CGEN(config_tcache, arenas_tcache_max, tcache_maxclass, size_t)
+CTL_RO_NL_GEN(arenas_tcache_max, tcache_maxclass, size_t)
 CTL_RO_NL_GEN(arenas_nbins, NBINS, unsigned)
-CTL_RO_NL_CGEN(config_tcache, arenas_nhbins, nhbins, unsigned)
+CTL_RO_NL_GEN(arenas_nhbins, nhbins, unsigned)
 CTL_RO_NL_GEN(arenas_bin_i_size, arena_bin_info[mib[2]].reg_size, size_t)
 CTL_RO_NL_GEN(arenas_bin_i_nregs, arena_bin_info[mib[2]].nregs, uint32_t)
-CTL_RO_NL_GEN(arenas_bin_i_run_size, arena_bin_info[mib[2]].run_size, size_t)
+CTL_RO_NL_GEN(arenas_bin_i_slab_size, arena_bin_info[mib[2]].slab_size, size_t)
 static const ctl_named_node_t *
-arenas_bin_i_index(const size_t *mib, size_t miblen, size_t i)
-{
-
-	if (i > NBINS)
-		return (NULL);
-	return (super_arenas_bin_i_node);
+arenas_bin_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) {
+	if (i > NBINS) {
+		return NULL;
+	}
+	return super_arenas_bin_i_node;
 }
 
-CTL_RO_NL_GEN(arenas_nlruns, nlclasses, size_t)
-CTL_RO_NL_GEN(arenas_lrun_i_size, ((mib[2]+1) << LG_PAGE), size_t)
+CTL_RO_NL_GEN(arenas_nlextents, NSIZES - NBINS, unsigned)
+CTL_RO_NL_GEN(arenas_lextent_i_size, sz_index2size(NBINS+(szind_t)mib[2]),
+    size_t)
 static const ctl_named_node_t *
-arenas_lrun_i_index(const size_t *mib, size_t miblen, size_t i)
-{
-
-	if (i > nlclasses)
-		return (NULL);
-	return (super_arenas_lrun_i_node);
+arenas_lextent_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen,
+    size_t i) {
+	if (i > NSIZES - NBINS) {
+		return NULL;
+	}
+	return super_arenas_lextent_i_node;
 }
 
 static int
-arenas_purge_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+arenas_create_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
+	extent_hooks_t *extent_hooks;
 	unsigned arena_ind;
 
-	malloc_mutex_lock(&ctl_mtx);
-	WRITEONLY();
-	arena_ind = UINT_MAX;
-	WRITE(arena_ind, unsigned);
-	if (newp != NULL && arena_ind >= ctl_stats.narenas)
-		ret = EFAULT;
-	else {
-		if (arena_ind == UINT_MAX)
-			arena_ind = ctl_stats.narenas;
-		arena_purge(arena_ind);
-		ret = 0;
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+
+	extent_hooks = (extent_hooks_t *)&extent_hooks_default;
+	WRITE(extent_hooks, extent_hooks_t *);
+	if ((arena_ind = ctl_arena_init(tsd, extent_hooks)) == UINT_MAX) {
+		ret = EAGAIN;
+		goto label_return;
 	}
+	READ(arena_ind, unsigned);
 
+	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return ret;
 }
 
+/******************************************************************************/
+
 static int
-arenas_extend_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+prof_thread_active_init_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
-	unsigned narenas;
+	bool oldval;
 
-	malloc_mutex_lock(&ctl_mtx);
-	READONLY();
-	if (ctl_grow()) {
-		ret = EAGAIN;
-		goto label_return;
+	if (!config_prof) {
+		return ENOENT;
 	}
-	narenas = ctl_stats.narenas - 1;
-	READ(narenas, unsigned);
+
+	if (newp != NULL) {
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		oldval = prof_thread_active_init_set(tsd_tsdn(tsd),
+		    *(bool *)newp);
+	} else {
+		oldval = prof_thread_active_init_get(tsd_tsdn(tsd));
+	}
+	READ(oldval, bool);
 
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	return ret;
 }
 
-/******************************************************************************/
-
 static int
-prof_active_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+prof_active_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	bool oldval;
 
-	if (config_prof == false)
-		return (ENOENT);
+	if (!config_prof) {
+		return ENOENT;
+	}
 
-	malloc_mutex_lock(&ctl_mtx); /* Protect opt_prof_active. */
-	oldval = opt_prof_active;
 	if (newp != NULL) {
-		/*
-		 * The memory barriers will tend to make opt_prof_active
-		 * propagate faster on systems with weak memory ordering.
-		 */
-		mb_write();
-		WRITE(opt_prof_active, bool);
-		mb_write();
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		oldval = prof_active_set(tsd_tsdn(tsd), *(bool *)newp);
+	} else {
+		oldval = prof_active_get(tsd_tsdn(tsd));
 	}
 	READ(oldval, bool);
 
 	ret = 0;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	return ret;
 }
 
 static int
-prof_dump_ctl(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-    void *newp, size_t newlen)
-{
+prof_dump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
 	int ret;
 	const char *filename = NULL;
 
-	if (config_prof == false)
-		return (ENOENT);
+	if (!config_prof) {
+		return ENOENT;
+	}
 
 	WRITEONLY();
 	WRITE(filename, const char *);
 
-	if (prof_mdump(filename)) {
+	if (prof_mdump(tsd, filename)) {
 		ret = EFAULT;
 		goto label_return;
 	}
 
 	ret = 0;
 label_return:
-	return (ret);
+	return ret;
+}
+
+static int
+prof_gdump_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	bool oldval;
+
+	if (!config_prof) {
+		return ENOENT;
+	}
+
+	if (newp != NULL) {
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		oldval = prof_gdump_set(tsd_tsdn(tsd), *(bool *)newp);
+	} else {
+		oldval = prof_gdump_get(tsd_tsdn(tsd));
+	}
+	READ(oldval, bool);
+
+	ret = 0;
+label_return:
+	return ret;
+}
+
+static int
+prof_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen) {
+	int ret;
+	size_t lg_sample = lg_prof_sample;
+
+	if (!config_prof) {
+		return ENOENT;
+	}
+
+	WRITEONLY();
+	WRITE(lg_sample, size_t);
+	if (lg_sample >= (sizeof(uint64_t) << 3)) {
+		lg_sample = (sizeof(uint64_t) << 3) - 1;
+	}
+
+	prof_reset(tsd, lg_sample);
+
+	ret = 0;
+label_return:
+	return ret;
 }
 
 CTL_RO_NL_CGEN(config_prof, prof_interval, prof_interval, uint64_t)
+CTL_RO_NL_CGEN(config_prof, lg_prof_sample, lg_prof_sample, size_t)
 
 /******************************************************************************/
 
-CTL_RO_CGEN(config_stats, stats_cactive, &stats_cactive, size_t *)
-CTL_RO_CGEN(config_stats, stats_allocated, ctl_stats.allocated, size_t)
-CTL_RO_CGEN(config_stats, stats_active, ctl_stats.active, size_t)
-CTL_RO_CGEN(config_stats, stats_mapped, ctl_stats.mapped, size_t)
+CTL_RO_CGEN(config_stats, stats_allocated, ctl_stats->allocated, size_t)
+CTL_RO_CGEN(config_stats, stats_active, ctl_stats->active, size_t)
+CTL_RO_CGEN(config_stats, stats_metadata, ctl_stats->metadata, size_t)
+CTL_RO_CGEN(config_stats, stats_resident, ctl_stats->resident, size_t)
+CTL_RO_CGEN(config_stats, stats_mapped, ctl_stats->mapped, size_t)
+CTL_RO_CGEN(config_stats, stats_retained, ctl_stats->retained, size_t)
+
+CTL_RO_CGEN(config_stats, stats_background_thread_num_threads,
+    ctl_stats->background_thread.num_threads, size_t)
+CTL_RO_CGEN(config_stats, stats_background_thread_num_runs,
+    ctl_stats->background_thread.num_runs, uint64_t)
+CTL_RO_CGEN(config_stats, stats_background_thread_run_interval,
+    nstime_ns(&ctl_stats->background_thread.run_interval), uint64_t)
+
+CTL_RO_GEN(stats_arenas_i_dss, arenas_i(mib[2])->dss, const char *)
+CTL_RO_GEN(stats_arenas_i_dirty_decay_ms, arenas_i(mib[2])->dirty_decay_ms,
+    ssize_t)
+CTL_RO_GEN(stats_arenas_i_muzzy_decay_ms, arenas_i(mib[2])->muzzy_decay_ms,
+    ssize_t)
+CTL_RO_GEN(stats_arenas_i_nthreads, arenas_i(mib[2])->nthreads, unsigned)
+CTL_RO_GEN(stats_arenas_i_uptime,
+    nstime_ns(&arenas_i(mib[2])->astats->astats.uptime), uint64_t)
+CTL_RO_GEN(stats_arenas_i_pactive, arenas_i(mib[2])->pactive, size_t)
+CTL_RO_GEN(stats_arenas_i_pdirty, arenas_i(mib[2])->pdirty, size_t)
+CTL_RO_GEN(stats_arenas_i_pmuzzy, arenas_i(mib[2])->pmuzzy, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_mapped,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.mapped, ATOMIC_RELAXED),
+    size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_retained,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.retained, ATOMIC_RELAXED),
+    size_t)
 
-CTL_RO_CGEN(config_stats, stats_chunks_current, ctl_stats.chunks.current,
+CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_npurge,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_dirty.npurge),
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_nmadvise,
+    arena_stats_read_u64(
+    &arenas_i(mib[2])->astats->astats.decay_dirty.nmadvise), uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_dirty_purged,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_dirty.purged),
+    uint64_t)
+
+CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_npurge,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_muzzy.npurge),
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_nmadvise,
+    arena_stats_read_u64(
+    &arenas_i(mib[2])->astats->astats.decay_muzzy.nmadvise), uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_muzzy_purged,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.decay_muzzy.purged),
+    uint64_t)
+
+CTL_RO_CGEN(config_stats, stats_arenas_i_base,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.base, ATOMIC_RELAXED),
+    size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_internal,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.internal, ATOMIC_RELAXED),
+    size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_tcache_bytes,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.tcache_bytes,
+    ATOMIC_RELAXED), size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_resident,
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.resident, ATOMIC_RELAXED),
     size_t)
-CTL_RO_CGEN(config_stats, stats_chunks_total, ctl_stats.chunks.total, uint64_t)
-CTL_RO_CGEN(config_stats, stats_chunks_high, ctl_stats.chunks.high, size_t)
-CTL_RO_CGEN(config_stats, stats_huge_allocated, huge_allocated, size_t)
-CTL_RO_CGEN(config_stats, stats_huge_nmalloc, huge_nmalloc, uint64_t)
-CTL_RO_CGEN(config_stats, stats_huge_ndalloc, huge_ndalloc, uint64_t)
-
-CTL_RO_GEN(stats_arenas_i_dss, ctl_stats.arenas[mib[2]].dss, const char *)
-CTL_RO_GEN(stats_arenas_i_nthreads, ctl_stats.arenas[mib[2]].nthreads, unsigned)
-CTL_RO_GEN(stats_arenas_i_pactive, ctl_stats.arenas[mib[2]].pactive, size_t)
-CTL_RO_GEN(stats_arenas_i_pdirty, ctl_stats.arenas[mib[2]].pdirty, size_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_mapped,
-    ctl_stats.arenas[mib[2]].astats.mapped, size_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_npurge,
-    ctl_stats.arenas[mib[2]].astats.npurge, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_nmadvise,
-    ctl_stats.arenas[mib[2]].astats.nmadvise, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_purged,
-    ctl_stats.arenas[mib[2]].astats.purged, uint64_t)
 
 CTL_RO_CGEN(config_stats, stats_arenas_i_small_allocated,
-    ctl_stats.arenas[mib[2]].allocated_small, size_t)
+    arenas_i(mib[2])->astats->allocated_small, size_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_small_nmalloc,
-    ctl_stats.arenas[mib[2]].nmalloc_small, uint64_t)
+    arenas_i(mib[2])->astats->nmalloc_small, uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_small_ndalloc,
-    ctl_stats.arenas[mib[2]].ndalloc_small, uint64_t)
+    arenas_i(mib[2])->astats->ndalloc_small, uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_small_nrequests,
-    ctl_stats.arenas[mib[2]].nrequests_small, uint64_t)
+    arenas_i(mib[2])->astats->nrequests_small, uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_large_allocated,
-    ctl_stats.arenas[mib[2]].astats.allocated_large, size_t)
+    atomic_load_zu(&arenas_i(mib[2])->astats->astats.allocated_large,
+    ATOMIC_RELAXED), size_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_large_nmalloc,
-    ctl_stats.arenas[mib[2]].astats.nmalloc_large, uint64_t)
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.nmalloc_large),
+    uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_large_ndalloc,
-    ctl_stats.arenas[mib[2]].astats.ndalloc_large, uint64_t)
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.ndalloc_large),
+    uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_large_nrequests,
-    ctl_stats.arenas[mib[2]].astats.nrequests_large, uint64_t)
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->astats.nmalloc_large),
+    uint64_t) /* Intentional. */
+
+/* Lock profiling related APIs below. */
+#define RO_MUTEX_CTL_GEN(n, l)						\
+CTL_RO_CGEN(config_stats, stats_##n##_num_ops,				\
+    l.n_lock_ops, uint64_t)						\
+CTL_RO_CGEN(config_stats, stats_##n##_num_wait,				\
+    l.n_wait_times, uint64_t)						\
+CTL_RO_CGEN(config_stats, stats_##n##_num_spin_acq,			\
+    l.n_spin_acquired, uint64_t)					\
+CTL_RO_CGEN(config_stats, stats_##n##_num_owner_switch,			\
+    l.n_owner_switches, uint64_t) 					\
+CTL_RO_CGEN(config_stats, stats_##n##_total_wait_time,			\
+    nstime_ns(&l.tot_wait_time), uint64_t)				\
+CTL_RO_CGEN(config_stats, stats_##n##_max_wait_time,			\
+    nstime_ns(&l.max_wait_time), uint64_t)				\
+CTL_RO_CGEN(config_stats, stats_##n##_max_num_thds,			\
+    l.max_n_thds, uint32_t)
+
+/* Global mutexes. */
+#define OP(mtx)								\
+    RO_MUTEX_CTL_GEN(mutexes_##mtx,					\
+        ctl_stats->mutex_prof_data[global_prof_mutex_##mtx])
+MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+
+/* Per arena mutexes */
+#define OP(mtx) RO_MUTEX_CTL_GEN(arenas_i_mutexes_##mtx,		\
+    arenas_i(mib[2])->astats->astats.mutex_prof_data[arena_prof_mutex_##mtx])
+MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+
+/* tcache bin mutex */
+RO_MUTEX_CTL_GEN(arenas_i_bins_j_mutex,
+    arenas_i(mib[2])->astats->bstats[mib[4]].mutex_data)
+#undef RO_MUTEX_CTL_GEN
+
+/* Resets all mutex stats, including global, arena and bin mutexes. */
+static int
+stats_mutexes_reset_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen) {
+	if (!config_stats) {
+		return ENOENT;
+	}
+
+	tsdn_t *tsdn = tsd_tsdn(tsd);
+
+#define MUTEX_PROF_RESET(mtx)						\
+    malloc_mutex_lock(tsdn, &mtx);					\
+    malloc_mutex_prof_data_reset(tsdn, &mtx);				\
+    malloc_mutex_unlock(tsdn, &mtx);
+
+	/* Global mutexes: ctl and prof. */
+	MUTEX_PROF_RESET(ctl_mtx);
+	if (have_background_thread) {
+		MUTEX_PROF_RESET(background_thread_lock);
+	}
+	if (config_prof && opt_prof) {
+		MUTEX_PROF_RESET(bt2gctx_mtx);
+	}
+
+
+	/* Per arena mutexes. */
+	unsigned n = narenas_total_get();
+
+	for (unsigned i = 0; i < n; i++) {
+		arena_t *arena = arena_get(tsdn, i, false);
+		if (!arena) {
+			continue;
+		}
+		MUTEX_PROF_RESET(arena->large_mtx);
+		MUTEX_PROF_RESET(arena->extent_avail_mtx);
+		MUTEX_PROF_RESET(arena->extents_dirty.mtx);
+		MUTEX_PROF_RESET(arena->extents_muzzy.mtx);
+		MUTEX_PROF_RESET(arena->extents_retained.mtx);
+		MUTEX_PROF_RESET(arena->decay_dirty.mtx);
+		MUTEX_PROF_RESET(arena->decay_muzzy.mtx);
+		MUTEX_PROF_RESET(arena->tcache_ql_mtx);
+		MUTEX_PROF_RESET(arena->base->mtx);
+
+		for (szind_t i = 0; i < NBINS; i++) {
+			arena_bin_t *bin = &arena->bins[i];
+			MUTEX_PROF_RESET(bin->lock);
+		}
+	}
+#undef MUTEX_PROF_RESET
+	return 0;
+}
 
-CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_allocated,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].allocated, size_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nmalloc,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].nmalloc, uint64_t)
+    arenas_i(mib[2])->astats->bstats[mib[4]].nmalloc, uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_ndalloc,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].ndalloc, uint64_t)
+    arenas_i(mib[2])->astats->bstats[mib[4]].ndalloc, uint64_t)
 CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nrequests,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].nrequests, uint64_t)
-CTL_RO_CGEN(config_stats && config_tcache, stats_arenas_i_bins_j_nfills,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].nfills, uint64_t)
-CTL_RO_CGEN(config_stats && config_tcache, stats_arenas_i_bins_j_nflushes,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].nflushes, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nruns,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].nruns, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nreruns,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].reruns, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_curruns,
-    ctl_stats.arenas[mib[2]].bstats[mib[4]].curruns, size_t)
+    arenas_i(mib[2])->astats->bstats[mib[4]].nrequests, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_curregs,
+    arenas_i(mib[2])->astats->bstats[mib[4]].curregs, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nfills,
+    arenas_i(mib[2])->astats->bstats[mib[4]].nfills, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nflushes,
+    arenas_i(mib[2])->astats->bstats[mib[4]].nflushes, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nslabs,
+    arenas_i(mib[2])->astats->bstats[mib[4]].nslabs, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nreslabs,
+    arenas_i(mib[2])->astats->bstats[mib[4]].reslabs, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_curslabs,
+    arenas_i(mib[2])->astats->bstats[mib[4]].curslabs, size_t)
 
 static const ctl_named_node_t *
-stats_arenas_i_bins_j_index(const size_t *mib, size_t miblen, size_t j)
-{
-
-	if (j > NBINS)
-		return (NULL);
-	return (super_stats_arenas_i_bins_j_node);
+stats_arenas_i_bins_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen,
+    size_t j) {
+	if (j > NBINS) {
+		return NULL;
+	}
+	return super_stats_arenas_i_bins_j_node;
 }
 
-CTL_RO_CGEN(config_stats, stats_arenas_i_lruns_j_nmalloc,
-    ctl_stats.arenas[mib[2]].lstats[mib[4]].nmalloc, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_lruns_j_ndalloc,
-    ctl_stats.arenas[mib[2]].lstats[mib[4]].ndalloc, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_lruns_j_nrequests,
-    ctl_stats.arenas[mib[2]].lstats[mib[4]].nrequests, uint64_t)
-CTL_RO_CGEN(config_stats, stats_arenas_i_lruns_j_curruns,
-    ctl_stats.arenas[mib[2]].lstats[mib[4]].curruns, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nmalloc,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].nmalloc),
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_ndalloc,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].ndalloc),
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_nrequests,
+    arena_stats_read_u64(&arenas_i(mib[2])->astats->lstats[mib[4]].nrequests),
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_lextents_j_curlextents,
+    arenas_i(mib[2])->astats->lstats[mib[4]].curlextents, size_t)
 
 static const ctl_named_node_t *
-stats_arenas_i_lruns_j_index(const size_t *mib, size_t miblen, size_t j)
-{
-
-	if (j > nlclasses)
-		return (NULL);
-	return (super_stats_arenas_i_lruns_j_node);
+stats_arenas_i_lextents_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen,
+    size_t j) {
+	if (j > NSIZES - NBINS) {
+		return NULL;
+	}
+	return super_stats_arenas_i_lextents_j_node;
 }
 
 static const ctl_named_node_t *
-stats_arenas_i_index(const size_t *mib, size_t miblen, size_t i)
-{
-	const ctl_named_node_t * ret;
+stats_arenas_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i) {
+	const ctl_named_node_t *ret;
+	size_t a;
 
-	malloc_mutex_lock(&ctl_mtx);
-	if (i > ctl_stats.narenas || ctl_stats.arenas[i].initialized == false) {
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	a = arenas_i2a_impl(i, true, true);
+	if (a == UINT_MAX || !ctl_arenas->arenas[a]->initialized) {
 		ret = NULL;
 		goto label_return;
 	}
 
 	ret = super_stats_arenas_i_node;
 label_return:
-	malloc_mutex_unlock(&ctl_mtx);
-	return (ret);
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return ret;
 }
diff --git a/modules/worldengine/deps/jemalloc/src/extent.c b/modules/worldengine/deps/jemalloc/src/extent.c
index 8c09b486ed..fa45c84d34 100644
--- a/modules/worldengine/deps/jemalloc/src/extent.c
+++ b/modules/worldengine/deps/jemalloc/src/extent.c
@@ -1,39 +1,1987 @@
-#define	JEMALLOC_EXTENT_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_EXTENT_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/ph.h"
+#include "jemalloc/internal/rtree.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/mutex_pool.h"
+
+/******************************************************************************/
+/* Data. */
+
+rtree_t		extents_rtree;
+/* Keyed by the address of the extent_t being protected. */
+mutex_pool_t	extent_mutex_pool;
+
+static const bitmap_info_t extents_bitmap_info =
+    BITMAP_INFO_INITIALIZER(NPSIZES+1);
+
+static void *extent_alloc_default(extent_hooks_t *extent_hooks, void *new_addr,
+    size_t size, size_t alignment, bool *zero, bool *commit,
+    unsigned arena_ind);
+static bool extent_dalloc_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, bool committed, unsigned arena_ind);
+static void extent_destroy_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, bool committed, unsigned arena_ind);
+static bool extent_commit_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, size_t offset, size_t length, unsigned arena_ind);
+static bool extent_commit_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained);
+static bool extent_decommit_default(extent_hooks_t *extent_hooks,
+    void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind);
+#ifdef PAGES_CAN_PURGE_LAZY
+static bool extent_purge_lazy_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, size_t offset, size_t length, unsigned arena_ind);
+#endif
+static bool extent_purge_lazy_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained);
+#ifdef PAGES_CAN_PURGE_FORCED
+static bool extent_purge_forced_default(extent_hooks_t *extent_hooks,
+    void *addr, size_t size, size_t offset, size_t length, unsigned arena_ind);
+#endif
+static bool extent_purge_forced_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained);
+#ifdef JEMALLOC_MAPS_COALESCE
+static bool extent_split_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, size_t size_a, size_t size_b, bool committed,
+    unsigned arena_ind);
+#endif
+static extent_t *extent_split_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a,
+    szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b,
+    bool growing_retained);
+#ifdef JEMALLOC_MAPS_COALESCE
+static bool extent_merge_default(extent_hooks_t *extent_hooks, void *addr_a,
+    size_t size_a, void *addr_b, size_t size_b, bool committed,
+    unsigned arena_ind);
+#endif
+static bool extent_merge_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b,
+    bool growing_retained);
+
+const extent_hooks_t	extent_hooks_default = {
+	extent_alloc_default,
+	extent_dalloc_default,
+	extent_destroy_default,
+	extent_commit_default,
+	extent_decommit_default
+#ifdef PAGES_CAN_PURGE_LAZY
+	,
+	extent_purge_lazy_default
+#else
+	,
+	NULL
+#endif
+#ifdef PAGES_CAN_PURGE_FORCED
+	,
+	extent_purge_forced_default
+#else
+	,
+	NULL
+#endif
+#ifdef JEMALLOC_MAPS_COALESCE
+	,
+	extent_split_default,
+	extent_merge_default
+#endif
+};
+
+/* Used exclusively for gdump triggering. */
+static atomic_zu_t curpages;
+static atomic_zu_t highpages;
+
+/******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
+
+static void extent_deregister(tsdn_t *tsdn, extent_t *extent);
+static extent_t *extent_recycle(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, void *new_addr,
+    size_t usize, size_t pad, size_t alignment, bool slab, szind_t szind,
+    bool *zero, bool *commit, bool growing_retained);
+static extent_t *extent_try_coalesce(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents,
+    extent_t *extent, bool *coalesced, bool growing_retained);
+static void extent_record(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extents_t *extents, extent_t *extent,
+    bool growing_retained);
 
 /******************************************************************************/
 
-static inline int
-extent_szad_comp(extent_node_t *a, extent_node_t *b)
-{
-	int ret;
-	size_t a_size = a->size;
-	size_t b_size = b->size;
+rb_gen(UNUSED, extent_avail_, extent_tree_t, extent_t, rb_link,
+    extent_esnead_comp)
+
+typedef enum {
+	lock_result_success,
+	lock_result_failure,
+	lock_result_no_extent
+} lock_result_t;
+
+static lock_result_t
+extent_rtree_leaf_elm_try_lock(tsdn_t *tsdn, rtree_leaf_elm_t *elm,
+    extent_t **result) {
+	extent_t *extent1 = rtree_leaf_elm_extent_read(tsdn, &extents_rtree,
+	    elm, true);
+
+	if (extent1 == NULL) {
+		return lock_result_no_extent;
+	}
+	/*
+	 * It's possible that the extent changed out from under us, and with it
+	 * the leaf->extent mapping.  We have to recheck while holding the lock.
+	 */
+	extent_lock(tsdn, extent1);
+	extent_t *extent2 = rtree_leaf_elm_extent_read(tsdn,
+	    &extents_rtree, elm, true);
+
+	if (extent1 == extent2) {
+		*result = extent1;
+		return lock_result_success;
+	} else {
+		extent_unlock(tsdn, extent1);
+		return lock_result_failure;
+	}
+}
+
+/*
+ * Returns a pool-locked extent_t * if there's one associated with the given
+ * address, and NULL otherwise.
+ */
+static extent_t *
+extent_lock_from_addr(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, void *addr) {
+	extent_t *ret = NULL;
+	rtree_leaf_elm_t *elm = rtree_leaf_elm_lookup(tsdn, &extents_rtree,
+	    rtree_ctx, (uintptr_t)addr, false, false);
+	if (elm == NULL) {
+		return NULL;
+	}
+	lock_result_t lock_result;
+	do {
+		lock_result = extent_rtree_leaf_elm_try_lock(tsdn, elm, &ret);
+	} while (lock_result == lock_result_failure);
+	return ret;
+}
+
+extent_t *
+extent_alloc(tsdn_t *tsdn, arena_t *arena) {
+	malloc_mutex_lock(tsdn, &arena->extent_avail_mtx);
+	extent_t *extent = extent_avail_first(&arena->extent_avail);
+	if (extent == NULL) {
+		malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx);
+		return base_alloc_extent(tsdn, arena->base);
+	}
+	extent_avail_remove(&arena->extent_avail, extent);
+	malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx);
+	return extent;
+}
+
+void
+extent_dalloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent) {
+	malloc_mutex_lock(tsdn, &arena->extent_avail_mtx);
+	extent_avail_insert(&arena->extent_avail, extent);
+	malloc_mutex_unlock(tsdn, &arena->extent_avail_mtx);
+}
+
+extent_hooks_t *
+extent_hooks_get(arena_t *arena) {
+	return base_extent_hooks_get(arena->base);
+}
+
+extent_hooks_t *
+extent_hooks_set(tsd_t *tsd, arena_t *arena, extent_hooks_t *extent_hooks) {
+	background_thread_info_t *info;
+	if (have_background_thread) {
+		info = arena_background_thread_info_get(arena);
+		malloc_mutex_lock(tsd_tsdn(tsd), &info->mtx);
+	}
+	extent_hooks_t *ret = base_extent_hooks_set(arena->base, extent_hooks);
+	if (have_background_thread) {
+		malloc_mutex_unlock(tsd_tsdn(tsd), &info->mtx);
+	}
+
+	return ret;
+}
+
+static void
+extent_hooks_assure_initialized(arena_t *arena,
+    extent_hooks_t **r_extent_hooks) {
+	if (*r_extent_hooks == EXTENT_HOOKS_INITIALIZER) {
+		*r_extent_hooks = extent_hooks_get(arena);
+	}
+}
+
+#ifndef JEMALLOC_JET
+static
+#endif
+size_t
+extent_size_quantize_floor(size_t size) {
+	size_t ret;
+	pszind_t pind;
+
+	assert(size > 0);
+	assert((size & PAGE_MASK) == 0);
+
+	pind = sz_psz2ind(size - sz_large_pad + 1);
+	if (pind == 0) {
+		/*
+		 * Avoid underflow.  This short-circuit would also do the right
+		 * thing for all sizes in the range for which there are
+		 * PAGE-spaced size classes, but it's simplest to just handle
+		 * the one case that would cause erroneous results.
+		 */
+		return size;
+	}
+	ret = sz_pind2sz(pind - 1) + sz_large_pad;
+	assert(ret <= size);
+	return ret;
+}
+
+#ifndef JEMALLOC_JET
+static
+#endif
+size_t
+extent_size_quantize_ceil(size_t size) {
+	size_t ret;
 
-	ret = (a_size > b_size) - (a_size < b_size);
-	if (ret == 0) {
-		uintptr_t a_addr = (uintptr_t)a->addr;
-		uintptr_t b_addr = (uintptr_t)b->addr;
+	assert(size > 0);
+	assert(size - sz_large_pad <= LARGE_MAXCLASS);
+	assert((size & PAGE_MASK) == 0);
 
-		ret = (a_addr > b_addr) - (a_addr < b_addr);
+	ret = extent_size_quantize_floor(size);
+	if (ret < size) {
+		/*
+		 * Skip a quantization that may have an adequately large extent,
+		 * because under-sized extents may be mixed in.  This only
+		 * happens when an unusual size is requested, i.e. for aligned
+		 * allocation, and is just one of several places where linear
+		 * search would potentially find sufficiently aligned available
+		 * memory somewhere lower.
+		 */
+		ret = sz_pind2sz(sz_psz2ind(ret - sz_large_pad + 1)) +
+		    sz_large_pad;
 	}
+	return ret;
+}
+
+/* Generate pairing heap functions. */
+ph_gen(, extent_heap_, extent_heap_t, extent_t, ph_link, extent_snad_comp)
+
+bool
+extents_init(tsdn_t *tsdn, extents_t *extents, extent_state_t state,
+    bool delay_coalesce) {
+	if (malloc_mutex_init(&extents->mtx, "extents", WITNESS_RANK_EXTENTS,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+	for (unsigned i = 0; i < NPSIZES+1; i++) {
+		extent_heap_new(&extents->heaps[i]);
+	}
+	bitmap_init(extents->bitmap, &extents_bitmap_info, true);
+	extent_list_init(&extents->lru);
+	atomic_store_zu(&extents->npages, 0, ATOMIC_RELAXED);
+	extents->state = state;
+	extents->delay_coalesce = delay_coalesce;
+	return false;
+}
+
+extent_state_t
+extents_state_get(const extents_t *extents) {
+	return extents->state;
+}
 
-	return (ret);
+size_t
+extents_npages_get(extents_t *extents) {
+	return atomic_load_zu(&extents->npages, ATOMIC_RELAXED);
 }
 
-/* Generate red-black tree functions. */
-rb_gen(, extent_tree_szad_, extent_tree_t, extent_node_t, link_szad,
-    extent_szad_comp)
+static void
+extents_insert_locked(tsdn_t *tsdn, extents_t *extents, extent_t *extent,
+    bool preserve_lru) {
+	malloc_mutex_assert_owner(tsdn, &extents->mtx);
+	assert(extent_state_get(extent) == extents->state);
 
-static inline int
-extent_ad_comp(extent_node_t *a, extent_node_t *b)
-{
-	uintptr_t a_addr = (uintptr_t)a->addr;
-	uintptr_t b_addr = (uintptr_t)b->addr;
+	size_t size = extent_size_get(extent);
+	size_t psz = extent_size_quantize_floor(size);
+	pszind_t pind = sz_psz2ind(psz);
+	if (extent_heap_empty(&extents->heaps[pind])) {
+		bitmap_unset(extents->bitmap, &extents_bitmap_info,
+		    (size_t)pind);
+	}
+	extent_heap_insert(&extents->heaps[pind], extent);
+	if (!preserve_lru) {
+		extent_list_append(&extents->lru, extent);
+	}
+	size_t npages = size >> LG_PAGE;
+	/*
+	 * All modifications to npages hold the mutex (as asserted above), so we
+	 * don't need an atomic fetch-add; we can get by with a load followed by
+	 * a store.
+	 */
+	size_t cur_extents_npages =
+	    atomic_load_zu(&extents->npages, ATOMIC_RELAXED);
+	atomic_store_zu(&extents->npages, cur_extents_npages + npages,
+	    ATOMIC_RELAXED);
+}
 
-	return ((a_addr > b_addr) - (a_addr < b_addr));
+static void
+extents_remove_locked(tsdn_t *tsdn, extents_t *extents, extent_t *extent,
+    bool preserve_lru) {
+	malloc_mutex_assert_owner(tsdn, &extents->mtx);
+	assert(extent_state_get(extent) == extents->state);
+
+	size_t size = extent_size_get(extent);
+	size_t psz = extent_size_quantize_floor(size);
+	pszind_t pind = sz_psz2ind(psz);
+	extent_heap_remove(&extents->heaps[pind], extent);
+	if (extent_heap_empty(&extents->heaps[pind])) {
+		bitmap_set(extents->bitmap, &extents_bitmap_info,
+		    (size_t)pind);
+	}
+	if (!preserve_lru) {
+		extent_list_remove(&extents->lru, extent);
+	}
+	size_t npages = size >> LG_PAGE;
+	/*
+	 * As in extents_insert_locked, we hold extents->mtx and so don't need
+	 * atomic operations for updating extents->npages.
+	 */
+	size_t cur_extents_npages =
+	    atomic_load_zu(&extents->npages, ATOMIC_RELAXED);
+	assert(cur_extents_npages >= npages);
+	atomic_store_zu(&extents->npages,
+	    cur_extents_npages - (size >> LG_PAGE), ATOMIC_RELAXED);
 }
 
-/* Generate red-black tree functions. */
-rb_gen(, extent_tree_ad_, extent_tree_t, extent_node_t, link_ad,
-    extent_ad_comp)
+/* Do any-best-fit extent selection, i.e. select any extent that best fits. */
+static extent_t *
+extents_best_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    size_t size) {
+	pszind_t pind = sz_psz2ind(extent_size_quantize_ceil(size));
+	pszind_t i = (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info,
+	    (size_t)pind);
+	if (i < NPSIZES+1) {
+		assert(!extent_heap_empty(&extents->heaps[i]));
+		extent_t *extent = extent_heap_any(&extents->heaps[i]);
+		assert(extent_size_get(extent) >= size);
+		return extent;
+	}
+
+	return NULL;
+}
+
+/*
+ * Do first-fit extent selection, i.e. select the oldest/lowest extent that is
+ * large enough.
+ */
+static extent_t *
+extents_first_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    size_t size) {
+	extent_t *ret = NULL;
+
+	pszind_t pind = sz_psz2ind(extent_size_quantize_ceil(size));
+	for (pszind_t i = (pszind_t)bitmap_ffu(extents->bitmap,
+	    &extents_bitmap_info, (size_t)pind); i < NPSIZES+1; i =
+	    (pszind_t)bitmap_ffu(extents->bitmap, &extents_bitmap_info,
+	    (size_t)i+1)) {
+		assert(!extent_heap_empty(&extents->heaps[i]));
+		extent_t *extent = extent_heap_first(&extents->heaps[i]);
+		assert(extent_size_get(extent) >= size);
+		if (ret == NULL || extent_snad_comp(extent, ret) < 0) {
+			ret = extent;
+		}
+		if (i == NPSIZES) {
+			break;
+		}
+		assert(i < NPSIZES);
+	}
+
+	return ret;
+}
+
+/*
+ * Do {best,first}-fit extent selection, where the selection policy choice is
+ * based on extents->delay_coalesce.  Best-fit selection requires less
+ * searching, but its layout policy is less stable and may cause higher virtual
+ * memory fragmentation as a side effect.
+ */
+static extent_t *
+extents_fit_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    size_t size) {
+	malloc_mutex_assert_owner(tsdn, &extents->mtx);
+
+	return extents->delay_coalesce ? extents_best_fit_locked(tsdn, arena,
+	    extents, size) : extents_first_fit_locked(tsdn, arena, extents,
+	    size);
+}
+
+static bool
+extent_try_delayed_coalesce(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents,
+    extent_t *extent) {
+	extent_state_set(extent, extent_state_active);
+	bool coalesced;
+	extent = extent_try_coalesce(tsdn, arena, r_extent_hooks, rtree_ctx,
+	    extents, extent, &coalesced, false);
+	extent_state_set(extent, extents_state_get(extents));
+
+	if (!coalesced) {
+		return true;
+	}
+	extents_insert_locked(tsdn, extents, extent, true);
+	return false;
+}
+
+extent_t *
+extents_alloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) {
+	assert(size + pad != 0);
+	assert(alignment != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	return extent_recycle(tsdn, arena, r_extent_hooks, extents, new_addr,
+	    size, pad, alignment, slab, szind, zero, commit, false);
+}
+
+void
+extents_dalloc(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, extent_t *extent) {
+	assert(extent_base_get(extent) != NULL);
+	assert(extent_size_get(extent) != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extent_addr_set(extent, extent_base_get(extent));
+	extent_zeroed_set(extent, false);
+
+	extent_record(tsdn, arena, r_extent_hooks, extents, extent, false);
+}
+
+extent_t *
+extents_evict(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, size_t npages_min) {
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	malloc_mutex_lock(tsdn, &extents->mtx);
+
+	/*
+	 * Get the LRU coalesced extent, if any.  If coalescing was delayed,
+	 * the loop will iterate until the LRU extent is fully coalesced.
+	 */
+	extent_t *extent;
+	while (true) {
+		/* Get the LRU extent, if any. */
+		extent = extent_list_first(&extents->lru);
+		if (extent == NULL) {
+			goto label_return;
+		}
+		/* Check the eviction limit. */
+		size_t npages = extent_size_get(extent) >> LG_PAGE;
+		size_t extents_npages = atomic_load_zu(&extents->npages,
+		    ATOMIC_RELAXED);
+		if (extents_npages - npages < npages_min) {
+			extent = NULL;
+			goto label_return;
+		}
+		extents_remove_locked(tsdn, extents, extent, false);
+		if (!extents->delay_coalesce) {
+			break;
+		}
+		/* Try to coalesce. */
+		if (extent_try_delayed_coalesce(tsdn, arena, r_extent_hooks,
+		    rtree_ctx, extents, extent)) {
+			break;
+		}
+		/*
+		 * The LRU extent was just coalesced and the result placed in
+		 * the LRU at its neighbor's position.  Start over.
+		 */
+	}
+
+	/*
+	 * Either mark the extent active or deregister it to protect against
+	 * concurrent operations.
+	 */
+	switch (extents_state_get(extents)) {
+	case extent_state_active:
+		not_reached();
+	case extent_state_dirty:
+	case extent_state_muzzy:
+		extent_state_set(extent, extent_state_active);
+		break;
+	case extent_state_retained:
+		extent_deregister(tsdn, extent);
+		break;
+	default:
+		not_reached();
+	}
+
+label_return:
+	malloc_mutex_unlock(tsdn, &extents->mtx);
+	return extent;
+}
+
+static void
+extents_leak(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, extent_t *extent, bool growing_retained) {
+	/*
+	 * Leak extent after making sure its pages have already been purged, so
+	 * that this is only a virtual memory leak.
+	 */
+	if (extents_state_get(extents) == extent_state_dirty) {
+		if (extent_purge_lazy_impl(tsdn, arena, r_extent_hooks,
+		    extent, 0, extent_size_get(extent), growing_retained)) {
+			extent_purge_forced_impl(tsdn, arena, r_extent_hooks,
+			    extent, 0, extent_size_get(extent),
+			    growing_retained);
+		}
+	}
+	extent_dalloc(tsdn, arena, extent);
+}
+
+void
+extents_prefork(tsdn_t *tsdn, extents_t *extents) {
+	malloc_mutex_prefork(tsdn, &extents->mtx);
+}
+
+void
+extents_postfork_parent(tsdn_t *tsdn, extents_t *extents) {
+	malloc_mutex_postfork_parent(tsdn, &extents->mtx);
+}
+
+void
+extents_postfork_child(tsdn_t *tsdn, extents_t *extents) {
+	malloc_mutex_postfork_child(tsdn, &extents->mtx);
+}
+
+static void
+extent_deactivate_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    extent_t *extent, bool preserve_lru) {
+	assert(extent_arena_get(extent) == arena);
+	assert(extent_state_get(extent) == extent_state_active);
+
+	extent_state_set(extent, extents_state_get(extents));
+	extents_insert_locked(tsdn, extents, extent, preserve_lru);
+}
+
+static void
+extent_deactivate(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    extent_t *extent, bool preserve_lru) {
+	malloc_mutex_lock(tsdn, &extents->mtx);
+	extent_deactivate_locked(tsdn, arena, extents, extent, preserve_lru);
+	malloc_mutex_unlock(tsdn, &extents->mtx);
+}
+
+static void
+extent_activate_locked(tsdn_t *tsdn, arena_t *arena, extents_t *extents,
+    extent_t *extent, bool preserve_lru) {
+	assert(extent_arena_get(extent) == arena);
+	assert(extent_state_get(extent) == extents_state_get(extents));
+
+	extents_remove_locked(tsdn, extents, extent, preserve_lru);
+	extent_state_set(extent, extent_state_active);
+}
+
+static bool
+extent_rtree_leaf_elms_lookup(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx,
+    const extent_t *extent, bool dependent, bool init_missing,
+    rtree_leaf_elm_t **r_elm_a, rtree_leaf_elm_t **r_elm_b) {
+	*r_elm_a = rtree_leaf_elm_lookup(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)extent_base_get(extent), dependent, init_missing);
+	if (!dependent && *r_elm_a == NULL) {
+		return true;
+	}
+	assert(*r_elm_a != NULL);
+
+	*r_elm_b = rtree_leaf_elm_lookup(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)extent_last_get(extent), dependent, init_missing);
+	if (!dependent && *r_elm_b == NULL) {
+		return true;
+	}
+	assert(*r_elm_b != NULL);
+
+	return false;
+}
+
+static void
+extent_rtree_write_acquired(tsdn_t *tsdn, rtree_leaf_elm_t *elm_a,
+    rtree_leaf_elm_t *elm_b, extent_t *extent, szind_t szind, bool slab) {
+	rtree_leaf_elm_write(tsdn, &extents_rtree, elm_a, extent, szind, slab);
+	if (elm_b != NULL) {
+		rtree_leaf_elm_write(tsdn, &extents_rtree, elm_b, extent, szind,
+		    slab);
+	}
+}
+
+static void
+extent_interior_register(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx, extent_t *extent,
+    szind_t szind) {
+	assert(extent_slab_get(extent));
+
+	/* Register interior. */
+	for (size_t i = 1; i < (extent_size_get(extent) >> LG_PAGE) - 1; i++) {
+		rtree_write(tsdn, &extents_rtree, rtree_ctx,
+		    (uintptr_t)extent_base_get(extent) + (uintptr_t)(i <<
+		    LG_PAGE), extent, szind, true);
+	}
+}
+
+static void
+extent_gdump_add(tsdn_t *tsdn, const extent_t *extent) {
+	cassert(config_prof);
+	/* prof_gdump() requirement. */
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	if (opt_prof && extent_state_get(extent) == extent_state_active) {
+		size_t nadd = extent_size_get(extent) >> LG_PAGE;
+		size_t cur = atomic_fetch_add_zu(&curpages, nadd,
+		    ATOMIC_RELAXED) + nadd;
+		size_t high = atomic_load_zu(&highpages, ATOMIC_RELAXED);
+		while (cur > high && !atomic_compare_exchange_weak_zu(
+		    &highpages, &high, cur, ATOMIC_RELAXED, ATOMIC_RELAXED)) {
+			/*
+			 * Don't refresh cur, because it may have decreased
+			 * since this thread lost the highpages update race.
+			 * Note that high is updated in case of CAS failure.
+			 */
+		}
+		if (cur > high && prof_gdump_get_unlocked()) {
+			prof_gdump(tsdn);
+		}
+	}
+}
+
+static void
+extent_gdump_sub(tsdn_t *tsdn, const extent_t *extent) {
+	cassert(config_prof);
+
+	if (opt_prof && extent_state_get(extent) == extent_state_active) {
+		size_t nsub = extent_size_get(extent) >> LG_PAGE;
+		assert(atomic_load_zu(&curpages, ATOMIC_RELAXED) >= nsub);
+		atomic_fetch_sub_zu(&curpages, nsub, ATOMIC_RELAXED);
+	}
+}
+
+static bool
+extent_register_impl(tsdn_t *tsdn, extent_t *extent, bool gdump_add) {
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	rtree_leaf_elm_t *elm_a, *elm_b;
+
+	/*
+	 * We need to hold the lock to protect against a concurrent coalesce
+	 * operation that sees us in a partial state.
+	 */
+	extent_lock(tsdn, extent);
+
+	if (extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, extent, false, true,
+	    &elm_a, &elm_b)) {
+		return true;
+	}
+
+	szind_t szind = extent_szind_get_maybe_invalid(extent);
+	bool slab = extent_slab_get(extent);
+	extent_rtree_write_acquired(tsdn, elm_a, elm_b, extent, szind, slab);
+	if (slab) {
+		extent_interior_register(tsdn, rtree_ctx, extent, szind);
+	}
+
+	extent_unlock(tsdn, extent);
+
+	if (config_prof && gdump_add) {
+		extent_gdump_add(tsdn, extent);
+	}
+
+	return false;
+}
+
+static bool
+extent_register(tsdn_t *tsdn, extent_t *extent) {
+	return extent_register_impl(tsdn, extent, true);
+}
+
+static bool
+extent_register_no_gdump_add(tsdn_t *tsdn, extent_t *extent) {
+	return extent_register_impl(tsdn, extent, false);
+}
+
+static void
+extent_reregister(tsdn_t *tsdn, extent_t *extent) {
+	bool err = extent_register(tsdn, extent);
+	assert(!err);
+}
+
+static void
+extent_interior_deregister(tsdn_t *tsdn, rtree_ctx_t *rtree_ctx,
+    extent_t *extent) {
+	size_t i;
+
+	assert(extent_slab_get(extent));
+
+	for (i = 1; i < (extent_size_get(extent) >> LG_PAGE) - 1; i++) {
+		rtree_clear(tsdn, &extents_rtree, rtree_ctx,
+		    (uintptr_t)extent_base_get(extent) + (uintptr_t)(i <<
+		    LG_PAGE));
+	}
+}
+
+static void
+extent_deregister(tsdn_t *tsdn, extent_t *extent) {
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	rtree_leaf_elm_t *elm_a, *elm_b;
+	extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, extent, true, false,
+	    &elm_a, &elm_b);
+
+	extent_lock(tsdn, extent);
+
+	extent_rtree_write_acquired(tsdn, elm_a, elm_b, NULL, NSIZES, false);
+	if (extent_slab_get(extent)) {
+		extent_interior_deregister(tsdn, rtree_ctx, extent);
+		extent_slab_set(extent, false);
+	}
+
+	extent_unlock(tsdn, extent);
+
+	if (config_prof) {
+		extent_gdump_sub(tsdn, extent);
+	}
+}
+
+static extent_t *
+extent_recycle_extract(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents,
+    void *new_addr, size_t size, size_t pad, size_t alignment, bool slab,
+    bool *zero, bool *commit, bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+	assert(alignment > 0);
+	if (config_debug && new_addr != NULL) {
+		/*
+		 * Non-NULL new_addr has two use cases:
+		 *
+		 *   1) Recycle a known-extant extent, e.g. during purging.
+		 *   2) Perform in-place expanding reallocation.
+		 *
+		 * Regardless of use case, new_addr must either refer to a
+		 * non-existing extent, or to the base of an extant extent,
+		 * since only active slabs support interior lookups (which of
+		 * course cannot be recycled).
+		 */
+		assert(PAGE_ADDR2BASE(new_addr) == new_addr);
+		assert(pad == 0);
+		assert(alignment <= PAGE);
+	}
+
+	size_t esize = size + pad;
+	size_t alloc_size = esize + PAGE_CEILING(alignment) - PAGE;
+	/* Beware size_t wrap-around. */
+	if (alloc_size < esize) {
+		return NULL;
+	}
+	malloc_mutex_lock(tsdn, &extents->mtx);
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+	extent_t *extent;
+	if (new_addr != NULL) {
+		extent = extent_lock_from_addr(tsdn, rtree_ctx, new_addr);
+		if (extent != NULL) {
+			/*
+			 * We might null-out extent to report an error, but we
+			 * still need to unlock the associated mutex after.
+			 */
+			extent_t *unlock_extent = extent;
+			assert(extent_base_get(extent) == new_addr);
+			if (extent_arena_get(extent) != arena ||
+			    extent_size_get(extent) < esize ||
+			    extent_state_get(extent) !=
+			    extents_state_get(extents)) {
+				extent = NULL;
+			}
+			extent_unlock(tsdn, unlock_extent);
+		}
+	} else {
+		extent = extents_fit_locked(tsdn, arena, extents, alloc_size);
+	}
+	if (extent == NULL) {
+		malloc_mutex_unlock(tsdn, &extents->mtx);
+		return NULL;
+	}
+
+	extent_activate_locked(tsdn, arena, extents, extent, false);
+	malloc_mutex_unlock(tsdn, &extents->mtx);
+
+	if (extent_zeroed_get(extent)) {
+		*zero = true;
+	}
+	if (extent_committed_get(extent)) {
+		*commit = true;
+	}
+
+	return extent;
+}
+
+static extent_t *
+extent_recycle_split(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents,
+    void *new_addr, size_t size, size_t pad, size_t alignment, bool slab,
+    szind_t szind, extent_t *extent, bool growing_retained) {
+	size_t esize = size + pad;
+	size_t leadsize = ALIGNMENT_CEILING((uintptr_t)extent_base_get(extent),
+	    PAGE_CEILING(alignment)) - (uintptr_t)extent_base_get(extent);
+	assert(new_addr == NULL || leadsize == 0);
+	assert(extent_size_get(extent) >= leadsize + esize);
+	size_t trailsize = extent_size_get(extent) - leadsize - esize;
+
+	/* Split the lead. */
+	if (leadsize != 0) {
+		extent_t *lead = extent;
+		extent = extent_split_impl(tsdn, arena, r_extent_hooks,
+		    lead, leadsize, NSIZES, false, esize + trailsize, szind,
+		    slab, growing_retained);
+		if (extent == NULL) {
+			extent_deregister(tsdn, lead);
+			extents_leak(tsdn, arena, r_extent_hooks, extents,
+			    lead, growing_retained);
+			return NULL;
+		}
+		extent_deactivate(tsdn, arena, extents, lead, false);
+	}
+
+	/* Split the trail. */
+	if (trailsize != 0) {
+		extent_t *trail = extent_split_impl(tsdn, arena,
+		    r_extent_hooks, extent, esize, szind, slab, trailsize,
+		    NSIZES, false, growing_retained);
+		if (trail == NULL) {
+			extent_deregister(tsdn, extent);
+			extents_leak(tsdn, arena, r_extent_hooks, extents,
+			    extent, growing_retained);
+			return NULL;
+		}
+		extent_deactivate(tsdn, arena, extents, trail, false);
+	} else if (leadsize == 0) {
+		/*
+		 * Splitting causes szind to be set as a side effect, but no
+		 * splitting occurred.
+		 */
+		extent_szind_set(extent, szind);
+		if (szind != NSIZES) {
+			rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx,
+			    (uintptr_t)extent_addr_get(extent), szind, slab);
+			if (slab && extent_size_get(extent) > PAGE) {
+				rtree_szind_slab_update(tsdn, &extents_rtree,
+				    rtree_ctx,
+				    (uintptr_t)extent_past_get(extent) -
+				    (uintptr_t)PAGE, szind, slab);
+			}
+		}
+	}
+
+	return extent;
+}
+
+static extent_t *
+extent_recycle(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit,
+    bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+	assert(new_addr == NULL || !slab);
+	assert(pad == 0 || !slab);
+	assert(!*zero || !slab);
+
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	bool committed = false;
+	extent_t *extent = extent_recycle_extract(tsdn, arena, r_extent_hooks,
+	    rtree_ctx, extents, new_addr, size, pad, alignment, slab, zero,
+	    &committed, growing_retained);
+	if (extent == NULL) {
+		return NULL;
+	}
+	if (committed) {
+		*commit = true;
+	}
+
+	extent = extent_recycle_split(tsdn, arena, r_extent_hooks, rtree_ctx,
+	    extents, new_addr, size, pad, alignment, slab, szind, extent,
+	    growing_retained);
+	if (extent == NULL) {
+		return NULL;
+	}
+
+	if (*commit && !extent_committed_get(extent)) {
+		if (extent_commit_impl(tsdn, arena, r_extent_hooks, extent,
+		    0, extent_size_get(extent), growing_retained)) {
+			extent_record(tsdn, arena, r_extent_hooks, extents,
+			    extent, growing_retained);
+			return NULL;
+		}
+		extent_zeroed_set(extent, true);
+	}
+
+	if (pad != 0) {
+		extent_addr_randomize(tsdn, extent, alignment);
+	}
+	assert(extent_state_get(extent) == extent_state_active);
+	if (slab) {
+		extent_slab_set(extent, slab);
+		extent_interior_register(tsdn, rtree_ctx, extent, szind);
+	}
+
+	if (*zero) {
+		void *addr = extent_base_get(extent);
+		size_t size = extent_size_get(extent);
+		if (!extent_zeroed_get(extent)) {
+			if (pages_purge_forced(addr, size)) {
+				memset(addr, 0, size);
+			}
+		} else if (config_debug) {
+			size_t *p = (size_t *)(uintptr_t)addr;
+			for (size_t i = 0; i < size / sizeof(size_t); i++) {
+				assert(p[i] == 0);
+			}
+		}
+	}
+	return extent;
+}
+
+/*
+ * If the caller specifies (!*zero), it is still possible to receive zeroed
+ * memory, in which case *zero is toggled to true.  arena_extent_alloc() takes
+ * advantage of this to avoid demanding zeroed extents, but taking advantage of
+ * them if they are returned.
+ */
+static void *
+extent_alloc_core(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size,
+    size_t alignment, bool *zero, bool *commit, dss_prec_t dss_prec) {
+	void *ret;
+
+	assert(size != 0);
+	assert(alignment != 0);
+
+	/* "primary" dss. */
+	if (have_dss && dss_prec == dss_prec_primary && (ret =
+	    extent_alloc_dss(tsdn, arena, new_addr, size, alignment, zero,
+	    commit)) != NULL) {
+		return ret;
+	}
+	/* mmap. */
+	if ((ret = extent_alloc_mmap(new_addr, size, alignment, zero, commit))
+	    != NULL) {
+		return ret;
+	}
+	/* "secondary" dss. */
+	if (have_dss && dss_prec == dss_prec_secondary && (ret =
+	    extent_alloc_dss(tsdn, arena, new_addr, size, alignment, zero,
+	    commit)) != NULL) {
+		return ret;
+	}
+
+	/* All strategies for allocation failed. */
+	return NULL;
+}
+
+static void *
+extent_alloc_default_impl(tsdn_t *tsdn, arena_t *arena, void *new_addr,
+    size_t size, size_t alignment, bool *zero, bool *commit) {
+	void *ret;
+
+	ret = extent_alloc_core(tsdn, arena, new_addr, size, alignment, zero,
+	    commit, (dss_prec_t)atomic_load_u(&arena->dss_prec,
+	    ATOMIC_RELAXED));
+	return ret;
+}
+
+static void *
+extent_alloc_default(extent_hooks_t *extent_hooks, void *new_addr, size_t size,
+    size_t alignment, bool *zero, bool *commit, unsigned arena_ind) {
+	tsdn_t *tsdn;
+	arena_t *arena;
+
+	tsdn = tsdn_fetch();
+	arena = arena_get(tsdn, arena_ind, false);
+	/*
+	 * The arena we're allocating on behalf of must have been initialized
+	 * already.
+	 */
+	assert(arena != NULL);
+
+	return extent_alloc_default_impl(tsdn, arena, new_addr, size,
+	    alignment, zero, commit);
+}
+
+static void
+extent_hook_pre_reentrancy(tsdn_t *tsdn, arena_t *arena) {
+	tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn);
+	pre_reentrancy(tsd, arena);
+}
+
+static void
+extent_hook_post_reentrancy(tsdn_t *tsdn) {
+	tsd_t *tsd = tsdn_null(tsdn) ? tsd_fetch() : tsdn_tsd(tsdn);
+	post_reentrancy(tsd);
+}
+
+/*
+ * If virtual memory is retained, create increasingly larger extents from which
+ * to split requested extents in order to limit the total number of disjoint
+ * virtual memory ranges retained by each arena.
+ */
+static extent_t *
+extent_grow_retained(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, size_t size, size_t pad, size_t alignment,
+    bool slab, szind_t szind, bool *zero, bool *commit) {
+	malloc_mutex_assert_owner(tsdn, &arena->extent_grow_mtx);
+	assert(pad == 0 || !slab);
+	assert(!*zero || !slab);
+
+	size_t esize = size + pad;
+	size_t alloc_size_min = esize + PAGE_CEILING(alignment) - PAGE;
+	/* Beware size_t wrap-around. */
+	if (alloc_size_min < esize) {
+		goto label_err;
+	}
+	/*
+	 * Find the next extent size in the series that would be large enough to
+	 * satisfy this request.
+	 */
+	pszind_t egn_skip = 0;
+	size_t alloc_size = sz_pind2sz(arena->extent_grow_next + egn_skip);
+	while (alloc_size < alloc_size_min) {
+		egn_skip++;
+		if (arena->extent_grow_next + egn_skip == NPSIZES) {
+			/* Outside legal range. */
+			goto label_err;
+		}
+		assert(arena->extent_grow_next + egn_skip < NPSIZES);
+		alloc_size = sz_pind2sz(arena->extent_grow_next + egn_skip);
+	}
+
+	extent_t *extent = extent_alloc(tsdn, arena);
+	if (extent == NULL) {
+		goto label_err;
+	}
+	bool zeroed = false;
+	bool committed = false;
+
+	void *ptr;
+	if (*r_extent_hooks == &extent_hooks_default) {
+		ptr = extent_alloc_core(tsdn, arena, NULL, alloc_size, PAGE,
+		    &zeroed, &committed, (dss_prec_t)atomic_load_u(
+		    &arena->dss_prec, ATOMIC_RELAXED));
+	} else {
+		extent_hook_pre_reentrancy(tsdn, arena);
+		ptr = (*r_extent_hooks)->alloc(*r_extent_hooks, NULL,
+		    alloc_size, PAGE, &zeroed, &committed,
+		    arena_ind_get(arena));
+		extent_hook_post_reentrancy(tsdn);
+	}
+
+	extent_init(extent, arena, ptr, alloc_size, false, NSIZES,
+	    arena_extent_sn_next(arena), extent_state_active, zeroed,
+	    committed);
+	if (ptr == NULL) {
+		extent_dalloc(tsdn, arena, extent);
+		goto label_err;
+	}
+	if (extent_register_no_gdump_add(tsdn, extent)) {
+		extents_leak(tsdn, arena, r_extent_hooks,
+		    &arena->extents_retained, extent, true);
+		goto label_err;
+	}
+
+	size_t leadsize = ALIGNMENT_CEILING((uintptr_t)ptr,
+	    PAGE_CEILING(alignment)) - (uintptr_t)ptr;
+	assert(alloc_size >= leadsize + esize);
+	size_t trailsize = alloc_size - leadsize - esize;
+	if (extent_zeroed_get(extent) && extent_committed_get(extent)) {
+		*zero = true;
+	}
+	if (extent_committed_get(extent)) {
+		*commit = true;
+	}
+
+	/* Split the lead. */
+	if (leadsize != 0) {
+		extent_t *lead = extent;
+		extent = extent_split_impl(tsdn, arena, r_extent_hooks, lead,
+		    leadsize, NSIZES, false, esize + trailsize, szind, slab,
+		    true);
+		if (extent == NULL) {
+			extent_deregister(tsdn, lead);
+			extents_leak(tsdn, arena, r_extent_hooks,
+			    &arena->extents_retained, lead, true);
+			goto label_err;
+		}
+		extent_record(tsdn, arena, r_extent_hooks,
+		    &arena->extents_retained, lead, true);
+	}
+
+	/* Split the trail. */
+	if (trailsize != 0) {
+		extent_t *trail = extent_split_impl(tsdn, arena, r_extent_hooks,
+		    extent, esize, szind, slab, trailsize, NSIZES, false, true);
+		if (trail == NULL) {
+			extent_deregister(tsdn, extent);
+			extents_leak(tsdn, arena, r_extent_hooks,
+			    &arena->extents_retained, extent, true);
+			goto label_err;
+		}
+		extent_record(tsdn, arena, r_extent_hooks,
+		    &arena->extents_retained, trail, true);
+	} else if (leadsize == 0) {
+		/*
+		 * Splitting causes szind to be set as a side effect, but no
+		 * splitting occurred.
+		 */
+		rtree_ctx_t rtree_ctx_fallback;
+		rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
+		    &rtree_ctx_fallback);
+
+		extent_szind_set(extent, szind);
+		if (szind != NSIZES) {
+			rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx,
+			    (uintptr_t)extent_addr_get(extent), szind, slab);
+			if (slab && extent_size_get(extent) > PAGE) {
+				rtree_szind_slab_update(tsdn, &extents_rtree,
+				    rtree_ctx,
+				    (uintptr_t)extent_past_get(extent) -
+				    (uintptr_t)PAGE, szind, slab);
+			}
+		}
+	}
+
+	if (*commit && !extent_committed_get(extent)) {
+		if (extent_commit_impl(tsdn, arena, r_extent_hooks, extent, 0,
+		    extent_size_get(extent), true)) {
+			extent_record(tsdn, arena, r_extent_hooks,
+			    &arena->extents_retained, extent, true);
+			goto label_err;
+		}
+		extent_zeroed_set(extent, true);
+	}
+
+	/*
+	 * Increment extent_grow_next if doing so wouldn't exceed the legal
+	 * range.
+	 */
+	if (arena->extent_grow_next + egn_skip + 1 < NPSIZES) {
+		arena->extent_grow_next += egn_skip + 1;
+	} else {
+		arena->extent_grow_next = NPSIZES - 1;
+	}
+	/* All opportunities for failure are past. */
+	malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx);
+
+	if (config_prof) {
+		/* Adjust gdump stats now that extent is final size. */
+		extent_gdump_add(tsdn, extent);
+	}
+	if (pad != 0) {
+		extent_addr_randomize(tsdn, extent, alignment);
+	}
+	if (slab) {
+		rtree_ctx_t rtree_ctx_fallback;
+		rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn,
+		    &rtree_ctx_fallback);
+
+		extent_slab_set(extent, true);
+		extent_interior_register(tsdn, rtree_ctx, extent, szind);
+	}
+	if (*zero && !extent_zeroed_get(extent)) {
+		void *addr = extent_base_get(extent);
+		size_t size = extent_size_get(extent);
+		if (pages_purge_forced(addr, size)) {
+			memset(addr, 0, size);
+		}
+	}
+
+	return extent;
+label_err:
+	malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx);
+	return NULL;
+}
+
+static extent_t *
+extent_alloc_retained(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) {
+	assert(size != 0);
+	assert(alignment != 0);
+
+	malloc_mutex_lock(tsdn, &arena->extent_grow_mtx);
+
+	extent_t *extent = extent_recycle(tsdn, arena, r_extent_hooks,
+	    &arena->extents_retained, new_addr, size, pad, alignment, slab,
+	    szind, zero, commit, true);
+	if (extent != NULL) {
+		malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx);
+		if (config_prof) {
+			extent_gdump_add(tsdn, extent);
+		}
+	} else if (opt_retain && new_addr == NULL) {
+		extent = extent_grow_retained(tsdn, arena, r_extent_hooks, size,
+		    pad, alignment, slab, szind, zero, commit);
+		/* extent_grow_retained() always releases extent_grow_mtx. */
+	} else {
+		malloc_mutex_unlock(tsdn, &arena->extent_grow_mtx);
+	}
+	malloc_mutex_assert_not_owner(tsdn, &arena->extent_grow_mtx);
+
+	return extent;
+}
+
+static extent_t *
+extent_alloc_wrapper_hard(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) {
+	size_t esize = size + pad;
+	extent_t *extent = extent_alloc(tsdn, arena);
+	if (extent == NULL) {
+		return NULL;
+	}
+	void *addr;
+	if (*r_extent_hooks == &extent_hooks_default) {
+		/* Call directly to propagate tsdn. */
+		addr = extent_alloc_default_impl(tsdn, arena, new_addr, esize,
+		    alignment, zero, commit);
+	} else {
+		extent_hook_pre_reentrancy(tsdn, arena);
+		addr = (*r_extent_hooks)->alloc(*r_extent_hooks, new_addr,
+		    esize, alignment, zero, commit, arena_ind_get(arena));
+		extent_hook_post_reentrancy(tsdn);
+	}
+	if (addr == NULL) {
+		extent_dalloc(tsdn, arena, extent);
+		return NULL;
+	}
+	extent_init(extent, arena, addr, esize, slab, szind,
+	    arena_extent_sn_next(arena), extent_state_active, zero, commit);
+	if (pad != 0) {
+		extent_addr_randomize(tsdn, extent, alignment);
+	}
+	if (extent_register(tsdn, extent)) {
+		extents_leak(tsdn, arena, r_extent_hooks,
+		    &arena->extents_retained, extent, false);
+		return NULL;
+	}
+
+	return extent;
+}
+
+extent_t *
+extent_alloc_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, void *new_addr, size_t size, size_t pad,
+    size_t alignment, bool slab, szind_t szind, bool *zero, bool *commit) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	extent_t *extent = extent_alloc_retained(tsdn, arena, r_extent_hooks,
+	    new_addr, size, pad, alignment, slab, szind, zero, commit);
+	if (extent == NULL) {
+		extent = extent_alloc_wrapper_hard(tsdn, arena, r_extent_hooks,
+		    new_addr, size, pad, alignment, slab, szind, zero, commit);
+	}
+
+	return extent;
+}
+
+static bool
+extent_can_coalesce(arena_t *arena, extents_t *extents, const extent_t *inner,
+    const extent_t *outer) {
+	assert(extent_arena_get(inner) == arena);
+	if (extent_arena_get(outer) != arena) {
+		return false;
+	}
+
+	assert(extent_state_get(inner) == extent_state_active);
+	if (extent_state_get(outer) != extents->state) {
+		return false;
+	}
+
+	if (extent_committed_get(inner) != extent_committed_get(outer)) {
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+extent_coalesce(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, extent_t *inner, extent_t *outer, bool forward,
+    bool growing_retained) {
+	assert(extent_can_coalesce(arena, extents, inner, outer));
+
+	if (forward && extents->delay_coalesce) {
+		/*
+		 * The extent that remains after coalescing must occupy the
+		 * outer extent's position in the LRU.  For forward coalescing,
+		 * swap the inner extent into the LRU.
+		 */
+		extent_list_replace(&extents->lru, outer, inner);
+	}
+	extent_activate_locked(tsdn, arena, extents, outer,
+	    extents->delay_coalesce);
+
+	malloc_mutex_unlock(tsdn, &extents->mtx);
+	bool err = extent_merge_impl(tsdn, arena, r_extent_hooks,
+	    forward ? inner : outer, forward ? outer : inner, growing_retained);
+	malloc_mutex_lock(tsdn, &extents->mtx);
+
+	if (err) {
+		if (forward && extents->delay_coalesce) {
+			extent_list_replace(&extents->lru, inner, outer);
+		}
+		extent_deactivate_locked(tsdn, arena, extents, outer,
+		    extents->delay_coalesce);
+	}
+
+	return err;
+}
+
+static extent_t *
+extent_try_coalesce(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, rtree_ctx_t *rtree_ctx, extents_t *extents,
+    extent_t *extent, bool *coalesced, bool growing_retained) {
+	/*
+	 * Continue attempting to coalesce until failure, to protect against
+	 * races with other threads that are thwarted by this one.
+	 */
+	bool again;
+	do {
+		again = false;
+
+		/* Try to coalesce forward. */
+		extent_t *next = extent_lock_from_addr(tsdn, rtree_ctx,
+		    extent_past_get(extent));
+		if (next != NULL) {
+			/*
+			 * extents->mtx only protects against races for
+			 * like-state extents, so call extent_can_coalesce()
+			 * before releasing next's pool lock.
+			 */
+			bool can_coalesce = extent_can_coalesce(arena, extents,
+			    extent, next);
+
+			extent_unlock(tsdn, next);
+
+			if (can_coalesce && !extent_coalesce(tsdn, arena,
+			    r_extent_hooks, extents, extent, next, true,
+			    growing_retained)) {
+				if (extents->delay_coalesce) {
+					/* Do minimal coalescing. */
+					*coalesced = true;
+					return extent;
+				}
+				again = true;
+			}
+		}
+
+		/* Try to coalesce backward. */
+		extent_t *prev = extent_lock_from_addr(tsdn, rtree_ctx,
+		    extent_before_get(extent));
+		if (prev != NULL) {
+			bool can_coalesce = extent_can_coalesce(arena, extents,
+			    extent, prev);
+			extent_unlock(tsdn, prev);
+
+			if (can_coalesce && !extent_coalesce(tsdn, arena,
+			    r_extent_hooks, extents, extent, prev, false,
+			    growing_retained)) {
+				extent = prev;
+				if (extents->delay_coalesce) {
+					/* Do minimal coalescing. */
+					*coalesced = true;
+					return extent;
+				}
+				again = true;
+			}
+		}
+	} while (again);
+
+	if (extents->delay_coalesce) {
+		*coalesced = false;
+	}
+	return extent;
+}
+
+static void
+extent_record(tsdn_t *tsdn, arena_t *arena, extent_hooks_t **r_extent_hooks,
+    extents_t *extents, extent_t *extent, bool growing_retained) {
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+
+	assert((extents_state_get(extents) != extent_state_dirty &&
+	    extents_state_get(extents) != extent_state_muzzy) ||
+	    !extent_zeroed_get(extent));
+
+	malloc_mutex_lock(tsdn, &extents->mtx);
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	extent_szind_set(extent, NSIZES);
+	if (extent_slab_get(extent)) {
+		extent_interior_deregister(tsdn, rtree_ctx, extent);
+		extent_slab_set(extent, false);
+	}
+
+	assert(rtree_extent_read(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)extent_base_get(extent), true) == extent);
+
+	if (!extents->delay_coalesce) {
+		extent = extent_try_coalesce(tsdn, arena, r_extent_hooks,
+		    rtree_ctx, extents, extent, NULL, growing_retained);
+	}
+
+	extent_deactivate_locked(tsdn, arena, extents, extent, false);
+
+	malloc_mutex_unlock(tsdn, &extents->mtx);
+}
+
+void
+extent_dalloc_gap(tsdn_t *tsdn, arena_t *arena, extent_t *extent) {
+	extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER;
+
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	if (extent_register(tsdn, extent)) {
+		extents_leak(tsdn, arena, &extent_hooks,
+		    &arena->extents_retained, extent, false);
+		return;
+	}
+	extent_dalloc_wrapper(tsdn, arena, &extent_hooks, extent);
+}
+
+static bool
+extent_dalloc_default_impl(void *addr, size_t size) {
+	if (!have_dss || !extent_in_dss(addr)) {
+		return extent_dalloc_mmap(addr, size);
+	}
+	return true;
+}
+
+static bool
+extent_dalloc_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    bool committed, unsigned arena_ind) {
+	return extent_dalloc_default_impl(addr, size);
+}
+
+static bool
+extent_dalloc_wrapper_try(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent) {
+	bool err;
+
+	assert(extent_base_get(extent) != NULL);
+	assert(extent_size_get(extent) != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extent_addr_set(extent, extent_base_get(extent));
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+	/* Try to deallocate. */
+	if (*r_extent_hooks == &extent_hooks_default) {
+		/* Call directly to propagate tsdn. */
+		err = extent_dalloc_default_impl(extent_base_get(extent),
+		    extent_size_get(extent));
+	} else {
+		extent_hook_pre_reentrancy(tsdn, arena);
+		err = ((*r_extent_hooks)->dalloc == NULL ||
+		    (*r_extent_hooks)->dalloc(*r_extent_hooks,
+		    extent_base_get(extent), extent_size_get(extent),
+		    extent_committed_get(extent), arena_ind_get(arena)));
+		extent_hook_post_reentrancy(tsdn);
+	}
+
+	if (!err) {
+		extent_dalloc(tsdn, arena, extent);
+	}
+
+	return err;
+}
+
+void
+extent_dalloc_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	/*
+	 * Deregister first to avoid a race with other allocating threads, and
+	 * reregister if deallocation fails.
+	 */
+	extent_deregister(tsdn, extent);
+	if (!extent_dalloc_wrapper_try(tsdn, arena, r_extent_hooks, extent)) {
+		return;
+	}
+
+	extent_reregister(tsdn, extent);
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	/* Try to decommit; purge if that fails. */
+	bool zeroed;
+	if (!extent_committed_get(extent)) {
+		zeroed = true;
+	} else if (!extent_decommit_wrapper(tsdn, arena, r_extent_hooks, extent,
+	    0, extent_size_get(extent))) {
+		zeroed = true;
+	} else if ((*r_extent_hooks)->purge_forced != NULL &&
+	    !(*r_extent_hooks)->purge_forced(*r_extent_hooks,
+	    extent_base_get(extent), extent_size_get(extent), 0,
+	    extent_size_get(extent), arena_ind_get(arena))) {
+		zeroed = true;
+	} else if (extent_state_get(extent) == extent_state_muzzy ||
+	    ((*r_extent_hooks)->purge_lazy != NULL &&
+	    !(*r_extent_hooks)->purge_lazy(*r_extent_hooks,
+	    extent_base_get(extent), extent_size_get(extent), 0,
+	    extent_size_get(extent), arena_ind_get(arena)))) {
+		zeroed = false;
+	} else {
+		zeroed = false;
+	}
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+	extent_zeroed_set(extent, zeroed);
+
+	if (config_prof) {
+		extent_gdump_sub(tsdn, extent);
+	}
+
+	extent_record(tsdn, arena, r_extent_hooks, &arena->extents_retained,
+	    extent, false);
+}
+
+static void
+extent_destroy_default_impl(void *addr, size_t size) {
+	if (!have_dss || !extent_in_dss(addr)) {
+		pages_unmap(addr, size);
+	}
+}
+
+static void
+extent_destroy_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    bool committed, unsigned arena_ind) {
+	extent_destroy_default_impl(addr, size);
+}
+
+void
+extent_destroy_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent) {
+	assert(extent_base_get(extent) != NULL);
+	assert(extent_size_get(extent) != 0);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	/* Deregister first to avoid a race with other allocating threads. */
+	extent_deregister(tsdn, extent);
+
+	extent_addr_set(extent, extent_base_get(extent));
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+	/* Try to destroy; silently fail otherwise. */
+	if (*r_extent_hooks == &extent_hooks_default) {
+		/* Call directly to propagate tsdn. */
+		extent_destroy_default_impl(extent_base_get(extent),
+		    extent_size_get(extent));
+	} else if ((*r_extent_hooks)->destroy != NULL) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+		(*r_extent_hooks)->destroy(*r_extent_hooks,
+		    extent_base_get(extent), extent_size_get(extent),
+		    extent_committed_get(extent), arena_ind_get(arena));
+		extent_hook_post_reentrancy(tsdn);
+	}
+
+	extent_dalloc(tsdn, arena, extent);
+}
+
+static bool
+extent_commit_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    size_t offset, size_t length, unsigned arena_ind) {
+	return pages_commit((void *)((uintptr_t)addr + (uintptr_t)offset),
+	    length);
+}
+
+static bool
+extent_commit_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	bool err = ((*r_extent_hooks)->commit == NULL ||
+	    (*r_extent_hooks)->commit(*r_extent_hooks, extent_base_get(extent),
+	    extent_size_get(extent), offset, length, arena_ind_get(arena)));
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+	extent_committed_set(extent, extent_committed_get(extent) || !err);
+	return err;
+}
+
+bool
+extent_commit_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length) {
+	return extent_commit_impl(tsdn, arena, r_extent_hooks, extent, offset,
+	    length, false);
+}
+
+static bool
+extent_decommit_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    size_t offset, size_t length, unsigned arena_ind) {
+	return pages_decommit((void *)((uintptr_t)addr + (uintptr_t)offset),
+	    length);
+}
+
+bool
+extent_decommit_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	bool err = ((*r_extent_hooks)->decommit == NULL ||
+	    (*r_extent_hooks)->decommit(*r_extent_hooks,
+	    extent_base_get(extent), extent_size_get(extent), offset, length,
+	    arena_ind_get(arena)));
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+	extent_committed_set(extent, extent_committed_get(extent) && err);
+	return err;
+}
+
+#ifdef PAGES_CAN_PURGE_LAZY
+static bool
+extent_purge_lazy_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    size_t offset, size_t length, unsigned arena_ind) {
+	assert(addr != NULL);
+	assert((offset & PAGE_MASK) == 0);
+	assert(length != 0);
+	assert((length & PAGE_MASK) == 0);
+
+	return pages_purge_lazy((void *)((uintptr_t)addr + (uintptr_t)offset),
+	    length);
+}
+#endif
+
+static bool
+extent_purge_lazy_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	if ((*r_extent_hooks)->purge_lazy == NULL) {
+		return true;
+	}
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	bool err = (*r_extent_hooks)->purge_lazy(*r_extent_hooks,
+	    extent_base_get(extent), extent_size_get(extent), offset, length,
+	    arena_ind_get(arena));
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+
+	return err;
+}
+
+bool
+extent_purge_lazy_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length) {
+	return extent_purge_lazy_impl(tsdn, arena, r_extent_hooks, extent,
+	    offset, length, false);
+}
+
+#ifdef PAGES_CAN_PURGE_FORCED
+static bool
+extent_purge_forced_default(extent_hooks_t *extent_hooks, void *addr,
+    size_t size, size_t offset, size_t length, unsigned arena_ind) {
+	assert(addr != NULL);
+	assert((offset & PAGE_MASK) == 0);
+	assert(length != 0);
+	assert((length & PAGE_MASK) == 0);
+
+	return pages_purge_forced((void *)((uintptr_t)addr +
+	    (uintptr_t)offset), length);
+}
+#endif
+
+static bool
+extent_purge_forced_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length, bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	if ((*r_extent_hooks)->purge_forced == NULL) {
+		return true;
+	}
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	bool err = (*r_extent_hooks)->purge_forced(*r_extent_hooks,
+	    extent_base_get(extent), extent_size_get(extent), offset, length,
+	    arena_ind_get(arena));
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+	return err;
+}
+
+bool
+extent_purge_forced_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t offset,
+    size_t length) {
+	return extent_purge_forced_impl(tsdn, arena, r_extent_hooks, extent,
+	    offset, length, false);
+}
+
+#ifdef JEMALLOC_MAPS_COALESCE
+static bool
+extent_split_default(extent_hooks_t *extent_hooks, void *addr, size_t size,
+    size_t size_a, size_t size_b, bool committed, unsigned arena_ind) {
+	return !maps_coalesce;
+}
+#endif
+
+static extent_t *
+extent_split_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a,
+    szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b,
+    bool growing_retained) {
+	assert(extent_size_get(extent) == size_a + size_b);
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	if ((*r_extent_hooks)->split == NULL) {
+		return NULL;
+	}
+
+	extent_t *trail = extent_alloc(tsdn, arena);
+	if (trail == NULL) {
+		goto label_error_a;
+	}
+
+	extent_init(trail, arena, (void *)((uintptr_t)extent_base_get(extent) +
+	    size_a), size_b, slab_b, szind_b, extent_sn_get(extent),
+	    extent_state_get(extent), extent_zeroed_get(extent),
+	    extent_committed_get(extent));
+
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	rtree_leaf_elm_t *lead_elm_a, *lead_elm_b;
+	{
+		extent_t lead;
+
+		extent_init(&lead, arena, extent_addr_get(extent), size_a,
+		    slab_a, szind_a, extent_sn_get(extent),
+		    extent_state_get(extent), extent_zeroed_get(extent),
+		    extent_committed_get(extent));
+
+		extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, &lead, false,
+		    true, &lead_elm_a, &lead_elm_b);
+	}
+	rtree_leaf_elm_t *trail_elm_a, *trail_elm_b;
+	extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, trail, false, true,
+	    &trail_elm_a, &trail_elm_b);
+
+	if (lead_elm_a == NULL || lead_elm_b == NULL || trail_elm_a == NULL
+	    || trail_elm_b == NULL) {
+		goto label_error_b;
+	}
+
+	extent_lock2(tsdn, extent, trail);
+
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_pre_reentrancy(tsdn, arena);
+	}
+	bool err = (*r_extent_hooks)->split(*r_extent_hooks, extent_base_get(extent),
+	    size_a + size_b, size_a, size_b, extent_committed_get(extent),
+	    arena_ind_get(arena));
+	if (*r_extent_hooks != &extent_hooks_default) {
+		extent_hook_post_reentrancy(tsdn);
+	}
+	if (err) {
+		goto label_error_c;
+	}
+
+	extent_size_set(extent, size_a);
+	extent_szind_set(extent, szind_a);
+
+	extent_rtree_write_acquired(tsdn, lead_elm_a, lead_elm_b, extent,
+	    szind_a, slab_a);
+	extent_rtree_write_acquired(tsdn, trail_elm_a, trail_elm_b, trail,
+	    szind_b, slab_b);
+
+	extent_unlock2(tsdn, extent, trail);
+
+	return trail;
+label_error_c:
+	extent_unlock2(tsdn, extent, trail);
+label_error_b:
+	extent_dalloc(tsdn, arena, trail);
+label_error_a:
+	return NULL;
+}
+
+extent_t *
+extent_split_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *extent, size_t size_a,
+    szind_t szind_a, bool slab_a, size_t size_b, szind_t szind_b, bool slab_b) {
+	return extent_split_impl(tsdn, arena, r_extent_hooks, extent, size_a,
+	    szind_a, slab_a, size_b, szind_b, slab_b, false);
+}
+
+static bool
+extent_merge_default_impl(void *addr_a, void *addr_b) {
+	if (!maps_coalesce) {
+		return true;
+	}
+	if (have_dss && !extent_dss_mergeable(addr_a, addr_b)) {
+		return true;
+	}
+
+	return false;
+}
+
+#ifdef JEMALLOC_MAPS_COALESCE
+static bool
+extent_merge_default(extent_hooks_t *extent_hooks, void *addr_a, size_t size_a,
+    void *addr_b, size_t size_b, bool committed, unsigned arena_ind) {
+	return extent_merge_default_impl(addr_a, addr_b);
+}
+#endif
+
+static bool
+extent_merge_impl(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b,
+    bool growing_retained) {
+	witness_assert_depth_to_rank(tsdn_witness_tsdp_get(tsdn),
+	    WITNESS_RANK_CORE, growing_retained ? 1 : 0);
+
+	extent_hooks_assure_initialized(arena, r_extent_hooks);
+
+	if ((*r_extent_hooks)->merge == NULL) {
+		return true;
+	}
+
+	bool err;
+	if (*r_extent_hooks == &extent_hooks_default) {
+		/* Call directly to propagate tsdn. */
+		err = extent_merge_default_impl(extent_base_get(a),
+		    extent_base_get(b));
+	} else {
+		extent_hook_pre_reentrancy(tsdn, arena);
+		err = (*r_extent_hooks)->merge(*r_extent_hooks,
+		    extent_base_get(a), extent_size_get(a), extent_base_get(b),
+		    extent_size_get(b), extent_committed_get(a),
+		    arena_ind_get(arena));
+		extent_hook_post_reentrancy(tsdn);
+	}
+
+	if (err) {
+		return true;
+	}
+
+	/*
+	 * The rtree writes must happen while all the relevant elements are
+	 * owned, so the following code uses decomposed helper functions rather
+	 * than extent_{,de}register() to do things in the right order.
+	 */
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	rtree_leaf_elm_t *a_elm_a, *a_elm_b, *b_elm_a, *b_elm_b;
+	extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, a, true, false, &a_elm_a,
+	    &a_elm_b);
+	extent_rtree_leaf_elms_lookup(tsdn, rtree_ctx, b, true, false, &b_elm_a,
+	    &b_elm_b);
+
+	extent_lock2(tsdn, a, b);
+
+	if (a_elm_b != NULL) {
+		rtree_leaf_elm_write(tsdn, &extents_rtree, a_elm_b, NULL,
+		    NSIZES, false);
+	}
+	if (b_elm_b != NULL) {
+		rtree_leaf_elm_write(tsdn, &extents_rtree, b_elm_a, NULL,
+		    NSIZES, false);
+	} else {
+		b_elm_b = b_elm_a;
+	}
+
+	extent_size_set(a, extent_size_get(a) + extent_size_get(b));
+	extent_szind_set(a, NSIZES);
+	extent_sn_set(a, (extent_sn_get(a) < extent_sn_get(b)) ?
+	    extent_sn_get(a) : extent_sn_get(b));
+	extent_zeroed_set(a, extent_zeroed_get(a) && extent_zeroed_get(b));
+
+	extent_rtree_write_acquired(tsdn, a_elm_a, b_elm_b, a, NSIZES, false);
+
+	extent_unlock2(tsdn, a, b);
+
+	extent_dalloc(tsdn, extent_arena_get(b), b);
+
+	return false;
+}
+
+bool
+extent_merge_wrapper(tsdn_t *tsdn, arena_t *arena,
+    extent_hooks_t **r_extent_hooks, extent_t *a, extent_t *b) {
+	return extent_merge_impl(tsdn, arena, r_extent_hooks, a, b, false);
+}
+
+bool
+extent_boot(void) {
+	if (rtree_new(&extents_rtree, true)) {
+		return true;
+	}
+
+	if (mutex_pool_init(&extent_mutex_pool, "extent_mutex_pool",
+	    WITNESS_RANK_EXTENT_POOL)) {
+		return true;
+	}
+
+	if (have_dss) {
+		extent_dss_boot();
+	}
+
+	return false;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/extent_dss.c b/modules/worldengine/deps/jemalloc/src/extent_dss.c
new file mode 100644
index 0000000000..e72da95870
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/extent_dss.c
@@ -0,0 +1,269 @@
+#define JEMALLOC_EXTENT_DSS_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/spin.h"
+
+/******************************************************************************/
+/* Data. */
+
+const char	*opt_dss = DSS_DEFAULT;
+
+const char	*dss_prec_names[] = {
+	"disabled",
+	"primary",
+	"secondary",
+	"N/A"
+};
+
+/*
+ * Current dss precedence default, used when creating new arenas.  NB: This is
+ * stored as unsigned rather than dss_prec_t because in principle there's no
+ * guarantee that sizeof(dss_prec_t) is the same as sizeof(unsigned), and we use
+ * atomic operations to synchronize the setting.
+ */
+static atomic_u_t	dss_prec_default = ATOMIC_INIT(
+    (unsigned)DSS_PREC_DEFAULT);
+
+/* Base address of the DSS. */
+static void		*dss_base;
+/* Atomic boolean indicating whether a thread is currently extending DSS. */
+static atomic_b_t	dss_extending;
+/* Atomic boolean indicating whether the DSS is exhausted. */
+static atomic_b_t	dss_exhausted;
+/* Atomic current upper limit on DSS addresses. */
+static atomic_p_t	dss_max;
+
+/******************************************************************************/
+
+static void *
+extent_dss_sbrk(intptr_t increment) {
+#ifdef JEMALLOC_DSS
+	return sbrk(increment);
+#else
+	not_implemented();
+	return NULL;
+#endif
+}
+
+dss_prec_t
+extent_dss_prec_get(void) {
+	dss_prec_t ret;
+
+	if (!have_dss) {
+		return dss_prec_disabled;
+	}
+	ret = (dss_prec_t)atomic_load_u(&dss_prec_default, ATOMIC_ACQUIRE);
+	return ret;
+}
+
+bool
+extent_dss_prec_set(dss_prec_t dss_prec) {
+	if (!have_dss) {
+		return (dss_prec != dss_prec_disabled);
+	}
+	atomic_store_u(&dss_prec_default, (unsigned)dss_prec, ATOMIC_RELEASE);
+	return false;
+}
+
+static void
+extent_dss_extending_start(void) {
+	spin_t spinner = SPIN_INITIALIZER;
+	while (true) {
+		bool expected = false;
+		if (atomic_compare_exchange_weak_b(&dss_extending, &expected,
+		    true, ATOMIC_ACQ_REL, ATOMIC_RELAXED)) {
+			break;
+		}
+		spin_adaptive(&spinner);
+	}
+}
+
+static void
+extent_dss_extending_finish(void) {
+	assert(atomic_load_b(&dss_extending, ATOMIC_RELAXED));
+
+	atomic_store_b(&dss_extending, false, ATOMIC_RELEASE);
+}
+
+static void *
+extent_dss_max_update(void *new_addr) {
+	/*
+	 * Get the current end of the DSS as max_cur and assure that dss_max is
+	 * up to date.
+	 */
+	void *max_cur = extent_dss_sbrk(0);
+	if (max_cur == (void *)-1) {
+		return NULL;
+	}
+	atomic_store_p(&dss_max, max_cur, ATOMIC_RELEASE);
+	/* Fixed new_addr can only be supported if it is at the edge of DSS. */
+	if (new_addr != NULL && max_cur != new_addr) {
+		return NULL;
+	}
+	return max_cur;
+}
+
+void *
+extent_alloc_dss(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size,
+    size_t alignment, bool *zero, bool *commit) {
+	extent_t *gap;
+
+	cassert(have_dss);
+	assert(size > 0);
+	assert(alignment > 0);
+
+	/*
+	 * sbrk() uses a signed increment argument, so take care not to
+	 * interpret a large allocation request as a negative increment.
+	 */
+	if ((intptr_t)size < 0) {
+		return NULL;
+	}
+
+	gap = extent_alloc(tsdn, arena);
+	if (gap == NULL) {
+		return NULL;
+	}
+
+	extent_dss_extending_start();
+	if (!atomic_load_b(&dss_exhausted, ATOMIC_ACQUIRE)) {
+		/*
+		 * The loop is necessary to recover from races with other
+		 * threads that are using the DSS for something other than
+		 * malloc.
+		 */
+		while (true) {
+			void *max_cur = extent_dss_max_update(new_addr);
+			if (max_cur == NULL) {
+				goto label_oom;
+			}
+
+			/*
+			 * Compute how much page-aligned gap space (if any) is
+			 * necessary to satisfy alignment.  This space can be
+			 * recycled for later use.
+			 */
+			void *gap_addr_page = (void *)(PAGE_CEILING(
+			    (uintptr_t)max_cur));
+			void *ret = (void *)ALIGNMENT_CEILING(
+			    (uintptr_t)gap_addr_page, alignment);
+			size_t gap_size_page = (uintptr_t)ret -
+			    (uintptr_t)gap_addr_page;
+			if (gap_size_page != 0) {
+				extent_init(gap, arena, gap_addr_page,
+				    gap_size_page, false, NSIZES,
+				    arena_extent_sn_next(arena),
+				    extent_state_active, false, true);
+			}
+			/*
+			 * Compute the address just past the end of the desired
+			 * allocation space.
+			 */
+			void *dss_next = (void *)((uintptr_t)ret + size);
+			if ((uintptr_t)ret < (uintptr_t)max_cur ||
+			    (uintptr_t)dss_next < (uintptr_t)max_cur) {
+				goto label_oom; /* Wrap-around. */
+			}
+			/* Compute the increment, including subpage bytes. */
+			void *gap_addr_subpage = max_cur;
+			size_t gap_size_subpage = (uintptr_t)ret -
+			    (uintptr_t)gap_addr_subpage;
+			intptr_t incr = gap_size_subpage + size;
+
+			assert((uintptr_t)max_cur + incr == (uintptr_t)ret +
+			    size);
+
+			/* Try to allocate. */
+			void *dss_prev = extent_dss_sbrk(incr);
+			if (dss_prev == max_cur) {
+				/* Success. */
+				atomic_store_p(&dss_max, dss_next,
+				    ATOMIC_RELEASE);
+				extent_dss_extending_finish();
+
+				if (gap_size_page != 0) {
+					extent_dalloc_gap(tsdn, arena, gap);
+				} else {
+					extent_dalloc(tsdn, arena, gap);
+				}
+				if (!*commit) {
+					*commit = pages_decommit(ret, size);
+				}
+				if (*zero && *commit) {
+					extent_hooks_t *extent_hooks =
+					    EXTENT_HOOKS_INITIALIZER;
+					extent_t extent;
+
+					extent_init(&extent, arena, ret, size,
+					    size, false, NSIZES,
+					    extent_state_active, false, true);
+					if (extent_purge_forced_wrapper(tsdn,
+					    arena, &extent_hooks, &extent, 0,
+					    size)) {
+						memset(ret, 0, size);
+					}
+				}
+				return ret;
+			}
+			/*
+			 * Failure, whether due to OOM or a race with a raw
+			 * sbrk() call from outside the allocator.
+			 */
+			if (dss_prev == (void *)-1) {
+				/* OOM. */
+				atomic_store_b(&dss_exhausted, true,
+				    ATOMIC_RELEASE);
+				goto label_oom;
+			}
+		}
+	}
+label_oom:
+	extent_dss_extending_finish();
+	extent_dalloc(tsdn, arena, gap);
+	return NULL;
+}
+
+static bool
+extent_in_dss_helper(void *addr, void *max) {
+	return ((uintptr_t)addr >= (uintptr_t)dss_base && (uintptr_t)addr <
+	    (uintptr_t)max);
+}
+
+bool
+extent_in_dss(void *addr) {
+	cassert(have_dss);
+
+	return extent_in_dss_helper(addr, atomic_load_p(&dss_max,
+	    ATOMIC_ACQUIRE));
+}
+
+bool
+extent_dss_mergeable(void *addr_a, void *addr_b) {
+	void *max;
+
+	cassert(have_dss);
+
+	if ((uintptr_t)addr_a < (uintptr_t)dss_base && (uintptr_t)addr_b <
+	    (uintptr_t)dss_base) {
+		return true;
+	}
+
+	max = atomic_load_p(&dss_max, ATOMIC_ACQUIRE);
+	return (extent_in_dss_helper(addr_a, max) ==
+	    extent_in_dss_helper(addr_b, max));
+}
+
+void
+extent_dss_boot(void) {
+	cassert(have_dss);
+
+	dss_base = extent_dss_sbrk(0);
+	atomic_store_b(&dss_extending, false, ATOMIC_RELAXED);
+	atomic_store_b(&dss_exhausted, dss_base == (void *)-1, ATOMIC_RELAXED);
+	atomic_store_p(&dss_max, dss_base, ATOMIC_RELAXED);
+}
+
+/******************************************************************************/
diff --git a/modules/worldengine/deps/jemalloc/src/extent_mmap.c b/modules/worldengine/deps/jemalloc/src/extent_mmap.c
new file mode 100644
index 0000000000..8d607dc803
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/extent_mmap.c
@@ -0,0 +1,42 @@
+#define JEMALLOC_EXTENT_MMAP_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_mmap.h"
+
+/******************************************************************************/
+/* Data. */
+
+bool	opt_retain =
+#ifdef JEMALLOC_RETAIN
+    true
+#else
+    false
+#endif
+    ;
+
+/******************************************************************************/
+
+void *
+extent_alloc_mmap(void *new_addr, size_t size, size_t alignment, bool *zero,
+    bool *commit) {
+	void *ret = pages_map(new_addr, size, ALIGNMENT_CEILING(alignment,
+	    PAGE), commit);
+	if (ret == NULL) {
+		return NULL;
+	}
+	assert(ret != NULL);
+	if (*commit) {
+		*zero = true;
+	}
+	return ret;
+}
+
+bool
+extent_dalloc_mmap(void *addr, size_t size) {
+	if (!opt_retain) {
+		pages_unmap(addr, size);
+	}
+	return opt_retain;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/hash.c b/modules/worldengine/deps/jemalloc/src/hash.c
index cfa4da0275..7b2bdc2bd6 100644
--- a/modules/worldengine/deps/jemalloc/src/hash.c
+++ b/modules/worldengine/deps/jemalloc/src/hash.c
@@ -1,2 +1,3 @@
-#define	JEMALLOC_HASH_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_HASH_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
diff --git a/modules/worldengine/deps/jemalloc/src/hooks.c b/modules/worldengine/deps/jemalloc/src/hooks.c
new file mode 100644
index 0000000000..6266ecd47f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/hooks.c
@@ -0,0 +1,12 @@
+#include "jemalloc/internal/jemalloc_preamble.h"
+
+/*
+ * The hooks are a little bit screwy -- they're not genuinely exported in the
+ * sense that we want them available to end-users, but we do want them visible
+ * from outside the generated library, so that we can use them in test code.
+ */
+JEMALLOC_EXPORT
+void (*hooks_arena_new_hook)() = NULL;
+
+JEMALLOC_EXPORT
+void (*hooks_libc_hook)() = NULL;
diff --git a/modules/worldengine/deps/jemalloc/src/jemalloc.c b/modules/worldengine/deps/jemalloc/src/jemalloc.c
index 204778bc89..0ee8ad48b9 100644
--- a/modules/worldengine/deps/jemalloc/src/jemalloc.c
+++ b/modules/worldengine/deps/jemalloc/src/jemalloc.c
@@ -1,15 +1,31 @@
-#define	JEMALLOC_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/ctl.h"
+#include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/jemalloc_internal_types.h"
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
+#include "jemalloc/internal/size_classes.h"
+#include "jemalloc/internal/spin.h"
+#include "jemalloc/internal/sz.h"
+#include "jemalloc/internal/ticker.h"
+#include "jemalloc/internal/util.h"
 
 /******************************************************************************/
 /* Data. */
 
-malloc_tsd_data(, arenas, arena_t *, NULL)
-malloc_tsd_data(, thread_allocated, thread_allocated_t,
-    THREAD_ALLOCATED_INITIALIZER)
-
 /* Runtime configuration options. */
-const char	*je_malloc_conf;
+const char	*je_malloc_conf
+#ifndef _WIN32
+    JEMALLOC_ATTR(weak)
+#endif
+    ;
 bool	opt_abort =
 #ifdef JEMALLOC_DEBUG
     true
@@ -17,30 +33,80 @@ bool	opt_abort =
     false
 #endif
     ;
-bool	opt_junk =
+bool	opt_abort_conf =
+#ifdef JEMALLOC_DEBUG
+    true
+#else
+    false
+#endif
+    ;
+const char	*opt_junk =
+#if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL))
+    "true"
+#else
+    "false"
+#endif
+    ;
+bool	opt_junk_alloc =
+#if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL))
+    true
+#else
+    false
+#endif
+    ;
+bool	opt_junk_free =
 #if (defined(JEMALLOC_DEBUG) && defined(JEMALLOC_FILL))
     true
 #else
     false
 #endif
     ;
-size_t	opt_quarantine = ZU(0);
-bool	opt_redzone = false;
+
 bool	opt_utrace = false;
-bool	opt_valgrind = false;
 bool	opt_xmalloc = false;
 bool	opt_zero = false;
-size_t	opt_narenas = 0;
+unsigned	opt_narenas = 0;
 
 unsigned	ncpus;
 
-malloc_mutex_t		arenas_lock;
-arena_t			**arenas;
-unsigned		narenas_total;
-unsigned		narenas_auto;
-
-/* Set to true once the allocator has been initialized. */
-static bool		malloc_initialized = false;
+/* Protects arenas initialization. */
+malloc_mutex_t arenas_lock;
+/*
+ * Arenas that are used to service external requests.  Not all elements of the
+ * arenas array are necessarily used; arenas are created lazily as needed.
+ *
+ * arenas[0..narenas_auto) are used for automatic multiplexing of threads and
+ * arenas.  arenas[narenas_auto..narenas_total) are only used if the application
+ * takes some action to create them and allocate from them.
+ *
+ * Points to an arena_t.
+ */
+JEMALLOC_ALIGNED(CACHELINE)
+atomic_p_t		arenas[MALLOCX_ARENA_LIMIT];
+static atomic_u_t	narenas_total; /* Use narenas_total_*(). */
+static arena_t		*a0; /* arenas[0]; read-only after initialization. */
+unsigned		narenas_auto; /* Read-only after initialization. */
+
+typedef enum {
+	malloc_init_uninitialized	= 3,
+	malloc_init_a0_initialized	= 2,
+	malloc_init_recursible		= 1,
+	malloc_init_initialized		= 0 /* Common case --> jnz. */
+} malloc_init_t;
+static malloc_init_t	malloc_init_state = malloc_init_uninitialized;
+
+/* False should be the common case.  Set to true to trigger initialization. */
+bool			malloc_slow = true;
+
+/* When malloc_slow is true, set the corresponding bits for sanity check. */
+enum {
+	flag_opt_junk_alloc	= (1U),
+	flag_opt_junk_free	= (1U << 1),
+	flag_opt_zero		= (1U << 2),
+	flag_opt_utrace		= (1U << 3),
+	flag_opt_xmalloc	= (1U << 4)
+};
+static uint8_t	malloc_slow_flags;
 
 #ifdef JEMALLOC_THREADED_INIT
 /* Used to let the initializing thread recursively allocate. */
@@ -57,14 +123,30 @@ static bool			malloc_initializer = NO_INITIALIZER;
 
 /* Used to avoid initialization races. */
 #ifdef _WIN32
+#if _WIN32_WINNT >= 0x0600
+static malloc_mutex_t	init_lock = SRWLOCK_INIT;
+#else
 static malloc_mutex_t	init_lock;
+static bool init_lock_initialized = false;
 
 JEMALLOC_ATTR(constructor)
 static void WINAPI
-_init_init_lock(void)
-{
-
-	malloc_mutex_init(&init_lock);
+_init_init_lock(void) {
+	/*
+	 * If another constructor in the same binary is using mallctl to e.g.
+	 * set up extent hooks, it may end up running before this one, and
+	 * malloc_init_hard will crash trying to lock the uninitialized lock. So
+	 * we force an initialization of the lock in malloc_init_hard as well.
+	 * We don't try to care about atomicity of the accessed to the
+	 * init_lock_initialized boolean, since it really only matters early in
+	 * the process creation, before any separate thread normally starts
+	 * doing anything.
+	 */
+	if (!init_lock_initialized) {
+		malloc_mutex_init(&init_lock, "init", WITNESS_RANK_INIT,
+		    malloc_mutex_rank_exclusive);
+	}
+	init_lock_initialized = true;
 }
 
 #ifdef _MSC_VER
@@ -72,7 +154,7 @@ _init_init_lock(void)
 JEMALLOC_SECTION(".CRT$XCU") JEMALLOC_ATTR(used)
 static const void (WINAPI *init_init_lock)(void) = _init_init_lock;
 #endif
-
+#endif
 #else
 static malloc_mutex_t	init_lock = MALLOC_MUTEX_INITIALIZER;
 #endif
@@ -85,7 +167,7 @@ typedef struct {
 
 #ifdef JEMALLOC_UTRACE
 #  define UTRACE(a, b, c) do {						\
-	if (opt_utrace) {						\
+	if (unlikely(opt_utrace)) {					\
 		int utrace_serrno = errno;				\
 		malloc_utrace_t ut;					\
 		ut.p = (a);						\
@@ -99,12 +181,16 @@ typedef struct {
 #  define UTRACE(a, b, c)
 #endif
 
+/* Whether encountered any invalid config options. */
+static bool had_conf_error = false;
+
 /******************************************************************************/
 /*
  * Function prototypes for static functions that are referenced prior to
  * definition.
  */
 
+static bool	malloc_init_hard_a0(void);
 static bool	malloc_init_hard(void);
 
 /******************************************************************************/
@@ -112,54 +198,337 @@ static bool	malloc_init_hard(void);
  * Begin miscellaneous support functions.
  */
 
+bool
+malloc_initialized(void) {
+	return (malloc_init_state == malloc_init_initialized);
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+malloc_init_a0(void) {
+	if (unlikely(malloc_init_state == malloc_init_uninitialized)) {
+		return malloc_init_hard_a0();
+	}
+	return false;
+}
+
+JEMALLOC_ALWAYS_INLINE bool
+malloc_init(void) {
+	if (unlikely(!malloc_initialized()) && malloc_init_hard()) {
+		return true;
+	}
+	return false;
+}
+
+/*
+ * The a0*() functions are used instead of i{d,}alloc() in situations that
+ * cannot tolerate TLS variable access.
+ */
+
+static void *
+a0ialloc(size_t size, bool zero, bool is_internal) {
+	if (unlikely(malloc_init_a0())) {
+		return NULL;
+	}
+
+	return iallocztm(TSDN_NULL, size, sz_size2index(size), zero, NULL,
+	    is_internal, arena_get(TSDN_NULL, 0, true), true);
+}
+
+static void
+a0idalloc(void *ptr, bool is_internal) {
+	idalloctm(TSDN_NULL, ptr, NULL, NULL, is_internal, true);
+}
+
+void *
+a0malloc(size_t size) {
+	return a0ialloc(size, false, true);
+}
+
+void
+a0dalloc(void *ptr) {
+	a0idalloc(ptr, true);
+}
+
+/*
+ * FreeBSD's libc uses the bootstrap_*() functions in bootstrap-senstive
+ * situations that cannot tolerate TLS variable access (TLS allocation and very
+ * early internal data structure initialization).
+ */
+
+void *
+bootstrap_malloc(size_t size) {
+	if (unlikely(size == 0)) {
+		size = 1;
+	}
+
+	return a0ialloc(size, false, false);
+}
+
+void *
+bootstrap_calloc(size_t num, size_t size) {
+	size_t num_size;
+
+	num_size = num * size;
+	if (unlikely(num_size == 0)) {
+		assert(num == 0 || size == 0);
+		num_size = 1;
+	}
+
+	return a0ialloc(num_size, true, false);
+}
+
+void
+bootstrap_free(void *ptr) {
+	if (unlikely(ptr == NULL)) {
+		return;
+	}
+
+	a0idalloc(ptr, false);
+}
+
+void
+arena_set(unsigned ind, arena_t *arena) {
+	atomic_store_p(&arenas[ind], arena, ATOMIC_RELEASE);
+}
+
+static void
+narenas_total_set(unsigned narenas) {
+	atomic_store_u(&narenas_total, narenas, ATOMIC_RELEASE);
+}
+
+static void
+narenas_total_inc(void) {
+	atomic_fetch_add_u(&narenas_total, 1, ATOMIC_RELEASE);
+}
+
+unsigned
+narenas_total_get(void) {
+	return atomic_load_u(&narenas_total, ATOMIC_ACQUIRE);
+}
+
 /* Create a new arena and insert it into the arenas array at index ind. */
+static arena_t *
+arena_init_locked(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) {
+	arena_t *arena;
+
+	assert(ind <= narenas_total_get());
+	if (ind >= MALLOCX_ARENA_LIMIT) {
+		return NULL;
+	}
+	if (ind == narenas_total_get()) {
+		narenas_total_inc();
+	}
+
+	/*
+	 * Another thread may have already initialized arenas[ind] if it's an
+	 * auto arena.
+	 */
+	arena = arena_get(tsdn, ind, false);
+	if (arena != NULL) {
+		assert(ind < narenas_auto);
+		return arena;
+	}
+
+	/* Actually initialize the arena. */
+	arena = arena_new(tsdn, ind, extent_hooks);
+
+	return arena;
+}
+
+static void
+arena_new_create_background_thread(tsdn_t *tsdn, unsigned ind) {
+	if (ind == 0) {
+		return;
+	}
+	if (have_background_thread) {
+		bool err;
+		malloc_mutex_lock(tsdn, &background_thread_lock);
+		err = background_thread_create(tsdn_tsd(tsdn), ind);
+		malloc_mutex_unlock(tsdn, &background_thread_lock);
+		if (err) {
+			malloc_printf("<jemalloc>: error in background thread "
+				      "creation for arena %u. Abort.\n", ind);
+			abort();
+		}
+	}
+}
+
 arena_t *
-arenas_extend(unsigned ind)
-{
-	arena_t *ret;
+arena_init(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks) {
+	arena_t *arena;
+
+	malloc_mutex_lock(tsdn, &arenas_lock);
+	arena = arena_init_locked(tsdn, ind, extent_hooks);
+	malloc_mutex_unlock(tsdn, &arenas_lock);
+
+	arena_new_create_background_thread(tsdn, ind);
+
+	return arena;
+}
+
+static void
+arena_bind(tsd_t *tsd, unsigned ind, bool internal) {
+	arena_t *arena = arena_get(tsd_tsdn(tsd), ind, false);
+	arena_nthreads_inc(arena, internal);
+
+	if (internal) {
+		tsd_iarena_set(tsd, arena);
+	} else {
+		tsd_arena_set(tsd, arena);
+	}
+}
 
-	ret = (arena_t *)base_alloc(sizeof(arena_t));
-	if (ret != NULL && arena_new(ret, ind) == false) {
-		arenas[ind] = ret;
-		return (ret);
+void
+arena_migrate(tsd_t *tsd, unsigned oldind, unsigned newind) {
+	arena_t *oldarena, *newarena;
+
+	oldarena = arena_get(tsd_tsdn(tsd), oldind, false);
+	newarena = arena_get(tsd_tsdn(tsd), newind, false);
+	arena_nthreads_dec(oldarena, false);
+	arena_nthreads_inc(newarena, false);
+	tsd_arena_set(tsd, newarena);
+}
+
+static void
+arena_unbind(tsd_t *tsd, unsigned ind, bool internal) {
+	arena_t *arena;
+
+	arena = arena_get(tsd_tsdn(tsd), ind, false);
+	arena_nthreads_dec(arena, internal);
+
+	if (internal) {
+		tsd_iarena_set(tsd, NULL);
+	} else {
+		tsd_arena_set(tsd, NULL);
 	}
-	/* Only reached if there is an OOM error. */
+}
+
+arena_tdata_t *
+arena_tdata_get_hard(tsd_t *tsd, unsigned ind) {
+	arena_tdata_t *tdata, *arenas_tdata_old;
+	arena_tdata_t *arenas_tdata = tsd_arenas_tdata_get(tsd);
+	unsigned narenas_tdata_old, i;
+	unsigned narenas_tdata = tsd_narenas_tdata_get(tsd);
+	unsigned narenas_actual = narenas_total_get();
 
 	/*
-	 * OOM here is quite inconvenient to propagate, since dealing with it
-	 * would require a check for failure in the fast path.  Instead, punt
-	 * by using arenas[0].  In practice, this is an extremely unlikely
-	 * failure.
+	 * Dissociate old tdata array (and set up for deallocation upon return)
+	 * if it's too small.
 	 */
-	malloc_write("<jemalloc>: Error initializing arena\n");
-	if (opt_abort)
-		abort();
+	if (arenas_tdata != NULL && narenas_tdata < narenas_actual) {
+		arenas_tdata_old = arenas_tdata;
+		narenas_tdata_old = narenas_tdata;
+		arenas_tdata = NULL;
+		narenas_tdata = 0;
+		tsd_arenas_tdata_set(tsd, arenas_tdata);
+		tsd_narenas_tdata_set(tsd, narenas_tdata);
+	} else {
+		arenas_tdata_old = NULL;
+		narenas_tdata_old = 0;
+	}
+
+	/* Allocate tdata array if it's missing. */
+	if (arenas_tdata == NULL) {
+		bool *arenas_tdata_bypassp = tsd_arenas_tdata_bypassp_get(tsd);
+		narenas_tdata = (ind < narenas_actual) ? narenas_actual : ind+1;
 
-	return (arenas[0]);
+		if (tsd_nominal(tsd) && !*arenas_tdata_bypassp) {
+			*arenas_tdata_bypassp = true;
+			arenas_tdata = (arena_tdata_t *)a0malloc(
+			    sizeof(arena_tdata_t) * narenas_tdata);
+			*arenas_tdata_bypassp = false;
+		}
+		if (arenas_tdata == NULL) {
+			tdata = NULL;
+			goto label_return;
+		}
+		assert(tsd_nominal(tsd) && !*arenas_tdata_bypassp);
+		tsd_arenas_tdata_set(tsd, arenas_tdata);
+		tsd_narenas_tdata_set(tsd, narenas_tdata);
+	}
+
+	/*
+	 * Copy to tdata array.  It's possible that the actual number of arenas
+	 * has increased since narenas_total_get() was called above, but that
+	 * causes no correctness issues unless two threads concurrently execute
+	 * the arenas.create mallctl, which we trust mallctl synchronization to
+	 * prevent.
+	 */
+
+	/* Copy/initialize tickers. */
+	for (i = 0; i < narenas_actual; i++) {
+		if (i < narenas_tdata_old) {
+			ticker_copy(&arenas_tdata[i].decay_ticker,
+			    &arenas_tdata_old[i].decay_ticker);
+		} else {
+			ticker_init(&arenas_tdata[i].decay_ticker,
+			    DECAY_NTICKS_PER_UPDATE);
+		}
+	}
+	if (narenas_tdata > narenas_actual) {
+		memset(&arenas_tdata[narenas_actual], 0, sizeof(arena_tdata_t)
+		    * (narenas_tdata - narenas_actual));
+	}
+
+	/* Read the refreshed tdata array. */
+	tdata = &arenas_tdata[ind];
+label_return:
+	if (arenas_tdata_old != NULL) {
+		a0dalloc(arenas_tdata_old);
+	}
+	return tdata;
 }
 
-/* Slow path, called only by choose_arena(). */
+/* Slow path, called only by arena_choose(). */
 arena_t *
-choose_arena_hard(void)
-{
-	arena_t *ret;
+arena_choose_hard(tsd_t *tsd, bool internal) {
+	arena_t *ret JEMALLOC_CC_SILENCE_INIT(NULL);
+
+	if (have_percpu_arena && PERCPU_ARENA_ENABLED(opt_percpu_arena)) {
+		unsigned choose = percpu_arena_choose();
+		ret = arena_get(tsd_tsdn(tsd), choose, true);
+		assert(ret != NULL);
+		arena_bind(tsd, arena_ind_get(ret), false);
+		arena_bind(tsd, arena_ind_get(ret), true);
+
+		return ret;
+	}
 
 	if (narenas_auto > 1) {
-		unsigned i, choose, first_null;
+		unsigned i, j, choose[2], first_null;
+		bool is_new_arena[2];
+
+		/*
+		 * Determine binding for both non-internal and internal
+		 * allocation.
+		 *
+		 *   choose[0]: For application allocation.
+		 *   choose[1]: For internal metadata allocation.
+		 */
+
+		for (j = 0; j < 2; j++) {
+			choose[j] = 0;
+			is_new_arena[j] = false;
+		}
 
-		choose = 0;
 		first_null = narenas_auto;
-		malloc_mutex_lock(&arenas_lock);
-		assert(arenas[0] != NULL);
+		malloc_mutex_lock(tsd_tsdn(tsd), &arenas_lock);
+		assert(arena_get(tsd_tsdn(tsd), 0, false) != NULL);
 		for (i = 1; i < narenas_auto; i++) {
-			if (arenas[i] != NULL) {
+			if (arena_get(tsd_tsdn(tsd), i, false) != NULL) {
 				/*
 				 * Choose the first arena that has the lowest
 				 * number of threads assigned to it.
 				 */
-				if (arenas[i]->nthreads <
-				    arenas[choose]->nthreads)
-					choose = i;
+				for (j = 0; j < 2; j++) {
+					if (arena_nthreads_get(arena_get(
+					    tsd_tsdn(tsd), i, false), !!j) <
+					    arena_nthreads_get(arena_get(
+					    tsd_tsdn(tsd), choose[j], false),
+					    !!j)) {
+						choose[j] = i;
+					}
+				}
 			} else if (first_null == narenas_auto) {
 				/*
 				 * Record the index of the first uninitialized
@@ -174,38 +543,99 @@ choose_arena_hard(void)
 			}
 		}
 
-		if (arenas[choose]->nthreads == 0
-		    || first_null == narenas_auto) {
-			/*
-			 * Use an unloaded arena, or the least loaded arena if
-			 * all arenas are already initialized.
-			 */
-			ret = arenas[choose];
-		} else {
-			/* Initialize a new arena. */
-			ret = arenas_extend(first_null);
+		for (j = 0; j < 2; j++) {
+			if (arena_nthreads_get(arena_get(tsd_tsdn(tsd),
+			    choose[j], false), !!j) == 0 || first_null ==
+			    narenas_auto) {
+				/*
+				 * Use an unloaded arena, or the least loaded
+				 * arena if all arenas are already initialized.
+				 */
+				if (!!j == internal) {
+					ret = arena_get(tsd_tsdn(tsd),
+					    choose[j], false);
+				}
+			} else {
+				arena_t *arena;
+
+				/* Initialize a new arena. */
+				choose[j] = first_null;
+				arena = arena_init_locked(tsd_tsdn(tsd),
+				    choose[j],
+				    (extent_hooks_t *)&extent_hooks_default);
+				if (arena == NULL) {
+					malloc_mutex_unlock(tsd_tsdn(tsd),
+					    &arenas_lock);
+					return NULL;
+				}
+				is_new_arena[j] = true;
+				if (!!j == internal) {
+					ret = arena;
+				}
+			}
+			arena_bind(tsd, choose[j], !!j);
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &arenas_lock);
+
+		for (j = 0; j < 2; j++) {
+			if (is_new_arena[j]) {
+				assert(choose[j] > 0);
+				arena_new_create_background_thread(
+				    tsd_tsdn(tsd), choose[j]);
+			}
 		}
-		ret->nthreads++;
-		malloc_mutex_unlock(&arenas_lock);
+
 	} else {
-		ret = arenas[0];
-		malloc_mutex_lock(&arenas_lock);
-		ret->nthreads++;
-		malloc_mutex_unlock(&arenas_lock);
+		ret = arena_get(tsd_tsdn(tsd), 0, false);
+		arena_bind(tsd, 0, false);
+		arena_bind(tsd, 0, true);
+	}
+
+	return ret;
+}
+
+void
+iarena_cleanup(tsd_t *tsd) {
+	arena_t *iarena;
+
+	iarena = tsd_iarena_get(tsd);
+	if (iarena != NULL) {
+		arena_unbind(tsd, arena_ind_get(iarena), true);
 	}
+}
 
-	arenas_tsd_set(&ret);
+void
+arena_cleanup(tsd_t *tsd) {
+	arena_t *arena;
 
-	return (ret);
+	arena = tsd_arena_get(tsd);
+	if (arena != NULL) {
+		arena_unbind(tsd, arena_ind_get(arena), false);
+	}
 }
 
-static void
-stats_print_atexit(void)
-{
+void
+arenas_tdata_cleanup(tsd_t *tsd) {
+	arena_tdata_t *arenas_tdata;
 
-	if (config_tcache && config_stats) {
+	/* Prevent tsd->arenas_tdata from being (re)created. */
+	*tsd_arenas_tdata_bypassp_get(tsd) = true;
+
+	arenas_tdata = tsd_arenas_tdata_get(tsd);
+	if (arenas_tdata != NULL) {
+		tsd_arenas_tdata_set(tsd, NULL);
+		a0dalloc(arenas_tdata);
+	}
+}
+
+static void
+stats_print_atexit(void) {
+	if (config_stats) {
+		tsdn_t *tsdn;
 		unsigned narenas, i;
 
+		tsdn = tsdn_fetch();
+
 		/*
 		 * Merge stats from extant threads.  This is racy, since
 		 * individual threads do not lock when recording tcache stats
@@ -214,25 +644,45 @@ stats_print_atexit(void)
 		 * continue to allocate.
 		 */
 		for (i = 0, narenas = narenas_total_get(); i < narenas; i++) {
-			arena_t *arena = arenas[i];
+			arena_t *arena = arena_get(tsdn, i, false);
 			if (arena != NULL) {
 				tcache_t *tcache;
 
-				/*
-				 * tcache_stats_merge() locks bins, so if any
-				 * code is introduced that acquires both arena
-				 * and bin locks in the opposite order,
-				 * deadlocks may result.
-				 */
-				malloc_mutex_lock(&arena->lock);
+				malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx);
 				ql_foreach(tcache, &arena->tcache_ql, link) {
-					tcache_stats_merge(tcache, arena);
+					tcache_stats_merge(tsdn, tcache, arena);
 				}
-				malloc_mutex_unlock(&arena->lock);
+				malloc_mutex_unlock(tsdn,
+				    &arena->tcache_ql_mtx);
 			}
 		}
 	}
-	je_malloc_stats_print(NULL, NULL, NULL);
+	je_malloc_stats_print(NULL, NULL, opt_stats_print_opts);
+}
+
+/*
+ * Ensure that we don't hold any locks upon entry to or exit from allocator
+ * code (in a "broad" sense that doesn't count a reentrant allocation as an
+ * entrance or exit).
+ */
+JEMALLOC_ALWAYS_INLINE void
+check_entry_exit_locking(tsdn_t *tsdn) {
+	if (!config_debug) {
+		return;
+	}
+	if (tsdn_null(tsdn)) {
+		return;
+	}
+	tsd_t *tsd = tsdn_tsd(tsdn);
+	/*
+	 * It's possible we hold locks at entry/exit if we're in a nested
+	 * allocation.
+	 */
+	int8_t reentrancy_level = tsd_reentrancy_level_get(tsd);
+	if (reentrancy_level != 0) {
+		return;
+	}
+	witness_assert_lockless(tsdn_witness_tsdp_get(tsdn));
 }
 
 /*
@@ -243,69 +693,82 @@ stats_print_atexit(void)
  * Begin initialization functions.
  */
 
+static char *
+jemalloc_secure_getenv(const char *name) {
+#ifdef JEMALLOC_HAVE_SECURE_GETENV
+	return secure_getenv(name);
+#else
+#  ifdef JEMALLOC_HAVE_ISSETUGID
+	if (issetugid() != 0) {
+		return NULL;
+	}
+#  endif
+	return getenv(name);
+#endif
+}
+
 static unsigned
-malloc_ncpus(void)
-{
+malloc_ncpus(void) {
 	long result;
 
 #ifdef _WIN32
 	SYSTEM_INFO si;
 	GetSystemInfo(&si);
 	result = si.dwNumberOfProcessors;
+#elif defined(JEMALLOC_GLIBC_MALLOC_HOOK) && defined(CPU_COUNT)
+	/*
+	 * glibc >= 2.6 has the CPU_COUNT macro.
+	 *
+	 * glibc's sysconf() uses isspace().  glibc allocates for the first time
+	 * *before* setting up the isspace tables.  Therefore we need a
+	 * different method to get the number of CPUs.
+	 */
+	{
+		cpu_set_t set;
+
+		pthread_getaffinity_np(pthread_self(), sizeof(set), &set);
+		result = CPU_COUNT(&set);
+	}
 #else
 	result = sysconf(_SC_NPROCESSORS_ONLN);
 #endif
 	return ((result == -1) ? 1 : (unsigned)result);
 }
 
-void
-arenas_cleanup(void *arg)
-{
-	arena_t *arena = *(arena_t **)arg;
-
-	malloc_mutex_lock(&arenas_lock);
-	arena->nthreads--;
-	malloc_mutex_unlock(&arenas_lock);
-}
-
-JEMALLOC_ALWAYS_INLINE_C void
-malloc_thread_init(void)
-{
-
-	/*
-	 * TSD initialization can't be safely done as a side effect of
-	 * deallocation, because it is possible for a thread to do nothing but
-	 * deallocate its TLS data via free(), in which case writing to TLS
-	 * would cause write-after-free memory corruption.  The quarantine
-	 * facility *only* gets used as a side effect of deallocation, so make
-	 * a best effort attempt at initializing its TSD by hooking all
-	 * allocation events.
-	 */
-	if (config_fill && opt_quarantine)
-		quarantine_alloc_hook();
-}
-
-JEMALLOC_ALWAYS_INLINE_C bool
-malloc_init(void)
-{
+static void
+init_opt_stats_print_opts(const char *v, size_t vlen) {
+	size_t opts_len = strlen(opt_stats_print_opts);
+	assert(opts_len <= stats_print_tot_num_options);
+
+	for (size_t i = 0; i < vlen; i++) {
+		switch (v[i]) {
+#define OPTION(o, v, d, s) case o: break;
+			STATS_PRINT_OPTIONS
+#undef OPTION
+		default: continue;
+		}
 
-	if (malloc_initialized == false && malloc_init_hard())
-		return (true);
-	malloc_thread_init();
+		if (strchr(opt_stats_print_opts, v[i]) != NULL) {
+			/* Ignore repeated. */
+			continue;
+		}
 
-	return (false);
+		opt_stats_print_opts[opts_len++] = v[i];
+		opt_stats_print_opts[opts_len] = '\0';
+		assert(opts_len <= stats_print_tot_num_options);
+	}
+	assert(opts_len == strlen(opt_stats_print_opts));
 }
 
 static bool
 malloc_conf_next(char const **opts_p, char const **k_p, size_t *klen_p,
-    char const **v_p, size_t *vlen_p)
-{
+    char const **v_p, size_t *vlen_p) {
 	bool accept;
 	const char *opts = *opts_p;
 
 	*k_p = opts;
 
-	for (accept = false; accept == false;) {
+	for (accept = false; !accept;) {
 		switch (*opts) {
 		case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
 		case 'G': case 'H': case 'I': case 'J': case 'K': case 'L':
@@ -333,14 +796,14 @@ malloc_conf_next(char const **opts_p, char const **k_p, size_t *klen_p,
 				malloc_write("<jemalloc>: Conf string ends "
 				    "with key\n");
 			}
-			return (true);
+			return true;
 		default:
 			malloc_write("<jemalloc>: Malformed conf string\n");
-			return (true);
+			return true;
 		}
 	}
 
-	for (accept = false; accept == false;) {
+	for (accept = false; !accept;) {
 		switch (*opts) {
 		case ',':
 			opts++;
@@ -369,46 +832,57 @@ malloc_conf_next(char const **opts_p, char const **k_p, size_t *klen_p,
 	}
 
 	*opts_p = opts;
-	return (false);
+	return false;
 }
 
 static void
-malloc_conf_error(const char *msg, const char *k, size_t klen, const char *v,
-    size_t vlen)
-{
+malloc_abort_invalid_conf(void) {
+	assert(opt_abort_conf);
+	malloc_printf("<jemalloc>: Abort (abort_conf:true) on invalid conf "
+	    "value (see above).\n");
+	abort();
+}
 
+static void
+malloc_conf_error(const char *msg, const char *k, size_t klen, const char *v,
+    size_t vlen) {
 	malloc_printf("<jemalloc>: %s: %.*s:%.*s\n", msg, (int)klen, k,
 	    (int)vlen, v);
+	had_conf_error = true;
+	if (opt_abort_conf) {
+		malloc_abort_invalid_conf();
+	}
 }
 
 static void
-malloc_conf_init(void)
-{
+malloc_slow_flag_init(void) {
+	/*
+	 * Combine the runtime options into malloc_slow for fast path.  Called
+	 * after processing all the options.
+	 */
+	malloc_slow_flags |= (opt_junk_alloc ? flag_opt_junk_alloc : 0)
+	    | (opt_junk_free ? flag_opt_junk_free : 0)
+	    | (opt_zero ? flag_opt_zero : 0)
+	    | (opt_utrace ? flag_opt_utrace : 0)
+	    | (opt_xmalloc ? flag_opt_xmalloc : 0);
+
+	malloc_slow = (malloc_slow_flags != 0);
+}
+
+static void
+malloc_conf_init(void) {
 	unsigned i;
 	char buf[PATH_MAX + 1];
 	const char *opts, *k, *v;
 	size_t klen, vlen;
 
-	/*
-	 * Automatically configure valgrind before processing options.  The
-	 * valgrind option remains in jemalloc 3.x for compatibility reasons.
-	 */
-	if (config_valgrind) {
-		opt_valgrind = (RUNNING_ON_VALGRIND != 0) ? true : false;
-		if (config_fill && opt_valgrind) {
-			opt_junk = false;
-			assert(opt_zero == false);
-			opt_quarantine = JEMALLOC_VALGRIND_QUARANTINE_DEFAULT;
-			opt_redzone = true;
-		}
-		if (config_tcache && opt_valgrind)
-			opt_tcache = false;
-	}
-
-	for (i = 0; i < 3; i++) {
+	for (i = 0; i < 4; i++) {
 		/* Get runtime configuration. */
 		switch (i) {
 		case 0:
+			opts = config_malloc_conf;
+			break;
+		case 1:
 			if (je_malloc_conf != NULL) {
 				/*
 				 * Use options that were compiled into the
@@ -421,8 +895,8 @@ malloc_conf_init(void)
 				opts = buf;
 			}
 			break;
-		case 1: {
-			int linklen = 0;
+		case 2: {
+			ssize_t linklen = 0;
 #ifndef _WIN32
 			int saved_errno = errno;
 			const char *linkname =
@@ -441,14 +915,14 @@ malloc_conf_init(void)
 			if (linklen == -1) {
 				/* No configuration specified. */
 				linklen = 0;
-				/* restore errno */
+				/* Restore errno. */
 				set_errno(saved_errno);
 			}
 #endif
 			buf[linklen] = '\0';
 			opts = buf;
 			break;
-		} case 2: {
+		} case 3: {
 			const char *envname =
 #ifdef JEMALLOC_PREFIX
 			    JEMALLOC_CPREFIX"MALLOC_CONF"
@@ -457,7 +931,7 @@ malloc_conf_init(void)
 #endif
 			    ;
 
-			if ((opts = getenv(envname)) != NULL) {
+			if ((opts = jemalloc_secure_getenv(envname)) != NULL) {
 				/*
 				 * Do nothing; opts is already initialized to
 				 * the value of the MALLOC_CONF environment
@@ -475,27 +949,31 @@ malloc_conf_init(void)
 			opts = buf;
 		}
 
-		while (*opts != '\0' && malloc_conf_next(&opts, &k, &klen, &v,
-		    &vlen) == false) {
-#define	CONF_HANDLE_BOOL(o, n)						\
-			if (sizeof(n)-1 == klen && strncmp(n, k,	\
-			    klen) == 0) {				\
-				if (strncmp("true", v, vlen) == 0 &&	\
-				    vlen == sizeof("true")-1)		\
+		while (*opts != '\0' && !malloc_conf_next(&opts, &k, &klen, &v,
+		    &vlen)) {
+#define CONF_MATCH(n)							\
+	(sizeof(n)-1 == klen && strncmp(n, k, klen) == 0)
+#define CONF_MATCH_VALUE(n)						\
+	(sizeof(n)-1 == vlen && strncmp(n, v, vlen) == 0)
+#define CONF_HANDLE_BOOL(o, n)						\
+			if (CONF_MATCH(n)) {				\
+				if (CONF_MATCH_VALUE("true")) {		\
 					o = true;			\
-				else if (strncmp("false", v, vlen) ==	\
-				    0 && vlen == sizeof("false")-1)	\
+				} else if (CONF_MATCH_VALUE("false")) {	\
 					o = false;			\
-				else {					\
+				} else {				\
 					malloc_conf_error(		\
 					    "Invalid conf value",	\
 					    k, klen, v, vlen);		\
 				}					\
 				continue;				\
 			}
-#define	CONF_HANDLE_SIZE_T(o, n, min, max, clip)			\
-			if (sizeof(n)-1 == klen && strncmp(n, k,	\
-			    klen) == 0) {				\
+#define CONF_MIN_no(um, min)	false
+#define CONF_MIN_yes(um, min)	((um) < (min))
+#define CONF_MAX_no(um, max)	false
+#define CONF_MAX_yes(um, max)	((um) > (max))
+#define CONF_HANDLE_T_U(t, o, n, min, max, check_min, check_max, clip)	\
+			if (CONF_MATCH(n)) {				\
 				uintmax_t um;				\
 				char *end;				\
 									\
@@ -507,27 +985,40 @@ malloc_conf_init(void)
 					    "Invalid conf value",	\
 					    k, klen, v, vlen);		\
 				} else if (clip) {			\
-					if (min != 0 && um < min)	\
-						o = min;		\
-					else if (um > max)		\
-						o = max;		\
-					else				\
-						o = um;			\
+					if (CONF_MIN_##check_min(um,	\
+					    (t)(min))) {		\
+						o = (t)(min);		\
+					} else if (			\
+					    CONF_MAX_##check_max(um,	\
+					    (t)(max))) {		\
+						o = (t)(max);		\
+					} else {			\
+						o = (t)um;		\
+					}				\
 				} else {				\
-					if ((min != 0 && um < min) ||	\
-					    um > max) {			\
+					if (CONF_MIN_##check_min(um,	\
+					    (t)(min)) ||		\
+					    CONF_MAX_##check_max(um,	\
+					    (t)(max))) {		\
 						malloc_conf_error(	\
 						    "Out-of-range "	\
 						    "conf value",	\
 						    k, klen, v, vlen);	\
-					} else				\
-						o = um;			\
+					} else {			\
+						o = (t)um;		\
+					}				\
 				}					\
 				continue;				\
 			}
-#define	CONF_HANDLE_SSIZE_T(o, n, min, max)				\
-			if (sizeof(n)-1 == klen && strncmp(n, k,	\
-			    klen) == 0) {				\
+#define CONF_HANDLE_UNSIGNED(o, n, min, max, check_min, check_max,	\
+    clip)								\
+			CONF_HANDLE_T_U(unsigned, o, n, min, max,	\
+			    check_min, check_max, clip)
+#define CONF_HANDLE_SIZE_T(o, n, min, max, check_min, check_max, clip)	\
+			CONF_HANDLE_T_U(size_t, o, n, min, max,		\
+			    check_min, check_max, clip)
+#define CONF_HANDLE_SSIZE_T(o, n, min, max)				\
+			if (CONF_MATCH(n)) {				\
 				long l;					\
 				char *end;				\
 									\
@@ -538,18 +1029,18 @@ malloc_conf_init(void)
 					malloc_conf_error(		\
 					    "Invalid conf value",	\
 					    k, klen, v, vlen);		\
-				} else if (l < (ssize_t)min || l >	\
-				    (ssize_t)max) {			\
+				} else if (l < (ssize_t)(min) || l >	\
+				    (ssize_t)(max)) {			\
 					malloc_conf_error(		\
 					    "Out-of-range conf value",	\
 					    k, klen, v, vlen);		\
-				} else					\
+				} else {				\
 					o = l;				\
+				}					\
 				continue;				\
 			}
-#define	CONF_HANDLE_CHAR_P(o, n, d)					\
-			if (sizeof(n)-1 == klen && strncmp(n, k,	\
-			    klen) == 0) {				\
+#define CONF_HANDLE_CHAR_P(o, n, d)					\
+			if (CONF_MATCH(n)) {				\
 				size_t cpylen = (vlen <=		\
 				    sizeof(o)-1) ? vlen :		\
 				    sizeof(o)-1;			\
@@ -559,23 +1050,18 @@ malloc_conf_init(void)
 			}
 
 			CONF_HANDLE_BOOL(opt_abort, "abort")
-			/*
-			 * Chunks always require at least one header page, plus
-			 * one data page in the absence of redzones, or three
-			 * pages in the presence of redzones.  In order to
-			 * simplify options processing, fix the limit based on
-			 * config_fill.
-			 */
-			CONF_HANDLE_SIZE_T(opt_lg_chunk, "lg_chunk", LG_PAGE +
-			    (config_fill ? 2 : 1), (sizeof(size_t) << 3) - 1,
-			    true)
+			CONF_HANDLE_BOOL(opt_abort_conf, "abort_conf")
+			if (opt_abort_conf && had_conf_error) {
+				malloc_abort_invalid_conf();
+			}
+			CONF_HANDLE_BOOL(opt_retain, "retain")
 			if (strncmp("dss", k, klen) == 0) {
 				int i;
 				bool match = false;
 				for (i = 0; i < dss_prec_limit; i++) {
 					if (strncmp(dss_prec_names[i], v, vlen)
 					    == 0) {
-						if (chunk_dss_prec_set(i)) {
+						if (extent_dss_prec_set(i)) {
 							malloc_conf_error(
 							    "Error setting dss",
 							    k, klen, v, vlen);
@@ -587,47 +1073,98 @@ malloc_conf_init(void)
 						}
 					}
 				}
-				if (match == false) {
+				if (!match) {
 					malloc_conf_error("Invalid conf value",
 					    k, klen, v, vlen);
 				}
 				continue;
 			}
-			CONF_HANDLE_SIZE_T(opt_narenas, "narenas", 1,
-			    SIZE_T_MAX, false)
-			CONF_HANDLE_SSIZE_T(opt_lg_dirty_mult, "lg_dirty_mult",
-			    -1, (sizeof(size_t) << 3) - 1)
+			CONF_HANDLE_UNSIGNED(opt_narenas, "narenas", 1,
+			    UINT_MAX, yes, no, false)
+			CONF_HANDLE_SSIZE_T(opt_dirty_decay_ms,
+			    "dirty_decay_ms", -1, NSTIME_SEC_MAX * KQU(1000) <
+			    QU(SSIZE_MAX) ? NSTIME_SEC_MAX * KQU(1000) :
+			    SSIZE_MAX);
+			CONF_HANDLE_SSIZE_T(opt_muzzy_decay_ms,
+			    "muzzy_decay_ms", -1, NSTIME_SEC_MAX * KQU(1000) <
+			    QU(SSIZE_MAX) ? NSTIME_SEC_MAX * KQU(1000) :
+			    SSIZE_MAX);
 			CONF_HANDLE_BOOL(opt_stats_print, "stats_print")
+			if (CONF_MATCH("stats_print_opts")) {
+				init_opt_stats_print_opts(v, vlen);
+				continue;
+			}
 			if (config_fill) {
-				CONF_HANDLE_BOOL(opt_junk, "junk")
-				CONF_HANDLE_SIZE_T(opt_quarantine, "quarantine",
-				    0, SIZE_T_MAX, false)
-				CONF_HANDLE_BOOL(opt_redzone, "redzone")
+				if (CONF_MATCH("junk")) {
+					if (CONF_MATCH_VALUE("true")) {
+						opt_junk = "true";
+						opt_junk_alloc = opt_junk_free =
+						    true;
+					} else if (CONF_MATCH_VALUE("false")) {
+						opt_junk = "false";
+						opt_junk_alloc = opt_junk_free =
+						    false;
+					} else if (CONF_MATCH_VALUE("alloc")) {
+						opt_junk = "alloc";
+						opt_junk_alloc = true;
+						opt_junk_free = false;
+					} else if (CONF_MATCH_VALUE("free")) {
+						opt_junk = "free";
+						opt_junk_alloc = false;
+						opt_junk_free = true;
+					} else {
+						malloc_conf_error(
+						    "Invalid conf value", k,
+						    klen, v, vlen);
+					}
+					continue;
+				}
 				CONF_HANDLE_BOOL(opt_zero, "zero")
 			}
 			if (config_utrace) {
 				CONF_HANDLE_BOOL(opt_utrace, "utrace")
 			}
-			if (config_valgrind) {
-				CONF_HANDLE_BOOL(opt_valgrind, "valgrind")
-			}
 			if (config_xmalloc) {
 				CONF_HANDLE_BOOL(opt_xmalloc, "xmalloc")
 			}
-			if (config_tcache) {
-				CONF_HANDLE_BOOL(opt_tcache, "tcache")
-				CONF_HANDLE_SSIZE_T(opt_lg_tcache_max,
-				    "lg_tcache_max", -1,
-				    (sizeof(size_t) << 3) - 1)
+			CONF_HANDLE_BOOL(opt_tcache, "tcache")
+			CONF_HANDLE_SSIZE_T(opt_lg_tcache_max, "lg_tcache_max",
+			    -1, (sizeof(size_t) << 3) - 1)
+			if (strncmp("percpu_arena", k, klen) == 0) {
+				int i;
+				bool match = false;
+				for (i = percpu_arena_mode_names_base; i <
+				    percpu_arena_mode_names_limit; i++) {
+					if (strncmp(percpu_arena_mode_names[i],
+					    v, vlen) == 0) {
+						if (!have_percpu_arena) {
+							malloc_conf_error(
+							    "No getcpu support",
+							    k, klen, v, vlen);
+						}
+						opt_percpu_arena = i;
+						match = true;
+						break;
+					}
+				}
+				if (!match) {
+					malloc_conf_error("Invalid conf value",
+					    k, klen, v, vlen);
+				}
+				continue;
 			}
+			CONF_HANDLE_BOOL(opt_background_thread,
+			    "background_thread");
 			if (config_prof) {
 				CONF_HANDLE_BOOL(opt_prof, "prof")
 				CONF_HANDLE_CHAR_P(opt_prof_prefix,
 				    "prof_prefix", "jeprof")
 				CONF_HANDLE_BOOL(opt_prof_active, "prof_active")
-				CONF_HANDLE_SSIZE_T(opt_lg_prof_sample,
-				    "lg_prof_sample", 0,
-				    (sizeof(uint64_t) << 3) - 1)
+				CONF_HANDLE_BOOL(opt_prof_thread_active_init,
+				    "prof_thread_active_init")
+				CONF_HANDLE_SIZE_T(opt_lg_prof_sample,
+				    "lg_prof_sample", 0, (sizeof(uint64_t) << 3)
+				    - 1, no, yes, true)
 				CONF_HANDLE_BOOL(opt_prof_accum, "prof_accum")
 				CONF_HANDLE_SSIZE_T(opt_lg_prof_interval,
 				    "lg_prof_interval", -1,
@@ -638,7 +1175,15 @@ malloc_conf_init(void)
 			}
 			malloc_conf_error("Invalid conf pair", k, klen, v,
 			    vlen);
+#undef CONF_MATCH
+#undef CONF_MATCH_VALUE
 #undef CONF_HANDLE_BOOL
+#undef CONF_MIN_no
+#undef CONF_MIN_yes
+#undef CONF_MAX_no
+#undef CONF_MAX_yes
+#undef CONF_HANDLE_T_U
+#undef CONF_HANDLE_UNSIGNED
 #undef CONF_HANDLE_SIZE_T
 #undef CONF_HANDLE_SSIZE_T
 #undef CONF_HANDLE_CHAR_P
@@ -647,195 +1192,325 @@ malloc_conf_init(void)
 }
 
 static bool
-malloc_init_hard(void)
-{
-	arena_t *init_arenas[1];
-
-	malloc_mutex_lock(&init_lock);
-	if (malloc_initialized || IS_INITIALIZER) {
+malloc_init_hard_needed(void) {
+	if (malloc_initialized() || (IS_INITIALIZER && malloc_init_state ==
+	    malloc_init_recursible)) {
 		/*
 		 * Another thread initialized the allocator before this one
 		 * acquired init_lock, or this thread is the initializing
 		 * thread, and it is recursively allocating.
 		 */
-		malloc_mutex_unlock(&init_lock);
-		return (false);
+		return false;
 	}
 #ifdef JEMALLOC_THREADED_INIT
-	if (malloc_initializer != NO_INITIALIZER && IS_INITIALIZER == false) {
+	if (malloc_initializer != NO_INITIALIZER && !IS_INITIALIZER) {
 		/* Busy-wait until the initializing thread completes. */
+		spin_t spinner = SPIN_INITIALIZER;
 		do {
-			malloc_mutex_unlock(&init_lock);
-			CPU_SPINWAIT;
-			malloc_mutex_lock(&init_lock);
-		} while (malloc_initialized == false);
-		malloc_mutex_unlock(&init_lock);
-		return (false);
+			malloc_mutex_unlock(TSDN_NULL, &init_lock);
+			spin_adaptive(&spinner);
+			malloc_mutex_lock(TSDN_NULL, &init_lock);
+		} while (!malloc_initialized());
+		return false;
 	}
 #endif
+	return true;
+}
+
+static bool
+malloc_init_hard_a0_locked() {
 	malloc_initializer = INITIALIZER;
 
-	malloc_tsd_boot();
-	if (config_prof)
+	if (config_prof) {
 		prof_boot0();
-
+	}
 	malloc_conf_init();
-
 	if (opt_stats_print) {
 		/* Print statistics at exit. */
 		if (atexit(stats_print_atexit) != 0) {
 			malloc_write("<jemalloc>: Error in atexit()\n");
-			if (opt_abort)
+			if (opt_abort) {
 				abort();
+			}
 		}
 	}
-
-	if (base_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	if (pages_boot()) {
+		return true;
 	}
-
-	if (chunk_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	if (base_boot(TSDN_NULL)) {
+		return true;
+	}
+	if (extent_boot()) {
+		return true;
 	}
-
 	if (ctl_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+		return true;
 	}
-
-	if (config_prof)
+	if (config_prof) {
 		prof_boot1();
-
-	arena_boot();
-
-	if (config_tcache && tcache_boot0()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
 	}
-
-	if (huge_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	arena_boot();
+	if (tcache_boot(TSDN_NULL)) {
+		return true;
 	}
-
-	if (malloc_mutex_init(&arenas_lock)) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	if (malloc_mutex_init(&arenas_lock, "arenas", WITNESS_RANK_ARENAS,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
 	}
-
 	/*
 	 * Create enough scaffolding to allow recursive allocation in
 	 * malloc_ncpus().
 	 */
-	narenas_total = narenas_auto = 1;
-	arenas = init_arenas;
+	narenas_auto = 1;
 	memset(arenas, 0, sizeof(arena_t *) * narenas_auto);
-
 	/*
 	 * Initialize one arena here.  The rest are lazily created in
-	 * choose_arena_hard().
+	 * arena_choose_hard().
 	 */
-	arenas_extend(0);
-	if (arenas[0] == NULL) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
-	}
-
-	/* Initialize allocation counters before any allocations can occur. */
-	if (config_stats && thread_allocated_tsd_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	if (arena_init(TSDN_NULL, 0, (extent_hooks_t *)&extent_hooks_default)
+	    == NULL) {
+		return true;
 	}
+	a0 = arena_get(TSDN_NULL, 0, false);
+	malloc_init_state = malloc_init_a0_initialized;
 
-	if (arenas_tsd_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
-	}
-
-	if (config_tcache && tcache_boot1()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
-	}
+	return false;
+}
 
-	if (config_fill && quarantine_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
-	}
+static bool
+malloc_init_hard_a0(void) {
+	bool ret;
 
-	if (config_prof && prof_boot2()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
-	}
+	malloc_mutex_lock(TSDN_NULL, &init_lock);
+	ret = malloc_init_hard_a0_locked();
+	malloc_mutex_unlock(TSDN_NULL, &init_lock);
+	return ret;
+}
 
-	malloc_mutex_unlock(&init_lock);
-	/**********************************************************************/
-	/* Recursive allocation may follow. */
+/* Initialize data structures which may trigger recursive allocation. */
+static bool
+malloc_init_hard_recursible(void) {
+	malloc_init_state = malloc_init_recursible;
 
 	ncpus = malloc_ncpus();
 
-#if (!defined(JEMALLOC_MUTEX_INIT_CB) && !defined(JEMALLOC_ZONE) \
-    && !defined(_WIN32))
-	/* LinuxThreads's pthread_atfork() allocates. */
+#if (defined(JEMALLOC_HAVE_PTHREAD_ATFORK) && !defined(JEMALLOC_MUTEX_INIT_CB) \
+    && !defined(JEMALLOC_ZONE) && !defined(_WIN32) && \
+    !defined(__native_client__))
+	/* LinuxThreads' pthread_atfork() allocates. */
 	if (pthread_atfork(jemalloc_prefork, jemalloc_postfork_parent,
 	    jemalloc_postfork_child) != 0) {
 		malloc_write("<jemalloc>: Error in pthread_atfork()\n");
-		if (opt_abort)
+		if (opt_abort) {
 			abort();
+		}
+		return true;
 	}
 #endif
 
-	/* Done recursively allocating. */
-	/**********************************************************************/
-	malloc_mutex_lock(&init_lock);
+	if (background_thread_boot0()) {
+		return true;
+	}
+
+	return false;
+}
+
+static unsigned
+malloc_narenas_default(void) {
+	assert(ncpus > 0);
+	/*
+	 * For SMP systems, create more than one arena per CPU by
+	 * default.
+	 */
+	if (ncpus > 1) {
+		return ncpus << 2;
+	} else {
+		return 1;
+	}
+}
+
+static percpu_arena_mode_t
+percpu_arena_as_initialized(percpu_arena_mode_t mode) {
+	assert(!malloc_initialized());
+	assert(mode <= percpu_arena_disabled);
 
-	if (mutex_boot()) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	if (mode != percpu_arena_disabled) {
+		mode += percpu_arena_mode_enabled_base;
 	}
 
+	return mode;
+}
+
+static bool
+malloc_init_narenas(void) {
+	assert(ncpus > 0);
+
+	if (opt_percpu_arena != percpu_arena_disabled) {
+		if (!have_percpu_arena || malloc_getcpu() < 0) {
+			opt_percpu_arena = percpu_arena_disabled;
+			malloc_printf("<jemalloc>: perCPU arena getcpu() not "
+			    "available. Setting narenas to %u.\n", opt_narenas ?
+			    opt_narenas : malloc_narenas_default());
+			if (opt_abort) {
+				abort();
+			}
+		} else {
+			if (ncpus >= MALLOCX_ARENA_LIMIT) {
+				malloc_printf("<jemalloc>: narenas w/ percpu"
+				    "arena beyond limit (%d)\n", ncpus);
+				if (opt_abort) {
+					abort();
+				}
+				return true;
+			}
+			/* NB: opt_percpu_arena isn't fully initialized yet. */
+			if (percpu_arena_as_initialized(opt_percpu_arena) ==
+			    per_phycpu_arena && ncpus % 2 != 0) {
+				malloc_printf("<jemalloc>: invalid "
+				    "configuration -- per physical CPU arena "
+				    "with odd number (%u) of CPUs (no hyper "
+				    "threading?).\n", ncpus);
+				if (opt_abort)
+					abort();
+			}
+			unsigned n = percpu_arena_ind_limit(
+			    percpu_arena_as_initialized(opt_percpu_arena));
+			if (opt_narenas < n) {
+				/*
+				 * If narenas is specified with percpu_arena
+				 * enabled, actual narenas is set as the greater
+				 * of the two. percpu_arena_choose will be free
+				 * to use any of the arenas based on CPU
+				 * id. This is conservative (at a small cost)
+				 * but ensures correctness.
+				 *
+				 * If for some reason the ncpus determined at
+				 * boot is not the actual number (e.g. because
+				 * of affinity setting from numactl), reserving
+				 * narenas this way provides a workaround for
+				 * percpu_arena.
+				 */
+				opt_narenas = n;
+			}
+		}
+	}
 	if (opt_narenas == 0) {
-		/*
-		 * For SMP systems, create more than one arena per CPU by
-		 * default.
-		 */
-		if (ncpus > 1)
-			opt_narenas = ncpus << 2;
-		else
-			opt_narenas = 1;
+		opt_narenas = malloc_narenas_default();
 	}
+	assert(opt_narenas > 0);
+
 	narenas_auto = opt_narenas;
 	/*
-	 * Make sure that the arenas array can be allocated.  In practice, this
-	 * limit is enough to allow the allocator to function, but the ctl
-	 * machinery will fail to allocate memory at far lower limits.
+	 * Limit the number of arenas to the indexing range of MALLOCX_ARENA().
 	 */
-	if (narenas_auto > chunksize / sizeof(arena_t *)) {
-		narenas_auto = chunksize / sizeof(arena_t *);
+	if (narenas_auto >= MALLOCX_ARENA_LIMIT) {
+		narenas_auto = MALLOCX_ARENA_LIMIT - 1;
 		malloc_printf("<jemalloc>: Reducing narenas to limit (%d)\n",
 		    narenas_auto);
 	}
-	narenas_total = narenas_auto;
+	narenas_total_set(narenas_auto);
 
-	/* Allocate and initialize arenas. */
-	arenas = (arena_t **)base_alloc(sizeof(arena_t *) * narenas_total);
-	if (arenas == NULL) {
-		malloc_mutex_unlock(&init_lock);
-		return (true);
+	return false;
+}
+
+static void
+malloc_init_percpu(void) {
+	opt_percpu_arena = percpu_arena_as_initialized(opt_percpu_arena);
+}
+
+static bool
+malloc_init_hard_finish(void) {
+	if (malloc_mutex_boot()) {
+		return true;
+	}
+
+	malloc_init_state = malloc_init_initialized;
+	malloc_slow_flag_init();
+
+	return false;
+}
+
+static void
+malloc_init_hard_cleanup(tsdn_t *tsdn, bool reentrancy_set) {
+	malloc_mutex_assert_owner(tsdn, &init_lock);
+	malloc_mutex_unlock(tsdn, &init_lock);
+	if (reentrancy_set) {
+		assert(!tsdn_null(tsdn));
+		tsd_t *tsd = tsdn_tsd(tsdn);
+		assert(tsd_reentrancy_level_get(tsd) > 0);
+		post_reentrancy(tsd);
+	}
+}
+
+static bool
+malloc_init_hard(void) {
+	tsd_t *tsd;
+
+#if defined(_WIN32) && _WIN32_WINNT < 0x0600
+	_init_init_lock();
+#endif
+	malloc_mutex_lock(TSDN_NULL, &init_lock);
+
+#define UNLOCK_RETURN(tsdn, ret, reentrancy)		\
+	malloc_init_hard_cleanup(tsdn, reentrancy);	\
+	return ret;
+
+	if (!malloc_init_hard_needed()) {
+		UNLOCK_RETURN(TSDN_NULL, false, false)
+	}
+
+	if (malloc_init_state != malloc_init_a0_initialized &&
+	    malloc_init_hard_a0_locked()) {
+		UNLOCK_RETURN(TSDN_NULL, true, false)
+	}
+
+	malloc_mutex_unlock(TSDN_NULL, &init_lock);
+	/* Recursive allocation relies on functional tsd. */
+	tsd = malloc_tsd_boot0();
+	if (tsd == NULL) {
+		return true;
+	}
+	if (malloc_init_hard_recursible()) {
+		return true;
+	}
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &init_lock);
+	/* Set reentrancy level to 1 during init. */
+	pre_reentrancy(tsd, NULL);
+	/* Initialize narenas before prof_boot2 (for allocation). */
+	if (malloc_init_narenas() || background_thread_boot1(tsd_tsdn(tsd))) {
+		UNLOCK_RETURN(tsd_tsdn(tsd), true, true)
+	}
+	if (config_prof && prof_boot2(tsd)) {
+		UNLOCK_RETURN(tsd_tsdn(tsd), true, true)
 	}
-	/*
-	 * Zero the array.  In practice, this should always be pre-zeroed,
-	 * since it was just mmap()ed, but let's be sure.
-	 */
-	memset(arenas, 0, sizeof(arena_t *) * narenas_total);
-	/* Copy the pointer to the one arena that was already initialized. */
-	arenas[0] = init_arenas[0];
 
-	malloc_initialized = true;
-	malloc_mutex_unlock(&init_lock);
+	malloc_init_percpu();
 
-	return (false);
+	if (malloc_init_hard_finish()) {
+		UNLOCK_RETURN(tsd_tsdn(tsd), true, true)
+	}
+	post_reentrancy(tsd);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &init_lock);
+
+	malloc_tsd_boot1();
+	/* Update TSD after tsd_boot1. */
+	tsd = tsd_fetch();
+	if (opt_background_thread) {
+		assert(have_background_thread);
+		/*
+		 * Need to finish init & unlock first before creating background
+		 * threads (pthread_create depends on malloc).
+		 */
+		malloc_mutex_lock(tsd_tsdn(tsd), &background_thread_lock);
+		bool err = background_thread_create(tsd, 0);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &background_thread_lock);
+		if (err) {
+			return true;
+		}
+	}
+#undef UNLOCK_RETURN
+	return false;
 }
 
 /*
@@ -843,469 +1518,779 @@ malloc_init_hard(void)
  */
 /******************************************************************************/
 /*
- * Begin malloc(3)-compatible functions.
+ * Begin allocation-path internal functions and data structures.
  */
 
-static void *
-imalloc_prof_sample(size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
-
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		p = imalloc(SMALL_MAXCLASS+1);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
-	} else
-		p = imalloc(usize);
+/*
+ * Settings determined by the documented behavior of the allocation functions.
+ */
+typedef struct static_opts_s static_opts_t;
+struct static_opts_s {
+	/* Whether or not allocation size may overflow. */
+	bool may_overflow;
+	/* Whether or not allocations of size 0 should be treated as size 1. */
+	bool bump_empty_alloc;
+	/*
+	 * Whether to assert that allocations are not of size 0 (after any
+	 * bumping).
+	 */
+	bool assert_nonempty_alloc;
 
-	return (p);
-}
+	/*
+	 * Whether or not to modify the 'result' argument to malloc in case of
+	 * error.
+	 */
+	bool null_out_result_on_error;
+	/* Whether to set errno when we encounter an error condition. */
+	bool set_errno_on_error;
 
-JEMALLOC_ALWAYS_INLINE_C void *
-imalloc_prof(size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
+	/*
+	 * The minimum valid alignment for functions requesting aligned storage.
+	 */
+	size_t min_alignment;
 
-	if ((uintptr_t)cnt != (uintptr_t)1U)
-		p = imalloc_prof_sample(usize, cnt);
-	else
-		p = imalloc(usize);
-	if (p == NULL)
-		return (NULL);
-	prof_malloc(p, usize, cnt);
+	/* The error string to use if we oom. */
+	const char *oom_string;
+	/* The error string to use if the passed-in alignment is invalid. */
+	const char *invalid_alignment_string;
 
-	return (p);
+	/*
+	 * False if we're configured to skip some time-consuming operations.
+	 *
+	 * This isn't really a malloc "behavior", but it acts as a useful
+	 * summary of several other static (or at least, static after program
+	 * initialization) options.
+	 */
+	bool slow;
+};
+
+JEMALLOC_ALWAYS_INLINE void
+static_opts_init(static_opts_t *static_opts) {
+	static_opts->may_overflow = false;
+	static_opts->bump_empty_alloc = false;
+	static_opts->assert_nonempty_alloc = false;
+	static_opts->null_out_result_on_error = false;
+	static_opts->set_errno_on_error = false;
+	static_opts->min_alignment = 0;
+	static_opts->oom_string = "";
+	static_opts->invalid_alignment_string = "";
+	static_opts->slow = false;
 }
 
 /*
- * MALLOC_BODY() is a macro rather than a function because its contents are in
- * the fast path, but inlining would cause reliability issues when determining
- * how many frames to discard from heap profiling backtraces.
+ * These correspond to the macros in jemalloc/jemalloc_macros.h.  Broadly, we
+ * should have one constant here per magic value there.  Note however that the
+ * representations need not be related.
  */
-#define	MALLOC_BODY(ret, size, usize) do {				\
-	if (malloc_init())						\
-		ret = NULL;						\
-	else {								\
-		if (config_prof && opt_prof) {				\
-			prof_thr_cnt_t *cnt;				\
-									\
-			usize = s2u(size);				\
-			/*						\
-			 * Call PROF_ALLOC_PREP() here rather than in	\
-			 * imalloc_prof() so that imalloc_prof() can be	\
-			 * inlined without introducing uncertainty	\
-			 * about the number of backtrace frames to	\
-			 * ignore.  imalloc_prof() is in the fast path	\
-			 * when heap profiling is enabled, so inlining	\
-			 * is critical to performance.  (For		\
-			 * consistency all callers of PROF_ALLOC_PREP()	\
-			 * are structured similarly, even though e.g.	\
-			 * realloc() isn't called enough for inlining	\
-			 * to be critical.)				\
-			 */						\
-			PROF_ALLOC_PREP(1, usize, cnt);			\
-			ret = imalloc_prof(usize, cnt);			\
-		} else {						\
-			if (config_stats || (config_valgrind &&		\
-			    opt_valgrind))				\
-				usize = s2u(size);			\
-			ret = imalloc(size);				\
-		}							\
-	}								\
-} while (0)
-
-void *
-je_malloc(size_t size)
-{
-	void *ret;
-	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
-
-	if (size == 0)
-		size = 1;
+#define TCACHE_IND_NONE ((unsigned)-1)
+#define TCACHE_IND_AUTOMATIC ((unsigned)-2)
+#define ARENA_IND_AUTOMATIC ((unsigned)-1)
+
+typedef struct dynamic_opts_s dynamic_opts_t;
+struct dynamic_opts_s {
+	void **result;
+	size_t num_items;
+	size_t item_size;
+	size_t alignment;
+	bool zero;
+	unsigned tcache_ind;
+	unsigned arena_ind;
+};
+
+JEMALLOC_ALWAYS_INLINE void
+dynamic_opts_init(dynamic_opts_t *dynamic_opts) {
+	dynamic_opts->result = NULL;
+	dynamic_opts->num_items = 0;
+	dynamic_opts->item_size = 0;
+	dynamic_opts->alignment = 0;
+	dynamic_opts->zero = false;
+	dynamic_opts->tcache_ind = TCACHE_IND_AUTOMATIC;
+	dynamic_opts->arena_ind = ARENA_IND_AUTOMATIC;
+}
 
-	MALLOC_BODY(ret, size, usize);
+/* ind is ignored if dopts->alignment > 0. */
+JEMALLOC_ALWAYS_INLINE void *
+imalloc_no_sample(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd,
+    size_t size, size_t usize, szind_t ind) {
+	tcache_t *tcache;
+	arena_t *arena;
 
-	if (ret == NULL) {
-		if (config_xmalloc && opt_xmalloc) {
-			malloc_write("<jemalloc>: Error in malloc(): "
-			    "out of memory\n");
-			abort();
+	/* Fill in the tcache. */
+	if (dopts->tcache_ind == TCACHE_IND_AUTOMATIC) {
+		if (likely(!sopts->slow)) {
+			/* Getting tcache ptr unconditionally. */
+			tcache = tsd_tcachep_get(tsd);
+			assert(tcache == tcache_get(tsd));
+		} else {
+			tcache = tcache_get(tsd);
 		}
-		set_errno(ENOMEM);
-	}
-	if (config_stats && ret != NULL) {
-		assert(usize == isalloc(ret, config_prof));
-		thread_allocated_tsd_get()->allocated += usize;
+	} else if (dopts->tcache_ind == TCACHE_IND_NONE) {
+		tcache = NULL;
+	} else {
+		tcache = tcaches_get(tsd, dopts->tcache_ind);
 	}
-	UTRACE(0, size, ret);
-	JEMALLOC_VALGRIND_MALLOC(ret != NULL, ret, usize, false);
-	return (ret);
-}
 
-static void *
-imemalign_prof_sample(size_t alignment, size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
+	/* Fill in the arena. */
+	if (dopts->arena_ind == ARENA_IND_AUTOMATIC) {
+		/*
+		 * In case of automatic arena management, we defer arena
+		 * computation until as late as we can, hoping to fill the
+		 * allocation out of the tcache.
+		 */
+		arena = NULL;
+	} else {
+		arena = arena_get(tsd_tsdn(tsd), dopts->arena_ind, true);
+	}
 
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		assert(sa2u(SMALL_MAXCLASS+1, alignment) != 0);
-		p = ipalloc(sa2u(SMALL_MAXCLASS+1, alignment), alignment,
-		    false);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
-	} else
-		p = ipalloc(usize, alignment, false);
+	if (unlikely(dopts->alignment != 0)) {
+		return ipalloct(tsd_tsdn(tsd), usize, dopts->alignment,
+		    dopts->zero, tcache, arena);
+	}
 
-	return (p);
+	return iallocztm(tsd_tsdn(tsd), size, ind, dopts->zero, tcache, false,
+	    arena, sopts->slow);
 }
 
-JEMALLOC_ALWAYS_INLINE_C void *
-imemalign_prof(size_t alignment, size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
+JEMALLOC_ALWAYS_INLINE void *
+imalloc_sample(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd,
+    size_t usize, szind_t ind) {
+	void *ret;
 
-	if ((uintptr_t)cnt != (uintptr_t)1U)
-		p = imemalign_prof_sample(alignment, usize, cnt);
-	else
-		p = ipalloc(usize, alignment, false);
-	if (p == NULL)
-		return (NULL);
-	prof_malloc(p, usize, cnt);
+	/*
+	 * For small allocations, sampling bumps the usize.  If so, we allocate
+	 * from the ind_large bucket.
+	 */
+	szind_t ind_large;
+	size_t bumped_usize = usize;
+
+	if (usize <= SMALL_MAXCLASS) {
+		assert(((dopts->alignment == 0) ? sz_s2u(LARGE_MINCLASS) :
+		    sz_sa2u(LARGE_MINCLASS, dopts->alignment))
+		    == LARGE_MINCLASS);
+		ind_large = sz_size2index(LARGE_MINCLASS);
+		bumped_usize = sz_s2u(LARGE_MINCLASS);
+		ret = imalloc_no_sample(sopts, dopts, tsd, bumped_usize,
+		    bumped_usize, ind_large);
+		if (unlikely(ret == NULL)) {
+			return NULL;
+		}
+		arena_prof_promote(tsd_tsdn(tsd), ret, usize);
+	} else {
+		ret = imalloc_no_sample(sopts, dopts, tsd, usize, usize, ind);
+	}
 
-	return (p);
+	return ret;
 }
 
-JEMALLOC_ATTR(nonnull(1))
-#ifdef JEMALLOC_PROF
 /*
- * Avoid any uncertainty as to how many backtrace frames to ignore in
- * PROF_ALLOC_PREP().
+ * Returns true if the allocation will overflow, and false otherwise.  Sets
+ * *size to the product either way.
  */
-JEMALLOC_NOINLINE
-#endif
-static int
-imemalign(void **memptr, size_t alignment, size_t size, size_t min_alignment)
-{
-	int ret;
-	size_t usize;
-	void *result;
+JEMALLOC_ALWAYS_INLINE bool
+compute_size_with_overflow(bool may_overflow, dynamic_opts_t *dopts,
+    size_t *size) {
+	/*
+	 * This function is just num_items * item_size, except that we may have
+	 * to check for overflow.
+	 */
 
-	assert(min_alignment != 0);
+	if (!may_overflow) {
+		assert(dopts->num_items == 1);
+		*size = dopts->item_size;
+		return false;
+	}
+
+	/* A size_t with its high-half bits all set to 1. */
+	const static size_t high_bits = SIZE_T_MAX << (sizeof(size_t) * 8 / 2);
+
+	*size = dopts->item_size * dopts->num_items;
+
+	if (unlikely(*size == 0)) {
+		return (dopts->num_items != 0 && dopts->item_size != 0);
+	}
+
+	/*
+	 * We got a non-zero size, but we don't know if we overflowed to get
+	 * there.  To avoid having to do a divide, we'll be clever and note that
+	 * if both A and B can be represented in N/2 bits, then their product
+	 * can be represented in N bits (without the possibility of overflow).
+	 */
+	if (likely((high_bits & (dopts->num_items | dopts->item_size)) == 0)) {
+		return false;
+	}
+	if (likely(*size / dopts->item_size == dopts->num_items)) {
+		return false;
+	}
+	return true;
+}
+
+JEMALLOC_ALWAYS_INLINE int
+imalloc_body(static_opts_t *sopts, dynamic_opts_t *dopts, tsd_t *tsd) {
+	/* Where the actual allocated memory will live. */
+	void *allocation = NULL;
+	/* Filled in by compute_size_with_overflow below. */
+	size_t size = 0;
+	/*
+	 * For unaligned allocations, we need only ind.  For aligned
+	 * allocations, or in case of stats or profiling we need usize.
+	 *
+	 * These are actually dead stores, in that their values are reset before
+	 * any branch on their value is taken.  Sometimes though, it's
+	 * convenient to pass them as arguments before this point.  To avoid
+	 * undefined behavior then, we initialize them with dummy stores.
+	 */
+	szind_t ind = 0;
+	size_t usize = 0;
 
-	if (malloc_init()) {
-		result = NULL;
+	/* Reentrancy is only checked on slow path. */
+	int8_t reentrancy_level;
+
+	/* Compute the amount of memory the user wants. */
+	if (unlikely(compute_size_with_overflow(sopts->may_overflow, dopts,
+	    &size))) {
 		goto label_oom;
-	} else {
-		if (size == 0)
-			size = 1;
+	}
 
-		/* Make sure that alignment is a large enough power of 2. */
-		if (((alignment - 1) & alignment) != 0
-		    || (alignment < min_alignment)) {
-			if (config_xmalloc && opt_xmalloc) {
-				malloc_write("<jemalloc>: Error allocating "
-				    "aligned memory: invalid alignment\n");
-				abort();
-			}
-			result = NULL;
-			ret = EINVAL;
-			goto label_return;
+	/* Validate the user input. */
+	if (sopts->bump_empty_alloc) {
+		if (unlikely(size == 0)) {
+			size = 1;
 		}
+	}
+
+	if (sopts->assert_nonempty_alloc) {
+		assert (size != 0);
+	}
+
+	if (unlikely(dopts->alignment < sopts->min_alignment
+	    || (dopts->alignment & (dopts->alignment - 1)) != 0)) {
+		goto label_invalid_alignment;
+	}
+
+	/* This is the beginning of the "core" algorithm. */
 
-		usize = sa2u(size, alignment);
-		if (usize == 0) {
-			result = NULL;
+	if (dopts->alignment == 0) {
+		ind = sz_size2index(size);
+		if (unlikely(ind >= NSIZES)) {
 			goto label_oom;
 		}
+		if (config_stats || (config_prof && opt_prof)) {
+			usize = sz_index2size(ind);
+			assert(usize > 0 && usize <= LARGE_MAXCLASS);
+		}
+	} else {
+		usize = sz_sa2u(size, dopts->alignment);
+		if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
+			goto label_oom;
+		}
+	}
 
-		if (config_prof && opt_prof) {
-			prof_thr_cnt_t *cnt;
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	/*
+	 * If we need to handle reentrancy, we can do it out of a
+	 * known-initialized arena (i.e. arena 0).
+	 */
+	reentrancy_level = tsd_reentrancy_level_get(tsd);
+	if (sopts->slow && unlikely(reentrancy_level > 0)) {
+		/*
+		 * We should never specify particular arenas or tcaches from
+		 * within our internal allocations.
+		 */
+		assert(dopts->tcache_ind == TCACHE_IND_AUTOMATIC ||
+		    dopts->tcache_ind == TCACHE_IND_NONE);
+		assert(dopts->arena_ind == ARENA_IND_AUTOMATIC);
+		dopts->tcache_ind = TCACHE_IND_NONE;
+		/* We know that arena 0 has already been initialized. */
+		dopts->arena_ind = 0;
+	}
+
+	/* If profiling is on, get our profiling context. */
+	if (config_prof && opt_prof) {
+		/*
+		 * Note that if we're going down this path, usize must have been
+		 * initialized in the previous if statement.
+		 */
+		prof_tctx_t *tctx = prof_alloc_prep(
+		    tsd, usize, prof_active_get_unlocked(), true);
+
+		alloc_ctx_t alloc_ctx;
+		if (likely((uintptr_t)tctx == (uintptr_t)1U)) {
+			alloc_ctx.slab = (usize <= SMALL_MAXCLASS);
+			allocation = imalloc_no_sample(
+			    sopts, dopts, tsd, usize, usize, ind);
+		} else if ((uintptr_t)tctx > (uintptr_t)1U) {
+			/*
+			 * Note that ind might still be 0 here.  This is fine;
+			 * imalloc_sample ignores ind if dopts->alignment > 0.
+			 */
+			allocation = imalloc_sample(
+			    sopts, dopts, tsd, usize, ind);
+			alloc_ctx.slab = false;
+		} else {
+			allocation = NULL;
+		}
 
-			PROF_ALLOC_PREP(2, usize, cnt);
-			result = imemalign_prof(alignment, usize, cnt);
-		} else
-			result = ipalloc(usize, alignment, false);
-		if (result == NULL)
+		if (unlikely(allocation == NULL)) {
+			prof_alloc_rollback(tsd, tctx, true);
+			goto label_oom;
+		}
+		prof_malloc(tsd_tsdn(tsd), allocation, usize, &alloc_ctx, tctx);
+	} else {
+		/*
+		 * If dopts->alignment > 0, then ind is still 0, but usize was
+		 * computed in the previous if statement.  Down the positive
+		 * alignment path, imalloc_no_sample ignores ind and size
+		 * (relying only on usize).
+		 */
+		allocation = imalloc_no_sample(sopts, dopts, tsd, size, usize,
+		    ind);
+		if (unlikely(allocation == NULL)) {
 			goto label_oom;
+		}
 	}
 
-	*memptr = result;
-	ret = 0;
-label_return:
-	if (config_stats && result != NULL) {
-		assert(usize == isalloc(result, config_prof));
-		thread_allocated_tsd_get()->allocated += usize;
+	/*
+	 * Allocation has been done at this point.  We still have some
+	 * post-allocation work to do though.
+	 */
+	assert(dopts->alignment == 0
+	    || ((uintptr_t)allocation & (dopts->alignment - 1)) == ZU(0));
+
+	if (config_stats) {
+		assert(usize == isalloc(tsd_tsdn(tsd), allocation));
+		*tsd_thread_allocatedp_get(tsd) += usize;
 	}
-	UTRACE(0, size, result);
-	return (ret);
+
+	if (sopts->slow) {
+		UTRACE(0, size, allocation);
+	}
+
+	/* Success! */
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	*dopts->result = allocation;
+	return 0;
+
 label_oom:
-	assert(result == NULL);
-	if (config_xmalloc && opt_xmalloc) {
-		malloc_write("<jemalloc>: Error allocating aligned memory: "
-		    "out of memory\n");
+	if (unlikely(sopts->slow) && config_xmalloc && unlikely(opt_xmalloc)) {
+		malloc_write(sopts->oom_string);
 		abort();
 	}
-	ret = ENOMEM;
-	goto label_return;
-}
 
-int
-je_posix_memalign(void **memptr, size_t alignment, size_t size)
-{
-	int ret = imemalign(memptr, alignment, size, sizeof(void *));
-	JEMALLOC_VALGRIND_MALLOC(ret == 0, *memptr, isalloc(*memptr,
-	    config_prof), false);
-	return (ret);
+	if (sopts->slow) {
+		UTRACE(NULL, size, NULL);
+	}
+
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	if (sopts->set_errno_on_error) {
+		set_errno(ENOMEM);
+	}
+
+	if (sopts->null_out_result_on_error) {
+		*dopts->result = NULL;
+	}
+
+	return ENOMEM;
+
+	/*
+	 * This label is only jumped to by one goto; we move it out of line
+	 * anyways to avoid obscuring the non-error paths, and for symmetry with
+	 * the oom case.
+	 */
+label_invalid_alignment:
+	if (config_xmalloc && unlikely(opt_xmalloc)) {
+		malloc_write(sopts->invalid_alignment_string);
+		abort();
+	}
+
+	if (sopts->set_errno_on_error) {
+		set_errno(EINVAL);
+	}
+
+	if (sopts->slow) {
+		UTRACE(NULL, size, NULL);
+	}
+
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	if (sopts->null_out_result_on_error) {
+		*dopts->result = NULL;
+	}
+
+	return EINVAL;
 }
 
-void *
-je_aligned_alloc(size_t alignment, size_t size)
-{
-	void *ret;
-	int err;
+/* Returns the errno-style error code of the allocation. */
+JEMALLOC_ALWAYS_INLINE int
+imalloc(static_opts_t *sopts, dynamic_opts_t *dopts) {
+	if (unlikely(!malloc_initialized()) && unlikely(malloc_init())) {
+		if (config_xmalloc && unlikely(opt_xmalloc)) {
+			malloc_write(sopts->oom_string);
+			abort();
+		}
+		UTRACE(NULL, dopts->num_items * dopts->item_size, NULL);
+		set_errno(ENOMEM);
+		*dopts->result = NULL;
+
+		return ENOMEM;
+	}
 
-	if ((err = imemalign(&ret, alignment, size, 1)) != 0) {
-		ret = NULL;
-		set_errno(err);
+	/* We always need the tsd.  Let's grab it right away. */
+	tsd_t *tsd = tsd_fetch();
+	assert(tsd);
+	if (likely(tsd_fast(tsd))) {
+		/* Fast and common path. */
+		tsd_assert_fast(tsd);
+		sopts->slow = false;
+		return imalloc_body(sopts, dopts, tsd);
+	} else {
+		sopts->slow = true;
+		return imalloc_body(sopts, dopts, tsd);
 	}
-	JEMALLOC_VALGRIND_MALLOC(err == 0, ret, isalloc(ret, config_prof),
-	    false);
-	return (ret);
 }
+/******************************************************************************/
+/*
+ * Begin malloc(3)-compatible functions.
+ */
 
-static void *
-icalloc_prof_sample(size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
+je_malloc(size_t size) {
+	void *ret;
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.bump_empty_alloc = true;
+	sopts.null_out_result_on_error = true;
+	sopts.set_errno_on_error = true;
+	sopts.oom_string = "<jemalloc>: Error in malloc(): out of memory\n";
 
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		p = icalloc(SMALL_MAXCLASS+1);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
-	} else
-		p = icalloc(usize);
+	dopts.result = &ret;
+	dopts.num_items = 1;
+	dopts.item_size = size;
 
-	return (p);
+	imalloc(&sopts, &dopts);
+
+	return ret;
 }
 
-JEMALLOC_ALWAYS_INLINE_C void *
-icalloc_prof(size_t usize, prof_thr_cnt_t *cnt)
-{
-	void *p;
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+JEMALLOC_ATTR(nonnull(1))
+je_posix_memalign(void **memptr, size_t alignment, size_t size) {
+	int ret;
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.bump_empty_alloc = true;
+	sopts.min_alignment = sizeof(void *);
+	sopts.oom_string =
+	    "<jemalloc>: Error allocating aligned memory: out of memory\n";
+	sopts.invalid_alignment_string =
+	    "<jemalloc>: Error allocating aligned memory: invalid alignment\n";
+
+	dopts.result = memptr;
+	dopts.num_items = 1;
+	dopts.item_size = size;
+	dopts.alignment = alignment;
+
+	ret = imalloc(&sopts, &dopts);
+	return ret;
+}
 
-	if ((uintptr_t)cnt != (uintptr_t)1U)
-		p = icalloc_prof_sample(usize, cnt);
-	else
-		p = icalloc(usize);
-	if (p == NULL)
-		return (NULL);
-	prof_malloc(p, usize, cnt);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(2)
+je_aligned_alloc(size_t alignment, size_t size) {
+	void *ret;
 
-	return (p);
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.bump_empty_alloc = true;
+	sopts.null_out_result_on_error = true;
+	sopts.set_errno_on_error = true;
+	sopts.min_alignment = 1;
+	sopts.oom_string =
+	    "<jemalloc>: Error allocating aligned memory: out of memory\n";
+	sopts.invalid_alignment_string =
+	    "<jemalloc>: Error allocating aligned memory: invalid alignment\n";
+
+	dopts.result = &ret;
+	dopts.num_items = 1;
+	dopts.item_size = size;
+	dopts.alignment = alignment;
+
+	imalloc(&sopts, &dopts);
+	return ret;
 }
 
-void *
-je_calloc(size_t num, size_t size)
-{
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE2(1, 2)
+je_calloc(size_t num, size_t size) {
 	void *ret;
-	size_t num_size;
-	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
 
-	if (malloc_init()) {
-		num_size = 0;
-		ret = NULL;
-		goto label_return;
-	}
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
 
-	num_size = num * size;
-	if (num_size == 0) {
-		if (num == 0 || size == 0)
-			num_size = 1;
-		else {
-			ret = NULL;
-			goto label_return;
-		}
-	/*
-	 * Try to avoid division here.  We know that it isn't possible to
-	 * overflow during multiplication if neither operand uses any of the
-	 * most significant half of the bits in a size_t.
-	 */
-	} else if (((num | size) & (SIZE_T_MAX << (sizeof(size_t) << 2)))
-	    && (num_size / size != num)) {
-		/* size_t overflow. */
-		ret = NULL;
-		goto label_return;
-	}
+	sopts.may_overflow = true;
+	sopts.bump_empty_alloc = true;
+	sopts.null_out_result_on_error = true;
+	sopts.set_errno_on_error = true;
+	sopts.oom_string = "<jemalloc>: Error in calloc(): out of memory\n";
 
-	if (config_prof && opt_prof) {
-		prof_thr_cnt_t *cnt;
+	dopts.result = &ret;
+	dopts.num_items = num;
+	dopts.item_size = size;
+	dopts.zero = true;
 
-		usize = s2u(num_size);
-		PROF_ALLOC_PREP(1, usize, cnt);
-		ret = icalloc_prof(usize, cnt);
-	} else {
-		if (config_stats || (config_valgrind && opt_valgrind))
-			usize = s2u(num_size);
-		ret = icalloc(num_size);
-	}
+	imalloc(&sopts, &dopts);
 
-label_return:
-	if (ret == NULL) {
-		if (config_xmalloc && opt_xmalloc) {
-			malloc_write("<jemalloc>: Error in calloc(): out of "
-			    "memory\n");
-			abort();
-		}
-		set_errno(ENOMEM);
-	}
-	if (config_stats && ret != NULL) {
-		assert(usize == isalloc(ret, config_prof));
-		thread_allocated_tsd_get()->allocated += usize;
-	}
-	UTRACE(0, num_size, ret);
-	JEMALLOC_VALGRIND_MALLOC(ret != NULL, ret, usize, true);
-	return (ret);
+	return ret;
 }
 
 static void *
-irealloc_prof_sample(void *oldptr, size_t usize, prof_thr_cnt_t *cnt)
-{
+irealloc_prof_sample(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize,
+    prof_tctx_t *tctx) {
 	void *p;
 
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		p = iralloc(oldptr, SMALL_MAXCLASS+1, 0, 0, false);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
-	} else
-		p = iralloc(oldptr, usize, 0, 0, false);
+	if (tctx == NULL) {
+		return NULL;
+	}
+	if (usize <= SMALL_MAXCLASS) {
+		p = iralloc(tsd, old_ptr, old_usize, LARGE_MINCLASS, 0, false);
+		if (p == NULL) {
+			return NULL;
+		}
+		arena_prof_promote(tsd_tsdn(tsd), p, usize);
+	} else {
+		p = iralloc(tsd, old_ptr, old_usize, usize, 0, false);
+	}
 
-	return (p);
+	return p;
 }
 
-JEMALLOC_ALWAYS_INLINE_C void *
-irealloc_prof(void *oldptr, size_t old_usize, size_t usize, prof_thr_cnt_t *cnt)
-{
+JEMALLOC_ALWAYS_INLINE void *
+irealloc_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize,
+   alloc_ctx_t *alloc_ctx) {
 	void *p;
-	prof_ctx_t *old_ctx;
-
-	old_ctx = prof_ctx_get(oldptr);
-	if ((uintptr_t)cnt != (uintptr_t)1U)
-		p = irealloc_prof_sample(oldptr, usize, cnt);
-	else
-		p = iralloc(oldptr, usize, 0, 0, false);
-	if (p == NULL)
-		return (NULL);
-	prof_realloc(p, usize, cnt, old_usize, old_ctx);
+	bool prof_active;
+	prof_tctx_t *old_tctx, *tctx;
+
+	prof_active = prof_active_get_unlocked();
+	old_tctx = prof_tctx_get(tsd_tsdn(tsd), old_ptr, alloc_ctx);
+	tctx = prof_alloc_prep(tsd, usize, prof_active, true);
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) {
+		p = irealloc_prof_sample(tsd, old_ptr, old_usize, usize, tctx);
+	} else {
+		p = iralloc(tsd, old_ptr, old_usize, usize, 0, false);
+	}
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, true);
+		return NULL;
+	}
+	prof_realloc(tsd, p, usize, tctx, prof_active, true, old_ptr, old_usize,
+	    old_tctx);
 
-	return (p);
+	return p;
 }
 
-JEMALLOC_INLINE_C void
-ifree(void *ptr)
-{
+JEMALLOC_ALWAYS_INLINE void
+ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path) {
+	if (!slow_path) {
+		tsd_assert_fast(tsd);
+	}
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	if (tsd_reentrancy_level_get(tsd) != 0) {
+		assert(slow_path);
+	}
+
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	alloc_ctx_t alloc_ctx;
+	rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+	rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+	assert(alloc_ctx.szind != NSIZES);
+
 	size_t usize;
-	UNUSED size_t rzsize JEMALLOC_CC_SILENCE_INIT(0);
+	if (config_prof && opt_prof) {
+		usize = sz_index2size(alloc_ctx.szind);
+		prof_free(tsd, ptr, usize, &alloc_ctx);
+	} else if (config_stats) {
+		usize = sz_index2size(alloc_ctx.szind);
+	}
+	if (config_stats) {
+		*tsd_thread_deallocatedp_get(tsd) += usize;
+	}
+
+	if (likely(!slow_path)) {
+		idalloctm(tsd_tsdn(tsd), ptr, tcache, &alloc_ctx, false,
+		    false);
+	} else {
+		idalloctm(tsd_tsdn(tsd), ptr, tcache, &alloc_ctx, false,
+		    true);
+	}
+}
+
+JEMALLOC_ALWAYS_INLINE void
+isfree(tsd_t *tsd, void *ptr, size_t usize, tcache_t *tcache, bool slow_path) {
+	if (!slow_path) {
+		tsd_assert_fast(tsd);
+	}
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	if (tsd_reentrancy_level_get(tsd) != 0) {
+		assert(slow_path);
+	}
 
 	assert(ptr != NULL);
-	assert(malloc_initialized || IS_INITIALIZER);
+	assert(malloc_initialized() || IS_INITIALIZER);
 
+	alloc_ctx_t alloc_ctx, *ctx;
 	if (config_prof && opt_prof) {
-		usize = isalloc(ptr, config_prof);
-		prof_free(ptr, usize);
-	} else if (config_stats || config_valgrind)
-		usize = isalloc(ptr, config_prof);
-	if (config_stats)
-		thread_allocated_tsd_get()->deallocated += usize;
-	if (config_valgrind && opt_valgrind)
-		rzsize = p2rz(ptr);
-	iqalloc(ptr);
-	JEMALLOC_VALGRIND_FREE(ptr, rzsize);
+		rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+		rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+		assert(alloc_ctx.szind == sz_size2index(usize));
+		ctx = &alloc_ctx;
+		prof_free(tsd, ptr, usize, ctx);
+	} else {
+		ctx = NULL;
+	}
+
+	if (config_stats) {
+		*tsd_thread_deallocatedp_get(tsd) += usize;
+	}
+
+	if (likely(!slow_path)) {
+		isdalloct(tsd_tsdn(tsd), ptr, usize, tcache, ctx, false);
+	} else {
+		isdalloct(tsd_tsdn(tsd), ptr, usize, tcache, ctx, true);
+	}
 }
 
-void *
-je_realloc(void *ptr, size_t size)
-{
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ALLOC_SIZE(2)
+je_realloc(void *ptr, size_t size) {
 	void *ret;
+	tsdn_t *tsdn JEMALLOC_CC_SILENCE_INIT(NULL);
 	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
 	size_t old_usize = 0;
-	UNUSED size_t old_rzsize JEMALLOC_CC_SILENCE_INIT(0);
 
-	if (size == 0) {
+	if (unlikely(size == 0)) {
 		if (ptr != NULL) {
 			/* realloc(ptr, 0) is equivalent to free(ptr). */
 			UTRACE(ptr, 0, 0);
-			ifree(ptr);
-			return (NULL);
+			tcache_t *tcache;
+			tsd_t *tsd = tsd_fetch();
+			if (tsd_reentrancy_level_get(tsd) == 0) {
+				tcache = tcache_get(tsd);
+			} else {
+				tcache = NULL;
+			}
+			ifree(tsd, ptr, tcache, true);
+			return NULL;
 		}
 		size = 1;
 	}
 
-	if (ptr != NULL) {
-		assert(malloc_initialized || IS_INITIALIZER);
-		malloc_thread_init();
+	if (likely(ptr != NULL)) {
+		assert(malloc_initialized() || IS_INITIALIZER);
+		tsd_t *tsd = tsd_fetch();
 
-		if ((config_prof && opt_prof) || config_stats ||
-		    (config_valgrind && opt_valgrind))
-			old_usize = isalloc(ptr, config_prof);
-		if (config_valgrind && opt_valgrind)
-			old_rzsize = config_prof ? p2rz(ptr) : u2rz(old_usize);
+		check_entry_exit_locking(tsd_tsdn(tsd));
 
+		alloc_ctx_t alloc_ctx;
+		rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+		rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+		    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+		assert(alloc_ctx.szind != NSIZES);
+		old_usize = sz_index2size(alloc_ctx.szind);
+		assert(old_usize == isalloc(tsd_tsdn(tsd), ptr));
 		if (config_prof && opt_prof) {
-			prof_thr_cnt_t *cnt;
-
-			usize = s2u(size);
-			PROF_ALLOC_PREP(1, usize, cnt);
-			ret = irealloc_prof(ptr, old_usize, usize, cnt);
+			usize = sz_s2u(size);
+			ret = unlikely(usize == 0 || usize > LARGE_MAXCLASS) ?
+			    NULL : irealloc_prof(tsd, ptr, old_usize, usize,
+			    &alloc_ctx);
 		} else {
-			if (config_stats || (config_valgrind && opt_valgrind))
-				usize = s2u(size);
-			ret = iralloc(ptr, size, 0, 0, false);
+			if (config_stats) {
+				usize = sz_s2u(size);
+			}
+			ret = iralloc(tsd, ptr, old_usize, size, 0, false);
 		}
+		tsdn = tsd_tsdn(tsd);
 	} else {
 		/* realloc(NULL, size) is equivalent to malloc(size). */
-		MALLOC_BODY(ret, size, usize);
+		return je_malloc(size);
 	}
 
-	if (ret == NULL) {
-		if (config_xmalloc && opt_xmalloc) {
+	if (unlikely(ret == NULL)) {
+		if (config_xmalloc && unlikely(opt_xmalloc)) {
 			malloc_write("<jemalloc>: Error in realloc(): "
 			    "out of memory\n");
 			abort();
 		}
 		set_errno(ENOMEM);
 	}
-	if (config_stats && ret != NULL) {
-		thread_allocated_t *ta;
-		assert(usize == isalloc(ret, config_prof));
-		ta = thread_allocated_tsd_get();
-		ta->allocated += usize;
-		ta->deallocated += old_usize;
+	if (config_stats && likely(ret != NULL)) {
+		tsd_t *tsd;
+
+		assert(usize == isalloc(tsdn, ret));
+		tsd = tsdn_tsd(tsdn);
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
 	}
 	UTRACE(ptr, size, ret);
-	JEMALLOC_VALGRIND_REALLOC(ret, usize, ptr, old_usize, old_rzsize,
-	    false);
-	return (ret);
+	check_entry_exit_locking(tsdn);
+	return ret;
 }
 
-void
-je_free(void *ptr)
-{
-
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_free(void *ptr) {
 	UTRACE(ptr, 0, 0);
-	if (ptr != NULL)
-		ifree(ptr);
+	if (likely(ptr != NULL)) {
+		/*
+		 * We avoid setting up tsd fully (e.g. tcache, arena binding)
+		 * based on only free() calls -- other activities trigger the
+		 * minimal to full transition.  This is because free() may
+		 * happen during thread shutdown after tls deallocation: if a
+		 * thread never had any malloc activities until then, a
+		 * fully-setup tsd won't be destructed properly.
+		 */
+		tsd_t *tsd = tsd_fetch_min();
+		check_entry_exit_locking(tsd_tsdn(tsd));
+
+		tcache_t *tcache;
+		if (likely(tsd_fast(tsd))) {
+			tsd_assert_fast(tsd);
+			/* Unconditionally get tcache ptr on fast path. */
+			tcache = tsd_tcachep_get(tsd);
+			ifree(tsd, ptr, tcache, false);
+		} else {
+			if (likely(tsd_reentrancy_level_get(tsd) == 0)) {
+				tcache = tcache_get(tsd);
+			} else {
+				tcache = NULL;
+			}
+			ifree(tsd, ptr, tcache, true);
+		}
+		check_entry_exit_locking(tsd_tsdn(tsd));
+	}
 }
 
 /*
@@ -1317,36 +2302,68 @@ je_free(void *ptr)
  */
 
 #ifdef JEMALLOC_OVERRIDE_MEMALIGN
-void *
-je_memalign(size_t alignment, size_t size)
-{
-	void *ret JEMALLOC_CC_SILENCE_INIT(NULL);
-	imemalign(&ret, alignment, size, 1);
-	JEMALLOC_VALGRIND_MALLOC(ret != NULL, ret, size, false);
-	return (ret);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc)
+je_memalign(size_t alignment, size_t size) {
+	void *ret;
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.bump_empty_alloc = true;
+	sopts.min_alignment = 1;
+	sopts.oom_string =
+	    "<jemalloc>: Error allocating aligned memory: out of memory\n";
+	sopts.invalid_alignment_string =
+	    "<jemalloc>: Error allocating aligned memory: invalid alignment\n";
+	sopts.null_out_result_on_error = true;
+
+	dopts.result = &ret;
+	dopts.num_items = 1;
+	dopts.item_size = size;
+	dopts.alignment = alignment;
+
+	imalloc(&sopts, &dopts);
+	return ret;
 }
 #endif
 
 #ifdef JEMALLOC_OVERRIDE_VALLOC
-void *
-je_valloc(size_t size)
-{
-	void *ret JEMALLOC_CC_SILENCE_INIT(NULL);
-	imemalign(&ret, PAGE, size, 1);
-	JEMALLOC_VALGRIND_MALLOC(ret != NULL, ret, size, false);
-	return (ret);
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc)
+je_valloc(size_t size) {
+	void *ret;
+
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.bump_empty_alloc = true;
+	sopts.null_out_result_on_error = true;
+	sopts.min_alignment = PAGE;
+	sopts.oom_string =
+	    "<jemalloc>: Error allocating aligned memory: out of memory\n";
+	sopts.invalid_alignment_string =
+	    "<jemalloc>: Error allocating aligned memory: invalid alignment\n";
+
+	dopts.result = &ret;
+	dopts.num_items = 1;
+	dopts.item_size = size;
+	dopts.alignment = PAGE;
+
+	imalloc(&sopts, &dopts);
+
+	return ret;
 }
 #endif
 
-/*
- * is_malloc(je_malloc) is some macro magic to detect if jemalloc_defs.h has
- * #define je_malloc malloc
- */
-#define	malloc_is_malloc 1
-#define	is_malloc_(a) malloc_is_ ## a
-#define	is_malloc(a) is_malloc_(a)
-
-#if ((is_malloc(je_malloc) == 1) && defined(__GLIBC__) && !defined(__UCLIBC__))
+#if defined(JEMALLOC_IS_MALLOC) && defined(JEMALLOC_GLIBC_MALLOC_HOOK)
 /*
  * glibc provides the RTLD_DEEPBIND flag for dlopen which can make it possible
  * to inconsistently reference libc's malloc(3)-compatible functions
@@ -1356,11 +2373,47 @@ je_valloc(size_t size)
  * passed an extra argument for the caller return address, which will be
  * ignored.
  */
-JEMALLOC_EXPORT void (* __free_hook)(void *ptr) = je_free;
-JEMALLOC_EXPORT void *(* __malloc_hook)(size_t size) = je_malloc;
-JEMALLOC_EXPORT void *(* __realloc_hook)(void *ptr, size_t size) = je_realloc;
-JEMALLOC_EXPORT void *(* __memalign_hook)(size_t alignment, size_t size) =
+JEMALLOC_EXPORT void (*__free_hook)(void *ptr) = je_free;
+JEMALLOC_EXPORT void *(*__malloc_hook)(size_t size) = je_malloc;
+JEMALLOC_EXPORT void *(*__realloc_hook)(void *ptr, size_t size) = je_realloc;
+#  ifdef JEMALLOC_GLIBC_MEMALIGN_HOOK
+JEMALLOC_EXPORT void *(*__memalign_hook)(size_t alignment, size_t size) =
     je_memalign;
+#  endif
+
+#  ifdef CPU_COUNT
+/*
+ * To enable static linking with glibc, the libc specific malloc interface must
+ * be implemented also, so none of glibc's malloc.o functions are added to the
+ * link.
+ */
+#    define ALIAS(je_fn)	__attribute__((alias (#je_fn), used))
+/* To force macro expansion of je_ prefix before stringification. */
+#    define PREALIAS(je_fn)	ALIAS(je_fn)
+#    ifdef JEMALLOC_OVERRIDE___LIBC_CALLOC
+void *__libc_calloc(size_t n, size_t size) PREALIAS(je_calloc);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___LIBC_FREE
+void __libc_free(void* ptr) PREALIAS(je_free);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___LIBC_MALLOC
+void *__libc_malloc(size_t size) PREALIAS(je_malloc);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___LIBC_MEMALIGN
+void *__libc_memalign(size_t align, size_t s) PREALIAS(je_memalign);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___LIBC_REALLOC
+void *__libc_realloc(void* ptr, size_t size) PREALIAS(je_realloc);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___LIBC_VALLOC
+void *__libc_valloc(size_t size) PREALIAS(je_valloc);
+#    endif
+#    ifdef JEMALLOC_OVERRIDE___POSIX_MEMALIGN
+int __posix_memalign(void** r, size_t a, size_t s) PREALIAS(je_posix_memalign);
+#    endif
+#    undef PREALIAS
+#    undef ALIAS
+#  endif
 #endif
 
 /*
@@ -1371,162 +2424,98 @@ JEMALLOC_EXPORT void *(* __memalign_hook)(size_t alignment, size_t size) =
  * Begin non-standard functions.
  */
 
-JEMALLOC_ALWAYS_INLINE_C void *
-imallocx(size_t usize, size_t alignment, bool zero, bool try_tcache,
-    arena_t *arena)
-{
-
-	assert(usize == ((alignment == 0) ? s2u(usize) : sa2u(usize,
-	    alignment)));
-
-	if (alignment != 0)
-		return (ipalloct(usize, alignment, zero, try_tcache, arena));
-	else if (zero)
-		return (icalloct(usize, try_tcache, arena));
-	else
-		return (imalloct(usize, try_tcache, arena));
-}
-
-static void *
-imallocx_prof_sample(size_t usize, size_t alignment, bool zero, bool try_tcache,
-    arena_t *arena, prof_thr_cnt_t *cnt)
-{
-	void *p;
-
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		size_t usize_promoted = (alignment == 0) ?
-		    s2u(SMALL_MAXCLASS+1) : sa2u(SMALL_MAXCLASS+1, alignment);
-		assert(usize_promoted != 0);
-		p = imallocx(usize_promoted, alignment, zero, try_tcache,
-		    arena);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
-	} else
-		p = imallocx(usize, alignment, zero, try_tcache, arena);
-
-	return (p);
-}
-
-JEMALLOC_ALWAYS_INLINE_C void *
-imallocx_prof(size_t usize, size_t alignment, bool zero, bool try_tcache,
-    arena_t *arena, prof_thr_cnt_t *cnt)
-{
-	void *p;
-
-	if ((uintptr_t)cnt != (uintptr_t)1U) {
-		p = imallocx_prof_sample(usize, alignment, zero, try_tcache,
-		    arena, cnt);
-	} else
-		p = imallocx(usize, alignment, zero, try_tcache, arena);
-	if (p == NULL)
-		return (NULL);
-	prof_malloc(p, usize, cnt);
-
-	return (p);
-}
-
-void *
-je_mallocx(size_t size, int flags)
-{
-	void *p;
-	size_t usize;
-	size_t alignment = (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK)
-	    & (SIZE_T_MAX-1));
-	bool zero = flags & MALLOCX_ZERO;
-	unsigned arena_ind = ((unsigned)(flags >> 8)) - 1;
-	arena_t *arena;
-	bool try_tcache;
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
+je_mallocx(size_t size, int flags) {
+	void *ret;
+	static_opts_t sopts;
+	dynamic_opts_t dopts;
+
+	static_opts_init(&sopts);
+	dynamic_opts_init(&dopts);
+
+	sopts.assert_nonempty_alloc = true;
+	sopts.null_out_result_on_error = true;
+	sopts.oom_string = "<jemalloc>: Error in mallocx(): out of memory\n";
+
+	dopts.result = &ret;
+	dopts.num_items = 1;
+	dopts.item_size = size;
+	if (unlikely(flags != 0)) {
+		if ((flags & MALLOCX_LG_ALIGN_MASK) != 0) {
+			dopts.alignment = MALLOCX_ALIGN_GET_SPECIFIED(flags);
+		}
 
-	assert(size != 0);
+		dopts.zero = MALLOCX_ZERO_GET(flags);
 
-	if (malloc_init())
-		goto label_oom;
+		if ((flags & MALLOCX_TCACHE_MASK) != 0) {
+			if ((flags & MALLOCX_TCACHE_MASK)
+			    == MALLOCX_TCACHE_NONE) {
+				dopts.tcache_ind = TCACHE_IND_NONE;
+			} else {
+				dopts.tcache_ind = MALLOCX_TCACHE_GET(flags);
+			}
+		} else {
+			dopts.tcache_ind = TCACHE_IND_AUTOMATIC;
+		}
 
-	if (arena_ind != UINT_MAX) {
-		arena = arenas[arena_ind];
-		try_tcache = false;
-	} else {
-		arena = NULL;
-		try_tcache = true;
+		if ((flags & MALLOCX_ARENA_MASK) != 0)
+			dopts.arena_ind = MALLOCX_ARENA_GET(flags);
 	}
 
-	usize = (alignment == 0) ? s2u(size) : sa2u(size, alignment);
-	assert(usize != 0);
-
-	if (config_prof && opt_prof) {
-		prof_thr_cnt_t *cnt;
-
-		PROF_ALLOC_PREP(1, usize, cnt);
-		p = imallocx_prof(usize, alignment, zero, try_tcache, arena,
-		    cnt);
-	} else
-		p = imallocx(usize, alignment, zero, try_tcache, arena);
-	if (p == NULL)
-		goto label_oom;
-
-	if (config_stats) {
-		assert(usize == isalloc(p, config_prof));
-		thread_allocated_tsd_get()->allocated += usize;
-	}
-	UTRACE(0, size, p);
-	JEMALLOC_VALGRIND_MALLOC(true, p, usize, zero);
-	return (p);
-label_oom:
-	if (config_xmalloc && opt_xmalloc) {
-		malloc_write("<jemalloc>: Error in mallocx(): out of memory\n");
-		abort();
-	}
-	UTRACE(0, size, 0);
-	return (NULL);
+	imalloc(&sopts, &dopts);
+	return ret;
 }
 
 static void *
-irallocx_prof_sample(void *oldptr, size_t size, size_t alignment, size_t usize,
-    bool zero, bool try_tcache_alloc, bool try_tcache_dalloc, arena_t *arena,
-    prof_thr_cnt_t *cnt)
-{
+irallocx_prof_sample(tsdn_t *tsdn, void *old_ptr, size_t old_usize,
+    size_t usize, size_t alignment, bool zero, tcache_t *tcache, arena_t *arena,
+    prof_tctx_t *tctx) {
 	void *p;
 
-	if (cnt == NULL)
-		return (NULL);
-	if (prof_promote && usize <= SMALL_MAXCLASS) {
-		p = iralloct(oldptr, SMALL_MAXCLASS+1, (SMALL_MAXCLASS+1 >=
-		    size) ? 0 : size - (SMALL_MAXCLASS+1), alignment, zero,
-		    try_tcache_alloc, try_tcache_dalloc, arena);
-		if (p == NULL)
-			return (NULL);
-		arena_prof_promoted(p, usize);
+	if (tctx == NULL) {
+		return NULL;
+	}
+	if (usize <= SMALL_MAXCLASS) {
+		p = iralloct(tsdn, old_ptr, old_usize, LARGE_MINCLASS,
+		    alignment, zero, tcache, arena);
+		if (p == NULL) {
+			return NULL;
+		}
+		arena_prof_promote(tsdn, p, usize);
 	} else {
-		p = iralloct(oldptr, size, 0, alignment, zero,
-		    try_tcache_alloc, try_tcache_dalloc, arena);
+		p = iralloct(tsdn, old_ptr, old_usize, usize, alignment, zero,
+		    tcache, arena);
 	}
 
-	return (p);
+	return p;
 }
 
-JEMALLOC_ALWAYS_INLINE_C void *
-irallocx_prof(void *oldptr, size_t old_usize, size_t size, size_t alignment,
-    size_t *usize, bool zero, bool try_tcache_alloc, bool try_tcache_dalloc,
-    arena_t *arena, prof_thr_cnt_t *cnt)
-{
+JEMALLOC_ALWAYS_INLINE void *
+irallocx_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t size,
+    size_t alignment, size_t *usize, bool zero, tcache_t *tcache,
+    arena_t *arena, alloc_ctx_t *alloc_ctx) {
 	void *p;
-	prof_ctx_t *old_ctx;
-
-	old_ctx = prof_ctx_get(oldptr);
-	if ((uintptr_t)cnt != (uintptr_t)1U)
-		p = irallocx_prof_sample(oldptr, size, alignment, *usize, zero,
-		    try_tcache_alloc, try_tcache_dalloc, arena, cnt);
-	else {
-		p = iralloct(oldptr, size, 0, alignment, zero,
-		    try_tcache_alloc, try_tcache_dalloc, arena);
+	bool prof_active;
+	prof_tctx_t *old_tctx, *tctx;
+
+	prof_active = prof_active_get_unlocked();
+	old_tctx = prof_tctx_get(tsd_tsdn(tsd), old_ptr, alloc_ctx);
+	tctx = prof_alloc_prep(tsd, *usize, prof_active, false);
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) {
+		p = irallocx_prof_sample(tsd_tsdn(tsd), old_ptr, old_usize,
+		    *usize, alignment, zero, tcache, arena, tctx);
+	} else {
+		p = iralloct(tsd_tsdn(tsd), old_ptr, old_usize, size, alignment,
+		    zero, tcache, arena);
+	}
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, false);
+		return NULL;
 	}
-	if (p == NULL)
-		return (NULL);
 
-	if (p == oldptr && alignment != 0) {
+	if (p == old_ptr && alignment != 0) {
 		/*
 		 * The allocation did not move, so it is possible that the size
 		 * class is smaller than would guarantee the requested
@@ -1535,421 +2524,467 @@ irallocx_prof(void *oldptr, size_t old_usize, size_t size, size_t alignment,
 		 * be the same as the current usize because of in-place large
 		 * reallocation.  Therefore, query the actual value of usize.
 		 */
-		*usize = isalloc(p, config_prof);
+		*usize = isalloc(tsd_tsdn(tsd), p);
 	}
-	prof_realloc(p, *usize, cnt, old_usize, old_ctx);
+	prof_realloc(tsd, p, *usize, tctx, prof_active, false, old_ptr,
+	    old_usize, old_tctx);
 
-	return (p);
+	return p;
 }
 
-void *
-je_rallocx(void *ptr, size_t size, int flags)
-{
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ALLOC_SIZE(2)
+je_rallocx(void *ptr, size_t size, int flags) {
 	void *p;
-	size_t usize, old_usize;
-	UNUSED size_t old_rzsize JEMALLOC_CC_SILENCE_INIT(0);
-	size_t alignment = (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK)
-	    & (SIZE_T_MAX-1));
+	tsd_t *tsd;
+	size_t usize;
+	size_t old_usize;
+	size_t alignment = MALLOCX_ALIGN_GET(flags);
 	bool zero = flags & MALLOCX_ZERO;
-	unsigned arena_ind = ((unsigned)(flags >> 8)) - 1;
-	bool try_tcache_alloc, try_tcache_dalloc;
 	arena_t *arena;
+	tcache_t *tcache;
 
 	assert(ptr != NULL);
 	assert(size != 0);
-	assert(malloc_initialized || IS_INITIALIZER);
-	malloc_thread_init();
-
-	if (arena_ind != UINT_MAX) {
-		arena_chunk_t *chunk;
-		try_tcache_alloc = false;
-		chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-		try_tcache_dalloc = (chunk == ptr || chunk->arena !=
-		    arenas[arena_ind]);
-		arena = arenas[arena_ind];
+	assert(malloc_initialized() || IS_INITIALIZER);
+	tsd = tsd_fetch();
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	if (unlikely((flags & MALLOCX_ARENA_MASK) != 0)) {
+		unsigned arena_ind = MALLOCX_ARENA_GET(flags);
+		arena = arena_get(tsd_tsdn(tsd), arena_ind, true);
+		if (unlikely(arena == NULL)) {
+			goto label_oom;
+		}
 	} else {
-		try_tcache_alloc = true;
-		try_tcache_dalloc = true;
 		arena = NULL;
 	}
 
-	if ((config_prof && opt_prof) || config_stats ||
-	    (config_valgrind && opt_valgrind))
-		old_usize = isalloc(ptr, config_prof);
-	if (config_valgrind && opt_valgrind)
-		old_rzsize = u2rz(old_usize);
+	if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) {
+		if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) {
+			tcache = NULL;
+		} else {
+			tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags));
+		}
+	} else {
+		tcache = tcache_get(tsd);
+	}
 
+	alloc_ctx_t alloc_ctx;
+	rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+	rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+	assert(alloc_ctx.szind != NSIZES);
+	old_usize = sz_index2size(alloc_ctx.szind);
+	assert(old_usize == isalloc(tsd_tsdn(tsd), ptr));
 	if (config_prof && opt_prof) {
-		prof_thr_cnt_t *cnt;
-
-		usize = (alignment == 0) ? s2u(size) : sa2u(size, alignment);
-		assert(usize != 0);
-		PROF_ALLOC_PREP(1, usize, cnt);
-		p = irallocx_prof(ptr, old_usize, size, alignment, &usize, zero,
-		    try_tcache_alloc, try_tcache_dalloc, arena, cnt);
-		if (p == NULL)
+		usize = (alignment == 0) ?
+		    sz_s2u(size) : sz_sa2u(size, alignment);
+		if (unlikely(usize == 0 || usize > LARGE_MAXCLASS)) {
+			goto label_oom;
+		}
+		p = irallocx_prof(tsd, ptr, old_usize, size, alignment, &usize,
+		    zero, tcache, arena, &alloc_ctx);
+		if (unlikely(p == NULL)) {
 			goto label_oom;
+		}
 	} else {
-		p = iralloct(ptr, size, 0, alignment, zero, try_tcache_alloc,
-		    try_tcache_dalloc, arena);
-		if (p == NULL)
+		p = iralloct(tsd_tsdn(tsd), ptr, old_usize, size, alignment,
+		    zero, tcache, arena);
+		if (unlikely(p == NULL)) {
 			goto label_oom;
-		if (config_stats || (config_valgrind && opt_valgrind))
-			usize = isalloc(p, config_prof);
+		}
+		if (config_stats) {
+			usize = isalloc(tsd_tsdn(tsd), p);
+		}
 	}
+	assert(alignment == 0 || ((uintptr_t)p & (alignment - 1)) == ZU(0));
 
 	if (config_stats) {
-		thread_allocated_t *ta;
-		ta = thread_allocated_tsd_get();
-		ta->allocated += usize;
-		ta->deallocated += old_usize;
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
 	}
 	UTRACE(ptr, size, p);
-	JEMALLOC_VALGRIND_REALLOC(p, usize, ptr, old_usize, old_rzsize, zero);
-	return (p);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return p;
 label_oom:
-	if (config_xmalloc && opt_xmalloc) {
+	if (config_xmalloc && unlikely(opt_xmalloc)) {
 		malloc_write("<jemalloc>: Error in rallocx(): out of memory\n");
 		abort();
 	}
 	UTRACE(ptr, size, 0);
-	return (NULL);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return NULL;
 }
 
-JEMALLOC_ALWAYS_INLINE_C size_t
-ixallocx_helper(void *ptr, size_t old_usize, size_t size, size_t extra,
-    size_t alignment, bool zero, arena_t *arena)
-{
+JEMALLOC_ALWAYS_INLINE size_t
+ixallocx_helper(tsdn_t *tsdn, void *ptr, size_t old_usize, size_t size,
+    size_t extra, size_t alignment, bool zero) {
 	size_t usize;
 
-	if (ixalloc(ptr, size, extra, alignment, zero))
-		return (old_usize);
-	usize = isalloc(ptr, config_prof);
+	if (ixalloc(tsdn, ptr, old_usize, size, extra, alignment, zero)) {
+		return old_usize;
+	}
+	usize = isalloc(tsdn, ptr);
 
-	return (usize);
+	return usize;
 }
 
 static size_t
-ixallocx_prof_sample(void *ptr, size_t old_usize, size_t size, size_t extra,
-    size_t alignment, size_t max_usize, bool zero, arena_t *arena,
-    prof_thr_cnt_t *cnt)
-{
+ixallocx_prof_sample(tsdn_t *tsdn, void *ptr, size_t old_usize, size_t size,
+    size_t extra, size_t alignment, bool zero, prof_tctx_t *tctx) {
 	size_t usize;
 
-	if (cnt == NULL)
-		return (old_usize);
-	/* Use minimum usize to determine whether promotion may happen. */
-	if (prof_promote && ((alignment == 0) ? s2u(size) : sa2u(size,
-	    alignment)) <= SMALL_MAXCLASS) {
-		if (ixalloc(ptr, SMALL_MAXCLASS+1, (SMALL_MAXCLASS+1 >=
-		    size+extra) ? 0 : size+extra - (SMALL_MAXCLASS+1),
-		    alignment, zero))
-			return (old_usize);
-		usize = isalloc(ptr, config_prof);
-		if (max_usize < PAGE)
-			arena_prof_promoted(ptr, usize);
-	} else {
-		usize = ixallocx_helper(ptr, old_usize, size, extra, alignment,
-		    zero, arena);
+	if (tctx == NULL) {
+		return old_usize;
 	}
+	usize = ixallocx_helper(tsdn, ptr, old_usize, size, extra, alignment,
+	    zero);
 
-	return (usize);
+	return usize;
 }
 
-JEMALLOC_ALWAYS_INLINE_C size_t
-ixallocx_prof(void *ptr, size_t old_usize, size_t size, size_t extra,
-    size_t alignment, size_t max_usize, bool zero, arena_t *arena,
-    prof_thr_cnt_t *cnt)
-{
-	size_t usize;
-	prof_ctx_t *old_ctx;
+JEMALLOC_ALWAYS_INLINE size_t
+ixallocx_prof(tsd_t *tsd, void *ptr, size_t old_usize, size_t size,
+    size_t extra, size_t alignment, bool zero, alloc_ctx_t *alloc_ctx) {
+	size_t usize_max, usize;
+	bool prof_active;
+	prof_tctx_t *old_tctx, *tctx;
 
-	old_ctx = prof_ctx_get(ptr);
-	if ((uintptr_t)cnt != (uintptr_t)1U) {
-		usize = ixallocx_prof_sample(ptr, old_usize, size, extra,
-		    alignment, zero, max_usize, arena, cnt);
+	prof_active = prof_active_get_unlocked();
+	old_tctx = prof_tctx_get(tsd_tsdn(tsd), ptr, alloc_ctx);
+	/*
+	 * usize isn't knowable before ixalloc() returns when extra is non-zero.
+	 * Therefore, compute its maximum possible value and use that in
+	 * prof_alloc_prep() to decide whether to capture a backtrace.
+	 * prof_realloc() will use the actual usize to decide whether to sample.
+	 */
+	if (alignment == 0) {
+		usize_max = sz_s2u(size+extra);
+		assert(usize_max > 0 && usize_max <= LARGE_MAXCLASS);
+	} else {
+		usize_max = sz_sa2u(size+extra, alignment);
+		if (unlikely(usize_max == 0 || usize_max > LARGE_MAXCLASS)) {
+			/*
+			 * usize_max is out of range, and chances are that
+			 * allocation will fail, but use the maximum possible
+			 * value and carry on with prof_alloc_prep(), just in
+			 * case allocation succeeds.
+			 */
+			usize_max = LARGE_MAXCLASS;
+		}
+	}
+	tctx = prof_alloc_prep(tsd, usize_max, prof_active, false);
+
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) {
+		usize = ixallocx_prof_sample(tsd_tsdn(tsd), ptr, old_usize,
+		    size, extra, alignment, zero, tctx);
 	} else {
-		usize = ixallocx_helper(ptr, old_usize, size, extra, alignment,
-		    zero, arena);
+		usize = ixallocx_helper(tsd_tsdn(tsd), ptr, old_usize, size,
+		    extra, alignment, zero);
 	}
-	if (usize == old_usize)
-		return (usize);
-	prof_realloc(ptr, usize, cnt, old_usize, old_ctx);
+	if (usize == old_usize) {
+		prof_alloc_rollback(tsd, tctx, false);
+		return usize;
+	}
+	prof_realloc(tsd, ptr, usize, tctx, prof_active, false, ptr, old_usize,
+	    old_tctx);
 
-	return (usize);
+	return usize;
 }
 
-size_t
-je_xallocx(void *ptr, size_t size, size_t extra, int flags)
-{
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW
+je_xallocx(void *ptr, size_t size, size_t extra, int flags) {
+	tsd_t *tsd;
 	size_t usize, old_usize;
-	UNUSED size_t old_rzsize JEMALLOC_CC_SILENCE_INIT(0);
-	size_t alignment = (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK)
-	    & (SIZE_T_MAX-1));
+	size_t alignment = MALLOCX_ALIGN_GET(flags);
 	bool zero = flags & MALLOCX_ZERO;
-	unsigned arena_ind = ((unsigned)(flags >> 8)) - 1;
-	arena_t *arena;
 
 	assert(ptr != NULL);
 	assert(size != 0);
 	assert(SIZE_T_MAX - size >= extra);
-	assert(malloc_initialized || IS_INITIALIZER);
-	malloc_thread_init();
-
-	if (arena_ind != UINT_MAX)
-		arena = arenas[arena_ind];
-	else
-		arena = NULL;
-
-	old_usize = isalloc(ptr, config_prof);
-	if (config_valgrind && opt_valgrind)
-		old_rzsize = u2rz(old_usize);
+	assert(malloc_initialized() || IS_INITIALIZER);
+	tsd = tsd_fetch();
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	alloc_ctx_t alloc_ctx;
+	rtree_ctx_t *rtree_ctx = tsd_rtree_ctx(tsd);
+	rtree_szind_slab_read(tsd_tsdn(tsd), &extents_rtree, rtree_ctx,
+	    (uintptr_t)ptr, true, &alloc_ctx.szind, &alloc_ctx.slab);
+	assert(alloc_ctx.szind != NSIZES);
+	old_usize = sz_index2size(alloc_ctx.szind);
+	assert(old_usize == isalloc(tsd_tsdn(tsd), ptr));
+	/*
+	 * The API explicitly absolves itself of protecting against (size +
+	 * extra) numerical overflow, but we may need to clamp extra to avoid
+	 * exceeding LARGE_MAXCLASS.
+	 *
+	 * Ordinarily, size limit checking is handled deeper down, but here we
+	 * have to check as part of (size + extra) clamping, since we need the
+	 * clamped value in the above helper functions.
+	 */
+	if (unlikely(size > LARGE_MAXCLASS)) {
+		usize = old_usize;
+		goto label_not_resized;
+	}
+	if (unlikely(LARGE_MAXCLASS - size < extra)) {
+		extra = LARGE_MAXCLASS - size;
+	}
 
 	if (config_prof && opt_prof) {
-		prof_thr_cnt_t *cnt;
-		/*
-		 * usize isn't knowable before ixalloc() returns when extra is
-		 * non-zero.  Therefore, compute its maximum possible value and
-		 * use that in PROF_ALLOC_PREP() to decide whether to capture a
-		 * backtrace.  prof_realloc() will use the actual usize to
-		 * decide whether to sample.
-		 */
-		size_t max_usize = (alignment == 0) ? s2u(size+extra) :
-		    sa2u(size+extra, alignment);
-		PROF_ALLOC_PREP(1, max_usize, cnt);
-		usize = ixallocx_prof(ptr, old_usize, size, extra, alignment,
-		    max_usize, zero, arena, cnt);
+		usize = ixallocx_prof(tsd, ptr, old_usize, size, extra,
+		    alignment, zero, &alloc_ctx);
 	} else {
-		usize = ixallocx_helper(ptr, old_usize, size, extra, alignment,
-		    zero, arena);
+		usize = ixallocx_helper(tsd_tsdn(tsd), ptr, old_usize, size,
+		    extra, alignment, zero);
 	}
-	if (usize == old_usize)
+	if (unlikely(usize == old_usize)) {
 		goto label_not_resized;
+	}
 
 	if (config_stats) {
-		thread_allocated_t *ta;
-		ta = thread_allocated_tsd_get();
-		ta->allocated += usize;
-		ta->deallocated += old_usize;
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
 	}
-	JEMALLOC_VALGRIND_REALLOC(ptr, usize, ptr, old_usize, old_rzsize, zero);
 label_not_resized:
 	UTRACE(ptr, size, ptr);
-	return (usize);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return usize;
 }
 
-size_t
-je_sallocx(const void *ptr, int flags)
-{
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW
+JEMALLOC_ATTR(pure)
+je_sallocx(const void *ptr, int flags) {
 	size_t usize;
+	tsdn_t *tsdn;
+
+	assert(malloc_initialized() || IS_INITIALIZER);
+	assert(ptr != NULL);
 
-	assert(malloc_initialized || IS_INITIALIZER);
-	malloc_thread_init();
+	tsdn = tsdn_fetch();
+	check_entry_exit_locking(tsdn);
 
-	if (config_ivsalloc)
-		usize = ivsalloc(ptr, config_prof);
-	else {
-		assert(ptr != NULL);
-		usize = isalloc(ptr, config_prof);
+	if (config_debug || force_ivsalloc) {
+		usize = ivsalloc(tsdn, ptr);
+		assert(force_ivsalloc || usize != 0);
+	} else {
+		usize = isalloc(tsdn, ptr);
 	}
 
-	return (usize);
+	check_entry_exit_locking(tsdn);
+	return usize;
 }
 
-void
-je_dallocx(void *ptr, int flags)
-{
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_dallocx(void *ptr, int flags) {
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	tsd_t *tsd = tsd_fetch();
+	bool fast = tsd_fast(tsd);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	tcache_t *tcache;
+	if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) {
+		/* Not allowed to be reentrant and specify a custom tcache. */
+		assert(tsd_reentrancy_level_get(tsd) == 0);
+		if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) {
+			tcache = NULL;
+		} else {
+			tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags));
+		}
+	} else {
+		if (likely(fast)) {
+			tcache = tsd_tcachep_get(tsd);
+			assert(tcache == tcache_get(tsd));
+		} else {
+			if (likely(tsd_reentrancy_level_get(tsd) == 0)) {
+				tcache = tcache_get(tsd);
+			}  else {
+				tcache = NULL;
+			}
+		}
+	}
+
+	UTRACE(ptr, 0, 0);
+	if (likely(fast)) {
+		tsd_assert_fast(tsd);
+		ifree(tsd, ptr, tcache, false);
+	} else {
+		ifree(tsd, ptr, tcache, true);
+	}
+	check_entry_exit_locking(tsd_tsdn(tsd));
+}
+
+JEMALLOC_ALWAYS_INLINE size_t
+inallocx(tsdn_t *tsdn, size_t size, int flags) {
+	check_entry_exit_locking(tsdn);
+
 	size_t usize;
-	UNUSED size_t rzsize JEMALLOC_CC_SILENCE_INIT(0);
-	unsigned arena_ind = ((unsigned)(flags >> 8)) - 1;
-	bool try_tcache;
+	if (likely((flags & MALLOCX_LG_ALIGN_MASK) == 0)) {
+		usize = sz_s2u(size);
+	} else {
+		usize = sz_sa2u(size, MALLOCX_ALIGN_GET_SPECIFIED(flags));
+	}
+	check_entry_exit_locking(tsdn);
+	return usize;
+}
 
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_sdallocx(void *ptr, size_t size, int flags) {
 	assert(ptr != NULL);
-	assert(malloc_initialized || IS_INITIALIZER);
-
-	if (arena_ind != UINT_MAX) {
-		arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-		try_tcache = (chunk == ptr || chunk->arena !=
-		    arenas[arena_ind]);
-	} else
-		try_tcache = true;
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	tsd_t *tsd = tsd_fetch();
+	bool fast = tsd_fast(tsd);
+	size_t usize = inallocx(tsd_tsdn(tsd), size, flags);
+	assert(usize == isalloc(tsd_tsdn(tsd), ptr));
+	check_entry_exit_locking(tsd_tsdn(tsd));
+
+	tcache_t *tcache;
+	if (unlikely((flags & MALLOCX_TCACHE_MASK) != 0)) {
+		/* Not allowed to be reentrant and specify a custom tcache. */
+		assert(tsd_reentrancy_level_get(tsd) == 0);
+		if ((flags & MALLOCX_TCACHE_MASK) == MALLOCX_TCACHE_NONE) {
+			tcache = NULL;
+		} else {
+			tcache = tcaches_get(tsd, MALLOCX_TCACHE_GET(flags));
+		}
+	} else {
+		if (likely(fast)) {
+			tcache = tsd_tcachep_get(tsd);
+			assert(tcache == tcache_get(tsd));
+		} else {
+			if (likely(tsd_reentrancy_level_get(tsd) == 0)) {
+				tcache = tcache_get(tsd);
+			} else {
+				tcache = NULL;
+			}
+		}
+	}
 
 	UTRACE(ptr, 0, 0);
-	if (config_stats || config_valgrind)
-		usize = isalloc(ptr, config_prof);
-	if (config_prof && opt_prof) {
-		if (config_stats == false && config_valgrind == false)
-			usize = isalloc(ptr, config_prof);
-		prof_free(ptr, usize);
+	if (likely(fast)) {
+		tsd_assert_fast(tsd);
+		isfree(tsd, ptr, usize, tcache, false);
+	} else {
+		isfree(tsd, ptr, usize, tcache, true);
 	}
-	if (config_stats)
-		thread_allocated_tsd_get()->deallocated += usize;
-	if (config_valgrind && opt_valgrind)
-		rzsize = p2rz(ptr);
-	iqalloct(ptr, try_tcache);
-	JEMALLOC_VALGRIND_FREE(ptr, rzsize);
+	check_entry_exit_locking(tsd_tsdn(tsd));
 }
 
-size_t
-je_nallocx(size_t size, int flags)
-{
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW
+JEMALLOC_ATTR(pure)
+je_nallocx(size_t size, int flags) {
 	size_t usize;
-	size_t alignment = (ZU(1) << (flags & MALLOCX_LG_ALIGN_MASK)
-	    & (SIZE_T_MAX-1));
+	tsdn_t *tsdn;
 
 	assert(size != 0);
 
-	if (malloc_init())
-		return (0);
+	if (unlikely(malloc_init())) {
+		return 0;
+	}
+
+	tsdn = tsdn_fetch();
+	check_entry_exit_locking(tsdn);
 
-	usize = (alignment == 0) ? s2u(size) : sa2u(size, alignment);
-	assert(usize != 0);
-	return (usize);
+	usize = inallocx(tsdn, size, flags);
+	if (unlikely(usize > LARGE_MAXCLASS)) {
+		return 0;
+	}
+
+	check_entry_exit_locking(tsdn);
+	return usize;
 }
 
-int
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
 je_mallctl(const char *name, void *oldp, size_t *oldlenp, void *newp,
-    size_t newlen)
-{
+    size_t newlen) {
+	int ret;
+	tsd_t *tsd;
 
-	if (malloc_init())
-		return (EAGAIN);
+	if (unlikely(malloc_init())) {
+		return EAGAIN;
+	}
 
-	return (ctl_byname(name, oldp, oldlenp, newp, newlen));
+	tsd = tsd_fetch();
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	ret = ctl_byname(tsd, name, oldp, oldlenp, newp, newlen);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return ret;
 }
 
-int
-je_mallctlnametomib(const char *name, size_t *mibp, size_t *miblenp)
-{
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+je_mallctlnametomib(const char *name, size_t *mibp, size_t *miblenp) {
+	int ret;
 
-	if (malloc_init())
-		return (EAGAIN);
+	if (unlikely(malloc_init())) {
+		return EAGAIN;
+	}
 
-	return (ctl_nametomib(name, mibp, miblenp));
+	tsd_t *tsd = tsd_fetch();
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	ret = ctl_nametomib(tsd, name, mibp, miblenp);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return ret;
 }
 
-int
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
 je_mallctlbymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
-  void *newp, size_t newlen)
-{
+  void *newp, size_t newlen) {
+	int ret;
+	tsd_t *tsd;
 
-	if (malloc_init())
-		return (EAGAIN);
+	if (unlikely(malloc_init())) {
+		return EAGAIN;
+	}
 
-	return (ctl_bymib(mib, miblen, oldp, oldlenp, newp, newlen));
+	tsd = tsd_fetch();
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	ret = ctl_bymib(tsd, mib, miblen, oldp, oldlenp, newp, newlen);
+	check_entry_exit_locking(tsd_tsdn(tsd));
+	return ret;
 }
 
-void
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
 je_malloc_stats_print(void (*write_cb)(void *, const char *), void *cbopaque,
-    const char *opts)
-{
+    const char *opts) {
+	tsdn_t *tsdn;
 
+	tsdn = tsdn_fetch();
+	check_entry_exit_locking(tsdn);
 	stats_print(write_cb, cbopaque, opts);
+	check_entry_exit_locking(tsdn);
 }
 
-size_t
-je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr)
-{
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW
+je_malloc_usable_size(JEMALLOC_USABLE_SIZE_CONST void *ptr) {
 	size_t ret;
+	tsdn_t *tsdn;
 
-	assert(malloc_initialized || IS_INITIALIZER);
-	malloc_thread_init();
-
-	if (config_ivsalloc)
-		ret = ivsalloc(ptr, config_prof);
-	else
-		ret = (ptr != NULL) ? isalloc(ptr, config_prof) : 0;
-
-	return (ret);
-}
-
-/*
- * End non-standard functions.
- */
-/******************************************************************************/
-/*
- * Begin experimental functions.
- */
-#ifdef JEMALLOC_EXPERIMENTAL
-
-int
-je_allocm(void **ptr, size_t *rsize, size_t size, int flags)
-{
-	void *p;
-
-	assert(ptr != NULL);
-
-	p = je_mallocx(size, flags);
-	if (p == NULL)
-		return (ALLOCM_ERR_OOM);
-	if (rsize != NULL)
-		*rsize = isalloc(p, config_prof);
-	*ptr = p;
-	return (ALLOCM_SUCCESS);
-}
-
-int
-je_rallocm(void **ptr, size_t *rsize, size_t size, size_t extra, int flags)
-{
-	int ret;
-	bool no_move = flags & ALLOCM_NO_MOVE;
+	assert(malloc_initialized() || IS_INITIALIZER);
 
-	assert(ptr != NULL);
-	assert(*ptr != NULL);
-	assert(size != 0);
-	assert(SIZE_T_MAX - size >= extra);
+	tsdn = tsdn_fetch();
+	check_entry_exit_locking(tsdn);
 
-	if (no_move) {
-		size_t usize = je_xallocx(*ptr, size, extra, flags);
-		ret = (usize >= size) ? ALLOCM_SUCCESS : ALLOCM_ERR_NOT_MOVED;
-		if (rsize != NULL)
-			*rsize = usize;
+	if (unlikely(ptr == NULL)) {
+		ret = 0;
 	} else {
-		void *p = je_rallocx(*ptr, size+extra, flags);
-		if (p != NULL) {
-			*ptr = p;
-			ret = ALLOCM_SUCCESS;
-		} else
-			ret = ALLOCM_ERR_OOM;
-		if (rsize != NULL)
-			*rsize = isalloc(*ptr, config_prof);
+		if (config_debug || force_ivsalloc) {
+			ret = ivsalloc(tsdn, ptr);
+			assert(force_ivsalloc || ret != 0);
+		} else {
+			ret = isalloc(tsdn, ptr);
+		}
 	}
-	return (ret);
-}
-
-int
-je_sallocm(const void *ptr, size_t *rsize, int flags)
-{
-
-	assert(rsize != NULL);
-	*rsize = je_sallocx(ptr, flags);
-	return (ALLOCM_SUCCESS);
-}
-
-int
-je_dallocm(void *ptr, int flags)
-{
 
-	je_dallocx(ptr, flags);
-	return (ALLOCM_SUCCESS);
+	check_entry_exit_locking(tsdn);
+	return ret;
 }
 
-int
-je_nallocm(size_t *rsize, size_t size, int flags)
-{
-	size_t usize;
-
-	usize = je_nallocx(size, flags);
-	if (usize == 0)
-		return (ALLOCM_ERR_OOM);
-	if (rsize != NULL)
-		*rsize = usize;
-	return (ALLOCM_SUCCESS);
-}
-
-#endif
 /*
- * End experimental functions.
+ * End non-standard functions.
  */
 /******************************************************************************/
 /*
@@ -1966,17 +3001,17 @@ je_nallocm(size_t *rsize, size_t size, int flags)
  * fork/malloc races via the following functions it registers during
  * initialization using pthread_atfork(), but of course that does no good if
  * the allocator isn't fully initialized at fork time.  The following library
- * constructor is a partial solution to this problem.  It may still possible to
- * trigger the deadlock described above, but doing so would involve forking via
- * a library constructor that runs before jemalloc's runs.
+ * constructor is a partial solution to this problem.  It may still be possible
+ * to trigger the deadlock described above, but doing so would involve forking
+ * via a library constructor that runs before jemalloc's runs.
  */
+#ifndef JEMALLOC_JET
 JEMALLOC_ATTR(constructor)
 static void
-jemalloc_constructor(void)
-{
-
+jemalloc_constructor(void) {
 	malloc_init();
 }
+#endif
 
 #ifndef JEMALLOC_MUTEX_INIT_CB
 void
@@ -1986,25 +3021,69 @@ JEMALLOC_EXPORT void
 _malloc_prefork(void)
 #endif
 {
-	unsigned i;
+	tsd_t *tsd;
+	unsigned i, j, narenas;
+	arena_t *arena;
 
 #ifdef JEMALLOC_MUTEX_INIT_CB
-	if (malloc_initialized == false)
+	if (!malloc_initialized()) {
 		return;
+	}
 #endif
-	assert(malloc_initialized);
+	assert(malloc_initialized());
 
+	tsd = tsd_fetch();
+
+	narenas = narenas_total_get();
+
+	witness_prefork(tsd_witness_tsdp_get(tsd));
 	/* Acquire all mutexes in a safe order. */
-	ctl_prefork();
-	prof_prefork();
-	malloc_mutex_prefork(&arenas_lock);
-	for (i = 0; i < narenas_total; i++) {
-		if (arenas[i] != NULL)
-			arena_prefork(arenas[i]);
+	ctl_prefork(tsd_tsdn(tsd));
+	tcache_prefork(tsd_tsdn(tsd));
+	malloc_mutex_prefork(tsd_tsdn(tsd), &arenas_lock);
+	if (have_background_thread) {
+		background_thread_prefork0(tsd_tsdn(tsd));
+	}
+	prof_prefork0(tsd_tsdn(tsd));
+	if (have_background_thread) {
+		background_thread_prefork1(tsd_tsdn(tsd));
+	}
+	/* Break arena prefork into stages to preserve lock order. */
+	for (i = 0; i < 8; i++) {
+		for (j = 0; j < narenas; j++) {
+			if ((arena = arena_get(tsd_tsdn(tsd), j, false)) !=
+			    NULL) {
+				switch (i) {
+				case 0:
+					arena_prefork0(tsd_tsdn(tsd), arena);
+					break;
+				case 1:
+					arena_prefork1(tsd_tsdn(tsd), arena);
+					break;
+				case 2:
+					arena_prefork2(tsd_tsdn(tsd), arena);
+					break;
+				case 3:
+					arena_prefork3(tsd_tsdn(tsd), arena);
+					break;
+				case 4:
+					arena_prefork4(tsd_tsdn(tsd), arena);
+					break;
+				case 5:
+					arena_prefork5(tsd_tsdn(tsd), arena);
+					break;
+				case 6:
+					arena_prefork6(tsd_tsdn(tsd), arena);
+					break;
+				case 7:
+					arena_prefork7(tsd_tsdn(tsd), arena);
+					break;
+				default: not_reached();
+				}
+			}
+		}
 	}
-	chunk_prefork();
-	base_prefork();
-	huge_prefork();
+	prof_prefork1(tsd_tsdn(tsd));
 }
 
 #ifndef JEMALLOC_MUTEX_INIT_CB
@@ -2015,97 +3094,61 @@ JEMALLOC_EXPORT void
 _malloc_postfork(void)
 #endif
 {
-	unsigned i;
+	tsd_t *tsd;
+	unsigned i, narenas;
 
 #ifdef JEMALLOC_MUTEX_INIT_CB
-	if (malloc_initialized == false)
+	if (!malloc_initialized()) {
 		return;
-#endif
-	assert(malloc_initialized);
-
-	/* Release all mutexes, now that fork() has completed. */
-	huge_postfork_parent();
-	base_postfork_parent();
-	chunk_postfork_parent();
-	for (i = 0; i < narenas_total; i++) {
-		if (arenas[i] != NULL)
-			arena_postfork_parent(arenas[i]);
 	}
-	malloc_mutex_postfork_parent(&arenas_lock);
-	prof_postfork_parent();
-	ctl_postfork_parent();
-}
-
-void
-jemalloc_postfork_child(void)
-{
-	unsigned i;
+#endif
+	assert(malloc_initialized());
 
-	assert(malloc_initialized);
+	tsd = tsd_fetch();
 
+	witness_postfork_parent(tsd_witness_tsdp_get(tsd));
 	/* Release all mutexes, now that fork() has completed. */
-	huge_postfork_child();
-	base_postfork_child();
-	chunk_postfork_child();
-	for (i = 0; i < narenas_total; i++) {
-		if (arenas[i] != NULL)
-			arena_postfork_child(arenas[i]);
-	}
-	malloc_mutex_postfork_child(&arenas_lock);
-	prof_postfork_child();
-	ctl_postfork_child();
-}
+	for (i = 0, narenas = narenas_total_get(); i < narenas; i++) {
+		arena_t *arena;
 
-/******************************************************************************/
-/*
- * The following functions are used for TLS allocation/deallocation in static
- * binaries on FreeBSD.  The primary difference between these and i[mcd]alloc()
- * is that these avoid accessing TLS variables.
- */
-
-static void *
-a0alloc(size_t size, bool zero)
-{
-
-	if (malloc_init())
-		return (NULL);
-
-	if (size == 0)
-		size = 1;
-
-	if (size <= arena_maxclass)
-		return (arena_malloc(arenas[0], size, zero, false));
-	else
-		return (huge_malloc(size, zero, huge_dss_prec_get(arenas[0])));
-}
-
-void *
-a0malloc(size_t size)
-{
-
-	return (a0alloc(size, false));
+		if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL) {
+			arena_postfork_parent(tsd_tsdn(tsd), arena);
+		}
+	}
+	prof_postfork_parent(tsd_tsdn(tsd));
+	if (have_background_thread) {
+		background_thread_postfork_parent(tsd_tsdn(tsd));
+	}
+	malloc_mutex_postfork_parent(tsd_tsdn(tsd), &arenas_lock);
+	tcache_postfork_parent(tsd_tsdn(tsd));
+	ctl_postfork_parent(tsd_tsdn(tsd));
 }
 
-void *
-a0calloc(size_t num, size_t size)
-{
+void
+jemalloc_postfork_child(void) {
+	tsd_t *tsd;
+	unsigned i, narenas;
 
-	return (a0alloc(num * size, true));
-}
+	assert(malloc_initialized());
 
-void
-a0free(void *ptr)
-{
-	arena_chunk_t *chunk;
+	tsd = tsd_fetch();
 
-	if (ptr == NULL)
-		return;
+	witness_postfork_child(tsd_witness_tsdp_get(tsd));
+	/* Release all mutexes, now that fork() has completed. */
+	for (i = 0, narenas = narenas_total_get(); i < narenas; i++) {
+		arena_t *arena;
 
-	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-	if (chunk != ptr)
-		arena_dalloc(chunk->arena, chunk, ptr, false);
-	else
-		huge_dalloc(ptr, true);
+		if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL) {
+			arena_postfork_child(tsd_tsdn(tsd), arena);
+		}
+	}
+	prof_postfork_child(tsd_tsdn(tsd));
+	if (have_background_thread) {
+		background_thread_postfork_child(tsd_tsdn(tsd));
+	}
+	malloc_mutex_postfork_child(tsd_tsdn(tsd), &arenas_lock);
+	tcache_postfork_child(tsd_tsdn(tsd));
+	ctl_postfork_child(tsd_tsdn(tsd));
 }
 
 /******************************************************************************/
diff --git a/modules/worldengine/deps/jemalloc/src/jemalloc_cpp.cpp b/modules/worldengine/deps/jemalloc/src/jemalloc_cpp.cpp
new file mode 100644
index 0000000000..844ab398a7
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/jemalloc_cpp.cpp
@@ -0,0 +1,132 @@
+#include <mutex>
+#include <new>
+
+#define JEMALLOC_CPP_CPP_
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#ifdef __cplusplus
+}
+#endif
+
+// All operators in this file are exported.
+
+// Possibly alias hidden versions of malloc and sdallocx to avoid an extra plt
+// thunk?
+//
+// extern __typeof (sdallocx) sdallocx_int
+//  __attribute ((alias ("sdallocx"),
+//		visibility ("hidden")));
+//
+// ... but it needs to work with jemalloc namespaces.
+
+void	*operator new(std::size_t size);
+void	*operator new[](std::size_t size);
+void	*operator new(std::size_t size, const std::nothrow_t &) noexcept;
+void	*operator new[](std::size_t size, const std::nothrow_t &) noexcept;
+void	operator delete(void *ptr) noexcept;
+void	operator delete[](void *ptr) noexcept;
+void	operator delete(void *ptr, const std::nothrow_t &) noexcept;
+void	operator delete[](void *ptr, const std::nothrow_t &) noexcept;
+
+#if __cpp_sized_deallocation >= 201309
+/* C++14's sized-delete operators. */
+void	operator delete(void *ptr, std::size_t size) noexcept;
+void	operator delete[](void *ptr, std::size_t size) noexcept;
+#endif
+
+template <bool IsNoExcept>
+void *
+newImpl(std::size_t size) noexcept(IsNoExcept) {
+	void *ptr = je_malloc(size);
+	if (likely(ptr != nullptr))
+		return ptr;
+
+	while (ptr == nullptr) {
+		std::new_handler handler;
+		// GCC-4.8 and clang 4.0 do not have std::get_new_handler.
+		{
+			static std::mutex mtx;
+			std::lock_guard<std::mutex> lock(mtx);
+
+			handler = std::set_new_handler(nullptr);
+			std::set_new_handler(handler);
+		}
+		if (handler == nullptr)
+			break;
+
+		try {
+			handler();
+		} catch (const std::bad_alloc &) {
+			break;
+		}
+
+		ptr = je_malloc(size);
+	}
+
+	if (ptr == nullptr && !IsNoExcept)
+		std::__throw_bad_alloc();
+	return ptr;
+}
+
+void *
+operator new(std::size_t size) {
+	return newImpl<false>(size);
+}
+
+void *
+operator new[](std::size_t size) {
+	return newImpl<false>(size);
+}
+
+void *
+operator new(std::size_t size, const std::nothrow_t &) noexcept {
+	return newImpl<true>(size);
+}
+
+void *
+operator new[](std::size_t size, const std::nothrow_t &) noexcept {
+	return newImpl<true>(size);
+}
+
+void
+operator delete(void *ptr) noexcept {
+	je_free(ptr);
+}
+
+void
+operator delete[](void *ptr) noexcept {
+	je_free(ptr);
+}
+
+void
+operator delete(void *ptr, const std::nothrow_t &) noexcept {
+	je_free(ptr);
+}
+
+void operator delete[](void *ptr, const std::nothrow_t &) noexcept {
+	je_free(ptr);
+}
+
+#if __cpp_sized_deallocation >= 201309
+
+void
+operator delete(void *ptr, std::size_t size) noexcept {
+	if (unlikely(ptr == nullptr)) {
+		return;
+	}
+	je_sdallocx(ptr, size, /*flags=*/0);
+}
+
+void operator delete[](void *ptr, std::size_t size) noexcept {
+	if (unlikely(ptr == nullptr)) {
+		return;
+	}
+	je_sdallocx(ptr, size, /*flags=*/0);
+}
+
+#endif  // __cpp_sized_deallocation
diff --git a/modules/worldengine/deps/jemalloc/src/large.c b/modules/worldengine/deps/jemalloc/src/large.c
new file mode 100644
index 0000000000..27a2c67987
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/large.c
@@ -0,0 +1,371 @@
+#define JEMALLOC_LARGE_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
+#include "jemalloc/internal/util.h"
+
+/******************************************************************************/
+
+void *
+large_malloc(tsdn_t *tsdn, arena_t *arena, size_t usize, bool zero) {
+	assert(usize == sz_s2u(usize));
+
+	return large_palloc(tsdn, arena, usize, CACHELINE, zero);
+}
+
+void *
+large_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero) {
+	size_t ausize;
+	extent_t *extent;
+	bool is_zeroed;
+	UNUSED bool idump JEMALLOC_CC_SILENCE_INIT(false);
+
+	assert(!tsdn_null(tsdn) || arena != NULL);
+
+	ausize = sz_sa2u(usize, alignment);
+	if (unlikely(ausize == 0 || ausize > LARGE_MAXCLASS)) {
+		return NULL;
+	}
+
+	if (config_fill && unlikely(opt_zero)) {
+		zero = true;
+	}
+	/*
+	 * Copy zero into is_zeroed and pass the copy when allocating the
+	 * extent, so that it is possible to make correct junk/zero fill
+	 * decisions below, even if is_zeroed ends up true when zero is false.
+	 */
+	is_zeroed = zero;
+	if (likely(!tsdn_null(tsdn))) {
+		arena = arena_choose(tsdn_tsd(tsdn), arena);
+	}
+	if (unlikely(arena == NULL) || (extent = arena_extent_alloc_large(tsdn,
+	    arena, usize, alignment, &is_zeroed)) == NULL) {
+		return NULL;
+	}
+
+	/* See comments in arena_bin_slabs_full_insert(). */
+	if (!arena_is_auto(arena)) {
+		/* Insert extent into large. */
+		malloc_mutex_lock(tsdn, &arena->large_mtx);
+		extent_list_append(&arena->large, extent);
+		malloc_mutex_unlock(tsdn, &arena->large_mtx);
+	}
+	if (config_prof && arena_prof_accum(tsdn, arena, usize)) {
+		prof_idump(tsdn);
+	}
+
+	if (zero) {
+		assert(is_zeroed);
+	} else if (config_fill && unlikely(opt_junk_alloc)) {
+		memset(extent_addr_get(extent), JEMALLOC_ALLOC_JUNK,
+		    extent_usize_get(extent));
+	}
+
+	arena_decay_tick(tsdn, arena);
+	return extent_addr_get(extent);
+}
+
+static void
+large_dalloc_junk_impl(void *ptr, size_t size) {
+	memset(ptr, JEMALLOC_FREE_JUNK, size);
+}
+large_dalloc_junk_t *JET_MUTABLE large_dalloc_junk = large_dalloc_junk_impl;
+
+static void
+large_dalloc_maybe_junk_impl(void *ptr, size_t size) {
+	if (config_fill && have_dss && unlikely(opt_junk_free)) {
+		/*
+		 * Only bother junk filling if the extent isn't about to be
+		 * unmapped.
+		 */
+		if (opt_retain || (have_dss && extent_in_dss(ptr))) {
+			large_dalloc_junk(ptr, size);
+		}
+	}
+}
+large_dalloc_maybe_junk_t *JET_MUTABLE large_dalloc_maybe_junk =
+    large_dalloc_maybe_junk_impl;
+
+static bool
+large_ralloc_no_move_shrink(tsdn_t *tsdn, extent_t *extent, size_t usize) {
+	arena_t *arena = extent_arena_get(extent);
+	size_t oldusize = extent_usize_get(extent);
+	extent_hooks_t *extent_hooks = extent_hooks_get(arena);
+	size_t diff = extent_size_get(extent) - (usize + sz_large_pad);
+
+	assert(oldusize > usize);
+
+	if (extent_hooks->split == NULL) {
+		return true;
+	}
+
+	/* Split excess pages. */
+	if (diff != 0) {
+		extent_t *trail = extent_split_wrapper(tsdn, arena,
+		    &extent_hooks, extent, usize + sz_large_pad,
+		    sz_size2index(usize), false, diff, NSIZES, false);
+		if (trail == NULL) {
+			return true;
+		}
+
+		if (config_fill && unlikely(opt_junk_free)) {
+			large_dalloc_maybe_junk(extent_addr_get(trail),
+			    extent_size_get(trail));
+		}
+
+		arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, trail);
+	}
+
+	arena_extent_ralloc_large_shrink(tsdn, arena, extent, oldusize);
+
+	return false;
+}
+
+static bool
+large_ralloc_no_move_expand(tsdn_t *tsdn, extent_t *extent, size_t usize,
+    bool zero) {
+	arena_t *arena = extent_arena_get(extent);
+	size_t oldusize = extent_usize_get(extent);
+	extent_hooks_t *extent_hooks = extent_hooks_get(arena);
+	size_t trailsize = usize - oldusize;
+
+	if (extent_hooks->merge == NULL) {
+		return true;
+	}
+
+	if (config_fill && unlikely(opt_zero)) {
+		zero = true;
+	}
+	/*
+	 * Copy zero into is_zeroed_trail and pass the copy when allocating the
+	 * extent, so that it is possible to make correct junk/zero fill
+	 * decisions below, even if is_zeroed_trail ends up true when zero is
+	 * false.
+	 */
+	bool is_zeroed_trail = zero;
+	bool commit = true;
+	extent_t *trail;
+	bool new_mapping;
+	if ((trail = extents_alloc(tsdn, arena, &extent_hooks,
+	    &arena->extents_dirty, extent_past_get(extent), trailsize, 0,
+	    CACHELINE, false, NSIZES, &is_zeroed_trail, &commit)) != NULL
+	    || (trail = extents_alloc(tsdn, arena, &extent_hooks,
+	    &arena->extents_muzzy, extent_past_get(extent), trailsize, 0,
+	    CACHELINE, false, NSIZES, &is_zeroed_trail, &commit)) != NULL) {
+		if (config_stats) {
+			new_mapping = false;
+		}
+	} else {
+		if ((trail = extent_alloc_wrapper(tsdn, arena, &extent_hooks,
+		    extent_past_get(extent), trailsize, 0, CACHELINE, false,
+		    NSIZES, &is_zeroed_trail, &commit)) == NULL) {
+			return true;
+		}
+		if (config_stats) {
+			new_mapping = true;
+		}
+	}
+
+	if (extent_merge_wrapper(tsdn, arena, &extent_hooks, extent, trail)) {
+		extent_dalloc_wrapper(tsdn, arena, &extent_hooks, trail);
+		return true;
+	}
+	rtree_ctx_t rtree_ctx_fallback;
+	rtree_ctx_t *rtree_ctx = tsdn_rtree_ctx(tsdn, &rtree_ctx_fallback);
+	szind_t szind = sz_size2index(usize);
+	extent_szind_set(extent, szind);
+	rtree_szind_slab_update(tsdn, &extents_rtree, rtree_ctx,
+	    (uintptr_t)extent_addr_get(extent), szind, false);
+
+	if (config_stats && new_mapping) {
+		arena_stats_mapped_add(tsdn, &arena->stats, trailsize);
+	}
+
+	if (zero) {
+		if (config_cache_oblivious) {
+			/*
+			 * Zero the trailing bytes of the original allocation's
+			 * last page, since they are in an indeterminate state.
+			 * There will always be trailing bytes, because ptr's
+			 * offset from the beginning of the extent is a multiple
+			 * of CACHELINE in [0 .. PAGE).
+			 */
+			void *zbase = (void *)
+			    ((uintptr_t)extent_addr_get(extent) + oldusize);
+			void *zpast = PAGE_ADDR2BASE((void *)((uintptr_t)zbase +
+			    PAGE));
+			size_t nzero = (uintptr_t)zpast - (uintptr_t)zbase;
+			assert(nzero > 0);
+			memset(zbase, 0, nzero);
+		}
+		assert(is_zeroed_trail);
+	} else if (config_fill && unlikely(opt_junk_alloc)) {
+		memset((void *)((uintptr_t)extent_addr_get(extent) + oldusize),
+		    JEMALLOC_ALLOC_JUNK, usize - oldusize);
+	}
+
+	arena_extent_ralloc_large_expand(tsdn, arena, extent, oldusize);
+
+	return false;
+}
+
+bool
+large_ralloc_no_move(tsdn_t *tsdn, extent_t *extent, size_t usize_min,
+    size_t usize_max, bool zero) {
+	size_t oldusize = extent_usize_get(extent);
+
+	/* The following should have been caught by callers. */
+	assert(usize_min > 0 && usize_max <= LARGE_MAXCLASS);
+	/* Both allocation sizes must be large to avoid a move. */
+	assert(oldusize >= LARGE_MINCLASS && usize_max >= LARGE_MINCLASS);
+
+	if (usize_max > oldusize) {
+		/* Attempt to expand the allocation in-place. */
+		if (!large_ralloc_no_move_expand(tsdn, extent, usize_max,
+		    zero)) {
+			arena_decay_tick(tsdn, extent_arena_get(extent));
+			return false;
+		}
+		/* Try again, this time with usize_min. */
+		if (usize_min < usize_max && usize_min > oldusize &&
+		    large_ralloc_no_move_expand(tsdn, extent, usize_min,
+		    zero)) {
+			arena_decay_tick(tsdn, extent_arena_get(extent));
+			return false;
+		}
+	}
+
+	/*
+	 * Avoid moving the allocation if the existing extent size accommodates
+	 * the new size.
+	 */
+	if (oldusize >= usize_min && oldusize <= usize_max) {
+		arena_decay_tick(tsdn, extent_arena_get(extent));
+		return false;
+	}
+
+	/* Attempt to shrink the allocation in-place. */
+	if (oldusize > usize_max) {
+		if (!large_ralloc_no_move_shrink(tsdn, extent, usize_max)) {
+			arena_decay_tick(tsdn, extent_arena_get(extent));
+			return false;
+		}
+	}
+	return true;
+}
+
+static void *
+large_ralloc_move_helper(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, bool zero) {
+	if (alignment <= CACHELINE) {
+		return large_malloc(tsdn, arena, usize, zero);
+	}
+	return large_palloc(tsdn, arena, usize, alignment, zero);
+}
+
+void *
+large_ralloc(tsdn_t *tsdn, arena_t *arena, extent_t *extent, size_t usize,
+    size_t alignment, bool zero, tcache_t *tcache) {
+	size_t oldusize = extent_usize_get(extent);
+
+	/* The following should have been caught by callers. */
+	assert(usize > 0 && usize <= LARGE_MAXCLASS);
+	/* Both allocation sizes must be large to avoid a move. */
+	assert(oldusize >= LARGE_MINCLASS && usize >= LARGE_MINCLASS);
+
+	/* Try to avoid moving the allocation. */
+	if (!large_ralloc_no_move(tsdn, extent, usize, usize, zero)) {
+		return extent_addr_get(extent);
+	}
+
+	/*
+	 * usize and old size are different enough that we need to use a
+	 * different size class.  In that case, fall back to allocating new
+	 * space and copying.
+	 */
+	void *ret = large_ralloc_move_helper(tsdn, arena, usize, alignment,
+	    zero);
+	if (ret == NULL) {
+		return NULL;
+	}
+
+	size_t copysize = (usize < oldusize) ? usize : oldusize;
+	memcpy(ret, extent_addr_get(extent), copysize);
+	isdalloct(tsdn, extent_addr_get(extent), oldusize, tcache, NULL, true);
+	return ret;
+}
+
+/*
+ * junked_locked indicates whether the extent's data have been junk-filled, and
+ * whether the arena's large_mtx is currently held.
+ */
+static void
+large_dalloc_prep_impl(tsdn_t *tsdn, arena_t *arena, extent_t *extent,
+    bool junked_locked) {
+	if (!junked_locked) {
+		/* See comments in arena_bin_slabs_full_insert(). */
+		if (!arena_is_auto(arena)) {
+			malloc_mutex_lock(tsdn, &arena->large_mtx);
+			extent_list_remove(&arena->large, extent);
+			malloc_mutex_unlock(tsdn, &arena->large_mtx);
+		}
+		large_dalloc_maybe_junk(extent_addr_get(extent),
+		    extent_usize_get(extent));
+	} else {
+		malloc_mutex_assert_owner(tsdn, &arena->large_mtx);
+		if (!arena_is_auto(arena)) {
+			extent_list_remove(&arena->large, extent);
+		}
+	}
+	arena_extent_dalloc_large_prep(tsdn, arena, extent);
+}
+
+static void
+large_dalloc_finish_impl(tsdn_t *tsdn, arena_t *arena, extent_t *extent) {
+	extent_hooks_t *extent_hooks = EXTENT_HOOKS_INITIALIZER;
+	arena_extents_dirty_dalloc(tsdn, arena, &extent_hooks, extent);
+}
+
+void
+large_dalloc_prep_junked_locked(tsdn_t *tsdn, extent_t *extent) {
+	large_dalloc_prep_impl(tsdn, extent_arena_get(extent), extent, true);
+}
+
+void
+large_dalloc_finish(tsdn_t *tsdn, extent_t *extent) {
+	large_dalloc_finish_impl(tsdn, extent_arena_get(extent), extent);
+}
+
+void
+large_dalloc(tsdn_t *tsdn, extent_t *extent) {
+	arena_t *arena = extent_arena_get(extent);
+	large_dalloc_prep_impl(tsdn, arena, extent, false);
+	large_dalloc_finish_impl(tsdn, arena, extent);
+	arena_decay_tick(tsdn, arena);
+}
+
+size_t
+large_salloc(tsdn_t *tsdn, const extent_t *extent) {
+	return extent_usize_get(extent);
+}
+
+prof_tctx_t *
+large_prof_tctx_get(tsdn_t *tsdn, const extent_t *extent) {
+	return extent_prof_tctx_get(extent);
+}
+
+void
+large_prof_tctx_set(tsdn_t *tsdn, extent_t *extent, prof_tctx_t *tctx) {
+	extent_prof_tctx_set(extent, tctx);
+}
+
+void
+large_prof_tctx_reset(tsdn_t *tsdn, extent_t *extent) {
+	large_prof_tctx_set(tsdn, extent, (prof_tctx_t *)(uintptr_t)1U);
+}
diff --git a/modules/worldengine/deps/jemalloc/src/malloc_io.c b/modules/worldengine/deps/jemalloc/src/malloc_io.c
new file mode 100644
index 0000000000..6b99afcd3f
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/malloc_io.c
@@ -0,0 +1,689 @@
+#define JEMALLOC_MALLOC_IO_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/util.h"
+
+#ifdef assert
+#  undef assert
+#endif
+#ifdef not_reached
+#  undef not_reached
+#endif
+#ifdef not_implemented
+#  undef not_implemented
+#endif
+#ifdef assert_not_implemented
+#  undef assert_not_implemented
+#endif
+
+/*
+ * Define simple versions of assertion macros that won't recurse in case
+ * of assertion failures in malloc_*printf().
+ */
+#define assert(e) do {							\
+	if (config_debug && !(e)) {					\
+		malloc_write("<jemalloc>: Failed assertion\n");		\
+		abort();						\
+	}								\
+} while (0)
+
+#define not_reached() do {						\
+	if (config_debug) {						\
+		malloc_write("<jemalloc>: Unreachable code reached\n");	\
+		abort();						\
+	}								\
+	unreachable();							\
+} while (0)
+
+#define not_implemented() do {						\
+	if (config_debug) {						\
+		malloc_write("<jemalloc>: Not implemented\n");		\
+		abort();						\
+	}								\
+} while (0)
+
+#define assert_not_implemented(e) do {					\
+	if (unlikely(config_debug && !(e))) {				\
+		not_implemented();					\
+	}								\
+} while (0)
+
+/******************************************************************************/
+/* Function prototypes for non-inline static functions. */
+
+static void wrtmessage(void *cbopaque, const char *s);
+#define U2S_BUFSIZE ((1U << (LG_SIZEOF_INTMAX_T + 3)) + 1)
+static char *u2s(uintmax_t x, unsigned base, bool uppercase, char *s,
+    size_t *slen_p);
+#define D2S_BUFSIZE (1 + U2S_BUFSIZE)
+static char *d2s(intmax_t x, char sign, char *s, size_t *slen_p);
+#define O2S_BUFSIZE (1 + U2S_BUFSIZE)
+static char *o2s(uintmax_t x, bool alt_form, char *s, size_t *slen_p);
+#define X2S_BUFSIZE (2 + U2S_BUFSIZE)
+static char *x2s(uintmax_t x, bool alt_form, bool uppercase, char *s,
+    size_t *slen_p);
+
+/******************************************************************************/
+
+/* malloc_message() setup. */
+static void
+wrtmessage(void *cbopaque, const char *s) {
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_write)
+	/*
+	 * Use syscall(2) rather than write(2) when possible in order to avoid
+	 * the possibility of memory allocation within libc.  This is necessary
+	 * on FreeBSD; most operating systems do not have this problem though.
+	 *
+	 * syscall() returns long or int, depending on platform, so capture the
+	 * unused result in the widest plausible type to avoid compiler
+	 * warnings.
+	 */
+	UNUSED long result = syscall(SYS_write, STDERR_FILENO, s, strlen(s));
+#else
+	UNUSED ssize_t result = write(STDERR_FILENO, s, strlen(s));
+#endif
+}
+
+JEMALLOC_EXPORT void	(*je_malloc_message)(void *, const char *s);
+
+/*
+ * Wrapper around malloc_message() that avoids the need for
+ * je_malloc_message(...) throughout the code.
+ */
+void
+malloc_write(const char *s) {
+	if (je_malloc_message != NULL) {
+		je_malloc_message(NULL, s);
+	} else {
+		wrtmessage(NULL, s);
+	}
+}
+
+/*
+ * glibc provides a non-standard strerror_r() when _GNU_SOURCE is defined, so
+ * provide a wrapper.
+ */
+int
+buferror(int err, char *buf, size_t buflen) {
+#ifdef _WIN32
+	FormatMessageA(FORMAT_MESSAGE_FROM_SYSTEM, NULL, err, 0,
+	    (LPSTR)buf, (DWORD)buflen, NULL);
+	return 0;
+#elif defined(__GLIBC__) && defined(_GNU_SOURCE)
+	char *b = strerror_r(err, buf, buflen);
+	if (b != buf) {
+		strncpy(buf, b, buflen);
+		buf[buflen-1] = '\0';
+	}
+	return 0;
+#else
+	return strerror_r(err, buf, buflen);
+#endif
+}
+
+uintmax_t
+malloc_strtoumax(const char *restrict nptr, char **restrict endptr, int base) {
+	uintmax_t ret, digit;
+	unsigned b;
+	bool neg;
+	const char *p, *ns;
+
+	p = nptr;
+	if (base < 0 || base == 1 || base > 36) {
+		ns = p;
+		set_errno(EINVAL);
+		ret = UINTMAX_MAX;
+		goto label_return;
+	}
+	b = base;
+
+	/* Swallow leading whitespace and get sign, if any. */
+	neg = false;
+	while (true) {
+		switch (*p) {
+		case '\t': case '\n': case '\v': case '\f': case '\r': case ' ':
+			p++;
+			break;
+		case '-':
+			neg = true;
+			/* Fall through. */
+		case '+':
+			p++;
+			/* Fall through. */
+		default:
+			goto label_prefix;
+		}
+	}
+
+	/* Get prefix, if any. */
+	label_prefix:
+	/*
+	 * Note where the first non-whitespace/sign character is so that it is
+	 * possible to tell whether any digits are consumed (e.g., "  0" vs.
+	 * "  -x").
+	 */
+	ns = p;
+	if (*p == '0') {
+		switch (p[1]) {
+		case '0': case '1': case '2': case '3': case '4': case '5':
+		case '6': case '7':
+			if (b == 0) {
+				b = 8;
+			}
+			if (b == 8) {
+				p++;
+			}
+			break;
+		case 'X': case 'x':
+			switch (p[2]) {
+			case '0': case '1': case '2': case '3': case '4':
+			case '5': case '6': case '7': case '8': case '9':
+			case 'A': case 'B': case 'C': case 'D': case 'E':
+			case 'F':
+			case 'a': case 'b': case 'c': case 'd': case 'e':
+			case 'f':
+				if (b == 0) {
+					b = 16;
+				}
+				if (b == 16) {
+					p += 2;
+				}
+				break;
+			default:
+				break;
+			}
+			break;
+		default:
+			p++;
+			ret = 0;
+			goto label_return;
+		}
+	}
+	if (b == 0) {
+		b = 10;
+	}
+
+	/* Convert. */
+	ret = 0;
+	while ((*p >= '0' && *p <= '9' && (digit = *p - '0') < b)
+	    || (*p >= 'A' && *p <= 'Z' && (digit = 10 + *p - 'A') < b)
+	    || (*p >= 'a' && *p <= 'z' && (digit = 10 + *p - 'a') < b)) {
+		uintmax_t pret = ret;
+		ret *= b;
+		ret += digit;
+		if (ret < pret) {
+			/* Overflow. */
+			set_errno(ERANGE);
+			ret = UINTMAX_MAX;
+			goto label_return;
+		}
+		p++;
+	}
+	if (neg) {
+		ret = (uintmax_t)(-((intmax_t)ret));
+	}
+
+	if (p == ns) {
+		/* No conversion performed. */
+		set_errno(EINVAL);
+		ret = UINTMAX_MAX;
+		goto label_return;
+	}
+
+label_return:
+	if (endptr != NULL) {
+		if (p == ns) {
+			/* No characters were converted. */
+			*endptr = (char *)nptr;
+		} else {
+			*endptr = (char *)p;
+		}
+	}
+	return ret;
+}
+
+static char *
+u2s(uintmax_t x, unsigned base, bool uppercase, char *s, size_t *slen_p) {
+	unsigned i;
+
+	i = U2S_BUFSIZE - 1;
+	s[i] = '\0';
+	switch (base) {
+	case 10:
+		do {
+			i--;
+			s[i] = "0123456789"[x % (uint64_t)10];
+			x /= (uint64_t)10;
+		} while (x > 0);
+		break;
+	case 16: {
+		const char *digits = (uppercase)
+		    ? "0123456789ABCDEF"
+		    : "0123456789abcdef";
+
+		do {
+			i--;
+			s[i] = digits[x & 0xf];
+			x >>= 4;
+		} while (x > 0);
+		break;
+	} default: {
+		const char *digits = (uppercase)
+		    ? "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+		    : "0123456789abcdefghijklmnopqrstuvwxyz";
+
+		assert(base >= 2 && base <= 36);
+		do {
+			i--;
+			s[i] = digits[x % (uint64_t)base];
+			x /= (uint64_t)base;
+		} while (x > 0);
+	}}
+
+	*slen_p = U2S_BUFSIZE - 1 - i;
+	return &s[i];
+}
+
+static char *
+d2s(intmax_t x, char sign, char *s, size_t *slen_p) {
+	bool neg;
+
+	if ((neg = (x < 0))) {
+		x = -x;
+	}
+	s = u2s(x, 10, false, s, slen_p);
+	if (neg) {
+		sign = '-';
+	}
+	switch (sign) {
+	case '-':
+		if (!neg) {
+			break;
+		}
+		/* Fall through. */
+	case ' ':
+	case '+':
+		s--;
+		(*slen_p)++;
+		*s = sign;
+		break;
+	default: not_reached();
+	}
+	return s;
+}
+
+static char *
+o2s(uintmax_t x, bool alt_form, char *s, size_t *slen_p) {
+	s = u2s(x, 8, false, s, slen_p);
+	if (alt_form && *s != '0') {
+		s--;
+		(*slen_p)++;
+		*s = '0';
+	}
+	return s;
+}
+
+static char *
+x2s(uintmax_t x, bool alt_form, bool uppercase, char *s, size_t *slen_p) {
+	s = u2s(x, 16, uppercase, s, slen_p);
+	if (alt_form) {
+		s -= 2;
+		(*slen_p) += 2;
+		memcpy(s, uppercase ? "0X" : "0x", 2);
+	}
+	return s;
+}
+
+size_t
+malloc_vsnprintf(char *str, size_t size, const char *format, va_list ap) {
+	size_t i;
+	const char *f;
+
+#define APPEND_C(c) do {						\
+	if (i < size) {							\
+		str[i] = (c);						\
+	}								\
+	i++;								\
+} while (0)
+#define APPEND_S(s, slen) do {						\
+	if (i < size) {							\
+		size_t cpylen = (slen <= size - i) ? slen : size - i;	\
+		memcpy(&str[i], s, cpylen);				\
+	}								\
+	i += slen;							\
+} while (0)
+#define APPEND_PADDED_S(s, slen, width, left_justify) do {		\
+	/* Left padding. */						\
+	size_t pad_len = (width == -1) ? 0 : ((slen < (size_t)width) ?	\
+	    (size_t)width - slen : 0);					\
+	if (!left_justify && pad_len != 0) {				\
+		size_t j;						\
+		for (j = 0; j < pad_len; j++) {				\
+			APPEND_C(' ');					\
+		}							\
+	}								\
+	/* Value. */							\
+	APPEND_S(s, slen);						\
+	/* Right padding. */						\
+	if (left_justify && pad_len != 0) {				\
+		size_t j;						\
+		for (j = 0; j < pad_len; j++) {				\
+			APPEND_C(' ');					\
+		}							\
+	}								\
+} while (0)
+#define GET_ARG_NUMERIC(val, len) do {					\
+	switch (len) {							\
+	case '?':							\
+		val = va_arg(ap, int);					\
+		break;							\
+	case '?' | 0x80:						\
+		val = va_arg(ap, unsigned int);				\
+		break;							\
+	case 'l':							\
+		val = va_arg(ap, long);					\
+		break;							\
+	case 'l' | 0x80:						\
+		val = va_arg(ap, unsigned long);			\
+		break;							\
+	case 'q':							\
+		val = va_arg(ap, long long);				\
+		break;							\
+	case 'q' | 0x80:						\
+		val = va_arg(ap, unsigned long long);			\
+		break;							\
+	case 'j':							\
+		val = va_arg(ap, intmax_t);				\
+		break;							\
+	case 'j' | 0x80:						\
+		val = va_arg(ap, uintmax_t);				\
+		break;							\
+	case 't':							\
+		val = va_arg(ap, ptrdiff_t);				\
+		break;							\
+	case 'z':							\
+		val = va_arg(ap, ssize_t);				\
+		break;							\
+	case 'z' | 0x80:						\
+		val = va_arg(ap, size_t);				\
+		break;							\
+	case 'p': /* Synthetic; used for %p. */				\
+		val = va_arg(ap, uintptr_t);				\
+		break;							\
+	default:							\
+		not_reached();						\
+		val = 0;						\
+	}								\
+} while (0)
+
+	i = 0;
+	f = format;
+	while (true) {
+		switch (*f) {
+		case '\0': goto label_out;
+		case '%': {
+			bool alt_form = false;
+			bool left_justify = false;
+			bool plus_space = false;
+			bool plus_plus = false;
+			int prec = -1;
+			int width = -1;
+			unsigned char len = '?';
+			char *s;
+			size_t slen;
+
+			f++;
+			/* Flags. */
+			while (true) {
+				switch (*f) {
+				case '#':
+					assert(!alt_form);
+					alt_form = true;
+					break;
+				case '-':
+					assert(!left_justify);
+					left_justify = true;
+					break;
+				case ' ':
+					assert(!plus_space);
+					plus_space = true;
+					break;
+				case '+':
+					assert(!plus_plus);
+					plus_plus = true;
+					break;
+				default: goto label_width;
+				}
+				f++;
+			}
+			/* Width. */
+			label_width:
+			switch (*f) {
+			case '*':
+				width = va_arg(ap, int);
+				f++;
+				if (width < 0) {
+					left_justify = true;
+					width = -width;
+				}
+				break;
+			case '0': case '1': case '2': case '3': case '4':
+			case '5': case '6': case '7': case '8': case '9': {
+				uintmax_t uwidth;
+				set_errno(0);
+				uwidth = malloc_strtoumax(f, (char **)&f, 10);
+				assert(uwidth != UINTMAX_MAX || get_errno() !=
+				    ERANGE);
+				width = (int)uwidth;
+				break;
+			} default:
+				break;
+			}
+			/* Width/precision separator. */
+			if (*f == '.') {
+				f++;
+			} else {
+				goto label_length;
+			}
+			/* Precision. */
+			switch (*f) {
+			case '*':
+				prec = va_arg(ap, int);
+				f++;
+				break;
+			case '0': case '1': case '2': case '3': case '4':
+			case '5': case '6': case '7': case '8': case '9': {
+				uintmax_t uprec;
+				set_errno(0);
+				uprec = malloc_strtoumax(f, (char **)&f, 10);
+				assert(uprec != UINTMAX_MAX || get_errno() !=
+				    ERANGE);
+				prec = (int)uprec;
+				break;
+			}
+			default: break;
+			}
+			/* Length. */
+			label_length:
+			switch (*f) {
+			case 'l':
+				f++;
+				if (*f == 'l') {
+					len = 'q';
+					f++;
+				} else {
+					len = 'l';
+				}
+				break;
+			case 'q': case 'j': case 't': case 'z':
+				len = *f;
+				f++;
+				break;
+			default: break;
+			}
+			/* Conversion specifier. */
+			switch (*f) {
+			case '%':
+				/* %% */
+				APPEND_C(*f);
+				f++;
+				break;
+			case 'd': case 'i': {
+				intmax_t val JEMALLOC_CC_SILENCE_INIT(0);
+				char buf[D2S_BUFSIZE];
+
+				GET_ARG_NUMERIC(val, len);
+				s = d2s(val, (plus_plus ? '+' : (plus_space ?
+				    ' ' : '-')), buf, &slen);
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			} case 'o': {
+				uintmax_t val JEMALLOC_CC_SILENCE_INIT(0);
+				char buf[O2S_BUFSIZE];
+
+				GET_ARG_NUMERIC(val, len | 0x80);
+				s = o2s(val, alt_form, buf, &slen);
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			} case 'u': {
+				uintmax_t val JEMALLOC_CC_SILENCE_INIT(0);
+				char buf[U2S_BUFSIZE];
+
+				GET_ARG_NUMERIC(val, len | 0x80);
+				s = u2s(val, 10, false, buf, &slen);
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			} case 'x': case 'X': {
+				uintmax_t val JEMALLOC_CC_SILENCE_INIT(0);
+				char buf[X2S_BUFSIZE];
+
+				GET_ARG_NUMERIC(val, len | 0x80);
+				s = x2s(val, alt_form, *f == 'X', buf, &slen);
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			} case 'c': {
+				unsigned char val;
+				char buf[2];
+
+				assert(len == '?' || len == 'l');
+				assert_not_implemented(len != 'l');
+				val = va_arg(ap, int);
+				buf[0] = val;
+				buf[1] = '\0';
+				APPEND_PADDED_S(buf, 1, width, left_justify);
+				f++;
+				break;
+			} case 's':
+				assert(len == '?' || len == 'l');
+				assert_not_implemented(len != 'l');
+				s = va_arg(ap, char *);
+				slen = (prec < 0) ? strlen(s) : (size_t)prec;
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			case 'p': {
+				uintmax_t val;
+				char buf[X2S_BUFSIZE];
+
+				GET_ARG_NUMERIC(val, 'p');
+				s = x2s(val, true, false, buf, &slen);
+				APPEND_PADDED_S(s, slen, width, left_justify);
+				f++;
+				break;
+			} default: not_reached();
+			}
+			break;
+		} default: {
+			APPEND_C(*f);
+			f++;
+			break;
+		}}
+	}
+	label_out:
+	if (i < size) {
+		str[i] = '\0';
+	} else {
+		str[size - 1] = '\0';
+	}
+
+#undef APPEND_C
+#undef APPEND_S
+#undef APPEND_PADDED_S
+#undef GET_ARG_NUMERIC
+	return i;
+}
+
+JEMALLOC_FORMAT_PRINTF(3, 4)
+size_t
+malloc_snprintf(char *str, size_t size, const char *format, ...) {
+	size_t ret;
+	va_list ap;
+
+	va_start(ap, format);
+	ret = malloc_vsnprintf(str, size, format, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+void
+malloc_vcprintf(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *format, va_list ap) {
+	char buf[MALLOC_PRINTF_BUFSIZE];
+
+	if (write_cb == NULL) {
+		/*
+		 * The caller did not provide an alternate write_cb callback
+		 * function, so use the default one.  malloc_write() is an
+		 * inline function, so use malloc_message() directly here.
+		 */
+		write_cb = (je_malloc_message != NULL) ? je_malloc_message :
+		    wrtmessage;
+		cbopaque = NULL;
+	}
+
+	malloc_vsnprintf(buf, sizeof(buf), format, ap);
+	write_cb(cbopaque, buf);
+}
+
+/*
+ * Print to a callback function in such a way as to (hopefully) avoid memory
+ * allocation.
+ */
+JEMALLOC_FORMAT_PRINTF(3, 4)
+void
+malloc_cprintf(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *format, ...) {
+	va_list ap;
+
+	va_start(ap, format);
+	malloc_vcprintf(write_cb, cbopaque, format, ap);
+	va_end(ap);
+}
+
+/* Print to stderr in such a way as to avoid memory allocation. */
+JEMALLOC_FORMAT_PRINTF(1, 2)
+void
+malloc_printf(const char *format, ...) {
+	va_list ap;
+
+	va_start(ap, format);
+	malloc_vcprintf(NULL, NULL, format, ap);
+	va_end(ap);
+}
+
+/*
+ * Restore normal assertion macros, in order to make it possible to compile all
+ * C files as a single concatenation.
+ */
+#undef assert
+#undef not_reached
+#undef not_implemented
+#undef assert_not_implemented
+#include "jemalloc/internal/assert.h"
diff --git a/modules/worldengine/deps/jemalloc/src/mutex.c b/modules/worldengine/deps/jemalloc/src/mutex.c
index 788eca3870..a528ef0c24 100644
--- a/modules/worldengine/deps/jemalloc/src/mutex.c
+++ b/modules/worldengine/deps/jemalloc/src/mutex.c
@@ -1,12 +1,12 @@
-#define	JEMALLOC_MUTEX_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_MUTEX_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
 
-#if defined(JEMALLOC_LAZY_LOCK) && !defined(_WIN32)
-#include <dlfcn.h>
-#endif
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/malloc_io.h"
 
 #ifndef _CRT_SPINCOUNT
-#define	_CRT_SPINCOUNT 4000
+#define _CRT_SPINCOUNT 4000
 #endif
 
 /******************************************************************************/
@@ -20,10 +20,6 @@ static bool		postpone_init = true;
 static malloc_mutex_t	*postponed_mutexes = NULL;
 #endif
 
-#if defined(JEMALLOC_LAZY_LOCK) && !defined(_WIN32)
-static void	pthread_create_once(void);
-#endif
-
 /******************************************************************************/
 /*
  * We intercept pthread_create() calls in order to toggle isthreaded if the
@@ -31,33 +27,11 @@ static void	pthread_create_once(void);
  */
 
 #if defined(JEMALLOC_LAZY_LOCK) && !defined(_WIN32)
-static int (*pthread_create_fptr)(pthread_t *__restrict, const pthread_attr_t *,
-    void *(*)(void *), void *__restrict);
-
-static void
-pthread_create_once(void)
-{
-
-	pthread_create_fptr = dlsym(RTLD_NEXT, "pthread_create");
-	if (pthread_create_fptr == NULL) {
-		malloc_write("<jemalloc>: Error in dlsym(RTLD_NEXT, "
-		    "\"pthread_create\")\n");
-		abort();
-	}
-
-	isthreaded = true;
-}
-
 JEMALLOC_EXPORT int
 pthread_create(pthread_t *__restrict thread,
     const pthread_attr_t *__restrict attr, void *(*start_routine)(void *),
-    void *__restrict arg)
-{
-	static pthread_once_t once_control = PTHREAD_ONCE_INIT;
-
-	pthread_once(&once_control, pthread_create_once);
-
-	return (pthread_create_fptr(thread, attr, start_routine, arg));
+    void *__restrict arg) {
+	return pthread_create_wrapper(thread, attr, start_routine, arg);
 }
 #endif
 
@@ -68,14 +42,108 @@ JEMALLOC_EXPORT int	_pthread_mutex_init_calloc_cb(pthread_mutex_t *mutex,
     void *(calloc_cb)(size_t, size_t));
 #endif
 
-bool
-malloc_mutex_init(malloc_mutex_t *mutex)
-{
+void
+malloc_mutex_lock_slow(malloc_mutex_t *mutex) {
+	mutex_prof_data_t *data = &mutex->prof_data;
+	UNUSED nstime_t before = NSTIME_ZERO_INITIALIZER;
+
+	if (ncpus == 1) {
+		goto label_spin_done;
+	}
+
+	int cnt = 0, max_cnt = MALLOC_MUTEX_MAX_SPIN;
+	do {
+		CPU_SPINWAIT;
+		if (!malloc_mutex_trylock_final(mutex)) {
+			data->n_spin_acquired++;
+			return;
+		}
+	} while (cnt++ < max_cnt);
+
+	if (!config_stats) {
+		/* Only spin is useful when stats is off. */
+		malloc_mutex_lock_final(mutex);
+		return;
+	}
+label_spin_done:
+	nstime_update(&before);
+	/* Copy before to after to avoid clock skews. */
+	nstime_t after;
+	nstime_copy(&after, &before);
+	uint32_t n_thds = atomic_fetch_add_u32(&data->n_waiting_thds, 1,
+	    ATOMIC_RELAXED) + 1;
+	/* One last try as above two calls may take quite some cycles. */
+	if (!malloc_mutex_trylock_final(mutex)) {
+		atomic_fetch_sub_u32(&data->n_waiting_thds, 1, ATOMIC_RELAXED);
+		data->n_spin_acquired++;
+		return;
+	}
+
+	/* True slow path. */
+	malloc_mutex_lock_final(mutex);
+	/* Update more slow-path only counters. */
+	atomic_fetch_sub_u32(&data->n_waiting_thds, 1, ATOMIC_RELAXED);
+	nstime_update(&after);
+
+	nstime_t delta;
+	nstime_copy(&delta, &after);
+	nstime_subtract(&delta, &before);
 
+	data->n_wait_times++;
+	nstime_add(&data->tot_wait_time, &delta);
+	if (nstime_compare(&data->max_wait_time, &delta) < 0) {
+		nstime_copy(&data->max_wait_time, &delta);
+	}
+	if (n_thds > data->max_n_thds) {
+		data->max_n_thds = n_thds;
+	}
+}
+
+static void
+mutex_prof_data_init(mutex_prof_data_t *data) {
+	memset(data, 0, sizeof(mutex_prof_data_t));
+	nstime_init(&data->max_wait_time, 0);
+	nstime_init(&data->tot_wait_time, 0);
+	data->prev_owner = NULL;
+}
+
+void
+malloc_mutex_prof_data_reset(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	malloc_mutex_assert_owner(tsdn, mutex);
+	mutex_prof_data_init(&mutex->prof_data);
+}
+
+static int
+mutex_addr_comp(const witness_t *witness1, void *mutex1,
+    const witness_t *witness2, void *mutex2) {
+	assert(mutex1 != NULL);
+	assert(mutex2 != NULL);
+	uintptr_t mu1int = (uintptr_t)mutex1;
+	uintptr_t mu2int = (uintptr_t)mutex2;
+	if (mu1int < mu2int) {
+		return -1;
+	} else if (mu1int == mu2int) {
+		return 0;
+	} else {
+		return 1;
+	}
+}
+
+bool
+malloc_mutex_init(malloc_mutex_t *mutex, const char *name,
+    witness_rank_t rank, malloc_mutex_lock_order_t lock_order) {
+	mutex_prof_data_init(&mutex->prof_data);
 #ifdef _WIN32
+#  if _WIN32_WINNT >= 0x0600
+	InitializeSRWLock(&mutex->lock);
+#  else
 	if (!InitializeCriticalSectionAndSpinCount(&mutex->lock,
-	    _CRT_SPINCOUNT))
-		return (true);
+	    _CRT_SPINCOUNT)) {
+		return true;
+	}
+#  endif
+#elif (defined(JEMALLOC_OS_UNFAIR_LOCK))
+	mutex->lock = OS_UNFAIR_LOCK_INIT;
 #elif (defined(JEMALLOC_OSSPIN))
 	mutex->lock = 0;
 #elif (defined(JEMALLOC_MUTEX_INIT_CB))
@@ -83,67 +151,73 @@ malloc_mutex_init(malloc_mutex_t *mutex)
 		mutex->postponed_next = postponed_mutexes;
 		postponed_mutexes = mutex;
 	} else {
-		if (_pthread_mutex_init_calloc_cb(&mutex->lock, base_calloc) !=
-		    0)
-			return (true);
+		if (_pthread_mutex_init_calloc_cb(&mutex->lock,
+		    bootstrap_calloc) != 0) {
+			return true;
+		}
 	}
 #else
 	pthread_mutexattr_t attr;
 
-	if (pthread_mutexattr_init(&attr) != 0)
-		return (true);
+	if (pthread_mutexattr_init(&attr) != 0) {
+		return true;
+	}
 	pthread_mutexattr_settype(&attr, MALLOC_MUTEX_TYPE);
 	if (pthread_mutex_init(&mutex->lock, &attr) != 0) {
 		pthread_mutexattr_destroy(&attr);
-		return (true);
+		return true;
 	}
 	pthread_mutexattr_destroy(&attr);
 #endif
-	return (false);
+	if (config_debug) {
+		mutex->lock_order = lock_order;
+		if (lock_order == malloc_mutex_address_ordered) {
+			witness_init(&mutex->witness, name, rank,
+			    mutex_addr_comp, &mutex);
+		} else {
+			witness_init(&mutex->witness, name, rank, NULL, NULL);
+		}
+	}
+	return false;
 }
 
 void
-malloc_mutex_prefork(malloc_mutex_t *mutex)
-{
-
-	malloc_mutex_lock(mutex);
+malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	malloc_mutex_lock(tsdn, mutex);
 }
 
 void
-malloc_mutex_postfork_parent(malloc_mutex_t *mutex)
-{
-
-	malloc_mutex_unlock(mutex);
+malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex) {
+	malloc_mutex_unlock(tsdn, mutex);
 }
 
 void
-malloc_mutex_postfork_child(malloc_mutex_t *mutex)
-{
-
+malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex) {
 #ifdef JEMALLOC_MUTEX_INIT_CB
-	malloc_mutex_unlock(mutex);
+	malloc_mutex_unlock(tsdn, mutex);
 #else
-	if (malloc_mutex_init(mutex)) {
+	if (malloc_mutex_init(mutex, mutex->witness.name,
+	    mutex->witness.rank, mutex->lock_order)) {
 		malloc_printf("<jemalloc>: Error re-initializing mutex in "
 		    "child\n");
-		if (opt_abort)
+		if (opt_abort) {
 			abort();
+		}
 	}
 #endif
 }
 
 bool
-mutex_boot(void)
-{
-
+malloc_mutex_boot(void) {
 #ifdef JEMALLOC_MUTEX_INIT_CB
 	postpone_init = false;
 	while (postponed_mutexes != NULL) {
 		if (_pthread_mutex_init_calloc_cb(&postponed_mutexes->lock,
-		    base_calloc) != 0)
-			return (true);
+		    bootstrap_calloc) != 0) {
+			return true;
+		}
 		postponed_mutexes = postponed_mutexes->postponed_next;
 	}
 #endif
-	return (false);
+	return false;
 }
diff --git a/modules/worldengine/deps/jemalloc/src/mutex_pool.c b/modules/worldengine/deps/jemalloc/src/mutex_pool.c
new file mode 100644
index 0000000000..f24d10e44a
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/mutex_pool.c
@@ -0,0 +1,18 @@
+#define JEMALLOC_MUTEX_POOL_C_
+
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/mutex_pool.h"
+
+bool
+mutex_pool_init(mutex_pool_t *pool, const char *name, witness_rank_t rank) {
+	for (int i = 0; i < MUTEX_POOL_SIZE; ++i) {
+		if (malloc_mutex_init(&pool->mutexes[i], name, rank,
+		    malloc_mutex_address_ordered)) {
+			return true;
+		}
+	}
+	return false;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/nstime.c b/modules/worldengine/deps/jemalloc/src/nstime.c
new file mode 100644
index 0000000000..71db353965
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/nstime.c
@@ -0,0 +1,170 @@
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/nstime.h"
+
+#include "jemalloc/internal/assert.h"
+
+#define BILLION	UINT64_C(1000000000)
+#define MILLION	UINT64_C(1000000)
+
+void
+nstime_init(nstime_t *time, uint64_t ns) {
+	time->ns = ns;
+}
+
+void
+nstime_init2(nstime_t *time, uint64_t sec, uint64_t nsec) {
+	time->ns = sec * BILLION + nsec;
+}
+
+uint64_t
+nstime_ns(const nstime_t *time) {
+	return time->ns;
+}
+
+uint64_t
+nstime_msec(const nstime_t *time) {
+	return time->ns / MILLION;
+}
+
+uint64_t
+nstime_sec(const nstime_t *time) {
+	return time->ns / BILLION;
+}
+
+uint64_t
+nstime_nsec(const nstime_t *time) {
+	return time->ns % BILLION;
+}
+
+void
+nstime_copy(nstime_t *time, const nstime_t *source) {
+	*time = *source;
+}
+
+int
+nstime_compare(const nstime_t *a, const nstime_t *b) {
+	return (a->ns > b->ns) - (a->ns < b->ns);
+}
+
+void
+nstime_add(nstime_t *time, const nstime_t *addend) {
+	assert(UINT64_MAX - time->ns >= addend->ns);
+
+	time->ns += addend->ns;
+}
+
+void
+nstime_iadd(nstime_t *time, uint64_t addend) {
+	assert(UINT64_MAX - time->ns >= addend);
+
+	time->ns += addend;
+}
+
+void
+nstime_subtract(nstime_t *time, const nstime_t *subtrahend) {
+	assert(nstime_compare(time, subtrahend) >= 0);
+
+	time->ns -= subtrahend->ns;
+}
+
+void
+nstime_isubtract(nstime_t *time, uint64_t subtrahend) {
+	assert(time->ns >= subtrahend);
+
+	time->ns -= subtrahend;
+}
+
+void
+nstime_imultiply(nstime_t *time, uint64_t multiplier) {
+	assert((((time->ns | multiplier) & (UINT64_MAX << (sizeof(uint64_t) <<
+	    2))) == 0) || ((time->ns * multiplier) / multiplier == time->ns));
+
+	time->ns *= multiplier;
+}
+
+void
+nstime_idivide(nstime_t *time, uint64_t divisor) {
+	assert(divisor != 0);
+
+	time->ns /= divisor;
+}
+
+uint64_t
+nstime_divide(const nstime_t *time, const nstime_t *divisor) {
+	assert(divisor->ns != 0);
+
+	return time->ns / divisor->ns;
+}
+
+#ifdef _WIN32
+#  define NSTIME_MONOTONIC true
+static void
+nstime_get(nstime_t *time) {
+	FILETIME ft;
+	uint64_t ticks_100ns;
+
+	GetSystemTimeAsFileTime(&ft);
+	ticks_100ns = (((uint64_t)ft.dwHighDateTime) << 32) | ft.dwLowDateTime;
+
+	nstime_init(time, ticks_100ns * 100);
+}
+#elif defined(JEMALLOC_HAVE_CLOCK_MONOTONIC_COARSE)
+#  define NSTIME_MONOTONIC true
+static void
+nstime_get(nstime_t *time) {
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC_COARSE, &ts);
+	nstime_init2(time, ts.tv_sec, ts.tv_nsec);
+}
+#elif defined(JEMALLOC_HAVE_CLOCK_MONOTONIC)
+#  define NSTIME_MONOTONIC true
+static void
+nstime_get(nstime_t *time) {
+	struct timespec ts;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	nstime_init2(time, ts.tv_sec, ts.tv_nsec);
+}
+#elif defined(JEMALLOC_HAVE_MACH_ABSOLUTE_TIME)
+#  define NSTIME_MONOTONIC true
+static void
+nstime_get(nstime_t *time) {
+	nstime_init(time, mach_absolute_time());
+}
+#else
+#  define NSTIME_MONOTONIC false
+static void
+nstime_get(nstime_t *time) {
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	nstime_init2(time, tv.tv_sec, tv.tv_usec * 1000);
+}
+#endif
+
+static bool
+nstime_monotonic_impl(void) {
+	return NSTIME_MONOTONIC;
+#undef NSTIME_MONOTONIC
+}
+nstime_monotonic_t *JET_MUTABLE nstime_monotonic = nstime_monotonic_impl;
+
+static bool
+nstime_update_impl(nstime_t *time) {
+	nstime_t old_time;
+
+	nstime_copy(&old_time, time);
+	nstime_get(time);
+
+	/* Handle non-monotonic clocks. */
+	if (unlikely(nstime_compare(&old_time, time) > 0)) {
+		nstime_copy(time, &old_time);
+		return true;
+	}
+
+	return false;
+}
+nstime_update_t *JET_MUTABLE nstime_update = nstime_update_impl;
diff --git a/modules/worldengine/deps/jemalloc/src/pages.c b/modules/worldengine/deps/jemalloc/src/pages.c
new file mode 100644
index 0000000000..6f2ba5669b
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/pages.c
@@ -0,0 +1,423 @@
+#define JEMALLOC_PAGES_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+
+#include "jemalloc/internal/pages.h"
+
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/malloc_io.h"
+
+#ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT
+#include <sys/sysctl.h>
+#endif
+
+/******************************************************************************/
+/* Data. */
+
+/* Actual operating system page size, detected during bootstrap, <= PAGE. */
+static size_t	os_page;
+
+#ifndef _WIN32
+#  define PAGES_PROT_COMMIT (PROT_READ | PROT_WRITE)
+#  define PAGES_PROT_DECOMMIT (PROT_NONE)
+static int	mmap_flags;
+#endif
+static bool	os_overcommits;
+
+/******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
+
+static void os_pages_unmap(void *addr, size_t size);
+
+/******************************************************************************/
+
+static void *
+os_pages_map(void *addr, size_t size, size_t alignment, bool *commit) {
+	assert(ALIGNMENT_ADDR2BASE(addr, os_page) == addr);
+	assert(ALIGNMENT_CEILING(size, os_page) == size);
+	assert(size != 0);
+
+	if (os_overcommits) {
+		*commit = true;
+	}
+
+	void *ret;
+#ifdef _WIN32
+	/*
+	 * If VirtualAlloc can't allocate at the given address when one is
+	 * given, it fails and returns NULL.
+	 */
+	ret = VirtualAlloc(addr, size, MEM_RESERVE | (*commit ? MEM_COMMIT : 0),
+	    PAGE_READWRITE);
+#else
+	/*
+	 * We don't use MAP_FIXED here, because it can cause the *replacement*
+	 * of existing mappings, and we only want to create new mappings.
+	 */
+	{
+		int prot = *commit ? PAGES_PROT_COMMIT : PAGES_PROT_DECOMMIT;
+
+		ret = mmap(addr, size, prot, mmap_flags, -1, 0);
+	}
+	assert(ret != NULL);
+
+	if (ret == MAP_FAILED) {
+		ret = NULL;
+	} else if (addr != NULL && ret != addr) {
+		/*
+		 * We succeeded in mapping memory, but not in the right place.
+		 */
+		os_pages_unmap(ret, size);
+		ret = NULL;
+	}
+#endif
+	assert(ret == NULL || (addr == NULL && ret != addr) || (addr != NULL &&
+	    ret == addr));
+	return ret;
+}
+
+static void *
+os_pages_trim(void *addr, size_t alloc_size, size_t leadsize, size_t size,
+    bool *commit) {
+	void *ret = (void *)((uintptr_t)addr + leadsize);
+
+	assert(alloc_size >= leadsize + size);
+#ifdef _WIN32
+	os_pages_unmap(addr, alloc_size);
+	void *new_addr = os_pages_map(ret, size, PAGE, commit);
+	if (new_addr == ret) {
+		return ret;
+	}
+	if (new_addr != NULL) {
+		os_pages_unmap(new_addr, size);
+	}
+	return NULL;
+#else
+	size_t trailsize = alloc_size - leadsize - size;
+
+	if (leadsize != 0) {
+		os_pages_unmap(addr, leadsize);
+	}
+	if (trailsize != 0) {
+		os_pages_unmap((void *)((uintptr_t)ret + size), trailsize);
+	}
+	return ret;
+#endif
+}
+
+static void
+os_pages_unmap(void *addr, size_t size) {
+	assert(ALIGNMENT_ADDR2BASE(addr, os_page) == addr);
+	assert(ALIGNMENT_CEILING(size, os_page) == size);
+
+#ifdef _WIN32
+	if (VirtualFree(addr, 0, MEM_RELEASE) == 0)
+#else
+	if (munmap(addr, size) == -1)
+#endif
+	{
+		char buf[BUFERROR_BUF];
+
+		buferror(get_errno(), buf, sizeof(buf));
+		malloc_printf("<jemalloc>: Error in "
+#ifdef _WIN32
+		    "VirtualFree"
+#else
+		    "munmap"
+#endif
+		    "(): %s\n", buf);
+		if (opt_abort) {
+			abort();
+		}
+	}
+}
+
+static void *
+pages_map_slow(size_t size, size_t alignment, bool *commit) {
+	size_t alloc_size = size + alignment - os_page;
+	/* Beware size_t wrap-around. */
+	if (alloc_size < size) {
+		return NULL;
+	}
+
+	void *ret;
+	do {
+		void *pages = os_pages_map(NULL, alloc_size, alignment, commit);
+		if (pages == NULL) {
+			return NULL;
+		}
+		size_t leadsize = ALIGNMENT_CEILING((uintptr_t)pages, alignment)
+		    - (uintptr_t)pages;
+		ret = os_pages_trim(pages, alloc_size, leadsize, size, commit);
+	} while (ret == NULL);
+
+	assert(ret != NULL);
+	assert(PAGE_ADDR2BASE(ret) == ret);
+	return ret;
+}
+
+void *
+pages_map(void *addr, size_t size, size_t alignment, bool *commit) {
+	assert(alignment >= PAGE);
+	assert(ALIGNMENT_ADDR2BASE(addr, alignment) == addr);
+
+	/*
+	 * Ideally, there would be a way to specify alignment to mmap() (like
+	 * NetBSD has), but in the absence of such a feature, we have to work
+	 * hard to efficiently create aligned mappings.  The reliable, but
+	 * slow method is to create a mapping that is over-sized, then trim the
+	 * excess.  However, that always results in one or two calls to
+	 * os_pages_unmap(), and it can leave holes in the process's virtual
+	 * memory map if memory grows downward.
+	 *
+	 * Optimistically try mapping precisely the right amount before falling
+	 * back to the slow method, with the expectation that the optimistic
+	 * approach works most of the time.
+	 */
+
+	void *ret = os_pages_map(addr, size, os_page, commit);
+	if (ret == NULL || ret == addr) {
+		return ret;
+	}
+	assert(addr == NULL);
+	if (ALIGNMENT_ADDR2OFFSET(ret, alignment) != 0) {
+		os_pages_unmap(ret, size);
+		return pages_map_slow(size, alignment, commit);
+	}
+
+	assert(PAGE_ADDR2BASE(ret) == ret);
+	return ret;
+}
+
+void
+pages_unmap(void *addr, size_t size) {
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+	os_pages_unmap(addr, size);
+}
+
+static bool
+pages_commit_impl(void *addr, size_t size, bool commit) {
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+	if (os_overcommits) {
+		return true;
+	}
+
+#ifdef _WIN32
+	return (commit ? (addr != VirtualAlloc(addr, size, MEM_COMMIT,
+	    PAGE_READWRITE)) : (!VirtualFree(addr, size, MEM_DECOMMIT)));
+#else
+	{
+		int prot = commit ? PAGES_PROT_COMMIT : PAGES_PROT_DECOMMIT;
+		void *result = mmap(addr, size, prot, mmap_flags | MAP_FIXED,
+		    -1, 0);
+		if (result == MAP_FAILED) {
+			return true;
+		}
+		if (result != addr) {
+			/*
+			 * We succeeded in mapping memory, but not in the right
+			 * place.
+			 */
+			os_pages_unmap(result, size);
+			return true;
+		}
+		return false;
+	}
+#endif
+}
+
+bool
+pages_commit(void *addr, size_t size) {
+	return pages_commit_impl(addr, size, true);
+}
+
+bool
+pages_decommit(void *addr, size_t size) {
+	return pages_commit_impl(addr, size, false);
+}
+
+bool
+pages_purge_lazy(void *addr, size_t size) {
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+	if (!pages_can_purge_lazy) {
+		return true;
+	}
+
+#ifdef _WIN32
+	VirtualAlloc(addr, size, MEM_RESET, PAGE_READWRITE);
+	return false;
+#elif defined(JEMALLOC_PURGE_MADVISE_FREE) && \
+    !defined(PAGES_CAN_PURGE_LAZY)
+	return (madvise(addr, size, MADV_FREE) != 0);
+#elif defined(JEMALLOC_PURGE_MADVISE_DONTNEED) && \
+    !defined(JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS)
+	return (madvise(addr, size, MADV_DONTNEED) != 0);
+#else
+	not_reached();
+#endif
+}
+
+bool
+pages_purge_forced(void *addr, size_t size) {
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+	if (!pages_can_purge_forced) {
+		return true;
+	}
+
+#if defined(JEMALLOC_PURGE_MADVISE_DONTNEED) && \
+    defined(JEMALLOC_PURGE_MADVISE_DONTNEED_ZEROS)
+	return (madvise(addr, size, MADV_DONTNEED) != 0);
+#elif defined(JEMALLOC_MAPS_COALESCE)
+	/* Try to overlay a new demand-zeroed mapping. */
+	return pages_commit(addr, size);
+#else
+	not_reached();
+#endif
+}
+
+bool
+pages_huge(void *addr, size_t size) {
+	assert(HUGEPAGE_ADDR2BASE(addr) == addr);
+	assert(HUGEPAGE_CEILING(size) == size);
+
+#ifdef JEMALLOC_THP
+	return (madvise(addr, size, MADV_HUGEPAGE) != 0);
+#else
+	return true;
+#endif
+}
+
+bool
+pages_nohuge(void *addr, size_t size) {
+	assert(HUGEPAGE_ADDR2BASE(addr) == addr);
+	assert(HUGEPAGE_CEILING(size) == size);
+
+#ifdef JEMALLOC_THP
+	return (madvise(addr, size, MADV_NOHUGEPAGE) != 0);
+#else
+	return false;
+#endif
+}
+
+static size_t
+os_page_detect(void) {
+#ifdef _WIN32
+	SYSTEM_INFO si;
+	GetSystemInfo(&si);
+	return si.dwPageSize;
+#else
+	long result = sysconf(_SC_PAGESIZE);
+	if (result == -1) {
+		return LG_PAGE;
+	}
+	return (size_t)result;
+#endif
+}
+
+#ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT
+static bool
+os_overcommits_sysctl(void) {
+	int vm_overcommit;
+	size_t sz;
+
+	sz = sizeof(vm_overcommit);
+	if (sysctlbyname("vm.overcommit", &vm_overcommit, &sz, NULL, 0) != 0) {
+		return false; /* Error. */
+	}
+
+	return ((vm_overcommit & 0x3) == 0);
+}
+#endif
+
+#ifdef JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY
+/*
+ * Use syscall(2) rather than {open,read,close}(2) when possible to avoid
+ * reentry during bootstrapping if another library has interposed system call
+ * wrappers.
+ */
+static bool
+os_overcommits_proc(void) {
+	int fd;
+	char buf[1];
+	ssize_t nread;
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_open)
+	fd = (int)syscall(SYS_open, "/proc/sys/vm/overcommit_memory", O_RDONLY |
+	    O_CLOEXEC);
+#elif defined(JEMALLOC_USE_SYSCALL) && defined(SYS_openat)
+	fd = (int)syscall(SYS_openat,
+	    AT_FDCWD, "/proc/sys/vm/overcommit_memory", O_RDONLY | O_CLOEXEC);
+#else
+	fd = open("/proc/sys/vm/overcommit_memory", O_RDONLY | O_CLOEXEC);
+#endif
+	if (fd == -1) {
+		return false; /* Error. */
+	}
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_read)
+	nread = (ssize_t)syscall(SYS_read, fd, &buf, sizeof(buf));
+#else
+	nread = read(fd, &buf, sizeof(buf));
+#endif
+
+#if defined(JEMALLOC_USE_SYSCALL) && defined(SYS_close)
+	syscall(SYS_close, fd);
+#else
+	close(fd);
+#endif
+
+	if (nread < 1) {
+		return false; /* Error. */
+	}
+	/*
+	 * /proc/sys/vm/overcommit_memory meanings:
+	 * 0: Heuristic overcommit.
+	 * 1: Always overcommit.
+	 * 2: Never overcommit.
+	 */
+	return (buf[0] == '0' || buf[0] == '1');
+}
+#endif
+
+bool
+pages_boot(void) {
+	os_page = os_page_detect();
+	if (os_page > PAGE) {
+		malloc_write("<jemalloc>: Unsupported system page size\n");
+		if (opt_abort) {
+			abort();
+		}
+		return true;
+	}
+
+#ifndef _WIN32
+	mmap_flags = MAP_PRIVATE | MAP_ANON;
+#endif
+
+#ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT
+	os_overcommits = os_overcommits_sysctl();
+#elif defined(JEMALLOC_PROC_SYS_VM_OVERCOMMIT_MEMORY)
+	os_overcommits = os_overcommits_proc();
+#  ifdef MAP_NORESERVE
+	if (os_overcommits) {
+		mmap_flags |= MAP_NORESERVE;
+	}
+#  endif
+#else
+	os_overcommits = false;
+#endif
+
+	return false;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/prng.c b/modules/worldengine/deps/jemalloc/src/prng.c
new file mode 100644
index 0000000000..83c04bf9b5
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/prng.c
@@ -0,0 +1,3 @@
+#define JEMALLOC_PRNG_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
diff --git a/modules/worldengine/deps/jemalloc/src/prof.c b/modules/worldengine/deps/jemalloc/src/prof.c
index 7722b7b437..975722c4c3 100644
--- a/modules/worldengine/deps/jemalloc/src/prof.c
+++ b/modules/worldengine/deps/jemalloc/src/prof.c
@@ -1,27 +1,41 @@
-#define	JEMALLOC_PROF_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_PROF_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/ckh.h"
+#include "jemalloc/internal/hash.h"
+#include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/mutex.h"
+
 /******************************************************************************/
 
 #ifdef JEMALLOC_PROF_LIBUNWIND
-#define	UNW_LOCAL_ONLY
+#define UNW_LOCAL_ONLY
 #include <libunwind.h>
 #endif
 
 #ifdef JEMALLOC_PROF_LIBGCC
+/*
+ * We have a circular dependency -- jemalloc_internal.h tells us if we should
+ * use libgcc's unwinding functionality, but after we've included that, we've
+ * already hooked _Unwind_Backtrace.  We'll temporarily disable hooking.
+ */
+#undef _Unwind_Backtrace
 #include <unwind.h>
+#define _Unwind_Backtrace JEMALLOC_HOOK(_Unwind_Backtrace, hooks_libc_hook)
 #endif
 
 /******************************************************************************/
 /* Data. */
 
-malloc_tsd_data(, prof_tdata, prof_tdata_t *, NULL)
-
 bool		opt_prof = false;
 bool		opt_prof_active = true;
+bool		opt_prof_thread_active_init = true;
 size_t		opt_lg_prof_sample = LG_PROF_SAMPLE_DEFAULT;
 ssize_t		opt_lg_prof_interval = LG_PROF_INTERVAL_DEFAULT;
 bool		opt_prof_gdump = false;
-bool		opt_prof_final = true;
+bool		opt_prof_final = false;
 bool		opt_prof_leak = false;
 bool		opt_prof_accum = false;
 char		opt_prof_prefix[
@@ -31,25 +45,66 @@ char		opt_prof_prefix[
 #endif
     1];
 
+/*
+ * Initialized as opt_prof_active, and accessed via
+ * prof_active_[gs]et{_unlocked,}().
+ */
+bool			prof_active;
+static malloc_mutex_t	prof_active_mtx;
+
+/*
+ * Initialized as opt_prof_thread_active_init, and accessed via
+ * prof_thread_active_init_[gs]et().
+ */
+static bool		prof_thread_active_init;
+static malloc_mutex_t	prof_thread_active_init_mtx;
+
+/*
+ * Initialized as opt_prof_gdump, and accessed via
+ * prof_gdump_[gs]et{_unlocked,}().
+ */
+bool			prof_gdump_val;
+static malloc_mutex_t	prof_gdump_mtx;
+
 uint64_t	prof_interval = 0;
-bool		prof_promote;
+
+size_t		lg_prof_sample;
 
 /*
- * Table of mutexes that are shared among ctx's.  These are leaf locks, so
- * there is no problem with using them for more than one ctx at the same time.
- * The primary motivation for this sharing though is that ctx's are ephemeral,
+ * Table of mutexes that are shared among gctx's.  These are leaf locks, so
+ * there is no problem with using them for more than one gctx at the same time.
+ * The primary motivation for this sharing though is that gctx's are ephemeral,
  * and destroying mutexes causes complications for systems that allocate when
  * creating/destroying mutexes.
  */
-static malloc_mutex_t	*ctx_locks;
-static unsigned		cum_ctxs; /* Atomic counter. */
+static malloc_mutex_t	*gctx_locks;
+static atomic_u_t	cum_gctxs; /* Atomic counter. */
 
 /*
- * Global hash of (prof_bt_t *)-->(prof_ctx_t *).  This is the master data
+ * Table of mutexes that are shared among tdata's.  No operations require
+ * holding multiple tdata locks, so there is no problem with using them for more
+ * than one tdata at the same time, even though a gctx lock may be acquired
+ * while holding a tdata lock.
+ */
+static malloc_mutex_t	*tdata_locks;
+
+/*
+ * Global hash of (prof_bt_t *)-->(prof_gctx_t *).  This is the master data
  * structure that knows about all backtraces currently captured.
  */
-static ckh_t		bt2ctx;
-static malloc_mutex_t	bt2ctx_mtx;
+static ckh_t		bt2gctx;
+/* Non static to enable profiling. */
+malloc_mutex_t		bt2gctx_mtx;
+
+/*
+ * Tree of all extant prof_tdata_t structures, regardless of state,
+ * {attached,detached,expired}.
+ */
+static prof_tdata_tree_t	tdatas;
+static malloc_mutex_t	tdatas_mtx;
+
+static uint64_t		next_thr_uid;
+static malloc_mutex_t	next_thr_uid_mtx;
 
 static malloc_mutex_t	prof_dump_seq_mtx;
 static uint64_t		prof_dump_seq;
@@ -70,161 +125,242 @@ static char		prof_dump_buf[
     1
 #endif
 ];
-static unsigned		prof_dump_buf_end;
+static size_t		prof_dump_buf_end;
 static int		prof_dump_fd;
 
 /* Do not dump any profiles until bootstrapping is complete. */
 static bool		prof_booted = false;
 
 /******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
 
-void
-bt_init(prof_bt_t *bt, void **vec)
-{
+static bool	prof_tctx_should_destroy(tsdn_t *tsdn, prof_tctx_t *tctx);
+static void	prof_tctx_destroy(tsd_t *tsd, prof_tctx_t *tctx);
+static bool	prof_tdata_should_destroy(tsdn_t *tsdn, prof_tdata_t *tdata,
+    bool even_if_attached);
+static void	prof_tdata_destroy(tsd_t *tsd, prof_tdata_t *tdata,
+    bool even_if_attached);
+static char	*prof_thread_name_alloc(tsdn_t *tsdn, const char *thread_name);
 
-	cassert(config_prof);
+/******************************************************************************/
+/* Red-black trees. */
 
-	bt->vec = vec;
-	bt->len = 0;
+static int
+prof_tctx_comp(const prof_tctx_t *a, const prof_tctx_t *b) {
+	uint64_t a_thr_uid = a->thr_uid;
+	uint64_t b_thr_uid = b->thr_uid;
+	int ret = (a_thr_uid > b_thr_uid) - (a_thr_uid < b_thr_uid);
+	if (ret == 0) {
+		uint64_t a_thr_discrim = a->thr_discrim;
+		uint64_t b_thr_discrim = b->thr_discrim;
+		ret = (a_thr_discrim > b_thr_discrim) - (a_thr_discrim <
+		    b_thr_discrim);
+		if (ret == 0) {
+			uint64_t a_tctx_uid = a->tctx_uid;
+			uint64_t b_tctx_uid = b->tctx_uid;
+			ret = (a_tctx_uid > b_tctx_uid) - (a_tctx_uid <
+			    b_tctx_uid);
+		}
+	}
+	return ret;
 }
 
-static void
-bt_destroy(prof_bt_t *bt)
-{
+rb_gen(static UNUSED, tctx_tree_, prof_tctx_tree_t, prof_tctx_t,
+    tctx_link, prof_tctx_comp)
 
-	cassert(config_prof);
+static int
+prof_gctx_comp(const prof_gctx_t *a, const prof_gctx_t *b) {
+	unsigned a_len = a->bt.len;
+	unsigned b_len = b->bt.len;
+	unsigned comp_len = (a_len < b_len) ? a_len : b_len;
+	int ret = memcmp(a->bt.vec, b->bt.vec, comp_len * sizeof(void *));
+	if (ret == 0) {
+		ret = (a_len > b_len) - (a_len < b_len);
+	}
+	return ret;
+}
+
+rb_gen(static UNUSED, gctx_tree_, prof_gctx_tree_t, prof_gctx_t, dump_link,
+    prof_gctx_comp)
+
+static int
+prof_tdata_comp(const prof_tdata_t *a, const prof_tdata_t *b) {
+	int ret;
+	uint64_t a_uid = a->thr_uid;
+	uint64_t b_uid = b->thr_uid;
+
+	ret = ((a_uid > b_uid) - (a_uid < b_uid));
+	if (ret == 0) {
+		uint64_t a_discrim = a->thr_discrim;
+		uint64_t b_discrim = b->thr_discrim;
 
-	idalloc(bt);
+		ret = ((a_discrim > b_discrim) - (a_discrim < b_discrim));
+	}
+	return ret;
 }
 
-static prof_bt_t *
-bt_dup(prof_bt_t *bt)
-{
-	prof_bt_t *ret;
+rb_gen(static UNUSED, tdata_tree_, prof_tdata_tree_t, prof_tdata_t, tdata_link,
+    prof_tdata_comp)
+
+/******************************************************************************/
+
+void
+prof_alloc_rollback(tsd_t *tsd, prof_tctx_t *tctx, bool updated) {
+	prof_tdata_t *tdata;
 
 	cassert(config_prof);
 
-	/*
-	 * Create a single allocation that has space for vec immediately
-	 * following the prof_bt_t structure.  The backtraces that get
-	 * stored in the backtrace caches are copied from stack-allocated
-	 * temporary variables, so size is known at creation time.  Making this
-	 * a contiguous object improves cache locality.
-	 */
-	ret = (prof_bt_t *)imalloc(QUANTUM_CEILING(sizeof(prof_bt_t)) +
-	    (bt->len * sizeof(void *)));
-	if (ret == NULL)
-		return (NULL);
-	ret->vec = (void **)((uintptr_t)ret +
-	    QUANTUM_CEILING(sizeof(prof_bt_t)));
-	memcpy(ret->vec, bt->vec, bt->len * sizeof(void *));
-	ret->len = bt->len;
+	if (updated) {
+		/*
+		 * Compute a new sample threshold.  This isn't very important in
+		 * practice, because this function is rarely executed, so the
+		 * potential for sample bias is minimal except in contrived
+		 * programs.
+		 */
+		tdata = prof_tdata_get(tsd, true);
+		if (tdata != NULL) {
+			prof_sample_threshold_update(tdata);
+		}
+	}
 
-	return (ret);
+	if ((uintptr_t)tctx > (uintptr_t)1U) {
+		malloc_mutex_lock(tsd_tsdn(tsd), tctx->tdata->lock);
+		tctx->prepared = false;
+		if (prof_tctx_should_destroy(tsd_tsdn(tsd), tctx)) {
+			prof_tctx_destroy(tsd, tctx);
+		} else {
+			malloc_mutex_unlock(tsd_tsdn(tsd), tctx->tdata->lock);
+		}
+	}
 }
 
-static inline void
-prof_enter(prof_tdata_t *prof_tdata)
-{
+void
+prof_malloc_sample_object(tsdn_t *tsdn, const void *ptr, size_t usize,
+    prof_tctx_t *tctx) {
+	prof_tctx_set(tsdn, ptr, usize, NULL, tctx);
 
-	cassert(config_prof);
+	malloc_mutex_lock(tsdn, tctx->tdata->lock);
+	tctx->cnts.curobjs++;
+	tctx->cnts.curbytes += usize;
+	if (opt_prof_accum) {
+		tctx->cnts.accumobjs++;
+		tctx->cnts.accumbytes += usize;
+	}
+	tctx->prepared = false;
+	malloc_mutex_unlock(tsdn, tctx->tdata->lock);
+}
+
+void
+prof_free_sampled_object(tsd_t *tsd, size_t usize, prof_tctx_t *tctx) {
+	malloc_mutex_lock(tsd_tsdn(tsd), tctx->tdata->lock);
+	assert(tctx->cnts.curobjs > 0);
+	assert(tctx->cnts.curbytes >= usize);
+	tctx->cnts.curobjs--;
+	tctx->cnts.curbytes -= usize;
+
+	if (prof_tctx_should_destroy(tsd_tsdn(tsd), tctx)) {
+		prof_tctx_destroy(tsd, tctx);
+	} else {
+		malloc_mutex_unlock(tsd_tsdn(tsd), tctx->tdata->lock);
+	}
+}
 
-	assert(prof_tdata->enq == false);
-	prof_tdata->enq = true;
+void
+bt_init(prof_bt_t *bt, void **vec) {
+	cassert(config_prof);
 
-	malloc_mutex_lock(&bt2ctx_mtx);
+	bt->vec = vec;
+	bt->len = 0;
 }
 
-static inline void
-prof_leave(prof_tdata_t *prof_tdata)
-{
-	bool idump, gdump;
+static void
+prof_enter(tsd_t *tsd, prof_tdata_t *tdata) {
+	cassert(config_prof);
+	assert(tdata == prof_tdata_get(tsd, false));
+
+	if (tdata != NULL) {
+		assert(!tdata->enq);
+		tdata->enq = true;
+	}
 
+	malloc_mutex_lock(tsd_tsdn(tsd), &bt2gctx_mtx);
+}
+
+static void
+prof_leave(tsd_t *tsd, prof_tdata_t *tdata) {
 	cassert(config_prof);
+	assert(tdata == prof_tdata_get(tsd, false));
 
-	malloc_mutex_unlock(&bt2ctx_mtx);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx);
 
-	assert(prof_tdata->enq);
-	prof_tdata->enq = false;
-	idump = prof_tdata->enq_idump;
-	prof_tdata->enq_idump = false;
-	gdump = prof_tdata->enq_gdump;
-	prof_tdata->enq_gdump = false;
+	if (tdata != NULL) {
+		bool idump, gdump;
 
-	if (idump)
-		prof_idump();
-	if (gdump)
-		prof_gdump();
+		assert(tdata->enq);
+		tdata->enq = false;
+		idump = tdata->enq_idump;
+		tdata->enq_idump = false;
+		gdump = tdata->enq_gdump;
+		tdata->enq_gdump = false;
+
+		if (idump) {
+			prof_idump(tsd_tsdn(tsd));
+		}
+		if (gdump) {
+			prof_gdump(tsd_tsdn(tsd));
+		}
+	}
 }
 
 #ifdef JEMALLOC_PROF_LIBUNWIND
 void
-prof_backtrace(prof_bt_t *bt, unsigned nignore)
-{
-	unw_context_t uc;
-	unw_cursor_t cursor;
-	unsigned i;
-	int err;
+prof_backtrace(prof_bt_t *bt) {
+	int nframes;
 
 	cassert(config_prof);
 	assert(bt->len == 0);
 	assert(bt->vec != NULL);
 
-	unw_getcontext(&uc);
-	unw_init_local(&cursor, &uc);
-
-	/* Throw away (nignore+1) stack frames, if that many exist. */
-	for (i = 0; i < nignore + 1; i++) {
-		err = unw_step(&cursor);
-		if (err <= 0)
-			return;
-	}
-
-	/*
-	 * Iterate over stack frames until there are no more, or until no space
-	 * remains in bt.
-	 */
-	for (i = 0; i < PROF_BT_MAX; i++) {
-		unw_get_reg(&cursor, UNW_REG_IP, (unw_word_t *)&bt->vec[i]);
-		bt->len++;
-		err = unw_step(&cursor);
-		if (err <= 0)
-			break;
+	nframes = unw_backtrace(bt->vec, PROF_BT_MAX);
+	if (nframes <= 0) {
+		return;
 	}
+	bt->len = nframes;
 }
 #elif (defined(JEMALLOC_PROF_LIBGCC))
 static _Unwind_Reason_Code
-prof_unwind_init_callback(struct _Unwind_Context *context, void *arg)
-{
-
+prof_unwind_init_callback(struct _Unwind_Context *context, void *arg) {
 	cassert(config_prof);
 
-	return (_URC_NO_REASON);
+	return _URC_NO_REASON;
 }
 
 static _Unwind_Reason_Code
-prof_unwind_callback(struct _Unwind_Context *context, void *arg)
-{
+prof_unwind_callback(struct _Unwind_Context *context, void *arg) {
 	prof_unwind_data_t *data = (prof_unwind_data_t *)arg;
+	void *ip;
 
 	cassert(config_prof);
 
-	if (data->nignore > 0)
-		data->nignore--;
-	else {
-		data->bt->vec[data->bt->len] = (void *)_Unwind_GetIP(context);
-		data->bt->len++;
-		if (data->bt->len == data->max)
-			return (_URC_END_OF_STACK);
+	ip = (void *)_Unwind_GetIP(context);
+	if (ip == NULL) {
+		return _URC_END_OF_STACK;
+	}
+	data->bt->vec[data->bt->len] = ip;
+	data->bt->len++;
+	if (data->bt->len == data->max) {
+		return _URC_END_OF_STACK;
 	}
 
-	return (_URC_NO_REASON);
+	return _URC_NO_REASON;
 }
 
 void
-prof_backtrace(prof_bt_t *bt, unsigned nignore)
-{
-	prof_unwind_data_t data = {bt, nignore, PROF_BT_MAX};
+prof_backtrace(prof_bt_t *bt) {
+	prof_unwind_data_t data = {bt, PROF_BT_MAX};
 
 	cassert(config_prof);
 
@@ -232,25 +368,24 @@ prof_backtrace(prof_bt_t *bt, unsigned nignore)
 }
 #elif (defined(JEMALLOC_PROF_GCC))
 void
-prof_backtrace(prof_bt_t *bt, unsigned nignore)
-{
-#define	BT_FRAME(i)							\
-	if ((i) < nignore + PROF_BT_MAX) {				\
+prof_backtrace(prof_bt_t *bt) {
+#define BT_FRAME(i)							\
+	if ((i) < PROF_BT_MAX) {					\
 		void *p;						\
-		if (__builtin_frame_address(i) == 0)			\
+		if (__builtin_frame_address(i) == 0) {			\
 			return;						\
+		}							\
 		p = __builtin_return_address(i);			\
-		if (p == NULL)						\
+		if (p == NULL) {					\
 			return;						\
-		if (i >= nignore) {					\
-			bt->vec[(i) - nignore] = p;			\
-			bt->len = (i) - nignore + 1;			\
 		}							\
-	} else								\
-		return;
+		bt->vec[(i)] = p;					\
+		bt->len = (i) + 1;					\
+	} else {							\
+		return;							\
+	}
 
 	cassert(config_prof);
-	assert(nignore <= 3);
 
 	BT_FRAME(0)
 	BT_FRAME(1)
@@ -392,307 +527,452 @@ prof_backtrace(prof_bt_t *bt, unsigned nignore)
 	BT_FRAME(125)
 	BT_FRAME(126)
 	BT_FRAME(127)
-
-	/* Extras to compensate for nignore. */
-	BT_FRAME(128)
-	BT_FRAME(129)
-	BT_FRAME(130)
 #undef BT_FRAME
 }
 #else
 void
-prof_backtrace(prof_bt_t *bt, unsigned nignore)
-{
-
+prof_backtrace(prof_bt_t *bt) {
 	cassert(config_prof);
 	not_reached();
 }
 #endif
 
 static malloc_mutex_t *
-prof_ctx_mutex_choose(void)
-{
-	unsigned nctxs = atomic_add_u(&cum_ctxs, 1);
+prof_gctx_mutex_choose(void) {
+	unsigned ngctxs = atomic_fetch_add_u(&cum_gctxs, 1, ATOMIC_RELAXED);
 
-	return (&ctx_locks[(nctxs - 1) % PROF_NCTX_LOCKS]);
+	return &gctx_locks[(ngctxs - 1) % PROF_NCTX_LOCKS];
 }
 
-static void
-prof_ctx_init(prof_ctx_t *ctx, prof_bt_t *bt)
-{
+static malloc_mutex_t *
+prof_tdata_mutex_choose(uint64_t thr_uid) {
+	return &tdata_locks[thr_uid % PROF_NTDATA_LOCKS];
+}
 
-	ctx->bt = bt;
-	ctx->lock = prof_ctx_mutex_choose();
+static prof_gctx_t *
+prof_gctx_create(tsdn_t *tsdn, prof_bt_t *bt) {
+	/*
+	 * Create a single allocation that has space for vec of length bt->len.
+	 */
+	size_t size = offsetof(prof_gctx_t, vec) + (bt->len * sizeof(void *));
+	prof_gctx_t *gctx = (prof_gctx_t *)iallocztm(tsdn, size,
+	    sz_size2index(size), false, NULL, true, arena_get(TSDN_NULL, 0, true),
+	    true);
+	if (gctx == NULL) {
+		return NULL;
+	}
+	gctx->lock = prof_gctx_mutex_choose();
 	/*
 	 * Set nlimbo to 1, in order to avoid a race condition with
-	 * prof_ctx_merge()/prof_ctx_destroy().
+	 * prof_tctx_destroy()/prof_gctx_try_destroy().
 	 */
-	ctx->nlimbo = 1;
-	ql_elm_new(ctx, dump_link);
-	memset(&ctx->cnt_merged, 0, sizeof(prof_cnt_t));
-	ql_new(&ctx->cnts_ql);
+	gctx->nlimbo = 1;
+	tctx_tree_new(&gctx->tctxs);
+	/* Duplicate bt. */
+	memcpy(gctx->vec, bt->vec, bt->len * sizeof(void *));
+	gctx->bt.vec = gctx->vec;
+	gctx->bt.len = bt->len;
+	return gctx;
 }
 
 static void
-prof_ctx_destroy(prof_ctx_t *ctx)
-{
-	prof_tdata_t *prof_tdata;
-
+prof_gctx_try_destroy(tsd_t *tsd, prof_tdata_t *tdata_self, prof_gctx_t *gctx,
+    prof_tdata_t *tdata) {
 	cassert(config_prof);
 
 	/*
-	 * Check that ctx is still unused by any thread cache before destroying
-	 * it.  prof_lookup() increments ctx->nlimbo in order to avoid a race
-	 * condition with this function, as does prof_ctx_merge() in order to
-	 * avoid a race between the main body of prof_ctx_merge() and entry
+	 * Check that gctx is still unused by any thread cache before destroying
+	 * it.  prof_lookup() increments gctx->nlimbo in order to avoid a race
+	 * condition with this function, as does prof_tctx_destroy() in order to
+	 * avoid a race between the main body of prof_tctx_destroy() and entry
 	 * into this function.
 	 */
-	prof_tdata = prof_tdata_get(false);
-	assert((uintptr_t)prof_tdata > (uintptr_t)PROF_TDATA_STATE_MAX);
-	prof_enter(prof_tdata);
-	malloc_mutex_lock(ctx->lock);
-	if (ql_first(&ctx->cnts_ql) == NULL && ctx->cnt_merged.curobjs == 0 &&
-	    ctx->nlimbo == 1) {
-		assert(ctx->cnt_merged.curbytes == 0);
-		assert(ctx->cnt_merged.accumobjs == 0);
-		assert(ctx->cnt_merged.accumbytes == 0);
-		/* Remove ctx from bt2ctx. */
-		if (ckh_remove(&bt2ctx, ctx->bt, NULL, NULL))
+	prof_enter(tsd, tdata_self);
+	malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock);
+	assert(gctx->nlimbo != 0);
+	if (tctx_tree_empty(&gctx->tctxs) && gctx->nlimbo == 1) {
+		/* Remove gctx from bt2gctx. */
+		if (ckh_remove(tsd, &bt2gctx, &gctx->bt, NULL, NULL)) {
 			not_reached();
-		prof_leave(prof_tdata);
-		/* Destroy ctx. */
-		malloc_mutex_unlock(ctx->lock);
-		bt_destroy(ctx->bt);
-		idalloc(ctx);
+		}
+		prof_leave(tsd, tdata_self);
+		/* Destroy gctx. */
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+		idalloctm(tsd_tsdn(tsd), gctx, NULL, NULL, true, true);
 	} else {
 		/*
-		 * Compensate for increment in prof_ctx_merge() or
+		 * Compensate for increment in prof_tctx_destroy() or
 		 * prof_lookup().
 		 */
-		ctx->nlimbo--;
-		malloc_mutex_unlock(ctx->lock);
-		prof_leave(prof_tdata);
+		gctx->nlimbo--;
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+		prof_leave(tsd, tdata_self);
 	}
 }
 
-static void
-prof_ctx_merge(prof_ctx_t *ctx, prof_thr_cnt_t *cnt)
-{
-	bool destroy;
+static bool
+prof_tctx_should_destroy(tsdn_t *tsdn, prof_tctx_t *tctx) {
+	malloc_mutex_assert_owner(tsdn, tctx->tdata->lock);
 
-	cassert(config_prof);
+	if (opt_prof_accum) {
+		return false;
+	}
+	if (tctx->cnts.curobjs != 0) {
+		return false;
+	}
+	if (tctx->prepared) {
+		return false;
+	}
+	return true;
+}
+
+static bool
+prof_gctx_should_destroy(prof_gctx_t *gctx) {
+	if (opt_prof_accum) {
+		return false;
+	}
+	if (!tctx_tree_empty(&gctx->tctxs)) {
+		return false;
+	}
+	if (gctx->nlimbo != 0) {
+		return false;
+	}
+	return true;
+}
 
-	/* Merge cnt stats and detach from ctx. */
-	malloc_mutex_lock(ctx->lock);
-	ctx->cnt_merged.curobjs += cnt->cnts.curobjs;
-	ctx->cnt_merged.curbytes += cnt->cnts.curbytes;
-	ctx->cnt_merged.accumobjs += cnt->cnts.accumobjs;
-	ctx->cnt_merged.accumbytes += cnt->cnts.accumbytes;
-	ql_remove(&ctx->cnts_ql, cnt, cnts_link);
-	if (opt_prof_accum == false && ql_first(&ctx->cnts_ql) == NULL &&
-	    ctx->cnt_merged.curobjs == 0 && ctx->nlimbo == 0) {
+static void
+prof_tctx_destroy(tsd_t *tsd, prof_tctx_t *tctx) {
+	prof_tdata_t *tdata = tctx->tdata;
+	prof_gctx_t *gctx = tctx->gctx;
+	bool destroy_tdata, destroy_tctx, destroy_gctx;
+
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), tctx->tdata->lock);
+
+	assert(tctx->cnts.curobjs == 0);
+	assert(tctx->cnts.curbytes == 0);
+	assert(!opt_prof_accum);
+	assert(tctx->cnts.accumobjs == 0);
+	assert(tctx->cnts.accumbytes == 0);
+
+	ckh_remove(tsd, &tdata->bt2tctx, &gctx->bt, NULL, NULL);
+	destroy_tdata = prof_tdata_should_destroy(tsd_tsdn(tsd), tdata, false);
+	malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock);
+	switch (tctx->state) {
+	case prof_tctx_state_nominal:
+		tctx_tree_remove(&gctx->tctxs, tctx);
+		destroy_tctx = true;
+		if (prof_gctx_should_destroy(gctx)) {
+			/*
+			 * Increment gctx->nlimbo in order to keep another
+			 * thread from winning the race to destroy gctx while
+			 * this one has gctx->lock dropped.  Without this, it
+			 * would be possible for another thread to:
+			 *
+			 * 1) Sample an allocation associated with gctx.
+			 * 2) Deallocate the sampled object.
+			 * 3) Successfully prof_gctx_try_destroy(gctx).
+			 *
+			 * The result would be that gctx no longer exists by the
+			 * time this thread accesses it in
+			 * prof_gctx_try_destroy().
+			 */
+			gctx->nlimbo++;
+			destroy_gctx = true;
+		} else {
+			destroy_gctx = false;
+		}
+		break;
+	case prof_tctx_state_dumping:
 		/*
-		 * Increment ctx->nlimbo in order to keep another thread from
-		 * winning the race to destroy ctx while this one has ctx->lock
-		 * dropped.  Without this, it would be possible for another
-		 * thread to:
-		 *
-		 * 1) Sample an allocation associated with ctx.
-		 * 2) Deallocate the sampled object.
-		 * 3) Successfully prof_ctx_destroy(ctx).
-		 *
-		 * The result would be that ctx no longer exists by the time
-		 * this thread accesses it in prof_ctx_destroy().
+		 * A dumping thread needs tctx to remain valid until dumping
+		 * has finished.  Change state such that the dumping thread will
+		 * complete destruction during a late dump iteration phase.
 		 */
-		ctx->nlimbo++;
-		destroy = true;
-	} else
-		destroy = false;
-	malloc_mutex_unlock(ctx->lock);
-	if (destroy)
-		prof_ctx_destroy(ctx);
+		tctx->state = prof_tctx_state_purgatory;
+		destroy_tctx = false;
+		destroy_gctx = false;
+		break;
+	default:
+		not_reached();
+		destroy_tctx = false;
+		destroy_gctx = false;
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+	if (destroy_gctx) {
+		prof_gctx_try_destroy(tsd, prof_tdata_get(tsd, false), gctx,
+		    tdata);
+	}
+
+	malloc_mutex_assert_not_owner(tsd_tsdn(tsd), tctx->tdata->lock);
+
+	if (destroy_tdata) {
+		prof_tdata_destroy(tsd, tdata, false);
+	}
+
+	if (destroy_tctx) {
+		idalloctm(tsd_tsdn(tsd), tctx, NULL, NULL, true, true);
+	}
 }
 
 static bool
-prof_lookup_global(prof_bt_t *bt, prof_tdata_t *prof_tdata, void **p_btkey,
-    prof_ctx_t **p_ctx, bool *p_new_ctx)
-{
+prof_lookup_global(tsd_t *tsd, prof_bt_t *bt, prof_tdata_t *tdata,
+    void **p_btkey, prof_gctx_t **p_gctx, bool *p_new_gctx) {
 	union {
-		prof_ctx_t	*p;
+		prof_gctx_t	*p;
 		void		*v;
-	} ctx;
+	} gctx, tgctx;
 	union {
 		prof_bt_t	*p;
 		void		*v;
 	} btkey;
-	bool new_ctx;
+	bool new_gctx;
 
-	prof_enter(prof_tdata);
-	if (ckh_search(&bt2ctx, bt, &btkey.v, &ctx.v)) {
+	prof_enter(tsd, tdata);
+	if (ckh_search(&bt2gctx, bt, &btkey.v, &gctx.v)) {
 		/* bt has never been seen before.  Insert it. */
-		ctx.v = imalloc(sizeof(prof_ctx_t));
-		if (ctx.v == NULL) {
-			prof_leave(prof_tdata);
-			return (true);
-		}
-		btkey.p = bt_dup(bt);
-		if (btkey.v == NULL) {
-			prof_leave(prof_tdata);
-			idalloc(ctx.v);
-			return (true);
+		prof_leave(tsd, tdata);
+		tgctx.p = prof_gctx_create(tsd_tsdn(tsd), bt);
+		if (tgctx.v == NULL) {
+			return true;
 		}
-		prof_ctx_init(ctx.p, btkey.p);
-		if (ckh_insert(&bt2ctx, btkey.v, ctx.v)) {
-			/* OOM. */
-			prof_leave(prof_tdata);
-			idalloc(btkey.v);
-			idalloc(ctx.v);
-			return (true);
+		prof_enter(tsd, tdata);
+		if (ckh_search(&bt2gctx, bt, &btkey.v, &gctx.v)) {
+			gctx.p = tgctx.p;
+			btkey.p = &gctx.p->bt;
+			if (ckh_insert(tsd, &bt2gctx, btkey.v, gctx.v)) {
+				/* OOM. */
+				prof_leave(tsd, tdata);
+				idalloctm(tsd_tsdn(tsd), gctx.v, NULL, NULL,
+				    true, true);
+				return true;
+			}
+			new_gctx = true;
+		} else {
+			new_gctx = false;
 		}
-		new_ctx = true;
 	} else {
+		tgctx.v = NULL;
+		new_gctx = false;
+	}
+
+	if (!new_gctx) {
 		/*
 		 * Increment nlimbo, in order to avoid a race condition with
-		 * prof_ctx_merge()/prof_ctx_destroy().
+		 * prof_tctx_destroy()/prof_gctx_try_destroy().
 		 */
-		malloc_mutex_lock(ctx.p->lock);
-		ctx.p->nlimbo++;
-		malloc_mutex_unlock(ctx.p->lock);
-		new_ctx = false;
+		malloc_mutex_lock(tsd_tsdn(tsd), gctx.p->lock);
+		gctx.p->nlimbo++;
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx.p->lock);
+		new_gctx = false;
+
+		if (tgctx.v != NULL) {
+			/* Lost race to insert. */
+			idalloctm(tsd_tsdn(tsd), tgctx.v, NULL, NULL, true,
+			    true);
+		}
 	}
-	prof_leave(prof_tdata);
+	prof_leave(tsd, tdata);
 
 	*p_btkey = btkey.v;
-	*p_ctx = ctx.p;
-	*p_new_ctx = new_ctx;
-	return (false);
+	*p_gctx = gctx.p;
+	*p_new_gctx = new_gctx;
+	return false;
 }
 
-prof_thr_cnt_t *
-prof_lookup(prof_bt_t *bt)
-{
+prof_tctx_t *
+prof_lookup(tsd_t *tsd, prof_bt_t *bt) {
 	union {
-		prof_thr_cnt_t	*p;
+		prof_tctx_t	*p;
 		void		*v;
 	} ret;
-	prof_tdata_t *prof_tdata;
+	prof_tdata_t *tdata;
+	bool not_found;
 
 	cassert(config_prof);
 
-	prof_tdata = prof_tdata_get(false);
-	if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
-		return (NULL);
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL) {
+		return NULL;
+	}
 
-	if (ckh_search(&prof_tdata->bt2cnt, bt, NULL, &ret.v)) {
+	malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock);
+	not_found = ckh_search(&tdata->bt2tctx, bt, NULL, &ret.v);
+	if (!not_found) { /* Note double negative! */
+		ret.p->prepared = true;
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock);
+	if (not_found) {
 		void *btkey;
-		prof_ctx_t *ctx;
-		bool new_ctx;
+		prof_gctx_t *gctx;
+		bool new_gctx, error;
 
 		/*
 		 * This thread's cache lacks bt.  Look for it in the global
 		 * cache.
 		 */
-		if (prof_lookup_global(bt, prof_tdata, &btkey, &ctx, &new_ctx))
-			return (NULL);
+		if (prof_lookup_global(tsd, bt, tdata, &btkey, &gctx,
+		    &new_gctx)) {
+			return NULL;
+		}
 
-		/* Link a prof_thd_cnt_t into ctx for this thread. */
-		if (ckh_count(&prof_tdata->bt2cnt) == PROF_TCMAX) {
-			assert(ckh_count(&prof_tdata->bt2cnt) > 0);
-			/*
-			 * Flush the least recently used cnt in order to keep
-			 * bt2cnt from becoming too large.
-			 */
-			ret.p = ql_last(&prof_tdata->lru_ql, lru_link);
-			assert(ret.v != NULL);
-			if (ckh_remove(&prof_tdata->bt2cnt, ret.p->ctx->bt,
-			    NULL, NULL))
-				not_reached();
-			ql_remove(&prof_tdata->lru_ql, ret.p, lru_link);
-			prof_ctx_merge(ret.p->ctx, ret.p);
-			/* ret can now be re-used. */
-		} else {
-			assert(ckh_count(&prof_tdata->bt2cnt) < PROF_TCMAX);
-			/* Allocate and partially initialize a new cnt. */
-			ret.v = imalloc(sizeof(prof_thr_cnt_t));
-			if (ret.p == NULL) {
-				if (new_ctx)
-					prof_ctx_destroy(ctx);
-				return (NULL);
+		/* Link a prof_tctx_t into gctx for this thread. */
+		ret.v = iallocztm(tsd_tsdn(tsd), sizeof(prof_tctx_t),
+		    sz_size2index(sizeof(prof_tctx_t)), false, NULL, true,
+		    arena_ichoose(tsd, NULL), true);
+		if (ret.p == NULL) {
+			if (new_gctx) {
+				prof_gctx_try_destroy(tsd, tdata, gctx, tdata);
 			}
-			ql_elm_new(ret.p, cnts_link);
-			ql_elm_new(ret.p, lru_link);
+			return NULL;
 		}
-		/* Finish initializing ret. */
-		ret.p->ctx = ctx;
-		ret.p->epoch = 0;
+		ret.p->tdata = tdata;
+		ret.p->thr_uid = tdata->thr_uid;
+		ret.p->thr_discrim = tdata->thr_discrim;
 		memset(&ret.p->cnts, 0, sizeof(prof_cnt_t));
-		if (ckh_insert(&prof_tdata->bt2cnt, btkey, ret.v)) {
-			if (new_ctx)
-				prof_ctx_destroy(ctx);
-			idalloc(ret.v);
-			return (NULL);
+		ret.p->gctx = gctx;
+		ret.p->tctx_uid = tdata->tctx_uid_next++;
+		ret.p->prepared = true;
+		ret.p->state = prof_tctx_state_initializing;
+		malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock);
+		error = ckh_insert(tsd, &tdata->bt2tctx, btkey, ret.v);
+		malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock);
+		if (error) {
+			if (new_gctx) {
+				prof_gctx_try_destroy(tsd, tdata, gctx, tdata);
+			}
+			idalloctm(tsd_tsdn(tsd), ret.v, NULL, NULL, true, true);
+			return NULL;
 		}
-		ql_head_insert(&prof_tdata->lru_ql, ret.p, lru_link);
-		malloc_mutex_lock(ctx->lock);
-		ql_tail_insert(&ctx->cnts_ql, ret.p, cnts_link);
-		ctx->nlimbo--;
-		malloc_mutex_unlock(ctx->lock);
-	} else {
-		/* Move ret to the front of the LRU. */
-		ql_remove(&prof_tdata->lru_ql, ret.p, lru_link);
-		ql_head_insert(&prof_tdata->lru_ql, ret.p, lru_link);
+		malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock);
+		ret.p->state = prof_tctx_state_nominal;
+		tctx_tree_insert(&gctx->tctxs, ret.p);
+		gctx->nlimbo--;
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
 	}
 
-	return (ret.p);
+	return ret.p;
+}
+
+/*
+ * The bodies of this function and prof_leakcheck() are compiled out unless heap
+ * profiling is enabled, so that it is possible to compile jemalloc with
+ * floating point support completely disabled.  Avoiding floating point code is
+ * important on memory-constrained systems, but it also enables a workaround for
+ * versions of glibc that don't properly save/restore floating point registers
+ * during dynamic lazy symbol loading (which internally calls into whatever
+ * malloc implementation happens to be integrated into the application).  Note
+ * that some compilers (e.g.  gcc 4.8) may use floating point registers for fast
+ * memory moves, so jemalloc must be compiled with such optimizations disabled
+ * (e.g.
+ * -mno-sse) in order for the workaround to be complete.
+ */
+void
+prof_sample_threshold_update(prof_tdata_t *tdata) {
+#ifdef JEMALLOC_PROF
+	uint64_t r;
+	double u;
+
+	if (!config_prof) {
+		return;
+	}
+
+	if (lg_prof_sample == 0) {
+		tdata->bytes_until_sample = 0;
+		return;
+	}
+
+	/*
+	 * Compute sample interval as a geometrically distributed random
+	 * variable with mean (2^lg_prof_sample).
+	 *
+	 *                             __        __
+	 *                             |  log(u)  |                     1
+	 * tdata->bytes_until_sample = | -------- |, where p = ---------------
+	 *                             | log(1-p) |             lg_prof_sample
+	 *                                                     2
+	 *
+	 * For more information on the math, see:
+	 *
+	 *   Non-Uniform Random Variate Generation
+	 *   Luc Devroye
+	 *   Springer-Verlag, New York, 1986
+	 *   pp 500
+	 *   (http://luc.devroye.org/rnbookindex.html)
+	 */
+	r = prng_lg_range_u64(&tdata->prng_state, 53);
+	u = (double)r * (1.0/9007199254740992.0L);
+	tdata->bytes_until_sample = (uint64_t)(log(u) /
+	    log(1.0 - (1.0 / (double)((uint64_t)1U << lg_prof_sample))))
+	    + (uint64_t)1U;
+#endif
 }
 
 #ifdef JEMALLOC_JET
+static prof_tdata_t *
+prof_tdata_count_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata,
+    void *arg) {
+	size_t *tdata_count = (size_t *)arg;
+
+	(*tdata_count)++;
+
+	return NULL;
+}
+
 size_t
-prof_bt_count(void)
-{
+prof_tdata_count(void) {
+	size_t tdata_count = 0;
+	tsdn_t *tsdn;
+
+	tsdn = tsdn_fetch();
+	malloc_mutex_lock(tsdn, &tdatas_mtx);
+	tdata_tree_iter(&tdatas, NULL, prof_tdata_count_iter,
+	    (void *)&tdata_count);
+	malloc_mutex_unlock(tsdn, &tdatas_mtx);
+
+	return tdata_count;
+}
+
+size_t
+prof_bt_count(void) {
 	size_t bt_count;
-	prof_tdata_t *prof_tdata;
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
 
-	prof_tdata = prof_tdata_get(false);
-	if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
-		return (0);
+	tsd = tsd_fetch();
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL) {
+		return 0;
+	}
 
-	prof_enter(prof_tdata);
-	bt_count = ckh_count(&bt2ctx);
-	prof_leave(prof_tdata);
+	malloc_mutex_lock(tsd_tsdn(tsd), &bt2gctx_mtx);
+	bt_count = ckh_count(&bt2gctx);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx);
 
-	return (bt_count);
+	return bt_count;
 }
 #endif
 
-#ifdef JEMALLOC_JET
-#undef prof_dump_open
-#define	prof_dump_open JEMALLOC_N(prof_dump_open_impl)
-#endif
 static int
-prof_dump_open(bool propagate_err, const char *filename)
-{
+prof_dump_open_impl(bool propagate_err, const char *filename) {
 	int fd;
 
 	fd = creat(filename, 0644);
-	if (fd == -1 && propagate_err == false) {
+	if (fd == -1 && !propagate_err) {
 		malloc_printf("<jemalloc>: creat(\"%s\"), 0644) failed\n",
 		    filename);
-		if (opt_abort)
+		if (opt_abort) {
 			abort();
+		}
 	}
 
-	return (fd);
+	return fd;
 }
-#ifdef JEMALLOC_JET
-#undef prof_dump_open
-#define	prof_dump_open JEMALLOC_N(prof_dump_open)
-prof_dump_open_t *prof_dump_open = JEMALLOC_N(prof_dump_open_impl);
-#endif
+prof_dump_open_t *JET_MUTABLE prof_dump_open = prof_dump_open_impl;
 
 static bool
-prof_dump_flush(bool propagate_err)
-{
+prof_dump_flush(bool propagate_err) {
 	bool ret = false;
 	ssize_t err;
 
@@ -700,22 +980,22 @@ prof_dump_flush(bool propagate_err)
 
 	err = write(prof_dump_fd, prof_dump_buf, prof_dump_buf_end);
 	if (err == -1) {
-		if (propagate_err == false) {
+		if (!propagate_err) {
 			malloc_write("<jemalloc>: write() failed during heap "
 			    "profile flush\n");
-			if (opt_abort)
+			if (opt_abort) {
 				abort();
+			}
 		}
 		ret = true;
 	}
 	prof_dump_buf_end = 0;
 
-	return (ret);
+	return ret;
 }
 
 static bool
-prof_dump_close(bool propagate_err)
-{
+prof_dump_close(bool propagate_err) {
 	bool ret;
 
 	assert(prof_dump_fd != -1);
@@ -723,13 +1003,12 @@ prof_dump_close(bool propagate_err)
 	close(prof_dump_fd);
 	prof_dump_fd = -1;
 
-	return (ret);
+	return ret;
 }
 
 static bool
-prof_dump_write(bool propagate_err, const char *s)
-{
-	unsigned i, slen, n;
+prof_dump_write(bool propagate_err, const char *s) {
+	size_t i, slen, n;
 
 	cassert(config_prof);
 
@@ -737,9 +1016,11 @@ prof_dump_write(bool propagate_err, const char *s)
 	slen = strlen(s);
 	while (i < slen) {
 		/* Flush the buffer if it is full. */
-		if (prof_dump_buf_end == PROF_DUMP_BUFSIZE)
-			if (prof_dump_flush(propagate_err) && propagate_err)
-				return (true);
+		if (prof_dump_buf_end == PROF_DUMP_BUFSIZE) {
+			if (prof_dump_flush(propagate_err) && propagate_err) {
+				return true;
+			}
+		}
 
 		if (prof_dump_buf_end + slen <= PROF_DUMP_BUFSIZE) {
 			/* Finish writing. */
@@ -753,13 +1034,12 @@ prof_dump_write(bool propagate_err, const char *s)
 		i += n;
 	}
 
-	return (false);
+	return false;
 }
 
-JEMALLOC_ATTR(format(printf, 2, 3))
+JEMALLOC_FORMAT_PRINTF(2, 3)
 static bool
-prof_dump_printf(bool propagate_err, const char *format, ...)
-{
+prof_dump_printf(bool propagate_err, const char *format, ...) {
 	bool ret;
 	va_list ap;
 	char buf[PROF_PRINTF_BUFSIZE];
@@ -769,179 +1049,401 @@ prof_dump_printf(bool propagate_err, const char *format, ...)
 	va_end(ap);
 	ret = prof_dump_write(propagate_err, buf);
 
-	return (ret);
+	return ret;
+}
+
+static void
+prof_tctx_merge_tdata(tsdn_t *tsdn, prof_tctx_t *tctx, prof_tdata_t *tdata) {
+	malloc_mutex_assert_owner(tsdn, tctx->tdata->lock);
+
+	malloc_mutex_lock(tsdn, tctx->gctx->lock);
+
+	switch (tctx->state) {
+	case prof_tctx_state_initializing:
+		malloc_mutex_unlock(tsdn, tctx->gctx->lock);
+		return;
+	case prof_tctx_state_nominal:
+		tctx->state = prof_tctx_state_dumping;
+		malloc_mutex_unlock(tsdn, tctx->gctx->lock);
+
+		memcpy(&tctx->dump_cnts, &tctx->cnts, sizeof(prof_cnt_t));
+
+		tdata->cnt_summed.curobjs += tctx->dump_cnts.curobjs;
+		tdata->cnt_summed.curbytes += tctx->dump_cnts.curbytes;
+		if (opt_prof_accum) {
+			tdata->cnt_summed.accumobjs +=
+			    tctx->dump_cnts.accumobjs;
+			tdata->cnt_summed.accumbytes +=
+			    tctx->dump_cnts.accumbytes;
+		}
+		break;
+	case prof_tctx_state_dumping:
+	case prof_tctx_state_purgatory:
+		not_reached();
+	}
 }
 
 static void
-prof_dump_ctx_prep(prof_ctx_t *ctx, prof_cnt_t *cnt_all, size_t *leak_nctx,
-    prof_ctx_list_t *ctx_ql)
-{
-	prof_thr_cnt_t *thr_cnt;
-	prof_cnt_t tcnt;
+prof_tctx_merge_gctx(tsdn_t *tsdn, prof_tctx_t *tctx, prof_gctx_t *gctx) {
+	malloc_mutex_assert_owner(tsdn, gctx->lock);
+
+	gctx->cnt_summed.curobjs += tctx->dump_cnts.curobjs;
+	gctx->cnt_summed.curbytes += tctx->dump_cnts.curbytes;
+	if (opt_prof_accum) {
+		gctx->cnt_summed.accumobjs += tctx->dump_cnts.accumobjs;
+		gctx->cnt_summed.accumbytes += tctx->dump_cnts.accumbytes;
+	}
+}
+
+static prof_tctx_t *
+prof_tctx_merge_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *arg) {
+	tsdn_t *tsdn = (tsdn_t *)arg;
+
+	malloc_mutex_assert_owner(tsdn, tctx->gctx->lock);
+
+	switch (tctx->state) {
+	case prof_tctx_state_nominal:
+		/* New since dumping started; ignore. */
+		break;
+	case prof_tctx_state_dumping:
+	case prof_tctx_state_purgatory:
+		prof_tctx_merge_gctx(tsdn, tctx, tctx->gctx);
+		break;
+	default:
+		not_reached();
+	}
+
+	return NULL;
+}
+
+struct prof_tctx_dump_iter_arg_s {
+	tsdn_t	*tsdn;
+	bool	propagate_err;
+};
+
+static prof_tctx_t *
+prof_tctx_dump_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *opaque) {
+	struct prof_tctx_dump_iter_arg_s *arg =
+	    (struct prof_tctx_dump_iter_arg_s *)opaque;
+
+	malloc_mutex_assert_owner(arg->tsdn, tctx->gctx->lock);
+
+	switch (tctx->state) {
+	case prof_tctx_state_initializing:
+	case prof_tctx_state_nominal:
+		/* Not captured by this dump. */
+		break;
+	case prof_tctx_state_dumping:
+	case prof_tctx_state_purgatory:
+		if (prof_dump_printf(arg->propagate_err,
+		    "  t%"FMTu64": %"FMTu64": %"FMTu64" [%"FMTu64": "
+		    "%"FMTu64"]\n", tctx->thr_uid, tctx->dump_cnts.curobjs,
+		    tctx->dump_cnts.curbytes, tctx->dump_cnts.accumobjs,
+		    tctx->dump_cnts.accumbytes)) {
+			return tctx;
+		}
+		break;
+	default:
+		not_reached();
+	}
+	return NULL;
+}
 
+static prof_tctx_t *
+prof_tctx_finish_iter(prof_tctx_tree_t *tctxs, prof_tctx_t *tctx, void *arg) {
+	tsdn_t *tsdn = (tsdn_t *)arg;
+	prof_tctx_t *ret;
+
+	malloc_mutex_assert_owner(tsdn, tctx->gctx->lock);
+
+	switch (tctx->state) {
+	case prof_tctx_state_nominal:
+		/* New since dumping started; ignore. */
+		break;
+	case prof_tctx_state_dumping:
+		tctx->state = prof_tctx_state_nominal;
+		break;
+	case prof_tctx_state_purgatory:
+		ret = tctx;
+		goto label_return;
+	default:
+		not_reached();
+	}
+
+	ret = NULL;
+label_return:
+	return ret;
+}
+
+static void
+prof_dump_gctx_prep(tsdn_t *tsdn, prof_gctx_t *gctx, prof_gctx_tree_t *gctxs) {
 	cassert(config_prof);
 
-	malloc_mutex_lock(ctx->lock);
+	malloc_mutex_lock(tsdn, gctx->lock);
 
 	/*
-	 * Increment nlimbo so that ctx won't go away before dump.
-	 * Additionally, link ctx into the dump list so that it is included in
+	 * Increment nlimbo so that gctx won't go away before dump.
+	 * Additionally, link gctx into the dump list so that it is included in
 	 * prof_dump()'s second pass.
 	 */
-	ctx->nlimbo++;
-	ql_tail_insert(ctx_ql, ctx, dump_link);
+	gctx->nlimbo++;
+	gctx_tree_insert(gctxs, gctx);
 
-	memcpy(&ctx->cnt_summed, &ctx->cnt_merged, sizeof(prof_cnt_t));
-	ql_foreach(thr_cnt, &ctx->cnts_ql, cnts_link) {
-		volatile unsigned *epoch = &thr_cnt->epoch;
+	memset(&gctx->cnt_summed, 0, sizeof(prof_cnt_t));
 
-		while (true) {
-			unsigned epoch0 = *epoch;
+	malloc_mutex_unlock(tsdn, gctx->lock);
+}
 
-			/* Make sure epoch is even. */
-			if (epoch0 & 1U)
-				continue;
+struct prof_gctx_merge_iter_arg_s {
+	tsdn_t	*tsdn;
+	size_t	leak_ngctx;
+};
+
+static prof_gctx_t *
+prof_gctx_merge_iter(prof_gctx_tree_t *gctxs, prof_gctx_t *gctx, void *opaque) {
+	struct prof_gctx_merge_iter_arg_s *arg =
+	    (struct prof_gctx_merge_iter_arg_s *)opaque;
+
+	malloc_mutex_lock(arg->tsdn, gctx->lock);
+	tctx_tree_iter(&gctx->tctxs, NULL, prof_tctx_merge_iter,
+	    (void *)arg->tsdn);
+	if (gctx->cnt_summed.curobjs != 0) {
+		arg->leak_ngctx++;
+	}
+	malloc_mutex_unlock(arg->tsdn, gctx->lock);
 
-			memcpy(&tcnt, &thr_cnt->cnts, sizeof(prof_cnt_t));
+	return NULL;
+}
 
-			/* Terminate if epoch didn't change while reading. */
-			if (*epoch == epoch0)
-				break;
-		}
+static void
+prof_gctx_finish(tsd_t *tsd, prof_gctx_tree_t *gctxs) {
+	prof_tdata_t *tdata = prof_tdata_get(tsd, false);
+	prof_gctx_t *gctx;
 
-		ctx->cnt_summed.curobjs += tcnt.curobjs;
-		ctx->cnt_summed.curbytes += tcnt.curbytes;
-		if (opt_prof_accum) {
-			ctx->cnt_summed.accumobjs += tcnt.accumobjs;
-			ctx->cnt_summed.accumbytes += tcnt.accumbytes;
+	/*
+	 * Standard tree iteration won't work here, because as soon as we
+	 * decrement gctx->nlimbo and unlock gctx, another thread can
+	 * concurrently destroy it, which will corrupt the tree.  Therefore,
+	 * tear down the tree one node at a time during iteration.
+	 */
+	while ((gctx = gctx_tree_first(gctxs)) != NULL) {
+		gctx_tree_remove(gctxs, gctx);
+		malloc_mutex_lock(tsd_tsdn(tsd), gctx->lock);
+		{
+			prof_tctx_t *next;
+
+			next = NULL;
+			do {
+				prof_tctx_t *to_destroy =
+				    tctx_tree_iter(&gctx->tctxs, next,
+				    prof_tctx_finish_iter,
+				    (void *)tsd_tsdn(tsd));
+				if (to_destroy != NULL) {
+					next = tctx_tree_next(&gctx->tctxs,
+					    to_destroy);
+					tctx_tree_remove(&gctx->tctxs,
+					    to_destroy);
+					idalloctm(tsd_tsdn(tsd), to_destroy,
+					    NULL, NULL, true, true);
+				} else {
+					next = NULL;
+				}
+			} while (next != NULL);
+		}
+		gctx->nlimbo--;
+		if (prof_gctx_should_destroy(gctx)) {
+			gctx->nlimbo++;
+			malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+			prof_gctx_try_destroy(tsd, tdata, gctx, tdata);
+		} else {
+			malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
 		}
 	}
+}
 
-	if (ctx->cnt_summed.curobjs != 0)
-		(*leak_nctx)++;
+struct prof_tdata_merge_iter_arg_s {
+	tsdn_t		*tsdn;
+	prof_cnt_t	cnt_all;
+};
+
+static prof_tdata_t *
+prof_tdata_merge_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata,
+    void *opaque) {
+	struct prof_tdata_merge_iter_arg_s *arg =
+	    (struct prof_tdata_merge_iter_arg_s *)opaque;
+
+	malloc_mutex_lock(arg->tsdn, tdata->lock);
+	if (!tdata->expired) {
+		size_t tabind;
+		union {
+			prof_tctx_t	*p;
+			void		*v;
+		} tctx;
+
+		tdata->dumping = true;
+		memset(&tdata->cnt_summed, 0, sizeof(prof_cnt_t));
+		for (tabind = 0; !ckh_iter(&tdata->bt2tctx, &tabind, NULL,
+		    &tctx.v);) {
+			prof_tctx_merge_tdata(arg->tsdn, tctx.p, tdata);
+		}
 
-	/* Add to cnt_all. */
-	cnt_all->curobjs += ctx->cnt_summed.curobjs;
-	cnt_all->curbytes += ctx->cnt_summed.curbytes;
-	if (opt_prof_accum) {
-		cnt_all->accumobjs += ctx->cnt_summed.accumobjs;
-		cnt_all->accumbytes += ctx->cnt_summed.accumbytes;
+		arg->cnt_all.curobjs += tdata->cnt_summed.curobjs;
+		arg->cnt_all.curbytes += tdata->cnt_summed.curbytes;
+		if (opt_prof_accum) {
+			arg->cnt_all.accumobjs += tdata->cnt_summed.accumobjs;
+			arg->cnt_all.accumbytes += tdata->cnt_summed.accumbytes;
+		}
+	} else {
+		tdata->dumping = false;
 	}
+	malloc_mutex_unlock(arg->tsdn, tdata->lock);
 
-	malloc_mutex_unlock(ctx->lock);
+	return NULL;
 }
 
-static bool
-prof_dump_header(bool propagate_err, const prof_cnt_t *cnt_all)
-{
-
-	if (opt_lg_prof_sample == 0) {
-		if (prof_dump_printf(propagate_err,
-		    "heap profile: %"PRId64": %"PRId64
-		    " [%"PRIu64": %"PRIu64"] @ heapprofile\n",
-		    cnt_all->curobjs, cnt_all->curbytes,
-		    cnt_all->accumobjs, cnt_all->accumbytes))
-			return (true);
-	} else {
-		if (prof_dump_printf(propagate_err,
-		    "heap profile: %"PRId64": %"PRId64
-		    " [%"PRIu64": %"PRIu64"] @ heap_v2/%"PRIu64"\n",
-		    cnt_all->curobjs, cnt_all->curbytes,
-		    cnt_all->accumobjs, cnt_all->accumbytes,
-		    ((uint64_t)1U << opt_lg_prof_sample)))
-			return (true);
+static prof_tdata_t *
+prof_tdata_dump_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata,
+    void *arg) {
+	bool propagate_err = *(bool *)arg;
+
+	if (!tdata->dumping) {
+		return NULL;
 	}
 
-	return (false);
+	if (prof_dump_printf(propagate_err,
+	    "  t%"FMTu64": %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]%s%s\n",
+	    tdata->thr_uid, tdata->cnt_summed.curobjs,
+	    tdata->cnt_summed.curbytes, tdata->cnt_summed.accumobjs,
+	    tdata->cnt_summed.accumbytes,
+	    (tdata->thread_name != NULL) ? " " : "",
+	    (tdata->thread_name != NULL) ? tdata->thread_name : "")) {
+		return tdata;
+	}
+	return NULL;
 }
 
-static void
-prof_dump_ctx_cleanup_locked(prof_ctx_t *ctx, prof_ctx_list_t *ctx_ql)
-{
-
-	ctx->nlimbo--;
-	ql_remove(ctx_ql, ctx, dump_link);
-}
+static bool
+prof_dump_header_impl(tsdn_t *tsdn, bool propagate_err,
+    const prof_cnt_t *cnt_all) {
+	bool ret;
 
-static void
-prof_dump_ctx_cleanup(prof_ctx_t *ctx, prof_ctx_list_t *ctx_ql)
-{
+	if (prof_dump_printf(propagate_err,
+	    "heap_v2/%"FMTu64"\n"
+	    "  t*: %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]\n",
+	    ((uint64_t)1U << lg_prof_sample), cnt_all->curobjs,
+	    cnt_all->curbytes, cnt_all->accumobjs, cnt_all->accumbytes)) {
+		return true;
+	}
 
-	malloc_mutex_lock(ctx->lock);
-	prof_dump_ctx_cleanup_locked(ctx, ctx_ql);
-	malloc_mutex_unlock(ctx->lock);
+	malloc_mutex_lock(tsdn, &tdatas_mtx);
+	ret = (tdata_tree_iter(&tdatas, NULL, prof_tdata_dump_iter,
+	    (void *)&propagate_err) != NULL);
+	malloc_mutex_unlock(tsdn, &tdatas_mtx);
+	return ret;
 }
+prof_dump_header_t *JET_MUTABLE prof_dump_header = prof_dump_header_impl;
 
 static bool
-prof_dump_ctx(bool propagate_err, prof_ctx_t *ctx, const prof_bt_t *bt,
-    prof_ctx_list_t *ctx_ql)
-{
+prof_dump_gctx(tsdn_t *tsdn, bool propagate_err, prof_gctx_t *gctx,
+    const prof_bt_t *bt, prof_gctx_tree_t *gctxs) {
 	bool ret;
 	unsigned i;
+	struct prof_tctx_dump_iter_arg_s prof_tctx_dump_iter_arg;
 
 	cassert(config_prof);
-
-	/*
-	 * Current statistics can sum to 0 as a result of unmerged per thread
-	 * statistics.  Additionally, interval- and growth-triggered dumps can
-	 * occur between the time a ctx is created and when its statistics are
-	 * filled in.  Avoid dumping any ctx that is an artifact of either
-	 * implementation detail.
-	 */
-	malloc_mutex_lock(ctx->lock);
-	if ((opt_prof_accum == false && ctx->cnt_summed.curobjs == 0) ||
-	    (opt_prof_accum && ctx->cnt_summed.accumobjs == 0)) {
-		assert(ctx->cnt_summed.curobjs == 0);
-		assert(ctx->cnt_summed.curbytes == 0);
-		assert(ctx->cnt_summed.accumobjs == 0);
-		assert(ctx->cnt_summed.accumbytes == 0);
+	malloc_mutex_assert_owner(tsdn, gctx->lock);
+
+	/* Avoid dumping such gctx's that have no useful data. */
+	if ((!opt_prof_accum && gctx->cnt_summed.curobjs == 0) ||
+	    (opt_prof_accum && gctx->cnt_summed.accumobjs == 0)) {
+		assert(gctx->cnt_summed.curobjs == 0);
+		assert(gctx->cnt_summed.curbytes == 0);
+		assert(gctx->cnt_summed.accumobjs == 0);
+		assert(gctx->cnt_summed.accumbytes == 0);
 		ret = false;
 		goto label_return;
 	}
 
-	if (prof_dump_printf(propagate_err, "%"PRId64": %"PRId64
-	    " [%"PRIu64": %"PRIu64"] @",
-	    ctx->cnt_summed.curobjs, ctx->cnt_summed.curbytes,
-	    ctx->cnt_summed.accumobjs, ctx->cnt_summed.accumbytes)) {
+	if (prof_dump_printf(propagate_err, "@")) {
 		ret = true;
 		goto label_return;
 	}
-
 	for (i = 0; i < bt->len; i++) {
-		if (prof_dump_printf(propagate_err, " %#"PRIxPTR,
+		if (prof_dump_printf(propagate_err, " %#"FMTxPTR,
 		    (uintptr_t)bt->vec[i])) {
 			ret = true;
 			goto label_return;
 		}
 	}
 
-	if (prof_dump_write(propagate_err, "\n")) {
+	if (prof_dump_printf(propagate_err,
+	    "\n"
+	    "  t*: %"FMTu64": %"FMTu64" [%"FMTu64": %"FMTu64"]\n",
+	    gctx->cnt_summed.curobjs, gctx->cnt_summed.curbytes,
+	    gctx->cnt_summed.accumobjs, gctx->cnt_summed.accumbytes)) {
+		ret = true;
+		goto label_return;
+	}
+
+	prof_tctx_dump_iter_arg.tsdn = tsdn;
+	prof_tctx_dump_iter_arg.propagate_err = propagate_err;
+	if (tctx_tree_iter(&gctx->tctxs, NULL, prof_tctx_dump_iter,
+	    (void *)&prof_tctx_dump_iter_arg) != NULL) {
 		ret = true;
 		goto label_return;
 	}
 
 	ret = false;
 label_return:
-	prof_dump_ctx_cleanup_locked(ctx, ctx_ql);
-	malloc_mutex_unlock(ctx->lock);
-	return (ret);
+	return ret;
+}
+
+#ifndef _WIN32
+JEMALLOC_FORMAT_PRINTF(1, 2)
+static int
+prof_open_maps(const char *format, ...) {
+	int mfd;
+	va_list ap;
+	char filename[PATH_MAX + 1];
+
+	va_start(ap, format);
+	malloc_vsnprintf(filename, sizeof(filename), format, ap);
+	va_end(ap);
+	mfd = open(filename, O_RDONLY | O_CLOEXEC);
+
+	return mfd;
+}
+#endif
+
+static int
+prof_getpid(void) {
+#ifdef _WIN32
+	return GetCurrentProcessId();
+#else
+	return getpid();
+#endif
 }
 
 static bool
-prof_dump_maps(bool propagate_err)
-{
+prof_dump_maps(bool propagate_err) {
 	bool ret;
 	int mfd;
-	char filename[PATH_MAX + 1];
 
 	cassert(config_prof);
 #ifdef __FreeBSD__
-	malloc_snprintf(filename, sizeof(filename), "/proc/curproc/map");
+	mfd = prof_open_maps("/proc/curproc/map");
+#elif defined(_WIN32)
+	mfd = -1; // Not implemented
 #else
-	malloc_snprintf(filename, sizeof(filename), "/proc/%d/maps",
-	    (int)getpid());
+	{
+		int pid = prof_getpid();
+
+		mfd = prof_open_maps("/proc/%d/task/%d/maps", pid, pid);
+		if (mfd == -1) {
+			mfd = prof_open_maps("/proc/%d/maps", pid);
+		}
+	}
 #endif
-	mfd = open(filename, O_RDONLY);
 	if (mfd != -1) {
 		ssize_t nread;
 
@@ -971,214 +1473,391 @@ prof_dump_maps(bool propagate_err)
 
 	ret = false;
 label_return:
-	if (mfd != -1)
+	if (mfd != -1) {
 		close(mfd);
-	return (ret);
+	}
+	return ret;
 }
 
+/*
+ * See prof_sample_threshold_update() comment for why the body of this function
+ * is conditionally compiled.
+ */
 static void
-prof_leakcheck(const prof_cnt_t *cnt_all, size_t leak_nctx,
-    const char *filename)
-{
-
+prof_leakcheck(const prof_cnt_t *cnt_all, size_t leak_ngctx,
+    const char *filename) {
+#ifdef JEMALLOC_PROF
+	/*
+	 * Scaling is equivalent AdjustSamples() in jeprof, but the result may
+	 * differ slightly from what jeprof reports, because here we scale the
+	 * summary values, whereas jeprof scales each context individually and
+	 * reports the sums of the scaled values.
+	 */
 	if (cnt_all->curbytes != 0) {
-		malloc_printf("<jemalloc>: Leak summary: %"PRId64" byte%s, %"
-		    PRId64" object%s, %zu context%s\n",
-		    cnt_all->curbytes, (cnt_all->curbytes != 1) ? "s" : "",
-		    cnt_all->curobjs, (cnt_all->curobjs != 1) ? "s" : "",
-		    leak_nctx, (leak_nctx != 1) ? "s" : "");
+		double sample_period = (double)((uint64_t)1 << lg_prof_sample);
+		double ratio = (((double)cnt_all->curbytes) /
+		    (double)cnt_all->curobjs) / sample_period;
+		double scale_factor = 1.0 / (1.0 - exp(-ratio));
+		uint64_t curbytes = (uint64_t)round(((double)cnt_all->curbytes)
+		    * scale_factor);
+		uint64_t curobjs = (uint64_t)round(((double)cnt_all->curobjs) *
+		    scale_factor);
+
+		malloc_printf("<jemalloc>: Leak approximation summary: ~%"FMTu64
+		    " byte%s, ~%"FMTu64" object%s, >= %zu context%s\n",
+		    curbytes, (curbytes != 1) ? "s" : "", curobjs, (curobjs !=
+		    1) ? "s" : "", leak_ngctx, (leak_ngctx != 1) ? "s" : "");
 		malloc_printf(
-		    "<jemalloc>: Run pprof on \"%s\" for leak detail\n",
+		    "<jemalloc>: Run jeprof on \"%s\" for leak detail\n",
 		    filename);
 	}
+#endif
 }
 
-static bool
-prof_dump(bool propagate_err, const char *filename, bool leakcheck)
-{
-	prof_tdata_t *prof_tdata;
-	prof_cnt_t cnt_all;
+struct prof_gctx_dump_iter_arg_s {
+	tsdn_t	*tsdn;
+	bool	propagate_err;
+};
+
+static prof_gctx_t *
+prof_gctx_dump_iter(prof_gctx_tree_t *gctxs, prof_gctx_t *gctx, void *opaque) {
+	prof_gctx_t *ret;
+	struct prof_gctx_dump_iter_arg_s *arg =
+	    (struct prof_gctx_dump_iter_arg_s *)opaque;
+
+	malloc_mutex_lock(arg->tsdn, gctx->lock);
+
+	if (prof_dump_gctx(arg->tsdn, arg->propagate_err, gctx, &gctx->bt,
+	    gctxs)) {
+		ret = gctx;
+		goto label_return;
+	}
+
+	ret = NULL;
+label_return:
+	malloc_mutex_unlock(arg->tsdn, gctx->lock);
+	return ret;
+}
+
+static void
+prof_dump_prep(tsd_t *tsd, prof_tdata_t *tdata,
+    struct prof_tdata_merge_iter_arg_s *prof_tdata_merge_iter_arg,
+    struct prof_gctx_merge_iter_arg_s *prof_gctx_merge_iter_arg,
+    prof_gctx_tree_t *gctxs) {
 	size_t tabind;
 	union {
-		prof_ctx_t	*p;
+		prof_gctx_t	*p;
 		void		*v;
-	} ctx;
-	size_t leak_nctx;
-	prof_ctx_list_t ctx_ql;
-
-	cassert(config_prof);
+	} gctx;
 
-	prof_tdata = prof_tdata_get(false);
-	if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
-		return (true);
+	prof_enter(tsd, tdata);
 
-	malloc_mutex_lock(&prof_dump_mtx);
+	/*
+	 * Put gctx's in limbo and clear their counters in preparation for
+	 * summing.
+	 */
+	gctx_tree_new(gctxs);
+	for (tabind = 0; !ckh_iter(&bt2gctx, &tabind, NULL, &gctx.v);) {
+		prof_dump_gctx_prep(tsd_tsdn(tsd), gctx.p, gctxs);
+	}
 
-	/* Merge per thread profile stats, and sum them in cnt_all. */
-	memset(&cnt_all, 0, sizeof(prof_cnt_t));
-	leak_nctx = 0;
-	ql_new(&ctx_ql);
-	prof_enter(prof_tdata);
-	for (tabind = 0; ckh_iter(&bt2ctx, &tabind, NULL, &ctx.v) == false;)
-		prof_dump_ctx_prep(ctx.p, &cnt_all, &leak_nctx, &ctx_ql);
-	prof_leave(prof_tdata);
+	/*
+	 * Iterate over tdatas, and for the non-expired ones snapshot their tctx
+	 * stats and merge them into the associated gctx's.
+	 */
+	prof_tdata_merge_iter_arg->tsdn = tsd_tsdn(tsd);
+	memset(&prof_tdata_merge_iter_arg->cnt_all, 0, sizeof(prof_cnt_t));
+	malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx);
+	tdata_tree_iter(&tdatas, NULL, prof_tdata_merge_iter,
+	    (void *)prof_tdata_merge_iter_arg);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx);
+
+	/* Merge tctx stats into gctx's. */
+	prof_gctx_merge_iter_arg->tsdn = tsd_tsdn(tsd);
+	prof_gctx_merge_iter_arg->leak_ngctx = 0;
+	gctx_tree_iter(gctxs, NULL, prof_gctx_merge_iter,
+	    (void *)prof_gctx_merge_iter_arg);
+
+	prof_leave(tsd, tdata);
+}
 
+static bool
+prof_dump_file(tsd_t *tsd, bool propagate_err, const char *filename,
+    bool leakcheck, prof_tdata_t *tdata,
+    struct prof_tdata_merge_iter_arg_s *prof_tdata_merge_iter_arg,
+    struct prof_gctx_merge_iter_arg_s *prof_gctx_merge_iter_arg,
+    struct prof_gctx_dump_iter_arg_s *prof_gctx_dump_iter_arg,
+    prof_gctx_tree_t *gctxs) {
 	/* Create dump file. */
-	if ((prof_dump_fd = prof_dump_open(propagate_err, filename)) == -1)
-		goto label_open_close_error;
+	if ((prof_dump_fd = prof_dump_open(propagate_err, filename)) == -1) {
+		return true;
+	}
 
 	/* Dump profile header. */
-	if (prof_dump_header(propagate_err, &cnt_all))
+	if (prof_dump_header(tsd_tsdn(tsd), propagate_err,
+	    &prof_tdata_merge_iter_arg->cnt_all)) {
 		goto label_write_error;
+	}
 
-	/* Dump per ctx profile stats. */
-	while ((ctx.p = ql_first(&ctx_ql)) != NULL) {
-		if (prof_dump_ctx(propagate_err, ctx.p, ctx.p->bt, &ctx_ql))
-			goto label_write_error;
+	/* Dump per gctx profile stats. */
+	prof_gctx_dump_iter_arg->tsdn = tsd_tsdn(tsd);
+	prof_gctx_dump_iter_arg->propagate_err = propagate_err;
+	if (gctx_tree_iter(gctxs, NULL, prof_gctx_dump_iter,
+	    (void *)prof_gctx_dump_iter_arg) != NULL) {
+		goto label_write_error;
 	}
 
 	/* Dump /proc/<pid>/maps if possible. */
-	if (prof_dump_maps(propagate_err))
+	if (prof_dump_maps(propagate_err)) {
 		goto label_write_error;
+	}
 
-	if (prof_dump_close(propagate_err))
-		goto label_open_close_error;
-
-	malloc_mutex_unlock(&prof_dump_mtx);
-
-	if (leakcheck)
-		prof_leakcheck(&cnt_all, leak_nctx, filename);
+	if (prof_dump_close(propagate_err)) {
+		return true;
+	}
 
-	return (false);
+	return false;
 label_write_error:
 	prof_dump_close(propagate_err);
-label_open_close_error:
-	while ((ctx.p = ql_first(&ctx_ql)) != NULL)
-		prof_dump_ctx_cleanup(ctx.p, &ctx_ql);
-	malloc_mutex_unlock(&prof_dump_mtx);
-	return (true);
+	return true;
 }
 
-#define	DUMP_FILENAME_BUFSIZE	(PATH_MAX + 1)
-#define	VSEQ_INVALID		UINT64_C(0xffffffffffffffff)
-static void
-prof_dump_filename(char *filename, char v, int64_t vseq)
-{
+static bool
+prof_dump(tsd_t *tsd, bool propagate_err, const char *filename,
+    bool leakcheck) {
+	cassert(config_prof);
+	assert(tsd_reentrancy_level_get(tsd) == 0);
+
+	prof_tdata_t * tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL) {
+		return true;
+	}
+
+	pre_reentrancy(tsd, NULL);
+	malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_mtx);
+
+	prof_gctx_tree_t gctxs;
+	struct prof_tdata_merge_iter_arg_s prof_tdata_merge_iter_arg;
+	struct prof_gctx_merge_iter_arg_s prof_gctx_merge_iter_arg;
+	struct prof_gctx_dump_iter_arg_s prof_gctx_dump_iter_arg;
+	prof_dump_prep(tsd, tdata, &prof_tdata_merge_iter_arg,
+	    &prof_gctx_merge_iter_arg, &gctxs);
+	bool err = prof_dump_file(tsd, propagate_err, filename, leakcheck, tdata,
+	    &prof_tdata_merge_iter_arg, &prof_gctx_merge_iter_arg,
+	    &prof_gctx_dump_iter_arg, &gctxs);
+	prof_gctx_finish(tsd, &gctxs);
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx);
+	post_reentrancy(tsd);
+
+	if (err) {
+		return true;
+	}
+
+	if (leakcheck) {
+		prof_leakcheck(&prof_tdata_merge_iter_arg.cnt_all,
+		    prof_gctx_merge_iter_arg.leak_ngctx, filename);
+	}
+	return false;
+}
+
+#ifdef JEMALLOC_JET
+void
+prof_cnt_all(uint64_t *curobjs, uint64_t *curbytes, uint64_t *accumobjs,
+    uint64_t *accumbytes) {
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
+	struct prof_tdata_merge_iter_arg_s prof_tdata_merge_iter_arg;
+	struct prof_gctx_merge_iter_arg_s prof_gctx_merge_iter_arg;
+	prof_gctx_tree_t gctxs;
+
+	tsd = tsd_fetch();
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL) {
+		if (curobjs != NULL) {
+			*curobjs = 0;
+		}
+		if (curbytes != NULL) {
+			*curbytes = 0;
+		}
+		if (accumobjs != NULL) {
+			*accumobjs = 0;
+		}
+		if (accumbytes != NULL) {
+			*accumbytes = 0;
+		}
+		return;
+	}
+
+	prof_dump_prep(tsd, tdata, &prof_tdata_merge_iter_arg,
+	    &prof_gctx_merge_iter_arg, &gctxs);
+	prof_gctx_finish(tsd, &gctxs);
+
+	if (curobjs != NULL) {
+		*curobjs = prof_tdata_merge_iter_arg.cnt_all.curobjs;
+	}
+	if (curbytes != NULL) {
+		*curbytes = prof_tdata_merge_iter_arg.cnt_all.curbytes;
+	}
+	if (accumobjs != NULL) {
+		*accumobjs = prof_tdata_merge_iter_arg.cnt_all.accumobjs;
+	}
+	if (accumbytes != NULL) {
+		*accumbytes = prof_tdata_merge_iter_arg.cnt_all.accumbytes;
+	}
+}
+#endif
 
+#define DUMP_FILENAME_BUFSIZE	(PATH_MAX + 1)
+#define VSEQ_INVALID		UINT64_C(0xffffffffffffffff)
+static void
+prof_dump_filename(char *filename, char v, uint64_t vseq) {
 	cassert(config_prof);
 
 	if (vseq != VSEQ_INVALID) {
 	        /* "<prefix>.<pid>.<seq>.v<vseq>.heap" */
 		malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE,
-		    "%s.%d.%"PRIu64".%c%"PRId64".heap",
-		    opt_prof_prefix, (int)getpid(), prof_dump_seq, v, vseq);
+		    "%s.%d.%"FMTu64".%c%"FMTu64".heap",
+		    opt_prof_prefix, prof_getpid(), prof_dump_seq, v, vseq);
 	} else {
 	        /* "<prefix>.<pid>.<seq>.<v>.heap" */
 		malloc_snprintf(filename, DUMP_FILENAME_BUFSIZE,
-		    "%s.%d.%"PRIu64".%c.heap",
-		    opt_prof_prefix, (int)getpid(), prof_dump_seq, v);
+		    "%s.%d.%"FMTu64".%c.heap",
+		    opt_prof_prefix, prof_getpid(), prof_dump_seq, v);
 	}
 	prof_dump_seq++;
 }
 
 static void
-prof_fdump(void)
-{
+prof_fdump(void) {
+	tsd_t *tsd;
 	char filename[DUMP_FILENAME_BUFSIZE];
 
 	cassert(config_prof);
+	assert(opt_prof_final);
+	assert(opt_prof_prefix[0] != '\0');
 
-	if (prof_booted == false)
+	if (!prof_booted) {
 		return;
+	}
+	tsd = tsd_fetch();
+	assert(tsd_reentrancy_level_get(tsd) == 0);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
+	prof_dump_filename(filename, 'f', VSEQ_INVALID);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
+	prof_dump(tsd, false, filename, opt_prof_leak);
+}
 
-	if (opt_prof_final && opt_prof_prefix[0] != '\0') {
-		malloc_mutex_lock(&prof_dump_seq_mtx);
-		prof_dump_filename(filename, 'f', VSEQ_INVALID);
-		malloc_mutex_unlock(&prof_dump_seq_mtx);
-		prof_dump(false, filename, opt_prof_leak);
+bool
+prof_accum_init(tsdn_t *tsdn, prof_accum_t *prof_accum) {
+	cassert(config_prof);
+
+#ifndef JEMALLOC_ATOMIC_U64
+	if (malloc_mutex_init(&prof_accum->mtx, "prof_accum",
+	    WITNESS_RANK_PROF_ACCUM, malloc_mutex_rank_exclusive)) {
+		return true;
 	}
+	prof_accum->accumbytes = 0;
+#else
+	atomic_store_u64(&prof_accum->accumbytes, 0, ATOMIC_RELAXED);
+#endif
+	return false;
 }
 
 void
-prof_idump(void)
-{
-	prof_tdata_t *prof_tdata;
-	char filename[PATH_MAX + 1];
+prof_idump(tsdn_t *tsdn) {
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
 
 	cassert(config_prof);
 
-	if (prof_booted == false)
+	if (!prof_booted || tsdn_null(tsdn)) {
+		return;
+	}
+	tsd = tsdn_tsd(tsdn);
+	if (tsd_reentrancy_level_get(tsd) > 0) {
 		return;
-	prof_tdata = prof_tdata_get(false);
-	if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
+	}
+
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL) {
 		return;
-	if (prof_tdata->enq) {
-		prof_tdata->enq_idump = true;
+	}
+	if (tdata->enq) {
+		tdata->enq_idump = true;
 		return;
 	}
 
 	if (opt_prof_prefix[0] != '\0') {
-		malloc_mutex_lock(&prof_dump_seq_mtx);
+		char filename[PATH_MAX + 1];
+		malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
 		prof_dump_filename(filename, 'i', prof_dump_iseq);
 		prof_dump_iseq++;
-		malloc_mutex_unlock(&prof_dump_seq_mtx);
-		prof_dump(false, filename, false);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
+		prof_dump(tsd, false, filename, false);
 	}
 }
 
 bool
-prof_mdump(const char *filename)
-{
-	char filename_buf[DUMP_FILENAME_BUFSIZE];
-
+prof_mdump(tsd_t *tsd, const char *filename) {
 	cassert(config_prof);
+	assert(tsd_reentrancy_level_get(tsd) == 0);
 
-	if (opt_prof == false || prof_booted == false)
-		return (true);
-
+	if (!opt_prof || !prof_booted) {
+		return true;
+	}
+	char filename_buf[DUMP_FILENAME_BUFSIZE];
 	if (filename == NULL) {
 		/* No filename specified, so automatically generate one. */
-		if (opt_prof_prefix[0] == '\0')
-			return (true);
-		malloc_mutex_lock(&prof_dump_seq_mtx);
+		if (opt_prof_prefix[0] == '\0') {
+			return true;
+		}
+		malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
 		prof_dump_filename(filename_buf, 'm', prof_dump_mseq);
 		prof_dump_mseq++;
-		malloc_mutex_unlock(&prof_dump_seq_mtx);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_seq_mtx);
 		filename = filename_buf;
 	}
-	return (prof_dump(true, filename, false));
+	return prof_dump(tsd, true, filename, false);
 }
 
 void
-prof_gdump(void)
-{
-	prof_tdata_t *prof_tdata;
-	char filename[DUMP_FILENAME_BUFSIZE];
+prof_gdump(tsdn_t *tsdn) {
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
 
 	cassert(config_prof);
 
-	if (prof_booted == false)
+	if (!prof_booted || tsdn_null(tsdn)) {
+		return;
+	}
+	tsd = tsdn_tsd(tsdn);
+	if (tsd_reentrancy_level_get(tsd) > 0) {
 		return;
-	prof_tdata = prof_tdata_get(false);
-	if ((uintptr_t)prof_tdata <= (uintptr_t)PROF_TDATA_STATE_MAX)
+	}
+
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL) {
 		return;
-	if (prof_tdata->enq) {
-		prof_tdata->enq_gdump = true;
+	}
+	if (tdata->enq) {
+		tdata->enq_gdump = true;
 		return;
 	}
 
 	if (opt_prof_prefix[0] != '\0') {
-		malloc_mutex_lock(&prof_dump_seq_mtx);
+		char filename[DUMP_FILENAME_BUFSIZE];
+		malloc_mutex_lock(tsdn, &prof_dump_seq_mtx);
 		prof_dump_filename(filename, 'u', prof_dump_useq);
 		prof_dump_useq++;
-		malloc_mutex_unlock(&prof_dump_seq_mtx);
-		prof_dump(false, filename, false);
+		malloc_mutex_unlock(tsdn, &prof_dump_seq_mtx);
+		prof_dump(tsd, false, filename, false);
 	}
 }
 
 static void
-prof_bt_hash(const void *key, size_t r_hash[2])
-{
+prof_bt_hash(const void *key, size_t r_hash[2]) {
 	prof_bt_t *bt = (prof_bt_t *)key;
 
 	cassert(config_prof);
@@ -1187,106 +1866,389 @@ prof_bt_hash(const void *key, size_t r_hash[2])
 }
 
 static bool
-prof_bt_keycomp(const void *k1, const void *k2)
-{
+prof_bt_keycomp(const void *k1, const void *k2) {
 	const prof_bt_t *bt1 = (prof_bt_t *)k1;
 	const prof_bt_t *bt2 = (prof_bt_t *)k2;
 
 	cassert(config_prof);
 
-	if (bt1->len != bt2->len)
-		return (false);
+	if (bt1->len != bt2->len) {
+		return false;
+	}
 	return (memcmp(bt1->vec, bt2->vec, bt1->len * sizeof(void *)) == 0);
 }
 
-prof_tdata_t *
-prof_tdata_init(void)
-{
-	prof_tdata_t *prof_tdata;
+static uint64_t
+prof_thr_uid_alloc(tsdn_t *tsdn) {
+	uint64_t thr_uid;
+
+	malloc_mutex_lock(tsdn, &next_thr_uid_mtx);
+	thr_uid = next_thr_uid;
+	next_thr_uid++;
+	malloc_mutex_unlock(tsdn, &next_thr_uid_mtx);
+
+	return thr_uid;
+}
+
+static prof_tdata_t *
+prof_tdata_init_impl(tsd_t *tsd, uint64_t thr_uid, uint64_t thr_discrim,
+    char *thread_name, bool active) {
+	prof_tdata_t *tdata;
 
 	cassert(config_prof);
 
 	/* Initialize an empty cache for this thread. */
-	prof_tdata = (prof_tdata_t *)imalloc(sizeof(prof_tdata_t));
-	if (prof_tdata == NULL)
-		return (NULL);
+	tdata = (prof_tdata_t *)iallocztm(tsd_tsdn(tsd), sizeof(prof_tdata_t),
+	    sz_size2index(sizeof(prof_tdata_t)), false, NULL, true,
+	    arena_get(TSDN_NULL, 0, true), true);
+	if (tdata == NULL) {
+		return NULL;
+	}
 
-	if (ckh_new(&prof_tdata->bt2cnt, PROF_CKH_MINITEMS,
-	    prof_bt_hash, prof_bt_keycomp)) {
-		idalloc(prof_tdata);
-		return (NULL);
+	tdata->lock = prof_tdata_mutex_choose(thr_uid);
+	tdata->thr_uid = thr_uid;
+	tdata->thr_discrim = thr_discrim;
+	tdata->thread_name = thread_name;
+	tdata->attached = true;
+	tdata->expired = false;
+	tdata->tctx_uid_next = 0;
+
+	if (ckh_new(tsd, &tdata->bt2tctx, PROF_CKH_MINITEMS, prof_bt_hash,
+	    prof_bt_keycomp)) {
+		idalloctm(tsd_tsdn(tsd), tdata, NULL, NULL, true, true);
+		return NULL;
 	}
-	ql_new(&prof_tdata->lru_ql);
 
-	prof_tdata->vec = imalloc(sizeof(void *) * PROF_BT_MAX);
-	if (prof_tdata->vec == NULL) {
-		ckh_delete(&prof_tdata->bt2cnt);
-		idalloc(prof_tdata);
-		return (NULL);
+	tdata->prng_state = (uint64_t)(uintptr_t)tdata;
+	prof_sample_threshold_update(tdata);
+
+	tdata->enq = false;
+	tdata->enq_idump = false;
+	tdata->enq_gdump = false;
+
+	tdata->dumping = false;
+	tdata->active = active;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx);
+	tdata_tree_insert(&tdatas, tdata);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx);
+
+	return tdata;
+}
+
+prof_tdata_t *
+prof_tdata_init(tsd_t *tsd) {
+	return prof_tdata_init_impl(tsd, prof_thr_uid_alloc(tsd_tsdn(tsd)), 0,
+	    NULL, prof_thread_active_init_get(tsd_tsdn(tsd)));
+}
+
+static bool
+prof_tdata_should_destroy_unlocked(prof_tdata_t *tdata, bool even_if_attached) {
+	if (tdata->attached && !even_if_attached) {
+		return false;
 	}
+	if (ckh_count(&tdata->bt2tctx) != 0) {
+		return false;
+	}
+	return true;
+}
+
+static bool
+prof_tdata_should_destroy(tsdn_t *tsdn, prof_tdata_t *tdata,
+    bool even_if_attached) {
+	malloc_mutex_assert_owner(tsdn, tdata->lock);
 
-	prof_tdata->prng_state = 0;
-	prof_tdata->threshold = 0;
-	prof_tdata->accum = 0;
+	return prof_tdata_should_destroy_unlocked(tdata, even_if_attached);
+}
+
+static void
+prof_tdata_destroy_locked(tsd_t *tsd, prof_tdata_t *tdata,
+    bool even_if_attached) {
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &tdatas_mtx);
 
-	prof_tdata->enq = false;
-	prof_tdata->enq_idump = false;
-	prof_tdata->enq_gdump = false;
+	tdata_tree_remove(&tdatas, tdata);
 
-	prof_tdata_tsd_set(&prof_tdata);
+	assert(prof_tdata_should_destroy_unlocked(tdata, even_if_attached));
 
-	return (prof_tdata);
+	if (tdata->thread_name != NULL) {
+		idalloctm(tsd_tsdn(tsd), tdata->thread_name, NULL, NULL, true,
+		    true);
+	}
+	ckh_delete(tsd, &tdata->bt2tctx);
+	idalloctm(tsd_tsdn(tsd), tdata, NULL, NULL, true, true);
 }
 
-void
-prof_tdata_cleanup(void *arg)
-{
-	prof_thr_cnt_t *cnt;
-	prof_tdata_t *prof_tdata = *(prof_tdata_t **)arg;
+static void
+prof_tdata_destroy(tsd_t *tsd, prof_tdata_t *tdata, bool even_if_attached) {
+	malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx);
+	prof_tdata_destroy_locked(tsd, tdata, even_if_attached);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx);
+}
 
-	cassert(config_prof);
+static void
+prof_tdata_detach(tsd_t *tsd, prof_tdata_t *tdata) {
+	bool destroy_tdata;
 
-	if (prof_tdata == PROF_TDATA_STATE_REINCARNATED) {
-		/*
-		 * Another destructor deallocated memory after this destructor
-		 * was called.  Reset prof_tdata to PROF_TDATA_STATE_PURGATORY
-		 * in order to receive another callback.
-		 */
-		prof_tdata = PROF_TDATA_STATE_PURGATORY;
-		prof_tdata_tsd_set(&prof_tdata);
-	} else if (prof_tdata == PROF_TDATA_STATE_PURGATORY) {
-		/*
-		 * The previous time this destructor was called, we set the key
-		 * to PROF_TDATA_STATE_PURGATORY so that other destructors
-		 * wouldn't cause re-creation of the prof_tdata.  This time, do
-		 * nothing, so that the destructor will not be called again.
-		 */
-	} else if (prof_tdata != NULL) {
-		/*
-		 * Delete the hash table.  All of its contents can still be
-		 * iterated over via the LRU.
-		 */
-		ckh_delete(&prof_tdata->bt2cnt);
+	malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock);
+	if (tdata->attached) {
+		destroy_tdata = prof_tdata_should_destroy(tsd_tsdn(tsd), tdata,
+		    true);
 		/*
-		 * Iteratively merge cnt's into the global stats and delete
-		 * them.
+		 * Only detach if !destroy_tdata, because detaching would allow
+		 * another thread to win the race to destroy tdata.
 		 */
-		while ((cnt = ql_last(&prof_tdata->lru_ql, lru_link)) != NULL) {
-			ql_remove(&prof_tdata->lru_ql, cnt, lru_link);
-			prof_ctx_merge(cnt->ctx, cnt);
-			idalloc(cnt);
+		if (!destroy_tdata) {
+			tdata->attached = false;
 		}
-		idalloc(prof_tdata->vec);
-		idalloc(prof_tdata);
-		prof_tdata = PROF_TDATA_STATE_PURGATORY;
-		prof_tdata_tsd_set(&prof_tdata);
+		tsd_prof_tdata_set(tsd, NULL);
+	} else {
+		destroy_tdata = false;
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), tdata->lock);
+	if (destroy_tdata) {
+		prof_tdata_destroy(tsd, tdata, true);
 	}
 }
 
+prof_tdata_t *
+prof_tdata_reinit(tsd_t *tsd, prof_tdata_t *tdata) {
+	uint64_t thr_uid = tdata->thr_uid;
+	uint64_t thr_discrim = tdata->thr_discrim + 1;
+	char *thread_name = (tdata->thread_name != NULL) ?
+	    prof_thread_name_alloc(tsd_tsdn(tsd), tdata->thread_name) : NULL;
+	bool active = tdata->active;
+
+	prof_tdata_detach(tsd, tdata);
+	return prof_tdata_init_impl(tsd, thr_uid, thr_discrim, thread_name,
+	    active);
+}
+
+static bool
+prof_tdata_expire(tsdn_t *tsdn, prof_tdata_t *tdata) {
+	bool destroy_tdata;
+
+	malloc_mutex_lock(tsdn, tdata->lock);
+	if (!tdata->expired) {
+		tdata->expired = true;
+		destroy_tdata = tdata->attached ? false :
+		    prof_tdata_should_destroy(tsdn, tdata, false);
+	} else {
+		destroy_tdata = false;
+	}
+	malloc_mutex_unlock(tsdn, tdata->lock);
+
+	return destroy_tdata;
+}
+
+static prof_tdata_t *
+prof_tdata_reset_iter(prof_tdata_tree_t *tdatas, prof_tdata_t *tdata,
+    void *arg) {
+	tsdn_t *tsdn = (tsdn_t *)arg;
+
+	return (prof_tdata_expire(tsdn, tdata) ? tdata : NULL);
+}
+
 void
-prof_boot0(void)
-{
+prof_reset(tsd_t *tsd, size_t lg_sample) {
+	prof_tdata_t *next;
+
+	assert(lg_sample < (sizeof(uint64_t) << 3));
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_mtx);
+	malloc_mutex_lock(tsd_tsdn(tsd), &tdatas_mtx);
+
+	lg_prof_sample = lg_sample;
+
+	next = NULL;
+	do {
+		prof_tdata_t *to_destroy = tdata_tree_iter(&tdatas, next,
+		    prof_tdata_reset_iter, (void *)tsd);
+		if (to_destroy != NULL) {
+			next = tdata_tree_next(&tdatas, to_destroy);
+			prof_tdata_destroy_locked(tsd, to_destroy, false);
+		} else {
+			next = NULL;
+		}
+	} while (next != NULL);
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tdatas_mtx);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx);
+}
+
+void
+prof_tdata_cleanup(tsd_t *tsd) {
+	prof_tdata_t *tdata;
+
+	if (!config_prof) {
+		return;
+	}
+
+	tdata = tsd_prof_tdata_get(tsd);
+	if (tdata != NULL) {
+		prof_tdata_detach(tsd, tdata);
+	}
+}
+
+bool
+prof_active_get(tsdn_t *tsdn) {
+	bool prof_active_current;
+
+	malloc_mutex_lock(tsdn, &prof_active_mtx);
+	prof_active_current = prof_active;
+	malloc_mutex_unlock(tsdn, &prof_active_mtx);
+	return prof_active_current;
+}
 
+bool
+prof_active_set(tsdn_t *tsdn, bool active) {
+	bool prof_active_old;
+
+	malloc_mutex_lock(tsdn, &prof_active_mtx);
+	prof_active_old = prof_active;
+	prof_active = active;
+	malloc_mutex_unlock(tsdn, &prof_active_mtx);
+	return prof_active_old;
+}
+
+const char *
+prof_thread_name_get(tsd_t *tsd) {
+	prof_tdata_t *tdata;
+
+	tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL) {
+		return "";
+	}
+	return (tdata->thread_name != NULL ? tdata->thread_name : "");
+}
+
+static char *
+prof_thread_name_alloc(tsdn_t *tsdn, const char *thread_name) {
+	char *ret;
+	size_t size;
+
+	if (thread_name == NULL) {
+		return NULL;
+	}
+
+	size = strlen(thread_name) + 1;
+	if (size == 1) {
+		return "";
+	}
+
+	ret = iallocztm(tsdn, size, sz_size2index(size), false, NULL, true,
+	    arena_get(TSDN_NULL, 0, true), true);
+	if (ret == NULL) {
+		return NULL;
+	}
+	memcpy(ret, thread_name, size);
+	return ret;
+}
+
+int
+prof_thread_name_set(tsd_t *tsd, const char *thread_name) {
+	prof_tdata_t *tdata;
+	unsigned i;
+	char *s;
+
+	tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL) {
+		return EAGAIN;
+	}
+
+	/* Validate input. */
+	if (thread_name == NULL) {
+		return EFAULT;
+	}
+	for (i = 0; thread_name[i] != '\0'; i++) {
+		char c = thread_name[i];
+		if (!isgraph(c) && !isblank(c)) {
+			return EFAULT;
+		}
+	}
+
+	s = prof_thread_name_alloc(tsd_tsdn(tsd), thread_name);
+	if (s == NULL) {
+		return EAGAIN;
+	}
+
+	if (tdata->thread_name != NULL) {
+		idalloctm(tsd_tsdn(tsd), tdata->thread_name, NULL, NULL, true,
+		    true);
+		tdata->thread_name = NULL;
+	}
+	if (strlen(s) > 0) {
+		tdata->thread_name = s;
+	}
+	return 0;
+}
+
+bool
+prof_thread_active_get(tsd_t *tsd) {
+	prof_tdata_t *tdata;
+
+	tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL) {
+		return false;
+	}
+	return tdata->active;
+}
+
+bool
+prof_thread_active_set(tsd_t *tsd, bool active) {
+	prof_tdata_t *tdata;
+
+	tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL) {
+		return true;
+	}
+	tdata->active = active;
+	return false;
+}
+
+bool
+prof_thread_active_init_get(tsdn_t *tsdn) {
+	bool active_init;
+
+	malloc_mutex_lock(tsdn, &prof_thread_active_init_mtx);
+	active_init = prof_thread_active_init;
+	malloc_mutex_unlock(tsdn, &prof_thread_active_init_mtx);
+	return active_init;
+}
+
+bool
+prof_thread_active_init_set(tsdn_t *tsdn, bool active_init) {
+	bool active_init_old;
+
+	malloc_mutex_lock(tsdn, &prof_thread_active_init_mtx);
+	active_init_old = prof_thread_active_init;
+	prof_thread_active_init = active_init;
+	malloc_mutex_unlock(tsdn, &prof_thread_active_init_mtx);
+	return active_init_old;
+}
+
+bool
+prof_gdump_get(tsdn_t *tsdn) {
+	bool prof_gdump_current;
+
+	malloc_mutex_lock(tsdn, &prof_gdump_mtx);
+	prof_gdump_current = prof_gdump_val;
+	malloc_mutex_unlock(tsdn, &prof_gdump_mtx);
+	return prof_gdump_current;
+}
+
+bool
+prof_gdump_set(tsdn_t *tsdn, bool gdump) {
+	bool prof_gdump_old;
+
+	malloc_mutex_lock(tsdn, &prof_gdump_mtx);
+	prof_gdump_old = prof_gdump_val;
+	prof_gdump_val = gdump;
+	malloc_mutex_unlock(tsdn, &prof_gdump_mtx);
+	return prof_gdump_old;
+}
+
+void
+prof_boot0(void) {
 	cassert(config_prof);
 
 	memcpy(opt_prof_prefix, PROF_PREFIX_DEFAULT,
@@ -1294,17 +2256,15 @@ prof_boot0(void)
 }
 
 void
-prof_boot1(void)
-{
-
+prof_boot1(void) {
 	cassert(config_prof);
 
 	/*
-	 * opt_prof and prof_promote must be in their final state before any
-	 * arenas are initialized, so this function must be executed early.
+	 * opt_prof must be in its final state before any arenas are
+	 * initialized, so this function must be executed early.
 	 */
 
-	if (opt_prof_leak && opt_prof == false) {
+	if (opt_prof_leak && !opt_prof) {
 		/*
 		 * Enable opt_prof, but in such a way that profiles are never
 		 * automatically dumped.
@@ -1317,48 +2277,101 @@ prof_boot1(void)
 			    opt_lg_prof_interval);
 		}
 	}
-
-	prof_promote = (opt_prof && opt_lg_prof_sample > LG_PAGE);
 }
 
 bool
-prof_boot2(void)
-{
-
+prof_boot2(tsd_t *tsd) {
 	cassert(config_prof);
 
 	if (opt_prof) {
 		unsigned i;
 
-		if (ckh_new(&bt2ctx, PROF_CKH_MINITEMS, prof_bt_hash,
-		    prof_bt_keycomp))
-			return (true);
-		if (malloc_mutex_init(&bt2ctx_mtx))
-			return (true);
-		if (prof_tdata_tsd_boot()) {
-			malloc_write(
-			    "<jemalloc>: Error in pthread_key_create()\n");
-			abort();
+		lg_prof_sample = opt_lg_prof_sample;
+
+		prof_active = opt_prof_active;
+		if (malloc_mutex_init(&prof_active_mtx, "prof_active",
+		    WITNESS_RANK_PROF_ACTIVE, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+
+		prof_gdump_val = opt_prof_gdump;
+		if (malloc_mutex_init(&prof_gdump_mtx, "prof_gdump",
+		    WITNESS_RANK_PROF_GDUMP, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+
+		prof_thread_active_init = opt_prof_thread_active_init;
+		if (malloc_mutex_init(&prof_thread_active_init_mtx,
+		    "prof_thread_active_init",
+		    WITNESS_RANK_PROF_THREAD_ACTIVE_INIT,
+		    malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+
+		if (ckh_new(tsd, &bt2gctx, PROF_CKH_MINITEMS, prof_bt_hash,
+		    prof_bt_keycomp)) {
+			return true;
+		}
+		if (malloc_mutex_init(&bt2gctx_mtx, "prof_bt2gctx",
+		    WITNESS_RANK_PROF_BT2GCTX, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+
+		tdata_tree_new(&tdatas);
+		if (malloc_mutex_init(&tdatas_mtx, "prof_tdatas",
+		    WITNESS_RANK_PROF_TDATAS, malloc_mutex_rank_exclusive)) {
+			return true;
 		}
 
-		if (malloc_mutex_init(&prof_dump_seq_mtx))
-			return (true);
-		if (malloc_mutex_init(&prof_dump_mtx))
-			return (true);
+		next_thr_uid = 0;
+		if (malloc_mutex_init(&next_thr_uid_mtx, "prof_next_thr_uid",
+		    WITNESS_RANK_PROF_NEXT_THR_UID, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+
+		if (malloc_mutex_init(&prof_dump_seq_mtx, "prof_dump_seq",
+		    WITNESS_RANK_PROF_DUMP_SEQ, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
+		if (malloc_mutex_init(&prof_dump_mtx, "prof_dump",
+		    WITNESS_RANK_PROF_DUMP, malloc_mutex_rank_exclusive)) {
+			return true;
+		}
 
-		if (atexit(prof_fdump) != 0) {
+		if (opt_prof_final && opt_prof_prefix[0] != '\0' &&
+		    atexit(prof_fdump) != 0) {
 			malloc_write("<jemalloc>: Error in atexit()\n");
-			if (opt_abort)
+			if (opt_abort) {
 				abort();
+			}
 		}
 
-		ctx_locks = (malloc_mutex_t *)base_alloc(PROF_NCTX_LOCKS *
-		    sizeof(malloc_mutex_t));
-		if (ctx_locks == NULL)
-			return (true);
+		gctx_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd),
+		    b0get(), PROF_NCTX_LOCKS * sizeof(malloc_mutex_t),
+		    CACHELINE);
+		if (gctx_locks == NULL) {
+			return true;
+		}
 		for (i = 0; i < PROF_NCTX_LOCKS; i++) {
-			if (malloc_mutex_init(&ctx_locks[i]))
-				return (true);
+			if (malloc_mutex_init(&gctx_locks[i], "prof_gctx",
+			    WITNESS_RANK_PROF_GCTX,
+			    malloc_mutex_rank_exclusive)) {
+				return true;
+			}
+		}
+
+		tdata_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd),
+		    b0get(), PROF_NTDATA_LOCKS * sizeof(malloc_mutex_t),
+		    CACHELINE);
+		if (tdata_locks == NULL) {
+			return true;
+		}
+		for (i = 0; i < PROF_NTDATA_LOCKS; i++) {
+			if (malloc_mutex_init(&tdata_locks[i], "prof_tdata",
+			    WITNESS_RANK_PROF_TDATA,
+			    malloc_mutex_rank_exclusive)) {
+				return true;
+			}
 		}
 	}
 
@@ -1372,48 +2385,79 @@ prof_boot2(void)
 
 	prof_booted = true;
 
-	return (false);
+	return false;
 }
 
 void
-prof_prefork(void)
-{
-
-	if (opt_prof) {
+prof_prefork0(tsdn_t *tsdn) {
+	if (config_prof && opt_prof) {
 		unsigned i;
 
-		malloc_mutex_prefork(&bt2ctx_mtx);
-		malloc_mutex_prefork(&prof_dump_seq_mtx);
-		for (i = 0; i < PROF_NCTX_LOCKS; i++)
-			malloc_mutex_prefork(&ctx_locks[i]);
+		malloc_mutex_prefork(tsdn, &prof_dump_mtx);
+		malloc_mutex_prefork(tsdn, &bt2gctx_mtx);
+		malloc_mutex_prefork(tsdn, &tdatas_mtx);
+		for (i = 0; i < PROF_NTDATA_LOCKS; i++) {
+			malloc_mutex_prefork(tsdn, &tdata_locks[i]);
+		}
+		for (i = 0; i < PROF_NCTX_LOCKS; i++) {
+			malloc_mutex_prefork(tsdn, &gctx_locks[i]);
+		}
 	}
 }
 
 void
-prof_postfork_parent(void)
-{
+prof_prefork1(tsdn_t *tsdn) {
+	if (config_prof && opt_prof) {
+		malloc_mutex_prefork(tsdn, &prof_active_mtx);
+		malloc_mutex_prefork(tsdn, &prof_dump_seq_mtx);
+		malloc_mutex_prefork(tsdn, &prof_gdump_mtx);
+		malloc_mutex_prefork(tsdn, &next_thr_uid_mtx);
+		malloc_mutex_prefork(tsdn, &prof_thread_active_init_mtx);
+	}
+}
 
-	if (opt_prof) {
+void
+prof_postfork_parent(tsdn_t *tsdn) {
+	if (config_prof && opt_prof) {
 		unsigned i;
 
-		for (i = 0; i < PROF_NCTX_LOCKS; i++)
-			malloc_mutex_postfork_parent(&ctx_locks[i]);
-		malloc_mutex_postfork_parent(&prof_dump_seq_mtx);
-		malloc_mutex_postfork_parent(&bt2ctx_mtx);
+		malloc_mutex_postfork_parent(tsdn,
+		    &prof_thread_active_init_mtx);
+		malloc_mutex_postfork_parent(tsdn, &next_thr_uid_mtx);
+		malloc_mutex_postfork_parent(tsdn, &prof_gdump_mtx);
+		malloc_mutex_postfork_parent(tsdn, &prof_dump_seq_mtx);
+		malloc_mutex_postfork_parent(tsdn, &prof_active_mtx);
+		for (i = 0; i < PROF_NCTX_LOCKS; i++) {
+			malloc_mutex_postfork_parent(tsdn, &gctx_locks[i]);
+		}
+		for (i = 0; i < PROF_NTDATA_LOCKS; i++) {
+			malloc_mutex_postfork_parent(tsdn, &tdata_locks[i]);
+		}
+		malloc_mutex_postfork_parent(tsdn, &tdatas_mtx);
+		malloc_mutex_postfork_parent(tsdn, &bt2gctx_mtx);
+		malloc_mutex_postfork_parent(tsdn, &prof_dump_mtx);
 	}
 }
 
 void
-prof_postfork_child(void)
-{
-
-	if (opt_prof) {
+prof_postfork_child(tsdn_t *tsdn) {
+	if (config_prof && opt_prof) {
 		unsigned i;
 
-		for (i = 0; i < PROF_NCTX_LOCKS; i++)
-			malloc_mutex_postfork_child(&ctx_locks[i]);
-		malloc_mutex_postfork_child(&prof_dump_seq_mtx);
-		malloc_mutex_postfork_child(&bt2ctx_mtx);
+		malloc_mutex_postfork_child(tsdn, &prof_thread_active_init_mtx);
+		malloc_mutex_postfork_child(tsdn, &next_thr_uid_mtx);
+		malloc_mutex_postfork_child(tsdn, &prof_gdump_mtx);
+		malloc_mutex_postfork_child(tsdn, &prof_dump_seq_mtx);
+		malloc_mutex_postfork_child(tsdn, &prof_active_mtx);
+		for (i = 0; i < PROF_NCTX_LOCKS; i++) {
+			malloc_mutex_postfork_child(tsdn, &gctx_locks[i]);
+		}
+		for (i = 0; i < PROF_NTDATA_LOCKS; i++) {
+			malloc_mutex_postfork_child(tsdn, &tdata_locks[i]);
+		}
+		malloc_mutex_postfork_child(tsdn, &tdatas_mtx);
+		malloc_mutex_postfork_child(tsdn, &bt2gctx_mtx);
+		malloc_mutex_postfork_child(tsdn, &prof_dump_mtx);
 	}
 }
 
diff --git a/modules/worldengine/deps/jemalloc/src/rtree.c b/modules/worldengine/deps/jemalloc/src/rtree.c
index 205957ac4e..53702cf723 100644
--- a/modules/worldengine/deps/jemalloc/src/rtree.c
+++ b/modules/worldengine/deps/jemalloc/src/rtree.c
@@ -1,105 +1,320 @@
-#define	JEMALLOC_RTREE_C_
-#include "jemalloc/internal/jemalloc_internal.h"
-
-rtree_t *
-rtree_new(unsigned bits, rtree_alloc_t *alloc, rtree_dalloc_t *dalloc)
-{
-	rtree_t *ret;
-	unsigned bits_per_level, bits_in_leaf, height, i;
-
-	assert(bits > 0 && bits <= (sizeof(uintptr_t) << 3));
-
-	bits_per_level = ffs(pow2_ceil((RTREE_NODESIZE / sizeof(void *)))) - 1;
-	bits_in_leaf = ffs(pow2_ceil((RTREE_NODESIZE / sizeof(uint8_t)))) - 1;
-	if (bits > bits_in_leaf) {
-		height = 1 + (bits - bits_in_leaf) / bits_per_level;
-		if ((height-1) * bits_per_level + bits_in_leaf != bits)
-			height++;
-	} else {
-		height = 1;
-	}
-	assert((height-1) * bits_per_level + bits_in_leaf >= bits);
-
-	ret = (rtree_t*)alloc(offsetof(rtree_t, level2bits) +
-	    (sizeof(unsigned) * height));
-	if (ret == NULL)
-		return (NULL);
-	memset(ret, 0, offsetof(rtree_t, level2bits) + (sizeof(unsigned) *
-	    height));
-
-	ret->alloc = alloc;
-	ret->dalloc = dalloc;
-	if (malloc_mutex_init(&ret->mutex)) {
-		if (dalloc != NULL)
-			dalloc(ret);
-		return (NULL);
-	}
-	ret->height = height;
-	if (height > 1) {
-		if ((height-1) * bits_per_level + bits_in_leaf > bits) {
-			ret->level2bits[0] = (bits - bits_in_leaf) %
-			    bits_per_level;
-		} else
-			ret->level2bits[0] = bits_per_level;
-		for (i = 1; i < height-1; i++)
-			ret->level2bits[i] = bits_per_level;
-		ret->level2bits[height-1] = bits_in_leaf;
-	} else
-		ret->level2bits[0] = bits;
-
-	ret->root = (void**)alloc(sizeof(void *) << ret->level2bits[0]);
-	if (ret->root == NULL) {
-		if (dalloc != NULL)
-			dalloc(ret);
-		return (NULL);
-	}
-	memset(ret->root, 0, sizeof(void *) << ret->level2bits[0]);
-
-	return (ret);
+#define JEMALLOC_RTREE_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/mutex.h"
+
+/*
+ * Only the most significant bits of keys passed to rtree_{read,write}() are
+ * used.
+ */
+bool
+rtree_new(rtree_t *rtree, bool zeroed) {
+#ifdef JEMALLOC_JET
+	if (!zeroed) {
+		memset(rtree, 0, sizeof(rtree_t)); /* Clear root. */
+	}
+#else
+	assert(zeroed);
+#endif
+
+	if (malloc_mutex_init(&rtree->init_lock, "rtree", WITNESS_RANK_RTREE,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+
+	return false;
+}
+
+static rtree_node_elm_t *
+rtree_node_alloc_impl(tsdn_t *tsdn, rtree_t *rtree, size_t nelms) {
+	return (rtree_node_elm_t *)base_alloc(tsdn, b0get(), nelms *
+	    sizeof(rtree_node_elm_t), CACHELINE);
 }
+rtree_node_alloc_t *JET_MUTABLE rtree_node_alloc = rtree_node_alloc_impl;
 
 static void
-rtree_delete_subtree(rtree_t *rtree, void **node, unsigned level)
-{
+rtree_node_dalloc_impl(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *node) {
+	/* Nodes are never deleted during normal operation. */
+	not_reached();
+}
+UNUSED rtree_node_dalloc_t *JET_MUTABLE rtree_node_dalloc =
+    rtree_node_dalloc_impl;
+
+static rtree_leaf_elm_t *
+rtree_leaf_alloc_impl(tsdn_t *tsdn, rtree_t *rtree, size_t nelms) {
+	return (rtree_leaf_elm_t *)base_alloc(tsdn, b0get(), nelms *
+	    sizeof(rtree_leaf_elm_t), CACHELINE);
+}
+rtree_leaf_alloc_t *JET_MUTABLE rtree_leaf_alloc = rtree_leaf_alloc_impl;
 
-	if (level < rtree->height - 1) {
-		size_t nchildren, i;
+static void
+rtree_leaf_dalloc_impl(tsdn_t *tsdn, rtree_t *rtree, rtree_leaf_elm_t *leaf) {
+	/* Leaves are never deleted during normal operation. */
+	not_reached();
+}
+UNUSED rtree_leaf_dalloc_t *JET_MUTABLE rtree_leaf_dalloc =
+    rtree_leaf_dalloc_impl;
 
-		nchildren = ZU(1) << rtree->level2bits[level];
-		for (i = 0; i < nchildren; i++) {
-			void **child = (void **)node[i];
-			if (child != NULL)
-				rtree_delete_subtree(rtree, child, level + 1);
+#ifdef JEMALLOC_JET
+#  if RTREE_HEIGHT > 1
+static void
+rtree_delete_subtree(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *subtree,
+    unsigned level) {
+	size_t nchildren = ZU(1) << rtree_levels[level].bits;
+	if (level + 2 < RTREE_HEIGHT) {
+		for (size_t i = 0; i < nchildren; i++) {
+			rtree_node_elm_t *node =
+			    (rtree_node_elm_t *)atomic_load_p(&subtree[i].child,
+			    ATOMIC_RELAXED);
+			if (node != NULL) {
+				rtree_delete_subtree(tsdn, rtree, node, level +
+				    1);
+			}
+		}
+	} else {
+		for (size_t i = 0; i < nchildren; i++) {
+			rtree_leaf_elm_t *leaf =
+			    (rtree_leaf_elm_t *)atomic_load_p(&subtree[i].child,
+			    ATOMIC_RELAXED);
+			if (leaf != NULL) {
+				rtree_leaf_dalloc(tsdn, rtree, leaf);
+			}
 		}
 	}
-	rtree->dalloc(node);
+
+	if (subtree != rtree->root) {
+		rtree_node_dalloc(tsdn, rtree, subtree);
+	}
 }
+#  endif
 
 void
-rtree_delete(rtree_t *rtree)
-{
+rtree_delete(tsdn_t *tsdn, rtree_t *rtree) {
+#  if RTREE_HEIGHT > 1
+	rtree_delete_subtree(tsdn, rtree, rtree->root, 0);
+#  endif
+}
+#endif
 
-	rtree_delete_subtree(rtree, rtree->root, 0);
-	rtree->dalloc(rtree);
+static rtree_node_elm_t *
+rtree_node_init(tsdn_t *tsdn, rtree_t *rtree, unsigned level,
+    atomic_p_t *elmp) {
+	malloc_mutex_lock(tsdn, &rtree->init_lock);
+	/*
+	 * If *elmp is non-null, then it was initialized with the init lock
+	 * held, so we can get by with 'relaxed' here.
+	 */
+	rtree_node_elm_t *node = atomic_load_p(elmp, ATOMIC_RELAXED);
+	if (node == NULL) {
+		node = rtree_node_alloc(tsdn, rtree, ZU(1) <<
+		    rtree_levels[level].bits);
+		if (node == NULL) {
+			malloc_mutex_unlock(tsdn, &rtree->init_lock);
+			return NULL;
+		}
+		/*
+		 * Even though we hold the lock, a later reader might not; we
+		 * need release semantics.
+		 */
+		atomic_store_p(elmp, node, ATOMIC_RELEASE);
+	}
+	malloc_mutex_unlock(tsdn, &rtree->init_lock);
+
+	return node;
 }
 
-void
-rtree_prefork(rtree_t *rtree)
-{
+static rtree_leaf_elm_t *
+rtree_leaf_init(tsdn_t *tsdn, rtree_t *rtree, atomic_p_t *elmp) {
+	malloc_mutex_lock(tsdn, &rtree->init_lock);
+	/*
+	 * If *elmp is non-null, then it was initialized with the init lock
+	 * held, so we can get by with 'relaxed' here.
+	 */
+	rtree_leaf_elm_t *leaf = atomic_load_p(elmp, ATOMIC_RELAXED);
+	if (leaf == NULL) {
+		leaf = rtree_leaf_alloc(tsdn, rtree, ZU(1) <<
+		    rtree_levels[RTREE_HEIGHT-1].bits);
+		if (leaf == NULL) {
+			malloc_mutex_unlock(tsdn, &rtree->init_lock);
+			return NULL;
+		}
+		/*
+		 * Even though we hold the lock, a later reader might not; we
+		 * need release semantics.
+		 */
+		atomic_store_p(elmp, leaf, ATOMIC_RELEASE);
+	}
+	malloc_mutex_unlock(tsdn, &rtree->init_lock);
 
-	malloc_mutex_prefork(&rtree->mutex);
+	return leaf;
 }
 
-void
-rtree_postfork_parent(rtree_t *rtree)
-{
+static bool
+rtree_node_valid(rtree_node_elm_t *node) {
+	return ((uintptr_t)node != (uintptr_t)0);
+}
 
-	malloc_mutex_postfork_parent(&rtree->mutex);
+static bool
+rtree_leaf_valid(rtree_leaf_elm_t *leaf) {
+	return ((uintptr_t)leaf != (uintptr_t)0);
 }
 
-void
-rtree_postfork_child(rtree_t *rtree)
-{
+static rtree_node_elm_t *
+rtree_child_node_tryread(rtree_node_elm_t *elm, bool dependent) {
+	rtree_node_elm_t *node;
+
+	if (dependent) {
+		node = (rtree_node_elm_t *)atomic_load_p(&elm->child,
+		    ATOMIC_RELAXED);
+	} else {
+		node = (rtree_node_elm_t *)atomic_load_p(&elm->child,
+		    ATOMIC_ACQUIRE);
+	}
 
-	malloc_mutex_postfork_child(&rtree->mutex);
+	assert(!dependent || node != NULL);
+	return node;
+}
+
+static rtree_node_elm_t *
+rtree_child_node_read(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *elm,
+    unsigned level, bool dependent) {
+	rtree_node_elm_t *node;
+
+	node = rtree_child_node_tryread(elm, dependent);
+	if (!dependent && unlikely(!rtree_node_valid(node))) {
+		node = rtree_node_init(tsdn, rtree, level + 1, &elm->child);
+	}
+	assert(!dependent || node != NULL);
+	return node;
+}
+
+static rtree_leaf_elm_t *
+rtree_child_leaf_tryread(rtree_node_elm_t *elm, bool dependent) {
+	rtree_leaf_elm_t *leaf;
+
+	if (dependent) {
+		leaf = (rtree_leaf_elm_t *)atomic_load_p(&elm->child,
+		    ATOMIC_RELAXED);
+	} else {
+		leaf = (rtree_leaf_elm_t *)atomic_load_p(&elm->child,
+		    ATOMIC_ACQUIRE);
+	}
+
+	assert(!dependent || leaf != NULL);
+	return leaf;
+}
+
+static rtree_leaf_elm_t *
+rtree_child_leaf_read(tsdn_t *tsdn, rtree_t *rtree, rtree_node_elm_t *elm,
+    unsigned level, bool dependent) {
+	rtree_leaf_elm_t *leaf;
+
+	leaf = rtree_child_leaf_tryread(elm, dependent);
+	if (!dependent && unlikely(!rtree_leaf_valid(leaf))) {
+		leaf = rtree_leaf_init(tsdn, rtree, &elm->child);
+	}
+	assert(!dependent || leaf != NULL);
+	return leaf;
+}
+
+rtree_leaf_elm_t *
+rtree_leaf_elm_lookup_hard(tsdn_t *tsdn, rtree_t *rtree, rtree_ctx_t *rtree_ctx,
+    uintptr_t key, bool dependent, bool init_missing) {
+	rtree_node_elm_t *node;
+	rtree_leaf_elm_t *leaf;
+#if RTREE_HEIGHT > 1
+	node = rtree->root;
+#else
+	leaf = rtree->root;
+#endif
+
+	if (config_debug) {
+		uintptr_t leafkey = rtree_leafkey(key);
+		for (unsigned i = 0; i < RTREE_CTX_NCACHE; i++) {
+			assert(rtree_ctx->cache[i].leafkey != leafkey);
+		}
+		for (unsigned i = 0; i < RTREE_CTX_NCACHE_L2; i++) {
+			assert(rtree_ctx->l2_cache[i].leafkey != leafkey);
+		}
+	}
+
+#define RTREE_GET_CHILD(level) {					\
+		assert(level < RTREE_HEIGHT-1);				\
+		if (level != 0 && !dependent &&				\
+		    unlikely(!rtree_node_valid(node))) {		\
+			return NULL;					\
+		}							\
+		uintptr_t subkey = rtree_subkey(key, level);		\
+		if (level + 2 < RTREE_HEIGHT) {				\
+			node = init_missing ?				\
+			    rtree_child_node_read(tsdn, rtree,		\
+			    &node[subkey], level, dependent) :		\
+			    rtree_child_node_tryread(&node[subkey],	\
+			    dependent);					\
+		} else {						\
+			leaf = init_missing ?				\
+			    rtree_child_leaf_read(tsdn, rtree,		\
+			    &node[subkey], level, dependent) :		\
+			    rtree_child_leaf_tryread(&node[subkey],	\
+			    dependent);					\
+		}							\
+	}
+	/*
+	 * Cache replacement upon hard lookup (i.e. L1 & L2 rtree cache miss):
+	 * (1) evict last entry in L2 cache; (2) move the collision slot from L1
+	 * cache down to L2; and 3) fill L1.
+	 */
+#define RTREE_GET_LEAF(level) {						\
+		assert(level == RTREE_HEIGHT-1);			\
+		if (!dependent && unlikely(!rtree_leaf_valid(leaf))) {	\
+			return NULL;					\
+		}							\
+		if (RTREE_CTX_NCACHE_L2 > 1) {				\
+			memmove(&rtree_ctx->l2_cache[1],		\
+			    &rtree_ctx->l2_cache[0],			\
+			    sizeof(rtree_ctx_cache_elm_t) *		\
+			    (RTREE_CTX_NCACHE_L2 - 1));			\
+		}							\
+		size_t slot = rtree_cache_direct_map(key);		\
+		rtree_ctx->l2_cache[0].leafkey =			\
+		    rtree_ctx->cache[slot].leafkey;			\
+		rtree_ctx->l2_cache[0].leaf =				\
+		    rtree_ctx->cache[slot].leaf;			\
+		uintptr_t leafkey = rtree_leafkey(key);			\
+		rtree_ctx->cache[slot].leafkey = leafkey;		\
+		rtree_ctx->cache[slot].leaf = leaf;			\
+		uintptr_t subkey = rtree_subkey(key, level);		\
+		return &leaf[subkey];					\
+	}
+	if (RTREE_HEIGHT > 1) {
+		RTREE_GET_CHILD(0)
+	}
+	if (RTREE_HEIGHT > 2) {
+		RTREE_GET_CHILD(1)
+	}
+	if (RTREE_HEIGHT > 3) {
+		for (unsigned i = 2; i < RTREE_HEIGHT-1; i++) {
+			RTREE_GET_CHILD(i)
+		}
+	}
+	RTREE_GET_LEAF(RTREE_HEIGHT-1)
+#undef RTREE_GET_CHILD
+#undef RTREE_GET_LEAF
+	not_reached();
+}
+
+void
+rtree_ctx_data_init(rtree_ctx_t *ctx) {
+	for (unsigned i = 0; i < RTREE_CTX_NCACHE; i++) {
+		rtree_ctx_cache_elm_t *cache = &ctx->cache[i];
+		cache->leafkey = RTREE_LEAFKEY_INVALID;
+		cache->leaf = NULL;
+	}
+	for (unsigned i = 0; i < RTREE_CTX_NCACHE_L2; i++) {
+		rtree_ctx_cache_elm_t *cache = &ctx->l2_cache[i];
+		cache->leafkey = RTREE_LEAFKEY_INVALID;
+		cache->leaf = NULL;
+	}
 }
diff --git a/modules/worldengine/deps/jemalloc/src/spin.c b/modules/worldengine/deps/jemalloc/src/spin.c
new file mode 100644
index 0000000000..24372c26c9
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/spin.c
@@ -0,0 +1,4 @@
+#define JEMALLOC_SPIN_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+
+#include "jemalloc/internal/spin.h"
diff --git a/modules/worldengine/deps/jemalloc/src/stats.c b/modules/worldengine/deps/jemalloc/src/stats.c
index bef2ab33cd..087df7676e 100644
--- a/modules/worldengine/deps/jemalloc/src/stats.c
+++ b/modules/worldengine/deps/jemalloc/src/stats.c
@@ -1,549 +1,1285 @@
-#define	JEMALLOC_STATS_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_STATS_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
 
-#define	CTL_GET(n, v, t) do {						\
-	size_t sz = sizeof(t);						\
-	xmallctl(n, v, &sz, NULL, 0);					\
-} while (0)
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/ctl.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/mutex_prof.h"
 
-#define	CTL_I_GET(n, v, t) do {						\
-	size_t mib[6];							\
-	size_t miblen = sizeof(mib) / sizeof(size_t);			\
+const char *global_mutex_names[mutex_prof_num_global_mutexes] = {
+#define OP(mtx) #mtx,
+	MUTEX_PROF_GLOBAL_MUTEXES
+#undef OP
+};
+
+const char *arena_mutex_names[mutex_prof_num_arena_mutexes] = {
+#define OP(mtx) #mtx,
+	MUTEX_PROF_ARENA_MUTEXES
+#undef OP
+};
+
+#define CTL_GET(n, v, t) do {						\
 	size_t sz = sizeof(t);						\
-	xmallctlnametomib(n, mib, &miblen);				\
-	mib[2] = i;							\
-	xmallctlbymib(mib, miblen, v, &sz, NULL, 0);			\
+	xmallctl(n, (void *)v, &sz, NULL, 0);				\
 } while (0)
 
-#define	CTL_J_GET(n, v, t) do {						\
-	size_t mib[6];							\
+#define CTL_M2_GET(n, i, v, t) do {					\
+	size_t mib[CTL_MAX_DEPTH];					\
 	size_t miblen = sizeof(mib) / sizeof(size_t);			\
 	size_t sz = sizeof(t);						\
 	xmallctlnametomib(n, mib, &miblen);				\
-	mib[2] = j;							\
-	xmallctlbymib(mib, miblen, v, &sz, NULL, 0);			\
+	mib[2] = (i);							\
+	xmallctlbymib(mib, miblen, (void *)v, &sz, NULL, 0);		\
 } while (0)
 
-#define	CTL_IJ_GET(n, v, t) do {					\
-	size_t mib[6];							\
+#define CTL_M2_M4_GET(n, i, j, v, t) do {				\
+	size_t mib[CTL_MAX_DEPTH];					\
 	size_t miblen = sizeof(mib) / sizeof(size_t);			\
 	size_t sz = sizeof(t);						\
 	xmallctlnametomib(n, mib, &miblen);				\
-	mib[2] = i;							\
-	mib[4] = j;							\
-	xmallctlbymib(mib, miblen, v, &sz, NULL, 0);			\
+	mib[2] = (i);							\
+	mib[4] = (j);							\
+	xmallctlbymib(mib, miblen, (void *)v, &sz, NULL, 0);		\
 } while (0)
 
 /******************************************************************************/
 /* Data. */
 
-bool	opt_stats_print = false;
-
-size_t	stats_cactive = 0;
+bool opt_stats_print = false;
+char opt_stats_print_opts[stats_print_tot_num_options+1] = "";
 
 /******************************************************************************/
-/* Function prototypes for non-inline static functions. */
 
-static void	stats_arena_bins_print(void (*write_cb)(void *, const char *),
-    void *cbopaque, unsigned i);
-static void	stats_arena_lruns_print(void (*write_cb)(void *, const char *),
-    void *cbopaque, unsigned i);
-static void	stats_arena_print(void (*write_cb)(void *, const char *),
-    void *cbopaque, unsigned i, bool bins, bool large);
+/* Calculate x.yyy and output a string (takes a fixed sized char array). */
+static bool
+get_rate_str(uint64_t dividend, uint64_t divisor, char str[6]) {
+	if (divisor == 0 || dividend > divisor) {
+		/* The rate is not supposed to be greater than 1. */
+		return true;
+	}
+	if (dividend > 0) {
+		assert(UINT64_MAX / dividend >= 1000);
+	}
 
-/******************************************************************************/
+	unsigned n = (unsigned)((dividend * 1000) / divisor);
+	if (n < 10) {
+		malloc_snprintf(str, 6, "0.00%u", n);
+	} else if (n < 100) {
+		malloc_snprintf(str, 6, "0.0%u", n);
+	} else if (n < 1000) {
+		malloc_snprintf(str, 6, "0.%u", n);
+	} else {
+		malloc_snprintf(str, 6, "1");
+	}
+
+	return false;
+}
+
+#define MUTEX_CTL_STR_MAX_LENGTH 128
+static void
+gen_mutex_ctl_str(char *str, size_t buf_len, const char *prefix,
+    const char *mutex, const char *counter) {
+	malloc_snprintf(str, buf_len, "stats.%s.%s.%s", prefix, mutex, counter);
+}
+
+static void
+read_arena_bin_mutex_stats(unsigned arena_ind, unsigned bin_ind,
+    uint64_t results[mutex_prof_num_counters]) {
+	char cmd[MUTEX_CTL_STR_MAX_LENGTH];
+#define OP(c, t)							\
+    gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH,			\
+        "arenas.0.bins.0","mutex", #c);					\
+    CTL_M2_M4_GET(cmd, arena_ind, bin_ind,				\
+        (t *)&results[mutex_counter_##c], t);
+MUTEX_PROF_COUNTERS
+#undef OP
+}
+
+static void
+mutex_stats_output_json(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *name, uint64_t stats[mutex_prof_num_counters],
+    const char *json_indent, bool last) {
+	malloc_cprintf(write_cb, cbopaque, "%s\"%s\": {\n", json_indent, name);
+
+	mutex_prof_counter_ind_t k = 0;
+	char *fmt_str[2] = {"%s\t\"%s\": %"FMTu32"%s\n",
+	    "%s\t\"%s\": %"FMTu64"%s\n"};
+#define OP(c, t)							\
+	malloc_cprintf(write_cb, cbopaque,				\
+	    fmt_str[sizeof(t) / sizeof(uint32_t) - 1], 			\
+	    json_indent, #c, (t)stats[mutex_counter_##c],		\
+	    (++k == mutex_prof_num_counters) ? "" : ",");
+MUTEX_PROF_COUNTERS
+#undef OP
+	malloc_cprintf(write_cb, cbopaque, "%s}%s\n", json_indent,
+	    last ? "" : ",");
+}
 
 static void
 stats_arena_bins_print(void (*write_cb)(void *, const char *), void *cbopaque,
-    unsigned i)
-{
+    bool json, bool large, bool mutex, unsigned i) {
 	size_t page;
-	bool config_tcache;
-	unsigned nbins, j, gap_start;
+	bool in_gap, in_gap_prev;
+	unsigned nbins, j;
 
 	CTL_GET("arenas.page", &page, size_t);
 
-	CTL_GET("config.tcache", &config_tcache, bool);
-	if (config_tcache) {
+	CTL_GET("arenas.nbins", &nbins, unsigned);
+	if (json) {
 		malloc_cprintf(write_cb, cbopaque,
-		    "bins:     bin  size regs pgs    allocated      nmalloc"
-		    "      ndalloc    nrequests       nfills     nflushes"
-		    "      newruns       reruns      curruns\n");
+		    "\t\t\t\t\"bins\": [\n");
 	} else {
+		char *mutex_counters = "   n_lock_ops    n_waiting"
+		    "   n_spin_acq  total_wait_ns  max_wait_ns\n";
 		malloc_cprintf(write_cb, cbopaque,
-		    "bins:     bin  size regs pgs    allocated      nmalloc"
-		    "      ndalloc      newruns       reruns      curruns\n");
+		    "bins:           size ind    allocated      nmalloc"
+		    "      ndalloc    nrequests      curregs     curslabs regs"
+		    " pgs  util       nfills     nflushes     newslabs"
+		    "      reslabs%s", mutex ? mutex_counters : "\n");
 	}
-	CTL_GET("arenas.nbins", &nbins, unsigned);
-	for (j = 0, gap_start = UINT_MAX; j < nbins; j++) {
-		uint64_t nruns;
+	for (j = 0, in_gap = false; j < nbins; j++) {
+		uint64_t nslabs;
+		size_t reg_size, slab_size, curregs;
+		size_t curslabs;
+		uint32_t nregs;
+		uint64_t nmalloc, ndalloc, nrequests, nfills, nflushes;
+		uint64_t nreslabs;
 
-		CTL_IJ_GET("stats.arenas.0.bins.0.nruns", &nruns, uint64_t);
-		if (nruns == 0) {
-			if (gap_start == UINT_MAX)
-				gap_start = j;
-		} else {
-			size_t reg_size, run_size, allocated;
-			uint32_t nregs;
-			uint64_t nmalloc, ndalloc, nrequests, nfills, nflushes;
-			uint64_t reruns;
-			size_t curruns;
-
-			if (gap_start != UINT_MAX) {
-				if (j > gap_start + 1) {
-					/* Gap of more than one size class. */
-					malloc_cprintf(write_cb, cbopaque,
-					    "[%u..%u]\n", gap_start,
-					    j - 1);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nslabs", i, j, &nslabs,
+		    uint64_t);
+		in_gap_prev = in_gap;
+		in_gap = (nslabs == 0);
+
+		if (!json && in_gap_prev && !in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
+		}
+
+		CTL_M2_GET("arenas.bin.0.size", j, &reg_size, size_t);
+		CTL_M2_GET("arenas.bin.0.nregs", j, &nregs, uint32_t);
+		CTL_M2_GET("arenas.bin.0.slab_size", j, &slab_size, size_t);
+
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nmalloc", i, j, &nmalloc,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.ndalloc", i, j, &ndalloc,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.curregs", i, j, &curregs,
+		    size_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nrequests", i, j,
+		    &nrequests, uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nfills", i, j, &nfills,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nflushes", i, j, &nflushes,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nreslabs", i, j, &nreslabs,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.curslabs", i, j, &curslabs,
+		    size_t);
+
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t{\n"
+			    "\t\t\t\t\t\t\"nmalloc\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"ndalloc\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"curregs\": %zu,\n"
+			    "\t\t\t\t\t\t\"nrequests\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"nfills\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"nflushes\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"nreslabs\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"curslabs\": %zu%s\n",
+			    nmalloc, ndalloc, curregs, nrequests, nfills,
+			    nflushes, nreslabs, curslabs, mutex ? "," : "");
+			if (mutex) {
+				uint64_t mutex_stats[mutex_prof_num_counters];
+				read_arena_bin_mutex_stats(i, j, mutex_stats);
+				mutex_stats_output_json(write_cb, cbopaque,
+				    "mutex", mutex_stats, "\t\t\t\t\t\t", true);
+			}
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t}%s\n",
+			    (j + 1 < nbins) ? "," : "");
+		} else if (!in_gap) {
+			size_t availregs = nregs * curslabs;
+			char util[6];
+			if (get_rate_str((uint64_t)curregs, (uint64_t)availregs,
+			    util)) {
+				if (availregs == 0) {
+					malloc_snprintf(util, sizeof(util),
+					    "1");
+				} else if (curregs > availregs) {
+					/*
+					 * Race detected: the counters were read
+					 * in separate mallctl calls and
+					 * concurrent operations happened in
+					 * between. In this case no meaningful
+					 * utilization can be computed.
+					 */
+					malloc_snprintf(util, sizeof(util),
+					    " race");
 				} else {
-					/* Gap of one size class. */
-					malloc_cprintf(write_cb, cbopaque,
-					    "[%u]\n", gap_start);
+					not_reached();
 				}
-				gap_start = UINT_MAX;
 			}
-			CTL_J_GET("arenas.bin.0.size", &reg_size, size_t);
-			CTL_J_GET("arenas.bin.0.nregs", &nregs, uint32_t);
-			CTL_J_GET("arenas.bin.0.run_size", &run_size, size_t);
-			CTL_IJ_GET("stats.arenas.0.bins.0.allocated",
-			    &allocated, size_t);
-			CTL_IJ_GET("stats.arenas.0.bins.0.nmalloc",
-			    &nmalloc, uint64_t);
-			CTL_IJ_GET("stats.arenas.0.bins.0.ndalloc",
-			    &ndalloc, uint64_t);
-			if (config_tcache) {
-				CTL_IJ_GET("stats.arenas.0.bins.0.nrequests",
-				    &nrequests, uint64_t);
-				CTL_IJ_GET("stats.arenas.0.bins.0.nfills",
-				    &nfills, uint64_t);
-				CTL_IJ_GET("stats.arenas.0.bins.0.nflushes",
-				    &nflushes, uint64_t);
+			uint64_t mutex_stats[mutex_prof_num_counters];
+			if (mutex) {
+				read_arena_bin_mutex_stats(i, j, mutex_stats);
 			}
-			CTL_IJ_GET("stats.arenas.0.bins.0.nreruns", &reruns,
-			    uint64_t);
-			CTL_IJ_GET("stats.arenas.0.bins.0.curruns", &curruns,
-			    size_t);
-			if (config_tcache) {
+
+			malloc_cprintf(write_cb, cbopaque, "%20zu %3u %12zu %12"
+			    FMTu64" %12"FMTu64" %12"FMTu64" %12zu %12zu %4u"
+			    " %3zu %-5s %12"FMTu64" %12"FMTu64" %12"FMTu64
+			    " %12"FMTu64, reg_size, j, curregs * reg_size,
+			    nmalloc, ndalloc, nrequests, curregs, curslabs,
+			    nregs, slab_size / page, util, nfills, nflushes,
+			    nslabs, nreslabs);
+
+			/* Output less info for bin mutexes to save space. */
+			if (mutex) {
 				malloc_cprintf(write_cb, cbopaque,
-				    "%13u %5zu %4u %3zu %12zu %12"PRIu64
-				    " %12"PRIu64" %12"PRIu64" %12"PRIu64
-				    " %12"PRIu64" %12"PRIu64" %12"PRIu64
-				    " %12zu\n",
-				    j, reg_size, nregs, run_size / page,
-				    allocated, nmalloc, ndalloc, nrequests,
-				    nfills, nflushes, nruns, reruns, curruns);
+				    " %12"FMTu64" %12"FMTu64" %12"FMTu64
+				    " %14"FMTu64" %12"FMTu64"\n",
+				    mutex_stats[mutex_counter_num_ops],
+				    mutex_stats[mutex_counter_num_wait],
+				    mutex_stats[mutex_counter_num_spin_acq],
+				    mutex_stats[mutex_counter_total_wait_time],
+				    mutex_stats[mutex_counter_max_wait_time]);
 			} else {
-				malloc_cprintf(write_cb, cbopaque,
-				    "%13u %5zu %4u %3zu %12zu %12"PRIu64
-				    " %12"PRIu64" %12"PRIu64" %12"PRIu64
-				    " %12zu\n",
-				    j, reg_size, nregs, run_size / page,
-				    allocated, nmalloc, ndalloc, nruns, reruns,
-				    curruns);
+				malloc_cprintf(write_cb, cbopaque, "\n");
 			}
 		}
 	}
-	if (gap_start != UINT_MAX) {
-		if (j > gap_start + 1) {
-			/* Gap of more than one size class. */
-			malloc_cprintf(write_cb, cbopaque, "[%u..%u]\n",
-			    gap_start, j - 1);
-		} else {
-			/* Gap of one size class. */
-			malloc_cprintf(write_cb, cbopaque, "[%u]\n", gap_start);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t]%s\n", large ? "," : "");
+	} else {
+		if (in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
 		}
 	}
 }
 
 static void
-stats_arena_lruns_print(void (*write_cb)(void *, const char *), void *cbopaque,
-    unsigned i)
-{
-	size_t page, nlruns, j;
-	ssize_t gap_start;
-
-	CTL_GET("arenas.page", &page, size_t);
+stats_arena_lextents_print(void (*write_cb)(void *, const char *),
+    void *cbopaque, bool json, unsigned i) {
+	unsigned nbins, nlextents, j;
+	bool in_gap, in_gap_prev;
 
-	malloc_cprintf(write_cb, cbopaque,
-	    "large:   size pages      nmalloc      ndalloc    nrequests"
-	    "      curruns\n");
-	CTL_GET("arenas.nlruns", &nlruns, size_t);
-	for (j = 0, gap_start = -1; j < nlruns; j++) {
+	CTL_GET("arenas.nbins", &nbins, unsigned);
+	CTL_GET("arenas.nlextents", &nlextents, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"lextents\": [\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "large:          size ind    allocated      nmalloc"
+		    "      ndalloc    nrequests  curlextents\n");
+	}
+	for (j = 0, in_gap = false; j < nlextents; j++) {
 		uint64_t nmalloc, ndalloc, nrequests;
-		size_t run_size, curruns;
+		size_t lextent_size, curlextents;
 
-		CTL_IJ_GET("stats.arenas.0.lruns.0.nmalloc", &nmalloc,
-		    uint64_t);
-		CTL_IJ_GET("stats.arenas.0.lruns.0.ndalloc", &ndalloc,
-		    uint64_t);
-		CTL_IJ_GET("stats.arenas.0.lruns.0.nrequests", &nrequests,
-		    uint64_t);
-		if (nrequests == 0) {
-			if (gap_start == -1)
-				gap_start = j;
-		} else {
-			CTL_J_GET("arenas.lrun.0.size", &run_size, size_t);
-			CTL_IJ_GET("stats.arenas.0.lruns.0.curruns", &curruns,
-			    size_t);
-			if (gap_start != -1) {
-				malloc_cprintf(write_cb, cbopaque, "[%zu]\n",
-				    j - gap_start);
-				gap_start = -1;
-			}
+		CTL_M2_M4_GET("stats.arenas.0.lextents.0.nmalloc", i, j,
+		    &nmalloc, uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.lextents.0.ndalloc", i, j,
+		    &ndalloc, uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.lextents.0.nrequests", i, j,
+		    &nrequests, uint64_t);
+		in_gap_prev = in_gap;
+		in_gap = (nrequests == 0);
+
+		if (!json && in_gap_prev && !in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
+		}
+
+		CTL_M2_GET("arenas.lextent.0.size", j, &lextent_size, size_t);
+		CTL_M2_M4_GET("stats.arenas.0.lextents.0.curlextents", i, j,
+		    &curlextents, size_t);
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t{\n"
+			    "\t\t\t\t\t\t\"curlextents\": %zu\n"
+			    "\t\t\t\t\t}%s\n",
+			    curlextents,
+			    (j + 1 < nlextents) ? "," : "");
+		} else if (!in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "%20zu %3u %12zu %12"FMTu64" %12"FMTu64
+			    " %12"FMTu64" %12zu\n",
+			    lextent_size, nbins + j,
+			    curlextents * lextent_size, nmalloc, ndalloc,
+			    nrequests, curlextents);
+		}
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t]\n");
+	} else {
+		if (in_gap) {
 			malloc_cprintf(write_cb, cbopaque,
-			    "%13zu %5zu %12"PRIu64" %12"PRIu64" %12"PRIu64
-			    " %12zu\n",
-			    run_size, run_size / page, nmalloc, ndalloc,
-			    nrequests, curruns);
+			    "                     ---\n");
+		}
+	}
+}
+
+static void
+read_arena_mutex_stats(unsigned arena_ind,
+    uint64_t results[mutex_prof_num_arena_mutexes][mutex_prof_num_counters]) {
+	char cmd[MUTEX_CTL_STR_MAX_LENGTH];
+
+	mutex_prof_arena_ind_t i;
+	for (i = 0; i < mutex_prof_num_arena_mutexes; i++) {
+#define OP(c, t)							\
+		gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH,	\
+		    "arenas.0.mutexes",	arena_mutex_names[i], #c);	\
+		CTL_M2_GET(cmd, arena_ind,				\
+		    (t *)&results[i][mutex_counter_##c], t);
+MUTEX_PROF_COUNTERS
+#undef OP
+	}
+}
+
+static void
+mutex_stats_output(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *name, uint64_t stats[mutex_prof_num_counters],
+    bool first_mutex) {
+	if (first_mutex) {
+		/* Print title. */
+		malloc_cprintf(write_cb, cbopaque,
+		    "                           n_lock_ops       n_waiting"
+		    "      n_spin_acq  n_owner_switch   total_wait_ns"
+		    "     max_wait_ns  max_n_thds\n");
+	}
+
+	malloc_cprintf(write_cb, cbopaque, "%s", name);
+	malloc_cprintf(write_cb, cbopaque, ":%*c",
+	    (int)(20 - strlen(name)), ' ');
+
+	char *fmt_str[2] = {"%12"FMTu32, "%16"FMTu64};
+#define OP(c, t)							\
+	malloc_cprintf(write_cb, cbopaque,				\
+	    fmt_str[sizeof(t) / sizeof(uint32_t) - 1],			\
+	    (t)stats[mutex_counter_##c]);
+MUTEX_PROF_COUNTERS
+#undef OP
+	malloc_cprintf(write_cb, cbopaque, "\n");
+}
+
+static void
+stats_arena_mutexes_print(void (*write_cb)(void *, const char *),
+    void *cbopaque, bool json, bool json_end, unsigned arena_ind) {
+	uint64_t mutex_stats[mutex_prof_num_arena_mutexes][mutex_prof_num_counters];
+	read_arena_mutex_stats(arena_ind, mutex_stats);
+
+	/* Output mutex stats. */
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque, "\t\t\t\t\"mutexes\": {\n");
+		mutex_prof_arena_ind_t i, last_mutex;
+		last_mutex = mutex_prof_num_arena_mutexes - 1;
+		for (i = 0; i < mutex_prof_num_arena_mutexes; i++) {
+			mutex_stats_output_json(write_cb, cbopaque,
+			    arena_mutex_names[i], mutex_stats[i],
+			    "\t\t\t\t\t", (i == last_mutex));
+		}
+		malloc_cprintf(write_cb, cbopaque, "\t\t\t\t}%s\n",
+		    json_end ? "" : ",");
+	} else {
+		mutex_prof_arena_ind_t i;
+		for (i = 0; i < mutex_prof_num_arena_mutexes; i++) {
+			mutex_stats_output(write_cb, cbopaque,
+			    arena_mutex_names[i], mutex_stats[i], i == 0);
 		}
 	}
-	if (gap_start != -1)
-		malloc_cprintf(write_cb, cbopaque, "[%zu]\n", j - gap_start);
 }
 
 static void
 stats_arena_print(void (*write_cb)(void *, const char *), void *cbopaque,
-    unsigned i, bool bins, bool large)
-{
+    bool json, unsigned i, bool bins, bool large, bool mutex) {
 	unsigned nthreads;
 	const char *dss;
-	size_t page, pactive, pdirty, mapped;
-	uint64_t npurge, nmadvise, purged;
+	ssize_t dirty_decay_ms, muzzy_decay_ms;
+	size_t page, pactive, pdirty, pmuzzy, mapped, retained;
+	size_t base, internal, resident;
+	uint64_t dirty_npurge, dirty_nmadvise, dirty_purged;
+	uint64_t muzzy_npurge, muzzy_nmadvise, muzzy_purged;
 	size_t small_allocated;
 	uint64_t small_nmalloc, small_ndalloc, small_nrequests;
 	size_t large_allocated;
 	uint64_t large_nmalloc, large_ndalloc, large_nrequests;
+	size_t tcache_bytes;
+	uint64_t uptime;
 
 	CTL_GET("arenas.page", &page, size_t);
 
-	CTL_I_GET("stats.arenas.0.nthreads", &nthreads, unsigned);
-	malloc_cprintf(write_cb, cbopaque,
-	    "assigned threads: %u\n", nthreads);
-	CTL_I_GET("stats.arenas.0.dss", &dss, const char *);
-	malloc_cprintf(write_cb, cbopaque, "dss allocation precedence: %s\n",
-	    dss);
-	CTL_I_GET("stats.arenas.0.pactive", &pactive, size_t);
-	CTL_I_GET("stats.arenas.0.pdirty", &pdirty, size_t);
-	CTL_I_GET("stats.arenas.0.npurge", &npurge, uint64_t);
-	CTL_I_GET("stats.arenas.0.nmadvise", &nmadvise, uint64_t);
-	CTL_I_GET("stats.arenas.0.purged", &purged, uint64_t);
-	malloc_cprintf(write_cb, cbopaque,
-	    "dirty pages: %zu:%zu active:dirty, %"PRIu64" sweep%s,"
-	    " %"PRIu64" madvise%s, %"PRIu64" purged\n",
-	    pactive, pdirty, npurge, npurge == 1 ? "" : "s",
-	    nmadvise, nmadvise == 1 ? "" : "s", purged);
-
-	malloc_cprintf(write_cb, cbopaque,
-	    "            allocated      nmalloc      ndalloc    nrequests\n");
-	CTL_I_GET("stats.arenas.0.small.allocated", &small_allocated, size_t);
-	CTL_I_GET("stats.arenas.0.small.nmalloc", &small_nmalloc, uint64_t);
-	CTL_I_GET("stats.arenas.0.small.ndalloc", &small_ndalloc, uint64_t);
-	CTL_I_GET("stats.arenas.0.small.nrequests", &small_nrequests, uint64_t);
-	malloc_cprintf(write_cb, cbopaque,
-	    "small:   %12zu %12"PRIu64" %12"PRIu64" %12"PRIu64"\n",
-	    small_allocated, small_nmalloc, small_ndalloc, small_nrequests);
-	CTL_I_GET("stats.arenas.0.large.allocated", &large_allocated, size_t);
-	CTL_I_GET("stats.arenas.0.large.nmalloc", &large_nmalloc, uint64_t);
-	CTL_I_GET("stats.arenas.0.large.ndalloc", &large_ndalloc, uint64_t);
-	CTL_I_GET("stats.arenas.0.large.nrequests", &large_nrequests, uint64_t);
-	malloc_cprintf(write_cb, cbopaque,
-	    "large:   %12zu %12"PRIu64" %12"PRIu64" %12"PRIu64"\n",
-	    large_allocated, large_nmalloc, large_ndalloc, large_nrequests);
-	malloc_cprintf(write_cb, cbopaque,
-	    "total:   %12zu %12"PRIu64" %12"PRIu64" %12"PRIu64"\n",
-	    small_allocated + large_allocated,
-	    small_nmalloc + large_nmalloc,
-	    small_ndalloc + large_ndalloc,
-	    small_nrequests + large_nrequests);
-	malloc_cprintf(write_cb, cbopaque, "active:  %12zu\n", pactive * page);
-	CTL_I_GET("stats.arenas.0.mapped", &mapped, size_t);
-	malloc_cprintf(write_cb, cbopaque, "mapped:  %12zu\n", mapped);
-
-	if (bins)
-		stats_arena_bins_print(write_cb, cbopaque, i);
-	if (large)
-		stats_arena_lruns_print(write_cb, cbopaque, i);
-}
+	CTL_M2_GET("stats.arenas.0.nthreads", i, &nthreads, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"nthreads\": %u,\n", nthreads);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "assigned threads: %u\n", nthreads);
+	}
 
-void
-stats_print(void (*write_cb)(void *, const char *), void *cbopaque,
-    const char *opts)
-{
-	int err;
-	uint64_t epoch;
-	size_t u64sz;
-	bool general = true;
-	bool merged = true;
-	bool unmerged = true;
-	bool bins = true;
-	bool large = true;
+	CTL_M2_GET("stats.arenas.0.uptime", i, &uptime, uint64_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"uptime_ns\": %"FMTu64",\n", uptime);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "uptime: %"FMTu64"\n", uptime);
+	}
 
-	/*
-	 * Refresh stats, in case mallctl() was called by the application.
-	 *
-	 * Check for OOM here, since refreshing the ctl cache can trigger
-	 * allocation.  In practice, none of the subsequent mallctl()-related
-	 * calls in this function will cause OOM if this one succeeds.
-	 * */
-	epoch = 1;
-	u64sz = sizeof(uint64_t);
-	err = je_mallctl("epoch", &epoch, &u64sz, &epoch, sizeof(uint64_t));
-	if (err != 0) {
-		if (err == EAGAIN) {
-			malloc_write("<jemalloc>: Memory allocation failure in "
-			    "mallctl(\"epoch\", ...)\n");
-			return;
+	CTL_M2_GET("stats.arenas.0.dss", i, &dss, const char *);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"dss\": \"%s\",\n", dss);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "dss allocation precedence: %s\n", dss);
+	}
+
+	CTL_M2_GET("stats.arenas.0.dirty_decay_ms", i, &dirty_decay_ms,
+	    ssize_t);
+	CTL_M2_GET("stats.arenas.0.muzzy_decay_ms", i, &muzzy_decay_ms,
+	    ssize_t);
+	CTL_M2_GET("stats.arenas.0.pactive", i, &pactive, size_t);
+	CTL_M2_GET("stats.arenas.0.pdirty", i, &pdirty, size_t);
+	CTL_M2_GET("stats.arenas.0.pmuzzy", i, &pmuzzy, size_t);
+	CTL_M2_GET("stats.arenas.0.dirty_npurge", i, &dirty_npurge, uint64_t);
+	CTL_M2_GET("stats.arenas.0.dirty_nmadvise", i, &dirty_nmadvise,
+	    uint64_t);
+	CTL_M2_GET("stats.arenas.0.dirty_purged", i, &dirty_purged, uint64_t);
+	CTL_M2_GET("stats.arenas.0.muzzy_npurge", i, &muzzy_npurge, uint64_t);
+	CTL_M2_GET("stats.arenas.0.muzzy_nmadvise", i, &muzzy_nmadvise,
+	    uint64_t);
+	CTL_M2_GET("stats.arenas.0.muzzy_purged", i, &muzzy_purged, uint64_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"dirty_decay_ms\": %zd,\n", dirty_decay_ms);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"muzzy_decay_ms\": %zd,\n", muzzy_decay_ms);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"pactive\": %zu,\n", pactive);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"pdirty\": %zu,\n", pdirty);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"pmuzzy\": %zu,\n", pmuzzy);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"dirty_npurge\": %"FMTu64",\n", dirty_npurge);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"dirty_nmadvise\": %"FMTu64",\n", dirty_nmadvise);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"dirty_purged\": %"FMTu64",\n", dirty_purged);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"muzzy_npurge\": %"FMTu64",\n", muzzy_npurge);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"muzzy_nmadvise\": %"FMTu64",\n", muzzy_nmadvise);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"muzzy_purged\": %"FMTu64",\n", muzzy_purged);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "decaying:  time       npages       sweeps     madvises"
+		    "       purged\n");
+		if (dirty_decay_ms >= 0) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "   dirty: %5zd %12zu %12"FMTu64" %12"FMTu64" %12"
+			    FMTu64"\n", dirty_decay_ms, pdirty, dirty_npurge,
+			    dirty_nmadvise, dirty_purged);
+		} else {
+			malloc_cprintf(write_cb, cbopaque,
+			    "   dirty:   N/A %12zu %12"FMTu64" %12"FMTu64" %12"
+			    FMTu64"\n", pdirty, dirty_npurge, dirty_nmadvise,
+			    dirty_purged);
+		}
+		if (muzzy_decay_ms >= 0) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "   muzzy: %5zd %12zu %12"FMTu64" %12"FMTu64" %12"
+			    FMTu64"\n", muzzy_decay_ms, pmuzzy, muzzy_npurge,
+			    muzzy_nmadvise, muzzy_purged);
+		} else {
+			malloc_cprintf(write_cb, cbopaque,
+			    "   muzzy:   N/A %12zu %12"FMTu64" %12"FMTu64" %12"
+			    FMTu64"\n", pmuzzy, muzzy_npurge, muzzy_nmadvise,
+			    muzzy_purged);
 		}
-		malloc_write("<jemalloc>: Failure in mallctl(\"epoch\", "
-		    "...)\n");
-		abort();
 	}
 
-	if (opts != NULL) {
-		unsigned i;
+	CTL_M2_GET("stats.arenas.0.small.allocated", i, &small_allocated,
+	    size_t);
+	CTL_M2_GET("stats.arenas.0.small.nmalloc", i, &small_nmalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.small.ndalloc", i, &small_ndalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.small.nrequests", i, &small_nrequests,
+	    uint64_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"small\": {\n");
 
-		for (i = 0; opts[i] != '\0'; i++) {
-			switch (opts[i]) {
-			case 'g':
-				general = false;
-				break;
-			case 'm':
-				merged = false;
-				break;
-			case 'a':
-				unmerged = false;
-				break;
-			case 'b':
-				bins = false;
-				break;
-			case 'l':
-				large = false;
-				break;
-			default:;
-			}
-		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"allocated\": %zu,\n", small_allocated);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nmalloc\": %"FMTu64",\n", small_nmalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"ndalloc\": %"FMTu64",\n", small_ndalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nrequests\": %"FMTu64"\n", small_nrequests);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t},\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "                            allocated      nmalloc"
+		    "      ndalloc    nrequests\n");
+		malloc_cprintf(write_cb, cbopaque,
+		    "small:                   %12zu %12"FMTu64" %12"FMTu64
+		    " %12"FMTu64"\n",
+		    small_allocated, small_nmalloc, small_ndalloc,
+		    small_nrequests);
 	}
 
-	malloc_cprintf(write_cb, cbopaque,
-	    "___ Begin jemalloc statistics ___\n");
-	if (general) {
-		int err;
-		const char *cpv;
-		bool bv;
-		unsigned uv;
-		ssize_t ssv;
-		size_t sv, bsz, ssz, sssz, cpsz;
-
-		bsz = sizeof(bool);
-		ssz = sizeof(size_t);
-		sssz = sizeof(ssize_t);
-		cpsz = sizeof(const char *);
-
-		CTL_GET("version", &cpv, const char *);
+	CTL_M2_GET("stats.arenas.0.large.allocated", i, &large_allocated,
+	    size_t);
+	CTL_M2_GET("stats.arenas.0.large.nmalloc", i, &large_nmalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.large.ndalloc", i, &large_ndalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.large.nrequests", i, &large_nrequests,
+	    uint64_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"large\": {\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"allocated\": %zu,\n", large_allocated);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nmalloc\": %"FMTu64",\n", large_nmalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"ndalloc\": %"FMTu64",\n", large_ndalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nrequests\": %"FMTu64"\n", large_nrequests);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t},\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "large:                   %12zu %12"FMTu64" %12"FMTu64
+		    " %12"FMTu64"\n",
+		    large_allocated, large_nmalloc, large_ndalloc,
+		    large_nrequests);
+		malloc_cprintf(write_cb, cbopaque,
+		    "total:                   %12zu %12"FMTu64" %12"FMTu64
+		    " %12"FMTu64"\n",
+		    small_allocated + large_allocated, small_nmalloc +
+		    large_nmalloc, small_ndalloc + large_ndalloc,
+		    small_nrequests + large_nrequests);
+	}
+	if (!json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "active:                  %12zu\n", pactive * page);
+	}
+
+	CTL_M2_GET("stats.arenas.0.mapped", i, &mapped, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"mapped\": %zu,\n", mapped);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "mapped:                  %12zu\n", mapped);
+	}
+
+	CTL_M2_GET("stats.arenas.0.retained", i, &retained, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"retained\": %zu,\n", retained);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "retained:                %12zu\n", retained);
+	}
+
+	CTL_M2_GET("stats.arenas.0.base", i, &base, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"base\": %zu,\n", base);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "base:                    %12zu\n", base);
+	}
+
+	CTL_M2_GET("stats.arenas.0.internal", i, &internal, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"internal\": %zu,\n", internal);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "internal:                %12zu\n", internal);
+	}
+
+	CTL_M2_GET("stats.arenas.0.tcache_bytes", i, &tcache_bytes, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"tcache\": %zu,\n", tcache_bytes);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "tcache:                  %12zu\n", tcache_bytes);
+	}
+
+	CTL_M2_GET("stats.arenas.0.resident", i, &resident, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"resident\": %zu%s\n", resident,
+		    (bins || large || mutex) ? "," : "");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "resident:                %12zu\n", resident);
+	}
+
+	if (mutex) {
+		stats_arena_mutexes_print(write_cb, cbopaque, json,
+		    !(bins || large), i);
+	}
+	if (bins) {
+		stats_arena_bins_print(write_cb, cbopaque, json, large, mutex,
+		    i);
+	}
+	if (large) {
+		stats_arena_lextents_print(write_cb, cbopaque, json, i);
+	}
+}
+
+static void
+stats_general_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool more) {
+	const char *cpv;
+	bool bv;
+	unsigned uv;
+	uint32_t u32v;
+	uint64_t u64v;
+	ssize_t ssv;
+	size_t sv, bsz, usz, ssz, sssz, cpsz;
+
+	bsz = sizeof(bool);
+	usz = sizeof(unsigned);
+	ssz = sizeof(size_t);
+	sssz = sizeof(ssize_t);
+	cpsz = sizeof(const char *);
+
+	CTL_GET("version", &cpv, const char *);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		"\t\t\"version\": \"%s\",\n", cpv);
+	} else {
 		malloc_cprintf(write_cb, cbopaque, "Version: %s\n", cpv);
-		CTL_GET("config.debug", &bv, bool);
+	}
+
+	/* config. */
+#define CONFIG_WRITE_BOOL_JSON(n, c)					\
+	if (json) {							\
+		CTL_GET("config."#n, &bv, bool);			\
+		malloc_cprintf(write_cb, cbopaque,			\
+		    "\t\t\t\""#n"\": %s%s\n", bv ? "true" : "false",	\
+		    (c));						\
+	}
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"config\": {\n");
+	}
+
+	CONFIG_WRITE_BOOL_JSON(cache_oblivious, ",")
+
+	CTL_GET("config.debug", &bv, bool);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"debug\": %s,\n", bv ? "true" : "false");
+	} else {
 		malloc_cprintf(write_cb, cbopaque, "Assertions %s\n",
 		    bv ? "enabled" : "disabled");
+	}
+
+	CONFIG_WRITE_BOOL_JSON(fill, ",")
+	CONFIG_WRITE_BOOL_JSON(lazy_lock, ",")
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"malloc_conf\": \"%s\",\n",
+		    config_malloc_conf);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "config.malloc_conf: \"%s\"\n", config_malloc_conf);
+	}
+
+	CONFIG_WRITE_BOOL_JSON(prof, ",")
+	CONFIG_WRITE_BOOL_JSON(prof_libgcc, ",")
+	CONFIG_WRITE_BOOL_JSON(prof_libunwind, ",")
+	CONFIG_WRITE_BOOL_JSON(stats, ",")
+	CONFIG_WRITE_BOOL_JSON(thp, ",")
+	CONFIG_WRITE_BOOL_JSON(utrace, ",")
+	CONFIG_WRITE_BOOL_JSON(xmalloc, "")
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t},\n");
+	}
+#undef CONFIG_WRITE_BOOL_JSON
 
-#define	OPT_WRITE_BOOL(n)						\
-		if ((err = je_mallctl("opt."#n, &bv, &bsz, NULL, 0))	\
-		    == 0) {						\
+	/* opt. */
+#define OPT_WRITE_BOOL(n, c)						\
+	if (je_mallctl("opt."#n, (void *)&bv, &bsz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": %s%s\n", bv ? "true" :	\
+			    "false", (c));				\
+		} else {						\
 			malloc_cprintf(write_cb, cbopaque,		\
 			    "  opt."#n": %s\n", bv ? "true" : "false");	\
-		}
-#define	OPT_WRITE_SIZE_T(n)						\
-		if ((err = je_mallctl("opt."#n, &sv, &ssz, NULL, 0))	\
-		    == 0) {						\
+		}							\
+	}
+#define OPT_WRITE_BOOL_MUTABLE(n, m, c) {				\
+	bool bv2;							\
+	if (je_mallctl("opt."#n, (void *)&bv, &bsz, NULL, 0) == 0 &&	\
+	    je_mallctl(#m, (void *)&bv2, &bsz, NULL, 0) == 0) {		\
+		if (json) {						\
 			malloc_cprintf(write_cb, cbopaque,		\
-			"  opt."#n": %zu\n", sv);			\
-		}
-#define	OPT_WRITE_SSIZE_T(n)						\
-		if ((err = je_mallctl("opt."#n, &ssv, &sssz, NULL, 0))	\
-		    == 0) {						\
+			    "\t\t\t\""#n"\": %s%s\n", bv ? "true" :	\
+			    "false", (c));				\
+		} else {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "  opt."#n": %s ("#m": %s)\n", bv ? "true"	\
+			    : "false", bv2 ? "true" : "false");		\
+		}							\
+	}								\
+}
+#define OPT_WRITE_UNSIGNED(n, c)					\
+	if (je_mallctl("opt."#n, (void *)&uv, &usz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": %u%s\n", uv, (c));		\
+		} else {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			"  opt."#n": %u\n", uv);			\
+		}							\
+	}
+#define OPT_WRITE_SSIZE_T(n, c)						\
+	if (je_mallctl("opt."#n, (void *)&ssv, &sssz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": %zd%s\n", ssv, (c));	\
+		} else {						\
 			malloc_cprintf(write_cb, cbopaque,		\
 			    "  opt."#n": %zd\n", ssv);			\
-		}
-#define	OPT_WRITE_CHAR_P(n)						\
-		if ((err = je_mallctl("opt."#n, &cpv, &cpsz, NULL, 0))	\
-		    == 0) {						\
+		}							\
+	}
+#define OPT_WRITE_SSIZE_T_MUTABLE(n, m, c) {				\
+	ssize_t ssv2;							\
+	if (je_mallctl("opt."#n, (void *)&ssv, &sssz, NULL, 0) == 0 &&	\
+	    je_mallctl(#m, (void *)&ssv2, &sssz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": %zd%s\n", ssv, (c));	\
+		} else {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "  opt."#n": %zd ("#m": %zd)\n",		\
+			    ssv, ssv2);					\
+		}							\
+	}								\
+}
+#define OPT_WRITE_CHAR_P(n, c)						\
+	if (je_mallctl("opt."#n, (void *)&cpv, &cpsz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": \"%s\"%s\n", cpv, (c));	\
+		} else {						\
 			malloc_cprintf(write_cb, cbopaque,		\
 			    "  opt."#n": \"%s\"\n", cpv);		\
-		}
+		}							\
+	}
 
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"opt\": {\n");
+	} else {
 		malloc_cprintf(write_cb, cbopaque,
 		    "Run-time option settings:\n");
-		OPT_WRITE_BOOL(abort)
-		OPT_WRITE_SIZE_T(lg_chunk)
-		OPT_WRITE_CHAR_P(dss)
-		OPT_WRITE_SIZE_T(narenas)
-		OPT_WRITE_SSIZE_T(lg_dirty_mult)
-		OPT_WRITE_BOOL(stats_print)
-		OPT_WRITE_BOOL(junk)
-		OPT_WRITE_SIZE_T(quarantine)
-		OPT_WRITE_BOOL(redzone)
-		OPT_WRITE_BOOL(zero)
-		OPT_WRITE_BOOL(utrace)
-		OPT_WRITE_BOOL(valgrind)
-		OPT_WRITE_BOOL(xmalloc)
-		OPT_WRITE_BOOL(tcache)
-		OPT_WRITE_SSIZE_T(lg_tcache_max)
-		OPT_WRITE_BOOL(prof)
-		OPT_WRITE_CHAR_P(prof_prefix)
-		OPT_WRITE_BOOL(prof_active)
-		OPT_WRITE_SSIZE_T(lg_prof_sample)
-		OPT_WRITE_BOOL(prof_accum)
-		OPT_WRITE_SSIZE_T(lg_prof_interval)
-		OPT_WRITE_BOOL(prof_gdump)
-		OPT_WRITE_BOOL(prof_final)
-		OPT_WRITE_BOOL(prof_leak)
+	}
+	OPT_WRITE_BOOL(abort, ",")
+	OPT_WRITE_BOOL(abort_conf, ",")
+	OPT_WRITE_BOOL(retain, ",")
+	OPT_WRITE_CHAR_P(dss, ",")
+	OPT_WRITE_UNSIGNED(narenas, ",")
+	OPT_WRITE_CHAR_P(percpu_arena, ",")
+	OPT_WRITE_BOOL_MUTABLE(background_thread, background_thread, ",")
+	OPT_WRITE_SSIZE_T_MUTABLE(dirty_decay_ms, arenas.dirty_decay_ms, ",")
+	OPT_WRITE_SSIZE_T_MUTABLE(muzzy_decay_ms, arenas.muzzy_decay_ms, ",")
+	OPT_WRITE_CHAR_P(junk, ",")
+	OPT_WRITE_BOOL(zero, ",")
+	OPT_WRITE_BOOL(utrace, ",")
+	OPT_WRITE_BOOL(xmalloc, ",")
+	OPT_WRITE_BOOL(tcache, ",")
+	OPT_WRITE_SSIZE_T(lg_tcache_max, ",")
+	OPT_WRITE_BOOL(prof, ",")
+	OPT_WRITE_CHAR_P(prof_prefix, ",")
+	OPT_WRITE_BOOL_MUTABLE(prof_active, prof.active, ",")
+	OPT_WRITE_BOOL_MUTABLE(prof_thread_active_init, prof.thread_active_init,
+	    ",")
+	OPT_WRITE_SSIZE_T_MUTABLE(lg_prof_sample, prof.lg_sample, ",")
+	OPT_WRITE_BOOL(prof_accum, ",")
+	OPT_WRITE_SSIZE_T(lg_prof_interval, ",")
+	OPT_WRITE_BOOL(prof_gdump, ",")
+	OPT_WRITE_BOOL(prof_final, ",")
+	OPT_WRITE_BOOL(prof_leak, ",")
+	OPT_WRITE_BOOL(stats_print, ",")
+	if (json || opt_stats_print) {
+		/*
+		 * stats_print_opts is always emitted for JSON, so as long as it
+		 * comes last it's safe to unconditionally omit the comma here
+		 * (rather than having to conditionally omit it elsewhere
+		 * depending on configuration).
+		 */
+		OPT_WRITE_CHAR_P(stats_print_opts, "")
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t},\n");
+	}
 
 #undef OPT_WRITE_BOOL
-#undef OPT_WRITE_SIZE_T
+#undef OPT_WRITE_BOOL_MUTABLE
 #undef OPT_WRITE_SSIZE_T
 #undef OPT_WRITE_CHAR_P
 
-		malloc_cprintf(write_cb, cbopaque, "CPUs: %u\n", ncpus);
+	/* arenas. */
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"arenas\": {\n");
+	}
 
-		CTL_GET("arenas.narenas", &uv, unsigned);
+	CTL_GET("arenas.narenas", &uv, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"narenas\": %u,\n", uv);
+	} else {
 		malloc_cprintf(write_cb, cbopaque, "Arenas: %u\n", uv);
+	}
+
+	if (json) {
+		CTL_GET("arenas.dirty_decay_ms", &ssv, ssize_t);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"dirty_decay_ms\": %zd,\n", ssv);
 
-		malloc_cprintf(write_cb, cbopaque, "Pointer size: %zu\n",
-		    sizeof(void *));
+		CTL_GET("arenas.muzzy_decay_ms", &ssv, ssize_t);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"muzzy_decay_ms\": %zd,\n", ssv);
+	}
 
-		CTL_GET("arenas.quantum", &sv, size_t);
+	CTL_GET("arenas.quantum", &sv, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"quantum\": %zu,\n", sv);
+	} else {
 		malloc_cprintf(write_cb, cbopaque, "Quantum size: %zu\n", sv);
+	}
 
-		CTL_GET("arenas.page", &sv, size_t);
+	CTL_GET("arenas.page", &sv, size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"page\": %zu,\n", sv);
+	} else {
 		malloc_cprintf(write_cb, cbopaque, "Page size: %zu\n", sv);
+	}
 
-		CTL_GET("opt.lg_dirty_mult", &ssv, ssize_t);
-		if (ssv >= 0) {
+	if (je_mallctl("arenas.tcache_max", (void *)&sv, &ssz, NULL, 0) == 0) {
+		if (json) {
 			malloc_cprintf(write_cb, cbopaque,
-			    "Min active:dirty page ratio per arena: %u:1\n",
-			    (1U << ssv));
+			    "\t\t\t\"tcache_max\": %zu,\n", sv);
 		} else {
 			malloc_cprintf(write_cb, cbopaque,
-			    "Min active:dirty page ratio per arena: N/A\n");
+			    "Maximum thread-cached size class: %zu\n", sv);
 		}
-		if ((err = je_mallctl("arenas.tcache_max", &sv, &ssz, NULL, 0))
-		    == 0) {
+	}
+
+	if (json) {
+		unsigned nbins, nlextents, i;
+
+		CTL_GET("arenas.nbins", &nbins, unsigned);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"nbins\": %u,\n", nbins);
+
+		CTL_GET("arenas.nhbins", &uv, unsigned);
+		malloc_cprintf(write_cb, cbopaque, "\t\t\t\"nhbins\": %u,\n",
+		    uv);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"bin\": [\n");
+		for (i = 0; i < nbins; i++) {
 			malloc_cprintf(write_cb, cbopaque,
-			    "Maximum thread-cached size class: %zu\n", sv);
+			    "\t\t\t\t{\n");
+
+			CTL_M2_GET("arenas.bin.0.size", i, &sv, size_t);
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\"size\": %zu,\n", sv);
+
+			CTL_M2_GET("arenas.bin.0.nregs", i, &u32v, uint32_t);
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\"nregs\": %"FMTu32",\n", u32v);
+
+			CTL_M2_GET("arenas.bin.0.slab_size", i, &sv, size_t);
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\"slab_size\": %zu\n", sv);
+
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t}%s\n", (i + 1 < nbins) ? "," : "");
 		}
-		if ((err = je_mallctl("opt.prof", &bv, &bsz, NULL, 0)) == 0 &&
-		    bv) {
-			CTL_GET("opt.lg_prof_sample", &sv, size_t);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t],\n");
+
+		CTL_GET("arenas.nlextents", &nlextents, unsigned);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"nlextents\": %u,\n", nlextents);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"lextent\": [\n");
+		for (i = 0; i < nlextents; i++) {
 			malloc_cprintf(write_cb, cbopaque,
-			    "Average profile sample interval: %"PRIu64
-			    " (2^%zu)\n", (((uint64_t)1U) << sv), sv);
+			    "\t\t\t\t{\n");
 
-			CTL_GET("opt.lg_prof_interval", &ssv, ssize_t);
-			if (ssv >= 0) {
-				malloc_cprintf(write_cb, cbopaque,
-				    "Average profile dump interval: %"PRIu64
-				    " (2^%zd)\n",
-				    (((uint64_t)1U) << ssv), ssv);
-			} else {
-				malloc_cprintf(write_cb, cbopaque,
-				    "Average profile dump interval: N/A\n");
+			CTL_M2_GET("arenas.lextent.0.size", i, &sv, size_t);
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\"size\": %zu\n", sv);
+
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t}%s\n", (i + 1 < nlextents) ? "," : "");
+		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t]\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t}%s\n", (config_prof || more) ? "," : "");
+	}
+
+	/* prof. */
+	if (config_prof && json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"prof\": {\n");
+
+		CTL_GET("prof.thread_active_init", &bv, bool);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"thread_active_init\": %s,\n", bv ? "true" :
+		    "false");
+
+		CTL_GET("prof.active", &bv, bool);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"active\": %s,\n", bv ? "true" : "false");
+
+		CTL_GET("prof.gdump", &bv, bool);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"gdump\": %s,\n", bv ? "true" : "false");
+
+		CTL_GET("prof.interval", &u64v, uint64_t);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"interval\": %"FMTu64",\n", u64v);
+
+		CTL_GET("prof.lg_sample", &ssv, ssize_t);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"lg_sample\": %zd\n", ssv);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t}%s\n", more ? "," : "");
+	}
+}
+
+static void
+read_global_mutex_stats(
+    uint64_t results[mutex_prof_num_global_mutexes][mutex_prof_num_counters]) {
+	char cmd[MUTEX_CTL_STR_MAX_LENGTH];
+
+	mutex_prof_global_ind_t i;
+	for (i = 0; i < mutex_prof_num_global_mutexes; i++) {
+#define OP(c, t)							\
+		gen_mutex_ctl_str(cmd, MUTEX_CTL_STR_MAX_LENGTH,	\
+		    "mutexes", global_mutex_names[i], #c);		\
+		CTL_GET(cmd, (t *)&results[i][mutex_counter_##c], t);
+MUTEX_PROF_COUNTERS
+#undef OP
+	}
+}
+
+static void
+stats_print_helper(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool merged, bool destroyed, bool unmerged, bool bins,
+    bool large, bool mutex) {
+	size_t allocated, active, metadata, resident, mapped, retained;
+	size_t num_background_threads;
+	uint64_t background_thread_num_runs, background_thread_run_interval;
+
+	CTL_GET("stats.allocated", &allocated, size_t);
+	CTL_GET("stats.active", &active, size_t);
+	CTL_GET("stats.metadata", &metadata, size_t);
+	CTL_GET("stats.resident", &resident, size_t);
+	CTL_GET("stats.mapped", &mapped, size_t);
+	CTL_GET("stats.retained", &retained, size_t);
+
+	uint64_t mutex_stats[mutex_prof_num_global_mutexes][mutex_prof_num_counters];
+	if (mutex) {
+		read_global_mutex_stats(mutex_stats);
+	}
+
+	if (have_background_thread) {
+		CTL_GET("stats.background_thread.num_threads",
+		    &num_background_threads, size_t);
+		CTL_GET("stats.background_thread.num_runs",
+		    &background_thread_num_runs, uint64_t);
+		CTL_GET("stats.background_thread.run_interval",
+		    &background_thread_run_interval, uint64_t);
+	} else {
+		num_background_threads = 0;
+		background_thread_num_runs = 0;
+		background_thread_run_interval = 0;
+	}
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"stats\": {\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"allocated\": %zu,\n", allocated);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"active\": %zu,\n", active);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"metadata\": %zu,\n", metadata);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"resident\": %zu,\n", resident);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"mapped\": %zu,\n", mapped);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"retained\": %zu,\n", retained);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"background_thread\": {\n");
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"num_threads\": %zu,\n", num_background_threads);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"num_runs\": %"FMTu64",\n",
+		    background_thread_num_runs);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"run_interval\": %"FMTu64"\n",
+		    background_thread_run_interval);
+		malloc_cprintf(write_cb, cbopaque, "\t\t\t}%s\n",
+		    mutex ? "," : "");
+
+		if (mutex) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\"mutexes\": {\n");
+			mutex_prof_global_ind_t i;
+			for (i = 0; i < mutex_prof_num_global_mutexes; i++) {
+				mutex_stats_output_json(write_cb, cbopaque,
+				    global_mutex_names[i], mutex_stats[i],
+				    "\t\t\t\t",
+				    i == mutex_prof_num_global_mutexes - 1);
+			}
+			malloc_cprintf(write_cb, cbopaque, "\t\t\t}\n");
+		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t}%s\n", (merged || unmerged || destroyed) ? "," : "");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "Allocated: %zu, active: %zu, metadata: %zu,"
+		    " resident: %zu, mapped: %zu, retained: %zu\n",
+		    allocated, active, metadata, resident, mapped, retained);
+
+		if (have_background_thread && num_background_threads > 0) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "Background threads: %zu, num_runs: %"FMTu64", "
+			    "run_interval: %"FMTu64" ns\n",
+			    num_background_threads,
+			    background_thread_num_runs,
+			    background_thread_run_interval);
+		}
+		if (mutex) {
+			mutex_prof_global_ind_t i;
+			for (i = 0; i < mutex_prof_num_global_mutexes; i++) {
+				mutex_stats_output(write_cb, cbopaque,
+				    global_mutex_names[i], mutex_stats[i],
+				    i == 0);
 			}
 		}
-		CTL_GET("opt.lg_chunk", &sv, size_t);
-		malloc_cprintf(write_cb, cbopaque, "Chunk size: %zu (2^%zu)\n",
-		    (ZU(1) << sv), sv);
 	}
 
-	if (config_stats) {
-		size_t *cactive;
-		size_t allocated, active, mapped;
-		size_t chunks_current, chunks_high;
-		uint64_t chunks_total;
-		size_t huge_allocated;
-		uint64_t huge_nmalloc, huge_ndalloc;
-
-		CTL_GET("stats.cactive", &cactive, size_t *);
-		CTL_GET("stats.allocated", &allocated, size_t);
-		CTL_GET("stats.active", &active, size_t);
-		CTL_GET("stats.mapped", &mapped, size_t);
-		malloc_cprintf(write_cb, cbopaque,
-		    "Allocated: %zu, active: %zu, mapped: %zu\n",
-		    allocated, active, mapped);
-		malloc_cprintf(write_cb, cbopaque,
-		    "Current active ceiling: %zu\n", atomic_read_z(cactive));
-
-		/* Print chunk stats. */
-		CTL_GET("stats.chunks.total", &chunks_total, uint64_t);
-		CTL_GET("stats.chunks.high", &chunks_high, size_t);
-		CTL_GET("stats.chunks.current", &chunks_current, size_t);
-		malloc_cprintf(write_cb, cbopaque, "chunks: nchunks   "
-		    "highchunks    curchunks\n");
-		malloc_cprintf(write_cb, cbopaque,
-		    "  %13"PRIu64" %12zu %12zu\n",
-		    chunks_total, chunks_high, chunks_current);
-
-		/* Print huge stats. */
-		CTL_GET("stats.huge.nmalloc", &huge_nmalloc, uint64_t);
-		CTL_GET("stats.huge.ndalloc", &huge_ndalloc, uint64_t);
-		CTL_GET("stats.huge.allocated", &huge_allocated, size_t);
-		malloc_cprintf(write_cb, cbopaque,
-		    "huge: nmalloc      ndalloc    allocated\n");
-		malloc_cprintf(write_cb, cbopaque,
-		    " %12"PRIu64" %12"PRIu64" %12zu\n",
-		    huge_nmalloc, huge_ndalloc, huge_allocated);
-
-		if (merged) {
-			unsigned narenas;
-
-			CTL_GET("arenas.narenas", &narenas, unsigned);
-			{
-				VARIABLE_ARRAY(bool, initialized, narenas);
-				size_t isz;
-				unsigned i, ninitialized;
-
-				isz = sizeof(bool) * narenas;
-				xmallctl("arenas.initialized", initialized,
-				    &isz, NULL, 0);
-				for (i = ninitialized = 0; i < narenas; i++) {
-					if (initialized[i])
-						ninitialized++;
+	if (merged || destroyed || unmerged) {
+		unsigned narenas;
+
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\"stats.arenas\": {\n");
+		}
+
+		CTL_GET("arenas.narenas", &narenas, unsigned);
+		{
+			size_t mib[3];
+			size_t miblen = sizeof(mib) / sizeof(size_t);
+			size_t sz;
+			VARIABLE_ARRAY(bool, initialized, narenas);
+			bool destroyed_initialized;
+			unsigned i, j, ninitialized;
+
+			xmallctlnametomib("arena.0.initialized", mib, &miblen);
+			for (i = ninitialized = 0; i < narenas; i++) {
+				mib[1] = i;
+				sz = sizeof(bool);
+				xmallctlbymib(mib, miblen, &initialized[i], &sz,
+				    NULL, 0);
+				if (initialized[i]) {
+					ninitialized++;
 				}
+			}
+			mib[1] = MALLCTL_ARENAS_DESTROYED;
+			sz = sizeof(bool);
+			xmallctlbymib(mib, miblen, &destroyed_initialized, &sz,
+			    NULL, 0);
 
-				if (ninitialized > 1 || unmerged == false) {
-					/* Print merged arena stats. */
+			/* Merged stats. */
+			if (merged && (ninitialized > 1 || !unmerged)) {
+				/* Print merged arena stats. */
+				if (json) {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\t\t\t\"merged\": {\n");
+				} else {
 					malloc_cprintf(write_cb, cbopaque,
 					    "\nMerged arenas stats:\n");
-					stats_arena_print(write_cb, cbopaque,
-					    narenas, bins, large);
+				}
+				stats_arena_print(write_cb, cbopaque, json,
+				    MALLCTL_ARENAS_ALL, bins, large, mutex);
+				if (json) {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\t\t\t}%s\n",
+					    ((destroyed_initialized &&
+					    destroyed) || unmerged) ?  "," :
+					    "");
 				}
 			}
-		}
-
-		if (unmerged) {
-			unsigned narenas;
 
-			/* Print stats for each arena. */
-
-			CTL_GET("arenas.narenas", &narenas, unsigned);
-			{
-				VARIABLE_ARRAY(bool, initialized, narenas);
-				size_t isz;
-				unsigned i;
-
-				isz = sizeof(bool) * narenas;
-				xmallctl("arenas.initialized", initialized,
-				    &isz, NULL, 0);
+			/* Destroyed stats. */
+			if (destroyed_initialized && destroyed) {
+				/* Print destroyed arena stats. */
+				if (json) {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\t\t\t\"destroyed\": {\n");
+				} else {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\nDestroyed arenas stats:\n");
+				}
+				stats_arena_print(write_cb, cbopaque, json,
+				    MALLCTL_ARENAS_DESTROYED, bins, large,
+				    mutex);
+				if (json) {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\t\t\t}%s\n", unmerged ?  "," :
+					    "");
+				}
+			}
 
-				for (i = 0; i < narenas; i++) {
+			/* Unmerged stats. */
+			if (unmerged) {
+				for (i = j = 0; i < narenas; i++) {
 					if (initialized[i]) {
-						malloc_cprintf(write_cb,
-						    cbopaque,
-						    "\narenas[%u]:\n", i);
+						if (json) {
+							j++;
+							malloc_cprintf(write_cb,
+							    cbopaque,
+							    "\t\t\t\"%u\": {\n",
+							    i);
+						} else {
+							malloc_cprintf(write_cb,
+							    cbopaque,
+							    "\narenas[%u]:\n",
+							    i);
+						}
 						stats_arena_print(write_cb,
-						    cbopaque, i, bins, large);
+						    cbopaque, json, i, bins,
+						    large, mutex);
+						if (json) {
+							malloc_cprintf(write_cb,
+							    cbopaque,
+							    "\t\t\t}%s\n", (j <
+							    ninitialized) ? ","
+							    : "");
+						}
 					}
 				}
 			}
 		}
+
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t}\n");
+		}
+	}
+}
+
+void
+stats_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *opts) {
+	int err;
+	uint64_t epoch;
+	size_t u64sz;
+#define OPTION(o, v, d, s) bool v = d;
+	STATS_PRINT_OPTIONS
+#undef OPTION
+
+	/*
+	 * Refresh stats, in case mallctl() was called by the application.
+	 *
+	 * Check for OOM here, since refreshing the ctl cache can trigger
+	 * allocation.  In practice, none of the subsequent mallctl()-related
+	 * calls in this function will cause OOM if this one succeeds.
+	 * */
+	epoch = 1;
+	u64sz = sizeof(uint64_t);
+	err = je_mallctl("epoch", (void *)&epoch, &u64sz, (void *)&epoch,
+	    sizeof(uint64_t));
+	if (err != 0) {
+		if (err == EAGAIN) {
+			malloc_write("<jemalloc>: Memory allocation failure in "
+			    "mallctl(\"epoch\", ...)\n");
+			return;
+		}
+		malloc_write("<jemalloc>: Failure in mallctl(\"epoch\", "
+		    "...)\n");
+		abort();
+	}
+
+	if (opts != NULL) {
+		for (unsigned i = 0; opts[i] != '\0'; i++) {
+			switch (opts[i]) {
+#define OPTION(o, v, d, s) case o: v = s; break;
+				STATS_PRINT_OPTIONS
+#undef OPTION
+			default:;
+			}
+		}
+	}
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "{\n"
+		    "\t\"jemalloc\": {\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "___ Begin jemalloc statistics ___\n");
+	}
+
+	if (general) {
+		stats_general_print(write_cb, cbopaque, json, config_stats);
+	}
+	if (config_stats) {
+		stats_print_helper(write_cb, cbopaque, json, merged, destroyed,
+		    unmerged, bins, large, mutex);
+	}
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t}\n"
+		    "}\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "--- End jemalloc statistics ---\n");
 	}
-	malloc_cprintf(write_cb, cbopaque, "--- End jemalloc statistics ---\n");
 }
diff --git a/modules/worldengine/deps/jemalloc/src/sz.c b/modules/worldengine/deps/jemalloc/src/sz.c
new file mode 100644
index 0000000000..0986615f71
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/sz.c
@@ -0,0 +1,106 @@
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/sz.h"
+
+JEMALLOC_ALIGNED(CACHELINE)
+const size_t sz_pind2sz_tab[NPSIZES+1] = {
+#define PSZ_yes(lg_grp, ndelta, lg_delta)				\
+	(((ZU(1)<<lg_grp) + (ZU(ndelta)<<lg_delta))),
+#define PSZ_no(lg_grp, ndelta, lg_delta)
+#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup) \
+	PSZ_##psz(lg_grp, ndelta, lg_delta)
+	SIZE_CLASSES
+#undef PSZ_yes
+#undef PSZ_no
+#undef SC
+	(LARGE_MAXCLASS + PAGE)
+};
+
+JEMALLOC_ALIGNED(CACHELINE)
+const size_t sz_index2size_tab[NSIZES] = {
+#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup) \
+	((ZU(1)<<lg_grp) + (ZU(ndelta)<<lg_delta)),
+	SIZE_CLASSES
+#undef SC
+};
+
+JEMALLOC_ALIGNED(CACHELINE)
+const uint8_t sz_size2index_tab[] = {
+#if LG_TINY_MIN == 0
+#warning "Dangerous LG_TINY_MIN"
+#define S2B_0(i)	i,
+#elif LG_TINY_MIN == 1
+#warning "Dangerous LG_TINY_MIN"
+#define S2B_1(i)	i,
+#elif LG_TINY_MIN == 2
+#warning "Dangerous LG_TINY_MIN"
+#define S2B_2(i)	i,
+#elif LG_TINY_MIN == 3
+#define S2B_3(i)	i,
+#elif LG_TINY_MIN == 4
+#define S2B_4(i)	i,
+#elif LG_TINY_MIN == 5
+#define S2B_5(i)	i,
+#elif LG_TINY_MIN == 6
+#define S2B_6(i)	i,
+#elif LG_TINY_MIN == 7
+#define S2B_7(i)	i,
+#elif LG_TINY_MIN == 8
+#define S2B_8(i)	i,
+#elif LG_TINY_MIN == 9
+#define S2B_9(i)	i,
+#elif LG_TINY_MIN == 10
+#define S2B_10(i)	i,
+#elif LG_TINY_MIN == 11
+#define S2B_11(i)	i,
+#else
+#error "Unsupported LG_TINY_MIN"
+#endif
+#if LG_TINY_MIN < 1
+#define S2B_1(i)	S2B_0(i) S2B_0(i)
+#endif
+#if LG_TINY_MIN < 2
+#define S2B_2(i)	S2B_1(i) S2B_1(i)
+#endif
+#if LG_TINY_MIN < 3
+#define S2B_3(i)	S2B_2(i) S2B_2(i)
+#endif
+#if LG_TINY_MIN < 4
+#define S2B_4(i)	S2B_3(i) S2B_3(i)
+#endif
+#if LG_TINY_MIN < 5
+#define S2B_5(i)	S2B_4(i) S2B_4(i)
+#endif
+#if LG_TINY_MIN < 6
+#define S2B_6(i)	S2B_5(i) S2B_5(i)
+#endif
+#if LG_TINY_MIN < 7
+#define S2B_7(i)	S2B_6(i) S2B_6(i)
+#endif
+#if LG_TINY_MIN < 8
+#define S2B_8(i)	S2B_7(i) S2B_7(i)
+#endif
+#if LG_TINY_MIN < 9
+#define S2B_9(i)	S2B_8(i) S2B_8(i)
+#endif
+#if LG_TINY_MIN < 10
+#define S2B_10(i)	S2B_9(i) S2B_9(i)
+#endif
+#if LG_TINY_MIN < 11
+#define S2B_11(i)	S2B_10(i) S2B_10(i)
+#endif
+#define S2B_no(i)
+#define SC(index, lg_grp, lg_delta, ndelta, psz, bin, pgs, lg_delta_lookup) \
+	S2B_##lg_delta_lookup(index)
+	SIZE_CLASSES
+#undef S2B_3
+#undef S2B_4
+#undef S2B_5
+#undef S2B_6
+#undef S2B_7
+#undef S2B_8
+#undef S2B_9
+#undef S2B_10
+#undef S2B_11
+#undef S2B_no
+#undef SC
+};
diff --git a/modules/worldengine/deps/jemalloc/src/tcache.c b/modules/worldengine/deps/jemalloc/src/tcache.c
index 6de92960b2..936ef3140d 100644
--- a/modules/worldengine/deps/jemalloc/src/tcache.c
+++ b/modules/worldengine/deps/jemalloc/src/tcache.c
@@ -1,131 +1,153 @@
-#define	JEMALLOC_TCACHE_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_TCACHE_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/size_classes.h"
 
 /******************************************************************************/
 /* Data. */
 
-malloc_tsd_data(, tcache, tcache_t *, NULL)
-malloc_tsd_data(, tcache_enabled, tcache_enabled_t, tcache_enabled_default)
-
 bool	opt_tcache = true;
 ssize_t	opt_lg_tcache_max = LG_TCACHE_MAXCLASS_DEFAULT;
 
 tcache_bin_info_t	*tcache_bin_info;
 static unsigned		stack_nelms; /* Total stack elms per tcache. */
 
-size_t			nhbins;
+unsigned		nhbins;
 size_t			tcache_maxclass;
 
-/******************************************************************************/
+tcaches_t		*tcaches;
+
+/* Index of first element within tcaches that has never been used. */
+static unsigned		tcaches_past;
+
+/* Head of singly linked list tracking available tcaches elements. */
+static tcaches_t	*tcaches_avail;
 
-size_t	tcache_salloc(const void *ptr)
-{
+/* Protects tcaches{,_past,_avail}. */
+static malloc_mutex_t	tcaches_mtx;
 
-	return (arena_salloc(ptr, false));
+/******************************************************************************/
+
+size_t
+tcache_salloc(tsdn_t *tsdn, const void *ptr) {
+	return arena_salloc(tsdn, ptr);
 }
 
 void
-tcache_event_hard(tcache_t *tcache)
-{
-	size_t binind = tcache->next_gc_bin;
-	tcache_bin_t *tbin = &tcache->tbins[binind];
-	tcache_bin_info_t *tbin_info = &tcache_bin_info[binind];
-
+tcache_event_hard(tsd_t *tsd, tcache_t *tcache) {
+	szind_t binind = tcache->next_gc_bin;
+
+	tcache_bin_t *tbin;
+	if (binind < NBINS) {
+		tbin = tcache_small_bin_get(tcache, binind);
+	} else {
+		tbin = tcache_large_bin_get(tcache, binind);
+	}
 	if (tbin->low_water > 0) {
 		/*
 		 * Flush (ceiling) 3/4 of the objects below the low water mark.
 		 */
 		if (binind < NBINS) {
-			tcache_bin_flush_small(tbin, binind, tbin->ncached -
-			    tbin->low_water + (tbin->low_water >> 2), tcache);
+			tcache_bin_flush_small(tsd, tcache, tbin, binind,
+			    tbin->ncached - tbin->low_water + (tbin->low_water
+			    >> 2));
+			/*
+			 * Reduce fill count by 2X.  Limit lg_fill_div such that
+			 * the fill count is always at least 1.
+			 */
+			tcache_bin_info_t *tbin_info = &tcache_bin_info[binind];
+			if ((tbin_info->ncached_max >>
+			     (tcache->lg_fill_div[binind] + 1)) >= 1) {
+				tcache->lg_fill_div[binind]++;
+			}
 		} else {
-			tcache_bin_flush_large(tbin, binind, tbin->ncached -
-			    tbin->low_water + (tbin->low_water >> 2), tcache);
+			tcache_bin_flush_large(tsd, tbin, binind, tbin->ncached
+			    - tbin->low_water + (tbin->low_water >> 2), tcache);
 		}
-		/*
-		 * Reduce fill count by 2X.  Limit lg_fill_div such that the
-		 * fill count is always at least 1.
-		 */
-		if ((tbin_info->ncached_max >> (tbin->lg_fill_div+1)) >= 1)
-			tbin->lg_fill_div++;
 	} else if (tbin->low_water < 0) {
 		/*
-		 * Increase fill count by 2X.  Make sure lg_fill_div stays
-		 * greater than 0.
+		 * Increase fill count by 2X for small bins.  Make sure
+		 * lg_fill_div stays greater than 0.
 		 */
-		if (tbin->lg_fill_div > 1)
-			tbin->lg_fill_div--;
+		if (binind < NBINS && tcache->lg_fill_div[binind] > 1) {
+			tcache->lg_fill_div[binind]--;
+		}
 	}
 	tbin->low_water = tbin->ncached;
 
 	tcache->next_gc_bin++;
-	if (tcache->next_gc_bin == nhbins)
+	if (tcache->next_gc_bin == nhbins) {
 		tcache->next_gc_bin = 0;
-	tcache->ev_cnt = 0;
+	}
 }
 
 void *
-tcache_alloc_small_hard(tcache_t *tcache, tcache_bin_t *tbin, size_t binind)
-{
+tcache_alloc_small_hard(tsdn_t *tsdn, arena_t *arena, tcache_t *tcache,
+    tcache_bin_t *tbin, szind_t binind, bool *tcache_success) {
 	void *ret;
 
-	arena_tcache_fill_small(tcache->arena, tbin, binind,
+	assert(tcache->arena != NULL);
+	arena_tcache_fill_small(tsdn, arena, tcache, tbin, binind,
 	    config_prof ? tcache->prof_accumbytes : 0);
-	if (config_prof)
+	if (config_prof) {
 		tcache->prof_accumbytes = 0;
-	ret = tcache_alloc_easy(tbin);
+	}
+	ret = tcache_alloc_easy(tbin, tcache_success);
 
-	return (ret);
+	return ret;
 }
 
 void
-tcache_bin_flush_small(tcache_bin_t *tbin, size_t binind, unsigned rem,
-    tcache_t *tcache)
-{
-	void *ptr;
-	unsigned i, nflush, ndeferred;
+tcache_bin_flush_small(tsd_t *tsd, tcache_t *tcache, tcache_bin_t *tbin,
+    szind_t binind, unsigned rem) {
 	bool merged_stats = false;
 
 	assert(binind < NBINS);
 	assert(rem <= tbin->ncached);
 
-	for (nflush = tbin->ncached - rem; nflush > 0; nflush = ndeferred) {
-		/* Lock the arena bin associated with the first object. */
-		arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(
-		    tbin->avail[0]);
-		arena_t *arena = chunk->arena;
-		arena_bin_t *bin = &arena->bins[binind];
+	arena_t *arena = tcache->arena;
+	assert(arena != NULL);
+	unsigned nflush = tbin->ncached - rem;
+	VARIABLE_ARRAY(extent_t *, item_extent, nflush);
+	/* Look up extent once per item. */
+	for (unsigned i = 0 ; i < nflush; i++) {
+		item_extent[i] = iealloc(tsd_tsdn(tsd), *(tbin->avail - 1 - i));
+	}
 
-		if (config_prof && arena == tcache->arena) {
-			if (arena_prof_accum(arena, tcache->prof_accumbytes))
-				prof_idump();
+	while (nflush > 0) {
+		/* Lock the arena bin associated with the first object. */
+		extent_t *extent = item_extent[0];
+		arena_t *bin_arena = extent_arena_get(extent);
+		arena_bin_t *bin = &bin_arena->bins[binind];
+
+		if (config_prof && bin_arena == arena) {
+			if (arena_prof_accum(tsd_tsdn(tsd), arena,
+			    tcache->prof_accumbytes)) {
+				prof_idump(tsd_tsdn(tsd));
+			}
 			tcache->prof_accumbytes = 0;
 		}
 
-		malloc_mutex_lock(&bin->lock);
-		if (config_stats && arena == tcache->arena) {
-			assert(merged_stats == false);
+		malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		if (config_stats && bin_arena == arena) {
+			assert(!merged_stats);
 			merged_stats = true;
 			bin->stats.nflushes++;
 			bin->stats.nrequests += tbin->tstats.nrequests;
 			tbin->tstats.nrequests = 0;
 		}
-		ndeferred = 0;
-		for (i = 0; i < nflush; i++) {
-			ptr = tbin->avail[i];
-			assert(ptr != NULL);
-			chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-			if (chunk->arena == arena) {
-				size_t pageind = ((uintptr_t)ptr -
-				    (uintptr_t)chunk) >> LG_PAGE;
-				arena_chunk_map_t *mapelm =
-				    arena_mapp_get(chunk, pageind);
-				if (config_fill && opt_junk) {
-					arena_alloc_junk_small(ptr,
-					    &arena_bin_info[binind], true);
-				}
-				arena_dalloc_bin_locked(arena, chunk, ptr,
-				    mapelm);
+		unsigned ndeferred = 0;
+		for (unsigned i = 0; i < nflush; i++) {
+			void *ptr = *(tbin->avail - 1 - i);
+			extent = item_extent[i];
+			assert(ptr != NULL && extent != NULL);
+
+			if (extent_arena_get(extent) == bin_arena) {
+				arena_dalloc_bin_junked_locked(tsd_tsdn(tsd),
+				    bin_arena, extent, ptr);
 			} else {
 				/*
 				 * This object was allocated via a different
@@ -133,276 +155,369 @@ tcache_bin_flush_small(tcache_bin_t *tbin, size_t binind, unsigned rem,
 				 * locked.  Stash the object, so that it can be
 				 * handled in a future pass.
 				 */
-				tbin->avail[ndeferred] = ptr;
+				*(tbin->avail - 1 - ndeferred) = ptr;
+				item_extent[ndeferred] = extent;
 				ndeferred++;
 			}
 		}
-		malloc_mutex_unlock(&bin->lock);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+		arena_decay_ticks(tsd_tsdn(tsd), bin_arena, nflush - ndeferred);
+		nflush = ndeferred;
 	}
-	if (config_stats && merged_stats == false) {
+	if (config_stats && !merged_stats) {
 		/*
 		 * The flush loop didn't happen to flush to this thread's
 		 * arena, so the stats didn't get merged.  Manually do so now.
 		 */
-		arena_bin_t *bin = &tcache->arena->bins[binind];
-		malloc_mutex_lock(&bin->lock);
+		arena_bin_t *bin = &arena->bins[binind];
+		malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
 		bin->stats.nflushes++;
 		bin->stats.nrequests += tbin->tstats.nrequests;
 		tbin->tstats.nrequests = 0;
-		malloc_mutex_unlock(&bin->lock);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
 	}
 
-	memmove(tbin->avail, &tbin->avail[tbin->ncached - rem],
-	    rem * sizeof(void *));
+	memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem *
+	    sizeof(void *));
 	tbin->ncached = rem;
-	if ((int)tbin->ncached < tbin->low_water)
+	if ((low_water_t)tbin->ncached < tbin->low_water) {
 		tbin->low_water = tbin->ncached;
+	}
 }
 
 void
-tcache_bin_flush_large(tcache_bin_t *tbin, size_t binind, unsigned rem,
-    tcache_t *tcache)
-{
-	void *ptr;
-	unsigned i, nflush, ndeferred;
+tcache_bin_flush_large(tsd_t *tsd, tcache_bin_t *tbin, szind_t binind,
+    unsigned rem, tcache_t *tcache) {
 	bool merged_stats = false;
 
 	assert(binind < nhbins);
 	assert(rem <= tbin->ncached);
 
-	for (nflush = tbin->ncached - rem; nflush > 0; nflush = ndeferred) {
+	arena_t *arena = tcache->arena;
+	assert(arena != NULL);
+	unsigned nflush = tbin->ncached - rem;
+	VARIABLE_ARRAY(extent_t *, item_extent, nflush);
+	/* Look up extent once per item. */
+	for (unsigned i = 0 ; i < nflush; i++) {
+		item_extent[i] = iealloc(tsd_tsdn(tsd), *(tbin->avail - 1 - i));
+	}
+
+	while (nflush > 0) {
 		/* Lock the arena associated with the first object. */
-		arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(
-		    tbin->avail[0]);
-		arena_t *arena = chunk->arena;
+		extent_t *extent = item_extent[0];
+		arena_t *locked_arena = extent_arena_get(extent);
 		UNUSED bool idump;
 
-		if (config_prof)
+		if (config_prof) {
 			idump = false;
-		malloc_mutex_lock(&arena->lock);
-		if ((config_prof || config_stats) && arena == tcache->arena) {
+		}
+
+		malloc_mutex_lock(tsd_tsdn(tsd), &locked_arena->large_mtx);
+		for (unsigned i = 0; i < nflush; i++) {
+			void *ptr = *(tbin->avail - 1 - i);
+			assert(ptr != NULL);
+			extent = item_extent[i];
+			if (extent_arena_get(extent) == locked_arena) {
+				large_dalloc_prep_junked_locked(tsd_tsdn(tsd),
+				    extent);
+			}
+		}
+		if ((config_prof || config_stats) && locked_arena == arena) {
 			if (config_prof) {
-				idump = arena_prof_accum_locked(arena,
+				idump = arena_prof_accum(tsd_tsdn(tsd), arena,
 				    tcache->prof_accumbytes);
 				tcache->prof_accumbytes = 0;
 			}
 			if (config_stats) {
 				merged_stats = true;
-				arena->stats.nrequests_large +=
-				    tbin->tstats.nrequests;
-				arena->stats.lstats[binind - NBINS].nrequests +=
-				    tbin->tstats.nrequests;
+				arena_stats_large_nrequests_add(tsd_tsdn(tsd),
+				    &arena->stats, binind,
+				    tbin->tstats.nrequests);
 				tbin->tstats.nrequests = 0;
 			}
 		}
-		ndeferred = 0;
-		for (i = 0; i < nflush; i++) {
-			ptr = tbin->avail[i];
-			assert(ptr != NULL);
-			chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
-			if (chunk->arena == arena)
-				arena_dalloc_large_locked(arena, chunk, ptr);
-			else {
+		malloc_mutex_unlock(tsd_tsdn(tsd), &locked_arena->large_mtx);
+
+		unsigned ndeferred = 0;
+		for (unsigned i = 0; i < nflush; i++) {
+			void *ptr = *(tbin->avail - 1 - i);
+			extent = item_extent[i];
+			assert(ptr != NULL && extent != NULL);
+
+			if (extent_arena_get(extent) == locked_arena) {
+				large_dalloc_finish(tsd_tsdn(tsd), extent);
+			} else {
 				/*
 				 * This object was allocated via a different
 				 * arena than the one that is currently locked.
 				 * Stash the object, so that it can be handled
 				 * in a future pass.
 				 */
-				tbin->avail[ndeferred] = ptr;
+				*(tbin->avail - 1 - ndeferred) = ptr;
+				item_extent[ndeferred] = extent;
 				ndeferred++;
 			}
 		}
-		malloc_mutex_unlock(&arena->lock);
-		if (config_prof && idump)
-			prof_idump();
+		if (config_prof && idump) {
+			prof_idump(tsd_tsdn(tsd));
+		}
+		arena_decay_ticks(tsd_tsdn(tsd), locked_arena, nflush -
+		    ndeferred);
+		nflush = ndeferred;
 	}
-	if (config_stats && merged_stats == false) {
+	if (config_stats && !merged_stats) {
 		/*
 		 * The flush loop didn't happen to flush to this thread's
 		 * arena, so the stats didn't get merged.  Manually do so now.
 		 */
-		arena_t *arena = tcache->arena;
-		malloc_mutex_lock(&arena->lock);
-		arena->stats.nrequests_large += tbin->tstats.nrequests;
-		arena->stats.lstats[binind - NBINS].nrequests +=
-		    tbin->tstats.nrequests;
+		arena_stats_large_nrequests_add(tsd_tsdn(tsd), &arena->stats,
+		    binind, tbin->tstats.nrequests);
 		tbin->tstats.nrequests = 0;
-		malloc_mutex_unlock(&arena->lock);
 	}
 
-	memmove(tbin->avail, &tbin->avail[tbin->ncached - rem],
-	    rem * sizeof(void *));
+	memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem *
+	    sizeof(void *));
 	tbin->ncached = rem;
-	if ((int)tbin->ncached < tbin->low_water)
+	if ((low_water_t)tbin->ncached < tbin->low_water) {
 		tbin->low_water = tbin->ncached;
+	}
 }
 
 void
-tcache_arena_associate(tcache_t *tcache, arena_t *arena)
-{
+tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) {
+	assert(tcache->arena == NULL);
+	tcache->arena = arena;
 
 	if (config_stats) {
 		/* Link into list of extant tcaches. */
-		malloc_mutex_lock(&arena->lock);
+		malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx);
 		ql_elm_new(tcache, link);
 		ql_tail_insert(&arena->tcache_ql, tcache, link);
-		malloc_mutex_unlock(&arena->lock);
+		malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx);
 	}
-	tcache->arena = arena;
 }
 
-void
-tcache_arena_dissociate(tcache_t *tcache)
-{
-
+static void
+tcache_arena_dissociate(tsdn_t *tsdn, tcache_t *tcache) {
+	arena_t *arena = tcache->arena;
+	assert(arena != NULL);
 	if (config_stats) {
 		/* Unlink from list of extant tcaches. */
-		malloc_mutex_lock(&tcache->arena->lock);
-		ql_remove(&tcache->arena->tcache_ql, tcache, link);
-		tcache_stats_merge(tcache, tcache->arena);
-		malloc_mutex_unlock(&tcache->arena->lock);
+		malloc_mutex_lock(tsdn, &arena->tcache_ql_mtx);
+		if (config_debug) {
+			bool in_ql = false;
+			tcache_t *iter;
+			ql_foreach(iter, &arena->tcache_ql, link) {
+				if (iter == tcache) {
+					in_ql = true;
+					break;
+				}
+			}
+			assert(in_ql);
+		}
+		ql_remove(&arena->tcache_ql, tcache, link);
+		tcache_stats_merge(tsdn, tcache, arena);
+		malloc_mutex_unlock(tsdn, &arena->tcache_ql_mtx);
 	}
+	tcache->arena = NULL;
 }
 
+void
+tcache_arena_reassociate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) {
+	tcache_arena_dissociate(tsdn, tcache);
+	tcache_arena_associate(tsdn, tcache, arena);
+}
+
+bool
+tsd_tcache_enabled_data_init(tsd_t *tsd) {
+	/* Called upon tsd initialization. */
+	tsd_tcache_enabled_set(tsd, opt_tcache);
+	tsd_slow_update(tsd);
+
+	if (opt_tcache) {
+		/* Trigger tcache init. */
+		tsd_tcache_data_init(tsd);
+	}
+
+	return false;
+}
+
+/* Initialize auto tcache (embedded in TSD). */
+static void
+tcache_init(tsd_t *tsd, tcache_t *tcache, void *avail_stack) {
+	memset(&tcache->link, 0, sizeof(ql_elm(tcache_t)));
+	tcache->prof_accumbytes = 0;
+	tcache->next_gc_bin = 0;
+	tcache->arena = NULL;
+
+	ticker_init(&tcache->gc_ticker, TCACHE_GC_INCR);
+
+	size_t stack_offset = 0;
+	assert((TCACHE_NSLOTS_SMALL_MAX & 1U) == 0);
+	memset(tcache->tbins_small, 0, sizeof(tcache_bin_t) * NBINS);
+	memset(tcache->tbins_large, 0, sizeof(tcache_bin_t) * (nhbins - NBINS));
+	unsigned i = 0;
+	for (; i < NBINS; i++) {
+		tcache->lg_fill_div[i] = 1;
+		stack_offset += tcache_bin_info[i].ncached_max * sizeof(void *);
+		/*
+		 * avail points past the available space.  Allocations will
+		 * access the slots toward higher addresses (for the benefit of
+		 * prefetch).
+		 */
+		tcache_small_bin_get(tcache, i)->avail =
+		    (void **)((uintptr_t)avail_stack + (uintptr_t)stack_offset);
+	}
+	for (; i < nhbins; i++) {
+		stack_offset += tcache_bin_info[i].ncached_max * sizeof(void *);
+		tcache_large_bin_get(tcache, i)->avail =
+		    (void **)((uintptr_t)avail_stack + (uintptr_t)stack_offset);
+	}
+	assert(stack_offset == stack_nelms * sizeof(void *));
+}
+
+/* Initialize auto tcache (embedded in TSD). */
+bool
+tsd_tcache_data_init(tsd_t *tsd) {
+	tcache_t *tcache = tsd_tcachep_get_unsafe(tsd);
+	assert(tcache_small_bin_get(tcache, 0)->avail == NULL);
+	size_t size = stack_nelms * sizeof(void *);
+	/* Avoid false cacheline sharing. */
+	size = sz_sa2u(size, CACHELINE);
+
+	void *avail_array = ipallocztm(tsd_tsdn(tsd), size, CACHELINE, true,
+	    NULL, true, arena_get(TSDN_NULL, 0, true));
+	if (avail_array == NULL) {
+		return true;
+	}
+
+	tcache_init(tsd, tcache, avail_array);
+	/*
+	 * Initialization is a bit tricky here.  After malloc init is done, all
+	 * threads can rely on arena_choose and associate tcache accordingly.
+	 * However, the thread that does actual malloc bootstrapping relies on
+	 * functional tsd, and it can only rely on a0.  In that case, we
+	 * associate its tcache to a0 temporarily, and later on
+	 * arena_choose_hard() will re-associate properly.
+	 */
+	tcache->arena = NULL;
+	arena_t *arena;
+	if (!malloc_initialized()) {
+		/* If in initialization, assign to a0. */
+		arena = arena_get(tsd_tsdn(tsd), 0, false);
+		tcache_arena_associate(tsd_tsdn(tsd), tcache, arena);
+	} else {
+		arena = arena_choose(tsd, NULL);
+		/* This may happen if thread.tcache.enabled is used. */
+		if (tcache->arena == NULL) {
+			tcache_arena_associate(tsd_tsdn(tsd), tcache, arena);
+		}
+	}
+	assert(arena == tcache->arena);
+
+	return false;
+}
+
+/* Created manual tcache for tcache.create mallctl. */
 tcache_t *
-tcache_create(arena_t *arena)
-{
+tcache_create_explicit(tsd_t *tsd) {
 	tcache_t *tcache;
 	size_t size, stack_offset;
-	unsigned i;
 
-	size = offsetof(tcache_t, tbins) + (sizeof(tcache_bin_t) * nhbins);
+	size = sizeof(tcache_t);
 	/* Naturally align the pointer stacks. */
 	size = PTR_CEILING(size);
 	stack_offset = size;
 	size += stack_nelms * sizeof(void *);
-	/*
-	 * Round up to the nearest multiple of the cacheline size, in order to
-	 * avoid the possibility of false cacheline sharing.
-	 *
-	 * That this works relies on the same logic as in ipalloc(), but we
-	 * cannot directly call ipalloc() here due to tcache bootstrapping
-	 * issues.
-	 */
-	size = (size + CACHELINE_MASK) & (-CACHELINE);
-
-	if (size <= SMALL_MAXCLASS)
-		tcache = (tcache_t *)arena_malloc_small(arena, size, true);
-	else if (size <= tcache_maxclass)
-		tcache = (tcache_t *)arena_malloc_large(arena, size, true);
-	else
-		tcache = (tcache_t *)icalloct(size, false, arena);
-
-	if (tcache == NULL)
-		return (NULL);
-
-	tcache_arena_associate(tcache, arena);
+	/* Avoid false cacheline sharing. */
+	size = sz_sa2u(size, CACHELINE);
 
-	assert((TCACHE_NSLOTS_SMALL_MAX & 1U) == 0);
-	for (i = 0; i < nhbins; i++) {
-		tcache->tbins[i].lg_fill_div = 1;
-		tcache->tbins[i].avail = (void **)((uintptr_t)tcache +
-		    (uintptr_t)stack_offset);
-		stack_offset += tcache_bin_info[i].ncached_max * sizeof(void *);
+	tcache = ipallocztm(tsd_tsdn(tsd), size, CACHELINE, true, NULL, true,
+	    arena_get(TSDN_NULL, 0, true));
+	if (tcache == NULL) {
+		return NULL;
 	}
 
-	tcache_tsd_set(&tcache);
+	tcache_init(tsd, tcache,
+	    (void *)((uintptr_t)tcache + (uintptr_t)stack_offset));
+	tcache_arena_associate(tsd_tsdn(tsd), tcache, arena_ichoose(tsd, NULL));
 
-	return (tcache);
+	return tcache;
 }
 
-void
-tcache_destroy(tcache_t *tcache)
-{
-	unsigned i;
-	size_t tcache_size;
+static void
+tcache_flush_cache(tsd_t *tsd, tcache_t *tcache) {
+	assert(tcache->arena != NULL);
 
-	tcache_arena_dissociate(tcache);
+	for (unsigned i = 0; i < NBINS; i++) {
+		tcache_bin_t *tbin = tcache_small_bin_get(tcache, i);
+		tcache_bin_flush_small(tsd, tcache, tbin, i, 0);
 
-	for (i = 0; i < NBINS; i++) {
-		tcache_bin_t *tbin = &tcache->tbins[i];
-		tcache_bin_flush_small(tbin, i, 0, tcache);
-
-		if (config_stats && tbin->tstats.nrequests != 0) {
-			arena_t *arena = tcache->arena;
-			arena_bin_t *bin = &arena->bins[i];
-			malloc_mutex_lock(&bin->lock);
-			bin->stats.nrequests += tbin->tstats.nrequests;
-			malloc_mutex_unlock(&bin->lock);
+		if (config_stats) {
+			assert(tbin->tstats.nrequests == 0);
 		}
 	}
+	for (unsigned i = NBINS; i < nhbins; i++) {
+		tcache_bin_t *tbin = tcache_large_bin_get(tcache, i);
+		tcache_bin_flush_large(tsd, tbin, i, 0, tcache);
 
-	for (; i < nhbins; i++) {
-		tcache_bin_t *tbin = &tcache->tbins[i];
-		tcache_bin_flush_large(tbin, i, 0, tcache);
-
-		if (config_stats && tbin->tstats.nrequests != 0) {
-			arena_t *arena = tcache->arena;
-			malloc_mutex_lock(&arena->lock);
-			arena->stats.nrequests_large += tbin->tstats.nrequests;
-			arena->stats.lstats[i - NBINS].nrequests +=
-			    tbin->tstats.nrequests;
-			malloc_mutex_unlock(&arena->lock);
+		if (config_stats) {
+			assert(tbin->tstats.nrequests == 0);
 		}
 	}
 
 	if (config_prof && tcache->prof_accumbytes > 0 &&
-	    arena_prof_accum(tcache->arena, tcache->prof_accumbytes))
-		prof_idump();
-
-	tcache_size = arena_salloc(tcache, false);
-	if (tcache_size <= SMALL_MAXCLASS) {
-		arena_chunk_t *chunk = CHUNK_ADDR2BASE(tcache);
-		arena_t *arena = chunk->arena;
-		size_t pageind = ((uintptr_t)tcache - (uintptr_t)chunk) >>
-		    LG_PAGE;
-		arena_chunk_map_t *mapelm = arena_mapp_get(chunk, pageind);
-
-		arena_dalloc_bin(arena, chunk, tcache, pageind, mapelm);
-	} else if (tcache_size <= tcache_maxclass) {
-		arena_chunk_t *chunk = CHUNK_ADDR2BASE(tcache);
-		arena_t *arena = chunk->arena;
-
-		arena_dalloc_large(arena, chunk, tcache);
-	} else
-		idalloct(tcache, false);
+	    arena_prof_accum(tsd_tsdn(tsd), tcache->arena,
+	    tcache->prof_accumbytes)) {
+		prof_idump(tsd_tsdn(tsd));
+	}
 }
 
 void
-tcache_thread_cleanup(void *arg)
-{
-	tcache_t *tcache = *(tcache_t **)arg;
+tcache_flush(tsd_t *tsd) {
+	assert(tcache_available(tsd));
+	tcache_flush_cache(tsd, tsd_tcachep_get(tsd));
+}
 
-	if (tcache == TCACHE_STATE_DISABLED) {
-		/* Do nothing. */
-	} else if (tcache == TCACHE_STATE_REINCARNATED) {
-		/*
-		 * Another destructor called an allocator function after this
-		 * destructor was called.  Reset tcache to
-		 * TCACHE_STATE_PURGATORY in order to receive another callback.
-		 */
-		tcache = TCACHE_STATE_PURGATORY;
-		tcache_tsd_set(&tcache);
-	} else if (tcache == TCACHE_STATE_PURGATORY) {
-		/*
-		 * The previous time this destructor was called, we set the key
-		 * to TCACHE_STATE_PURGATORY so that other destructors wouldn't
-		 * cause re-creation of the tcache.  This time, do nothing, so
-		 * that the destructor will not be called again.
-		 */
-	} else if (tcache != NULL) {
-		assert(tcache != TCACHE_STATE_PURGATORY);
-		tcache_destroy(tcache);
-		tcache = TCACHE_STATE_PURGATORY;
-		tcache_tsd_set(&tcache);
+static void
+tcache_destroy(tsd_t *tsd, tcache_t *tcache, bool tsd_tcache) {
+	tcache_flush_cache(tsd, tcache);
+	tcache_arena_dissociate(tsd_tsdn(tsd), tcache);
+
+	if (tsd_tcache) {
+		/* Release the avail array for the TSD embedded auto tcache. */
+		void *avail_array =
+		    (void *)((uintptr_t)tcache_small_bin_get(tcache, 0)->avail -
+		    (uintptr_t)tcache_bin_info[0].ncached_max * sizeof(void *));
+		idalloctm(tsd_tsdn(tsd), avail_array, NULL, NULL, true, true);
+	} else {
+		/* Release both the tcache struct and avail array. */
+		idalloctm(tsd_tsdn(tsd), tcache, NULL, NULL, true, true);
 	}
 }
 
-/* Caller must own arena->lock. */
+/* For auto tcache (embedded in TSD) only. */
 void
-tcache_stats_merge(tcache_t *tcache, arena_t *arena)
-{
+tcache_cleanup(tsd_t *tsd) {
+	tcache_t *tcache = tsd_tcachep_get(tsd);
+	if (!tcache_available(tsd)) {
+		assert(tsd_tcache_enabled_get(tsd) == false);
+		if (config_debug) {
+			assert(tcache_small_bin_get(tcache, 0)->avail == NULL);
+		}
+		return;
+	}
+	assert(tsd_tcache_enabled_get(tsd));
+	assert(tcache_small_bin_get(tcache, 0)->avail != NULL);
+
+	tcache_destroy(tsd, tcache, true);
+	if (config_debug) {
+		tcache_small_bin_get(tcache, 0)->avail = NULL;
+	}
+}
+
+void
+tcache_stats_merge(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena) {
 	unsigned i;
 
 	cassert(config_stats);
@@ -410,48 +525,151 @@ tcache_stats_merge(tcache_t *tcache, arena_t *arena)
 	/* Merge and reset tcache stats. */
 	for (i = 0; i < NBINS; i++) {
 		arena_bin_t *bin = &arena->bins[i];
-		tcache_bin_t *tbin = &tcache->tbins[i];
-		malloc_mutex_lock(&bin->lock);
+		tcache_bin_t *tbin = tcache_small_bin_get(tcache, i);
+		malloc_mutex_lock(tsdn, &bin->lock);
 		bin->stats.nrequests += tbin->tstats.nrequests;
-		malloc_mutex_unlock(&bin->lock);
+		malloc_mutex_unlock(tsdn, &bin->lock);
 		tbin->tstats.nrequests = 0;
 	}
 
 	for (; i < nhbins; i++) {
-		malloc_large_stats_t *lstats = &arena->stats.lstats[i - NBINS];
-		tcache_bin_t *tbin = &tcache->tbins[i];
-		arena->stats.nrequests_large += tbin->tstats.nrequests;
-		lstats->nrequests += tbin->tstats.nrequests;
+		tcache_bin_t *tbin = tcache_large_bin_get(tcache, i);
+		arena_stats_large_nrequests_add(tsdn, &arena->stats, i,
+		    tbin->tstats.nrequests);
 		tbin->tstats.nrequests = 0;
 	}
 }
 
+static bool
+tcaches_create_prep(tsd_t *tsd) {
+	bool err;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx);
+
+	if (tcaches == NULL) {
+		tcaches = base_alloc(tsd_tsdn(tsd), b0get(), sizeof(tcache_t *)
+		    * (MALLOCX_TCACHE_MAX+1), CACHELINE);
+		if (tcaches == NULL) {
+			err = true;
+			goto label_return;
+		}
+	}
+
+	if (tcaches_avail == NULL && tcaches_past > MALLOCX_TCACHE_MAX) {
+		err = true;
+		goto label_return;
+	}
+
+	err = false;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx);
+	return err;
+}
+
 bool
-tcache_boot0(void)
-{
-	unsigned i;
+tcaches_create(tsd_t *tsd, unsigned *r_ind) {
+	witness_assert_depth(tsdn_witness_tsdp_get(tsd_tsdn(tsd)), 0);
 
-	/*
-	 * If necessary, clamp opt_lg_tcache_max, now that arena_maxclass is
-	 * known.
-	 */
-	if (opt_lg_tcache_max < 0 || (1U << opt_lg_tcache_max) < SMALL_MAXCLASS)
+	bool err;
+
+	if (tcaches_create_prep(tsd)) {
+		err = true;
+		goto label_return;
+	}
+
+	tcache_t *tcache = tcache_create_explicit(tsd);
+	if (tcache == NULL) {
+		err = true;
+		goto label_return;
+	}
+
+	tcaches_t *elm;
+	malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx);
+	if (tcaches_avail != NULL) {
+		elm = tcaches_avail;
+		tcaches_avail = tcaches_avail->next;
+		elm->tcache = tcache;
+		*r_ind = (unsigned)(elm - tcaches);
+	} else {
+		elm = &tcaches[tcaches_past];
+		elm->tcache = tcache;
+		*r_ind = tcaches_past;
+		tcaches_past++;
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx);
+
+	err = false;
+label_return:
+	witness_assert_depth(tsdn_witness_tsdp_get(tsd_tsdn(tsd)), 0);
+	return err;
+}
+
+static tcache_t *
+tcaches_elm_remove(tsd_t *tsd, tcaches_t *elm) {
+	malloc_mutex_assert_owner(tsd_tsdn(tsd), &tcaches_mtx);
+
+	if (elm->tcache == NULL) {
+		return NULL;
+	}
+	tcache_t *tcache = elm->tcache;
+	elm->tcache = NULL;
+	return tcache;
+}
+
+void
+tcaches_flush(tsd_t *tsd, unsigned ind) {
+	malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx);
+	tcache_t *tcache = tcaches_elm_remove(tsd, &tcaches[ind]);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx);
+	if (tcache != NULL) {
+		tcache_destroy(tsd, tcache, false);
+	}
+}
+
+void
+tcaches_destroy(tsd_t *tsd, unsigned ind) {
+	malloc_mutex_lock(tsd_tsdn(tsd), &tcaches_mtx);
+	tcaches_t *elm = &tcaches[ind];
+	tcache_t *tcache = tcaches_elm_remove(tsd, elm);
+	elm->next = tcaches_avail;
+	tcaches_avail = elm;
+	malloc_mutex_unlock(tsd_tsdn(tsd), &tcaches_mtx);
+	if (tcache != NULL) {
+		tcache_destroy(tsd, tcache, false);
+	}
+}
+
+bool
+tcache_boot(tsdn_t *tsdn) {
+	/* If necessary, clamp opt_lg_tcache_max. */
+	if (opt_lg_tcache_max < 0 || (ZU(1) << opt_lg_tcache_max) <
+	    SMALL_MAXCLASS) {
 		tcache_maxclass = SMALL_MAXCLASS;
-	else if ((1U << opt_lg_tcache_max) > arena_maxclass)
-		tcache_maxclass = arena_maxclass;
-	else
-		tcache_maxclass = (1U << opt_lg_tcache_max);
+	} else {
+		tcache_maxclass = (ZU(1) << opt_lg_tcache_max);
+	}
 
-	nhbins = NBINS + (tcache_maxclass >> LG_PAGE);
+	if (malloc_mutex_init(&tcaches_mtx, "tcaches", WITNESS_RANK_TCACHES,
+	    malloc_mutex_rank_exclusive)) {
+		return true;
+	}
+
+	nhbins = sz_size2index(tcache_maxclass) + 1;
 
 	/* Initialize tcache_bin_info. */
-	tcache_bin_info = (tcache_bin_info_t *)base_alloc(nhbins *
-	    sizeof(tcache_bin_info_t));
-	if (tcache_bin_info == NULL)
-		return (true);
+	tcache_bin_info = (tcache_bin_info_t *)base_alloc(tsdn, b0get(), nhbins
+	    * sizeof(tcache_bin_info_t), CACHELINE);
+	if (tcache_bin_info == NULL) {
+		return true;
+	}
 	stack_nelms = 0;
+	unsigned i;
 	for (i = 0; i < NBINS; i++) {
-		if ((arena_bin_info[i].nregs << 1) <= TCACHE_NSLOTS_SMALL_MAX) {
+		if ((arena_bin_info[i].nregs << 1) <= TCACHE_NSLOTS_SMALL_MIN) {
+			tcache_bin_info[i].ncached_max =
+			    TCACHE_NSLOTS_SMALL_MIN;
+		} else if ((arena_bin_info[i].nregs << 1) <=
+		    TCACHE_NSLOTS_SMALL_MAX) {
 			tcache_bin_info[i].ncached_max =
 			    (arena_bin_info[i].nregs << 1);
 		} else {
@@ -465,15 +683,26 @@ tcache_boot0(void)
 		stack_nelms += tcache_bin_info[i].ncached_max;
 	}
 
-	return (false);
+	return false;
 }
 
-bool
-tcache_boot1(void)
-{
+void
+tcache_prefork(tsdn_t *tsdn) {
+	if (!config_prof && opt_tcache) {
+		malloc_mutex_prefork(tsdn, &tcaches_mtx);
+	}
+}
 
-	if (tcache_tsd_boot() || tcache_enabled_tsd_boot())
-		return (true);
+void
+tcache_postfork_parent(tsdn_t *tsdn) {
+	if (!config_prof && opt_tcache) {
+		malloc_mutex_postfork_parent(tsdn, &tcaches_mtx);
+	}
+}
 
-	return (false);
+void
+tcache_postfork_child(tsdn_t *tsdn) {
+	if (!config_prof && opt_tcache) {
+		malloc_mutex_postfork_child(tsdn, &tcaches_mtx);
+	}
 }
diff --git a/modules/worldengine/deps/jemalloc/src/ticker.c b/modules/worldengine/deps/jemalloc/src/ticker.c
new file mode 100644
index 0000000000..d7b8cd26c0
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/ticker.c
@@ -0,0 +1,3 @@
+#define JEMALLOC_TICKER_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
diff --git a/modules/worldengine/deps/jemalloc/src/tsd.c b/modules/worldengine/deps/jemalloc/src/tsd.c
index 700caabfe4..f968992f2b 100644
--- a/modules/worldengine/deps/jemalloc/src/tsd.c
+++ b/modules/worldengine/deps/jemalloc/src/tsd.c
@@ -1,5 +1,10 @@
-#define	JEMALLOC_TSD_C_
-#include "jemalloc/internal/jemalloc_internal.h"
+#define JEMALLOC_TSD_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
 
 /******************************************************************************/
 /* Data. */
@@ -7,28 +12,148 @@
 static unsigned ncleanups;
 static malloc_tsd_cleanup_t cleanups[MALLOC_TSD_CLEANUPS_MAX];
 
+#ifdef JEMALLOC_MALLOC_THREAD_CLEANUP
+__thread tsd_t JEMALLOC_TLS_MODEL tsd_tls = TSD_INITIALIZER;
+__thread bool JEMALLOC_TLS_MODEL tsd_initialized = false;
+bool tsd_booted = false;
+#elif (defined(JEMALLOC_TLS))
+__thread tsd_t JEMALLOC_TLS_MODEL tsd_tls = TSD_INITIALIZER;
+pthread_key_t tsd_tsd;
+bool tsd_booted = false;
+#elif (defined(_WIN32))
+DWORD tsd_tsd;
+tsd_wrapper_t tsd_boot_wrapper = {false, TSD_INITIALIZER};
+bool tsd_booted = false;
+#else
+
+/*
+ * This contains a mutex, but it's pretty convenient to allow the mutex code to
+ * have a dependency on tsd.  So we define the struct here, and only refer to it
+ * by pointer in the header.
+ */
+struct tsd_init_head_s {
+	ql_head(tsd_init_block_t) blocks;
+	malloc_mutex_t lock;
+};
+
+pthread_key_t tsd_tsd;
+tsd_init_head_t	tsd_init_head = {
+	ql_head_initializer(blocks),
+	MALLOC_MUTEX_INITIALIZER
+};
+tsd_wrapper_t tsd_boot_wrapper = {
+	false,
+	TSD_INITIALIZER
+};
+bool tsd_booted = false;
+#endif
+
+
 /******************************************************************************/
 
-void *
-malloc_tsd_malloc(size_t size)
-{
+void
+tsd_slow_update(tsd_t *tsd) {
+	if (tsd_nominal(tsd)) {
+		if (malloc_slow || !tsd_tcache_enabled_get(tsd) ||
+		    tsd_reentrancy_level_get(tsd) > 0) {
+			tsd->state = tsd_state_nominal_slow;
+		} else {
+			tsd->state = tsd_state_nominal;
+		}
+	}
+}
+
+static bool
+tsd_data_init(tsd_t *tsd) {
+	/*
+	 * We initialize the rtree context first (before the tcache), since the
+	 * tcache initialization depends on it.
+	 */
+	rtree_ctx_data_init(tsd_rtree_ctxp_get_unsafe(tsd));
 
-	/* Avoid choose_arena() in order to dodge bootstrapping issues. */
-	return (arena_malloc(arenas[0], size, false, false));
+	return tsd_tcache_enabled_data_init(tsd);
 }
 
-void
-malloc_tsd_dalloc(void *wrapper)
-{
+static void
+assert_tsd_data_cleanup_done(tsd_t *tsd) {
+	assert(!tsd_nominal(tsd));
+	assert(*tsd_arenap_get_unsafe(tsd) == NULL);
+	assert(*tsd_iarenap_get_unsafe(tsd) == NULL);
+	assert(*tsd_arenas_tdata_bypassp_get_unsafe(tsd) == true);
+	assert(*tsd_arenas_tdatap_get_unsafe(tsd) == NULL);
+	assert(*tsd_tcache_enabledp_get_unsafe(tsd) == false);
+	assert(*tsd_prof_tdatap_get_unsafe(tsd) == NULL);
+}
+
+static bool
+tsd_data_init_nocleanup(tsd_t *tsd) {
+	assert(tsd->state == tsd_state_reincarnated ||
+	    tsd->state == tsd_state_minimal_initialized);
+	/*
+	 * During reincarnation, there is no guarantee that the cleanup function
+	 * will be called (deallocation may happen after all tsd destructors).
+	 * We set up tsd in a way that no cleanup is needed.
+	 */
+	rtree_ctx_data_init(tsd_rtree_ctxp_get_unsafe(tsd));
+	*tsd_arenas_tdata_bypassp_get(tsd) = true;
+	*tsd_tcache_enabledp_get_unsafe(tsd) = false;
+	*tsd_reentrancy_levelp_get(tsd) = 1;
+	assert_tsd_data_cleanup_done(tsd);
 
-	idalloct(wrapper, false);
+	return false;
 }
 
-void
-malloc_tsd_no_cleanup(void *arg)
-{
+tsd_t *
+tsd_fetch_slow(tsd_t *tsd, bool minimal) {
+	assert(!tsd_fast(tsd));
+
+	if (tsd->state == tsd_state_nominal_slow) {
+		/* On slow path but no work needed. */
+		assert(malloc_slow || !tsd_tcache_enabled_get(tsd) ||
+		    tsd_reentrancy_level_get(tsd) > 0 ||
+		    *tsd_arenas_tdata_bypassp_get(tsd));
+	} else if (tsd->state == tsd_state_uninitialized) {
+		if (!minimal) {
+			tsd->state = tsd_state_nominal;
+			tsd_slow_update(tsd);
+			/* Trigger cleanup handler registration. */
+			tsd_set(tsd);
+			tsd_data_init(tsd);
+		} else {
+			tsd->state = tsd_state_minimal_initialized;
+			tsd_set(tsd);
+			tsd_data_init_nocleanup(tsd);
+		}
+	} else if (tsd->state == tsd_state_minimal_initialized) {
+		if (!minimal) {
+			/* Switch to fully initialized. */
+			tsd->state = tsd_state_nominal;
+			assert(*tsd_reentrancy_levelp_get(tsd) >= 1);
+			(*tsd_reentrancy_levelp_get(tsd))--;
+			tsd_slow_update(tsd);
+			tsd_data_init(tsd);
+		} else {
+			assert_tsd_data_cleanup_done(tsd);
+		}
+	} else if (tsd->state == tsd_state_purgatory) {
+		tsd->state = tsd_state_reincarnated;
+		tsd_set(tsd);
+		tsd_data_init_nocleanup(tsd);
+	} else {
+		assert(tsd->state == tsd_state_reincarnated);
+	}
+
+	return tsd;
+}
+
+void *
+malloc_tsd_malloc(size_t size) {
+	return a0malloc(CACHELINE_CEILING(size));
+}
 
-	not_reached();
+void
+malloc_tsd_dalloc(void *wrapper) {
+	a0dalloc(wrapper);
 }
 
 #if defined(JEMALLOC_MALLOC_THREAD_CLEANUP) || defined(_WIN32)
@@ -36,21 +161,22 @@ malloc_tsd_no_cleanup(void *arg)
 JEMALLOC_EXPORT
 #endif
 void
-_malloc_thread_cleanup(void)
-{
+_malloc_thread_cleanup(void) {
 	bool pending[MALLOC_TSD_CLEANUPS_MAX], again;
 	unsigned i;
 
-	for (i = 0; i < ncleanups; i++)
+	for (i = 0; i < ncleanups; i++) {
 		pending[i] = true;
+	}
 
 	do {
 		again = false;
 		for (i = 0; i < ncleanups; i++) {
 			if (pending[i]) {
 				pending[i] = cleanups[i]();
-				if (pending[i])
+				if (pending[i]) {
 					again = true;
+				}
 			}
 		}
 	} while (again);
@@ -58,26 +184,92 @@ _malloc_thread_cleanup(void)
 #endif
 
 void
-malloc_tsd_cleanup_register(bool (*f)(void))
-{
-
+malloc_tsd_cleanup_register(bool (*f)(void)) {
 	assert(ncleanups < MALLOC_TSD_CLEANUPS_MAX);
 	cleanups[ncleanups] = f;
 	ncleanups++;
 }
 
+static void
+tsd_do_data_cleanup(tsd_t *tsd) {
+	prof_tdata_cleanup(tsd);
+	iarena_cleanup(tsd);
+	arena_cleanup(tsd);
+	arenas_tdata_cleanup(tsd);
+	tcache_cleanup(tsd);
+	witnesses_cleanup(tsd_witness_tsdp_get_unsafe(tsd));
+}
+
 void
-malloc_tsd_boot(void)
-{
+tsd_cleanup(void *arg) {
+	tsd_t *tsd = (tsd_t *)arg;
+
+	switch (tsd->state) {
+	case tsd_state_uninitialized:
+		/* Do nothing. */
+		break;
+	case tsd_state_minimal_initialized:
+		/* This implies the thread only did free() in its life time. */
+		/* Fall through. */
+	case tsd_state_reincarnated:
+		/*
+		 * Reincarnated means another destructor deallocated memory
+		 * after the destructor was called.  Cleanup isn't required but
+		 * is still called for testing and completeness.
+		 */
+		assert_tsd_data_cleanup_done(tsd);
+		/* Fall through. */
+	case tsd_state_nominal:
+	case tsd_state_nominal_slow:
+		tsd_do_data_cleanup(tsd);
+		tsd->state = tsd_state_purgatory;
+		tsd_set(tsd);
+		break;
+	case tsd_state_purgatory:
+		/*
+		 * The previous time this destructor was called, we set the
+		 * state to tsd_state_purgatory so that other destructors
+		 * wouldn't cause re-creation of the tsd.  This time, do
+		 * nothing, and do not request another callback.
+		 */
+		break;
+	default:
+		not_reached();
+	}
+#ifdef JEMALLOC_JET
+	test_callback_t test_callback = *tsd_test_callbackp_get_unsafe(tsd);
+	int *data = tsd_test_datap_get_unsafe(tsd);
+	if (test_callback != NULL) {
+		test_callback(data);
+	}
+#endif
+}
+
+tsd_t *
+malloc_tsd_boot0(void) {
+	tsd_t *tsd;
 
 	ncleanups = 0;
+	if (tsd_boot0()) {
+		return NULL;
+	}
+	tsd = tsd_fetch();
+	*tsd_arenas_tdata_bypassp_get(tsd) = true;
+	return tsd;
+}
+
+void
+malloc_tsd_boot1(void) {
+	tsd_boot1();
+	tsd_t *tsd = tsd_fetch();
+	/* malloc_slow has been set properly.  Update tsd_slow. */
+	tsd_slow_update(tsd);
+	*tsd_arenas_tdata_bypassp_get(tsd) = false;
 }
 
 #ifdef _WIN32
 static BOOL WINAPI
-_tls_callback(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved)
-{
-
+_tls_callback(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved) {
 	switch (fdwReason) {
 #ifdef JEMALLOC_LAZY_LOCK
 	case DLL_THREAD_ATTACH:
@@ -90,52 +282,60 @@ _tls_callback(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved)
 	default:
 		break;
 	}
-	return (true);
+	return true;
 }
 
+/*
+ * We need to be able to say "read" here (in the "pragma section"), but have
+ * hooked "read". We won't read for the rest of the file, so we can get away
+ * with unhooking.
+ */
+#ifdef read
+#  undef read
+#endif
+
 #ifdef _MSC_VER
 #  ifdef _M_IX86
 #    pragma comment(linker, "/INCLUDE:__tls_used")
+#    pragma comment(linker, "/INCLUDE:_tls_callback")
 #  else
 #    pragma comment(linker, "/INCLUDE:_tls_used")
+#    pragma comment(linker, "/INCLUDE:tls_callback")
 #  endif
 #  pragma section(".CRT$XLY",long,read)
 #endif
 JEMALLOC_SECTION(".CRT$XLY") JEMALLOC_ATTR(used)
-static const BOOL	(WINAPI *tls_callback)(HINSTANCE hinstDLL,
+BOOL	(WINAPI *const tls_callback)(HINSTANCE hinstDLL,
     DWORD fdwReason, LPVOID lpvReserved) = _tls_callback;
 #endif
 
 #if (!defined(JEMALLOC_MALLOC_THREAD_CLEANUP) && !defined(JEMALLOC_TLS) && \
     !defined(_WIN32))
 void *
-tsd_init_check_recursion(tsd_init_head_t *head, tsd_init_block_t *block)
-{
+tsd_init_check_recursion(tsd_init_head_t *head, tsd_init_block_t *block) {
 	pthread_t self = pthread_self();
 	tsd_init_block_t *iter;
 
 	/* Check whether this thread has already inserted into the list. */
-	malloc_mutex_lock(&head->lock);
+	malloc_mutex_lock(TSDN_NULL, &head->lock);
 	ql_foreach(iter, &head->blocks, link) {
 		if (iter->thread == self) {
-			malloc_mutex_unlock(&head->lock);
-			return (iter->data);
+			malloc_mutex_unlock(TSDN_NULL, &head->lock);
+			return iter->data;
 		}
 	}
 	/* Insert block into list. */
 	ql_elm_new(block, link);
 	block->thread = self;
 	ql_tail_insert(&head->blocks, block, link);
-	malloc_mutex_unlock(&head->lock);
-	return (NULL);
+	malloc_mutex_unlock(TSDN_NULL, &head->lock);
+	return NULL;
 }
 
 void
-tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block)
-{
-
-	malloc_mutex_lock(&head->lock);
+tsd_init_finish(tsd_init_head_t *head, tsd_init_block_t *block) {
+	malloc_mutex_lock(TSDN_NULL, &head->lock);
 	ql_remove(&head->blocks, block, link);
-	malloc_mutex_unlock(&head->lock);
+	malloc_mutex_unlock(TSDN_NULL, &head->lock);
 }
 #endif
diff --git a/modules/worldengine/deps/jemalloc/src/witness.c b/modules/worldengine/deps/jemalloc/src/witness.c
new file mode 100644
index 0000000000..f42b72ad1a
--- /dev/null
+++ b/modules/worldengine/deps/jemalloc/src/witness.c
@@ -0,0 +1,100 @@
+#define JEMALLOC_WITNESS_C_
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/malloc_io.h"
+
+void
+witness_init(witness_t *witness, const char *name, witness_rank_t rank,
+    witness_comp_t *comp, void *opaque) {
+	witness->name = name;
+	witness->rank = rank;
+	witness->comp = comp;
+	witness->opaque = opaque;
+}
+
+static void
+witness_lock_error_impl(const witness_list_t *witnesses,
+    const witness_t *witness) {
+	witness_t *w;
+
+	malloc_printf("<jemalloc>: Lock rank order reversal:");
+	ql_foreach(w, witnesses, link) {
+		malloc_printf(" %s(%u)", w->name, w->rank);
+	}
+	malloc_printf(" %s(%u)\n", witness->name, witness->rank);
+	abort();
+}
+witness_lock_error_t *JET_MUTABLE witness_lock_error = witness_lock_error_impl;
+
+static void
+witness_owner_error_impl(const witness_t *witness) {
+	malloc_printf("<jemalloc>: Should own %s(%u)\n", witness->name,
+	    witness->rank);
+	abort();
+}
+witness_owner_error_t *JET_MUTABLE witness_owner_error =
+    witness_owner_error_impl;
+
+static void
+witness_not_owner_error_impl(const witness_t *witness) {
+	malloc_printf("<jemalloc>: Should not own %s(%u)\n", witness->name,
+	    witness->rank);
+	abort();
+}
+witness_not_owner_error_t *JET_MUTABLE witness_not_owner_error =
+    witness_not_owner_error_impl;
+
+static void
+witness_depth_error_impl(const witness_list_t *witnesses,
+    witness_rank_t rank_inclusive, unsigned depth) {
+	witness_t *w;
+
+	malloc_printf("<jemalloc>: Should own %u lock%s of rank >= %u:", depth,
+	    (depth != 1) ?  "s" : "", rank_inclusive);
+	ql_foreach(w, witnesses, link) {
+		malloc_printf(" %s(%u)", w->name, w->rank);
+	}
+	malloc_printf("\n");
+	abort();
+}
+witness_depth_error_t *JET_MUTABLE witness_depth_error =
+    witness_depth_error_impl;
+
+void
+witnesses_cleanup(witness_tsd_t *witness_tsd) {
+	witness_assert_lockless(witness_tsd_tsdn(witness_tsd));
+
+	/* Do nothing. */
+}
+
+void
+witness_prefork(witness_tsd_t *witness_tsd) {
+	if (!config_debug) {
+		return;
+	}
+	witness_tsd->forking = true;
+}
+
+void
+witness_postfork_parent(witness_tsd_t *witness_tsd) {
+	if (!config_debug) {
+		return;
+	}
+	witness_tsd->forking = false;
+}
+
+void
+witness_postfork_child(witness_tsd_t *witness_tsd) {
+	if (!config_debug) {
+		return;
+	}
+#ifndef JEMALLOC_MUTEX_INIT_CB
+	witness_list_t *witnesses;
+
+	witnesses = &witness_tsd->witnesses;
+	ql_new(witnesses);
+#endif
+	witness_tsd->forking = false;
+}
diff --git a/modules/worldengine/deps/jemalloc/src/zone.c b/modules/worldengine/deps/jemalloc/src/zone.c
index e0302ef4ed..9d3b7b4952 100644
--- a/modules/worldengine/deps/jemalloc/src/zone.c
+++ b/modules/worldengine/deps/jemalloc/src/zone.c
@@ -1,10 +1,83 @@
-#include "jemalloc/internal/jemalloc_internal.h"
+#include "jemalloc/internal/jemalloc_preamble.h"
+#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/assert.h"
+
 #ifndef JEMALLOC_ZONE
 #  error "This source file is for zones on Darwin (OS X)."
 #endif
 
+/* Definitions of the following structs in malloc/malloc.h might be too old
+ * for the built binary to run on newer versions of OSX. So use the newest
+ * possible version of those structs.
+ */
+typedef struct _malloc_zone_t {
+	void *reserved1;
+	void *reserved2;
+	size_t (*size)(struct _malloc_zone_t *, const void *);
+	void *(*malloc)(struct _malloc_zone_t *, size_t);
+	void *(*calloc)(struct _malloc_zone_t *, size_t, size_t);
+	void *(*valloc)(struct _malloc_zone_t *, size_t);
+	void (*free)(struct _malloc_zone_t *, void *);
+	void *(*realloc)(struct _malloc_zone_t *, void *, size_t);
+	void (*destroy)(struct _malloc_zone_t *);
+	const char *zone_name;
+	unsigned (*batch_malloc)(struct _malloc_zone_t *, size_t, void **, unsigned);
+	void (*batch_free)(struct _malloc_zone_t *, void **, unsigned);
+	struct malloc_introspection_t *introspect;
+	unsigned version;
+	void *(*memalign)(struct _malloc_zone_t *, size_t, size_t);
+	void (*free_definite_size)(struct _malloc_zone_t *, void *, size_t);
+	size_t (*pressure_relief)(struct _malloc_zone_t *, size_t);
+} malloc_zone_t;
+
+typedef struct {
+	vm_address_t address;
+	vm_size_t size;
+} vm_range_t;
+
+typedef struct malloc_statistics_t {
+	unsigned blocks_in_use;
+	size_t size_in_use;
+	size_t max_size_in_use;
+	size_t size_allocated;
+} malloc_statistics_t;
+
+typedef kern_return_t memory_reader_t(task_t, vm_address_t, vm_size_t, void **);
+
+typedef void vm_range_recorder_t(task_t, void *, unsigned type, vm_range_t *, unsigned);
+
+typedef struct malloc_introspection_t {
+	kern_return_t (*enumerator)(task_t, void *, unsigned, vm_address_t, memory_reader_t, vm_range_recorder_t);
+	size_t (*good_size)(malloc_zone_t *, size_t);
+	boolean_t (*check)(malloc_zone_t *);
+	void (*print)(malloc_zone_t *, boolean_t);
+	void (*log)(malloc_zone_t *, void *);
+	void (*force_lock)(malloc_zone_t *);
+	void (*force_unlock)(malloc_zone_t *);
+	void (*statistics)(malloc_zone_t *, malloc_statistics_t *);
+	boolean_t (*zone_locked)(malloc_zone_t *);
+	boolean_t (*enable_discharge_checking)(malloc_zone_t *);
+	boolean_t (*disable_discharge_checking)(malloc_zone_t *);
+	void (*discharge)(malloc_zone_t *, void *);
+#ifdef __BLOCKS__
+	void (*enumerate_discharged_pointers)(malloc_zone_t *, void (^)(void *, void *));
+#else
+	void *enumerate_unavailable_without_blocks;
+#endif
+	void (*reinit_lock)(malloc_zone_t *);
+} malloc_introspection_t;
+
+extern kern_return_t malloc_get_all_zones(task_t, memory_reader_t, vm_address_t **, unsigned *);
+
+extern malloc_zone_t *malloc_default_zone(void);
+
+extern void malloc_zone_register(malloc_zone_t *zone);
+
+extern void malloc_zone_unregister(malloc_zone_t *zone);
+
 /*
- * The malloc_default_purgeable_zone function is only available on >= 10.6.
+ * The malloc_default_purgeable_zone() function is only available on >= 10.6.
  * We need to check whether it is present at runtime, thus the weak_import.
  */
 extern malloc_zone_t *malloc_default_purgeable_zone(void)
@@ -13,30 +86,42 @@ JEMALLOC_ATTR(weak_import);
 /******************************************************************************/
 /* Data. */
 
-static malloc_zone_t zone;
-static struct malloc_introspection_t zone_introspect;
+static malloc_zone_t *default_zone, *purgeable_zone;
+static malloc_zone_t jemalloc_zone;
+static struct malloc_introspection_t jemalloc_zone_introspect;
 
 /******************************************************************************/
 /* Function prototypes for non-inline static functions. */
 
-static size_t	zone_size(malloc_zone_t *zone, void *ptr);
+static size_t	zone_size(malloc_zone_t *zone, const void *ptr);
 static void	*zone_malloc(malloc_zone_t *zone, size_t size);
 static void	*zone_calloc(malloc_zone_t *zone, size_t num, size_t size);
 static void	*zone_valloc(malloc_zone_t *zone, size_t size);
 static void	zone_free(malloc_zone_t *zone, void *ptr);
 static void	*zone_realloc(malloc_zone_t *zone, void *ptr, size_t size);
-#if (JEMALLOC_ZONE_VERSION >= 5)
 static void	*zone_memalign(malloc_zone_t *zone, size_t alignment,
-#endif
-#if (JEMALLOC_ZONE_VERSION >= 6)
     size_t size);
 static void	zone_free_definite_size(malloc_zone_t *zone, void *ptr,
     size_t size);
-#endif
-static void	*zone_destroy(malloc_zone_t *zone);
+static void	zone_destroy(malloc_zone_t *zone);
+static unsigned	zone_batch_malloc(struct _malloc_zone_t *zone, size_t size,
+    void **results, unsigned num_requested);
+static void	zone_batch_free(struct _malloc_zone_t *zone,
+    void **to_be_freed, unsigned num_to_be_freed);
+static size_t	zone_pressure_relief(struct _malloc_zone_t *zone, size_t goal);
 static size_t	zone_good_size(malloc_zone_t *zone, size_t size);
+static kern_return_t	zone_enumerator(task_t task, void *data, unsigned type_mask,
+    vm_address_t zone_address, memory_reader_t reader,
+    vm_range_recorder_t recorder);
+static boolean_t	zone_check(malloc_zone_t *zone);
+static void	zone_print(malloc_zone_t *zone, boolean_t verbose);
+static void	zone_log(malloc_zone_t *zone, void *address);
 static void	zone_force_lock(malloc_zone_t *zone);
 static void	zone_force_unlock(malloc_zone_t *zone);
+static void	zone_statistics(malloc_zone_t *zone,
+    malloc_statistics_t *stats);
+static boolean_t	zone_locked(malloc_zone_t *zone);
+static void	zone_reinit_lock(malloc_zone_t *zone);
 
 /******************************************************************************/
 /*
@@ -44,9 +129,7 @@ static void	zone_force_unlock(malloc_zone_t *zone);
  */
 
 static size_t
-zone_size(malloc_zone_t *zone, void *ptr)
-{
-
+zone_size(malloc_zone_t *zone, const void *ptr) {
 	/*
 	 * There appear to be places within Darwin (such as setenv(3)) that
 	 * cause calls to this function with pointers that *no* zone owns.  If
@@ -54,40 +137,33 @@ zone_size(malloc_zone_t *zone, void *ptr)
 	 * our zone into two parts, and use one as the default allocator and
 	 * the other as the default deallocator/reallocator.  Since that will
 	 * not work in practice, we must check all pointers to assure that they
-	 * reside within a mapped chunk before determining size.
+	 * reside within a mapped extent before determining size.
 	 */
-	return (ivsalloc(ptr, config_prof));
+	return ivsalloc(tsdn_fetch(), ptr);
 }
 
 static void *
-zone_malloc(malloc_zone_t *zone, size_t size)
-{
-
-	return (je_malloc(size));
+zone_malloc(malloc_zone_t *zone, size_t size) {
+	return je_malloc(size);
 }
 
 static void *
-zone_calloc(malloc_zone_t *zone, size_t num, size_t size)
-{
-
-	return (je_calloc(num, size));
+zone_calloc(malloc_zone_t *zone, size_t num, size_t size) {
+	return je_calloc(num, size);
 }
 
 static void *
-zone_valloc(malloc_zone_t *zone, size_t size)
-{
+zone_valloc(malloc_zone_t *zone, size_t size) {
 	void *ret = NULL; /* Assignment avoids useless compiler warning. */
 
 	je_posix_memalign(&ret, PAGE, size);
 
-	return (ret);
+	return ret;
 }
 
 static void
-zone_free(malloc_zone_t *zone, void *ptr)
-{
-
-	if (ivsalloc(ptr, config_prof) != 0) {
+zone_free(malloc_zone_t *zone, void *ptr) {
+	if (ivsalloc(tsdn_fetch(), ptr) != 0) {
 		je_free(ptr);
 		return;
 	}
@@ -96,163 +172,280 @@ zone_free(malloc_zone_t *zone, void *ptr)
 }
 
 static void *
-zone_realloc(malloc_zone_t *zone, void *ptr, size_t size)
-{
-
-	if (ivsalloc(ptr, config_prof) != 0)
-		return (je_realloc(ptr, size));
+zone_realloc(malloc_zone_t *zone, void *ptr, size_t size) {
+	if (ivsalloc(tsdn_fetch(), ptr) != 0) {
+		return je_realloc(ptr, size);
+	}
 
-	return (realloc(ptr, size));
+	return realloc(ptr, size);
 }
 
-#if (JEMALLOC_ZONE_VERSION >= 5)
 static void *
-zone_memalign(malloc_zone_t *zone, size_t alignment, size_t size)
-{
+zone_memalign(malloc_zone_t *zone, size_t alignment, size_t size) {
 	void *ret = NULL; /* Assignment avoids useless compiler warning. */
 
 	je_posix_memalign(&ret, alignment, size);
 
-	return (ret);
+	return ret;
 }
-#endif
 
-#if (JEMALLOC_ZONE_VERSION >= 6)
 static void
-zone_free_definite_size(malloc_zone_t *zone, void *ptr, size_t size)
-{
+zone_free_definite_size(malloc_zone_t *zone, void *ptr, size_t size) {
+	size_t alloc_size;
 
-	if (ivsalloc(ptr, config_prof) != 0) {
-		assert(ivsalloc(ptr, config_prof) == size);
+	alloc_size = ivsalloc(tsdn_fetch(), ptr);
+	if (alloc_size != 0) {
+		assert(alloc_size == size);
 		je_free(ptr);
 		return;
 	}
 
 	free(ptr);
 }
-#endif
-
-static void *
-zone_destroy(malloc_zone_t *zone)
-{
 
+static void
+zone_destroy(malloc_zone_t *zone) {
 	/* This function should never be called. */
 	not_reached();
-	return (NULL);
+}
+
+static unsigned
+zone_batch_malloc(struct _malloc_zone_t *zone, size_t size, void **results,
+    unsigned num_requested) {
+	unsigned i;
+
+	for (i = 0; i < num_requested; i++) {
+		results[i] = je_malloc(size);
+		if (!results[i])
+			break;
+	}
+
+	return i;
+}
+
+static void
+zone_batch_free(struct _malloc_zone_t *zone, void **to_be_freed,
+    unsigned num_to_be_freed) {
+	unsigned i;
+
+	for (i = 0; i < num_to_be_freed; i++) {
+		zone_free(zone, to_be_freed[i]);
+		to_be_freed[i] = NULL;
+	}
 }
 
 static size_t
-zone_good_size(malloc_zone_t *zone, size_t size)
-{
+zone_pressure_relief(struct _malloc_zone_t *zone, size_t goal) {
+	return 0;
+}
 
-	if (size == 0)
+static size_t
+zone_good_size(malloc_zone_t *zone, size_t size) {
+	if (size == 0) {
 		size = 1;
-	return (s2u(size));
+	}
+	return sz_s2u(size);
+}
+
+static kern_return_t
+zone_enumerator(task_t task, void *data, unsigned type_mask,
+    vm_address_t zone_address, memory_reader_t reader,
+    vm_range_recorder_t recorder) {
+	return KERN_SUCCESS;
+}
+
+static boolean_t
+zone_check(malloc_zone_t *zone) {
+	return true;
+}
+
+static void
+zone_print(malloc_zone_t *zone, boolean_t verbose) {
 }
 
 static void
-zone_force_lock(malloc_zone_t *zone)
-{
+zone_log(malloc_zone_t *zone, void *address) {
+}
 
-	if (isthreaded)
+static void
+zone_force_lock(malloc_zone_t *zone) {
+	if (isthreaded) {
 		jemalloc_prefork();
+	}
+}
+
+static void
+zone_force_unlock(malloc_zone_t *zone) {
+	/*
+	 * Call jemalloc_postfork_child() rather than
+	 * jemalloc_postfork_parent(), because this function is executed by both
+	 * parent and child.  The parent can tolerate having state
+	 * reinitialized, but the child cannot unlock mutexes that were locked
+	 * by the parent.
+	 */
+	if (isthreaded) {
+		jemalloc_postfork_child();
+	}
+}
+
+static void
+zone_statistics(malloc_zone_t *zone, malloc_statistics_t *stats) {
+	/* We make no effort to actually fill the values */
+	stats->blocks_in_use = 0;
+	stats->size_in_use = 0;
+	stats->max_size_in_use = 0;
+	stats->size_allocated = 0;
+}
+
+static boolean_t
+zone_locked(malloc_zone_t *zone) {
+	/* Pretend no lock is being held */
+	return false;
+}
+
+static void
+zone_reinit_lock(malloc_zone_t *zone) {
+	/* As of OSX 10.12, this function is only used when force_unlock would
+	 * be used if the zone version were < 9. So just use force_unlock. */
+	zone_force_unlock(zone);
+}
+
+static void
+zone_init(void) {
+	jemalloc_zone.size = zone_size;
+	jemalloc_zone.malloc = zone_malloc;
+	jemalloc_zone.calloc = zone_calloc;
+	jemalloc_zone.valloc = zone_valloc;
+	jemalloc_zone.free = zone_free;
+	jemalloc_zone.realloc = zone_realloc;
+	jemalloc_zone.destroy = zone_destroy;
+	jemalloc_zone.zone_name = "jemalloc_zone";
+	jemalloc_zone.batch_malloc = zone_batch_malloc;
+	jemalloc_zone.batch_free = zone_batch_free;
+	jemalloc_zone.introspect = &jemalloc_zone_introspect;
+	jemalloc_zone.version = 9;
+	jemalloc_zone.memalign = zone_memalign;
+	jemalloc_zone.free_definite_size = zone_free_definite_size;
+	jemalloc_zone.pressure_relief = zone_pressure_relief;
+
+	jemalloc_zone_introspect.enumerator = zone_enumerator;
+	jemalloc_zone_introspect.good_size = zone_good_size;
+	jemalloc_zone_introspect.check = zone_check;
+	jemalloc_zone_introspect.print = zone_print;
+	jemalloc_zone_introspect.log = zone_log;
+	jemalloc_zone_introspect.force_lock = zone_force_lock;
+	jemalloc_zone_introspect.force_unlock = zone_force_unlock;
+	jemalloc_zone_introspect.statistics = zone_statistics;
+	jemalloc_zone_introspect.zone_locked = zone_locked;
+	jemalloc_zone_introspect.enable_discharge_checking = NULL;
+	jemalloc_zone_introspect.disable_discharge_checking = NULL;
+	jemalloc_zone_introspect.discharge = NULL;
+#ifdef __BLOCKS__
+	jemalloc_zone_introspect.enumerate_discharged_pointers = NULL;
+#else
+	jemalloc_zone_introspect.enumerate_unavailable_without_blocks = NULL;
+#endif
+	jemalloc_zone_introspect.reinit_lock = zone_reinit_lock;
+}
+
+static malloc_zone_t *
+zone_default_get(void) {
+	malloc_zone_t **zones = NULL;
+	unsigned int num_zones = 0;
+
+	/*
+	 * On OSX 10.12, malloc_default_zone returns a special zone that is not
+	 * present in the list of registered zones. That zone uses a "lite zone"
+	 * if one is present (apparently enabled when malloc stack logging is
+	 * enabled), or the first registered zone otherwise. In practice this
+	 * means unless malloc stack logging is enabled, the first registered
+	 * zone is the default.  So get the list of zones to get the first one,
+	 * instead of relying on malloc_default_zone.
+	 */
+	if (KERN_SUCCESS != malloc_get_all_zones(0, NULL,
+	    (vm_address_t**)&zones, &num_zones)) {
+		/*
+		 * Reset the value in case the failure happened after it was
+		 * set.
+		 */
+		num_zones = 0;
+	}
+
+	if (num_zones) {
+		return zones[0];
+	}
+
+	return malloc_default_zone();
 }
 
+/* As written, this function can only promote jemalloc_zone. */
 static void
-zone_force_unlock(malloc_zone_t *zone)
-{
+zone_promote(void) {
+	malloc_zone_t *zone;
+
+	do {
+		/*
+		 * Unregister and reregister the default zone.  On OSX >= 10.6,
+		 * unregistering takes the last registered zone and places it
+		 * at the location of the specified zone.  Unregistering the
+		 * default zone thus makes the last registered one the default.
+		 * On OSX < 10.6, unregistering shifts all registered zones.
+		 * The first registered zone then becomes the default.
+		 */
+		malloc_zone_unregister(default_zone);
+		malloc_zone_register(default_zone);
 
-	if (isthreaded)
-		jemalloc_postfork_parent();
+		/*
+		 * On OSX 10.6, having the default purgeable zone appear before
+		 * the default zone makes some things crash because it thinks it
+		 * owns the default zone allocated pointers.  We thus
+		 * unregister/re-register it in order to ensure it's always
+		 * after the default zone.  On OSX < 10.6, there is no purgeable
+		 * zone, so this does nothing.  On OSX >= 10.6, unregistering
+		 * replaces the purgeable zone with the last registered zone
+		 * above, i.e. the default zone.  Registering it again then puts
+		 * it at the end, obviously after the default zone.
+		 */
+		if (purgeable_zone != NULL) {
+			malloc_zone_unregister(purgeable_zone);
+			malloc_zone_register(purgeable_zone);
+		}
+
+		zone = zone_default_get();
+	} while (zone != &jemalloc_zone);
 }
 
 JEMALLOC_ATTR(constructor)
 void
-register_zone(void)
-{
-
+zone_register(void) {
 	/*
 	 * If something else replaced the system default zone allocator, don't
 	 * register jemalloc's.
 	 */
-	malloc_zone_t *default_zone = malloc_default_zone();
-	if (!default_zone->zone_name ||
-	    strcmp(default_zone->zone_name, "DefaultMallocZone") != 0) {
+	default_zone = zone_default_get();
+	if (!default_zone->zone_name || strcmp(default_zone->zone_name,
+	    "DefaultMallocZone") != 0) {
 		return;
 	}
 
-	zone.size = (void *)zone_size;
-	zone.malloc = (void *)zone_malloc;
-	zone.calloc = (void *)zone_calloc;
-	zone.valloc = (void *)zone_valloc;
-	zone.free = (void *)zone_free;
-	zone.realloc = (void *)zone_realloc;
-	zone.destroy = (void *)zone_destroy;
-	zone.zone_name = "jemalloc_zone";
-	zone.batch_malloc = NULL;
-	zone.batch_free = NULL;
-	zone.introspect = &zone_introspect;
-	zone.version = JEMALLOC_ZONE_VERSION;
-#if (JEMALLOC_ZONE_VERSION >= 5)
-	zone.memalign = zone_memalign;
-#endif
-#if (JEMALLOC_ZONE_VERSION >= 6)
-	zone.free_definite_size = zone_free_definite_size;
-#endif
-#if (JEMALLOC_ZONE_VERSION >= 8)
-	zone.pressure_relief = NULL;
-#endif
-
-	zone_introspect.enumerator = NULL;
-	zone_introspect.good_size = (void *)zone_good_size;
-	zone_introspect.check = NULL;
-	zone_introspect.print = NULL;
-	zone_introspect.log = NULL;
-	zone_introspect.force_lock = (void *)zone_force_lock;
-	zone_introspect.force_unlock = (void *)zone_force_unlock;
-	zone_introspect.statistics = NULL;
-#if (JEMALLOC_ZONE_VERSION >= 6)
-	zone_introspect.zone_locked = NULL;
-#endif
-#if (JEMALLOC_ZONE_VERSION >= 7)
-	zone_introspect.enable_discharge_checking = NULL;
-	zone_introspect.disable_discharge_checking = NULL;
-	zone_introspect.discharge = NULL;
-#ifdef __BLOCKS__
-	zone_introspect.enumerate_discharged_pointers = NULL;
-#else
-	zone_introspect.enumerate_unavailable_without_blocks = NULL;
-#endif
-#endif
-
 	/*
 	 * The default purgeable zone is created lazily by OSX's libc.  It uses
 	 * the default zone when it is created for "small" allocations
 	 * (< 15 KiB), but assumes the default zone is a scalable_zone.  This
 	 * obviously fails when the default zone is the jemalloc zone, so
-	 * malloc_default_purgeable_zone is called beforehand so that the
+	 * malloc_default_purgeable_zone() is called beforehand so that the
 	 * default purgeable zone is created when the default zone is still
 	 * a scalable_zone.  As purgeable zones only exist on >= 10.6, we need
 	 * to check for the existence of malloc_default_purgeable_zone() at
 	 * run time.
 	 */
-	if (malloc_default_purgeable_zone != NULL)
-		malloc_default_purgeable_zone();
+	purgeable_zone = (malloc_default_purgeable_zone == NULL) ? NULL :
+	    malloc_default_purgeable_zone();
 
 	/* Register the custom zone.  At this point it won't be the default. */
-	malloc_zone_register(&zone);
+	zone_init();
+	malloc_zone_register(&jemalloc_zone);
 
-	/*
-	 * Unregister and reregister the default zone.  On OSX >= 10.6,
-	 * unregistering takes the last registered zone and places it at the
-	 * location of the specified zone.  Unregistering the default zone thus
-	 * makes the last registered one the default.  On OSX < 10.6,
-	 * unregistering shifts all registered zones.  The first registered zone
-	 * then becomes the default.
-	 */
-	do {
-		default_zone = malloc_default_zone();
-		malloc_zone_unregister(default_zone);
-		malloc_zone_register(default_zone);
-	} while (malloc_default_zone() != &zone);
+	/* Promote the custom zone to be default. */
+	zone_promote();
 }