Init commit.HEADmaster

30 files changed, 18006 insertions, 0 deletions

diff --git a/deps/jemalloc/src/arena.c b/deps/jemalloc/src/arena.c
new file mode 100644
index 0000000..648a8da
--- /dev/null
+++ b/deps/jemalloc/src/arena.c
@@ -0,0 +1,3863 @@
+#define	JEMALLOC_ARENA_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+purge_mode_t	opt_purge = PURGE_DEFAULT;
+const char	*purge_mode_names[] = {
+	"ratio",
+	"decay",
+	"N/A"
+};
+ssize_t		opt_lg_dirty_mult = LG_DIRTY_MULT_DEFAULT;
+static ssize_t	lg_dirty_mult_default;
+ssize_t		opt_decay_time = DECAY_TIME_DEFAULT;
+static ssize_t	decay_time_default;
+
+arena_bin_info_t	arena_bin_info[NBINS];
+
+size_t		map_bias;
+size_t		map_misc_offset;
+size_t		arena_maxrun; /* Max run size for arenas. */
+size_t		large_maxclass; /* Max large size class. */
+unsigned	nlclasses; /* Number of large size classes. */
+unsigned	nhclasses; /* Number of huge size classes. */
+
+/******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
+
+static void	arena_chunk_dalloc(tsdn_t *tsdn, arena_t *arena,
+    arena_chunk_t *chunk);
+static void	arena_purge_to_limit(tsdn_t *tsdn, arena_t *arena,
+    size_t ndirty_limit);
+static void	arena_run_dalloc(tsdn_t *tsdn, arena_t *arena, arena_run_t *run,
+    bool dirty, bool cleaned, bool decommitted);
+static void	arena_dalloc_bin_run(tsdn_t *tsdn, 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_run_t *run,
+    arena_bin_t *bin);
+
+/******************************************************************************/
+
+JEMALLOC_INLINE_C size_t
+arena_miscelm_size_get(const arena_chunk_map_misc_t *miscelm)
+{
+	arena_chunk_t *chunk;
+	size_t pageind, mapbits;
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(miscelm);
+	pageind = arena_miscelm_to_pageind(miscelm);
+	mapbits = arena_mapbits_get(chunk, pageind);
+	return (arena_mapbits_size_decode(mapbits));
+}
+
+JEMALLOC_INLINE_C const extent_node_t *
+arena_miscelm_extent_get(const arena_chunk_map_misc_t *miscelm)
+{
+	arena_chunk_t *chunk;
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(miscelm);
+	return (&chunk->node);
+}
+
+JEMALLOC_INLINE_C int
+arena_sn_comp(const arena_chunk_map_misc_t *a, const arena_chunk_map_misc_t *b)
+{
+	size_t a_sn, b_sn;
+
+	assert(a != NULL);
+	assert(b != NULL);
+
+	a_sn = extent_node_sn_get(arena_miscelm_extent_get(a));
+	b_sn = extent_node_sn_get(arena_miscelm_extent_get(b));
+
+	return ((a_sn > b_sn) - (a_sn < b_sn));
+}
+
+JEMALLOC_INLINE_C int
+arena_ad_comp(const arena_chunk_map_misc_t *a,
+    const arena_chunk_map_misc_t *b)
+{
+	uintptr_t a_miscelm = (uintptr_t)a;
+	uintptr_t b_miscelm = (uintptr_t)b;
+
+	assert(a != NULL);
+	assert(b != NULL);
+
+	return ((a_miscelm > b_miscelm) - (a_miscelm < b_miscelm));
+}
+
+JEMALLOC_INLINE_C int
+arena_snad_comp(const arena_chunk_map_misc_t *a,
+    const arena_chunk_map_misc_t *b)
+{
+	int ret;
+
+	assert(a != NULL);
+	assert(b != NULL);
+
+	ret = arena_sn_comp(a, b);
+	if (ret != 0)
+		return (ret);
+
+	ret = arena_ad_comp(a, b);
+	return (ret);
+}
+
+/* Generate pairing heap functions. */
+ph_gen(static UNUSED, arena_run_heap_, arena_run_heap_t, arena_chunk_map_misc_t,
+    ph_link, arena_snad_comp)
+
+#ifdef JEMALLOC_JET
+#undef run_quantize_floor
+#define	run_quantize_floor JEMALLOC_N(n_run_quantize_floor)
+#endif
+static size_t
+run_quantize_floor(size_t size)
+{
+	size_t ret;
+	pszind_t pind;
+
+	assert(size > 0);
+	assert(size <= HUGE_MAXCLASS);
+	assert((size & PAGE_MASK) == 0);
+
+	assert(size != 0);
+	assert(size == PAGE_CEILING(size));
+
+	pind = psz2ind(size - 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 = pind2sz(pind - 1) + large_pad;
+	assert(ret <= size);
+	return (ret);
+}
+#ifdef JEMALLOC_JET
+#undef run_quantize_floor
+#define	run_quantize_floor JEMALLOC_N(run_quantize_floor)
+run_quantize_t *run_quantize_floor = JEMALLOC_N(n_run_quantize_floor);
+#endif
+
+#ifdef JEMALLOC_JET
+#undef run_quantize_ceil
+#define	run_quantize_ceil JEMALLOC_N(n_run_quantize_ceil)
+#endif
+static size_t
+run_quantize_ceil(size_t size)
+{
+	size_t ret;
+
+	assert(size > 0);
+	assert(size <= HUGE_MAXCLASS);
+	assert((size & PAGE_MASK) == 0);
+
+	ret = run_quantize_floor(size);
+	if (ret < size) {
+		/*
+		 * Skip a quantization that may have an adequately large run,
+		 * because under-sized runs 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 = pind2sz(psz2ind(ret - large_pad + 1)) + large_pad;
+	}
+	return (ret);
+}
+#ifdef JEMALLOC_JET
+#undef run_quantize_ceil
+#define	run_quantize_ceil JEMALLOC_N(run_quantize_ceil)
+run_quantize_t *run_quantize_ceil = JEMALLOC_N(n_run_quantize_ceil);
+#endif
+
+static void
+arena_avail_insert(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
+    size_t npages)
+{
+	pszind_t pind = psz2ind(run_quantize_floor(arena_miscelm_size_get(
+	    arena_miscelm_get_const(chunk, pageind))));
+	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
+	    LG_PAGE));
+	assert((npages << LG_PAGE) < chunksize);
+	assert(pind2sz(pind) <= chunksize);
+	arena_run_heap_insert(&arena->runs_avail[pind],
+	    arena_miscelm_get_mutable(chunk, pageind));
+}
+
+static void
+arena_avail_remove(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
+    size_t npages)
+{
+	pszind_t pind = psz2ind(run_quantize_floor(arena_miscelm_size_get(
+	    arena_miscelm_get_const(chunk, pageind))));
+	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
+	    LG_PAGE));
+	assert((npages << LG_PAGE) < chunksize);
+	assert(pind2sz(pind) <= chunksize);
+	arena_run_heap_remove(&arena->runs_avail[pind],
+	    arena_miscelm_get_mutable(chunk, pageind));
+}
+
+static void
+arena_run_dirty_insert(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
+    size_t npages)
+{
+	arena_chunk_map_misc_t *miscelm = arena_miscelm_get_mutable(chunk,
+	    pageind);
+
+	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
+	    LG_PAGE));
+	assert(arena_mapbits_dirty_get(chunk, pageind) == CHUNK_MAP_DIRTY);
+	assert(arena_mapbits_dirty_get(chunk, pageind+npages-1) ==
+	    CHUNK_MAP_DIRTY);
+
+	qr_new(&miscelm->rd, rd_link);
+	qr_meld(&arena->runs_dirty, &miscelm->rd, rd_link);
+	arena->ndirty += npages;
+}
+
+static void
+arena_run_dirty_remove(arena_t *arena, arena_chunk_t *chunk, size_t pageind,
+    size_t npages)
+{
+	arena_chunk_map_misc_t *miscelm = arena_miscelm_get_mutable(chunk,
+	    pageind);
+
+	assert(npages == (arena_mapbits_unallocated_size_get(chunk, pageind) >>
+	    LG_PAGE));
+	assert(arena_mapbits_dirty_get(chunk, pageind) == CHUNK_MAP_DIRTY);
+	assert(arena_mapbits_dirty_get(chunk, pageind+npages-1) ==
+	    CHUNK_MAP_DIRTY);
+
+	qr_remove(&miscelm->rd, rd_link);
+	assert(arena->ndirty >= npages);
+	arena->ndirty -= npages;
+}
+
+static size_t
+arena_chunk_dirty_npages(const extent_node_t *node)
+{
+
+	return (extent_node_size_get(node) >> LG_PAGE);
+}
+
+void
+arena_chunk_cache_maybe_insert(arena_t *arena, extent_node_t *node, bool cache)
+{
+
+	if (cache) {
+		extent_node_dirty_linkage_init(node);
+		extent_node_dirty_insert(node, &arena->runs_dirty,
+		    &arena->chunks_cache);
+		arena->ndirty += arena_chunk_dirty_npages(node);
+	}
+}
+
+void
+arena_chunk_cache_maybe_remove(arena_t *arena, extent_node_t *node, bool dirty)
+{
+
+	if (dirty) {
+		extent_node_dirty_remove(node);
+		assert(arena->ndirty >= arena_chunk_dirty_npages(node));
+		arena->ndirty -= arena_chunk_dirty_npages(node);
+	}
+}
+
+JEMALLOC_INLINE_C void *
+arena_run_reg_alloc(arena_run_t *run, arena_bin_info_t *bin_info)
+{
+	void *ret;
+	size_t regind;
+	arena_chunk_map_misc_t *miscelm;
+	void *rpages;
+
+	assert(run->nfree > 0);
+	assert(!bitmap_full(run->bitmap, &bin_info->bitmap_info));
+
+	regind = (unsigned)bitmap_sfu(run->bitmap, &bin_info->bitmap_info);
+	miscelm = arena_run_to_miscelm(run);
+	rpages = arena_miscelm_to_rpages(miscelm);
+	ret = (void *)((uintptr_t)rpages + (uintptr_t)bin_info->reg0_offset +
+	    (uintptr_t)(bin_info->reg_interval * regind));
+	run->nfree--;
+	return (ret);
+}
+
+JEMALLOC_INLINE_C 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);
+	szind_t binind = arena_ptr_small_binind_get(ptr, mapbits);
+	arena_bin_info_t *bin_info = &arena_bin_info[binind];
+	size_t regind = arena_run_regind(run, bin_info, ptr);
+
+	assert(run->nfree < bin_info->nregs);
+	/* Freeing an interior pointer can cause assertion failure. */
+	assert(((uintptr_t)ptr -
+	    ((uintptr_t)arena_miscelm_to_rpages(arena_run_to_miscelm(run)) +
+	    (uintptr_t)bin_info->reg0_offset)) %
+	    (uintptr_t)bin_info->reg_interval == 0);
+	assert((uintptr_t)ptr >=
+	    (uintptr_t)arena_miscelm_to_rpages(arena_run_to_miscelm(run)) +
+	    (uintptr_t)bin_info->reg0_offset);
+	/* Freeing an unallocated pointer can cause assertion failure. */
+	assert(bitmap_get(run->bitmap, &bin_info->bitmap_info, regind));
+
+	bitmap_unset(run->bitmap, &bin_info->bitmap_info, regind);
+	run->nfree++;
+}
+
+JEMALLOC_INLINE_C void
+arena_run_zero(arena_chunk_t *chunk, size_t run_ind, size_t npages)
+{
+
+	JEMALLOC_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));
+}
+
+JEMALLOC_INLINE_C void
+arena_run_page_mark_zeroed(arena_chunk_t *chunk, size_t run_ind)
+{
+
+	JEMALLOC_VALGRIND_MAKE_MEM_DEFINED((void *)((uintptr_t)chunk + (run_ind
+	    << LG_PAGE)), PAGE);
+}
+
+JEMALLOC_INLINE_C 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));
+
+	arena_run_page_mark_zeroed(chunk, run_ind);
+	for (i = 0; i < PAGE / sizeof(size_t); i++)
+		assert(p[i] == 0);
+}
+
+static void
+arena_nactive_add(arena_t *arena, size_t add_pages)
+{
+
+	if (config_stats) {
+		size_t cactive_add = CHUNK_CEILING((arena->nactive +
+		    add_pages) << LG_PAGE) - CHUNK_CEILING(arena->nactive <<
+		    LG_PAGE);
+		if (cactive_add != 0)
+			stats_cactive_add(cactive_add);
+	}
+	arena->nactive += add_pages;
+}
+
+static void
+arena_nactive_sub(arena_t *arena, size_t sub_pages)
+{
+
+	if (config_stats) {
+		size_t cactive_sub = CHUNK_CEILING(arena->nactive << LG_PAGE) -
+		    CHUNK_CEILING((arena->nactive - sub_pages) << LG_PAGE);
+		if (cactive_sub != 0)
+			stats_cactive_sub(cactive_sub);
+	}
+	arena->nactive -= sub_pages;
+}
+
+static void
+arena_run_split_remove(arena_t *arena, arena_chunk_t *chunk, size_t run_ind,
+    size_t flag_dirty, size_t flag_decommitted, size_t need_pages)
+{
+	size_t total_pages, rem_pages;
+
+	assert(flag_dirty == 0 || flag_decommitted == 0);
+
+	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);
+	if (flag_dirty != 0)
+		arena_run_dirty_remove(arena, chunk, run_ind, total_pages);
+	arena_nactive_add(arena, need_pages);
+
+	/* Keep track of trailing unused pages for later use. */
+	if (rem_pages > 0) {
+		size_t flags = flag_dirty | flag_decommitted;
+		size_t flag_unzeroed_mask = (flags == 0) ?  CHUNK_MAP_UNZEROED :
+		    0;
+
+		arena_mapbits_unallocated_set(chunk, run_ind+need_pages,
+		    (rem_pages << LG_PAGE), flags |
+		    (arena_mapbits_unzeroed_get(chunk, run_ind+need_pages) &
+		    flag_unzeroed_mask));
+		arena_mapbits_unallocated_set(chunk, run_ind+total_pages-1,
+		    (rem_pages << LG_PAGE), flags |
+		    (arena_mapbits_unzeroed_get(chunk, run_ind+total_pages-1) &
+		    flag_unzeroed_mask));
+		if (flag_dirty != 0) {
+			arena_run_dirty_insert(arena, chunk, run_ind+need_pages,
+			    rem_pages);
+		}
+		arena_avail_insert(arena, chunk, run_ind+need_pages, rem_pages);
+	}
+}
+
+static bool
+arena_run_split_large_helper(arena_t *arena, arena_run_t *run, size_t size,
+    bool remove, bool zero)
+{
+	arena_chunk_t *chunk;
+	arena_chunk_map_misc_t *miscelm;
+	size_t flag_dirty, flag_decommitted, run_ind, need_pages;
+	size_t flag_unzeroed_mask;
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
+	miscelm = arena_run_to_miscelm(run);
+	run_ind = arena_miscelm_to_pageind(miscelm);
+	flag_dirty = arena_mapbits_dirty_get(chunk, run_ind);
+	flag_decommitted = arena_mapbits_decommitted_get(chunk, run_ind);
+	need_pages = (size >> LG_PAGE);
+	assert(need_pages > 0);
+
+	if (flag_decommitted != 0 && arena->chunk_hooks.commit(chunk, chunksize,
+	    run_ind << LG_PAGE, size, arena->ind))
+		return (true);
+
+	if (remove) {
+		arena_run_split_remove(arena, chunk, run_ind, flag_dirty,
+		    flag_decommitted, need_pages);
+	}
+
+	if (zero) {
+		if (flag_decommitted != 0) {
+			/* The run is untouched, and therefore zeroed. */
+			JEMALLOC_VALGRIND_MAKE_MEM_DEFINED((void
+			    *)((uintptr_t)chunk + (run_ind << LG_PAGE)),
+			    (need_pages << LG_PAGE));
+		} else if (flag_dirty != 0) {
+			/* The run is dirty, so all pages must be zeroed. */
+			arena_run_zero(chunk, run_ind, need_pages);
+		} else {
+			/*
+			 * The run is clean, so some pages may be zeroed (i.e.
+			 * never before touched).
+			 */
+			size_t i;
+			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);
+				}
+			}
+		}
+	} else {
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED((void *)((uintptr_t)chunk +
+		    (run_ind << LG_PAGE)), (need_pages << LG_PAGE));
+	}
+
+	/*
+	 * Set the last element first, in case the run only contains one page
+	 * (i.e. both statements set the same element).
+	 */
+	flag_unzeroed_mask = (flag_dirty | flag_decommitted) == 0 ?
+	    CHUNK_MAP_UNZEROED : 0;
+	arena_mapbits_large_set(chunk, run_ind+need_pages-1, 0, flag_dirty |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+	    run_ind+need_pages-1)));
+	arena_mapbits_large_set(chunk, run_ind, size, flag_dirty |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk, run_ind)));
+	return (false);
+}
+
+static bool
+arena_run_split_large(arena_t *arena, arena_run_t *run, size_t size, bool zero)
+{
+
+	return (arena_run_split_large_helper(arena, run, size, true, zero));
+}
+
+static bool
+arena_run_init_large(arena_t *arena, arena_run_t *run, size_t size, bool zero)
+{
+
+	return (arena_run_split_large_helper(arena, run, size, false, zero));
+}
+
+static bool
+arena_run_split_small(arena_t *arena, arena_run_t *run, size_t size,
+    szind_t binind)
+{
+	arena_chunk_t *chunk;
+	arena_chunk_map_misc_t *miscelm;
+	size_t flag_dirty, flag_decommitted, run_ind, need_pages, i;
+
+	assert(binind != BININD_INVALID);
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
+	miscelm = arena_run_to_miscelm(run);
+	run_ind = arena_miscelm_to_pageind(miscelm);
+	flag_dirty = arena_mapbits_dirty_get(chunk, run_ind);
+	flag_decommitted = arena_mapbits_decommitted_get(chunk, run_ind);
+	need_pages = (size >> LG_PAGE);
+	assert(need_pages > 0);
+
+	if (flag_decommitted != 0 && arena->chunk_hooks.commit(chunk, chunksize,
+	    run_ind << LG_PAGE, size, arena->ind))
+		return (true);
+
+	arena_run_split_remove(arena, chunk, run_ind, flag_dirty,
+	    flag_decommitted, need_pages);
+
+	for (i = 0; i < need_pages; i++) {
+		size_t flag_unzeroed = arena_mapbits_unzeroed_get(chunk,
+		    run_ind+i);
+		arena_mapbits_small_set(chunk, run_ind+i, i, binind,
+		    flag_unzeroed);
+		if (config_debug && flag_dirty == 0 && flag_unzeroed == 0)
+			arena_run_page_validate_zeroed(chunk, run_ind+i);
+	}
+	JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED((void *)((uintptr_t)chunk +
+	    (run_ind << LG_PAGE)), (need_pages << LG_PAGE));
+	return (false);
+}
+
+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_maxrun);
+	assert(arena_mapbits_unallocated_size_get(chunk, chunk_npages-1) ==
+	    arena_maxrun);
+	assert(arena_mapbits_dirty_get(chunk, map_bias) ==
+	    arena_mapbits_dirty_get(chunk, chunk_npages-1));
+
+	return (chunk);
+}
+
+static bool
+arena_chunk_register(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    size_t sn, bool zero)
+{
+
+	/*
+	 * The extent node notion of "committed" doesn't directly apply to
+	 * arena chunks.  Arbitrarily mark them as committed.  The commit state
+	 * of runs is tracked individually, and upon chunk deallocation the
+	 * entire chunk is in a consistent commit state.
+	 */
+	extent_node_init(&chunk->node, arena, chunk, chunksize, sn, zero, true);
+	extent_node_achunk_set(&chunk->node, true);
+	return (chunk_register(tsdn, chunk, &chunk->node));
+}
+
+static arena_chunk_t *
+arena_chunk_alloc_internal_hard(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks, bool *zero, bool *commit)
+{
+	arena_chunk_t *chunk;
+	size_t sn;
+
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	chunk = (arena_chunk_t *)chunk_alloc_wrapper(tsdn, arena, chunk_hooks,
+	    NULL, chunksize, chunksize, &sn, zero, commit);
+	if (chunk != NULL && !*commit) {
+		/* Commit header. */
+		if (chunk_hooks->commit(chunk, chunksize, 0, map_bias <<
+		    LG_PAGE, arena->ind)) {
+			chunk_dalloc_wrapper(tsdn, arena, chunk_hooks,
+			    (void *)chunk, chunksize, sn, *zero, *commit);
+			chunk = NULL;
+		}
+	}
+	if (chunk != NULL && arena_chunk_register(tsdn, arena, chunk, sn,
+	    *zero)) {
+		if (!*commit) {
+			/* Undo commit of header. */
+			chunk_hooks->decommit(chunk, chunksize, 0, map_bias <<
+			    LG_PAGE, arena->ind);
+		}
+		chunk_dalloc_wrapper(tsdn, arena, chunk_hooks, (void *)chunk,
+		    chunksize, sn, *zero, *commit);
+		chunk = NULL;
+	}
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	return (chunk);
+}
+
+static arena_chunk_t *
+arena_chunk_alloc_internal(tsdn_t *tsdn, arena_t *arena, bool *zero,
+    bool *commit)
+{
+	arena_chunk_t *chunk;
+	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+	size_t sn;
+
+	chunk = chunk_alloc_cache(tsdn, arena, &chunk_hooks, NULL, chunksize,
+	    chunksize, &sn, zero, commit, true);
+	if (chunk != NULL) {
+		if (arena_chunk_register(tsdn, arena, chunk, sn, *zero)) {
+			chunk_dalloc_cache(tsdn, arena, &chunk_hooks, chunk,
+			    chunksize, sn, true);
+			return (NULL);
+		}
+	}
+	if (chunk == NULL) {
+		chunk = arena_chunk_alloc_internal_hard(tsdn, arena,
+		    &chunk_hooks, zero, commit);
+	}
+
+	if (config_stats && chunk != NULL) {
+		arena->stats.mapped += chunksize;
+		arena->stats.metadata_mapped += (map_bias << LG_PAGE);
+	}
+
+	return (chunk);
+}
+
+static arena_chunk_t *
+arena_chunk_init_hard(tsdn_t *tsdn, arena_t *arena)
+{
+	arena_chunk_t *chunk;
+	bool zero, commit;
+	size_t flag_unzeroed, flag_decommitted, i;
+
+	assert(arena->spare == NULL);
+
+	zero = false;
+	commit = false;
+	chunk = arena_chunk_alloc_internal(tsdn, arena, &zero, &commit);
+	if (chunk == NULL)
+		return (NULL);
+
+	chunk->hugepage = true;
+
+	/*
+	 * Initialize the map to contain one maximal free untouched run.  Mark
+	 * the pages as zeroed if arena_chunk_alloc_internal() returned a zeroed
+	 * or decommitted chunk.
+	 */
+	flag_unzeroed = (zero || !commit) ? 0 : CHUNK_MAP_UNZEROED;
+	flag_decommitted = commit ? 0 : CHUNK_MAP_DECOMMITTED;
+	arena_mapbits_unallocated_set(chunk, map_bias, arena_maxrun,
+	    flag_unzeroed | flag_decommitted);
+	/*
+	 * There is no need to initialize the internal page map entries unless
+	 * the chunk is not zeroed.
+	 */
+	if (!zero) {
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(
+		    (void *)arena_bitselm_get_const(chunk, map_bias+1),
+		    (size_t)((uintptr_t)arena_bitselm_get_const(chunk,
+		    chunk_npages-1) -
+		    (uintptr_t)arena_bitselm_get_const(chunk, map_bias+1)));
+		for (i = map_bias+1; i < chunk_npages-1; i++)
+			arena_mapbits_internal_set(chunk, i, flag_unzeroed);
+	} else {
+		JEMALLOC_VALGRIND_MAKE_MEM_DEFINED((void
+		    *)arena_bitselm_get_const(chunk, map_bias+1),
+		    (size_t)((uintptr_t)arena_bitselm_get_const(chunk,
+		    chunk_npages-1) -
+		    (uintptr_t)arena_bitselm_get_const(chunk, map_bias+1)));
+		if (config_debug) {
+			for (i = map_bias+1; i < chunk_npages-1; i++) {
+				assert(arena_mapbits_unzeroed_get(chunk, i) ==
+				    flag_unzeroed);
+			}
+		}
+	}
+	arena_mapbits_unallocated_set(chunk, chunk_npages-1, arena_maxrun,
+	    flag_unzeroed);
+
+	return (chunk);
+}
+
+static arena_chunk_t *
+arena_chunk_alloc(tsdn_t *tsdn, arena_t *arena)
+{
+	arena_chunk_t *chunk;
+
+	if (arena->spare != NULL)
+		chunk = arena_chunk_init_spare(arena);
+	else {
+		chunk = arena_chunk_init_hard(tsdn, arena);
+		if (chunk == NULL)
+			return (NULL);
+	}
+
+	ql_elm_new(&chunk->node, ql_link);
+	ql_tail_insert(&arena->achunks, &chunk->node, ql_link);
+	arena_avail_insert(arena, chunk, map_bias, chunk_npages-map_bias);
+
+	return (chunk);
+}
+
+static void
+arena_chunk_discard(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk)
+{
+	size_t sn, hugepage;
+	bool committed;
+	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+
+	chunk_deregister(chunk, &chunk->node);
+
+	sn = extent_node_sn_get(&chunk->node);
+	hugepage = chunk->hugepage;
+	committed = (arena_mapbits_decommitted_get(chunk, map_bias) == 0);
+	if (!committed) {
+		/*
+		 * Decommit the header.  Mark the chunk as decommitted even if
+		 * header decommit fails, since treating a partially committed
+		 * chunk as committed has a high potential for causing later
+		 * access of decommitted memory.
+		 */
+		chunk_hooks = chunk_hooks_get(tsdn, arena);
+		chunk_hooks.decommit(chunk, chunksize, 0, map_bias << LG_PAGE,
+		    arena->ind);
+	}
+	if (!hugepage) {
+		/*
+		 * Convert chunk back to the default state, so that all
+		 * subsequent chunk allocations start out with chunks that can
+		 * be backed by transparent huge pages.
+		 */
+		pages_huge(chunk, chunksize);
+	}
+
+	chunk_dalloc_cache(tsdn, arena, &chunk_hooks, (void *)chunk, chunksize,
+	    sn, committed);
+
+	if (config_stats) {
+		arena->stats.mapped -= chunksize;
+		arena->stats.metadata_mapped -= (map_bias << LG_PAGE);
+	}
+}
+
+static void
+arena_spare_discard(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *spare)
+{
+
+	assert(arena->spare != spare);
+
+	if (arena_mapbits_dirty_get(spare, map_bias) != 0) {
+		arena_run_dirty_remove(arena, spare, map_bias,
+		    chunk_npages-map_bias);
+	}
+
+	arena_chunk_discard(tsdn, arena, spare);
+}
+
+static void
+arena_chunk_dalloc(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk)
+{
+	arena_chunk_t *spare;
+
+	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_maxrun);
+	assert(arena_mapbits_unallocated_size_get(chunk, chunk_npages-1) ==
+	    arena_maxrun);
+	assert(arena_mapbits_dirty_get(chunk, map_bias) ==
+	    arena_mapbits_dirty_get(chunk, chunk_npages-1));
+	assert(arena_mapbits_decommitted_get(chunk, map_bias) ==
+	    arena_mapbits_decommitted_get(chunk, chunk_npages-1));
+
+	/* Remove run from runs_avail, so that the arena does not use it. */
+	arena_avail_remove(arena, chunk, map_bias, chunk_npages-map_bias);
+
+	ql_remove(&arena->achunks, &chunk->node, ql_link);
+	spare = arena->spare;
+	arena->spare = chunk;
+	if (spare != NULL)
+		arena_spare_discard(tsdn, arena, spare);
+}
+
+static void
+arena_huge_malloc_stats_update(arena_t *arena, size_t usize)
+{
+	szind_t index = size2index(usize) - nlclasses - NBINS;
+
+	cassert(config_stats);
+
+	arena->stats.nmalloc_huge++;
+	arena->stats.allocated_huge += usize;
+	arena->stats.hstats[index].nmalloc++;
+	arena->stats.hstats[index].curhchunks++;
+}
+
+static void
+arena_huge_malloc_stats_update_undo(arena_t *arena, size_t usize)
+{
+	szind_t index = size2index(usize) - nlclasses - NBINS;
+
+	cassert(config_stats);
+
+	arena->stats.nmalloc_huge--;
+	arena->stats.allocated_huge -= usize;
+	arena->stats.hstats[index].nmalloc--;
+	arena->stats.hstats[index].curhchunks--;
+}
+
+static void
+arena_huge_dalloc_stats_update(arena_t *arena, size_t usize)
+{
+	szind_t index = size2index(usize) - nlclasses - NBINS;
+
+	cassert(config_stats);
+
+	arena->stats.ndalloc_huge++;
+	arena->stats.allocated_huge -= usize;
+	arena->stats.hstats[index].ndalloc++;
+	arena->stats.hstats[index].curhchunks--;
+}
+
+static void
+arena_huge_reset_stats_cancel(arena_t *arena, size_t usize)
+{
+	szind_t index = size2index(usize) - nlclasses - NBINS;
+
+	cassert(config_stats);
+
+	arena->stats.ndalloc_huge++;
+	arena->stats.hstats[index].ndalloc--;
+}
+
+static void
+arena_huge_dalloc_stats_update_undo(arena_t *arena, size_t usize)
+{
+	szind_t index = size2index(usize) - nlclasses - NBINS;
+
+	cassert(config_stats);
+
+	arena->stats.ndalloc_huge--;
+	arena->stats.allocated_huge += usize;
+	arena->stats.hstats[index].ndalloc--;
+	arena->stats.hstats[index].curhchunks++;
+}
+
+static void
+arena_huge_ralloc_stats_update(arena_t *arena, size_t oldsize, size_t usize)
+{
+
+	arena_huge_dalloc_stats_update(arena, oldsize);
+	arena_huge_malloc_stats_update(arena, usize);
+}
+
+static void
+arena_huge_ralloc_stats_update_undo(arena_t *arena, size_t oldsize,
+    size_t usize)
+{
+
+	arena_huge_dalloc_stats_update_undo(arena, oldsize);
+	arena_huge_malloc_stats_update_undo(arena, usize);
+}
+
+extent_node_t *
+arena_node_alloc(tsdn_t *tsdn, arena_t *arena)
+{
+	extent_node_t *node;
+
+	malloc_mutex_lock(tsdn, &arena->node_cache_mtx);
+	node = ql_last(&arena->node_cache, ql_link);
+	if (node == NULL) {
+		malloc_mutex_unlock(tsdn, &arena->node_cache_mtx);
+		return (base_alloc(tsdn, sizeof(extent_node_t)));
+	}
+	ql_tail_remove(&arena->node_cache, extent_node_t, ql_link);
+	malloc_mutex_unlock(tsdn, &arena->node_cache_mtx);
+	return (node);
+}
+
+void
+arena_node_dalloc(tsdn_t *tsdn, arena_t *arena, extent_node_t *node)
+{
+
+	malloc_mutex_lock(tsdn, &arena->node_cache_mtx);
+	ql_elm_new(node, ql_link);
+	ql_tail_insert(&arena->node_cache, node, ql_link);
+	malloc_mutex_unlock(tsdn, &arena->node_cache_mtx);
+}
+
+static void *
+arena_chunk_alloc_huge_hard(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks, size_t usize, size_t alignment, size_t *sn,
+    bool *zero, size_t csize)
+{
+	void *ret;
+	bool commit = true;
+
+	ret = chunk_alloc_wrapper(tsdn, arena, chunk_hooks, NULL, csize,
+	    alignment, sn, zero, &commit);
+	if (ret == NULL) {
+		/* Revert optimistic stats updates. */
+		malloc_mutex_lock(tsdn, &arena->lock);
+		if (config_stats) {
+			arena_huge_malloc_stats_update_undo(arena, usize);
+			arena->stats.mapped -= usize;
+		}
+		arena_nactive_sub(arena, usize >> LG_PAGE);
+		malloc_mutex_unlock(tsdn, &arena->lock);
+	}
+
+	return (ret);
+}
+
+void *
+arena_chunk_alloc_huge(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, size_t *sn, bool *zero)
+{
+	void *ret;
+	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+	size_t csize = CHUNK_CEILING(usize);
+	bool commit = true;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+
+	/* Optimistically update stats. */
+	if (config_stats) {
+		arena_huge_malloc_stats_update(arena, usize);
+		arena->stats.mapped += usize;
+	}
+	arena_nactive_add(arena, usize >> LG_PAGE);
+
+	ret = chunk_alloc_cache(tsdn, arena, &chunk_hooks, NULL, csize,
+	    alignment, sn, zero, &commit, true);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	if (ret == NULL) {
+		ret = arena_chunk_alloc_huge_hard(tsdn, arena, &chunk_hooks,
+		    usize, alignment, sn, zero, csize);
+	}
+
+	return (ret);
+}
+
+void
+arena_chunk_dalloc_huge(tsdn_t *tsdn, arena_t *arena, void *chunk, size_t usize,
+    size_t sn)
+{
+	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+	size_t csize;
+
+	csize = CHUNK_CEILING(usize);
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (config_stats) {
+		arena_huge_dalloc_stats_update(arena, usize);
+		arena->stats.mapped -= usize;
+	}
+	arena_nactive_sub(arena, usize >> LG_PAGE);
+
+	chunk_dalloc_cache(tsdn, arena, &chunk_hooks, chunk, csize, sn, true);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+void
+arena_chunk_ralloc_huge_similar(tsdn_t *tsdn, arena_t *arena, void *chunk,
+    size_t oldsize, size_t usize)
+{
+
+	assert(CHUNK_CEILING(oldsize) == CHUNK_CEILING(usize));
+	assert(oldsize != usize);
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (config_stats)
+		arena_huge_ralloc_stats_update(arena, oldsize, usize);
+	if (oldsize < usize)
+		arena_nactive_add(arena, (usize - oldsize) >> LG_PAGE);
+	else
+		arena_nactive_sub(arena, (oldsize - usize) >> LG_PAGE);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+void
+arena_chunk_ralloc_huge_shrink(tsdn_t *tsdn, arena_t *arena, void *chunk,
+    size_t oldsize, size_t usize, size_t sn)
+{
+	size_t udiff = oldsize - usize;
+	size_t cdiff = CHUNK_CEILING(oldsize) - CHUNK_CEILING(usize);
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (config_stats) {
+		arena_huge_ralloc_stats_update(arena, oldsize, usize);
+		if (cdiff != 0)
+			arena->stats.mapped -= cdiff;
+	}
+	arena_nactive_sub(arena, udiff >> LG_PAGE);
+
+	if (cdiff != 0) {
+		chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+		void *nchunk = (void *)((uintptr_t)chunk +
+		    CHUNK_CEILING(usize));
+
+		chunk_dalloc_cache(tsdn, arena, &chunk_hooks, nchunk, cdiff,
+		    sn, true);
+	}
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+static bool
+arena_chunk_ralloc_huge_expand_hard(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks, void *chunk, size_t oldsize, size_t usize,
+    size_t *sn, bool *zero, void *nchunk, size_t udiff, size_t cdiff)
+{
+	bool err;
+	bool commit = true;
+
+	err = (chunk_alloc_wrapper(tsdn, arena, chunk_hooks, nchunk, cdiff,
+	    chunksize, sn, zero, &commit) == NULL);
+	if (err) {
+		/* Revert optimistic stats updates. */
+		malloc_mutex_lock(tsdn, &arena->lock);
+		if (config_stats) {
+			arena_huge_ralloc_stats_update_undo(arena, oldsize,
+			    usize);
+			arena->stats.mapped -= cdiff;
+		}
+		arena_nactive_sub(arena, udiff >> LG_PAGE);
+		malloc_mutex_unlock(tsdn, &arena->lock);
+	} else if (chunk_hooks->merge(chunk, CHUNK_CEILING(oldsize), nchunk,
+	    cdiff, true, arena->ind)) {
+		chunk_dalloc_wrapper(tsdn, arena, chunk_hooks, nchunk, cdiff,
+		    *sn, *zero, true);
+		err = true;
+	}
+	return (err);
+}
+
+bool
+arena_chunk_ralloc_huge_expand(tsdn_t *tsdn, arena_t *arena, void *chunk,
+    size_t oldsize, size_t usize, bool *zero)
+{
+	bool err;
+	chunk_hooks_t chunk_hooks = chunk_hooks_get(tsdn, arena);
+	void *nchunk = (void *)((uintptr_t)chunk + CHUNK_CEILING(oldsize));
+	size_t udiff = usize - oldsize;
+	size_t cdiff = CHUNK_CEILING(usize) - CHUNK_CEILING(oldsize);
+	size_t sn;
+	bool commit = true;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+
+	/* Optimistically update stats. */
+	if (config_stats) {
+		arena_huge_ralloc_stats_update(arena, oldsize, usize);
+		arena->stats.mapped += cdiff;
+	}
+	arena_nactive_add(arena, udiff >> LG_PAGE);
+
+	err = (chunk_alloc_cache(tsdn, arena, &chunk_hooks, nchunk, cdiff,
+	    chunksize, &sn, zero, &commit, true) == NULL);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	if (err) {
+		err = arena_chunk_ralloc_huge_expand_hard(tsdn, arena,
+		    &chunk_hooks, chunk, oldsize, usize, &sn, zero, nchunk,
+		    udiff, cdiff);
+	} else if (chunk_hooks.merge(chunk, CHUNK_CEILING(oldsize), nchunk,
+	    cdiff, true, arena->ind)) {
+		chunk_dalloc_wrapper(tsdn, arena, &chunk_hooks, nchunk, cdiff,
+		    sn, *zero, true);
+		err = true;
+	}
+
+	return (err);
+}
+
+/*
+ * Do first-best-fit run selection, i.e. select the lowest run that best fits.
+ * Run sizes are indexed, so not all candidate runs are necessarily exactly the
+ * same size.
+ */
+static arena_run_t *
+arena_run_first_best_fit(arena_t *arena, size_t size)
+{
+	pszind_t pind, i;
+
+	pind = psz2ind(run_quantize_ceil(size));
+
+	for (i = pind; pind2sz(i) <= chunksize; i++) {
+		arena_chunk_map_misc_t *miscelm = arena_run_heap_first(
+		    &arena->runs_avail[i]);
+		if (miscelm != NULL)
+			return (&miscelm->run);
+	}
+
+	return (NULL);
+}
+
+static arena_run_t *
+arena_run_alloc_large_helper(arena_t *arena, size_t size, bool zero)
+{
+	arena_run_t *run = arena_run_first_best_fit(arena, size);
+	if (run != NULL) {
+		if (arena_run_split_large(arena, run, size, zero))
+			run = NULL;
+	}
+	return (run);
+}
+
+static arena_run_t *
+arena_run_alloc_large(tsdn_t *tsdn, arena_t *arena, size_t size, bool zero)
+{
+	arena_chunk_t *chunk;
+	arena_run_t *run;
+
+	assert(size <= arena_maxrun);
+	assert(size == PAGE_CEILING(size));
+
+	/* Search the arena's chunks for the lowest best fit. */
+	run = arena_run_alloc_large_helper(arena, size, zero);
+	if (run != NULL)
+		return (run);
+
+	/*
+	 * No usable runs.  Create a new chunk from which to allocate the run.
+	 */
+	chunk = arena_chunk_alloc(tsdn, arena);
+	if (chunk != NULL) {
+		run = &arena_miscelm_get_mutable(chunk, map_bias)->run;
+		if (arena_run_split_large(arena, run, size, zero))
+			run = NULL;
+		return (run);
+	}
+
+	/*
+	 * 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));
+}
+
+static arena_run_t *
+arena_run_alloc_small_helper(arena_t *arena, size_t size, szind_t binind)
+{
+	arena_run_t *run = arena_run_first_best_fit(arena, size);
+	if (run != NULL) {
+		if (arena_run_split_small(arena, run, size, binind))
+			run = NULL;
+	}
+	return (run);
+}
+
+static arena_run_t *
+arena_run_alloc_small(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t binind)
+{
+	arena_chunk_t *chunk;
+	arena_run_t *run;
+
+	assert(size <= arena_maxrun);
+	assert(size == PAGE_CEILING(size));
+	assert(binind != BININD_INVALID);
+
+	/* Search the arena's chunks for the lowest best fit. */
+	run = arena_run_alloc_small_helper(arena, size, binind);
+	if (run != NULL)
+		return (run);
+
+	/*
+	 * No usable runs.  Create a new chunk from which to allocate the run.
+	 */
+	chunk = arena_chunk_alloc(tsdn, arena);
+	if (chunk != NULL) {
+		run = &arena_miscelm_get_mutable(chunk, map_bias)->run;
+		if (arena_run_split_small(arena, run, size, binind))
+			run = NULL;
+		return (run);
+	}
+
+	/*
+	 * 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_lg_dirty_mult_valid(ssize_t lg_dirty_mult)
+{
+
+	return (lg_dirty_mult >= -1 && lg_dirty_mult < (ssize_t)(sizeof(size_t)
+	    << 3));
+}
+
+ssize_t
+arena_lg_dirty_mult_get(tsdn_t *tsdn, arena_t *arena)
+{
+	ssize_t lg_dirty_mult;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	lg_dirty_mult = arena->lg_dirty_mult;
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	return (lg_dirty_mult);
+}
+
+bool
+arena_lg_dirty_mult_set(tsdn_t *tsdn, arena_t *arena, ssize_t lg_dirty_mult)
+{
+
+	if (!arena_lg_dirty_mult_valid(lg_dirty_mult))
+		return (true);
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena->lg_dirty_mult = lg_dirty_mult;
+	arena_maybe_purge(tsdn, arena);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	return (false);
+}
+
+static void
+arena_decay_deadline_init(arena_t *arena)
+{
+
+	assert(opt_purge == purge_mode_decay);
+
+	/*
+	 * Generate a new deadline that is uniformly random within the next
+	 * epoch after the current one.
+	 */
+	nstime_copy(&arena->decay.deadline, &arena->decay.epoch);
+	nstime_add(&arena->decay.deadline, &arena->decay.interval);
+	if (arena->decay.time > 0) {
+		nstime_t jitter;
+
+		nstime_init(&jitter, prng_range_u64(&arena->decay.jitter_state,
+		    nstime_ns(&arena->decay.interval)));
+		nstime_add(&arena->decay.deadline, &jitter);
+	}
+}
+
+static bool
+arena_decay_deadline_reached(const arena_t *arena, const nstime_t *time)
+{
+
+	assert(opt_purge == purge_mode_decay);
+
+	return (nstime_compare(&arena->decay.deadline, time) <= 0);
+}
+
+static size_t
+arena_decay_backlog_npages_limit(const arena_t *arena)
+{
+	static const uint64_t h_steps[] = {
+#define	STEP(step, h, x, y) \
+		h,
+		SMOOTHSTEP
+#undef STEP
+	};
+	uint64_t sum;
+	size_t npages_limit_backlog;
+	unsigned i;
+
+	assert(opt_purge == purge_mode_decay);
+
+	/*
+	 * 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.
+	 */
+	sum = 0;
+	for (i = 0; i < SMOOTHSTEP_NSTEPS; i++)
+		sum += arena->decay.backlog[i] * h_steps[i];
+	npages_limit_backlog = (size_t)(sum >> SMOOTHSTEP_BFP);
+
+	return (npages_limit_backlog);
+}
+
+static void
+arena_decay_backlog_update_last(arena_t *arena)
+{
+	size_t ndirty_delta = (arena->ndirty > arena->decay.ndirty) ?
+	    arena->ndirty - arena->decay.ndirty : 0;
+	arena->decay.backlog[SMOOTHSTEP_NSTEPS-1] = ndirty_delta;
+}
+
+static void
+arena_decay_backlog_update(arena_t *arena, uint64_t nadvance_u64)
+{
+
+	if (nadvance_u64 >= SMOOTHSTEP_NSTEPS) {
+		memset(arena->decay.backlog, 0, (SMOOTHSTEP_NSTEPS-1) *
+		    sizeof(size_t));
+	} else {
+		size_t nadvance_z = (size_t)nadvance_u64;
+
+		assert((uint64_t)nadvance_z == nadvance_u64);
+
+		memmove(arena->decay.backlog, &arena->decay.backlog[nadvance_z],
+		    (SMOOTHSTEP_NSTEPS - nadvance_z) * sizeof(size_t));
+		if (nadvance_z > 1) {
+			memset(&arena->decay.backlog[SMOOTHSTEP_NSTEPS -
+			    nadvance_z], 0, (nadvance_z-1) * sizeof(size_t));
+		}
+	}
+
+	arena_decay_backlog_update_last(arena);
+}
+
+static void
+arena_decay_epoch_advance_helper(arena_t *arena, const nstime_t *time)
+{
+	uint64_t nadvance_u64;
+	nstime_t delta;
+
+	assert(opt_purge == purge_mode_decay);
+	assert(arena_decay_deadline_reached(arena, time));
+
+	nstime_copy(&delta, time);
+	nstime_subtract(&delta, &arena->decay.epoch);
+	nadvance_u64 = nstime_divide(&delta, &arena->decay.interval);
+	assert(nadvance_u64 > 0);
+
+	/* Add nadvance_u64 decay intervals to epoch. */
+	nstime_copy(&delta, &arena->decay.interval);
+	nstime_imultiply(&delta, nadvance_u64);
+	nstime_add(&arena->decay.epoch, &delta);
+
+	/* Set a new deadline. */
+	arena_decay_deadline_init(arena);
+
+	/* Update the backlog. */
+	arena_decay_backlog_update(arena, nadvance_u64);
+}
+
+static void
+arena_decay_epoch_advance_purge(tsdn_t *tsdn, arena_t *arena)
+{
+	size_t ndirty_limit = arena_decay_backlog_npages_limit(arena);
+
+	if (arena->ndirty > ndirty_limit)
+		arena_purge_to_limit(tsdn, arena, ndirty_limit);
+	arena->decay.ndirty = arena->ndirty;
+}
+
+static void
+arena_decay_epoch_advance(tsdn_t *tsdn, arena_t *arena, const nstime_t *time)
+{
+
+	arena_decay_epoch_advance_helper(arena, time);
+	arena_decay_epoch_advance_purge(tsdn, arena);
+}
+
+static void
+arena_decay_init(arena_t *arena, ssize_t decay_time)
+{
+
+	arena->decay.time = decay_time;
+	if (decay_time > 0) {
+		nstime_init2(&arena->decay.interval, decay_time, 0);
+		nstime_idivide(&arena->decay.interval, SMOOTHSTEP_NSTEPS);
+	}
+
+	nstime_init(&arena->decay.epoch, 0);
+	nstime_update(&arena->decay.epoch);
+	arena->decay.jitter_state = (uint64_t)(uintptr_t)arena;
+	arena_decay_deadline_init(arena);
+	arena->decay.ndirty = arena->ndirty;
+	memset(arena->decay.backlog, 0, SMOOTHSTEP_NSTEPS * sizeof(size_t));
+}
+
+static bool
+arena_decay_time_valid(ssize_t decay_time)
+{
+
+	if (decay_time < -1)
+		return (false);
+	if (decay_time == -1 || (uint64_t)decay_time <= NSTIME_SEC_MAX)
+		return (true);
+	return (false);
+}
+
+ssize_t
+arena_decay_time_get(tsdn_t *tsdn, arena_t *arena)
+{
+	ssize_t decay_time;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	decay_time = arena->decay.time;
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	return (decay_time);
+}
+
+bool
+arena_decay_time_set(tsdn_t *tsdn, arena_t *arena, ssize_t decay_time)
+{
+
+	if (!arena_decay_time_valid(decay_time))
+		return (true);
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	/*
+	 * 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_time changes are intended to be
+	 * infrequent, either between the {-1, 0, >0} states, or a one-time
+	 * arbitrary change during initial arena configuration.
+	 */
+	arena_decay_init(arena, decay_time);
+	arena_maybe_purge(tsdn, arena);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	return (false);
+}
+
+static void
+arena_maybe_purge_ratio(tsdn_t *tsdn, arena_t *arena)
+{
+
+	assert(opt_purge == purge_mode_ratio);
+
+	/* Don't purge if the option is disabled. */
+	if (arena->lg_dirty_mult < 0)
+		return;
+
+	/*
+	 * Iterate, since preventing recursive purging could otherwise leave too
+	 * many dirty pages.
+	 */
+	while (true) {
+		size_t threshold = (arena->nactive >> arena->lg_dirty_mult);
+		if (threshold < chunk_npages)
+			threshold = chunk_npages;
+		/*
+		 * Don't purge unless the number of purgeable pages exceeds the
+		 * threshold.
+		 */
+		if (arena->ndirty <= threshold)
+			return;
+		arena_purge_to_limit(tsdn, arena, threshold);
+	}
+}
+
+static void
+arena_maybe_purge_decay(tsdn_t *tsdn, arena_t *arena)
+{
+	nstime_t time;
+
+	assert(opt_purge == purge_mode_decay);
+
+	/* Purge all or nothing if the option is disabled. */
+	if (arena->decay.time <= 0) {
+		if (arena->decay.time == 0)
+			arena_purge_to_limit(tsdn, arena, 0);
+		return;
+	}
+
+	nstime_init(&time, 0);
+	nstime_update(&time);
+	if (unlikely(!nstime_monotonic() && nstime_compare(&arena->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(&arena->decay.epoch, &time);
+		arena_decay_deadline_init(arena);
+	} else {
+		/* Verify that time does not go backwards. */
+		assert(nstime_compare(&arena->decay.epoch, &time) <= 0);
+	}
+
+	/*
+	 * 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.
+	 */
+	if (arena_decay_deadline_reached(arena, &time))
+		arena_decay_epoch_advance(tsdn, arena, &time);
+}
+
+void
+arena_maybe_purge(tsdn_t *tsdn, arena_t *arena)
+{
+
+	/* Don't recursively purge. */
+	if (arena->purging)
+		return;
+
+	if (opt_purge == purge_mode_ratio)
+		arena_maybe_purge_ratio(tsdn, arena);
+	else
+		arena_maybe_purge_decay(tsdn, arena);
+}
+
+static size_t
+arena_dirty_count(arena_t *arena)
+{
+	size_t ndirty = 0;
+	arena_runs_dirty_link_t *rdelm;
+	extent_node_t *chunkselm;
+
+	for (rdelm = qr_next(&arena->runs_dirty, rd_link),
+	    chunkselm = qr_next(&arena->chunks_cache, cc_link);
+	    rdelm != &arena->runs_dirty; rdelm = qr_next(rdelm, rd_link)) {
+		size_t npages;
+
+		if (rdelm == &chunkselm->rd) {
+			npages = extent_node_size_get(chunkselm) >> LG_PAGE;
+			chunkselm = qr_next(chunkselm, cc_link);
+		} else {
+			arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(
+			    rdelm);
+			arena_chunk_map_misc_t *miscelm =
+			    arena_rd_to_miscelm(rdelm);
+			size_t pageind = arena_miscelm_to_pageind(miscelm);
+			assert(arena_mapbits_allocated_get(chunk, pageind) ==
+			    0);
+			assert(arena_mapbits_large_get(chunk, pageind) == 0);
+			assert(arena_mapbits_dirty_get(chunk, pageind) != 0);
+			npages = arena_mapbits_unallocated_size_get(chunk,
+			    pageind) >> LG_PAGE;
+		}
+		ndirty += npages;
+	}
+
+	return (ndirty);
+}
+
+static size_t
+arena_stash_dirty(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    size_t ndirty_limit, arena_runs_dirty_link_t *purge_runs_sentinel,
+    extent_node_t *purge_chunks_sentinel)
+{
+	arena_runs_dirty_link_t *rdelm, *rdelm_next;
+	extent_node_t *chunkselm;
+	size_t nstashed = 0;
+
+	/* Stash runs/chunks according to ndirty_limit. */
+	for (rdelm = qr_next(&arena->runs_dirty, rd_link),
+	    chunkselm = qr_next(&arena->chunks_cache, cc_link);
+	    rdelm != &arena->runs_dirty; rdelm = rdelm_next) {
+		size_t npages;
+		rdelm_next = qr_next(rdelm, rd_link);
+
+		if (rdelm == &chunkselm->rd) {
+			extent_node_t *chunkselm_next;
+			size_t sn;
+			bool zero, commit;
+			UNUSED void *chunk;
+
+			npages = extent_node_size_get(chunkselm) >> LG_PAGE;
+			if (opt_purge == purge_mode_decay && arena->ndirty -
+			    (nstashed + npages) < ndirty_limit)
+				break;
+
+			chunkselm_next = qr_next(chunkselm, cc_link);
+			/*
+			 * Allocate.  chunkselm remains valid due to the
+			 * dalloc_node=false argument to chunk_alloc_cache().
+			 */
+			zero = false;
+			commit = false;
+			chunk = chunk_alloc_cache(tsdn, arena, chunk_hooks,
+			    extent_node_addr_get(chunkselm),
+			    extent_node_size_get(chunkselm), chunksize, &sn,
+			    &zero, &commit, false);
+			assert(chunk == extent_node_addr_get(chunkselm));
+			assert(zero == extent_node_zeroed_get(chunkselm));
+			extent_node_dirty_insert(chunkselm, purge_runs_sentinel,
+			    purge_chunks_sentinel);
+			assert(npages == (extent_node_size_get(chunkselm) >>
+			    LG_PAGE));
+			chunkselm = chunkselm_next;
+		} else {
+			arena_chunk_t *chunk =
+			    (arena_chunk_t *)CHUNK_ADDR2BASE(rdelm);
+			arena_chunk_map_misc_t *miscelm =
+			    arena_rd_to_miscelm(rdelm);
+			size_t pageind = arena_miscelm_to_pageind(miscelm);
+			arena_run_t *run = &miscelm->run;
+			size_t run_size =
+			    arena_mapbits_unallocated_size_get(chunk, pageind);
+
+			npages = run_size >> LG_PAGE;
+			if (opt_purge == purge_mode_decay && arena->ndirty -
+			    (nstashed + npages) < ndirty_limit)
+				break;
+
+			assert(pageind + npages <= chunk_npages);
+			assert(arena_mapbits_dirty_get(chunk, pageind) ==
+			    arena_mapbits_dirty_get(chunk, pageind+npages-1));
+
+			/*
+			 * If purging the spare chunk's run, make it available
+			 * prior to allocation.
+			 */
+			if (chunk == arena->spare)
+				arena_chunk_alloc(tsdn, arena);
+
+			/* Temporarily allocate the free dirty run. */
+			arena_run_split_large(arena, run, run_size, false);
+			/* Stash. */
+			if (false)
+				qr_new(rdelm, rd_link); /* Redundant. */
+			else {
+				assert(qr_next(rdelm, rd_link) == rdelm);
+				assert(qr_prev(rdelm, rd_link) == rdelm);
+			}
+			qr_meld(purge_runs_sentinel, rdelm, rd_link);
+		}
+
+		nstashed += npages;
+		if (opt_purge == purge_mode_ratio && arena->ndirty - nstashed <=
+		    ndirty_limit)
+			break;
+	}
+
+	return (nstashed);
+}
+
+static size_t
+arena_purge_stashed(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    arena_runs_dirty_link_t *purge_runs_sentinel,
+    extent_node_t *purge_chunks_sentinel)
+{
+	size_t npurged, nmadvise;
+	arena_runs_dirty_link_t *rdelm;
+	extent_node_t *chunkselm;
+
+	if (config_stats)
+		nmadvise = 0;
+	npurged = 0;
+
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	for (rdelm = qr_next(purge_runs_sentinel, rd_link),
+	    chunkselm = qr_next(purge_chunks_sentinel, cc_link);
+	    rdelm != purge_runs_sentinel; rdelm = qr_next(rdelm, rd_link)) {
+		size_t npages;
+
+		if (rdelm == &chunkselm->rd) {
+			/*
+			 * Don't actually purge the chunk here because 1)
+			 * chunkselm is embedded in the chunk and must remain
+			 * valid, and 2) we deallocate the chunk in
+			 * arena_unstash_purged(), where it is destroyed,
+			 * decommitted, or purged, depending on chunk
+			 * deallocation policy.
+			 */
+			size_t size = extent_node_size_get(chunkselm);
+			npages = size >> LG_PAGE;
+			chunkselm = qr_next(chunkselm, cc_link);
+		} else {
+			size_t pageind, run_size, flag_unzeroed, flags, i;
+			bool decommitted;
+			arena_chunk_t *chunk =
+			    (arena_chunk_t *)CHUNK_ADDR2BASE(rdelm);
+			arena_chunk_map_misc_t *miscelm =
+			    arena_rd_to_miscelm(rdelm);
+			pageind = arena_miscelm_to_pageind(miscelm);
+			run_size = arena_mapbits_large_size_get(chunk, pageind);
+			npages = run_size >> LG_PAGE;
+
+			/*
+			 * If this is the first run purged within chunk, mark
+			 * the chunk as non-huge.  This will prevent all use of
+			 * transparent huge pages for this chunk until the chunk
+			 * as a whole is deallocated.
+			 */
+			if (chunk->hugepage) {
+				pages_nohuge(chunk, chunksize);
+				chunk->hugepage = false;
+			}
+
+			assert(pageind + npages <= chunk_npages);
+			assert(!arena_mapbits_decommitted_get(chunk, pageind));
+			assert(!arena_mapbits_decommitted_get(chunk,
+			    pageind+npages-1));
+			decommitted = !chunk_hooks->decommit(chunk, chunksize,
+			    pageind << LG_PAGE, npages << LG_PAGE, arena->ind);
+			if (decommitted) {
+				flag_unzeroed = 0;
+				flags = CHUNK_MAP_DECOMMITTED;
+			} else {
+				flag_unzeroed = chunk_purge_wrapper(tsdn, arena,
+				    chunk_hooks, chunk, chunksize, pageind <<
+				    LG_PAGE, run_size) ? CHUNK_MAP_UNZEROED : 0;
+				flags = flag_unzeroed;
+			}
+			arena_mapbits_large_set(chunk, pageind+npages-1, 0,
+			    flags);
+			arena_mapbits_large_set(chunk, pageind, run_size,
+			    flags);
+
+			/*
+			 * Set the unzeroed flag for internal pages, now that
+			 * chunk_purge_wrapper() 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 = 1; i < npages-1; i++) {
+				arena_mapbits_internal_set(chunk, pageind+i,
+				    flag_unzeroed);
+			}
+		}
+
+		npurged += npages;
+		if (config_stats)
+			nmadvise++;
+	}
+	malloc_mutex_lock(tsdn, &arena->lock);
+
+	if (config_stats) {
+		arena->stats.nmadvise += nmadvise;
+		arena->stats.purged += npurged;
+	}
+
+	return (npurged);
+}
+
+static void
+arena_unstash_purged(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    arena_runs_dirty_link_t *purge_runs_sentinel,
+    extent_node_t *purge_chunks_sentinel)
+{
+	arena_runs_dirty_link_t *rdelm, *rdelm_next;
+	extent_node_t *chunkselm;
+
+	/* Deallocate chunks/runs. */
+	for (rdelm = qr_next(purge_runs_sentinel, rd_link),
+	    chunkselm = qr_next(purge_chunks_sentinel, cc_link);
+	    rdelm != purge_runs_sentinel; rdelm = rdelm_next) {
+		rdelm_next = qr_next(rdelm, rd_link);
+		if (rdelm == &chunkselm->rd) {
+			extent_node_t *chunkselm_next = qr_next(chunkselm,
+			    cc_link);
+			void *addr = extent_node_addr_get(chunkselm);
+			size_t size = extent_node_size_get(chunkselm);
+			size_t sn = extent_node_sn_get(chunkselm);
+			bool zeroed = extent_node_zeroed_get(chunkselm);
+			bool committed = extent_node_committed_get(chunkselm);
+			extent_node_dirty_remove(chunkselm);
+			arena_node_dalloc(tsdn, arena, chunkselm);
+			chunkselm = chunkselm_next;
+			chunk_dalloc_wrapper(tsdn, arena, chunk_hooks, addr,
+			    size, sn, zeroed, committed);
+		} else {
+			arena_chunk_t *chunk =
+			    (arena_chunk_t *)CHUNK_ADDR2BASE(rdelm);
+			arena_chunk_map_misc_t *miscelm =
+			    arena_rd_to_miscelm(rdelm);
+			size_t pageind = arena_miscelm_to_pageind(miscelm);
+			bool decommitted = (arena_mapbits_decommitted_get(chunk,
+			    pageind) != 0);
+			arena_run_t *run = &miscelm->run;
+			qr_remove(rdelm, rd_link);
+			arena_run_dalloc(tsdn, arena, run, false, true,
+			    decommitted);
+		}
+	}
+}
+
+/*
+ * NB: ndirty_limit is interpreted differently depending on opt_purge:
+ *   - purge_mode_ratio: Purge as few dirty run/chunks as possible to reach the
+ *                       desired state:
+ *                       (arena->ndirty <= ndirty_limit)
+ *   - purge_mode_decay: Purge as many dirty runs/chunks as possible without
+ *                       violating the invariant:
+ *                       (arena->ndirty >= ndirty_limit)
+ */
+static void
+arena_purge_to_limit(tsdn_t *tsdn, arena_t *arena, size_t ndirty_limit)
+{
+	chunk_hooks_t chunk_hooks = chunk_hooks_get(tsdn, arena);
+	size_t npurge, npurged;
+	arena_runs_dirty_link_t purge_runs_sentinel;
+	extent_node_t purge_chunks_sentinel;
+
+	arena->purging = true;
+
+	/*
+	 * Calls to arena_dirty_count() are disabled even for debug builds
+	 * because overhead grows nonlinearly as memory usage increases.
+	 */
+	if (false && config_debug) {
+		size_t ndirty = arena_dirty_count(arena);
+		assert(ndirty == arena->ndirty);
+	}
+	assert(opt_purge != purge_mode_ratio || (arena->nactive >>
+	    arena->lg_dirty_mult) < arena->ndirty || ndirty_limit == 0);
+
+	qr_new(&purge_runs_sentinel, rd_link);
+	extent_node_dirty_linkage_init(&purge_chunks_sentinel);
+
+	npurge = arena_stash_dirty(tsdn, arena, &chunk_hooks, ndirty_limit,
+	    &purge_runs_sentinel, &purge_chunks_sentinel);
+	if (npurge == 0)
+		goto label_return;
+	npurged = arena_purge_stashed(tsdn, arena, &chunk_hooks,
+	    &purge_runs_sentinel, &purge_chunks_sentinel);
+	assert(npurged == npurge);
+	arena_unstash_purged(tsdn, arena, &chunk_hooks, &purge_runs_sentinel,
+	    &purge_chunks_sentinel);
+
+	if (config_stats)
+		arena->stats.npurge++;
+
+label_return:
+	arena->purging = false;
+}
+
+void
+arena_purge(tsdn_t *tsdn, arena_t *arena, bool all)
+{
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (all)
+		arena_purge_to_limit(tsdn, arena, 0);
+	else
+		arena_maybe_purge(tsdn, arena);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+static void
+arena_achunk_prof_reset(tsd_t *tsd, arena_t *arena, arena_chunk_t *chunk)
+{
+	size_t pageind, npages;
+
+	cassert(config_prof);
+	assert(opt_prof);
+
+	/*
+	 * Iterate over the allocated runs and remove profiled allocations from
+	 * the sample set.
+	 */
+	for (pageind = map_bias; pageind < chunk_npages; pageind += npages) {
+		if (arena_mapbits_allocated_get(chunk, pageind) != 0) {
+			if (arena_mapbits_large_get(chunk, pageind) != 0) {
+				void *ptr = (void *)((uintptr_t)chunk + (pageind
+				    << LG_PAGE));
+				size_t usize = isalloc(tsd_tsdn(tsd), ptr,
+				    config_prof);
+
+				prof_free(tsd, ptr, usize);
+				npages = arena_mapbits_large_size_get(chunk,
+				    pageind) >> LG_PAGE;
+			} else {
+				/* Skip small run. */
+				size_t binind = arena_mapbits_binind_get(chunk,
+				    pageind);
+				arena_bin_info_t *bin_info =
+				    &arena_bin_info[binind];
+				npages = bin_info->run_size >> LG_PAGE;
+			}
+		} else {
+			/* Skip unallocated run. */
+			npages = arena_mapbits_unallocated_size_get(chunk,
+			    pageind) >> LG_PAGE;
+		}
+		assert(pageind + npages <= chunk_npages);
+	}
+}
+
+void
+arena_reset(tsd_t *tsd, arena_t *arena)
+{
+	unsigned i;
+	extent_node_t *node;
+
+	/*
+	 * 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.
+	 */
+
+	/* Remove large allocations from prof sample set. */
+	if (config_prof && opt_prof) {
+		ql_foreach(node, &arena->achunks, ql_link) {
+			arena_achunk_prof_reset(tsd, arena,
+			    extent_node_addr_get(node));
+		}
+	}
+
+	/* Reset curruns for large size classes. */
+	if (config_stats) {
+		for (i = 0; i < nlclasses; i++)
+			arena->stats.lstats[i].curruns = 0;
+	}
+
+	/* Huge allocations. */
+	malloc_mutex_lock(tsd_tsdn(tsd), &arena->huge_mtx);
+	for (node = ql_last(&arena->huge, ql_link); node != NULL; node =
+	    ql_last(&arena->huge, ql_link)) {
+		void *ptr = extent_node_addr_get(node);
+		size_t usize;
+
+		malloc_mutex_unlock(tsd_tsdn(tsd), &arena->huge_mtx);
+		if (config_stats || (config_prof && opt_prof))
+			usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+		/* Remove huge allocation from prof sample set. */
+		if (config_prof && opt_prof)
+			prof_free(tsd, ptr, usize);
+		huge_dalloc(tsd_tsdn(tsd), ptr);
+		malloc_mutex_lock(tsd_tsdn(tsd), &arena->huge_mtx);
+		/* Cancel out unwanted effects on stats. */
+		if (config_stats)
+			arena_huge_reset_stats_cancel(arena, usize);
+	}
+	malloc_mutex_unlock(tsd_tsdn(tsd), &arena->huge_mtx);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &arena->lock);
+
+	/* Bins. */
+	for (i = 0; i < NBINS; i++) {
+		arena_bin_t *bin = &arena->bins[i];
+		malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+		bin->runcur = NULL;
+		arena_run_heap_new(&bin->runs);
+		if (config_stats) {
+			bin->stats.curregs = 0;
+			bin->stats.curruns = 0;
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+	}
+
+	/*
+	 * Re-initialize runs_dirty such that the chunks_cache and runs_dirty
+	 * chains directly correspond.
+	 */
+	qr_new(&arena->runs_dirty, rd_link);
+	for (node = qr_next(&arena->chunks_cache, cc_link);
+	    node != &arena->chunks_cache; node = qr_next(node, cc_link)) {
+		qr_new(&node->rd, rd_link);
+		qr_meld(&arena->runs_dirty, &node->rd, rd_link);
+	}
+
+	/* Arena chunks. */
+	for (node = ql_last(&arena->achunks, ql_link); node != NULL; node =
+	    ql_last(&arena->achunks, ql_link)) {
+		ql_remove(&arena->achunks, node, ql_link);
+		arena_chunk_discard(tsd_tsdn(tsd), arena,
+		    extent_node_addr_get(node));
+	}
+
+	/* Spare. */
+	if (arena->spare != NULL) {
+		arena_chunk_discard(tsd_tsdn(tsd), arena, arena->spare);
+		arena->spare = NULL;
+	}
+
+	assert(!arena->purging);
+	arena->nactive = 0;
+
+	for (i = 0; i < NPSIZES; i++)
+		arena_run_heap_new(&arena->runs_avail[i]);
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &arena->lock);
+}
+
+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 flag_decommitted)
+{
+	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 &&
+	    arena_mapbits_decommitted_get(chunk, run_ind+run_pages) ==
+	    flag_decommitted) {
+		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);
+		assert(arena_mapbits_decommitted_get(chunk,
+		    run_ind+run_pages+nrun_pages-1) == flag_decommitted);
+		arena_avail_remove(arena, chunk, run_ind+run_pages, nrun_pages);
+
+		/*
+		 * If the successor is dirty, remove it from the set of dirty
+		 * pages.
+		 */
+		if (flag_dirty != 0) {
+			arena_run_dirty_remove(arena, chunk, run_ind+run_pages,
+			    nrun_pages);
+		}
+
+		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 && arena_mapbits_decommitted_get(chunk, run_ind-1) ==
+	    flag_decommitted) {
+		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;
+
+		/*
+		 * 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);
+		assert(arena_mapbits_decommitted_get(chunk, run_ind) ==
+		    flag_decommitted);
+		arena_avail_remove(arena, chunk, run_ind, prun_pages);
+
+		/*
+		 * If the predecessor is dirty, remove it from the set of dirty
+		 * pages.
+		 */
+		if (flag_dirty != 0) {
+			arena_run_dirty_remove(arena, chunk, run_ind,
+			    prun_pages);
+		}
+
+		size += prun_size;
+		run_pages += prun_pages;
+
+		arena_mapbits_unallocated_size_set(chunk, run_ind, size);
+		arena_mapbits_unallocated_size_set(chunk, run_ind+run_pages-1,
+		    size);
+	}
+
+	*p_size = size;
+	*p_run_ind = run_ind;
+	*p_run_pages = run_pages;
+}
+
+static size_t
+arena_run_size_get(arena_t *arena, arena_chunk_t *chunk, arena_run_t *run,
+    size_t run_ind)
+{
+	size_t size;
+
+	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 {
+		arena_bin_info_t *bin_info = &arena_bin_info[run->binind];
+		size = bin_info->run_size;
+	}
+
+	return (size);
+}
+
+static void
+arena_run_dalloc(tsdn_t *tsdn, arena_t *arena, arena_run_t *run, bool dirty,
+    bool cleaned, bool decommitted)
+{
+	arena_chunk_t *chunk;
+	arena_chunk_map_misc_t *miscelm;
+	size_t size, run_ind, run_pages, flag_dirty, flag_decommitted;
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
+	miscelm = arena_run_to_miscelm(run);
+	run_ind = arena_miscelm_to_pageind(miscelm);
+	assert(run_ind >= map_bias);
+	assert(run_ind < chunk_npages);
+	size = arena_run_size_get(arena, chunk, run, run_ind);
+	run_pages = (size >> LG_PAGE);
+	arena_nactive_sub(arena, run_pages);
+
+	/*
+	 * 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.
+	 */
+	assert(arena_mapbits_dirty_get(chunk, run_ind) ==
+	    arena_mapbits_dirty_get(chunk, run_ind+run_pages-1));
+	if (!cleaned && !decommitted && arena_mapbits_dirty_get(chunk, run_ind)
+	    != 0)
+		dirty = true;
+	flag_dirty = dirty ? CHUNK_MAP_DIRTY : 0;
+	flag_decommitted = decommitted ? CHUNK_MAP_DECOMMITTED : 0;
+
+	/* Mark pages as unallocated in the chunk map. */
+	if (dirty || decommitted) {
+		size_t flags = flag_dirty | flag_decommitted;
+		arena_mapbits_unallocated_set(chunk, run_ind, size, flags);
+		arena_mapbits_unallocated_set(chunk, run_ind+run_pages-1, size,
+		    flags);
+	} 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));
+	}
+
+	arena_run_coalesce(arena, chunk, &size, &run_ind, &run_pages,
+	    flag_dirty, flag_decommitted);
+
+	/* 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));
+	assert(arena_mapbits_decommitted_get(chunk, run_ind) ==
+	    arena_mapbits_decommitted_get(chunk, run_ind+run_pages-1));
+	arena_avail_insert(arena, chunk, run_ind, run_pages);
+
+	if (dirty)
+		arena_run_dirty_insert(arena, chunk, run_ind, run_pages);
+
+	/* Deallocate chunk if it is now completely unused. */
+	if (size == arena_maxrun) {
+		assert(run_ind == map_bias);
+		assert(run_pages == (arena_maxrun >> LG_PAGE));
+		arena_chunk_dalloc(tsdn, arena, chunk);
+	}
+
+	/*
+	 * 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.
+	 */
+	if (dirty)
+		arena_maybe_purge(tsdn, arena);
+}
+
+static void
+arena_run_trim_head(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    arena_run_t *run, size_t oldsize, size_t newsize)
+{
+	arena_chunk_map_misc_t *miscelm = arena_run_to_miscelm(run);
+	size_t pageind = arena_miscelm_to_pageind(miscelm);
+	size_t head_npages = (oldsize - newsize) >> LG_PAGE;
+	size_t flag_dirty = arena_mapbits_dirty_get(chunk, pageind);
+	size_t flag_decommitted = arena_mapbits_decommitted_get(chunk, pageind);
+	size_t flag_unzeroed_mask = (flag_dirty | flag_decommitted) == 0 ?
+	    CHUNK_MAP_UNZEROED : 0;
+
+	assert(oldsize > newsize);
+
+	/*
+	 * 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 |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+	    pageind+head_npages-1)));
+	arena_mapbits_large_set(chunk, pageind, oldsize-newsize, flag_dirty |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk, pageind)));
+
+	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);
+	}
+	arena_mapbits_large_set(chunk, pageind+head_npages, newsize,
+	    flag_dirty | (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+	    pageind+head_npages)));
+
+	arena_run_dalloc(tsdn, arena, run, false, false, (flag_decommitted !=
+	    0));
+}
+
+static void
+arena_run_trim_tail(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    arena_run_t *run, size_t oldsize, size_t newsize, bool dirty)
+{
+	arena_chunk_map_misc_t *miscelm = arena_run_to_miscelm(run);
+	size_t pageind = arena_miscelm_to_pageind(miscelm);
+	size_t head_npages = newsize >> LG_PAGE;
+	size_t flag_dirty = arena_mapbits_dirty_get(chunk, pageind);
+	size_t flag_decommitted = arena_mapbits_decommitted_get(chunk, pageind);
+	size_t flag_unzeroed_mask = (flag_dirty | flag_decommitted) == 0 ?
+	    CHUNK_MAP_UNZEROED : 0;
+	arena_chunk_map_misc_t *tail_miscelm;
+	arena_run_t *tail_run;
+
+	assert(oldsize > newsize);
+
+	/*
+	 * 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.
+	 */
+	assert(arena_mapbits_large_size_get(chunk, pageind) == oldsize);
+	arena_mapbits_large_set(chunk, pageind+head_npages-1, 0, flag_dirty |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+	    pageind+head_npages-1)));
+	arena_mapbits_large_set(chunk, pageind, newsize, flag_dirty |
+	    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk, pageind)));
+
+	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);
+	}
+	arena_mapbits_large_set(chunk, pageind+head_npages, oldsize-newsize,
+	    flag_dirty | (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+	    pageind+head_npages)));
+
+	tail_miscelm = arena_miscelm_get_mutable(chunk, pageind + head_npages);
+	tail_run = &tail_miscelm->run;
+	arena_run_dalloc(tsdn, arena, tail_run, dirty, false, (flag_decommitted
+	    != 0));
+}
+
+static void
+arena_bin_runs_insert(arena_bin_t *bin, arena_run_t *run)
+{
+	arena_chunk_map_misc_t *miscelm = arena_run_to_miscelm(run);
+
+	arena_run_heap_insert(&bin->runs, miscelm);
+}
+
+static arena_run_t *
+arena_bin_nonfull_run_tryget(arena_bin_t *bin)
+{
+	arena_chunk_map_misc_t *miscelm;
+
+	miscelm = arena_run_heap_remove_first(&bin->runs);
+	if (miscelm == NULL)
+		return (NULL);
+	if (config_stats)
+		bin->stats.reruns++;
+
+	return (&miscelm->run);
+}
+
+static arena_run_t *
+arena_bin_nonfull_run_get(tsdn_t *tsdn, arena_t *arena, arena_bin_t *bin)
+{
+	arena_run_t *run;
+	szind_t binind;
+	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. */
+
+	binind = arena_bin_index(arena, bin);
+	bin_info = &arena_bin_info[binind];
+
+	/* Allocate a new run. */
+	malloc_mutex_unlock(tsdn, &bin->lock);
+	/******************************/
+	malloc_mutex_lock(tsdn, &arena->lock);
+	run = arena_run_alloc_small(tsdn, arena, bin_info->run_size, binind);
+	if (run != NULL) {
+		/* Initialize run internals. */
+		run->binind = binind;
+		run->nfree = bin_info->nregs;
+		bitmap_init(run->bitmap, &bin_info->bitmap_info);
+	}
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	/********************************/
+	malloc_mutex_lock(tsdn, &bin->lock);
+	if (run != NULL) {
+		if (config_stats) {
+			bin->stats.nruns++;
+			bin->stats.curruns++;
+		}
+		return (run);
+	}
+
+	/*
+	 * arena_run_alloc_small() 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);
+
+	return (NULL);
+}
+
+/* Re-fill bin->runcur, then call arena_run_reg_alloc(). */
+static void *
+arena_bin_malloc_hard(tsdn_t *tsdn, arena_t *arena, arena_bin_t *bin)
+{
+	szind_t binind;
+	arena_bin_info_t *bin_info;
+	arena_run_t *run;
+
+	binind = arena_bin_index(arena, bin);
+	bin_info = &arena_bin_info[binind];
+	bin->runcur = NULL;
+	run = arena_bin_nonfull_run_get(tsdn, arena, bin);
+	if (bin->runcur != NULL && bin->runcur->nfree > 0) {
+		/*
+		 * Another thread updated runcur while this one ran without the
+		 * bin lock in arena_bin_nonfull_run_get().
+		 */
+		void *ret;
+		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(tsdn, arena, chunk, run,
+				    bin);
+			} else
+				arena_bin_lower_run(arena, run, bin);
+		}
+		return (ret);
+	}
+
+	if (run == NULL)
+		return (NULL);
+
+	bin->runcur = run;
+
+	assert(bin->runcur->nfree > 0);
+
+	return (arena_run_reg_alloc(bin->runcur, bin_info));
+}
+
+void
+arena_tcache_fill_small(tsdn_t *tsdn, arena_t *arena, tcache_bin_t *tbin,
+    szind_t binind, uint64_t prof_accumbytes)
+{
+	unsigned i, nfill;
+	arena_bin_t *bin;
+
+	assert(tbin->ncached == 0);
+
+	if (config_prof && arena_prof_accum(tsdn, arena, prof_accumbytes))
+		prof_idump(tsdn);
+	bin = &arena->bins[binind];
+	malloc_mutex_lock(tsdn, &bin->lock);
+	for (i = 0, nfill = (tcache_bin_info[binind].ncached_max >>
+	    tbin->lg_fill_div); i < nfill; i++) {
+		arena_run_t *run;
+		void *ptr;
+		if ((run = bin->runcur) != NULL && run->nfree > 0)
+			ptr = arena_run_reg_alloc(run, &arena_bin_info[binind]);
+		else
+			ptr = arena_bin_malloc_hard(tsdn, arena, bin);
+		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 && 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 + i) = ptr;
+	}
+	if (config_stats) {
+		bin->stats.nmalloc += i;
+		bin->stats.nrequests += tbin->tstats.nrequests;
+		bin->stats.curregs += i;
+		bin->stats.nfills++;
+		tbin->tstats.nrequests = 0;
+	}
+	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)
+{
+
+	size_t redzone_size = bin_info->redzone_size;
+
+	if (zero) {
+		memset((void *)((uintptr_t)ptr - redzone_size),
+		    JEMALLOC_ALLOC_JUNK, redzone_size);
+		memset((void *)((uintptr_t)ptr + bin_info->reg_size),
+		    JEMALLOC_ALLOC_JUNK, redzone_size);
+	} else {
+		memset((void *)((uintptr_t)ptr - redzone_size),
+		    JEMALLOC_ALLOC_JUNK, bin_info->reg_interval);
+	}
+}
+
+#ifdef JEMALLOC_JET
+#undef arena_redzone_corruption
+#define	arena_redzone_corruption JEMALLOC_N(n_arena_redzone_corruption)
+#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(n_arena_redzone_corruption);
+#endif
+
+static void
+arena_redzones_validate(void *ptr, arena_bin_info_t *bin_info, bool reset)
+{
+	bool error = false;
+
+	if (opt_junk_alloc) {
+		size_t size = bin_info->reg_size;
+		size_t redzone_size = bin_info->redzone_size;
+		size_t i;
+
+		for (i = 1; i <= redzone_size; i++) {
+			uint8_t *byte = (uint8_t *)((uintptr_t)ptr - i);
+			if (*byte != JEMALLOC_ALLOC_JUNK) {
+				error = true;
+				arena_redzone_corruption(ptr, size, false, i,
+				    *byte);
+				if (reset)
+					*byte = JEMALLOC_ALLOC_JUNK;
+			}
+		}
+		for (i = 0; i < redzone_size; i++) {
+			uint8_t *byte = (uint8_t *)((uintptr_t)ptr + size + i);
+			if (*byte != JEMALLOC_ALLOC_JUNK) {
+				error = true;
+				arena_redzone_corruption(ptr, size, true, i,
+				    *byte);
+				if (reset)
+					*byte = JEMALLOC_ALLOC_JUNK;
+			}
+		}
+	}
+
+	if (opt_abort && error)
+		abort();
+}
+
+#ifdef JEMALLOC_JET
+#undef arena_dalloc_junk_small
+#define	arena_dalloc_junk_small JEMALLOC_N(n_arena_dalloc_junk_small)
+#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), JEMALLOC_FREE_JUNK,
+	    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(n_arena_dalloc_junk_small);
+#endif
+
+void
+arena_quarantine_junk_small(void *ptr, size_t usize)
+{
+	szind_t binind;
+	arena_bin_info_t *bin_info;
+	cassert(config_fill);
+	assert(opt_junk_free);
+	assert(opt_quarantine);
+	assert(usize <= SMALL_MAXCLASS);
+
+	binind = size2index(usize);
+	bin_info = &arena_bin_info[binind];
+	arena_redzones_validate(ptr, bin_info, true);
+}
+
+static void *
+arena_malloc_small(tsdn_t *tsdn, arena_t *arena, szind_t binind, bool zero)
+{
+	void *ret;
+	arena_bin_t *bin;
+	size_t usize;
+	arena_run_t *run;
+
+	assert(binind < NBINS);
+	bin = &arena->bins[binind];
+	usize = index2size(binind);
+
+	malloc_mutex_lock(tsdn, &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(tsdn, arena, bin);
+
+	if (ret == NULL) {
+		malloc_mutex_unlock(tsdn, &bin->lock);
+		return (NULL);
+	}
+
+	if (config_stats) {
+		bin->stats.nmalloc++;
+		bin->stats.nrequests++;
+		bin->stats.curregs++;
+	}
+	malloc_mutex_unlock(tsdn, &bin->lock);
+	if (config_prof && !isthreaded && arena_prof_accum(tsdn, arena, usize))
+		prof_idump(tsdn);
+
+	if (!zero) {
+		if (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);
+		}
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, usize);
+	} else {
+		if (config_fill && unlikely(opt_junk_alloc)) {
+			arena_alloc_junk_small(ret, &arena_bin_info[binind],
+			    true);
+		}
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, usize);
+		memset(ret, 0, usize);
+	}
+
+	arena_decay_tick(tsdn, arena);
+	return (ret);
+}
+
+void *
+arena_malloc_large(tsdn_t *tsdn, arena_t *arena, szind_t binind, bool zero)
+{
+	void *ret;
+	size_t usize;
+	uintptr_t random_offset;
+	arena_run_t *run;
+	arena_chunk_map_misc_t *miscelm;
+	UNUSED bool idump JEMALLOC_CC_SILENCE_INIT(false);
+
+	/* Large allocation. */
+	usize = index2size(binind);
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (config_cache_oblivious) {
+		uint64_t r;
+
+		/*
+		 * Compute a uniformly distributed offset within the first page
+		 * that is a multiple of the cacheline size, e.g. [0 .. 63) * 64
+		 * for 4 KiB pages and 64-byte cachelines.
+		 */
+		r = prng_lg_range_zu(&arena->offset_state, LG_PAGE -
+		    LG_CACHELINE, false);
+		random_offset = ((uintptr_t)r) << LG_CACHELINE;
+	} else
+		random_offset = 0;
+	run = arena_run_alloc_large(tsdn, arena, usize + large_pad, zero);
+	if (run == NULL) {
+		malloc_mutex_unlock(tsdn, &arena->lock);
+		return (NULL);
+	}
+	miscelm = arena_run_to_miscelm(run);
+	ret = (void *)((uintptr_t)arena_miscelm_to_rpages(miscelm) +
+	    random_offset);
+	if (config_stats) {
+		szind_t index = binind - NBINS;
+
+		arena->stats.nmalloc_large++;
+		arena->stats.nrequests_large++;
+		arena->stats.allocated_large += usize;
+		arena->stats.lstats[index].nmalloc++;
+		arena->stats.lstats[index].nrequests++;
+		arena->stats.lstats[index].curruns++;
+	}
+	if (config_prof)
+		idump = arena_prof_accum_locked(arena, usize);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	if (config_prof && idump)
+		prof_idump(tsdn);
+
+	if (!zero) {
+		if (config_fill) {
+			if (unlikely(opt_junk_alloc))
+				memset(ret, JEMALLOC_ALLOC_JUNK, usize);
+			else if (unlikely(opt_zero))
+				memset(ret, 0, usize);
+		}
+	}
+
+	arena_decay_tick(tsdn, arena);
+	return (ret);
+}
+
+void *
+arena_malloc_hard(tsdn_t *tsdn, arena_t *arena, size_t size, szind_t ind,
+    bool zero)
+{
+
+	assert(!tsdn_null(tsdn) || arena != NULL);
+
+	if (likely(!tsdn_null(tsdn)))
+		arena = arena_choose(tsdn_tsd(tsdn), arena);
+	if (unlikely(arena == NULL))
+		return (NULL);
+
+	if (likely(size <= SMALL_MAXCLASS))
+		return (arena_malloc_small(tsdn, arena, ind, zero));
+	if (likely(size <= large_maxclass))
+		return (arena_malloc_large(tsdn, arena, ind, zero));
+	return (huge_malloc(tsdn, arena, index2size(ind), zero));
+}
+
+/* Only handles large allocations that require more than page alignment. */
+static void *
+arena_palloc_large(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero)
+{
+	void *ret;
+	size_t alloc_size, leadsize, trailsize;
+	arena_run_t *run;
+	arena_chunk_t *chunk;
+	arena_chunk_map_misc_t *miscelm;
+	void *rpages;
+
+	assert(!tsdn_null(tsdn) || arena != NULL);
+	assert(usize == PAGE_CEILING(usize));
+
+	if (likely(!tsdn_null(tsdn)))
+		arena = arena_choose(tsdn_tsd(tsdn), arena);
+	if (unlikely(arena == NULL))
+		return (NULL);
+
+	alignment = PAGE_CEILING(alignment);
+	alloc_size = usize + large_pad + alignment - PAGE;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	run = arena_run_alloc_large(tsdn, arena, alloc_size, false);
+	if (run == NULL) {
+		malloc_mutex_unlock(tsdn, &arena->lock);
+		return (NULL);
+	}
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(run);
+	miscelm = arena_run_to_miscelm(run);
+	rpages = arena_miscelm_to_rpages(miscelm);
+
+	leadsize = ALIGNMENT_CEILING((uintptr_t)rpages, alignment) -
+	    (uintptr_t)rpages;
+	assert(alloc_size >= leadsize + usize);
+	trailsize = alloc_size - leadsize - usize - large_pad;
+	if (leadsize != 0) {
+		arena_chunk_map_misc_t *head_miscelm = miscelm;
+		arena_run_t *head_run = run;
+
+		miscelm = arena_miscelm_get_mutable(chunk,
+		    arena_miscelm_to_pageind(head_miscelm) + (leadsize >>
+		    LG_PAGE));
+		run = &miscelm->run;
+
+		arena_run_trim_head(tsdn, arena, chunk, head_run, alloc_size,
+		    alloc_size - leadsize);
+	}
+	if (trailsize != 0) {
+		arena_run_trim_tail(tsdn, arena, chunk, run, usize + large_pad +
+		    trailsize, usize + large_pad, false);
+	}
+	if (arena_run_init_large(arena, run, usize + large_pad, zero)) {
+		size_t run_ind =
+		    arena_miscelm_to_pageind(arena_run_to_miscelm(run));
+		bool dirty = (arena_mapbits_dirty_get(chunk, run_ind) != 0);
+		bool decommitted = (arena_mapbits_decommitted_get(chunk,
+		    run_ind) != 0);
+
+		assert(decommitted); /* Cause of OOM. */
+		arena_run_dalloc(tsdn, arena, run, dirty, false, decommitted);
+		malloc_mutex_unlock(tsdn, &arena->lock);
+		return (NULL);
+	}
+	ret = arena_miscelm_to_rpages(miscelm);
+
+	if (config_stats) {
+		szind_t index = size2index(usize) - NBINS;
+
+		arena->stats.nmalloc_large++;
+		arena->stats.nrequests_large++;
+		arena->stats.allocated_large += usize;
+		arena->stats.lstats[index].nmalloc++;
+		arena->stats.lstats[index].nrequests++;
+		arena->stats.lstats[index].curruns++;
+	}
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	if (config_fill && !zero) {
+		if (unlikely(opt_junk_alloc))
+			memset(ret, JEMALLOC_ALLOC_JUNK, usize);
+		else if (unlikely(opt_zero))
+			memset(ret, 0, usize);
+	}
+	arena_decay_tick(tsdn, arena);
+	return (ret);
+}
+
+void *
+arena_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero, tcache_t *tcache)
+{
+	void *ret;
+
+	if (usize <= SMALL_MAXCLASS && (alignment < PAGE || (alignment == PAGE
+	    && (usize & PAGE_MASK) == 0))) {
+		/* Small; alignment doesn't require special run placement. */
+		ret = arena_malloc(tsdn, arena, usize, size2index(usize), zero,
+		    tcache, true);
+	} else if (usize <= large_maxclass && alignment <= PAGE) {
+		/*
+		 * Large; alignment doesn't require special run placement.
+		 * However, the cached pointer may be at a random offset from
+		 * the base of the run, so do some bit manipulation to retrieve
+		 * the base.
+		 */
+		ret = arena_malloc(tsdn, arena, usize, size2index(usize), zero,
+		    tcache, true);
+		if (config_cache_oblivious)
+			ret = (void *)((uintptr_t)ret & ~PAGE_MASK);
+	} else {
+		if (likely(usize <= large_maxclass)) {
+			ret = arena_palloc_large(tsdn, arena, usize, alignment,
+			    zero);
+		} else if (likely(alignment <= chunksize))
+			ret = huge_malloc(tsdn, arena, usize, zero);
+		else {
+			ret = huge_palloc(tsdn, arena, usize, alignment, zero);
+		}
+	}
+	return (ret);
+}
+
+void
+arena_prof_promoted(tsdn_t *tsdn, const void *ptr, size_t size)
+{
+	arena_chunk_t *chunk;
+	size_t pageind;
+	szind_t binind;
+
+	cassert(config_prof);
+	assert(ptr != NULL);
+	assert(CHUNK_ADDR2BASE(ptr) != ptr);
+	assert(isalloc(tsdn, ptr, false) == LARGE_MINCLASS);
+	assert(isalloc(tsdn, ptr, true) == LARGE_MINCLASS);
+	assert(size <= SMALL_MAXCLASS);
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+	pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+	binind = size2index(size);
+	assert(binind < NBINS);
+	arena_mapbits_large_binind_set(chunk, pageind, binind);
+
+	assert(isalloc(tsdn, ptr, false) == LARGE_MINCLASS);
+	assert(isalloc(tsdn, ptr, true) == size);
+}
+
+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 {
+		szind_t binind = arena_bin_index(extent_node_arena_get(
+		    &chunk->node), bin);
+		arena_bin_info_t *bin_info = &arena_bin_info[binind];
+
+		/*
+		 * The following block's conditional is necessary because if the
+		 * run only contains one region, then it never gets inserted
+		 * into the non-full runs tree.
+		 */
+		if (bin_info->nregs != 1) {
+			arena_chunk_map_misc_t *miscelm =
+			    arena_run_to_miscelm(run);
+
+			arena_run_heap_remove(&bin->runs, miscelm);
+		}
+	}
+}
+
+static void
+arena_dalloc_bin_run(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    arena_run_t *run, arena_bin_t *bin)
+{
+
+	assert(run != bin->runcur);
+
+	malloc_mutex_unlock(tsdn, &bin->lock);
+	/******************************/
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena_run_dalloc(tsdn, arena, run, true, false, false);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	/****************************/
+	malloc_mutex_lock(tsdn, &bin->lock);
+	if (config_stats)
+		bin->stats.curruns--;
+}
+
+static void
+arena_bin_lower_run(arena_t *arena, arena_run_t *run, arena_bin_t *bin)
+{
+
+	/*
+	 * Make sure that if bin->runcur is non-NULL, it refers to the
+	 * oldest/lowest non-full run.  It is okay to NULL runcur out rather
+	 * than proactively keeping it pointing at the oldest/lowest non-full
+	 * run.
+	 */
+	if (bin->runcur != NULL &&
+	    arena_snad_comp(arena_run_to_miscelm(bin->runcur),
+	    arena_run_to_miscelm(run)) > 0) {
+		/* 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);
+}
+
+static void
+arena_dalloc_bin_locked_impl(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    void *ptr, arena_chunk_map_bits_t *bitselm, bool junked)
+{
+	size_t pageind, rpages_ind;
+	arena_run_t *run;
+	arena_bin_t *bin;
+	arena_bin_info_t *bin_info;
+	szind_t binind;
+
+	pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+	rpages_ind = pageind - arena_mapbits_small_runind_get(chunk, pageind);
+	run = &arena_miscelm_get_mutable(chunk, rpages_ind)->run;
+	binind = run->binind;
+	bin = &arena->bins[binind];
+	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(tsdn, arena, chunk, run, bin);
+	} else if (run->nfree == 1 && run != bin->runcur)
+		arena_bin_lower_run(arena, run, bin);
+
+	if (config_stats) {
+		bin->stats.ndalloc++;
+		bin->stats.curregs--;
+	}
+}
+
+void
+arena_dalloc_bin_junked_locked(tsdn_t *tsdn, arena_t *arena,
+    arena_chunk_t *chunk, void *ptr, arena_chunk_map_bits_t *bitselm)
+{
+
+	arena_dalloc_bin_locked_impl(tsdn, arena, chunk, ptr, bitselm, true);
+}
+
+void
+arena_dalloc_bin(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk, void *ptr,
+    size_t pageind, arena_chunk_map_bits_t *bitselm)
+{
+	arena_run_t *run;
+	arena_bin_t *bin;
+	size_t rpages_ind;
+
+	rpages_ind = pageind - arena_mapbits_small_runind_get(chunk, pageind);
+	run = &arena_miscelm_get_mutable(chunk, rpages_ind)->run;
+	bin = &arena->bins[run->binind];
+	malloc_mutex_lock(tsdn, &bin->lock);
+	arena_dalloc_bin_locked_impl(tsdn, arena, chunk, ptr, bitselm, false);
+	malloc_mutex_unlock(tsdn, &bin->lock);
+}
+
+void
+arena_dalloc_small(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    void *ptr, size_t pageind)
+{
+	arena_chunk_map_bits_t *bitselm;
+
+	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);
+	}
+	bitselm = arena_bitselm_get_mutable(chunk, pageind);
+	arena_dalloc_bin(tsdn, arena, chunk, ptr, pageind, bitselm);
+	arena_decay_tick(tsdn, arena);
+}
+
+#ifdef JEMALLOC_JET
+#undef arena_dalloc_junk_large
+#define	arena_dalloc_junk_large JEMALLOC_N(n_arena_dalloc_junk_large)
+#endif
+void
+arena_dalloc_junk_large(void *ptr, size_t usize)
+{
+
+	if (config_fill && unlikely(opt_junk_free))
+		memset(ptr, JEMALLOC_FREE_JUNK, 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(n_arena_dalloc_junk_large);
+#endif
+
+static void
+arena_dalloc_large_locked_impl(tsdn_t *tsdn, arena_t *arena,
+    arena_chunk_t *chunk, void *ptr, bool junked)
+{
+	size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+	arena_chunk_map_misc_t *miscelm = arena_miscelm_get_mutable(chunk,
+	    pageind);
+	arena_run_t *run = &miscelm->run;
+
+	if (config_fill || config_stats) {
+		size_t usize = arena_mapbits_large_size_get(chunk, pageind) -
+		    large_pad;
+
+		if (!junked)
+			arena_dalloc_junk_large(ptr, usize);
+		if (config_stats) {
+			szind_t index = size2index(usize) - NBINS;
+
+			arena->stats.ndalloc_large++;
+			arena->stats.allocated_large -= usize;
+			arena->stats.lstats[index].ndalloc++;
+			arena->stats.lstats[index].curruns--;
+		}
+	}
+
+	arena_run_dalloc(tsdn, arena, run, true, false, false);
+}
+
+void
+arena_dalloc_large_junked_locked(tsdn_t *tsdn, arena_t *arena,
+    arena_chunk_t *chunk, void *ptr)
+{
+
+	arena_dalloc_large_locked_impl(tsdn, arena, chunk, ptr, true);
+}
+
+void
+arena_dalloc_large(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    void *ptr)
+{
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena_dalloc_large_locked_impl(tsdn, arena, chunk, ptr, false);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	arena_decay_tick(tsdn, arena);
+}
+
+static void
+arena_ralloc_large_shrink(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    void *ptr, size_t oldsize, size_t size)
+{
+	size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+	arena_chunk_map_misc_t *miscelm = arena_miscelm_get_mutable(chunk,
+	    pageind);
+	arena_run_t *run = &miscelm->run;
+
+	assert(size < oldsize);
+
+	/*
+	 * Shrink the run, and make trailing pages available for other
+	 * allocations.
+	 */
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena_run_trim_tail(tsdn, arena, chunk, run, oldsize + large_pad, size +
+	    large_pad, true);
+	if (config_stats) {
+		szind_t oldindex = size2index(oldsize) - NBINS;
+		szind_t index = size2index(size) - NBINS;
+
+		arena->stats.ndalloc_large++;
+		arena->stats.allocated_large -= oldsize;
+		arena->stats.lstats[oldindex].ndalloc++;
+		arena->stats.lstats[oldindex].curruns--;
+
+		arena->stats.nmalloc_large++;
+		arena->stats.nrequests_large++;
+		arena->stats.allocated_large += size;
+		arena->stats.lstats[index].nmalloc++;
+		arena->stats.lstats[index].nrequests++;
+		arena->stats.lstats[index].curruns++;
+	}
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+static bool
+arena_ralloc_large_grow(tsdn_t *tsdn, arena_t *arena, arena_chunk_t *chunk,
+    void *ptr, size_t oldsize, size_t usize_min, size_t usize_max, bool zero)
+{
+	size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+	size_t npages = (oldsize + large_pad) >> LG_PAGE;
+	size_t followsize;
+
+	assert(oldsize == arena_mapbits_large_size_get(chunk, pageind) -
+	    large_pad);
+
+	/* Try to extend the run. */
+	malloc_mutex_lock(tsdn, &arena->lock);
+	if (pageind+npages >= chunk_npages || arena_mapbits_allocated_get(chunk,
+	    pageind+npages) != 0)
+		goto label_fail;
+	followsize = arena_mapbits_unallocated_size_get(chunk, pageind+npages);
+	if (oldsize + followsize >= usize_min) {
+		/*
+		 * The next run is available and sufficiently large.  Split the
+		 * following run, then merge the first part with the existing
+		 * allocation.
+		 */
+		arena_run_t *run;
+		size_t usize, splitsize, size, flag_dirty, flag_unzeroed_mask;
+
+		usize = usize_max;
+		while (oldsize + followsize < usize)
+			usize = index2size(size2index(usize)-1);
+		assert(usize >= usize_min);
+		assert(usize >= oldsize);
+		splitsize = usize - oldsize;
+		if (splitsize == 0)
+			goto label_fail;
+
+		run = &arena_miscelm_get_mutable(chunk, pageind+npages)->run;
+		if (arena_run_split_large(arena, run, splitsize, zero))
+			goto label_fail;
+
+		if (config_cache_oblivious && zero) {
+			/*
+			 * 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 run is a multiple of
+			 * CACHELINE in [0 .. PAGE).
+			 */
+			void *zbase = (void *)((uintptr_t)ptr + oldsize);
+			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);
+		}
+
+		size = oldsize + splitsize;
+		npages = (size + large_pad) >> 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);
+		flag_unzeroed_mask = flag_dirty == 0 ? CHUNK_MAP_UNZEROED : 0;
+		arena_mapbits_large_set(chunk, pageind, size + large_pad,
+		    flag_dirty | (flag_unzeroed_mask &
+		    arena_mapbits_unzeroed_get(chunk, pageind)));
+		arena_mapbits_large_set(chunk, pageind+npages-1, 0, flag_dirty |
+		    (flag_unzeroed_mask & arena_mapbits_unzeroed_get(chunk,
+		    pageind+npages-1)));
+
+		if (config_stats) {
+			szind_t oldindex = size2index(oldsize) - NBINS;
+			szind_t index = size2index(size) - NBINS;
+
+			arena->stats.ndalloc_large++;
+			arena->stats.allocated_large -= oldsize;
+			arena->stats.lstats[oldindex].ndalloc++;
+			arena->stats.lstats[oldindex].curruns--;
+
+			arena->stats.nmalloc_large++;
+			arena->stats.nrequests_large++;
+			arena->stats.allocated_large += size;
+			arena->stats.lstats[index].nmalloc++;
+			arena->stats.lstats[index].nrequests++;
+			arena->stats.lstats[index].curruns++;
+		}
+		malloc_mutex_unlock(tsdn, &arena->lock);
+		return (false);
+	}
+label_fail:
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	return (true);
+}
+
+#ifdef JEMALLOC_JET
+#undef arena_ralloc_junk_large
+#define	arena_ralloc_junk_large JEMALLOC_N(n_arena_ralloc_junk_large)
+#endif
+static void
+arena_ralloc_junk_large(void *ptr, size_t old_usize, size_t usize)
+{
+
+	if (config_fill && unlikely(opt_junk_free)) {
+		memset((void *)((uintptr_t)ptr + usize), JEMALLOC_FREE_JUNK,
+		    old_usize - usize);
+	}
+}
+#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(n_arena_ralloc_junk_large);
+#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(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t usize_min,
+    size_t usize_max, bool zero)
+{
+	arena_chunk_t *chunk;
+	arena_t *arena;
+
+	if (oldsize == usize_max) {
+		/* Current size class is compatible and maximal. */
+		return (false);
+	}
+
+	chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+	arena = extent_node_arena_get(&chunk->node);
+
+	if (oldsize < usize_max) {
+		bool ret = arena_ralloc_large_grow(tsdn, arena, chunk, ptr,
+		    oldsize, usize_min, usize_max, zero);
+		if (config_fill && !ret && !zero) {
+			if (unlikely(opt_junk_alloc)) {
+				memset((void *)((uintptr_t)ptr + oldsize),
+				    JEMALLOC_ALLOC_JUNK,
+				    isalloc(tsdn, ptr, config_prof) - oldsize);
+			} else if (unlikely(opt_zero)) {
+				memset((void *)((uintptr_t)ptr + oldsize), 0,
+				    isalloc(tsdn, ptr, config_prof) - oldsize);
+			}
+		}
+		return (ret);
+	}
+
+	assert(oldsize > usize_max);
+	/* Fill before shrinking in order avoid a race. */
+	arena_ralloc_junk_large(ptr, oldsize, usize_max);
+	arena_ralloc_large_shrink(tsdn, arena, chunk, ptr, oldsize, usize_max);
+	return (false);
+}
+
+bool
+arena_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t size,
+    size_t extra, bool zero)
+{
+	size_t usize_min, usize_max;
+
+	/* Calls with non-zero extra had to clamp extra. */
+	assert(extra == 0 || size + extra <= HUGE_MAXCLASS);
+
+	if (unlikely(size > HUGE_MAXCLASS))
+		return (true);
+
+	usize_min = s2u(size);
+	usize_max = s2u(size + extra);
+	if (likely(oldsize <= large_maxclass && usize_min <= large_maxclass)) {
+		arena_chunk_t *chunk;
+
+		/*
+		 * Avoid moving the allocation if the size class can be left the
+		 * same.
+		 */
+		if (oldsize <= SMALL_MAXCLASS) {
+			assert(arena_bin_info[size2index(oldsize)].reg_size ==
+			    oldsize);
+			if ((usize_max > SMALL_MAXCLASS ||
+			    size2index(usize_max) != size2index(oldsize)) &&
+			    (size > oldsize || usize_max < oldsize))
+				return (true);
+		} else {
+			if (usize_max <= SMALL_MAXCLASS)
+				return (true);
+			if (arena_ralloc_large(tsdn, ptr, oldsize, usize_min,
+			    usize_max, zero))
+				return (true);
+		}
+
+		chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+		arena_decay_tick(tsdn, extent_node_arena_get(&chunk->node));
+		return (false);
+	} else {
+		return (huge_ralloc_no_move(tsdn, ptr, oldsize, usize_min,
+		    usize_max, zero));
+	}
+}
+
+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, size2index(usize),
+		    zero, tcache, true));
+	usize = sa2u(usize, alignment);
+	if (unlikely(usize == 0 || usize > HUGE_MAXCLASS))
+		return (NULL);
+	return (ipalloct(tsdn, usize, alignment, zero, tcache, arena));
+}
+
+void *
+arena_ralloc(tsd_t *tsd, arena_t *arena, void *ptr, size_t oldsize, size_t size,
+    size_t alignment, bool zero, tcache_t *tcache)
+{
+	void *ret;
+	size_t usize;
+
+	usize = s2u(size);
+	if (unlikely(usize == 0 || size > HUGE_MAXCLASS))
+		return (NULL);
+
+	if (likely(usize <= large_maxclass)) {
+		size_t copysize;
+
+		/* Try to avoid moving the allocation. */
+		if (!arena_ralloc_no_move(tsd_tsdn(tsd), ptr, oldsize, usize, 0,
+		    zero))
+			return (ptr);
+
+		/*
+		 * size and oldsize are different enough that we need to move
+		 * the object.  In that case, fall back to allocating new space
+		 * and copying.
+		 */
+		ret = arena_ralloc_move_helper(tsd_tsdn(tsd), arena, usize,
+		    alignment, zero, tcache);
+		if (ret == NULL)
+			return (NULL);
+
+		/*
+		 * Junk/zero-filling were already done by
+		 * ipalloc()/arena_malloc().
+		 */
+
+		copysize = (usize < oldsize) ? usize : oldsize;
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, copysize);
+		memcpy(ret, ptr, copysize);
+		isqalloc(tsd, ptr, oldsize, tcache, true);
+	} else {
+		ret = huge_ralloc(tsd, arena, ptr, oldsize, usize, alignment,
+		    zero, tcache);
+	}
+	return (ret);
+}
+
+dss_prec_t
+arena_dss_prec_get(tsdn_t *tsdn, arena_t *arena)
+{
+	dss_prec_t ret;
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	ret = arena->dss_prec;
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	return (ret);
+}
+
+bool
+arena_dss_prec_set(tsdn_t *tsdn, arena_t *arena, dss_prec_t dss_prec)
+{
+
+	if (!have_dss)
+		return (dss_prec != dss_prec_disabled);
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena->dss_prec = dss_prec;
+	malloc_mutex_unlock(tsdn, &arena->lock);
+	return (false);
+}
+
+ssize_t
+arena_lg_dirty_mult_default_get(void)
+{
+
+	return ((ssize_t)atomic_read_z((size_t *)&lg_dirty_mult_default));
+}
+
+bool
+arena_lg_dirty_mult_default_set(ssize_t lg_dirty_mult)
+{
+
+	if (opt_purge != purge_mode_ratio)
+		return (true);
+	if (!arena_lg_dirty_mult_valid(lg_dirty_mult))
+		return (true);
+	atomic_write_z((size_t *)&lg_dirty_mult_default, (size_t)lg_dirty_mult);
+	return (false);
+}
+
+ssize_t
+arena_decay_time_default_get(void)
+{
+
+	return ((ssize_t)atomic_read_z((size_t *)&decay_time_default));
+}
+
+bool
+arena_decay_time_default_set(ssize_t decay_time)
+{
+
+	if (opt_purge != purge_mode_decay)
+		return (true);
+	if (!arena_decay_time_valid(decay_time))
+		return (true);
+	atomic_write_z((size_t *)&decay_time_default, (size_t)decay_time);
+	return (false);
+}
+
+static void
+arena_basic_stats_merge_locked(arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *lg_dirty_mult, ssize_t *decay_time,
+    size_t *nactive, size_t *ndirty)
+{
+
+	*nthreads += arena_nthreads_get(arena, false);
+	*dss = dss_prec_names[arena->dss_prec];
+	*lg_dirty_mult = arena->lg_dirty_mult;
+	*decay_time = arena->decay.time;
+	*nactive += arena->nactive;
+	*ndirty += arena->ndirty;
+}
+
+void
+arena_basic_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *lg_dirty_mult, ssize_t *decay_time,
+    size_t *nactive, size_t *ndirty)
+{
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena_basic_stats_merge_locked(arena, nthreads, dss, lg_dirty_mult,
+	    decay_time, nactive, ndirty);
+	malloc_mutex_unlock(tsdn, &arena->lock);
+}
+
+void
+arena_stats_merge(tsdn_t *tsdn, arena_t *arena, unsigned *nthreads,
+    const char **dss, ssize_t *lg_dirty_mult, ssize_t *decay_time,
+    size_t *nactive, size_t *ndirty, arena_stats_t *astats,
+    malloc_bin_stats_t *bstats, malloc_large_stats_t *lstats,
+    malloc_huge_stats_t *hstats)
+{
+	unsigned i;
+
+	cassert(config_stats);
+
+	malloc_mutex_lock(tsdn, &arena->lock);
+	arena_basic_stats_merge_locked(arena, nthreads, dss, lg_dirty_mult,
+	    decay_time, nactive, ndirty);
+
+	astats->mapped += arena->stats.mapped;
+	astats->retained += arena->stats.retained;
+	astats->npurge += arena->stats.npurge;
+	astats->nmadvise += arena->stats.nmadvise;
+	astats->purged += arena->stats.purged;
+	astats->metadata_mapped += arena->stats.metadata_mapped;
+	astats->metadata_allocated += arena_metadata_allocated_get(arena);
+	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;
+	astats->allocated_huge += arena->stats.allocated_huge;
+	astats->nmalloc_huge += arena->stats.nmalloc_huge;
+	astats->ndalloc_huge += arena->stats.ndalloc_huge;
+
+	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;
+	}
+
+	for (i = 0; i < nhclasses; i++) {
+		hstats[i].nmalloc += arena->stats.hstats[i].nmalloc;
+		hstats[i].ndalloc += arena->stats.hstats[i].ndalloc;
+		hstats[i].curhchunks += arena->stats.hstats[i].curhchunks;
+	}
+	malloc_mutex_unlock(tsdn, &arena->lock);
+
+	for (i = 0; i < NBINS; i++) {
+		arena_bin_t *bin = &arena->bins[i];
+
+		malloc_mutex_lock(tsdn, &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;
+		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(tsdn, &bin->lock);
+	}
+}
+
+unsigned
+arena_nthreads_get(arena_t *arena, bool internal)
+{
+
+	return (atomic_read_u(&arena->nthreads[internal]));
+}
+
+void
+arena_nthreads_inc(arena_t *arena, bool internal)
+{
+
+	atomic_add_u(&arena->nthreads[internal], 1);
+}
+
+void
+arena_nthreads_dec(arena_t *arena, bool internal)
+{
+
+	atomic_sub_u(&arena->nthreads[internal], 1);
+}
+
+size_t
+arena_extent_sn_next(arena_t *arena)
+{
+
+	return (atomic_add_z(&arena->extent_sn_next, 1) - 1);
+}
+
+arena_t *
+arena_new(tsdn_t *tsdn, unsigned ind)
+{
+	arena_t *arena;
+	unsigned i;
+
+	/*
+	 * Allocate arena, arena->lstats, and arena->hstats contiguously, mainly
+	 * because there is no way to clean up if base_alloc() OOMs.
+	 */
+	if (config_stats) {
+		arena = (arena_t *)base_alloc(tsdn,
+		    CACHELINE_CEILING(sizeof(arena_t)) +
+		    QUANTUM_CEILING((nlclasses * sizeof(malloc_large_stats_t)))
+		    + (nhclasses * sizeof(malloc_huge_stats_t)));
+	} else
+		arena = (arena_t *)base_alloc(tsdn, sizeof(arena_t));
+	if (arena == NULL)
+		return (NULL);
+
+	arena->ind = ind;
+	arena->nthreads[0] = arena->nthreads[1] = 0;
+	if (malloc_mutex_init(&arena->lock, "arena", WITNESS_RANK_ARENA))
+		return (NULL);
+
+	if (config_stats) {
+		memset(&arena->stats, 0, sizeof(arena_stats_t));
+		arena->stats.lstats = (malloc_large_stats_t *)((uintptr_t)arena
+		    + CACHELINE_CEILING(sizeof(arena_t)));
+		memset(arena->stats.lstats, 0, nlclasses *
+		    sizeof(malloc_large_stats_t));
+		arena->stats.hstats = (malloc_huge_stats_t *)((uintptr_t)arena
+		    + CACHELINE_CEILING(sizeof(arena_t)) +
+		    QUANTUM_CEILING(nlclasses * sizeof(malloc_large_stats_t)));
+		memset(arena->stats.hstats, 0, nhclasses *
+		    sizeof(malloc_huge_stats_t));
+		if (config_tcache)
+			ql_new(&arena->tcache_ql);
+	}
+
+	if (config_prof)
+		arena->prof_accumbytes = 0;
+
+	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.
+		 */
+		arena->offset_state = config_debug ? ind :
+		    (size_t)(uintptr_t)arena;
+	}
+
+	arena->dss_prec = chunk_dss_prec_get();
+
+	ql_new(&arena->achunks);
+
+	arena->extent_sn_next = 0;
+
+	arena->spare = NULL;
+
+	arena->lg_dirty_mult = arena_lg_dirty_mult_default_get();
+	arena->purging = false;
+	arena->nactive = 0;
+	arena->ndirty = 0;
+
+	for (i = 0; i < NPSIZES; i++)
+		arena_run_heap_new(&arena->runs_avail[i]);
+
+	qr_new(&arena->runs_dirty, rd_link);
+	qr_new(&arena->chunks_cache, cc_link);
+
+	if (opt_purge == purge_mode_decay)
+		arena_decay_init(arena, arena_decay_time_default_get());
+
+	ql_new(&arena->huge);
+	if (malloc_mutex_init(&arena->huge_mtx, "arena_huge",
+	    WITNESS_RANK_ARENA_HUGE))
+		return (NULL);
+
+	extent_tree_szsnad_new(&arena->chunks_szsnad_cached);
+	extent_tree_ad_new(&arena->chunks_ad_cached);
+	extent_tree_szsnad_new(&arena->chunks_szsnad_retained);
+	extent_tree_ad_new(&arena->chunks_ad_retained);
+	if (malloc_mutex_init(&arena->chunks_mtx, "arena_chunks",
+	    WITNESS_RANK_ARENA_CHUNKS))
+		return (NULL);
+	ql_new(&arena->node_cache);
+	if (malloc_mutex_init(&arena->node_cache_mtx, "arena_node_cache",
+	    WITNESS_RANK_ARENA_NODE_CACHE))
+		return (NULL);
+
+	arena->chunk_hooks = chunk_hooks_default;
+
+	/* 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))
+			return (NULL);
+		bin->runcur = NULL;
+		arena_run_heap_new(&bin->runs);
+		if (config_stats)
+			memset(&bin->stats, 0, sizeof(malloc_bin_stats_t));
+	}
+
+	return (arena);
+}
+
+/*
+ * Calculate bin_info->run_size such that it meets the following constraints:
+ *
+ *   *) bin_info->run_size <= arena_maxrun
+ *   *) bin_info->nregs <= RUN_MAXREGS
+ *
+ * bin_info->nregs and bin_info->reg0_offset are also calculated here, since
+ * these settings are all interdependent.
+ */
+static void
+bin_info_run_size_calc(arena_bin_info_t *bin_info)
+{
+	size_t pad_size;
+	size_t try_run_size, perfect_run_size, actual_run_size;
+	uint32_t try_nregs, perfect_nregs, actual_nregs;
+
+	/*
+	 * 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.
+	 */
+	if (config_fill && unlikely(opt_redzone)) {
+		size_t align_min = ZU(1) << (ffs_zu(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;
+	}
+	bin_info->reg_interval = bin_info->reg_size +
+	    (bin_info->redzone_size << 1);
+
+	/*
+	 * Compute run size under ideal conditions (no redzones, no limit on run
+	 * size).
+	 */
+	try_run_size = PAGE;
+	try_nregs = (uint32_t)(try_run_size / bin_info->reg_size);
+	do {
+		perfect_run_size = try_run_size;
+		perfect_nregs = try_nregs;
+
+		try_run_size += PAGE;
+		try_nregs = (uint32_t)(try_run_size / bin_info->reg_size);
+	} while (perfect_run_size != perfect_nregs * bin_info->reg_size);
+	assert(perfect_nregs <= RUN_MAXREGS);
+
+	actual_run_size = perfect_run_size;
+	actual_nregs = (uint32_t)((actual_run_size - pad_size) /
+	    bin_info->reg_interval);
+
+	/*
+	 * Redzones can require enough padding that not even a single region can
+	 * fit within the number of pages that would normally be dedicated to a
+	 * run for this size class.  Increase the run size until at least one
+	 * region fits.
+	 */
+	while (actual_nregs == 0) {
+		assert(config_fill && unlikely(opt_redzone));
+
+		actual_run_size += PAGE;
+		actual_nregs = (uint32_t)((actual_run_size - pad_size) /
+		    bin_info->reg_interval);
+	}
+
+	/*
+	 * Make sure that the run will fit within an arena chunk.
+	 */
+	while (actual_run_size > arena_maxrun) {
+		actual_run_size -= PAGE;
+		actual_nregs = (uint32_t)((actual_run_size - pad_size) /
+		    bin_info->reg_interval);
+	}
+	assert(actual_nregs > 0);
+	assert(actual_run_size == s2u(actual_run_size));
+
+	/* Copy final settings. */
+	bin_info->run_size = actual_run_size;
+	bin_info->nregs = actual_nregs;
+	bin_info->reg0_offset = (uint32_t)(actual_run_size - (actual_nregs *
+	    bin_info->reg_interval) - pad_size + bin_info->redzone_size);
+
+	assert(bin_info->reg0_offset - bin_info->redzone_size + (bin_info->nregs
+	    * bin_info->reg_interval) + pad_size == bin_info->run_size);
+}
+
+static void
+bin_info_init(void)
+{
+	arena_bin_info_t *bin_info;
+
+#define	BIN_INFO_INIT_bin_yes(index, size)				\
+	bin_info = &arena_bin_info[index];				\
+	bin_info->reg_size = size;					\
+	bin_info_run_size_calc(bin_info);				\
+	bitmap_info_init(&bin_info->bitmap_info, bin_info->nregs);
+#define	BIN_INFO_INIT_bin_no(index, size)
+#define	SC(index, lg_grp, lg_delta, ndelta, psz, bin, lg_delta_lookup)	\
+	BIN_INFO_INIT_bin_##bin(index, (ZU(1)<<lg_grp) + (ZU(ndelta)<<lg_delta))
+	SIZE_CLASSES
+#undef BIN_INFO_INIT_bin_yes
+#undef BIN_INFO_INIT_bin_no
+#undef SC
+}
+
+void
+arena_boot(void)
+{
+	unsigned i;
+
+	arena_lg_dirty_mult_default_set(opt_lg_dirty_mult);
+	arena_decay_time_default_set(opt_decay_time);
+
+	/*
+	 * 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++) {
+		size_t header_size = offsetof(arena_chunk_t, map_bits) +
+		    ((sizeof(arena_chunk_map_bits_t) +
+		    sizeof(arena_chunk_map_misc_t)) * (chunk_npages-map_bias));
+		map_bias = (header_size + PAGE_MASK) >> LG_PAGE;
+	}
+	assert(map_bias > 0);
+
+	map_misc_offset = offsetof(arena_chunk_t, map_bits) +
+	    sizeof(arena_chunk_map_bits_t) * (chunk_npages-map_bias);
+
+	arena_maxrun = chunksize - (map_bias << LG_PAGE);
+	assert(arena_maxrun > 0);
+	large_maxclass = index2size(size2index(chunksize)-1);
+	if (large_maxclass > arena_maxrun) {
+		/*
+		 * For small chunk sizes it's possible for there to be fewer
+		 * non-header pages available than are necessary to serve the
+		 * size classes just below chunksize.
+		 */
+		large_maxclass = arena_maxrun;
+	}
+	assert(large_maxclass > 0);
+	nlclasses = size2index(large_maxclass) - size2index(SMALL_MAXCLASS);
+	nhclasses = NSIZES - nlclasses - NBINS;
+
+	bin_info_init();
+}
+
+void
+arena_prefork0(tsdn_t *tsdn, arena_t *arena)
+{
+
+	malloc_mutex_prefork(tsdn, &arena->lock);
+}
+
+void
+arena_prefork1(tsdn_t *tsdn, arena_t *arena)
+{
+
+	malloc_mutex_prefork(tsdn, &arena->chunks_mtx);
+}
+
+void
+arena_prefork2(tsdn_t *tsdn, arena_t *arena)
+{
+
+	malloc_mutex_prefork(tsdn, &arena->node_cache_mtx);
+}
+
+void
+arena_prefork3(tsdn_t *tsdn, arena_t *arena)
+{
+	unsigned i;
+
+	for (i = 0; i < NBINS; i++)
+		malloc_mutex_prefork(tsdn, &arena->bins[i].lock);
+	malloc_mutex_prefork(tsdn, &arena->huge_mtx);
+}
+
+void
+arena_postfork_parent(tsdn_t *tsdn, arena_t *arena)
+{
+	unsigned i;
+
+	malloc_mutex_postfork_parent(tsdn, &arena->huge_mtx);
+	for (i = 0; i < NBINS; i++)
+		malloc_mutex_postfork_parent(tsdn, &arena->bins[i].lock);
+	malloc_mutex_postfork_parent(tsdn, &arena->node_cache_mtx);
+	malloc_mutex_postfork_parent(tsdn, &arena->chunks_mtx);
+	malloc_mutex_postfork_parent(tsdn, &arena->lock);
+}
+
+void
+arena_postfork_child(tsdn_t *tsdn, arena_t *arena)
+{
+	unsigned i;
+
+	malloc_mutex_postfork_child(tsdn, &arena->huge_mtx);
+	for (i = 0; i < NBINS; i++)
+		malloc_mutex_postfork_child(tsdn, &arena->bins[i].lock);
+	malloc_mutex_postfork_child(tsdn, &arena->node_cache_mtx);
+	malloc_mutex_postfork_child(tsdn, &arena->chunks_mtx);
+	malloc_mutex_postfork_child(tsdn, &arena->lock);
+}
diff --git a/deps/jemalloc/src/atomic.c b/deps/jemalloc/src/atomic.c
new file mode 100644
index 0000000..77ee313
--- /dev/null
+++ b/deps/jemalloc/src/atomic.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_ATOMIC_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/base.c b/deps/jemalloc/src/base.c
new file mode 100644
index 0000000..5681a3f
--- /dev/null
+++ b/deps/jemalloc/src/base.c
@@ -0,0 +1,187 @@
+#define	JEMALLOC_BASE_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+static malloc_mutex_t	base_mtx;
+static size_t		base_extent_sn_next;
+static extent_tree_t	base_avail_szsnad;
+static extent_node_t	*base_nodes;
+static size_t		base_allocated;
+static size_t		base_resident;
+static size_t		base_mapped;
+
+/******************************************************************************/
+
+static extent_node_t *
+base_node_try_alloc(tsdn_t *tsdn)
+{
+	extent_node_t *node;
+
+	malloc_mutex_assert_owner(tsdn, &base_mtx);
+
+	if (base_nodes == NULL)
+		return (NULL);
+	node = base_nodes;
+	base_nodes = *(extent_node_t **)node;
+	JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(node, sizeof(extent_node_t));
+	return (node);
+}
+
+static void
+base_node_dalloc(tsdn_t *tsdn, extent_node_t *node)
+{
+
+	malloc_mutex_assert_owner(tsdn, &base_mtx);
+
+	JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(node, sizeof(extent_node_t));
+	*(extent_node_t **)node = base_nodes;
+	base_nodes = node;
+}
+
+static void
+base_extent_node_init(extent_node_t *node, void *addr, size_t size)
+{
+	size_t sn = atomic_add_z(&base_extent_sn_next, 1) - 1;
+
+	extent_node_init(node, NULL, addr, size, sn, true, true);
+}
+
+static extent_node_t *
+base_chunk_alloc(tsdn_t *tsdn, size_t minsize)
+{
+	extent_node_t *node;
+	size_t csize, nsize;
+	void *addr;
+
+	malloc_mutex_assert_owner(tsdn, &base_mtx);
+	assert(minsize != 0);
+	node = base_node_try_alloc(tsdn);
+	/* Allocate enough space to also carve a node out if necessary. */
+	nsize = (node == NULL) ? CACHELINE_CEILING(sizeof(extent_node_t)) : 0;
+	csize = CHUNK_CEILING(minsize + nsize);
+	addr = chunk_alloc_base(csize);
+	if (addr == NULL) {
+		if (node != NULL)
+			base_node_dalloc(tsdn, node);
+		return (NULL);
+	}
+	base_mapped += csize;
+	if (node == NULL) {
+		node = (extent_node_t *)addr;
+		addr = (void *)((uintptr_t)addr + nsize);
+		csize -= nsize;
+		if (config_stats) {
+			base_allocated += nsize;
+			base_resident += PAGE_CEILING(nsize);
+		}
+	}
+	base_extent_node_init(node, addr, csize);
+	return (node);
+}
+
+/*
+ * base_alloc() guarantees demand-zeroed memory, in order to make multi-page
+ * sparse data structures such as radix tree nodes efficient with respect to
+ * physical memory usage.
+ */
+void *
+base_alloc(tsdn_t *tsdn, size_t size)
+{
+	void *ret;
+	size_t csize, usize;
+	extent_node_t *node;
+	extent_node_t key;
+
+	/*
+	 * Round size up to nearest multiple of the cacheline size, so that
+	 * there is no chance of false cache line sharing.
+	 */
+	csize = CACHELINE_CEILING(size);
+
+	usize = s2u(csize);
+	extent_node_init(&key, NULL, NULL, usize, 0, false, false);
+	malloc_mutex_lock(tsdn, &base_mtx);
+	node = extent_tree_szsnad_nsearch(&base_avail_szsnad, &key);
+	if (node != NULL) {
+		/* Use existing space. */
+		extent_tree_szsnad_remove(&base_avail_szsnad, node);
+	} else {
+		/* Try to allocate more space. */
+		node = base_chunk_alloc(tsdn, csize);
+	}
+	if (node == NULL) {
+		ret = NULL;
+		goto label_return;
+	}
+
+	ret = extent_node_addr_get(node);
+	if (extent_node_size_get(node) > csize) {
+		extent_node_addr_set(node, (void *)((uintptr_t)ret + csize));
+		extent_node_size_set(node, extent_node_size_get(node) - csize);
+		extent_tree_szsnad_insert(&base_avail_szsnad, node);
+	} else
+		base_node_dalloc(tsdn, node);
+	if (config_stats) {
+		base_allocated += csize;
+		/*
+		 * Add one PAGE to base_resident for every page boundary that is
+		 * crossed by the new allocation.
+		 */
+		base_resident += PAGE_CEILING((uintptr_t)ret + csize) -
+		    PAGE_CEILING((uintptr_t)ret);
+	}
+	JEMALLOC_VALGRIND_MAKE_MEM_DEFINED(ret, csize);
+label_return:
+	malloc_mutex_unlock(tsdn, &base_mtx);
+	return (ret);
+}
+
+void
+base_stats_get(tsdn_t *tsdn, size_t *allocated, size_t *resident,
+    size_t *mapped)
+{
+
+	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);
+}
+
+bool
+base_boot(void)
+{
+
+	if (malloc_mutex_init(&base_mtx, "base", WITNESS_RANK_BASE))
+		return (true);
+	base_extent_sn_next = 0;
+	extent_tree_szsnad_new(&base_avail_szsnad);
+	base_nodes = NULL;
+
+	return (false);
+}
+
+void
+base_prefork(tsdn_t *tsdn)
+{
+
+	malloc_mutex_prefork(tsdn, &base_mtx);
+}
+
+void
+base_postfork_parent(tsdn_t *tsdn)
+{
+
+	malloc_mutex_postfork_parent(tsdn, &base_mtx);
+}
+
+void
+base_postfork_child(tsdn_t *tsdn)
+{
+
+	malloc_mutex_postfork_child(tsdn, &base_mtx);
+}
diff --git a/deps/jemalloc/src/bitmap.c b/deps/jemalloc/src/bitmap.c
new file mode 100644
index 0000000..ac0f3b3
--- /dev/null
+++ b/deps/jemalloc/src/bitmap.c
@@ -0,0 +1,111 @@
+#define	JEMALLOC_BITMAP_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+
+#ifdef USE_TREE
+
+void
+bitmap_info_init(bitmap_info_t *binfo, size_t nbits)
+{
+	unsigned i;
+	size_t group_count;
+
+	assert(nbits > 0);
+	assert(nbits <= (ZU(1) << LG_BITMAP_MAXBITS));
+
+	/*
+	 * Compute the number of groups necessary to store nbits bits, and
+	 * progressively work upward through the levels until reaching a level
+	 * that requires only one group.
+	 */
+	binfo->levels[0].group_offset = 0;
+	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 = 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;
+}
+
+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)
+{
+	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.
+	 */
+	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->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)
+			bitmap[binfo->levels[i+1].group_offset - 1] >>= extra;
+	}
+}
+
+#else /* 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)
+{
+	size_t extra;
+
+	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 /* USE_TREE */
+
+size_t
+bitmap_size(const bitmap_info_t *binfo)
+{
+
+	return (bitmap_info_ngroups(binfo) << LG_SIZEOF_BITMAP);
+}
diff --git a/deps/jemalloc/src/chunk.c b/deps/jemalloc/src/chunk.c
new file mode 100644
index 0000000..c1c514a
--- /dev/null
+++ b/deps/jemalloc/src/chunk.c
@@ -0,0 +1,795 @@
+#define	JEMALLOC_CHUNK_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+const char	*opt_dss = DSS_DEFAULT;
+size_t		opt_lg_chunk = 0;
+
+/* Used exclusively for gdump triggering. */
+static size_t	curchunks;
+static size_t	highchunks;
+
+rtree_t		chunks_rtree;
+
+/* Various chunk-related settings. */
+size_t		chunksize;
+size_t		chunksize_mask; /* (chunksize - 1). */
+size_t		chunk_npages;
+
+static void	*chunk_alloc_default(void *new_addr, size_t size,
+    size_t alignment, bool *zero, bool *commit, unsigned arena_ind);
+static bool	chunk_dalloc_default(void *chunk, size_t size, bool committed,
+    unsigned arena_ind);
+static bool	chunk_commit_default(void *chunk, size_t size, size_t offset,
+    size_t length, unsigned arena_ind);
+static bool	chunk_decommit_default(void *chunk, size_t size, size_t offset,
+    size_t length, unsigned arena_ind);
+static bool	chunk_purge_default(void *chunk, size_t size, size_t offset,
+    size_t length, unsigned arena_ind);
+static bool	chunk_split_default(void *chunk, size_t size, size_t size_a,
+    size_t size_b, bool committed, unsigned arena_ind);
+static bool	chunk_merge_default(void *chunk_a, size_t size_a, void *chunk_b,
+    size_t size_b, bool committed, unsigned arena_ind);
+
+const chunk_hooks_t	chunk_hooks_default = {
+	chunk_alloc_default,
+	chunk_dalloc_default,
+	chunk_commit_default,
+	chunk_decommit_default,
+	chunk_purge_default,
+	chunk_split_default,
+	chunk_merge_default
+};
+
+/******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
+
+static void	chunk_record(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks, extent_tree_t *chunks_szsnad,
+    extent_tree_t *chunks_ad, bool cache, void *chunk, size_t size, size_t sn,
+    bool zeroed, bool committed);
+
+/******************************************************************************/
+
+static chunk_hooks_t
+chunk_hooks_get_locked(arena_t *arena)
+{
+
+	return (arena->chunk_hooks);
+}
+
+chunk_hooks_t
+chunk_hooks_get(tsdn_t *tsdn, arena_t *arena)
+{
+	chunk_hooks_t chunk_hooks;
+
+	malloc_mutex_lock(tsdn, &arena->chunks_mtx);
+	chunk_hooks = chunk_hooks_get_locked(arena);
+	malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+
+	return (chunk_hooks);
+}
+
+chunk_hooks_t
+chunk_hooks_set(tsdn_t *tsdn, arena_t *arena, const chunk_hooks_t *chunk_hooks)
+{
+	chunk_hooks_t old_chunk_hooks;
+
+	malloc_mutex_lock(tsdn, &arena->chunks_mtx);
+	old_chunk_hooks = arena->chunk_hooks;
+	/*
+	 * Copy each field atomically so that it is impossible for readers to
+	 * see partially updated pointers.  There are places where readers only
+	 * need one hook function pointer (therefore no need to copy the
+	 * entirety of arena->chunk_hooks), and stale reads do not affect
+	 * correctness, so they perform unlocked reads.
+	 */
+#define	ATOMIC_COPY_HOOK(n) do {					\
+	union {								\
+		chunk_##n##_t	**n;					\
+		void		**v;					\
+	} u;								\
+	u.n = &arena->chunk_hooks.n;					\
+	atomic_write_p(u.v, chunk_hooks->n);				\
+} while (0)
+	ATOMIC_COPY_HOOK(alloc);
+	ATOMIC_COPY_HOOK(dalloc);
+	ATOMIC_COPY_HOOK(commit);
+	ATOMIC_COPY_HOOK(decommit);
+	ATOMIC_COPY_HOOK(purge);
+	ATOMIC_COPY_HOOK(split);
+	ATOMIC_COPY_HOOK(merge);
+#undef ATOMIC_COPY_HOOK
+	malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+
+	return (old_chunk_hooks);
+}
+
+static void
+chunk_hooks_assure_initialized_impl(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks, bool locked)
+{
+	static const chunk_hooks_t uninitialized_hooks =
+	    CHUNK_HOOKS_INITIALIZER;
+
+	if (memcmp(chunk_hooks, &uninitialized_hooks, sizeof(chunk_hooks_t)) ==
+	    0) {
+		*chunk_hooks = locked ? chunk_hooks_get_locked(arena) :
+		    chunk_hooks_get(tsdn, arena);
+	}
+}
+
+static void
+chunk_hooks_assure_initialized_locked(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks)
+{
+
+	chunk_hooks_assure_initialized_impl(tsdn, arena, chunk_hooks, true);
+}
+
+static void
+chunk_hooks_assure_initialized(tsdn_t *tsdn, arena_t *arena,
+    chunk_hooks_t *chunk_hooks)
+{
+
+	chunk_hooks_assure_initialized_impl(tsdn, arena, chunk_hooks, false);
+}
+
+bool
+chunk_register(tsdn_t *tsdn, const void *chunk, const extent_node_t *node)
+{
+
+	assert(extent_node_addr_get(node) == chunk);
+
+	if (rtree_set(&chunks_rtree, (uintptr_t)chunk, node))
+		return (true);
+	if (config_prof && opt_prof) {
+		size_t size = extent_node_size_get(node);
+		size_t nadd = (size == 0) ? 1 : size / chunksize;
+		size_t cur = atomic_add_z(&curchunks, nadd);
+		size_t high = atomic_read_z(&highchunks);
+		while (cur > high && atomic_cas_z(&highchunks, high, cur)) {
+			/*
+			 * Don't refresh cur, because it may have decreased
+			 * since this thread lost the highchunks update race.
+			 */
+			high = atomic_read_z(&highchunks);
+		}
+		if (cur > high && prof_gdump_get_unlocked())
+			prof_gdump(tsdn);
+	}
+
+	return (false);
+}
+
+void
+chunk_deregister(const void *chunk, const extent_node_t *node)
+{
+	bool err;
+
+	err = rtree_set(&chunks_rtree, (uintptr_t)chunk, NULL);
+	assert(!err);
+	if (config_prof && opt_prof) {
+		size_t size = extent_node_size_get(node);
+		size_t nsub = (size == 0) ? 1 : size / chunksize;
+		assert(atomic_read_z(&curchunks) >= nsub);
+		atomic_sub_z(&curchunks, nsub);
+	}
+}
+
+/*
+ * Do first-best-fit chunk selection, i.e. select the oldest/lowest chunk that
+ * best fits.
+ */
+static extent_node_t *
+chunk_first_best_fit(arena_t *arena, extent_tree_t *chunks_szsnad, size_t size)
+{
+	extent_node_t key;
+
+	assert(size == CHUNK_CEILING(size));
+
+	extent_node_init(&key, arena, NULL, size, 0, false, false);
+	return (extent_tree_szsnad_nsearch(chunks_szsnad, &key));
+}
+
+static void *
+chunk_recycle(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    extent_tree_t *chunks_szsnad, extent_tree_t *chunks_ad, bool cache,
+    void *new_addr, size_t size, size_t alignment, size_t *sn, bool *zero,
+    bool *commit, bool dalloc_node)
+{
+	void *ret;
+	extent_node_t *node;
+	size_t alloc_size, leadsize, trailsize;
+	bool zeroed, committed;
+
+	assert(CHUNK_CEILING(size) == size);
+	assert(alignment > 0);
+	assert(new_addr == NULL || alignment == chunksize);
+	assert(CHUNK_ADDR2BASE(new_addr) == new_addr);
+	/*
+	 * Cached chunks use the node linkage embedded in their headers, in
+	 * which case dalloc_node is true, and new_addr is non-NULL because
+	 * we're operating on a specific chunk.
+	 */
+	assert(dalloc_node || new_addr != NULL);
+
+	alloc_size = size + CHUNK_CEILING(alignment) - chunksize;
+	/* Beware size_t wrap-around. */
+	if (alloc_size < size)
+		return (NULL);
+	malloc_mutex_lock(tsdn, &arena->chunks_mtx);
+	chunk_hooks_assure_initialized_locked(tsdn, arena, chunk_hooks);
+	if (new_addr != NULL) {
+		extent_node_t key;
+		extent_node_init(&key, arena, new_addr, alloc_size, 0, false,
+		    false);
+		node = extent_tree_ad_search(chunks_ad, &key);
+	} else {
+		node = chunk_first_best_fit(arena, chunks_szsnad, alloc_size);
+	}
+	if (node == NULL || (new_addr != NULL && extent_node_size_get(node) <
+	    size)) {
+		malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+		return (NULL);
+	}
+	leadsize = ALIGNMENT_CEILING((uintptr_t)extent_node_addr_get(node),
+	    alignment) - (uintptr_t)extent_node_addr_get(node);
+	assert(new_addr == NULL || leadsize == 0);
+	assert(extent_node_size_get(node) >= leadsize + size);
+	trailsize = extent_node_size_get(node) - leadsize - size;
+	ret = (void *)((uintptr_t)extent_node_addr_get(node) + leadsize);
+	*sn = extent_node_sn_get(node);
+	zeroed = extent_node_zeroed_get(node);
+	if (zeroed)
+		*zero = true;
+	committed = extent_node_committed_get(node);
+	if (committed)
+		*commit = true;
+	/* Split the lead. */
+	if (leadsize != 0 &&
+	    chunk_hooks->split(extent_node_addr_get(node),
+	    extent_node_size_get(node), leadsize, size, false, arena->ind)) {
+		malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+		return (NULL);
+	}
+	/* Remove node from the tree. */
+	extent_tree_szsnad_remove(chunks_szsnad, node);
+	extent_tree_ad_remove(chunks_ad, node);
+	arena_chunk_cache_maybe_remove(arena, node, cache);
+	if (leadsize != 0) {
+		/* Insert the leading space as a smaller chunk. */
+		extent_node_size_set(node, leadsize);
+		extent_tree_szsnad_insert(chunks_szsnad, node);
+		extent_tree_ad_insert(chunks_ad, node);
+		arena_chunk_cache_maybe_insert(arena, node, cache);
+		node = NULL;
+	}
+	if (trailsize != 0) {
+		/* Split the trail. */
+		if (chunk_hooks->split(ret, size + trailsize, size,
+		    trailsize, false, arena->ind)) {
+			if (dalloc_node && node != NULL)
+				arena_node_dalloc(tsdn, arena, node);
+			malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+			chunk_record(tsdn, arena, chunk_hooks, chunks_szsnad,
+			    chunks_ad, cache, ret, size + trailsize, *sn,
+			    zeroed, committed);
+			return (NULL);
+		}
+		/* Insert the trailing space as a smaller chunk. */
+		if (node == NULL) {
+			node = arena_node_alloc(tsdn, arena);
+			if (node == NULL) {
+				malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+				chunk_record(tsdn, arena, chunk_hooks,
+				    chunks_szsnad, chunks_ad, cache, ret, size
+				    + trailsize, *sn, zeroed, committed);
+				return (NULL);
+			}
+		}
+		extent_node_init(node, arena, (void *)((uintptr_t)(ret) + size),
+		    trailsize, *sn, zeroed, committed);
+		extent_tree_szsnad_insert(chunks_szsnad, node);
+		extent_tree_ad_insert(chunks_ad, node);
+		arena_chunk_cache_maybe_insert(arena, node, cache);
+		node = NULL;
+	}
+	if (!committed && chunk_hooks->commit(ret, size, 0, size, arena->ind)) {
+		malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+		chunk_record(tsdn, arena, chunk_hooks, chunks_szsnad, chunks_ad,
+		    cache, ret, size, *sn, zeroed, committed);
+		return (NULL);
+	}
+	malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+
+	assert(dalloc_node || node != NULL);
+	if (dalloc_node && node != NULL)
+		arena_node_dalloc(tsdn, arena, node);
+	if (*zero) {
+		if (!zeroed)
+			memset(ret, 0, size);
+		else if (config_debug) {
+			size_t i;
+			size_t *p = (size_t *)(uintptr_t)ret;
+
+			for (i = 0; i < size / sizeof(size_t); i++)
+				assert(p[i] == 0);
+		}
+		if (config_valgrind)
+			JEMALLOC_VALGRIND_MAKE_MEM_DEFINED(ret, size);
+	}
+	return (ret);
+}
+
+/*
+ * If the caller specifies (!*zero), it is still possible to receive zeroed
+ * memory, in which case *zero is toggled to true.  arena_chunk_alloc() takes
+ * advantage of this to avoid demanding zeroed chunks, but taking advantage of
+ * them if they are returned.
+ */
+static void *
+chunk_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((size & chunksize_mask) == 0);
+	assert(alignment != 0);
+	assert((alignment & chunksize_mask) == 0);
+
+	/* "primary" dss. */
+	if (have_dss && dss_prec == dss_prec_primary && (ret =
+	    chunk_alloc_dss(tsdn, arena, new_addr, size, alignment, zero,
+	    commit)) != NULL)
+		return (ret);
+	/* mmap. */
+	if ((ret = chunk_alloc_mmap(new_addr, size, alignment, zero, commit)) !=
+	    NULL)
+		return (ret);
+	/* "secondary" dss. */
+	if (have_dss && dss_prec == dss_prec_secondary && (ret =
+	    chunk_alloc_dss(tsdn, arena, new_addr, size, alignment, zero,
+	    commit)) != NULL)
+		return (ret);
+
+	/* All strategies for allocation failed. */
+	return (NULL);
+}
+
+void *
+chunk_alloc_base(size_t size)
+{
+	void *ret;
+	bool zero, commit;
+
+	/*
+	 * Directly call chunk_alloc_mmap() rather than chunk_alloc_core()
+	 * because it's critical that chunk_alloc_base() return untouched
+	 * demand-zeroed virtual memory.
+	 */
+	zero = true;
+	commit = true;
+	ret = chunk_alloc_mmap(NULL, size, chunksize, &zero, &commit);
+	if (ret == NULL)
+		return (NULL);
+	if (config_valgrind)
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
+
+	return (ret);
+}
+
+void *
+chunk_alloc_cache(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *new_addr, size_t size, size_t alignment, size_t *sn, bool *zero,
+    bool *commit, bool dalloc_node)
+{
+	void *ret;
+
+	assert(size != 0);
+	assert((size & chunksize_mask) == 0);
+	assert(alignment != 0);
+	assert((alignment & chunksize_mask) == 0);
+
+	ret = chunk_recycle(tsdn, arena, chunk_hooks,
+	    &arena->chunks_szsnad_cached, &arena->chunks_ad_cached, true,
+	    new_addr, size, alignment, sn, zero, commit, dalloc_node);
+	if (ret == NULL)
+		return (NULL);
+	if (config_valgrind)
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
+	return (ret);
+}
+
+static arena_t *
+chunk_arena_get(tsdn_t *tsdn, unsigned arena_ind)
+{
+	arena_t *arena;
+
+	arena = arena_get(tsdn, arena_ind, false);
+	/*
+	 * The arena we're allocating on behalf of must have been initialized
+	 * already.
+	 */
+	assert(arena != NULL);
+	return (arena);
+}
+
+static void *
+chunk_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 = chunk_alloc_core(tsdn, arena, new_addr, size, alignment, zero,
+	    commit, arena->dss_prec);
+	if (ret == NULL)
+		return (NULL);
+	if (config_valgrind)
+		JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, size);
+
+	return (ret);
+}
+
+static void *
+chunk_alloc_default(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 = chunk_arena_get(tsdn, arena_ind);
+
+	return (chunk_alloc_default_impl(tsdn, arena, new_addr, size, alignment,
+	    zero, commit));
+}
+
+static void *
+chunk_alloc_retained(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *new_addr, size_t size, size_t alignment, size_t *sn, bool *zero,
+    bool *commit)
+{
+	void *ret;
+
+	assert(size != 0);
+	assert((size & chunksize_mask) == 0);
+	assert(alignment != 0);
+	assert((alignment & chunksize_mask) == 0);
+
+	ret = chunk_recycle(tsdn, arena, chunk_hooks,
+	    &arena->chunks_szsnad_retained, &arena->chunks_ad_retained, false,
+	    new_addr, size, alignment, sn, zero, commit, true);
+
+	if (config_stats && ret != NULL)
+		arena->stats.retained -= size;
+
+	return (ret);
+}
+
+void *
+chunk_alloc_wrapper(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *new_addr, size_t size, size_t alignment, size_t *sn, bool *zero,
+    bool *commit)
+{
+	void *ret;
+
+	chunk_hooks_assure_initialized(tsdn, arena, chunk_hooks);
+
+	ret = chunk_alloc_retained(tsdn, arena, chunk_hooks, new_addr, size,
+	    alignment, sn, zero, commit);
+	if (ret == NULL) {
+		if (chunk_hooks->alloc == chunk_alloc_default) {
+			/* Call directly to propagate tsdn. */
+			ret = chunk_alloc_default_impl(tsdn, arena, new_addr,
+			    size, alignment, zero, commit);
+		} else {
+			ret = chunk_hooks->alloc(new_addr, size, alignment,
+			    zero, commit, arena->ind);
+		}
+
+		if (ret == NULL)
+			return (NULL);
+
+		*sn = arena_extent_sn_next(arena);
+
+		if (config_valgrind && chunk_hooks->alloc !=
+		    chunk_alloc_default)
+			JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(ret, chunksize);
+	}
+
+	return (ret);
+}
+
+static void
+chunk_record(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    extent_tree_t *chunks_szsnad, extent_tree_t *chunks_ad, bool cache,
+    void *chunk, size_t size, size_t sn, bool zeroed, bool committed)
+{
+	bool unzeroed;
+	extent_node_t *node, *prev;
+	extent_node_t key;
+
+	assert(!cache || !zeroed);
+	unzeroed = cache || !zeroed;
+	JEMALLOC_VALGRIND_MAKE_MEM_NOACCESS(chunk, size);
+
+	malloc_mutex_lock(tsdn, &arena->chunks_mtx);
+	chunk_hooks_assure_initialized_locked(tsdn, arena, chunk_hooks);
+	extent_node_init(&key, arena, (void *)((uintptr_t)chunk + size), 0, 0,
+	    false, false);
+	node = extent_tree_ad_nsearch(chunks_ad, &key);
+	/* Try to coalesce forward. */
+	if (node != NULL && extent_node_addr_get(node) ==
+	    extent_node_addr_get(&key) && extent_node_committed_get(node) ==
+	    committed && !chunk_hooks->merge(chunk, size,
+	    extent_node_addr_get(node), extent_node_size_get(node), false,
+	    arena->ind)) {
+		/*
+		 * Coalesce chunk with the following address range.  This does
+		 * not change the position within chunks_ad, so only
+		 * remove/insert from/into chunks_szsnad.
+		 */
+		extent_tree_szsnad_remove(chunks_szsnad, node);
+		arena_chunk_cache_maybe_remove(arena, node, cache);
+		extent_node_addr_set(node, chunk);
+		extent_node_size_set(node, size + extent_node_size_get(node));
+		if (sn < extent_node_sn_get(node))
+			extent_node_sn_set(node, sn);
+		extent_node_zeroed_set(node, extent_node_zeroed_get(node) &&
+		    !unzeroed);
+		extent_tree_szsnad_insert(chunks_szsnad, node);
+		arena_chunk_cache_maybe_insert(arena, node, cache);
+	} else {
+		/* Coalescing forward failed, so insert a new node. */
+		node = arena_node_alloc(tsdn, arena);
+		if (node == NULL) {
+			/*
+			 * Node allocation failed, which is an exceedingly
+			 * unlikely failure.  Leak chunk after making sure its
+			 * pages have already been purged, so that this is only
+			 * a virtual memory leak.
+			 */
+			if (cache) {
+				chunk_purge_wrapper(tsdn, arena, chunk_hooks,
+				    chunk, size, 0, size);
+			}
+			goto label_return;
+		}
+		extent_node_init(node, arena, chunk, size, sn, !unzeroed,
+		    committed);
+		extent_tree_ad_insert(chunks_ad, node);
+		extent_tree_szsnad_insert(chunks_szsnad, node);
+		arena_chunk_cache_maybe_insert(arena, node, cache);
+	}
+
+	/* Try to coalesce backward. */
+	prev = extent_tree_ad_prev(chunks_ad, node);
+	if (prev != NULL && (void *)((uintptr_t)extent_node_addr_get(prev) +
+	    extent_node_size_get(prev)) == chunk &&
+	    extent_node_committed_get(prev) == committed &&
+	    !chunk_hooks->merge(extent_node_addr_get(prev),
+	    extent_node_size_get(prev), chunk, size, false, arena->ind)) {
+		/*
+		 * Coalesce chunk with the previous address range.  This does
+		 * not change the position within chunks_ad, so only
+		 * remove/insert node from/into chunks_szsnad.
+		 */
+		extent_tree_szsnad_remove(chunks_szsnad, prev);
+		extent_tree_ad_remove(chunks_ad, prev);
+		arena_chunk_cache_maybe_remove(arena, prev, cache);
+		extent_tree_szsnad_remove(chunks_szsnad, node);
+		arena_chunk_cache_maybe_remove(arena, node, cache);
+		extent_node_addr_set(node, extent_node_addr_get(prev));
+		extent_node_size_set(node, extent_node_size_get(prev) +
+		    extent_node_size_get(node));
+		if (extent_node_sn_get(prev) < extent_node_sn_get(node))
+			extent_node_sn_set(node, extent_node_sn_get(prev));
+		extent_node_zeroed_set(node, extent_node_zeroed_get(prev) &&
+		    extent_node_zeroed_get(node));
+		extent_tree_szsnad_insert(chunks_szsnad, node);
+		arena_chunk_cache_maybe_insert(arena, node, cache);
+
+		arena_node_dalloc(tsdn, arena, prev);
+	}
+
+label_return:
+	malloc_mutex_unlock(tsdn, &arena->chunks_mtx);
+}
+
+void
+chunk_dalloc_cache(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *chunk, size_t size, size_t sn, bool committed)
+{
+
+	assert(chunk != NULL);
+	assert(CHUNK_ADDR2BASE(chunk) == chunk);
+	assert(size != 0);
+	assert((size & chunksize_mask) == 0);
+
+	chunk_record(tsdn, arena, chunk_hooks, &arena->chunks_szsnad_cached,
+	    &arena->chunks_ad_cached, true, chunk, size, sn, false,
+	    committed);
+	arena_maybe_purge(tsdn, arena);
+}
+
+static bool
+chunk_dalloc_default_impl(void *chunk, size_t size)
+{
+
+	if (!have_dss || !chunk_in_dss(chunk))
+		return (chunk_dalloc_mmap(chunk, size));
+	return (true);
+}
+
+static bool
+chunk_dalloc_default(void *chunk, size_t size, bool committed,
+    unsigned arena_ind)
+{
+
+	return (chunk_dalloc_default_impl(chunk, size));
+}
+
+void
+chunk_dalloc_wrapper(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *chunk, size_t size, size_t sn, bool zeroed, bool committed)
+{
+	bool err;
+
+	assert(chunk != NULL);
+	assert(CHUNK_ADDR2BASE(chunk) == chunk);
+	assert(size != 0);
+	assert((size & chunksize_mask) == 0);
+
+	chunk_hooks_assure_initialized(tsdn, arena, chunk_hooks);
+	/* Try to deallocate. */
+	if (chunk_hooks->dalloc == chunk_dalloc_default) {
+		/* Call directly to propagate tsdn. */
+		err = chunk_dalloc_default_impl(chunk, size);
+	} else
+		err = chunk_hooks->dalloc(chunk, size, committed, arena->ind);
+
+	if (!err)
+		return;
+	/* Try to decommit; purge if that fails. */
+	if (committed) {
+		committed = chunk_hooks->decommit(chunk, size, 0, size,
+		    arena->ind);
+	}
+	zeroed = !committed || !chunk_hooks->purge(chunk, size, 0, size,
+	    arena->ind);
+	chunk_record(tsdn, arena, chunk_hooks, &arena->chunks_szsnad_retained,
+	    &arena->chunks_ad_retained, false, chunk, size, sn, zeroed,
+	    committed);
+
+	if (config_stats)
+		arena->stats.retained += size;
+}
+
+static bool
+chunk_commit_default(void *chunk, size_t size, size_t offset, size_t length,
+    unsigned arena_ind)
+{
+
+	return (pages_commit((void *)((uintptr_t)chunk + (uintptr_t)offset),
+	    length));
+}
+
+static bool
+chunk_decommit_default(void *chunk, size_t size, size_t offset, size_t length,
+    unsigned arena_ind)
+{
+
+	return (pages_decommit((void *)((uintptr_t)chunk + (uintptr_t)offset),
+	    length));
+}
+
+static bool
+chunk_purge_default(void *chunk, size_t size, size_t offset, size_t length,
+    unsigned arena_ind)
+{
+
+	assert(chunk != NULL);
+	assert(CHUNK_ADDR2BASE(chunk) == chunk);
+	assert((offset & PAGE_MASK) == 0);
+	assert(length != 0);
+	assert((length & PAGE_MASK) == 0);
+
+	return (pages_purge((void *)((uintptr_t)chunk + (uintptr_t)offset),
+	    length));
+}
+
+bool
+chunk_purge_wrapper(tsdn_t *tsdn, arena_t *arena, chunk_hooks_t *chunk_hooks,
+    void *chunk, size_t size, size_t offset, size_t length)
+{
+
+	chunk_hooks_assure_initialized(tsdn, arena, chunk_hooks);
+	return (chunk_hooks->purge(chunk, size, offset, length, arena->ind));
+}
+
+static bool
+chunk_split_default(void *chunk, size_t size, size_t size_a, size_t size_b,
+    bool committed, unsigned arena_ind)
+{
+
+	if (!maps_coalesce)
+		return (true);
+	return (false);
+}
+
+static bool
+chunk_merge_default_impl(void *chunk_a, void *chunk_b)
+{
+
+	if (!maps_coalesce)
+		return (true);
+	if (have_dss && !chunk_dss_mergeable(chunk_a, chunk_b))
+		return (true);
+
+	return (false);
+}
+
+static bool
+chunk_merge_default(void *chunk_a, size_t size_a, void *chunk_b, size_t size_b,
+    bool committed, unsigned arena_ind)
+{
+
+	return (chunk_merge_default_impl(chunk_a, chunk_b));
+}
+
+static rtree_node_elm_t *
+chunks_rtree_node_alloc(size_t nelms)
+{
+
+	return ((rtree_node_elm_t *)base_alloc(TSDN_NULL, nelms *
+	    sizeof(rtree_node_elm_t)));
+}
+
+bool
+chunk_boot(void)
+{
+#ifdef _WIN32
+	SYSTEM_INFO info;
+	GetSystemInfo(&info);
+
+	/*
+	 * Verify actual page size is equal to or an integral multiple of
+	 * configured page size.
+	 */
+	if (info.dwPageSize & ((1U << LG_PAGE) - 1))
+		return (true);
+
+	/*
+	 * Configure chunksize (if not set) to match granularity (usually 64K),
+	 * so pages_map will always take fast path.
+	 */
+	if (!opt_lg_chunk) {
+		opt_lg_chunk = ffs_u((unsigned)info.dwAllocationGranularity)
+		    - 1;
+	}
+#else
+	if (!opt_lg_chunk)
+		opt_lg_chunk = LG_CHUNK_DEFAULT;
+#endif
+
+	/* Set variables according to the value of opt_lg_chunk. */
+	chunksize = (ZU(1) << opt_lg_chunk);
+	assert(chunksize >= PAGE);
+	chunksize_mask = chunksize - 1;
+	chunk_npages = (chunksize >> LG_PAGE);
+
+	if (have_dss)
+		chunk_dss_boot();
+	if (rtree_new(&chunks_rtree, (unsigned)((ZU(1) << (LG_SIZEOF_PTR+3)) -
+	    opt_lg_chunk), chunks_rtree_node_alloc, NULL))
+		return (true);
+
+	return (false);
+}
diff --git a/deps/jemalloc/src/chunk_dss.c b/deps/jemalloc/src/chunk_dss.c
new file mode 100644
index 0000000..ee3f838
--- /dev/null
+++ b/deps/jemalloc/src/chunk_dss.c
@@ -0,0 +1,238 @@
+#define	JEMALLOC_CHUNK_DSS_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+/******************************************************************************/
+/* Data. */
+
+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 unsigned		dss_prec_default = (unsigned)DSS_PREC_DEFAULT;
+
+/* Base address of the DSS. */
+static void		*dss_base;
+/* Atomic boolean indicating whether the DSS is exhausted. */
+static unsigned		dss_exhausted;
+/* Atomic current upper limit on DSS addresses. */
+static void		*dss_max;
+
+/******************************************************************************/
+
+static void *
+chunk_dss_sbrk(intptr_t increment)
+{
+
+#ifdef JEMALLOC_DSS
+	return (sbrk(increment));
+#else
+	not_implemented();
+	return (NULL);
+#endif
+}
+
+dss_prec_t
+chunk_dss_prec_get(void)
+{
+	dss_prec_t ret;
+
+	if (!have_dss)
+		return (dss_prec_disabled);
+	ret = (dss_prec_t)atomic_read_u(&dss_prec_default);
+	return (ret);
+}
+
+bool
+chunk_dss_prec_set(dss_prec_t dss_prec)
+{
+
+	if (!have_dss)
+		return (dss_prec != dss_prec_disabled);
+	atomic_write_u(&dss_prec_default, (unsigned)dss_prec);
+	return (false);
+}
+
+static void *
+chunk_dss_max_update(void *new_addr)
+{
+	void *max_cur;
+	spin_t spinner;
+
+	/*
+	 * Get the current end of the DSS as max_cur and assure that dss_max is
+	 * up to date.
+	 */
+	spin_init(&spinner);
+	while (true) {
+		void *max_prev = atomic_read_p(&dss_max);
+
+		max_cur = chunk_dss_sbrk(0);
+		if ((uintptr_t)max_prev > (uintptr_t)max_cur) {
+			/*
+			 * Another thread optimistically updated dss_max.  Wait
+			 * for it to finish.
+			 */
+			spin_adaptive(&spinner);
+			continue;
+		}
+		if (!atomic_cas_p(&dss_max, max_prev, max_cur))
+			break;
+	}
+	/* 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 *
+chunk_alloc_dss(tsdn_t *tsdn, arena_t *arena, void *new_addr, size_t size,
+    size_t alignment, bool *zero, bool *commit)
+{
+	cassert(have_dss);
+	assert(size > 0 && (size & chunksize_mask) == 0);
+	assert(alignment > 0 && (alignment & chunksize_mask) == 0);
+
+	/*
+	 * sbrk() uses a signed increment argument, so take care not to
+	 * interpret a huge allocation request as a negative increment.
+	 */
+	if ((intptr_t)size < 0)
+		return (NULL);
+
+	if (!atomic_read_u(&dss_exhausted)) {
+		/*
+		 * The loop is necessary to recover from races with other
+		 * threads that are using the DSS for something other than
+		 * malloc.
+		 */
+		while (true) {
+			void *ret, *cpad, *max_cur, *dss_next, *dss_prev;
+			size_t gap_size, cpad_size;
+			intptr_t incr;
+
+			max_cur = chunk_dss_max_update(new_addr);
+			if (max_cur == NULL)
+				goto label_oom;
+
+			/*
+			 * Calculate how much padding is necessary to
+			 * chunk-align the end of the DSS.
+			 */
+			gap_size = (chunksize - CHUNK_ADDR2OFFSET(dss_max)) &
+			    chunksize_mask;
+			/*
+			 * Compute how much chunk-aligned pad space (if any) is
+			 * necessary to satisfy alignment.  This space can be
+			 * recycled for later use.
+			 */
+			cpad = (void *)((uintptr_t)dss_max + gap_size);
+			ret = (void *)ALIGNMENT_CEILING((uintptr_t)dss_max,
+			    alignment);
+			cpad_size = (uintptr_t)ret - (uintptr_t)cpad;
+			dss_next = (void *)((uintptr_t)ret + size);
+			if ((uintptr_t)ret < (uintptr_t)dss_max ||
+			    (uintptr_t)dss_next < (uintptr_t)dss_max)
+				goto label_oom; /* Wrap-around. */
+			incr = gap_size + cpad_size + size;
+
+			/*
+			 * Optimistically update dss_max, and roll back below if
+			 * sbrk() fails.  No other thread will try to extend the
+			 * DSS while dss_max is greater than the current DSS
+			 * max reported by sbrk(0).
+			 */
+			if (atomic_cas_p(&dss_max, max_cur, dss_next))
+				continue;
+
+			/* Try to allocate. */
+			dss_prev = chunk_dss_sbrk(incr);
+			if (dss_prev == max_cur) {
+				/* Success. */
+				if (cpad_size != 0) {
+					chunk_hooks_t chunk_hooks =
+					    CHUNK_HOOKS_INITIALIZER;
+					chunk_dalloc_wrapper(tsdn, arena,
+					    &chunk_hooks, cpad, cpad_size,
+					    arena_extent_sn_next(arena), false,
+					    true);
+				}
+				if (*zero) {
+					JEMALLOC_VALGRIND_MAKE_MEM_UNDEFINED(
+					    ret, size);
+					memset(ret, 0, size);
+				}
+				if (!*commit)
+					*commit = pages_decommit(ret, size);
+				return (ret);
+			}
+
+			/*
+			 * Failure, whether due to OOM or a race with a raw
+			 * sbrk() call from outside the allocator.  Try to roll
+			 * back optimistic dss_max update; if rollback fails,
+			 * it's due to another caller of this function having
+			 * succeeded since this invocation started, in which
+			 * case rollback is not necessary.
+			 */
+			atomic_cas_p(&dss_max, dss_next, max_cur);
+			if (dss_prev == (void *)-1) {
+				/* OOM. */
+				atomic_write_u(&dss_exhausted, (unsigned)true);
+				goto label_oom;
+			}
+		}
+	}
+label_oom:
+	return (NULL);
+}
+
+static bool
+chunk_in_dss_helper(void *chunk, void *max)
+{
+
+	return ((uintptr_t)chunk >= (uintptr_t)dss_base && (uintptr_t)chunk <
+	    (uintptr_t)max);
+}
+
+bool
+chunk_in_dss(void *chunk)
+{
+
+	cassert(have_dss);
+
+	return (chunk_in_dss_helper(chunk, atomic_read_p(&dss_max)));
+}
+
+bool
+chunk_dss_mergeable(void *chunk_a, void *chunk_b)
+{
+	void *max;
+
+	cassert(have_dss);
+
+	max = atomic_read_p(&dss_max);
+	return (chunk_in_dss_helper(chunk_a, max) ==
+	    chunk_in_dss_helper(chunk_b, max));
+}
+
+void
+chunk_dss_boot(void)
+{
+
+	cassert(have_dss);
+
+	dss_base = chunk_dss_sbrk(0);
+	dss_exhausted = (unsigned)(dss_base == (void *)-1);
+	dss_max = dss_base;
+}
+
+/******************************************************************************/
diff --git a/deps/jemalloc/src/chunk_mmap.c b/deps/jemalloc/src/chunk_mmap.c
new file mode 100644
index 0000000..73fc497
--- /dev/null
+++ b/deps/jemalloc/src/chunk_mmap.c
@@ -0,0 +1,78 @@
+#define	JEMALLOC_CHUNK_MMAP_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+
+static void *
+chunk_alloc_mmap_slow(size_t size, size_t alignment, bool *zero, bool *commit)
+{
+	void *ret;
+	size_t alloc_size;
+
+	alloc_size = size + alignment - PAGE;
+	/* Beware size_t wrap-around. */
+	if (alloc_size < size)
+		return (NULL);
+	do {
+		void *pages;
+		size_t leadsize;
+		pages = pages_map(NULL, alloc_size, commit);
+		if (pages == NULL)
+			return (NULL);
+		leadsize = ALIGNMENT_CEILING((uintptr_t)pages, alignment) -
+		    (uintptr_t)pages;
+		ret = pages_trim(pages, alloc_size, leadsize, size, commit);
+	} while (ret == NULL);
+
+	assert(ret != NULL);
+	*zero = true;
+	return (ret);
+}
+
+void *
+chunk_alloc_mmap(void *new_addr, size_t size, size_t alignment, bool *zero,
+    bool *commit)
+{
+	void *ret;
+	size_t offset;
+
+	/*
+	 * 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
+	 * pages_unmap().
+	 *
+	 * 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.
+	 */
+
+	assert(alignment != 0);
+	assert((alignment & chunksize_mask) == 0);
+
+	ret = pages_map(new_addr, size, commit);
+	if (ret == NULL || ret == new_addr)
+		return (ret);
+	assert(new_addr == NULL);
+	offset = ALIGNMENT_ADDR2OFFSET(ret, alignment);
+	if (offset != 0) {
+		pages_unmap(ret, size);
+		return (chunk_alloc_mmap_slow(size, alignment, zero, commit));
+	}
+
+	assert(ret != NULL);
+	*zero = true;
+	return (ret);
+}
+
+bool
+chunk_dalloc_mmap(void *chunk, size_t size)
+{
+
+	if (config_munmap)
+		pages_unmap(chunk, size);
+
+	return (!config_munmap);
+}
diff --git a/deps/jemalloc/src/ckh.c b/deps/jemalloc/src/ckh.c
new file mode 100644
index 0000000..159bd8a
--- /dev/null
+++ b/deps/jemalloc/src/ckh.c
@@ -0,0 +1,569 @@
+/*
+ *******************************************************************************
+ * Implementation of (2^1+,2) cuckoo hashing, where 2^1+ indicates that each
+ * hash bucket contains 2^n cells, for n >= 1, and 2 indicates that two hash
+ * functions are employed.  The original cuckoo hashing algorithm was described
+ * in:
+ *
+ *   Pagh, R., F.F. Rodler (2004) Cuckoo Hashing.  Journal of Algorithms
+ *     51(2):122-144.
+ *
+ * Generalization of cuckoo hashing was discussed in:
+ *
+ *   Erlingsson, U., M. Manasse, F. McSherry (2006) A cool and practical
+ *     alternative to traditional hash tables.  In Proceedings of the 7th
+ *     Workshop on Distributed Data and Structures (WDAS'06), Santa Clara, CA,
+ *     January 2006.
+ *
+ * This implementation uses precisely two hash functions because that is the
+ * fewest that can work, and supporting multiple hashes is an implementation
+ * burden.  Here is a reproduction of Figure 1 from Erlingsson et al. (2006)
+ * that shows approximate expected maximum load factors for various
+ * configurations:
+ *
+ *           |         #cells/bucket         |
+ *   #hashes |   1   |   2   |   4   |   8   |
+ *   --------+-------+-------+-------+-------+
+ *         1 | 0.006 | 0.006 | 0.03  | 0.12  |
+ *         2 | 0.49  | 0.86  |>0.93< |>0.96< |
+ *         3 | 0.91  | 0.97  | 0.98  | 0.999 |
+ *         4 | 0.97  | 0.99  | 0.999 |       |
+ *
+ * The number of cells per bucket is chosen such that a bucket fits in one cache
+ * line.  So, on 32- and 64-bit systems, we use (8,2) and (4,2) cuckoo hashing,
+ * respectively.
+ *
+ ******************************************************************************/
+#define	JEMALLOC_CKH_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Function prototypes for non-inline static functions. */
+
+static bool	ckh_grow(tsd_t *tsd, ckh_t *ckh);
+static void	ckh_shrink(tsd_t *tsd, 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)
+{
+	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);
+	}
+
+	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)
+{
+	size_t hashes[2], bucket, cell;
+
+	assert(ckh != NULL);
+
+	ckh->hash(key, hashes);
+
+	/* 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);
+
+	/* Search secondary bucket. */
+	bucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1);
+	cell = ckh_bucket_search(ckh, bucket, key);
+	return (cell);
+}
+
+JEMALLOC_INLINE_C bool
+ckh_try_bucket_insert(ckh_t *ckh, size_t bucket, const void *key,
+    const void *data)
+{
+	ckhc_t *cell;
+	unsigned offset, i;
+
+	/*
+	 * Cycle through the cells in the bucket, starting at a random position.
+	 * The randomness avoids worst-case search overhead as buckets fill up.
+	 */
+	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))];
+		if (cell->key == NULL) {
+			cell->key = key;
+			cell->data = data;
+			ckh->count++;
+			return (false);
+		}
+	}
+
+	return (true);
+}
+
+/*
+ * No space is available in bucket.  Randomly evict an item, then try to find an
+ * alternate location for that item.  Iteratively repeat this
+ * eviction/relocation procedure until either success or detection of an
+ * eviction/relocation bucket cycle.
+ */
+JEMALLOC_INLINE_C bool
+ckh_evict_reloc_insert(ckh_t *ckh, size_t argbucket, void const **argkey,
+    void const **argdata)
+{
+	const void *key, *data, *tkey, *tdata;
+	ckhc_t *cell;
+	size_t hashes[2], bucket, tbucket;
+	unsigned i;
+
+	bucket = argbucket;
+	key = *argkey;
+	data = *argdata;
+	while (true) {
+		/*
+		 * Choose a random item within the bucket to evict.  This is
+		 * critical to correct function, because without (eventually)
+		 * evicting all items within a bucket during iteration, it
+		 * would be possible to get stuck in an infinite loop if there
+		 * were an item for which both hashes indicated the same
+		 * bucket.
+		 */
+		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);
+
+		/* Swap cell->{key,data} and {key,data} (evict). */
+		tkey = cell->key; tdata = cell->data;
+		cell->key = key; cell->data = data;
+		key = tkey; data = tdata;
+
+#ifdef CKH_COUNT
+		ckh->nrelocs++;
+#endif
+
+		/* Find the alternate bucket for the evicted item. */
+		ckh->hash(key, hashes);
+		tbucket = hashes[1] & ((ZU(1) << ckh->lg_curbuckets) - 1);
+		if (tbucket == bucket) {
+			tbucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets)
+			    - 1);
+			/*
+			 * It may be that (tbucket == bucket) still, if the
+			 * item's hashes both indicate this bucket.  However,
+			 * we are guaranteed to eventually escape this bucket
+			 * during iteration, assuming pseudo-random item
+			 * selection (true randomness would make infinite
+			 * looping a remote possibility).  The reason we can
+			 * never get trapped forever is that there are two
+			 * cases:
+			 *
+			 * 1) This bucket == argbucket, so we will quickly
+			 *    detect an eviction cycle and terminate.
+			 * 2) An item was evicted to this bucket from another,
+			 *    which means that at least one item in this bucket
+			 *    has hashes that indicate distinct buckets.
+			 */
+		}
+		/* Check for a cycle. */
+		if (tbucket == argbucket) {
+			*argkey = key;
+			*argdata = data;
+			return (true);
+		}
+
+		bucket = tbucket;
+		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)
+{
+	size_t hashes[2], bucket;
+	const void *key = *argkey;
+	const void *data = *argdata;
+
+	ckh->hash(key, hashes);
+
+	/* Try to insert in primary bucket. */
+	bucket = hashes[0] & ((ZU(1) << ckh->lg_curbuckets) - 1);
+	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))
+		return (false);
+
+	/*
+	 * Try to find a place for this item via iterative eviction/relocation.
+	 */
+	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)
+{
+	size_t count, i, nins;
+	const void *key, *data;
+
+	count = ckh->count;
+	ckh->count = 0;
+	for (i = nins = 0; nins < count; i++) {
+		if (aTab[i].key != NULL) {
+			key = aTab[i].key;
+			data = aTab[i].data;
+			if (ckh_try_insert(ckh, &key, &data)) {
+				ckh->count = count;
+				return (true);
+			}
+			nins++;
+		}
+	}
+
+	return (false);
+}
+
+static bool
+ckh_grow(tsd_t *tsd, ckh_t *ckh)
+{
+	bool ret;
+	ckhc_t *tab, *ttab;
+	unsigned lg_prevbuckets, lg_curcells;
+
+#ifdef CKH_COUNT
+	ckh->ngrows++;
+#endif
+
+	/*
+	 * It is possible (though unlikely, given well behaved hashes) that the
+	 * table will have to be doubled more than once in order to create a
+	 * usable table.
+	 */
+	lg_prevbuckets = ckh->lg_curbuckets;
+	lg_curcells = ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS;
+	while (true) {
+		size_t usize;
+
+		lg_curcells++;
+		usize = sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
+		if (unlikely(usize == 0 || usize > HUGE_MAXCLASS)) {
+			ret = true;
+			goto label_return;
+		}
+		tab = (ckhc_t *)ipallocztm(tsd_tsdn(tsd), usize, CACHELINE,
+		    true, NULL, true, arena_ichoose(tsd, NULL));
+		if (tab == NULL) {
+			ret = true;
+			goto label_return;
+		}
+		/* Swap in new table. */
+		ttab = ckh->tab;
+		ckh->tab = tab;
+		tab = ttab;
+		ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS;
+
+		if (!ckh_rebuild(ckh, tab)) {
+			idalloctm(tsd_tsdn(tsd), tab, NULL, true, true);
+			break;
+		}
+
+		/* Rebuilding failed, so back out partially rebuilt table. */
+		idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, true, true);
+		ckh->tab = tab;
+		ckh->lg_curbuckets = lg_prevbuckets;
+	}
+
+	ret = false;
+label_return:
+	return (ret);
+}
+
+static void
+ckh_shrink(tsd_t *tsd, ckh_t *ckh)
+{
+	ckhc_t *tab, *ttab;
+	size_t usize;
+	unsigned lg_prevbuckets, lg_curcells;
+
+	/*
+	 * It is possible (though unlikely, given well behaved hashes) that the
+	 * table rebuild will fail.
+	 */
+	lg_prevbuckets = ckh->lg_curbuckets;
+	lg_curcells = ckh->lg_curbuckets + LG_CKH_BUCKET_CELLS - 1;
+	usize = sa2u(sizeof(ckhc_t) << lg_curcells, CACHELINE);
+	if (unlikely(usize == 0 || usize > HUGE_MAXCLASS))
+		return;
+	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
+		 * prevent this or future operations from proceeding.
+		 */
+		return;
+	}
+	/* Swap in new table. */
+	ttab = ckh->tab;
+	ckh->tab = tab;
+	tab = ttab;
+	ckh->lg_curbuckets = lg_curcells - LG_CKH_BUCKET_CELLS;
+
+	if (!ckh_rebuild(ckh, tab)) {
+		idalloctm(tsd_tsdn(tsd), tab, NULL, true, true);
+#ifdef CKH_COUNT
+		ckh->nshrinks++;
+#endif
+		return;
+	}
+
+	/* Rebuilding failed, so back out partially rebuilt table. */
+	idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, true, true);
+	ckh->tab = tab;
+	ckh->lg_curbuckets = lg_prevbuckets;
+#ifdef CKH_COUNT
+	ckh->nshrinkfails++;
+#endif
+}
+
+bool
+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;
+
+	assert(minitems > 0);
+	assert(hash != NULL);
+	assert(keycomp != NULL);
+
+#ifdef CKH_COUNT
+	ckh->ngrows = 0;
+	ckh->nshrinks = 0;
+	ckh->nshrinkfails = 0;
+	ckh->ninserts = 0;
+	ckh->nrelocs = 0;
+#endif
+	ckh->prng_state = 42; /* Value doesn't really matter. */
+	ckh->count = 0;
+
+	/*
+	 * 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 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. */
+	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 (unlikely(usize == 0 || usize > HUGE_MAXCLASS)) {
+		ret = true;
+		goto label_return;
+	}
+	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;
+	}
+
+	ret = false;
+label_return:
+	return (ret);
+}
+
+void
+ckh_delete(tsd_t *tsd, ckh_t *ckh)
+{
+
+	assert(ckh != NULL);
+
+#ifdef CKH_VERBOSE
+	malloc_printf(
+	    "%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,
+	    (unsigned long long)ckh->ninserts,
+	    (unsigned long long)ckh->nrelocs);
+#endif
+
+	idalloctm(tsd_tsdn(tsd), ckh->tab, NULL, true, true);
+	if (config_debug)
+		memset(ckh, JEMALLOC_FREE_JUNK, sizeof(ckh_t));
+}
+
+size_t
+ckh_count(ckh_t *ckh)
+{
+
+	assert(ckh != NULL);
+
+	return (ckh->count);
+}
+
+bool
+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)
+				*key = (void *)ckh->tab[i].key;
+			if (data != NULL)
+				*data = (void *)ckh->tab[i].data;
+			*tabind = i + 1;
+			return (false);
+		}
+	}
+
+	return (true);
+}
+
+bool
+ckh_insert(tsd_t *tsd, ckh_t *ckh, const void *key, const void *data)
+{
+	bool ret;
+
+	assert(ckh != NULL);
+	assert(ckh_search(ckh, key, NULL, NULL));
+
+#ifdef CKH_COUNT
+	ckh->ninserts++;
+#endif
+
+	while (ckh_try_insert(ckh, &key, &data)) {
+		if (ckh_grow(tsd, ckh)) {
+			ret = true;
+			goto label_return;
+		}
+	}
+
+	ret = false;
+label_return:
+	return (ret);
+}
+
+bool
+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)
+			*key = (void *)ckh->tab[cell].key;
+		if (data != NULL)
+			*data = (void *)ckh->tab[cell].data;
+		ckh->tab[cell].key = NULL;
+		ckh->tab[cell].data = NULL; /* Not necessary. */
+
+		ckh->count--;
+		/* Try to halve the table if it is less than 1/4 full. */
+		if (ckh->count < (ZU(1) << (ckh->lg_curbuckets
+		    + LG_CKH_BUCKET_CELLS - 2)) && ckh->lg_curbuckets
+		    > ckh->lg_minbuckets) {
+			/* Ignore error due to OOM. */
+			ckh_shrink(tsd, ckh);
+		}
+
+		return (false);
+	}
+
+	return (true);
+}
+
+bool
+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)
+			*key = (void *)ckh->tab[cell].key;
+		if (data != NULL)
+			*data = (void *)ckh->tab[cell].data;
+		return (false);
+	}
+
+	return (true);
+}
+
+void
+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);
+
+    return (strcmp((char *)k1, (char *)k2) ? false : true);
+}
+
+void
+ckh_pointer_hash(const void *key, size_t r_hash[2])
+{
+	union {
+		const void	*v;
+		size_t		i;
+	} u;
+
+	assert(sizeof(u.v) == sizeof(u.i));
+	u.v = key;
+	hash(&u.i, sizeof(u.i), 0xd983396eU, r_hash);
+}
+
+bool
+ckh_pointer_keycomp(const void *k1, const void *k2)
+{
+
+	return ((k1 == k2) ? true : false);
+}
diff --git a/deps/jemalloc/src/ctl.c b/deps/jemalloc/src/ctl.c
new file mode 100644
index 0000000..bc78b20
--- /dev/null
+++ b/deps/jemalloc/src/ctl.c
@@ -0,0 +1,2254 @@
+#define	JEMALLOC_CTL_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+/*
+ * ctl_mtx protects the following:
+ * - ctl_stats.*
+ */
+static malloc_mutex_t	ctl_mtx;
+static bool		ctl_initialized;
+static uint64_t		ctl_epoch;
+static ctl_stats_t	ctl_stats;
+
+/******************************************************************************/
+/* Helpers for named and indexed nodes. */
+
+JEMALLOC_INLINE_C const ctl_named_node_t *
+ctl_named_node(const ctl_node_t *node)
+{
+
+	return ((node->named) ? (const ctl_named_node_t *)node : NULL);
+}
+
+JEMALLOC_INLINE_C 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);
+}
+
+JEMALLOC_INLINE_C 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(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);
+
+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(tsdn_t *tsdn, 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(tsdn_t *tsdn, arena_t *arena, unsigned i);
+static bool	ctl_grow(tsdn_t *tsdn);
+static void	ctl_refresh(tsdn_t *tsdn);
+static bool	ctl_init(tsdn_t *tsdn);
+static int	ctl_lookup(tsdn_t *tsdn, const char *name,
+    ctl_node_t const **nodesp, size_t *mibp, size_t *depthp);
+
+CTL_PROTO(version)
+CTL_PROTO(epoch)
+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_fill)
+CTL_PROTO(config_lazy_lock)
+CTL_PROTO(config_malloc_conf)
+CTL_PROTO(config_munmap)
+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_utrace)
+CTL_PROTO(config_valgrind)
+CTL_PROTO(config_xmalloc)
+CTL_PROTO(opt_abort)
+CTL_PROTO(opt_dss)
+CTL_PROTO(opt_lg_chunk)
+CTL_PROTO(opt_narenas)
+CTL_PROTO(opt_purge)
+CTL_PROTO(opt_lg_dirty_mult)
+CTL_PROTO(opt_decay_time)
+CTL_PROTO(opt_stats_print)
+CTL_PROTO(opt_junk)
+CTL_PROTO(opt_zero)
+CTL_PROTO(opt_quarantine)
+CTL_PROTO(opt_redzone)
+CTL_PROTO(opt_utrace)
+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)
+static void	arena_i_purge(tsdn_t *tsdn, unsigned arena_ind, bool all);
+CTL_PROTO(arena_i_purge)
+CTL_PROTO(arena_i_decay)
+CTL_PROTO(arena_i_reset)
+CTL_PROTO(arena_i_dss)
+CTL_PROTO(arena_i_lg_dirty_mult)
+CTL_PROTO(arena_i_decay_time)
+CTL_PROTO(arena_i_chunk_hooks)
+INDEX_PROTO(arena_i)
+CTL_PROTO(arenas_bin_i_size)
+CTL_PROTO(arenas_bin_i_nregs)
+CTL_PROTO(arenas_bin_i_run_size)
+INDEX_PROTO(arenas_bin_i)
+CTL_PROTO(arenas_lrun_i_size)
+INDEX_PROTO(arenas_lrun_i)
+CTL_PROTO(arenas_hchunk_i_size)
+INDEX_PROTO(arenas_hchunk_i)
+CTL_PROTO(arenas_narenas)
+CTL_PROTO(arenas_initialized)
+CTL_PROTO(arenas_lg_dirty_mult)
+CTL_PROTO(arenas_decay_time)
+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_nhchunks)
+CTL_PROTO(arenas_extend)
+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(lg_prof_sample)
+CTL_PROTO(stats_arenas_i_small_allocated)
+CTL_PROTO(stats_arenas_i_small_nmalloc)
+CTL_PROTO(stats_arenas_i_small_ndalloc)
+CTL_PROTO(stats_arenas_i_small_nrequests)
+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_huge_allocated)
+CTL_PROTO(stats_arenas_i_huge_nmalloc)
+CTL_PROTO(stats_arenas_i_huge_ndalloc)
+CTL_PROTO(stats_arenas_i_huge_nrequests)
+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)
+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_hchunks_j_nmalloc)
+CTL_PROTO(stats_arenas_i_hchunks_j_ndalloc)
+CTL_PROTO(stats_arenas_i_hchunks_j_nrequests)
+CTL_PROTO(stats_arenas_i_hchunks_j_curhchunks)
+INDEX_PROTO(stats_arenas_i_hchunks_j)
+CTL_PROTO(stats_arenas_i_nthreads)
+CTL_PROTO(stats_arenas_i_dss)
+CTL_PROTO(stats_arenas_i_lg_dirty_mult)
+CTL_PROTO(stats_arenas_i_decay_time)
+CTL_PROTO(stats_arenas_i_pactive)
+CTL_PROTO(stats_arenas_i_pdirty)
+CTL_PROTO(stats_arenas_i_mapped)
+CTL_PROTO(stats_arenas_i_retained)
+CTL_PROTO(stats_arenas_i_npurge)
+CTL_PROTO(stats_arenas_i_nmadvise)
+CTL_PROTO(stats_arenas_i_purged)
+CTL_PROTO(stats_arenas_i_metadata_mapped)
+CTL_PROTO(stats_arenas_i_metadata_allocated)
+INDEX_PROTO(stats_arenas_i)
+CTL_PROTO(stats_cactive)
+CTL_PROTO(stats_allocated)
+CTL_PROTO(stats_active)
+CTL_PROTO(stats_metadata)
+CTL_PROTO(stats_resident)
+CTL_PROTO(stats_mapped)
+CTL_PROTO(stats_retained)
+
+/******************************************************************************/
+/* mallctl tree. */
+
+/* Maximum tree depth. */
+#define	CTL_MAX_DEPTH	6
+
+#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
+
+/*
+ * Only handles internal indexed nodes, since there are currently no external
+ * ones.
+ */
+#define	INDEX(i)	{false},	i##_index
+
+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, thread_tcache)},
+	{NAME("prof"),		CHILD(named, thread_prof)}
+};
+
+static const ctl_named_node_t	config_node[] = {
+	{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("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)}
+};
+
+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("purge"),		CTL(opt_purge)},
+	{NAME("lg_dirty_mult"),	CTL(opt_lg_dirty_mult)},
+	{NAME("decay_time"),	CTL(opt_decay_time)},
+	{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("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("decay"),		CTL(arena_i_decay)},
+	{NAME("reset"),		CTL(arena_i_reset)},
+	{NAME("dss"),		CTL(arena_i_dss)},
+	{NAME("lg_dirty_mult"),	CTL(arena_i_lg_dirty_mult)},
+	{NAME("decay_time"),	CTL(arena_i_decay_time)},
+	{NAME("chunk_hooks"),	CTL(arena_i_chunk_hooks)}
+};
+static const ctl_named_node_t super_arena_i_node[] = {
+	{NAME(""),		CHILD(named, arena_i)}
+};
+
+static const ctl_indexed_node_t arena_node[] = {
+	{INDEX(arena_i)}
+};
+
+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)}
+};
+static const ctl_named_node_t super_arenas_bin_i_node[] = {
+	{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 super_arenas_lrun_i_node[] = {
+	{NAME(""),		CHILD(named, arenas_lrun_i)}
+};
+
+static const ctl_indexed_node_t arenas_lrun_node[] = {
+	{INDEX(arenas_lrun_i)}
+};
+
+static const ctl_named_node_t arenas_hchunk_i_node[] = {
+	{NAME("size"),		CTL(arenas_hchunk_i_size)}
+};
+static const ctl_named_node_t super_arenas_hchunk_i_node[] = {
+	{NAME(""),		CHILD(named, arenas_hchunk_i)}
+};
+
+static const ctl_indexed_node_t arenas_hchunk_node[] = {
+	{INDEX(arenas_hchunk_i)}
+};
+
+static const ctl_named_node_t arenas_node[] = {
+	{NAME("narenas"),	CTL(arenas_narenas)},
+	{NAME("initialized"),	CTL(arenas_initialized)},
+	{NAME("lg_dirty_mult"),	CTL(arenas_lg_dirty_mult)},
+	{NAME("decay_time"),	CTL(arenas_decay_time)},
+	{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("nhchunks"),	CTL(arenas_nhchunks)},
+	{NAME("hchunk"),	CHILD(indexed, arenas_hchunk)},
+	{NAME("extend"),	CTL(arenas_extend)}
+};
+
+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("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_arenas_i_metadata_node[] = {
+	{NAME("mapped"),	CTL(stats_arenas_i_metadata_mapped)},
+	{NAME("allocated"),	CTL(stats_arenas_i_metadata_allocated)}
+};
+
+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_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_huge_node[] = {
+	{NAME("allocated"),	CTL(stats_arenas_i_huge_allocated)},
+	{NAME("nmalloc"),	CTL(stats_arenas_i_huge_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_huge_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_huge_nrequests)}
+};
+
+static const ctl_named_node_t stats_arenas_i_bins_j_node[] = {
+	{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("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)}
+};
+static const ctl_named_node_t super_stats_arenas_i_bins_j_node[] = {
+	{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 super_stats_arenas_i_lruns_j_node[] = {
+	{NAME(""),		CHILD(named, stats_arenas_i_lruns_j)}
+};
+
+static const ctl_indexed_node_t stats_arenas_i_lruns_node[] = {
+	{INDEX(stats_arenas_i_lruns_j)}
+};
+
+static const ctl_named_node_t stats_arenas_i_hchunks_j_node[] = {
+	{NAME("nmalloc"),	CTL(stats_arenas_i_hchunks_j_nmalloc)},
+	{NAME("ndalloc"),	CTL(stats_arenas_i_hchunks_j_ndalloc)},
+	{NAME("nrequests"),	CTL(stats_arenas_i_hchunks_j_nrequests)},
+	{NAME("curhchunks"),	CTL(stats_arenas_i_hchunks_j_curhchunks)}
+};
+static const ctl_named_node_t super_stats_arenas_i_hchunks_j_node[] = {
+	{NAME(""),		CHILD(named, stats_arenas_i_hchunks_j)}
+};
+
+static const ctl_indexed_node_t stats_arenas_i_hchunks_node[] = {
+	{INDEX(stats_arenas_i_hchunks_j)}
+};
+
+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("lg_dirty_mult"),	CTL(stats_arenas_i_lg_dirty_mult)},
+	{NAME("decay_time"),	CTL(stats_arenas_i_decay_time)},
+	{NAME("pactive"),	CTL(stats_arenas_i_pactive)},
+	{NAME("pdirty"),	CTL(stats_arenas_i_pdirty)},
+	{NAME("mapped"),	CTL(stats_arenas_i_mapped)},
+	{NAME("retained"),	CTL(stats_arenas_i_retained)},
+	{NAME("npurge"),	CTL(stats_arenas_i_npurge)},
+	{NAME("nmadvise"),	CTL(stats_arenas_i_nmadvise)},
+	{NAME("purged"),	CTL(stats_arenas_i_purged)},
+	{NAME("metadata"),	CHILD(named, stats_arenas_i_metadata)},
+	{NAME("small"),		CHILD(named, stats_arenas_i_small)},
+	{NAME("large"),		CHILD(named, stats_arenas_i_large)},
+	{NAME("huge"),		CHILD(named, stats_arenas_i_huge)},
+	{NAME("bins"),		CHILD(indexed, stats_arenas_i_bins)},
+	{NAME("lruns"),		CHILD(indexed, stats_arenas_i_lruns)},
+	{NAME("hchunks"),	CHILD(indexed, stats_arenas_i_hchunks)}
+};
+static const ctl_named_node_t super_stats_arenas_i_node[] = {
+	{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_node[] = {
+	{NAME("cactive"),	CTL(stats_cactive)},
+	{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("arenas"),	CHILD(indexed, stats_arenas)}
+};
+
+static const ctl_named_node_t	root_node[] = {
+	{NAME("version"),	CTL(version)},
+	{NAME("epoch"),		CTL(epoch)},
+	{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)},
+	{NAME("stats"),		CHILD(named, stats)}
+};
+static const ctl_named_node_t super_root_node[] = {
+	{NAME(""),		CHILD(named, root)}
+};
+
+#undef NAME
+#undef CHILD
+#undef CTL
+#undef INDEX
+
+/******************************************************************************/
+
+static bool
+ctl_arena_init(ctl_arena_stats_t *astats)
+{
+
+	if (astats->lstats == NULL) {
+		astats->lstats = (malloc_large_stats_t *)a0malloc(nlclasses *
+		    sizeof(malloc_large_stats_t));
+		if (astats->lstats == NULL)
+			return (true);
+	}
+
+	if (astats->hstats == NULL) {
+		astats->hstats = (malloc_huge_stats_t *)a0malloc(nhclasses *
+		    sizeof(malloc_huge_stats_t));
+		if (astats->hstats == NULL)
+			return (true);
+	}
+
+	return (false);
+}
+
+static void
+ctl_arena_clear(ctl_arena_stats_t *astats)
+{
+
+	astats->nthreads = 0;
+	astats->dss = dss_prec_names[dss_prec_limit];
+	astats->lg_dirty_mult = -1;
+	astats->decay_time = -1;
+	astats->pactive = 0;
+	astats->pdirty = 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 *
+		    sizeof(malloc_large_stats_t));
+		memset(astats->hstats, 0, nhclasses *
+		    sizeof(malloc_huge_stats_t));
+	}
+}
+
+static void
+ctl_arena_stats_amerge(tsdn_t *tsdn, ctl_arena_stats_t *cstats, arena_t *arena)
+{
+	unsigned i;
+
+	if (config_stats) {
+		arena_stats_merge(tsdn, arena, &cstats->nthreads, &cstats->dss,
+		    &cstats->lg_dirty_mult, &cstats->decay_time,
+		    &cstats->pactive, &cstats->pdirty, &cstats->astats,
+		    cstats->bstats, cstats->lstats, cstats->hstats);
+
+		for (i = 0; i < NBINS; i++) {
+			cstats->allocated_small += cstats->bstats[i].curregs *
+			    index2size(i);
+			cstats->nmalloc_small += cstats->bstats[i].nmalloc;
+			cstats->ndalloc_small += cstats->bstats[i].ndalloc;
+			cstats->nrequests_small += cstats->bstats[i].nrequests;
+		}
+	} else {
+		arena_basic_stats_merge(tsdn, arena, &cstats->nthreads,
+		    &cstats->dss, &cstats->lg_dirty_mult, &cstats->decay_time,
+		    &cstats->pactive, &cstats->pdirty);
+	}
+}
+
+static void
+ctl_arena_stats_smerge(ctl_arena_stats_t *sstats, ctl_arena_stats_t *astats)
+{
+	unsigned i;
+
+	sstats->nthreads += astats->nthreads;
+	sstats->pactive += astats->pactive;
+	sstats->pdirty += astats->pdirty;
+
+	if (config_stats) {
+		sstats->astats.mapped += astats->astats.mapped;
+		sstats->astats.retained += astats->astats.retained;
+		sstats->astats.npurge += astats->astats.npurge;
+		sstats->astats.nmadvise += astats->astats.nmadvise;
+		sstats->astats.purged += astats->astats.purged;
+
+		sstats->astats.metadata_mapped +=
+		    astats->astats.metadata_mapped;
+		sstats->astats.metadata_allocated +=
+		    astats->astats.metadata_allocated;
+
+		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;
+
+		sstats->astats.allocated_huge += astats->astats.allocated_huge;
+		sstats->astats.nmalloc_huge += astats->astats.nmalloc_huge;
+		sstats->astats.ndalloc_huge += astats->astats.ndalloc_huge;
+
+		for (i = 0; i < NBINS; i++) {
+			sstats->bstats[i].nmalloc += astats->bstats[i].nmalloc;
+			sstats->bstats[i].ndalloc += astats->bstats[i].ndalloc;
+			sstats->bstats[i].nrequests +=
+			    astats->bstats[i].nrequests;
+			sstats->bstats[i].curregs += astats->bstats[i].curregs;
+			if (config_tcache) {
+				sstats->bstats[i].nfills +=
+				    astats->bstats[i].nfills;
+				sstats->bstats[i].nflushes +=
+				    astats->bstats[i].nflushes;
+			}
+			sstats->bstats[i].nruns += astats->bstats[i].nruns;
+			sstats->bstats[i].reruns += astats->bstats[i].reruns;
+			sstats->bstats[i].curruns += astats->bstats[i].curruns;
+		}
+
+		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 < nhclasses; i++) {
+			sstats->hstats[i].nmalloc += astats->hstats[i].nmalloc;
+			sstats->hstats[i].ndalloc += astats->hstats[i].ndalloc;
+			sstats->hstats[i].curhchunks +=
+			    astats->hstats[i].curhchunks;
+		}
+	}
+}
+
+static void
+ctl_arena_refresh(tsdn_t *tsdn, 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_clear(astats);
+	ctl_arena_stats_amerge(tsdn, astats, arena);
+	/* Merge into sum stats as well. */
+	ctl_arena_stats_smerge(sstats, astats);
+}
+
+static bool
+ctl_grow(tsdn_t *tsdn)
+{
+	ctl_arena_stats_t *astats;
+
+	/* Initialize new arena. */
+	if (arena_init(tsdn, ctl_stats.narenas) == NULL)
+		return (true);
+
+	/* Allocate extended arena stats. */
+	astats = (ctl_arena_stats_t *)a0malloc((ctl_stats.narenas + 2) *
+	    sizeof(ctl_arena_stats_t));
+	if (astats == NULL)
+		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])) {
+		a0dalloc(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));
+	}
+	a0dalloc(ctl_stats.arenas);
+	ctl_stats.arenas = astats;
+	ctl_stats.narenas++;
+
+	return (false);
+}
+
+static void
+ctl_refresh(tsdn_t *tsdn)
+{
+	unsigned i;
+	VARIABLE_ARRAY(arena_t *, tarenas, ctl_stats.narenas);
+
+	/*
+	 * Clear sum stats, since they will be merged into by
+	 * ctl_arena_refresh().
+	 */
+	ctl_arena_clear(&ctl_stats.arenas[ctl_stats.narenas]);
+
+	for (i = 0; i < ctl_stats.narenas; i++)
+		tarenas[i] = arena_get(tsdn, i, false);
+
+	for (i = 0; i < ctl_stats.narenas; i++) {
+		bool initialized = (tarenas[i] != NULL);
+
+		ctl_stats.arenas[i].initialized = initialized;
+		if (initialized)
+			ctl_arena_refresh(tsdn, tarenas[i], i);
+	}
+
+	if (config_stats) {
+		size_t base_allocated, base_resident, base_mapped;
+		base_stats_get(tsdn, &base_allocated, &base_resident,
+		    &base_mapped);
+		ctl_stats.allocated =
+		    ctl_stats.arenas[ctl_stats.narenas].allocated_small +
+		    ctl_stats.arenas[ctl_stats.narenas].astats.allocated_large +
+		    ctl_stats.arenas[ctl_stats.narenas].astats.allocated_huge;
+		ctl_stats.active =
+		    (ctl_stats.arenas[ctl_stats.narenas].pactive << LG_PAGE);
+		ctl_stats.metadata = base_allocated +
+		    ctl_stats.arenas[ctl_stats.narenas].astats.metadata_mapped +
+		    ctl_stats.arenas[ctl_stats.narenas].astats
+		    .metadata_allocated;
+		ctl_stats.resident = base_resident +
+		    ctl_stats.arenas[ctl_stats.narenas].astats.metadata_mapped +
+		    ((ctl_stats.arenas[ctl_stats.narenas].pactive +
+		    ctl_stats.arenas[ctl_stats.narenas].pdirty) << LG_PAGE);
+		ctl_stats.mapped = base_mapped +
+		    ctl_stats.arenas[ctl_stats.narenas].astats.mapped;
+		ctl_stats.retained =
+		    ctl_stats.arenas[ctl_stats.narenas].astats.retained;
+	}
+
+	ctl_epoch++;
+}
+
+static bool
+ctl_init(tsdn_t *tsdn)
+{
+	bool ret;
+
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	if (!ctl_initialized) {
+		/*
+		 * Allocate space for one extra arena stats element, which
+		 * contains summed stats across all arenas.
+		 */
+		ctl_stats.narenas = narenas_total_get();
+		ctl_stats.arenas = (ctl_arena_stats_t *)a0malloc(
+		    (ctl_stats.narenas + 1) * sizeof(ctl_arena_stats_t));
+		if (ctl_stats.arenas == NULL) {
+			ret = true;
+			goto label_return;
+		}
+		memset(ctl_stats.arenas, 0, (ctl_stats.narenas + 1) *
+		    sizeof(ctl_arena_stats_t));
+
+		/*
+		 * 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.
+		 */
+		if (config_stats) {
+			unsigned i;
+			for (i = 0; i <= ctl_stats.narenas; i++) {
+				if (ctl_arena_init(&ctl_stats.arenas[i])) {
+					unsigned j;
+					for (j = 0; j < i; j++) {
+						a0dalloc(
+						    ctl_stats.arenas[j].lstats);
+						a0dalloc(
+						    ctl_stats.arenas[j].hstats);
+					}
+					a0dalloc(ctl_stats.arenas);
+					ctl_stats.arenas = NULL;
+					ret = true;
+					goto label_return;
+				}
+			}
+		}
+		ctl_stats.arenas[ctl_stats.narenas].initialized = true;
+
+		ctl_epoch = 0;
+		ctl_refresh(tsdn);
+		ctl_initialized = true;
+	}
+
+	ret = false;
+label_return:
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return (ret);
+}
+
+static int
+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;
+	const ctl_named_node_t *node;
+
+	elm = name;
+	/* Equivalent to strchrnul(). */
+	dot = ((tdot = strchr(elm, '.')) != NULL) ? tdot : strchr(elm, '\0');
+	elen = (size_t)((uintptr_t)dot - (uintptr_t)elm);
+	if (elen == 0) {
+		ret = ENOENT;
+		goto label_return;
+	}
+	node = super_root_node;
+	for (i = 0; i < *depthp; i++) {
+		assert(node);
+		assert(node->nchildren > 0);
+		if (ctl_named_node(node->children) != NULL) {
+			const ctl_named_node_t *pnode = node;
+
+			/* Children are named. */
+			for (j = 0; j < node->nchildren; j++) {
+				const ctl_named_node_t *child =
+				    ctl_named_children(node, j);
+				if (strlen(child->name) == elen &&
+				    strncmp(elm, child->name, elen) == 0) {
+					node = child;
+					if (nodesp != NULL)
+						nodesp[i] =
+						    (const ctl_node_t *)node;
+					mibp[i] = j;
+					break;
+				}
+			}
+			if (node == pnode) {
+				ret = ENOENT;
+				goto label_return;
+			}
+		} else {
+			uintmax_t index;
+			const ctl_indexed_node_t *inode;
+
+			/* Children are indexed. */
+			index = malloc_strtoumax(elm, NULL, 10);
+			if (index == UINTMAX_MAX || index > SIZE_T_MAX) {
+				ret = ENOENT;
+				goto label_return;
+			}
+
+			inode = ctl_indexed_node(node->children);
+			node = inode->index(tsdn, mibp, *depthp, (size_t)index);
+			if (node == NULL) {
+				ret = ENOENT;
+				goto label_return;
+			}
+
+			if (nodesp != NULL)
+				nodesp[i] = (const ctl_node_t *)node;
+			mibp[i] = (size_t)index;
+		}
+
+		if (node->ctl != NULL) {
+			/* Terminal node. */
+			if (*dot != '\0') {
+				/*
+				 * The name contains more elements than are
+				 * in this path through the tree.
+				 */
+				ret = ENOENT;
+				goto label_return;
+			}
+			/* Complete lookup successful. */
+			*depthp = i + 1;
+			break;
+		}
+
+		/* Update elm. */
+		if (*dot == '\0') {
+			/* No more elements. */
+			ret = ENOENT;
+			goto label_return;
+		}
+		elm = &dot[1];
+		dot = ((tdot = strchr(elm, '.')) != NULL) ? tdot :
+		    strchr(elm, '\0');
+		elen = (size_t)((uintptr_t)dot - (uintptr_t)elm);
+	}
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+int
+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 && ctl_init(tsd_tsdn(tsd))) {
+		ret = EAGAIN;
+		goto label_return;
+	}
+
+	depth = CTL_MAX_DEPTH;
+	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(tsd, mib, depth, oldp, oldlenp, newp, newlen);
+	else {
+		/* The name refers to a partial path through the ctl tree. */
+		ret = ENOENT;
+	}
+
+label_return:
+	return(ret);
+}
+
+int
+ctl_nametomib(tsdn_t *tsdn, const char *name, size_t *mibp, size_t *miblenp)
+{
+	int ret;
+
+	if (!ctl_initialized && ctl_init(tsdn)) {
+		ret = EAGAIN;
+		goto label_return;
+	}
+
+	ret = ctl_lookup(tsdn, name, NULL, mibp, miblenp);
+label_return:
+	return(ret);
+}
+
+int
+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 && ctl_init(tsd_tsdn(tsd))) {
+		ret = EAGAIN;
+		goto label_return;
+	}
+
+	/* Iterate down the tree. */
+	node = super_root_node;
+	for (i = 0; i < miblen; i++) {
+		assert(node);
+		assert(node->nchildren > 0);
+		if (ctl_named_node(node->children) != NULL) {
+			/* Children are named. */
+			if (node->nchildren <= (unsigned)mib[i]) {
+				ret = ENOENT;
+				goto label_return;
+			}
+			node = ctl_named_children(node, mib[i]);
+		} else {
+			const ctl_indexed_node_t *inode;
+
+			/* Indexed element. */
+			inode = ctl_indexed_node(node->children);
+			node = inode->index(tsd_tsdn(tsd), mib, miblen, mib[i]);
+			if (node == NULL) {
+				ret = ENOENT;
+				goto label_return;
+			}
+		}
+	}
+
+	/* Call the ctl function. */
+	if (node && node->ctl)
+		ret = node->ctl(tsd, mib, miblen, oldp, oldlenp, newp, newlen);
+	else {
+		/* Partial MIB. */
+		ret = ENOENT;
+	}
+
+label_return:
+	return(ret);
+}
+
+bool
+ctl_boot(void)
+{
+
+	if (malloc_mutex_init(&ctl_mtx, "ctl", WITNESS_RANK_CTL))
+		return (true);
+
+	ctl_initialized = false;
+
+	return (false);
+}
+
+void
+ctl_prefork(tsdn_t *tsdn)
+{
+
+	malloc_mutex_prefork(tsdn, &ctl_mtx);
+}
+
+void
+ctl_postfork_parent(tsdn_t *tsdn)
+{
+
+	malloc_mutex_postfork_parent(tsdn, &ctl_mtx);
+}
+
+void
+ctl_postfork_child(tsdn_t *tsdn)
+{
+
+	malloc_mutex_postfork_child(tsdn, &ctl_mtx);
+}
+
+/******************************************************************************/
+/* *_ctl() functions. */
+
+#define	READONLY()	do {						\
+	if (newp != NULL || newlen != 0) {				\
+		ret = EPERM;						\
+		goto label_return;					\
+	}								\
+} while (0)
+
+#define	WRITEONLY()	do {						\
+	if (oldp != NULL || oldlenp != NULL) {				\
+		ret = EPERM;						\
+		goto label_return;					\
+	}								\
+} while (0)
+
+#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)	\
+			    ? sizeof(t) : *oldlenp;			\
+			memcpy(oldp, (void *)&(v), copylen);		\
+			ret = EINVAL;					\
+			goto label_return;				\
+		}							\
+		*(t *)oldp = (v);					\
+	}								\
+} while (0)
+
+#define	WRITE(v, t)	do {						\
+	if (newp != NULL) {						\
+		if (newlen != sizeof(t)) {				\
+			ret = EINVAL;					\
+			goto label_return;				\
+		}							\
+		(v) = *(t *)newp;					\
+	}								\
+} 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)					\
+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;							\
+									\
+	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(tsd_tsdn(tsd), &ctl_mtx);		\
+	return (ret);							\
+}
+
+#define	CTL_RO_CGEN(c, n, v, 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;							\
+									\
+	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(tsd_tsdn(tsd), &ctl_mtx);			\
+	return (ret);							\
+}
+
+#define	CTL_RO_GEN(n, v, 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;							\
+									\
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);			\
+	READONLY();							\
+	oldval = (v);							\
+	READ(oldval, t);						\
+									\
+	ret = 0;							\
+label_return:								\
+	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)					\
+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;							\
+									\
+	if (!(c))							\
+		return (ENOENT);					\
+	READONLY();							\
+	oldval = (v);							\
+	READ(oldval, t);						\
+									\
+	ret = 0;							\
+label_return:								\
+	return (ret);							\
+}
+
+#define	CTL_RO_NL_GEN(n, v, 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 = (v);							\
+	READ(oldval, t);						\
+									\
+	ret = 0;							\
+label_return:								\
+	return (ret);							\
+}
+
+#define	CTL_TSD_RO_NL_CGEN(c, n, m, 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;							\
+									\
+	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, t);						\
+									\
+	ret = 0;							\
+label_return:								\
+	return (ret);							\
+}
+
+/******************************************************************************/
+
+CTL_RO_NL_GEN(version, JEMALLOC_VERSION, const char *)
+
+static int
+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(tsd_tsdn(tsd), &ctl_mtx);
+	WRITE(newval, uint64_t);
+	if (newp != NULL)
+		ctl_refresh(tsd_tsdn(tsd));
+	READ(ctl_epoch, uint64_t);
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+/******************************************************************************/
+
+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_munmap, bool)
+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_tcache, bool)
+CTL_RO_CONFIG_GEN(config_tls, bool)
+CTL_RO_CONFIG_GEN(config_utrace, bool)
+CTL_RO_CONFIG_GEN(config_valgrind, bool)
+CTL_RO_CONFIG_GEN(config_xmalloc, bool)
+
+/******************************************************************************/
+
+CTL_RO_NL_GEN(opt_abort, opt_abort, 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, unsigned)
+CTL_RO_NL_GEN(opt_purge, purge_mode_names[opt_purge], const char *)
+CTL_RO_NL_GEN(opt_lg_dirty_mult, opt_lg_dirty_mult, ssize_t)
+CTL_RO_NL_GEN(opt_decay_time, opt_decay_time, ssize_t)
+CTL_RO_NL_GEN(opt_stats_print, opt_stats_print, bool)
+CTL_RO_NL_CGEN(config_fill, opt_junk, opt_junk, const char *)
+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_CGEN(config_fill, opt_zero, opt_zero, bool)
+CTL_RO_NL_CGEN(config_utrace, opt_utrace, opt_utrace, 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_CGEN(config_prof, opt_prof, opt_prof, bool)
+CTL_RO_NL_CGEN(config_prof, opt_prof_prefix, opt_prof_prefix, const char *)
+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)
+CTL_RO_NL_CGEN(config_prof, opt_prof_gdump, opt_prof_gdump, bool)
+CTL_RO_NL_CGEN(config_prof, opt_prof_final, opt_prof_final, bool)
+CTL_RO_NL_CGEN(config_prof, opt_prof_leak, opt_prof_leak, bool)
+
+/******************************************************************************/
+
+static int
+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;
+
+	oldarena = arena_choose(tsd, NULL);
+	if (oldarena == NULL)
+		return (EAGAIN);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	newind = oldind = oldarena->ind;
+	WRITE(newind, unsigned);
+	READ(oldind, unsigned);
+	if (newind != oldind) {
+		arena_t *newarena;
+
+		if (newind >= ctl_stats.narenas) {
+			/* New arena index is out of range. */
+			ret = EFAULT;
+			goto label_return;
+		}
+
+		/* Initialize arena if necessary. */
+		newarena = arena_get(tsd_tsdn(tsd), newind, true);
+		if (newarena == NULL) {
+			ret = EAGAIN;
+			goto label_return;
+		}
+		/* Set new arena/tcache associations. */
+		arena_migrate(tsd, oldind, newind);
+		if (config_tcache) {
+			tcache_t *tcache = tsd_tcache_get(tsd);
+			if (tcache != NULL) {
+				tcache_arena_reassociate(tsd_tsdn(tsd), tcache,
+				    oldarena, newarena);
+			}
+		}
+	}
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+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(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)
+		return (ENOENT);
+
+	oldval = tcache_enabled_get();
+	if (newp != NULL) {
+		if (newlen != sizeof(bool)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		tcache_enabled_set(*(bool *)newp);
+	}
+	READ(oldval, bool);
+
+	ret = 0;
+label_return:
+	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 (!config_tcache)
+		return (ENOENT);
+
+	READONLY();
+	WRITEONLY();
+
+	tcache_flush();
+
+	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_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)
+		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;
+
+	if (!config_tcache)
+		return (ENOENT);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	READONLY();
+	if (tcaches_create(tsd, &tcache_ind)) {
+		ret = EFAULT;
+		goto label_return;
+	}
+	READ(tcache_ind, unsigned);
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	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;
+
+	if (!config_tcache)
+		return (ENOENT);
+
+	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;
+
+	if (!config_tcache)
+		return (ENOENT);
+
+	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);
+}
+
+/******************************************************************************/
+
+static void
+arena_i_purge(tsdn_t *tsdn, unsigned arena_ind, bool all)
+{
+
+	malloc_mutex_lock(tsdn, &ctl_mtx);
+	{
+		unsigned narenas = ctl_stats.narenas;
+
+		if (arena_ind == narenas) {
+			unsigned i;
+			VARIABLE_ARRAY(arena_t *, tarenas, narenas);
+
+			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_purge(tsdn, tarenas[i], 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_purge(tsdn, tarena, all);
+		}
+	}
+}
+
+static int
+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;
+
+	READONLY();
+	WRITEONLY();
+	arena_i_purge(tsd_tsdn(tsd), (unsigned)mib[1], true);
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+static int
+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;
+
+	READONLY();
+	WRITEONLY();
+	arena_i_purge(tsd_tsdn(tsd), (unsigned)mib[1], false);
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+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;
+
+	READONLY();
+	WRITEONLY();
+
+	if ((config_valgrind && unlikely(in_valgrind)) || (config_fill &&
+	    unlikely(opt_quarantine))) {
+		ret = EFAULT;
+		goto label_return;
+	}
+
+	arena_ind = (unsigned)mib[1];
+	if (config_debug) {
+		malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+		assert(arena_ind < ctl_stats.narenas);
+		malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	}
+	assert(arena_ind >= opt_narenas);
+
+	arena = arena_get(tsd_tsdn(tsd), arena_ind, false);
+
+	arena_reset(tsd, arena);
+
+	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 = (unsigned)mib[1];
+	dss_prec_t dss_prec_old = dss_prec_limit;
+	dss_prec_t dss_prec = dss_prec_limit;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	WRITE(dss, const char *);
+	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 (arena_ind < ctl_stats.narenas) {
+		arena_t *arena = arena_get(tsd_tsdn(tsd), arena_ind, false);
+		if (arena == NULL || (dss_prec != dss_prec_limit &&
+		    arena_dss_prec_set(tsd_tsdn(tsd), arena, dss_prec))) {
+			ret = EFAULT;
+			goto label_return;
+		}
+		dss_prec_old = arena_dss_prec_get(tsd_tsdn(tsd), arena);
+	} else {
+		if (dss_prec != dss_prec_limit &&
+		    chunk_dss_prec_set(dss_prec)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+		dss_prec_old = chunk_dss_prec_get();
+	}
+
+	dss = dss_prec_names[dss_prec_old];
+	READ(dss, const char *);
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+static int
+arena_i_lg_dirty_mult_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 = (unsigned)mib[1];
+	arena_t *arena;
+
+	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 = arena_lg_dirty_mult_get(tsd_tsdn(tsd), arena);
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (arena_lg_dirty_mult_set(tsd_tsdn(tsd), arena,
+		    *(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+	}
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+static int
+arena_i_decay_time_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 = (unsigned)mib[1];
+	arena_t *arena;
+
+	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 = arena_decay_time_get(tsd_tsdn(tsd), arena);
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (arena_decay_time_set(tsd_tsdn(tsd), arena,
+		    *(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+	}
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+static int
+arena_i_chunk_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 = (unsigned)mib[1];
+	arena_t *arena;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	if (arena_ind < narenas_total_get() && (arena =
+	    arena_get(tsd_tsdn(tsd), arena_ind, false)) != NULL) {
+		if (newp != NULL) {
+			chunk_hooks_t old_chunk_hooks, new_chunk_hooks;
+			WRITE(new_chunk_hooks, chunk_hooks_t);
+			old_chunk_hooks = chunk_hooks_set(tsd_tsdn(tsd), arena,
+			    &new_chunk_hooks);
+			READ(old_chunk_hooks, chunk_hooks_t);
+		} else {
+			chunk_hooks_t old_chunk_hooks =
+			    chunk_hooks_get(tsd_tsdn(tsd), arena);
+			READ(old_chunk_hooks, chunk_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);
+	if (i > ctl_stats.narenas) {
+		ret = NULL;
+		goto label_return;
+	}
+
+	ret = super_arena_i_node;
+label_return:
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return (ret);
+}
+
+/******************************************************************************/
+
+static int
+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(tsd_tsdn(tsd), &ctl_mtx);
+	READONLY();
+	if (*oldlenp != sizeof(unsigned)) {
+		ret = EINVAL;
+		goto label_return;
+	}
+	narenas = ctl_stats.narenas;
+	READ(narenas, unsigned);
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+static int
+arenas_initialized_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen)
+{
+	int ret;
+	unsigned nread, i;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &ctl_mtx);
+	READONLY();
+	if (*oldlenp != ctl_stats.narenas * sizeof(bool)) {
+		ret = EINVAL;
+		nread = (*oldlenp < ctl_stats.narenas * sizeof(bool))
+		    ? (unsigned)(*oldlenp / sizeof(bool)) : ctl_stats.narenas;
+	} else {
+		ret = 0;
+		nread = ctl_stats.narenas;
+	}
+
+	for (i = 0; i < nread; i++)
+		((bool *)oldp)[i] = ctl_stats.arenas[i].initialized;
+
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+static int
+arenas_lg_dirty_mult_ctl(tsd_t *tsd, const size_t *mib, size_t miblen,
+    void *oldp, size_t *oldlenp, void *newp, size_t newlen)
+{
+	int ret;
+
+	if (oldp != NULL && oldlenp != NULL) {
+		size_t oldval = arena_lg_dirty_mult_default_get();
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (arena_lg_dirty_mult_default_set(*(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+	}
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+static int
+arenas_decay_time_ctl(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
+    size_t *oldlenp, void *newp, size_t newlen)
+{
+	int ret;
+
+	if (oldp != NULL && oldlenp != NULL) {
+		size_t oldval = arena_decay_time_default_get();
+		READ(oldval, ssize_t);
+	}
+	if (newp != NULL) {
+		if (newlen != sizeof(ssize_t)) {
+			ret = EINVAL;
+			goto label_return;
+		}
+		if (arena_decay_time_default_set(*(ssize_t *)newp)) {
+			ret = EFAULT;
+			goto label_return;
+		}
+	}
+
+	ret = 0;
+label_return:
+	return (ret);
+}
+
+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_nbins, NBINS, unsigned)
+CTL_RO_NL_CGEN(config_tcache, 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)
+static const ctl_named_node_t *
+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, unsigned)
+CTL_RO_NL_GEN(arenas_lrun_i_size, index2size(NBINS+(szind_t)mib[2]), size_t)
+static const ctl_named_node_t *
+arenas_lrun_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i)
+{
+
+	if (i > nlclasses)
+		return (NULL);
+	return (super_arenas_lrun_i_node);
+}
+
+CTL_RO_NL_GEN(arenas_nhchunks, nhclasses, unsigned)
+CTL_RO_NL_GEN(arenas_hchunk_i_size, index2size(NBINS+nlclasses+(szind_t)mib[2]),
+    size_t)
+static const ctl_named_node_t *
+arenas_hchunk_i_index(tsdn_t *tsdn, const size_t *mib, size_t miblen, size_t i)
+{
+
+	if (i > nhclasses)
+		return (NULL);
+	return (super_arenas_hchunk_i_node);
+}
+
+static int
+arenas_extend_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(tsd_tsdn(tsd), &ctl_mtx);
+	READONLY();
+	if (ctl_grow(tsd_tsdn(tsd))) {
+		ret = EAGAIN;
+		goto label_return;
+	}
+	narenas = ctl_stats.narenas - 1;
+	READ(narenas, unsigned);
+
+	ret = 0;
+label_return:
+	malloc_mutex_unlock(tsd_tsdn(tsd), &ctl_mtx);
+	return (ret);
+}
+
+/******************************************************************************/
+
+static int
+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;
+	bool oldval;
+
+	if (!config_prof)
+		return (ENOENT);
+
+	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:
+	return (ret);
+}
+
+static int
+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)
+		return (ENOENT);
+
+	if (newp != NULL) {
+		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:
+	return (ret);
+}
+
+static int
+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)
+		return (ENOENT);
+
+	WRITEONLY();
+	WRITE(filename, const char *);
+
+	if (prof_mdump(tsd, filename)) {
+		ret = EFAULT;
+		goto label_return;
+	}
+
+	ret = 0;
+label_return:
+	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_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_GEN(stats_arenas_i_dss, ctl_stats.arenas[mib[2]].dss, const char *)
+CTL_RO_GEN(stats_arenas_i_lg_dirty_mult, ctl_stats.arenas[mib[2]].lg_dirty_mult,
+    ssize_t)
+CTL_RO_GEN(stats_arenas_i_decay_time, ctl_stats.arenas[mib[2]].decay_time,
+    ssize_t)
+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_retained,
+    ctl_stats.arenas[mib[2]].astats.retained, 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_metadata_mapped,
+    ctl_stats.arenas[mib[2]].astats.metadata_mapped, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_metadata_allocated,
+    ctl_stats.arenas[mib[2]].astats.metadata_allocated, size_t)
+
+CTL_RO_CGEN(config_stats, stats_arenas_i_small_allocated,
+    ctl_stats.arenas[mib[2]].allocated_small, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_small_nmalloc,
+    ctl_stats.arenas[mib[2]].nmalloc_small, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_small_ndalloc,
+    ctl_stats.arenas[mib[2]].ndalloc_small, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_small_nrequests,
+    ctl_stats.arenas[mib[2]].nrequests_small, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_large_allocated,
+    ctl_stats.arenas[mib[2]].astats.allocated_large, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_large_nmalloc,
+    ctl_stats.arenas[mib[2]].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)
+CTL_RO_CGEN(config_stats, stats_arenas_i_large_nrequests,
+    ctl_stats.arenas[mib[2]].astats.nrequests_large, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_huge_allocated,
+    ctl_stats.arenas[mib[2]].astats.allocated_huge, size_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_huge_nmalloc,
+    ctl_stats.arenas[mib[2]].astats.nmalloc_huge, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_huge_ndalloc,
+    ctl_stats.arenas[mib[2]].astats.ndalloc_huge, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_huge_nrequests,
+    ctl_stats.arenas[mib[2]].astats.nmalloc_huge, uint64_t) /* Intentional. */
+
+CTL_RO_CGEN(config_stats, stats_arenas_i_bins_j_nmalloc,
+    ctl_stats.arenas[mib[2]].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)
+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, stats_arenas_i_bins_j_curregs,
+    ctl_stats.arenas[mib[2]].bstats[mib[4]].curregs, size_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)
+
+static const ctl_named_node_t *
+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)
+
+static const ctl_named_node_t *
+stats_arenas_i_lruns_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen,
+    size_t j)
+{
+
+	if (j > nlclasses)
+		return (NULL);
+	return (super_stats_arenas_i_lruns_j_node);
+}
+
+CTL_RO_CGEN(config_stats, stats_arenas_i_hchunks_j_nmalloc,
+    ctl_stats.arenas[mib[2]].hstats[mib[4]].nmalloc, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_hchunks_j_ndalloc,
+    ctl_stats.arenas[mib[2]].hstats[mib[4]].ndalloc, uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_hchunks_j_nrequests,
+    ctl_stats.arenas[mib[2]].hstats[mib[4]].nmalloc, /* Intentional. */
+    uint64_t)
+CTL_RO_CGEN(config_stats, stats_arenas_i_hchunks_j_curhchunks,
+    ctl_stats.arenas[mib[2]].hstats[mib[4]].curhchunks, size_t)
+
+static const ctl_named_node_t *
+stats_arenas_i_hchunks_j_index(tsdn_t *tsdn, const size_t *mib, size_t miblen,
+    size_t j)
+{
+
+	if (j > nhclasses)
+		return (NULL);
+	return (super_stats_arenas_i_hchunks_j_node);
+}
+
+static const ctl_named_node_t *
+stats_arenas_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);
+	if (i > ctl_stats.narenas || !ctl_stats.arenas[i].initialized) {
+		ret = NULL;
+		goto label_return;
+	}
+
+	ret = super_stats_arenas_i_node;
+label_return:
+	malloc_mutex_unlock(tsdn, &ctl_mtx);
+	return (ret);
+}
diff --git a/deps/jemalloc/src/extent.c b/deps/jemalloc/src/extent.c
new file mode 100644
index 0000000..218156c
--- /dev/null
+++ b/deps/jemalloc/src/extent.c
@@ -0,0 +1,77 @@
+#define	JEMALLOC_EXTENT_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+
+/*
+ * Round down to the nearest chunk size that can actually be requested during
+ * normal huge allocation.
+ */
+JEMALLOC_INLINE_C size_t
+extent_quantize(size_t size)
+{
+	size_t ret;
+	szind_t ind;
+
+	assert(size > 0);
+
+	ind = size2index(size + 1);
+	if (ind == 0) {
+		/* Avoid underflow. */
+		return (index2size(0));
+	}
+	ret = index2size(ind - 1);
+	assert(ret <= size);
+	return (ret);
+}
+
+JEMALLOC_INLINE_C int
+extent_sz_comp(const extent_node_t *a, const extent_node_t *b)
+{
+	size_t a_qsize = extent_quantize(extent_node_size_get(a));
+	size_t b_qsize = extent_quantize(extent_node_size_get(b));
+
+	return ((a_qsize > b_qsize) - (a_qsize < b_qsize));
+}
+
+JEMALLOC_INLINE_C int
+extent_sn_comp(const extent_node_t *a, const extent_node_t *b)
+{
+	size_t a_sn = extent_node_sn_get(a);
+	size_t b_sn = extent_node_sn_get(b);
+
+	return ((a_sn > b_sn) - (a_sn < b_sn));
+}
+
+JEMALLOC_INLINE_C int
+extent_ad_comp(const extent_node_t *a, const extent_node_t *b)
+{
+	uintptr_t a_addr = (uintptr_t)extent_node_addr_get(a);
+	uintptr_t b_addr = (uintptr_t)extent_node_addr_get(b);
+
+	return ((a_addr > b_addr) - (a_addr < b_addr));
+}
+
+JEMALLOC_INLINE_C int
+extent_szsnad_comp(const extent_node_t *a, const extent_node_t *b)
+{
+	int ret;
+
+	ret = extent_sz_comp(a, b);
+	if (ret != 0)
+		return (ret);
+
+	ret = extent_sn_comp(a, b);
+	if (ret != 0)
+		return (ret);
+
+	ret = extent_ad_comp(a, b);
+	return (ret);
+}
+
+/* Generate red-black tree functions. */
+rb_gen(, extent_tree_szsnad_, extent_tree_t, extent_node_t, szsnad_link,
+    extent_szsnad_comp)
+
+/* Generate red-black tree functions. */
+rb_gen(, extent_tree_ad_, extent_tree_t, extent_node_t, ad_link, extent_ad_comp)
diff --git a/deps/jemalloc/src/hash.c b/deps/jemalloc/src/hash.c
new file mode 100644
index 0000000..cfa4da0
--- /dev/null
+++ b/deps/jemalloc/src/hash.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_HASH_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/huge.c b/deps/jemalloc/src/huge.c
new file mode 100644
index 0000000..8abd8c0
--- /dev/null
+++ b/deps/jemalloc/src/huge.c
@@ -0,0 +1,477 @@
+#define	JEMALLOC_HUGE_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+
+static extent_node_t *
+huge_node_get(const void *ptr)
+{
+	extent_node_t *node;
+
+	node = chunk_lookup(ptr, true);
+	assert(!extent_node_achunk_get(node));
+
+	return (node);
+}
+
+static bool
+huge_node_set(tsdn_t *tsdn, const void *ptr, extent_node_t *node)
+{
+
+	assert(extent_node_addr_get(node) == ptr);
+	assert(!extent_node_achunk_get(node));
+	return (chunk_register(tsdn, ptr, node));
+}
+
+static void
+huge_node_reset(tsdn_t *tsdn, const void *ptr, extent_node_t *node)
+{
+	bool err;
+
+	err = huge_node_set(tsdn, ptr, node);
+	assert(!err);
+}
+
+static void
+huge_node_unset(const void *ptr, const extent_node_t *node)
+{
+
+	chunk_deregister(ptr, node);
+}
+
+void *
+huge_malloc(tsdn_t *tsdn, arena_t *arena, size_t usize, bool zero)
+{
+
+	assert(usize == s2u(usize));
+
+	return (huge_palloc(tsdn, arena, usize, chunksize, zero));
+}
+
+void *
+huge_palloc(tsdn_t *tsdn, arena_t *arena, size_t usize, size_t alignment,
+    bool zero)
+{
+	void *ret;
+	size_t ausize;
+	arena_t *iarena;
+	extent_node_t *node;
+	size_t sn;
+	bool is_zeroed;
+
+	/* Allocate one or more contiguous chunks for this request. */
+
+	assert(!tsdn_null(tsdn) || arena != NULL);
+
+	ausize = sa2u(usize, alignment);
+	if (unlikely(ausize == 0 || ausize > HUGE_MAXCLASS))
+		return (NULL);
+	assert(ausize >= chunksize);
+
+	/* Allocate an extent node with which to track the chunk. */
+	iarena = (!tsdn_null(tsdn)) ? arena_ichoose(tsdn_tsd(tsdn), NULL) :
+	    a0get();
+	node = ipallocztm(tsdn, CACHELINE_CEILING(sizeof(extent_node_t)),
+	    CACHELINE, false, NULL, true, iarena);
+	if (node == NULL)
+		return (NULL);
+
+	/*
+	 * Copy zero into is_zeroed and pass the copy to chunk_alloc(), so that
+	 * it is possible to make correct junk/zero fill decisions below.
+	 */
+	is_zeroed = zero;
+	if (likely(!tsdn_null(tsdn)))
+		arena = arena_choose(tsdn_tsd(tsdn), arena);
+	if (unlikely(arena == NULL) || (ret = arena_chunk_alloc_huge(tsdn,
+	    arena, usize, alignment, &sn, &is_zeroed)) == NULL) {
+		idalloctm(tsdn, node, NULL, true, true);
+		return (NULL);
+	}
+
+	extent_node_init(node, arena, ret, usize, sn, is_zeroed, true);
+
+	if (huge_node_set(tsdn, ret, node)) {
+		arena_chunk_dalloc_huge(tsdn, arena, ret, usize, sn);
+		idalloctm(tsdn, node, NULL, true, true);
+		return (NULL);
+	}
+
+	/* Insert node into huge. */
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	ql_elm_new(node, ql_link);
+	ql_tail_insert(&arena->huge, node, ql_link);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	if (zero || (config_fill && unlikely(opt_zero))) {
+		if (!is_zeroed)
+			memset(ret, 0, usize);
+	} else if (config_fill && unlikely(opt_junk_alloc))
+		memset(ret, JEMALLOC_ALLOC_JUNK, usize);
+
+	arena_decay_tick(tsdn, arena);
+	return (ret);
+}
+
+#ifdef JEMALLOC_JET
+#undef huge_dalloc_junk
+#define	huge_dalloc_junk JEMALLOC_N(huge_dalloc_junk_impl)
+#endif
+static void
+huge_dalloc_junk(void *ptr, size_t usize)
+{
+
+	if (config_fill && have_dss && unlikely(opt_junk_free)) {
+		/*
+		 * Only bother junk filling if the chunk isn't about to be
+		 * unmapped.
+		 */
+		if (!config_munmap || (have_dss && chunk_in_dss(ptr)))
+			memset(ptr, JEMALLOC_FREE_JUNK, usize);
+	}
+}
+#ifdef JEMALLOC_JET
+#undef huge_dalloc_junk
+#define	huge_dalloc_junk JEMALLOC_N(huge_dalloc_junk)
+huge_dalloc_junk_t *huge_dalloc_junk = JEMALLOC_N(huge_dalloc_junk_impl);
+#endif
+
+static void
+huge_ralloc_no_move_similar(tsdn_t *tsdn, void *ptr, size_t oldsize,
+    size_t usize_min, size_t usize_max, bool zero)
+{
+	size_t usize, usize_next;
+	extent_node_t *node;
+	arena_t *arena;
+	chunk_hooks_t chunk_hooks = CHUNK_HOOKS_INITIALIZER;
+	bool pre_zeroed, post_zeroed;
+
+	/* Increase usize to incorporate extra. */
+	for (usize = usize_min; usize < usize_max && (usize_next = s2u(usize+1))
+	    <= oldsize; usize = usize_next)
+		; /* Do nothing. */
+
+	if (oldsize == usize)
+		return;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	pre_zeroed = extent_node_zeroed_get(node);
+
+	/* Fill if necessary (shrinking). */
+	if (oldsize > usize) {
+		size_t sdiff = oldsize - usize;
+		if (config_fill && unlikely(opt_junk_free)) {
+			memset((void *)((uintptr_t)ptr + usize),
+			    JEMALLOC_FREE_JUNK, sdiff);
+			post_zeroed = false;
+		} else {
+			post_zeroed = !chunk_purge_wrapper(tsdn, arena,
+			    &chunk_hooks, ptr, CHUNK_CEILING(oldsize), usize,
+			    sdiff);
+		}
+	} else
+		post_zeroed = pre_zeroed;
+
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	/* Update the size of the huge allocation. */
+	huge_node_unset(ptr, node);
+	assert(extent_node_size_get(node) != usize);
+	extent_node_size_set(node, usize);
+	huge_node_reset(tsdn, ptr, node);
+	/* Update zeroed. */
+	extent_node_zeroed_set(node, post_zeroed);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	arena_chunk_ralloc_huge_similar(tsdn, arena, ptr, oldsize, usize);
+
+	/* Fill if necessary (growing). */
+	if (oldsize < usize) {
+		if (zero || (config_fill && unlikely(opt_zero))) {
+			if (!pre_zeroed) {
+				memset((void *)((uintptr_t)ptr + oldsize), 0,
+				    usize - oldsize);
+			}
+		} else if (config_fill && unlikely(opt_junk_alloc)) {
+			memset((void *)((uintptr_t)ptr + oldsize),
+			    JEMALLOC_ALLOC_JUNK, usize - oldsize);
+		}
+	}
+}
+
+static bool
+huge_ralloc_no_move_shrink(tsdn_t *tsdn, void *ptr, size_t oldsize,
+    size_t usize)
+{
+	extent_node_t *node;
+	arena_t *arena;
+	chunk_hooks_t chunk_hooks;
+	size_t cdiff;
+	bool pre_zeroed, post_zeroed;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	pre_zeroed = extent_node_zeroed_get(node);
+	chunk_hooks = chunk_hooks_get(tsdn, arena);
+
+	assert(oldsize > usize);
+
+	/* Split excess chunks. */
+	cdiff = CHUNK_CEILING(oldsize) - CHUNK_CEILING(usize);
+	if (cdiff != 0 && chunk_hooks.split(ptr, CHUNK_CEILING(oldsize),
+	    CHUNK_CEILING(usize), cdiff, true, arena->ind))
+		return (true);
+
+	if (oldsize > usize) {
+		size_t sdiff = oldsize - usize;
+		if (config_fill && unlikely(opt_junk_free)) {
+			huge_dalloc_junk((void *)((uintptr_t)ptr + usize),
+			    sdiff);
+			post_zeroed = false;
+		} else {
+			post_zeroed = !chunk_purge_wrapper(tsdn, arena,
+			    &chunk_hooks, CHUNK_ADDR2BASE((uintptr_t)ptr +
+			    usize), CHUNK_CEILING(oldsize),
+			    CHUNK_ADDR2OFFSET((uintptr_t)ptr + usize), sdiff);
+		}
+	} else
+		post_zeroed = pre_zeroed;
+
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	/* Update the size of the huge allocation. */
+	huge_node_unset(ptr, node);
+	extent_node_size_set(node, usize);
+	huge_node_reset(tsdn, ptr, node);
+	/* Update zeroed. */
+	extent_node_zeroed_set(node, post_zeroed);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	/* Zap the excess chunks. */
+	arena_chunk_ralloc_huge_shrink(tsdn, arena, ptr, oldsize, usize,
+	    extent_node_sn_get(node));
+
+	return (false);
+}
+
+static bool
+huge_ralloc_no_move_expand(tsdn_t *tsdn, void *ptr, size_t oldsize,
+    size_t usize, bool zero) {
+	extent_node_t *node;
+	arena_t *arena;
+	bool is_zeroed_subchunk, is_zeroed_chunk;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	is_zeroed_subchunk = extent_node_zeroed_get(node);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	/*
+	 * Use is_zeroed_chunk to detect whether the trailing memory is zeroed,
+	 * update extent's zeroed field, and zero as necessary.
+	 */
+	is_zeroed_chunk = false;
+	if (arena_chunk_ralloc_huge_expand(tsdn, arena, ptr, oldsize, usize,
+	     &is_zeroed_chunk))
+		return (true);
+
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	huge_node_unset(ptr, node);
+	extent_node_size_set(node, usize);
+	extent_node_zeroed_set(node, extent_node_zeroed_get(node) &&
+	    is_zeroed_chunk);
+	huge_node_reset(tsdn, ptr, node);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	if (zero || (config_fill && unlikely(opt_zero))) {
+		if (!is_zeroed_subchunk) {
+			memset((void *)((uintptr_t)ptr + oldsize), 0,
+			    CHUNK_CEILING(oldsize) - oldsize);
+		}
+		if (!is_zeroed_chunk) {
+			memset((void *)((uintptr_t)ptr +
+			    CHUNK_CEILING(oldsize)), 0, usize -
+			    CHUNK_CEILING(oldsize));
+		}
+	} else if (config_fill && unlikely(opt_junk_alloc)) {
+		memset((void *)((uintptr_t)ptr + oldsize), JEMALLOC_ALLOC_JUNK,
+		    usize - oldsize);
+	}
+
+	return (false);
+}
+
+bool
+huge_ralloc_no_move(tsdn_t *tsdn, void *ptr, size_t oldsize, size_t usize_min,
+    size_t usize_max, bool zero)
+{
+
+	assert(s2u(oldsize) == oldsize);
+	/* The following should have been caught by callers. */
+	assert(usize_min > 0 && usize_max <= HUGE_MAXCLASS);
+
+	/* Both allocations must be huge to avoid a move. */
+	if (oldsize < chunksize || usize_max < chunksize)
+		return (true);
+
+	if (CHUNK_CEILING(usize_max) > CHUNK_CEILING(oldsize)) {
+		/* Attempt to expand the allocation in-place. */
+		if (!huge_ralloc_no_move_expand(tsdn, ptr, oldsize, usize_max,
+		    zero)) {
+			arena_decay_tick(tsdn, huge_aalloc(ptr));
+			return (false);
+		}
+		/* Try again, this time with usize_min. */
+		if (usize_min < usize_max && CHUNK_CEILING(usize_min) >
+		    CHUNK_CEILING(oldsize) && huge_ralloc_no_move_expand(tsdn,
+		    ptr, oldsize, usize_min, zero)) {
+			arena_decay_tick(tsdn, huge_aalloc(ptr));
+			return (false);
+		}
+	}
+
+	/*
+	 * Avoid moving the allocation if the existing chunk size accommodates
+	 * the new size.
+	 */
+	if (CHUNK_CEILING(oldsize) >= CHUNK_CEILING(usize_min)
+	    && CHUNK_CEILING(oldsize) <= CHUNK_CEILING(usize_max)) {
+		huge_ralloc_no_move_similar(tsdn, ptr, oldsize, usize_min,
+		    usize_max, zero);
+		arena_decay_tick(tsdn, huge_aalloc(ptr));
+		return (false);
+	}
+
+	/* Attempt to shrink the allocation in-place. */
+	if (CHUNK_CEILING(oldsize) > CHUNK_CEILING(usize_max)) {
+		if (!huge_ralloc_no_move_shrink(tsdn, ptr, oldsize,
+		    usize_max)) {
+			arena_decay_tick(tsdn, huge_aalloc(ptr));
+			return (false);
+		}
+	}
+	return (true);
+}
+
+static void *
+huge_ralloc_move_helper(tsdn_t *tsdn, arena_t *arena, size_t usize,
+    size_t alignment, bool zero)
+{
+
+	if (alignment <= chunksize)
+		return (huge_malloc(tsdn, arena, usize, zero));
+	return (huge_palloc(tsdn, arena, usize, alignment, zero));
+}
+
+void *
+huge_ralloc(tsd_t *tsd, arena_t *arena, void *ptr, size_t oldsize,
+    size_t usize, size_t alignment, bool zero, tcache_t *tcache)
+{
+	void *ret;
+	size_t copysize;
+
+	/* The following should have been caught by callers. */
+	assert(usize > 0 && usize <= HUGE_MAXCLASS);
+
+	/* Try to avoid moving the allocation. */
+	if (!huge_ralloc_no_move(tsd_tsdn(tsd), ptr, oldsize, usize, usize,
+	    zero))
+		return (ptr);
+
+	/*
+	 * usize and oldsize are different enough that we need to use a
+	 * different size class.  In that case, fall back to allocating new
+	 * space and copying.
+	 */
+	ret = huge_ralloc_move_helper(tsd_tsdn(tsd), arena, usize, alignment,
+	    zero);
+	if (ret == NULL)
+		return (NULL);
+
+	copysize = (usize < oldsize) ? usize : oldsize;
+	memcpy(ret, ptr, copysize);
+	isqalloc(tsd, ptr, oldsize, tcache, true);
+	return (ret);
+}
+
+void
+huge_dalloc(tsdn_t *tsdn, void *ptr)
+{
+	extent_node_t *node;
+	arena_t *arena;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	huge_node_unset(ptr, node);
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	ql_remove(&arena->huge, node, ql_link);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	huge_dalloc_junk(extent_node_addr_get(node),
+	    extent_node_size_get(node));
+	arena_chunk_dalloc_huge(tsdn, extent_node_arena_get(node),
+	    extent_node_addr_get(node), extent_node_size_get(node),
+	    extent_node_sn_get(node));
+	idalloctm(tsdn, node, NULL, true, true);
+
+	arena_decay_tick(tsdn, arena);
+}
+
+arena_t *
+huge_aalloc(const void *ptr)
+{
+
+	return (extent_node_arena_get(huge_node_get(ptr)));
+}
+
+size_t
+huge_salloc(tsdn_t *tsdn, const void *ptr)
+{
+	size_t size;
+	extent_node_t *node;
+	arena_t *arena;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	size = extent_node_size_get(node);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	return (size);
+}
+
+prof_tctx_t *
+huge_prof_tctx_get(tsdn_t *tsdn, const void *ptr)
+{
+	prof_tctx_t *tctx;
+	extent_node_t *node;
+	arena_t *arena;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	tctx = extent_node_prof_tctx_get(node);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+
+	return (tctx);
+}
+
+void
+huge_prof_tctx_set(tsdn_t *tsdn, const void *ptr, prof_tctx_t *tctx)
+{
+	extent_node_t *node;
+	arena_t *arena;
+
+	node = huge_node_get(ptr);
+	arena = extent_node_arena_get(node);
+	malloc_mutex_lock(tsdn, &arena->huge_mtx);
+	extent_node_prof_tctx_set(node, tctx);
+	malloc_mutex_unlock(tsdn, &arena->huge_mtx);
+}
+
+void
+huge_prof_tctx_reset(tsdn_t *tsdn, const void *ptr)
+{
+
+	huge_prof_tctx_set(tsdn, ptr, (prof_tctx_t *)(uintptr_t)1U);
+}
diff --git a/deps/jemalloc/src/jemalloc.c b/deps/jemalloc/src/jemalloc.c
new file mode 100644
index 0000000..07389ca
--- /dev/null
+++ b/deps/jemalloc/src/jemalloc.c
@@ -0,0 +1,2949 @@
+#define	JEMALLOC_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+/* Runtime configuration options. */
+const char	*je_malloc_conf
+#ifndef _WIN32
+    JEMALLOC_ATTR(weak)
+#endif
+    ;
+bool	opt_abort =
+#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_xmalloc = false;
+bool	opt_zero = false;
+unsigned	opt_narenas = 0;
+
+/* Initialized to true if the process is running inside Valgrind. */
+bool	in_valgrind;
+
+unsigned	ncpus;
+
+/* Protects arenas initialization. */
+static 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.
+ */
+arena_t			**arenas;
+static unsigned		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. */
+static 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_quarantine	= (1U << 2),
+	flag_opt_zero		= (1U << 3),
+	flag_opt_utrace		= (1U << 4),
+	flag_in_valgrind	= (1U << 5),
+	flag_opt_xmalloc	= (1U << 6)
+};
+static uint8_t	malloc_slow_flags;
+
+JEMALLOC_ALIGNED(CACHELINE)
+const size_t	pind2sz_tab[NPSIZES] = {
+#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, lg_delta_lookup)	\
+	PSZ_##psz(lg_grp, ndelta, lg_delta)
+	SIZE_CLASSES
+#undef PSZ_yes
+#undef PSZ_no
+#undef SC
+};
+
+JEMALLOC_ALIGNED(CACHELINE)
+const size_t	index2size_tab[NSIZES] = {
+#define	SC(index, lg_grp, lg_delta, ndelta, psz, bin, lg_delta_lookup)	\
+	((ZU(1)<<lg_grp) + (ZU(ndelta)<<lg_delta)),
+	SIZE_CLASSES
+#undef SC
+};
+
+JEMALLOC_ALIGNED(CACHELINE)
+const uint8_t	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, 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
+};
+
+#ifdef JEMALLOC_THREADED_INIT
+/* Used to let the initializing thread recursively allocate. */
+#  define NO_INITIALIZER	((unsigned long)0)
+#  define INITIALIZER		pthread_self()
+#  define IS_INITIALIZER	(malloc_initializer == pthread_self())
+static pthread_t		malloc_initializer = NO_INITIALIZER;
+#else
+#  define NO_INITIALIZER	false
+#  define INITIALIZER		true
+#  define IS_INITIALIZER	malloc_initializer
+static bool			malloc_initializer = NO_INITIALIZER;
+#endif
+
+/* 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)
+{
+
+	/* If another constructor in the same binary is using mallctl to
+	 * e.g. setup chunk 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);
+	init_lock_initialized = true;
+}
+
+#ifdef _MSC_VER
+#  pragma section(".CRT$XCU", read)
+JEMALLOC_SECTION(".CRT$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
+
+typedef struct {
+	void	*p;	/* Input pointer (as in realloc(p, s)). */
+	size_t	s;	/* Request size. */
+	void	*r;	/* Result pointer. */
+} malloc_utrace_t;
+
+#ifdef JEMALLOC_UTRACE
+#  define UTRACE(a, b, c) do {						\
+	if (unlikely(opt_utrace)) {					\
+		int utrace_serrno = errno;				\
+		malloc_utrace_t ut;					\
+		ut.p = (a);						\
+		ut.s = (b);						\
+		ut.r = (c);						\
+		utrace(&ut, sizeof(ut));				\
+		errno = utrace_serrno;					\
+	}								\
+} while (0)
+#else
+#  define UTRACE(a, b, c)
+#endif
+
+/******************************************************************************/
+/*
+ * Function prototypes for static functions that are referenced prior to
+ * definition.
+ */
+
+static bool	malloc_init_hard_a0(void);
+static bool	malloc_init_hard(void);
+
+/******************************************************************************/
+/*
+ * Begin miscellaneous support functions.
+ */
+
+JEMALLOC_ALWAYS_INLINE_C bool
+malloc_initialized(void)
+{
+
+	return (malloc_init_state == malloc_init_initialized);
+}
+
+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 && unlikely(opt_quarantine))
+		quarantine_alloc_hook();
+}
+
+JEMALLOC_ALWAYS_INLINE_C bool
+malloc_init_a0(void)
+{
+
+	if (unlikely(malloc_init_state == malloc_init_uninitialized))
+		return (malloc_init_hard_a0());
+	return (false);
+}
+
+JEMALLOC_ALWAYS_INLINE_C bool
+malloc_init(void)
+{
+
+	if (unlikely(!malloc_initialized()) && malloc_init_hard())
+		return (true);
+	malloc_thread_init();
+
+	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_metadata)
+{
+
+	if (unlikely(malloc_init_a0()))
+		return (NULL);
+
+	return (iallocztm(TSDN_NULL, size, size2index(size), zero, NULL,
+	    is_metadata, arena_get(TSDN_NULL, 0, true), true));
+}
+
+static void
+a0idalloc(void *ptr, bool is_metadata)
+{
+
+	idalloctm(TSDN_NULL, ptr, false, is_metadata, true);
+}
+
+arena_t *
+a0get(void)
+{
+
+	return (a0);
+}
+
+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);
+}
+
+static void
+arena_set(unsigned ind, arena_t *arena)
+{
+
+	atomic_write_p((void **)&arenas[ind], arena);
+}
+
+static void
+narenas_total_set(unsigned narenas)
+{
+
+	atomic_write_u(&narenas_total, narenas);
+}
+
+static void
+narenas_total_inc(void)
+{
+
+	atomic_add_u(&narenas_total, 1);
+}
+
+unsigned
+narenas_total_get(void)
+{
+
+	return (atomic_read_u(&narenas_total));
+}
+
+/* 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)
+{
+	arena_t *arena;
+
+	assert(ind <= narenas_total_get());
+	if (ind > MALLOCX_ARENA_MAX)
+		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);
+	arena_set(ind, arena);
+	return (arena);
+}
+
+arena_t *
+arena_init(tsdn_t *tsdn, unsigned ind)
+{
+	arena_t *arena;
+
+	malloc_mutex_lock(tsdn, &arenas_lock);
+	arena = arena_init_locked(tsdn, ind);
+	malloc_mutex_unlock(tsdn, &arenas_lock);
+	return (arena);
+}
+
+static void
+arena_bind(tsd_t *tsd, unsigned ind, bool internal)
+{
+	arena_t *arena;
+
+	if (!tsd_nominal(tsd))
+		return;
+
+	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);
+}
+
+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);
+}
+
+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();
+
+	/*
+	 * Dissociate old tdata array (and set up for deallocation upon return)
+	 * if it's too small.
+	 */
+	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;
+
+		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.extend 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 arena_choose(). */
+arena_t *
+arena_choose_hard(tsd_t *tsd, bool internal)
+{
+	arena_t *ret JEMALLOC_CC_SILENCE_INIT(NULL);
+
+	if (narenas_auto > 1) {
+		unsigned i, j, choose[2], first_null;
+
+		/*
+		 * 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;
+
+		first_null = narenas_auto;
+		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 (arena_get(tsd_tsdn(tsd), i, false) != NULL) {
+				/*
+				 * Choose the first arena that has the lowest
+				 * number of threads assigned to it.
+				 */
+				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
+				 * arena, in case all extant arenas are in use.
+				 *
+				 * NB: It is possible for there to be
+				 * discontinuities in terms of initialized
+				 * versus uninitialized arenas, due to the
+				 * "thread.arena" mallctl.
+				 */
+				first_null = i;
+			}
+		}
+
+		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]);
+				if (arena == NULL) {
+					malloc_mutex_unlock(tsd_tsdn(tsd),
+					    &arenas_lock);
+					return (NULL);
+				}
+				if (!!j == internal)
+					ret = arena;
+			}
+			arena_bind(tsd, choose[j], !!j);
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &arenas_lock);
+	} else {
+		ret = arena_get(tsd_tsdn(tsd), 0, false);
+		arena_bind(tsd, 0, false);
+		arena_bind(tsd, 0, true);
+	}
+
+	return (ret);
+}
+
+void
+thread_allocated_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+void
+thread_deallocated_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+void
+iarena_cleanup(tsd_t *tsd)
+{
+	arena_t *iarena;
+
+	iarena = tsd_iarena_get(tsd);
+	if (iarena != NULL)
+		arena_unbind(tsd, iarena->ind, true);
+}
+
+void
+arena_cleanup(tsd_t *tsd)
+{
+	arena_t *arena;
+
+	arena = tsd_arena_get(tsd);
+	if (arena != NULL)
+		arena_unbind(tsd, arena->ind, false);
+}
+
+void
+arenas_tdata_cleanup(tsd_t *tsd)
+{
+	arena_tdata_t *arenas_tdata;
+
+	/* 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);
+	}
+}
+
+void
+narenas_tdata_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+void
+arenas_tdata_bypass_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+static void
+stats_print_atexit(void)
+{
+
+	if (config_tcache && 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
+		 * events.  As a consequence, the final stats may be slightly
+		 * out of date by the time they are reported, if other threads
+		 * continue to allocate.
+		 */
+		for (i = 0, narenas = narenas_total_get(); i < narenas; 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(tsdn, &arena->lock);
+				ql_foreach(tcache, &arena->tcache_ql, link) {
+					tcache_stats_merge(tsdn, tcache, arena);
+				}
+				malloc_mutex_unlock(tsdn, &arena->lock);
+			}
+		}
+	}
+	je_malloc_stats_print(NULL, NULL, NULL);
+}
+
+/*
+ * End miscellaneous support functions.
+ */
+/******************************************************************************/
+/*
+ * Begin initialization functions.
+ */
+
+#ifndef JEMALLOC_HAVE_SECURE_GETENV
+static char *
+secure_getenv(const char *name)
+{
+
+#  ifdef JEMALLOC_HAVE_ISSETUGID
+	if (issetugid() != 0)
+		return (NULL);
+#  endif
+	return (getenv(name));
+}
+#endif
+
+static unsigned
+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);
+}
+
+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)
+{
+	bool accept;
+	const char *opts = *opts_p;
+
+	*k_p = opts;
+
+	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':
+		case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
+		case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
+		case 'Y': case 'Z':
+		case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
+		case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
+		case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
+		case 's': case 't': case 'u': case 'v': case 'w': case 'x':
+		case 'y': case 'z':
+		case '0': case '1': case '2': case '3': case '4': case '5':
+		case '6': case '7': case '8': case '9':
+		case '_':
+			opts++;
+			break;
+		case ':':
+			opts++;
+			*klen_p = (uintptr_t)opts - 1 - (uintptr_t)*k_p;
+			*v_p = opts;
+			accept = true;
+			break;
+		case '\0':
+			if (opts != *opts_p) {
+				malloc_write("<jemalloc>: Conf string ends "
+				    "with key\n");
+			}
+			return (true);
+		default:
+			malloc_write("<jemalloc>: Malformed conf string\n");
+			return (true);
+		}
+	}
+
+	for (accept = false; !accept;) {
+		switch (*opts) {
+		case ',':
+			opts++;
+			/*
+			 * Look ahead one character here, because the next time
+			 * this function is called, it will assume that end of
+			 * input has been cleanly reached if no input remains,
+			 * but we have optimistically already consumed the
+			 * comma if one exists.
+			 */
+			if (*opts == '\0') {
+				malloc_write("<jemalloc>: Conf string ends "
+				    "with comma\n");
+			}
+			*vlen_p = (uintptr_t)opts - 1 - (uintptr_t)*v_p;
+			accept = true;
+			break;
+		case '\0':
+			*vlen_p = (uintptr_t)opts - (uintptr_t)*v_p;
+			accept = true;
+			break;
+		default:
+			opts++;
+			break;
+		}
+	}
+
+	*opts_p = opts;
+	return (false);
+}
+
+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);
+}
+
+static 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_quarantine ? flag_opt_quarantine : 0)
+	    | (opt_zero ? flag_opt_zero : 0)
+	    | (opt_utrace ? flag_opt_utrace : 0)
+	    | (opt_xmalloc ? flag_opt_xmalloc : 0);
+
+	if (config_valgrind)
+		malloc_slow_flags |= (in_valgrind ? flag_in_valgrind : 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) {
+		in_valgrind = (RUNNING_ON_VALGRIND != 0) ? true : false;
+		if (config_fill && unlikely(in_valgrind)) {
+			opt_junk = "false";
+			opt_junk_alloc = false;
+			opt_junk_free = false;
+			assert(!opt_zero);
+			opt_quarantine = JEMALLOC_VALGRIND_QUARANTINE_DEFAULT;
+			opt_redzone = true;
+		}
+		if (config_tcache && unlikely(in_valgrind))
+			opt_tcache = false;
+	}
+
+	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
+				 * program.
+				 */
+				opts = je_malloc_conf;
+			} else {
+				/* No configuration specified. */
+				buf[0] = '\0';
+				opts = buf;
+			}
+			break;
+		case 2: {
+			ssize_t linklen = 0;
+#ifndef _WIN32
+			int saved_errno = errno;
+			const char *linkname =
+#  ifdef JEMALLOC_PREFIX
+			    "/etc/"JEMALLOC_PREFIX"malloc.conf"
+#  else
+			    "/etc/malloc.conf"
+#  endif
+			    ;
+
+			/*
+			 * Try to use the contents of the "/etc/malloc.conf"
+			 * symbolic link's name.
+			 */
+			linklen = readlink(linkname, buf, sizeof(buf) - 1);
+			if (linklen == -1) {
+				/* No configuration specified. */
+				linklen = 0;
+				/* Restore errno. */
+				set_errno(saved_errno);
+			}
+#endif
+			buf[linklen] = '\0';
+			opts = buf;
+			break;
+		} case 3: {
+			const char *envname =
+#ifdef JEMALLOC_PREFIX
+			    JEMALLOC_CPREFIX"MALLOC_CONF"
+#else
+			    "MALLOC_CONF"
+#endif
+			    ;
+
+			if ((opts = secure_getenv(envname)) != NULL) {
+				/*
+				 * Do nothing; opts is already initialized to
+				 * the value of the MALLOC_CONF environment
+				 * variable.
+				 */
+			} else {
+				/* No configuration specified. */
+				buf[0] = '\0';
+				opts = buf;
+			}
+			break;
+		} default:
+			not_reached();
+			buf[0] = '\0';
+			opts = buf;
+		}
+
+		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, cont)					\
+			if (CONF_MATCH(n)) {				\
+				if (CONF_MATCH_VALUE("true"))		\
+					o = true;			\
+				else if (CONF_MATCH_VALUE("false"))	\
+					o = false;			\
+				else {					\
+					malloc_conf_error(		\
+					    "Invalid conf value",	\
+					    k, klen, v, vlen);		\
+				}					\
+				if (cont)				\
+					continue;			\
+			}
+#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;				\
+									\
+				set_errno(0);				\
+				um = malloc_strtoumax(v, &end, 0);	\
+				if (get_errno() != 0 || (uintptr_t)end -\
+				    (uintptr_t)v != vlen) {		\
+					malloc_conf_error(		\
+					    "Invalid conf value",	\
+					    k, klen, v, vlen);		\
+				} else if (clip) {			\
+					if (CONF_MIN_##check_min(um,	\
+					    (min)))			\
+						o = (t)(min);		\
+					else if (CONF_MAX_##check_max(	\
+					    um, (max)))			\
+						o = (t)(max);		\
+					else				\
+						o = (t)um;		\
+				} else {				\
+					if (CONF_MIN_##check_min(um,	\
+					    (min)) ||			\
+					    CONF_MAX_##check_max(um,	\
+					    (max))) {			\
+						malloc_conf_error(	\
+						    "Out-of-range "	\
+						    "conf value",	\
+						    k, klen, v, vlen);	\
+					} else				\
+						o = (t)um;		\
+				}					\
+				continue;				\
+			}
+#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;				\
+									\
+				set_errno(0);				\
+				l = strtol(v, &end, 0);			\
+				if (get_errno() != 0 || (uintptr_t)end -\
+				    (uintptr_t)v != vlen) {		\
+					malloc_conf_error(		\
+					    "Invalid conf value",	\
+					    k, klen, v, vlen);		\
+				} else if (l < (ssize_t)(min) || l >	\
+				    (ssize_t)(max)) {			\
+					malloc_conf_error(		\
+					    "Out-of-range conf value",	\
+					    k, klen, v, vlen);		\
+				} else					\
+					o = l;				\
+				continue;				\
+			}
+#define	CONF_HANDLE_CHAR_P(o, n, d)					\
+			if (CONF_MATCH(n)) {				\
+				size_t cpylen = (vlen <=		\
+				    sizeof(o)-1) ? vlen :		\
+				    sizeof(o)-1;			\
+				strncpy(o, v, cpylen);			\
+				o[cpylen] = '\0';			\
+				continue;				\
+			}
+
+			CONF_HANDLE_BOOL(opt_abort, "abort", true)
+			/*
+			 * Chunks always require at least one header page,
+			 * as many as 2^(LG_SIZE_CLASS_GROUP+1) data pages, and
+			 * possibly an additional page in the presence of
+			 * redzones.  In order to simplify options processing,
+			 * use a conservative bound that accommodates all these
+			 * constraints.
+			 */
+			CONF_HANDLE_SIZE_T(opt_lg_chunk, "lg_chunk", LG_PAGE +
+			    LG_SIZE_CLASS_GROUP + (config_fill ? 2 : 1),
+			    (sizeof(size_t) << 3) - 1, yes, yes, true)
+			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)) {
+							malloc_conf_error(
+							    "Error setting dss",
+							    k, klen, v, vlen);
+						} else {
+							opt_dss =
+							    dss_prec_names[i];
+							match = true;
+							break;
+						}
+					}
+				}
+				if (!match) {
+					malloc_conf_error("Invalid conf value",
+					    k, klen, v, vlen);
+				}
+				continue;
+			}
+			CONF_HANDLE_UNSIGNED(opt_narenas, "narenas", 1,
+			    UINT_MAX, yes, no, false)
+			if (strncmp("purge", k, klen) == 0) {
+				int i;
+				bool match = false;
+				for (i = 0; i < purge_mode_limit; i++) {
+					if (strncmp(purge_mode_names[i], v,
+					    vlen) == 0) {
+						opt_purge = (purge_mode_t)i;
+						match = true;
+						break;
+					}
+				}
+				if (!match) {
+					malloc_conf_error("Invalid conf value",
+					    k, klen, v, vlen);
+				}
+				continue;
+			}
+			CONF_HANDLE_SSIZE_T(opt_lg_dirty_mult, "lg_dirty_mult",
+			    -1, (sizeof(size_t) << 3) - 1)
+			CONF_HANDLE_SSIZE_T(opt_decay_time, "decay_time", -1,
+			    NSTIME_SEC_MAX);
+			CONF_HANDLE_BOOL(opt_stats_print, "stats_print", true)
+			if (config_fill) {
+				if (CONF_MATCH("junk")) {
+					if (CONF_MATCH_VALUE("true")) {
+						if (config_valgrind &&
+						    unlikely(in_valgrind)) {
+							malloc_conf_error(
+							"Deallocation-time "
+							"junk filling cannot "
+							"be enabled while "
+							"running inside "
+							"Valgrind", k, klen, v,
+							vlen);
+						} else {
+							opt_junk = "true";
+							opt_junk_alloc = true;
+							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")) {
+						if (config_valgrind &&
+						    unlikely(in_valgrind)) {
+							malloc_conf_error(
+							"Deallocation-time "
+							"junk filling cannot "
+							"be enabled while "
+							"running inside "
+							"Valgrind", k, klen, v,
+							vlen);
+						} else {
+							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_SIZE_T(opt_quarantine, "quarantine",
+				    0, SIZE_T_MAX, no, no, false)
+				CONF_HANDLE_BOOL(opt_redzone, "redzone", true)
+				CONF_HANDLE_BOOL(opt_zero, "zero", true)
+			}
+			if (config_utrace) {
+				CONF_HANDLE_BOOL(opt_utrace, "utrace", true)
+			}
+			if (config_xmalloc) {
+				CONF_HANDLE_BOOL(opt_xmalloc, "xmalloc", true)
+			}
+			if (config_tcache) {
+				CONF_HANDLE_BOOL(opt_tcache, "tcache",
+				    !config_valgrind || !in_valgrind)
+				if (CONF_MATCH("tcache")) {
+					assert(config_valgrind && in_valgrind);
+					if (opt_tcache) {
+						opt_tcache = false;
+						malloc_conf_error(
+						"tcache cannot be enabled "
+						"while running inside Valgrind",
+						k, klen, v, vlen);
+					}
+					continue;
+				}
+				CONF_HANDLE_SSIZE_T(opt_lg_tcache_max,
+				    "lg_tcache_max", -1,
+				    (sizeof(size_t) << 3) - 1)
+			}
+			if (config_prof) {
+				CONF_HANDLE_BOOL(opt_prof, "prof", true)
+				CONF_HANDLE_CHAR_P(opt_prof_prefix,
+				    "prof_prefix", "jeprof")
+				CONF_HANDLE_BOOL(opt_prof_active, "prof_active",
+				    true)
+				CONF_HANDLE_BOOL(opt_prof_thread_active_init,
+				    "prof_thread_active_init", true)
+				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",
+				    true)
+				CONF_HANDLE_SSIZE_T(opt_lg_prof_interval,
+				    "lg_prof_interval", -1,
+				    (sizeof(uint64_t) << 3) - 1)
+				CONF_HANDLE_BOOL(opt_prof_gdump, "prof_gdump",
+				    true)
+				CONF_HANDLE_BOOL(opt_prof_final, "prof_final",
+				    true)
+				CONF_HANDLE_BOOL(opt_prof_leak, "prof_leak",
+				    true)
+			}
+			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
+		}
+	}
+}
+
+static bool
+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.
+		 */
+		return (false);
+	}
+#ifdef JEMALLOC_THREADED_INIT
+	if (malloc_initializer != NO_INITIALIZER && !IS_INITIALIZER) {
+		spin_t spinner;
+
+		/* Busy-wait until the initializing thread completes. */
+		spin_init(&spinner);
+		do {
+			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;
+
+	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)
+				abort();
+		}
+	}
+	pages_boot();
+	if (base_boot())
+		return (true);
+	if (chunk_boot())
+		return (true);
+	if (ctl_boot())
+		return (true);
+	if (config_prof)
+		prof_boot1();
+	arena_boot();
+	if (config_tcache && tcache_boot(TSDN_NULL))
+		return (true);
+	if (malloc_mutex_init(&arenas_lock, "arenas", WITNESS_RANK_ARENAS))
+		return (true);
+	/*
+	 * Create enough scaffolding to allow recursive allocation in
+	 * malloc_ncpus().
+	 */
+	narenas_auto = 1;
+	narenas_total_set(narenas_auto);
+	arenas = &a0;
+	memset(arenas, 0, sizeof(arena_t *) * narenas_auto);
+	/*
+	 * Initialize one arena here.  The rest are lazily created in
+	 * arena_choose_hard().
+	 */
+	if (arena_init(TSDN_NULL, 0) == NULL)
+		return (true);
+
+	malloc_init_state = malloc_init_a0_initialized;
+
+	return (false);
+}
+
+static bool
+malloc_init_hard_a0(void)
+{
+	bool ret;
+
+	malloc_mutex_lock(TSDN_NULL, &init_lock);
+	ret = malloc_init_hard_a0_locked();
+	malloc_mutex_unlock(TSDN_NULL, &init_lock);
+	return (ret);
+}
+
+/* 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_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)
+			abort();
+		return (true);
+	}
+#endif
+
+	return (false);
+}
+
+static bool
+malloc_init_hard_finish(tsdn_t *tsdn)
+{
+
+	if (malloc_mutex_boot())
+		return (true);
+
+	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;
+	}
+	narenas_auto = opt_narenas;
+	/*
+	 * Limit the number of arenas to the indexing range of MALLOCX_ARENA().
+	 */
+	if (narenas_auto > MALLOCX_ARENA_MAX) {
+		narenas_auto = MALLOCX_ARENA_MAX;
+		malloc_printf("<jemalloc>: Reducing narenas to limit (%d)\n",
+		    narenas_auto);
+	}
+	narenas_total_set(narenas_auto);
+
+	/* Allocate and initialize arenas. */
+	arenas = (arena_t **)base_alloc(tsdn, sizeof(arena_t *) *
+	    (MALLOCX_ARENA_MAX+1));
+	if (arenas == NULL)
+		return (true);
+	/* Copy the pointer to the one arena that was already initialized. */
+	arena_set(0, a0);
+
+	malloc_init_state = malloc_init_initialized;
+	malloc_slow_flag_init();
+
+	return (false);
+}
+
+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);
+	if (!malloc_init_hard_needed()) {
+		malloc_mutex_unlock(TSDN_NULL, &init_lock);
+		return (false);
+	}
+
+	if (malloc_init_state != malloc_init_a0_initialized &&
+	    malloc_init_hard_a0_locked()) {
+		malloc_mutex_unlock(TSDN_NULL, &init_lock);
+		return (true);
+	}
+
+	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);
+
+	if (config_prof && prof_boot2(tsd)) {
+		malloc_mutex_unlock(tsd_tsdn(tsd), &init_lock);
+		return (true);
+	}
+
+	if (malloc_init_hard_finish(tsd_tsdn(tsd))) {
+		malloc_mutex_unlock(tsd_tsdn(tsd), &init_lock);
+		return (true);
+	}
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &init_lock);
+	malloc_tsd_boot1();
+	return (false);
+}
+
+/*
+ * End initialization functions.
+ */
+/******************************************************************************/
+/*
+ * Begin malloc(3)-compatible functions.
+ */
+
+static void *
+ialloc_prof_sample(tsd_t *tsd, size_t usize, szind_t ind, bool zero,
+    prof_tctx_t *tctx, bool slow_path)
+{
+	void *p;
+
+	if (tctx == NULL)
+		return (NULL);
+	if (usize <= SMALL_MAXCLASS) {
+		szind_t ind_large = size2index(LARGE_MINCLASS);
+		p = ialloc(tsd, LARGE_MINCLASS, ind_large, zero, slow_path);
+		if (p == NULL)
+			return (NULL);
+		arena_prof_promoted(tsd_tsdn(tsd), p, usize);
+	} else
+		p = ialloc(tsd, usize, ind, zero, slow_path);
+
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+ialloc_prof(tsd_t *tsd, size_t usize, szind_t ind, bool zero, bool slow_path)
+{
+	void *p;
+	prof_tctx_t *tctx;
+
+	tctx = prof_alloc_prep(tsd, usize, prof_active_get_unlocked(), true);
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U))
+		p = ialloc_prof_sample(tsd, usize, ind, zero, tctx, slow_path);
+	else
+		p = ialloc(tsd, usize, ind, zero, slow_path);
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, true);
+		return (NULL);
+	}
+	prof_malloc(tsd_tsdn(tsd), p, usize, tctx);
+
+	return (p);
+}
+
+/*
+ * ialloc_body() is inlined so that fast and slow paths are generated separately
+ * with statically known slow_path.
+ *
+ * This function guarantees that *tsdn is non-NULL on success.
+ */
+JEMALLOC_ALWAYS_INLINE_C void *
+ialloc_body(size_t size, bool zero, tsdn_t **tsdn, size_t *usize,
+    bool slow_path)
+{
+	tsd_t *tsd;
+	szind_t ind;
+
+	if (slow_path && unlikely(malloc_init())) {
+		*tsdn = NULL;
+		return (NULL);
+	}
+
+	tsd = tsd_fetch();
+	*tsdn = tsd_tsdn(tsd);
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	ind = size2index(size);
+	if (unlikely(ind >= NSIZES))
+		return (NULL);
+
+	if (config_stats || (config_prof && opt_prof) || (slow_path &&
+	    config_valgrind && unlikely(in_valgrind))) {
+		*usize = index2size(ind);
+		assert(*usize > 0 && *usize <= HUGE_MAXCLASS);
+	}
+
+	if (config_prof && opt_prof)
+		return (ialloc_prof(tsd, *usize, ind, zero, slow_path));
+
+	return (ialloc(tsd, size, ind, zero, slow_path));
+}
+
+JEMALLOC_ALWAYS_INLINE_C void
+ialloc_post_check(void *ret, tsdn_t *tsdn, size_t usize, const char *func,
+    bool update_errno, bool slow_path)
+{
+
+	assert(!tsdn_null(tsdn) || ret == NULL);
+
+	if (unlikely(ret == NULL)) {
+		if (slow_path && config_xmalloc && unlikely(opt_xmalloc)) {
+			malloc_printf("<jemalloc>: Error in %s(): out of "
+			    "memory\n", func);
+			abort();
+		}
+		if (update_errno)
+			set_errno(ENOMEM);
+	}
+	if (config_stats && likely(ret != NULL)) {
+		assert(usize == isalloc(tsdn, ret, config_prof));
+		*tsd_thread_allocatedp_get(tsdn_tsd(tsdn)) += usize;
+	}
+	witness_assert_lockless(tsdn);
+}
+
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
+je_malloc(size_t size)
+{
+	void *ret;
+	tsdn_t *tsdn;
+	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
+
+	if (size == 0)
+		size = 1;
+
+	if (likely(!malloc_slow)) {
+		ret = ialloc_body(size, false, &tsdn, &usize, false);
+		ialloc_post_check(ret, tsdn, usize, "malloc", true, false);
+	} else {
+		ret = ialloc_body(size, false, &tsdn, &usize, true);
+		ialloc_post_check(ret, tsdn, usize, "malloc", true, true);
+		UTRACE(0, size, ret);
+		JEMALLOC_VALGRIND_MALLOC(ret != NULL, tsdn, ret, usize, false);
+	}
+
+	return (ret);
+}
+
+static void *
+imemalign_prof_sample(tsd_t *tsd, size_t alignment, size_t usize,
+    prof_tctx_t *tctx)
+{
+	void *p;
+
+	if (tctx == NULL)
+		return (NULL);
+	if (usize <= SMALL_MAXCLASS) {
+		assert(sa2u(LARGE_MINCLASS, alignment) == LARGE_MINCLASS);
+		p = ipalloc(tsd, LARGE_MINCLASS, alignment, false);
+		if (p == NULL)
+			return (NULL);
+		arena_prof_promoted(tsd_tsdn(tsd), p, usize);
+	} else
+		p = ipalloc(tsd, usize, alignment, false);
+
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+imemalign_prof(tsd_t *tsd, size_t alignment, size_t usize)
+{
+	void *p;
+	prof_tctx_t *tctx;
+
+	tctx = prof_alloc_prep(tsd, usize, prof_active_get_unlocked(), true);
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U))
+		p = imemalign_prof_sample(tsd, alignment, usize, tctx);
+	else
+		p = ipalloc(tsd, usize, alignment, false);
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, true);
+		return (NULL);
+	}
+	prof_malloc(tsd_tsdn(tsd), p, usize, tctx);
+
+	return (p);
+}
+
+JEMALLOC_ATTR(nonnull(1))
+static int
+imemalign(void **memptr, size_t alignment, size_t size, size_t min_alignment)
+{
+	int ret;
+	tsd_t *tsd;
+	size_t usize;
+	void *result;
+
+	assert(min_alignment != 0);
+
+	if (unlikely(malloc_init())) {
+		tsd = NULL;
+		result = NULL;
+		goto label_oom;
+	}
+	tsd = tsd_fetch();
+	witness_assert_lockless(tsd_tsdn(tsd));
+	if (size == 0)
+		size = 1;
+
+	/* Make sure that alignment is a large enough power of 2. */
+	if (unlikely(((alignment - 1) & alignment) != 0
+	    || (alignment < min_alignment))) {
+		if (config_xmalloc && unlikely(opt_xmalloc)) {
+			malloc_write("<jemalloc>: Error allocating "
+			    "aligned memory: invalid alignment\n");
+			abort();
+		}
+		result = NULL;
+		ret = EINVAL;
+		goto label_return;
+	}
+
+	usize = sa2u(size, alignment);
+	if (unlikely(usize == 0 || usize > HUGE_MAXCLASS)) {
+		result = NULL;
+		goto label_oom;
+	}
+
+	if (config_prof && opt_prof)
+		result = imemalign_prof(tsd, alignment, usize);
+	else
+		result = ipalloc(tsd, usize, alignment, false);
+	if (unlikely(result == NULL))
+		goto label_oom;
+	assert(((uintptr_t)result & (alignment - 1)) == ZU(0));
+
+	*memptr = result;
+	ret = 0;
+label_return:
+	if (config_stats && likely(result != NULL)) {
+		assert(usize == isalloc(tsd_tsdn(tsd), result, config_prof));
+		*tsd_thread_allocatedp_get(tsd) += usize;
+	}
+	UTRACE(0, size, result);
+	JEMALLOC_VALGRIND_MALLOC(result != NULL, tsd_tsdn(tsd), result, usize,
+	    false);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (ret);
+label_oom:
+	assert(result == NULL);
+	if (config_xmalloc && unlikely(opt_xmalloc)) {
+		malloc_write("<jemalloc>: Error allocating aligned memory: "
+		    "out of memory\n");
+		abort();
+	}
+	ret = ENOMEM;
+	witness_assert_lockless(tsd_tsdn(tsd));
+	goto label_return;
+}
+
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+JEMALLOC_ATTR(nonnull(1))
+je_posix_memalign(void **memptr, size_t alignment, size_t size)
+{
+	int ret;
+
+	ret = imemalign(memptr, alignment, size, sizeof(void *));
+
+	return (ret);
+}
+
+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;
+	int err;
+
+	if (unlikely((err = imemalign(&ret, alignment, size, 1)) != 0)) {
+		ret = NULL;
+		set_errno(err);
+	}
+
+	return (ret);
+}
+
+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;
+	tsdn_t *tsdn;
+	size_t num_size;
+	size_t usize JEMALLOC_CC_SILENCE_INIT(0);
+
+	num_size = num * size;
+	if (unlikely(num_size == 0)) {
+		if (num == 0 || size == 0)
+			num_size = 1;
+		else
+			num_size = HUGE_MAXCLASS + 1; /* Trigger OOM. */
+	/*
+	 * 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 (unlikely(((num | size) & (SIZE_T_MAX << (sizeof(size_t) <<
+	    2))) && (num_size / size != num)))
+		num_size = HUGE_MAXCLASS + 1; /* size_t overflow. */
+
+	if (likely(!malloc_slow)) {
+		ret = ialloc_body(num_size, true, &tsdn, &usize, false);
+		ialloc_post_check(ret, tsdn, usize, "calloc", true, false);
+	} else {
+		ret = ialloc_body(num_size, true, &tsdn, &usize, true);
+		ialloc_post_check(ret, tsdn, usize, "calloc", true, true);
+		UTRACE(0, num_size, ret);
+		JEMALLOC_VALGRIND_MALLOC(ret != NULL, tsdn, ret, usize, true);
+	}
+
+	return (ret);
+}
+
+static void *
+irealloc_prof_sample(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize,
+    prof_tctx_t *tctx)
+{
+	void *p;
+
+	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_promoted(tsd_tsdn(tsd), p, usize);
+	} else
+		p = iralloc(tsd, old_ptr, old_usize, usize, 0, false);
+
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+irealloc_prof(tsd_t *tsd, void *old_ptr, size_t old_usize, size_t usize)
+{
+	void *p;
+	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);
+	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);
+}
+
+JEMALLOC_INLINE_C void
+ifree(tsd_t *tsd, void *ptr, tcache_t *tcache, bool slow_path)
+{
+	size_t usize;
+	UNUSED size_t rzsize JEMALLOC_CC_SILENCE_INIT(0);
+
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	if (config_prof && opt_prof) {
+		usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+		prof_free(tsd, ptr, usize);
+	} else if (config_stats || config_valgrind)
+		usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+	if (config_stats)
+		*tsd_thread_deallocatedp_get(tsd) += usize;
+
+	if (likely(!slow_path))
+		iqalloc(tsd, ptr, tcache, false);
+	else {
+		if (config_valgrind && unlikely(in_valgrind))
+			rzsize = p2rz(tsd_tsdn(tsd), ptr);
+		iqalloc(tsd, ptr, tcache, true);
+		JEMALLOC_VALGRIND_FREE(ptr, rzsize);
+	}
+}
+
+JEMALLOC_INLINE_C void
+isfree(tsd_t *tsd, void *ptr, size_t usize, tcache_t *tcache, bool slow_path)
+{
+	UNUSED size_t rzsize JEMALLOC_CC_SILENCE_INIT(0);
+
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	if (config_prof && opt_prof)
+		prof_free(tsd, ptr, usize);
+	if (config_stats)
+		*tsd_thread_deallocatedp_get(tsd) += usize;
+	if (config_valgrind && unlikely(in_valgrind))
+		rzsize = p2rz(tsd_tsdn(tsd), ptr);
+	isqalloc(tsd, ptr, usize, tcache, slow_path);
+	JEMALLOC_VALGRIND_FREE(ptr, rzsize);
+}
+
+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 (unlikely(size == 0)) {
+		if (ptr != NULL) {
+			tsd_t *tsd;
+
+			/* realloc(ptr, 0) is equivalent to free(ptr). */
+			UTRACE(ptr, 0, 0);
+			tsd = tsd_fetch();
+			ifree(tsd, ptr, tcache_get(tsd, false), true);
+			return (NULL);
+		}
+		size = 1;
+	}
+
+	if (likely(ptr != NULL)) {
+		tsd_t *tsd;
+
+		assert(malloc_initialized() || IS_INITIALIZER);
+		malloc_thread_init();
+		tsd = tsd_fetch();
+
+		witness_assert_lockless(tsd_tsdn(tsd));
+
+		old_usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+		if (config_valgrind && unlikely(in_valgrind)) {
+			old_rzsize = config_prof ? p2rz(tsd_tsdn(tsd), ptr) :
+			    u2rz(old_usize);
+		}
+
+		if (config_prof && opt_prof) {
+			usize = s2u(size);
+			ret = unlikely(usize == 0 || usize > HUGE_MAXCLASS) ?
+			    NULL : irealloc_prof(tsd, ptr, old_usize, usize);
+		} else {
+			if (config_stats || (config_valgrind &&
+			    unlikely(in_valgrind)))
+				usize = s2u(size);
+			ret = iralloc(tsd, ptr, old_usize, size, 0, false);
+		}
+		tsdn = tsd_tsdn(tsd);
+	} else {
+		/* realloc(NULL, size) is equivalent to malloc(size). */
+		if (likely(!malloc_slow))
+			ret = ialloc_body(size, false, &tsdn, &usize, false);
+		else
+			ret = ialloc_body(size, false, &tsdn, &usize, true);
+		assert(!tsdn_null(tsdn) || ret == NULL);
+	}
+
+	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 && likely(ret != NULL)) {
+		tsd_t *tsd;
+
+		assert(usize == isalloc(tsdn, ret, config_prof));
+		tsd = tsdn_tsd(tsdn);
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
+	}
+	UTRACE(ptr, size, ret);
+	JEMALLOC_VALGRIND_REALLOC(maybe, tsdn, ret, usize, maybe, ptr,
+	    old_usize, old_rzsize, maybe, false);
+	witness_assert_lockless(tsdn);
+	return (ret);
+}
+
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_free(void *ptr)
+{
+
+	UTRACE(ptr, 0, 0);
+	if (likely(ptr != NULL)) {
+		tsd_t *tsd = tsd_fetch();
+		witness_assert_lockless(tsd_tsdn(tsd));
+		if (likely(!malloc_slow))
+			ifree(tsd, ptr, tcache_get(tsd, false), false);
+		else
+			ifree(tsd, ptr, tcache_get(tsd, false), true);
+		witness_assert_lockless(tsd_tsdn(tsd));
+	}
+}
+
+/*
+ * End malloc(3)-compatible functions.
+ */
+/******************************************************************************/
+/*
+ * Begin non-standard override functions.
+ */
+
+#ifdef JEMALLOC_OVERRIDE_MEMALIGN
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc)
+je_memalign(size_t alignment, size_t size)
+{
+	void *ret JEMALLOC_CC_SILENCE_INIT(NULL);
+	if (unlikely(imemalign(&ret, alignment, size, 1) != 0))
+		ret = NULL;
+	return (ret);
+}
+#endif
+
+#ifdef JEMALLOC_OVERRIDE_VALLOC
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc)
+je_valloc(size_t size)
+{
+	void *ret JEMALLOC_CC_SILENCE_INIT(NULL);
+	if (unlikely(imemalign(&ret, PAGE, size, 1) != 0))
+		ret = NULL;
+	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(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
+ * (https://bugzilla.mozilla.org/show_bug.cgi?id=493541).
+ *
+ * These definitions interpose hooks in glibc.  The functions are actually
+ * 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;
+# 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)
+void	*__libc_malloc(size_t size) PREALIAS(je_malloc);
+void	__libc_free(void* ptr) PREALIAS(je_free);
+void	*__libc_realloc(void* ptr, size_t size) PREALIAS(je_realloc);
+void	*__libc_calloc(size_t n, size_t size) PREALIAS(je_calloc);
+void	*__libc_memalign(size_t align, size_t s) PREALIAS(je_memalign);
+void	*__libc_valloc(size_t size) PREALIAS(je_valloc);
+int	__posix_memalign(void** r, size_t a, size_t s)
+    PREALIAS(je_posix_memalign);
+#undef PREALIAS
+#undef ALIAS
+
+#endif
+
+#endif
+
+/*
+ * End non-standard override functions.
+ */
+/******************************************************************************/
+/*
+ * Begin non-standard functions.
+ */
+
+JEMALLOC_ALWAYS_INLINE_C bool
+imallocx_flags_decode(tsd_t *tsd, size_t size, int flags, size_t *usize,
+    size_t *alignment, bool *zero, tcache_t **tcache, arena_t **arena)
+{
+
+	if ((flags & MALLOCX_LG_ALIGN_MASK) == 0) {
+		*alignment = 0;
+		*usize = s2u(size);
+	} else {
+		*alignment = MALLOCX_ALIGN_GET_SPECIFIED(flags);
+		*usize = sa2u(size, *alignment);
+	}
+	if (unlikely(*usize == 0 || *usize > HUGE_MAXCLASS))
+		return (true);
+	*zero = MALLOCX_ZERO_GET(flags);
+	if ((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, true);
+	if ((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))
+			return (true);
+	} else
+		*arena = NULL;
+	return (false);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+imallocx_flags(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero,
+    tcache_t *tcache, arena_t *arena, bool slow_path)
+{
+	szind_t ind;
+
+	if (unlikely(alignment != 0))
+		return (ipalloct(tsdn, usize, alignment, zero, tcache, arena));
+	ind = size2index(usize);
+	assert(ind < NSIZES);
+	return (iallocztm(tsdn, usize, ind, zero, tcache, false, arena,
+	    slow_path));
+}
+
+static void *
+imallocx_prof_sample(tsdn_t *tsdn, size_t usize, size_t alignment, bool zero,
+    tcache_t *tcache, arena_t *arena, bool slow_path)
+{
+	void *p;
+
+	if (usize <= SMALL_MAXCLASS) {
+		assert(((alignment == 0) ? s2u(LARGE_MINCLASS) :
+		    sa2u(LARGE_MINCLASS, alignment)) == LARGE_MINCLASS);
+		p = imallocx_flags(tsdn, LARGE_MINCLASS, alignment, zero,
+		    tcache, arena, slow_path);
+		if (p == NULL)
+			return (NULL);
+		arena_prof_promoted(tsdn, p, usize);
+	} else {
+		p = imallocx_flags(tsdn, usize, alignment, zero, tcache, arena,
+		    slow_path);
+	}
+
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+imallocx_prof(tsd_t *tsd, size_t size, int flags, size_t *usize, bool slow_path)
+{
+	void *p;
+	size_t alignment;
+	bool zero;
+	tcache_t *tcache;
+	arena_t *arena;
+	prof_tctx_t *tctx;
+
+	if (unlikely(imallocx_flags_decode(tsd, size, flags, usize, &alignment,
+	    &zero, &tcache, &arena)))
+		return (NULL);
+	tctx = prof_alloc_prep(tsd, *usize, prof_active_get_unlocked(), true);
+	if (likely((uintptr_t)tctx == (uintptr_t)1U)) {
+		p = imallocx_flags(tsd_tsdn(tsd), *usize, alignment, zero,
+		    tcache, arena, slow_path);
+	} else if ((uintptr_t)tctx > (uintptr_t)1U) {
+		p = imallocx_prof_sample(tsd_tsdn(tsd), *usize, alignment, zero,
+		    tcache, arena, slow_path);
+	} else
+		p = NULL;
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, true);
+		return (NULL);
+	}
+	prof_malloc(tsd_tsdn(tsd), p, *usize, tctx);
+
+	assert(alignment == 0 || ((uintptr_t)p & (alignment - 1)) == ZU(0));
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C void *
+imallocx_no_prof(tsd_t *tsd, size_t size, int flags, size_t *usize,
+    bool slow_path)
+{
+	void *p;
+	size_t alignment;
+	bool zero;
+	tcache_t *tcache;
+	arena_t *arena;
+
+	if (unlikely(imallocx_flags_decode(tsd, size, flags, usize, &alignment,
+	    &zero, &tcache, &arena)))
+		return (NULL);
+	p = imallocx_flags(tsd_tsdn(tsd), *usize, alignment, zero, tcache,
+	    arena, slow_path);
+	assert(alignment == 0 || ((uintptr_t)p & (alignment - 1)) == ZU(0));
+	return (p);
+}
+
+/* This function guarantees that *tsdn is non-NULL on success. */
+JEMALLOC_ALWAYS_INLINE_C void *
+imallocx_body(size_t size, int flags, tsdn_t **tsdn, size_t *usize,
+    bool slow_path)
+{
+	tsd_t *tsd;
+
+	if (slow_path && unlikely(malloc_init())) {
+		*tsdn = NULL;
+		return (NULL);
+	}
+
+	tsd = tsd_fetch();
+	*tsdn = tsd_tsdn(tsd);
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	if (likely(flags == 0)) {
+		szind_t ind = size2index(size);
+		if (unlikely(ind >= NSIZES))
+			return (NULL);
+		if (config_stats || (config_prof && opt_prof) || (slow_path &&
+		    config_valgrind && unlikely(in_valgrind))) {
+			*usize = index2size(ind);
+			assert(*usize > 0 && *usize <= HUGE_MAXCLASS);
+		}
+
+		if (config_prof && opt_prof) {
+			return (ialloc_prof(tsd, *usize, ind, false,
+			    slow_path));
+		}
+
+		return (ialloc(tsd, size, ind, false, slow_path));
+	}
+
+	if (config_prof && opt_prof)
+		return (imallocx_prof(tsd, size, flags, usize, slow_path));
+
+	return (imallocx_no_prof(tsd, size, flags, usize, slow_path));
+}
+
+JEMALLOC_EXPORT JEMALLOC_ALLOCATOR JEMALLOC_RESTRICT_RETURN
+void JEMALLOC_NOTHROW *
+JEMALLOC_ATTR(malloc) JEMALLOC_ALLOC_SIZE(1)
+je_mallocx(size_t size, int flags)
+{
+	tsdn_t *tsdn;
+	void *p;
+	size_t usize;
+
+	assert(size != 0);
+
+	if (likely(!malloc_slow)) {
+		p = imallocx_body(size, flags, &tsdn, &usize, false);
+		ialloc_post_check(p, tsdn, usize, "mallocx", false, false);
+	} else {
+		p = imallocx_body(size, flags, &tsdn, &usize, true);
+		ialloc_post_check(p, tsdn, usize, "mallocx", false, true);
+		UTRACE(0, size, p);
+		JEMALLOC_VALGRIND_MALLOC(p != NULL, tsdn, p, usize,
+		    MALLOCX_ZERO_GET(flags));
+	}
+
+	return (p);
+}
+
+static void *
+irallocx_prof_sample(tsd_t *tsd, 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 (tctx == NULL)
+		return (NULL);
+	if (usize <= SMALL_MAXCLASS) {
+		p = iralloct(tsd, old_ptr, old_usize, LARGE_MINCLASS, alignment,
+		    zero, tcache, arena);
+		if (p == NULL)
+			return (NULL);
+		arena_prof_promoted(tsd_tsdn(tsd), p, usize);
+	} else {
+		p = iralloct(tsd, old_ptr, old_usize, usize, alignment, zero,
+		    tcache, arena);
+	}
+
+	return (p);
+}
+
+JEMALLOC_ALWAYS_INLINE_C 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)
+{
+	void *p;
+	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);
+	tctx = prof_alloc_prep(tsd, *usize, prof_active, false);
+	if (unlikely((uintptr_t)tctx != (uintptr_t)1U)) {
+		p = irallocx_prof_sample(tsd, old_ptr, old_usize, *usize,
+		    alignment, zero, tcache, arena, tctx);
+	} else {
+		p = iralloct(tsd, old_ptr, old_usize, size, alignment, zero,
+		    tcache, arena);
+	}
+	if (unlikely(p == NULL)) {
+		prof_alloc_rollback(tsd, tctx, false);
+		return (NULL);
+	}
+
+	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
+		 * alignment, and that the alignment constraint was
+		 * serendipitously satisfied.  Additionally, old_usize may not
+		 * be the same as the current usize because of in-place large
+		 * reallocation.  Therefore, query the actual value of usize.
+		 */
+		*usize = isalloc(tsd_tsdn(tsd), p, config_prof);
+	}
+	prof_realloc(tsd, p, *usize, tctx, prof_active, false, old_ptr,
+	    old_usize, old_tctx);
+
+	return (p);
+}
+
+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;
+	tsd_t *tsd;
+	size_t usize;
+	size_t old_usize;
+	UNUSED size_t old_rzsize JEMALLOC_CC_SILENCE_INIT(0);
+	size_t alignment = MALLOCX_ALIGN_GET(flags);
+	bool zero = flags & MALLOCX_ZERO;
+	arena_t *arena;
+	tcache_t *tcache;
+
+	assert(ptr != NULL);
+	assert(size != 0);
+	assert(malloc_initialized() || IS_INITIALIZER);
+	malloc_thread_init();
+	tsd = tsd_fetch();
+	witness_assert_lockless(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
+		arena = NULL;
+
+	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, true);
+
+	old_usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+	if (config_valgrind && unlikely(in_valgrind))
+		old_rzsize = u2rz(old_usize);
+
+	if (config_prof && opt_prof) {
+		usize = (alignment == 0) ? s2u(size) : sa2u(size, alignment);
+		if (unlikely(usize == 0 || usize > HUGE_MAXCLASS))
+			goto label_oom;
+		p = irallocx_prof(tsd, ptr, old_usize, size, alignment, &usize,
+		    zero, tcache, arena);
+		if (unlikely(p == NULL))
+			goto label_oom;
+	} else {
+		p = iralloct(tsd, ptr, old_usize, size, alignment, zero,
+		     tcache, arena);
+		if (unlikely(p == NULL))
+			goto label_oom;
+		if (config_stats || (config_valgrind && unlikely(in_valgrind)))
+			usize = isalloc(tsd_tsdn(tsd), p, config_prof);
+	}
+	assert(alignment == 0 || ((uintptr_t)p & (alignment - 1)) == ZU(0));
+
+	if (config_stats) {
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
+	}
+	UTRACE(ptr, size, p);
+	JEMALLOC_VALGRIND_REALLOC(maybe, tsd_tsdn(tsd), p, usize, no, ptr,
+	    old_usize, old_rzsize, no, zero);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (p);
+label_oom:
+	if (config_xmalloc && unlikely(opt_xmalloc)) {
+		malloc_write("<jemalloc>: Error in rallocx(): out of memory\n");
+		abort();
+	}
+	UTRACE(ptr, size, 0);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (NULL);
+}
+
+JEMALLOC_ALWAYS_INLINE_C 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(tsdn, ptr, old_usize, size, extra, alignment, zero))
+		return (old_usize);
+	usize = isalloc(tsdn, ptr, config_prof);
+
+	return (usize);
+}
+
+static size_t
+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 (tctx == NULL)
+		return (old_usize);
+	usize = ixallocx_helper(tsdn, ptr, old_usize, size, extra, alignment,
+	    zero);
+
+	return (usize);
+}
+
+JEMALLOC_ALWAYS_INLINE_C size_t
+ixallocx_prof(tsd_t *tsd, void *ptr, size_t old_usize, size_t size,
+    size_t extra, size_t alignment, bool zero)
+{
+	size_t usize_max, usize;
+	bool prof_active;
+	prof_tctx_t *old_tctx, *tctx;
+
+	prof_active = prof_active_get_unlocked();
+	old_tctx = prof_tctx_get(tsd_tsdn(tsd), ptr);
+	/*
+	 * 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 = s2u(size+extra);
+		assert(usize_max > 0 && usize_max <= HUGE_MAXCLASS);
+	} else {
+		usize_max = sa2u(size+extra, alignment);
+		if (unlikely(usize_max == 0 || usize_max > HUGE_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 = HUGE_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(tsd_tsdn(tsd), ptr, old_usize, size,
+		    extra, alignment, zero);
+	}
+	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);
+}
+
+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 = MALLOCX_ALIGN_GET(flags);
+	bool zero = flags & MALLOCX_ZERO;
+
+	assert(ptr != NULL);
+	assert(size != 0);
+	assert(SIZE_T_MAX - size >= extra);
+	assert(malloc_initialized() || IS_INITIALIZER);
+	malloc_thread_init();
+	tsd = tsd_fetch();
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	old_usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+
+	/*
+	 * The API explicitly absolves itself of protecting against (size +
+	 * extra) numerical overflow, but we may need to clamp extra to avoid
+	 * exceeding HUGE_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 > HUGE_MAXCLASS)) {
+		usize = old_usize;
+		goto label_not_resized;
+	}
+	if (unlikely(HUGE_MAXCLASS - size < extra))
+		extra = HUGE_MAXCLASS - size;
+
+	if (config_valgrind && unlikely(in_valgrind))
+		old_rzsize = u2rz(old_usize);
+
+	if (config_prof && opt_prof) {
+		usize = ixallocx_prof(tsd, ptr, old_usize, size, extra,
+		    alignment, zero);
+	} else {
+		usize = ixallocx_helper(tsd_tsdn(tsd), ptr, old_usize, size,
+		    extra, alignment, zero);
+	}
+	if (unlikely(usize == old_usize))
+		goto label_not_resized;
+
+	if (config_stats) {
+		*tsd_thread_allocatedp_get(tsd) += usize;
+		*tsd_thread_deallocatedp_get(tsd) += old_usize;
+	}
+	JEMALLOC_VALGRIND_REALLOC(no, tsd_tsdn(tsd), ptr, usize, no, ptr,
+	    old_usize, old_rzsize, no, zero);
+label_not_resized:
+	UTRACE(ptr, size, ptr);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (usize);
+}
+
+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);
+	malloc_thread_init();
+
+	tsdn = tsdn_fetch();
+	witness_assert_lockless(tsdn);
+
+	if (config_ivsalloc)
+		usize = ivsalloc(tsdn, ptr, config_prof);
+	else
+		usize = isalloc(tsdn, ptr, config_prof);
+
+	witness_assert_lockless(tsdn);
+	return (usize);
+}
+
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_dallocx(void *ptr, int flags)
+{
+	tsd_t *tsd;
+	tcache_t *tcache;
+
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+
+	tsd = tsd_fetch();
+	witness_assert_lockless(tsd_tsdn(tsd));
+	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, false);
+
+	UTRACE(ptr, 0, 0);
+	if (likely(!malloc_slow))
+		ifree(tsd, ptr, tcache, false);
+	else
+		ifree(tsd, ptr, tcache, true);
+	witness_assert_lockless(tsd_tsdn(tsd));
+}
+
+JEMALLOC_ALWAYS_INLINE_C size_t
+inallocx(tsdn_t *tsdn, size_t size, int flags)
+{
+	size_t usize;
+
+	witness_assert_lockless(tsdn);
+
+	if (likely((flags & MALLOCX_LG_ALIGN_MASK) == 0))
+		usize = s2u(size);
+	else
+		usize = sa2u(size, MALLOCX_ALIGN_GET_SPECIFIED(flags));
+	witness_assert_lockless(tsdn);
+	return (usize);
+}
+
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_sdallocx(void *ptr, size_t size, int flags)
+{
+	tsd_t *tsd;
+	tcache_t *tcache;
+	size_t usize;
+
+	assert(ptr != NULL);
+	assert(malloc_initialized() || IS_INITIALIZER);
+	tsd = tsd_fetch();
+	usize = inallocx(tsd_tsdn(tsd), size, flags);
+	assert(usize == isalloc(tsd_tsdn(tsd), ptr, config_prof));
+
+	witness_assert_lockless(tsd_tsdn(tsd));
+	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, false);
+
+	UTRACE(ptr, 0, 0);
+	if (likely(!malloc_slow))
+		isfree(tsd, ptr, usize, tcache, false);
+	else
+		isfree(tsd, ptr, usize, tcache, true);
+	witness_assert_lockless(tsd_tsdn(tsd));
+}
+
+JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW
+JEMALLOC_ATTR(pure)
+je_nallocx(size_t size, int flags)
+{
+	size_t usize;
+	tsdn_t *tsdn;
+
+	assert(size != 0);
+
+	if (unlikely(malloc_init()))
+		return (0);
+
+	tsdn = tsdn_fetch();
+	witness_assert_lockless(tsdn);
+
+	usize = inallocx(tsdn, size, flags);
+	if (unlikely(usize > HUGE_MAXCLASS))
+		return (0);
+
+	witness_assert_lockless(tsdn);
+	return (usize);
+}
+
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+je_mallctl(const char *name, void *oldp, size_t *oldlenp, void *newp,
+    size_t newlen)
+{
+	int ret;
+	tsd_t *tsd;
+
+	if (unlikely(malloc_init()))
+		return (EAGAIN);
+
+	tsd = tsd_fetch();
+	witness_assert_lockless(tsd_tsdn(tsd));
+	ret = ctl_byname(tsd, name, oldp, oldlenp, newp, newlen);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (ret);
+}
+
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+je_mallctlnametomib(const char *name, size_t *mibp, size_t *miblenp)
+{
+	int ret;
+	tsdn_t *tsdn;
+
+	if (unlikely(malloc_init()))
+		return (EAGAIN);
+
+	tsdn = tsdn_fetch();
+	witness_assert_lockless(tsdn);
+	ret = ctl_nametomib(tsdn, name, mibp, miblenp);
+	witness_assert_lockless(tsdn);
+	return (ret);
+}
+
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+je_mallctlbymib(const size_t *mib, size_t miblen, void *oldp, size_t *oldlenp,
+  void *newp, size_t newlen)
+{
+	int ret;
+	tsd_t *tsd;
+
+	if (unlikely(malloc_init()))
+		return (EAGAIN);
+
+	tsd = tsd_fetch();
+	witness_assert_lockless(tsd_tsdn(tsd));
+	ret = ctl_bymib(tsd, mib, miblen, oldp, oldlenp, newp, newlen);
+	witness_assert_lockless(tsd_tsdn(tsd));
+	return (ret);
+}
+
+JEMALLOC_EXPORT void JEMALLOC_NOTHROW
+je_malloc_stats_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    const char *opts)
+{
+	tsdn_t *tsdn;
+
+	tsdn = tsdn_fetch();
+	witness_assert_lockless(tsdn);
+	stats_print(write_cb, cbopaque, opts);
+	witness_assert_lockless(tsdn);
+}
+
+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();
+
+	tsdn = tsdn_fetch();
+	witness_assert_lockless(tsdn);
+
+	if (config_ivsalloc)
+		ret = ivsalloc(tsdn, ptr, config_prof);
+	else
+		ret = (ptr == NULL) ? 0 : isalloc(tsdn, ptr, config_prof);
+
+	witness_assert_lockless(tsdn);
+	return (ret);
+}
+
+/*
+ * End non-standard functions.
+ */
+/******************************************************************************/
+/*
+ * The following functions are used by threading libraries for protection of
+ * malloc during fork().
+ */
+
+/*
+ * If an application creates a thread before doing any allocation in the main
+ * thread, then calls fork(2) in the main thread followed by memory allocation
+ * in the child process, a race can occur that results in deadlock within the
+ * child: the main thread may have forked while the created thread had
+ * partially initialized the allocator.  Ordinarily jemalloc prevents
+ * 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 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)
+{
+
+	malloc_init();
+}
+#endif
+
+#ifndef JEMALLOC_MUTEX_INIT_CB
+void
+jemalloc_prefork(void)
+#else
+JEMALLOC_EXPORT void
+_malloc_prefork(void)
+#endif
+{
+	tsd_t *tsd;
+	unsigned i, j, narenas;
+	arena_t *arena;
+
+#ifdef JEMALLOC_MUTEX_INIT_CB
+	if (!malloc_initialized())
+		return;
+#endif
+	assert(malloc_initialized());
+
+	tsd = tsd_fetch();
+
+	narenas = narenas_total_get();
+
+	witness_prefork(tsd);
+	/* Acquire all mutexes in a safe order. */
+	ctl_prefork(tsd_tsdn(tsd));
+	malloc_mutex_prefork(tsd_tsdn(tsd), &arenas_lock);
+	prof_prefork0(tsd_tsdn(tsd));
+	for (i = 0; i < 3; 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;
+				default: not_reached();
+				}
+			}
+		}
+	}
+	base_prefork(tsd_tsdn(tsd));
+	for (i = 0; i < narenas; i++) {
+		if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL)
+			arena_prefork3(tsd_tsdn(tsd), arena);
+	}
+	prof_prefork1(tsd_tsdn(tsd));
+}
+
+#ifndef JEMALLOC_MUTEX_INIT_CB
+void
+jemalloc_postfork_parent(void)
+#else
+JEMALLOC_EXPORT void
+_malloc_postfork(void)
+#endif
+{
+	tsd_t *tsd;
+	unsigned i, narenas;
+
+#ifdef JEMALLOC_MUTEX_INIT_CB
+	if (!malloc_initialized())
+		return;
+#endif
+	assert(malloc_initialized());
+
+	tsd = tsd_fetch();
+
+	witness_postfork_parent(tsd);
+	/* Release all mutexes, now that fork() has completed. */
+	base_postfork_parent(tsd_tsdn(tsd));
+	for (i = 0, narenas = narenas_total_get(); i < narenas; i++) {
+		arena_t *arena;
+
+		if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL)
+			arena_postfork_parent(tsd_tsdn(tsd), arena);
+	}
+	prof_postfork_parent(tsd_tsdn(tsd));
+	malloc_mutex_postfork_parent(tsd_tsdn(tsd), &arenas_lock);
+	ctl_postfork_parent(tsd_tsdn(tsd));
+}
+
+void
+jemalloc_postfork_child(void)
+{
+	tsd_t *tsd;
+	unsigned i, narenas;
+
+	assert(malloc_initialized());
+
+	tsd = tsd_fetch();
+
+	witness_postfork_child(tsd);
+	/* Release all mutexes, now that fork() has completed. */
+	base_postfork_child(tsd_tsdn(tsd));
+	for (i = 0, narenas = narenas_total_get(); i < narenas; i++) {
+		arena_t *arena;
+
+		if ((arena = arena_get(tsd_tsdn(tsd), i, false)) != NULL)
+			arena_postfork_child(tsd_tsdn(tsd), arena);
+	}
+	prof_postfork_child(tsd_tsdn(tsd));
+	malloc_mutex_postfork_child(tsd_tsdn(tsd), &arenas_lock);
+	ctl_postfork_child(tsd_tsdn(tsd));
+}
+
+/******************************************************************************/
+
+/* Helps the application decide if a pointer is worth re-allocating in order to reduce fragmentation.
+ * returns 0 if the allocation is in the currently active run,
+ * or when it is not causing any frag issue (large or huge bin)
+ * returns the bin utilization and run utilization both in fixed point 16:16.
+ * If the application decides to re-allocate it should use MALLOCX_TCACHE_NONE when doing so. */
+JEMALLOC_EXPORT int JEMALLOC_NOTHROW
+je_get_defrag_hint(void* ptr, int *bin_util, int *run_util) {
+    int defrag = 0;
+    arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+    if (likely(chunk != ptr)) { /* indication that this is not a HUGE alloc */
+        size_t pageind = ((uintptr_t)ptr - (uintptr_t)chunk) >> LG_PAGE;
+        size_t mapbits = arena_mapbits_get(chunk, pageind);
+        if (likely((mapbits & CHUNK_MAP_LARGE) == 0)) { /* indication that this is not a LARGE alloc */
+            arena_t *arena = extent_node_arena_get(&chunk->node);
+            size_t rpages_ind = pageind - arena_mapbits_small_runind_get(chunk, pageind);
+            arena_run_t *run = &arena_miscelm_get_mutable(chunk, rpages_ind)->run;
+            arena_bin_t *bin = &arena->bins[run->binind];
+            tsd_t *tsd = tsd_fetch();
+            malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+            /* runs that are in the same chunk in as the current chunk, are likely to be the next currun */
+            if (chunk != (arena_chunk_t *)CHUNK_ADDR2BASE(bin->runcur)) {
+                arena_bin_info_t *bin_info = &arena_bin_info[run->binind];
+                size_t availregs = bin_info->nregs * bin->stats.curruns;
+                *bin_util = (bin->stats.curregs<<16) / availregs;
+                *run_util = ((bin_info->nregs - run->nfree)<<16) / bin_info->nregs;
+                defrag = 1;
+            }
+	    malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+        }
+    }
+    return defrag;
+}
diff --git a/deps/jemalloc/src/mb.c b/deps/jemalloc/src/mb.c
new file mode 100644
index 0000000..dc2c0a2
--- /dev/null
+++ b/deps/jemalloc/src/mb.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_MB_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/mutex.c b/deps/jemalloc/src/mutex.c
new file mode 100644
index 0000000..6333e73
--- /dev/null
+++ b/deps/jemalloc/src/mutex.c
@@ -0,0 +1,158 @@
+#define	JEMALLOC_MUTEX_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+#if defined(JEMALLOC_LAZY_LOCK) && !defined(_WIN32)
+#include <dlfcn.h>
+#endif
+
+#ifndef _CRT_SPINCOUNT
+#define	_CRT_SPINCOUNT 4000
+#endif
+
+/******************************************************************************/
+/* Data. */
+
+#ifdef JEMALLOC_LAZY_LOCK
+bool isthreaded = false;
+#endif
+#ifdef JEMALLOC_MUTEX_INIT_CB
+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
+ * process goes multi-threaded.
+ */
+
+#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));
+}
+#endif
+
+/******************************************************************************/
+
+#ifdef JEMALLOC_MUTEX_INIT_CB
+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, const char *name, witness_rank_t rank)
+{
+
+#ifdef _WIN32
+#  if _WIN32_WINNT >= 0x0600
+	InitializeSRWLock(&mutex->lock);
+#  else
+	if (!InitializeCriticalSectionAndSpinCount(&mutex->lock,
+	    _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))
+	if (postpone_init) {
+		mutex->postponed_next = postponed_mutexes;
+		postponed_mutexes = mutex;
+	} else {
+		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);
+	pthread_mutexattr_settype(&attr, MALLOC_MUTEX_TYPE);
+	if (pthread_mutex_init(&mutex->lock, &attr) != 0) {
+		pthread_mutexattr_destroy(&attr);
+		return (true);
+	}
+	pthread_mutexattr_destroy(&attr);
+#endif
+	if (config_debug)
+		witness_init(&mutex->witness, name, rank, NULL);
+	return (false);
+}
+
+void
+malloc_mutex_prefork(tsdn_t *tsdn, malloc_mutex_t *mutex)
+{
+
+	malloc_mutex_lock(tsdn, mutex);
+}
+
+void
+malloc_mutex_postfork_parent(tsdn_t *tsdn, malloc_mutex_t *mutex)
+{
+
+	malloc_mutex_unlock(tsdn, mutex);
+}
+
+void
+malloc_mutex_postfork_child(tsdn_t *tsdn, malloc_mutex_t *mutex)
+{
+
+#ifdef JEMALLOC_MUTEX_INIT_CB
+	malloc_mutex_unlock(tsdn, mutex);
+#else
+	if (malloc_mutex_init(mutex, mutex->witness.name,
+	    mutex->witness.rank)) {
+		malloc_printf("<jemalloc>: Error re-initializing mutex in "
+		    "child\n");
+		if (opt_abort)
+			abort();
+	}
+#endif
+}
+
+bool
+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,
+		    bootstrap_calloc) != 0)
+			return (true);
+		postponed_mutexes = postponed_mutexes->postponed_next;
+	}
+#endif
+	return (false);
+}
diff --git a/deps/jemalloc/src/nstime.c b/deps/jemalloc/src/nstime.c
new file mode 100644
index 0000000..0948e29
--- /dev/null
+++ b/deps/jemalloc/src/nstime.c
@@ -0,0 +1,194 @@
+#include "jemalloc/internal/jemalloc_internal.h"
+
+#define	BILLION	UINT64_C(1000000000)
+
+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_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_subtract(nstime_t *time, const nstime_t *subtrahend)
+{
+
+	assert(nstime_compare(time, subtrahend) >= 0);
+
+	time->ns -= subtrahend->ns;
+}
+
+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 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 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 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
+
+#ifdef JEMALLOC_JET
+#undef nstime_monotonic
+#define	nstime_monotonic JEMALLOC_N(n_nstime_monotonic)
+#endif
+bool
+nstime_monotonic(void)
+{
+
+	return (NSTIME_MONOTONIC);
+#undef NSTIME_MONOTONIC
+}
+#ifdef JEMALLOC_JET
+#undef nstime_monotonic
+#define	nstime_monotonic JEMALLOC_N(nstime_monotonic)
+nstime_monotonic_t *nstime_monotonic = JEMALLOC_N(n_nstime_monotonic);
+#endif
+
+#ifdef JEMALLOC_JET
+#undef nstime_update
+#define	nstime_update JEMALLOC_N(n_nstime_update)
+#endif
+bool
+nstime_update(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);
+}
+#ifdef JEMALLOC_JET
+#undef nstime_update
+#define	nstime_update JEMALLOC_N(nstime_update)
+nstime_update_t *nstime_update = JEMALLOC_N(n_nstime_update);
+#endif
diff --git a/deps/jemalloc/src/pages.c b/deps/jemalloc/src/pages.c
new file mode 100644
index 0000000..5f0c966
--- /dev/null
+++ b/deps/jemalloc/src/pages.c
@@ -0,0 +1,302 @@
+#define	JEMALLOC_PAGES_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+#ifdef JEMALLOC_SYSCTL_VM_OVERCOMMIT
+#include <sys/sysctl.h>
+#endif
+
+/******************************************************************************/
+/* Data. */
+
+#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;
+
+/******************************************************************************/
+
+void *
+pages_map(void *addr, size_t size, bool *commit)
+{
+	void *ret;
+
+	assert(size != 0);
+
+	if (os_overcommits)
+		*commit = true;
+
+#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.
+		 */
+		pages_unmap(ret, size);
+		ret = NULL;
+	}
+#endif
+	assert(ret == NULL || (addr == NULL && ret != addr)
+	    || (addr != NULL && ret == addr));
+	return (ret);
+}
+
+void
+pages_unmap(void *addr, size_t 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();
+	}
+}
+
+void *
+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
+	{
+		void *new_addr;
+
+		pages_unmap(addr, alloc_size);
+		new_addr = pages_map(ret, size, commit);
+		if (new_addr == ret)
+			return (ret);
+		if (new_addr)
+			pages_unmap(new_addr, size);
+		return (NULL);
+	}
+#else
+	{
+		size_t trailsize = alloc_size - leadsize - size;
+
+		if (leadsize != 0)
+			pages_unmap(addr, leadsize);
+		if (trailsize != 0)
+			pages_unmap((void *)((uintptr_t)ret + size), trailsize);
+		return (ret);
+	}
+#endif
+}
+
+static bool
+pages_commit_impl(void *addr, size_t size, bool commit)
+{
+
+	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.
+			 */
+			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(void *addr, size_t size)
+{
+	bool unzeroed;
+
+#ifdef _WIN32
+	VirtualAlloc(addr, size, MEM_RESET, PAGE_READWRITE);
+	unzeroed = true;
+#elif (defined(JEMALLOC_PURGE_MADVISE_FREE) || \
+    defined(JEMALLOC_PURGE_MADVISE_DONTNEED))
+#  if defined(JEMALLOC_PURGE_MADVISE_FREE)
+#    define JEMALLOC_MADV_PURGE MADV_FREE
+#    define JEMALLOC_MADV_ZEROS false
+#  elif defined(JEMALLOC_PURGE_MADVISE_DONTNEED)
+#    define JEMALLOC_MADV_PURGE MADV_DONTNEED
+#    define JEMALLOC_MADV_ZEROS true
+#  else
+#    error No madvise(2) flag defined for purging unused dirty pages
+#  endif
+	int err = madvise(addr, size, JEMALLOC_MADV_PURGE);
+	unzeroed = (!JEMALLOC_MADV_ZEROS || err != 0);
+#  undef JEMALLOC_MADV_PURGE
+#  undef JEMALLOC_MADV_ZEROS
+#else
+	/* Last resort no-op. */
+	unzeroed = true;
+#endif
+	return (unzeroed);
+}
+
+bool
+pages_huge(void *addr, size_t size)
+{
+
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+#ifdef JEMALLOC_THP
+	return (madvise(addr, size, MADV_HUGEPAGE) != 0);
+#else
+	return (false);
+#endif
+}
+
+bool
+pages_nohuge(void *addr, size_t size)
+{
+
+	assert(PAGE_ADDR2BASE(addr) == addr);
+	assert(PAGE_CEILING(size) == size);
+
+#ifdef JEMALLOC_THP
+	return (madvise(addr, size, MADV_NOHUGEPAGE) != 0);
+#else
+	return (false);
+#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);
+#else
+	fd = open("/proc/sys/vm/overcommit_memory", O_RDONLY);
+#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
+
+void
+pages_boot(void)
+{
+
+#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
+}
diff --git a/deps/jemalloc/src/prng.c b/deps/jemalloc/src/prng.c
new file mode 100644
index 0000000..76646a2
--- /dev/null
+++ b/deps/jemalloc/src/prng.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_PRNG_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/prof.c b/deps/jemalloc/src/prof.c
new file mode 100644
index 0000000..c89dade
--- /dev/null
+++ b/deps/jemalloc/src/prof.c
@@ -0,0 +1,2355 @@
+#define	JEMALLOC_PROF_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+/******************************************************************************/
+
+#ifdef JEMALLOC_PROF_LIBUNWIND
+#define	UNW_LOCAL_ONLY
+#include <libunwind.h>
+#endif
+
+#ifdef JEMALLOC_PROF_LIBGCC
+#include <unwind.h>
+#endif
+
+/******************************************************************************/
+/* Data. */
+
+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 = false;
+bool		opt_prof_leak = false;
+bool		opt_prof_accum = false;
+char		opt_prof_prefix[
+    /* Minimize memory bloat for non-prof builds. */
+#ifdef JEMALLOC_PROF
+    PATH_MAX +
+#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;
+
+size_t		lg_prof_sample;
+
+/*
+ * 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	*gctx_locks;
+static unsigned		cum_gctxs; /* Atomic counter. */
+
+/*
+ * 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		bt2gctx;
+static 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;
+static uint64_t		prof_dump_iseq;
+static uint64_t		prof_dump_mseq;
+static uint64_t		prof_dump_useq;
+
+/*
+ * This buffer is rather large for stack allocation, so use a single buffer for
+ * all profile dumps.
+ */
+static malloc_mutex_t	prof_dump_mtx;
+static char		prof_dump_buf[
+    /* Minimize memory bloat for non-prof builds. */
+#ifdef JEMALLOC_PROF
+    PROF_DUMP_BUFSIZE
+#else
+    1
+#endif
+];
+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.
+ */
+
+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);
+
+/******************************************************************************/
+/* Red-black trees. */
+
+JEMALLOC_INLINE_C 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);
+}
+
+rb_gen(static UNUSED, tctx_tree_, prof_tctx_tree_t, prof_tctx_t,
+    tctx_link, prof_tctx_comp)
+
+JEMALLOC_INLINE_C 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)
+
+JEMALLOC_INLINE_C 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;
+
+		ret = ((a_discrim > b_discrim) - (a_discrim < b_discrim));
+	}
+	return (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);
+
+	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);
+	}
+
+	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);
+	}
+}
+
+void
+prof_malloc_sample_object(tsdn_t *tsdn, const void *ptr, size_t usize,
+    prof_tctx_t *tctx)
+{
+
+	prof_tctx_set(tsdn, ptr, usize, tctx);
+
+	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);
+}
+
+void
+bt_init(prof_bt_t *bt, void **vec)
+{
+
+	cassert(config_prof);
+
+	bt->vec = vec;
+	bt->len = 0;
+}
+
+JEMALLOC_INLINE_C 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);
+}
+
+JEMALLOC_INLINE_C void
+prof_leave(tsd_t *tsd, prof_tdata_t *tdata)
+{
+
+	cassert(config_prof);
+	assert(tdata == prof_tdata_get(tsd, false));
+
+	malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx);
+
+	if (tdata != NULL) {
+		bool idump, 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)
+{
+	int nframes;
+
+	cassert(config_prof);
+	assert(bt->len == 0);
+	assert(bt->vec != NULL);
+
+	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)
+{
+
+	cassert(config_prof);
+
+	return (_URC_NO_REASON);
+}
+
+static _Unwind_Reason_Code
+prof_unwind_callback(struct _Unwind_Context *context, void *arg)
+{
+	prof_unwind_data_t *data = (prof_unwind_data_t *)arg;
+	void *ip;
+
+	cassert(config_prof);
+
+	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);
+}
+
+void
+prof_backtrace(prof_bt_t *bt)
+{
+	prof_unwind_data_t data = {bt, PROF_BT_MAX};
+
+	cassert(config_prof);
+
+	_Unwind_Backtrace(prof_unwind_callback, &data);
+}
+#elif (defined(JEMALLOC_PROF_GCC))
+void
+prof_backtrace(prof_bt_t *bt)
+{
+#define	BT_FRAME(i)							\
+	if ((i) < PROF_BT_MAX) {					\
+		void *p;						\
+		if (__builtin_frame_address(i) == 0)			\
+			return;						\
+		p = __builtin_return_address(i);			\
+		if (p == NULL)						\
+			return;						\
+		bt->vec[(i)] = p;					\
+		bt->len = (i) + 1;					\
+	} else								\
+		return;
+
+	cassert(config_prof);
+
+	BT_FRAME(0)
+	BT_FRAME(1)
+	BT_FRAME(2)
+	BT_FRAME(3)
+	BT_FRAME(4)
+	BT_FRAME(5)
+	BT_FRAME(6)
+	BT_FRAME(7)
+	BT_FRAME(8)
+	BT_FRAME(9)
+
+	BT_FRAME(10)
+	BT_FRAME(11)
+	BT_FRAME(12)
+	BT_FRAME(13)
+	BT_FRAME(14)
+	BT_FRAME(15)
+	BT_FRAME(16)
+	BT_FRAME(17)
+	BT_FRAME(18)
+	BT_FRAME(19)
+
+	BT_FRAME(20)
+	BT_FRAME(21)
+	BT_FRAME(22)
+	BT_FRAME(23)
+	BT_FRAME(24)
+	BT_FRAME(25)
+	BT_FRAME(26)
+	BT_FRAME(27)
+	BT_FRAME(28)
+	BT_FRAME(29)
+
+	BT_FRAME(30)
+	BT_FRAME(31)
+	BT_FRAME(32)
+	BT_FRAME(33)
+	BT_FRAME(34)
+	BT_FRAME(35)
+	BT_FRAME(36)
+	BT_FRAME(37)
+	BT_FRAME(38)
+	BT_FRAME(39)
+
+	BT_FRAME(40)
+	BT_FRAME(41)
+	BT_FRAME(42)
+	BT_FRAME(43)
+	BT_FRAME(44)
+	BT_FRAME(45)
+	BT_FRAME(46)
+	BT_FRAME(47)
+	BT_FRAME(48)
+	BT_FRAME(49)
+
+	BT_FRAME(50)
+	BT_FRAME(51)
+	BT_FRAME(52)
+	BT_FRAME(53)
+	BT_FRAME(54)
+	BT_FRAME(55)
+	BT_FRAME(56)
+	BT_FRAME(57)
+	BT_FRAME(58)
+	BT_FRAME(59)
+
+	BT_FRAME(60)
+	BT_FRAME(61)
+	BT_FRAME(62)
+	BT_FRAME(63)
+	BT_FRAME(64)
+	BT_FRAME(65)
+	BT_FRAME(66)
+	BT_FRAME(67)
+	BT_FRAME(68)
+	BT_FRAME(69)
+
+	BT_FRAME(70)
+	BT_FRAME(71)
+	BT_FRAME(72)
+	BT_FRAME(73)
+	BT_FRAME(74)
+	BT_FRAME(75)
+	BT_FRAME(76)
+	BT_FRAME(77)
+	BT_FRAME(78)
+	BT_FRAME(79)
+
+	BT_FRAME(80)
+	BT_FRAME(81)
+	BT_FRAME(82)
+	BT_FRAME(83)
+	BT_FRAME(84)
+	BT_FRAME(85)
+	BT_FRAME(86)
+	BT_FRAME(87)
+	BT_FRAME(88)
+	BT_FRAME(89)
+
+	BT_FRAME(90)
+	BT_FRAME(91)
+	BT_FRAME(92)
+	BT_FRAME(93)
+	BT_FRAME(94)
+	BT_FRAME(95)
+	BT_FRAME(96)
+	BT_FRAME(97)
+	BT_FRAME(98)
+	BT_FRAME(99)
+
+	BT_FRAME(100)
+	BT_FRAME(101)
+	BT_FRAME(102)
+	BT_FRAME(103)
+	BT_FRAME(104)
+	BT_FRAME(105)
+	BT_FRAME(106)
+	BT_FRAME(107)
+	BT_FRAME(108)
+	BT_FRAME(109)
+
+	BT_FRAME(110)
+	BT_FRAME(111)
+	BT_FRAME(112)
+	BT_FRAME(113)
+	BT_FRAME(114)
+	BT_FRAME(115)
+	BT_FRAME(116)
+	BT_FRAME(117)
+	BT_FRAME(118)
+	BT_FRAME(119)
+
+	BT_FRAME(120)
+	BT_FRAME(121)
+	BT_FRAME(122)
+	BT_FRAME(123)
+	BT_FRAME(124)
+	BT_FRAME(125)
+	BT_FRAME(126)
+	BT_FRAME(127)
+#undef BT_FRAME
+}
+#else
+void
+prof_backtrace(prof_bt_t *bt)
+{
+
+	cassert(config_prof);
+	not_reached();
+}
+#endif
+
+static malloc_mutex_t *
+prof_gctx_mutex_choose(void)
+{
+	unsigned ngctxs = atomic_add_u(&cum_gctxs, 1);
+
+	return (&gctx_locks[(ngctxs - 1) % PROF_NCTX_LOCKS]);
+}
+
+static malloc_mutex_t *
+prof_tdata_mutex_choose(uint64_t thr_uid)
+{
+
+	return (&tdata_locks[thr_uid % PROF_NTDATA_LOCKS]);
+}
+
+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,
+	    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_tctx_destroy()/prof_gctx_try_destroy().
+	 */
+	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_gctx_try_destroy(tsd_t *tsd, prof_tdata_t *tdata_self, prof_gctx_t *gctx,
+    prof_tdata_t *tdata)
+{
+
+	cassert(config_prof);
+
+	/*
+	 * 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_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(tsd, tdata_self);
+		/* Destroy gctx. */
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+		idalloctm(tsd_tsdn(tsd), gctx, NULL, true, true);
+	} else {
+		/*
+		 * Compensate for increment in prof_tctx_destroy() or
+		 * prof_lookup().
+		 */
+		gctx->nlimbo--;
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx->lock);
+		prof_leave(tsd, tdata_self);
+	}
+}
+
+static bool
+prof_tctx_should_destroy(tsdn_t *tsdn, prof_tctx_t *tctx)
+{
+
+	malloc_mutex_assert_owner(tsdn, tctx->tdata->lock);
+
+	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);
+}
+
+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:
+		/*
+		 * 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.
+		 */
+		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, true, true);
+}
+
+static bool
+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_gctx_t	*p;
+		void		*v;
+	} gctx;
+	union {
+		prof_bt_t	*p;
+		void		*v;
+	} btkey;
+	bool new_gctx;
+
+	prof_enter(tsd, tdata);
+	if (ckh_search(&bt2gctx, bt, &btkey.v, &gctx.v)) {
+		/* bt has never been seen before.  Insert it. */
+		gctx.p = prof_gctx_create(tsd_tsdn(tsd), bt);
+		if (gctx.v == NULL) {
+			prof_leave(tsd, tdata);
+			return (true);
+		}
+		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, true, true);
+			return (true);
+		}
+		new_gctx = true;
+	} else {
+		/*
+		 * Increment nlimbo, in order to avoid a race condition with
+		 * prof_tctx_destroy()/prof_gctx_try_destroy().
+		 */
+		malloc_mutex_lock(tsd_tsdn(tsd), gctx.p->lock);
+		gctx.p->nlimbo++;
+		malloc_mutex_unlock(tsd_tsdn(tsd), gctx.p->lock);
+		new_gctx = false;
+	}
+	prof_leave(tsd, tdata);
+
+	*p_btkey = btkey.v;
+	*p_gctx = gctx.p;
+	*p_new_gctx = new_gctx;
+	return (false);
+}
+
+prof_tctx_t *
+prof_lookup(tsd_t *tsd, prof_bt_t *bt)
+{
+	union {
+		prof_tctx_t	*p;
+		void		*v;
+	} ret;
+	prof_tdata_t *tdata;
+	bool not_found;
+
+	cassert(config_prof);
+
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL)
+		return (NULL);
+
+	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_gctx_t *gctx;
+		bool new_gctx, error;
+
+		/*
+		 * This thread's cache lacks bt.  Look for it in the global
+		 * cache.
+		 */
+		if (prof_lookup_global(tsd, bt, tdata, &btkey, &gctx,
+		    &new_gctx))
+			return (NULL);
+
+		/* Link a prof_tctx_t into gctx for this thread. */
+		ret.v = iallocztm(tsd_tsdn(tsd), sizeof(prof_tctx_t),
+		    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);
+			return (NULL);
+		}
+		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));
+		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, true, true);
+			return (NULL);
+		}
+		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);
+}
+
+/*
+ * 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_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);
+}
+#endif
+
+#ifdef JEMALLOC_JET
+size_t
+prof_bt_count(void)
+{
+	size_t bt_count;
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
+
+	tsd = tsd_fetch();
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL)
+		return (0);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &bt2gctx_mtx);
+	bt_count = ckh_count(&bt2gctx);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &bt2gctx_mtx);
+
+	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)
+{
+	int fd;
+
+	fd = creat(filename, 0644);
+	if (fd == -1 && !propagate_err) {
+		malloc_printf("<jemalloc>: creat(\"%s\"), 0644) failed\n",
+		    filename);
+		if (opt_abort)
+			abort();
+	}
+
+	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
+
+static bool
+prof_dump_flush(bool propagate_err)
+{
+	bool ret = false;
+	ssize_t err;
+
+	cassert(config_prof);
+
+	err = write(prof_dump_fd, prof_dump_buf, prof_dump_buf_end);
+	if (err == -1) {
+		if (!propagate_err) {
+			malloc_write("<jemalloc>: write() failed during heap "
+			    "profile flush\n");
+			if (opt_abort)
+				abort();
+		}
+		ret = true;
+	}
+	prof_dump_buf_end = 0;
+
+	return (ret);
+}
+
+static bool
+prof_dump_close(bool propagate_err)
+{
+	bool ret;
+
+	assert(prof_dump_fd != -1);
+	ret = prof_dump_flush(propagate_err);
+	close(prof_dump_fd);
+	prof_dump_fd = -1;
+
+	return (ret);
+}
+
+static bool
+prof_dump_write(bool propagate_err, const char *s)
+{
+	size_t i, slen, n;
+
+	cassert(config_prof);
+
+	i = 0;
+	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 + slen <= PROF_DUMP_BUFSIZE) {
+			/* Finish writing. */
+			n = slen - i;
+		} else {
+			/* Write as much of s as will fit. */
+			n = PROF_DUMP_BUFSIZE - prof_dump_buf_end;
+		}
+		memcpy(&prof_dump_buf[prof_dump_buf_end], &s[i], n);
+		prof_dump_buf_end += n;
+		i += n;
+	}
+
+	return (false);
+}
+
+JEMALLOC_FORMAT_PRINTF(2, 3)
+static bool
+prof_dump_printf(bool propagate_err, const char *format, ...)
+{
+	bool ret;
+	va_list ap;
+	char buf[PROF_PRINTF_BUFSIZE];
+
+	va_start(ap, format);
+	malloc_vsnprintf(buf, sizeof(buf), format, ap);
+	va_end(ap);
+	ret = prof_dump_write(propagate_err, buf);
+
+	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_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(tsdn, gctx->lock);
+
+	/*
+	 * 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.
+	 */
+	gctx->nlimbo++;
+	gctx_tree_insert(gctxs, gctx);
+
+	memset(&gctx->cnt_summed, 0, sizeof(prof_cnt_t));
+
+	malloc_mutex_unlock(tsdn, gctx->lock);
+}
+
+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);
+
+	return (NULL);
+}
+
+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;
+
+	/*
+	 * 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, 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);
+	}
+}
+
+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);
+
+		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);
+
+	return (NULL);
+}
+
+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);
+
+	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);
+}
+
+#ifdef JEMALLOC_JET
+#undef prof_dump_header
+#define	prof_dump_header JEMALLOC_N(prof_dump_header_impl)
+#endif
+static bool
+prof_dump_header(tsdn_t *tsdn, bool propagate_err, const prof_cnt_t *cnt_all)
+{
+	bool ret;
+
+	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(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);
+}
+#ifdef JEMALLOC_JET
+#undef prof_dump_header
+#define	prof_dump_header JEMALLOC_N(prof_dump_header)
+prof_dump_header_t *prof_dump_header = JEMALLOC_N(prof_dump_header_impl);
+#endif
+
+static bool
+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);
+	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, "@")) {
+		ret = true;
+		goto label_return;
+	}
+	for (i = 0; i < bt->len; i++) {
+		if (prof_dump_printf(propagate_err, " %#"FMTxPTR,
+		    (uintptr_t)bt->vec[i])) {
+			ret = true;
+			goto label_return;
+		}
+	}
+
+	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:
+	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);
+
+	return (mfd);
+}
+#endif
+
+static int
+prof_getpid(void)
+{
+
+#ifdef _WIN32
+	return (GetCurrentProcessId());
+#else
+	return (getpid());
+#endif
+}
+
+static bool
+prof_dump_maps(bool propagate_err)
+{
+	bool ret;
+	int mfd;
+
+	cassert(config_prof);
+#ifdef __FreeBSD__
+	mfd = prof_open_maps("/proc/curproc/map");
+#elif defined(_WIN32)
+	mfd = -1; // Not implemented
+#else
+	{
+		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
+	if (mfd != -1) {
+		ssize_t nread;
+
+		if (prof_dump_write(propagate_err, "\nMAPPED_LIBRARIES:\n") &&
+		    propagate_err) {
+			ret = true;
+			goto label_return;
+		}
+		nread = 0;
+		do {
+			prof_dump_buf_end += nread;
+			if (prof_dump_buf_end == PROF_DUMP_BUFSIZE) {
+				/* Make space in prof_dump_buf before read(). */
+				if (prof_dump_flush(propagate_err) &&
+				    propagate_err) {
+					ret = true;
+					goto label_return;
+				}
+			}
+			nread = read(mfd, &prof_dump_buf[prof_dump_buf_end],
+			    PROF_DUMP_BUFSIZE - prof_dump_buf_end);
+		} while (nread > 0);
+	} else {
+		ret = true;
+		goto label_return;
+	}
+
+	ret = false;
+label_return:
+	if (mfd != -1)
+		close(mfd);
+	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_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) {
+		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 jeprof on \"%s\" for leak detail\n",
+		    filename);
+	}
+#endif
+}
+
+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 bool
+prof_dump(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;
+	size_t tabind;
+	union {
+		prof_gctx_t	*p;
+		void		*v;
+	} gctx;
+	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;
+
+	cassert(config_prof);
+
+	tdata = prof_tdata_get(tsd, true);
+	if (tdata == NULL)
+		return (true);
+
+	malloc_mutex_lock(tsd_tsdn(tsd), &prof_dump_mtx);
+	prof_enter(tsd, tdata);
+
+	/*
+	 * 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);
+
+	/*
+	 * 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);
+
+	/* Create dump file. */
+	if ((prof_dump_fd = prof_dump_open(propagate_err, filename)) == -1)
+		goto label_open_close_error;
+
+	/* Dump profile header. */
+	if (prof_dump_header(tsd_tsdn(tsd), propagate_err,
+	    &prof_tdata_merge_iter_arg.cnt_all))
+		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))
+		goto label_write_error;
+
+	if (prof_dump_close(propagate_err))
+		goto label_open_close_error;
+
+	prof_gctx_finish(tsd, &gctxs);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx);
+
+	if (leakcheck) {
+		prof_leakcheck(&prof_tdata_merge_iter_arg.cnt_all,
+		    prof_gctx_merge_iter_arg.leak_ngctx, filename);
+	}
+	return (false);
+label_write_error:
+	prof_dump_close(propagate_err);
+label_open_close_error:
+	prof_gctx_finish(tsd, &gctxs);
+	malloc_mutex_unlock(tsd_tsdn(tsd), &prof_dump_mtx);
+	return (true);
+}
+
+#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.%"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.%"FMTu64".%c.heap",
+		    opt_prof_prefix, prof_getpid(), prof_dump_seq, v);
+	}
+	prof_dump_seq++;
+}
+
+static 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)
+		return;
+	tsd = tsd_fetch();
+
+	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);
+}
+
+void
+prof_idump(tsdn_t *tsdn)
+{
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
+
+	cassert(config_prof);
+
+	if (!prof_booted || tsdn_null(tsdn))
+		return;
+	tsd = tsdn_tsd(tsdn);
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL)
+		return;
+	if (tdata->enq) {
+		tdata->enq_idump = true;
+		return;
+	}
+
+	if (opt_prof_prefix[0] != '\0') {
+		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(tsd_tsdn(tsd), &prof_dump_seq_mtx);
+		prof_dump(tsd, false, filename, false);
+	}
+}
+
+bool
+prof_mdump(tsd_t *tsd, const char *filename)
+{
+	char filename_buf[DUMP_FILENAME_BUFSIZE];
+
+	cassert(config_prof);
+
+	if (!opt_prof || !prof_booted)
+		return (true);
+
+	if (filename == NULL) {
+		/* No filename specified, so automatically generate one. */
+		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(tsd_tsdn(tsd), &prof_dump_seq_mtx);
+		filename = filename_buf;
+	}
+	return (prof_dump(tsd, true, filename, false));
+}
+
+void
+prof_gdump(tsdn_t *tsdn)
+{
+	tsd_t *tsd;
+	prof_tdata_t *tdata;
+
+	cassert(config_prof);
+
+	if (!prof_booted || tsdn_null(tsdn))
+		return;
+	tsd = tsdn_tsd(tsdn);
+	tdata = prof_tdata_get(tsd, false);
+	if (tdata == NULL)
+		return;
+	if (tdata->enq) {
+		tdata->enq_gdump = true;
+		return;
+	}
+
+	if (opt_prof_prefix[0] != '\0') {
+		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(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_t *bt = (prof_bt_t *)key;
+
+	cassert(config_prof);
+
+	hash(bt->vec, bt->len * sizeof(void *), 0x94122f33U, r_hash);
+}
+
+static bool
+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);
+	return (memcmp(bt1->vec, bt2->vec, bt1->len * sizeof(void *)) == 0);
+}
+
+JEMALLOC_INLINE_C 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. */
+	tdata = (prof_tdata_t *)iallocztm(tsd_tsdn(tsd), sizeof(prof_tdata_t),
+	    size2index(sizeof(prof_tdata_t)), false, NULL, true,
+	    arena_get(TSDN_NULL, 0, true), true);
+	if (tdata == NULL)
+		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, true, true);
+		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);
+
+	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);
+
+	tdata_tree_remove(&tdatas, tdata);
+
+	assert(prof_tdata_should_destroy_unlocked(tdata, even_if_attached));
+
+	if (tdata->thread_name != NULL)
+		idalloctm(tsd_tsdn(tsd), tdata->thread_name, NULL, true, true);
+	ckh_delete(tsd, &tdata->bt2tctx);
+	idalloctm(tsd_tsdn(tsd), tdata, NULL, true, true);
+}
+
+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);
+}
+
+static void
+prof_tdata_detach(tsd_t *tsd, prof_tdata_t *tdata)
+{
+	bool destroy_tdata;
+
+	malloc_mutex_lock(tsd_tsdn(tsd), tdata->lock);
+	if (tdata->attached) {
+		destroy_tdata = prof_tdata_should_destroy(tsd_tsdn(tsd), tdata,
+		    true);
+		/*
+		 * Only detach if !destroy_tdata, because detaching would allow
+		 * another thread to win the race to destroy tdata.
+		 */
+		if (!destroy_tdata)
+			tdata->attached = false;
+		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_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, 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, 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,
+	    sizeof(PROF_PREFIX_DEFAULT));
+}
+
+void
+prof_boot1(void)
+{
+
+	cassert(config_prof);
+
+	/*
+	 * 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) {
+		/*
+		 * Enable opt_prof, but in such a way that profiles are never
+		 * automatically dumped.
+		 */
+		opt_prof = true;
+		opt_prof_gdump = false;
+	} else if (opt_prof) {
+		if (opt_lg_prof_interval >= 0) {
+			prof_interval = (((uint64_t)1U) <<
+			    opt_lg_prof_interval);
+		}
+	}
+}
+
+bool
+prof_boot2(tsd_t *tsd)
+{
+
+	cassert(config_prof);
+
+	if (opt_prof) {
+		unsigned i;
+
+		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))
+			return (true);
+
+		prof_gdump_val = opt_prof_gdump;
+		if (malloc_mutex_init(&prof_gdump_mtx, "prof_gdump",
+		    WITNESS_RANK_PROF_GDUMP))
+			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))
+			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))
+			return (true);
+
+		tdata_tree_new(&tdatas);
+		if (malloc_mutex_init(&tdatas_mtx, "prof_tdatas",
+		    WITNESS_RANK_PROF_TDATAS))
+			return (true);
+
+		next_thr_uid = 0;
+		if (malloc_mutex_init(&next_thr_uid_mtx, "prof_next_thr_uid",
+		    WITNESS_RANK_PROF_NEXT_THR_UID))
+			return (true);
+
+		if (malloc_mutex_init(&prof_dump_seq_mtx, "prof_dump_seq",
+		    WITNESS_RANK_PROF_DUMP_SEQ))
+			return (true);
+		if (malloc_mutex_init(&prof_dump_mtx, "prof_dump",
+		    WITNESS_RANK_PROF_DUMP))
+			return (true);
+
+		if (opt_prof_final && opt_prof_prefix[0] != '\0' &&
+		    atexit(prof_fdump) != 0) {
+			malloc_write("<jemalloc>: Error in atexit()\n");
+			if (opt_abort)
+				abort();
+		}
+
+		gctx_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd),
+		    PROF_NCTX_LOCKS * sizeof(malloc_mutex_t));
+		if (gctx_locks == NULL)
+			return (true);
+		for (i = 0; i < PROF_NCTX_LOCKS; i++) {
+			if (malloc_mutex_init(&gctx_locks[i], "prof_gctx",
+			    WITNESS_RANK_PROF_GCTX))
+				return (true);
+		}
+
+		tdata_locks = (malloc_mutex_t *)base_alloc(tsd_tsdn(tsd),
+		    PROF_NTDATA_LOCKS * sizeof(malloc_mutex_t));
+		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))
+				return (true);
+		}
+	}
+
+#ifdef JEMALLOC_PROF_LIBGCC
+	/*
+	 * Cause the backtracing machinery to allocate its internal state
+	 * before enabling profiling.
+	 */
+	_Unwind_Backtrace(prof_unwind_init_callback, NULL);
+#endif
+
+	prof_booted = true;
+
+	return (false);
+}
+
+void
+prof_prefork0(tsdn_t *tsdn)
+{
+
+	if (opt_prof) {
+		unsigned 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_prefork1(tsdn_t *tsdn)
+{
+
+	if (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);
+	}
+}
+
+void
+prof_postfork_parent(tsdn_t *tsdn)
+{
+
+	if (opt_prof) {
+		unsigned i;
+
+		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(tsdn_t *tsdn)
+{
+
+	if (opt_prof) {
+		unsigned i;
+
+		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/deps/jemalloc/src/quarantine.c b/deps/jemalloc/src/quarantine.c
new file mode 100644
index 0000000..18903fb
--- /dev/null
+++ b/deps/jemalloc/src/quarantine.c
@@ -0,0 +1,183 @@
+#define	JEMALLOC_QUARANTINE_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/*
+ * Quarantine pointers close to NULL are used to encode state information that
+ * is used for cleaning up during thread shutdown.
+ */
+#define	QUARANTINE_STATE_REINCARNATED	((quarantine_t *)(uintptr_t)1)
+#define	QUARANTINE_STATE_PURGATORY	((quarantine_t *)(uintptr_t)2)
+#define	QUARANTINE_STATE_MAX		QUARANTINE_STATE_PURGATORY
+
+/******************************************************************************/
+/* Function prototypes for non-inline static functions. */
+
+static quarantine_t	*quarantine_grow(tsd_t *tsd, quarantine_t *quarantine);
+static void	quarantine_drain_one(tsdn_t *tsdn, quarantine_t *quarantine);
+static void	quarantine_drain(tsdn_t *tsdn, quarantine_t *quarantine,
+    size_t upper_bound);
+
+/******************************************************************************/
+
+static quarantine_t *
+quarantine_init(tsdn_t *tsdn, size_t lg_maxobjs)
+{
+	quarantine_t *quarantine;
+	size_t size;
+
+	size = offsetof(quarantine_t, objs) + ((ZU(1) << lg_maxobjs) *
+	    sizeof(quarantine_obj_t));
+	quarantine = (quarantine_t *)iallocztm(tsdn, size, size2index(size),
+	    false, NULL, true, arena_get(TSDN_NULL, 0, true), true);
+	if (quarantine == NULL)
+		return (NULL);
+	quarantine->curbytes = 0;
+	quarantine->curobjs = 0;
+	quarantine->first = 0;
+	quarantine->lg_maxobjs = lg_maxobjs;
+
+	return (quarantine);
+}
+
+void
+quarantine_alloc_hook_work(tsd_t *tsd)
+{
+	quarantine_t *quarantine;
+
+	if (!tsd_nominal(tsd))
+		return;
+
+	quarantine = quarantine_init(tsd_tsdn(tsd), LG_MAXOBJS_INIT);
+	/*
+	 * Check again whether quarantine has been initialized, because
+	 * quarantine_init() may have triggered recursive initialization.
+	 */
+	if (tsd_quarantine_get(tsd) == NULL)
+		tsd_quarantine_set(tsd, quarantine);
+	else
+		idalloctm(tsd_tsdn(tsd), quarantine, NULL, true, true);
+}
+
+static quarantine_t *
+quarantine_grow(tsd_t *tsd, quarantine_t *quarantine)
+{
+	quarantine_t *ret;
+
+	ret = quarantine_init(tsd_tsdn(tsd), quarantine->lg_maxobjs + 1);
+	if (ret == NULL) {
+		quarantine_drain_one(tsd_tsdn(tsd), quarantine);
+		return (quarantine);
+	}
+
+	ret->curbytes = quarantine->curbytes;
+	ret->curobjs = quarantine->curobjs;
+	if (quarantine->first + quarantine->curobjs <= (ZU(1) <<
+	    quarantine->lg_maxobjs)) {
+		/* objs ring buffer data are contiguous. */
+		memcpy(ret->objs, &quarantine->objs[quarantine->first],
+		    quarantine->curobjs * sizeof(quarantine_obj_t));
+	} else {
+		/* objs ring buffer data wrap around. */
+		size_t ncopy_a = (ZU(1) << quarantine->lg_maxobjs) -
+		    quarantine->first;
+		size_t ncopy_b = quarantine->curobjs - ncopy_a;
+
+		memcpy(ret->objs, &quarantine->objs[quarantine->first], ncopy_a
+		    * sizeof(quarantine_obj_t));
+		memcpy(&ret->objs[ncopy_a], quarantine->objs, ncopy_b *
+		    sizeof(quarantine_obj_t));
+	}
+	idalloctm(tsd_tsdn(tsd), quarantine, NULL, true, true);
+
+	tsd_quarantine_set(tsd, ret);
+	return (ret);
+}
+
+static void
+quarantine_drain_one(tsdn_t *tsdn, quarantine_t *quarantine)
+{
+	quarantine_obj_t *obj = &quarantine->objs[quarantine->first];
+	assert(obj->usize == isalloc(tsdn, obj->ptr, config_prof));
+	idalloctm(tsdn, obj->ptr, NULL, false, true);
+	quarantine->curbytes -= obj->usize;
+	quarantine->curobjs--;
+	quarantine->first = (quarantine->first + 1) & ((ZU(1) <<
+	    quarantine->lg_maxobjs) - 1);
+}
+
+static void
+quarantine_drain(tsdn_t *tsdn, quarantine_t *quarantine, size_t upper_bound)
+{
+
+	while (quarantine->curbytes > upper_bound && quarantine->curobjs > 0)
+		quarantine_drain_one(tsdn, quarantine);
+}
+
+void
+quarantine(tsd_t *tsd, void *ptr)
+{
+	quarantine_t *quarantine;
+	size_t usize = isalloc(tsd_tsdn(tsd), ptr, config_prof);
+
+	cassert(config_fill);
+	assert(opt_quarantine);
+
+	if ((quarantine = tsd_quarantine_get(tsd)) == NULL) {
+		idalloctm(tsd_tsdn(tsd), ptr, NULL, false, true);
+		return;
+	}
+	/*
+	 * Drain one or more objects if the quarantine size limit would be
+	 * exceeded by appending ptr.
+	 */
+	if (quarantine->curbytes + usize > opt_quarantine) {
+		size_t upper_bound = (opt_quarantine >= usize) ? opt_quarantine
+		    - usize : 0;
+		quarantine_drain(tsd_tsdn(tsd), quarantine, upper_bound);
+	}
+	/* Grow the quarantine ring buffer if it's full. */
+	if (quarantine->curobjs == (ZU(1) << quarantine->lg_maxobjs))
+		quarantine = quarantine_grow(tsd, quarantine);
+	/* quarantine_grow() must free a slot if it fails to grow. */
+	assert(quarantine->curobjs < (ZU(1) << quarantine->lg_maxobjs));
+	/* Append ptr if its size doesn't exceed the quarantine size. */
+	if (quarantine->curbytes + usize <= opt_quarantine) {
+		size_t offset = (quarantine->first + quarantine->curobjs) &
+		    ((ZU(1) << quarantine->lg_maxobjs) - 1);
+		quarantine_obj_t *obj = &quarantine->objs[offset];
+		obj->ptr = ptr;
+		obj->usize = usize;
+		quarantine->curbytes += usize;
+		quarantine->curobjs++;
+		if (config_fill && unlikely(opt_junk_free)) {
+			/*
+			 * Only do redzone validation if Valgrind isn't in
+			 * operation.
+			 */
+			if ((!config_valgrind || likely(!in_valgrind))
+			    && usize <= SMALL_MAXCLASS)
+				arena_quarantine_junk_small(ptr, usize);
+			else
+				memset(ptr, JEMALLOC_FREE_JUNK, usize);
+		}
+	} else {
+		assert(quarantine->curbytes == 0);
+		idalloctm(tsd_tsdn(tsd), ptr, NULL, false, true);
+	}
+}
+
+void
+quarantine_cleanup(tsd_t *tsd)
+{
+	quarantine_t *quarantine;
+
+	if (!config_fill)
+		return;
+
+	quarantine = tsd_quarantine_get(tsd);
+	if (quarantine != NULL) {
+		quarantine_drain(tsd_tsdn(tsd), quarantine, 0);
+		idalloctm(tsd_tsdn(tsd), quarantine, NULL, true, true);
+		tsd_quarantine_set(tsd, NULL);
+	}
+}
diff --git a/deps/jemalloc/src/rtree.c b/deps/jemalloc/src/rtree.c
new file mode 100644
index 0000000..f2e2997
--- /dev/null
+++ b/deps/jemalloc/src/rtree.c
@@ -0,0 +1,132 @@
+#define	JEMALLOC_RTREE_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+static unsigned
+hmin(unsigned ha, unsigned hb)
+{
+
+	return (ha < hb ? ha : hb);
+}
+
+/* Only the most significant bits of keys passed to rtree_[gs]et() are used. */
+bool
+rtree_new(rtree_t *rtree, unsigned bits, rtree_node_alloc_t *alloc,
+    rtree_node_dalloc_t *dalloc)
+{
+	unsigned bits_in_leaf, height, i;
+
+	assert(RTREE_HEIGHT_MAX == ((ZU(1) << (LG_SIZEOF_PTR+3)) /
+	    RTREE_BITS_PER_LEVEL));
+	assert(bits > 0 && bits <= (sizeof(uintptr_t) << 3));
+
+	bits_in_leaf = (bits % RTREE_BITS_PER_LEVEL) == 0 ? RTREE_BITS_PER_LEVEL
+	    : (bits % RTREE_BITS_PER_LEVEL);
+	if (bits > bits_in_leaf) {
+		height = 1 + (bits - bits_in_leaf) / RTREE_BITS_PER_LEVEL;
+		if ((height-1) * RTREE_BITS_PER_LEVEL + bits_in_leaf != bits)
+			height++;
+	} else
+		height = 1;
+	assert((height-1) * RTREE_BITS_PER_LEVEL + bits_in_leaf == bits);
+
+	rtree->alloc = alloc;
+	rtree->dalloc = dalloc;
+	rtree->height = height;
+
+	/* Root level. */
+	rtree->levels[0].subtree = NULL;
+	rtree->levels[0].bits = (height > 1) ? RTREE_BITS_PER_LEVEL :
+	    bits_in_leaf;
+	rtree->levels[0].cumbits = rtree->levels[0].bits;
+	/* Interior levels. */
+	for (i = 1; i < height-1; i++) {
+		rtree->levels[i].subtree = NULL;
+		rtree->levels[i].bits = RTREE_BITS_PER_LEVEL;
+		rtree->levels[i].cumbits = rtree->levels[i-1].cumbits +
+		    RTREE_BITS_PER_LEVEL;
+	}
+	/* Leaf level. */
+	if (height > 1) {
+		rtree->levels[height-1].subtree = NULL;
+		rtree->levels[height-1].bits = bits_in_leaf;
+		rtree->levels[height-1].cumbits = bits;
+	}
+
+	/* Compute lookup table to be used by rtree_start_level(). */
+	for (i = 0; i < RTREE_HEIGHT_MAX; i++) {
+		rtree->start_level[i] = hmin(RTREE_HEIGHT_MAX - 1 - i, height -
+		    1);
+	}
+
+	return (false);
+}
+
+static void
+rtree_delete_subtree(rtree_t *rtree, rtree_node_elm_t *node, unsigned level)
+{
+
+	if (level + 1 < rtree->height) {
+		size_t nchildren, i;
+
+		nchildren = ZU(1) << rtree->levels[level].bits;
+		for (i = 0; i < nchildren; i++) {
+			rtree_node_elm_t *child = node[i].child;
+			if (child != NULL)
+				rtree_delete_subtree(rtree, child, level + 1);
+		}
+	}
+	rtree->dalloc(node);
+}
+
+void
+rtree_delete(rtree_t *rtree)
+{
+	unsigned i;
+
+	for (i = 0; i < rtree->height; i++) {
+		rtree_node_elm_t *subtree = rtree->levels[i].subtree;
+		if (subtree != NULL)
+			rtree_delete_subtree(rtree, subtree, i);
+	}
+}
+
+static rtree_node_elm_t *
+rtree_node_init(rtree_t *rtree, unsigned level, rtree_node_elm_t **elmp)
+{
+	rtree_node_elm_t *node;
+
+	if (atomic_cas_p((void **)elmp, NULL, RTREE_NODE_INITIALIZING)) {
+		spin_t spinner;
+
+		/*
+		 * Another thread is already in the process of initializing.
+		 * Spin-wait until initialization is complete.
+		 */
+		spin_init(&spinner);
+		do {
+			spin_adaptive(&spinner);
+			node = atomic_read_p((void **)elmp);
+		} while (node == RTREE_NODE_INITIALIZING);
+	} else {
+		node = rtree->alloc(ZU(1) << rtree->levels[level].bits);
+		if (node == NULL)
+			return (NULL);
+		atomic_write_p((void **)elmp, node);
+	}
+
+	return (node);
+}
+
+rtree_node_elm_t *
+rtree_subtree_read_hard(rtree_t *rtree, unsigned level)
+{
+
+	return (rtree_node_init(rtree, level, &rtree->levels[level].subtree));
+}
+
+rtree_node_elm_t *
+rtree_child_read_hard(rtree_t *rtree, rtree_node_elm_t *elm, unsigned level)
+{
+
+	return (rtree_node_init(rtree, level+1, &elm->child));
+}
diff --git a/deps/jemalloc/src/spin.c b/deps/jemalloc/src/spin.c
new file mode 100644
index 0000000..5242d95
--- /dev/null
+++ b/deps/jemalloc/src/spin.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_SPIN_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/stats.c b/deps/jemalloc/src/stats.c
new file mode 100644
index 0000000..1360f3b
--- /dev/null
+++ b/deps/jemalloc/src/stats.c
@@ -0,0 +1,1154 @@
+#define	JEMALLOC_STATS_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+#define	CTL_GET(n, v, t) do {						\
+	size_t sz = sizeof(t);						\
+	xmallctl(n, (void *)v, &sz, NULL, 0);				\
+} while (0)
+
+#define	CTL_M2_GET(n, i, v, t) do {					\
+	size_t mib[6];							\
+	size_t miblen = sizeof(mib) / sizeof(size_t);			\
+	size_t sz = sizeof(t);						\
+	xmallctlnametomib(n, mib, &miblen);				\
+	mib[2] = (i);							\
+	xmallctlbymib(mib, miblen, (void *)v, &sz, NULL, 0);		\
+} while (0)
+
+#define	CTL_M2_M4_GET(n, i, j, v, t) do {				\
+	size_t mib[6];							\
+	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, (void *)v, &sz, NULL, 0);		\
+} while (0)
+
+/******************************************************************************/
+/* Data. */
+
+bool	opt_stats_print = false;
+
+size_t	stats_cactive = 0;
+
+/******************************************************************************/
+
+static void
+stats_arena_bins_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool large, bool huge, unsigned i)
+{
+	size_t page;
+	bool config_tcache, in_gap, in_gap_prev;
+	unsigned nbins, j;
+
+	CTL_GET("arenas.page", &page, size_t);
+
+	CTL_GET("arenas.nbins", &nbins, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"bins\": [\n");
+	} else {
+		CTL_GET("config.tcache", &config_tcache, bool);
+		if (config_tcache) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "bins:           size ind    allocated      nmalloc"
+			    "      ndalloc    nrequests      curregs"
+			    "      curruns regs pgs  util       nfills"
+			    "     nflushes      newruns       reruns\n");
+		} else {
+			malloc_cprintf(write_cb, cbopaque,
+			    "bins:           size ind    allocated      nmalloc"
+			    "      ndalloc    nrequests      curregs"
+			    "      curruns regs pgs  util      newruns"
+			    "       reruns\n");
+		}
+	}
+	for (j = 0, in_gap = false; j < nbins; j++) {
+		uint64_t nruns;
+		size_t reg_size, run_size, curregs;
+		size_t curruns;
+		uint32_t nregs;
+		uint64_t nmalloc, ndalloc, nrequests, nfills, nflushes;
+		uint64_t nreruns;
+
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.nruns", i, j, &nruns,
+		    uint64_t);
+		in_gap_prev = in_gap;
+		in_gap = (nruns == 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.run_size", j, &run_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);
+		if (config_tcache) {
+			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.nreruns", i, j, &nreruns,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.bins.0.curruns", i, j, &curruns,
+		    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",
+			    nmalloc,
+			    ndalloc,
+			    curregs,
+			    nrequests);
+			if (config_tcache) {
+				malloc_cprintf(write_cb, cbopaque,
+				    "\t\t\t\t\t\t\"nfills\": %"FMTu64",\n"
+				    "\t\t\t\t\t\t\"nflushes\": %"FMTu64",\n",
+				    nfills,
+				    nflushes);
+			}
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\t\"nreruns\": %"FMTu64",\n"
+			    "\t\t\t\t\t\t\"curruns\": %zu\n"
+			    "\t\t\t\t\t}%s\n",
+			    nreruns,
+			    curruns,
+			    (j + 1 < nbins) ? "," : "");
+		} else if (!in_gap) {
+			size_t availregs, milli;
+			char util[6]; /* "x.yyy". */
+
+			availregs = nregs * curruns;
+			milli = (availregs != 0) ? (1000 * curregs) / availregs
+			    : 1000;
+			assert(milli <= 1000);
+			if (milli < 10) {
+				malloc_snprintf(util, sizeof(util),
+				    "0.00%zu", milli);
+			} else if (milli < 100) {
+				malloc_snprintf(util, sizeof(util), "0.0%zu",
+				    milli);
+			} else if (milli < 1000) {
+				malloc_snprintf(util, sizeof(util), "0.%zu",
+				    milli);
+			} else
+				malloc_snprintf(util, sizeof(util), "1");
+
+			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"\n",
+				    reg_size, j, curregs * reg_size, nmalloc,
+				    ndalloc, nrequests, curregs, curruns, nregs,
+				    run_size / page, util, nfills, nflushes,
+				    nruns, nreruns);
+			} else {
+				malloc_cprintf(write_cb, cbopaque,
+				    "%20zu %3u %12zu %12"FMTu64
+				    " %12"FMTu64" %12"FMTu64" %12zu"
+				    " %12zu %4u %3zu %-5s %12"FMTu64
+				    " %12"FMTu64"\n",
+				    reg_size, j, curregs * reg_size, nmalloc,
+				    ndalloc, nrequests, curregs, curruns, nregs,
+				    run_size / page, util, nruns, nreruns);
+			}
+		}
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t]%s\n", (large || huge) ? "," : "");
+	} else {
+		if (in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
+		}
+	}
+}
+
+static void
+stats_arena_lruns_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool huge, unsigned i)
+{
+	unsigned nbins, nlruns, j;
+	bool in_gap, in_gap_prev;
+
+	CTL_GET("arenas.nbins", &nbins, unsigned);
+	CTL_GET("arenas.nlruns", &nlruns, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"lruns\": [\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "large:          size ind    allocated      nmalloc"
+		    "      ndalloc    nrequests      curruns\n");
+	}
+	for (j = 0, in_gap = false; j < nlruns; j++) {
+		uint64_t nmalloc, ndalloc, nrequests;
+		size_t run_size, curruns;
+
+		CTL_M2_M4_GET("stats.arenas.0.lruns.0.nmalloc", i, j, &nmalloc,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.lruns.0.ndalloc", i, j, &ndalloc,
+		    uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.lruns.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.lrun.0.size", j, &run_size, size_t);
+		CTL_M2_M4_GET("stats.arenas.0.lruns.0.curruns", i, j, &curruns,
+		    size_t);
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t{\n"
+			    "\t\t\t\t\t\t\"curruns\": %zu\n"
+			    "\t\t\t\t\t}%s\n",
+			    curruns,
+			    (j + 1 < nlruns) ? "," : "");
+		} else if (!in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "%20zu %3u %12zu %12"FMTu64" %12"FMTu64
+			    " %12"FMTu64" %12zu\n",
+			    run_size, nbins + j, curruns * run_size, nmalloc,
+			    ndalloc, nrequests, curruns);
+		}
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t]%s\n", huge ? "," : "");
+	} else {
+		if (in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
+		}
+	}
+}
+
+static void
+stats_arena_hchunks_print(void (*write_cb)(void *, const char *),
+    void *cbopaque, bool json, unsigned i)
+{
+	unsigned nbins, nlruns, nhchunks, j;
+	bool in_gap, in_gap_prev;
+
+	CTL_GET("arenas.nbins", &nbins, unsigned);
+	CTL_GET("arenas.nlruns", &nlruns, unsigned);
+	CTL_GET("arenas.nhchunks", &nhchunks, unsigned);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"hchunks\": [\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "huge:           size ind    allocated      nmalloc"
+		    "      ndalloc    nrequests   curhchunks\n");
+	}
+	for (j = 0, in_gap = false; j < nhchunks; j++) {
+		uint64_t nmalloc, ndalloc, nrequests;
+		size_t hchunk_size, curhchunks;
+
+		CTL_M2_M4_GET("stats.arenas.0.hchunks.0.nmalloc", i, j,
+		    &nmalloc, uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.hchunks.0.ndalloc", i, j,
+		    &ndalloc, uint64_t);
+		CTL_M2_M4_GET("stats.arenas.0.hchunks.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.hchunk.0.size", j, &hchunk_size, size_t);
+		CTL_M2_M4_GET("stats.arenas.0.hchunks.0.curhchunks", i, j,
+		    &curhchunks, size_t);
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t{\n"
+			    "\t\t\t\t\t\t\"curhchunks\": %zu\n"
+			    "\t\t\t\t\t}%s\n",
+			    curhchunks,
+			    (j + 1 < nhchunks) ? "," : "");
+		} else if (!in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "%20zu %3u %12zu %12"FMTu64" %12"FMTu64
+			    " %12"FMTu64" %12zu\n",
+			    hchunk_size, nbins + nlruns + j,
+			    curhchunks * hchunk_size, nmalloc, ndalloc,
+			    nrequests, curhchunks);
+		}
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t]\n");
+	} else {
+		if (in_gap) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "                     ---\n");
+		}
+	}
+}
+
+static void
+stats_arena_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, unsigned i, bool bins, bool large, bool huge)
+{
+	unsigned nthreads;
+	const char *dss;
+	ssize_t lg_dirty_mult, decay_time;
+	size_t page, pactive, pdirty, mapped, retained;
+	size_t metadata_mapped, metadata_allocated;
+	uint64_t npurge, nmadvise, 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 huge_allocated;
+	uint64_t huge_nmalloc, huge_ndalloc, huge_nrequests;
+
+	CTL_GET("arenas.page", &page, size_t);
+
+	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);
+	}
+
+	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.lg_dirty_mult", i, &lg_dirty_mult, ssize_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"lg_dirty_mult\": %zd,\n", lg_dirty_mult);
+	} else {
+		if (opt_purge == purge_mode_ratio) {
+			if (lg_dirty_mult >= 0) {
+				malloc_cprintf(write_cb, cbopaque,
+				    "min active:dirty page ratio: %u:1\n",
+				    (1U << lg_dirty_mult));
+			} else {
+				malloc_cprintf(write_cb, cbopaque,
+				    "min active:dirty page ratio: N/A\n");
+			}
+		}
+	}
+
+	CTL_M2_GET("stats.arenas.0.decay_time", i, &decay_time, ssize_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"decay_time\": %zd,\n", decay_time);
+	} else {
+		if (opt_purge == purge_mode_decay) {
+			if (decay_time >= 0) {
+				malloc_cprintf(write_cb, cbopaque,
+				    "decay time: %zd\n", decay_time);
+			} else {
+				malloc_cprintf(write_cb, cbopaque,
+				    "decay time: N/A\n");
+			}
+		}
+	}
+
+	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.npurge", i, &npurge, uint64_t);
+	CTL_M2_GET("stats.arenas.0.nmadvise", i, &nmadvise, uint64_t);
+	CTL_M2_GET("stats.arenas.0.purged", i, &purged, uint64_t);
+	if (json) {
+		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\"npurge\": %"FMTu64",\n", npurge);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"nmadvise\": %"FMTu64",\n", nmadvise);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"purged\": %"FMTu64",\n", purged);
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "purging: dirty: %zu, sweeps: %"FMTu64", madvises: %"FMTu64
+		    ", purged: %"FMTu64"\n", pdirty, npurge, nmadvise, purged);
+	}
+
+	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");
+
+		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);
+	}
+
+	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);
+	}
+
+	CTL_M2_GET("stats.arenas.0.huge.allocated", i, &huge_allocated, size_t);
+	CTL_M2_GET("stats.arenas.0.huge.nmalloc", i, &huge_nmalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.huge.ndalloc", i, &huge_ndalloc, uint64_t);
+	CTL_M2_GET("stats.arenas.0.huge.nrequests", i, &huge_nrequests,
+	    uint64_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"huge\": {\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"allocated\": %zu,\n", huge_allocated);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nmalloc\": %"FMTu64",\n", huge_nmalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"ndalloc\": %"FMTu64",\n", huge_ndalloc);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"nrequests\": %"FMTu64"\n", huge_nrequests);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t},\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "huge:                    %12zu %12"FMTu64" %12"FMTu64
+		    " %12"FMTu64"\n",
+		    huge_allocated, huge_nmalloc, huge_ndalloc, huge_nrequests);
+		malloc_cprintf(write_cb, cbopaque,
+		    "total:                   %12zu %12"FMTu64" %12"FMTu64
+		    " %12"FMTu64"\n",
+		    small_allocated + large_allocated + huge_allocated,
+		    small_nmalloc + large_nmalloc + huge_nmalloc,
+		    small_ndalloc + large_ndalloc + huge_ndalloc,
+		    small_nrequests + large_nrequests + huge_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.metadata.mapped", i, &metadata_mapped,
+	    size_t);
+	CTL_M2_GET("stats.arenas.0.metadata.allocated", i, &metadata_allocated,
+	    size_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\"metadata\": {\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"mapped\": %zu,\n", metadata_mapped);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t\t\"allocated\": %zu\n", metadata_allocated);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\t},\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "metadata: mapped: %zu, allocated: %zu\n",
+		    metadata_mapped, metadata_allocated);
+	}
+
+	if (bins) {
+		stats_arena_bins_print(write_cb, cbopaque, json, large, huge,
+		    i);
+	}
+	if (large)
+		stats_arena_lruns_print(write_cb, cbopaque, json, huge, i);
+	if (huge)
+		stats_arena_hchunks_print(write_cb, cbopaque, json, i);
+}
+
+static void
+stats_general_print(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool merged, bool unmerged)
+{
+	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);
+
+	/* 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(munmap, ",")
+	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(tcache, ",")
+	CONFIG_WRITE_BOOL_JSON(tls, ",")
+	CONFIG_WRITE_BOOL_JSON(utrace, ",")
+	CONFIG_WRITE_BOOL_JSON(valgrind, ",")
+	CONFIG_WRITE_BOOL_JSON(xmalloc, "")
+
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t},\n");
+	}
+#undef CONFIG_WRITE_BOOL_JSON
+
+	/* 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_BOOL_MUTABLE(n, m, c) {				\
+	bool bv2;							\
+	if (je_mallctl("opt."#n, (void *)&bv, &bsz, NULL, 0) == 0 &&	\
+	    je_mallctl(#m, &bv2, (void *)&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 ("#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_SIZE_T(n, c)						\
+	if (je_mallctl("opt."#n, (void *)&sv, &ssz, NULL, 0) == 0) {	\
+		if (json) {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			    "\t\t\t\""#n"\": %zu%s\n", sv, (c));	\
+		} else {						\
+			malloc_cprintf(write_cb, cbopaque,		\
+			"  opt."#n": %zu\n", sv);			\
+		}							\
+	}
+#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_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_UNSIGNED(narenas, ",")
+	OPT_WRITE_CHAR_P(purge, ",")
+	if (json || opt_purge == purge_mode_ratio) {
+		OPT_WRITE_SSIZE_T_MUTABLE(lg_dirty_mult,
+		    arenas.lg_dirty_mult, ",")
+	}
+	if (json || opt_purge == purge_mode_decay) {
+		OPT_WRITE_SSIZE_T_MUTABLE(decay_time, arenas.decay_time, ",")
+	}
+	OPT_WRITE_CHAR_P(junk, ",")
+	OPT_WRITE_SIZE_T(quarantine, ",")
+	OPT_WRITE_BOOL(redzone, ",")
+	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, ",")
+	/*
+	 * stats_print is always emitted, so as long as stats_print comes last
+	 * it's safe to unconditionally omit the comma here (rather than having
+	 * to conditionally omit it elsewhere depending on configuration).
+	 */
+	OPT_WRITE_BOOL(stats_print, "")
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t},\n");
+	}
+
+#undef OPT_WRITE_BOOL
+#undef OPT_WRITE_BOOL_MUTABLE
+#undef OPT_WRITE_SIZE_T
+#undef OPT_WRITE_SSIZE_T
+#undef OPT_WRITE_CHAR_P
+
+	/* arenas. */
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"arenas\": {\n");
+	}
+
+	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);
+
+	CTL_GET("arenas.lg_dirty_mult", &ssv, ssize_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"lg_dirty_mult\": %zd,\n", ssv);
+	} else if (opt_purge == purge_mode_ratio) {
+		if (ssv >= 0) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "Min active:dirty page ratio per arena: "
+			    "%u:1\n", (1U << ssv));
+		} else {
+			malloc_cprintf(write_cb, cbopaque,
+			    "Min active:dirty page ratio per arena: "
+			    "N/A\n");
+		}
+	}
+	CTL_GET("arenas.decay_time", &ssv, ssize_t);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"decay_time\": %zd,\n", ssv);
+	} else if (opt_purge == purge_mode_decay) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "Unused dirty page decay time: %zd%s\n",
+		    ssv, (ssv < 0) ? " (no decay)" : "");
+	}
+
+	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);
+	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);
+
+	if (je_mallctl("arenas.tcache_max", (void *)&sv, &ssz, NULL, 0) == 0) {
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\"tcache_max\": %zu,\n", sv);
+		} else {
+			malloc_cprintf(write_cb, cbopaque,
+			    "Maximum thread-cached size class: %zu\n", sv);
+		}
+	}
+
+	if (json) {
+		unsigned nbins, nlruns, nhchunks, 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,
+			    "\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.run_size", i, &sv, size_t);
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t\t\"run_size\": %zu\n", sv);
+
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t}%s\n", (i + 1 < nbins) ? "," : "");
+		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t],\n");
+
+		CTL_GET("arenas.nlruns", &nlruns, unsigned);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"nlruns\": %u,\n", nlruns);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"lrun\": [\n");
+		for (i = 0; i < nlruns; i++) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t{\n");
+
+			CTL_M2_GET("arenas.lrun.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 < nlruns) ? "," : "");
+		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t],\n");
+
+		CTL_GET("arenas.nhchunks", &nhchunks, unsigned);
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"nhchunks\": %u,\n", nhchunks);
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"hchunk\": [\n");
+		for (i = 0; i < nhchunks; i++) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\t\t{\n");
+
+			CTL_M2_GET("arenas.hchunk.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 < nhchunks) ? "," : "");
+		}
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t]\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t},\n");
+	}
+
+	/* prof. */
+	if (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", (config_stats || merged || unmerged) ? "," :
+		    "");
+	}
+}
+
+static void
+stats_print_helper(void (*write_cb)(void *, const char *), void *cbopaque,
+    bool json, bool merged, bool unmerged, bool bins, bool large, bool huge)
+{
+	size_t *cactive;
+	size_t allocated, active, metadata, resident, mapped, retained;
+
+	CTL_GET("stats.cactive", &cactive, size_t *);
+	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);
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\"stats\": {\n");
+
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t\t\t\"cactive\": %zu,\n", atomic_read_z(cactive));
+		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}%s\n", (merged || unmerged) ? "," : "");
+	} 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);
+		malloc_cprintf(write_cb, cbopaque,
+		    "Current active ceiling: %zu\n",
+		    atomic_read_z(cactive));
+	}
+
+	if (merged || unmerged) {
+		unsigned narenas;
+
+		if (json) {
+			malloc_cprintf(write_cb, cbopaque,
+			    "\t\t\"stats.arenas\": {\n");
+		}
+
+		CTL_GET("arenas.narenas", &narenas, unsigned);
+		{
+			VARIABLE_ARRAY(bool, initialized, narenas);
+			size_t isz;
+			unsigned i, j, ninitialized;
+
+			isz = sizeof(bool) * narenas;
+			xmallctl("arenas.initialized", (void *)initialized,
+			    &isz, NULL, 0);
+			for (i = ninitialized = 0; i < narenas; i++) {
+				if (initialized[i])
+					ninitialized++;
+			}
+
+			/* 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, json,
+				    narenas, bins, large, huge);
+				if (json) {
+					malloc_cprintf(write_cb, cbopaque,
+					    "\t\t\t}%s\n", (ninitialized > 1) ?
+					    "," : "");
+				}
+			}
+
+			/* Unmerged stats. */
+			for (i = j = 0; i < narenas; i++) {
+				if (initialized[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,
+					    json, i, bins, large, huge);
+					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;
+	bool json = false;
+	bool general = true;
+	bool merged = true;
+	bool unmerged = true;
+	bool bins = true;
+	bool large = true;
+	bool huge = true;
+
+	/*
+	 * 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) {
+		unsigned i;
+
+		for (i = 0; opts[i] != '\0'; i++) {
+			switch (opts[i]) {
+			case 'J':
+				json = true;
+				break;
+			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;
+			case 'h':
+				huge = false;
+				break;
+			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, merged, unmerged);
+	if (config_stats) {
+		stats_print_helper(write_cb, cbopaque, json, merged, unmerged,
+		    bins, large, huge);
+	}
+	if (json) {
+		malloc_cprintf(write_cb, cbopaque,
+		    "\t}\n"
+		    "}\n");
+	} else {
+		malloc_cprintf(write_cb, cbopaque,
+		    "--- End jemalloc statistics ---\n");
+	}
+}
diff --git a/deps/jemalloc/src/tcache.c b/deps/jemalloc/src/tcache.c
new file mode 100644
index 0000000..21540ff
--- /dev/null
+++ b/deps/jemalloc/src/tcache.c
@@ -0,0 +1,555 @@
+#define	JEMALLOC_TCACHE_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+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. */
+
+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(tsdn_t *tsdn, const void *ptr)
+{
+
+	return (arena_salloc(tsdn, ptr, false));
+}
+
+void
+tcache_event_hard(tsd_t *tsd, tcache_t *tcache)
+{
+	szind_t binind = tcache->next_gc_bin;
+	tcache_bin_t *tbin = &tcache->tbins[binind];
+	tcache_bin_info_t *tbin_info = &tcache_bin_info[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(tsd, tcache, tbin, binind,
+			    tbin->ncached - tbin->low_water + (tbin->low_water
+			    >> 2));
+		} else {
+			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.
+		 */
+		if (tbin->lg_fill_div > 1)
+			tbin->lg_fill_div--;
+	}
+	tbin->low_water = tbin->ncached;
+
+	tcache->next_gc_bin++;
+	if (tcache->next_gc_bin == nhbins)
+		tcache->next_gc_bin = 0;
+}
+
+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 *ret;
+
+	arena_tcache_fill_small(tsdn, arena, tbin, binind, config_prof ?
+	    tcache->prof_accumbytes : 0);
+	if (config_prof)
+		tcache->prof_accumbytes = 0;
+	ret = tcache_alloc_easy(tbin, tcache_success);
+
+	return (ret);
+}
+
+void
+tcache_bin_flush_small(tsd_t *tsd, tcache_t *tcache, tcache_bin_t *tbin,
+    szind_t binind, unsigned rem)
+{
+	arena_t *arena;
+	void *ptr;
+	unsigned i, nflush, ndeferred;
+	bool merged_stats = false;
+
+	assert(binind < NBINS);
+	assert(rem <= tbin->ncached);
+
+	arena = arena_choose(tsd, NULL);
+	assert(arena != NULL);
+	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 - 1));
+		arena_t *bin_arena = extent_node_arena_get(&chunk->node);
+		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(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 - 1 - i);
+			assert(ptr != NULL);
+			chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+			if (extent_node_arena_get(&chunk->node) == bin_arena) {
+				size_t pageind = ((uintptr_t)ptr -
+				    (uintptr_t)chunk) >> LG_PAGE;
+				arena_chunk_map_bits_t *bitselm =
+				    arena_bitselm_get_mutable(chunk, pageind);
+				arena_dalloc_bin_junked_locked(tsd_tsdn(tsd),
+				    bin_arena, chunk, ptr, bitselm);
+			} else {
+				/*
+				 * This object was allocated via a different
+				 * arena bin than the one that is currently
+				 * locked.  Stash the object, so that it can be
+				 * handled in a future pass.
+				 */
+				*(tbin->avail - 1 - ndeferred) = ptr;
+				ndeferred++;
+			}
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+		arena_decay_ticks(tsd_tsdn(tsd), bin_arena, nflush - ndeferred);
+	}
+	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 = &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(tsd_tsdn(tsd), &bin->lock);
+	}
+
+	memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem *
+	    sizeof(void *));
+	tbin->ncached = rem;
+	if ((int)tbin->ncached < tbin->low_water)
+		tbin->low_water = tbin->ncached;
+}
+
+void
+tcache_bin_flush_large(tsd_t *tsd, tcache_bin_t *tbin, szind_t binind,
+    unsigned rem, tcache_t *tcache)
+{
+	arena_t *arena;
+	void *ptr;
+	unsigned i, nflush, ndeferred;
+	bool merged_stats = false;
+
+	assert(binind < nhbins);
+	assert(rem <= tbin->ncached);
+
+	arena = arena_choose(tsd, NULL);
+	assert(arena != NULL);
+	for (nflush = tbin->ncached - rem; nflush > 0; nflush = ndeferred) {
+		/* Lock the arena associated with the first object. */
+		arena_chunk_t *chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(
+		    *(tbin->avail - 1));
+		arena_t *locked_arena = extent_node_arena_get(&chunk->node);
+		UNUSED bool idump;
+
+		if (config_prof)
+			idump = false;
+		malloc_mutex_lock(tsd_tsdn(tsd), &locked_arena->lock);
+		if ((config_prof || config_stats) && locked_arena == arena) {
+			if (config_prof) {
+				idump = arena_prof_accum_locked(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;
+				tbin->tstats.nrequests = 0;
+			}
+		}
+		ndeferred = 0;
+		for (i = 0; i < nflush; i++) {
+			ptr = *(tbin->avail - 1 - i);
+			assert(ptr != NULL);
+			chunk = (arena_chunk_t *)CHUNK_ADDR2BASE(ptr);
+			if (extent_node_arena_get(&chunk->node) ==
+			    locked_arena) {
+				arena_dalloc_large_junked_locked(tsd_tsdn(tsd),
+				    locked_arena, chunk, ptr);
+			} 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 - 1 - ndeferred) = ptr;
+				ndeferred++;
+			}
+		}
+		malloc_mutex_unlock(tsd_tsdn(tsd), &locked_arena->lock);
+		if (config_prof && idump)
+			prof_idump(tsd_tsdn(tsd));
+		arena_decay_ticks(tsd_tsdn(tsd), locked_arena, nflush -
+		    ndeferred);
+	}
+	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.
+		 */
+		malloc_mutex_lock(tsd_tsdn(tsd), &arena->lock);
+		arena->stats.nrequests_large += tbin->tstats.nrequests;
+		arena->stats.lstats[binind - NBINS].nrequests +=
+		    tbin->tstats.nrequests;
+		tbin->tstats.nrequests = 0;
+		malloc_mutex_unlock(tsd_tsdn(tsd), &arena->lock);
+	}
+
+	memmove(tbin->avail - rem, tbin->avail - tbin->ncached, rem *
+	    sizeof(void *));
+	tbin->ncached = rem;
+	if ((int)tbin->ncached < tbin->low_water)
+		tbin->low_water = tbin->ncached;
+}
+
+static void
+tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena)
+{
+
+	if (config_stats) {
+		/* Link into list of extant tcaches. */
+		malloc_mutex_lock(tsdn, &arena->lock);
+		ql_elm_new(tcache, link);
+		ql_tail_insert(&arena->tcache_ql, tcache, link);
+		malloc_mutex_unlock(tsdn, &arena->lock);
+	}
+}
+
+static void
+tcache_arena_dissociate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena)
+{
+
+	if (config_stats) {
+		/* Unlink from list of extant tcaches. */
+		malloc_mutex_lock(tsdn, &arena->lock);
+		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->lock);
+	}
+}
+
+void
+tcache_arena_reassociate(tsdn_t *tsdn, tcache_t *tcache, arena_t *oldarena,
+    arena_t *newarena)
+{
+
+	tcache_arena_dissociate(tsdn, tcache, oldarena);
+	tcache_arena_associate(tsdn, tcache, newarena);
+}
+
+tcache_t *
+tcache_get_hard(tsd_t *tsd)
+{
+	arena_t *arena;
+
+	if (!tcache_enabled_get()) {
+		if (tsd_nominal(tsd))
+			tcache_enabled_set(false); /* Memoize. */
+		return (NULL);
+	}
+	arena = arena_choose(tsd, NULL);
+	if (unlikely(arena == NULL))
+		return (NULL);
+	return (tcache_create(tsd_tsdn(tsd), arena));
+}
+
+tcache_t *
+tcache_create(tsdn_t *tsdn, arena_t *arena)
+{
+	tcache_t *tcache;
+	size_t size, stack_offset;
+	unsigned i;
+
+	size = offsetof(tcache_t, tbins) + (sizeof(tcache_bin_t) * nhbins);
+	/* Naturally align the pointer stacks. */
+	size = PTR_CEILING(size);
+	stack_offset = size;
+	size += stack_nelms * sizeof(void *);
+	/* Avoid false cacheline sharing. */
+	size = sa2u(size, CACHELINE);
+
+	tcache = ipallocztm(tsdn, size, CACHELINE, true, NULL, true,
+	    arena_get(TSDN_NULL, 0, true));
+	if (tcache == NULL)
+		return (NULL);
+
+	tcache_arena_associate(tsdn, tcache, arena);
+
+	ticker_init(&tcache->gc_ticker, TCACHE_GC_INCR);
+
+	assert((TCACHE_NSLOTS_SMALL_MAX & 1U) == 0);
+	for (i = 0; i < nhbins; i++) {
+		tcache->tbins[i].lg_fill_div = 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->tbins[i].avail = (void **)((uintptr_t)tcache +
+		    (uintptr_t)stack_offset);
+	}
+
+	return (tcache);
+}
+
+static void
+tcache_destroy(tsd_t *tsd, tcache_t *tcache)
+{
+	arena_t *arena;
+	unsigned i;
+
+	arena = arena_choose(tsd, NULL);
+	tcache_arena_dissociate(tsd_tsdn(tsd), tcache, arena);
+
+	for (i = 0; i < NBINS; i++) {
+		tcache_bin_t *tbin = &tcache->tbins[i];
+		tcache_bin_flush_small(tsd, tcache, tbin, i, 0);
+
+		if (config_stats && tbin->tstats.nrequests != 0) {
+			arena_bin_t *bin = &arena->bins[i];
+			malloc_mutex_lock(tsd_tsdn(tsd), &bin->lock);
+			bin->stats.nrequests += tbin->tstats.nrequests;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &bin->lock);
+		}
+	}
+
+	for (; i < nhbins; i++) {
+		tcache_bin_t *tbin = &tcache->tbins[i];
+		tcache_bin_flush_large(tsd, tbin, i, 0, tcache);
+
+		if (config_stats && tbin->tstats.nrequests != 0) {
+			malloc_mutex_lock(tsd_tsdn(tsd), &arena->lock);
+			arena->stats.nrequests_large += tbin->tstats.nrequests;
+			arena->stats.lstats[i - NBINS].nrequests +=
+			    tbin->tstats.nrequests;
+			malloc_mutex_unlock(tsd_tsdn(tsd), &arena->lock);
+		}
+	}
+
+	if (config_prof && tcache->prof_accumbytes > 0 &&
+	    arena_prof_accum(tsd_tsdn(tsd), arena, tcache->prof_accumbytes))
+		prof_idump(tsd_tsdn(tsd));
+
+	idalloctm(tsd_tsdn(tsd), tcache, NULL, true, true);
+}
+
+void
+tcache_cleanup(tsd_t *tsd)
+{
+	tcache_t *tcache;
+
+	if (!config_tcache)
+		return;
+
+	if ((tcache = tsd_tcache_get(tsd)) != NULL) {
+		tcache_destroy(tsd, tcache);
+		tsd_tcache_set(tsd, NULL);
+	}
+}
+
+void
+tcache_enabled_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+void
+tcache_stats_merge(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena)
+{
+	unsigned i;
+
+	cassert(config_stats);
+
+	malloc_mutex_assert_owner(tsdn, &arena->lock);
+
+	/* 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(tsdn, &bin->lock);
+		bin->stats.nrequests += tbin->tstats.nrequests;
+		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;
+		tbin->tstats.nrequests = 0;
+	}
+}
+
+bool
+tcaches_create(tsd_t *tsd, unsigned *r_ind)
+{
+	arena_t *arena;
+	tcache_t *tcache;
+	tcaches_t *elm;
+
+	if (tcaches == NULL) {
+		tcaches = base_alloc(tsd_tsdn(tsd), sizeof(tcache_t *) *
+		    (MALLOCX_TCACHE_MAX+1));
+		if (tcaches == NULL)
+			return (true);
+	}
+
+	if (tcaches_avail == NULL && tcaches_past > MALLOCX_TCACHE_MAX)
+		return (true);
+	arena = arena_ichoose(tsd, NULL);
+	if (unlikely(arena == NULL))
+		return (true);
+	tcache = tcache_create(tsd_tsdn(tsd), arena);
+	if (tcache == NULL)
+		return (true);
+
+	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++;
+	}
+
+	return (false);
+}
+
+static void
+tcaches_elm_flush(tsd_t *tsd, tcaches_t *elm)
+{
+
+	if (elm->tcache == NULL)
+		return;
+	tcache_destroy(tsd, elm->tcache);
+	elm->tcache = NULL;
+}
+
+void
+tcaches_flush(tsd_t *tsd, unsigned ind)
+{
+
+	tcaches_elm_flush(tsd, &tcaches[ind]);
+}
+
+void
+tcaches_destroy(tsd_t *tsd, unsigned ind)
+{
+	tcaches_t *elm = &tcaches[ind];
+	tcaches_elm_flush(tsd, elm);
+	elm->next = tcaches_avail;
+	tcaches_avail = elm;
+}
+
+bool
+tcache_boot(tsdn_t *tsdn)
+{
+	unsigned i;
+
+	/*
+	 * If necessary, clamp opt_lg_tcache_max, now that large_maxclass is
+	 * known.
+	 */
+	if (opt_lg_tcache_max < 0 || (ZU(1) << opt_lg_tcache_max) < SMALL_MAXCLASS)
+		tcache_maxclass = SMALL_MAXCLASS;
+	else if ((ZU(1) << opt_lg_tcache_max) > large_maxclass)
+		tcache_maxclass = large_maxclass;
+	else
+		tcache_maxclass = (ZU(1) << opt_lg_tcache_max);
+
+	nhbins = size2index(tcache_maxclass) + 1;
+
+	/* Initialize tcache_bin_info. */
+	tcache_bin_info = (tcache_bin_info_t *)base_alloc(tsdn, nhbins *
+	    sizeof(tcache_bin_info_t));
+	if (tcache_bin_info == NULL)
+		return (true);
+	stack_nelms = 0;
+	for (i = 0; i < NBINS; i++) {
+		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 {
+			tcache_bin_info[i].ncached_max =
+			    TCACHE_NSLOTS_SMALL_MAX;
+		}
+		stack_nelms += tcache_bin_info[i].ncached_max;
+	}
+	for (; i < nhbins; i++) {
+		tcache_bin_info[i].ncached_max = TCACHE_NSLOTS_LARGE;
+		stack_nelms += tcache_bin_info[i].ncached_max;
+	}
+
+	return (false);
+}
diff --git a/deps/jemalloc/src/ticker.c b/deps/jemalloc/src/ticker.c
new file mode 100644
index 0000000..db09024
--- /dev/null
+++ b/deps/jemalloc/src/ticker.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_TICKER_C_
+#include "jemalloc/internal/jemalloc_internal.h"
diff --git a/deps/jemalloc/src/tsd.c b/deps/jemalloc/src/tsd.c
new file mode 100644
index 0000000..ec69a51
--- /dev/null
+++ b/deps/jemalloc/src/tsd.c
@@ -0,0 +1,197 @@
+#define	JEMALLOC_TSD_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* Data. */
+
+static unsigned ncleanups;
+static malloc_tsd_cleanup_t cleanups[MALLOC_TSD_CLEANUPS_MAX];
+
+malloc_tsd_data(, , tsd_t, TSD_INITIALIZER)
+
+/******************************************************************************/
+
+void *
+malloc_tsd_malloc(size_t size)
+{
+
+	return (a0malloc(CACHELINE_CEILING(size)));
+}
+
+void
+malloc_tsd_dalloc(void *wrapper)
+{
+
+	a0dalloc(wrapper);
+}
+
+void
+malloc_tsd_no_cleanup(void *arg)
+{
+
+	not_reached();
+}
+
+#if defined(JEMALLOC_MALLOC_THREAD_CLEANUP) || defined(_WIN32)
+#ifndef _WIN32
+JEMALLOC_EXPORT
+#endif
+void
+_malloc_thread_cleanup(void)
+{
+	bool pending[MALLOC_TSD_CLEANUPS_MAX], again;
+	unsigned 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])
+					again = true;
+			}
+		}
+	} while (again);
+}
+#endif
+
+void
+malloc_tsd_cleanup_register(bool (*f)(void))
+{
+
+	assert(ncleanups < MALLOC_TSD_CLEANUPS_MAX);
+	cleanups[ncleanups] = f;
+	ncleanups++;
+}
+
+void
+tsd_cleanup(void *arg)
+{
+	tsd_t *tsd = (tsd_t *)arg;
+
+	switch (tsd->state) {
+	case tsd_state_uninitialized:
+		/* Do nothing. */
+		break;
+	case tsd_state_nominal:
+#define	O(n, t)								\
+		n##_cleanup(tsd);
+MALLOC_TSD
+#undef O
+		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;
+	case tsd_state_reincarnated:
+		/*
+		 * Another destructor deallocated memory after this destructor
+		 * was called.  Reset state to tsd_state_purgatory and request
+		 * another callback.
+		 */
+		tsd->state = tsd_state_purgatory;
+		tsd_set(tsd);
+		break;
+	default:
+		not_reached();
+	}
+}
+
+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_arenas_tdata_bypassp_get(tsd_fetch()) = false;
+}
+
+#ifdef _WIN32
+static BOOL WINAPI
+_tls_callback(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpvReserved)
+{
+
+	switch (fdwReason) {
+#ifdef JEMALLOC_LAZY_LOCK
+	case DLL_THREAD_ATTACH:
+		isthreaded = true;
+		break;
+#endif
+	case DLL_THREAD_DETACH:
+		_malloc_thread_cleanup();
+		break;
+	default:
+		break;
+	}
+	return (true);
+}
+
+#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)
+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)
+{
+	pthread_t self = pthread_self();
+	tsd_init_block_t *iter;
+
+	/* Check whether this thread has already inserted into the list. */
+	malloc_mutex_lock(TSDN_NULL, &head->lock);
+	ql_foreach(iter, &head->blocks, link) {
+		if (iter->thread == self) {
+			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(TSDN_NULL, &head->lock);
+	return (NULL);
+}
+
+void
+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(TSDN_NULL, &head->lock);
+}
+#endif
diff --git a/deps/jemalloc/src/util.c b/deps/jemalloc/src/util.c
new file mode 100644
index 0000000..dd8c236
--- /dev/null
+++ b/deps/jemalloc/src/util.c
@@ -0,0 +1,666 @@
+/*
+ * 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	JEMALLOC_UTIL_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+/******************************************************************************/
+/* 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
+#include "jemalloc/internal/assert.h"
diff --git a/deps/jemalloc/src/valgrind.c b/deps/jemalloc/src/valgrind.c
new file mode 100644
index 0000000..8e7ef3a
--- /dev/null
+++ b/deps/jemalloc/src/valgrind.c
@@ -0,0 +1,34 @@
+#include "jemalloc/internal/jemalloc_internal.h"
+#ifndef JEMALLOC_VALGRIND
+#  error "This source file is for Valgrind integration."
+#endif
+
+#include <valgrind/memcheck.h>
+
+void
+valgrind_make_mem_noaccess(void *ptr, size_t usize)
+{
+
+	VALGRIND_MAKE_MEM_NOACCESS(ptr, usize);
+}
+
+void
+valgrind_make_mem_undefined(void *ptr, size_t usize)
+{
+
+	VALGRIND_MAKE_MEM_UNDEFINED(ptr, usize);
+}
+
+void
+valgrind_make_mem_defined(void *ptr, size_t usize)
+{
+
+	VALGRIND_MAKE_MEM_DEFINED(ptr, usize);
+}
+
+void
+valgrind_freelike_block(void *ptr, size_t usize)
+{
+
+	VALGRIND_FREELIKE_BLOCK(ptr, usize);
+}
diff --git a/deps/jemalloc/src/witness.c b/deps/jemalloc/src/witness.c
new file mode 100644
index 0000000..23753f2
--- /dev/null
+++ b/deps/jemalloc/src/witness.c
@@ -0,0 +1,136 @@
+#define	JEMALLOC_WITNESS_C_
+#include "jemalloc/internal/jemalloc_internal.h"
+
+void
+witness_init(witness_t *witness, const char *name, witness_rank_t rank,
+    witness_comp_t *comp)
+{
+
+	witness->name = name;
+	witness->rank = rank;
+	witness->comp = comp;
+}
+
+#ifdef JEMALLOC_JET
+#undef witness_lock_error
+#define	witness_lock_error JEMALLOC_N(n_witness_lock_error)
+#endif
+void
+witness_lock_error(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();
+}
+#ifdef JEMALLOC_JET
+#undef witness_lock_error
+#define	witness_lock_error JEMALLOC_N(witness_lock_error)
+witness_lock_error_t *witness_lock_error = JEMALLOC_N(n_witness_lock_error);
+#endif
+
+#ifdef JEMALLOC_JET
+#undef witness_owner_error
+#define	witness_owner_error JEMALLOC_N(n_witness_owner_error)
+#endif
+void
+witness_owner_error(const witness_t *witness)
+{
+
+	malloc_printf("<jemalloc>: Should own %s(%u)\n", witness->name,
+	    witness->rank);
+	abort();
+}
+#ifdef JEMALLOC_JET
+#undef witness_owner_error
+#define	witness_owner_error JEMALLOC_N(witness_owner_error)
+witness_owner_error_t *witness_owner_error = JEMALLOC_N(n_witness_owner_error);
+#endif
+
+#ifdef JEMALLOC_JET
+#undef witness_not_owner_error
+#define	witness_not_owner_error JEMALLOC_N(n_witness_not_owner_error)
+#endif
+void
+witness_not_owner_error(const witness_t *witness)
+{
+
+	malloc_printf("<jemalloc>: Should not own %s(%u)\n", witness->name,
+	    witness->rank);
+	abort();
+}
+#ifdef JEMALLOC_JET
+#undef witness_not_owner_error
+#define	witness_not_owner_error JEMALLOC_N(witness_not_owner_error)
+witness_not_owner_error_t *witness_not_owner_error =
+    JEMALLOC_N(n_witness_not_owner_error);
+#endif
+
+#ifdef JEMALLOC_JET
+#undef witness_lockless_error
+#define	witness_lockless_error JEMALLOC_N(n_witness_lockless_error)
+#endif
+void
+witness_lockless_error(const witness_list_t *witnesses)
+{
+	witness_t *w;
+
+	malloc_printf("<jemalloc>: Should not own any locks:");
+	ql_foreach(w, witnesses, link) {
+		malloc_printf(" %s(%u)", w->name, w->rank);
+	}
+	malloc_printf("\n");
+	abort();
+}
+#ifdef JEMALLOC_JET
+#undef witness_lockless_error
+#define	witness_lockless_error JEMALLOC_N(witness_lockless_error)
+witness_lockless_error_t *witness_lockless_error =
+    JEMALLOC_N(n_witness_lockless_error);
+#endif
+
+void
+witnesses_cleanup(tsd_t *tsd)
+{
+
+	witness_assert_lockless(tsd_tsdn(tsd));
+
+	/* Do nothing. */
+}
+
+void
+witness_fork_cleanup(tsd_t *tsd)
+{
+
+	/* Do nothing. */
+}
+
+void
+witness_prefork(tsd_t *tsd)
+{
+
+	tsd_witness_fork_set(tsd, true);
+}
+
+void
+witness_postfork_parent(tsd_t *tsd)
+{
+
+	tsd_witness_fork_set(tsd, false);
+}
+
+void
+witness_postfork_child(tsd_t *tsd)
+{
+#ifndef JEMALLOC_MUTEX_INIT_CB
+	witness_list_t *witnesses;
+
+	witnesses = tsd_witnessesp_get(tsd);
+	ql_new(witnesses);
+#endif
+	tsd_witness_fork_set(tsd, false);
+}
diff --git a/deps/jemalloc/src/zone.c b/deps/jemalloc/src/zone.c
new file mode 100644
index 0000000..0571920
--- /dev/null
+++ b/deps/jemalloc/src/zone.c
@@ -0,0 +1,330 @@
+#include "jemalloc/internal/jemalloc_internal.h"
+#ifndef JEMALLOC_ZONE
+#  error "This source file is for zones on Darwin (OS X)."
+#endif
+
+/*
+ * 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)
+JEMALLOC_ATTR(weak_import);
+
+/******************************************************************************/
+/* Data. */
+
+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 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 size_t	zone_good_size(malloc_zone_t *zone, size_t size);
+static void	zone_force_lock(malloc_zone_t *zone);
+static void	zone_force_unlock(malloc_zone_t *zone);
+
+/******************************************************************************/
+/*
+ * Functions.
+ */
+
+static size_t
+zone_size(malloc_zone_t *zone, 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
+	 * we knew that all pointers were owned by *some* zone, we could split
+	 * 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.
+	 */
+	return (ivsalloc(tsdn_fetch(), ptr, config_prof));
+}
+
+static void *
+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));
+}
+
+static void *
+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);
+}
+
+static void
+zone_free(malloc_zone_t *zone, void *ptr)
+{
+
+	if (ivsalloc(tsdn_fetch(), ptr, config_prof) != 0) {
+		je_free(ptr);
+		return;
+	}
+
+	free(ptr);
+}
+
+static void *
+zone_realloc(malloc_zone_t *zone, void *ptr, size_t size)
+{
+
+	if (ivsalloc(tsdn_fetch(), ptr, config_prof) != 0)
+		return (je_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)
+{
+	void *ret = NULL; /* Assignment avoids useless compiler warning. */
+
+	je_posix_memalign(&ret, alignment, size);
+
+	return (ret);
+}
+#endif
+
+#if (JEMALLOC_ZONE_VERSION >= 6)
+static void
+zone_free_definite_size(malloc_zone_t *zone, void *ptr, size_t size)
+{
+	size_t alloc_size;
+
+	alloc_size = ivsalloc(tsdn_fetch(), ptr, config_prof);
+	if (alloc_size != 0) {
+		assert(alloc_size == size);
+		je_free(ptr);
+		return;
+	}
+
+	free(ptr);
+}
+#endif
+
+static void *
+zone_destroy(malloc_zone_t *zone)
+{
+
+	/* This function should never be called. */
+	not_reached();
+	return (NULL);
+}
+
+static size_t
+zone_good_size(malloc_zone_t *zone, size_t size)
+{
+
+	if (size == 0)
+		size = 1;
+	return (s2u(size));
+}
+
+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_init(void)
+{
+
+	jemalloc_zone.size = (void *)zone_size;
+	jemalloc_zone.malloc = (void *)zone_malloc;
+	jemalloc_zone.calloc = (void *)zone_calloc;
+	jemalloc_zone.valloc = (void *)zone_valloc;
+	jemalloc_zone.free = (void *)zone_free;
+	jemalloc_zone.realloc = (void *)zone_realloc;
+	jemalloc_zone.destroy = (void *)zone_destroy;
+	jemalloc_zone.zone_name = "jemalloc_zone";
+	jemalloc_zone.batch_malloc = NULL;
+	jemalloc_zone.batch_free = NULL;
+	jemalloc_zone.introspect = &jemalloc_zone_introspect;
+	jemalloc_zone.version = JEMALLOC_ZONE_VERSION;
+#if (JEMALLOC_ZONE_VERSION >= 5)
+	jemalloc_zone.memalign = zone_memalign;
+#endif
+#if (JEMALLOC_ZONE_VERSION >= 6)
+	jemalloc_zone.free_definite_size = zone_free_definite_size;
+#endif
+#if (JEMALLOC_ZONE_VERSION >= 8)
+	jemalloc_zone.pressure_relief = NULL;
+#endif
+
+	jemalloc_zone_introspect.enumerator = NULL;
+	jemalloc_zone_introspect.good_size = (void *)zone_good_size;
+	jemalloc_zone_introspect.check = NULL;
+	jemalloc_zone_introspect.print = NULL;
+	jemalloc_zone_introspect.log = NULL;
+	jemalloc_zone_introspect.force_lock = (void *)zone_force_lock;
+	jemalloc_zone_introspect.force_unlock = (void *)zone_force_unlock;
+	jemalloc_zone_introspect.statistics = NULL;
+#if (JEMALLOC_ZONE_VERSION >= 6)
+	jemalloc_zone_introspect.zone_locked = NULL;
+#endif
+#if (JEMALLOC_ZONE_VERSION >= 7)
+	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
+#endif
+}
+
+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_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);
+
+		/*
+		 * 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
+zone_register(void)
+{
+
+	/*
+	 * If something else replaced the system default zone allocator, don't
+	 * register jemalloc's.
+	 */
+	default_zone = zone_default_get();
+	if (!default_zone->zone_name || strcmp(default_zone->zone_name,
+	    "DefaultMallocZone") != 0)
+		return;
+
+	/*
+	 * 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
+	 * 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.
+	 */
+	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. */
+	zone_init();
+	malloc_zone_register(&jemalloc_zone);
+
+	/* Promote the custom zone to be default. */
+	zone_promote();
+}