Merge branch 'dev'

ChangeLog

@@ -4,6 +4,41 @@ brevity.  Much more detail can be found in the git revision history:
 
     https://github.com/jemalloc/jemalloc
 
+* 5.0.1 (July 1, 2017)
+
+  This bugfix release fixes several issues, most of which are obscure enough
+  that typical applications are not impacted.
+
+  Bug fixes:
+  - Update decay->nunpurged before purging, in order to avoid potential update
+    races and subsequent incorrect purging volume.  (@interwq)
+  - Only abort on dlsym(3) error if the failure impacts an enabled feature (lazy
+    locking and/or background threads).  This mitigates an initialization
+    failure bug for which we still do not have a clear reproduction test case.
+    (@interwq)
+  - Modify tsd management so that it neither crashes nor leaks if a thread's
+    only allocation activity is to call free() after TLS destructors have been
+    executed.  This behavior was observed when operating with GNU libc, and is
+    unlikely to be an issue with other libc implementations.  (@interwq)
+  - Mask signals during background thread creation.  This prevents signals from
+    being inadvertently delivered to background threads.  (@jasone,
+    @davidgoldblatt, @interwq)
+  - Avoid inactivity checks within background threads, in order to prevent
+    recursive mutex acquisition.  (@interwq)
+  - Fix extent_grow_retained() to use the specified hooks when the
+    arena.<i>.extent_hooks mallctl is used to override the default hooks.
+    (@interwq)
+  - Add missing reentrancy support for custom extent hooks which allocate.
+    (@interwq)
+  - Post-fork(2), re-initialize the list of tcaches associated with each arena
+    to contain no tcaches except the forking thread's.  (@interwq)
+  - Add missing post-fork(2) mutex reinitialization for extent_grow_mtx.  This
+    fixes potential deadlocks after fork(2).  (@interwq)
+  - Enforce minimum autoconf version (currently 2.68), since 2.63 is known to
+    generate corrupt configure scripts.  (@jasone)
+  - Ensure that the configured page size (--with-lg-page) is no larger than the
+    configured huge page size (--with-lg-hugepage).  (@jasone)
+
 * 5.0.0 (June 13, 2017)
 
   Unlike all previous jemalloc releases, this release does not use naturally

configure.ac

@@ -1,4 +1,5 @@
 dnl Process this file with autoconf to produce a configure script.
+AC_PREREQ(2.68)
 AC_INIT([Makefile.in])
 
 AC_CONFIG_AUX_DIR([build-aux])
@@ -1373,6 +1374,10 @@ if test "x${je_cv_lg_hugepage}" = "x" ; then
     je_cv_lg_hugepage=21
   fi
 fi
+if test "x${LG_PAGE}" != "xundefined" -a \
+        "${je_cv_lg_hugepage}" -lt "${LG_PAGE}" ; then
+  AC_MSG_ERROR([Huge page size (2^${je_cv_lg_hugepage}) must be at least page size (2^${LG_PAGE})])
+fi
 AC_DEFINE_UNQUOTED([LG_HUGEPAGE], [${je_cv_lg_hugepage}])
 
 AC_ARG_WITH([lg_page_sizes],
@@ -1470,6 +1475,15 @@ if test "x$abi" != "xpecoff" ; then
   if test "x${je_cv_pthread_atfork}" = "xyes" ; then
     AC_DEFINE([JEMALLOC_HAVE_PTHREAD_ATFORK], [ ])
   fi
+  dnl Check if pthread_setname_np is available with the expected API.
+  JE_COMPILABLE([pthread_setname_np(3)], [
+#include <pthread.h>
+], [
+  pthread_setname_np(pthread_self(), "setname_test");
+], [je_cv_pthread_setname_np])
+  if test "x${je_cv_pthread_setname_np}" = "xyes" ; then
+    AC_DEFINE([JEMALLOC_HAVE_PTHREAD_SETNAME_NP], [ ])
+  fi
 fi
 
 JE_APPEND_VS(CPPFLAGS, -D_REENTRANT)

include/jemalloc/internal/arena_externs.h

@@ -90,6 +90,7 @@ void arena_prefork3(tsdn_t *tsdn, arena_t *arena);
 void arena_prefork4(tsdn_t *tsdn, arena_t *arena);
 void arena_prefork5(tsdn_t *tsdn, arena_t *arena);
 void arena_prefork6(tsdn_t *tsdn, arena_t *arena);
+void arena_prefork7(tsdn_t *tsdn, arena_t *arena);
 void arena_postfork_parent(tsdn_t *tsdn, arena_t *arena);
 void arena_postfork_child(tsdn_t *tsdn, arena_t *arena);
 

include/jemalloc/internal/background_thread_externs.h

@@ -6,6 +6,7 @@ extern malloc_mutex_t background_thread_lock;
 extern atomic_b_t background_thread_enabled_state;
 extern size_t n_background_threads;
 extern background_thread_info_t *background_thread_info;
+extern bool can_enable_background_thread;
 
 bool background_thread_create(tsd_t *tsd, unsigned arena_ind);
 bool background_threads_enable(tsd_t *tsd);

include/jemalloc/internal/background_thread_inlines.h

@@ -41,8 +41,9 @@ background_thread_indefinite_sleep(background_thread_info_t *info) {
 }
 
 JEMALLOC_ALWAYS_INLINE void
-arena_background_thread_inactivity_check(tsdn_t *tsdn, arena_t *arena) {
-	if (!background_thread_enabled()) {
+arena_background_thread_inactivity_check(tsdn_t *tsdn, arena_t *arena,
+    bool is_background_thread) {
+	if (!background_thread_enabled() || is_background_thread) {
 		return;
 	}
 	background_thread_info_t *info =

include/jemalloc/internal/base_externs.h

@@ -3,7 +3,7 @@
 
 base_t *b0get(void);
 base_t *base_new(tsdn_t *tsdn, unsigned ind, extent_hooks_t *extent_hooks);
-void base_delete(base_t *base);
+void base_delete(tsdn_t *tsdn, base_t *base);
 extent_hooks_t *base_extent_hooks_get(base_t *base);
 extent_hooks_t *base_extent_hooks_set(base_t *base,
     extent_hooks_t *extent_hooks);

include/jemalloc/internal/ctl.h

@@ -91,8 +91,7 @@ typedef struct ctl_arenas_s {
 
 int ctl_byname(tsd_t *tsd, const char *name, void *oldp, size_t *oldlenp,
     void *newp, size_t newlen);
-int ctl_nametomib(tsdn_t *tsdn, const char *name, size_t *mibp,
-    size_t *miblenp);
+int ctl_nametomib(tsd_t *tsd, const char *name, size_t *mibp, size_t *miblenp);
 
 int ctl_bymib(tsd_t *tsd, const size_t *mib, size_t miblen, void *oldp,
     size_t *oldlenp, void *newp, size_t newlen);

include/jemalloc/internal/jemalloc_internal_decls.h

@@ -22,6 +22,7 @@
 #    include <sys/uio.h>
 #  endif
 #  include <pthread.h>
+#  include <signal.h>
 #  ifdef JEMALLOC_OS_UNFAIR_LOCK
 #    include <os/lock.h>
 #  endif

include/jemalloc/internal/jemalloc_internal_defs.h.in

@@ -98,6 +98,9 @@
 /* Defined if pthread_atfork(3) is available. */
 #undef JEMALLOC_HAVE_PTHREAD_ATFORK
 
+/* Defined if pthread_setname_np(3) is available. */
+#undef JEMALLOC_HAVE_PTHREAD_SETNAME_NP
+
 /*
  * Defined if clock_gettime(CLOCK_MONOTONIC_COARSE, ...) is available.
  */

include/jemalloc/internal/jemalloc_internal_inlines_a.h

@@ -146,7 +146,10 @@ tcache_get(tsd_t *tsd) {
 }
 
 static inline void
-pre_reentrancy(tsd_t *tsd) {
+pre_reentrancy(tsd_t *tsd, arena_t *arena) {
+	/* arena is the current context.  Reentry from a0 is not allowed. */
+	assert(arena != arena_get(tsd_tsdn(tsd), 0, false));
+
 	bool fast = tsd_fast(tsd);
 	++*tsd_reentrancy_levelp_get(tsd);
 	if (fast) {

include/jemalloc/internal/tcache_externs.h

@@ -48,7 +48,7 @@ void tcache_arena_associate(tsdn_t *tsdn, tcache_t *tcache, arena_t *arena);
 void tcache_prefork(tsdn_t *tsdn);
 void tcache_postfork_parent(tsdn_t *tsdn);
 void tcache_postfork_child(tsdn_t *tsdn);
-void tcache_flush(void);
+void tcache_flush(tsd_t *tsd);
 bool tsd_tcache_data_init(tsd_t *tsd);
 bool tsd_tcache_enabled_data_init(tsd_t *tsd);
 

include/jemalloc/internal/tsd.h

@@ -99,9 +99,10 @@ enum {
 	tsd_state_nominal_slow = 1, /* Initialized but on slow path. */
 	/* the above 2 nominal states should be lower values. */
 	tsd_state_nominal_max = 1, /* used for comparison only. */
-	tsd_state_purgatory = 2,
-	tsd_state_reincarnated = 3,
-	tsd_state_uninitialized = 4
+	tsd_state_minimal_initialized = 2,
+	tsd_state_purgatory = 3,
+	tsd_state_reincarnated = 4,
+	tsd_state_uninitialized = 5
 };
 
 /* Manually limit tsd_state_t to a single byte. */
@@ -190,7 +191,8 @@ JEMALLOC_ALWAYS_INLINE t *						\
 tsd_##n##p_get(tsd_t *tsd) {						\
 	assert(tsd->state == tsd_state_nominal ||			\
 	    tsd->state == tsd_state_nominal_slow ||			\
-	    tsd->state == tsd_state_reincarnated);			\
+	    tsd->state == tsd_state_reincarnated ||			\
+	    tsd->state == tsd_state_minimal_initialized);		\
 	return tsd_##n##p_get_unsafe(tsd);				\
 }
 MALLOC_TSD
@@ -225,7 +227,8 @@ MALLOC_TSD
 #define O(n, t, nt)							\
 JEMALLOC_ALWAYS_INLINE void						\
 tsd_##n##_set(tsd_t *tsd, t val) {					\
-	assert(tsd->state != tsd_state_reincarnated);			\
+	assert(tsd->state != tsd_state_reincarnated &&			\
+	    tsd->state != tsd_state_minimal_initialized);		\
 	*tsd_##n##p_get(tsd) = val;					\
 }
 MALLOC_TSD
@@ -248,7 +251,7 @@ tsd_fast(tsd_t *tsd) {
 }
 
 JEMALLOC_ALWAYS_INLINE tsd_t *
-tsd_fetch_impl(bool init, bool internal) {
+tsd_fetch_impl(bool init, bool minimal) {
 	tsd_t *tsd = tsd_get(init);
 
 	if (!init && tsd_get_allocates() && tsd == NULL) {
@@ -257,19 +260,30 @@ tsd_fetch_impl(bool init, bool internal) {
 	assert(tsd != NULL);
 
 	if (unlikely(tsd->state != tsd_state_nominal)) {
-		return tsd_fetch_slow(tsd, internal);
+		return tsd_fetch_slow(tsd, minimal);
 	}
 	assert(tsd_fast(tsd));
 	tsd_assert_fast(tsd);
 
 	return tsd;
 }
 
+/* Get a minimal TSD that requires no cleanup.  See comments in free(). */
 JEMALLOC_ALWAYS_INLINE tsd_t *
-tsd_internal_fetch(void) {
+tsd_fetch_min(void) {
 	return tsd_fetch_impl(true, true);
 }
 
+/* For internal background threads use only. */
+JEMALLOC_ALWAYS_INLINE tsd_t *
+tsd_internal_fetch(void) {
+	tsd_t *tsd = tsd_fetch_min();
+	/* Use reincarnated state to prevent full initialization. */
+	tsd->state = tsd_state_reincarnated;
+
+	return tsd;
+}
+
 JEMALLOC_ALWAYS_INLINE tsd_t *
 tsd_fetch(void) {
 	return tsd_fetch_impl(true, false);