Add/use adaptive spinning.

Add spin_t and spin_{init,adaptive}(), which provide a simple
abstraction for adaptive spinning.

Adaptively spin during busy waits in bootstrapping and rtree node
initialization.

Makefile.in

@@ -98,6 +98,7 @@ C_SRCS := $(srcroot)src/jemalloc.c \
 	$(srcroot)src/prof.c \
 	$(srcroot)src/rtree.c \
 	$(srcroot)src/stats.c \
+	$(srcroot)src/spin.c \
 	$(srcroot)src/tcache.c \
 	$(srcroot)src/ticker.c \
 	$(srcroot)src/tsd.c \

include/jemalloc/internal/jemalloc_internal.h.in

@@ -346,6 +346,7 @@ typedef unsigned szind_t;
 #include "jemalloc/internal/nstime.h"
 #include "jemalloc/internal/util.h"
 #include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/spin.h"
 #include "jemalloc/internal/prng.h"
 #include "jemalloc/internal/ticker.h"
 #include "jemalloc/internal/ckh.h"
@@ -375,6 +376,7 @@ typedef unsigned szind_t;
 #include "jemalloc/internal/nstime.h"
 #include "jemalloc/internal/util.h"
 #include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/spin.h"
 #include "jemalloc/internal/prng.h"
 #include "jemalloc/internal/ticker.h"
 #include "jemalloc/internal/ckh.h"
@@ -465,6 +467,7 @@ void	jemalloc_postfork_child(void);
 #include "jemalloc/internal/nstime.h"
 #include "jemalloc/internal/util.h"
 #include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/spin.h"
 #include "jemalloc/internal/prng.h"
 #include "jemalloc/internal/ticker.h"
 #include "jemalloc/internal/ckh.h"
@@ -494,6 +497,7 @@ void	jemalloc_postfork_child(void);
 #include "jemalloc/internal/nstime.h"
 #include "jemalloc/internal/util.h"
 #include "jemalloc/internal/atomic.h"
+#include "jemalloc/internal/spin.h"
 #include "jemalloc/internal/prng.h"
 #include "jemalloc/internal/ticker.h"
 #include "jemalloc/internal/ckh.h"

include/jemalloc/internal/spin.h

@@ -0,0 +1,51 @@
+/******************************************************************************/
+#ifdef JEMALLOC_H_TYPES
+
+typedef struct spin_s spin_t;
+
+#endif /* JEMALLOC_H_TYPES */
+/******************************************************************************/
+#ifdef JEMALLOC_H_STRUCTS
+
+struct spin_s {
+	unsigned iteration;
+};
+
+#endif /* JEMALLOC_H_STRUCTS */
+/******************************************************************************/
+#ifdef JEMALLOC_H_EXTERNS
+
+#endif /* JEMALLOC_H_EXTERNS */
+/******************************************************************************/
+#ifdef JEMALLOC_H_INLINES
+
+#ifndef JEMALLOC_ENABLE_INLINE
+void	spin_init(spin_t *spin);
+void	spin_adaptive(spin_t *spin);
+#endif
+
+#if (defined(JEMALLOC_ENABLE_INLINE) || defined(JEMALLOC_SPIN_C_))
+JEMALLOC_INLINE void
+spin_init(spin_t *spin)
+{
+
+	spin->iteration = 0;
+}
+
+JEMALLOC_INLINE void
+spin_adaptive(spin_t *spin)
+{
+	volatile uint64_t i;
+
+	for (i = 0; i < (KQU(1) << spin->iteration); i++)
+		CPU_SPINWAIT;
+
+	if (spin->iteration < 63)
+		spin->iteration++;
+}
+
+#endif
+
+#endif /* JEMALLOC_H_INLINES */
+/******************************************************************************/
+

src/jemalloc.c

@@ -1142,10 +1142,13 @@ malloc_init_hard_needed(void)
 	}
 #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);
-			CPU_SPINWAIT;
+			spin_adaptive(&spinner);
 			malloc_mutex_lock(TSDN_NULL, &init_lock);
 		} while (!malloc_initialized());
 		return (false);

src/rtree.c

@@ -136,12 +136,15 @@ rtree_node_init(tsdn_t *tsdn, rtree_t *rtree, unsigned level,
 	rtree_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 {
-			CPU_SPINWAIT;
+			spin_adaptive(&spinner);
 			node = atomic_read_p((void **)elmp);
 		} while (node == RTREE_NODE_INITIALIZING);
 	} else {

src/spin.c

@@ -0,0 +1,2 @@
+#define	JEMALLOC_SPIN_C_
+#include "jemalloc/internal/jemalloc_internal.h"