From 9737685943fedf5796ff157306ca70aaa25750c7 Mon Sep 17 00:00:00 2001
From: Jason Evans <jasone@canonware.com>
Date: Thu, 13 Oct 2016 14:47:50 -0700
Subject: [PATCH] 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                                   |  1 +
 .../jemalloc/internal/jemalloc_internal.h.in  |  4 ++
 include/jemalloc/internal/spin.h              | 51 +++++++++++++++++++
 src/jemalloc.c                                |  5 +-
 src/rtree.c                                   |  5 +-
 src/spin.c                                    |  2 +
 6 files changed, 66 insertions(+), 2 deletions(-)
 create mode 100644 include/jemalloc/internal/spin.h
 create mode 100644 src/spin.c

diff --git a/Makefile.in b/Makefile.in
index 8789c451..a2d5594b 100644
--- a/Makefile.in
+++ b/Makefile.in
@@ -101,6 +101,7 @@ C_SRCS := $(srcroot)src/jemalloc.c \
 	$(srcroot)src/quarantine.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 \
diff --git a/include/jemalloc/internal/jemalloc_internal.h.in b/include/jemalloc/internal/jemalloc_internal.h.in
index 9708df99..d644cea3 100644
--- a/include/jemalloc/internal/jemalloc_internal.h.in
+++ b/include/jemalloc/internal/jemalloc_internal.h.in
@@ -369,6 +369,7 @@ typedef unsigned szind_t;
 #include "jemalloc/internal/valgrind.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"
@@ -401,6 +402,7 @@ typedef unsigned szind_t;
 #include "jemalloc/internal/valgrind.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"
@@ -502,6 +504,7 @@ void	jemalloc_postfork_child(void);
 #include "jemalloc/internal/valgrind.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"
@@ -534,6 +537,7 @@ void	jemalloc_postfork_child(void);
 #include "jemalloc/internal/valgrind.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"
diff --git a/include/jemalloc/internal/spin.h b/include/jemalloc/internal/spin.h
new file mode 100644
index 00000000..9ef5ceb9
--- /dev/null
+++ b/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 */
+/******************************************************************************/
+
diff --git a/src/jemalloc.c b/src/jemalloc.c
index 8731934f..aec2a5eb 100644
--- a/src/jemalloc.c
+++ b/src/jemalloc.c
@@ -1283,10 +1283,13 @@ 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);
diff --git a/src/rtree.c b/src/rtree.c
index 3166b45f..5590034b 100644
--- a/src/rtree.c
+++ b/src/rtree.c
@@ -96,12 +96,15 @@ 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 {
-			CPU_SPINWAIT;
+			spin_adaptive(&spinner);
 			node = atomic_read_p((void **)elmp);
 		} while (node == RTREE_NODE_INITIALIZING);
 	} else {
diff --git a/src/spin.c b/src/spin.c
new file mode 100644
index 00000000..5242d95a
--- /dev/null
+++ b/src/spin.c
@@ -0,0 +1,2 @@
+#define	JEMALLOC_SPIN_C_
+#include "jemalloc/internal/jemalloc_internal.h"