Optimized ARM RWSEM algorithm

RWSEM implementation for ARM using atomic functions.
Heavily based on arch/sh/include/asm/rwsem.h

Signed-off-by: Ashwin Chaugule <ashwinc@codeaurora.org>

arch/arm/Kconfig

@@ -115,10 +115,9 @@ config GENERIC_LOCKBREAK
 
 config RWSEM_GENERIC_SPINLOCK
 	bool
-	default y
 
 config RWSEM_XCHGADD_ALGORITHM
-	bool
+	def_bool y
 
 config ARCH_HAS_ILOG2_U32
 	bool

arch/arm/include/asm/rwsem.h

@@ -0,0 +1,185 @@
+/* rwsem.h: R/W semaphores implemented using ARM atomic functions.
+ *
+ * Copyright (c) 2010, Code Aurora Forum. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+#ifndef _ASM_ARM_RWSEM_H
+#define _ASM_ARM_RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
+#endif
+
+#ifdef __KERNEL__
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+
+/*
+ * the semaphore definition
+ */
+struct rw_semaphore {
+	long		count;
+#define RWSEM_UNLOCKED_VALUE		0x00000000
+#define RWSEM_ACTIVE_BIAS		0x00000001
+#define RWSEM_ACTIVE_MASK		0x0000ffff
+#define RWSEM_WAITING_BIAS		(-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+	spinlock_t		wait_lock;
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+#define __RWSEM_INITIALIZER(name) \
+	{ RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
+	  LIST_HEAD_INIT((name).wait_list) \
+	  __RWSEM_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(name)		\
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+			 struct lock_class_key *key);
+
+#define init_rwsem(sem)				\
+do {						\
+	static struct lock_class_key __key;	\
+						\
+	__init_rwsem((sem), #sem, &__key);	\
+} while (0)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (atomic_inc_return((atomic_t *)(&sem->count)) < 0)
+		rwsem_down_read_failed(sem);
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	while ((tmp = sem->count) >= 0) {
+		if (tmp == cmpxchg(&sem->count, tmp,
+				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = atomic_add_return(RWSEM_ACTIVE_WRITE_BIAS,
+				(atomic_t *)(&sem->count));
+	if (tmp != RWSEM_ACTIVE_WRITE_BIAS)
+		rwsem_down_write_failed(sem);
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
+		      RWSEM_ACTIVE_WRITE_BIAS);
+	return tmp == RWSEM_UNLOCKED_VALUE;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = atomic_dec_return((atomic_t *)(&sem->count));
+	if (tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	if (atomic_sub_return(RWSEM_ACTIVE_WRITE_BIAS,
+			      (atomic_t *)(&sem->count)) < 0)
+		rwsem_wake(sem);
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+	atomic_add(delta, (atomic_t *)(&sem->count));
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	int tmp;
+
+	tmp = atomic_add_return(-RWSEM_WAITING_BIAS, (atomic_t *)(&sem->count));
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
+
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	__down_write(sem);
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+	return atomic_add_return(delta, (atomic_t *)(&sem->count));
+}
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return (sem->count != 0);
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_ARM_RWSEM_H */