mutex subsystem, add include/asm-arm/mutex.h

Index: linux/include/asm-arm/mutex.h
===================================================================
@@ -0,0 +1,102 @@
+/*
+ * include/asm-arm/mutex.h
+ *
+ * ARM optimized mutex locking primitives
+ *
+ * Please look into asm-generic/mutex-xchg.h for a formal definition.
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+#if __LINUX_ARM_ARCH__ < 6
+/* On pre-ARMv6 hardware the swp based implementation is the most efficient. */
+# include <asm-generic/mutex-xchg.h>
+#else
+
+/*
+ * Attempting to lock a mutex on ARMv6+ can be done with a bastardized
+ * atomic decrement (it is not a reliable atomic decrement but it satisfies
+ * the defined semantics for our purpose, while being smaller and faster
+ * than a real atomic decrement or atomic swap.  The idea is to attempt
+ * decrementing the lock value only once.  If once decremented it isn't zero,
+ * or if its store-back fails due to a dispute on the exclusive store, we
+ * simply bail out immediately through the slow path where the lock will be
+ * reattempted until it succeeds.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)				\
+do {									\
+	/* type-check the function too: */				\
+	void fastcall (*__tmp)(atomic_t *) = fail_fn;			\
+	int __ex_flag, __res;						\
+									\
+	(void)__tmp;							\
+	typecheck(atomic_t *, count);					\
+									\
+	__asm__ (							\
+	"ldrex	%0, [%2]\n\t"						\
+	"sub	%0, %0, #1\n\t"						\
+	"strex	%1, %0, [%2]"						\
+	: "=&r" (__res), "=&r" (__ex_flag)				\
+	: "r" (&(count)->counter)					\
+	: "cc","memory" );						\
+	__res |= __ex_flag;						\
+	if (unlikely(__res != 0))					\
+		fail_fn(count);						\
+} while (0)
+
+#define __mutex_fastpath_lock_retval(count, fail_fn)			\
+({									\
+	/* type-check the function too: */				\
+	int fastcall (*__tmp)(atomic_t *) = fail_fn;			\
+	int __ex_flag, __res;						\
+									\
+	(void)__tmp;							\
+	typecheck(atomic_t *, count);					\
+									\
+	__asm__ (							\
+	"ldrex	%0, [%2]\n\t"						\
+	"sub	%0, %0, #1\n\t"						\
+	"strex	%1, %0, [%2]"						\
+	: "=&r" (__res), "=&r" (__ex_flag)				\
+	: "r" (&(count)->counter)					\
+	: "cc","memory" );						\
+	__res |= __ex_flag;						\
+	if (unlikely(__res != 0))					\
+		__res = fail_fn(count);					\
+	__res;								\
+})
+
+/*
+ * Same trick is used for the unlock fast path. However the original value,
+ * rather than the result, is used to test for success in order to have
+ * better generated assembly.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)				\
+do {									\
+	/* type-check the function too: */				\
+	void fastcall (*__tmp)(atomic_t *) = fail_fn;			\
+	int __ex_flag, __res, __orig;					\
+									\
+	(void)__tmp;							\
+	typecheck(atomic_t *, count);					\
+									\
+	__asm__ (							\
+	"ldrex	%0, [%3]\n\t"						\
+	"add	%1, %0, #1\n\t"						\
+	"strex	%2, %1, [%3]"						\
+	: "=&r" (__orig), "=&r" (__res), "=&r" (__ex_flag)		\
+	: "r" (&(count)->counter)					\
+	: "cc","memory" );						\
+	__orig |= __ex_flag;						\
+	if (unlikely(__orig != 0))					\
+		fail_fn(count);						\
+} while (0)
+
+/*
+ * If the unlock was done on a contended lock, or if the unlock simply fails
+ * then the mutex remains locked.
+ */
+#define __mutex_slowpath_needs_to_unlock()	1
+
+#endif
+#endif