[patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[Ingo Molnar]

From: Arjan van de Ven <arjan@infradead.org>

add the i386 version of mutex.h, optimized in assembly.

Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

----

 include/asm-i386/mutex.h |  136 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 136 insertions(+)

Index: linux/include/asm-i386/mutex.h
===================================================================
--- /dev/null
+++ linux/include/asm-i386/mutex.h
@@ -0,0 +1,136 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   decl (%%eax)	\n"			\
+			"   js 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+			     int fastcall (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value
+ * to 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   incl (%%eax)	\n"			\
+			"   jle 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	/*
+	 * We have two variants here. The cmpxchg based one is the best one
+	 * because it never induce a false contention state.  It is included
+	 * here because architectures using the inc/dec algorithms over the
+	 * xchg ones are much more likely to support cmpxchg natively.
+	 *
+	 * If not we fall back to the spinlock based variant - that is
+	 * just as efficient (and simpler) as a 'destructive' probing of
+	 * the mutex state would be.
+	 */
+#ifdef __HAVE_ARCH_CMPXCHG
+	if (likely(atomic_cmpxchg(count, 1, 0)) == 1)
+		return 1;
+	return 0;
+#else
+	return fail_fn(count);
+#endif
+}
+
+#endif

Re: [patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[Nick Piggin]

Ingo Molnar wrote:
> From: Arjan van de Ven <arjan@infradead.org>
> 
> add the i386 version of mutex.h, optimized in assembly.
> 

> +static inline int
> +__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
> +{
> +	/*
> +	 * We have two variants here. The cmpxchg based one is the best one
> +	 * because it never induce a false contention state.  It is included
> +	 * here because architectures using the inc/dec algorithms over the
> +	 * xchg ones are much more likely to support cmpxchg natively.
> +	 *
> +	 * If not we fall back to the spinlock based variant - that is
> +	 * just as efficient (and simpler) as a 'destructive' probing of
> +	 * the mutex state would be.
> +	 */
> +#ifdef __HAVE_ARCH_CMPXCHG
> +	if (likely(atomic_cmpxchg(count, 1, 0)) == 1)
> +		return 1;
> +	return 0;
> +#else
> +	return fail_fn(count);
> +#endif
> +}

asm-i386 version I think really should just use atomic_cmpxchg unconditionally,
because otherwise an i386 compatible kernel will not use cmpxchg even when
running on 486+ (not sure how important that is these days, but still...).

-- 
SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 

Re: [patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[Ingo Molnar]

* Nick Piggin <nickpiggin@yahoo.com.au> wrote:

> >+#ifdef __HAVE_ARCH_CMPXCHG
> >+	if (likely(atomic_cmpxchg(count, 1, 0)) == 1)
> >+		return 1;
> >+	return 0;
> >+#else
> >+	return fail_fn(count);
> >+#endif
> >+}
> 
> asm-i386 version I think really should just use atomic_cmpxchg 
> unconditionally, because otherwise an i386 compatible kernel will not 
> use cmpxchg even when running on 486+ (not sure how important that is 
> these days, but still...).

yeah. This code predates the generic-atomic-cmpxchg code. (Feel free to 
review all __HAVE_ARCH_CMPXCHG users after this goes in, and remove 
__HAVE_ARCH_CMPXCHG altogether with a CONFIG_ flag.)

but ... the spinlock based variant is quite likely faster (on i386) than 
generic-cmpxchg. Couldnt we introduce a new API, something along the 
lines of:

	atomic_cmpxchg_lock(&count, &lock->wait_lock);

and if the cmpxchg fails, it would hold the spinlock? The cmpxchg 
semantics could be guaranteed by the spinlock. (because it is 'global' 
for that particular critical section)

	Ingo

[patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[Ingo Molnar]

From: Arjan van de Ven <arjan@infradead.org>

add the i386 version of mutex.h, optimized in assembly.

Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

----

 include/asm-i386/mutex.h |  136 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 136 insertions(+)

Index: linux/include/asm-i386/mutex.h
===================================================================
--- /dev/null
+++ linux/include/asm-i386/mutex.h
@@ -0,0 +1,136 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   decl (%%eax)	\n"			\
+			"   js 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+			     int fastcall (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value
+ * to 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   incl (%%eax)	\n"			\
+			"   jle 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	/*
+	 * We have two variants here. The cmpxchg based one is the best one
+	 * because it never induce a false contention state.  It is included
+	 * here because architectures using the inc/dec algorithms over the
+	 * xchg ones are much more likely to support cmpxchg natively.
+	 *
+	 * If not we fall back to the spinlock based variant - that is
+	 * just as efficient (and simpler) as a 'destructive' probing of
+	 * the mutex state would be.
+	 */
+#ifdef __HAVE_ARCH_CMPXCHG
+	if (likely(atomic_cmpxchg(count, 1, 0)) == 1)
+		return 1;
+	return 0;
+#else
+	return fail_fn(count);
+#endif
+}
+
+#endif

[patch 04/19] mutex subsystem, add include/asm-i386/mutex.h

[Ingo Molnar, Arjan van de Ven]

add the i386 version of mutex.h, optimized in assembly.

Signed-off-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

----

 include/asm-i386/mutex.h |  136 +++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 136 insertions(+)

Index: linux/include/asm-i386/mutex.h
===================================================================
--- /dev/null
+++ linux/include/asm-i386/mutex.h
@@ -0,0 +1,136 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   decl (%%eax)	\n"			\
+			"   js 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+			     int fastcall (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value
+ * to 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)				\
+do {									\
+	unsigned int dummy;						\
+									\
+	typecheck(atomic_t *, count);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   incl (%%eax)	\n"			\
+			"   jle 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=a" (dummy)						\
+		: "a" (count)						\
+		: "memory", "ecx", "edx");				\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	/*
+	 * We have two variants here. The cmpxchg based one is the best one
+	 * because it never induce a false contention state.  It is included
+	 * here because architectures using the inc/dec algorithms over the
+	 * xchg ones are much more likely to support cmpxchg natively.
+	 *
+	 * If not we fall back to the spinlock based variant - that is
+	 * just as efficient (and simpler) as a 'destructive' probing of
+	 * the mutex state would be.
+	 */
+#ifdef __HAVE_ARCH_CMPXCHG
+	if (likely(atomic_cmpxchg(count, 1, 0)) == 1)
+		return 1;
+	return 0;
+#else
+	return fail_fn(count);
+#endif
+}
+
+#endif