[PATCH] unify x86/x86-64 semaphore code

	  486, 586, Pentiums, and various instruction-set-compatible chips by

	  AMD, Cyrix, and others.

config SEMAPHORE_SLEEPERS

	bool

	default y

config MMU

	bool

	default y

 * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>

 */

#include <linux/config.h>

#include <linux/sched.h>

#include <linux/err.h>

#include <linux/init.h>

#include <asm/semaphore.h>

/*

 * Semaphores are implemented using a two-way counter:

 * The "count" variable is decremented for each process

 * that tries to acquire the semaphore, while the "sleeping"

 * variable is a count of such acquires.

 *

 * Notably, the inline "up()" and "down()" functions can

 * efficiently test if they need to do any extra work (up

 * needs to do something only if count was negative before

 * the increment operation.

 *

 * "sleeping" and the contention routine ordering is protected

 * by the spinlock in the semaphore's waitqueue head.

 *

 * Note that these functions are only called when there is

 * contention on the lock, and as such all this is the

 * "non-critical" part of the whole semaphore business. The

 * critical part is the inline stuff in <asm/semaphore.h>

 * where we want to avoid any extra jumps and calls.

 */

/*

 * Logic:

 *  - only on a boundary condition do we need to care. When we go

 *    from a negative count to a non-negative, we wake people up.

 *  - when we go from a non-negative count to a negative do we

 *    (a) synchronize with the "sleeper" count and (b) make sure

 *    that we're on the wakeup list before we synchronize so that

 *    we cannot lose wakeup events.

 */

static fastcall void __attribute_used__  __up(struct semaphore *sem)

{

	wake_up(&sem->wait);

}

static fastcall void __attribute_used__ __sched __down(struct semaphore * sem)

{

	struct task_struct *tsk = current;

	DECLARE_WAITQUEUE(wait, tsk);

	unsigned long flags;

	tsk->state = TASK_UNINTERRUPTIBLE;

	spin_lock_irqsave(&sem->wait.lock, flags);

	add_wait_queue_exclusive_locked(&sem->wait, &wait);

	sem->sleepers++;

	for (;;) {

		int sleepers = sem->sleepers;

		/*

		 * Add "everybody else" into it. They aren't

		 * playing, because we own the spinlock in

		 * the wait_queue_head.

		 */

		if (!atomic_add_negative(sleepers - 1, &sem->count)) {

			sem->sleepers = 0;

			break;

		}

		sem->sleepers = 1;	/* us - see -1 above */

		spin_unlock_irqrestore(&sem->wait.lock, flags);

		schedule();

		spin_lock_irqsave(&sem->wait.lock, flags);

		tsk->state = TASK_UNINTERRUPTIBLE;

	}

	remove_wait_queue_locked(&sem->wait, &wait);

	wake_up_locked(&sem->wait);

	spin_unlock_irqrestore(&sem->wait.lock, flags);

	tsk->state = TASK_RUNNING;

}

static fastcall int __attribute_used__ __sched __down_interruptible(struct semaphore * sem)

{

	int retval = 0;

	struct task_struct *tsk = current;

	DECLARE_WAITQUEUE(wait, tsk);

	unsigned long flags;

	tsk->state = TASK_INTERRUPTIBLE;

	spin_lock_irqsave(&sem->wait.lock, flags);

	add_wait_queue_exclusive_locked(&sem->wait, &wait);

	sem->sleepers++;

	for (;;) {

		int sleepers = sem->sleepers;

		/*

		 * With signals pending, this turns into

		 * the trylock failure case - we won't be

		 * sleeping, and we* can't get the lock as

		 * it has contention. Just correct the count

		 * and exit.

		 */

		if (signal_pending(current)) {

			retval = -EINTR;

			sem->sleepers = 0;

			atomic_add(sleepers, &sem->count);

			break;

		}

		/*

		 * Add "everybody else" into it. They aren't

		 * playing, because we own the spinlock in

		 * wait_queue_head. The "-1" is because we're

		 * still hoping to get the semaphore.

		 */

		if (!atomic_add_negative(sleepers - 1, &sem->count)) {

			sem->sleepers = 0;

			break;

		}

		sem->sleepers = 1;	/* us - see -1 above */

		spin_unlock_irqrestore(&sem->wait.lock, flags);

		schedule();

		spin_lock_irqsave(&sem->wait.lock, flags);

		tsk->state = TASK_INTERRUPTIBLE;

	}

	remove_wait_queue_locked(&sem->wait, &wait);

	wake_up_locked(&sem->wait);

	spin_unlock_irqrestore(&sem->wait.lock, flags);

	tsk->state = TASK_RUNNING;

	return retval;

}

/*

 * Trylock failed - make sure we correct for

 * having decremented the count.

 *

 * We could have done the trylock with a

 * single "cmpxchg" without failure cases,

 * but then it wouldn't work on a 386.

 */

static fastcall int __attribute_used__ __down_trylock(struct semaphore * sem)

{

	int sleepers;

	unsigned long flags;

	spin_lock_irqsave(&sem->wait.lock, flags);

	sleepers = sem->sleepers + 1;

	sem->sleepers = 0;

	/*

	 * Add "everybody else" and us into it. They aren't

	 * playing, because we own the spinlock in the

	 * wait_queue_head.

	 */

	if (!atomic_add_negative(sleepers, &sem->count)) {

		wake_up_locked(&sem->wait);

	}

	spin_unlock_irqrestore(&sem->wait.lock, flags);

	return 1;

}

/*

 * The semaphore operations have a special calling sequence that

 * allow us to do a simpler in-line version of them. These routines

	bool

	default n

config SEMAPHORE_SLEEPERS

	bool

	default y

config TOP_ADDR

 	hex

 	default 0xc0000000 if !HOST_2G_2G

	bool

	default y

config SEMAPHORE_SLEEPERS

	bool

	default y

config TOP_ADDR

 	hex

	default 0x80000000

#XXX: why into lib-y?

lib-y = bitops.o bugs.o csum-partial.o delay.o fault.o mem.o memcpy.o \

	ptrace.o ptrace_user.o semaphore.o sigcontext.o signal.o stub.o \

	ptrace.o ptrace_user.o sigcontext.o signal.o stub.o \

	stub_segv.o syscalls.o syscall_table.o sysrq.o thunk.o

obj-y := ksyms.o

USER_OBJS := ptrace_user.o sigcontext.o

SYMLINKS = bitops.c csum-copy.S csum-partial.c csum-wrappers.c memcpy.S \

	semaphore.c thunk.S module.c

	thunk.S module.c

include arch/um/scripts/Makefile.rules

csum-partial.c-dir = lib

csum-wrappers.c-dir = lib

memcpy.S-dir = lib

semaphore.c-dir = kernel

thunk.S-dir = lib

module.c-dir = kernel