[PATCH] unify x86/x86-64 semaphore code

This patch moves the common code in x86 and x86-64's semaphore.c into a
single file in lib/semaphore-sleepers.c.  The arch specific asm stubs are
left in the arch tree (in semaphore.c for i386 and in the asm for x86-64).
There should be no changes in code/functionality with this patch.

Signed-off-by: Benjamin LaHaise <benjamin.c.lahaise@intel.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Jeff Dike <jdike@addtoit.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 178 insertions, 0 deletions

diff --git a/lib/Makefile b/lib/Makefile
index 52f83380f704..3e2bd0df23bb 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -18,6 +18,7 @@ endif
 
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
+lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
 lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
diff --git a/lib/semaphore-sleepers.c b/lib/semaphore-sleepers.c
new file mode 100644
index 000000000000..4d5f18889fa5
--- /dev/null
+++ b/lib/semaphore-sleepers.c
@@ -0,0 +1,177 @@
+/*
+ * i386 and x86-64 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ *
+ * 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.
+ */
+
+fastcall void __up(struct semaphore *sem)
+{
+        wake_up(&sem->wait);
+}
+
+fastcall void __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;
+}
+
+fastcall int __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.
+ */
+fastcall int __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;
+}