[PATCH] avr32 architecture

This adds support for the Atmel AVR32 architecture as well as the AT32AP7000
CPU and the AT32STK1000 development board.

AVR32 is a new high-performance 32-bit RISC microprocessor core, designed for
cost-sensitive embedded applications, with particular emphasis on low power
consumption and high code density.  The AVR32 architecture is not binary
compatible with earlier 8-bit AVR architectures.

The AVR32 architecture, including the instruction set, is described by the
AVR32 Architecture Manual, available from

http://www.atmel.com/dyn/resources/prod_documents/doc32000.pdf

The Atmel AT32AP7000 is the first CPU implementing the AVR32 architecture.  It
features a 7-stage pipeline, 16KB instruction and data caches and a full
Memory Management Unit.  It also comes with a large set of integrated
peripherals, many of which are shared with the AT91 ARM-based controllers from
Atmel.

Full data sheet is available from

http://www.atmel.com/dyn/resources/prod_documents/doc32003.pdf

while the CPU core implementation including caches and MMU is documented by
the AVR32 AP Technical Reference, available from

http://www.atmel.com/dyn/resources/prod_documents/doc32001.pdf

Information about the AT32STK1000 development board can be found at

http://www.atmel.com/dyn/products/tools_card.asp?tool_id=3918

including a BSP CD image with an earlier version of this patch, development
tools (binaries and source/patches) and a root filesystem image suitable for
booting from SD card.

Alternatively, there's a preliminary "getting started" guide available at
http://avr32linux.org/twiki/bin/view/Main/GettingStarted which provides links
to the sources and patches you will need in order to set up a cross-compiling
environment for avr32-linux.

This patch, as well as the other patches included with the BSP and the
toolchain patches, is actively supported by Atmel Corporation.

[dmccr@us.ibm.com: Fix more pxx_page macro locations]
[bunk@stusta.de: fix `make defconfig']
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Dave McCracken <dmccr@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/avr32/kernel/semaphore.c b/arch/avr32/kernel/semaphore.c
new file mode 100644
index 0000000..1e2705a
--- /dev/null
+++ b/arch/avr32/kernel/semaphore.c
@@ -0,0 +1,148 @@
+/*
+ * AVR32 sempahore implementation.
+ *
+ * Copyright (C) 2004-2006 Atmel Corporation
+ *
+ * Based on linux/arch/i386/kernel/semaphore.c
+ *  Copyright (C) 1999 Linus Torvalds
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+
+#include <asm/semaphore.h>
+#include <asm/atomic.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.
+ */
+
+void __up(struct semaphore *sem)
+{
+	wake_up(&sem->wait);
+}
+EXPORT_SYMBOL(__up);
+
+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_return(sleepers - 1, &sem->count) >= 0) {
+                        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;
+}
+EXPORT_SYMBOL(__down);
+
+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
+                 * the wait_queue_head.
+                 */
+                if (atomic_add_return(sleepers - 1, &sem->count) >= 0) {
+                        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;
+}
+EXPORT_SYMBOL(__down_interruptible);