[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/include/asm-avr32/io.h b/include/asm-avr32/io.h
new file mode 100644
index 0000000..2fc8f11
--- /dev/null
+++ b/include/asm-avr32/io.h
@@ -0,0 +1,253 @@
+#ifndef __ASM_AVR32_IO_H
+#define __ASM_AVR32_IO_H
+
+#include <linux/string.h>
+
+#ifdef __KERNEL__
+
+#include <asm/addrspace.h>
+#include <asm/byteorder.h>
+
+/* virt_to_phys will only work when address is in P1 or P2 */
+static __inline__ unsigned long virt_to_phys(volatile void *address)
+{
+	return PHYSADDR(address);
+}
+
+static __inline__ void * phys_to_virt(unsigned long address)
+{
+	return (void *)P1SEGADDR(address);
+}
+
+#define cached_to_phys(addr)	((unsigned long)PHYSADDR(addr))
+#define uncached_to_phys(addr)	((unsigned long)PHYSADDR(addr))
+#define phys_to_cached(addr)	((void *)P1SEGADDR(addr))
+#define phys_to_uncached(addr)	((void *)P2SEGADDR(addr))
+
+/*
+ * Generic IO read/write.  These perform native-endian accesses.  Note
+ * that some architectures will want to re-define __raw_{read,write}w.
+ */
+extern void __raw_writesb(unsigned int addr, const void *data, int bytelen);
+extern void __raw_writesw(unsigned int addr, const void *data, int wordlen);
+extern void __raw_writesl(unsigned int addr, const void *data, int longlen);
+
+extern void __raw_readsb(unsigned int addr, void *data, int bytelen);
+extern void __raw_readsw(unsigned int addr, void *data, int wordlen);
+extern void __raw_readsl(unsigned int addr, void *data, int longlen);
+
+static inline void writeb(unsigned char b, volatile void __iomem *addr)
+{
+	*(volatile unsigned char __force *)addr = b;
+}
+static inline void writew(unsigned short b, volatile void __iomem *addr)
+{
+	*(volatile unsigned short __force *)addr = b;
+}
+static inline void writel(unsigned int b, volatile void __iomem *addr)
+{
+	*(volatile unsigned int __force *)addr = b;
+}
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+
+static inline unsigned char readb(const volatile void __iomem *addr)
+{
+	return *(const volatile unsigned char __force *)addr;
+}
+static inline unsigned short readw(const volatile void __iomem *addr)
+{
+	return *(const volatile unsigned short __force *)addr;
+}
+static inline unsigned int readl(const volatile void __iomem *addr)
+{
+	return *(const volatile unsigned int __force *)addr;
+}
+#define __raw_readb readb
+#define __raw_readw readw
+#define __raw_readl readl
+
+#define writesb(p, d, l)	__raw_writesb((unsigned int)p, d, l)
+#define writesw(p, d, l)	__raw_writesw((unsigned int)p, d, l)
+#define writesl(p, d, l)	__raw_writesl((unsigned int)p, d, l)
+
+#define readsb(p, d, l)		__raw_readsb((unsigned int)p, d, l)
+#define readsw(p, d, l)		__raw_readsw((unsigned int)p, d, l)
+#define readsl(p, d, l)		__raw_readsl((unsigned int)p, d, l)
+
+/*
+ * These two are only here because ALSA _thinks_ it needs them...
+ */
+static inline void memcpy_fromio(void * to, const volatile void __iomem *from,
+				 unsigned long count)
+{
+	char *p = to;
+	while (count) {
+		count--;
+		*p = readb(from);
+		p++;
+		from++;
+	}
+}
+
+static inline void  memcpy_toio(volatile void __iomem *to, const void * from,
+				unsigned long count)
+{
+	const char *p = from;
+	while (count) {
+		count--;
+		writeb(*p, to);
+		p++;
+		to++;
+	}
+}
+
+static inline void memset_io(volatile void __iomem *addr, unsigned char val,
+			     unsigned long count)
+{
+	memset((void __force *)addr, val, count);
+}
+
+/*
+ * Bad read/write accesses...
+ */
+extern void __readwrite_bug(const char *fn);
+
+#define IO_SPACE_LIMIT	0xffffffff
+
+/* Convert I/O port address to virtual address */
+#define __io(p)		((void __iomem *)phys_to_uncached(p))
+
+/*
+ *  IO port access primitives
+ *  -------------------------
+ *
+ * The AVR32 doesn't have special IO access instructions; all IO is memory
+ * mapped. Note that these are defined to perform little endian accesses
+ * only. Their primary purpose is to access PCI and ISA peripherals.
+ *
+ * Note that for a big endian machine, this implies that the following
+ * big endian mode connectivity is in place.
+ *
+ * The machine specific io.h include defines __io to translate an "IO"
+ * address to a memory address.
+ *
+ * Note that we prevent GCC re-ordering or caching values in expressions
+ * by introducing sequence points into the in*() definitions.  Note that
+ * __raw_* do not guarantee this behaviour.
+ *
+ * The {in,out}[bwl] macros are for emulating x86-style PCI/ISA IO space.
+ */
+#define outb(v, p)		__raw_writeb(v, __io(p))
+#define outw(v, p)		__raw_writew(cpu_to_le16(v), __io(p))
+#define outl(v, p)		__raw_writel(cpu_to_le32(v), __io(p))
+
+#define inb(p)			__raw_readb(__io(p))
+#define inw(p)			le16_to_cpu(__raw_readw(__io(p)))
+#define inl(p)			le32_to_cpu(__raw_readl(__io(p)))
+
+static inline void __outsb(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		outb(*(u8 *)addr, port);
+		addr++;
+	}
+}
+
+static inline void __insb(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		*(u8 *)addr = inb(port);
+		addr++;
+	}
+}
+
+static inline void __outsw(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		outw(*(u16 *)addr, port);
+		addr += 2;
+	}
+}
+
+static inline void __insw(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		*(u16 *)addr = inw(port);
+		addr += 2;
+	}
+}
+
+static inline void __outsl(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		outl(*(u32 *)addr, port);
+		addr += 4;
+	}
+}
+
+static inline void __insl(unsigned long port, void *addr, unsigned int count)
+{
+	while (count--) {
+		*(u32 *)addr = inl(port);
+		addr += 4;
+	}
+}
+
+#define outsb(port, addr, count)	__outsb(port, addr, count)
+#define insb(port, addr, count)		__insb(port, addr, count)
+#define outsw(port, addr, count)	__outsw(port, addr, count)
+#define insw(port, addr, count)		__insw(port, addr, count)
+#define outsl(port, addr, count)	__outsl(port, addr, count)
+#define insl(port, addr, count)		__insl(port, addr, count)
+
+extern void __iomem *__ioremap(unsigned long offset, size_t size,
+			       unsigned long flags);
+extern void __iounmap(void __iomem *addr);
+
+/*
+ * ioremap	-   map bus memory into CPU space
+ * @offset	bus address of the memory
+ * @size	size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to make
+ * bus memory CPU accessible via the readb/.../writel functions and
+ * the other mmio helpers. The returned address is not guaranteed to
+ * be usable directly as a virtual address.
+ */
+#define ioremap(offset, size)			\
+	__ioremap((offset), (size), 0)
+
+#define iounmap(addr)				\
+	__iounmap(addr)
+
+#define cached(addr) P1SEGADDR(addr)
+#define uncached(addr) P2SEGADDR(addr)
+
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+#define page_to_bus page_to_phys
+#define bus_to_page phys_to_page
+
+#define dma_cache_wback_inv(_start, _size)	\
+	flush_dcache_region(_start, _size)
+#define dma_cache_inv(_start, _size)		\
+	invalidate_dcache_region(_start, _size)
+#define dma_cache_wback(_start, _size)		\
+	clean_dcache_region(_start, _size)
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)    __va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)   p
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_AVR32_IO_H */