[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>

1 files changed, 154 insertions, 0 deletions

diff --git a/arch/avr32/lib/findbit.S b/arch/avr32/lib/findbit.S
new file mode 100644
index 000000000000..2b4856f4bf7c
--- /dev/null
+++ b/arch/avr32/lib/findbit.S
@@ -0,0 +1,154 @@
+/*
+ * Copyright (C) 2006 Atmel Corporation
+ *
+ * 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/linkage.h>
+
+        .text
+        /*
+         * unsigned long find_first_zero_bit(const unsigned long *addr,
+         *                                   unsigned long size)
+         */
+ENTRY(find_first_zero_bit)
+        cp.w    r11, 0
+        reteq   r11
+        mov     r9, r11
+1:      ld.w    r8, r12[0]
+        com     r8
+        brne    .L_found
+        sub     r12, -4
+        sub     r9, 32
+        brgt    1b
+        retal   r11
+
+        /*
+         * unsigned long find_next_zero_bit(const unsigned long *addr,
+         *                                  unsigned long size,
+         *                                  unsigned long offset)
+         */
+ENTRY(find_next_zero_bit)
+        lsr     r8, r10, 5
+        sub     r9, r11, r10
+        retle   r11
+
+        lsl     r8, 2
+        add     r12, r8
+        andl    r10, 31, COH
+        breq    1f
+
+        /* offset is not word-aligned. Handle the first (32 - r10) bits */
+        ld.w    r8, r12[0]
+        com     r8
+        sub     r12, -4
+        lsr     r8, r8, r10
+        brne    .L_found
+
+        /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
+        add     r9, r10
+        sub     r9, 32
+        retle   r11
+
+        /* Main loop. offset must be word-aligned */
+1:      ld.w    r8, r12[0]
+        com     r8
+        brne    .L_found
+        sub     r12, -4
+        sub     r9, 32
+        brgt    1b
+        retal   r11
+
+        /* Common return path for when a bit is actually found. */
+.L_found:
+        brev    r8
+        clz     r10, r8
+        rsub    r9, r11
+        add     r10, r9
+
+        /* XXX: If we don't have to return exactly "size" when the bit
+           is not found, we may drop this "min" thing */
+        min     r12, r11, r10
+        retal   r12
+
+        /*
+         * unsigned long find_first_bit(const unsigned long *addr,
+         *                              unsigned long size)
+         */
+ENTRY(find_first_bit)
+        cp.w    r11, 0
+        reteq   r11
+        mov     r9, r11
+1:      ld.w    r8, r12[0]
+        cp.w    r8, 0
+        brne    .L_found
+        sub     r12, -4
+        sub     r9, 32
+        brgt    1b
+        retal   r11
+
+        /*
+         * unsigned long find_next_bit(const unsigned long *addr,
+         *                             unsigned long size,
+         *                             unsigned long offset)
+         */
+ENTRY(find_next_bit)
+        lsr     r8, r10, 5
+        sub     r9, r11, r10
+        retle   r11
+
+        lsl     r8, 2
+        add     r12, r8
+        andl    r10, 31, COH
+        breq    1f
+
+        /* offset is not word-aligned. Handle the first (32 - r10) bits */
+        ld.w    r8, r12[0]
+        sub     r12, -4
+        lsr     r8, r8, r10
+        brne    .L_found
+
+        /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
+        add     r9, r10
+        sub     r9, 32
+        retle   r11
+
+        /* Main loop. offset must be word-aligned */
+1:      ld.w    r8, r12[0]
+        cp.w    r8, 0
+        brne    .L_found
+        sub     r12, -4
+        sub     r9, 32
+        brgt    1b
+        retal   r11
+
+ENTRY(generic_find_next_zero_le_bit)
+        lsr     r8, r10, 5
+        sub     r9, r11, r10
+        retle   r11
+
+        lsl     r8, 2
+        add     r12, r8
+        andl    r10, 31, COH
+        breq    1f
+
+        /* offset is not word-aligned. Handle the first (32 - r10) bits */
+        ldswp.w r8, r12[0]
+        sub     r12, -4
+        lsr     r8, r8, r10
+        brne    .L_found
+
+        /* r9 = r9 - (32 - r10) = r9 + r10 - 32 */
+        add     r9, r10
+        sub     r9, 32
+        retle   r11
+
+        /* Main loop. offset must be word-aligned */
+1:      ldswp.w r8, r12[0]
+        cp.w    r8, 0
+        brne    .L_found
+        sub     r12, -4
+        sub     r9, 32
+        brgt    1b
+        retal   r11