[ARM] nommu: add ARM940T core support

This patch adds ARM940T core support which has 4KB D-cache, 4KB I-cache
and a MPU.

Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index a29e641..4c424c9 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -59,6 +59,7 @@
 tune-$(CONFIG_CPU_ARM720T)	:=-mtune=arm7tdmi
 tune-$(CONFIG_CPU_ARM740T)	:=-mtune=arm7tdmi
 tune-$(CONFIG_CPU_ARM9TDMI)	:=-mtune=arm9tdmi
+tune-$(CONFIG_CPU_ARM940T)	:=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM920T)	:=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM922T)	:=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM925T)	:=-mtune=arm9tdmi
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index ed9d32c..34d0073 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -184,6 +184,22 @@
 	  Say Y if you want support for the ARM926T processor.
 	  Otherwise, say N.
 
+# ARM940T
+config CPU_ARM940T
+	bool "Support ARM940T processor" if ARCH_INTEGRATOR
+	select CPU_32v4T
+	select CPU_ABRT_EV4T
+	select CPU_CACHE_VIVT
+	select CPU_CP15_MPU
+	help
+	  ARM940T is a member of the ARM9TDMI family of general-
+	  purpose microprocessors with MPU and seperate 4KB
+	  instruction and 4KB data cases, each with a 4-word line
+	  length.
+
+	  Say Y if you want support for the ARM940T processor.
+	  Otherwise, say N.
+
 # ARM1020 - needs validating
 config CPU_ARM1020
 	bool "Support ARM1020T (rev 0) processor"
@@ -464,7 +480,7 @@
 
 config ARM_THUMB
 	bool "Support Thumb user binaries"
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_V6
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_V6
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
@@ -501,7 +517,7 @@
 
 config CPU_DCACHE_WRITETHROUGH
 	bool "Force write through D-cache"
-	depends on (CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM1020 || CPU_V6) && !CPU_DCACHE_DISABLE
+	depends on (CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM1020 || CPU_V6) && !CPU_DCACHE_DISABLE
 	default y if CPU_ARM925T
 	help
 	  Say Y here to use the data cache in writethrough mode. Unless you
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 053957e..f89fe1b 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -54,6 +54,7 @@
 obj-$(CONFIG_CPU_ARM922T)	+= proc-arm922.o
 obj-$(CONFIG_CPU_ARM925T)	+= proc-arm925.o
 obj-$(CONFIG_CPU_ARM926T)	+= proc-arm926.o
+obj-$(CONFIG_CPU_ARM940T)	+= proc-arm940.o
 obj-$(CONFIG_CPU_ARM1020)	+= proc-arm1020.o
 obj-$(CONFIG_CPU_ARM1020E)	+= proc-arm1020e.o
 obj-$(CONFIG_CPU_ARM1022)	+= proc-arm1022.o
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
new file mode 100644
index 0000000..14846ac
--- /dev/null
+++ b/arch/arm/mm/proc-arm940.S
@@ -0,0 +1,369 @@
+/*
+ *  linux/arch/arm/mm/arm940.S: utility functions for ARM940T
+ *
+ *  Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
+ *
+ * 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>
+#include <linux/init.h>
+#include <asm/assembler.h>
+#include <asm/pgtable-hwdef.h>
+#include <asm/pgtable.h>
+#include <asm/procinfo.h>
+#include <asm/ptrace.h>
+
+/* ARM940T has a 4KB DCache comprising 256 lines of 4 words */
+#define CACHE_DLINESIZE	16
+#define CACHE_DSEGMENTS	4
+#define CACHE_DENTRIES	64
+
+	.text
+/*
+ * cpu_arm940_proc_init()
+ * cpu_arm940_switch_mm()
+ *
+ * These are not required.
+ */
+ENTRY(cpu_arm940_proc_init)
+ENTRY(cpu_arm940_switch_mm)
+	mov	pc, lr
+
+/*
+ * cpu_arm940_proc_fin()
+ */
+ENTRY(cpu_arm940_proc_fin)
+	stmfd	sp!, {lr}
+	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
+	msr	cpsr_c, ip
+	bl	arm940_flush_kern_cache_all
+	mrc	p15, 0, r0, c1, c0, 0		@ ctrl register
+	bic	r0, r0, #0x00001000		@ i-cache
+	bic	r0, r0, #0x00000004		@ d-cache
+	mcr	p15, 0, r0, c1, c0, 0		@ disable caches
+	ldmfd	sp!, {pc}
+
+/*
+ * cpu_arm940_reset(loc)
+ * Params  : r0 = address to jump to
+ * Notes   : This sets up everything for a reset
+ */
+ENTRY(cpu_arm940_reset)
+	mov	ip, #0
+	mcr	p15, 0, ip, c7, c5, 0		@ flush I cache
+	mcr	p15, 0, ip, c7, c6, 0		@ flush D cache
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mrc	p15, 0, ip, c1, c0, 0		@ ctrl register
+	bic	ip, ip, #0x00000005		@ .............c.p
+	bic	ip, ip, #0x00001000		@ i-cache
+	mcr	p15, 0, ip, c1, c0, 0		@ ctrl register
+	mov	pc, r0
+
+/*
+ * cpu_arm940_do_idle()
+ */
+	.align	5
+ENTRY(cpu_arm940_do_idle)
+	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
+	mov	pc, lr
+
+/*
+ *	flush_user_cache_all()
+ */
+ENTRY(arm940_flush_user_cache_all)
+	/* FALLTHROUGH */
+
+/*
+ *	flush_kern_cache_all()
+ *
+ *	Clean and invalidate the entire cache.
+ */
+ENTRY(arm940_flush_kern_cache_all)
+	mov	r2, #VM_EXEC
+	/* FALLTHROUGH */
+
+/*
+ *	flush_user_cache_range(start, end, flags)
+ *
+ *	There is no efficient way to flush a range of cache entries
+ *	in the specified address range. Thus, flushes all.
+ *
+ *	- start	- start address (inclusive)
+ *	- end	- end address (exclusive)
+ *	- flags	- vm_flags describing address space
+ */
+ENTRY(arm940_flush_user_cache_range)
+	mov	ip, #0
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mcr	p15, 0, ip, c7, c6, 0		@ flush D cache
+#else
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
+2:	mcr	p15, 0, r3, c7, c14, 2		@ clean/flush D index
+	subs	r3, r3, #1 << 26
+	bcs	2b				@ entries 63 to 0
+	subs	r1, r1, #1 << 4
+	bcs	1b				@ segments 3 to 0
+#endif
+	tst	r2, #VM_EXEC
+	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate I cache
+	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	coherent_kern_range(start, end)
+ *
+ *	Ensure coherency between the Icache and the Dcache in the
+ *	region described by start, end.  If you have non-snooping
+ *	Harvard caches, you need to implement this function.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ */
+ENTRY(arm940_coherent_kern_range)
+	/* FALLTHROUGH */
+
+/*
+ *	coherent_user_range(start, end)
+ *
+ *	Ensure coherency between the Icache and the Dcache in the
+ *	region described by start, end.  If you have non-snooping
+ *	Harvard caches, you need to implement this function.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ */
+ENTRY(arm940_coherent_user_range)
+	/* FALLTHROUGH */
+
+/*
+ *	flush_kern_dcache_page(void *page)
+ *
+ *	Ensure no D cache aliasing occurs, either with itself or
+ *	the I cache
+ *
+ *	- addr	- page aligned address
+ */
+ENTRY(arm940_flush_kern_dcache_page)
+	mov	ip, #0
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
+2:	mcr	p15, 0, r3, c7, c14, 2		@ clean/flush D index
+	subs	r3, r3, #1 << 26
+	bcs	2b				@ entries 63 to 0
+	subs	r1, r1, #1 << 4
+	bcs	1b				@ segments 7 to 0
+	mcr	p15, 0, ip, c7, c5, 0		@ invalidate I cache
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_inv_range(start, end)
+ *
+ *	There is no efficient way to invalidate a specifid virtual
+ *	address range. Thus, invalidates all.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ */
+ENTRY(arm940_dma_inv_range)
+	mov	ip, #0
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
+2:	mcr	p15, 0, r3, c7, c6, 2		@ flush D entry
+	subs	r3, r3, #1 << 26
+	bcs	2b				@ entries 63 to 0
+	subs	r1, r1, #1 << 4
+	bcs	1b				@ segments 7 to 0
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_clean_range(start, end)
+ *
+ *	There is no efficient way to clean a specifid virtual
+ *	address range. Thus, cleans all.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ */
+ENTRY(arm940_dma_clean_range)
+ENTRY(cpu_arm940_dcache_clean_area)
+	mov	ip, #0
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
+2:	mcr	p15, 0, r3, c7, c10, 2		@ clean D entry
+	subs	r3, r3, #1 << 26
+	bcs	2b				@ entries 63 to 0
+	subs	r1, r1, #1 << 4
+	bcs	1b				@ segments 7 to 0
+#endif
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_flush_range(start, end)
+ *
+ *	There is no efficient way to clean and invalidate a specifid
+ *	virtual address range.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ */
+ENTRY(arm940_dma_flush_range)
+	mov	ip, #0
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 4	@ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 26 @ 64 entries
+2:
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mcr	p15, 0, r3, c7, c14, 2		@ clean/flush D entry
+#else
+	mcr	p15, 0, r3, c7, c10, 2		@ clean D entry
+#endif
+	subs	r3, r3, #1 << 26
+	bcs	2b				@ entries 63 to 0
+	subs	r1, r1, #1 << 4
+	bcs	1b				@ segments 7 to 0
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+ENTRY(arm940_cache_fns)
+	.long	arm940_flush_kern_cache_all
+	.long	arm940_flush_user_cache_all
+	.long	arm940_flush_user_cache_range
+	.long	arm940_coherent_kern_range
+	.long	arm940_coherent_user_range
+	.long	arm940_flush_kern_dcache_page
+	.long	arm940_dma_inv_range
+	.long	arm940_dma_clean_range
+	.long	arm940_dma_flush_range
+
+	__INIT
+
+	.type	__arm940_setup, #function
+__arm940_setup:
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mcr	p15, 0, r0, c7, c6, 0		@ invalidate D cache
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+
+	mcr	p15, 0, r0, c6, c3, 0		@ disable data area 3~7
+	mcr	p15, 0, r0, c6, c4, 0
+	mcr	p15, 0, r0, c6, c5, 0
+	mcr	p15, 0, r0, c6, c6, 0
+	mcr	p15, 0, r0, c6, c7, 0
+
+	mcr	p15, 0, r0, c6, c3, 1		@ disable instruction area 3~7
+	mcr	p15, 0, r0, c6, c4, 1
+	mcr	p15, 0, r0, c6, c5, 1
+	mcr	p15, 0, r0, c6, c6, 1
+	mcr	p15, 0, r0, c6, c7, 1
+
+	mov	r0, #0x0000003F			@ base = 0, size = 4GB
+	mcr	p15, 0, r0, c6,	c0, 0		@ set area 0, default
+	mcr	p15, 0, r0, c6,	c0, 1
+
+	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
+	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
+	mov	r2, #10				@ 11 is the minimum (4KB)
+1:	add	r2, r2, #1			@ area size *= 2
+	mov	r1, r1, lsr #1
+	bne	1b				@ count not zero r-shift
+	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, #1			@ set enable bit
+	mcr	p15, 0, r0, c6,	c1, 0		@ set area 1, RAM
+	mcr	p15, 0, r0, c6,	c1, 1
+
+	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
+	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
+	mov	r2, #10				@ 11 is the minimum (4KB)
+1:	add	r2, r2, #1			@ area size *= 2
+	mov	r1, r1, lsr #1
+	bne	1b				@ count not zero r-shift
+	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, #1			@ set enable bit
+	mcr	p15, 0, r0, c6,	c2, 0		@ set area 2, ROM/FLASH
+	mcr	p15, 0, r0, c6,	c2, 1
+
+	mov	r0, #0x06
+	mcr	p15, 0, r0, c2, c0, 0		@ Region 1&2 cacheable
+	mcr	p15, 0, r0, c2, c0, 1
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mov	r0, #0x00			@ disable whole write buffer
+#else
+	mov	r0, #0x02			@ Region 1 write bufferred
+#endif
+	mcr	p15, 0, r0, c3, c0, 0
+
+	mov	r0, #0x10000
+	sub	r0, r0, #1			@ r0 = 0xffff
+	mcr	p15, 0, r0, c5, c0, 0		@ all read/write access
+	mcr	p15, 0, r0, c5, c0, 1
+
+	mrc	p15, 0, r0, c1, c0		@ get control register
+	orr	r0, r0, #0x00001000		@ I-cache
+	orr	r0, r0, #0x00000005		@ MPU/D-cache
+
+	mov	pc, lr
+
+	.size	__arm940_setup, . - __arm940_setup
+
+	__INITDATA
+
+/*
+ * Purpose : Function pointers used to access above functions - all calls
+ *	     come through these
+ */
+	.type	arm940_processor_functions, #object
+ENTRY(arm940_processor_functions)
+	.word	v4t_early_abort
+	.word	cpu_arm940_proc_init
+	.word	cpu_arm940_proc_fin
+	.word	cpu_arm940_reset
+	.word   cpu_arm940_do_idle
+	.word	cpu_arm940_dcache_clean_area
+	.word	cpu_arm940_switch_mm
+	.word	0		@ cpu_*_set_pte
+	.size	arm940_processor_functions, . - arm940_processor_functions
+
+	.section ".rodata"
+
+.type	cpu_arch_name, #object
+cpu_arch_name:
+	.asciz	"armv4t"
+	.size	cpu_arch_name, . - cpu_arch_name
+
+	.type	cpu_elf_name, #object
+cpu_elf_name:
+	.asciz	"v4"
+	.size	cpu_elf_name, . - cpu_elf_name
+
+	.type	cpu_arm940_name, #object
+cpu_arm940_name:
+	.ascii	"ARM940T"
+	.size	cpu_arm940_name, . - cpu_arm940_name
+
+	.align
+
+	.section ".proc.info.init", #alloc, #execinstr
+
+	.type	__arm940_proc_info,#object
+__arm940_proc_info:
+	.long	0x41009400
+	.long	0xff00fff0
+	.long	0
+	b	__arm940_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
+	.long	cpu_arm940_name
+	.long	arm940_processor_functions
+	.long	0
+	.long	0
+	.long	arm940_cache_fns
+	.size	__arm940_proc_info, . - __arm940_proc_info
+