[ARM] nommu: add ARM946E-S core support

This patch adds ARM946E-S core support which has typically 8KB I&D cache.
It has a MPU and supports ARMv5TE instruction set.

Because the ARM946E-S core can be synthesizable with various cache size,
CONFIG_CPU_DCACHE_SIZE is defined for vendor specific configurations.
Signed-off-by: Hyok S. Choi <hyok.choi@samsung.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/Makefile

@@ -60,6 +60,7 @@ 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-$(CONFIG_CPU_ARM946T)	:=$(call cc-option,-mtune=arm9e,-mtune=arm9tdmi)
 tune-$(CONFIG_CPU_ARM920T)	:=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM922T)	:=-mtune=arm9tdmi
 tune-$(CONFIG_CPU_ARM925T)	:=-mtune=arm9tdmi

arch/arm/mm/Kconfig

@@ -200,6 +200,21 @@ config CPU_ARM940T
 	  Say Y if you want support for the ARM940T processor.
 	  Otherwise, say N.
 
+# ARM946E-S
+config CPU_ARM946E
+	bool "Support ARM946E-S processor" if ARCH_INTEGRATOR
+	select CPU_32v5
+	select CPU_ABRT_EV5T
+	select CPU_CACHE_VIVT
+	select CPU_CP15_MPU
+	help
+	  ARM946E-S is a member of the ARM9E-S family of high-
+	  performance, 32-bit system-on-chip processor solutions.
+	  The TCM and ARMv5TE 32-bit instruction set is supported.
+
+	  Say Y if you want support for the ARM946E-S processor.
+	  Otherwise, say N.
+
 # ARM1020 - needs validating
 config CPU_ARM1020
 	bool "Support ARM1020T (rev 0) processor"
@@ -480,7 +495,7 @@ comment "Processor Features"
 
 config ARM_THUMB
 	bool "Support Thumb user binaries"
-	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
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || 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
@@ -515,9 +530,22 @@ config CPU_DCACHE_DISABLE
 	  Say Y here to disable the processor data cache. Unless
 	  you have a reason not to or are unsure, say N.
 
+config CPU_DCACHE_SIZE
+	hex
+	depends on CPU_ARM740T || CPU_ARM946E
+	default 0x00001000 if CPU_ARM740T
+	default 0x00002000 # default size for ARM946E-S
+	help
+	  Some cores are synthesizable to have various sized cache. For
+	  ARM946E-S case, it can vary from 0KB to 1MB.
+	  To support such cache operations, it is efficient to know the size
+	  before compile time.
+	  If your SoC is configured to have a different size, define the value
+	  here with proper conditions.
+
 config CPU_DCACHE_WRITETHROUGH
 	bool "Force write through D-cache"
-	depends on (CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM1020 || CPU_V6) && !CPU_DCACHE_DISABLE
+	depends on (CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || 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
@@ -525,7 +553,7 @@ config CPU_DCACHE_WRITETHROUGH
 
 config CPU_CACHE_ROUND_ROBIN
 	bool "Round robin I and D cache replacement algorithm"
-	depends on (CPU_ARM926T || CPU_ARM1020) && (!CPU_ICACHE_DISABLE || !CPU_DCACHE_DISABLE)
+	depends on (CPU_ARM926T || CPU_ARM946E || CPU_ARM1020) && (!CPU_ICACHE_DISABLE || !CPU_DCACHE_DISABLE)
 	help
 	  Say Y here to use the predictable round-robin cache replacement
 	  policy.  Unless you specifically require this or are unsure, say N.

arch/arm/mm/Makefile

@@ -55,6 +55,7 @@ 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-$(CONFIG_CPU_ARM946E)	+= proc-arm946.o
 obj-$(CONFIG_CPU_ARM1020)	+= proc-arm1020.o
 obj-$(CONFIG_CPU_ARM1020E)	+= proc-arm1020e.o
 obj-$(CONFIG_CPU_ARM1022)	+= proc-arm1022.o

arch/arm/mm/proc-arm946.S

+/*
+ *  linux/arch/arm/mm/arm946.S: utility functions for ARM946E-S
+ *
+ *  Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
+ *
+ *  (Many of cache codes are from proc-arm926.S)
+ *
+ * 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>
+
+/*
+ * ARM946E-S is synthesizable to have 0KB to 1MB sized D-Cache,
+ * comprising 256 lines of 32 bytes (8 words).
+ */
+#define CACHE_DSIZE	(CONFIG_CPU_DCACHE_SIZE) /* typically 8KB. */
+#define CACHE_DLINESIZE	32			/* fixed */
+#define CACHE_DSEGMENTS	4			/* fixed */
+#define CACHE_DENTRIES	(CACHE_DSIZE / CACHE_DSEGMENTS / CACHE_DLINESIZE)
+#define CACHE_DLIMIT	(CACHE_DSIZE * 4)	/* benchmark needed */
+
+	.text
+/*
+ * cpu_arm946_proc_init()
+ * cpu_arm946_switch_mm()
+ *
+ * These are not required.
+ */
+ENTRY(cpu_arm946_proc_init)
+ENTRY(cpu_arm946_switch_mm)
+	mov	pc, lr
+
+/*
+ * cpu_arm946_proc_fin()
+ */
+ENTRY(cpu_arm946_proc_fin)
+	stmfd	sp!, {lr}
+	mov	ip, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
+	msr	cpsr_c, ip
+	bl	arm946_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_arm946_reset(loc)
+ * Params  : r0 = address to jump to
+ * Notes   : This sets up everything for a reset
+ */
+ENTRY(cpu_arm946_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_arm946_do_idle()
+ */
+	.align	5
+ENTRY(cpu_arm946_do_idle)
+	mcr	p15, 0, r0, c7, c0, 4		@ Wait for interrupt
+	mov	pc, lr
+
+/*
+ *	flush_user_cache_all()
+ */
+ENTRY(arm946_flush_user_cache_all)
+	/* FALLTHROUGH */
+
+/*
+ *	flush_kern_cache_all()
+ *
+ *	Clean and invalidate the entire cache.
+ */
+ENTRY(arm946_flush_kern_cache_all)
+	mov	r2, #VM_EXEC
+	mov	ip, #0
+__flush_whole_cache:
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mcr	p15, 0, ip, c7, c6, 0		@ flush D cache
+#else
+	mov	r1, #(CACHE_DSEGMENTS - 1) << 29 @ 4 segments
+1:	orr	r3, r1, #(CACHE_DENTRIES - 1) << 4 @ n entries
+2:	mcr	p15, 0, r3, c7, c14, 2		@ clean/flush D index
+	subs	r3, r3, #1 << 4
+	bcs	2b				@ entries n to 0
+	subs	r1, r1, #1 << 29
+	bcs	1b				@ segments 3 to 0
+#endif
+	tst	r2, #VM_EXEC
+	mcrne	p15, 0, ip, c7, c5, 0		@ flush I cache
+	mcrne	p15, 0, ip, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	flush_user_cache_range(start, end, flags)
+ *
+ *	Clean and invalidate a range of cache entries in the
+ *	specified address range.
+ *
+ *	- start	- start address (inclusive)
+ *	- end	- end address (exclusive)
+ *	- flags	- vm_flags describing address space
+ * (same as arm926)
+ */
+ENTRY(arm946_flush_user_cache_range)
+	mov	ip, #0
+	sub	r3, r1, r0			@ calculate total size
+	cmp	r3, #CACHE_DLIMIT
+	bhs	__flush_whole_cache
+
+1:	tst	r2, #VM_EXEC
+#ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
+	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate I entry
+	add	r0, r0, #CACHE_DLINESIZE
+	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
+	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate I entry
+	add	r0, r0, #CACHE_DLINESIZE
+#else
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D entry
+	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate I entry
+	add	r0, r0, #CACHE_DLINESIZE
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D entry
+	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate I entry
+	add	r0, r0, #CACHE_DLINESIZE
+#endif
+	cmp	r0, r1
+	blo	1b
+	tst	r2, #VM_EXEC
+	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(arm946_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
+ * (same as arm926)
+ */
+ENTRY(arm946_coherent_user_range)
+	bic	r0, r0, #CACHE_DLINESIZE - 1
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+	mcr	p15, 0, r0, c7, c5, 1		@ invalidate I entry
+	add	r0, r0, #CACHE_DLINESIZE
+	cmp	r0, r1
+	blo	1b
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	flush_kern_dcache_page(void *page)
+ *
+ *	Ensure no D cache aliasing occurs, either with itself or
+ *	the I cache
+ *
+ *	- addr	- page aligned address
+ * (same as arm926)
+ */
+ENTRY(arm946_flush_kern_dcache_page)
+	add	r1, r0, #PAGE_SZ
+1:	mcr	p15, 0, r0, c7, c14, 1		@ clean+invalidate D entry
+	add	r0, r0, #CACHE_DLINESIZE
+	cmp	r0, r1
+	blo	1b
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_inv_range(start, end)
+ *
+ *	Invalidate (discard) the specified virtual address range.
+ *	May not write back any entries.  If 'start' or 'end'
+ *	are not cache line aligned, those lines must be written
+ *	back.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ * (same as arm926)
+ */
+ENTRY(arm946_dma_inv_range)
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+	tst	r0, #CACHE_DLINESIZE - 1
+	mcrne	p15, 0, r0, c7, c10, 1		@ clean D entry
+	tst	r1, #CACHE_DLINESIZE - 1
+	mcrne	p15, 0, r1, c7, c10, 1		@ clean D entry
+#endif
+	bic	r0, r0, #CACHE_DLINESIZE - 1
+1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D entry
+	add	r0, r0, #CACHE_DLINESIZE
+	cmp	r0, r1
+	blo	1b
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_clean_range(start, end)
+ *
+ *	Clean the specified virtual address range.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ *
+ * (same as arm926)
+ */
+ENTRY(arm946_dma_clean_range)
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+	bic	r0, r0, #CACHE_DLINESIZE - 1
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+	add	r0, r0, #CACHE_DLINESIZE
+	cmp	r0, r1
+	blo	1b
+#endif
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+/*
+ *	dma_flush_range(start, end)
+ *
+ *	Clean and invalidate the specified virtual address range.
+ *
+ *	- start	- virtual start address
+ *	- end	- virtual end address
+ *
+ * (same as arm926)
+ */
+ENTRY(arm946_dma_flush_range)
+	bic	r0, r0, #CACHE_DLINESIZE - 1
+1:
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+	mcr	p15, 0, r0, c7, c14, 1		@ clean+invalidate D entry
+#else
+	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+#endif
+	add	r0, r0, #CACHE_DLINESIZE
+	cmp	r0, r1
+	blo	1b
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+ENTRY(arm946_cache_fns)
+	.long	arm946_flush_kern_cache_all
+	.long	arm946_flush_user_cache_all
+	.long	arm946_flush_user_cache_range
+	.long	arm946_coherent_kern_range
+	.long	arm946_coherent_user_range
+	.long	arm946_flush_kern_dcache_page
+	.long	arm946_dma_inv_range
+	.long	arm946_dma_clean_range
+	.long	arm946_dma_flush_range
+
+
+ENTRY(cpu_arm946_dcache_clean_area)
+#ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+	add	r0, r0, #CACHE_DLINESIZE
+	subs	r1, r1, #CACHE_DLINESIZE
+	bhi	1b
+#endif
+	mcr	p15, 0, r0, c7, c10, 4		@ drain WB
+	mov	pc, lr
+
+	__INIT
+
+	.type	__arm946_setup, #function
+__arm946_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 memory region 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
+
+	mov	r0, #0x0000003F			@ base = 0, size = 4GB
+	mcr	p15, 0, r0, c6,	c0, 0		@ set region 0, default
+
+	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 region register value
+	orr	r0, r0, #1			@ set enable bit
+	mcr	p15, 0, r0, c6,	c1, 0		@ set region 1, RAM
+
+	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 region register value
+	orr	r0, r0, #1			@ set enable bit
+	mcr	p15, 0, r0, c6,	c2, 0		@ set region 2, ROM/FLASH
+
+	mov	r0, #0x06
+	mcr	p15, 0, r0, c2, c0, 0		@ region 1,2 d-cacheable
+	mcr	p15, 0, r0, c2, c0, 1		@ region 1,2 i-cacheable
+#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
+
+/*
+ *  Access Permission Settings for future permission control by PU.
+ *
+ *				priv.	user
+ * 	region 0 (whole)	rw	--	: b0001
+ * 	region 1 (RAM)		rw	rw	: b0011
+ * 	region 2 (FLASH)	rw	r-	: b0010
+ *	region 3~7 (none)	--	--	: b0000
+ */
+	mov	r0, #0x00000031
+	orr	r0, r0, #0x00000200
+	mcr	p15, 0, r0, c5, c0, 2		@ set data access permission
+	mcr	p15, 0, r0, c5, c0, 3		@ set inst. access permission
+
+	mrc	p15, 0, r0, c1, c0		@ get control register
+	orr	r0, r0, #0x00001000		@ I-cache
+	orr	r0, r0, #0x00000005		@ MPU/D-cache
+#ifdef CONFIG_CPU_CACHE_ROUND_ROBIN
+	orr	r0, r0, #0x00004000		@ .1.. .... .... ....
+#endif
+	mov	pc, lr
+
+	.size	__arm946_setup, . - __arm946_setup
+
+	__INITDATA
+
+/*
+ * Purpose : Function pointers used to access above functions - all calls
+ *	     come through these
+ */
+	.type	arm946_processor_functions, #object
+ENTRY(arm946_processor_functions)
+	.word	v5t_early_abort
+	.word	cpu_arm946_proc_init
+	.word	cpu_arm946_proc_fin
+	.word	cpu_arm946_reset
+	.word   cpu_arm946_do_idle
+
+	.word	cpu_arm946_dcache_clean_area
+	.word	cpu_arm946_switch_mm
+	.word	0		@ cpu_*_set_pte
+	.size	arm946_processor_functions, . - arm946_processor_functions
+
+	.section ".rodata"
+
+	.type	cpu_arch_name, #object
+cpu_arch_name:
+	.asciz	"armv5te"
+	.size	cpu_arch_name, . - cpu_arch_name
+
+	.type	cpu_elf_name, #object
+cpu_elf_name:
+	.asciz	"v5t"
+	.size	cpu_elf_name, . - cpu_elf_name
+
+	.type	cpu_arm946_name, #object
+cpu_arm946_name:
+	.ascii	"ARM946E-S"
+	.size	cpu_arm946_name, . - cpu_arm946_name
+
+	.align
+
+	.section ".proc.info.init", #alloc, #execinstr
+	.type	__arm946_proc_info,#object
+__arm946_proc_info:
+	.long	0x41009460
+	.long	0xff00fff0
+	.long	0
+	b	__arm946_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
+	.long	cpu_arm946_name
+	.long	arm946_processor_functions
+	.long	0
+	.long	0
+	.long	arm940_cache_fns
+	.size	__arm946_proc_info, . - __arm946_proc_info
+

include/asm-arm/cacheflush.h

@@ -64,6 +64,14 @@
 # endif
 #endif
 
+#if defined(CONFIG_CPU_ARM946E)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm946
+# endif
+#endif
+
 #if defined(CONFIG_CPU_SA110) || defined(CONFIG_CPU_SA1100)
 # ifdef _CACHE
 #  define MULTI_CACHE 1

include/asm-arm/proc-fns.h

@@ -113,6 +113,14 @@
 #   define CPU_NAME cpu_arm940
 #  endif
 # endif
+# ifdef CONFIG_CPU_ARM946E
+#  ifdef CPU_NAME
+#   undef  MULTI_CPU
+#   define MULTI_CPU
+#  else
+#   define CPU_NAME cpu_arm946
+#  endif
+# endif
 # ifdef CONFIG_CPU_SA110
 #  ifdef CPU_NAME
 #   undef  MULTI_CPU