Merge branch 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'for-linus' of master.kernel.org:/home/rmk/linux-2.6-arm: (117 commits)
  [ARM] 4058/2: iop32x: set ->broken_parity_status on n2100 onboard r8169 ports
  [ARM] 4140/1: AACI stability add ac97 timeout and retries
  [ARM] 4139/1: AACI record support
  [ARM] 4138/1: AACI: multiple channel support for IRQ handling
  [ARM] 4211/1: Provide a defconfig for ns9xxx
  [ARM] 4210/1: base for new machine type "NetSilicon NS9360"
  [ARM] 4222/1: S3C2443: Remove reference to missing S3C2443_PM
  [ARM] 4221/1: S3C2443: DMA support
  [ARM] 4220/1: S3C24XX: DMA system initialised from sysdev
  [ARM] 4219/1: S3C2443: DMA source definitions
  [ARM] 4218/1: S3C2412: fix CONFIG_CPU_S3C2412_ONLY wrt to S3C2443
  [ARM] 4217/1: S3C24XX: remove the dma channel show at startup
  [ARM] 4090/2: avoid clash between PXA and SA1111 defines
  [ARM] 4216/1: add .gitignore entries for ARM specific files
  [ARM] 4214/2: S3C2410: Add Armzone QT2410
  [ARM] 4215/1: s3c2410 usb device:  per-platform vbus_draw
  [ARM] 4213/1: S3C2410 - Update definition of ADCTSC_XY_PST
  [ARM] 4098/1: ARM: rtc_lock only used with rtc_cmos
  [ARM] 4137/1: Add kexec support
  [ARM] 4201/1: SMP barriers pair needed for the secondary boot process
  ...

Fix up conflict due to typedef removal in sound/arm/aaci.h

10 files changed, 231 insertions, 97 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index aade2f72c92..4b277199d0e 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -171,8 +171,8 @@ config CPU_ARM925T
 # ARM926T
 config CPU_ARM926T
 	bool "Support ARM926T processor"
-	depends on ARCH_INTEGRATOR || ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX || MACH_REALVIEW_EB || ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || ARCH_AT91SAM9260 || ARCH_AT91SAM9261
-	default y if ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX || ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || ARCH_AT91SAM9260 || ARCH_AT91SAM9261
+	depends on ARCH_INTEGRATOR || ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX || MACH_REALVIEW_EB || ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || ARCH_AT91SAM9260 || ARCH_AT91SAM9261 || ARCH_AT91SAM9263 || ARCH_NS9XXX
+	default y if ARCH_VERSATILE_PB || MACH_VERSATILE_AB || ARCH_OMAP730 || ARCH_OMAP16XX || ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || ARCH_AT91SAM9260 || ARCH_AT91SAM9261 || ARCH_AT91SAM9263 || ARCH_NS9XXX
 	select CPU_32v5
 	select CPU_ABRT_EV5TJ
 	select CPU_CACHE_VIVT
@@ -609,3 +609,10 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 	  Forget about fast user space cmpxchg support.
 	  It is just not possible.
 
+config OUTER_CACHE
+	bool
+	default n
+
+config CACHE_L2X0
+	bool
+	select OUTER_CACHE
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index d2f5672ecf6..2f8b9594777 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -66,3 +66,5 @@ obj-$(CONFIG_CPU_SA1100)	+= proc-sa1100.o
 obj-$(CONFIG_CPU_XSCALE)	+= proc-xscale.o
 obj-$(CONFIG_CPU_XSC3)		+= proc-xsc3.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
+
+obj-$(CONFIG_CACHE_L2X0)	+= cache-l2x0.o
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
new file mode 100644
index 00000000000..08a36f1b35d
--- /dev/null
+++ b/arch/arm/mm/cache-l2x0.c
@@ -0,0 +1,104 @@
+/*
+ * arch/arm/mm/cache-l2x0.c - L210/L220 cache controller support
+ *
+ * Copyright (C) 2007 ARM Limited
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+#include <linux/init.h>
+
+#include <asm/cacheflush.h>
+#include <asm/io.h>
+#include <asm/hardware/cache-l2x0.h>
+
+#define CACHE_LINE_SIZE		32
+
+static void __iomem *l2x0_base;
+
+static inline void sync_writel(unsigned long val, unsigned long reg,
+			       unsigned long complete_mask)
+{
+	writel(val, l2x0_base + reg);
+	/* wait for the operation to complete */
+	while (readl(l2x0_base + reg) & complete_mask)
+		;
+}
+
+static inline void cache_sync(void)
+{
+	sync_writel(0, L2X0_CACHE_SYNC, 1);
+}
+
+static inline void l2x0_inv_all(void)
+{
+	/* invalidate all ways */
+	sync_writel(0xff, L2X0_INV_WAY, 0xff);
+	cache_sync();
+}
+
+static void l2x0_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	start &= ~(CACHE_LINE_SIZE - 1);
+	for (addr = start; addr < end; addr += CACHE_LINE_SIZE)
+		sync_writel(addr, L2X0_INV_LINE_PA, 1);
+	cache_sync();
+}
+
+static void l2x0_clean_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	start &= ~(CACHE_LINE_SIZE - 1);
+	for (addr = start; addr < end; addr += CACHE_LINE_SIZE)
+		sync_writel(addr, L2X0_CLEAN_LINE_PA, 1);
+	cache_sync();
+}
+
+static void l2x0_flush_range(unsigned long start, unsigned long end)
+{
+	unsigned long addr;
+
+	start &= ~(CACHE_LINE_SIZE - 1);
+	for (addr = start; addr < end; addr += CACHE_LINE_SIZE)
+		sync_writel(addr, L2X0_CLEAN_INV_LINE_PA, 1);
+	cache_sync();
+}
+
+void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
+{
+	__u32 aux;
+
+	l2x0_base = base;
+
+	/* disable L2X0 */
+	writel(0, l2x0_base + L2X0_CTRL);
+
+	aux = readl(l2x0_base + L2X0_AUX_CTRL);
+	aux &= aux_mask;
+	aux |= aux_val;
+	writel(aux, l2x0_base + L2X0_AUX_CTRL);
+
+	l2x0_inv_all();
+
+	/* enable L2X0 */
+	writel(1, l2x0_base + L2X0_CTRL);
+
+	outer_cache.inv_range = l2x0_inv_range;
+	outer_cache.clean_range = l2x0_clean_range;
+	outer_cache.flush_range = l2x0_flush_range;
+
+	printk(KERN_INFO "L2X0 cache controller enabled\n");
+}
diff --git a/arch/arm/mm/consistent.c b/arch/arm/mm/consistent.c
index 6a9c362fef5..1f9f94f9af4 100644
--- a/arch/arm/mm/consistent.c
+++ b/arch/arm/mm/consistent.c
@@ -205,9 +205,10 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	 * kernel direct-mapped region for device DMA.
 	 */
 	{
-		unsigned long kaddr = (unsigned long)page_address(page);
-		memset(page_address(page), 0, size);
-		dmac_flush_range(kaddr, kaddr + size);
+		void *ptr = page_address(page);
+		memset(ptr, 0, size);
+		dmac_flush_range(ptr, ptr + size);
+		outer_flush_range(__pa(ptr), __pa(ptr) + size);
 	}
 
 	/*
@@ -480,20 +481,24 @@ core_initcall(consistent_init);
  * platforms with CONFIG_DMABOUNCE.
  * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
  */
-void consistent_sync(void *vaddr, size_t size, int direction)
+void consistent_sync(const void *start, size_t size, int direction)
 {
-	unsigned long start = (unsigned long)vaddr;
-	unsigned long end   = start + size;
+	const void *end = start + size;
+
+	BUG_ON(!virt_addr_valid(start) || !virt_addr_valid(end - 1));
 
 	switch (direction) {
 	case DMA_FROM_DEVICE:		/* invalidate only */
 		dmac_inv_range(start, end);
+		outer_inv_range(__pa(start), __pa(end));
 		break;
 	case DMA_TO_DEVICE:		/* writeback only */
 		dmac_clean_range(start, end);
+		outer_clean_range(__pa(start), __pa(end));
 		break;
 	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
 		dmac_flush_range(start, end);
+		outer_flush_range(__pa(start), __pa(end));
 		break;
 	default:
 		BUG();
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 79e80020242..9da43a0fdcd 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -19,7 +19,8 @@ unsigned int cpu_last_asid = { 1 << ASID_BITS };
 /*
  * We fork()ed a process, and we need a new context for the child
  * to run in.  We reserve version 0 for initial tasks so we will
- * always allocate an ASID.
+ * always allocate an ASID. The ASID 0 is reserved for the TTBR
+ * register changing sequence.
  */
 void __init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
@@ -38,8 +39,15 @@ void __new_context(struct mm_struct *mm)
 	 * If we've used up all our ASIDs, we need
 	 * to start a new version and flush the TLB.
 	 */
-	if ((asid & ~ASID_MASK) == 0)
+	if ((asid & ~ASID_MASK) == 0) {
+		asid = ++cpu_last_asid;
+		/* set the reserved ASID before flushing the TLB */
+		asm("mcr	p15, 0, %0, c13, c0, 1	@ set reserved context ID\n"
+		    :
+		    : "r" (0));
+		isb();
 		flush_tlb_all();
+	}
 
 	mm->context.id = asid;
 }
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index cf95c5d0ce4..44558d5f931 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -119,8 +119,6 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma, unsigne
 		flush_cache_page(vma, addr, pfn);
 }
 
-void __flush_dcache_page(struct address_space *mapping, struct page *page);
-
 /*
  * Take care of architecture specific things when placing a new PTE into
  * a page table, or changing an existing PTE.  Basically, there are two
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 655c8376f0b..94fd4bf5cb9 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -49,8 +49,10 @@ pmd_t *top_pmd;
 
 static unsigned int cachepolicy __initdata = CPOLICY_WRITEBACK;
 static unsigned int ecc_mask __initdata = 0;
+pgprot_t pgprot_user;
 pgprot_t pgprot_kernel;
 
+EXPORT_SYMBOL(pgprot_user);
 EXPORT_SYMBOL(pgprot_kernel);
 
 struct cachepolicy {
@@ -345,6 +347,7 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_MINICLEAN].prot_sect &= ~PMD_SECT_TEX(1);
 	}
 
+	pgprot_user   = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG | user_pgprot);
 	pgprot_kernel = __pgprot(L_PTE_PRESENT | L_PTE_YOUNG |
 				 L_PTE_DIRTY | L_PTE_WRITE |
 				 L_PTE_EXEC | kern_pgprot);
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 7b1843befb9..eb42e5b9486 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -14,10 +14,13 @@
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/elf.h>
-#include <asm/hardware/arm_scu.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/pgtable.h>
 
+#ifdef CONFIG_SMP
+#include <asm/hardware/arm_scu.h>
+#endif
+
 #include "proc-macros.S"
 
 #define D_CACHE_LINE_SIZE	32
@@ -30,6 +33,12 @@
 #define TTB_RGN_WT	(2 << 3)
 #define TTB_RGN_WB	(3 << 3)
 
+#ifndef CONFIG_SMP
+#define TTB_FLAGS	TTB_RGN_WBWA
+#else
+#define TTB_FLAGS	TTB_RGN_WBWA|TTB_S
+#endif
+
 ENTRY(cpu_v6_proc_init)
 	mov	pc, lr
 
@@ -92,9 +101,7 @@ ENTRY(cpu_v6_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-#ifdef CONFIG_SMP
-	orr	r0, r0, #TTB_RGN_WBWA|TTB_S	@ mark PTWs shared, outer cacheable
-#endif
+	orr	r0, r0, #TTB_FLAGS
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ drain write buffer
 	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
@@ -183,8 +190,7 @@ __v6_setup:
 	/* Set up the SCU on core 0 only */
 	mrc	p15, 0, r0, c0, c0, 5		@ CPU core number
 	ands	r0, r0, #15
-	moveq	r0, #0x10000000 @ SCU_BASE
-	orreq	r0, r0, #0x00100000
+	ldreq	r0, =SCU_BASE
 	ldreq	r5, [r0, #SCU_CTRL]
 	orreq	r5, r5, #1
 	streq	r5, [r0, #SCU_CTRL]
@@ -204,9 +210,7 @@ __v6_setup:
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r0, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r0, c2, c0, 2		@ TTB control register
-#ifdef CONFIG_SMP
-	orr	r4, r4, #TTB_RGN_WBWA|TTB_S	@ mark PTWs shared, outer cacheable
-#endif
+	orr	r4, r4, #TTB_FLAGS
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 94a58455f34..d95921a2ab9 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -5,23 +5,23 @@
  * Current Maintainer: Lennert Buytenhek <buytenh@wantstofly.org>
  *
  * Copyright 2004 (C) Intel Corp.
- * Copyright 2005 (c) MontaVista Software, Inc.
+ * Copyright 2005 (C) MontaVista Software, Inc.
  *
  * 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.
  *
- * MMU functions for the Intel XScale3 Core (XSC3).  The XSC3 core is an
- * extension to Intel's original XScale core that adds the following
+ * MMU functions for the Intel XScale3 Core (XSC3).  The XSC3 core is
+ * an extension to Intel's original XScale core that adds the following
  * features:
  *
  * - ARMv6 Supersections
  * - Low Locality Reference pages (replaces mini-cache)
  * - 36-bit addressing
  * - L2 cache
- * - Cache-coherency if chipset supports it
+ * - Cache coherency if chipset supports it
  *
- * Based on orignal XScale code by Nicolas Pitre
+ * Based on original XScale code by Nicolas Pitre.
  */
 
 #include <linux/linkage.h>
@@ -42,12 +42,12 @@
 #define MAX_AREA_SIZE	32768
 
 /*
- * The cache line size of the I and D cache.
+ * The cache line size of the L1 I, L1 D and unified L2 cache.
  */
 #define CACHELINESIZE	32
 
 /*
- * The size of the data cache.
+ * The size of the L1 D cache.
  */
 #define CACHESIZE	32768
 
@@ -57,9 +57,9 @@
 #define L2_CACHE_ENABLE	1
 
 /*
- * This macro is used to wait for a CP15 write and is needed
- * when we have to ensure that the last operation to the co-pro
- * was completed before continuing with operation.
+ * This macro is used to wait for a CP15 write and is needed when we
+ * have to ensure that the last operation to the coprocessor was
+ * completed before continuing with operation.
  */
 	.macro	cpwait_ret, lr, rd
 	mrc	p15, 0, \rd, c2, c0, 0		@ arbitrary read of cp15
@@ -68,13 +68,13 @@
 	.endm
 
 /*
- * This macro cleans & invalidates the entire xsc3 dcache by set & way.
+ * This macro cleans and invalidates the entire L1 D cache.
  */
 
  	.macro  clean_d_cache rd, rs
 	mov	\rd, #0x1f00
 	orr	\rd, \rd, #0x00e0
-1:	mcr	p15, 0, \rd, c7, c14, 2		@ clean/inv set/way
+1:	mcr	p15, 0, \rd, c7, c14, 2		@ clean/invalidate L1 D line
 	adds	\rd, \rd, #0x40000000
 	bcc	1b
 	subs	\rd, \rd, #0x20
@@ -119,15 +119,15 @@ ENTRY(cpu_xsc3_reset)
 	mov	r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
 	msr	cpsr_c, r1			@ reset CPSR
 	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
-	bic	r1, r1, #0x0086			@ ........B....CA.
 	bic	r1, r1, #0x3900			@ ..VIZ..S........
+	bic	r1, r1, #0x0086			@ ........B....CA.
 	mcr	p15, 0, r1, c1, c0, 0		@ ctrl register
-	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I,D caches & BTB
+	mcr	p15, 0, ip, c7, c7, 0		@ invalidate L1 caches and BTB
 	bic	r1, r1, #0x0001			@ ...............M
 	mcr	p15, 0, r1, c1, c0, 0		@ ctrl register
 	@ CAUTION: MMU turned off from this point.  We count on the pipeline
 	@ already containing those two last instructions to survive.
-	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
+	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I and D TLBs
 	mov	pc, r0
 
 /*
@@ -139,14 +139,12 @@ ENTRY(cpu_xsc3_reset)
  *
  * XScale supports clock switching, but using idle mode support
  * allows external hardware to react to system state changes.
-
- MMG: Come back to this one.
  */
 	.align	5
 
 ENTRY(cpu_xsc3_do_idle)
 	mov	r0, #1
-	mcr	p14, 0, r0, c7, c0, 0		@ Go to IDLE
+	mcr	p14, 0, r0, c7, c0, 0		@ go to idle
 	mov	pc, lr
 
 /* ================================= CACHE ================================ */
@@ -171,9 +169,9 @@ ENTRY(xsc3_flush_kern_cache_all)
 __flush_whole_cache:
 	clean_d_cache r0, r1
 	tst	r2, #VM_EXEC
-	mcrne	p15, 0, ip, c7, c5, 0		@ Invalidate I cache & BTB
-	mcrne	p15, 0, ip, c7, c10, 4		@ Drain Write Buffer
-	mcrne	p15, 0, ip, c7, c5, 4		@ Prefetch Flush
+	mcrne	p15, 0, ip, c7, c5, 0		@ invalidate L1 I cache and BTB
+	mcrne	p15, 0, ip, c7, c10, 4		@ data write barrier
+	mcrne	p15, 0, ip, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 /*
@@ -194,21 +192,21 @@ ENTRY(xsc3_flush_user_cache_range)
 	bhs	__flush_whole_cache
 
 1:	tst	r2, #VM_EXEC
-	mcrne	p15, 0, r0, c7, c5, 1		@ Invalidate I cache line
-	mcr	p15, 0, r0, c7, c14, 1		@ Clean/invalidate D cache line
+	mcrne	p15, 0, r0, c7, c5, 1		@ invalidate L1 I line
+	mcr	p15, 0, r0, c7, c14, 1		@ clean/invalidate L1 D line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
 	tst	r2, #VM_EXEC
-	mcrne	p15, 0, ip, c7, c5, 6		@ Invalidate BTB
-	mcrne	p15, 0, ip, c7, c10, 4		@ Drain Write Buffer
-	mcrne	p15, 0, ip, c7, c5, 4		@ Prefetch Flush
+	mcrne	p15, 0, ip, c7, c5, 6		@ invalidate BTB
+	mcrne	p15, 0, ip, c7, c10, 4		@ data write barrier
+	mcrne	p15, 0, ip, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 /*
  *	coherent_kern_range(start, end)
  *
- *	Ensure coherency between the Icache and the Dcache in the
+ *	Ensure coherency between the I cache and the D cache in the
  *	region described by start.  If you have non-snooping
  *	Harvard caches, you need to implement this function.
  *
@@ -222,34 +220,34 @@ ENTRY(xsc3_coherent_kern_range)
 /* FALLTHROUGH */
 ENTRY(xsc3_coherent_user_range)
 	bic	r0, r0, #CACHELINESIZE - 1
-1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean L1 D line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
-	mcr	p15, 0, r0, c7, c5, 0		@ Invalidate I cache & BTB
-	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write Buffer
-	mcr	p15, 0, r0, c7, c5, 4		@ Prefetch Flush
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate L1 I cache and BTB
+	mcr	p15, 0, r0, c7, c10, 4		@ data write barrier
+	mcr	p15, 0, r0, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 /*
  *	flush_kern_dcache_page(void *page)
  *
  *	Ensure no D cache aliasing occurs, either with itself or
- *	the I cache
+ *	the I cache.
  *
  *	- addr	- page aligned address
  */
 ENTRY(xsc3_flush_kern_dcache_page)
 	add	r1, r0, #PAGE_SZ
-1:	mcr	p15, 0, r0, c7, c14, 1		@ Clean/Invalidate D Cache line
+1:	mcr	p15, 0, r0, c7, c14, 1		@ clean/invalidate L1 D line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
 	mov	r0, #0
-	mcr	p15, 0, r0, c7, c5, 0		@ Invalidate I cache & BTB
-	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write Buffer
-	mcr	p15, 0, r0, c7, c5, 4		@ Prefetch Flush
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate L1 I cache and BTB
+	mcr	p15, 0, r0, c7, c10, 4		@ data write barrier
+	mcr	p15, 0, r0, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 /*
@@ -266,17 +264,17 @@ ENTRY(xsc3_flush_kern_dcache_page)
 ENTRY(xsc3_dma_inv_range)
 	tst	r0, #CACHELINESIZE - 1
 	bic	r0, r0, #CACHELINESIZE - 1
-	mcrne	p15, 0, r0, c7, c10, 1		@ clean L1 D entry
-	mcrne	p15, 1, r0, c7, c11, 1		@ clean L2 D entry
+	mcrne	p15, 0, r0, c7, c10, 1		@ clean L1 D line
+	mcrne	p15, 1, r0, c7, c11, 1		@ clean L2 line
 	tst	r1, #CACHELINESIZE - 1
-	mcrne	p15, 0, r1, c7, c10, 1		@ clean L1 D entry
-	mcrne	p15, 1, r1, c7, c11, 1		@ clean L2 D entry
-1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate L1 D entry
-	mcr	p15, 1, r0, c7, c7, 1		@ Invalidate L2 D cache line
+	mcrne	p15, 0, r1, c7, c10, 1		@ clean L1 D line
+	mcrne	p15, 1, r1, c7, c11, 1		@ clean L2 line
+1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate L1 D line
+	mcr	p15, 1, r0, c7, c7, 1		@ invalidate L2 line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
-	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write Buffer
+	mcr	p15, 0, r0, c7, c10, 4		@ data write barrier
 	mov	pc, lr
 
 /*
@@ -289,12 +287,12 @@ ENTRY(xsc3_dma_inv_range)
  */
 ENTRY(xsc3_dma_clean_range)
 	bic	r0, r0, #CACHELINESIZE - 1
-1:	mcr	p15, 0, r0, c7, c10, 1		@ clean L1 D entry
-	mcr	p15, 1, r0, c7, c11, 1		@ clean L2 D entry
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean L1 D line
+	mcr	p15, 1, r0, c7, c11, 1		@ clean L2 line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
-	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write Buffer
+	mcr	p15, 0, r0, c7, c10, 4		@ data write barrier
 	mov	pc, lr
 
 /*
@@ -307,13 +305,13 @@ ENTRY(xsc3_dma_clean_range)
  */
 ENTRY(xsc3_dma_flush_range)
 	bic	r0, r0, #CACHELINESIZE - 1
-1:	mcr	p15, 0, r0, c7, c14, 1	@ Clean/invalidate L1 D cache line
-	mcr	p15, 1, r0, c7, c11, 1	@ Clean L2 D cache line
-	mcr	p15, 1, r0, c7, c7, 1	@ Invalidate L2 D cache line
+1:	mcr	p15, 0, r0, c7, c14, 1		@ clean/invalidate L1 D line
+	mcr	p15, 1, r0, c7, c11, 1		@ clean L2 line
+	mcr	p15, 1, r0, c7, c7, 1		@ invalidate L2 line
 	add	r0, r0, #CACHELINESIZE
 	cmp	r0, r1
 	blo	1b
-	mcr	p15, 0, r0, c7, c10, 4		@ Drain Write Buffer
+	mcr	p15, 0, r0, c7, c10, 4		@ data write barrier
 	mov	pc, lr
 
 ENTRY(xsc3_cache_fns)
@@ -328,7 +326,7 @@ ENTRY(xsc3_cache_fns)
 	.long	xsc3_dma_flush_range
 
 ENTRY(cpu_xsc3_dcache_clean_area)
-1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
+1:	mcr	p15, 0, r0, c7, c10, 1		@ clean L1 D line
 	add	r0, r0, #CACHELINESIZE
 	subs	r1, r1, #CACHELINESIZE
 	bhi	1b
@@ -346,14 +344,14 @@ ENTRY(cpu_xsc3_dcache_clean_area)
 	.align	5
 ENTRY(cpu_xsc3_switch_mm)
 	clean_d_cache r1, r2
-	mcr	p15, 0, ip, c7, c5, 0		@ Invalidate I cache & BTB
-	mcr	p15, 0, ip, c7, c10, 4		@ Drain Write Buffer
-	mcr	p15, 0, ip, c7, c5, 4		@ Prefetch Flush
+	mcr	p15, 0, ip, c7, c5, 0		@ invalidate L1 I cache and BTB
+	mcr	p15, 0, ip, c7, c10, 4		@ data write barrier
+	mcr	p15, 0, ip, c7, c5, 4		@ prefetch flush
 #ifdef L2_CACHE_ENABLE
 	orr	r0, r0, #0x18			@ cache the page table in L2
 #endif
 	mcr	p15, 0, r0, c2, c0, 0		@ load page table pointer
-	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I & D TLBs
+	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I and D TLBs
 	cpwait_ret lr, ip
 
 /*
@@ -366,34 +364,34 @@ ENTRY(cpu_xsc3_switch_mm)
 ENTRY(cpu_xsc3_set_pte_ext)
 	str	r1, [r0], #-2048		@ linux version
 
-	bic	r2, r1, #0xff0			@ Keep C, B bits
+	bic	r2, r1, #0xff0			@ keep C, B bits
 	orr	r2, r2, #PTE_TYPE_EXT		@ extended page
-	tst	r1, #L_PTE_SHARED		@ Shared?
+	tst	r1, #L_PTE_SHARED		@ shared?
 	orrne	r2, r2, #0x200
 
 	eor	r3, r1, #L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_WRITE | L_PTE_DIRTY
 
-	tst	r3, #L_PTE_USER			@ User?
+	tst	r3, #L_PTE_USER			@ user?
 	orrne	r2, r2, #PTE_EXT_AP_URO_SRW	@ yes -> user r/o, system r/w
 
-	tst	r3, #L_PTE_WRITE | L_PTE_DIRTY	@ Write and Dirty?
+	tst	r3, #L_PTE_WRITE | L_PTE_DIRTY	@ write and dirty?
 	orreq	r2, r2, #PTE_EXT_AP_UNO_SRW	@ yes -> user n/a, system r/w
 						@ combined with user -> user r/w
 
 #if L2_CACHE_ENABLE
-	@ If its cacheable it needs to be in L2 also.
+	@ If it's cacheable, it needs to be in L2 also.
 	eor	ip, r1, #L_PTE_CACHEABLE
 	tst	ip, #L_PTE_CACHEABLE
 	orreq	r2, r2, #PTE_EXT_TEX(0x5)
 #endif
 
-	tst	r3, #L_PTE_PRESENT | L_PTE_YOUNG	@ Present and Young?
+	tst	r3, #L_PTE_PRESENT | L_PTE_YOUNG	@ present and young?
 	movne	r2, #0				@ no -> fault
 
 	str	r2, [r0]			@ hardware version
 	mov	ip, #0
-	mcr	p15, 0, r0, c7, c10, 1		@ Clean D cache line mcr
-	mcr	p15, 0, ip, c7, c10, 4		@ Drain Write Buffer
+	mcr	p15, 0, r0, c7, c10, 1		@ clean L1 D line
+	mcr	p15, 0, ip, c7, c10, 4		@ data write barrier
 	mov	pc, lr
 
 	.ltorg
@@ -406,17 +404,18 @@ ENTRY(cpu_xsc3_set_pte_ext)
 __xsc3_setup:
 	mov	r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
 	msr	cpsr_c, r0
-	mcr	p15, 0, ip, c7, c7, 0		@ invalidate I, D caches & BTB
-	mcr	p15, 0, ip, c7, c10, 4		@ Drain Write Buffer
-	mcr	p15, 0, ip, c7, c5, 4		@ Prefetch Flush
-	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I, D TLBs
+	mcr	p15, 0, ip, c7, c7, 0		@ invalidate L1 caches and BTB
+	mcr	p15, 0, ip, c7, c10, 4		@ data write barrier
+	mcr	p15, 0, ip, c7, c5, 4		@ prefetch flush
+	mcr	p15, 0, ip, c8, c7, 0		@ invalidate I and D TLBs
 #if L2_CACHE_ENABLE
 	orr	r4, r4, #0x18			@ cache the page table in L2
 #endif
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
-	mov	r0, #1				@ Allow access to CP0 and CP13
-	orr	r0, r0, #1 << 13		@ Its undefined whether this
-	mcr	p15, 0, r0, c15, c1, 0		@ affects USR or SVC modes
+
+	mov	r0, #0				@ don't allow CP access
+	mcr	p15, 0, r0, c15, c1, 0		@ write CP access register
+
 	mrc	p15, 0, r0, c1, c0, 1		@ get auxiliary control reg
 	and	r0, r0, #2			@ preserve bit P bit setting
 #if L2_CACHE_ENABLE
@@ -427,9 +426,9 @@ __xsc3_setup:
 	adr	r5, xsc3_crval
 	ldmia	r5, {r5, r6}
 	mrc	p15, 0, r0, c1, c0, 0		@ get control register
-	bic	r0, r0, r5			@ .... .... .... ..A.
-	orr	r0, r0, r6			@ .... .... .... .C.M
-	orr	r0, r0, #0x00000800		@ ..VI Z..S .... ....
+	bic	r0, r0, r5			@ ..V. ..R. .... ..A.
+	orr	r0, r0, r6			@ ..VI Z..S .... .C.M (mmu)
+						@ ...I Z..S .... .... (uc)
 #if L2_CACHE_ENABLE
 	orr 	r0, r0, #0x04000000		@ L2 enable
 #endif
@@ -439,7 +438,7 @@ __xsc3_setup:
 
 	.type	xsc3_crval, #object
 xsc3_crval:
-	crval	clear=0x04003b02, mmuset=0x00003105, ucset=0x00001100
+	crval	clear=0x04002202, mmuset=0x00003905, ucset=0x00001900
 
 	__INITDATA
 
@@ -474,7 +473,7 @@ cpu_elf_name:
 
 	.type	cpu_xsc3_name, #object
 cpu_xsc3_name:
-	.asciz	"XScale-Core3"
+	.asciz	"XScale-V3 based processor"
 	.size	cpu_xsc3_name, . - cpu_xsc3_name
 
 	.align
@@ -490,7 +489,7 @@ __xsc3_proc_info:
 		PMD_SECT_CACHEABLE | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	.long   PMD_TYPE_SECT | \
+	.long	PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
 	b	__xsc3_setup
diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S
index fd6adde3909..20f84bbaa9b 100644
--- a/arch/arm/mm/tlb-v6.S
+++ b/arch/arm/mm/tlb-v6.S
@@ -53,6 +53,8 @@ ENTRY(v6wbi_flush_user_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
+	mcr	p15, 0, ip, c7, c5, 6		@ flush BTAC/BTB
+	mcr	p15, 0, ip, c7, c10, 4		@ data synchronization barrier
 	mov	pc, lr
 
 /*
@@ -80,7 +82,9 @@ ENTRY(v6wbi_flush_kern_tlb_range)
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
+	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ data synchronization barrier
+	mcr	p15, 0, r2, c7, c5, 4		@ prefetch flush
 	mov	pc, lr
 
 	.section ".text.init", #alloc, #execinstr