Merge commit 'v2.6.37-rc8' into x86/apic

Conflicts:
	arch/x86/include/asm/io_apic.h

Merge reason: move to a fresh -rc, resolve the conflict.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

31 files changed, 555 insertions, 131 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index a0a2928..4414a01 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -779,6 +779,14 @@ config CACHE_L2X0
 	help
 	  This option enables the L2x0 PrimeCell.
 
+config CACHE_PL310
+	bool
+	depends on CACHE_L2X0
+	default y if CPU_V7 && !CPU_V6
+	help
+	  This option enables optimisations for the PL310 cache
+	  controller.
+
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
 	depends on (ARCH_DOVE || ARCH_MMP)
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index 7148e53..1fa6f71 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -38,6 +38,17 @@
 #define CACHE_DLIMIT	(CACHE_DSIZE * 2)
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(fa_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(fa_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular address
@@ -233,6 +244,7 @@ ENDPROC(fa_dma_unmap_area)
 
 	.type	fa_cache_fns, #object
 ENTRY(fa_cache_fns)
+	.long	fa_flush_icache_all
 	.long	fa_flush_kern_cache_all
 	.long	fa_flush_user_cache_all
 	.long	fa_flush_user_cache_range
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9982eb3..170c9bb 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -28,14 +28,24 @@
 static void __iomem *l2x0_base;
 static DEFINE_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
+static uint32_t l2x0_size;
 
-static inline void cache_wait(void __iomem *reg, unsigned long mask)
+static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
-	/* wait for the operation to complete */
+	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
 		;
 }
 
+#ifdef CONFIG_CACHE_PL310
+static inline void cache_wait(void __iomem *reg, unsigned long mask)
+{
+	/* cache operations by line are atomic on PL310 */
+}
+#else
+#define cache_wait	cache_wait_way
+#endif
+
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
@@ -103,14 +113,40 @@ static void l2x0_cache_sync(void)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static inline void l2x0_inv_all(void)
+static void l2x0_flush_all(void)
+{
+	unsigned long flags;
+
+	/* clean all ways */
+	spin_lock_irqsave(&l2x0_lock, flags);
+	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
+	cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
+	cache_sync();
+	spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2x0_clean_all(void)
+{
+	unsigned long flags;
+
+	/* clean all ways */
+	spin_lock_irqsave(&l2x0_lock, flags);
+	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY);
+	cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask);
+	cache_sync();
+	spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2x0_inv_all(void)
 {
 	unsigned long flags;
 
 	/* invalidate all ways */
 	spin_lock_irqsave(&l2x0_lock, flags);
+	/* Invalidating when L2 is enabled is a nono */
+	BUG_ON(readl(l2x0_base + L2X0_CTRL) & 1);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
-	cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
+	cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
@@ -159,6 +195,11 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
+	if ((end - start) >= l2x0_size) {
+		l2x0_clean_all();
+		return;
+	}
+
 	spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
@@ -184,6 +225,11 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
+	if ((end - start) >= l2x0_size) {
+		l2x0_flush_all();
+		return;
+	}
+
 	spin_lock_irqsave(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
@@ -206,10 +252,20 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
+static void l2x0_disable(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&l2x0_lock, flags);
+	writel(0, l2x0_base + L2X0_CTRL);
+	spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
 void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 {
 	__u32 aux;
 	__u32 cache_id;
+	__u32 way_size = 0;
 	int ways;
 	const char *type;
 
@@ -244,6 +300,13 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	l2x0_way_mask = (1 << ways) - 1;
 
 	/*
+	 * L2 cache Size =  Way size * Number of ways
+	 */
+	way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
+	way_size = 1 << (way_size + 3);
+	l2x0_size = ways * way_size * SZ_1K;
+
+	/*
 	 * Check if l2x0 controller is already enabled.
 	 * If you are booting from non-secure mode
 	 * accessing the below registers will fault.
@@ -263,8 +326,11 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 	outer_cache.clean_range = l2x0_clean_range;
 	outer_cache.flush_range = l2x0_flush_range;
 	outer_cache.sync = l2x0_cache_sync;
+	outer_cache.flush_all = l2x0_flush_all;
+	outer_cache.inv_all = l2x0_inv_all;
+	outer_cache.disable = l2x0_disable;
 
 	printk(KERN_INFO "%s cache controller enabled\n", type);
-	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n",
-			 ways, cache_id, aux);
+	printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n",
+			ways, cache_id, aux, l2x0_size);
 }
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index c2ff3c5..2e2bc40 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -13,6 +13,15 @@
 #include "proc-macros.S"
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(v3_flush_icache_all)
+	mov	pc, lr
+ENDPROC(v3_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -122,6 +131,7 @@ ENDPROC(v3_dma_map_area)
 
 	.type	v3_cache_fns, #object
 ENTRY(v3_cache_fns)
+	.long	v3_flush_icache_all
 	.long	v3_flush_kern_cache_all
 	.long	v3_flush_user_cache_all
 	.long	v3_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 4810f7e..a8fefb5 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -13,6 +13,15 @@
 #include "proc-macros.S"
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(v4_flush_icache_all)
+	mov	pc, lr
+ENDPROC(v4_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -134,6 +143,7 @@ ENDPROC(v4_dma_map_area)
 
 	.type	v4_cache_fns, #object
 ENTRY(v4_cache_fns)
+	.long	v4_flush_icache_all
 	.long	v4_flush_kern_cache_all
 	.long	v4_flush_user_cache_all
 	.long	v4_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index df8368a..d3644db 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -51,6 +51,17 @@ flush_base:
 	.text
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(v4wb_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(v4wb_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular address
@@ -244,6 +255,7 @@ ENDPROC(v4wb_dma_unmap_area)
 
 	.type	v4wb_cache_fns, #object
 ENTRY(v4wb_cache_fns)
+	.long	v4wb_flush_icache_all
 	.long	v4wb_flush_kern_cache_all
 	.long	v4wb_flush_user_cache_all
 	.long	v4wb_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index 45c7031..49c2b66 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -41,6 +41,17 @@
 #define CACHE_DLIMIT	16384
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(v4wt_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(v4wt_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -188,6 +199,7 @@ ENDPROC(v4wt_dma_map_area)
 
 	.type	v4wt_cache_fns, #object
 ENTRY(v4wt_cache_fns)
+	.long	v4wt_flush_icache_all
 	.long	v4wt_flush_kern_cache_all
 	.long	v4wt_flush_user_cache_all
 	.long	v4wt_flush_user_cache_range
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 99fa688..c96fa1b 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -203,6 +203,10 @@ ENTRY(v6_flush_kern_dcache_area)
  *	- end     - virtual end address of region
  */
 v6_dma_inv_range:
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldrb	r2, [r0]			@ read for ownership
+	strb	r2, [r0]			@ write for ownership
+#endif
 	tst	r0, #D_CACHE_LINE_SIZE - 1
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -211,6 +215,10 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r0, c7, c11, 1		@ clean unified line
 #endif
 	tst	r1, #D_CACHE_LINE_SIZE - 1
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldrneb	r2, [r1, #-1]			@ read for ownership
+	strneb	r2, [r1, #-1]			@ write for ownership
+#endif
 	bic	r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
 	mcrne	p15, 0, r1, c7, c14, 1		@ clean & invalidate D line
@@ -218,10 +226,6 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r1, c7, c15, 1		@ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_DMA_CACHE_RWFO
-	ldr	r2, [r0]			@ read for ownership
-	str	r2, [r0]			@ write for ownership
-#endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D line
 #else
@@ -229,6 +233,10 @@ v6_dma_inv_range:
 #endif
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldrlo	r2, [r0]			@ read for ownership
+	strlo	r2, [r0]			@ write for ownership
+#endif
 	blo	1b
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
@@ -263,12 +271,12 @@ v6_dma_clean_range:
  *	- end     - virtual end address of region
  */
 ENTRY(v6_dma_flush_range)
-	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
-1:
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldr	r2, [r0]			@ read for ownership
-	str	r2, [r0]			@ write for ownership
+	ldrb	r2, [r0]		@ read for ownership
+	strb	r2, [r0]		@ write for ownership
 #endif
+	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
+1:
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line
 #else
@@ -276,6 +284,10 @@ ENTRY(v6_dma_flush_range)
 #endif
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldrlob	r2, [r0]			@ read for ownership
+	strlob	r2, [r0]			@ write for ownership
+#endif
 	blo	1b
 	mov	r0, #0
 	mcr	p15, 0, r0, c7, c10, 4		@ drain write buffer
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index a3ebf7a..6136e68 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -173,15 +173,22 @@ ENTRY(v7_coherent_user_range)
  UNWIND(.fnstart		)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
-	bic	r0, r0, r3
+	bic	r12, r0, r3
 1:
- USER(	mcr	p15, 0, r0, c7, c11, 1	)	@ clean D line to the point of unification
+ USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
+	add	r12, r12, r2
+	cmp	r12, r1
+	blo	1b
 	dsb
- USER(	mcr	p15, 0, r0, c7, c5, 1	)	@ invalidate I line
-	add	r0, r0, r2
+	icache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r12, r0, r3
 2:
-	cmp	r0, r1
-	blo	1b
+ USER(	mcr	p15, 0, r12, c7, c5, 1	)	@ invalidate I line
+	add	r12, r12, r2
+	cmp	r12, r1
+	blo	2b
+3:
 	mov	r0, #0
 	ALT_SMP(mcr	p15, 0, r0, c7, c1, 6)	@ invalidate BTB Inner Shareable
 	ALT_UP(mcr	p15, 0, r0, c7, c5, 6)	@ invalidate BTB
@@ -194,10 +201,10 @@ ENTRY(v7_coherent_user_range)
  * isn't mapped, just try the next page.
  */
 9001:
-	mov	r0, r0, lsr #12
-	mov	r0, r0, lsl #12
-	add	r0, r0, #4096
-	b	2b
+	mov	r12, r12, lsr #12
+	mov	r12, r12, lsl #12
+	add	r12, r12, #4096
+	b	3b
  UNWIND(.fnend		)
 ENDPROC(v7_coherent_kern_range)
 ENDPROC(v7_coherent_user_range)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e4dd064..ac6a361 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -198,7 +198,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 	 * fragmentation of the DMA space, and also prevents allocations
 	 * smaller than a section from crossing a section boundary.
 	 */
-	bit = fls(size - 1) + 1;
+	bit = fls(size - 1);
 	if (bit > SECTION_SHIFT)
 		bit = SECTION_SHIFT;
 	align = 1 << bit;
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 8440d95..83e59f8 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -66,6 +66,30 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	return ret;
 }
 
+#if USE_SPLIT_PTLOCKS
+/*
+ * If we are using split PTE locks, then we need to take the page
+ * lock here.  Otherwise we are using shared mm->page_table_lock
+ * which is already locked, thus cannot take it.
+ */
+static inline void do_pte_lock(spinlock_t *ptl)
+{
+	/*
+	 * Use nested version here to indicate that we are already
+	 * holding one similar spinlock.
+	 */
+	spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+}
+
+static inline void do_pte_unlock(spinlock_t *ptl)
+{
+	spin_unlock(ptl);
+}
+#else /* !USE_SPLIT_PTLOCKS */
+static inline void do_pte_lock(spinlock_t *ptl) {}
+static inline void do_pte_unlock(spinlock_t *ptl) {}
+#endif /* USE_SPLIT_PTLOCKS */
+
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pfn)
 {
@@ -89,13 +113,13 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	 * open-code the spin-locking.
 	 */
 	ptl = pte_lockptr(vma->vm_mm, pmd);
-	pte = pte_offset_map_nested(pmd, address);
-	spin_lock(ptl);
+	pte = pte_offset_map(pmd, address);
+	do_pte_lock(ptl);
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	spin_unlock(ptl);
-	pte_unmap_nested(pte);
+	do_pte_unlock(ptl);
+	pte_unmap(pte);
 
 	return ret;
 }
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 1fbdb55..c435fd9 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -36,18 +36,17 @@ void kunmap(struct page *page)
 }
 EXPORT_SYMBOL(kunmap);
 
-void *kmap_atomic(struct page *page, enum km_type type)
+void *__kmap_atomic(struct page *page)
 {
 	unsigned int idx;
 	unsigned long vaddr;
 	void *kmap;
+	int type;
 
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
 
-	debug_kmap_atomic(type);
-
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
 	 * There is no cache coherency issue when non VIVT, so force the
@@ -61,6 +60,8 @@ void *kmap_atomic(struct page *page, enum km_type type)
 	if (kmap)
 		return kmap;
 
+	type = kmap_atomic_idx_push();
+
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
@@ -80,14 +81,17 @@ void *kmap_atomic(struct page *page, enum km_type type)
 
 	return (void *)vaddr;
 }
-EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(__kmap_atomic);
 
-void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type)
+void __kunmap_atomic(void *kvaddr)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	unsigned int idx = type + KM_TYPE_NR * smp_processor_id();
+	int idx, type;
 
 	if (kvaddr >= (void *)FIXADDR_START) {
+		type = kmap_atomic_idx();
+		idx = type + KM_TYPE_NR * smp_processor_id();
+
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
@@ -97,21 +101,23 @@ void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type)
 #else
 		(void) idx;  /* to kill a warning */
 #endif
+		kmap_atomic_idx_pop();
 	} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
 }
-EXPORT_SYMBOL(kunmap_atomic_notypecheck);
+EXPORT_SYMBOL(__kunmap_atomic);
 
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
+void *kmap_atomic_pfn(unsigned long pfn)
 {
-	unsigned int idx;
 	unsigned long vaddr;
+	int idx, type;
 
 	pagefault_disable();
 
+	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 7fd9b5e..5164069 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
+#include <linux/sort.h>
 
 #include <asm/mach-types.h>
 #include <asm/sections.h>
@@ -121,9 +122,10 @@ void show_mem(void)
 	printk("%d pages swap cached\n", cached);
 }
 
-static void __init find_limits(struct meminfo *mi,
-	unsigned long *min, unsigned long *max_low, unsigned long *max_high)
+static void __init find_limits(unsigned long *min, unsigned long *max_low,
+	unsigned long *max_high)
 {
+	struct meminfo *mi = &meminfo;
 	int i;
 
 	*min = -1UL;
@@ -147,14 +149,13 @@ static void __init find_limits(struct meminfo *mi,
 	}
 }
 
-static void __init arm_bootmem_init(struct meminfo *mi,
-	unsigned long start_pfn, unsigned long end_pfn)
+static void __init arm_bootmem_init(unsigned long start_pfn,
+	unsigned long end_pfn)
 {
 	struct memblock_region *reg;
 	unsigned int boot_pages;
 	phys_addr_t bitmap;
 	pg_data_t *pgdat;
-	int i;
 
 	/*
 	 * Allocate the bootmem bitmap page.  This must be in a region
@@ -172,30 +173,39 @@ static void __init arm_bootmem_init(struct meminfo *mi,
 	pgdat = NODE_DATA(0);
 	init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
 
-	for_each_bank(i, mi) {
-		struct membank *bank = &mi->bank[i];
-		if (!bank->highmem)
-			free_bootmem(bank_phys_start(bank), bank_phys_size(bank));
+	/* Free the lowmem regions from memblock into bootmem. */
+	for_each_memblock(memory, reg) {
+		unsigned long start = memblock_region_memory_base_pfn(reg);
+		unsigned long end = memblock_region_memory_end_pfn(reg);
+
+		if (end >= end_pfn)
+			end = end_pfn;
+		if (start >= end)
+			break;
+
+		free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
 	}
 
-	/*
-	 * Reserve the memblock reserved regions in bootmem.
-	 */
+	/* Reserve the lowmem memblock reserved regions in bootmem. */
 	for_each_memblock(reserved, reg) {
-		phys_addr_t start = memblock_region_reserved_base_pfn(reg);
-		phys_addr_t end = memblock_region_reserved_end_pfn(reg);
-		if (start >= start_pfn && end <= end_pfn)
-			reserve_bootmem_node(pgdat, __pfn_to_phys(start),
-					     (end - start) << PAGE_SHIFT,
-					     BOOTMEM_DEFAULT);
+		unsigned long start = memblock_region_reserved_base_pfn(reg);
+		unsigned long end = memblock_region_reserved_end_pfn(reg);
+
+		if (end >= end_pfn)
+			end = end_pfn;
+		if (start >= end)
+			break;
+
+		reserve_bootmem(__pfn_to_phys(start),
+			        (end - start) << PAGE_SHIFT, BOOTMEM_DEFAULT);
 	}
 }
 
-static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min,
-	unsigned long max_low, unsigned long max_high)
+static void __init arm_bootmem_free(unsigned long min, unsigned long max_low,
+	unsigned long max_high)
 {
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	int i;
+	struct memblock_region *reg;
 
 	/*
 	 * initialise the zones.
@@ -217,13 +227,20 @@ static void __init arm_bootmem_free(struct meminfo *mi, unsigned long min,
 	 *  holes = node_size - sum(bank_sizes)
 	 */
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
-	for_each_bank(i, mi) {
-		int idx = 0;
+	for_each_memblock(memory, reg) {
+		unsigned long start = memblock_region_memory_base_pfn(reg);
+		unsigned long end = memblock_region_memory_end_pfn(reg);
+
+		if (start < max_low) {
+			unsigned long low_end = min(end, max_low);
+			zhole_size[0] -= low_end - start;
+		}
 #ifdef CONFIG_HIGHMEM
-		if (mi->bank[i].highmem)
-			idx = ZONE_HIGHMEM;
+		if (end > max_low) {
+			unsigned long high_start = max(start, max_low);
+			zhole_size[ZONE_HIGHMEM] -= end - high_start;
+		}
 #endif
-		zhole_size[idx] -= bank_pfn_size(&mi->bank[i]);
 	}
 
 	/*
@@ -256,10 +273,19 @@ static void arm_memory_present(void)
 }
 #endif
 
+static int __init meminfo_cmp(const void *_a, const void *_b)
+{
+	const struct membank *a = _a, *b = _b;
+	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
+	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
+}
+
 void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 {
 	int i;
 
+	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
+
 	memblock_init();
 	for (i = 0; i < mi->nr_banks; i++)
 		memblock_add(mi->bank[i].start, mi->bank[i].size);
@@ -292,14 +318,13 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc)
 
 void __init bootmem_init(void)
 {
-	struct meminfo *mi = &meminfo;
 	unsigned long min, max_low, max_high;
 
 	max_low = max_high = 0;
 
-	find_limits(mi, &min, &max_low, &max_high);
+	find_limits(&min, &max_low, &max_high);
 
-	arm_bootmem_init(mi, min, max_low);
+	arm_bootmem_init(min, max_low);
 
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),
@@ -317,7 +342,7 @@ void __init bootmem_init(void)
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
-	arm_bootmem_free(mi, min, max_low, max_high);
+	arm_bootmem_free(min, max_low, max_high);
 
 	high_memory = __va((max_low << PAGE_SHIFT) - 1) + 1;
 
@@ -411,6 +436,56 @@ static void __init free_unused_memmap(struct meminfo *mi)
 	}
 }
 
+static void __init free_highpages(void)
+{
+#ifdef CONFIG_HIGHMEM
+	unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET;
+	struct memblock_region *mem, *res;
+
+	/* set highmem page free */
+	for_each_memblock(memory, mem) {
+		unsigned long start = memblock_region_memory_base_pfn(mem);
+		unsigned long end = memblock_region_memory_end_pfn(mem);
+
+		/* Ignore complete lowmem entries */
+		if (end <= max_low)
+			continue;
+
+		/* Truncate partial highmem entries */
+		if (start < max_low)
+			start = max_low;
+
+		/* Find and exclude any reserved regions */
+		for_each_memblock(reserved, res) {
+			unsigned long res_start, res_end;
+
+			res_start = memblock_region_reserved_base_pfn(res);
+			res_end = memblock_region_reserved_end_pfn(res);
+
+			if (res_end < start)
+				continue;
+			if (res_start < start)
+				res_start = start;
+			if (res_start > end)
+				res_start = end;
+			if (res_end > end)
+				res_end = end;
+			if (res_start != start)
+				totalhigh_pages += free_area(start, res_start,
+							     NULL);
+			start = res_end;
+			if (start == end)
+				break;
+		}
+
+		/* And now free anything which remains */
+		if (start < end)
+			totalhigh_pages += free_area(start, end, NULL);
+	}
+	totalram_pages += totalhigh_pages;
+#endif
+}
+
 /*
  * mem_init() marks the free areas in the mem_map and tells us how much
  * memory is free.  This is done after various parts of the system have
@@ -419,6 +494,7 @@ static void __init free_unused_memmap(struct meminfo *mi)
 void __init mem_init(void)
 {
 	unsigned long reserved_pages, free_pages;
+	struct memblock_region *reg;
 	int i;
 #ifdef CONFIG_HAVE_TCM
 	/* These pointers are filled in on TCM detection */
@@ -439,16 +515,7 @@ void __init mem_init(void)
 				    __phys_to_pfn(__pa(swapper_pg_dir)), NULL);
 #endif
 
-#ifdef CONFIG_HIGHMEM
-	/* set highmem page free */
-	for_each_bank (i, &meminfo) {
-		unsigned long start = bank_pfn_start(&meminfo.bank[i]);
-		unsigned long end = bank_pfn_end(&meminfo.bank[i]);
-		if (start >= max_low_pfn + PHYS_PFN_OFFSET)
-			totalhigh_pages += free_area(start, end, NULL);
-	}
-	totalram_pages += totalhigh_pages;
-#endif
+	free_highpages();
 
 	reserved_pages = free_pages = 0;
 
@@ -478,9 +545,11 @@ void __init mem_init(void)
 	 */
 	printk(KERN_INFO "Memory:");
 	num_physpages = 0;
-	for (i = 0; i < meminfo.nr_banks; i++) {
-		num_physpages += bank_pfn_size(&meminfo.bank[i]);
-		printk(" %ldMB", bank_phys_size(&meminfo.bank[i]) >> 20);
+	for_each_memblock(memory, reg) {
+		unsigned long pages = memblock_region_memory_end_pfn(reg) -
+			memblock_region_memory_base_pfn(reg);
+		num_physpages += pages;
+		printk(" %ldMB", pages >> (20 - PAGE_SHIFT));
 	}
 	printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 17e7b0b..55c17a6 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -206,8 +206,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	 */
 	if (pfn_valid(pfn)) {
 		printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
-		       KERN_WARNING "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
-		       KERN_WARNING "will fail in the next kernel release.  Please fix your driver.\n");
+		       "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
+		       "will fail in the next kernel release.  Please fix your driver.\n");
 		WARN_ON(1);
 	}
 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index c32f731..72ad3e1 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -14,7 +14,6 @@
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
-#include <linux/sort.h>
 #include <linux/fs.h>
 
 #include <asm/cputype.h>
@@ -265,17 +264,17 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_DTCM] = {
-		.prot_pte	= L_PTE_PRESENT | L_PTE_YOUNG |
-		                  L_PTE_DIRTY | L_PTE_WRITE,
-		.prot_l1	= PMD_TYPE_TABLE,
-		.prot_sect	= PMD_TYPE_SECT | PMD_SECT_XN,
-		.domain		= DOMAIN_KERNEL,
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_WRITE,
+		.prot_l1   = PMD_TYPE_TABLE,
+		.prot_sect = PMD_TYPE_SECT | PMD_SECT_XN,
+		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_ITCM] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
-				L_PTE_USER | L_PTE_EXEC,
+				L_PTE_WRITE | L_PTE_EXEC,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_IO,
+		.domain    = DOMAIN_KERNEL,
 	},
 };
 
@@ -745,13 +744,14 @@ static int __init early_vmalloc(char *arg)
 }
 early_param("vmalloc", early_vmalloc);
 
-phys_addr_t lowmem_end_addr;
+static phys_addr_t lowmem_limit __initdata = 0;
 
 static void __init sanity_check_meminfo(void)
 {
 	int i, j, highmem = 0;
 
-	lowmem_end_addr = __pa(vmalloc_min - 1) + 1;
+	lowmem_limit = __pa(vmalloc_min - 1) + 1;
+	memblock_set_current_limit(lowmem_limit);
 
 	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
 		struct membank *bank = &meminfo.bank[j];
@@ -852,6 +852,7 @@ static void __init sanity_check_meminfo(void)
 static inline void prepare_page_table(void)
 {
 	unsigned long addr;
+	phys_addr_t end;
 
 	/*
 	 * Clear out all the mappings below the kernel image.
@@ -867,10 +868,17 @@ static inline void prepare_page_table(void)
 		pmd_clear(pmd_off_k(addr));
 
 	/*
+	 * Find the end of the first block of lowmem.
+	 */
+	end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
+	if (end >= lowmem_limit)
+		end = lowmem_limit;
+
+	/*
 	 * Clear out all the kernel space mappings, except for the first
 	 * memory bank, up to the end of the vmalloc region.
 	 */
-	for (addr = __phys_to_virt(bank_phys_end(&meminfo.bank[0]));
+	for (addr = __phys_to_virt(end);
 	     addr < VMALLOC_END; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
@@ -987,37 +995,28 @@ static void __init kmap_init(void)
 #endif
 }
 
-static inline void map_memory_bank(struct membank *bank)
-{
-	struct map_desc map;
-
-	map.pfn = bank_pfn_start(bank);
-	map.virtual = __phys_to_virt(bank_phys_start(bank));
-	map.length = bank_phys_size(bank);
-	map.type = MT_MEMORY;
-
-	create_mapping(&map);
-}
-
 static void __init map_lowmem(void)
 {
-	struct meminfo *mi = &meminfo;
-	int i;
+	struct memblock_region *reg;
 
 	/* Map all the lowmem memory banks. */
-	for (i = 0; i < mi->nr_banks; i++) {
-		struct membank *bank = &mi->bank[i];
+	for_each_memblock(memory, reg) {
+		phys_addr_t start = reg->base;
+		phys_addr_t end = start + reg->size;
+		struct map_desc map;
+
+		if (end > lowmem_limit)
+			end = lowmem_limit;
+		if (start >= end)
+			break;
 
-		if (!bank->highmem)
-			map_memory_bank(bank);
-	}
-}
+		map.pfn = __phys_to_pfn(start);
+		map.virtual = __phys_to_virt(start);
+		map.length = end - start;
+		map.type = MT_MEMORY;
 
-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-	const struct membank *a = _a, *b = _b;
-	long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-	return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
+		create_mapping(&map);
+	}
 }
 
 /*
@@ -1028,8 +1027,6 @@ void __init paging_init(struct machine_desc *mdesc)
 {
 	void *zero_page;
 
-	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-
 	build_mem_type_table();
 	sanity_check_meminfo();
 	prepare_page_table();
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index be5f58e..69bbfc6 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -57,9 +57,9 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 			goto no_pte;
 
 		init_pmd = pmd_offset(init_pgd, 0);
-		init_pte = pte_offset_map_nested(init_pmd, 0);
+		init_pte = pte_offset_map(init_pmd, 0);
 		set_pte_ext(new_pte, *init_pte, 0);
-		pte_unmap_nested(init_pte);
+		pte_unmap(init_pte);
 		pte_unmap(new_pte);
 	}
 
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index a6f5f84..bcf748d 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -119,6 +119,20 @@ ENTRY(cpu_arm1020_do_idle)
 /* ================================= CACHE ================================ */
 
 	.align	5
+
+/*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm1020_flush_icache_all)
+#ifndef CONFIG_CPU_ICACHE_DISABLE
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+#endif
+	mov	pc, lr
+ENDPROC(arm1020_flush_icache_all)
+
 /*
  *	flush_user_cache_all()
  *
@@ -351,6 +365,7 @@ ENTRY(arm1020_dma_unmap_area)
 ENDPROC(arm1020_dma_unmap_area)
 
 ENTRY(arm1020_cache_fns)
+	.long	arm1020_flush_icache_all
 	.long	arm1020_flush_kern_cache_all
 	.long	arm1020_flush_user_cache_all
 	.long	arm1020_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index afc06b9..ab7ec26 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -119,6 +119,20 @@ ENTRY(cpu_arm1020e_do_idle)
 /* ================================= CACHE ================================ */
 
 	.align	5
+
+/*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm1020e_flush_icache_all)
+#ifndef CONFIG_CPU_ICACHE_DISABLE
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+#endif
+	mov	pc, lr
+ENDPROC(arm1020e_flush_icache_all)
+
 /*
  *	flush_user_cache_all()
  *
@@ -337,6 +351,7 @@ ENTRY(arm1020e_dma_unmap_area)
 ENDPROC(arm1020e_dma_unmap_area)
 
 ENTRY(arm1020e_cache_fns)
+	.long	arm1020e_flush_icache_all
 	.long	arm1020e_flush_kern_cache_all
 	.long	arm1020e_flush_user_cache_all
 	.long	arm1020e_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 8915e0b..831c5e5 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -108,6 +108,20 @@ ENTRY(cpu_arm1022_do_idle)
 /* ================================= CACHE ================================ */
 
 	.align	5
+
+/*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm1022_flush_icache_all)
+#ifndef CONFIG_CPU_ICACHE_DISABLE
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+#endif
+	mov	pc, lr
+ENDPROC(arm1022_flush_icache_all)
+
 /*
  *	flush_user_cache_all()
  *
@@ -326,6 +340,7 @@ ENTRY(arm1022_dma_unmap_area)
 ENDPROC(arm1022_dma_unmap_area)
 
 ENTRY(arm1022_cache_fns)
+	.long	arm1022_flush_icache_all
 	.long	arm1022_flush_kern_cache_all
 	.long	arm1022_flush_user_cache_all
 	.long	arm1022_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index ff446c5..e3f7e9a 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -108,6 +108,20 @@ ENTRY(cpu_arm1026_do_idle)
 /* ================================= CACHE ================================ */
 
 	.align	5
+
+/*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm1026_flush_icache_all)
+#ifndef CONFIG_CPU_ICACHE_DISABLE
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+#endif
+	mov	pc, lr
+ENDPROC(arm1026_flush_icache_all)
+
 /*
  *	flush_user_cache_all()
  *
@@ -320,6 +334,7 @@ ENTRY(arm1026_dma_unmap_area)
 ENDPROC(arm1026_dma_unmap_area)
 
 ENTRY(arm1026_cache_fns)
+	.long	arm1026_flush_icache_all
 	.long	arm1026_flush_kern_cache_all
 	.long	arm1026_flush_user_cache_all
 	.long	arm1026_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index fecf570..6109f27 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -110,6 +110,17 @@ ENTRY(cpu_arm920_do_idle)
 #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm920_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm920_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -305,6 +316,7 @@ ENTRY(arm920_dma_unmap_area)
 ENDPROC(arm920_dma_unmap_area)
 
 ENTRY(arm920_cache_fns)
+	.long	arm920_flush_icache_all
 	.long	arm920_flush_kern_cache_all
 	.long	arm920_flush_user_cache_all
 	.long	arm920_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index e3cbf87..bb2f0f4 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -112,6 +112,17 @@ ENTRY(cpu_arm922_do_idle)
 #ifndef CONFIG_CPU_DCACHE_WRITETHROUGH
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm922_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm922_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular
@@ -307,6 +318,7 @@ ENTRY(arm922_dma_unmap_area)
 ENDPROC(arm922_dma_unmap_area)
 
 ENTRY(arm922_cache_fns)
+	.long	arm922_flush_icache_all
 	.long	arm922_flush_kern_cache_all
 	.long	arm922_flush_user_cache_all
 	.long	arm922_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 572424c..c13e01a 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -145,6 +145,17 @@ ENTRY(cpu_arm925_do_idle)
 	mov	pc, lr
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm925_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm925_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular
@@ -362,6 +373,7 @@ ENTRY(arm925_dma_unmap_area)
 ENDPROC(arm925_dma_unmap_area)
 
 ENTRY(arm925_cache_fns)
+	.long	arm925_flush_icache_all
 	.long	arm925_flush_kern_cache_all
 	.long	arm925_flush_user_cache_all
 	.long	arm925_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 63d168b..42eb431 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -111,6 +111,17 @@ ENTRY(cpu_arm926_do_idle)
 	mov	pc, lr
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm926_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm926_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular
@@ -325,6 +336,7 @@ ENTRY(arm926_dma_unmap_area)
 ENDPROC(arm926_dma_unmap_area)
 
 ENTRY(arm926_cache_fns)
+	.long	arm926_flush_icache_all
 	.long	arm926_flush_kern_cache_all
 	.long	arm926_flush_user_cache_all
 	.long	arm926_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index f6a6282..7b11cdb 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -68,6 +68,17 @@ ENTRY(cpu_arm940_do_idle)
 	mov	pc, lr
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm940_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm940_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  */
 ENTRY(arm940_flush_user_cache_all)
@@ -254,6 +265,7 @@ ENTRY(arm940_dma_unmap_area)
 ENDPROC(arm940_dma_unmap_area)
 
 ENTRY(arm940_cache_fns)
+	.long	arm940_flush_icache_all
 	.long	arm940_flush_kern_cache_all
 	.long	arm940_flush_user_cache_all
 	.long	arm940_flush_user_cache_range
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index ea2e7f2..1a5bbf08 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -75,6 +75,17 @@ ENTRY(cpu_arm946_do_idle)
 	mov	pc, lr
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(arm946_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(arm946_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  */
 ENTRY(arm946_flush_user_cache_all)
@@ -296,6 +307,7 @@ ENTRY(arm946_dma_unmap_area)
 ENDPROC(arm946_dma_unmap_area)
 
 ENTRY(arm946_cache_fns)
+	.long	arm946_flush_icache_all
 	.long	arm946_flush_kern_cache_all
 	.long	arm946_flush_user_cache_all
 	.long	arm946_flush_user_cache_range
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 578da69..b4597ed 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -124,6 +124,17 @@ ENTRY(cpu_feroceon_do_idle)
 	mov	pc, lr
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(feroceon_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(feroceon_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Clean and invalidate all cache entries in a particular
@@ -401,6 +412,7 @@ ENTRY(feroceon_dma_unmap_area)
 ENDPROC(feroceon_dma_unmap_area)
 
 ENTRY(feroceon_cache_fns)
+	.long	feroceon_flush_icache_all
 	.long	feroceon_flush_kern_cache_all
 	.long	feroceon_flush_user_cache_all
 	.long	feroceon_flush_user_cache_range
@@ -412,6 +424,7 @@ ENTRY(feroceon_cache_fns)
 	.long	feroceon_dma_flush_range
 
 ENTRY(feroceon_range_cache_fns)
+	.long	feroceon_flush_icache_all
 	.long	feroceon_flush_kern_cache_all
 	.long	feroceon_flush_user_cache_all
 	.long	feroceon_flush_user_cache_range
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 7d63bea..b795afd 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -61,17 +61,27 @@
 	.endm
 
 /*
- * cache_line_size - get the cache line size from the CSIDR register
- * (available on ARMv7+). It assumes that the CSSR register was configured
- * to access the L1 data cache CSIDR.
+ * dcache_line_size - get the minimum D-cache line size from the CTR register
+ * on ARMv7.
  */
 	.macro	dcache_line_size, reg, tmp
-	mrc	p15, 1, \tmp, c0, c0, 0		@ read CSIDR
-	and	\tmp, \tmp, #7			@ cache line size encoding
-	mov	\reg, #16			@ size offset
+	mrc	p15, 0, \tmp, c0, c0, 1		@ read ctr
+	lsr	\tmp, \tmp, #16
+	and	\tmp, \tmp, #0xf		@ cache line size encoding
+	mov	\reg, #4			@ bytes per word
 	mov	\reg, \reg, lsl \tmp		@ actual cache line size
 	.endm
 
+/*
+ * icache_line_size - get the minimum I-cache line size from the CTR register
+ * on ARMv7.
+ */
+	.macro	icache_line_size, reg, tmp
+	mrc	p15, 0, \tmp, c0, c0, 1		@ read ctr
+	and	\tmp, \tmp, #0xf		@ cache line size encoding
+	mov	\reg, #4			@ bytes per word
+	mov	\reg, \reg, lsl \tmp		@ actual cache line size
+	.endm
 
 /*
  * Sanity check the PTE configuration for the code below - which makes
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 53cbe22..9b9ff5d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -381,7 +381,7 @@ __v7_ca9mp_proc_info:
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__v7_ca9mp_setup
+	W(b)	__v7_ca9mp_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
@@ -413,7 +413,7 @@ __v7_proc_info:
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__v7_setup
+	W(b)	__v7_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_TLS
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index cad07e4..ec26355 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -141,6 +141,17 @@ ENTRY(cpu_xsc3_do_idle)
 /* ================================= CACHE ================================ */
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(xsc3_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(xsc3_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -325,6 +336,7 @@ ENTRY(xsc3_dma_unmap_area)
 ENDPROC(xsc3_dma_unmap_area)
 
 ENTRY(xsc3_cache_fns)
+	.long	xsc3_flush_icache_all
 	.long	xsc3_flush_kern_cache_all
 	.long	xsc3_flush_user_cache_all
 	.long	xsc3_flush_user_cache_range
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index cb245ed..523408c 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -181,6 +181,17 @@ ENTRY(cpu_xscale_do_idle)
 /* ================================= CACHE ================================ */
 
 /*
+ *	flush_icache_all()
+ *
+ *	Unconditionally clean and invalidate the entire icache.
+ */
+ENTRY(xscale_flush_icache_all)
+	mov	r0, #0
+	mcr	p15, 0, r0, c7, c5, 0		@ invalidate I cache
+	mov	pc, lr
+ENDPROC(xscale_flush_icache_all)
+
+/*
  *	flush_user_cache_all()
  *
  *	Invalidate all cache entries in a particular address
@@ -397,6 +408,7 @@ ENTRY(xscale_dma_unmap_area)
 ENDPROC(xscale_dma_unmap_area)
 
 ENTRY(xscale_cache_fns)
+	.long	xscale_flush_icache_all
 	.long	xscale_flush_kern_cache_all
 	.long	xscale_flush_user_cache_all
 	.long	xscale_flush_user_cache_range