11 files changed, 408 insertions, 348 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9264d814cd7..7b7d4c36c11 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -774,5 +774,5 @@ config CACHE_XSC3L2
 
 config ARM_L1_CACHE_SHIFT
 	int
-	default 6 if ARCH_OMAP3
+	default 6 if ARCH_OMAP3 || ARCH_S5PC1XX
 	default 5
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 055cb2aa813..42352e75742 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -6,7 +6,7 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   iomap.o
 
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o ioremap.o mmap.o \
-				   pgd.o mmu.o
+				   pgd.o mmu.o vmregion.o
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index b480f1d3591..747f9a9021b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -99,18 +99,25 @@ void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
 
 	l2x0_base = base;
 
-	/* disable L2X0 */
-	writel(0, l2x0_base + L2X0_CTRL);
+	/*
+	 * Check if l2x0 controller is already enabled.
+	 * If you are booting from non-secure mode
+	 * accessing the below registers will fault.
+	 */
+	if (!(readl(l2x0_base + L2X0_CTRL) & 1)) {
 
-	aux = readl(l2x0_base + L2X0_AUX_CTRL);
-	aux &= aux_mask;
-	aux |= aux_val;
-	writel(aux, l2x0_base + L2X0_AUX_CTRL);
+		/* l2x0 controller is disabled */
 
-	l2x0_inv_all();
+		aux = readl(l2x0_base + L2X0_AUX_CTRL);
+		aux &= aux_mask;
+		aux |= aux_val;
+		writel(aux, l2x0_base + L2X0_AUX_CTRL);
 
-	/* enable L2X0 */
-	writel(1, l2x0_base + L2X0_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;
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 4127a7bddfe..841f355319b 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -41,6 +41,14 @@ static void v6_copy_user_highpage_nonaliasing(struct page *to,
 	kfrom = kmap_atomic(from, KM_USER0);
 	kto = kmap_atomic(to, KM_USER1);
 	copy_page(kto, kfrom);
+#ifdef CONFIG_HIGHMEM
+	/*
+	 * kmap_atomic() doesn't set the page virtual address, and
+	 * kunmap_atomic() takes care of cache flushing already.
+	 */
+	if (page_address(to) != NULL)
+#endif
+		__cpuc_flush_dcache_page(kto);
 	kunmap_atomic(kto, KM_USER1);
 	kunmap_atomic(kfrom, KM_USER0);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index b9590a7085c..26325cb5d36 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -63,194 +63,152 @@ static u64 get_coherent_dma_mask(struct device *dev)
 	return mask;
 }
 
-#ifdef CONFIG_MMU
 /*
- * These are the page tables (2MB each) covering uncached, DMA consistent allocations
+ * Allocate a DMA buffer for 'dev' of size 'size' using the
+ * specified gfp mask.  Note that 'size' must be page aligned.
  */
-static pte_t *consistent_pte[NUM_CONSISTENT_PTES];
-static DEFINE_SPINLOCK(consistent_lock);
+static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp)
+{
+	unsigned long order = get_order(size);
+	struct page *page, *p, *e;
+	void *ptr;
+	u64 mask = get_coherent_dma_mask(dev);
 
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- *  struct vm_struct {
- *    struct vm_region	region;
- *    unsigned long	flags;
- *    struct page	**pages;
- *    unsigned int	nr_pages;
- *    unsigned long	phys_addr;
- *  };
- *
- * get_vm_area() would then call vm_region_alloc with an appropriate
- * struct vm_region head (eg):
- *
- *  struct vm_region vmalloc_head = {
- *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
- *	.vm_start	= VMALLOC_START,
- *	.vm_end		= VMALLOC_END,
- *  };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vm_region_alloc().
- */
-struct arm_vm_region {
-	struct list_head	vm_list;
-	unsigned long		vm_start;
-	unsigned long		vm_end;
-	struct page		*vm_pages;
-	int			vm_active;
-};
+#ifdef CONFIG_DMA_API_DEBUG
+	u64 limit = (mask + 1) & ~mask;
+	if (limit && size >= limit) {
+		dev_warn(dev, "coherent allocation too big (requested %#x mask %#llx)\n",
+			size, mask);
+		return NULL;
+	}
+#endif
 
-static struct arm_vm_region consistent_head = {
-	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_start	= CONSISTENT_BASE,
-	.vm_end		= CONSISTENT_END,
-};
+	if (!mask)
+		return NULL;
 
-static struct arm_vm_region *
-arm_vm_region_alloc(struct arm_vm_region *head, size_t size, gfp_t gfp)
-{
-	unsigned long addr = head->vm_start, end = head->vm_end - size;
-	unsigned long flags;
-	struct arm_vm_region *c, *new;
-
-	new = kmalloc(sizeof(struct arm_vm_region), gfp);
-	if (!new)
-		goto out;
-
-	spin_lock_irqsave(&consistent_lock, flags);
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if ((addr + size) < addr)
-			goto nospc;
-		if ((addr + size) <= c->vm_start)
-			goto found;
-		addr = c->vm_end;
-		if (addr > end)
-			goto nospc;
-	}
+	if (mask < 0xffffffffULL)
+		gfp |= GFP_DMA;
+
+	page = alloc_pages(gfp, order);
+	if (!page)
+		return NULL;
 
- found:
 	/*
-	 * Insert this entry _before_ the one we found.
+	 * Now split the huge page and free the excess pages
 	 */
-	list_add_tail(&new->vm_list, &c->vm_list);
-	new->vm_start = addr;
-	new->vm_end = addr + size;
-	new->vm_active = 1;
-
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	return new;
-
- nospc:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	kfree(new);
- out:
-	return NULL;
+	split_page(page, order);
+	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)
+		__free_page(p);
+
+	/*
+	 * Ensure that the allocated pages are zeroed, and that any data
+	 * lurking in the kernel direct-mapped region is invalidated.
+	 */
+	ptr = page_address(page);
+	memset(ptr, 0, size);
+	dmac_flush_range(ptr, ptr + size);
+	outer_flush_range(__pa(ptr), __pa(ptr) + size);
+
+	return page;
 }
 
-static struct arm_vm_region *arm_vm_region_find(struct arm_vm_region *head, unsigned long addr)
+/*
+ * Free a DMA buffer.  'size' must be page aligned.
+ */
+static void __dma_free_buffer(struct page *page, size_t size)
 {
-	struct arm_vm_region *c;
-	
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if (c->vm_active && c->vm_start == addr)
-			goto out;
+	struct page *e = page + (size >> PAGE_SHIFT);
+
+	while (page < e) {
+		__free_page(page);
+		page++;
 	}
-	c = NULL;
- out:
-	return c;
 }
 
+#ifdef CONFIG_MMU
+/*
+ * These are the page tables (2MB each) covering uncached, DMA consistent allocations
+ */
+static pte_t *consistent_pte[NUM_CONSISTENT_PTES];
+
+#include "vmregion.h"
+
+static struct arm_vmregion_head consistent_head = {
+	.vm_lock	= __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
+	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
+	.vm_start	= CONSISTENT_BASE,
+	.vm_end		= CONSISTENT_END,
+};
+
 #ifdef CONFIG_HUGETLB_PAGE
 #error ARM Coherent DMA allocator does not (yet) support huge TLB
 #endif
 
-static void *
-__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
-	    pgprot_t prot)
+/*
+ * Initialise the consistent memory allocation.
+ */
+static int __init consistent_init(void)
 {
-	struct page *page;
-	struct arm_vm_region *c;
-	unsigned long order;
-	u64 mask = get_coherent_dma_mask(dev);
-	u64 limit;
+	int ret = 0;
+	pgd_t *pgd;
+	pmd_t *pmd;
+	pte_t *pte;
+	int i = 0;
+	u32 base = CONSISTENT_BASE;
 
-	if (!consistent_pte[0]) {
-		printk(KERN_ERR "%s: not initialised\n", __func__);
-		dump_stack();
-		return NULL;
-	}
+	do {
+		pgd = pgd_offset(&init_mm, base);
+		pmd = pmd_alloc(&init_mm, pgd, base);
+		if (!pmd) {
+			printk(KERN_ERR "%s: no pmd tables\n", __func__);
+			ret = -ENOMEM;
+			break;
+		}
+		WARN_ON(!pmd_none(*pmd));
 
-	if (!mask)
-		goto no_page;
+		pte = pte_alloc_kernel(pmd, base);
+		if (!pte) {
+			printk(KERN_ERR "%s: no pte tables\n", __func__);
+			ret = -ENOMEM;
+			break;
+		}
 
-	/*
-	 * Sanity check the allocation size.
-	 */
-	size = PAGE_ALIGN(size);
-	limit = (mask + 1) & ~mask;
-	if ((limit && size >= limit) ||
-	    size >= (CONSISTENT_END - CONSISTENT_BASE)) {
-		printk(KERN_WARNING "coherent allocation too big "
-		       "(requested %#x mask %#llx)\n", size, mask);
-		goto no_page;
-	}
+		consistent_pte[i++] = pte;
+		base += (1 << PGDIR_SHIFT);
+	} while (base < CONSISTENT_END);
 
-	order = get_order(size);
+	return ret;
+}
 
-	if (mask < 0xffffffffULL)
-		gfp |= GFP_DMA;
+core_initcall(consistent_init);
 
-	page = alloc_pages(gfp, order);
-	if (!page)
-		goto no_page;
+static void *
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
+{
+	struct arm_vmregion *c;
 
-	/*
-	 * Invalidate any data that might be lurking in the
-	 * kernel direct-mapped region for device DMA.
-	 */
-	{
-		void *ptr = page_address(page);
-		memset(ptr, 0, size);
-		dmac_flush_range(ptr, ptr + size);
-		outer_flush_range(__pa(ptr), __pa(ptr) + size);
+	if (!consistent_pte[0]) {
+		printk(KERN_ERR "%s: not initialised\n", __func__);
+		dump_stack();
+		return NULL;
 	}
 
 	/*
 	 * Allocate a virtual address in the consistent mapping region.
 	 */
-	c = arm_vm_region_alloc(&consistent_head, size,
+	c = arm_vmregion_alloc(&consistent_head, size,
 			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
 	if (c) {
 		pte_t *pte;
-		struct page *end = page + (1 << order);
 		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
 		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
 
 		pte = consistent_pte[idx] + off;
 		c->vm_pages = page;
 
-		split_page(page, order);
-
-		/*
-		 * Set the "dma handle"
-		 */
-		*handle = page_to_dma(dev, page);
-
 		do {
 			BUG_ON(!pte_none(*pte));
 
-			/*
-			 * x86 does not mark the pages reserved...
-			 */
-			SetPageReserved(page);
 			set_pte_ext(pte, mk_pte(page, prot), 0);
 			page++;
 			pte++;
@@ -261,48 +219,90 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 			}
 		} while (size -= PAGE_SIZE);
 
-		/*
-		 * Free the otherwise unused pages.
-		 */
-		while (page < end) {
-			__free_page(page);
-			page++;
-		}
-
 		return (void *)c->vm_start;
 	}
-
-	if (page)
-		__free_pages(page, order);
- no_page:
-	*handle = ~0;
 	return NULL;
 }
+
+static void __dma_free_remap(void *cpu_addr, size_t size)
+{
+	struct arm_vmregion *c;
+	unsigned long addr;
+	pte_t *ptep;
+	int idx;
+	u32 off;
+
+	c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
+	if (!c) {
+		printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
+		       __func__, cpu_addr);
+		dump_stack();
+		return;
+	}
+
+	if ((c->vm_end - c->vm_start) != size) {
+		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
+		       __func__, c->vm_end - c->vm_start, size);
+		dump_stack();
+		size = c->vm_end - c->vm_start;
+	}
+
+	idx = CONSISTENT_PTE_INDEX(c->vm_start);
+	off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
+	ptep = consistent_pte[idx] + off;
+	addr = c->vm_start;
+	do {
+		pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
+
+		ptep++;
+		addr += PAGE_SIZE;
+		off++;
+		if (off >= PTRS_PER_PTE) {
+			off = 0;
+			ptep = consistent_pte[++idx];
+		}
+
+		if (pte_none(pte) || !pte_present(pte))
+			printk(KERN_CRIT "%s: bad page in kernel page table\n",
+			       __func__);
+	} while (size -= PAGE_SIZE);
+
+	flush_tlb_kernel_range(c->vm_start, c->vm_end);
+
+	arm_vmregion_free(&consistent_head, c);
+}
+
 #else	/* !CONFIG_MMU */
+
+#define __dma_alloc_remap(page, size, gfp, prot)	page_address(page)
+#define __dma_free_remap(addr, size)			do { } while (0)
+
+#endif	/* CONFIG_MMU */
+
 static void *
 __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	    pgprot_t prot)
 {
-	void *virt;
-	u64 mask = get_coherent_dma_mask(dev);
+	struct page *page;
+	void *addr;
 
-	if (!mask)
-		goto error;
+	*handle = ~0;
+	size = PAGE_ALIGN(size);
 
-	if (mask < 0xffffffffULL)
-		gfp |= GFP_DMA;
-	virt = kmalloc(size, gfp);
-	if (!virt)
-		goto error;
+	page = __dma_alloc_buffer(dev, size, gfp);
+	if (!page)
+		return NULL;
 
-	*handle =  virt_to_dma(dev, virt);
-	return virt;
+	if (!arch_is_coherent())
+		addr = __dma_alloc_remap(page, size, gfp, prot);
+	else
+		addr = page_address(page);
 
-error:
-	*handle = ~0;
-	return NULL;
+	if (addr)
+		*handle = page_to_dma(dev, page);
+
+	return addr;
 }
-#endif	/* CONFIG_MMU */
 
 /*
  * Allocate DMA-coherent memory space and return both the kernel remapped
@@ -316,19 +316,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
 		return memory;
 
-	if (arch_is_coherent()) {
-		void *virt;
-
-		virt = kmalloc(size, gfp);
-		if (!virt)
-			return NULL;
-		*handle =  virt_to_dma(dev, virt);
-
-		return virt;
-	}
-
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_noncached(pgprot_kernel));
+			   pgprot_dmacoherent(pgprot_kernel));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
@@ -349,15 +338,12 @@ static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
 {
 	int ret = -ENXIO;
 #ifdef CONFIG_MMU
-	unsigned long flags, user_size, kern_size;
-	struct arm_vm_region *c;
+	unsigned long user_size, kern_size;
+	struct arm_vmregion *c;
 
 	user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 
-	spin_lock_irqsave(&consistent_lock, flags);
-	c = arm_vm_region_find(&consistent_head, (unsigned long)cpu_addr);
-	spin_unlock_irqrestore(&consistent_lock, flags);
-
+	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
 	if (c) {
 		unsigned long off = vma->vm_pgoff;
 
@@ -379,7 +365,7 @@ static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
 int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
 		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_page_prot = pgprot_dmacoherent(vma->vm_page_prot);
 	return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
 }
 EXPORT_SYMBOL(dma_mmap_coherent);
@@ -396,144 +382,23 @@ EXPORT_SYMBOL(dma_mmap_writecombine);
  * free a page as defined by the above mapping.
  * Must not be called with IRQs disabled.
  */
-#ifdef CONFIG_MMU
 void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
 {
-	struct arm_vm_region *c;
-	unsigned long flags, addr;
-	pte_t *ptep;
-	int idx;
-	u32 off;
-
 	WARN_ON(irqs_disabled());
 
 	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
 		return;
 
-	if (arch_is_coherent()) {
-		kfree(cpu_addr);
-		return;
-	}
-
 	size = PAGE_ALIGN(size);
 
-	spin_lock_irqsave(&consistent_lock, flags);
-	c = arm_vm_region_find(&consistent_head, (unsigned long)cpu_addr);
-	if (!c)
-		goto no_area;
-
-	c->vm_active = 0;
-	spin_unlock_irqrestore(&consistent_lock, flags);
-
-	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
-	}
-
-	idx = CONSISTENT_PTE_INDEX(c->vm_start);
-	off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-	ptep = consistent_pte[idx] + off;
-	addr = c->vm_start;
-	do {
-		pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
-		unsigned long pfn;
-
-		ptep++;
-		addr += PAGE_SIZE;
-		off++;
-		if (off >= PTRS_PER_PTE) {
-			off = 0;
-			ptep = consistent_pte[++idx];
-		}
-
-		if (!pte_none(pte) && pte_present(pte)) {
-			pfn = pte_pfn(pte);
-
-			if (pfn_valid(pfn)) {
-				struct page *page = pfn_to_page(pfn);
-
-				/*
-				 * x86 does not mark the pages reserved...
-				 */
-				ClearPageReserved(page);
-
-				__free_page(page);
-				continue;
-			}
-		}
-
-		printk(KERN_CRIT "%s: bad page in kernel page table\n",
-		       __func__);
-	} while (size -= PAGE_SIZE);
-
-	flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
-	spin_lock_irqsave(&consistent_lock, flags);
-	list_del(&c->vm_list);
-	spin_unlock_irqrestore(&consistent_lock, flags);
-
-	kfree(c);
-	return;
+	if (!arch_is_coherent())
+		__dma_free_remap(cpu_addr, size);
 
- no_area:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
-	       __func__, cpu_addr);
-	dump_stack();
+	__dma_free_buffer(dma_to_page(dev, handle), size);
 }
-#else	/* !CONFIG_MMU */
-void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t handle)
-{
-	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
-		return;
-	kfree(cpu_addr);
-}
-#endif	/* CONFIG_MMU */
 EXPORT_SYMBOL(dma_free_coherent);
 
 /*
- * Initialise the consistent memory allocation.
- */
-static int __init consistent_init(void)
-{
-	int ret = 0;
-#ifdef CONFIG_MMU
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-	int i = 0;
-	u32 base = CONSISTENT_BASE;
-
-	do {
-		pgd = pgd_offset(&init_mm, base);
-		pmd = pmd_alloc(&init_mm, pgd, base);
-		if (!pmd) {
-			printk(KERN_ERR "%s: no pmd tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-		WARN_ON(!pmd_none(*pmd));
-
-		pte = pte_alloc_kernel(pmd, base);
-		if (!pte) {
-			printk(KERN_ERR "%s: no pte tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-
-		consistent_pte[i++] = pte;
-		base += (1 << PGDIR_SHIFT);
-	} while (base < CONSISTENT_END);
-#endif	/* !CONFIG_MMU */
-
-	return ret;
-}
-
-core_initcall(consistent_init);
-
-/*
  * Make an area consistent for devices.
  * Note: Drivers should NOT use this function directly, as it will break
  * platforms with CONFIG_DMABOUNCE.
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index d0d17b6a370..72960229195 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -23,6 +23,8 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+#include "mm.h"
+
 static unsigned long shared_pte_mask = L_PTE_MT_BUFFERABLE;
 
 /*
@@ -151,7 +153,14 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 	if (!pfn_valid(pfn))
 		return;
 
+	/*
+	 * The zero page is never written to, so never has any dirty
+	 * cache lines, and therefore never needs to be flushed.
+	 */
 	page = pfn_to_page(pfn);
+	if (page == ZERO_PAGE(0))
+		return;
+
 	mapping = page_mapping(page);
 #ifndef CONFIG_SMP
 	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 7f294f307c8..329594e760c 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -35,14 +35,12 @@ static void flush_pfn_alias(unsigned long pfn, unsigned long vaddr)
 	    :
 	    : "r" (to), "r" (to + PAGE_SIZE - L1_CACHE_BYTES), "r" (zero)
 	    : "cc");
-	__flush_icache_all();
 }
 
 void flush_cache_mm(struct mm_struct *mm)
 {
 	if (cache_is_vivt()) {
-		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
-			__cpuc_flush_user_all();
+		vivt_flush_cache_mm(mm);
 		return;
 	}
 
@@ -52,16 +50,13 @@ void flush_cache_mm(struct mm_struct *mm)
 		    :
 		    : "r" (0)
 		    : "cc");
-		__flush_icache_all();
 	}
 }
 
 void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
 	if (cache_is_vivt()) {
-		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
-			__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
-						vma->vm_flags);
+		vivt_flush_cache_range(vma, start, end);
 		return;
 	}
 
@@ -71,22 +66,26 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 		    :
 		    : "r" (0)
 		    : "cc");
-		__flush_icache_all();
 	}
+
+	if (vma->vm_flags & VM_EXEC)
+		__flush_icache_all();
 }
 
 void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsigned long pfn)
 {
 	if (cache_is_vivt()) {
-		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-			unsigned long addr = user_addr & PAGE_MASK;
-			__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
-		}
+		vivt_flush_cache_page(vma, user_addr, pfn);
 		return;
 	}
 
-	if (cache_is_vipt_aliasing())
+	if (cache_is_vipt_aliasing()) {
 		flush_pfn_alias(pfn, user_addr);
+		__flush_icache_all();
+	}
+
+	if (vma->vm_flags & VM_EXEC && icache_is_vivt_asid_tagged())
+		__flush_icache_all();
 }
 
 void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
@@ -94,15 +93,13 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 			 unsigned long len, int write)
 {
 	if (cache_is_vivt()) {
-		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-			unsigned long addr = (unsigned long)kaddr;
-			__cpuc_coherent_kern_range(addr, addr + len);
-		}
+		vivt_flush_ptrace_access(vma, page, uaddr, kaddr, len, write);
 		return;
 	}
 
 	if (cache_is_vipt_aliasing()) {
 		flush_pfn_alias(page_to_pfn(page), uaddr);
+		__flush_icache_all();
 		return;
 	}
 
@@ -120,6 +117,8 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 
 void __flush_dcache_page(struct address_space *mapping, struct page *page)
 {
+	void *addr = page_address(page);
+
 	/*
 	 * Writeback any data associated with the kernel mapping of this
 	 * page.  This ensures that data in the physical page is mutually
@@ -130,9 +129,9 @@ void __flush_dcache_page(struct address_space *mapping, struct page *page)
 	 * kmap_atomic() doesn't set the page virtual address, and
 	 * kunmap_atomic() takes care of cache flushing already.
 	 */
-	if (page_address(page))
+	if (addr)
 #endif
-		__cpuc_flush_dcache_page(page_address(page));
+		__cpuc_flush_dcache_page(addr);
 
 	/*
 	 * If this is a page cache page, and we have an aliasing VIPT cache,
@@ -196,7 +195,16 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p
  */
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping;
+
+	/*
+	 * The zero page is never written to, so never has any dirty
+	 * cache lines, and therefore never needs to be flushed.
+	 */
+	if (page == ZERO_PAGE(0))
+		return;
+
+	mapping = page_mapping(page);
 
 #ifndef CONFIG_SMP
 	if (!PageHighMem(page) && mapping && !mapping_mapped(mapping))
@@ -242,6 +250,7 @@ void __flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned l
 		 * userspace address only.
 		 */
 		flush_pfn_alias(pfn, vmaddr);
+		__flush_icache_all();
 	}
 
 	/*
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index c4f6f05198e..a888363398f 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -24,6 +24,8 @@ struct mem_type {
 
 const struct mem_type *get_mem_type(unsigned int type);
 
+extern void __flush_dcache_page(struct address_space *mapping, struct page *page);
+
 #endif
 
 struct map_desc;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ea67be0223a..2427cdcd909 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1036,7 +1036,7 @@ void __init paging_init(struct machine_desc *mdesc)
 	 */
 	zero_page = alloc_bootmem_low_pages(PAGE_SIZE);
 	empty_zero_page = virt_to_page(zero_page);
-	flush_dcache_page(empty_zero_page);
+	__flush_dcache_page(NULL, empty_zero_page);
 }
 
 /*
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
new file mode 100644
index 00000000000..19e09bdb1b8
--- /dev/null
+++ b/arch/arm/mm/vmregion.c
@@ -0,0 +1,131 @@
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include "vmregion.h"
+
+/*
+ * VM region handling support.
+ *
+ * This should become something generic, handling VM region allocations for
+ * vmalloc and similar (ioremap, module space, etc).
+ *
+ * I envisage vmalloc()'s supporting vm_struct becoming:
+ *
+ *  struct vm_struct {
+ *    struct vmregion	region;
+ *    unsigned long	flags;
+ *    struct page	**pages;
+ *    unsigned int	nr_pages;
+ *    unsigned long	phys_addr;
+ *  };
+ *
+ * get_vm_area() would then call vmregion_alloc with an appropriate
+ * struct vmregion head (eg):
+ *
+ *  struct vmregion vmalloc_head = {
+ *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
+ *	.vm_start	= VMALLOC_START,
+ *	.vm_end		= VMALLOC_END,
+ *  };
+ *
+ * However, vmalloc_head.vm_start is variable (typically, it is dependent on
+ * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
+ * would have to initialise this each time prior to calling vmregion_alloc().
+ */
+
+struct arm_vmregion *
+arm_vmregion_alloc(struct arm_vmregion_head *head, size_t size, gfp_t gfp)
+{
+	unsigned long addr = head->vm_start, end = head->vm_end - size;
+	unsigned long flags;
+	struct arm_vmregion *c, *new;
+
+	if (head->vm_end - head->vm_start < size) {
+		printk(KERN_WARNING "%s: allocation too big (requested %#x)\n",
+			__func__, size);
+		goto out;
+	}
+
+	new = kmalloc(sizeof(struct arm_vmregion), gfp);
+	if (!new)
+		goto out;
+
+	spin_lock_irqsave(&head->vm_lock, flags);
+
+	list_for_each_entry(c, &head->vm_list, vm_list) {
+		if ((addr + size) < addr)
+			goto nospc;
+		if ((addr + size) <= c->vm_start)
+			goto found;
+		addr = c->vm_end;
+		if (addr > end)
+			goto nospc;
+	}
+
+ found:
+	/*
+	 * Insert this entry _before_ the one we found.
+	 */
+	list_add_tail(&new->vm_list, &c->vm_list);
+	new->vm_start = addr;
+	new->vm_end = addr + size;
+	new->vm_active = 1;
+
+	spin_unlock_irqrestore(&head->vm_lock, flags);
+	return new;
+
+ nospc:
+	spin_unlock_irqrestore(&head->vm_lock, flags);
+	kfree(new);
+ out:
+	return NULL;
+}
+
+static struct arm_vmregion *__arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr)
+{
+	struct arm_vmregion *c;
+
+	list_for_each_entry(c, &head->vm_list, vm_list) {
+		if (c->vm_active && c->vm_start == addr)
+			goto out;
+	}
+	c = NULL;
+ out:
+	return c;
+}
+
+struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *head, unsigned long addr)
+{
+	struct arm_vmregion *c;
+	unsigned long flags;
+
+	spin_lock_irqsave(&head->vm_lock, flags);
+	c = __arm_vmregion_find(head, addr);
+	spin_unlock_irqrestore(&head->vm_lock, flags);
+	return c;
+}
+
+struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *head, unsigned long addr)
+{
+	struct arm_vmregion *c;
+	unsigned long flags;
+
+	spin_lock_irqsave(&head->vm_lock, flags);
+	c = __arm_vmregion_find(head, addr);
+	if (c)
+		c->vm_active = 0;
+	spin_unlock_irqrestore(&head->vm_lock, flags);
+	return c;
+}
+
+void arm_vmregion_free(struct arm_vmregion_head *head, struct arm_vmregion *c)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&head->vm_lock, flags);
+	list_del(&c->vm_list);
+	spin_unlock_irqrestore(&head->vm_lock, flags);
+
+	kfree(c);
+}
diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h
new file mode 100644
index 00000000000..6b2cdbdf3a8
--- /dev/null
+++ b/arch/arm/mm/vmregion.h
@@ -0,0 +1,29 @@
+#ifndef VMREGION_H
+#define VMREGION_H
+
+#include <linux/spinlock.h>
+#include <linux/list.h>
+
+struct page;
+
+struct arm_vmregion_head {
+	spinlock_t		vm_lock;
+	struct list_head	vm_list;
+	unsigned long		vm_start;
+	unsigned long		vm_end;
+};
+
+struct arm_vmregion {
+	struct list_head	vm_list;
+	unsigned long		vm_start;
+	unsigned long		vm_end;
+	struct page		*vm_pages;
+	int			vm_active;
+};
+
+struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, gfp_t);
+struct arm_vmregion *arm_vmregion_find(struct arm_vmregion_head *, unsigned long);
+struct arm_vmregion *arm_vmregion_find_remove(struct arm_vmregion_head *, unsigned long);
+void arm_vmregion_free(struct arm_vmregion_head *, struct arm_vmregion *);
+
+#endif