13 files changed, 268 insertions, 321 deletions

diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 8a9c4cb50a9..4e333fa2756 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 idmap.o ioremap.o \
-				   mmap.o pgd.o mmu.o vmregion.o
+				   mmap.o pgd.o mmu.o
 
 ifneq ($(CONFIG_MMU),y)
 obj-y				+= nommu.o
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 7539ec27506..15451ee4acc 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -19,6 +19,52 @@
 #include "proc-macros.S"
 
 /*
+ * The secondary kernel init calls v7_flush_dcache_all before it enables
+ * the L1; however, the L1 comes out of reset in an undefined state, so
+ * the clean + invalidate performed by v7_flush_dcache_all causes a bunch
+ * of cache lines with uninitialized data and uninitialized tags to get
+ * written out to memory, which does really unpleasant things to the main
+ * processor.  We fix this by performing an invalidate, rather than a
+ * clean + invalidate, before jumping into the kernel.
+ *
+ * This function is cloned from arch/arm/mach-tegra/headsmp.S, and needs
+ * to be called for both secondary cores startup and primary core resume
+ * procedures.
+ */
+ENTRY(v7_invalidate_l1)
+       mov     r0, #0
+       mcr     p15, 2, r0, c0, c0, 0
+       mrc     p15, 1, r0, c0, c0, 0
+
+       ldr     r1, =0x7fff
+       and     r2, r1, r0, lsr #13
+
+       ldr     r1, =0x3ff
+
+       and     r3, r1, r0, lsr #3      @ NumWays - 1
+       add     r2, r2, #1              @ NumSets
+
+       and     r0, r0, #0x7
+       add     r0, r0, #4      @ SetShift
+
+       clz     r1, r3          @ WayShift
+       add     r4, r3, #1      @ NumWays
+1:     sub     r2, r2, #1      @ NumSets--
+       mov     r3, r4          @ Temp = NumWays
+2:     subs    r3, r3, #1      @ Temp--
+       mov     r5, r3, lsl r1
+       mov     r6, r2, lsl r0
+       orr     r5, r5, r6      @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+       mcr     p15, 0, r5, c7, c6, 2
+       bgt     2b
+       cmp     r2, #0
+       bgt     1b
+       dsb
+       isb
+       mov     pc, lr
+ENDPROC(v7_invalidate_l1)
+
+/*
  *	v7_flush_icache_all()
  *
  *	Flush the whole I-cache.
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index bc4a5e9ebb7..7a0511191f6 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -34,6 +34,9 @@
  * The ASID is used to tag entries in the CPU caches and TLBs.
  * The context ID is used by debuggers and trace logic, and
  * should be unique within all running processes.
+ *
+ * In big endian operation, the two 32 bit words are swapped if accesed by
+ * non 64-bit operations.
  */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
 #define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index dda3904dc64..c7e3759f16d 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -186,13 +186,24 @@ static u64 get_coherent_dma_mask(struct device *dev)
 
 static void __dma_clear_buffer(struct page *page, size_t size)
 {
-	void *ptr;
 	/*
 	 * Ensure that the allocated pages are zeroed, and that any data
 	 * lurking in the kernel direct-mapped region is invalidated.
 	 */
-	ptr = page_address(page);
-	if (ptr) {
+	if (PageHighMem(page)) {
+		phys_addr_t base = __pfn_to_phys(page_to_pfn(page));
+		phys_addr_t end = base + size;
+		while (size > 0) {
+			void *ptr = kmap_atomic(page);
+			memset(ptr, 0, PAGE_SIZE);
+			dmac_flush_range(ptr, ptr + PAGE_SIZE);
+			kunmap_atomic(ptr);
+			page++;
+			size -= PAGE_SIZE;
+		}
+		outer_flush_range(base, end);
+	} else {
+		void *ptr = page_address(page);
 		memset(ptr, 0, size);
 		dmac_flush_range(ptr, ptr + size);
 		outer_flush_range(__pa(ptr), __pa(ptr) + size);
@@ -243,7 +254,8 @@ static void __dma_free_buffer(struct page *page, size_t size)
 #endif
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
-				     pgprot_t prot, struct page **ret_page);
+				     pgprot_t prot, struct page **ret_page,
+				     const void *caller);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
@@ -346,10 +358,11 @@ static int __init atomic_pool_init(void)
 		goto no_pages;
 
 	if (IS_ENABLED(CONFIG_CMA))
-		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
+		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
+					      atomic_pool_init);
 	else
 		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
-					   &page, NULL);
+					   &page, atomic_pool_init);
 	if (ptr) {
 		int i;
 
@@ -542,27 +555,41 @@ static int __free_from_pool(void *start, size_t size)
 }
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
-				     pgprot_t prot, struct page **ret_page)
+				     pgprot_t prot, struct page **ret_page,
+				     const void *caller)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
 	struct page *page;
+	void *ptr;
 
 	page = dma_alloc_from_contiguous(dev, count, order);
 	if (!page)
 		return NULL;
 
 	__dma_clear_buffer(page, size);
-	__dma_remap(page, size, prot);
 
+	if (PageHighMem(page)) {
+		ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller);
+		if (!ptr) {
+			dma_release_from_contiguous(dev, page, count);
+			return NULL;
+		}
+	} else {
+		__dma_remap(page, size, prot);
+		ptr = page_address(page);
+	}
 	*ret_page = page;
-	return page_address(page);
+	return ptr;
 }
 
 static void __free_from_contiguous(struct device *dev, struct page *page,
-				   size_t size)
+				   void *cpu_addr, size_t size)
 {
-	__dma_remap(page, size, pgprot_kernel);
+	if (PageHighMem(page))
+		__dma_free_remap(cpu_addr, size);
+	else
+		__dma_remap(page, size, pgprot_kernel);
 	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
 }
 
@@ -583,9 +610,9 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 #define __get_dma_pgprot(attrs, prot)	__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret)		NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c)	NULL
 #define __free_from_pool(cpu_addr, size)			0
-#define __free_from_contiguous(dev, page, size)			do { } while (0)
+#define __free_from_contiguous(dev, page, cpu_addr, size)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
@@ -645,7 +672,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
-		addr = __alloc_from_contiguous(dev, size, prot, &page);
+		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
@@ -739,7 +766,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		 * Non-atomic allocations cannot be freed with IRQs disabled
 		 */
 		WARN_ON(irqs_disabled());
-		__free_from_contiguous(dev, page, size);
+		__free_from_contiguous(dev, page, cpu_addr, size);
 	}
 }
 
@@ -1002,6 +1029,9 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	unsigned int count, start;
 	unsigned long flags;
 
+	if (order > CONFIG_ARM_DMA_IOMMU_ALIGNMENT)
+		order = CONFIG_ARM_DMA_IOMMU_ALIGNMENT;
+
 	count = ((PAGE_ALIGN(size) >> PAGE_SHIFT) +
 		 (1 << mapping->order) - 1) >> mapping->order;
 
@@ -1068,12 +1098,17 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 		return pages;
 	}
 
+	/*
+	 * IOMMU can map any pages, so himem can also be used here
+	 */
+	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
+
 	while (count) {
 		int j, order = __fls(count);
 
-		pages[i] = alloc_pages(gfp | __GFP_NOWARN, order);
+		pages[i] = alloc_pages(gfp, order);
 		while (!pages[i] && order)
-			pages[i] = alloc_pages(gfp | __GFP_NOWARN, --order);
+			pages[i] = alloc_pages(gfp, --order);
 		if (!pages[i])
 			goto error;
 
@@ -1257,11 +1292,11 @@ err_mapping:
 	return NULL;
 }
 
-static void __iommu_free_atomic(struct device *dev, struct page **pages,
+static void __iommu_free_atomic(struct device *dev, void *cpu_addr,
 				dma_addr_t handle, size_t size)
 {
 	__iommu_remove_mapping(dev, handle, size);
-	__free_from_pool(page_address(pages[0]), size);
+	__free_from_pool(cpu_addr, size);
 }
 
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
@@ -1344,7 +1379,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (__in_atomic_pool(cpu_addr, size)) {
-		__iommu_free_atomic(dev, pages, handle, size);
+		__iommu_free_atomic(dev, cpu_addr, handle, size);
 		return;
 	}
 
@@ -1732,6 +1767,8 @@ struct dma_map_ops iommu_ops = {
 	.unmap_sg		= arm_iommu_unmap_sg,
 	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
+
+	.set_dma_mask		= arm_dma_set_mask,
 };
 
 struct dma_map_ops iommu_coherent_ops = {
@@ -1745,6 +1782,8 @@ struct dma_map_ops iommu_coherent_ops = {
 
 	.map_sg		= arm_coherent_iommu_map_sg,
 	.unmap_sg	= arm_coherent_iommu_unmap_sg,
+
+	.set_dma_mask	= arm_dma_set_mask,
 };
 
 /**
@@ -1799,6 +1838,7 @@ err2:
 err:
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL_GPL(arm_iommu_create_mapping);
 
 static void release_iommu_mapping(struct kref *kref)
 {
@@ -1815,6 +1855,7 @@ void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping)
 	if (mapping)
 		kref_put(&mapping->kref, release_iommu_mapping);
 }
+EXPORT_SYMBOL_GPL(arm_iommu_release_mapping);
 
 /**
  * arm_iommu_attach_device
@@ -1843,5 +1884,32 @@ int arm_iommu_attach_device(struct device *dev,
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
 }
+EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
+
+/**
+ * arm_iommu_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ * This voids the dma operations (dma_map_ops pointer)
+ */
+void arm_iommu_detach_device(struct device *dev)
+{
+	struct dma_iommu_mapping *mapping;
+
+	mapping = to_dma_iommu_mapping(dev);
+	if (!mapping) {
+		dev_warn(dev, "Not attached\n");
+		return;
+	}
+
+	iommu_detach_device(mapping->domain, dev);
+	kref_put(&mapping->kref, release_iommu_mapping);
+	mapping = NULL;
+	set_dma_ops(dev, NULL);
+
+	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
+}
+EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 #endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 88fd86cf3d9..04d9006eab1 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -39,6 +39,70 @@
 #include <asm/mach/pci.h>
 #include "mm.h"
 
+
+LIST_HEAD(static_vmlist);
+
+static struct static_vm *find_static_vm_paddr(phys_addr_t paddr,
+			size_t size, unsigned int mtype)
+{
+	struct static_vm *svm;
+	struct vm_struct *vm;
+
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
+		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
+			continue;
+		if ((vm->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
+			continue;
+
+		if (vm->phys_addr > paddr ||
+			paddr + size - 1 > vm->phys_addr + vm->size - 1)
+			continue;
+
+		return svm;
+	}
+
+	return NULL;
+}
+
+struct static_vm *find_static_vm_vaddr(void *vaddr)
+{
+	struct static_vm *svm;
+	struct vm_struct *vm;
+
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
+
+		/* static_vmlist is ascending order */
+		if (vm->addr > vaddr)
+			break;
+
+		if (vm->addr <= vaddr && vm->addr + vm->size > vaddr)
+			return svm;
+	}
+
+	return NULL;
+}
+
+void __init add_static_vm_early(struct static_vm *svm)
+{
+	struct static_vm *curr_svm;
+	struct vm_struct *vm;
+	void *vaddr;
+
+	vm = &svm->vm;
+	vm_area_add_early(vm);
+	vaddr = vm->addr;
+
+	list_for_each_entry(curr_svm, &static_vmlist, list) {
+		vm = &curr_svm->vm;
+
+		if (vm->addr > vaddr)
+			break;
+	}
+	list_add_tail(&svm->list, &curr_svm->list);
+}
+
 int ioremap_page(unsigned long virt, unsigned long phys,
 		 const struct mem_type *mtype)
 {
@@ -197,13 +261,14 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	const struct mem_type *type;
 	int err;
 	unsigned long addr;
- 	struct vm_struct * area;
+	struct vm_struct *area;
+	phys_addr_t paddr = __pfn_to_phys(pfn);
 
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * High mappings must be supersection aligned
 	 */
-	if (pfn >= 0x100000 && (__pfn_to_phys(pfn) & ~SUPERSECTION_MASK))
+	if (pfn >= 0x100000 && (paddr & ~SUPERSECTION_MASK))
 		return NULL;
 #endif
 
@@ -219,24 +284,16 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	/*
 	 * Try to reuse one of the static mapping whenever possible.
 	 */
-	read_lock(&vmlist_lock);
-	for (area = vmlist; area; area = area->next) {
-		if (!size || (sizeof(phys_addr_t) == 4 && pfn >= 0x100000))
-			break;
-		if (!(area->flags & VM_ARM_STATIC_MAPPING))
-			continue;
-		if ((area->flags & VM_ARM_MTYPE_MASK) != VM_ARM_MTYPE(mtype))
-			continue;
-		if (__phys_to_pfn(area->phys_addr) > pfn ||
-		    __pfn_to_phys(pfn) + size-1 > area->phys_addr + area->size-1)
-			continue;
-		/* we can drop the lock here as we know *area is static */
-		read_unlock(&vmlist_lock);
-		addr = (unsigned long)area->addr;
-		addr += __pfn_to_phys(pfn) - area->phys_addr;
-		return (void __iomem *) (offset + addr);
+	if (size && !(sizeof(phys_addr_t) == 4 && pfn >= 0x100000)) {
+		struct static_vm *svm;
+
+		svm = find_static_vm_paddr(paddr, size, mtype);
+		if (svm) {
+			addr = (unsigned long)svm->vm.addr;
+			addr += paddr - svm->vm.phys_addr;
+			return (void __iomem *) (offset + addr);
+		}
 	}
-	read_unlock(&vmlist_lock);
 
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
@@ -248,21 +305,21 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
  	if (!area)
  		return NULL;
  	addr = (unsigned long)area->addr;
-	area->phys_addr = __pfn_to_phys(pfn);
+	area->phys_addr = paddr;
 
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 	if (DOMAIN_IO == 0 &&
 	    (((cpu_architecture() >= CPU_ARCH_ARMv6) && (get_cr() & CR_XP)) ||
 	       cpu_is_xsc3()) && pfn >= 0x100000 &&
-	       !((__pfn_to_phys(pfn) | size | addr) & ~SUPERSECTION_MASK)) {
+	       !((paddr | size | addr) & ~SUPERSECTION_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_supersections(addr, pfn, size, type);
-	} else if (!((__pfn_to_phys(pfn) | size | addr) & ~PMD_MASK)) {
+	} else if (!((paddr | size | addr) & ~PMD_MASK)) {
 		area->flags |= VM_ARM_SECTION_MAPPING;
 		err = remap_area_sections(addr, pfn, size, type);
 	} else
 #endif
-		err = ioremap_page_range(addr, addr + size, __pfn_to_phys(pfn),
+		err = ioremap_page_range(addr, addr + size, paddr,
 					 __pgprot(type->prot_pte));
 
 	if (err) {
@@ -346,34 +403,28 @@ __arm_ioremap_exec(unsigned long phys_addr, size_t size, bool cached)
 void __iounmap(volatile void __iomem *io_addr)
 {
 	void *addr = (void *)(PAGE_MASK & (unsigned long)io_addr);
-	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	/* If this is a static mapping, we must leave it alone */
+	svm = find_static_vm_vaddr(addr);
+	if (svm)
+		return;
 
-	read_lock(&vmlist_lock);
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (vm->addr > addr)
-			break;
-		if (!(vm->flags & VM_IOREMAP))
-			continue;
-		/* If this is a static mapping we must leave it alone */
-		if ((vm->flags & VM_ARM_STATIC_MAPPING) &&
-		    (vm->addr <= addr) && (vm->addr + vm->size > addr)) {
-			read_unlock(&vmlist_lock);
-			return;
-		}
 #if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
+	{
+		struct vm_struct *vm;
+
+		vm = find_vm_area(addr);
+
 		/*
 		 * If this is a section based mapping we need to handle it
 		 * specially as the VM subsystem does not know how to handle
 		 * such a beast.
 		 */
-		if ((vm->addr == addr) &&
-		    (vm->flags & VM_ARM_SECTION_MAPPING)) {
+		if (vm && (vm->flags & VM_ARM_SECTION_MAPPING))
 			unmap_area_sections((unsigned long)vm->addr, vm->size);
-			break;
-		}
-#endif
 	}
-	read_unlock(&vmlist_lock);
+#endif
 
 	vunmap(addr);
 }
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index a8ee92da354..d5a4e9ad8f0 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -1,4 +1,6 @@
 #ifdef CONFIG_MMU
+#include <linux/list.h>
+#include <linux/vmalloc.h>
 
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
@@ -65,6 +67,16 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 /* consistent regions used by dma_alloc_attrs() */
 #define VM_ARM_DMA_CONSISTENT	0x20000000
 
+
+struct static_vm {
+	struct vm_struct vm;
+	struct list_head list;
+};
+
+extern struct list_head static_vmlist;
+extern struct static_vm *find_static_vm_vaddr(void *vaddr);
+extern __init void add_static_vm_early(struct static_vm *svm);
+
 #endif
 
 #ifdef CONFIG_ZONE_DMA
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 8fcf8bd3ee4..e95a996ab78 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -779,21 +779,24 @@ void __init iotable_init(struct map_desc *io_desc, int nr)
 {
 	struct map_desc *md;
 	struct vm_struct *vm;
+	struct static_vm *svm;
 
 	if (!nr)
 		return;
 
-	vm = early_alloc_aligned(sizeof(*vm) * nr, __alignof__(*vm));
+	svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
+
+		vm = &svm->vm;
 		vm->addr = (void *)(md->virtual & PAGE_MASK);
 		vm->size = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
 		vm->phys_addr = __pfn_to_phys(md->pfn);
 		vm->flags = VM_IOREMAP | VM_ARM_STATIC_MAPPING;
 		vm->flags |= VM_ARM_MTYPE(md->type);
 		vm->caller = iotable_init;
-		vm_area_add_early(vm++);
+		add_static_vm_early(svm++);
 	}
 }
 
@@ -801,13 +804,16 @@ void __init vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller)
 {
 	struct vm_struct *vm;
+	struct static_vm *svm;
+
+	svm = early_alloc_aligned(sizeof(*svm), __alignof__(*svm));
 
-	vm = early_alloc_aligned(sizeof(*vm), __alignof__(*vm));
+	vm = &svm->vm;
 	vm->addr = (void *)addr;
 	vm->size = size;
 	vm->flags = VM_IOREMAP | VM_ARM_EMPTY_MAPPING;
 	vm->caller = caller;
-	vm_area_add_early(vm);
+	add_static_vm_early(svm);
 }
 
 #ifndef CONFIG_ARM_LPAE
@@ -832,14 +838,13 @@ static void __init pmd_empty_section_gap(unsigned long addr)
 
 static void __init fill_pmd_gaps(void)
 {
+	struct static_vm *svm;
 	struct vm_struct *vm;
 	unsigned long addr, next = 0;
 	pmd_t *pmd;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & (VM_ARM_STATIC_MAPPING | VM_ARM_EMPTY_MAPPING)))
-			continue;
+	list_for_each_entry(svm, &static_vmlist, list) {
+		vm = &svm->vm;
 		addr = (unsigned long)vm->addr;
 		if (addr < next)
 			continue;
@@ -879,19 +884,12 @@ static void __init fill_pmd_gaps(void)
 #if defined(CONFIG_PCI) && !defined(CONFIG_NEED_MACH_IO_H)
 static void __init pci_reserve_io(void)
 {
-	struct vm_struct *vm;
-	unsigned long addr;
+	struct static_vm *svm;
 
-	/* we're still single threaded hence no lock needed here */
-	for (vm = vmlist; vm; vm = vm->next) {
-		if (!(vm->flags & VM_ARM_STATIC_MAPPING))
-			continue;
-		addr = (unsigned long)vm->addr;
-		addr &= ~(SZ_2M - 1);
-		if (addr == PCI_IO_VIRT_BASE)
-			return;
+	svm = find_static_vm_vaddr((void *)PCI_IO_VIRT_BASE);
+	if (svm)
+		return;
 
-	}
 	vm_reserve_area_early(PCI_IO_VIRT_BASE, SZ_2M, pci_reserve_io);
 }
 #else
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index eb6aa73bc8b..f9a0aa725ea 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -38,9 +38,14 @@
 
 /*
  * mmid - get context id from mm pointer (mm->context.id)
+ * note, this field is 64bit, so in big-endian the two words are swapped too.
  */
 	.macro	mmid, rd, rn
+#ifdef __ARMEB__
+	ldr	\rd, [\rn, #MM_CONTEXT_ID + 4 ]
+#else
 	ldr	\rd, [\rn, #MM_CONTEXT_ID]
+#endif
 	.endm
 
 /*
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 09c5233f4df..bcaaa8de932 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -101,7 +101,7 @@ ENTRY(cpu_v6_dcache_clean_area)
 ENTRY(cpu_v6_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 6d98c13ab82..78f520bc0e9 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -40,7 +40,7 @@
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 7b56386f949..50bf1dafc9e 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -47,7 +47,7 @@
  */
 ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
-	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
+	mmid	r1, r1				@ get mm->context.id
 	and	r3, r1, #0xff
 	mov	r3, r3, lsl #(48 - 32)		@ ASID
 	mcrr	p15, 0, r0, r3, c2		@ set TTB 0
diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
deleted file mode 100644
index a631016e1f8..00000000000
--- a/arch/arm/mm/vmregion.c
+++ /dev/null
@@ -1,205 +0,0 @@
-#include <linux/fs.h>
-#include <linux/spinlock.h>
-#include <linux/list.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.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 align,
-		   size_t size, gfp_t gfp, const void *caller)
-{
-	unsigned long start = head->vm_start, addr = head->vm_end;
-	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;
-
-	new->caller = caller;
-
-	spin_lock_irqsave(&head->vm_lock, flags);
-
-	addr = rounddown(addr - size, align);
-	list_for_each_entry_reverse(c, &head->vm_list, vm_list) {
-		if (addr >= c->vm_end)
-			goto found;
-		addr = rounddown(c->vm_start - size, align);
-		if (addr < start)
-			goto nospc;
-	}
-
- found:
-	/*
-	 * Insert this entry after the one we found.
-	 */
-	list_add(&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);
-}
-
-#ifdef CONFIG_PROC_FS
-static int arm_vmregion_show(struct seq_file *m, void *p)
-{
-	struct arm_vmregion *c = list_entry(p, struct arm_vmregion, vm_list);
-
-	seq_printf(m, "0x%08lx-0x%08lx %7lu", c->vm_start, c->vm_end,
-		c->vm_end - c->vm_start);
-	if (c->caller)
-		seq_printf(m, " %pS", (void *)c->caller);
-	seq_putc(m, '\n');
-	return 0;
-}
-
-static void *arm_vmregion_start(struct seq_file *m, loff_t *pos)
-{
-	struct arm_vmregion_head *h = m->private;
-	spin_lock_irq(&h->vm_lock);
-	return seq_list_start(&h->vm_list, *pos);
-}
-
-static void *arm_vmregion_next(struct seq_file *m, void *p, loff_t *pos)
-{
-	struct arm_vmregion_head *h = m->private;
-	return seq_list_next(p, &h->vm_list, pos);
-}
-
-static void arm_vmregion_stop(struct seq_file *m, void *p)
-{
-	struct arm_vmregion_head *h = m->private;
-	spin_unlock_irq(&h->vm_lock);
-}
-
-static const struct seq_operations arm_vmregion_ops = {
-	.start	= arm_vmregion_start,
-	.stop	= arm_vmregion_stop,
-	.next	= arm_vmregion_next,
-	.show	= arm_vmregion_show,
-};
-
-static int arm_vmregion_open(struct inode *inode, struct file *file)
-{
-	struct arm_vmregion_head *h = PDE(inode)->data;
-	int ret = seq_open(file, &arm_vmregion_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = h;
-	}
-	return ret;
-}
-
-static const struct file_operations arm_vmregion_fops = {
-	.open	= arm_vmregion_open,
-	.read	= seq_read,
-	.llseek	= seq_lseek,
-	.release = seq_release,
-};
-
-int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
-{
-	proc_create_data(path, S_IRUSR, NULL, &arm_vmregion_fops, h);
-	return 0;
-}
-#else
-int arm_vmregion_create_proc(const char *path, struct arm_vmregion_head *h)
-{
-	return 0;
-}
-#endif
diff --git a/arch/arm/mm/vmregion.h b/arch/arm/mm/vmregion.h
deleted file mode 100644
index 0f5a5f2a2c7..00000000000
--- a/arch/arm/mm/vmregion.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#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;
-	int			vm_active;
-	const void		*caller;
-};
-
-struct arm_vmregion *arm_vmregion_alloc(struct arm_vmregion_head *, size_t, size_t, gfp_t, const void *);
-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 *);
-
-int arm_vmregion_create_proc(const char *, struct arm_vmregion_head *);
-
-#endif