diff --git a/arch/arm/boards/phytec-som-imx6/lowlevel.c b/arch/arm/boards/phytec-som-imx6/lowlevel.c
index f9d70c7..05f918f 100644
--- a/arch/arm/boards/phytec-som-imx6/lowlevel.c
+++ b/arch/arm/boards/phytec-som-imx6/lowlevel.c
@@ -38,6 +38,7 @@
 	putc_ll('>');
 }
 
+#undef SZ_4G
 #define SZ_4G 0xEFFFFFF8
 
 BAREBOX_IMD_TAG_STRING(physom_mx6_memsize_SZ_128M, IMD_TYPE_PARAMETER, "memsize=128", 0);
diff --git a/arch/arm/cpu/Makefile b/arch/arm/cpu/Makefile
index 0316d25..5b4b832 100644
--- a/arch/arm/cpu/Makefile
+++ b/arch/arm/cpu/Makefile
@@ -17,7 +17,7 @@
 obj-$(CONFIG_OFDEVICE) += dtb.o
 
 ifeq ($(CONFIG_MMU),)
-obj-y += no-mmu.o
+obj-$(CONFIG_CPU_32v7) += no-mmu.o
 endif
 
 obj-$(CONFIG_ARM_PSCI) += psci.o
diff --git a/arch/arm/cpu/mmu-early.c b/arch/arm/cpu/mmu-early.c
index 70cb5fe..d39a03e 100644
--- a/arch/arm/cpu/mmu-early.c
+++ b/arch/arm/cpu/mmu-early.c
@@ -5,49 +5,30 @@
 #include <asm/memory.h>
 #include <asm/system.h>
 #include <asm/cache.h>
-#include <asm/pgtable.h>
 
 #include "mmu.h"
 
 static uint32_t *ttb;
 
-static void create_sections(unsigned long addr, int size_m, unsigned int flags)
-{
-	int i;
-
-	addr >>= 20;
-
-	for (i = size_m; i > 0; i--, addr++)
-		ttb[addr] = (addr << 20) | flags;
-}
-
 static void map_cachable(unsigned long start, unsigned long size)
 {
-	start &= ~(SZ_1M - 1);
-	size = (size + (SZ_1M - 1)) & ~(SZ_1M - 1);
+	start = ALIGN_DOWN(start, SZ_1M);
+	size  = ALIGN(size, SZ_1M);
 
-	create_sections(start, size >> 20, PMD_SECT_AP_WRITE |
-			PMD_SECT_AP_READ | PMD_TYPE_SECT | PMD_SECT_WB);
+	create_sections(ttb, start, start + size - 1, PMD_SECT_DEF_CACHED);
 }
 
 void mmu_early_enable(unsigned long membase, unsigned long memsize,
 		      unsigned long _ttb)
 {
-	int i;
-
 	ttb = (uint32_t *)_ttb;
 
 	arm_set_cache_functions();
 
-	/* Set the ttb register */
-	asm volatile ("mcr  p15,0,%0,c2,c0,0" : : "r"(ttb) /*:*/);
+	set_ttbr(ttb);
+	set_domain(DOMAIN_MANAGER);
 
-	/* Set the Domain Access Control Register */
-	i = 0x3;
-	asm volatile ("mcr  p15,0,%0,c3,c0,0" : : "r"(i) /*:*/);
-
-	create_sections(0, 4096, PMD_SECT_AP_WRITE |
-			PMD_SECT_AP_READ | PMD_TYPE_SECT);
+	create_flat_mapping(ttb);
 
 	map_cachable(membase, memsize);
 
diff --git a/arch/arm/cpu/mmu.c b/arch/arm/cpu/mmu.c
index 6ccd589..7e2e5bf 100644
--- a/arch/arm/cpu/mmu.c
+++ b/arch/arm/cpu/mmu.c
@@ -27,31 +27,17 @@
 #include <asm/barebox-arm.h>
 #include <asm/system.h>
 #include <asm/cache.h>
-#include <asm/pgtable.h>
 #include <memory.h>
 #include <asm/system_info.h>
 #include <asm/sections.h>
 
 #include "mmu.h"
 
-#define PMD_SECT_DEF_UNCACHED (PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT)
 #define PMD_SECT_DEF_CACHED (PMD_SECT_WB | PMD_SECT_DEF_UNCACHED)
+#define PTRS_PER_PTE		(PGDIR_SIZE / PAGE_SIZE)
+#define ARCH_MAP_WRITECOMBINE	((unsigned)-1)
 
-static unsigned long *ttb;
-
-static void create_sections(unsigned long virt, unsigned long phys, int size_m,
-		unsigned int flags)
-{
-	int i;
-
-	phys >>= 20;
-	virt >>= 20;
-
-	for (i = size_m; i > 0; i--, virt++, phys++)
-		ttb[virt] = (phys << 20) | flags;
-
-	__mmu_cache_flush();
-}
+static uint32_t *ttb;
 
 /*
  * Do it the simple way for now and invalidate the entire
@@ -75,6 +61,7 @@
 #define PTE_FLAGS_UNCACHED_V7 (0)
 #define PTE_FLAGS_CACHED_V4 (PTE_SMALL_AP_UNO_SRW | PTE_BUFFERABLE | PTE_CACHEABLE)
 #define PTE_FLAGS_UNCACHED_V4 PTE_SMALL_AP_UNO_SRW
+#define PGD_FLAGS_WC_V7 PMD_SECT_TEX(1)
 
 /*
  * PTE flags to set cached and uncached areas.
@@ -83,6 +70,7 @@
 static uint32_t pte_flags_cached;
 static uint32_t pte_flags_wc;
 static uint32_t pte_flags_uncached;
+static uint32_t pgd_flags_wc;
 
 #define PTE_MASK ((1 << 12) - 1)
 
@@ -102,26 +90,34 @@
  * We initially create a flat uncached mapping on it.
  * Not yet exported, but may be later if someone finds use for it.
  */
-static u32 *arm_create_pte(unsigned long virt)
+static u32 *arm_create_pte(unsigned long virt, uint32_t flags)
 {
 	u32 *table;
 	int i;
 
-	table = memalign(0x400, 0x400);
+	virt = ALIGN_DOWN(virt, PGDIR_SIZE);
+
+	table = xmemalign(PTRS_PER_PTE * sizeof(u32),
+			  PTRS_PER_PTE * sizeof(u32));
 
 	if (!ttb)
 		arm_mmu_not_initialized_error();
 
-	ttb[virt >> 20] = (unsigned long)table | PMD_TYPE_TABLE;
+	ttb[pgd_index(virt)] = (unsigned long)table | PMD_TYPE_TABLE;
 
-	for (i = 0; i < 256; i++) {
-		table[i] = virt | PTE_TYPE_SMALL | pte_flags_uncached;
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		table[i] = virt | PTE_TYPE_SMALL | flags;
 		virt += PAGE_SIZE;
 	}
 
 	return table;
 }
 
+static bool pgd_type_table(u32 pgd)
+{
+	return (pgd & PMD_TYPE_MASK) == PMD_TYPE_TABLE;
+}
+
 static u32 *find_pte(unsigned long adr)
 {
 	u32 *table;
@@ -129,33 +125,21 @@
 	if (!ttb)
 		arm_mmu_not_initialized_error();
 
-	if ((ttb[adr >> 20] & PMD_TYPE_MASK) != PMD_TYPE_TABLE) {
-		struct memory_bank *bank;
-		int i = 0;
-
-		/*
-		 * This should only be called for page mapped memory inside our
-		 * memory banks. It's a bug to call it with section mapped memory
-		 * locations.
-		 */
-		pr_crit("%s: TTB for address 0x%08lx is not of type table\n",
-				__func__, adr);
-		pr_crit("Memory banks:\n");
-		for_each_memory_bank(bank)
-			pr_crit("#%d 0x%08lx - 0x%08lx\n", i, bank->start,
-					bank->start + bank->size - 1);
-		BUG();
-	}
+	if (!pgd_type_table(ttb[pgd_index(adr)]))
+		return NULL;
 
 	/* find the coarse page table base address */
-	table = (u32 *)(ttb[adr >> 20] & ~0x3ff);
+	table = (u32 *)(ttb[pgd_index(adr)] & ~0x3ff);
 
 	/* find second level descriptor */
 	return &table[(adr >> PAGE_SHIFT) & 0xff];
 }
 
-static void dma_flush_range(unsigned long start, unsigned long end)
+static void dma_flush_range(void *ptr, size_t size)
 {
+	unsigned long start = (unsigned long)ptr;
+	unsigned long end = start + size;
+
 	__dma_flush_range(start, end);
 	if (outer_cache.flush_range)
 		outer_cache.flush_range(start, end);
@@ -168,115 +152,128 @@
 	__dma_inv_range(start, end);
 }
 
-static int __remap_range(void *_start, size_t size, u32 pte_flags)
-{
-	unsigned long start = (unsigned long)_start;
-	u32 *p;
-	int numentries, i;
-
-	numentries = size >> PAGE_SHIFT;
-	p = find_pte(start);
-
-	for (i = 0; i < numentries; i++) {
-		p[i] &= ~PTE_MASK;
-		p[i] |= pte_flags | PTE_TYPE_SMALL;
-	}
-
-	dma_flush_range((unsigned long)p,
-			(unsigned long)p + numentries * sizeof(u32));
-
-	tlb_invalidate();
-
-	return 0;
-}
-
 int arch_remap_range(void *start, size_t size, unsigned flags)
 {
+	u32 addr = (u32)start;
 	u32 pte_flags;
+	u32 pgd_flags;
+
+	BUG_ON(!IS_ALIGNED(addr, PAGE_SIZE));
 
 	switch (flags) {
 	case MAP_CACHED:
 		pte_flags = pte_flags_cached;
+		pgd_flags = PMD_SECT_DEF_CACHED;
 		break;
 	case MAP_UNCACHED:
 		pte_flags = pte_flags_uncached;
+		pgd_flags = PMD_SECT_DEF_UNCACHED;
+		break;
+	case ARCH_MAP_WRITECOMBINE:
+		pte_flags = pte_flags_wc;
+		pgd_flags = pgd_flags_wc;
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	return __remap_range(start, size, pte_flags);
+	while (size) {
+		const bool pgdir_size_aligned = IS_ALIGNED(addr, PGDIR_SIZE);
+		u32 *pgd = (u32 *)&ttb[pgd_index(addr)];
+		size_t chunk;
+
+		if (size >= PGDIR_SIZE && pgdir_size_aligned &&
+		    !pgd_type_table(*pgd)) {
+			/*
+			 * TODO: Add code to discard a page table and
+			 * replace it with a section
+			 */
+			chunk = PGDIR_SIZE;
+			*pgd = addr | pgd_flags;
+			dma_flush_range(pgd, sizeof(*pgd));
+		} else {
+			unsigned int num_ptes;
+			u32 *table = NULL;
+			unsigned int i;
+			u32 *pte;
+			/*
+			 * We only want to cover pages up until next
+			 * section boundary in case there we would
+			 * have an opportunity to re-map the whole
+			 * section (say if we got here becasue address
+			 * was not aligned on PGDIR_SIZE boundary)
+			 */
+			chunk = pgdir_size_aligned ?
+				PGDIR_SIZE : ALIGN(addr, PGDIR_SIZE) - addr;
+			/*
+			 * At the same time we want to make sure that
+			 * we don't go on remapping past requested
+			 * size in case that is less that the distance
+			 * to next PGDIR_SIZE boundary.
+			 */
+			chunk = min(chunk, size);
+			num_ptes = chunk / PAGE_SIZE;
+
+			pte = find_pte(addr);
+			if (!pte) {
+				/*
+				 * If PTE is not found it means that
+				 * we needs to split this section and
+				 * create a new page table for it
+				 *
+				 * NOTE: Here we assume that section
+				 * we just split was mapped as cached
+				 */
+				table = arm_create_pte(addr, pte_flags_cached);
+				pte = find_pte(addr);
+				BUG_ON(!pte);
+				/*
+				 * We just split this section and
+				 * modified it's Level 1 descriptor,
+				 * so it needs to be flushed.
+				 */
+				dma_flush_range(pgd, sizeof(*pgd));
+			}
+
+			for (i = 0; i < num_ptes; i++) {
+				pte[i] &= ~PTE_MASK;
+				pte[i] |= pte_flags | PTE_TYPE_SMALL;
+			}
+
+			if (table) {
+				/*
+				 * If we just created a new page
+				 * table, the whole table would have
+				 * to be flushed, not just PTEs that
+				 * we touched when re-mapping.
+				 */
+				pte = table;
+				num_ptes = PTRS_PER_PTE;
+			}
+
+			dma_flush_range(pte, num_ptes * sizeof(u32));
+		}
+
+		addr += chunk;
+		size -= chunk;
+	}
+
+	tlb_invalidate();
+	return 0;
 }
 
 void *map_io_sections(unsigned long phys, void *_start, size_t size)
 {
 	unsigned long start = (unsigned long)_start, sec;
 
-	phys >>= 20;
-	for (sec = start; sec < start + size; sec += (1 << 20))
-		ttb[sec >> 20] = (phys++ << 20) | PMD_SECT_DEF_UNCACHED;
+	for (sec = start; sec < start + size; sec += PGDIR_SIZE, phys += PGDIR_SIZE)
+		ttb[pgd_index(sec)] = phys | PMD_SECT_DEF_UNCACHED;
 
-	dma_flush_range((unsigned long)ttb, (unsigned long)ttb + 0x4000);
+	dma_flush_range(ttb, 0x4000);
 	tlb_invalidate();
 	return _start;
 }
 
-/*
- * remap the memory bank described by mem cachable and
- * bufferable
- */
-static int arm_mmu_remap_sdram(struct memory_bank *bank)
-{
-	unsigned long phys = (unsigned long)bank->start;
-	unsigned long ttb_start = phys >> 20;
-	unsigned long ttb_end = (phys >> 20) + (bank->size >> 20);
-	unsigned long num_ptes = bank->size >> 12;
-	int i, pte;
-	u32 *ptes;
-
-	pr_debug("remapping SDRAM from 0x%08lx (size 0x%08lx)\n",
-			phys, bank->size);
-
-	/*
-	 * We replace each 1MiB section in this range with second level page
-	 * tables, therefore we must have 1Mib aligment here.
-	 */
-	if ((phys & (SZ_1M - 1)) || (bank->size & (SZ_1M - 1)))
-		return -EINVAL;
-
-	ptes = xmemalign(PAGE_SIZE, num_ptes * sizeof(u32));
-
-	pr_debug("ptes: 0x%p ttb_start: 0x%08lx ttb_end: 0x%08lx\n",
-			ptes, ttb_start, ttb_end);
-
-	for (i = 0; i < num_ptes; i++) {
-		ptes[i] = (phys + i * PAGE_SIZE) | PTE_TYPE_SMALL |
-			pte_flags_cached;
-	}
-
-	pte = 0;
-
-	for (i = ttb_start; i < ttb_end; i++) {
-		ttb[i] = (unsigned long)(&ptes[pte]) | PMD_TYPE_TABLE |
-			(0 << 4);
-		pte += 256;
-	}
-
-	dma_flush_range((unsigned long)ttb, (unsigned long)ttb + 0x4000);
-	dma_flush_range((unsigned long)ptes,
-			(unsigned long)ptes + num_ptes * sizeof(u32));
-
-	tlb_invalidate();
-
-	return 0;
-}
-/*
- * We have 8 exception vectors and the table consists of absolute
- * jumps, so we need 8 * 4 bytes for the instructions and another
- * 8 * 4 bytes for the addresses.
- */
-#define ARM_VECTORS_SIZE	(sizeof(u32) * 8 * 2)
-
 #define ARM_HIGH_VECTORS	0xffff0000
 #define ARM_LOW_VECTORS		0x0
 
@@ -291,10 +288,9 @@
 {
 	struct resource *vectors_sdram;
 	void *vectors;
-	u32 *exc;
-	int idx;
+	u32 *pte;
 
-	vectors_sdram = request_sdram_region("vector table", adr, SZ_4K);
+	vectors_sdram = request_sdram_region("vector table", adr, PAGE_SIZE);
 	if (vectors_sdram) {
 		/*
 		 * The vector table address is inside the SDRAM physical
@@ -312,9 +308,9 @@
 		vectors = xmemalign(PAGE_SIZE, PAGE_SIZE);
 		pr_debug("Creating vector table, virt = 0x%p, phys = 0x%08lx\n",
 			 vectors, adr);
-		exc = arm_create_pte(ALIGN_DOWN(adr, SZ_1M));
-		idx = (adr & (SZ_1M - 1)) >> PAGE_SHIFT;
-		exc[idx] = (u32)vectors | PTE_TYPE_SMALL | pte_flags_cached;
+		arm_create_pte(adr, pte_flags_uncached);
+		pte = find_pte(adr);
+		*pte = (u32)vectors | PTE_TYPE_SMALL | pte_flags_cached;
 	}
 
 	arm_fixup_vectors();
@@ -375,7 +371,7 @@
 	struct resource *zero_sdram;
 	u32 *zero;
 
-	zero_sdram = request_sdram_region("zero page", 0x0, SZ_4K);
+	zero_sdram = request_sdram_region("zero page", 0x0, PAGE_SIZE);
 	if (zero_sdram) {
 		/*
 		 * Here we would need to set the second level page table
@@ -383,7 +379,7 @@
 		 */
 		pr_debug("zero page is in SDRAM area, currently not supported\n");
 	} else {
-		zero = arm_create_pte(0x0);
+		zero = arm_create_pte(0x0, pte_flags_uncached);
 		zero[0] = 0;
 		pr_debug("Created zero page\n");
 	}
@@ -428,7 +424,6 @@
 static int mmu_init(void)
 {
 	struct memory_bank *bank;
-	int i;
 
 	if (list_empty(&memory_banks))
 		/*
@@ -444,10 +439,12 @@
 	if (cpu_architecture() >= CPU_ARCH_ARMv7) {
 		pte_flags_cached = PTE_FLAGS_CACHED_V7;
 		pte_flags_wc = PTE_FLAGS_WC_V7;
+		pgd_flags_wc = PGD_FLAGS_WC_V7;
 		pte_flags_uncached = PTE_FLAGS_UNCACHED_V7;
 	} else {
 		pte_flags_cached = PTE_FLAGS_CACHED_V4;
 		pte_flags_wc = PTE_FLAGS_UNCACHED_V4;
+		pgd_flags_wc = PMD_SECT_DEF_UNCACHED;
 		pte_flags_uncached = PTE_FLAGS_UNCACHED_V4;
 	}
 
@@ -459,7 +456,7 @@
 		asm volatile ("mrc  p15,0,%0,c2,c0,0" : "=r"(ttb));
 
 		/* Clear unpredictable bits [13:0] */
-		ttb = (unsigned long *)((unsigned long)ttb & ~0x3fff);
+		ttb = (uint32_t *)((unsigned long)ttb & ~0x3fff);
 
 		if (!request_sdram_region("ttb", (unsigned long)ttb, SZ_16K))
 			/*
@@ -472,22 +469,17 @@
 			pr_crit("Critical Error: Can't request SDRAM region for ttb at %p\n",
 					ttb);
 	} else {
-		ttb = memalign(0x10000, 0x4000);
+		ttb = xmemalign(ARM_TTB_SIZE, ARM_TTB_SIZE);
+
+		set_ttbr(ttb);
+		set_domain(DOMAIN_MANAGER);
+
+		create_flat_mapping(ttb);
+		__mmu_cache_flush();
 	}
 
 	pr_debug("ttb: 0x%p\n", ttb);
 
-	/* Set the ttb register */
-	asm volatile ("mcr  p15,0,%0,c2,c0,0" : : "r"(ttb) /*:*/);
-
-	/* Set the Domain Access Control Register */
-	i = 0x3;
-	asm volatile ("mcr  p15,0,%0,c3,c0,0" : : "r"(i) /*:*/);
-
-	/* create a flat mapping using 1MiB sections */
-	create_sections(0, 0, PAGE_SIZE, PMD_SECT_AP_WRITE | PMD_SECT_AP_READ |
-			PMD_TYPE_SECT);
-
 	vectors_init();
 
 	/*
@@ -495,19 +487,14 @@
 	 * This is to speed up the generation of 2nd level page tables
 	 * below
 	 */
-	for_each_memory_bank(bank)
-		create_sections(bank->start, bank->start, bank->size >> 20,
+	for_each_memory_bank(bank) {
+		create_sections(ttb, bank->start, bank->start + bank->size - 1,
 				PMD_SECT_DEF_CACHED);
+		__mmu_cache_flush();
+	}
 
 	__mmu_cache_on();
 
-	/*
-	 * Now that we have the MMU and caches on remap sdram again using
-	 * page tables
-	 */
-	for_each_memory_bank(bank)
-		arm_mmu_remap_sdram(bank);
-
 	return 0;
 }
 mmu_initcall(mmu_init);
@@ -525,7 +512,7 @@
 	__mmu_cache_off();
 }
 
-void *dma_alloc_coherent(size_t size, dma_addr_t *dma_handle)
+static void *dma_alloc(size_t size, dma_addr_t *dma_handle, unsigned flags)
 {
 	void *ret;
 
@@ -536,25 +523,19 @@
 
 	dma_inv_range((unsigned long)ret, (unsigned long)ret + size);
 
-	__remap_range(ret, size, pte_flags_uncached);
+	arch_remap_range(ret, size, flags);
 
 	return ret;
 }
 
+void *dma_alloc_coherent(size_t size, dma_addr_t *dma_handle)
+{
+	return dma_alloc(size, dma_handle, MAP_UNCACHED);
+}
+
 void *dma_alloc_writecombine(size_t size, dma_addr_t *dma_handle)
 {
-	void *ret;
-
-	size = PAGE_ALIGN(size);
-	ret = xmemalign(PAGE_SIZE, size);
-	if (dma_handle)
-		*dma_handle = (dma_addr_t)ret;
-
-	dma_inv_range((unsigned long)ret, (unsigned long)ret + size);
-
-	__remap_range(ret, size, pte_flags_wc);
-
-	return ret;
+	return dma_alloc(size, dma_handle, ARCH_MAP_WRITECOMBINE);
 }
 
 unsigned long virt_to_phys(volatile void *virt)
@@ -570,7 +551,7 @@
 void dma_free_coherent(void *mem, dma_addr_t dma_handle, size_t size)
 {
 	size = PAGE_ALIGN(size);
-	__remap_range(mem, size, pte_flags_cached);
+	arch_remap_range(mem, size, MAP_CACHED);
 
 	free(mem);
 }
@@ -578,11 +559,8 @@
 void dma_sync_single_for_cpu(dma_addr_t address, size_t size,
 			     enum dma_data_direction dir)
 {
-	if (dir != DMA_TO_DEVICE) {
-		if (outer_cache.inv_range)
-			outer_cache.inv_range(address, address + size);
-		__dma_inv_range(address, address + size);
-	}
+	if (dir != DMA_TO_DEVICE)
+		dma_inv_range(address, address + size);
 }
 
 void dma_sync_single_for_device(dma_addr_t address, size_t size,
diff --git a/arch/arm/cpu/mmu.h b/arch/arm/cpu/mmu.h
index 79ebc80..e5bb370 100644
--- a/arch/arm/cpu/mmu.h
+++ b/arch/arm/cpu/mmu.h
@@ -1,6 +1,14 @@
 #ifndef __ARM_MMU_H
 #define __ARM_MMU_H
 
+#include <asm/pgtable.h>
+#include <linux/sizes.h>
+
+#define PGDIR_SHIFT	20
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+
+#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
+
 #ifdef CONFIG_MMU
 void __mmu_cache_on(void);
 void __mmu_cache_off(void);
@@ -11,4 +19,40 @@
 static inline void __mmu_cache_flush(void) {}
 #endif
 
+static inline void set_ttbr(void *ttb)
+{
+	asm volatile ("mcr  p15,0,%0,c2,c0,0" : : "r"(ttb) /*:*/);
+}
+
+#define DOMAIN_MANAGER	3
+
+static inline void set_domain(unsigned val)
+{
+	/* Set the Domain Access Control Register */
+	asm volatile ("mcr  p15,0,%0,c3,c0,0" : : "r"(val) /*:*/);
+}
+
+static inline void
+create_sections(uint32_t *ttb, unsigned long first,
+		unsigned long last, unsigned int flags)
+{
+	unsigned long ttb_start = pgd_index(first);
+	unsigned long ttb_end = pgd_index(last) + 1;
+	unsigned int i, addr = first;
+
+	for (i = ttb_start; i < ttb_end; i++) {
+		ttb[i] = addr | flags;
+		addr += PGDIR_SIZE;
+	}
+}
+
+#define PMD_SECT_DEF_UNCACHED (PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | PMD_TYPE_SECT)
+#define PMD_SECT_DEF_CACHED (PMD_SECT_WB | PMD_SECT_DEF_UNCACHED)
+
+static inline void create_flat_mapping(uint32_t *ttb)
+{
+	/* create a flat mapping using 1MiB sections */
+	create_sections(ttb, 0, 0xffffffff, PMD_SECT_DEF_UNCACHED);
+}
+
 #endif /* __ARM_MMU_H */
diff --git a/arch/arm/cpu/mmu_64.c b/arch/arm/cpu/mmu_64.c
index d5a3d22..b6287ae 100644
--- a/arch/arm/cpu/mmu_64.c
+++ b/arch/arm/cpu/mmu_64.c
@@ -126,6 +126,7 @@
 	uint64_t idx;
 	uint64_t addr;
 	uint64_t *table;
+	uint64_t type;
 	int level;
 
 	if (!ttb)
@@ -145,11 +146,9 @@
 			pte = table + idx;
 
 			if (size >= block_size && IS_ALIGNED(addr, block_size)) {
-				if (level == 3)
-					*pte = phys | attr | PTE_TYPE_PAGE;
-				else
-					*pte = phys | attr | PTE_TYPE_BLOCK;
-
+				type = (level == 3) ?
+					PTE_TYPE_PAGE : PTE_TYPE_BLOCK;
+				*pte = phys | attr | type;
 				addr += block_size;
 				phys += block_size;
 				size -= block_size;
@@ -172,6 +171,17 @@
 
 int arch_remap_range(void *_start, size_t size, unsigned flags)
 {
+	switch (flags) {
+	case MAP_CACHED:
+		flags = CACHED_MEM;
+		break;
+	case MAP_UNCACHED:
+		flags = UNCACHED_MEM;
+		break;
+	default:
+		return -EINVAL;
+	}
+
 	map_region((uint64_t)_start, (uint64_t)_start, (uint64_t)size, flags);
 	tlb_invalidate();
 
@@ -204,10 +214,7 @@
 	if (get_cr() & CR_M)
 		mmu_disable();
 
-	ttb = xmemalign(GRANULE_SIZE, GRANULE_SIZE);
-
-	memset(ttb, 0, GRANULE_SIZE);
-
+	ttb = create_table();
 	el = current_el();
 	set_ttbr_tcr_mair(el, (uint64_t)ttb, calc_tcr(el), MEMORY_ATTRIBUTES);
 
diff --git a/arch/arm/cpu/mmu_64.h b/arch/arm/cpu/mmu_64.h
index c280d2c..2cbe720 100644
--- a/arch/arm/cpu/mmu_64.h
+++ b/arch/arm/cpu/mmu_64.h
@@ -28,7 +28,7 @@
 
 static inline void set_ttbr_tcr_mair(int el, uint64_t table, uint64_t tcr, uint64_t attr)
 {
-	asm volatile("dsb sy");
+	dsb();
 	if (el == 1) {
 		asm volatile("msr ttbr0_el1, %0" : : "r" (table) : "memory");
 		asm volatile("msr tcr_el1, %0" : : "r" (tcr) : "memory");
@@ -44,7 +44,7 @@
 	} else {
 		hang();
 	}
-	asm volatile("isb");
+	isb();
 }
 
 static inline uint64_t get_ttbr(int el)
diff --git a/arch/arm/include/asm/barebox-arm.h b/arch/arm/include/asm/barebox-arm.h
index 4803237..bd355f6 100644
--- a/arch/arm/include/asm/barebox-arm.h
+++ b/arch/arm/include/asm/barebox-arm.h
@@ -32,6 +32,12 @@
 #include <linux/compiler.h>
 #include <asm/barebox-arm-head.h>
 
+/*
+ * We have a 4GiB address space split into 1MiB sections, with each
+ * section header taking 4 bytes
+ */
+#define ARM_TTB_SIZE	(SZ_4G / SZ_1M * sizeof(u32))
+
 unsigned long get_runtime_offset(void);
 
 /* global_variable_offset() - Access global variables when not running at link address
@@ -114,7 +120,7 @@
 					unsigned long endmem)
 {
 	endmem = arm_mem_stack(membase, endmem);
-	endmem = ALIGN_DOWN(endmem, SZ_16K) - SZ_16K;
+	endmem = ALIGN_DOWN(endmem, ARM_TTB_SIZE) - ARM_TTB_SIZE;
 
 	return endmem;
 }
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index ce3e815..fbde0bc 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -8,6 +8,8 @@
 #ifndef __LINUX_SIZES_H__
 #define __LINUX_SIZES_H__
 
+#include <linux/const.h>
+
 #define SZ_1				0x00000001
 #define SZ_2				0x00000002
 #define SZ_4				0x00000004
@@ -44,4 +46,6 @@
 #define SZ_1G				0x40000000
 #define SZ_2G				0x80000000
 
+#define SZ_4G				_AC(0x100000000, ULL)
+
 #endif /* __LINUX_SIZES_H__ */