diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 9ecccc8..6976b03 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -100,23 +100,19 @@
 #define TASK_UNMAPPED_BASE	UL(0x00000000)
 #endif
 
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET 		UL(CONFIG_DRAM_BASE)
-#endif
-
 #ifndef END_MEM
 #define END_MEM     		(UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
 #ifndef PAGE_OFFSET
-#define PAGE_OFFSET		(PHYS_OFFSET)
+#define PAGE_OFFSET		PLAT_PHYS_OFFSET
 #endif
 
 /*
  * The module can be at any place in ram in nommu mode.
  */
 #define MODULES_END		(END_MEM)
-#define MODULES_VADDR		(PHYS_OFFSET)
+#define MODULES_VADDR		PAGE_OFFSET
 
 #define XIP_VIRT_ADDR(physaddr)  (physaddr)
 
@@ -157,6 +153,16 @@
 #endif
 #define ARCH_PGD_MASK		((1 << ARCH_PGD_SHIFT) - 1)
 
+/*
+ * PLAT_PHYS_OFFSET is the offset (from zero) of the start of physical
+ * memory.  This is used for XIP and NoMMU kernels, or by kernels which
+ * have their own mach/memory.h.  Assembly code must always use
+ * PLAT_PHYS_OFFSET and not PHYS_OFFSET.
+ */
+#ifndef PLAT_PHYS_OFFSET
+#define PLAT_PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
+#endif
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -239,6 +245,8 @@
 
 #else
 
+#define PHYS_OFFSET	PLAT_PHYS_OFFSET
+
 static inline phys_addr_t __virt_to_phys(unsigned long x)
 {
 	return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
@@ -251,17 +259,6 @@
 
 #endif
 #endif
-#endif /* __ASSEMBLY__ */
-
-#ifndef PHYS_OFFSET
-#ifdef PLAT_PHYS_OFFSET
-#define PHYS_OFFSET	PLAT_PHYS_OFFSET
-#else
-#define PHYS_OFFSET	UL(CONFIG_PHYS_OFFSET)
-#endif
-#endif
-
-#ifndef __ASSEMBLY__
 
 /*
  * PFNs are used to describe any physical page; this means
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 14235ba..716249c 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -68,7 +68,7 @@
 
 #ifdef CONFIG_ARM_MPU
 	/* Calculate the size of a region covering just the kernel */
-	ldr	r5, =PHYS_OFFSET		@ Region start: PHYS_OFFSET
+	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
 	ldr     r6, =(_end)			@ Cover whole kernel
 	sub	r6, r6, r5			@ Minimum size of region to map
 	clz	r6, r6				@ Region size must be 2^N...
@@ -213,7 +213,7 @@
 	set_region_nr r0, #MPU_RAM_REGION
 	isb
 	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
-	ldr	r0, =PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
+	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
 	ldr	r5,=(MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL)
 
 	setup_region r0, r5, r6, MPU_DATA_SIDE	@ PHYS_OFFSET, shared, enabled
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 11d59b3..32f317e 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -110,7 +110,7 @@
 	sub	r4, r3, r4			@ (PHYS_OFFSET - PAGE_OFFSET)
 	add	r8, r8, r4			@ PHYS_OFFSET
 #else
-	ldr	r8, =PHYS_OFFSET		@ always constant in this case
+	ldr	r8, =PLAT_PHYS_OFFSET		@ always constant in this case
 #endif
 
 	/*
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 94f6b05..92f7b15 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -404,6 +404,7 @@
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
+	unsigned long stack_page;
 	int count = 0;
 	if (!p || p == current || p->state == TASK_RUNNING)
 		return 0;
@@ -412,9 +413,11 @@
 	frame.sp = thread_saved_sp(p);
 	frame.lr = 0;			/* recovered from the stack */
 	frame.pc = thread_saved_pc(p);
+	stack_page = (unsigned long)task_stack_page(p);
 	do {
-		int ret = unwind_frame(&frame);
-		if (ret < 0)
+		if (frame.sp < stack_page ||
+		    frame.sp >= stack_page + THREAD_SIZE ||
+		    unwind_frame(&frame) < 0)
 			return 0;
 		if (!in_sched_functions(frame.pc))
 			return frame.pc;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 6a1b8a8..987a7f5 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -873,8 +873,6 @@
 	machine_desc = mdesc;
 	machine_name = mdesc->name;
 
-	setup_dma_zone(mdesc);
-
 	if (mdesc->reboot_mode != REBOOT_HARD)
 		reboot_mode = mdesc->reboot_mode;
 
@@ -892,6 +890,7 @@
 	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
 
 	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
+	setup_dma_zone(mdesc);
 	sanity_check_meminfo();
 	arm_memblock_init(&meminfo, mdesc);
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 00f79e5..af4e8c8 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -31,7 +31,7 @@
 	high = ALIGN(low, THREAD_SIZE);
 
 	/* check current frame pointer is within bounds */
-	if (fp < (low + 12) || fp + 4 >= high)
+	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
 
 	/* restore the registers from the stack frame */
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index dbf0923..7940241 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -509,9 +509,10 @@
 __do_cache_op(unsigned long start, unsigned long end)
 {
 	int ret;
-	unsigned long chunk = PAGE_SIZE;
 
 	do {
+		unsigned long chunk = min(PAGE_SIZE, end - start);
+
 		if (signal_pending(current)) {
 			struct thread_info *ti = current_thread_info();
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f6b6bfa..f61a570 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -158,13 +158,49 @@
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
+static int __dma_supported(struct device *dev, u64 mask, bool warn)
+{
+	unsigned long max_dma_pfn;
+
+	/*
+	 * If the mask allows for more memory than we can address,
+	 * and we actually have that much memory, then we must
+	 * indicate that DMA to this device is not supported.
+	 */
+	if (sizeof(mask) != sizeof(dma_addr_t) &&
+	    mask > (dma_addr_t)~0 &&
+	    dma_to_pfn(dev, ~0) < max_pfn) {
+		if (warn) {
+			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
+				 mask);
+			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
+		}
+		return 0;
+	}
+
+	max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+
+	/*
+	 * Translate the device's DMA mask to a PFN limit.  This
+	 * PFN number includes the page which we can DMA to.
+	 */
+	if (dma_to_pfn(dev, mask) < max_dma_pfn) {
+		if (warn)
+			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
+				 mask,
+				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
+				 max_dma_pfn + 1);
+		return 0;
+	}
+
+	return 1;
+}
+
 static u64 get_coherent_dma_mask(struct device *dev)
 {
 	u64 mask = (u64)DMA_BIT_MASK(32);
 
 	if (dev) {
-		unsigned long max_dma_pfn;
-
 		mask = dev->coherent_dma_mask;
 
 		/*
@@ -176,34 +212,8 @@
 			return 0;
 		}
 
-		max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
-
-		/*
-		 * If the mask allows for more memory than we can address,
-		 * and we actually have that much memory, then fail the
-		 * allocation.
-		 */
-		if (sizeof(mask) != sizeof(dma_addr_t) &&
-		    mask > (dma_addr_t)~0 &&
-		    dma_to_pfn(dev, ~0) > max_dma_pfn) {
-			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
-				 mask);
-			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
+		if (!__dma_supported(dev, mask, true))
 			return 0;
-		}
-
-		/*
-		 * Now check that the mask, when translated to a PFN,
-		 * fits within the allowable addresses which we can
-		 * allocate.
-		 */
-		if (dma_to_pfn(dev, mask) < max_dma_pfn) {
-			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
-				 mask,
-				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
-				 arm_dma_pfn_limit + 1);
-			return 0;
-		}
 	}
 
 	return mask;
@@ -1032,28 +1042,7 @@
  */
 int dma_supported(struct device *dev, u64 mask)
 {
-	unsigned long limit;
-
-	/*
-	 * If the mask allows for more memory than we can address,
-	 * and we actually have that much memory, then we must
-	 * indicate that DMA to this device is not supported.
-	 */
-	if (sizeof(mask) != sizeof(dma_addr_t) &&
-	    mask > (dma_addr_t)~0 &&
-	    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit)
-		return 0;
-
-	/*
-	 * Translate the device's DMA mask to a PFN limit.  This
-	 * PFN number includes the page which we can DMA to.
-	 */
-	limit = dma_to_pfn(dev, mask);
-
-	if (limit < arm_dma_pfn_limit)
-		return 0;
-
-	return 1;
+	return __dma_supported(dev, mask, false);
 }
 EXPORT_SYMBOL(dma_supported);
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 3e8f106..1f7b19a 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -229,7 +229,7 @@
 #ifdef CONFIG_ZONE_DMA
 	if (mdesc->dma_zone_size) {
 		arm_dma_zone_size = mdesc->dma_zone_size;
-		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
+		arm_dma_limit = __pv_phys_offset + arm_dma_zone_size - 1;
 	} else
 		arm_dma_limit = 0xffffffff;
 	arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;