diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 68be9017593df10f235ca228a6837aaa11f5c818..132c70e2d2f11cfb4e655ddcb05931be5bd03498 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -263,16 +263,37 @@ restart:	adr	r0, LC0
 		 * OK... Let's do some funky business here.
 		 * If we do have a DTB appended to zImage, and we do have
 		 * an ATAG list around, we want the later to be translated
-		 * and folded into the former here.  To be on the safe side,
-		 * let's temporarily move  the stack away into the malloc
-		 * area.  No GOT fixup has occurred yet, but none of the
-		 * code we're about to call uses any global variable.
+		 * and folded into the former here. No GOT fixup has occurred
+		 * yet, but none of the code we're about to call uses any
+		 * global variable.
 		*/
-		add	sp, sp, #0x10000
+
+		/* Get the initial DTB size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+		/* 50% DTB growth should be good enough */
+		add	r5, r5, r5, lsr #1
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+		/* clamp to 32KB min and 1MB max */
+		cmp	r5, #(1 << 15)
+		movlo	r5, #(1 << 15)
+		cmp	r5, #(1 << 20)
+		movhi	r5, #(1 << 20)
+		/* temporarily relocate the stack past the DTB work space */
+		add	sp, sp, r5
+
 		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bl	atags_to_fdt
 
 		/*
@@ -285,11 +306,11 @@ restart:	adr	r0, LC0
 		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
-		sub	sp, sp, #0x10000
+		sub	sp, sp, r5
 #endif
 
 		mov	r8, r6			@ use the appended device tree
@@ -306,7 +327,7 @@ restart:	adr	r0, LC0
 		subs	r1, r5, r1
 		addhi	r9, r9, r1
 
-		/* Get the dtb's size */
+		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
 #ifndef __ARMEB__
 		/* convert r5 (dtb size) to little endian */
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 2260f1855820fa2d2961025b2683c2e30982a8e0..8944f4991c3cfd4e76585cdc11b78e3c3b2257d2 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -22,10 +22,12 @@
 
 __invalid_entry:
 	v7m_exception_entry
+#ifdef CONFIG_PRINTK
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
 	bl	printk
+#endif
 	mov	r0, sp
 	bl	show_regs
 1:	b	1b
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 03823e784f63e7acf91fdda4d5f58927ccf527d9..c43c714555661337048b72a5a21a6b5357659567 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1012,6 +1012,7 @@ config ARCH_SUPPORTS_BIG_ENDIAN
 
 config ARM_KERNMEM_PERMS
 	bool "Restrict kernel memory permissions"
+	depends on MMU
 	help
 	  If this is set, kernel memory other than kernel text (and rodata)
 	  will be made non-executable. The tradeoff is that each region is
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 91892569710f5ab79127218e808e84ef14ef33eb..845769e413323120b6d7b4afed7640746413bc98 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@ static void flush_context(unsigned int cpu)
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index a673c7f7e208efe1bc9b2e2d4ff0cb8ab6a1c5da..903dba064a034c7e5d9fff950d3fa334301130d9 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2048,6 +2048,9 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 
+	if (!mapping)
+		return;
+
 	__arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }