diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 201ccaa11f61b1ff647b55e5ed12e52e2b74c32f..11397687f42c56578ae2d7be2135efcdf44a8b9f 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -304,13 +304,23 @@ PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
 
 static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
+#define __pgprot_modify(prot,mask,bits)		\
+	__pgprot((pgprot_val(prot) & ~(mask)) | (bits))
+
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
 #define pgprot_noncached(prot) \
-	__pgprot((pgprot_val(prot) & ~L_PTE_MT_MASK) | L_PTE_MT_UNCACHED)
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
 #define pgprot_writecombine(prot) \
-	__pgprot((pgprot_val(prot) & ~L_PTE_MT_MASK) | L_PTE_MT_BUFFERABLE)
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE)
+#if __LINUX_ARM_ARCH__ >= 7
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#else
+#define pgprot_dmacoherent(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
+#endif
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index d65b2f5bf41f60cfd21163ef0e5b92e76bc58db8..058e7e90881d6a86103df826f43ec9ab2563682b 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -138,21 +138,26 @@ extern unsigned int user_debug;
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 #endif
 
-#ifndef CONFIG_SMP
+#if __LINUX_ARM_ARCH__ >= 7 || defined(CONFIG_SMP)
+#define mb()		dmb()
+#define rmb()		dmb()
+#define wmb()		dmb()
+#else
 #define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define wmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
+#endif
+
+#ifndef CONFIG_SMP
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #else
-#define mb()		dmb()
-#define rmb()		dmb()
-#define wmb()		dmb()
-#define smp_mb()	dmb()
-#define smp_rmb()	dmb()
-#define smp_wmb()	dmb()
+#define smp_mb()	mb()
+#define smp_rmb()	rmb()
+#define smp_wmb()	wmb()
 #endif
+
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 6fac793329c65081fcc021f4449dbf699f3e9f1a..26325cb5d368e504e6eb7c669b28ac3ed023e3c6 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -317,7 +317,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp,
-			   pgprot_noncached(pgprot_kernel));
+			   pgprot_dmacoherent(pgprot_kernel));
 }
 EXPORT_SYMBOL(dma_alloc_coherent);
 
@@ -365,7 +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);