diff --git a/doc/README.arm-caches b/doc/README.arm-caches
index cd2b4587c2..f6a52e3e38 100644
--- a/doc/README.arm-caches
+++ b/doc/README.arm-caches
@@ -40,6 +40,8 @@ Buffer Requirements:
 - If the buffer is not cache-line aligned invalidation will be restricted
   to the aligned part. That is, one cache-line at the respective boundary
   may be left out while doing invalidation.
+- A suitable buffer can be alloced on the stack using the
+  ALLOC_CACHE_ALIGN_BUFFER macro.
 
 Cleanup Before Linux:
 - cleanup_before_linux() should flush the D-cache, invalidate I-cache, and
diff --git a/include/common.h b/include/common.h
index a1683a20aa..13575272b4 100644
--- a/include/common.h
+++ b/include/common.h
@@ -843,6 +843,64 @@ int cpu_release(int nr, int argc, char * const argv[]);
 #include <asm/cache.h>
 #endif
 
+/*
+ * The ALLOC_CACHE_ALIGN_BUFFER macro is used to allocate a buffer on the
+ * stack that meets the minimum architecture alignment requirements for DMA.
+ * Such a buffer is useful for DMA operations where flushing and invalidating
+ * the cache before and after a read and/or write operation is required for
+ * correct operations.
+ *
+ * When called the macro creates an array on the stack that is sized such
+ * that:
+ *
+ * 1) The beginning of the array can be advanced enough to be aligned.
+ *
+ * 2) The size of the aligned portion of the array is a multiple of the minimum
+ *    architecture alignment required for DMA.
+ *
+ * 3) The aligned portion contains enough space for the original number of
+ *    elements requested.
+ *
+ * The macro then creates a pointer to the aligned portion of this array and
+ * assigns to the pointer the address of the first element in the aligned
+ * portion of the array.
+ *
+ * Calling the macro as:
+ *
+ *     ALLOC_CACHE_ALIGN_BUFFER(uint32_t, buffer, 1024);
+ *
+ * Will result in something similar to saying:
+ *
+ *     uint32_t    buffer[1024];
+ *
+ * The following differences exist:
+ *
+ * 1) The resulting buffer is guaranteed to be aligned to the value of
+ *    ARCH_DMA_MINALIGN.
+ *
+ * 2) The buffer variable created by the macro is a pointer to the specified
+ *    type, and NOT an array of the specified type.  This can be very important
+ *    if you want the address of the buffer, which you probably do, to pass it
+ *    to the DMA hardware.  The value of &buffer is different in the two cases.
+ *    In the macro case it will be the address of the pointer, not the address
+ *    of the space reserved for the buffer.  However, in the second case it
+ *    would be the address of the buffer.  So if you are replacing hard coded
+ *    stack buffers with this macro you need to make sure you remove the & from
+ *    the locations where you are taking the address of the buffer.
+ *
+ * Note that the size parameter is the number of array elements to allocate,
+ * not the number of bytes.
+ *
+ * This macro can not be used outside of function scope, or for the creation
+ * of a function scoped static buffer.  It can not be used to create a cache
+ * line aligned global buffer.
+ */
+#define ALLOC_CACHE_ALIGN_BUFFER(type, name, size)			\
+	char __##name[ROUND(size * sizeof(type), ARCH_DMA_MINALIGN) +	\
+		      ARCH_DMA_MINALIGN - 1];				\
+									\
+	type *name = (type *) ALIGN((uintptr_t)__##name, ARCH_DMA_MINALIGN)
+
 /* Pull in stuff for the build system */
 #ifdef DO_DEPS_ONLY
 # include <environment.h>