diff --git a/common/memsize.c b/common/memsize.c
index 66d5be6..d646df8 100644
--- a/common/memsize.c
+++ b/common/memsize.c
@@ -7,9 +7,18 @@
 #include <common.h>
 #include <init.h>
 #include <asm/global_data.h>
+#include <cpu_func.h>
+#include <stdint.h>
 
 DECLARE_GLOBAL_DATA_PTR;
 
+#ifdef CONFIG_SYS_CACHELINE_SIZE
+# define MEMSIZE_CACHELINE_SIZE CONFIG_SYS_CACHELINE_SIZE
+#else
+/* Just use the greatest cache flush alignment requirement I'm aware of */
+# define MEMSIZE_CACHELINE_SIZE 128
+#endif
+
 #ifdef __PPC__
 /*
  * At least on G2 PowerPC cores, sequential accesses to non-existent
@@ -20,6 +29,15 @@
 # define sync()		/* nothing */
 #endif
 
+static void dcache_flush_invalidate(volatile long *p)
+{
+	uintptr_t start, stop;
+	start = ALIGN_DOWN((uintptr_t)p, MEMSIZE_CACHELINE_SIZE);
+	stop = start + MEMSIZE_CACHELINE_SIZE;
+	flush_dcache_range(start, stop);
+	invalidate_dcache_range(start, stop);
+}
+
 /*
  * Check memory range for valid RAM. A simple memory test determines
  * the actually available RAM size between addresses `base' and
@@ -34,6 +52,7 @@
 	long           val;
 	long           size;
 	int            i = 0;
+	int            dcache_en = dcache_status();
 
 	for (cnt = (maxsize / sizeof(long)) >> 1; cnt > 0; cnt >>= 1) {
 		addr = base + cnt;	/* pointer arith! */
@@ -41,6 +60,8 @@
 		save[i++] = *addr;
 		sync();
 		*addr = ~cnt;
+		if (dcache_en)
+			dcache_flush_invalidate(addr);
 	}
 
 	addr = base;
@@ -50,6 +71,9 @@
 	*addr = 0;
 
 	sync();
+	if (dcache_en)
+		dcache_flush_invalidate(addr);
+
 	if ((val = *addr) != 0) {
 		/* Restore the original data before leaving the function. */
 		sync();