diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index bb02e9f6944e264f52e13d3f4cc1ea51beaccce2..b316ab787a3bcd8febe5e4aae15a3304dbbc586d 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/code-patching.h>
 
 #define DBG(fmt...)
 
@@ -116,6 +117,8 @@ notrace void __init machine_init(u64 dt_ptr)
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
+	patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
+
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));
 
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 2ef50c6294709674ad69167b14ac8a5bede4631e..da5847d0971880f3e73833c8ded7e7646927149a 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -128,6 +128,10 @@ _GLOBAL(memset)
  * the destination area is cacheable.
  * We only use this version if the source and dest don't overlap.
  * -- paulus.
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memmove)
 	cmplw	0,r3,r4
@@ -135,6 +139,7 @@ _GLOBAL(memmove)
 	/* fall through */
 
 _GLOBAL(memcpy)
+	b	generic_memcpy
 	add	r7,r3,r5		/* test if the src & dst overlap */
 	add	r8,r4,r5
 	cmplw	0,r4,r7