powerpc: Align thread->fpr to 16 bytes

On newer CPUs we use VSX loads and stores to the thread->fpr array.
For best performance we need to ensure 16 byte alignment.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/processor.h

@@ -200,7 +200,7 @@ struct thread_struct {
 #endif
 #endif
 	/* FP and VSX 0-31 register set */
-	double		fpr[32][TS_FPRWIDTH];
+	double		fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
 	struct {
 
 		unsigned int pad;