crypto: hisilicon/qm - optimize the barrier operation

A 'dma_wmb' barrier is enough to guarantee previous writes
before accessing by acc device in the outer shareable domain.

A 'smp_wmb' barrier is enough to guarantee previous writes
before accessing by other cpus in the inner shareble domain.

Signed-off-by: Hui Tang <[e-mail]>
Signed-off-by: Herbert Xu <[e-mail]>

drivers/crypto/hisilicon/qm.c

···
 
 	if (!IS_ENABLED(CONFIG_ARM64)) {
 		memcpy_toio(fun_base, src, 16);
-		wmb();
+		dma_wmb();
 		return;
 	}
 
 	asm volatile("ldp %0, %1, %3\n"
 		     "stp %0, %1, %2\n"
-		     "dsb sy\n"
+		     "dmb oshst\n"
 		     : "=&r" (tmp0),
 		       "=&r" (tmp1),
 		       "+Q" (*((char __iomem *)fun_base))
···
 	*addr = 1;
 
 	/* make sure setup is completed */
-	mb();
+	smp_wmb();
 }
 
 static void qm_disable_qp(struct hisi_qm *qm, u32 qp_id)