crypto: caam/jr - Remove extra memory barrier during job ring dequeue

In function caam_jr_dequeue(), a full memory barrier is used before
writing response job ring's register to signal removal of the completed
job. Therefore for writing the register, we do not need another write
memory barrier. Hence it is removed by replacing the call to wr_reg32()
with a newly defined function wr_reg32_relaxed().
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

drivers/crypto/caam/jr.c

@@ -213,7 +213,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 		mb();
 
 		/* set done */
-		wr_reg32(&jrp->rregs->outring_rmvd, 1);
+		wr_reg32_relaxed(&jrp->rregs->outring_rmvd, 1);
 
 		jrp->out_ring_read_index = (jrp->out_ring_read_index + 1) &
 					   (JOBR_DEPTH - 1);

drivers/crypto/caam/regs.h

@@ -96,6 +96,14 @@ cpu_to_caam(16)
 cpu_to_caam(32)
 cpu_to_caam(64)
 
+static inline void wr_reg32_relaxed(void __iomem *reg, u32 data)
+{
+	if (caam_little_end)
+		writel_relaxed(data, reg);
+	else
+		writel_relaxed(cpu_to_be32(data), reg);
+}
+
 static inline void wr_reg32(void __iomem *reg, u32 data)
 {
 	if (caam_little_end)