RDMA/hns: Replace wmb&__raw_writeq with writeq

mainline inclusion
from mainline-v5.12-rc1
commit 86f767e6
category: bugfix
bugzilla: 174002
CVE:NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=86f767e6fc1e719215ccf2b2ec65466f505f731b

----------------------------------------------------------------------

Currently, the driver updates doorbell looks like this:

post()
{
	wqe.field = 0x111;
	wmb();
	update_wq_db();
}

update_wq_db()
{
	db.field = 0x222;
	__raw_writeq(db, db_reg);
}

writeq() is a better choice than __raw_writeq() because it calls dma_wmb()
to barrier in ARM64, and dma_wmb() is better than wmb() for ROCEE device.

This patch removes all wmb() before updating doorbell of SQ/RQ/CQ/SRQ by
replacing __raw_writeq() with writeq() to improve performence.  The new
process looks like this:

post()
{
	wqe.field = 0x111;
	update_wq_db();
}

update_wq_db()
{
	db.field = 0x222;
	writeq(db, db_reg);
}

Link: https://lore.kernel.org/r/1612517974-31867-8-git-send-email-liweihang@huawei.comSigned-off-by: NLang Cheng <chenglang@huawei.com>
Signed-off-by: NWeihang Li <liweihang@huawei.com>
Signed-off-by: NJason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nwangsirong <wangsirong@huawei.com>
Reviewed-by: NChunZhi Hu <huchunzhi@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

drivers/infiniband/hw/hns/hns_roce_device.h

@@ -1077,7 +1077,7 @@ static inline struct hns_roce_srq *to_hr_srq(struct ib_srq *ibsrq)
 
 static inline void hns_roce_write64_k(__le32 val[2], void __iomem *dest)
 {
-	__raw_writeq(*(u64 *) val, dest);
+	writeq(*(u64 *)val, dest);
 }
 
 static inline struct hns_roce_qp

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -330,8 +330,6 @@ static int hns_roce_v1_post_send(struct ib_qp *ibqp,
 	/* Set DB return */
 	if (likely(nreq)) {
 		qp->sq.head += nreq;
-		/* Memory barrier */
-		wmb();
 
 		roce_set_field(sq_db.u32_4, SQ_DOORBELL_U32_4_SQ_HEAD_M,
 			       SQ_DOORBELL_U32_4_SQ_HEAD_S,
@@ -411,8 +409,6 @@ static int hns_roce_v1_post_recv(struct ib_qp *ibqp,
 out:
 	if (likely(nreq)) {
 		hr_qp->rq.head += nreq;
-		/* Memory barrier */
-		wmb();
 
 		if (ibqp->qp_type == IB_QPT_GSI) {
 			__le32 tmp;
@@ -1984,12 +1980,6 @@ static void __hns_roce_v1_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn,
 
 	if (nfreed) {
 		hr_cq->cons_index += nfreed;
-		/*
-		 * Make sure update of buffer contents is done before
-		 * updating consumer index.
-		 */
-		wmb();
-
 		hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
 	}
 }
@@ -2335,8 +2325,6 @@ int hns_roce_v1_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 		*hr_cq->tptr_addr = hr_cq->cons_index &
 			((hr_cq->cq_depth << 1) - 1);
 
-		/* Memroy barrier */
-		wmb();
 		hns_roce_v1_cq_set_ci(hr_cq, hr_cq->cons_index);
 	}
 
@@ -3225,9 +3213,6 @@ static int hns_roce_v1_m_qp(struct ib_qp *ibqp, const struct ib_qp_attr *attr,
 	 * need to hw to flash RQ HEAD by DB again
 	 */
 	if (cur_state == IB_QPS_INIT && new_state == IB_QPS_INIT) {
-		/* Memory barrier */
-		wmb();
-
 		roce_set_field(doorbell[0], RQ_DOORBELL_U32_4_RQ_HEAD_M,
 			       RQ_DOORBELL_U32_4_RQ_HEAD_S, hr_qp->rq.head);
 		roce_set_field(doorbell[1], RQ_DOORBELL_U32_8_QPN_M,

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

@@ -744,8 +744,6 @@ static int hns_roce_v2_post_send(struct ib_qp *ibqp,
 	if (likely(nreq)) {
 		qp->sq.head += nreq;
 		qp->next_sge = sge_idx;
-		/* Memory barrier */
-		wmb();
 
 		if (nreq == 1 && qp->sq.head == qp->sq.tail + 1 &&
 		    (qp->en_flags & HNS_ROCE_QP_CAP_DIRECT_WQE))
@@ -875,8 +873,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp,
 out:
 	if (likely(nreq)) {
 		hr_qp->rq.head += nreq;
-		/* Memory barrier */
-		wmb();
 
 		/*
 		 * Hip08 hardware cannot flush the WQEs in RQ if the QP state
@@ -1015,12 +1011,6 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq,
 	}
 
 	if (likely(nreq)) {
-		/*
-		 * Make sure that descriptors are written before
-		 * doorbell record.
-		 */
-		wmb();
-
 		srq_db.byte_4 =
 			cpu_to_le32(HNS_ROCE_V2_SRQ_DB << V2_DB_BYTE_4_CMD_S |
 				    (srq->srqn & V2_DB_BYTE_4_TAG_M));
@@ -3197,11 +3187,6 @@ static void __hns_roce_v2_cq_clean(struct hns_roce_cq *hr_cq, u32 qpn,
 
 	if (nfreed) {
 		hr_cq->cons_index += nfreed;
-		/*
-		 * Make sure update of buffer contents is done before
-		 * updating consumer index.
-		 */
-		wmb();
 		hns_roce_v2_cq_set_ci(hr_cq, hr_cq->cons_index);
 	}
 }
@@ -3710,11 +3695,8 @@ static int hns_roce_v2_poll_cq(struct ib_cq *ibcq, int num_entries,
 			break;
 	}
 
-	if (npolled) {
-		/* Memory barrier */
-		wmb();
+	if (npolled)
 		hns_roce_v2_cq_set_ci(hr_cq, hr_cq->cons_index);
-	}
 
 out:
 	spin_unlock_irqrestore(&hr_cq->lock, flags);