block/rnbd-clt: Support polling mode for IO latency optimization

RNBD can make double-queues for irq-mode and poll-mode.
For example, on 4-CPU system 8 request-queues are created,
4 for irq-mode and 4 for poll-mode.
If the IO has HIPRI flag, the block-layer will call .poll function
of RNBD. Then IO is sent to the poll-mode queue.
Add optional nr_poll_queues argument for map_devices interface.

To support polling of RNBD, RTRS client creates connections
for both of irq-mode and direct-poll-mode.

For example, on 4-CPU system it could've create 5 connections:
con[0] => user message (softirq cq)
con[1:4] => softirq cq

After this patch, it can create 9 connections:
con[0] => user message (softirq cq)
con[1:4] => softirq cq
con[5:8] => DIRECT-POLL cq

Cc: Leon Romanovsky <leonro@nvidia.com>
Cc: linux-rdma@vger.kernel.org
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Acked-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20210419073722.15351-14-gi-oh.kim@ionos.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 52 insertions, 14 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 7efd49bdc78c..eb0a5e2058ae 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -174,7 +174,7 @@ struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
 	int id = 0;
 
 	if (likely(permit->con_type == RTRS_IO_CON))
-		id = (permit->cpu_id % (sess->s.con_num - 1)) + 1;
+		id = (permit->cpu_id % (sess->s.irq_con_num - 1)) + 1;
 
 	return to_clt_con(sess->s.con[id]);
 }
@@ -1400,23 +1400,29 @@ static void rtrs_clt_close_work(struct work_struct *work);
 static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 					 const struct rtrs_addr *path,
 					 size_t con_num, u16 max_segments,
-					 size_t max_segment_size)
+					 size_t max_segment_size, u32 nr_poll_queues)
 {
 	struct rtrs_clt_sess *sess;
 	int err = -ENOMEM;
 	int cpu;
+	size_t total_con;
 
 	sess = kzalloc(sizeof(*sess), GFP_KERNEL);
 	if (!sess)
 		goto err;
 
-	/* Extra connection for user messages */
-	con_num += 1;
-
-	sess->s.con = kcalloc(con_num, sizeof(*sess->s.con), GFP_KERNEL);
+	/*
+	 * irqmode and poll
+	 * +1: Extra connection for user messages
+	 */
+	total_con = con_num + nr_poll_queues + 1;
+	sess->s.con = kcalloc(total_con, sizeof(*sess->s.con), GFP_KERNEL);
 	if (!sess->s.con)
 		goto err_free_sess;
 
+	sess->s.con_num = total_con;
+	sess->s.irq_con_num = con_num + 1;
+
 	sess->stats = kzalloc(sizeof(*sess->stats), GFP_KERNEL);
 	if (!sess->stats)
 		goto err_free_con;
@@ -1435,7 +1441,6 @@ static struct rtrs_clt_sess *alloc_sess(struct rtrs_clt *clt,
 		memcpy(&sess->s.src_addr, path->src,
 		       rdma_addr_size((struct sockaddr *)path->src));
 	strlcpy(sess->s.sessname, clt->sessname, sizeof(sess->s.sessname));
-	sess->s.con_num = con_num;
 	sess->clt = clt;
 	sess->max_pages_per_mr = max_segments * max_segment_size >> 12;
 	init_waitqueue_head(&sess->state_wq);
@@ -1576,9 +1581,14 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 	}
 	cq_size = max_send_wr + max_recv_wr;
 	cq_vector = con->cpu % sess->s.dev->ib_dev->num_comp_vectors;
-	err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
-				 cq_vector, cq_size, max_send_wr,
-				 max_recv_wr, IB_POLL_SOFTIRQ);
+	if (con->c.cid >= sess->s.irq_con_num)
+		err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+					cq_vector, cq_size, max_send_wr,
+					max_recv_wr, IB_POLL_DIRECT);
+	else
+		err = rtrs_cq_qp_create(&sess->s, &con->c, sess->max_send_sge,
+					cq_vector, cq_size, max_send_wr,
+					max_recv_wr, IB_POLL_SOFTIRQ);
 	/*
 	 * In case of error we do not bother to clean previous allocations,
 	 * since destroy_con_cq_qp() must be called.
@@ -2631,6 +2641,7 @@ static void free_clt(struct rtrs_clt *clt)
  * @max_segment_size: Max. size of one segment
  * @max_reconnect_attempts: Number of times to reconnect on error before giving
  *			    up, 0 for * disabled, -1 for forever
+ * @nr_poll_queues: number of polling mode connection using IB_POLL_DIRECT flag
  *
  * Starts session establishment with the rtrs_server. The function can block
  * up to ~2000ms before it returns.
@@ -2644,7 +2655,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 u16 max_segments,
 				 size_t max_segment_size,
-				 s16 max_reconnect_attempts)
+				 s16 max_reconnect_attempts, u32 nr_poll_queues)
 {
 	struct rtrs_clt_sess *sess, *tmp;
 	struct rtrs_clt *clt;
@@ -2662,7 +2673,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 		struct rtrs_clt_sess *sess;
 
 		sess = alloc_sess(clt, &paths[i], nr_cpu_ids,
-				  max_segments, max_segment_size);
+				  max_segments, max_segment_size, nr_poll_queues);
 		if (IS_ERR(sess)) {
 			err = PTR_ERR(sess);
 			goto close_all_sess;
@@ -2887,6 +2898,31 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 }
 EXPORT_SYMBOL(rtrs_clt_request);
 
+int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index)
+{
+	int cnt;
+	struct rtrs_con *con;
+	struct rtrs_clt_sess *sess;
+	struct path_it it;
+
+	rcu_read_lock();
+	for (path_it_init(&it, clt);
+	     (sess = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
+		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
+			continue;
+
+		con = sess->s.con[index + 1];
+		cnt = ib_process_cq_direct(con->cq, -1);
+		if (cnt)
+			break;
+	}
+	path_it_deinit(&it);
+	rcu_read_unlock();
+
+	return cnt;
+}
+EXPORT_SYMBOL(rtrs_clt_rdma_cq_direct);
+
 /**
  * rtrs_clt_query() - queries RTRS session attributes
  *@clt: session pointer
@@ -2916,7 +2952,7 @@ int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 	int err;
 
 	sess = alloc_sess(clt, addr, nr_cpu_ids, clt->max_segments,
-			  clt->max_segment_size);
+			  clt->max_segment_size, 0);
 	if (IS_ERR(sess))
 		return PTR_ERR(sess);
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
index 8caad0a2322b..00eb45053339 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
@@ -101,6 +101,7 @@ struct rtrs_sess {
 	uuid_t			uuid;
 	struct rtrs_con	**con;
 	unsigned int		con_num;
+	unsigned int		irq_con_num;
 	unsigned int		recon_cnt;
 	struct rtrs_ib_dev	*dev;
 	int			dev_ref;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.h b/drivers/infiniband/ulp/rtrs/rtrs.h
index 2db1b5eb3ab0..f891fbe7abe6 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs.h
@@ -59,7 +59,7 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 				 size_t pdu_sz, u8 reconnect_delay_sec,
 				 u16 max_segments,
 				 size_t max_segment_size,
-				 s16 max_reconnect_attempts);
+				 s16 max_reconnect_attempts, u32 nr_poll_queues);
 
 void rtrs_clt_close(struct rtrs_clt *sess);
 
@@ -103,6 +103,7 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 		     struct rtrs_clt *sess, struct rtrs_permit *permit,
 		     const struct kvec *vec, size_t nr, size_t len,
 		     struct scatterlist *sg, unsigned int sg_cnt);
+int rtrs_clt_rdma_cq_direct(struct rtrs_clt *clt, unsigned int index);
 
 /**
  * rtrs_attrs - RTRS session attributes