1 files changed, 61 insertions, 66 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 67f86c405a26..0a08b4b742a3 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -31,6 +31,8 @@
  */
 #define RTRS_RECONNECT_SEED 8
 
+#define FIRST_CONN 0x01
+
 MODULE_DESCRIPTION("RDMA Transport Client");
 MODULE_LICENSE("GPL");
 
@@ -178,18 +180,18 @@ struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
 }
 
 /**
- * __rtrs_clt_change_state() - change the session state through session state
+ * rtrs_clt_change_state() - change the session state through session state
  * machine.
  *
  * @sess: client session to change the state of.
  * @new_state: state to change to.
  *
- * returns true if successful, false if the requested state can not be set.
+ * returns true if sess's state is changed to new state, otherwise return false.
  *
  * Locks:
  * state_wq lock must be hold.
  */
-static bool __rtrs_clt_change_state(struct rtrs_clt_sess *sess,
+static bool rtrs_clt_change_state(struct rtrs_clt_sess *sess,
 				     enum rtrs_clt_state new_state)
 {
 	enum rtrs_clt_state old_state;
@@ -286,7 +288,7 @@ static bool rtrs_clt_change_state_from_to(struct rtrs_clt_sess *sess,
 
 	spin_lock_irq(&sess->state_wq.lock);
 	if (sess->state == old_state)
-		changed = __rtrs_clt_change_state(sess, new_state);
+		changed = rtrs_clt_change_state(sess, new_state);
 	spin_unlock_irq(&sess->state_wq.lock);
 
 	return changed;
@@ -494,7 +496,7 @@ static void rtrs_clt_recv_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 	int err;
 	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
 
-	WARN_ON(sess->flags != RTRS_MSG_NEW_RKEY_F);
+	WARN_ON((sess->flags & RTRS_MSG_NEW_RKEY_F) == 0);
 	iu = container_of(wc->wr_cqe, struct rtrs_iu,
 			  cqe);
 	err = rtrs_iu_post_recv(&con->c, iu);
@@ -514,7 +516,7 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 	u32 buf_id;
 	int err;
 
-	WARN_ON(sess->flags != RTRS_MSG_NEW_RKEY_F);
+	WARN_ON((sess->flags & RTRS_MSG_NEW_RKEY_F) == 0);
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 
@@ -621,12 +623,12 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		} else if (imm_type == RTRS_HB_MSG_IMM) {
 			WARN_ON(con->c.cid);
 			rtrs_send_hb_ack(&sess->s);
-			if (sess->flags == RTRS_MSG_NEW_RKEY_F)
+			if (sess->flags & RTRS_MSG_NEW_RKEY_F)
 				return  rtrs_clt_recv_done(con, wc);
 		} else if (imm_type == RTRS_HB_ACK_IMM) {
 			WARN_ON(con->c.cid);
 			sess->s.hb_missed_cnt = 0;
-			if (sess->flags == RTRS_MSG_NEW_RKEY_F)
+			if (sess->flags & RTRS_MSG_NEW_RKEY_F)
 				return  rtrs_clt_recv_done(con, wc);
 		} else {
 			rtrs_wrn(con->c.sess, "Unknown IMM type %u\n",
@@ -654,7 +656,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		WARN_ON(!(wc->wc_flags & IB_WC_WITH_INVALIDATE ||
 			  wc->wc_flags & IB_WC_WITH_IMM));
 		WARN_ON(wc->wr_cqe->done != rtrs_clt_rdma_done);
-		if (sess->flags == RTRS_MSG_NEW_RKEY_F) {
+		if (sess->flags & RTRS_MSG_NEW_RKEY_F) {
 			if (wc->wc_flags & IB_WC_WITH_INVALIDATE)
 				return  rtrs_clt_recv_done(con, wc);
 
@@ -664,7 +666,6 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 	case IB_WC_RDMA_WRITE:
 		/*
 		 * post_send() RDMA write completions of IO reqs (read/write)
-		 * and hb
 		 */
 		break;
 
@@ -680,7 +681,7 @@ static int post_recv_io(struct rtrs_clt_con *con, size_t q_size)
 	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
 
 	for (i = 0; i < q_size; i++) {
-		if (sess->flags == RTRS_MSG_NEW_RKEY_F) {
+		if (sess->flags & RTRS_MSG_NEW_RKEY_F) {
 			struct rtrs_iu *iu = &con->rsp_ius[i];
 
 			err = rtrs_iu_post_recv(&con->c, iu);
@@ -1318,6 +1319,12 @@ out_err:
 
 static void free_permits(struct rtrs_clt *clt)
 {
+	if (clt->permits_map) {
+		size_t sz = clt->queue_depth;
+
+		wait_event(clt->permits_wait,
+			   find_first_bit(clt->permits_map, sz) >= sz);
+	}
 	kfree(clt->permits_map);
 	clt->permits_map = NULL;
 	kfree(clt->permits);
@@ -1353,21 +1360,14 @@ static bool rtrs_clt_change_state_get_old(struct rtrs_clt_sess *sess,
 	bool changed;
 
 	spin_lock_irq(&sess->state_wq.lock);
-	*old_state = sess->state;
-	changed = __rtrs_clt_change_state(sess, new_state);
+	if (old_state)
+		*old_state = sess->state;
+	changed = rtrs_clt_change_state(sess, new_state);
 	spin_unlock_irq(&sess->state_wq.lock);
 
 	return changed;
 }
 
-static bool rtrs_clt_change_state(struct rtrs_clt_sess *sess,
-				   enum rtrs_clt_state new_state)
-{
-	enum rtrs_clt_state old_state;
-
-	return rtrs_clt_change_state_get_old(sess, new_state, &old_state);
-}
-
 static void rtrs_clt_hb_err_handler(struct rtrs_con *c)
 {
 	struct rtrs_clt_con *con = container_of(c, typeof(*con), c);
@@ -1511,7 +1511,7 @@ static void destroy_con(struct rtrs_clt_con *con)
 static int create_con_cq_qp(struct rtrs_clt_con *con)
 {
 	struct rtrs_clt_sess *sess = to_clt_sess(con->c.sess);
-	u16 wr_queue_size;
+	u32 max_send_wr, max_recv_wr, cq_size;
 	int err, cq_vector;
 	struct rtrs_msg_rkey_rsp *rsp;
 
@@ -1523,7 +1523,8 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 		 * + 2 for drain and heartbeat
 		 * in case qp gets into error state
 		 */
-		wr_queue_size = SERVICE_CON_QUEUE_DEPTH * 3 + 2;
+		max_send_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
+		max_recv_wr = SERVICE_CON_QUEUE_DEPTH * 2 + 2;
 		/* We must be the first here */
 		if (WARN_ON(sess->s.dev))
 			return -EINVAL;
@@ -1555,25 +1556,29 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 
 		/* Shared between connections */
 		sess->s.dev_ref++;
-		wr_queue_size =
+		max_send_wr =
 			min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
 			      /* QD * (REQ + RSP + FR REGS or INVS) + drain */
 			      sess->queue_depth * 3 + 1);
+		max_recv_wr =
+			min_t(int, sess->s.dev->ib_dev->attrs.max_qp_wr,
+			      sess->queue_depth * 3 + 1);
 	}
 	/* alloc iu to recv new rkey reply when server reports flags set */
-	if (sess->flags == RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
-		con->rsp_ius = rtrs_iu_alloc(wr_queue_size, sizeof(*rsp),
+	if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
+		con->rsp_ius = rtrs_iu_alloc(max_recv_wr, sizeof(*rsp),
 					      GFP_KERNEL, sess->s.dev->ib_dev,
 					      DMA_FROM_DEVICE,
 					      rtrs_clt_rdma_done);
 		if (!con->rsp_ius)
 			return -ENOMEM;
-		con->queue_size = wr_queue_size;
+		con->queue_size = max_recv_wr;
 	}
+	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, wr_queue_size, wr_queue_size,
-				 IB_POLL_SOFTIRQ);
+				 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.
@@ -1657,6 +1662,7 @@ static int rtrs_rdma_route_resolved(struct rtrs_clt_con *con)
 		.cid_num = cpu_to_le16(sess->s.con_num),
 		.recon_cnt = cpu_to_le16(sess->s.recon_cnt),
 	};
+	msg.first_conn = sess->for_new_clt ? FIRST_CONN : 0;
 	uuid_copy(&msg.sess_uuid, &sess->s.uuid);
 	uuid_copy(&msg.paths_uuid, &clt->paths_uuid);
 
@@ -1742,6 +1748,8 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 		scnprintf(sess->hca_name, sizeof(sess->hca_name),
 			  sess->s.dev->ib_dev->name);
 		sess->s.src_addr = con->c.cm_id->route.addr.src_addr;
+		/* set for_new_clt, to allow future reconnect on any path */
+		sess->for_new_clt = 1;
 	}
 
 	return 0;
@@ -1788,7 +1796,7 @@ static int rtrs_rdma_conn_rejected(struct rtrs_clt_con *con,
 
 static void rtrs_clt_close_conns(struct rtrs_clt_sess *sess, bool wait)
 {
-	if (rtrs_clt_change_state(sess, RTRS_CLT_CLOSING))
+	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_CLOSING, NULL))
 		queue_work(rtrs_wq, &sess->close_work);
 	if (wait)
 		flush_work(&sess->close_work);
@@ -2174,7 +2182,7 @@ static void rtrs_clt_close_work(struct work_struct *work)
 
 	cancel_delayed_work_sync(&sess->reconnect_dwork);
 	rtrs_clt_stop_and_destroy_conns(sess);
-	rtrs_clt_change_state(sess, RTRS_CLT_CLOSED);
+	rtrs_clt_change_state_get_old(sess, RTRS_CLT_CLOSED, NULL);
 }
 
 static int init_conns(struct rtrs_clt_sess *sess)
@@ -2226,7 +2234,7 @@ destroy:
 	 * doing rdma_resolve_addr(), switch to CONNECTION_ERR state
 	 * manually to keep reconnecting.
 	 */
-	rtrs_clt_change_state(sess, RTRS_CLT_CONNECTING_ERR);
+	rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
 
 	return err;
 }
@@ -2243,7 +2251,7 @@ static void rtrs_clt_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 	if (unlikely(wc->status != IB_WC_SUCCESS)) {
 		rtrs_err(sess->clt, "Sess info request send failed: %s\n",
 			  ib_wc_status_msg(wc->status));
-		rtrs_clt_change_state(sess, RTRS_CLT_CONNECTING_ERR);
+		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
 		return;
 	}
 
@@ -2367,7 +2375,7 @@ static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 out:
 	rtrs_clt_update_wc_stats(con);
 	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
-	rtrs_clt_change_state(sess, state);
+	rtrs_clt_change_state_get_old(sess, state, NULL);
 }
 
 static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
@@ -2423,7 +2431,6 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 			err = -ECONNRESET;
 		else
 			err = -ETIMEDOUT;
-		goto out;
 	}
 
 out:
@@ -2433,7 +2440,7 @@ out:
 		rtrs_iu_free(rx_iu, sess->s.dev->ib_dev, 1);
 	if (unlikely(err))
 		/* If we've never taken async path because of malloc problems */
-		rtrs_clt_change_state(sess, RTRS_CLT_CONNECTING_ERR);
+		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
 
 	return err;
 }
@@ -2490,7 +2497,7 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 	/* Stop everything */
 	rtrs_clt_stop_and_destroy_conns(sess);
 	msleep(RTRS_RECONNECT_BACKOFF);
-	if (rtrs_clt_change_state(sess, RTRS_CLT_CONNECTING)) {
+	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING, NULL)) {
 		err = init_sess(sess);
 		if (err)
 			goto reconnect_again;
@@ -2499,7 +2506,7 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 	return;
 
 reconnect_again:
-	if (rtrs_clt_change_state(sess, RTRS_CLT_RECONNECTING)) {
+	if (rtrs_clt_change_state_get_old(sess, RTRS_CLT_RECONNECTING, NULL)) {
 		sess->stats->reconnects.fail_cnt++;
 		delay_ms = clt->reconnect_delay_sec * 1000;
 		queue_delayed_work(rtrs_wq, &sess->reconnect_dwork,
@@ -2565,11 +2572,8 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num,
 	clt->dev.class = rtrs_clt_dev_class;
 	clt->dev.release = rtrs_clt_dev_release;
 	err = dev_set_name(&clt->dev, "%s", sessname);
-	if (err) {
-		free_percpu(clt->pcpu_path);
-		kfree(clt);
-		return ERR_PTR(err);
-	}
+	if (err)
+		goto err;
 	/*
 	 * Suppress user space notification until
 	 * sysfs files are created
@@ -2577,44 +2581,35 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num,
 	dev_set_uevent_suppress(&clt->dev, true);
 	err = device_register(&clt->dev);
 	if (err) {
-		free_percpu(clt->pcpu_path);
 		put_device(&clt->dev);
-		return ERR_PTR(err);
+		goto err;
 	}
 
 	clt->kobj_paths = kobject_create_and_add("paths", &clt->dev.kobj);
 	if (!clt->kobj_paths) {
-		free_percpu(clt->pcpu_path);
-		device_unregister(&clt->dev);
-		return NULL;
+		err = -ENOMEM;
+		goto err_dev;
 	}
 	err = rtrs_clt_create_sysfs_root_files(clt);
 	if (err) {
-		free_percpu(clt->pcpu_path);
 		kobject_del(clt->kobj_paths);
 		kobject_put(clt->kobj_paths);
-		device_unregister(&clt->dev);
-		return ERR_PTR(err);
+		goto err_dev;
 	}
 	dev_set_uevent_suppress(&clt->dev, false);
 	kobject_uevent(&clt->dev.kobj, KOBJ_ADD);
 
 	return clt;
-}
-
-static void wait_for_inflight_permits(struct rtrs_clt *clt)
-{
-	if (clt->permits_map) {
-		size_t sz = clt->queue_depth;
-
-		wait_event(clt->permits_wait,
-			   find_first_bit(clt->permits_map, sz) >= sz);
-	}
+err_dev:
+	device_unregister(&clt->dev);
+err:
+	free_percpu(clt->pcpu_path);
+	kfree(clt);
+	return ERR_PTR(err);
 }
 
 static void free_clt(struct rtrs_clt *clt)
 {
-	wait_for_inflight_permits(clt);
 	free_permits(clt);
 	free_percpu(clt->pcpu_path);
 	mutex_destroy(&clt->paths_ev_mutex);
@@ -2672,6 +2667,8 @@ struct rtrs_clt *rtrs_clt_open(struct rtrs_clt_ops *ops,
 			err = PTR_ERR(sess);
 			goto close_all_sess;
 		}
+		if (!i)
+			sess->for_new_clt = 1;
 		list_add_tail_rcu(&sess->s.entry, &clt->paths_list);
 
 		err = init_sess(sess);
@@ -2702,8 +2699,7 @@ close_all_sess:
 		rtrs_clt_close_conns(sess, true);
 		kobject_put(&sess->kobj);
 	}
-	rtrs_clt_destroy_sysfs_root_files(clt);
-	rtrs_clt_destroy_sysfs_root_folders(clt);
+	rtrs_clt_destroy_sysfs_root(clt);
 	free_clt(clt);
 
 out:
@@ -2720,8 +2716,7 @@ void rtrs_clt_close(struct rtrs_clt *clt)
 	struct rtrs_clt_sess *sess, *tmp;
 
 	/* Firstly forbid sysfs access */
-	rtrs_clt_destroy_sysfs_root_files(clt);
-	rtrs_clt_destroy_sysfs_root_folders(clt);
+	rtrs_clt_destroy_sysfs_root(clt);
 
 	/* Now it is safe to iterate over all paths without locks */
 	list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) {