16 files changed, 115 insertions, 49 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_comp.c b/drivers/infiniband/sw/rxe/rxe_comp.c
index 6c5e29db88e3..cd27cbde7652 100644
--- a/drivers/infiniband/sw/rxe/rxe_comp.c
+++ b/drivers/infiniband/sw/rxe/rxe_comp.c
@@ -420,11 +420,12 @@ static void do_complete(struct rxe_qp *qp, struct rxe_send_wqe *wqe)
 	    (wqe->wr.send_flags & IB_SEND_SIGNALED) ||
 	    (qp->req.state == QP_STATE_ERROR)) {
 		make_send_cqe(qp, wqe, &cqe);
+		advance_consumer(qp->sq.queue);
 		rxe_cq_post(qp->scq, &cqe, 0);
+	} else {
+		advance_consumer(qp->sq.queue);
 	}
 
-	advance_consumer(qp->sq.queue);
-
 	/*
 	 * we completed something so let req run again
 	 * if it is trying to fence
@@ -510,6 +511,8 @@ int rxe_completer(void *arg)
 	struct rxe_pkt_info *pkt = NULL;
 	enum comp_state state;
 
+	rxe_add_ref(qp);
+
 	if (!qp->valid) {
 		while ((skb = skb_dequeue(&qp->resp_pkts))) {
 			rxe_drop_ref(qp);
@@ -739,11 +742,13 @@ exit:
 	/* we come here if we are done with processing and want the task to
 	 * exit from the loop calling us
 	 */
+	rxe_drop_ref(qp);
 	return -EAGAIN;
 
 done:
 	/* we come here if we have processed a packet we want the task to call
 	 * us again to see if there is anything else to do
 	 */
+	rxe_drop_ref(qp);
 	return 0;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 73849a5a91b3..efe4c6a35442 100644
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -266,8 +266,6 @@ static inline int rxe_xmit_packet(struct rxe_dev *rxe, struct rxe_qp *qp,
 		return err;
 	}
 
-	atomic_inc(&qp->skb_out);
-
 	if ((qp_type(qp) != IB_QPT_RC) &&
 	    (pkt->mask & RXE_END_MASK)) {
 		pkt->wqe->state = wqe_state_done;
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 1869152f1d23..d0faca294006 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -355,6 +355,9 @@ int rxe_mem_copy(struct rxe_mem *mem, u64 iova, void *addr, int length,
 	size_t			offset;
 	u32			crc = crcp ? (*crcp) : 0;
 
+	if (length == 0)
+		return 0;
+
 	if (mem->type == RXE_MEM_TYPE_DMA) {
 		u8 *src, *dest;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index b8258e4f0aea..16967cdb45df 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -46,7 +46,7 @@
 #include "rxe_loc.h"
 
 static LIST_HEAD(rxe_dev_list);
-static spinlock_t dev_list_lock; /* spinlock for device list */
+static DEFINE_SPINLOCK(dev_list_lock); /* spinlock for device list */
 
 struct rxe_dev *net_to_rxe(struct net_device *ndev)
 {
@@ -243,10 +243,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
 {
 	int err;
 	struct socket *sock;
-	struct udp_port_cfg udp_cfg;
-	struct udp_tunnel_sock_cfg tnl_cfg;
-
-	memset(&udp_cfg, 0, sizeof(udp_cfg));
+	struct udp_port_cfg udp_cfg = {0};
+	struct udp_tunnel_sock_cfg tnl_cfg = {0};
 
 	if (ipv6) {
 		udp_cfg.family = AF_INET6;
@@ -264,10 +262,8 @@ static struct socket *rxe_setup_udp_tunnel(struct net *net, __be16 port,
 		return ERR_PTR(err);
 	}
 
-	tnl_cfg.sk_user_data = NULL;
 	tnl_cfg.encap_type = 1;
 	tnl_cfg.encap_rcv = rxe_udp_encap_recv;
-	tnl_cfg.encap_destroy = NULL;
 
 	/* Setup UDP tunnel */
 	setup_udp_tunnel_sock(net, sock, &tnl_cfg);
@@ -459,6 +455,8 @@ static int send(struct rxe_dev *rxe, struct rxe_pkt_info *pkt,
 		return -EAGAIN;
 	}
 
+	if (pkt->qp)
+		atomic_inc(&pkt->qp->skb_out);
 	kfree_skb(skb);
 
 	return 0;
@@ -663,8 +661,6 @@ struct notifier_block rxe_net_notifier = {
 
 int rxe_net_ipv4_init(void)
 {
-	spin_lock_init(&dev_list_lock);
-
 	recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
 				htons(ROCE_V2_UDP_DPORT), false);
 	if (IS_ERR(recv_sockets.sk4)) {
@@ -680,8 +676,6 @@ int rxe_net_ipv6_init(void)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 
-	spin_lock_init(&dev_list_lock);
-
 	recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
 						htons(ROCE_V2_UDP_DPORT), true);
 	if (IS_ERR(recv_sockets.sk6)) {
diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h
index f459c43a77c8..13ed2cc6eaa2 100644
--- a/drivers/infiniband/sw/rxe/rxe_param.h
+++ b/drivers/infiniband/sw/rxe/rxe_param.h
@@ -82,7 +82,7 @@ enum rxe_device_param {
 	RXE_MAX_SGE			= 32,
 	RXE_MAX_SGE_RD			= 32,
 	RXE_MAX_CQ			= 16384,
-	RXE_MAX_LOG_CQE			= 13,
+	RXE_MAX_LOG_CQE			= 15,
 	RXE_MAX_MR			= 2 * 1024,
 	RXE_MAX_PD			= 0x7ffc,
 	RXE_MAX_QP_RD_ATOM		= 128,
diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c
index 6bac0717c540..d723947a8542 100644
--- a/drivers/infiniband/sw/rxe/rxe_pool.c
+++ b/drivers/infiniband/sw/rxe/rxe_pool.c
@@ -180,7 +180,6 @@ static int rxe_pool_init_index(struct rxe_pool *pool, u32 max, u32 min)
 	size = BITS_TO_LONGS(max - min + 1) * sizeof(long);
 	pool->table = kmalloc(size, GFP_KERNEL);
 	if (!pool->table) {
-		pr_warn("no memory for bit table\n");
 		err = -ENOMEM;
 		goto out;
 	}
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index b8036cfbce04..c3e60e4bde6e 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -522,6 +522,7 @@ static void rxe_qp_reset(struct rxe_qp *qp)
 	if (qp->sq.queue) {
 		__rxe_do_task(&qp->comp.task);
 		__rxe_do_task(&qp->req.task);
+		rxe_queue_reset(qp->sq.queue);
 	}
 
 	/* cleanup attributes */
@@ -573,6 +574,7 @@ void rxe_qp_error(struct rxe_qp *qp)
 {
 	qp->req.state = QP_STATE_ERROR;
 	qp->resp.state = QP_STATE_ERROR;
+	qp->attr.qp_state = IB_QPS_ERR;
 
 	/* drain work and packet queues */
 	rxe_run_task(&qp->resp.task, 1);
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c
index 08274254eb88..d14bf496d62d 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.c
+++ b/drivers/infiniband/sw/rxe/rxe_queue.c
@@ -84,6 +84,15 @@ err1:
 	return -EINVAL;
 }
 
+inline void rxe_queue_reset(struct rxe_queue *q)
+{
+	/* queue is comprised from header and the memory
+	 * of the actual queue. See "struct rxe_queue_buf" in rxe_queue.h
+	 * reset only the queue itself and not the management header
+	 */
+	memset(q->buf->data, 0, q->buf_size - sizeof(struct rxe_queue_buf));
+}
+
 struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe,
 				 int *num_elem,
 				 unsigned int elem_size)
diff --git a/drivers/infiniband/sw/rxe/rxe_queue.h b/drivers/infiniband/sw/rxe/rxe_queue.h
index 239fd609c31e..8c8641c87817 100644
--- a/drivers/infiniband/sw/rxe/rxe_queue.h
+++ b/drivers/infiniband/sw/rxe/rxe_queue.h
@@ -84,6 +84,8 @@ int do_mmap_info(struct rxe_dev *rxe,
 		 size_t buf_size,
 		 struct rxe_mmap_info **ip_p);
 
+void rxe_queue_reset(struct rxe_queue *q);
+
 struct rxe_queue *rxe_queue_init(struct rxe_dev *rxe,
 				 int *num_elem,
 				 unsigned int elem_size);
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index 46f062842a9a..252b4d637d45 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -391,16 +391,15 @@ int rxe_rcv(struct sk_buff *skb)
 			     payload_size(pkt));
 	calc_icrc = cpu_to_be32(~calc_icrc);
 	if (unlikely(calc_icrc != pack_icrc)) {
-		char saddr[sizeof(struct in6_addr)];
-
 		if (skb->protocol == htons(ETH_P_IPV6))
-			sprintf(saddr, "%pI6", &ipv6_hdr(skb)->saddr);
+			pr_warn_ratelimited("bad ICRC from %pI6c\n",
+					    &ipv6_hdr(skb)->saddr);
 		else if (skb->protocol == htons(ETH_P_IP))
-			sprintf(saddr, "%pI4", &ip_hdr(skb)->saddr);
+			pr_warn_ratelimited("bad ICRC from %pI4\n",
+					    &ip_hdr(skb)->saddr);
 		else
-			sprintf(saddr, "unknown");
+			pr_warn_ratelimited("bad ICRC from unknown\n");
 
-		pr_warn_ratelimited("bad ICRC from %s\n", saddr);
 		goto drop;
 	}
 
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 832846b73ea0..73d4a97603a1 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -548,23 +548,23 @@ static void update_wqe_psn(struct rxe_qp *qp,
 static void save_state(struct rxe_send_wqe *wqe,
 		       struct rxe_qp *qp,
 		       struct rxe_send_wqe *rollback_wqe,
-		       struct rxe_qp *rollback_qp)
+		       u32 *rollback_psn)
 {
 	rollback_wqe->state     = wqe->state;
 	rollback_wqe->first_psn = wqe->first_psn;
 	rollback_wqe->last_psn  = wqe->last_psn;
-	rollback_qp->req.psn    = qp->req.psn;
+	*rollback_psn		= qp->req.psn;
 }
 
 static void rollback_state(struct rxe_send_wqe *wqe,
 			   struct rxe_qp *qp,
 			   struct rxe_send_wqe *rollback_wqe,
-			   struct rxe_qp *rollback_qp)
+			   u32 rollback_psn)
 {
 	wqe->state     = rollback_wqe->state;
 	wqe->first_psn = rollback_wqe->first_psn;
 	wqe->last_psn  = rollback_wqe->last_psn;
-	qp->req.psn    = rollback_qp->req.psn;
+	qp->req.psn    = rollback_psn;
 }
 
 static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
@@ -593,8 +593,10 @@ int rxe_requester(void *arg)
 	int mtu;
 	int opcode;
 	int ret;
-	struct rxe_qp rollback_qp;
 	struct rxe_send_wqe rollback_wqe;
+	u32 rollback_psn;
+
+	rxe_add_ref(qp);
 
 next_wqe:
 	if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
@@ -696,7 +698,9 @@ next_wqe:
 						       qp->req.wqe_index);
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
-			goto complete;
+			__rxe_do_task(&qp->comp.task);
+			rxe_drop_ref(qp);
+			return 0;
 		}
 		payload = mtu;
 	}
@@ -718,7 +722,7 @@ next_wqe:
 	 * rxe_xmit_packet().
 	 * Otherwise, completer might initiate an unjustified retry flow.
 	 */
-	save_state(wqe, qp, &rollback_wqe, &rollback_qp);
+	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
 	update_wqe_state(qp, wqe, &pkt);
 	update_wqe_psn(qp, wqe, &pkt, payload);
 	ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
@@ -726,7 +730,7 @@ next_wqe:
 		qp->need_req_skb = 1;
 		kfree_skb(skb);
 
-		rollback_state(wqe, qp, &rollback_wqe, &rollback_qp);
+		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
 		if (ret == -EAGAIN) {
 			rxe_run_task(&qp->req.task, 1);
@@ -745,14 +749,17 @@ err:
 	wqe->status = IB_WC_LOC_PROT_ERR;
 	wqe->state = wqe_state_error;
 
-complete:
-	if (qp_type(qp) != IB_QPT_RC) {
-		while (rxe_completer(qp) == 0)
-			;
-	}
-
-	return 0;
-
+	/*
+	 * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS
+	 * ---------8<---------8<-------------
+	 * ...Note that if a completion error occurs, a Work Completion
+	 * will always be generated, even if the signaling
+	 * indicator requests an Unsignaled Completion.
+	 * ---------8<---------8<-------------
+	 */
+	wqe->wr.send_flags |= IB_SEND_SIGNALED;
+	__rxe_do_task(&qp->comp.task);
 exit:
+	rxe_drop_ref(qp);
 	return -EAGAIN;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index dd3d88adc003..7a36ec9dbc0c 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -444,6 +444,13 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 		return RESPST_EXECUTE;
 	}
 
+	/* A zero-byte op is not required to set an addr or rkey. */
+	if ((pkt->mask & (RXE_READ_MASK | RXE_WRITE_OR_SEND)) &&
+	    (pkt->mask & RXE_RETH_MASK) &&
+	    reth_len(pkt) == 0) {
+		return RESPST_EXECUTE;
+	}
+
 	va	= qp->resp.va;
 	rkey	= qp->resp.rkey;
 	resid	= qp->resp.resid;
@@ -680,9 +687,14 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 		res->read.va_org	= qp->resp.va;
 
 		res->first_psn		= req_pkt->psn;
-		res->last_psn		= req_pkt->psn +
-					  (reth_len(req_pkt) + mtu - 1) /
-					  mtu - 1;
+
+		if (reth_len(req_pkt)) {
+			res->last_psn	= (req_pkt->psn +
+					   (reth_len(req_pkt) + mtu - 1) /
+					   mtu - 1) & BTH_PSN_MASK;
+		} else {
+			res->last_psn	= res->first_psn;
+		}
 		res->cur_psn		= req_pkt->psn;
 
 		res->read.resid		= qp->resp.resid;
@@ -742,7 +754,8 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	} else {
 		qp->resp.res = NULL;
 		qp->resp.opcode = -1;
-		qp->resp.psn = res->cur_psn;
+		if (psn_compare(res->cur_psn, qp->resp.psn) >= 0)
+			qp->resp.psn = res->cur_psn;
 		state = RESPST_CLEANUP;
 	}
 
@@ -1132,6 +1145,7 @@ static enum resp_states duplicate_request(struct rxe_qp *qp,
 					     pkt, skb_copy);
 			if (rc) {
 				pr_err("Failed resending result. This flow is not handled - skb ignored\n");
+				rxe_drop_ref(qp);
 				kfree_skb(skb_copy);
 				rc = RESPST_CLEANUP;
 				goto out;
@@ -1198,6 +1212,8 @@ int rxe_responder(void *arg)
 	struct rxe_pkt_info *pkt = NULL;
 	int ret = 0;
 
+	rxe_add_ref(qp);
+
 	qp->resp.aeth_syndrome = AETH_ACK_UNLIMITED;
 
 	if (!qp->valid) {
@@ -1386,5 +1402,6 @@ int rxe_responder(void *arg)
 exit:
 	ret = -EAGAIN;
 done:
+	rxe_drop_ref(qp);
 	return ret;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_srq.c b/drivers/infiniband/sw/rxe/rxe_srq.c
index 2a6e3cd2d4e8..efc832a2d7c6 100644
--- a/drivers/infiniband/sw/rxe/rxe_srq.c
+++ b/drivers/infiniband/sw/rxe/rxe_srq.c
@@ -169,7 +169,7 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
 			}
 		}
 
-		err = rxe_queue_resize(q, (unsigned int *)&attr->max_wr,
+		err = rxe_queue_resize(q, &attr->max_wr,
 				       rcv_wqe_size(srq->rq.max_sge),
 				       srq->rq.queue->ip ?
 						srq->rq.queue->ip->context :
diff --git a/drivers/infiniband/sw/rxe/rxe_task.c b/drivers/infiniband/sw/rxe/rxe_task.c
index 1e19bf828a6e..d2a14a1bdc7f 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.c
+++ b/drivers/infiniband/sw/rxe/rxe_task.c
@@ -121,6 +121,7 @@ int rxe_init_task(void *obj, struct rxe_task *task,
 	task->arg	= arg;
 	task->func	= func;
 	snprintf(task->name, sizeof(task->name), "%s", name);
+	task->destroyed	= false;
 
 	tasklet_init(&task->tasklet, rxe_do_task, (unsigned long)task);
 
@@ -132,11 +133,29 @@ int rxe_init_task(void *obj, struct rxe_task *task,
 
 void rxe_cleanup_task(struct rxe_task *task)
 {
+	unsigned long flags;
+	bool idle;
+
+	/*
+	 * Mark the task, then wait for it to finish. It might be
+	 * running in a non-tasklet (direct call) context.
+	 */
+	task->destroyed = true;
+
+	do {
+		spin_lock_irqsave(&task->state_lock, flags);
+		idle = (task->state == TASK_STATE_START);
+		spin_unlock_irqrestore(&task->state_lock, flags);
+	} while (!idle);
+
 	tasklet_kill(&task->tasklet);
 }
 
 void rxe_run_task(struct rxe_task *task, int sched)
 {
+	if (task->destroyed)
+		return;
+
 	if (sched)
 		tasklet_schedule(&task->tasklet);
 	else
diff --git a/drivers/infiniband/sw/rxe/rxe_task.h b/drivers/infiniband/sw/rxe/rxe_task.h
index d14aa6daed05..08ff42d451c6 100644
--- a/drivers/infiniband/sw/rxe/rxe_task.h
+++ b/drivers/infiniband/sw/rxe/rxe_task.h
@@ -54,6 +54,7 @@ struct rxe_task {
 	int			(*func)(void *arg);
 	int			ret;
 	char			name[16];
+	bool			destroyed;
 };
 
 /*
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 19841c863daf..beb7021ff18a 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -316,7 +316,9 @@ static int rxe_init_av(struct rxe_dev *rxe, struct ib_ah_attr *attr,
 	return err;
 }
 
-static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
+static struct ib_ah *rxe_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr,
+				   struct ib_udata *udata)
+
 {
 	int err;
 	struct rxe_dev *rxe = to_rdev(ibpd->device);
@@ -564,7 +566,7 @@ static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd,
 	if (udata) {
 		if (udata->inlen) {
 			err = -EINVAL;
-			goto err1;
+			goto err2;
 		}
 		qp->is_user = 1;
 	}
@@ -573,12 +575,13 @@ static struct ib_qp *rxe_create_qp(struct ib_pd *ibpd,
 
 	err = rxe_qp_from_init(rxe, qp, pd, init, udata, ibpd);
 	if (err)
-		goto err2;
+		goto err3;
 
 	return &qp->ibqp;
 
-err2:
+err3:
 	rxe_drop_index(qp);
+err2:
 	rxe_drop_ref(qp);
 err1:
 	return ERR_PTR(err);
@@ -1007,11 +1010,19 @@ static int rxe_peek_cq(struct ib_cq *ibcq, int wc_cnt)
 static int rxe_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
 {
 	struct rxe_cq *cq = to_rcq(ibcq);
+	unsigned long irq_flags;
+	int ret = 0;
 
+	spin_lock_irqsave(&cq->cq_lock, irq_flags);
 	if (cq->notify != IB_CQ_NEXT_COMP)
 		cq->notify = flags & IB_CQ_SOLICITED_MASK;
 
-	return 0;
+	if ((flags & IB_CQ_REPORT_MISSED_EVENTS) && !queue_empty(cq->queue))
+		ret = 1;
+
+	spin_unlock_irqrestore(&cq->cq_lock, irq_flags);
+
+	return ret;
 }
 
 static struct ib_mr *rxe_get_dma_mr(struct ib_pd *ibpd, int access)