Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma

Pull rdma updates from Doug Ledford:
 "This is the complete update for the rdma stack for this release cycle.

  Most of it is typical driver and core updates, but there is the
  entirely new VMWare pvrdma driver. You may have noticed that there
  were changes in DaveM's pull request to the bnxt Ethernet driver to
  support a RoCE RDMA driver. The bnxt_re driver was tentatively set to
  be pulled in this release cycle, but it simply wasn't ready in time
  and was dropped (a few review comments still to address, and some
  multi-arch build issues like prefetch() not working across all
  arches).

  Summary:

   - shared mlx5 updates with net stack (will drop out on merge if
     Dave's tree has already been merged)

   - driver updates: cxgb4, hfi1, hns-roce, i40iw, mlx4, mlx5, qedr, rxe

   - debug cleanups

   - new connection rejection helpers

   - SRP updates

   - various misc fixes

   - new paravirt driver from vmware"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (210 commits)
  IB: Add vmw_pvrdma driver
  IB/mlx4: fix improper return value
  IB/ocrdma: fix bad initialization
  infiniband: nes: return value of skb_linearize should be handled
  MAINTAINERS: Update Intel RDMA RNIC driver maintainers
  MAINTAINERS: Remove Mitesh Ahuja from emulex maintainers
  IB/core: fix unmap_sg argument
  qede: fix general protection fault may occur on probe
  IB/mthca: Replace pci_pool_alloc by pci_pool_zalloc
  mlx5, calc_sq_size(): Make a debug message more informative
  mlx5: Remove a set-but-not-used variable
  mlx5: Use { } instead of { 0 } to init struct
  IB/srp: Make writing the add_target sysfs attr interruptible
  IB/srp: Make mapping failures easier to debug
  IB/srp: Make login failures easier to debug
  IB/srp: Introduce a local variable in srp_add_one()
  IB/srp: Fix CONFIG_DYNAMIC_DEBUG=n build
  IB/multicast: Check ib_find_pkey() return value
  IPoIB: Avoid reading an uninitialized member variable
  IB/mad: Fix an array index check
  ...

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;
 }

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;

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;
 

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)
 {
@@ -455,6 +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;
@@ -659,8 +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)) {
@@ -676,8 +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)) {

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,

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;
 	}

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;
 	}
 

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))
@@ -697,6 +699,7 @@ next_wqe:
 			wqe->state = wqe_state_done;
 			wqe->status = IB_WC_SUCCESS;
 			__rxe_do_task(&qp->comp.task);
+			rxe_drop_ref(qp);
 			return 0;
 		}
 		payload = mtu;
@@ -719,7 +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);
@@ -727,7 +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);
@@ -756,8 +759,7 @@ err:
 	 */
 	wqe->wr.send_flags |= IB_SEND_SIGNALED;
 	__rxe_do_task(&qp->comp.task);
-	return -EAGAIN;
-
 exit:
+	rxe_drop_ref(qp);
 	return -EAGAIN;
 }

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;
 }

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 :

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

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;
 };
 
 /*

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)