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

Pull rdma fixes from Jason Gunthorpe:
 "A few recent regressions in rxe's multicast code, and some old driver
  bugs:

   - Error case unwind bug in rxe for rkeys

   - Dot not call netdev functions under a spinlock in rxe multicast
     code

   - Use the proper BH lock type in rxe multicast code

   - Fix idrma deadlock and crash

   - Add a missing flush to drain irdma QPs when in error

   - Fix high userspace latency in irdma during destroy due to
     synchronize_rcu()

   - Rare race in siw MPA processing"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/rxe: Change mcg_lock to a _bh lock
  RDMA/rxe: Do not call  dev_mc_add/del() under a spinlock
  RDMA/siw: Fix a condition race issue in MPA request processing
  RDMA/irdma: Fix possible crash due to NULL netdev in notifier
  RDMA/irdma: Reduce iWARP QP destroy time
  RDMA/irdma: Flush iWARP QP if modified to ERR from RTR state
  RDMA/rxe: Recheck the MR in when generating a READ reply
  RDMA/irdma: Fix deadlock in irdma_cleanup_cm_core()
  RDMA/rxe: Fix "Replace mr by rkey in responder resources"

drivers/infiniband/hw/irdma/cm.c

@@ -2308,10 +2308,8 @@ irdma_make_cm_node(struct irdma_cm_core *cm_core, struct irdma_device *iwdev,
 	return NULL;
 }
 
-static void irdma_cm_node_free_cb(struct rcu_head *rcu_head)
+static void irdma_destroy_connection(struct irdma_cm_node *cm_node)
 {
-	struct irdma_cm_node *cm_node =
-			    container_of(rcu_head, struct irdma_cm_node, rcu_head);
 	struct irdma_cm_core *cm_core = cm_node->cm_core;
 	struct irdma_qp *iwqp;
 	struct irdma_cm_info nfo;
@@ -2359,7 +2357,6 @@ static void irdma_cm_node_free_cb(struct rcu_head *rcu_head)
 	}
 
 	cm_core->cm_free_ah(cm_node);
-	kfree(cm_node);
 }
 
 /**
@@ -2387,8 +2384,9 @@ void irdma_rem_ref_cm_node(struct irdma_cm_node *cm_node)
 
 	spin_unlock_irqrestore(&cm_core->ht_lock, flags);
 
-	/* wait for all list walkers to exit their grace period */
-	call_rcu(&cm_node->rcu_head, irdma_cm_node_free_cb);
+	irdma_destroy_connection(cm_node);
+
+	kfree_rcu(cm_node, rcu_head);
 }
 
 /**
@@ -3246,15 +3244,10 @@ int irdma_setup_cm_core(struct irdma_device *iwdev, u8 rdma_ver)
  */
 void irdma_cleanup_cm_core(struct irdma_cm_core *cm_core)
 {
-	unsigned long flags;
-
 	if (!cm_core)
 		return;
 
-	spin_lock_irqsave(&cm_core->ht_lock, flags);
-	if (timer_pending(&cm_core->tcp_timer))
 	del_timer_sync(&cm_core->tcp_timer);
-	spin_unlock_irqrestore(&cm_core->ht_lock, flags);
 
 	destroy_workqueue(cm_core->event_wq);
 	cm_core->dev->ws_reset(&cm_core->iwdev->vsi);
@@ -3467,12 +3460,6 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp)
 	}
 
 	cm_id = iwqp->cm_id;
-	/* make sure we havent already closed this connection */
-	if (!cm_id) {
-		spin_unlock_irqrestore(&iwqp->lock, flags);
-		return;
-	}
-
 	original_hw_tcp_state = iwqp->hw_tcp_state;
 	original_ibqp_state = iwqp->ibqp_state;
 	last_ae = iwqp->last_aeq;
@@ -3494,11 +3481,11 @@ static void irdma_cm_disconn_true(struct irdma_qp *iwqp)
 			disconn_status = -ECONNRESET;
 	}
 
-	if ((original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED ||
+	if (original_hw_tcp_state == IRDMA_TCP_STATE_CLOSED ||
 	    original_hw_tcp_state == IRDMA_TCP_STATE_TIME_WAIT ||
 	    last_ae == IRDMA_AE_RDMAP_ROE_BAD_LLP_CLOSE ||
 	    last_ae == IRDMA_AE_BAD_CLOSE ||
-	     last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset)) {
+	    last_ae == IRDMA_AE_LLP_CONNECTION_RESET || iwdev->rf->reset || !cm_id) {
 		issue_close = 1;
 		iwqp->cm_id = NULL;
 		qp->term_flags = 0;

drivers/infiniband/hw/irdma/utils.c

@@ -258,18 +258,16 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event,
 	u32 local_ipaddr[4] = {};
 	bool ipv4 = true;
 
+	switch (event) {
+	case NETEVENT_NEIGH_UPDATE:
 		real_dev = rdma_vlan_dev_real_dev(netdev);
 		if (!real_dev)
 			real_dev = netdev;
-
 		ibdev = ib_device_get_by_netdev(real_dev, RDMA_DRIVER_IRDMA);
 		if (!ibdev)
 			return NOTIFY_DONE;
 
 		iwdev = to_iwdev(ibdev);
-
-	switch (event) {
-	case NETEVENT_NEIGH_UPDATE:
 		p = (__be32 *)neigh->primary_key;
 		if (neigh->tbl->family == AF_INET6) {
 			ipv4 = false;
@@ -290,13 +288,12 @@ int irdma_net_event(struct notifier_block *notifier, unsigned long event,
 			irdma_manage_arp_cache(iwdev->rf, neigh->ha,
 					       local_ipaddr, ipv4,
 					       IRDMA_ARP_DELETE);
+		ib_device_put(ibdev);
 		break;
 	default:
 		break;
 	}
 
-	ib_device_put(ibdev);
-
 	return NOTIFY_DONE;
 }
 

drivers/infiniband/hw/irdma/verbs.c

@@ -1618,13 +1618,13 @@ int irdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
 
 	if (issue_modify_qp && iwqp->ibqp_state > IB_QPS_RTS) {
 		if (dont_wait) {
-			if (iwqp->cm_id && iwqp->hw_tcp_state) {
+			if (iwqp->hw_tcp_state) {
 				spin_lock_irqsave(&iwqp->lock, flags);
 				iwqp->hw_tcp_state = IRDMA_TCP_STATE_CLOSED;
 				iwqp->last_aeq = IRDMA_AE_RESET_SENT;
 				spin_unlock_irqrestore(&iwqp->lock, flags);
-				irdma_cm_disconn(iwqp);
 			}
+			irdma_cm_disconn(iwqp);
 		} else {
 			int close_timer_started;
 

drivers/infiniband/sw/rxe/rxe_mcast.c

@@ -38,13 +38,13 @@ static int rxe_mcast_add(struct rxe_dev *rxe, union ib_gid *mgid)
 }
 
 /**
- * rxe_mcast_delete - delete multicast address from rxe device
+ * rxe_mcast_del - delete multicast address from rxe device
  * @rxe: rxe device object
  * @mgid: multicast address as a gid
  *
  * Returns 0 on success else an error
  */
-static int rxe_mcast_delete(struct rxe_dev *rxe, union ib_gid *mgid)
+static int rxe_mcast_del(struct rxe_dev *rxe, union ib_gid *mgid)
 {
 	unsigned char ll_addr[ETH_ALEN];
 
@@ -143,11 +143,10 @@ static struct rxe_mcg *__rxe_lookup_mcg(struct rxe_dev *rxe,
 struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
 {
 	struct rxe_mcg *mcg;
-	unsigned long flags;
 
-	spin_lock_irqsave(&rxe->mcg_lock, flags);
+	spin_lock_bh(&rxe->mcg_lock);
 	mcg = __rxe_lookup_mcg(rxe, mgid);
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+	spin_unlock_bh(&rxe->mcg_lock);
 
 	return mcg;
 }
@@ -159,17 +158,10 @@ struct rxe_mcg *rxe_lookup_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
  * @mcg: new mcg object
  *
  * Context: caller should hold rxe->mcg lock
- * Returns: 0 on success else an error
  */
-static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid,
+static void __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid,
 			   struct rxe_mcg *mcg)
 {
-	int err;
-
-	err = rxe_mcast_add(rxe, mgid);
-	if (unlikely(err))
-		return err;
-
 	kref_init(&mcg->ref_cnt);
 	memcpy(&mcg->mgid, mgid, sizeof(mcg->mgid));
 	INIT_LIST_HEAD(&mcg->qp_list);
@@ -184,8 +176,6 @@ static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid,
 	 */
 	kref_get(&mcg->ref_cnt);
 	__rxe_insert_mcg(mcg);
-
-	return 0;
 }
 
 /**
@@ -198,7 +188,6 @@ static int __rxe_init_mcg(struct rxe_dev *rxe, union ib_gid *mgid,
 static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
 {
 	struct rxe_mcg *mcg, *tmp;
-	unsigned long flags;
 	int err;
 
 	if (rxe->attr.max_mcast_grp == 0)
@@ -209,36 +198,38 @@ static struct rxe_mcg *rxe_get_mcg(struct rxe_dev *rxe, union ib_gid *mgid)
 	if (mcg)
 		return mcg;
 
+	/* check to see if we have reached limit */
+	if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) {
+		err = -ENOMEM;
+		goto err_dec;
+	}
+
 	/* speculative alloc of new mcg */
 	mcg = kzalloc(sizeof(*mcg), GFP_KERNEL);
 	if (!mcg)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_irqsave(&rxe->mcg_lock, flags);
+	spin_lock_bh(&rxe->mcg_lock);
 	/* re-check to see if someone else just added it */
 	tmp = __rxe_lookup_mcg(rxe, mgid);
 	if (tmp) {
+		spin_unlock_bh(&rxe->mcg_lock);
+		atomic_dec(&rxe->mcg_num);
 		kfree(mcg);
-		mcg = tmp;
-		goto out;
+		return tmp;
 	}
 
-	if (atomic_inc_return(&rxe->mcg_num) > rxe->attr.max_mcast_grp) {
-		err = -ENOMEM;
-		goto err_dec;
-	}
+	__rxe_init_mcg(rxe, mgid, mcg);
+	spin_unlock_bh(&rxe->mcg_lock);
 
-	err = __rxe_init_mcg(rxe, mgid, mcg);
-	if (err)
-		goto err_dec;
-out:
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+	/* add mcast address outside of lock */
+	err = rxe_mcast_add(rxe, mgid);
+	if (!err)
 		return mcg;
 
+	kfree(mcg);
 err_dec:
 	atomic_dec(&rxe->mcg_num);
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
-	kfree(mcg);
 	return ERR_PTR(err);
 }
 
@@ -268,7 +259,6 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg)
 	__rxe_remove_mcg(mcg);
 	kref_put(&mcg->ref_cnt, rxe_cleanup_mcg);
 
-	rxe_mcast_delete(mcg->rxe, &mcg->mgid);
 	atomic_dec(&rxe->mcg_num);
 }
 
@@ -280,11 +270,12 @@ static void __rxe_destroy_mcg(struct rxe_mcg *mcg)
  */
 static void rxe_destroy_mcg(struct rxe_mcg *mcg)
 {
-	unsigned long flags;
+	/* delete mcast address outside of lock */
+	rxe_mcast_del(mcg->rxe, &mcg->mgid);
 
-	spin_lock_irqsave(&mcg->rxe->mcg_lock, flags);
+	spin_lock_bh(&mcg->rxe->mcg_lock);
 	__rxe_destroy_mcg(mcg);
-	spin_unlock_irqrestore(&mcg->rxe->mcg_lock, flags);
+	spin_unlock_bh(&mcg->rxe->mcg_lock);
 }
 
 /**
@@ -339,25 +330,24 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
 {
 	struct rxe_dev *rxe = mcg->rxe;
 	struct rxe_mca *mca, *tmp;
-	unsigned long flags;
 	int err;
 
 	/* check to see if the qp is already a member of the group */
-	spin_lock_irqsave(&rxe->mcg_lock, flags);
+	spin_lock_bh(&rxe->mcg_lock);
 	list_for_each_entry(mca, &mcg->qp_list, qp_list) {
 		if (mca->qp == qp) {
-			spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+			spin_unlock_bh(&rxe->mcg_lock);
 			return 0;
 		}
 	}
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+	spin_unlock_bh(&rxe->mcg_lock);
 
 	/* speculative alloc new mca without using GFP_ATOMIC */
 	mca = kzalloc(sizeof(*mca), GFP_KERNEL);
 	if (!mca)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&rxe->mcg_lock, flags);
+	spin_lock_bh(&rxe->mcg_lock);
 	/* re-check to see if someone else just attached qp */
 	list_for_each_entry(tmp, &mcg->qp_list, qp_list) {
 		if (tmp->qp == qp) {
@@ -371,7 +361,7 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
 	if (err)
 		kfree(mca);
 out:
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+	spin_unlock_bh(&rxe->mcg_lock);
 	return err;
 }
 
@@ -405,9 +395,8 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
 {
 	struct rxe_dev *rxe = mcg->rxe;
 	struct rxe_mca *mca, *tmp;
-	unsigned long flags;
 
-	spin_lock_irqsave(&rxe->mcg_lock, flags);
+	spin_lock_bh(&rxe->mcg_lock);
 	list_for_each_entry_safe(mca, tmp, &mcg->qp_list, qp_list) {
 		if (mca->qp == qp) {
 			__rxe_cleanup_mca(mca, mcg);
@@ -421,13 +410,13 @@ static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
 			if (atomic_read(&mcg->qp_num) <= 0)
 				__rxe_destroy_mcg(mcg);
 
-			spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+			spin_unlock_bh(&rxe->mcg_lock);
 			return 0;
 		}
 	}
 
 	/* we didn't find the qp on the list */
-	spin_unlock_irqrestore(&rxe->mcg_lock, flags);
+	spin_unlock_bh(&rxe->mcg_lock);
 	return -EINVAL;
 }
 

drivers/infiniband/sw/rxe/rxe_resp.c

@@ -680,6 +680,11 @@ static struct resp_res *rxe_prepare_read_res(struct rxe_qp *qp,
  * It is assumed that the access permissions if originally good
  * are OK and the mappings to be unchanged.
  *
+ * TODO: If someone reregisters an MR to change its size or
+ * access permissions during the processing of an RDMA read
+ * we should kill the responder resource and complete the
+ * operation with an error.
+ *
  * Return: mr on success else NULL
  */
 static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey)
@@ -690,23 +695,27 @@ static struct rxe_mr *rxe_recheck_mr(struct rxe_qp *qp, u32 rkey)
 
 	if (rkey_is_mw(rkey)) {
 		mw = rxe_pool_get_index(&rxe->mw_pool, rkey >> 8);
-		if (!mw || mw->rkey != rkey)
+		if (!mw)
 			return NULL;
 
-		if (mw->state != RXE_MW_STATE_VALID) {
+		mr = mw->mr;
+		if (mw->rkey != rkey || mw->state != RXE_MW_STATE_VALID ||
+		    !mr || mr->state != RXE_MR_STATE_VALID) {
 			rxe_put(mw);
 			return NULL;
 		}
 
-		mr = mw->mr;
+		rxe_get(mr);
 		rxe_put(mw);
-	} else {
+
+		return mr;
+	}
+
 	mr = rxe_pool_get_index(&rxe->mr_pool, rkey >> 8);
-		if (!mr || mr->rkey != rkey)
+	if (!mr)
 		return NULL;
-	}
 
-	if (mr->state != RXE_MR_STATE_VALID) {
+	if (mr->rkey != rkey || mr->state != RXE_MR_STATE_VALID) {
 		rxe_put(mr);
 		return NULL;
 	}
@@ -736,8 +745,14 @@ static enum resp_states read_reply(struct rxe_qp *qp,
 	}
 
 	if (res->state == rdatm_res_state_new) {
+		if (!res->replay) {
 			mr = qp->resp.mr;
 			qp->resp.mr = NULL;
+		} else {
+			mr = rxe_recheck_mr(qp, res->read.rkey);
+			if (!mr)
+				return RESPST_ERR_RKEY_VIOLATION;
+		}
 
 		if (res->read.resid <= mtu)
 			opcode = IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY;

drivers/infiniband/sw/siw/siw_cm.c

@@ -968,15 +968,16 @@ static void siw_accept_newconn(struct siw_cep *cep)
 
 		siw_cep_set_inuse(new_cep);
 		rv = siw_proc_mpareq(new_cep);
-		siw_cep_set_free(new_cep);
-
 		if (rv != -EAGAIN) {
 			siw_cep_put(cep);
 			new_cep->listen_cep = NULL;
-			if (rv)
+			if (rv) {
+				siw_cep_set_free(new_cep);
 				goto error;
 			}
 		}
+		siw_cep_set_free(new_cep);
+	}
 	return;
 
 error: