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

Pull rdma fixes from Doug Ledford:
 "This is our first pull request of the rc cycle. It's not that it's
  been overly quiet, we were just waiting on a few things before sending
  this off.

  For instance, the 6 patch series from Intel for the hfi1 driver had
  actually been pulled in on Tuesday for a Wednesday pull request, only
  to have Jason notice something I missed, so we held off for some
  testing, and then on Thursday had to respin the series because the
  very first patch needed a minor fix (unnecessary cast is all).

  There is a sizable hns patch series in here, as well as a reasonably
  largish hfi1 patch series, then all of the lines of uapi updates are
  just the change to the new official Linux-OpenIB SPDX tag (a bunch of
  our files had what amounts to a BSD-2-Clause + MIT Warranty statement
  as their license as a result of the initial code submission years ago,
  and the SPDX folks decided it was unique enough to warrant a unique
  tag), then the typical mlx4 and mlx5 updates, and finally some cxgb4
  and core/cache/cma updates to round out the bunch.

  None of it was overly large by itself, but in the 2 1/2 weeks we've
  been collecting patches, it has added up :-/.

  As best I can tell, it's been through 0day (I got a notice about my
  last for-next push, but not for my for-rc push, but Jason seems to
  think that failure messages are prioritized and success messages not
  so much). It's also been through linux-next. And yes, we did notice in
  the context portion of the CMA query gid fix patch that there is a
  dubious BUG_ON() in the code, and have plans to audit our BUG_ON usage
  and remove it anywhere we can.

  Summary:

   - Various build fixes (USER_ACCESS=m and ADDR_TRANS turned off)

   - SPDX license tag cleanups (new tag Linux-OpenIB)

   - RoCE GID fixes related to default GIDs

   - Various fixes to: cxgb4, uverbs, cma, iwpm, rxe, hns (big batch),
     mlx4, mlx5, and hfi1 (medium batch)"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (52 commits)
  RDMA/cma: Do not query GID during QP state transition to RTR
  IB/mlx4: Fix integer overflow when calculating optimal MTT size
  IB/hfi1: Fix memory leak in exception path in get_irq_affinity()
  IB/{hfi1, rdmavt}: Fix memory leak in hfi1_alloc_devdata() upon failure
  IB/hfi1: Fix NULL pointer dereference when invalid num_vls is used
  IB/hfi1: Fix loss of BECN with AHG
  IB/hfi1 Use correct type for num_user_context
  IB/hfi1: Fix handling of FECN marked multicast packet
  IB/core: Make ib_mad_client_id atomic
  iw_cxgb4: Atomically flush per QP HW CQEs
  IB/uverbs: Fix kernel crash during MR deregistration flow
  IB/uverbs: Prevent reregistration of DM_MR to regular MR
  RDMA/mlx4: Add missed RSS hash inner header flag
  RDMA/hns: Fix a couple misspellings
  RDMA/hns: Submit bad wr
  RDMA/hns: Update assignment method for owner field of send wqe
  RDMA/hns: Adjust the order of cleanup hem table
  RDMA/hns: Only assign dqpn if IB_QP_PATH_DEST_QPN bit is set
  RDMA/hns: Remove some unnecessary attr_mask judgement
  RDMA/hns: Only assign mtu if IB_QP_PATH_MTU bit is set
  ...

1 files changed, 43 insertions, 17 deletions

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 51a641002e10..a693fcd4c513 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -382,6 +382,8 @@ struct cma_hdr {
 #define CMA_VERSION 0x00
 
 struct cma_req_info {
+	struct sockaddr_storage listen_addr_storage;
+	struct sockaddr_storage src_addr_storage;
 	struct ib_device *device;
 	int port;
 	union ib_gid local_gid;
@@ -866,7 +868,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 {
 	struct ib_qp_attr qp_attr;
 	int qp_attr_mask, ret;
-	union ib_gid sgid;
 
 	mutex_lock(&id_priv->qp_mutex);
 	if (!id_priv->id.qp) {
@@ -889,12 +890,6 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	if (ret)
 		goto out;
 
-	ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
-			   rdma_ah_read_grh(&qp_attr.ah_attr)->sgid_index,
-			   &sgid, NULL);
-	if (ret)
-		goto out;
-
 	BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
 
 	if (conn_param)
@@ -1340,11 +1335,11 @@ static bool validate_net_dev(struct net_device *net_dev,
 }
 
 static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
-					  const struct cma_req_info *req)
+					  struct cma_req_info *req)
 {
-	struct sockaddr_storage listen_addr_storage, src_addr_storage;
-	struct sockaddr *listen_addr = (struct sockaddr *)&listen_addr_storage,
-			*src_addr = (struct sockaddr *)&src_addr_storage;
+	struct sockaddr *listen_addr =
+			(struct sockaddr *)&req->listen_addr_storage;
+	struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage;
 	struct net_device *net_dev;
 	const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL;
 	int err;
@@ -1359,11 +1354,6 @@ static struct net_device *cma_get_net_dev(struct ib_cm_event *ib_event,
 	if (!net_dev)
 		return ERR_PTR(-ENODEV);
 
-	if (!validate_net_dev(net_dev, listen_addr, src_addr)) {
-		dev_put(net_dev);
-		return ERR_PTR(-EHOSTUNREACH);
-	}
-
 	return net_dev;
 }
 
@@ -1490,15 +1480,51 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
+	/*
+	 * Net namespace might be getting deleted while route lookup,
+	 * cm_id lookup is in progress. Therefore, perform netdevice
+	 * validation, cm_id lookup under rcu lock.
+	 * RCU lock along with netdevice state check, synchronizes with
+	 * netdevice migrating to different net namespace and also avoids
+	 * case where net namespace doesn't get deleted while lookup is in
+	 * progress.
+	 * If the device state is not IFF_UP, its properties such as ifindex
+	 * and nd_net cannot be trusted to remain valid without rcu lock.
+	 * net/core/dev.c change_net_namespace() ensures to synchronize with
+	 * ongoing operations on net device after device is closed using
+	 * synchronize_net().
+	 */
+	rcu_read_lock();
+	if (*net_dev) {
+		/*
+		 * If netdevice is down, it is likely that it is administratively
+		 * down or it might be migrating to different namespace.
+		 * In that case avoid further processing, as the net namespace
+		 * or ifindex may change.
+		 */
+		if (((*net_dev)->flags & IFF_UP) == 0) {
+			id_priv = ERR_PTR(-EHOSTUNREACH);
+			goto err;
+		}
+
+		if (!validate_net_dev(*net_dev,
+				 (struct sockaddr *)&req.listen_addr_storage,
+				 (struct sockaddr *)&req.src_addr_storage)) {
+			id_priv = ERR_PTR(-EHOSTUNREACH);
+			goto err;
+		}
+	}
+
 	bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net,
 				rdma_ps_from_service_id(req.service_id),
 				cma_port_from_service_id(req.service_id));
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
+err:
+	rcu_read_unlock();
 	if (IS_ERR(id_priv) && *net_dev) {
 		dev_put(*net_dev);
 		*net_dev = NULL;
 	}
-
 	return id_priv;
 }