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

Pull inifiniband/rdma updates from Doug Ledford:
 "This is a fairly sizeable set of changes.  I've put them through a
  decent amount of testing prior to sending the pull request due to
  that.

  There are still a few fixups that I know are coming, but I wanted to
  go ahead and get the big, sizable chunk into your hands sooner rather
  than waiting for those last few fixups.

  Of note is the fact that this creates what is intended to be a
  temporary area in the drivers/staging tree specifically for some
  cleanups and additions that are coming for the RDMA stack.  We
  deprecated two drivers (ipath and amso1100) and are waiting to hear
  back if we can deprecate another one (ehca).  We also put Intel's new
  hfi1 driver into this area because it needs to be refactored and a
  transfer library created out of the factored out code, and then it and
  the qib driver and the soft-roce driver should all be modified to use
  that library.

  I expect drivers/staging/rdma to be around for three or four kernel
  releases and then to go away as all of the work is completed and final
  deletions of deprecated drivers are done.

  Summary of changes for 4.3:

   - Create drivers/staging/rdma
   - Move amso1100 driver to staging/rdma and schedule for deletion
   - Move ipath driver to staging/rdma and schedule for deletion
   - Add hfi1 driver to staging/rdma and set TODO for move to regular
     tree
   - Initial support for namespaces to be used on RDMA devices
   - Add RoCE GID table handling to the RDMA core caching code
   - Infrastructure to support handling of devices with differing read
     and write scatter gather capabilities
   - Various iSER updates
   - Kill off unsafe usage of global mr registrations
   - Update SRP driver
   - Misc  mlx4 driver updates
   - Support for the mr_alloc verb
   - Support for a netlink interface between kernel and user space cache
     daemon to speed path record queries and route resolution
   - Ininitial support for safe hot removal of verbs devices"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (136 commits)
  IB/ipoib: Suppress warning for send only join failures
  IB/ipoib: Clean up send-only multicast joins
  IB/srp: Fix possible protection fault
  IB/core: Move SM class defines from ib_mad.h to ib_smi.h
  IB/core: Remove unnecessary defines from ib_mad.h
  IB/hfi1: Add PSM2 user space header to header_install
  IB/hfi1: Add CSRs for CONFIG_SDMA_VERBOSITY
  mlx5: Fix incorrect wc pkey_index assignment for GSI messages
  IB/mlx5: avoid destroying a NULL mr in reg_user_mr error flow
  IB/uverbs: reject invalid or unknown opcodes
  IB/cxgb4: Fix if statement in pick_local_ip6adddrs
  IB/sa: Fix rdma netlink message flags
  IB/ucma: HW Device hot-removal support
  IB/mlx4_ib: Disassociate support
  IB/uverbs: Enable device removal when there are active user space applications
  IB/uverbs: Explicitly pass ib_dev to uverbs commands
  IB/uverbs: Fix race between ib_uverbs_open and remove_one
  IB/uverbs: Fix reference counting usage of event files
  IB/core: Make ib_dealloc_pd return void
  IB/srp: Create an insecure all physical rkey only if needed
  ...

1 files changed, 37 insertions, 13 deletions

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 0d23e0568deb..09a1748f9d13 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -393,8 +393,13 @@ static int ipoib_mcast_join_complete(int status,
 			goto out_locked;
 		}
 	} else {
-		if (mcast->logcount++ < 20) {
-			if (status == -ETIMEDOUT || status == -EAGAIN) {
+		bool silent_fail =
+		    test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
+		    status == -EINVAL;
+
+		if (mcast->logcount < 20) {
+			if (status == -ETIMEDOUT || status == -EAGAIN ||
+			    silent_fail) {
 				ipoib_dbg_mcast(priv, "%smulticast join failed for %pI6, status %d\n",
 						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
 						mcast->mcmember.mgid.raw, status);
@@ -403,6 +408,9 @@ static int ipoib_mcast_join_complete(int status,
 						test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) ? "sendonly " : "",
 					   mcast->mcmember.mgid.raw, status);
 			}
+
+			if (!silent_fail)
+				mcast->logcount++;
 		}
 
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
@@ -448,8 +456,7 @@ out_locked:
 	return status;
 }
 
-static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
-			     int create)
+static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_sa_multicast *multicast;
@@ -471,7 +478,14 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
 		IB_SA_MCMEMBER_REC_PKEY		|
 		IB_SA_MCMEMBER_REC_JOIN_STATE;
 
-	if (create) {
+	if (mcast != priv->broadcast) {
+		/*
+		 * RFC 4391:
+		 *  The MGID MUST use the same P_Key, Q_Key, SL, MTU,
+		 *  and HopLimit as those used in the broadcast-GID.  The rest
+		 *  of attributes SHOULD follow the values used in the
+		 *  broadcast-GID as well.
+		 */
 		comp_mask |=
 			IB_SA_MCMEMBER_REC_QKEY			|
 			IB_SA_MCMEMBER_REC_MTU_SELECTOR		|
@@ -492,6 +506,22 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast,
 		rec.sl		  = priv->broadcast->mcmember.sl;
 		rec.flow_label	  = priv->broadcast->mcmember.flow_label;
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
+
+		/*
+		 * Historically Linux IPoIB has never properly supported SEND
+		 * ONLY join. It emulated it by not providing all the required
+		 * attributes, which is enough to prevent group creation and
+		 * detect if there are full members or not. A major problem
+		 * with supporting SEND ONLY is detecting when the group is
+		 * auto-destroyed as IPoIB will cache the MLID..
+		 */
+#if 1
+		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
+#else
+		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+			rec.join_state = 4;
+#endif
 	}
 
 	multicast = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
@@ -517,7 +547,6 @@ void ipoib_mcast_join_task(struct work_struct *work)
 	struct ib_port_attr port_attr;
 	unsigned long delay_until = 0;
 	struct ipoib_mcast *mcast = NULL;
-	int create = 1;
 
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
 		return;
@@ -566,7 +595,6 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
 		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags)) {
 			mcast = priv->broadcast;
-			create = 0;
 			if (mcast->backoff > 1 &&
 			    time_before(jiffies, mcast->delay_until)) {
 				delay_until = mcast->delay_until;
@@ -590,12 +618,8 @@ void ipoib_mcast_join_task(struct work_struct *work)
 				/* Found the next unjoined group */
 				init_completion(&mcast->done);
 				set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-				if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-					create = 0;
-				else
-					create = 1;
 				spin_unlock_irq(&priv->lock);
-				ipoib_mcast_join(dev, mcast, create);
+				ipoib_mcast_join(dev, mcast);
 				spin_lock_irq(&priv->lock);
 			} else if (!delay_until ||
 				 time_before(mcast->delay_until, delay_until))
@@ -618,7 +642,7 @@ out:
 	}
 	spin_unlock_irq(&priv->lock);
 	if (mcast)
-		ipoib_mcast_join(dev, mcast, create);
+		ipoib_mcast_join(dev, mcast);
 }
 
 int ipoib_mcast_start_thread(struct net_device *dev)