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

Pull rdma fixes from Doug Ledford:
 - Fixes for mlx5 related issues
 - Fixes for ipoib multicast handling

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma:
  IB/ipoib: increase the max mcast backlog queue
  IB/ipoib: Make sendonly multicast joins create the mcast group
  IB/ipoib: Expire sendonly multicast joins
  IB/mlx5: Remove pa_lkey usages
  IB/mlx5: Remove support for IB_DEVICE_LOCAL_DMA_LKEY
  IB/iser: Add module parameter for always register memory
  xprtrdma: Replace global lkey with lkey local to PD

10 files changed, 68 insertions, 98 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 41d6911e244e..f1ccd40beae9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -245,7 +245,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
 	if (MLX5_CAP_GEN(mdev, apm))
 		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
-	props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
 	if (MLX5_CAP_GEN(mdev, xrc))
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
@@ -795,53 +794,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
-static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
-{
-	struct mlx5_create_mkey_mbox_in *in;
-	struct mlx5_mkey_seg *seg;
-	struct mlx5_core_mr mr;
-	int err;
-
-	in = kzalloc(sizeof(*in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	seg = &in->seg;
-	seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA;
-	seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
-	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-	seg->start_addr = 0;
-
-	err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in),
-				    NULL, NULL, NULL);
-	if (err) {
-		mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
-		goto err_in;
-	}
-
-	kfree(in);
-	*key = mr.key;
-
-	return 0;
-
-err_in:
-	kfree(in);
-
-	return err;
-}
-
-static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key)
-{
-	struct mlx5_core_mr mr;
-	int err;
-
-	memset(&mr, 0, sizeof(mr));
-	mr.key = key;
-	err = mlx5_core_destroy_mkey(dev->mdev, &mr);
-	if (err)
-		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key);
-}
-
 static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 				      struct ib_ucontext *context,
 				      struct ib_udata *udata)
@@ -867,13 +819,6 @@ static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 			kfree(pd);
 			return ERR_PTR(-EFAULT);
 		}
-	} else {
-		err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn);
-		if (err) {
-			mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn);
-			kfree(pd);
-			return ERR_PTR(err);
-		}
 	}
 
 	return &pd->ibpd;
@@ -884,9 +829,6 @@ static int mlx5_ib_dealloc_pd(struct ib_pd *pd)
 	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
 	struct mlx5_ib_pd *mpd = to_mpd(pd);
 
-	if (!pd->uobject)
-		free_pa_mkey(mdev, mpd->pa_lkey);
-
 	mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn);
 	kfree(mpd);
 
@@ -1245,18 +1187,10 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	struct ib_srq_init_attr attr;
 	struct mlx5_ib_dev *dev;
 	struct ib_cq_init_attr cq_attr = {.cqe = 1};
-	u32 rsvd_lkey;
 	int ret = 0;
 
 	dev = container_of(devr, struct mlx5_ib_dev, devr);
 
-	ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey);
-	if (ret) {
-		pr_err("Failed to query special context %d\n", ret);
-		return ret;
-	}
-	dev->ib_dev.local_dma_lkey = rsvd_lkey;
-
 	devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
 	if (IS_ERR(devr->p0)) {
 		ret = PTR_ERR(devr->p0);
@@ -1418,6 +1352,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
 	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
+	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->num_ports		= MLX5_CAP_GEN(mdev, num_ports);
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors    =
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bb8cda79e881..22123b79d550 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -103,7 +103,6 @@ static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibuconte
 struct mlx5_ib_pd {
 	struct ib_pd		ibpd;
 	u32			pdn;
-	u32			pa_lkey;
 };
 
 /* Use macros here so that don't have to duplicate
@@ -213,7 +212,6 @@ struct mlx5_ib_qp {
 	int			uuarn;
 
 	int			create_type;
-	u32			pa_lkey;
 
 	/* Store signature errors */
 	bool			signature_en;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index c745c6c5e10d..6f521a3418e8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -925,8 +925,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
 			if (err)
 				mlx5_ib_dbg(dev, "err %d\n", err);
-			else
-				qp->pa_lkey = to_mpd(pd)->pa_lkey;
 		}
 
 		if (err)
@@ -2045,7 +2043,7 @@ static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
 		mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
 	dseg->addr = cpu_to_be64(mfrpl->map);
 	dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64));
-	dseg->lkey = cpu_to_be32(pd->pa_lkey);
+	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
 }
 
 static __be32 send_ieth(struct ib_send_wr *wr)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca2873698d75..4cd5428a2399 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -548,6 +548,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce5a3e2..f74316e679d2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,8 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+		ipoib_mcast_leave(dev, mcast);
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748f9d13..136cbefe00f8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		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..
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
 		 */
-#if 1
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
 			rec.join_state = 4;
 #endif
@@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1ace5d83a4d7..f58ff96b6cbb 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -97,6 +97,11 @@ unsigned int iser_max_sectors = ISER_DEF_MAX_SECTORS;
 module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
 
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+		 "Always register memory, even for continuous memory regions (default:true)");
+
 bool iser_pi_enable = false;
 module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
 MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 86f6583485ef..a5edd6ede692 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -611,6 +611,7 @@ extern int iser_debug_level;
 extern bool iser_pi_enable;
 extern int iser_pi_guard;
 extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
 
 int iser_assign_reg_ops(struct iser_device *device);
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 2493cc748db8..4c46d67d37a1 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -803,11 +803,12 @@ static int
 iser_reg_prot_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
@@ -817,11 +818,12 @@ static int
 iser_reg_data_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
@@ -836,14 +838,17 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	struct iser_mem_reg *reg = &task->rdma_reg[dir];
 	struct iser_mem_reg *data_reg;
 	struct iser_fr_desc *desc = NULL;
+	bool use_dma_key;
 	int err;
 
 	err = iser_handle_unaligned_buf(task, mem, dir);
 	if (unlikely(err))
 		return err;
 
-	if (mem->dma_nents != 1 ||
-	    scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+	use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+		       scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+	if (!use_dma_key) {
 		desc = device->reg_ops->reg_desc_get(ib_conn);
 		reg->mem_h = desc;
 	}
@@ -853,7 +858,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	else
 		data_reg = &task->desc.data_reg;
 
-	err = iser_reg_data_sg(task, mem, desc, data_reg);
+	err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
 	if (unlikely(err))
 		goto err_reg;
 
@@ -866,7 +871,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 			if (unlikely(err))
 				goto err_reg;
 
-			err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+			err = iser_reg_prot_sg(task, mem, desc,
+					       use_dma_key, prot_reg);
 			if (unlikely(err))
 				goto err_reg;
 		}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1463ac..85132d867bc8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -133,11 +133,15 @@ static int iser_create_device_ib_res(struct iser_device *device)
 			     (unsigned long)comp);
 	}
 
-	device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
-				   IB_ACCESS_REMOTE_WRITE |
-				   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(device->mr))
-		goto dma_mr_err;
+	if (!iser_always_reg) {
+		int access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_WRITE |
+			     IB_ACCESS_REMOTE_READ;
+
+		device->mr = ib_get_dma_mr(device->pd, access);
+		if (IS_ERR(device->mr))
+			goto dma_mr_err;
+	}
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
 				iser_event_handler);
@@ -147,7 +151,8 @@ static int iser_create_device_ib_res(struct iser_device *device)
 	return 0;
 
 handler_err:
-	ib_dereg_mr(device->mr);
+	if (device->mr)
+		ib_dereg_mr(device->mr);
 dma_mr_err:
 	for (i = 0; i < device->comps_used; i++)
 		tasklet_kill(&device->comps[i].tasklet);
@@ -173,7 +178,6 @@ comps_err:
 static void iser_free_device_ib_res(struct iser_device *device)
 {
 	int i;
-	BUG_ON(device->mr == NULL);
 
 	for (i = 0; i < device->comps_used; i++) {
 		struct iser_comp *comp = &device->comps[i];
@@ -184,7 +188,8 @@ static void iser_free_device_ib_res(struct iser_device *device)
 	}
 
 	(void)ib_unregister_event_handler(&device->event_handler);
-	(void)ib_dereg_mr(device->mr);
+	if (device->mr)
+		(void)ib_dereg_mr(device->mr);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);