Merge mlx5-next into rdma.git for-next

Synchronize the shared mlx5 branch with net:
 - From Jiri: fixe a deadlock in mlx5_ib's netdev notifier unregister.
 - From Mark and Patrisious: add IPsec RoCEv2 support.
 - From Or: Rely on firmware to get special mkeys

* branch mlx5-next:
  RDMA/mlx5: Use query_special_contexts for mkeys
  net/mlx5e: Use query_special_contexts for mkeys
  net/mlx5: Change define name for 0x100 lkey value
  net/mlx5: Expose bits for querying special mkeys
  net/mlx5: Configure IPsec steering for egress RoCEv2 traffic
  net/mlx5: Configure IPsec steering for ingress RoCEv2 traffic
  net/mlx5: Add IPSec priorities in RDMA namespaces
  net/mlx5: Implement new destination type TABLE_TYPE
  net/mlx5: Introduce new destination type TABLE_TYPE
  RDMA/mlx5: Track netdev to avoid deadlock during netdev notifier unregister
  net/mlx5e: Propagate an internal event in case uplink netdev changes
  net/mlx5e: Fix trap event handling

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

7 files changed, 108 insertions, 71 deletions

diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index ff3742b0460a..1d0c8d5e745b 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -5,34 +5,41 @@
 
 #include "cmd.h"
 
-int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey)
+int mlx5r_cmd_query_special_mkeys(struct mlx5_ib_dev *dev)
 {
 	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
 	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
+	bool is_terminate, is_dump, is_null;
 	int err;
 
-	MLX5_SET(query_special_contexts_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out);
-	if (!err)
-		*mkey = MLX5_GET(query_special_contexts_out, out,
-				 dump_fill_mkey);
-	return err;
-}
+	is_terminate = MLX5_CAP_GEN(dev->mdev, terminate_scatter_list_mkey);
+	is_dump = MLX5_CAP_GEN(dev->mdev, dump_fill_mkey);
+	is_null = MLX5_CAP_GEN(dev->mdev, null_mkey);
 
-int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey)
-{
-	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
-	int err;
+	dev->mkeys.terminate_scatter_list_mkey = MLX5_TERMINATE_SCATTER_LIST_LKEY;
+	if (!is_terminate && !is_dump && !is_null)
+		return 0;
 
 	MLX5_SET(query_special_contexts_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out);
-	if (!err)
-		*null_mkey = MLX5_GET(query_special_contexts_out, out,
-				      null_mkey);
-	return err;
+	err = mlx5_cmd_exec_inout(dev->mdev, query_special_contexts, in, out);
+	if (err)
+		return err;
+
+	if (is_dump)
+		dev->mkeys.dump_fill_mkey = MLX5_GET(query_special_contexts_out,
+						     out, dump_fill_mkey);
+
+	if (is_null)
+		dev->mkeys.null_mkey = cpu_to_be32(
+			MLX5_GET(query_special_contexts_out, out, null_mkey));
+
+	if (is_terminate)
+		dev->mkeys.terminate_scatter_list_mkey =
+			cpu_to_be32(MLX5_GET(query_special_contexts_out, out,
+					     terminate_scatter_list_mkey));
+
+	return 0;
 }
 
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index ee46638db5de..93a971a40d11 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -37,8 +37,7 @@
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
 
-int mlx5_cmd_dump_fill_mkey(struct mlx5_core_dev *dev, u32 *mkey);
-int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
+int mlx5r_cmd_query_special_mkeys(struct mlx5_ib_dev *dev);
 int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
 			       void *out);
 int mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 2ccf6a504087..8b664a57123e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1756,13 +1756,9 @@ static int set_ucontext_resp(struct ib_ucontext *uctx,
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_ib_ucontext *context = to_mucontext(uctx);
 	struct mlx5_bfreg_info *bfregi = &context->bfregi;
-	int err;
 
 	if (MLX5_CAP_GEN(dev->mdev, dump_fill_mkey)) {
-		err = mlx5_cmd_dump_fill_mkey(dev->mdev,
-					      &resp->dump_fill_mkey);
-		if (err)
-			return err;
+		resp->dump_fill_mkey = dev->mkeys.dump_fill_mkey;
 		resp->comp_mask |=
 			MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY;
 	}
@@ -3012,26 +3008,63 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev)
 	}
 }
 
-static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
+static void mlx5_netdev_notifier_register(struct mlx5_roce *roce,
+					  struct net_device *netdev)
 {
 	int err;
 
-	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
-	if (err) {
-		dev->port[port_num].roce.nb.notifier_call = NULL;
-		return err;
-	}
+	if (roce->tracking_netdev)
+		return;
+	roce->tracking_netdev = netdev;
+	roce->nb.notifier_call = mlx5_netdev_event;
+	err = register_netdevice_notifier_dev_net(netdev, &roce->nb, &roce->nn);
+	WARN_ON(err);
+}
 
-	return 0;
+static void mlx5_netdev_notifier_unregister(struct mlx5_roce *roce)
+{
+	if (!roce->tracking_netdev)
+		return;
+	unregister_netdevice_notifier_dev_net(roce->tracking_netdev, &roce->nb,
+					      &roce->nn);
+	roce->tracking_netdev = NULL;
 }
 
-static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
+static int mlx5e_mdev_notifier_event(struct notifier_block *nb,
+				     unsigned long event, void *data)
 {
-	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
-		dev->port[port_num].roce.nb.notifier_call = NULL;
+	struct mlx5_roce *roce = container_of(nb, struct mlx5_roce, mdev_nb);
+	struct net_device *netdev = data;
+
+	switch (event) {
+	case MLX5_DRIVER_EVENT_UPLINK_NETDEV:
+		if (netdev)
+			mlx5_netdev_notifier_register(roce, netdev);
+		else
+			mlx5_netdev_notifier_unregister(roce);
+		break;
+	default:
+		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_OK;
+}
+
+static void mlx5_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	struct mlx5_roce *roce = &dev->port[port_num].roce;
+
+	roce->mdev_nb.notifier_call = mlx5e_mdev_notifier_event;
+	mlx5_blocking_notifier_register(dev->mdev, &roce->mdev_nb);
+	mlx5_core_uplink_netdev_event_replay(dev->mdev);
+}
+
+static void mlx5_mdev_netdev_untrack(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	struct mlx5_roce *roce = &dev->port[port_num].roce;
+
+	mlx5_blocking_notifier_unregister(dev->mdev, &roce->mdev_nb);
+	mlx5_netdev_notifier_unregister(roce);
 }
 
 static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
@@ -3138,7 +3171,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 	if (mpi->mdev_events.notifier_call)
 		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
 	mpi->mdev_events.notifier_call = NULL;
-	mlx5_remove_netdev_notifier(ibdev, port_num);
+	mlx5_mdev_netdev_untrack(ibdev, port_num);
 	spin_lock(&port->mp.mpi_lock);
 
 	comps = mpi->mdev_refcnt;
@@ -3196,12 +3229,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 	if (err)
 		goto unbind;
 
-	err = mlx5_add_netdev_notifier(ibdev, port_num);
-	if (err) {
-		mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n",
-			    port_num + 1);
-		goto unbind;
-	}
+	mlx5_mdev_netdev_track(ibdev, port_num);
 
 	mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port;
 	mlx5_notifier_register(mpi->mdev, &mpi->mdev_events);
@@ -3634,6 +3662,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 		dev->port[i].roce.last_port_state = IB_PORT_DOWN;
 	}
 
+	err = mlx5r_cmd_query_special_mkeys(dev);
+	if (err)
+		return err;
+
 	err = mlx5_ib_init_multiport_master(dev);
 	if (err)
 		return err;
@@ -3909,9 +3941,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
 		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
 
 		/* Register only for native ports */
-		err = mlx5_add_netdev_notifier(dev, port_num);
-		if (err)
-			return err;
+		mlx5_mdev_netdev_track(dev, port_num);
 
 		err = mlx5_enable_eth(dev);
 		if (err)
@@ -3920,7 +3950,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
 
 	return 0;
 cleanup:
-	mlx5_remove_netdev_notifier(dev, port_num);
+	mlx5_mdev_netdev_untrack(dev, port_num);
 	return err;
 }
 
@@ -3938,7 +3968,7 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev)
 		mlx5_disable_eth(dev);
 
 		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
-		mlx5_remove_netdev_notifier(dev, port_num);
+		mlx5_mdev_netdev_untrack(dev, port_num);
 	}
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 4ef14ac3a34d..f6c799f75b8e 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -843,6 +843,9 @@ struct mlx5_roce {
 	rwlock_t		netdev_lock;
 	struct net_device	*netdev;
 	struct notifier_block	nb;
+	struct netdev_net_notifier nn;
+	struct notifier_block	mdev_nb;
+	struct net_device	*tracking_netdev;
 	atomic_t		tx_port_affinity;
 	enum ib_port_state last_port_state;
 	struct mlx5_ib_dev	*dev;
@@ -1062,6 +1065,13 @@ struct mlx5_port_caps {
 	u8 ext_port_cap;
 };
 
+
+struct mlx5_special_mkeys {
+	u32 dump_fill_mkey;
+	__be32 null_mkey;
+	__be32 terminate_scatter_list_mkey;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;
@@ -1092,7 +1102,6 @@ struct mlx5_ib_dev {
 
 	struct xarray		odp_mkeys;
 
-	u32			null_mkey;
 	struct mlx5_ib_flow_db	*flow_db;
 	/* protect resources needed as part of reset flow */
 	spinlock_t		reset_flow_resource_lock;
@@ -1121,6 +1130,7 @@ struct mlx5_ib_dev {
 	struct mlx5_port_caps port_caps[MLX5_MAX_PORTS];
 	u16 pkey_table_len;
 	u8 lag_ports;
+	struct mlx5_special_mkeys mkeys;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 6f447095218f..4a04cbc5b78a 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -104,7 +104,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
 	if (flags & MLX5_IB_UPD_XLT_ZAP) {
 		for (; pklm != end; pklm++, idx++) {
 			pklm->bcount = cpu_to_be32(MLX5_IMR_MTT_SIZE);
-			pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey);
+			pklm->key = mr_to_mdev(imr)->mkeys.null_mkey;
 			pklm->va = 0;
 		}
 		return;
@@ -137,7 +137,7 @@ static void populate_klm(struct mlx5_klm *pklm, size_t idx, size_t nentries,
 			pklm->key = cpu_to_be32(mtt->ibmr.lkey);
 			pklm->va = cpu_to_be64(idx * MLX5_IMR_MTT_SIZE);
 		} else {
-			pklm->key = cpu_to_be32(mr_to_mdev(imr)->null_mkey);
+			pklm->key = mr_to_mdev(imr)->mkeys.null_mkey;
 			pklm->va = 0;
 		}
 	}
@@ -986,7 +986,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 {
 	int ret = 0, npages = 0;
 	u64 io_virt;
-	u32 key;
+	__be32 key;
 	u32 byte_count;
 	size_t bcnt;
 	int inline_segment;
@@ -1000,7 +1000,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 		struct mlx5_wqe_data_seg *dseg = wqe;
 
 		io_virt = be64_to_cpu(dseg->addr);
-		key = be32_to_cpu(dseg->lkey);
+		key = dseg->lkey;
 		byte_count = be32_to_cpu(dseg->byte_count);
 		inline_segment = !!(byte_count &  MLX5_INLINE_SEG);
 		bcnt	       = byte_count & ~MLX5_INLINE_SEG;
@@ -1014,7 +1014,8 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 		}
 
 		/* receive WQE end of sg list. */
-		if (receive_queue && bcnt == 0 && key == MLX5_INVALID_LKEY &&
+		if (receive_queue && bcnt == 0 &&
+		    key == dev->mkeys.terminate_scatter_list_mkey &&
 		    io_virt == 0)
 			break;
 
@@ -1034,7 +1035,7 @@ static int pagefault_data_segments(struct mlx5_ib_dev *dev,
 			continue;
 		}
 
-		ret = pagefault_single_data_segment(dev, NULL, key,
+		ret = pagefault_single_data_segment(dev, NULL, be32_to_cpu(key),
 						    io_virt, bcnt,
 						    &pfault->bytes_committed,
 						    bytes_mapped);
@@ -1611,25 +1612,15 @@ static const struct ib_device_ops mlx5_ib_dev_odp_ops = {
 
 int mlx5_ib_odp_init_one(struct mlx5_ib_dev *dev)
 {
-	int ret = 0;
-
 	internal_fill_odp_caps(dev);
 
 	if (!(dev->odp_caps.general_caps & IB_ODP_SUPPORT))
-		return ret;
+		return 0;
 
 	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_odp_ops);
 
-	if (dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT) {
-		ret = mlx5_cmd_null_mkey(dev->mdev, &dev->null_mkey);
-		if (ret) {
-			mlx5_ib_err(dev, "Error getting null_mkey %d\n", ret);
-			return ret;
-		}
-	}
-
 	mutex_init(&dev->odp_eq_mutex);
-	return ret;
+	return 0;
 }
 
 void mlx5_ib_odp_cleanup_one(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 09b365a98bbf..a056ea835da5 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -447,7 +447,7 @@ int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 
 		if (i < srq->msrq.max_avail_gather) {
 			scat[i].byte_count = 0;
-			scat[i].lkey       = cpu_to_be32(MLX5_INVALID_LKEY);
+			scat[i].lkey = dev->mkeys.terminate_scatter_list_mkey;
 			scat[i].addr       = 0;
 		}
 	}
diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c
index 855f3f4fefad..df1d1b0a3ef7 100644
--- a/drivers/infiniband/hw/mlx5/wr.c
+++ b/drivers/infiniband/hw/mlx5/wr.c
@@ -1252,7 +1252,7 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 		if (i < qp->rq.max_gs) {
 			scat[i].byte_count = 0;
-			scat[i].lkey       = cpu_to_be32(MLX5_INVALID_LKEY);
+			scat[i].lkey = dev->mkeys.terminate_scatter_list_mkey;
 			scat[i].addr       = 0;
 		}