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

Pull rdma updates from Jason Gunthorpe:
 "Usual collection of small improvements and fixes, nothing especially
  stands out to me here.

  The new multipath PCI feature is a sign of things to come, I think we
  will see more of this in the next 10 years. Broadcom and HNS continue
  to update their drivers for their new HW generations.

  Summary:

   - Bug fixes and minor improvments in cxgb4, siw, mlx5, rxe, efa, rts,
     hfi, erdma, hns, irdma

   - Code cleanups/typos/etc. Tidy alloc_ordered_workqueue() calls

   - Multipath PCI for mlx5

   - Variable size work queue, SRQ changes, and relaxed ordering for new
     bnxt HW

   - New ODP fault resolution FW protocol in mlx5

   - New 'rdma monitor' netlink mechanism"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (99 commits)
  RDMA/bnxt_re: Remove the unused variable en_dev
  RDMA/nldev: Add missing break in rdma_nl_notify_err_msg()
  RDMA/irdma: fix error message in irdma_modify_qp_roce()
  RDMA/cxgb4: Added NULL check for lookup_atid
  RDMA/hns: Fix ah error counter in sw stat not increasing
  RDMA/bnxt_re: Recover the device when FW error is detected
  RDMA/bnxt_re: Group all operations under add_device and remove_device
  RDMA/bnxt_re: Use the aux device for L2 ULP callbacks
  RDMA/bnxt_re: Change aux driver data to en_info to hold more information
  RDMA/nldev: Expose whether RDMA monitoring is supported
  RDMA/nldev: Add support for RDMA monitoring
  RDMA/mlx5: Use IB set_netdev and get_netdev functions
  RDMA/device: Remove optimization in ib_device_get_netdev()
  RDMA/mlx5: Initialize phys_port_cnt earlier in RDMA device creation
  RDMA/mlx5: Obtain upper net device only when needed
  RDMA/mlx5: Check RoCE LAG status before getting netdev
  RDMA/mlx5: Consider the query_vuid cap for data_direct
  net/mlx5: Handle memory scheme ODP capabilities
  RDMA/mlx5: Add implicit MR handling to ODP memory scheme
  RDMA/mlx5: Add handling for memory scheme page fault events
  ...

2 files changed, 75 insertions, 55 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index cf8045b92689..8577db3308cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -445,6 +445,34 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports)
 	return mlx5_cmd_modify_lag(dev0, ldev->ports, ports);
 }
 
+static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev *dev)
+{
+	struct net_device *ndev = NULL;
+	struct mlx5_lag *ldev;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&lag_lock, flags);
+	ldev = mlx5_lag_dev(dev);
+
+	if (!ldev)
+		goto unlock;
+
+	for (i = 0; i < ldev->ports; i++)
+		if (ldev->tracker.netdev_state[i].tx_enabled)
+			ndev = ldev->pf[i].netdev;
+	if (!ndev)
+		ndev = ldev->pf[ldev->ports - 1].netdev;
+
+	if (ndev)
+		dev_hold(ndev);
+
+unlock:
+	spin_unlock_irqrestore(&lag_lock, flags);
+
+	return ndev;
+}
+
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker)
 {
@@ -477,9 +505,18 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 		}
 	}
 
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
-	    !(ldev->mode == MLX5_LAG_MODE_ROCE))
-		mlx5_lag_drop_rule_setup(ldev, tracker);
+	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
+		struct net_device *ndev = mlx5_lag_active_backup_get_netdev(dev0);
+
+		if(!(ldev->mode == MLX5_LAG_MODE_ROCE))
+			mlx5_lag_drop_rule_setup(ldev, tracker);
+		/** Only sriov and roce lag should have tracker->tx_type set so
+		 *  no need to check the mode
+		 */
+		blocking_notifier_call_chain(&dev0->priv.lag_nh,
+					     MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE,
+					     ndev);
+	}
 }
 
 static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
@@ -613,6 +650,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 			mlx5_core_err(dev0,
 				      "Failed to deactivate RoCE LAG; driver restart required\n");
 	}
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev0->priv.lag_nh);
 
 	return err;
 }
@@ -1492,38 +1530,6 @@ void mlx5_lag_enable_change(struct mlx5_core_dev *dev)
 	mlx5_queue_bond_work(ldev, 0);
 }
 
-struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
-{
-	struct net_device *ndev = NULL;
-	struct mlx5_lag *ldev;
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&lag_lock, flags);
-	ldev = mlx5_lag_dev(dev);
-
-	if (!(ldev && __mlx5_lag_is_roce(ldev)))
-		goto unlock;
-
-	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		for (i = 0; i < ldev->ports; i++)
-			if (ldev->tracker.netdev_state[i].tx_enabled)
-				ndev = ldev->pf[i].netdev;
-		if (!ndev)
-			ndev = ldev->pf[ldev->ports - 1].netdev;
-	} else {
-		ndev = ldev->pf[MLX5_LAG_P1].netdev;
-	}
-	if (ndev)
-		dev_hold(ndev);
-
-unlock:
-	spin_unlock_irqrestore(&lag_lock, flags);
-
-	return ndev;
-}
-EXPORT_SYMBOL(mlx5_lag_get_roce_netdev);
-
 u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 			   struct net_device *slave)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 8b0abd61eca6..220a9ac75c8b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -454,8 +454,8 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev, void *set_ctx)
 
 static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 {
+	bool do_set = false, mem_page_fault = false;
 	void *set_hca_cap;
-	bool do_set = false;
 	int err;
 
 	if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
@@ -470,6 +470,17 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 	memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_ODP]->cur,
 	       MLX5_ST_SZ_BYTES(odp_cap));
 
+	/* For best performance, enable memory scheme ODP only when
+	 * it has page prefetch enabled.
+	 */
+	if (MLX5_CAP_ODP_MAX(dev, mem_page_fault) &&
+	    MLX5_CAP_ODP_MAX(dev, memory_page_fault_scheme_cap.page_prefetch)) {
+		mem_page_fault = true;
+		do_set = true;
+		MLX5_SET(odp_cap, set_hca_cap, mem_page_fault, mem_page_fault);
+		goto set;
+	}
+
 #define ODP_CAP_SET_MAX(dev, field)                                            \
 	do {                                                                   \
 		u32 _res = MLX5_CAP_ODP_MAX(dev, field);                       \
@@ -479,25 +490,28 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 		}                                                              \
 	} while (0)
 
-	ODP_CAP_SET_MAX(dev, ud_odp_caps.srq_receive);
-	ODP_CAP_SET_MAX(dev, rc_odp_caps.srq_receive);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.srq_receive);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.send);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.receive);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.write);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.read);
-	ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.send);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.receive);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.write);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.read);
-	ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic);
-
-	if (!do_set)
-		return 0;
-
-	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.ud_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.rc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.send);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.write);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.read);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.xrc_odp_caps.atomic);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.send);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.receive);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.write);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.read);
+	ODP_CAP_SET_MAX(dev, transport_page_fault_scheme_cap.dc_odp_caps.atomic);
+
+set:
+	if (do_set)
+		err = set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
+
+	mlx5_core_dbg(dev, "Using ODP %s scheme\n",
+		      mem_page_fault ? "memory" : "transport");
+	return err;
 }
 
 static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)