Merge branch 'mlx5-next' into rdma.git for-next

From
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

To resolve conflicts with net-next and pick up the first patch.

* branch 'mlx5-next':
  net/mlx5: Factor out HCA capabilities functions
  IB/mlx5: Add support for 50Gbps per lane link modes
  net/mlx5: Add support to ext_* fields introduced in Port Type and Speed register
  net/mlx5: Add new fields to Port Type and Speed register
  net/mlx5: Refactor queries to speed fields in Port Type and Speed register
  net/mlx5: E-Switch, Avoid magic numbers when initializing offloads mode
  net/mlx5: Relocate vport macros to the vport header file
  net/mlx5: E-Switch, Normalize the name of uplink vport number
  net/mlx5: Provide an alternative VF upper bound for ECPF
  net/mlx5: Add host params change event
  net/mlx5: Add query host params command
  net/mlx5: Update enable HCA dependency
  net/mlx5: Introduce Mellanox SmartNIC and modify page management logic
  IB/mlx5: Use unified register/load function for uplink and VF vports
  net/mlx5: Use consistent vport num argument type
  net/mlx5: Use void pointer as the type in address_of macro
  net/mlx5: Align ODP capability function with netdev coding style
  mlx5: use RCU lock in mlx5_eq_cq_get()

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

3 files changed, 101 insertions, 77 deletions

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 95ac97af6166..0b5bf264cf1c 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -3,10 +3,11 @@
  * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
  */
 
+#include <linux/mlx5/vport.h>
 #include "ib_rep.h"
 #include "srq.h"
 
-static const struct mlx5_ib_profile rep_profile = {
+static const struct mlx5_ib_profile vf_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -46,30 +47,16 @@ static const struct mlx5_ib_profile rep_profile = {
 };
 
 static int
-mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	if (!__mlx5_ib_add(ibdev, ibdev->profile))
-		return -EINVAL;
-	return 0;
-}
-
-static void
-mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep)
-{
-	struct mlx5_ib_dev *ibdev;
-
-	ibdev = mlx5_ib_rep_to_dev(rep);
-	__mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX);
-}
-
-static int
 mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
+	const struct mlx5_ib_profile *profile;
 	struct mlx5_ib_dev *ibdev;
 
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		profile = &uplink_rep_profile;
+	else
+		profile = &vf_rep_profile;
+
 	ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);
 	if (!ibdev)
 		return -ENOMEM;
@@ -78,7 +65,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	ibdev->mdev = dev;
 	ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports),
 			       MLX5_CAP_GEN(dev, num_vhca_ports));
-	if (!__mlx5_ib_add(ibdev, &rep_profile)) {
+	if (!__mlx5_ib_add(ibdev, profile)) {
 		ib_dealloc_device(&ibdev->ib_dev);
 		return -EINVAL;
 	}
@@ -107,15 +94,14 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return mlx5_ib_rep_to_dev(rep);
 }
 
-static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev)
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vports = MLX5_TOTAL_VPORTS(mdev);
+	struct mlx5_eswitch_rep_if rep_if = {};
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
-
+	for (vport = 0; vport < total_vports; vport++) {
 		rep_if.load = mlx5_ib_vport_rep_load;
 		rep_if.unload = mlx5_ib_vport_rep_unload;
 		rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
@@ -123,39 +109,16 @@ static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev)
 	}
 }
 
-static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev)
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev);
+	struct mlx5_eswitch *esw = mdev->priv.eswitch;
+	int total_vports = MLX5_TOTAL_VPORTS(mdev);
 	int vport;
 
-	for (vport = 1; vport < total_vfs; vport++)
+	for (vport = total_vports - 1; vport >= 0; vport--)
 		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB);
 }
 
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if = {};
-
-	rep_if.load = mlx5_ib_nic_rep_load;
-	rep_if.unload = mlx5_ib_nic_rep_unload;
-	rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev;
-	rep_if.priv = dev;
-
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB);
-
-	mlx5_ib_rep_register_vf_vports(dev);
-}
-
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev)
-{
-	struct mlx5_eswitch *esw   = dev->mdev->priv.eswitch;
-
-	mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/
-}
-
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)
 {
 	return mlx5_eswitch_mode(esw);
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h
index 2ba73636a2fb..798d41e61fb4 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.h
+++ b/drivers/infiniband/hw/mlx5/ib_rep.h
@@ -10,14 +10,16 @@
 #include "mlx5_ib.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
+extern const struct mlx5_ib_profile uplink_rep_profile;
+
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
 					  int vport_index);
 struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw);
 struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 					   int vport_index);
-void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev);
-void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev);
+void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev);
+void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev);
 int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 			      struct mlx5_ib_sq *sq);
 struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
@@ -48,8 +50,8 @@ struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw,
 	return NULL;
 }
 
-static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {}
-static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {}
+static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {}
 static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev,
 					    struct mlx5_ib_sq *sq)
 {
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index f9cddc6f2ab6..45afe1d9e125 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -331,8 +331,8 @@ out:
 	spin_unlock(&port->mp.mpi_lock);
 }
 
-static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
-				    u8 *active_width)
+static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+					   u8 *active_width)
 {
 	switch (eth_proto_oper) {
 	case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII):
@@ -389,10 +389,66 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
 	return 0;
 }
 
+static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+					u8 *active_width)
+{
+	switch (eth_proto_oper) {
+	case MLX5E_PROT_MASK(MLX5E_SGMII_100M):
+	case MLX5E_PROT_MASK(MLX5E_1000BASE_X_SGMII):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_SDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_5GBASE_R):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_DDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_10GBASE_XFI_XAUI_1):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_QDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_40GBASE_XLAUI_4_XLPPI_4):
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_QDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_25GAUI_1_25GBASE_CR_KR):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_EDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2):
+	case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR):
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2):
+		*active_width = IB_WIDTH_2X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4):
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_HDR;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed,
+				    u8 *active_width, bool ext)
+{
+	return ext ?
+		translate_eth_ext_proto_oper(eth_proto_oper, active_speed,
+					     active_width) :
+		translate_eth_legacy_proto_oper(eth_proto_oper, active_speed,
+						active_width);
+}
+
 static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 				struct ib_port_attr *props)
 {
 	struct mlx5_ib_dev *dev = to_mdev(device);
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
 	struct mlx5_core_dev *mdev;
 	struct net_device *ndev, *upper;
 	enum ib_mtu ndev_ib_mtu;
@@ -400,6 +456,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	u16 qkey_viol_cntr;
 	u32 eth_prot_oper;
 	u8 mdev_port_num;
+	bool ext;
 	int err;
 
 	mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num);
@@ -416,16 +473,18 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num,
 	/* Possible bad flows are checked before filling out props so in case
 	 * of an error it will still be zeroed out.
 	 */
-	err = mlx5_query_port_eth_proto_oper(mdev, &eth_prot_oper,
-					     mdev_port_num);
+	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN,
+				   mdev_port_num);
 	if (err)
 		goto out;
+	ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet);
+	eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
 
 	props->active_width     = IB_WIDTH_4X;
 	props->active_speed     = IB_SPEED_QDR;
 
 	translate_eth_proto_oper(eth_prot_oper, &props->active_speed,
-				 &props->active_width);
+				 &props->active_width, ext);
 
 	props->port_cap_flags |= IB_PORT_CM_SUP;
 	props->ip_gids = true;
@@ -6435,7 +6494,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_delay_drop_cleanup),
 };
 
-static const struct mlx5_ib_profile nic_rep_profile = {
+const struct mlx5_ib_profile uplink_rep_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -6528,6 +6587,12 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 
 	printk_once(KERN_INFO "%s", mlx5_version);
 
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
+	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+		mlx5_ib_register_vport_reps(mdev);
+		return mdev;
+	}
+
 	port_type_cap = MLX5_CAP_GEN(mdev, port_type);
 	ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap);
 
@@ -6542,14 +6607,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			     MLX5_CAP_GEN(mdev, num_vhca_ports));
 
-	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
-		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
-		dev->profile = &nic_rep_profile;
-		mlx5_ib_register_vport_reps(dev);
-		return dev;
-	}
-
 	return __mlx5_ib_add(dev, &pf_profile);
 }
 
@@ -6558,6 +6615,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	struct mlx5_ib_multiport_info *mpi;
 	struct mlx5_ib_dev *dev;
 
+	if (MLX5_ESWITCH_MANAGER(mdev) && context == mdev) {
+		mlx5_ib_unregister_vport_reps(mdev);
+		return;
+	}
+
 	if (mlx5_core_is_mp_slave(mdev)) {
 		mpi = context;
 		mutex_lock(&mlx5_ib_multiport_mutex);
@@ -6569,10 +6631,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	}
 
 	dev = context;
-	if (dev->profile == &nic_rep_profile)
-		mlx5_ib_unregister_vport_reps(dev);
-	else
-		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
+	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
 
 	ib_dealloc_device((struct ib_device *)dev);
 }