Merge branch 'ib-guids' into rdma.git for-next

Danit Goldberg says:

====================
This series extends RTNETLINK to provide IB port and node GUIDs, which
were configured for Infiniband VFs.

The functionality to set VF GUIDs already existed for a long time, and
here we are adding the missing "get" so that netlink will be symmetric and
various cloud orchestration tools will be able to manage such VFs more
naturally.

The iproute2 was extended too to present those GUIDs.

- ip link show <device>

For example:
- ip link set ib4 vf 0 node_guid 22:44:33:00:33:11:00:33
- ip link set ib4 vf 0 port_guid 10:21:33:12:00:11:22:10
- ip link show ib4
    ib4: <BROADCAST,MULTICAST> mtu 4092 qdisc noop state DOWN mode DEFAULT group default qlen 256
    link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff
    vf 0     link/infiniband 00:00:0a:2d:fe:80:00:00:00:00:00:00:ec:0d:9a:03:00:44:36:8d brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff,
    spoof checking off, NODE_GUID 22:44:33:00:33:11:00:33, PORT_GUID 10:21:33:12:00:11:22:10, link-state disable, trust off, query_rss off
====================

Based on the mlx5-next branch from
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux for
dependencies

* branch 'ib-guids': (35 commits)
  IB/mlx5: Implement callbacks for getting VFs GUID attributes
  IB/ipoib: Add ndo operation for getting VFs GUID attributes
  IB/core: Add interfaces to get VF node and port GUIDs
  net/core: Add support for getting VF GUIDs

  net/mlx5: Add new chain for netfilter flow table offload
  net/mlx5: Refactor creating fast path prio chains
  net/mlx5: Accumulate levels for chains prio namespaces
  net/mlx5: Define fdb tc levels per prio
  net/mlx5: Rename FDB_* tc related defines to FDB_TC_* defines
  net/mlx5: Simplify fdb chain and prio eswitch defines
  IB/mlx5: Load profile according to RoCE enablement state
  IB/mlx5: Rename profile and init methods
  net/mlx5: Handle "enable_roce" devlink param
  net/mlx5: Document flow_steering_mode devlink param
  devlink: Add new "enable_roce" generic device param
  net/mlx5: fix spelling mistake "metdata" -> "metadata"
  net/mlx5: fix kvfree of uninitialized pointer spec
  IB/mlx5: Introduce and use mlx5_core_is_vf()
  net/mlx5: E-switch, Enable metadata on own vport
  net/mlx5: Refactor ingress acl configuration
  ...

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

8 files changed, 72 insertions, 22 deletions

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 1ad39b209252..cadc9aebc572 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2631,6 +2631,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, get_port_immutable);
 	SET_DEVICE_OP(dev_ops, get_vector_affinity);
 	SET_DEVICE_OP(dev_ops, get_vf_config);
+	SET_DEVICE_OP(dev_ops, get_vf_guid);
 	SET_DEVICE_OP(dev_ops, get_vf_stats);
 	SET_DEVICE_OP(dev_ops, init_port);
 	SET_DEVICE_OP(dev_ops, invalidate_range);
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index d357ac077bd8..4c2e8f3c48fe 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -2460,6 +2460,16 @@ int ib_set_vf_guid(struct ib_device *device, int vf, u8 port, u64 guid,
 }
 EXPORT_SYMBOL(ib_set_vf_guid);
 
+int ib_get_vf_guid(struct ib_device *device, int vf, u8 port,
+		   struct ifla_vf_guid *node_guid,
+		   struct ifla_vf_guid *port_guid)
+{
+	if (!device->ops.get_vf_guid)
+		return -EOPNOTSUPP;
+
+	return device->ops.get_vf_guid(device, vf, port, node_guid, port_guid);
+}
+EXPORT_SYMBOL(ib_get_vf_guid);
 /**
  * ib_map_mr_sg_pi() - Map the dma mapped SG lists for PI (protection
  *     information) and set an appropriate memory region for registration.
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 74ce9249e75a..5c3d052ac30b 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -35,7 +35,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	int vport_index;
 
 	if (rep->vport == MLX5_VPORT_UPLINK)
-		profile = &uplink_rep_profile;
+		profile = &raw_eth_profile;
 	else
 		return mlx5_ib_set_vport_rep(dev, rep);
 
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h
index de43b423bafc..3b6750cba796 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.h
+++ b/drivers/infiniband/hw/mlx5/ib_rep.h
@@ -10,7 +10,7 @@
 #include "mlx5_ib.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
-extern const struct mlx5_ib_profile uplink_rep_profile;
+extern const struct mlx5_ib_profile raw_eth_profile;
 
 u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw,
diff --git a/drivers/infiniband/hw/mlx5/ib_virt.c b/drivers/infiniband/hw/mlx5/ib_virt.c
index 649a3364f838..4f0edd4832bd 100644
--- a/drivers/infiniband/hw/mlx5/ib_virt.c
+++ b/drivers/infiniband/hw/mlx5/ib_virt.c
@@ -201,3 +201,27 @@ int mlx5_ib_set_vf_guid(struct ib_device *device, int vf, u8 port,
 
 	return -EINVAL;
 }
+
+int mlx5_ib_get_vf_guid(struct ib_device *device, int vf, u8 port,
+			struct ifla_vf_guid *node_guid,
+			struct ifla_vf_guid *port_guid)
+{
+	struct mlx5_ib_dev *dev = to_mdev(device);
+	struct mlx5_core_dev *mdev = dev->mdev;
+	struct mlx5_hca_vport_context *rep;
+	int err;
+
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (!rep)
+		return -ENOMEM;
+
+	err = mlx5_query_hca_vport_context(mdev, 1, 1, vf+1, rep);
+	if (err)
+		goto ex;
+
+	port_guid->guid = rep->port_guid;
+	node_guid->guid = rep->node_guid;
+ex:
+	kfree(rep);
+	return err;
+}
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4ced72185172..97b26e9a5234 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1019,7 +1019,7 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (MLX5_CAP_GEN(mdev, cd))
 		props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL;
 
-	if (!mlx5_core_is_pf(mdev))
+	if (mlx5_core_is_vf(mdev))
 		props->device_cap_flags |= IB_DEVICE_VIRTUAL_FUNCTION;
 
 	if (mlx5_ib_port_link_layer(ibdev, 1) ==
@@ -5141,8 +5141,7 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	immutable->pkey_tbl_len = attr.pkey_tbl_len;
 	immutable->gid_tbl_len = attr.gid_tbl_len;
 	immutable->core_cap_flags = get_core_cap_flags(ibdev, &rep);
-	if ((ll == IB_LINK_LAYER_INFINIBAND) || MLX5_CAP_GEN(dev->mdev, roce))
-		immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
 
 	return 0;
 }
@@ -5245,11 +5244,9 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
 {
 	int err;
 
-	if (MLX5_CAP_GEN(dev->mdev, roce)) {
-		err = mlx5_nic_vport_enable_roce(dev->mdev);
-		if (err)
-			return err;
-	}
+	err = mlx5_nic_vport_enable_roce(dev->mdev);
+	if (err)
+		return err;
 
 	err = mlx5_eth_lag_init(dev);
 	if (err)
@@ -5258,8 +5255,7 @@ static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
 	return 0;
 
 err_disable_roce:
-	if (MLX5_CAP_GEN(dev->mdev, roce))
-		mlx5_nic_vport_disable_roce(dev->mdev);
+	mlx5_nic_vport_disable_roce(dev->mdev);
 
 	return err;
 }
@@ -5267,8 +5263,7 @@ err_disable_roce:
 static void mlx5_disable_eth(struct mlx5_ib_dev *dev)
 {
 	mlx5_eth_lag_cleanup(dev);
-	if (MLX5_CAP_GEN(dev->mdev, roce))
-		mlx5_nic_vport_disable_roce(dev->mdev);
+	mlx5_nic_vport_disable_roce(dev->mdev);
 }
 
 struct mlx5_ib_counter {
@@ -6313,6 +6308,7 @@ static const struct ib_device_ops mlx5_ib_dev_ipoib_enhanced_ops = {
 
 static const struct ib_device_ops mlx5_ib_dev_sriov_ops = {
 	.get_vf_config = mlx5_ib_get_vf_config,
+	.get_vf_guid = mlx5_ib_get_vf_guid,
 	.get_vf_stats = mlx5_ib_get_vf_stats,
 	.set_vf_guid = mlx5_ib_set_vf_guid,
 	.set_vf_link_state = mlx5_ib_set_vf_link_state,
@@ -6442,7 +6438,7 @@ static const struct ib_device_ops mlx5_ib_dev_port_rep_ops = {
 	.query_port = mlx5_ib_rep_query_port,
 };
 
-static int mlx5_ib_stage_rep_non_default_cb(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_raw_eth_non_default_cb(struct mlx5_ib_dev *dev)
 {
 	ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_port_rep_ops);
 	return 0;
@@ -6482,7 +6478,7 @@ static void mlx5_ib_stage_common_roce_cleanup(struct mlx5_ib_dev *dev)
 	mlx5_remove_netdev_notifier(dev, port_num);
 }
 
-static int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev)
+static int mlx5_ib_stage_raw_eth_roce_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
 	enum rdma_link_layer ll;
@@ -6498,7 +6494,7 @@ static int mlx5_ib_stage_rep_roce_init(struct mlx5_ib_dev *dev)
 	return err;
 }
 
-static void mlx5_ib_stage_rep_roce_cleanup(struct mlx5_ib_dev *dev)
+static void mlx5_ib_stage_raw_eth_roce_cleanup(struct mlx5_ib_dev *dev)
 {
 	mlx5_ib_stage_common_roce_cleanup(dev);
 }
@@ -6817,7 +6813,7 @@ static const struct mlx5_ib_profile pf_profile = {
 		     mlx5_ib_stage_delay_drop_cleanup),
 };
 
-const struct mlx5_ib_profile uplink_rep_profile = {
+const struct mlx5_ib_profile raw_eth_profile = {
 	STAGE_CREATE(MLX5_IB_STAGE_INIT,
 		     mlx5_ib_stage_init_init,
 		     mlx5_ib_stage_init_cleanup),
@@ -6828,11 +6824,11 @@ const struct mlx5_ib_profile uplink_rep_profile = {
 		     mlx5_ib_stage_caps_init,
 		     NULL),
 	STAGE_CREATE(MLX5_IB_STAGE_NON_DEFAULT_CB,
-		     mlx5_ib_stage_rep_non_default_cb,
+		     mlx5_ib_stage_raw_eth_non_default_cb,
 		     NULL),
 	STAGE_CREATE(MLX5_IB_STAGE_ROCE,
-		     mlx5_ib_stage_rep_roce_init,
-		     mlx5_ib_stage_rep_roce_cleanup),
+		     mlx5_ib_stage_raw_eth_roce_init,
+		     mlx5_ib_stage_raw_eth_roce_cleanup),
 	STAGE_CREATE(MLX5_IB_STAGE_SRQ,
 		     mlx5_init_srq_table,
 		     mlx5_cleanup_srq_table),
@@ -6908,6 +6904,7 @@ static void *mlx5_ib_add_slave_port(struct mlx5_core_dev *mdev)
 
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
+	const struct mlx5_ib_profile *profile;
 	enum rdma_link_layer ll;
 	struct mlx5_ib_dev *dev;
 	int port_type_cap;
@@ -6943,7 +6940,12 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->mdev = mdev;
 	dev->num_ports = num_ports;
 
-	return __mlx5_ib_add(dev, &pf_profile);
+	if (ll == IB_LINK_LAYER_ETHERNET && !mlx5_is_roce_enabled(mdev))
+		profile = &raw_eth_profile;
+	else
+		profile = &pf_profile;
+
+	return __mlx5_ib_add(dev, profile);
 }
 
 static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 5e826eb7e4fe..b983e385a8c5 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -1314,6 +1314,9 @@ int mlx5_ib_set_vf_link_state(struct ib_device *device, int vf,
 			      u8 port, int state);
 int mlx5_ib_get_vf_stats(struct ib_device *device, int vf,
 			 u8 port, struct ifla_vf_stats *stats);
+int mlx5_ib_get_vf_guid(struct ib_device *device, int vf, u8 port,
+			struct ifla_vf_guid *node_guid,
+			struct ifla_vf_guid *port_guid);
 int mlx5_ib_set_vf_guid(struct ib_device *device, int vf, u8 port,
 			u64 guid, int type);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ac0583ff280d..e5f438ab716c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -2019,6 +2019,15 @@ static int ipoib_set_vf_guid(struct net_device *dev, int vf, u64 guid, int type)
 	return ib_set_vf_guid(priv->ca, vf, priv->port, guid, type);
 }
 
+static int ipoib_get_vf_guid(struct net_device *dev, int vf,
+			     struct ifla_vf_guid *node_guid,
+			     struct ifla_vf_guid *port_guid)
+{
+	struct ipoib_dev_priv *priv = ipoib_priv(dev);
+
+	return ib_get_vf_guid(priv->ca, vf, priv->port, node_guid, port_guid);
+}
+
 static int ipoib_get_vf_stats(struct net_device *dev, int vf,
 			      struct ifla_vf_stats *vf_stats)
 {
@@ -2045,6 +2054,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
 	.ndo_set_vf_link_state	 = ipoib_set_vf_link_state,
 	.ndo_get_vf_config	 = ipoib_get_vf_config,
 	.ndo_get_vf_stats	 = ipoib_get_vf_stats,
+	.ndo_get_vf_guid	 = ipoib_get_vf_guid,
 	.ndo_set_vf_guid	 = ipoib_set_vf_guid,
 	.ndo_set_mac_address	 = ipoib_set_mac,
 	.ndo_get_stats64	 = ipoib_get_stats,