diff mbox series

[net-next,v3,5/6] devlink: Introduce controller number

Message ID 20200909045038.63181-6-parav@mellanox.com
State New
Headers show
Series devlink show controller number | expand

Commit Message

Parav Pandit Sept. 9, 2020, 4:50 a.m. UTC 
From: Parav Pandit <parav@nvidia.com>

A devlink port may be for a controller consist of PCI device.
A devlink instance holds ports of two types of controllers.
(1) controller discovered on same system where eswitch resides
This is the case where PCI PF/VF of a controller and devlink eswitch
instance both are located on a single system.
(2) controller located on external host system.
This is the case where a controller is located in one system and its
devlink eswitch ports are located in a different system.

When a devlink eswitch instance serves the devlink ports of both
controllers together, PCI PF/VF numbers may overlap.
Due to this a unique phys_port_name cannot be constructed.

For example in below such system controller-0 and controller-1, each has
PCI PF pf0 whose eswitch ports can be present in controller-0.
These results in phys_port_name as "pf0" for both.
Similar problem exists for VFs and upcoming Sub functions.

An example view of two controller systems:

             ---------------------------------------------------------
             |                                                       |
             |           --------- ---------         ------- ------- |
-----------  |           | vf(s) | | sf(s) |         |vf(s)| |sf(s)| |
| server  |  | -------   ----/---- ---/----- ------- ---/--- ---/--- |
| pci rc  |=== | pf0 |______/________/       | pf1 |___/_______/     |
| connect |  | -------                       -------                 |
-----------  |     | controller_num=1 (no eswitch)                   |
             ------|--------------------------------------------------
             (internal wire)
                   |
             ---------------------------------------------------------
             | devlink eswitch ports and reps                        |
             | ----------------------------------------------------- |
             | |ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 | ctrl-0 |ctrl-0 | |
             | |pf0    | pf0vfN | pf0sfN | pf1    | pf1vfN |pf1sfN | |
             | ----------------------------------------------------- |
             | |ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 | ctrl-1 |ctrl-1 | |
             | |pf1    | pf1vfN | pf1sfN | pf1    | pf1vfN |pf0sfN | |
             | ----------------------------------------------------- |
             |                                                       |
             |                                                       |
             |           --------- ---------         ------- ------- |
             |           | vf(s) | | sf(s) |         |vf(s)| |sf(s)| |
             | -------   ----/---- ---/----- ------- ---/--- ---/--- |
             | | pf0 |______/________/       | pf1 |___/_______/     |
             | -------                       -------                 |
             |                                                       |
             |  local controller_num=0 (eswitch)                     |
             ---------------------------------------------------------

An example devlink port for external controller with controller
number = 1 for a VF 1 of PF 0:

$ devlink port show pci/0000:06:00.0/2
pci/0000:06:00.0/2: type eth netdev ens2f0pf0vf1 flavour pcivf controller 1 pfnum 0 vfnum 1 external true splittable false
  function:
    hw_addr 00:00:00:00:00:00

$ devlink port show pci/0000:06:00.0/2 -jp
{
    "port": {
        "pci/0000:06:00.0/2": {
            "type": "eth",
            "netdev": "ens2f0pf0vf1",
            "flavour": "pcivf",
            "controller": 1,
            "pfnum": 0,
            "vfnum": 1,
            "external": true,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:00:00"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
---
Changelog:
v2->v3:
 - Updated diagram to get rid of controller 'A' and 'B'
 - Kept ports of single controller together in diagram
 - Updated diagram for pf1's VF and SF and its ports
v1->v2:
 - Added text diagram of multiple controllers
 - Updated example for a VF
 - Addressed comments from Jiri and Jakub
 - Moved controller number attribute to PCI port flavours
   This enables to better, hirerchical view with controller and its
    PF, VF numbers
 - Split 'external' and 'controller number' attributes as two
   different attributes
 - Merged mlx5_core driver to avoid compiliation break
---
 .../net/ethernet/mellanox/mlx5/core/en_rep.c  |  9 ++++++--
 include/net/devlink.h                         |  9 ++++++--
 include/uapi/linux/devlink.h                  |  1 +
 net/core/devlink.c                            | 23 +++++++++++--------
 4 files changed, 29 insertions(+), 13 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 5b3599caa007..135ee26881c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1210,11 +1210,13 @@  is_devlink_port_supported(const struct mlx5_core_dev *dev,
 static int register_devlink_port(struct mlx5_core_dev *dev,
 				 struct mlx5e_rep_priv *rpriv)
 {
+	struct mlx5_esw_offload *offloads = &dev->priv.eswitch->offloads;
 	struct devlink *devlink = priv_to_devlink(dev);
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct devlink_port_attrs attrs = {};
 	struct netdev_phys_item_id ppid = {};
 	unsigned int dl_port_index = 0;
+	u32 controller_num = 0;
 	bool external;
 	u16 pfnum;
 
@@ -1222,6 +1224,8 @@  static int register_devlink_port(struct mlx5_core_dev *dev,
 		return 0;
 
 	external = mlx5_core_is_ecpf_esw_manager(dev);
+	if (external)
+		controller_num = offloads->host_number + 1;
 	mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, rep->vport);
 	pfnum = PCI_FUNC(dev->pdev->devfn);
@@ -1234,11 +1238,12 @@  static int register_devlink_port(struct mlx5_core_dev *dev,
 	} else if (rep->vport == MLX5_VPORT_PF) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, pfnum, external);
+		devlink_port_attrs_pci_pf_set(&rpriv->dl_port, controller_num,
+					      pfnum, external);
 	} else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) {
 		memcpy(rpriv->dl_port.attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 		rpriv->dl_port.attrs.switch_id.id_len = ppid.id_len;
-		devlink_port_attrs_pci_vf_set(&rpriv->dl_port,
+		devlink_port_attrs_pci_vf_set(&rpriv->dl_port, controller_num,
 					      pfnum, rep->vport - 1, external);
 	}
 	return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index);
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 2dad8c9151f4..eaec0a8cc5ef 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -59,21 +59,25 @@  struct devlink_port_phys_attrs {
 
 /**
  * struct devlink_port_pci_pf_attrs - devlink port's PCI PF attributes
+ * @controller: Associated controller number
  * @pf: Associated PCI PF number for this port.
  * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_pf_attrs {
+	u32 controller;
 	u16 pf;
 	u8 external:1;
 };
 
 /**
  * struct devlink_port_pci_vf_attrs - devlink port's PCI VF attributes
+ * @controller: Associated controller number
  * @pf: Associated PCI PF number for this port.
  * @vf: Associated PCI VF for of the PCI PF for this port.
  * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_vf_attrs {
+	u32 controller;
 	u16 pf;
 	u16 vf;
 	u8 external:1;
@@ -1219,8 +1223,9 @@  void devlink_port_type_ib_set(struct devlink_port *devlink_port,
 void devlink_port_type_clear(struct devlink_port *devlink_port);
 void devlink_port_attrs_set(struct devlink_port *devlink_port,
 			    struct devlink_port_attrs *devlink_port_attrs);
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external);
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external);
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 40823ed7e05a..40d35145c879 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -459,6 +459,7 @@  enum devlink_attr {
 	DEVLINK_ATTR_PORT_SPLITTABLE,			/* u8 */
 
 	DEVLINK_ATTR_PORT_EXTERNAL,		/* u8 */
+	DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,	/* u32 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6f5f85372721..9cf5b118253b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -523,17 +523,18 @@  static int devlink_nl_port_attrs_put(struct sk_buff *msg,
 		return -EMSGSIZE;
 	switch (devlink_port->attrs.flavour) {
 	case DEVLINK_PORT_FLAVOUR_PCI_PF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_pf.pf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_pf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
 			return -EMSGSIZE;
 		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
 			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_VF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_vf.pf) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
-				attrs->pci_vf.vf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_vf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
 			return -EMSGSIZE;
 		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
 			return -EMSGSIZE;
@@ -7719,10 +7720,12 @@  EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
  *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bool external)
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
@@ -7731,7 +7734,7 @@  void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf, bo
 				       DEVLINK_PORT_FLAVOUR_PCI_PF);
 	if (ret)
 		return;
-
+	attrs->pci_pf.controller = controller;
 	attrs->pci_pf.pf = pf;
 	attrs->pci_pf.external = external;
 }
@@ -7741,11 +7744,12 @@  EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
  *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@vf: associated VF of a PF for the devlink port instance
  *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
@@ -7755,6 +7759,7 @@  void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_VF);
 	if (ret)
 		return;
+	attrs->pci_vf.controller = controller;
 	attrs->pci_vf.pf = pf;
 	attrs->pci_vf.vf = vf;
 	attrs->pci_vf.external = external;