From b8288837ef6bdaac331752b401f5ca3b59b37430 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:13 -0800
Subject: devlink: Introduce PCI SF port flavour and port attribute

A PCI sub-function (SF) represents a portion of the device similar
to PCI VF.

In an eswitch, PCI SF may have port which is normally represented
using a representor netdevice.
To have better visibility of eswitch port, its association with SF,
and its representor netdevice, introduce a PCI SF port flavour.

When devlink port flavour is PCI SF, fill up PCI SF attributes of the
port.

Extend port name creation using PCI PF and SF number scheme on best
effort basis, so that vendor drivers can skip defining their own
scheme.
This is done as cApfNSfM, where A, N and M are controller, PCI PF and
PCI SF number respectively.
This is similar to existing naming for PCI PF and PCI VF ports.

An example view of a PCI SF port:

$ devlink port show pci/0000:06:00.0/32768
pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:88:88 state active opstate attached

$ devlink port show pci/0000:06:00.0/32768 -jp
{
    "port": {
        "pci/0000:06:00.0/32768": {
            "type": "eth",
            "netdev": "ens2f0npf0sf88",
            "flavour": "pcisf",
            "controller": 0,
            "pfnum": 0,
            "sfnum": 88,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:88:88",
                "state": "active",
                "opstate": "attached"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/net/devlink.h        | 16 ++++++++++++++++
 include/uapi/linux/devlink.h |  5 +++++
 2 files changed, 21 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index f466819cc477..dc3bf8000082 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -93,6 +93,18 @@ struct devlink_port_pci_vf_attrs {
 	u8 external:1;
 };
 
+/**
+ * struct devlink_port_pci_sf_attrs - devlink port's PCI SF attributes
+ * @controller: Associated controller number
+ * @sf: Associated PCI SF for of the PCI PF for this port.
+ * @pf: Associated PCI PF number for this port.
+ */
+struct devlink_port_pci_sf_attrs {
+	u32 controller;
+	u32 sf;
+	u16 pf;
+};
+
 /**
  * struct devlink_port_attrs - devlink port object
  * @flavour: flavour of the port
@@ -103,6 +115,7 @@ struct devlink_port_pci_vf_attrs {
  * @phys: physical port attributes
  * @pci_pf: PCI PF port attributes
  * @pci_vf: PCI VF port attributes
+ * @pci_sf: PCI SF port attributes
  */
 struct devlink_port_attrs {
 	u8 split:1,
@@ -114,6 +127,7 @@ struct devlink_port_attrs {
 		struct devlink_port_phys_attrs phys;
 		struct devlink_port_pci_pf_attrs pci_pf;
 		struct devlink_port_pci_vf_attrs pci_vf;
+		struct devlink_port_pci_sf_attrs pci_sf;
 	};
 };
 
@@ -1404,6 +1418,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro
 				   u16 pf, bool external);
 void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external);
+void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
+				   u32 controller, u16 pf, u32 sf);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index cf89c318f2ac..1a241b09a7f8 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -200,6 +200,10 @@ enum devlink_port_flavour {
 	DEVLINK_PORT_FLAVOUR_UNUSED, /* Port which exists in the switch, but
 				      * is not used in any way.
 				      */
+	DEVLINK_PORT_FLAVOUR_PCI_SF, /* Represents eswitch port
+				      * for the PCI SF. It is an internal
+				      * port that faces the PCI SF.
+				      */
 };
 
 enum devlink_param_cmode {
@@ -529,6 +533,7 @@ enum devlink_attr {
 	DEVLINK_ATTR_RELOAD_ACTION_INFO,        /* nested */
 	DEVLINK_ATTR_RELOAD_ACTION_STATS,       /* nested */
 
+	DEVLINK_ATTR_PORT_PCI_SF_NUMBER,	/* u32 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
-- 
cgit v1.2.3


From cd76dcd68d96aa5bbc63b7ef25a87a1dbea3d73c Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:14 -0800
Subject: devlink: Support add and delete devlink port

Extended devlink interface for the user to add and delete a port.
Extend devlink to connect user requests to driver to add/delete
a port in the device.

Driver routines are invoked without holding devlink instance lock.
This enables driver to perform several devlink objects registration,
unregistration such as (port, health reporter, resource etc) by using
existing devlink APIs.
This also helps to uniformly use the code for port unregistration
during driver unload and during port deletion initiated by user.

Examples of add, show and delete commands:
$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev

$ devlink port show
pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false

$ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ devlink port show pci/0000:06:00.0/32768
pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ udevadm test-builtin net_id /sys/class/net/eth6
Load module index
Parsed configuration file /usr/lib/systemd/network/99-default.link
Created link configuration context.
Using default interface naming scheme 'v245'.
ID_NET_NAMING_SCHEME=v245
ID_NET_NAME_PATH=enp6s0f0npf0sf88
ID_NET_NAME_SLOT=ens2f0npf0sf88
Unload module index
Unloaded link configuration context.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/net/devlink.h |  52 ++++++++++++++++++++++
 net/core/devlink.c    | 121 ++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 173 insertions(+)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index dc3bf8000082..d8edd9a10907 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -152,6 +152,17 @@ struct devlink_port {
 	struct mutex reporters_lock; /* Protects reporter_list */
 };
 
+struct devlink_port_new_attrs {
+	enum devlink_port_flavour flavour;
+	unsigned int port_index;
+	u32 controller;
+	u32 sfnum;
+	u16 pfnum;
+	u8 port_index_valid:1,
+	   controller_valid:1,
+	   sfnum_valid:1;
+};
+
 struct devlink_sb_pool_info {
 	enum devlink_sb_pool_type pool_type;
 	u32 size;
@@ -1362,6 +1373,47 @@ struct devlink_ops {
 	int (*port_function_hw_addr_set)(struct devlink *devlink, struct devlink_port *port,
 					 const u8 *hw_addr, int hw_addr_len,
 					 struct netlink_ext_ack *extack);
+	/**
+	 * port_new() - Add a new port function of a specified flavor
+	 * @devlink: Devlink instance
+	 * @attrs: attributes of the new port
+	 * @extack: extack for reporting error messages
+	 * @new_port_index: index of the new port
+	 *
+	 * Devlink core will call this device driver function upon user request
+	 * to create a new port function of a specified flavor and optional
+	 * attributes
+	 *
+	 * Notes:
+	 *	- Called without devlink instance lock being held. Drivers must
+	 *	  implement own means of synchronization
+	 *	- On success, drivers must register a port with devlink core
+	 *
+	 * Return: 0 on success, negative value otherwise.
+	 */
+	int (*port_new)(struct devlink *devlink,
+			const struct devlink_port_new_attrs *attrs,
+			struct netlink_ext_ack *extack,
+			unsigned int *new_port_index);
+	/**
+	 * port_del() - Delete a port function
+	 * @devlink: Devlink instance
+	 * @port_index: port function index to delete
+	 * @extack: extack for reporting error messages
+	 *
+	 * Devlink core will call this device driver function upon user request
+	 * to delete a previously created port function
+	 *
+	 * Notes:
+	 *	- Called without devlink instance lock being held. Drivers must
+	 *	  implement own means of synchronization
+	 *	- On success, drivers must unregister the corresponding devlink
+	 *	  port
+	 *
+	 * Return: 0 on success, negative value otherwise.
+	 */
+	int (*port_del)(struct devlink *devlink, unsigned int port_index,
+			struct netlink_ext_ack *extack);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 4cbc02fb602d..541b5f549274 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -1147,6 +1147,111 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb,
 	return devlink_port_unsplit(devlink, port_index, info->extack);
 }
 
+static int devlink_port_new_notifiy(struct devlink *devlink,
+				    unsigned int port_index,
+				    struct genl_info *info)
+{
+	struct devlink_port *devlink_port;
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	mutex_lock(&devlink->lock);
+	devlink_port = devlink_port_get_by_index(devlink, port_index);
+	if (!devlink_port) {
+		err = -ENODEV;
+		goto out;
+	}
+
+	err = devlink_nl_port_fill(msg, devlink, devlink_port,
+				   DEVLINK_CMD_NEW, info->snd_portid,
+				   info->snd_seq, 0, NULL);
+	if (err)
+		goto out;
+
+	err = genlmsg_reply(msg, info);
+	mutex_unlock(&devlink->lock);
+	return err;
+
+out:
+	mutex_unlock(&devlink->lock);
+	nlmsg_free(msg);
+	return err;
+}
+
+static int devlink_nl_cmd_port_new_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink_port_new_attrs new_attrs = {};
+	struct devlink *devlink = info->user_ptr[0];
+	unsigned int new_port_index;
+	int err;
+
+	if (!devlink->ops->port_new || !devlink->ops->port_del)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[DEVLINK_ATTR_PORT_FLAVOUR] ||
+	    !info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]) {
+		NL_SET_ERR_MSG_MOD(extack, "Port flavour or PCI PF are not specified");
+		return -EINVAL;
+	}
+	new_attrs.flavour = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_FLAVOUR]);
+	new_attrs.pfnum =
+		nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_PCI_PF_NUMBER]);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		/* Port index of the new port being created by driver. */
+		new_attrs.port_index =
+			nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+		new_attrs.port_index_valid = true;
+	}
+	if (info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]) {
+		new_attrs.controller =
+			nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER]);
+		new_attrs.controller_valid = true;
+	}
+	if (new_attrs.flavour == DEVLINK_PORT_FLAVOUR_PCI_SF &&
+	    info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]) {
+		new_attrs.sfnum = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_PCI_SF_NUMBER]);
+		new_attrs.sfnum_valid = true;
+	}
+
+	err = devlink->ops->port_new(devlink, &new_attrs, extack,
+				     &new_port_index);
+	if (err)
+		return err;
+
+	err = devlink_port_new_notifiy(devlink, new_port_index, info);
+	if (err && err != -ENODEV) {
+		/* Fail to send the response; destroy newly created port. */
+		devlink->ops->port_del(devlink, new_port_index, extack);
+	}
+	return err;
+}
+
+static int devlink_nl_cmd_port_del_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct netlink_ext_ack *extack = info->extack;
+	struct devlink *devlink = info->user_ptr[0];
+	unsigned int port_index;
+
+	if (!devlink->ops->port_del)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		NL_SET_ERR_MSG_MOD(extack, "Port index is not specified");
+		return -EINVAL;
+	}
+	port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+	return devlink->ops->port_del(devlink, port_index, extack);
+}
+
 static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink,
 			      struct devlink_sb *devlink_sb,
 			      enum devlink_command cmd, u32 portid,
@@ -7605,6 +7710,10 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
 							DEVLINK_RELOAD_ACTION_MAX),
 	[DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK),
+	[DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 },
+	[DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 },
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7644,6 +7753,18 @@ static const struct genl_small_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NO_LOCK,
 	},
+	{
+		.cmd = DEVLINK_CMD_PORT_NEW,
+		.doit = devlink_nl_cmd_port_new_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NO_LOCK,
+	},
+	{
+		.cmd = DEVLINK_CMD_PORT_DEL,
+		.doit = devlink_nl_cmd_port_del_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NO_LOCK,
+	},
 	{
 		.cmd = DEVLINK_CMD_SB_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-- 
cgit v1.2.3


From a556dded9c23c51c82654f1ebe389cbc0bc22057 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:15 -0800
Subject: devlink: Support get and set state of port function

devlink port function can be in active or inactive state.
Allow users to get and set port function's state.

When the port function it activated, its operational state may change
after a while when the device is created and driver binds to it.
Similarly on deactivation flow.

To clearly describe the state of the port function and its device's
operational state in the host system, define state and opstate
attributes.

Example of a PCI SF port which supports a port function:

$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev

$ devlink port show
pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false

$ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ devlink port show pci/0000:06:00.0/32768
pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:88:88 state inactive opstate detached

$ devlink port function set pci/0000:06:00.0/32768 hw_addr 00:00:00:00:88:88 state active

$ devlink port show pci/0000:06:00.0/32768 -jp
{
    "port": {
        "pci/0000:06:00.0/32768": {
            "type": "eth",
            "netdev": "ens2f0npf0sf88",
            "flavour": "pcisf",
            "controller": 0,
            "pfnum": 0,
            "sfnum": 88,
            "external": false,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:88:88",
                "state": "active",
                "opstate": "attached"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/net/devlink.h        | 32 ++++++++++++++++
 include/uapi/linux/devlink.h | 20 ++++++++++
 net/core/devlink.c           | 90 +++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 141 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/devlink.h b/include/net/devlink.h
index d8edd9a10907..691ee76ca548 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1414,6 +1414,38 @@ struct devlink_ops {
 	 */
 	int (*port_del)(struct devlink *devlink, unsigned int port_index,
 			struct netlink_ext_ack *extack);
+	/**
+	 * port_fn_state_get() - Get the state of a port function
+	 * @devlink: Devlink instance
+	 * @port: The devlink port
+	 * @state: Admin configured state
+	 * @opstate: Current operational state
+	 * @extack: extack for reporting error messages
+	 *
+	 * Reports the admin and operational state of a devlink port function
+	 *
+	 * Return: 0 on success, negative value otherwise.
+	 */
+	int (*port_fn_state_get)(struct devlink *devlink,
+				 struct devlink_port *port,
+				 enum devlink_port_fn_state *state,
+				 enum devlink_port_fn_opstate *opstate,
+				 struct netlink_ext_ack *extack);
+	/**
+	 * port_fn_state_set() - Set the admin state of a port function
+	 * @devlink: Devlink instance
+	 * @port: The devlink port
+	 * @state: Admin state
+	 * @extack: extack for reporting error messages
+	 *
+	 * Set the admin state of a devlink port function
+	 *
+	 * Return: 0 on success, negative value otherwise.
+	 */
+	int (*port_fn_state_set)(struct devlink *devlink,
+				 struct devlink_port *port,
+				 enum devlink_port_fn_state state,
+				 struct netlink_ext_ack *extack);
 };
 
 static inline void *devlink_priv(struct devlink *devlink)
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 1a241b09a7f8..f6008b2fa60f 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -583,9 +583,29 @@ enum devlink_resource_unit {
 enum devlink_port_function_attr {
 	DEVLINK_PORT_FUNCTION_ATTR_UNSPEC,
 	DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR,	/* binary */
+	DEVLINK_PORT_FN_ATTR_STATE,	/* u8 */
+	DEVLINK_PORT_FN_ATTR_OPSTATE,	/* u8 */
 
 	__DEVLINK_PORT_FUNCTION_ATTR_MAX,
 	DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1
 };
 
+enum devlink_port_fn_state {
+	DEVLINK_PORT_FN_STATE_INACTIVE,
+	DEVLINK_PORT_FN_STATE_ACTIVE,
+};
+
+/**
+ * enum devlink_port_fn_opstate - indicates operational state of the function
+ * @DEVLINK_PORT_FN_OPSTATE_ATTACHED: Driver is attached to the function.
+ * For graceful tear down of the function, after inactivation of the
+ * function, user should wait for operational state to turn DETACHED.
+ * @DEVLINK_PORT_FN_OPSTATE_DETACHED: Driver is detached from the function.
+ * It is safe to delete the port.
+ */
+enum devlink_port_fn_opstate {
+	DEVLINK_PORT_FN_OPSTATE_DETACHED,
+	DEVLINK_PORT_FN_OPSTATE_ATTACHED,
+};
+
 #endif /* _UAPI_LINUX_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 541b5f549274..9f1be69bd5f8 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -87,6 +87,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
+	[DEVLINK_PORT_FN_ATTR_STATE] =
+		NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
+				 DEVLINK_PORT_FN_STATE_ACTIVE),
 };
 
 static LIST_HEAD(devlink_list);
@@ -746,6 +749,58 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *
 	return 0;
 }
 
+static bool
+devlink_port_fn_state_valid(enum devlink_port_fn_state state)
+{
+	return state == DEVLINK_PORT_FN_STATE_INACTIVE ||
+	       state == DEVLINK_PORT_FN_STATE_ACTIVE;
+}
+
+static bool
+devlink_port_fn_opstate_valid(enum devlink_port_fn_opstate opstate)
+{
+	return opstate == DEVLINK_PORT_FN_OPSTATE_DETACHED ||
+	       opstate == DEVLINK_PORT_FN_OPSTATE_ATTACHED;
+}
+
+static int
+devlink_port_fn_state_fill(struct devlink *devlink,
+			   const struct devlink_ops *ops,
+			   struct devlink_port *port, struct sk_buff *msg,
+			   struct netlink_ext_ack *extack,
+			   bool *msg_updated)
+{
+	enum devlink_port_fn_opstate opstate;
+	enum devlink_port_fn_state state;
+	int err;
+
+	if (!ops->port_fn_state_get)
+		return 0;
+
+	err = ops->port_fn_state_get(devlink, port, &state, &opstate, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+	if (!devlink_port_fn_state_valid(state)) {
+		WARN_ON_ONCE(1);
+		NL_SET_ERR_MSG_MOD(extack, "Invalid state read from driver");
+		return -EINVAL;
+	}
+	if (!devlink_port_fn_opstate_valid(opstate)) {
+		WARN_ON_ONCE(1);
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid operational state read from driver");
+		return -EINVAL;
+	}
+	if (nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_STATE, state) ||
+	    nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_OPSTATE, opstate))
+		return -EMSGSIZE;
+	*msg_updated = true;
+	return 0;
+}
+
 static int
 devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
 				   struct netlink_ext_ack *extack)
@@ -763,6 +818,11 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por
 	ops = devlink->ops;
 	err = devlink_port_fn_hw_addr_fill(devlink, ops, port, msg,
 					   extack, &msg_updated);
+	if (err)
+		goto out;
+	err = devlink_port_fn_state_fill(devlink, ops, port, msg, extack,
+					 &msg_updated);
+out:
 	if (err || !msg_updated)
 		nla_nest_cancel(msg, function_attr);
 	else
@@ -1028,6 +1088,24 @@ devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port *
 	return ops->port_function_hw_addr_set(devlink, port, hw_addr, hw_addr_len, extack);
 }
 
+static int devlink_port_fn_state_set(struct devlink *devlink,
+				     struct devlink_port *port,
+				     const struct nlattr *attr,
+				     struct netlink_ext_ack *extack)
+{
+	enum devlink_port_fn_state state;
+	const struct devlink_ops *ops;
+
+	state = nla_get_u8(attr);
+	ops = devlink->ops;
+	if (!ops->port_fn_state_set) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Function does not support state setting");
+		return -EOPNOTSUPP;
+	}
+	return ops->port_fn_state_set(devlink, port, state, extack);
+}
+
 static int
 devlink_port_function_set(struct devlink *devlink, struct devlink_port *port,
 			  const struct nlattr *attr, struct netlink_ext_ack *extack)
@@ -1043,8 +1121,18 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port,
 	}
 
 	attr = tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR];
-	if (attr)
+	if (attr) {
 		err = devlink_port_function_hw_addr_set(devlink, port, attr, extack);
+		if (err)
+			return err;
+	}
+	/* Keep this as the last function attribute set, so that when
+	 * multiple port function attributes are set along with state,
+	 * Those can be applied first before activating the state.
+	 */
+	attr = tb[DEVLINK_PORT_FN_ATTR_STATE];
+	if (attr)
+		err = devlink_port_fn_state_set(devlink, port, attr, extack);
 
 	if (!err)
 		devlink_port_notify(port, DEVLINK_CMD_PORT_NEW);
-- 
cgit v1.2.3


From f3196bb0f14c0ffb5089c15668bda196c98d3900 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:16 -0800
Subject: net/mlx5: Introduce vhca state event notifier

vhca state events indicates change in the state of the vhca that may
occur due to a SF allocation, deallocation or enabling/disabling the
SF HCA.

Introduce vhca state event handler which will be used by SF devlink
port manager and SF hardware id allocator in subsequent patches
to act on the event.

This enables single entity to subscribe, query and rearm the event
for a function.

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |   9 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/events.c   |   7 +
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  16 ++
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   2 +
 .../mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h    |  82 +++++++++
 drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h    |  45 +++++
 .../ethernet/mellanox/mlx5/core/sf/vhca_event.c    | 189 +++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/sf/vhca_event.h    |  57 +++++++
 include/linux/mlx5/driver.h                        |   4 +
 12 files changed, 422 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 6e4d7bb7fea2..d6c48582e7a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -203,3 +203,12 @@ config MLX5_SW_STEERING
 	default y
 	help
 	Build support for software-managed steering in the NIC.
+
+config MLX5_SF
+	bool "Mellanox Technologies subfunction device support using auxiliary device"
+	depends on MLX5_CORE && MLX5_CORE_EN
+	default n
+	help
+	Build support for subfuction device in the NIC. A Mellanox subfunction
+	device can support RDMA, netdevice and vdpa device.
+	It is similar to a SRIOV VF but it doesn't require SRIOV support.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 134bd038ae8a..22ef2ebbee96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -86,3 +86,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
 					steering/dr_ste_v0.o \
 					steering/dr_cmd.o steering/dr_fw.o \
 					steering/dr_action.o steering/fs_dr.o
+#
+# SF device
+#
+mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 50c7b9ee80c3..47dcc3ac2cf0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -464,6 +464,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_ALLOC_MEMIC:
 	case MLX5_CMD_OP_MODIFY_XRQ:
 	case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
+	case MLX5_CMD_OP_QUERY_VHCA_STATE:
+	case MLX5_CMD_OP_MODIFY_VHCA_STATE:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
 		return -EIO;
@@ -657,6 +659,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(DESTROY_UMEM);
 	MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR);
 	MLX5_COMMAND_STR_CASE(MODIFY_XRQ);
+	MLX5_COMMAND_STR_CASE(QUERY_VHCA_STATE);
+	MLX5_COMMAND_STR_CASE(MODIFY_VHCA_STATE);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index fc0afa03d407..421febebc658 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -595,6 +595,9 @@ static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
 		async_event_mask |=
 			(1ull << MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED);
 
+	if (MLX5_CAP_GEN_MAX(dev, vhca_state))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_VHCA_STATE_CHANGE);
+
 	mask[0] = async_event_mask;
 
 	if (MLX5_CAP_GEN(dev, event_cap))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index 3ce17c3d7a00..5523d218e5fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -110,6 +110,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_CMD";
 	case MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED:
 		return "MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED";
+	case MLX5_EVENT_TYPE_VHCA_STATE_CHANGE:
+		return "MLX5_EVENT_TYPE_VHCA_STATE_CHANGE";
 	case MLX5_EVENT_TYPE_PAGE_REQUEST:
 		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
 	case MLX5_EVENT_TYPE_PAGE_FAULT:
@@ -403,3 +405,8 @@ int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, voi
 {
 	return atomic_notifier_call_chain(&events->nh, event, data);
 }
+
+void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work)
+{
+	queue_work(dev->priv.events->wq, work);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ca6f2fc39ea0..b16f57befe52 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -73,6 +73,7 @@
 #include "ecpf.h"
 #include "lib/hv_vhca.h"
 #include "diag/rsc_dump.h"
+#include "sf/vhca_event.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -567,6 +568,8 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN_MAX(dev, mkey_by_name))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, mkey_by_name, 1);
 
+	mlx5_vhca_state_cap_handle(dev, set_hca_cap);
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
@@ -884,6 +887,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_eswitch_cleanup;
 	}
 
+	err = mlx5_vhca_event_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to init vhca event notifier %d\n", err);
+		goto err_fpga_cleanup;
+	}
+
 	dev->dm = mlx5_dm_create(dev);
 	if (IS_ERR(dev->dm))
 		mlx5_core_warn(dev, "Failed to init device memory%d\n", err);
@@ -894,6 +903,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	return 0;
 
+err_fpga_cleanup:
+	mlx5_fpga_cleanup(dev);
 err_eswitch_cleanup:
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 err_sriov_cleanup:
@@ -925,6 +936,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_dm_cleanup(dev);
+	mlx5_vhca_event_cleanup(dev);
 	mlx5_fpga_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_sriov_cleanup(dev);
@@ -1129,6 +1141,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_sriov;
 	}
 
+	mlx5_vhca_event_start(dev);
+
 	err = mlx5_ec_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init embedded CPU\n");
@@ -1146,6 +1160,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 err_sriov:
 	mlx5_ec_cleanup(dev);
 err_ec:
+	mlx5_vhca_event_stop(dev);
 	mlx5_cleanup_fs(dev);
 err_fs:
 	mlx5_accel_tls_cleanup(dev);
@@ -1173,6 +1188,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 {
 	mlx5_sriov_detach(dev);
 	mlx5_ec_cleanup(dev);
+	mlx5_vhca_event_stop(dev);
 	mlx5_cleanup_fs(dev);
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_accel_tls_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 0a0302ce7144..a33b7496d748 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -259,4 +259,6 @@ void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state);
 
 void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup);
 int mlx5_load_one(struct mlx5_core_dev *dev, bool boot);
+
+void mlx5_events_work_enqueue(struct mlx5_core_dev *dev, struct work_struct *work);
 #endif /* __MLX5_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
new file mode 100644
index 000000000000..1daf5a122ba3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_IFC_VHCA_EVENT_H__
+#define __MLX5_IFC_VHCA_EVENT_H__
+
+enum mlx5_ifc_vhca_state {
+	MLX5_VHCA_STATE_INVALID = 0x0,
+	MLX5_VHCA_STATE_ALLOCATED = 0x1,
+	MLX5_VHCA_STATE_ACTIVE = 0x2,
+	MLX5_VHCA_STATE_IN_USE = 0x3,
+	MLX5_VHCA_STATE_TEARDOWN_REQUEST = 0x4,
+};
+
+struct mlx5_ifc_vhca_state_context_bits {
+	u8         arm_change_event[0x1];
+	u8         reserved_at_1[0xb];
+	u8         vhca_state[0x4];
+	u8         reserved_at_10[0x10];
+
+	u8         sw_function_id[0x20];
+
+	u8         reserved_at_40[0x80];
+};
+
+struct mlx5_ifc_query_vhca_state_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_vhca_state_context_bits vhca_state_context;
+};
+
+struct mlx5_ifc_query_vhca_state_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_vhca_state_field_select_bits {
+	u8         reserved_at_0[0x1e];
+	u8         sw_function_id[0x1];
+	u8         arm_change_event[0x1];
+};
+
+struct mlx5_ifc_modify_vhca_state_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_modify_vhca_state_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         embedded_cpu_function[0x1];
+	u8         reserved_at_41[0xf];
+	u8         function_id[0x10];
+
+	struct mlx5_ifc_vhca_state_field_select_bits vhca_state_field_select;
+
+	struct mlx5_ifc_vhca_state_context_bits vhca_state_context;
+};
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
new file mode 100644
index 000000000000..623191679b49
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_H__
+#define __MLX5_SF_H__
+
+#include <linux/mlx5/driver.h>
+
+static inline u16 mlx5_sf_start_function_id(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, sf_base_id);
+}
+
+#ifdef CONFIG_MLX5_SF
+
+static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, sf);
+}
+
+static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
+{
+	if (!mlx5_sf_supported(dev))
+		return 0;
+	if (MLX5_CAP_GEN(dev, max_num_sf))
+		return MLX5_CAP_GEN(dev, max_num_sf);
+	else
+		return 1 << MLX5_CAP_GEN(dev, log_max_sf);
+}
+
+#else
+
+static inline bool mlx5_sf_supported(const struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
new file mode 100644
index 000000000000..af2f2dd9db25
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_ifc_vhca_event.h"
+#include "mlx5_core.h"
+#include "vhca_event.h"
+#include "ecpf.h"
+
+struct mlx5_vhca_state_notifier {
+	struct mlx5_core_dev *dev;
+	struct mlx5_nb nb;
+	struct blocking_notifier_head n_head;
+};
+
+struct mlx5_vhca_event_work {
+	struct work_struct work;
+	struct mlx5_vhca_state_notifier *notifier;
+	struct mlx5_vhca_state_event event;
+};
+
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
+			      bool ecpu, u32 *out, u32 outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {};
+
+	MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE);
+	MLX5_SET(query_vhca_state_in, in, function_id, function_id);
+	MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
+				      bool ecpu, u32 *in, u32 inlen)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
+
+	MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
+	MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
+	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+
+	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+}
+
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
+
+	MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
+	MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
+	MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+	MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1);
+	MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id);
+
+	return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out);
+}
+
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
+
+	MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1);
+	MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1);
+
+	return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in));
+}
+
+static void
+mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event *event)
+{
+	u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
+	int err;
+
+	err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out));
+	if (err)
+		return;
+
+	event->sw_function_id = MLX5_GET(query_vhca_state_out, out,
+					 vhca_state_context.sw_function_id);
+	event->new_vhca_state = MLX5_GET(query_vhca_state_out, out,
+					 vhca_state_context.vhca_state);
+
+	mlx5_vhca_event_arm(dev, event->function_id, event->ecpu);
+
+	blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
+}
+
+static void mlx5_vhca_state_work_handler(struct work_struct *_work)
+{
+	struct mlx5_vhca_event_work *work = container_of(_work, struct mlx5_vhca_event_work, work);
+	struct mlx5_vhca_state_notifier *notifier = work->notifier;
+	struct mlx5_core_dev *dev = notifier->dev;
+
+	mlx5_vhca_event_notify(dev, &work->event);
+}
+
+static int
+mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_vhca_state_notifier *notifier =
+				mlx5_nb_cof(nb, struct mlx5_vhca_state_notifier, nb);
+	struct mlx5_vhca_event_work *work;
+	struct mlx5_eqe *eqe = data;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return NOTIFY_DONE;
+	INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
+	work->notifier = notifier;
+	work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
+	work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function);
+	mlx5_events_work_enqueue(notifier->dev, &work->work);
+	return NOTIFY_OK;
+}
+
+void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
+{
+	if (!mlx5_vhca_event_supported(dev))
+		return;
+
+	MLX5_SET(cmd_hca_cap, set_hca_cap, vhca_state, 1);
+	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_allocated, 1);
+	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_active, 1);
+	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_in_use, 1);
+	MLX5_SET(cmd_hca_cap, set_hca_cap, event_on_vhca_state_teardown_request, 1);
+}
+
+int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_vhca_state_notifier *notifier;
+
+	if (!mlx5_vhca_event_supported(dev))
+		return 0;
+
+	notifier = kzalloc(sizeof(*notifier), GFP_KERNEL);
+	if (!notifier)
+		return -ENOMEM;
+
+	dev->priv.vhca_state_notifier = notifier;
+	notifier->dev = dev;
+	BLOCKING_INIT_NOTIFIER_HEAD(&notifier->n_head);
+	MLX5_NB_INIT(&notifier->nb, mlx5_vhca_state_change_notifier, VHCA_STATE_CHANGE);
+	return 0;
+}
+
+void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
+{
+	if (!mlx5_vhca_event_supported(dev))
+		return;
+
+	kfree(dev->priv.vhca_state_notifier);
+	dev->priv.vhca_state_notifier = NULL;
+}
+
+void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
+{
+	struct mlx5_vhca_state_notifier *notifier;
+
+	if (!dev->priv.vhca_state_notifier)
+		return;
+
+	notifier = dev->priv.vhca_state_notifier;
+	mlx5_eq_notifier_register(dev, &notifier->nb);
+}
+
+void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
+{
+	struct mlx5_vhca_state_notifier *notifier;
+
+	if (!dev->priv.vhca_state_notifier)
+		return;
+
+	notifier = dev->priv.vhca_state_notifier;
+	mlx5_eq_notifier_unregister(dev, &notifier->nb);
+}
+
+int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	if (!dev->priv.vhca_state_notifier)
+		return -EOPNOTSUPP;
+	return blocking_notifier_chain_register(&dev->priv.vhca_state_notifier->n_head, nb);
+}
+
+void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&dev->priv.vhca_state_notifier->n_head, nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
new file mode 100644
index 000000000000..1fe1ec6f4d4b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_VHCA_EVENT_H__
+#define __MLX5_VHCA_EVENT_H__
+
+#ifdef CONFIG_MLX5_SF
+
+struct mlx5_vhca_state_event {
+	u16 function_id;
+	u16 sw_function_id;
+	u8 new_vhca_state;
+	bool ecpu;
+};
+
+static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN_MAX(dev, vhca_state);
+}
+
+void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap);
+int mlx5_vhca_event_init(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_start(struct mlx5_core_dev *dev);
+void mlx5_vhca_event_stop(struct mlx5_core_dev *dev);
+int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
+void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id);
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu);
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
+			      bool ecpu, u32 *out, u32 outlen);
+#else
+
+static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
+{
+}
+
+static inline int mlx5_vhca_event_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
+static inline void mlx5_vhca_event_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_vhca_event_start(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_vhca_event_stop(struct mlx5_core_dev *dev)
+{
+}
+
+#endif
+
+#endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f93bfe7473aa..ffba0786051e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -507,6 +507,7 @@ struct mlx5_devcom;
 struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
+struct mlx5_vhca_state_notifier;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -603,6 +604,9 @@ struct mlx5_priv {
 
 	struct mlx5_bfreg_data		bfregs;
 	struct mlx5_uars_page	       *uar;
+#ifdef CONFIG_MLX5_SF
+	struct mlx5_vhca_state_notifier *vhca_state_notifier;
+#endif
 };
 
 enum mlx5_device_state {
-- 
cgit v1.2.3


From 90d010b8634b89a97ca3b7aa6a88fd566fc77717 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:17 -0800
Subject: net/mlx5: SF, Add auxiliary device support

Introduce API to add and delete an auxiliary device for an SF.
Each SF has its own dedicated window in the PCI BAR 2.

SF device is similar to PCI PF and VF that supports multiple class of
devices such as net, rdma and vdpa.

SF device will be added or removed in subsequent patch during SF
devlink port function state change command.

A subfunction device exposes user supplied subfunction number which will
be further used by systemd/udev to have deterministic name for its
netdevice and rdma device.

An mlx5 subfunction auxiliary device example:

$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev

$ devlink port show
pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false

$ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
pci/0000:08:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ devlink port show ens2f0npf0sf88
pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:88:88 state inactive opstate detached

$ devlink port function set ens2f0npf0sf88 hw_addr 00:00:00:00:88:88 state active

On activation,

$ ls -l /sys/bus/auxiliary/devices/
mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4

$ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum
88

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../device_drivers/ethernet/mellanox/mlx5.rst      |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   4 +
 .../net/ethernet/mellanox/mlx5/core/sf/dev/dev.c   | 265 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/sf/dev/dev.h   |  35 +++
 include/linux/mlx5/driver.h                        |   2 +
 6 files changed, 312 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h

(limited to 'include')

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
index e9b65035cd47..a5eb22793bb9 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst
@@ -97,6 +97,11 @@ Enabling the driver and kconfig options
 
 |   Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support.
 
+**CONFIG_MLX5_SF=(y/n)**
+
+|   Build support for subfunction.
+|   Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option
+|   will enable support for creating subfunction devices.
 
 **External options** ( Choose if the corresponding mlx5 feature is required )
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 22ef2ebbee96..f5b2e9101348 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -89,4 +89,4 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
 #
 # SF device
 #
-mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o
+mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index b16f57befe52..26b5502712a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -74,6 +74,7 @@
 #include "lib/hv_vhca.h"
 #include "diag/rsc_dump.h"
 #include "sf/vhca_event.h"
+#include "sf/dev/dev.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -1155,6 +1156,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_sriov;
 	}
 
+	mlx5_sf_dev_table_create(dev);
+
 	return 0;
 
 err_sriov:
@@ -1186,6 +1189,7 @@ err_irq_table:
 
 static void mlx5_unload(struct mlx5_core_dev *dev)
 {
+	mlx5_sf_dev_table_destroy(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_ec_cleanup(dev);
 	mlx5_vhca_event_stop(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
new file mode 100644
index 000000000000..4a8eeb7c853e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_core.h"
+#include "dev.h"
+#include "sf/vhca_event.h"
+#include "sf/sf.h"
+#include "sf/mlx5_ifc_vhca_event.h"
+#include "ecpf.h"
+
+struct mlx5_sf_dev_table {
+	struct xarray devices;
+	unsigned int max_sfs;
+	phys_addr_t base_address;
+	u64 sf_bar_length;
+	struct notifier_block nb;
+	struct mlx5_core_dev *dev;
+};
+
+static bool mlx5_sf_dev_supported(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, sf) && mlx5_vhca_event_supported(dev);
+}
+
+static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev);
+	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", sf_dev->sfnum);
+}
+static DEVICE_ATTR_RO(sfnum);
+
+static struct attribute *sf_device_attrs[] = {
+	&dev_attr_sfnum.attr,
+	NULL,
+};
+
+static const struct attribute_group sf_attr_group = {
+	.attrs = sf_device_attrs,
+};
+
+static const struct attribute_group *sf_attr_groups[2] = {
+	&sf_attr_group,
+	NULL
+};
+
+static void mlx5_sf_dev_release(struct device *device)
+{
+	struct auxiliary_device *adev = container_of(device, struct auxiliary_device, dev);
+	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+	mlx5_adev_idx_free(adev->id);
+	kfree(sf_dev);
+}
+
+static void mlx5_sf_dev_remove(struct mlx5_sf_dev *sf_dev)
+{
+	auxiliary_device_delete(&sf_dev->adev);
+	auxiliary_device_uninit(&sf_dev->adev);
+}
+
+static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u32 sfnum)
+{
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+	struct mlx5_sf_dev *sf_dev;
+	struct pci_dev *pdev;
+	int err;
+	int id;
+
+	id = mlx5_adev_idx_alloc();
+	if (id < 0) {
+		err = id;
+		goto add_err;
+	}
+
+	sf_dev = kzalloc(sizeof(*sf_dev), GFP_KERNEL);
+	if (!sf_dev) {
+		mlx5_adev_idx_free(id);
+		err = -ENOMEM;
+		goto add_err;
+	}
+	pdev = dev->pdev;
+	sf_dev->adev.id = id;
+	sf_dev->adev.name = MLX5_SF_DEV_ID_NAME;
+	sf_dev->adev.dev.release = mlx5_sf_dev_release;
+	sf_dev->adev.dev.parent = &pdev->dev;
+	sf_dev->adev.dev.groups = sf_attr_groups;
+	sf_dev->sfnum = sfnum;
+	sf_dev->parent_mdev = dev;
+
+	if (!table->max_sfs) {
+		mlx5_adev_idx_free(id);
+		kfree(sf_dev);
+		err = -EOPNOTSUPP;
+		goto add_err;
+	}
+	sf_dev->bar_base_addr = table->base_address + (sf_index * table->sf_bar_length);
+
+	err = auxiliary_device_init(&sf_dev->adev);
+	if (err) {
+		mlx5_adev_idx_free(id);
+		kfree(sf_dev);
+		goto add_err;
+	}
+
+	err = auxiliary_device_add(&sf_dev->adev);
+	if (err) {
+		put_device(&sf_dev->adev.dev);
+		goto add_err;
+	}
+
+	err = xa_insert(&table->devices, sf_index, sf_dev, GFP_KERNEL);
+	if (err)
+		goto xa_err;
+	return;
+
+xa_err:
+	mlx5_sf_dev_remove(sf_dev);
+add_err:
+	mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n",
+		      sf_index, sfnum, err);
+}
+
+static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev, u16 sf_index)
+{
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+	xa_erase(&table->devices, sf_index);
+	mlx5_sf_dev_remove(sf_dev);
+}
+
+static int
+mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_code, void *data)
+{
+	struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb);
+	const struct mlx5_vhca_state_event *event = data;
+	struct mlx5_sf_dev *sf_dev;
+	u16 sf_index;
+
+	sf_index = event->function_id - MLX5_CAP_GEN(table->dev, sf_base_id);
+	sf_dev = xa_load(&table->devices, sf_index);
+	switch (event->new_vhca_state) {
+	case MLX5_VHCA_STATE_ALLOCATED:
+		if (sf_dev)
+			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+		break;
+	case MLX5_VHCA_STATE_TEARDOWN_REQUEST:
+		if (sf_dev)
+			mlx5_sf_dev_del(table->dev, sf_dev, sf_index);
+		else
+			mlx5_core_err(table->dev,
+				      "SF DEV: teardown state for invalid dev index=%d fn_id=0x%x\n",
+				      sf_index, event->sw_function_id);
+		break;
+	case MLX5_VHCA_STATE_ACTIVE:
+		if (!sf_dev)
+			mlx5_sf_dev_add(table->dev, sf_index, event->sw_function_id);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table)
+{
+	struct mlx5_core_dev *dev = table->dev;
+	u16 max_functions;
+	u16 function_id;
+	int err = 0;
+	bool ecpu;
+	int i;
+
+	max_functions = mlx5_sf_max_functions(dev);
+	function_id = MLX5_CAP_GEN(dev, sf_base_id);
+	ecpu = mlx5_read_embedded_cpu(dev);
+	/* Arm the vhca context as the vhca event notifier */
+	for (i = 0; i < max_functions; i++) {
+		err = mlx5_vhca_event_arm(dev, function_id, ecpu);
+		if (err)
+			return err;
+
+		function_id++;
+	}
+	return 0;
+}
+
+void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_dev_table *table;
+	unsigned int max_sfs;
+	int err;
+
+	if (!mlx5_sf_dev_supported(dev) || !mlx5_vhca_event_supported(dev))
+		return;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table) {
+		err = -ENOMEM;
+		goto table_err;
+	}
+
+	table->nb.notifier_call = mlx5_sf_dev_state_change_handler;
+	table->dev = dev;
+	if (MLX5_CAP_GEN(dev, max_num_sf))
+		max_sfs = MLX5_CAP_GEN(dev, max_num_sf);
+	else
+		max_sfs = 1 << MLX5_CAP_GEN(dev, log_max_sf);
+	table->sf_bar_length = 1 << (MLX5_CAP_GEN(dev, log_min_sf_size) + 12);
+	table->base_address = pci_resource_start(dev->pdev, 2);
+	table->max_sfs = max_sfs;
+	xa_init(&table->devices);
+	dev->priv.sf_dev_table = table;
+
+	err = mlx5_vhca_event_notifier_register(dev, &table->nb);
+	if (err)
+		goto vhca_err;
+	err = mlx5_sf_dev_vhca_arm_all(table);
+	if (err)
+		goto arm_err;
+	mlx5_core_dbg(dev, "SF DEV: max sf devices=%d\n", max_sfs);
+	return;
+
+arm_err:
+	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
+vhca_err:
+	table->max_sfs = 0;
+	kfree(table);
+	dev->priv.sf_dev_table = NULL;
+table_err:
+	mlx5_core_err(dev, "SF DEV table create err = %d\n", err);
+}
+
+static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
+{
+	struct mlx5_sf_dev *sf_dev;
+	unsigned long index;
+
+	xa_for_each(&table->devices, index, sf_dev) {
+		xa_erase(&table->devices, index);
+		mlx5_sf_dev_remove(sf_dev);
+	}
+}
+
+void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+	if (!table)
+		return;
+
+	mlx5_vhca_event_notifier_unregister(dev, &table->nb);
+
+	/* Now that event handler is not running, it is safe to destroy
+	 * the sf device without race.
+	 */
+	mlx5_sf_dev_destroy_all(table);
+
+	WARN_ON(!xa_empty(&table->devices));
+	kfree(table);
+	dev->priv.sf_dev_table = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
new file mode 100644
index 000000000000..a6fb7289ba2c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_DEV_H__
+#define __MLX5_SF_DEV_H__
+
+#ifdef CONFIG_MLX5_SF
+
+#include <linux/auxiliary_bus.h>
+
+#define MLX5_SF_DEV_ID_NAME "sf"
+
+struct mlx5_sf_dev {
+	struct auxiliary_device adev;
+	struct mlx5_core_dev *parent_mdev;
+	phys_addr_t bar_base_addr;
+	u32 sfnum;
+};
+
+void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
+void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev);
+
+#else
+
+static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
+{
+}
+
+static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
+{
+}
+
+#endif
+
+#endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ffba0786051e..08e5fbe97df0 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -508,6 +508,7 @@ struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
 struct mlx5_vhca_state_notifier;
+struct mlx5_sf_dev_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -606,6 +607,7 @@ struct mlx5_priv {
 	struct mlx5_uars_page	       *uar;
 #ifdef CONFIG_MLX5_SF
 	struct mlx5_vhca_state_notifier *vhca_state_notifier;
+	struct mlx5_sf_dev_table *sf_dev_table;
 #endif
 };
 
-- 
cgit v1.2.3


From 1958fc2f0712ae771bfd2351b55e5a5b6b0bcfa4 Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:18 -0800
Subject: net/mlx5: SF, Add auxiliary device driver

Add auxiliary device driver for mlx5 subfunction auxiliary device.

A mlx5 subfunction is similar to PCI PF and VF. For a subfunction
an auxiliary device is created.

As a result, when mlx5 SF auxiliary device binds to the driver,
its netdev and rdma device are created, they appear as

$ ls -l /sys/bus/auxiliary/devices/
mlx5_core.sf.4 -> ../../../devices/pci0000:00/0000:00:03.0/0000:06:00.0/mlx5_core.sf.4

$ ls -l /sys/class/net/eth1/device
/sys/class/net/eth1/device -> ../../../mlx5_core.sf.4

$ cat /sys/bus/auxiliary/devices/mlx5_core.sf.4/sfnum
88

$ devlink dev show
pci/0000:06:00.0
auxiliary/mlx5_core.sf.4

$ devlink port show auxiliary/mlx5_core.sf.4/1
auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false

$ rdma link show mlx5_0/1
link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88

$ rdma dev show
8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112
13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112

In future, devlink device instance name will adapt to have sfnum
annotation using either an alias or as devlink instance name described
in RFC [1].

[1] https://lore.kernel.org/netdev/20200519092258.GF4655@nanopsycho/

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c  |  12 +++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  12 ++-
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  10 ++
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c  |  20 ++++
 .../net/ethernet/mellanox/mlx5/core/sf/dev/dev.c   |  10 ++
 .../net/ethernet/mellanox/mlx5/core/sf/dev/dev.h   |  20 ++++
 .../ethernet/mellanox/mlx5/core/sf/dev/driver.c    | 101 +++++++++++++++++++++
 include/linux/mlx5/driver.h                        |   4 +-
 10 files changed, 187 insertions(+), 6 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index f5b2e9101348..43fa5efd403c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -89,4 +89,4 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
 #
 # SF device
 #
-mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o
+mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 3261d0dc1104..9afe918c5827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -7,6 +7,7 @@
 #include "fw_reset.h"
 #include "fs_core.h"
 #include "eswitch.h"
+#include "sf/dev/dev.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
 				     struct devlink_flash_update_params *params,
@@ -127,6 +128,17 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
 				    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	bool sf_dev_allocated;
+
+	sf_dev_allocated = mlx5_sf_dev_allocated(dev);
+	if (sf_dev_allocated) {
+		/* Reload results in deleting SF device which further results in
+		 * unregistering devlink instance while holding devlink_mutext.
+		 * Hence, do not support reload.
+		 */
+		NL_SET_ERR_MSG_MOD(extack, "reload is unsupported when SFs are allocated\n");
+		return -EOPNOTSUPP;
+	}
 
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 421febebc658..174dfbc996c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -467,7 +467,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 	for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
 		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
 
-	eq_table->irq_table = dev->priv.irq_table;
+	eq_table->irq_table = mlx5_irq_table_get(dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 26b5502712a6..ab68320e5516 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -84,7 +84,6 @@ unsigned int mlx5_core_debug_mask;
 module_param_named(debug_mask, mlx5_core_debug_mask, uint, 0644);
 MODULE_PARM_DESC(debug_mask, "debug mask: 1 = dump cmd data, 2 = dump cmd exec time, 3 = both. Default=0");
 
-#define MLX5_DEFAULT_PROF	2
 static unsigned int prof_sel = MLX5_DEFAULT_PROF;
 module_param_named(prof_sel, prof_sel, uint, 0444);
 MODULE_PARM_DESC(prof_sel, "profile selector. Valid range 0 - 2");
@@ -1303,7 +1302,7 @@ out:
 	mutex_unlock(&dev->intf_state_mutex);
 }
 
-static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
+int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	int err;
@@ -1353,7 +1352,7 @@ err_health_init:
 	return err;
 }
 
-static void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
+void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
@@ -1696,6 +1695,10 @@ static int __init init(void)
 	if (err)
 		goto err_debug;
 
+	err = mlx5_sf_driver_register();
+	if (err)
+		goto err_sf;
+
 #ifdef CONFIG_MLX5_CORE_EN
 	err = mlx5e_init();
 	if (err) {
@@ -1706,6 +1709,8 @@ static int __init init(void)
 
 	return 0;
 
+err_sf:
+	pci_unregister_driver(&mlx5_core_driver);
 err_debug:
 	mlx5_unregister_debugfs();
 	return err;
@@ -1716,6 +1721,7 @@ static void __exit cleanup(void)
 #ifdef CONFIG_MLX5_CORE_EN
 	mlx5e_cleanup();
 #endif
+	mlx5_sf_driver_unregister();
 	pci_unregister_driver(&mlx5_core_driver);
 	mlx5_unregister_debugfs();
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index a33b7496d748..3754ef98554f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -117,6 +117,8 @@ enum mlx5_semaphore_space_address {
 	MLX5_SEMAPHORE_SW_RESET         = 0x20,
 };
 
+#define MLX5_DEFAULT_PROF       2
+
 int mlx5_query_hca_caps(struct mlx5_core_dev *dev);
 int mlx5_query_board_id(struct mlx5_core_dev *dev);
 int mlx5_cmd_init(struct mlx5_core_dev *dev);
@@ -176,6 +178,7 @@ struct cpumask *
 mlx5_irq_get_affinity_mask(struct mlx5_irq_table *irq_table, int vecidx);
 struct cpu_rmap *mlx5_irq_get_rmap(struct mlx5_irq_table *table);
 int mlx5_irq_get_num_comp(struct mlx5_irq_table *table);
+struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
 
 int mlx5_events_init(struct mlx5_core_dev *dev);
 void mlx5_events_cleanup(struct mlx5_core_dev *dev);
@@ -257,6 +260,13 @@ enum {
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
 void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state);
 
+static inline bool mlx5_core_is_sf(const struct mlx5_core_dev *dev)
+{
+	return dev->coredev_type == MLX5_COREDEV_SF;
+}
+
+int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx);
+void mlx5_mdev_uninit(struct mlx5_core_dev *dev);
 void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup);
 int mlx5_load_one(struct mlx5_core_dev *dev, bool boot);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 6fd974920394..a61e09aff152 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -30,6 +30,9 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *irq_table;
 
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
 	irq_table = kvzalloc(sizeof(*irq_table), GFP_KERNEL);
 	if (!irq_table)
 		return -ENOMEM;
@@ -40,6 +43,9 @@ int mlx5_irq_table_init(struct mlx5_core_dev *dev)
 
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
 {
+	if (mlx5_core_is_sf(dev))
+		return;
+
 	kvfree(dev->priv.irq_table);
 }
 
@@ -268,6 +274,9 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev)
 	int nvec;
 	int err;
 
+	if (mlx5_core_is_sf(dev))
+		return 0;
+
 	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
 	       MLX5_IRQ_VEC_COMP_BASE;
 	nvec = min_t(int, nvec, num_eqs);
@@ -319,6 +328,9 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
 	struct mlx5_irq_table *table = dev->priv.irq_table;
 	int i;
 
+	if (mlx5_core_is_sf(dev))
+		return;
+
 	/* free_irq requires that affinity and rmap will be cleared
 	 * before calling it. This is why there is asymmetry with set_rmap
 	 * which should be called after alloc_irq but before request_irq.
@@ -332,3 +344,11 @@ void mlx5_irq_table_destroy(struct mlx5_core_dev *dev)
 	kfree(table->irq);
 }
 
+struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_MLX5_SF
+	if (mlx5_core_is_sf(dev))
+		return dev->priv.parent_mdev->priv.irq_table;
+#endif
+	return dev->priv.irq_table;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 4a8eeb7c853e..b265f27b2166 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -24,6 +24,16 @@ static bool mlx5_sf_dev_supported(const struct mlx5_core_dev *dev)
 	return MLX5_CAP_GEN(dev, sf) && mlx5_vhca_event_supported(dev);
 }
 
+bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
+
+	if (!mlx5_sf_dev_supported(dev))
+		return false;
+
+	return !xa_empty(&table->devices);
+}
+
 static ssize_t sfnum_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct auxiliary_device *adev = container_of(dev, struct auxiliary_device, dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
index a6fb7289ba2c..4de02902aef1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.h
@@ -13,6 +13,7 @@
 struct mlx5_sf_dev {
 	struct auxiliary_device adev;
 	struct mlx5_core_dev *parent_mdev;
+	struct mlx5_core_dev *mdev;
 	phys_addr_t bar_base_addr;
 	u32 sfnum;
 };
@@ -20,6 +21,11 @@ struct mlx5_sf_dev {
 void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev);
 void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev);
 
+int mlx5_sf_driver_register(void);
+void mlx5_sf_driver_unregister(void);
+
+bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev);
+
 #else
 
 static inline void mlx5_sf_dev_table_create(struct mlx5_core_dev *dev)
@@ -30,6 +36,20 @@ static inline void mlx5_sf_dev_table_destroy(struct mlx5_core_dev *dev)
 {
 }
 
+static inline int mlx5_sf_driver_register(void)
+{
+	return 0;
+}
+
+static inline void mlx5_sf_driver_unregister(void)
+{
+}
+
+static inline bool mlx5_sf_dev_allocated(const struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 #endif
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
new file mode 100644
index 000000000000..daf63a8115e0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+#include "mlx5_core.h"
+#include "dev.h"
+#include "devlink.h"
+
+static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxiliary_device_id *id)
+{
+	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+	struct mlx5_core_dev *mdev;
+	struct devlink *devlink;
+	int err;
+
+	devlink = mlx5_devlink_alloc();
+	if (!devlink)
+		return -ENOMEM;
+
+	mdev = devlink_priv(devlink);
+	mdev->device = &adev->dev;
+	mdev->pdev = sf_dev->parent_mdev->pdev;
+	mdev->bar_addr = sf_dev->bar_base_addr;
+	mdev->iseg_base = sf_dev->bar_base_addr;
+	mdev->coredev_type = MLX5_COREDEV_SF;
+	mdev->priv.parent_mdev = sf_dev->parent_mdev;
+	mdev->priv.adev_idx = adev->id;
+	sf_dev->mdev = mdev;
+
+	err = mlx5_mdev_init(mdev, MLX5_DEFAULT_PROF);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_mdev_init on err=%d\n", err);
+		goto mdev_err;
+	}
+
+	mdev->iseg = ioremap(mdev->iseg_base, sizeof(*mdev->iseg));
+	if (!mdev->iseg) {
+		mlx5_core_warn(mdev, "remap error\n");
+		goto remap_err;
+	}
+
+	err = mlx5_load_one(mdev, true);
+	if (err) {
+		mlx5_core_warn(mdev, "mlx5_load_one err=%d\n", err);
+		goto load_one_err;
+	}
+	return 0;
+
+load_one_err:
+	iounmap(mdev->iseg);
+remap_err:
+	mlx5_mdev_uninit(mdev);
+mdev_err:
+	mlx5_devlink_free(devlink);
+	return err;
+}
+
+static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
+{
+	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+	struct devlink *devlink;
+
+	devlink = priv_to_devlink(sf_dev->mdev);
+	mlx5_unload_one(sf_dev->mdev, true);
+	iounmap(sf_dev->mdev->iseg);
+	mlx5_mdev_uninit(sf_dev->mdev);
+	mlx5_devlink_free(devlink);
+}
+
+static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
+{
+	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+
+	mlx5_unload_one(sf_dev->mdev, false);
+}
+
+static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {
+	{ .name = MLX5_ADEV_NAME "." MLX5_SF_DEV_ID_NAME, },
+	{ },
+};
+
+MODULE_DEVICE_TABLE(auxiliary, mlx5_sf_dev_id_table);
+
+static struct auxiliary_driver mlx5_sf_driver = {
+	.name = MLX5_SF_DEV_ID_NAME,
+	.probe = mlx5_sf_dev_probe,
+	.remove = mlx5_sf_dev_remove,
+	.shutdown = mlx5_sf_dev_shutdown,
+	.id_table = mlx5_sf_dev_id_table,
+};
+
+int mlx5_sf_driver_register(void)
+{
+	return auxiliary_driver_register(&mlx5_sf_driver);
+}
+
+void mlx5_sf_driver_unregister(void)
+{
+	auxiliary_driver_unregister(&mlx5_sf_driver);
+}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 08e5fbe97df0..48e3638b1185 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -193,7 +193,8 @@ enum port_state_policy {
 
 enum mlx5_coredev_type {
 	MLX5_COREDEV_PF,
-	MLX5_COREDEV_VF
+	MLX5_COREDEV_VF,
+	MLX5_COREDEV_SF,
 };
 
 struct mlx5_field_desc {
@@ -608,6 +609,7 @@ struct mlx5_priv {
 #ifdef CONFIG_MLX5_SF
 	struct mlx5_vhca_state_notifier *vhca_state_notifier;
 	struct mlx5_sf_dev_table *sf_dev_table;
+	struct mlx5_core_dev *parent_mdev;
 #endif
 };
 
-- 
cgit v1.2.3


From 8f01054186683fe0986d54d584aa13723d51edce Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@nvidia.com>
Date: Fri, 11 Dec 2020 22:12:21 -0800
Subject: net/mlx5: SF, Add port add delete functionality

To handle SF port management outside of the eswitch as independent
software layer, introduce eswitch notifier APIs so that mlx5 upper
layer who wish to support sf port management in switchdev mode can
perform its task whenever eswitch mode is set to switchdev or before
eswitch is disabled.

Initialize sf port table on such eswitch event.

Add SF port add and delete functionality in switchdev mode.
Destroy all SF ports when eswitch is disabled.
Expose SF port add and delete to user via devlink commands.

$ devlink dev eswitch set pci/0000:06:00.0 mode switchdev

$ devlink port show
pci/0000:06:00.0/65535: type eth netdev ens2f0np0 flavour physical port 0 splittable false

$ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88
pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ devlink port show ens2f0npf0sf88
pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

or by its unique port index:
$ devlink port show pci/0000:06:00.0/32768
pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

$ devlink port show ens2f0npf0sf88 -jp
{
    "port": {
        "pci/0000:06:00.0/32768": {
            "type": "eth",
            "netdev": "ens2f0npf0sf88",
            "flavour": "pcisf",
            "controller": 0,
            "pfnum": 0,
            "sfnum": 88,
            "external": false,
            "splittable": false,
            "function": {
                "hw_addr": "00:00:00:00:00:00",
                "state": "inactive",
                "opstate": "detached"
            }
        }
    }
}

Signed-off-by: Parav Pandit <parav@nvidia.com>
Reviewed-by: Vu Pham <vuhuong@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |  10 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c  |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c  |  25 ++
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  12 +
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  18 ++
 drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c   |  27 ++
 .../net/ethernet/mellanox/mlx5/core/sf/devlink.c   | 316 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/sf/hw_table.c  | 125 ++++++++
 drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h  |  17 ++
 drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h    |  37 +++
 include/linux/mlx5/driver.h                        |   6 +
 13 files changed, 607 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index d6c48582e7a8..ad45d20f9d44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -212,3 +212,13 @@ config MLX5_SF
 	Build support for subfuction device in the NIC. A Mellanox subfunction
 	device can support RDMA, netdevice and vdpa device.
 	It is similar to a SRIOV VF but it doesn't require SRIOV support.
+
+config MLX5_SF_MANAGER
+	bool
+	depends on MLX5_SF && MLX5_ESWITCH
+	default y
+	help
+	Build support for subfuction port in the NIC. A Mellanox subfunction
+	port is managed through devlink.  A subfunction supports RDMA, netdevice
+	and vdpa device. It is similar to a SRIOV VF but it doesn't require
+	SRIOV support.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 43fa5efd403c..40ed31574c80 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -90,3 +90,8 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o
 # SF device
 #
 mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o
+
+#
+# SF manager
+#
+mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 47dcc3ac2cf0..e8cecd50558d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -333,6 +333,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
 	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 	case MLX5_CMD_OP_QUERY_ESW_FUNCTIONS:
+	case MLX5_CMD_OP_DEALLOC_SF:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -466,6 +467,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_RELEASE_XRQ_ERROR:
 	case MLX5_CMD_OP_QUERY_VHCA_STATE:
 	case MLX5_CMD_OP_MODIFY_VHCA_STATE:
+	case MLX5_CMD_OP_ALLOC_SF:
 		*status = MLX5_DRIVER_STATUS_ABORTED;
 		*synd = MLX5_DRIVER_SYND;
 		return -EIO;
@@ -661,6 +663,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(MODIFY_XRQ);
 	MLX5_COMMAND_STR_CASE(QUERY_VHCA_STATE);
 	MLX5_COMMAND_STR_CASE(MODIFY_VHCA_STATE);
+	MLX5_COMMAND_STR_CASE(ALLOC_SF);
+	MLX5_COMMAND_STR_CASE(DEALLOC_SF);
 	default: return "unknown command opcode";
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 9afe918c5827..d4c0cdf5edd9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -8,6 +8,7 @@
 #include "fs_core.h"
 #include "eswitch.h"
 #include "sf/dev/dev.h"
+#include "sf/sf.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
 				     struct devlink_flash_update_params *params,
@@ -190,6 +191,10 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.eswitch_encap_mode_get = mlx5_devlink_eswitch_encap_mode_get,
 	.port_function_hw_addr_get = mlx5_devlink_port_function_hw_addr_get,
 	.port_function_hw_addr_set = mlx5_devlink_port_function_hw_addr_set,
+#endif
+#ifdef CONFIG_MLX5_SF_MANAGER
+	.port_new = mlx5_devlink_sf_port_new,
+	.port_del = mlx5_devlink_sf_port_del,
 #endif
 	.flash_update = mlx5_devlink_flash_update,
 	.info_get = mlx5_devlink_info_get,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 538d2e44a589..820305b1664e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1599,6 +1599,15 @@ mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, int num_vfs)
 	kvfree(out);
 }
 
+static void mlx5_esw_mode_change_notify(struct mlx5_eswitch *esw, u16 mode)
+{
+	struct mlx5_esw_event_info info = {};
+
+	info.new_mode = mode;
+
+	blocking_notifier_call_chain(&esw->n_head, 0, &info);
+}
+
 /**
  * mlx5_eswitch_enable_locked - Enable eswitch
  * @esw:	Pointer to eswitch
@@ -1659,6 +1668,8 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int mode, int num_vfs)
 		 mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
 		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
+	mlx5_esw_mode_change_notify(esw, mode);
+
 	return 0;
 
 abort:
@@ -1715,6 +1726,11 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw, bool clear_vf)
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
 		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
+	/* Notify eswitch users that it is exiting from current mode.
+	 * So that it can do necessary cleanup before the eswitch is disabled.
+	 */
+	mlx5_esw_mode_change_notify(esw, MLX5_ESWITCH_NONE);
+
 	mlx5_eswitch_event_handlers_unregister(esw);
 
 	if (esw->mode == MLX5_ESWITCH_LEGACY)
@@ -1815,6 +1831,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
 
 	dev->priv.eswitch = esw;
+	BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
 	return 0;
 abort:
 	if (esw->work_queue)
@@ -2506,4 +2523,12 @@ bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 		dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
 }
 
+int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&esw->n_head, nb);
+}
 
+void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&esw->n_head, nb);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 54514b04808d..479d2ac2cd85 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -278,6 +278,7 @@ struct mlx5_eswitch {
 	struct {
 		u32             large_group_num;
 	}  params;
+	struct blocking_notifier_head n_head;
 };
 
 void esw_offloads_disable(struct mlx5_eswitch *esw);
@@ -733,6 +734,17 @@ int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_p
 				      u16 vport_num, u32 sfnum);
 void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num);
 
+/**
+ * mlx5_esw_event_info - Indicates eswitch mode changed/changing.
+ *
+ * @new_mode: New mode of eswitch.
+ */
+struct mlx5_esw_event_info {
+	u16 new_mode;
+};
+
+int mlx5_esw_event_notifier_register(struct mlx5_eswitch *esw, struct notifier_block *n);
+void mlx5_esw_event_notifier_unregister(struct mlx5_eswitch *esw, struct notifier_block *n);
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ab68320e5516..d6bd09dd7490 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -893,6 +893,18 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_fpga_cleanup;
 	}
 
+	err = mlx5_sf_hw_table_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to init SF HW table %d\n", err);
+		goto err_sf_hw_table_cleanup;
+	}
+
+	err = mlx5_sf_table_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to init SF table %d\n", err);
+		goto err_sf_table_cleanup;
+	}
+
 	dev->dm = mlx5_dm_create(dev);
 	if (IS_ERR(dev->dm))
 		mlx5_core_warn(dev, "Failed to init device memory%d\n", err);
@@ -903,6 +915,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	return 0;
 
+err_sf_table_cleanup:
+	mlx5_sf_hw_table_cleanup(dev);
+err_sf_hw_table_cleanup:
+	mlx5_vhca_event_cleanup(dev);
 err_fpga_cleanup:
 	mlx5_fpga_cleanup(dev);
 err_eswitch_cleanup:
@@ -936,6 +952,8 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_dm_cleanup(dev);
+	mlx5_sf_table_cleanup(dev);
+	mlx5_sf_hw_table_cleanup(dev);
 	mlx5_vhca_event_cleanup(dev);
 	mlx5_fpga_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c
new file mode 100644
index 000000000000..0bc3075f34fa
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/cmd.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "priv.h"
+
+int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_sf_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(alloc_sf_in)] = {};
+
+	MLX5_SET(alloc_sf_in, in, opcode, MLX5_CMD_OP_ALLOC_SF);
+	MLX5_SET(alloc_sf_in, in, function_id, function_id);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id)
+{
+	u32 out[MLX5_ST_SZ_DW(dealloc_sf_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(dealloc_sf_in)] = {};
+
+	MLX5_SET(dealloc_sf_in, in, opcode, MLX5_CMD_OP_DEALLOC_SF);
+	MLX5_SET(dealloc_sf_in, in, function_id, function_id);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
new file mode 100644
index 000000000000..7ad0d210ec30
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#include <linux/mlx5/driver.h>
+#include "eswitch.h"
+#include "priv.h"
+
+struct mlx5_sf {
+	struct devlink_port dl_port;
+	unsigned int port_index;
+	u16 id;
+};
+
+struct mlx5_sf_table {
+	struct mlx5_core_dev *dev; /* To refer from notifier context. */
+	struct xarray port_indices; /* port index based lookup. */
+	refcount_t refcount;
+	struct completion disable_complete;
+	struct notifier_block esw_nb;
+};
+
+static struct mlx5_sf *
+mlx5_sf_lookup_by_index(struct mlx5_sf_table *table, unsigned int port_index)
+{
+	return xa_load(&table->port_indices, port_index);
+}
+
+static int mlx5_sf_id_insert(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+	return xa_insert(&table->port_indices, sf->port_index, sf, GFP_KERNEL);
+}
+
+static void mlx5_sf_id_erase(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+	xa_erase(&table->port_indices, sf->port_index);
+}
+
+static struct mlx5_sf *
+mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *extack)
+{
+	unsigned int dl_port_index;
+	struct mlx5_sf *sf;
+	u16 hw_fn_id;
+	int id_err;
+	int err;
+
+	id_err = mlx5_sf_hw_table_sf_alloc(table->dev, sfnum);
+	if (id_err < 0) {
+		err = id_err;
+		goto id_err;
+	}
+
+	sf = kzalloc(sizeof(*sf), GFP_KERNEL);
+	if (!sf) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+	sf->id = id_err;
+	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sf->id);
+	dl_port_index = mlx5_esw_vport_to_devlink_port_index(table->dev, hw_fn_id);
+	sf->port_index = dl_port_index;
+
+	err = mlx5_sf_id_insert(table, sf);
+	if (err)
+		goto insert_err;
+
+	return sf;
+
+insert_err:
+	kfree(sf);
+alloc_err:
+	mlx5_sf_hw_table_sf_free(table->dev, id_err);
+id_err:
+	if (err == -EEXIST)
+		NL_SET_ERR_MSG_MOD(extack, "SF already exist. Choose different sfnum");
+	return ERR_PTR(err);
+}
+
+static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+	mlx5_sf_id_erase(table, sf);
+	mlx5_sf_hw_table_sf_free(table->dev, sf->id);
+	kfree(sf);
+}
+
+static struct mlx5_sf_table *mlx5_sf_table_try_get(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return NULL;
+
+	return refcount_inc_not_zero(&table->refcount) ? table : NULL;
+}
+
+static void mlx5_sf_table_put(struct mlx5_sf_table *table)
+{
+	if (refcount_dec_and_test(&table->refcount))
+		complete(&table->disable_complete);
+}
+
+static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
+		       const struct devlink_port_new_attrs *new_attr,
+		       struct netlink_ext_ack *extack,
+		       unsigned int *new_port_index)
+{
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_sf *sf;
+	u16 hw_fn_id;
+	int err;
+
+	sf = mlx5_sf_alloc(table, new_attr->sfnum, extack);
+	if (IS_ERR(sf))
+		return PTR_ERR(sf);
+
+	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, sf->id);
+	err = mlx5_esw_offloads_sf_vport_enable(esw, &sf->dl_port, hw_fn_id, new_attr->sfnum);
+	if (err)
+		goto esw_err;
+	*new_port_index = sf->port_index;
+	return 0;
+
+esw_err:
+	mlx5_sf_free(table, sf);
+	return err;
+}
+
+static void mlx5_sf_del(struct mlx5_core_dev *dev, struct mlx5_sf_table *table, struct mlx5_sf *sf)
+{
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	u16 hw_fn_id;
+
+	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, sf->id);
+	mlx5_esw_offloads_sf_vport_disable(esw, hw_fn_id);
+	mlx5_sf_free(table, sf);
+}
+
+static int
+mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_attrs *new_attr,
+		       struct netlink_ext_ack *extack)
+{
+	if (new_attr->flavour != DEVLINK_PORT_FLAVOUR_PCI_SF) {
+		NL_SET_ERR_MSG_MOD(extack, "Driver supports only SF port addition");
+		return -EOPNOTSUPP;
+	}
+	if (new_attr->port_index_valid) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Driver does not support user defined port index assignment");
+		return -EOPNOTSUPP;
+	}
+	if (!new_attr->sfnum_valid) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "User must provide unique sfnum. Driver does not support auto assignment");
+		return -EOPNOTSUPP;
+	}
+	if (new_attr->controller_valid && new_attr->controller) {
+		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
+		return -EOPNOTSUPP;
+	}
+	if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+int mlx5_devlink_sf_port_new(struct devlink *devlink,
+			     const struct devlink_port_new_attrs *new_attr,
+			     struct netlink_ext_ack *extack,
+			     unsigned int *new_port_index)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_sf_table *table;
+	int err;
+
+	err = mlx5_sf_new_check_attr(dev, new_attr, extack);
+	if (err)
+		return err;
+
+	table = mlx5_sf_table_try_get(dev);
+	if (!table) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port add is only supported in eswitch switchdev mode or SF ports are disabled.");
+		return -EOPNOTSUPP;
+	}
+	err = mlx5_sf_add(dev, table, new_attr, extack, new_port_index);
+	mlx5_sf_table_put(table);
+	return err;
+}
+
+int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index,
+			     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	struct mlx5_sf_table *table;
+	struct mlx5_sf *sf;
+	int err = 0;
+
+	table = mlx5_sf_table_try_get(dev);
+	if (!table) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port del is only supported in eswitch switchdev mode or SF ports are disabled.");
+		return -EOPNOTSUPP;
+	}
+	sf = mlx5_sf_lookup_by_index(table, port_index);
+	if (!sf) {
+		err = -ENODEV;
+		goto sf_err;
+	}
+
+	mlx5_sf_del(dev, table, sf);
+sf_err:
+	mlx5_sf_table_put(table);
+	return err;
+}
+
+static void mlx5_sf_destroy_all(struct mlx5_sf_table *table)
+{
+	struct mlx5_core_dev *dev = table->dev;
+	unsigned long index;
+	struct mlx5_sf *sf;
+
+	xa_for_each(&table->port_indices, index, sf)
+		mlx5_sf_del(dev, table, sf);
+}
+
+static void mlx5_sf_table_enable(struct mlx5_sf_table *table)
+{
+	if (!mlx5_sf_max_functions(table->dev))
+		return;
+
+	init_completion(&table->disable_complete);
+	refcount_set(&table->refcount, 1);
+}
+
+static void mlx5_sf_table_disable(struct mlx5_sf_table *table)
+{
+	if (!mlx5_sf_max_functions(table->dev))
+		return;
+
+	if (!refcount_read(&table->refcount))
+		return;
+
+	/* Balances with refcount_set; drop the reference so that new user cmd cannot start. */
+	mlx5_sf_table_put(table);
+	wait_for_completion(&table->disable_complete);
+
+	/* At this point, no new user commands can start.
+	 * It is safe to destroy all user created SFs.
+	 */
+	mlx5_sf_destroy_all(table);
+}
+
+static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5_sf_table *table = container_of(nb, struct mlx5_sf_table, esw_nb);
+	const struct mlx5_esw_event_info *mode = data;
+
+	switch (mode->new_mode) {
+	case MLX5_ESWITCH_OFFLOADS:
+		mlx5_sf_table_enable(table);
+		break;
+	case MLX5_ESWITCH_NONE:
+		mlx5_sf_table_disable(table);
+		break;
+	default:
+		break;
+	};
+
+	return 0;
+}
+
+static bool mlx5_sf_table_supported(const struct mlx5_core_dev *dev)
+{
+	return dev->priv.eswitch && MLX5_ESWITCH_MANAGER(dev) && mlx5_sf_supported(dev);
+}
+
+int mlx5_sf_table_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table;
+	int err;
+
+	if (!mlx5_sf_table_supported(dev))
+		return 0;
+
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	table->dev = dev;
+	xa_init(&table->port_indices);
+	dev->priv.sf_table = table;
+	table->esw_nb.notifier_call = mlx5_sf_esw_event;
+	err = mlx5_esw_event_notifier_register(dev->priv.eswitch, &table->esw_nb);
+	if (err)
+		goto reg_err;
+	return 0;
+
+reg_err:
+	kfree(table);
+	dev->priv.sf_table = NULL;
+	return err;
+}
+
+void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_table *table = dev->priv.sf_table;
+
+	if (!table)
+		return;
+
+	mlx5_esw_event_notifier_unregister(dev->priv.eswitch, &table->esw_nb);
+	WARN_ON(refcount_read(&table->refcount));
+	WARN_ON(!xa_empty(&table->port_indices));
+	kfree(table);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
new file mode 100644
index 000000000000..c7757f399e8a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -0,0 +1,125 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+#include <linux/mlx5/driver.h>
+#include "vhca_event.h"
+#include "priv.h"
+#include "sf.h"
+#include "ecpf.h"
+
+struct mlx5_sf_hw {
+	u32 usr_sfnum;
+	u8 allocated: 1;
+};
+
+struct mlx5_sf_hw_table {
+	struct mlx5_core_dev *dev;
+	struct mlx5_sf_hw *sfs;
+	int max_local_functions;
+	u8 ecpu: 1;
+};
+
+u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id)
+{
+	return sw_id + mlx5_sf_start_function_id(dev);
+}
+
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum)
+{
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+	int sw_id = -ENOSPC;
+	u16 hw_fn_id;
+	int err;
+	int i;
+
+	if (!table->max_local_functions)
+		return -EOPNOTSUPP;
+
+	/* Check if sf with same sfnum already exists or not. */
+	for (i = 0; i < table->max_local_functions; i++) {
+		if (table->sfs[i].allocated && table->sfs[i].usr_sfnum == usr_sfnum)
+			return -EEXIST;
+	}
+
+	/* Find the free entry and allocate the entry from the array */
+	for (i = 0; i < table->max_local_functions; i++) {
+		if (!table->sfs[i].allocated) {
+			table->sfs[i].usr_sfnum = usr_sfnum;
+			table->sfs[i].allocated = true;
+			sw_id = i;
+			break;
+		}
+	}
+	if (sw_id == -ENOSPC) {
+		err = -ENOSPC;
+		goto err;
+	}
+
+	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id);
+	err = mlx5_cmd_alloc_sf(table->dev, hw_fn_id);
+	if (err)
+		goto err;
+
+	err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum);
+	if (err)
+		goto vhca_err;
+
+	return sw_id;
+
+vhca_err:
+	mlx5_cmd_dealloc_sf(table->dev, hw_fn_id);
+err:
+	table->sfs[i].allocated = false;
+	return err;
+}
+
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id)
+{
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+	u16 hw_fn_id;
+
+	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, id);
+	mlx5_cmd_dealloc_sf(table->dev, hw_fn_id);
+	table->sfs[id].allocated = false;
+}
+
+int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_hw_table *table;
+	struct mlx5_sf_hw *sfs;
+	int max_functions;
+
+	if (!mlx5_sf_supported(dev))
+		return 0;
+
+	max_functions = mlx5_sf_max_functions(dev);
+	table = kzalloc(sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
+
+	sfs = kcalloc(max_functions, sizeof(*sfs), GFP_KERNEL);
+	if (!sfs)
+		goto table_err;
+
+	table->dev = dev;
+	table->sfs = sfs;
+	table->max_local_functions = max_functions;
+	table->ecpu = mlx5_read_embedded_cpu(dev);
+	dev->priv.sf_hw_table = table;
+	mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions);
+	return 0;
+
+table_err:
+	kfree(table);
+	return -ENOMEM;
+}
+
+void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+
+	if (!table)
+		return;
+
+	kfree(table->sfs);
+	kfree(table);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
new file mode 100644
index 000000000000..7f3622375a9c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies Ltd */
+
+#ifndef __MLX5_SF_PRIV_H__
+#define __MLX5_SF_PRIV_H__
+
+#include <linux/mlx5/driver.h>
+
+int mlx5_cmd_alloc_sf(struct mlx5_core_dev *dev, u16 function_id);
+int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id);
+
+u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id);
+
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum);
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
index 623191679b49..31278dc42e72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/sf.h
@@ -42,4 +42,41 @@ static inline u16 mlx5_sf_max_functions(const struct mlx5_core_dev *dev)
 
 #endif
 
+#ifdef CONFIG_MLX5_SF_MANAGER
+
+int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev);
+
+int mlx5_sf_table_init(struct mlx5_core_dev *dev);
+void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev);
+
+int mlx5_devlink_sf_port_new(struct devlink *devlink,
+			     const struct devlink_port_new_attrs *add_attr,
+			     struct netlink_ext_ack *extack,
+			     unsigned int *new_port_index);
+int mlx5_devlink_sf_port_del(struct devlink *devlink, unsigned int port_index,
+			     struct netlink_ext_ack *extack);
+
+#else
+
+static inline int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
+static inline void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+static inline int mlx5_sf_table_init(struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
+static inline void mlx5_sf_table_cleanup(struct mlx5_core_dev *dev)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 48e3638b1185..7e357c7f0d5e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -510,6 +510,8 @@ struct mlx5_eq_table;
 struct mlx5_irq_table;
 struct mlx5_vhca_state_notifier;
 struct mlx5_sf_dev_table;
+struct mlx5_sf_hw_table;
+struct mlx5_sf_table;
 
 struct mlx5_rate_limit {
 	u32			rate;
@@ -611,6 +613,10 @@ struct mlx5_priv {
 	struct mlx5_sf_dev_table *sf_dev_table;
 	struct mlx5_core_dev *parent_mdev;
 #endif
+#ifdef CONFIG_MLX5_SF_MANAGER
+	struct mlx5_sf_hw_table *sf_hw_table;
+	struct mlx5_sf_table *sf_table;
+#endif
 };
 
 enum mlx5_device_state {
-- 
cgit v1.2.3