devlink: Expose port function commands to control RoCE

Expose port function commands to enable / disable RoCE, this is used to
control the port RoCE device capabilities.

When RoCE is disabled for a function of the port, function cannot create
any RoCE specific resources (e.g GID table).
It also saves system memory utilization. For example disabling RoCE enable a
VF/SF saves 1 Mbytes of system memory per function.

Example of a PCI VF port which supports function configuration:
Set RoCE of the VF's port function.

$ devlink port show pci/0000:06:00.0/2
pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0
vfnum 1
    function:
        hw_addr 00:00:00:00:00:00 roce enable

$ devlink port function set pci/0000:06:00.0/2 roce disable

$ devlink port show pci/0000:06:00.0/2
pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0
vfnum 1
    function:
        hw_addr 00:00:00:00:00:00 roce disable

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 174 insertions, 1 deletions

diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index 2c637f4aae8e..c3302d23e480 100644
--- a/Documentation/networking/devlink/devlink-port.rst
+++ b/Documentation/networking/devlink/devlink-port.rst
@@ -110,7 +110,7 @@ devlink ports for both the controllers.
 Function configuration
 ======================
 
-A user can configure the function attribute before enumerating the PCI
+Users can configure one or more function attributes before enumerating the PCI
 function. Usually it means, user should configure function attribute
 before a bus specific device for the function is created. However, when
 SRIOV is enabled, virtual function devices are created on the PCI bus.
@@ -122,6 +122,9 @@ A user may set the hardware address of the function using
 `devlink port function set hw_addr` command. For Ethernet port function
 this means a MAC address.
 
+Users may also set the RoCE capability of the function using
+`devlink port function set roce` command.
+
 Function attributes
 ===================
 
@@ -162,6 +165,35 @@ device created for the PCI VF/SF.
       function:
         hw_addr 00:00:00:00:88:88
 
+RoCE capability setup
+---------------------
+Not all PCI VFs/SFs require RoCE capability.
+
+When RoCE capability is disabled, it saves system memory per PCI VF/SF.
+
+When user disables RoCE capability for a VF/SF, user application cannot send or
+receive any RoCE packets through this VF/SF and RoCE GID table for this PCI
+will be empty.
+
+When RoCE capability is disabled in the device using port function attribute,
+VF/SF driver cannot override it.
+
+- Get RoCE capability of the VF device::
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 roce enable
+
+- Set RoCE capability of the VF device::
+
+    $ devlink port function set pci/0000:06:00.0/2 roce disable
+
+    $ devlink port show pci/0000:06:00.0/2
+    pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1
+        function:
+            hw_addr 00:00:00:00:00:00 roce disable
+
 Subfunction
 ============
 
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 5f6eca5e4a40..ce4c65d2f2e7 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1452,6 +1452,24 @@ struct devlink_ops {
 					 const u8 *hw_addr, int hw_addr_len,
 					 struct netlink_ext_ack *extack);
 	/**
+	 * @port_fn_roce_get: Port function's roce get function.
+	 *
+	 * Query RoCE state of a function managed by the devlink port.
+	 * Return -EOPNOTSUPP if port function RoCE handling is not supported.
+	 */
+	int (*port_fn_roce_get)(struct devlink_port *devlink_port,
+				bool *is_enable,
+				struct netlink_ext_ack *extack);
+	/**
+	 * @port_fn_roce_set: Port function's roce set function.
+	 *
+	 * Enable/Disable the RoCE state of a function managed by the devlink
+	 * port.
+	 * Return -EOPNOTSUPP if port function RoCE handling is not supported.
+	 */
+	int (*port_fn_roce_set)(struct devlink_port *devlink_port,
+				bool enable, 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
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 70191d96af89..6cc2925bd478 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -658,11 +658,21 @@ enum devlink_resource_unit {
 	DEVLINK_RESOURCE_UNIT_ENTRY,
 };
 
+enum devlink_port_fn_attr_cap {
+	DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT,
+
+	/* Add new caps above */
+	__DEVLINK_PORT_FN_ATTR_CAPS_MAX,
+};
+
+#define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT)
+
 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_FN_ATTR_CAPS,	/* bitfield32 */
 
 	__DEVLINK_PORT_FUNCTION_ATTR_MAX,
 	DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 035249c5dd17..8c0ad52431c5 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -195,11 +195,16 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
+#define DEVLINK_PORT_FN_CAPS_VALID_MASK \
+	(_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1)
+
 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),
+	[DEVLINK_PORT_FN_ATTR_CAPS] =
+		NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK),
 };
 
 static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = {
@@ -680,6 +685,60 @@ devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb,
 	return 0;
 }
 
+static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps,
+				     u32 cap, bool is_enable)
+{
+	caps->selector |= cap;
+	if (is_enable)
+		caps->value |= cap;
+}
+
+static int devlink_port_fn_roce_fill(const struct devlink_ops *ops,
+				     struct devlink_port *devlink_port,
+				     struct nla_bitfield32 *caps,
+				     struct netlink_ext_ack *extack)
+{
+	bool is_enable;
+	int err;
+
+	if (!ops->port_fn_roce_get)
+		return 0;
+
+	err = ops->port_fn_roce_get(devlink_port, &is_enable, extack);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable);
+	return 0;
+}
+
+static int devlink_port_fn_caps_fill(const struct devlink_ops *ops,
+				     struct devlink_port *devlink_port,
+				     struct sk_buff *msg,
+				     struct netlink_ext_ack *extack,
+				     bool *msg_updated)
+{
+	struct nla_bitfield32 caps = {};
+	int err;
+
+	err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack);
+	if (err)
+		return err;
+
+	if (!caps.selector)
+		return 0;
+	err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value,
+				 caps.selector);
+	if (err)
+		return err;
+
+	*msg_updated = true;
+	return 0;
+}
+
 static int
 devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 				  struct genl_info *info,
@@ -1264,6 +1323,35 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops,
 }
 
 static int
+devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable,
+			 struct netlink_ext_ack *extack)
+{
+	const struct devlink_ops *ops = devlink_port->devlink->ops;
+
+	return ops->port_fn_roce_set(devlink_port, enable, extack);
+}
+
+static int devlink_port_fn_caps_set(struct devlink_port *devlink_port,
+				    const struct nlattr *attr,
+				    struct netlink_ext_ack *extack)
+{
+	struct nla_bitfield32 caps;
+	u32 caps_value;
+	int err;
+
+	caps = nla_get_bitfield32(attr);
+	caps_value = caps.value & caps.selector;
+	if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) {
+		err = devlink_port_fn_roce_set(devlink_port,
+					       caps_value & DEVLINK_PORT_FN_CAP_ROCE,
+					       extack);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int
 devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port,
 				   struct netlink_ext_ack *extack)
 {
@@ -1281,6 +1369,10 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por
 					   &msg_updated);
 	if (err)
 		goto out;
+	err = devlink_port_fn_caps_fill(ops, port, msg, extack,
+					&msg_updated);
+	if (err)
+		goto out;
 	err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated);
 out:
 	if (err || !msg_updated)
@@ -1653,6 +1745,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 					  struct netlink_ext_ack *extack)
 {
 	const struct devlink_ops *ops = devlink_port->devlink->ops;
+	struct nlattr *attr;
 
 	if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] &&
 	    !ops->port_function_hw_addr_set) {
@@ -1665,6 +1758,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 				    "Function does not support state setting");
 		return -EOPNOTSUPP;
 	}
+	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
+	if (attr) {
+		struct nla_bitfield32 caps;
+
+		caps = nla_get_bitfield32(attr);
+		if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE &&
+		    !ops->port_fn_roce_set) {
+			NL_SET_ERR_MSG_ATTR(extack, attr,
+					    "Port doesn't support RoCE function attribute");
+			return -EOPNOTSUPP;
+		}
+	}
 	return 0;
 }
 
@@ -1692,6 +1797,14 @@ static int devlink_port_function_set(struct devlink_port *port,
 		if (err)
 			return err;
 	}
+
+	attr = tb[DEVLINK_PORT_FN_ATTR_CAPS];
+	if (attr) {
+		err = devlink_port_fn_caps_set(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.