Expose port function commands to turn on / off 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 on 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 on
$ devlink port function set pci/0000:06:00.0/2 roce off
$ 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 00:11:22:33:44:55 roce off
Signed-off-by: Yishai Hadas <yishaih@xxxxxxxxxx>
Reviewed-by: Parav Pandit <parav@xxxxxxxxxx>
Reviewed-by: Jiri Pirko <jiri@xxxxxxxxxx>
Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxx>
---
.../networking/devlink/devlink-port.rst | 5 +-
include/net/devlink.h | 22 +++++++
include/uapi/linux/devlink.h | 1 +
net/core/devlink.c | 63 +++++++++++++++++++
4 files changed, 90 insertions(+), 1 deletion(-)
diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst
index e99b41599465..541e19f9d256 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
+A user 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.
+A user may set also the roce capability of the function using
+'devlink port function set roce' command.
+
Subfunction
============
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 47b4b063401b..055280212b58 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1451,6 +1451,28 @@ struct devlink_ops {
struct devlink_port *port,
enum devlink_port_fn_state state,
struct netlink_ext_ack *extack);
+ /**
+ * @port_fn_roce_get: Port function's roce get function.
+ *
+ * Should be used by device drivers to report the roce state of
+ * a function managed by the devlink port. Driver should return
+ * -EOPNOTSUPP if it doesn't support port function handling for
+ * a particular port.
+ */
+ int (*port_fn_roce_get)(struct devlink *devlink,
+ struct devlink_port *port, bool *on,
+ struct netlink_ext_ack *extack);
+ /**
+ * @port_fn_roce_set: Port function's roce set function.
+ *
+ * Should be used by device drivers to enable/disable the roce state of
+ * a function managed by the devlink port. Driver should return
+ * -EOPNOTSUPP if it doesn't support port function handling for
+ * a particular port.
+ */
+ int (*port_fn_roce_set)(struct devlink *devlink,
+ struct devlink_port *port, bool on,
+ 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 f6008b2fa60f..77990b563d80 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -585,6 +585,7 @@ enum devlink_port_function_attr {
DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */
DEVLINK_PORT_FN_ATTR_STATE, /* u8 */
DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */
+ DEVLINK_PORT_FN_ATTR_ROCE, /* u8 */
__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 737b61c2976e..d04318e79dc2 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -90,6 +90,7 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_
[DEVLINK_PORT_FN_ATTR_STATE] =
NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE,
DEVLINK_PORT_FN_STATE_ACTIVE),
+ [DEVLINK_PORT_FN_ATTR_ROCE] = NLA_POLICY_RANGE(NLA_U8, 0, 1),
};
static LIST_HEAD(devlink_list);
@@ -724,6 +725,34 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
return 0;
}
+static int devlink_port_function_roce_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)
+{
+ bool on;
+ int err;
+
+ if (!ops->port_fn_roce_get)
+ return 0;
+
+ err = ops->port_fn_roce_get(devlink, port, &on, extack);
+ if (err) {
+ if (err == -EOPNOTSUPP)
+ return 0;
+ return err;
+ }
+
+ err = nla_put_u8(msg, DEVLINK_PORT_FN_ATTR_ROCE, on);
+ if (err)
+ return err;
+
+ *msg_updated = true;
+ return 0;
+}
+
static int
devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *ops,
struct devlink_port *port, struct sk_buff *msg,
@@ -820,6 +849,12 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por
extack, &msg_updated);
if (err)
goto out;
+
+ err = devlink_port_function_roce_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:
@@ -1054,6 +1089,26 @@ static int devlink_port_type_set(struct devlink *devlink,
return -EOPNOTSUPP;
}
+static int
+devlink_port_fn_roce_set(struct devlink *devlink, struct devlink_port *port,
+ const struct nlattr *attr,
+ struct netlink_ext_ack *extack)
+{
+ const struct devlink_ops *ops;
+ bool on;
+
+ on = nla_get_u8(attr);
+
+ ops = devlink->ops;
+ if (!ops->port_fn_roce_set) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Port doesn't support roce function attribute");
+ return -EOPNOTSUPP;
+ }
+
+ return ops->port_fn_roce_set(devlink, port, on, extack);
+}
+
static int
devlink_port_function_hw_addr_set(struct devlink *devlink, struct devlink_port *port,
const struct nlattr *attr, struct netlink_ext_ack *extack)
@@ -1126,6 +1181,14 @@ devlink_port_function_set(struct devlink *devlink, struct devlink_port *port,
if (err)
return err;
}
+
+ attr = tb[DEVLINK_PORT_FN_ATTR_ROCE];
+ if (attr) {
+ err = devlink_port_fn_roce_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.
--
2.18.1
