devlink: Introduce rate object

Allow registering rate object for devlink ports with dedicated
devlink_rate_leaf_{create|destroy}() API. Implement new netlink
DEVLINK_CMD_RATE_GET command that is used to retrieve rate object info.
Add new DEVLINK_CMD_RATE_{NEW|DEL} commands that are used for
notifications when creating/deleting leaf rate object.

Rate API is intended to be used for rate limiting of individual
devlink ports (leafs) and their aggregates (nodes).

Example:

$ devlink port show
pci/0000:03:00.0/0
pci/0000:03:00.0/1

$ devlink port function rate show
pci/0000:03:00.0/0: type leaf
pci/0000:03:00.0/1: type leaf
Co-developed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/devlink.h

@@ -34,6 +34,7 @@ struct devlink_ops;
 struct devlink {
 	struct list_head list;
 	struct list_head port_list;
+	struct list_head rate_list;
 	struct list_head sb_list;
 	struct list_head dpipe_table_list;
 	struct list_head resource_list;
@@ -133,6 +134,15 @@ struct devlink_port_attrs {
 	};
 };
 
+struct devlink_rate {
+	struct list_head list;
+	enum devlink_rate_type type;
+	struct devlink *devlink;
+	void *priv;
+
+	struct devlink_port *devlink_port;
+};
+
 struct devlink_port {
 	struct list_head list;
 	struct list_head param_list;
@@ -152,6 +162,8 @@ struct devlink_port {
 	struct delayed_work type_warn_dw;
 	struct list_head reporter_list;
 	struct mutex reporters_lock; /* Protects reporter_list */
+
+	struct devlink_rate *devlink_rate;
 };
 
 struct devlink_port_new_attrs {
@@ -1512,6 +1524,8 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro
 void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
 				   u32 controller, u16 pf, u32 sf,
 				   bool external);
+int devlink_rate_leaf_create(struct devlink_port *port, void *priv);
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port);
 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,

include/uapi/linux/devlink.h

@@ -126,6 +126,11 @@ enum devlink_command {
 
 	DEVLINK_CMD_HEALTH_REPORTER_TEST,
 
+	DEVLINK_CMD_RATE_GET,		/* can dump */
+	DEVLINK_CMD_RATE_SET,
+	DEVLINK_CMD_RATE_NEW,
+	DEVLINK_CMD_RATE_DEL,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -206,6 +211,10 @@ enum devlink_port_flavour {
 				      */
 };
 
+enum devlink_rate_type {
+	DEVLINK_RATE_TYPE_LEAF,
+};
+
 enum devlink_param_cmode {
 	DEVLINK_PARAM_CMODE_RUNTIME,
 	DEVLINK_PARAM_CMODE_DRIVERINIT,
@@ -534,6 +543,8 @@ enum devlink_attr {
 	DEVLINK_ATTR_RELOAD_ACTION_STATS,       /* nested */
 
 	DEVLINK_ATTR_PORT_PCI_SF_NUMBER,	/* u32 */
+
+	DEVLINK_ATTR_RATE_TYPE,			/* u16 */
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,

net/core/devlink.c

@@ -190,6 +190,25 @@ static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink,
 	return devlink_port_get_from_attrs(devlink, info->attrs);
 }
 
+static inline bool
+devlink_rate_is_leaf(struct devlink_rate *devlink_rate)
+{
+	return devlink_rate->type == DEVLINK_RATE_TYPE_LEAF;
+}
+
+static struct devlink_rate *
+devlink_rate_leaf_get_from_info(struct devlink *devlink, struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink_port *devlink_port;
+
+	devlink_port = devlink_port_get_from_attrs(devlink, info->attrs);
+	if (IS_ERR(devlink_port))
+		return ERR_CAST(devlink_port);
+	devlink_rate = devlink_port->devlink_rate;
+	return devlink_rate ?: ERR_PTR(-ENODEV);
+}
+
 struct devlink_sb {
 	struct list_head list;
 	unsigned int index;
@@ -408,12 +427,13 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 
 #define DEVLINK_NL_FLAG_NEED_PORT		BIT(0)
 #define DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT	BIT(1)
+#define DEVLINK_NL_FLAG_NEED_RATE		BIT(2)
 
 /* The per devlink instance lock is taken by default in the pre-doit
  * operation, yet several commands do not require this. The global
  * devlink lock is taken and protects from disruption by user-calls.
  */
-#define DEVLINK_NL_FLAG_NO_LOCK			BIT(2)
+#define DEVLINK_NL_FLAG_NO_LOCK			BIT(3)
 
 static int devlink_nl_pre_doit(const struct genl_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info)
@@ -442,6 +462,15 @@ static int devlink_nl_pre_doit(const struct genl_ops *ops,
 		devlink_port = devlink_port_get_from_info(devlink, info);
 		if (!IS_ERR(devlink_port))
 			info->user_ptr[1] = devlink_port;
+	} else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_RATE) {
+		struct devlink_rate *devlink_rate;
+
+		devlink_rate = devlink_rate_leaf_get_from_info(devlink, info);
+		if (IS_ERR(devlink_rate)) {
+			err = PTR_ERR(devlink_rate);
+			goto unlock;
+		}
+		info->user_ptr[1] = devlink_rate;
 	}
 	return 0;
 
@@ -749,6 +778,39 @@ devlink_port_fn_hw_addr_fill(struct devlink *devlink, const struct devlink_ops *
 	return 0;
 }
 
+static int devlink_nl_rate_fill(struct sk_buff *msg,
+				struct devlink *devlink,
+				struct devlink_rate *devlink_rate,
+				enum devlink_command cmd, u32 portid,
+				u32 seq, int flags,
+				struct netlink_ext_ack *extack)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_u16(msg, DEVLINK_ATTR_RATE_TYPE, devlink_rate->type))
+		goto nla_put_failure;
+
+	if (devlink_rate_is_leaf(devlink_rate)) {
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				devlink_rate->devlink_port->index))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
 static bool
 devlink_port_fn_state_valid(enum devlink_port_fn_state state)
 {
@@ -920,6 +982,99 @@ static void devlink_port_notify(struct devlink_port *devlink_port,
 				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
 }
 
+static void devlink_rate_notify(struct devlink_rate *devlink_rate,
+				enum devlink_command cmd)
+{
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_RATE_NEW &&
+		cmd != DEVLINK_CMD_RATE_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   cmd, 0, 0, 0, NULL);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg,
+					  struct netlink_callback *cb)
+{
+	struct devlink_rate *devlink_rate;
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err = 0;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		mutex_lock(&devlink->lock);
+		list_for_each_entry(devlink_rate, &devlink->rate_list, list) {
+			enum devlink_command cmd = DEVLINK_CMD_RATE_NEW;
+			u32 id = NETLINK_CB(cb->skb).portid;
+
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_rate_fill(msg, devlink,
+						   devlink_rate,
+						   cmd, id,
+						   cb->nlh->nlmsg_seq,
+						   NLM_F_MULTI, NULL);
+			if (err) {
+				mutex_unlock(&devlink->lock);
+				goto out;
+			}
+			idx++;
+		}
+		mutex_unlock(&devlink->lock);
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+	if (err != -EMSGSIZE)
+		return err;
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static int devlink_nl_cmd_rate_get_doit(struct sk_buff *skb,
+					struct genl_info *info)
+{
+	struct devlink_rate *devlink_rate = info->user_ptr[1];
+	struct devlink *devlink = devlink_rate->devlink;
+	struct sk_buff *msg;
+	int err;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_rate_fill(msg, devlink, devlink_rate,
+				   DEVLINK_CMD_RATE_NEW,
+				   info->snd_portid, info->snd_seq, 0,
+				   info->extack);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
 static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
@@ -7802,6 +7957,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[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 },
+	[DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 },
 };
 
 static const struct genl_small_ops devlink_nl_ops[] = {
@@ -7827,6 +7983,13 @@ static const struct genl_small_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_PORT,
 	},
+	{
+		.cmd = DEVLINK_CMD_RATE_GET,
+		.doit = devlink_nl_cmd_rate_get_doit,
+		.dumpit = devlink_nl_cmd_rate_get_dumpit,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_RATE,
+		/* can be retrieved by unprivileged users */
+	},
 	{
 		.cmd = DEVLINK_CMD_PORT_SPLIT,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -8202,6 +8365,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	xa_init_flags(&devlink->snapshot_ids, XA_FLAGS_ALLOC);
 	__devlink_net_set(devlink, &init_net);
 	INIT_LIST_HEAD(&devlink->port_list);
+	INIT_LIST_HEAD(&devlink->rate_list);
 	INIT_LIST_HEAD(&devlink->sb_list);
 	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	INIT_LIST_HEAD(&devlink->resource_list);
@@ -8304,6 +8468,7 @@ void devlink_free(struct devlink *devlink)
 	WARN_ON(!list_empty(&devlink->resource_list));
 	WARN_ON(!list_empty(&devlink->dpipe_table_list));
 	WARN_ON(!list_empty(&devlink->sb_list));
+	WARN_ON(!list_empty(&devlink->rate_list));
 	WARN_ON(!list_empty(&devlink->port_list));
 
 	xa_destroy(&devlink->snapshot_ids);
@@ -8620,6 +8785,68 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
 
+/**
+ * devlink_rate_leaf_create - create devlink rate leaf
+ *
+ * @devlink_port: devlink port object to create rate object on
+ * @priv: driver private data
+ *
+ * Create devlink rate object of type leaf on provided @devlink_port.
+ * Throws call trace if @devlink_port already has a devlink rate object.
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ *
+ * Return: -ENOMEM if failed to allocate rate object, 0 otherwise.
+ */
+int
+devlink_rate_leaf_create(struct devlink_port *devlink_port, void *priv)
+{
+	struct devlink *devlink = devlink_port->devlink;
+	struct devlink_rate *devlink_rate;
+
+	devlink_rate = kzalloc(sizeof(*devlink_rate), GFP_KERNEL);
+	if (!devlink_rate)
+		return -ENOMEM;
+
+	mutex_lock(&devlink->lock);
+	WARN_ON(devlink_port->devlink_rate);
+	devlink_rate->type = DEVLINK_RATE_TYPE_LEAF;
+	devlink_rate->devlink = devlink;
+	devlink_rate->devlink_port = devlink_port;
+	devlink_rate->priv = priv;
+	list_add_tail(&devlink_rate->list, &devlink->rate_list);
+	devlink_port->devlink_rate = devlink_rate;
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_NEW);
+	mutex_unlock(&devlink->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_create);
+
+/**
+ * devlink_rate_leaf_destroy - destroy devlink rate leaf
+ *
+ * @devlink_port: devlink port linked to the rate object
+ *
+ * Context: Takes and release devlink->lock <mutex>.
+ */
+void devlink_rate_leaf_destroy(struct devlink_port *devlink_port)
+{
+	struct devlink_rate *devlink_rate = devlink_port->devlink_rate;
+	struct devlink *devlink = devlink_port->devlink;
+
+	if (!devlink_rate)
+		return;
+
+	mutex_lock(&devlink->lock);
+	devlink_rate_notify(devlink_rate, DEVLINK_CMD_RATE_DEL);
+	list_del(&devlink_rate->list);
+	devlink_port->devlink_rate = NULL;
+	mutex_unlock(&devlink->lock);
+	kfree(devlink_rate);
+}
+EXPORT_SYMBOL_GPL(devlink_rate_leaf_destroy);
+
 static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 					     char *name, size_t len)
 {