net: introduce TX H/W shaping API

80 lines not on this page · raw message

55 lines not on this page · raw message

127 lines not on this page · raw message

new file mode 100644
index 000000000000..0fe95a03f1b5
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/net_shaper.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_NET_SHAPER_GEN_H
+#define _LINUX_NET_SHAPER_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/net_shaper.h>
+
+/* Common nested types */
+extern const struct nla_policy net_shaper_handle_nl_policy[NET_SHAPER_A_HANDLE_ID + 1];
+extern const struct nla_policy net_shaper_info_nl_policy[NET_SHAPER_A_WEIGHT + 1];
+extern const struct nla_policy net_shaper_node_info_nl_policy[NET_SHAPER_A_PARENT + 1];
+
+int net_shaper_nl_pre_doit(const struct genl_split_ops *ops,
+			   struct sk_buff *skb, struct genl_info *info);
+void
+net_shaper_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+			struct genl_info *info);
+int net_shaper_nl_pre_dumpit(struct netlink_callback *cb);
+int net_shaper_nl_post_dumpit(struct netlink_callback *cb);
+
+int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_delete_doit(struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info);
+
+extern struct genl_family net_shaper_nl_family;
+
+#endif /* _LINUX_NET_SHAPER_GEN_H */

index fce70990b209..71bd011fde7b 100644
@@ -1603,6 +1603,14 @@ struct net_device_ops {
 	int			(*ndo_hwtstamp_set)(struct net_device *dev,
 						    struct kernel_hwtstamp_config *kernel_config,
 						    struct netlink_ext_ack *extack);
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	/**
+	 * @net_shaper_ops: Device shaping offload operations
+	 * see include/net/net_shapers.h
+	 */
+	const struct net_shaper_ops *net_shaper_ops;
+#endif
 };
 
 /**

@@ -2383,6 +2391,13 @@ struct net_device {
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
 
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	/**
+	 * @net_shaper_data: data tracking the current shaper status
+	 *  see include/net/net_shapers.h
+	 */
+	struct net_shaper_data *net_shaper_data;
+#endif
 	u8			priv[] ____cacheline_aligned
 				       __counted_by(priv_len);
 } ____cacheline_aligned;

121 lines not on this page · raw message

index 63987b8b7c85..23629abd3ef7 100644
@@ -11201,6 +11201,8 @@ void free_netdev(struct net_device *dev)
 	/* Flush device addresses */
 	dev_addr_flush(dev);
 
+	net_shaper_flush_netdev(dev);
+
 	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
 		netif_napi_del(p);
 

index 5654325c5b71..13c558874af3 100644
@@ -35,6 +35,12 @@ void dev_addr_flush(struct net_device *dev);
 int dev_addr_init(struct net_device *dev);
 void dev_addr_check(struct net_device *dev);
 
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+void net_shaper_flush_netdev(struct net_device *dev);
+#else
+static inline void net_shaper_flush_netdev(struct net_device *dev) {}
+#endif
+
 /* sysctls not referred to from outside net/core/ */
 extern int		netdev_unregister_timeout_secs;
 extern int		weight_p;

400 lines not on this page · raw message

index 2ed80df25765..a58bdd2ec013 100644
@@ -23,6 +23,10 @@
 
 struct net_shaper_data {
 	struct xarray shapers;
+
+	/* Serialize write ops and protects node_ids updates. */
+	struct mutex lock;
+	struct idr node_ids;
 };
 
 struct net_shaper_nl_ctx {

@@ -47,6 +51,27 @@ net_shaper_binding_data(struct net_shaper_binding *binding)
 	return NULL;
 }
 
+static struct net_shaper_data *
+net_shaper_binding_set_data(struct net_shaper_binding *binding,
+			    struct net_shaper_data *data)
+{
+	if (binding->type == NET_SHAPER_BINDING_TYPE_NETDEV)
+		return cmpxchg(&binding->netdev->net_shaper_data, NULL, data);
+
+	/* No devlink implementation yet.*/
+	return NULL;
+}
+
+static const struct net_shaper_ops *
+net_shaper_binding_ops(struct net_shaper_binding *binding)
+{
+	if (binding->type == NET_SHAPER_BINDING_TYPE_NETDEV)
+		return binding->netdev->netdev_ops->net_shaper_ops;
+
+	/* No devlink implementation yet.*/
+	return NULL;
+}
+
 static int net_shaper_fill_binding(struct sk_buff *msg,
 				   const struct net_shaper_binding *binding,
 				   u32 type)

@@ -178,6 +203,26 @@ static void net_shaper_index_to_handle(u32 index,
 	handle->id = FIELD_GET(NET_SHAPER_ID_MASK, index);
 }
 
+static void net_shaper_default_parent(const struct net_shaper_handle *handle,
+				      struct net_shaper_handle *parent)
+{
+	switch (handle->scope) {
+	case NET_SHAPER_SCOPE_UNSPEC:
+	case NET_SHAPER_SCOPE_NETDEV:
+	case __NET_SHAPER_SCOPE_MAX:
+		parent->scope = NET_SHAPER_SCOPE_UNSPEC;
+		break;
+
+	case NET_SHAPER_SCOPE_QUEUE:
+	case NET_SHAPER_SCOPE_NODE:
+		parent->scope = NET_SHAPER_SCOPE_NETDEV;
+		break;
+	}
+	parent->id = 0;
+}
+
+#define NET_SHAPER_CACHE_NOT_VALID XA_MARK_0
+
 /* Lookup the given shaper inside the cache. */
 static struct net_shaper_info *
 net_shaper_cache_lookup(struct net_shaper_binding *binding,

@@ -186,7 +231,132 @@ net_shaper_cache_lookup(struct net_shaper_binding *binding,
 	struct net_shaper_data *data = net_shaper_binding_data(binding);
 	u32 index = net_shaper_handle_to_index(handle);
 
-	return data ? xa_load(&data->shapers, index) : NULL;
+	if (!data || xa_get_mark(&data->shapers, index,
+				 NET_SHAPER_CACHE_NOT_VALID))
+		return NULL;
+
+	return xa_load(&data->shapers, index);
+}
+
+/* Allocate on demand the per device shaper's cache. */
+static struct net_shaper_data *
+net_shaper_cache_init(struct net_shaper_binding *binding,
+		      struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *new, *data = net_shaper_binding_data(binding);
+
+	if (!data) {
+		new = kmalloc(sizeof(*data), GFP_KERNEL);
+		if (!new) {
+			NL_SET_ERR_MSG(extack, "Can't allocate memory for shaper data");
+			return NULL;
+		}
+
+		mutex_init(&new->lock);
+		xa_init(&new->shapers);
+		idr_init(&new->node_ids);
+
+		/* No lock acquired yet, we can race with other operations. */
+		data = net_shaper_binding_set_data(binding, new);
+		if (!data)
+			data = new;
+		else
+			kfree(new);
+	}
+	return data;
+}
+
+/* Prepare the cache to actually insert the given shaper, doing
+ * in advance the needed allocations.
+ */
+static int net_shaper_cache_pre_insert(struct net_shaper_binding *binding,
+				       struct net_shaper_handle *handle,
+				       struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_info *prev, *cur;
+	bool id_allocated = false;
+	int ret, id, index;
+
+	if (!data)
+		return -ENOMEM;
+
+	index = net_shaper_handle_to_index(handle);
+	cur = xa_load(&data->shapers, index);
+	if (cur)
+		return 0;
+
+	/* Allocated a new id, if needed. */
+	if (handle->scope == NET_SHAPER_SCOPE_NODE &&
+	    handle->id == NET_SHAPER_ID_UNSPEC) {
+		id = idr_alloc(&data->node_ids, NULL,
+			       0, NET_SHAPER_ID_UNSPEC, GFP_ATOMIC);
+
+		if (id < 0) {
+			NL_SET_ERR_MSG(extack, "Can't allocate new id for NODE shaper");
+			return id;
+		}
+
+		handle->id = id;
+		index = net_shaper_handle_to_index(handle);
+		id_allocated = true;
+	}
+
+	cur = kmalloc(sizeof(*cur), GFP_KERNEL | __GFP_ZERO);
+	if (!cur) {
+		NL_SET_ERR_MSG(extack, "Can't allocate memory for cached shaper");
+		ret = -ENOMEM;
+		goto free_id;
+	}
+
+	/* Mark 'tentative' shaper inside the cache. */
+	xa_lock(&data->shapers);
+	prev = __xa_store(&data->shapers, index, cur, GFP_KERNEL);
+	__xa_set_mark(&data->shapers, index, NET_SHAPER_CACHE_NOT_VALID);
+	xa_unlock(&data->shapers);
+	if (xa_err(prev)) {
+		NL_SET_ERR_MSG(extack, "Can't insert shaper into cache");
+		kfree(cur);
+		ret = xa_err(prev);
+		goto free_id;
+	}
+	return 0;
+
+free_id:
+	if (id_allocated)
+		idr_remove(&data->node_ids, handle->id);
+	return ret;
+}
+
+/* Commit the tentative insert with the actual values.
+ * Must be called only after a successful net_shaper_pre_insert().
+ */
+static void net_shaper_cache_commit(struct net_shaper_binding *binding,
+				    int nr_shapers,
+				    const struct net_shaper_handle *handle,
+				    const struct net_shaper_info *shapers)
+{
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_info *cur;
+	int index;
+	int i;
+
+	xa_lock(&data->shapers);
+	for (i = 0; i < nr_shapers; ++i) {
+		index = net_shaper_handle_to_index(&handle[i]);
+
+		cur = xa_load(&data->shapers, index);
+		if (WARN_ON_ONCE(!cur))
+			continue;
+
+		/* Successful update: drop the tentative mark
+		 * and update the cache.
+		 */
+		__xa_clear_mark(&data->shapers, index,
+				NET_SHAPER_CACHE_NOT_VALID);
+		*cur = shapers[i];
+	}
+	xa_unlock(&data->shapers);
 }
 
 static int net_shaper_parse_handle(const struct nlattr *attr,

@@ -227,6 +397,85 @@ static int net_shaper_parse_handle(const struct nlattr *attr,
 	return 0;
 }
 
+static int net_shaper_parse_info(struct net_shaper_binding *binding,
+				 struct nlattr **tb,
+				 const struct genl_info *info,
+				 struct net_shaper_handle *handle,
+				 struct net_shaper_info *shaper,
+				 bool *cached)
+{
+	struct net_shaper_info *old;
+	int ret;
+
+	/* The shaper handle is the only mandatory attribute. */
+	if (NL_REQ_ATTR_CHECK(info->extack, NULL, tb, NET_SHAPER_A_HANDLE))
+		return -EINVAL;
+
+	ret = net_shaper_parse_handle(tb[NET_SHAPER_A_HANDLE], info, handle);
+	if (ret)
+		return ret;
+
+	if (handle->scope == NET_SHAPER_SCOPE_UNSPEC) {
+		NL_SET_BAD_ATTR(info->extack,
+				info->attrs[NET_SHAPER_A_HANDLE]);
+		return -EINVAL;
+	}
+
+	/* Fetch existing data, if any, so that user provide info will
+	 * incrementally update the existing shaper configuration.
+	 */
+	old = net_shaper_cache_lookup(binding, handle);
+	if (old)
+		*shaper = *old;
+	*cached = !!old;
+
+	if (tb[NET_SHAPER_A_METRIC])
+		shaper->metric = nla_get_u32(tb[NET_SHAPER_A_METRIC]);
+
+	if (tb[NET_SHAPER_A_BW_MIN])
+		shaper->bw_min = nla_get_uint(tb[NET_SHAPER_A_BW_MIN]);
+
+	if (tb[NET_SHAPER_A_BW_MAX])
+		shaper->bw_max = nla_get_uint(tb[NET_SHAPER_A_BW_MAX]);
+
+	if (tb[NET_SHAPER_A_BURST])
+		shaper->burst = nla_get_uint(tb[NET_SHAPER_A_BURST]);
+
+	if (tb[NET_SHAPER_A_PRIORITY])
+		shaper->priority = nla_get_u32(tb[NET_SHAPER_A_PRIORITY]);
+
+	if (tb[NET_SHAPER_A_WEIGHT])
+		shaper->weight = nla_get_u32(tb[NET_SHAPER_A_WEIGHT]);
+	return 0;
+}
+
+/* Fetch the cached shaper info and update them with the user-provided
+ * attributes.
+ */
+static int net_shaper_parse_info_nest(struct net_shaper_binding *binding,
+				      const struct nlattr *attr,
+				      const struct genl_info *info,
+				      struct net_shaper_handle *handle,
+				      struct net_shaper_info *shaper)
+{
+	struct nlattr *tb[NET_SHAPER_A_WEIGHT + 1];
+	bool cached;
+	int ret;
+
+	ret = nla_parse_nested(tb, NET_SHAPER_A_WEIGHT, attr,
+			       net_shaper_info_nl_policy, info->extack);
+	if (ret < 0)
+		return ret;
+
+	ret = net_shaper_parse_info(binding, tb, info, handle, shaper, &cached);
+	if (ret < 0)
+		return ret;
+
+	if (!cached)
+		net_shaper_default_parent(handle, &shaper->parent);
+	return 0;
+}
+
 static int net_shaper_generic_pre(struct genl_info *info, int type)
 {
 	struct net_shaper_nl_ctx *ctx;

@@ -358,14 +607,153 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb,
 	return 0;
 }
 
+/* Update the H/W and on success update the local cache, too. */
+static int net_shaper_set(struct net_shaper_binding *binding,
+			  const struct net_shaper_handle *h,
+			  const struct net_shaper_info *shaper,
+			  struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *data = net_shaper_cache_init(binding, extack);
+	const struct net_shaper_ops *ops = net_shaper_binding_ops(binding);
+	struct net_shaper_handle handle = *h;
+	int ret;
+
+	if (!data)
+		return -ENOMEM;
+
+	/* Should never happen: binding lookup validates the ops presence */
+	if (WARN_ON_ONCE(!ops))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&data->lock);
+	if (handle.scope == NET_SHAPER_SCOPE_NODE &&
+	    net_shaper_cache_lookup(binding, &handle)) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = net_shaper_cache_pre_insert(binding, &handle, extack);
+	if (ret)
+		goto unlock;
+
+	ret = ops->set(binding, &handle, shaper, extack);
+	net_shaper_cache_commit(binding, 1, &handle, shaper);
+
+unlock:
+	mutex_unlock(&data->lock);
+	return ret;
+}
+
 int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct net_shaper_binding *binding;
+	struct net_shaper_handle handle;
+	struct net_shaper_info shaper;
+	struct nlattr *attr;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_SHAPER))
+		return -EINVAL;
+
+	binding = net_shaper_binding_from_ctx(info->user_ptr[0]);
+	attr = info->attrs[NET_SHAPER_A_SHAPER];
+	ret = net_shaper_parse_info_nest(binding, attr, info, &handle,
+					 &shaper);
+	if (ret)
+		return ret;
+
+	return net_shaper_set(binding, &handle, &shaper, info->extack);
+}
+
+static int __net_shaper_delete(struct net_shaper_binding *binding,
+			       const struct net_shaper_handle *h,
+			       struct net_shaper_info *shaper,
+			       struct netlink_ext_ack *extack)
+{
+	const struct net_shaper_ops *ops = net_shaper_binding_ops(binding);
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_handle parent_handle, handle = *h;
+	int ret;
+
+	/* Should never happen: we are under the cache lock, the cache
+	 * is already initialized.
+	 */
+	if (WARN_ON_ONCE(!data || !ops))
+		return -EINVAL;
+
+again:
+	parent_handle = shaper->parent;
+
+	ret = ops->delete(binding, &handle, extack);
+	if (ret < 0)
+		return ret;
+
+	xa_erase(&data->shapers, net_shaper_handle_to_index(&handle));
+	if (handle.scope == NET_SHAPER_SCOPE_NODE)
+		idr_remove(&data->node_ids, handle.id);
+	kfree(shaper);
+
+	/* Eventually delete the parent, if it is left over with no leaves. */
+	if (parent_handle.scope == NET_SHAPER_SCOPE_NODE) {
+		shaper = net_shaper_cache_lookup(binding, &parent_handle);
+		if (shaper && !--shaper->leaves) {
+			handle = parent_handle;
+			goto again;
+		}
+	}
+	return 0;
+}
+
+static int net_shaper_delete(struct net_shaper_binding *binding,
+			     const struct net_shaper_handle *handle,
+			     struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_info *shaper;
+	int ret;
+
+	/* The lock is null when the cache is not initialized, and thus
+	 * no shaper has been created yet.
+	 */
+	if (!data)
+		return -ENOENT;
+
+	mutex_lock(&data->lock);
+	shaper = net_shaper_cache_lookup(binding, handle);
+	if (!shaper) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	if (handle->scope == NET_SHAPER_SCOPE_NODE) {
+		/* TODO: implement support for scope NODE delete. */
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ret = __net_shaper_delete(binding, handle, shaper, extack);
+
+unlock:
+	mutex_unlock(&data->lock);
+	return ret;
 }
 
 int net_shaper_nl_delete_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct net_shaper_binding *binding;
+	struct net_shaper_handle handle;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_HANDLE))
+		return -EINVAL;
+
+	binding = net_shaper_binding_from_ctx(info->user_ptr[0]);
+	ret = net_shaper_parse_handle(info->attrs[NET_SHAPER_A_HANDLE], info,
+				      &handle);
+	if (ret)
+		return ret;
+
+	return net_shaper_delete(binding, &handle, info->extack);
 }
 
 static void net_shaper_flush(struct net_shaper_binding *binding)

@@ -377,12 +765,16 @@ static void net_shaper_flush(struct net_shaper_binding *binding)
 	if (!data)
 		return;
 
+	mutex_lock(&data->lock);
 	xa_lock(&data->shapers);
 	xa_for_each(&data->shapers, index, cur) {
 		__xa_erase(&data->shapers, index);
 		kfree(cur);
 	}
 	xa_unlock(&data->shapers);
+	idr_destroy(&data->node_ids);
+	mutex_unlock(&data->lock);
+
 	kfree(data);
 }
 

index a58bdd2ec013..f5e8464b8408 100644
@@ -72,6 +72,24 @@ net_shaper_binding_ops(struct net_shaper_binding *binding)
 	return NULL;
 }
 
+/* Count the number of [multi] attributes of the given type. */
+static int net_shaper_list_len(struct genl_info *info, int type)
+{
+	struct nlattr *attr;
+	int rem, cnt = 0;
+
+	nla_for_each_attr_type(attr, type, genlmsg_data(info->genlhdr),
+			       genlmsg_len(info->genlhdr), rem)
+		cnt++;
+	return cnt;
+}
+
+static int net_shaper_handle_size(void)
+{
+	return nla_total_size(nla_total_size(sizeof(u32)) +
+			      nla_total_size(sizeof(u32)));
+}
+
 static int net_shaper_fill_binding(struct sk_buff *msg,
 				   const struct net_shaper_binding *binding,
 				   u32 type)

@@ -359,6 +377,29 @@ static void net_shaper_cache_commit(struct net_shaper_binding *binding,
 	xa_unlock(&data->shapers);
 }
 
+/* Rollback all the tentative inserts from the shaper cache. */
+static void net_shaper_cache_rollback(struct net_shaper_binding *binding)
+{
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_handle handle;
+	struct net_shaper_info *cur;
+	unsigned long index;
+
+	if (!data)
+		return;
+
+	xa_lock(&data->shapers);
+	xa_for_each_marked(&data->shapers, index, cur,
+			   NET_SHAPER_CACHE_NOT_VALID) {
+		net_shaper_index_to_handle(index, &handle);
+		if (handle.scope == NET_SHAPER_SCOPE_NODE)
+			idr_remove(&data->node_ids, handle.id);
+		__xa_erase(&data->shapers, index);
+		kfree(cur);
+	}
+	xa_unlock(&data->shapers);
+}
+
 static int net_shaper_parse_handle(const struct nlattr *attr,
 				   const struct genl_info *info,
 				   struct net_shaper_handle *handle)

@@ -455,6 +496,7 @@ static int net_shaper_parse_info(struct net_shaper_binding *binding,
 static int net_shaper_parse_info_nest(struct net_shaper_binding *binding,
 				      const struct nlattr *attr,
 				      const struct genl_info *info,
+				      enum net_shaper_scope expected_scope,
 				      struct net_shaper_handle *handle,
 				      struct net_shaper_info *shaper)
 {

@@ -471,11 +513,62 @@ static int net_shaper_parse_info_nest(struct net_shaper_binding *binding,
 	if (ret < 0)
 		return ret;
 
+	if (expected_scope != NET_SHAPER_SCOPE_UNSPEC &&
+	    handle->scope != expected_scope) {
+		NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
+		return -EINVAL;
+	}
+
 	if (!cached)
 		net_shaper_default_parent(handle, &shaper->parent);
 	return 0;
 }
 
+/* Alike net_parse_shaper_info(), but additionally allow the user specifying
+ * the shaper's parent handle.
+ */
+static int net_shaper_parse_node(struct net_shaper_binding *binding,
+				 const struct nlattr *attr,
+				 const struct genl_info *info,
+				 struct net_shaper_handle *handle,
+				 struct net_shaper_info *shaper)
+{
+	struct nlattr *tb[NET_SHAPER_A_PARENT + 1];
+	bool cached;
+	int ret;
+
+	ret = nla_parse_nested(tb, NET_SHAPER_A_PARENT, attr,
+			       net_shaper_node_info_nl_policy,
+			       info->extack);
+	if (ret < 0)
+		return ret;
+
+	ret = net_shaper_parse_info(binding, tb, info, handle, shaper,
+				    &cached);
+	if (ret)
+		return ret;
+
+	if (handle->scope != NET_SHAPER_SCOPE_NODE &&
+	    handle->scope != NET_SHAPER_SCOPE_NETDEV) {
+		NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
+		return -EINVAL;
+	}
+
+	if (tb[NET_SHAPER_A_PARENT]) {
+		ret = net_shaper_parse_handle(tb[NET_SHAPER_A_PARENT], info,
+					      &shaper->parent);
+		if (ret)
+			return ret;
+
+		if (shaper->parent.scope != NET_SHAPER_SCOPE_NODE &&
+		    shaper->parent.scope != NET_SHAPER_SCOPE_NETDEV) {
+			NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_PARENT]);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 static int net_shaper_generic_pre(struct genl_info *info, int type)
 {
 	struct net_shaper_nl_ctx *ctx;

@@ -657,8 +750,9 @@ int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info)
 
 	binding = net_shaper_binding_from_ctx(info->user_ptr[0]);
 	attr = info->attrs[NET_SHAPER_A_SHAPER];
-	ret = net_shaper_parse_info_nest(binding, attr, info, &handle,
-					 &shaper);
+	ret = net_shaper_parse_info_nest(binding, attr, info,
+					 NET_SHAPER_SCOPE_UNSPEC,
+					 &handle, &shaper);
 	if (ret)
 		return ret;
 

@@ -704,6 +798,100 @@ static int __net_shaper_delete(struct net_shaper_binding *binding,
 	return 0;
 }
 
+static int __net_shaper_group(struct net_shaper_binding *binding,
+			      int leaves_count,
+			      const struct net_shaper_handle *leaves_handles,
+			      struct net_shaper_info *leaves,
+			      struct net_shaper_handle *node_handle,
+			      struct net_shaper_info *node,
+			      struct netlink_ext_ack *extack)
+{
+	const struct net_shaper_ops *ops = net_shaper_binding_ops(binding);
+	struct net_shaper_info *parent = NULL;
+	struct net_shaper_handle leaf_handle;
+	int i, ret;
+
+	if (node_handle->scope == NET_SHAPER_SCOPE_NODE) {
+		if (node_handle->id != NET_SHAPER_ID_UNSPEC &&
+		    !net_shaper_cache_lookup(binding, node_handle)) {
+			NL_SET_ERR_MSG_FMT(extack, "Node shaper %d:%d does not exists",
+					   node_handle->scope, node_handle->id);
+			return -ENOENT;
+		}
+
+		/* When unspecified, the node parent scope is inherited from
+		 * the leaves.
+		 */
+		if (node->parent.scope == NET_SHAPER_SCOPE_UNSPEC) {
+			for (i = 1; i < leaves_count; ++i) {
+				if (leaves[i].parent.scope !=
+				    leaves[0].parent.scope ||
+				    leaves[i].parent.id !=
+				    leaves[0].parent.id) {
+					NL_SET_ERR_MSG_FMT(extack, "All the leaves shapers must have the same old parent");
+					return -EINVAL;
+				}
+			}
+
+			if (leaves_count > 0)
+				node->parent = leaves[0].parent;
+		}
+
+	} else {
+		net_shaper_default_parent(node_handle, &node->parent);
+	}
+
+	if (node->parent.scope == NET_SHAPER_SCOPE_NODE) {
+		parent = net_shaper_cache_lookup(binding, &node->parent);
+		if (!parent) {
+			NL_SET_ERR_MSG_FMT(extack, "Node parent shaper %d:%d does not exists",
+					   node->parent.scope, node->parent.id);
+			return -ENOENT;
+		}
+	}
+
+	/* For newly created node scope shaper, the following will update
+	 * the handle, due to id allocation.
+	 */
+	ret = net_shaper_cache_pre_insert(binding, node_handle, extack);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < leaves_count; ++i) {
+		leaf_handle = leaves_handles[i];
+
+		ret = net_shaper_cache_pre_insert(binding, &leaf_handle,
+						  extack);
+		if (ret)
+			goto rollback;
+
+		if (leaves[i].parent.scope == node_handle->scope &&
+		    leaves[i].parent.id == node_handle->id)
+			continue;
+
+		/* The leaves shapers will be nested to the node, update the
+		 * linking accordingly.
+		 */
+		leaves[i].parent = *node_handle;
+		node->leaves++;
+	}
+
+	ret = ops->group(binding, leaves_count, leaves_handles, leaves,
+			 node_handle, node, extack);
+	if (ret < 0)
+		goto rollback;
+
+	if (parent)
+		parent->leaves++;
+	net_shaper_cache_commit(binding, 1, node_handle, node);
+	net_shaper_cache_commit(binding, leaves_count, leaves_handles, leaves);
+	return 0;
+
+rollback:
+	net_shaper_cache_rollback(binding);
+	return ret;
+}
+
 static int net_shaper_delete(struct net_shaper_binding *binding,
 			     const struct net_shaper_handle *handle,
 			     struct netlink_ext_ack *extack)

@@ -756,6 +944,162 @@ int net_shaper_nl_delete_doit(struct sk_buff *skb, struct genl_info *info)
 	return net_shaper_delete(binding, &handle, info->extack);
 }
 
+/* Update the H/W and on success update the local cache, too */
+static int net_shaper_group(struct net_shaper_binding *binding,
+			    int leaves_count,
+			    const struct net_shaper_handle *leaves_handles,
+			    struct net_shaper_info *leaves,
+			    struct net_shaper_handle *node_handle,
+			    struct net_shaper_info *node,
+			    struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *data = net_shaper_cache_init(binding, extack);
+	struct net_shaper_handle *old_nodes;
+	int i, ret, old_nodes_count = 0;
+
+	if (!data)
+		return -ENOMEM;
+
+	old_nodes = kcalloc(leaves_count, sizeof(struct net_shaper_handle),
+			    GFP_KERNEL);
+	if (!old_nodes)
+		return -ENOMEM;
+
+	for (i = 0; i < leaves_count; i++)
+		if (leaves[i].parent.scope == NET_SHAPER_SCOPE_NODE &&
+		    (leaves[i].parent.scope != node_handle->scope ||
+		     leaves[i].parent.id != node_handle->id))
+			old_nodes[old_nodes_count++] = leaves[i].parent;
+
+	mutex_lock(&data->lock);
+	ret = __net_shaper_group(binding, leaves_count, leaves_handles,
+				 leaves, node_handle, node, extack);
+
+	/* Check if we need to delete any NODE left alone by the new leaves
+	 * linkage.
+	 */
+	for (i = 0; i < old_nodes_count; ++i) {
+		node = net_shaper_cache_lookup(binding, &old_nodes[i]);
+		if (!node)
+			continue;
+
+		if (--node->leaves > 0)
+			continue;
+
+		/* Errors here are not fatal: the grouping operation is
+		 * completed, and user-space can still explicitly clean-up
+		 * left-over nodes.
+		 */
+		__net_shaper_delete(binding, &old_nodes[i], node, extack);
+	}
+
+	mutex_unlock(&data->lock);
+
+	kfree(old_nodes);
+	return ret;
+}
+
+static int net_shaper_group_send_reply(struct genl_info *info,
+				       struct net_shaper_handle *handle)
+{
+	struct net_shaper_binding *binding = info->user_ptr[0];
+	struct sk_buff *msg;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	/* Prepare the msg reply in advance, to avoid device operation
+	 * rollback.
+	 */
+	msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL);
+	if (!msg)
+		return ret;
+
+	hdr = genlmsg_iput(msg, info);
+	if (!hdr)
+		goto free_msg;
+
+	if (net_shaper_fill_binding(msg, binding, NET_SHAPER_A_IFINDEX))
+		goto free_msg;
+
+	if (net_shaper_fill_handle(msg, handle, NET_SHAPER_A_HANDLE))
+		goto free_msg;
+
+	genlmsg_end(msg, hdr);
+
+	ret = genlmsg_reply(msg, info);
+	if (ret)
+		goto free_msg;
+
+	return ret;
+
+free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
+int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_shaper_handle *leaves_handles, node_handle;
+	struct net_shaper_info *leaves, node;
+	struct net_shaper_binding *binding;
+	int i, ret, rem, leaves_count;
+	struct nlattr *attr;
+
+	if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_LEAVES) ||
+	    GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_NODE))
+		return -EINVAL;
+
+	binding = net_shaper_binding_from_ctx(info->user_ptr[0]);
+	leaves_count = net_shaper_list_len(info, NET_SHAPER_A_LEAVES);
+	leaves = kcalloc(leaves_count, sizeof(struct net_shaper_info) +
+			 sizeof(struct net_shaper_handle), GFP_KERNEL);
+	if (!leaves) {
+		GENL_SET_ERR_MSG_FMT(info, "Can't allocate memory for %d leaves shapers",
+				     leaves_count);
+		return -ENOMEM;
+	}
+	leaves_handles = (struct net_shaper_handle *)&leaves[leaves_count];
+
+	ret = net_shaper_parse_node(binding, info->attrs[NET_SHAPER_A_NODE],
+				    info, &node_handle, &node);
+	if (ret)
+		goto free_shapers;
+
+	i = 0;
+	nla_for_each_attr_type(attr, NET_SHAPER_A_LEAVES,
+			       genlmsg_data(info->genlhdr),
+			       genlmsg_len(info->genlhdr), rem) {
+		if (WARN_ON_ONCE(i >= leaves_count))
+			goto free_shapers;
+
+		ret = net_shaper_parse_info_nest(binding, attr, info,
+						 NET_SHAPER_SCOPE_QUEUE,
+						 &leaves_handles[i],
+						 &leaves[i]);
+		if (ret)
+			goto free_shapers;
+		i++;
+	}
+
+	ret = net_shaper_group(binding, leaves_count, leaves_handles, leaves,
+			       &node_handle, &node, info->extack);
+	if (ret < 0)
+		goto free_shapers;
+
+	ret = net_shaper_group_send_reply(info, &node_handle);
+	if (ret) {
+		/* Error on reply is not fatal to avoid rollback a successful
+		 * configuration.
+		 */
+		GENL_SET_ERR_MSG_FMT(info, "Can't send reply %d", ret);
+		ret = 0;
+	}
+
+free_shapers:
+	kfree(leaves);
+	return ret;
+}
+
 static void net_shaper_flush(struct net_shaper_binding *binding)
 {
 	struct net_shaper_data *data = net_shaper_binding_data(binding);

index f5e8464b8408..f0d594a34588 100644
@@ -799,7 +799,7 @@ static int __net_shaper_delete(struct net_shaper_binding *binding,
 }
 
 static int __net_shaper_group(struct net_shaper_binding *binding,
-			      int leaves_count,
+			      bool cache_node, int leaves_count,
 			      const struct net_shaper_handle *leaves_handles,
 			      struct net_shaper_info *leaves,
 			      struct net_shaper_handle *node_handle,

@@ -850,12 +850,15 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
 		}
 	}
 
-	/* For newly created node scope shaper, the following will update
-	 * the handle, due to id allocation.
-	 */
-	ret = net_shaper_cache_pre_insert(binding, node_handle, extack);
-	if (ret)
-		return ret;
+	if (cache_node) {
+		/* For newly created node scope shaper, the following will
+		 * update the handle, due to id allocation.
+		 */
+		ret = net_shaper_cache_pre_insert(binding, node_handle,
+						  extack);
+		if (ret)
+			return ret;
+	}
 
 	for (i = 0; i < leaves_count; ++i) {
 		leaf_handle = leaves_handles[i];

@@ -883,7 +886,8 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
 
 	if (parent)
 		parent->leaves++;
-	net_shaper_cache_commit(binding, 1, node_handle, node);
+	if (cache_node)
+		net_shaper_cache_commit(binding, 1, node_handle, node);
 	net_shaper_cache_commit(binding, leaves_count, leaves_handles, leaves);
 	return 0;
 

@@ -892,6 +896,76 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
 	return ret;
 }
 
+static int __net_shaper_pre_del_node(struct net_shaper_binding *binding,
+				     const struct net_shaper_handle *handle,
+				     const struct net_shaper_info *shaper,
+				     struct netlink_ext_ack *extack)
+{
+	struct net_shaper_data *data = net_shaper_binding_data(binding);
+	struct net_shaper_handle *leaves_handles, node_handle;
+	struct net_shaper_info *cur, *leaves, node = {};
+	int ret, leaves_count = 0;
+	unsigned long index;
+	bool cache_node;
+
+	if (!shaper->leaves)
+		return 0;
+
+	if (WARN_ON_ONCE(!data))
+		return -EINVAL;
+
+	/* Fetch the new node information. */
+	node_handle = shaper->parent;
+	cur = net_shaper_cache_lookup(binding, &node_handle);
+	if (cur) {
+		node = *cur;
+	} else {
+		/* A scope NODE shaper can be nested only to the NETDEV scope
+		 * shaper without creating the latter, this check may fail only
+		 * if the cache is in inconsistent status.
+		 */
+		if (WARN_ON_ONCE(node_handle.scope != NET_SHAPER_SCOPE_NETDEV))
+			return -EINVAL;
+	}
+
+	leaves = kcalloc(shaper->leaves,
+			 sizeof(struct net_shaper_info) +
+			 sizeof(struct net_shaper_handle), GFP_KERNEL);
+	if (!leaves)
+		return -ENOMEM;
+
+	leaves_handles = (struct net_shaper_handle *)&leaves[shaper->leaves];
+
+	/* Build the leaves arrays. */
+	xa_for_each(&data->shapers, index, cur) {
+		if (cur->parent.scope != handle->scope ||
+		    cur->parent.id != handle->id)
+			continue;
+
+		if (WARN_ON_ONCE(leaves_count == shaper->leaves)) {
+			ret = -EINVAL;
+			goto free;
+		}
+
+		net_shaper_index_to_handle(index,
+					   &leaves_handles[leaves_count]);
+		leaves[leaves_count++] = *cur;
+	}
+
+	/* When re-linking to the netdev shaper, avoid the eventual, implicit,
+	 * creation of the new node, would be surprising since the user is
+	 * doing a delete operation.
+	 */
+	cache_node = node_handle.scope != NET_SHAPER_SCOPE_NETDEV;
+	ret = __net_shaper_group(binding, cache_node, leaves_count,
+				 leaves_handles, leaves, &node_handle, &node,
+				 extack);
+
+free:
+	kfree(leaves);
+	return ret;
+}
+
 static int net_shaper_delete(struct net_shaper_binding *binding,
 			     const struct net_shaper_handle *handle,
 			     struct netlink_ext_ack *extack)

@@ -914,9 +988,10 @@ static int net_shaper_delete(struct net_shaper_binding *binding,
 	}
 
 	if (handle->scope == NET_SHAPER_SCOPE_NODE) {
-		/* TODO: implement support for scope NODE delete. */
-		ret = -EINVAL;
-		goto unlock;
+		ret = __net_shaper_pre_del_node(binding, handle, shaper,
+						extack);
+		if (ret)
+			goto unlock;
 	}
 
 	ret = __net_shaper_delete(binding, handle, shaper, extack);

@@ -972,7 +1047,7 @@ static int net_shaper_group(struct net_shaper_binding *binding,
 			old_nodes[old_nodes_count++] = leaves[i].parent;
 
 	mutex_lock(&data->lock);
-	ret = __net_shaper_group(binding, leaves_count, leaves_handles,
+	ret = __net_shaper_group(binding, true, leaves_count, leaves_handles,
 				 leaves, node_handle, node, extack);
 
 	/* Check if we need to delete any NODE left alone by the new leaves

index 03c774a2bec1..c0112119ca2a 100644
@@ -67,11 +67,28 @@ enum {
 	NET_SHAPER_A_HANDLE_MAX = (__NET_SHAPER_A_HANDLE_MAX - 1)
 };
 
+enum {
+	NET_SHAPER_A_CAPABILITIES_IFINDEX = 1,
+	NET_SHAPER_A_CAPABILITIES_SCOPE,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_METRIC_BPS,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_METRIC_PPS,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_NESTING,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_BW_MIN,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_BW_MAX,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_BURST,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_PRIORITY,
+	NET_SHAPER_A_CAPABILITIES_SUPPORT_WEIGHT,
+
+	__NET_SHAPER_A_CAPABILITIES_MAX,
+	NET_SHAPER_A_CAPABILITIES_MAX = (__NET_SHAPER_A_CAPABILITIES_MAX - 1)
+};
+
 enum {
 	NET_SHAPER_CMD_GET = 1,
 	NET_SHAPER_CMD_SET,
 	NET_SHAPER_CMD_DELETE,
 	NET_SHAPER_CMD_GROUP,
+	NET_SHAPER_CMD_CAP_GET,
 
 	__NET_SHAPER_CMD_MAX,
 	NET_SHAPER_CMD_MAX = (__NET_SHAPER_CMD_MAX - 1)

index f0d594a34588..98e17a95f39f 100644
@@ -626,6 +626,27 @@ int net_shaper_nl_post_dumpit(struct netlink_callback *cb)
 	return 0;
 }
 
+int net_shaper_nl_cap_pre_doit(const struct genl_split_ops *ops,
+			       struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+void net_shaper_nl_cap_post_doit(const struct genl_split_ops *ops,
+				 struct sk_buff *skb, struct genl_info *info)
+{
+}
+
+int net_shaper_nl_cap_pre_dumpit(struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
+int net_shaper_nl_cap_post_dumpit(struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
 int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net_shaper_binding *binding;

@@ -1175,6 +1196,17 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
+int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return 0;
+}
+
+int net_shaper_nl_cap_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	return 0;
+}
+
 static void net_shaper_flush(struct net_shaper_binding *binding)
 {
 	struct net_shaper_data *data = net_shaper_binding_data(binding);

index 06641811bfc1..0c7b026d3066 100644
@@ -67,6 +67,17 @@ static const struct nla_policy net_shaper_group_nl_policy[NET_SHAPER_A_NODE + 1]
 	[NET_SHAPER_A_NODE] = NLA_POLICY_NESTED(net_shaper_node_info_nl_policy),
 };
 
+/* NET_SHAPER_CMD_CAP_GET - do */
+static const struct nla_policy net_shaper_cap_get_do_nl_policy[NET_SHAPER_A_CAPABILITIES_SCOPE + 1] = {
+	[NET_SHAPER_A_CAPABILITIES_IFINDEX] = { .type = NLA_U32, },
+	[NET_SHAPER_A_CAPABILITIES_SCOPE] = NLA_POLICY_MAX(NLA_U32, 3),
+};
+
+/* NET_SHAPER_CMD_CAP_GET - dump */
+static const struct nla_policy net_shaper_cap_get_dump_nl_policy[NET_SHAPER_A_CAPABILITIES_IFINDEX + 1] = {
+	[NET_SHAPER_A_CAPABILITIES_IFINDEX] = { .type = NLA_U32, },
+};
+
 /* Ops table for net_shaper */
 static const struct genl_split_ops net_shaper_nl_ops[] = {
 	{

@@ -114,6 +125,24 @@ static const struct genl_split_ops net_shaper_nl_ops[] = {
 		.maxattr	= NET_SHAPER_A_NODE,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= NET_SHAPER_CMD_CAP_GET,
+		.pre_doit	= net_shaper_nl_cap_pre_doit,
+		.doit		= net_shaper_nl_cap_get_doit,
+		.post_doit	= net_shaper_nl_cap_post_doit,
+		.policy		= net_shaper_cap_get_do_nl_policy,
+		.maxattr	= NET_SHAPER_A_CAPABILITIES_SCOPE,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= NET_SHAPER_CMD_CAP_GET,
+		.start		= net_shaper_nl_cap_pre_dumpit,
+		.dumpit		= net_shaper_nl_cap_get_dumpit,
+		.done		= net_shaper_nl_cap_post_dumpit,
+		.policy		= net_shaper_cap_get_dump_nl_policy,
+		.maxattr	= NET_SHAPER_A_CAPABILITIES_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
 
 struct genl_family net_shaper_nl_family __ro_after_init = {

index 0fe95a03f1b5..557c0c63f125 100644
@@ -18,17 +18,27 @@ extern const struct nla_policy net_shaper_node_info_nl_policy[NET_SHAPER_A_PAREN
 
 int net_shaper_nl_pre_doit(const struct genl_split_ops *ops,
 			   struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_cap_pre_doit(const struct genl_split_ops *ops,
+			       struct sk_buff *skb, struct genl_info *info);
 void
 net_shaper_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 			struct genl_info *info);
+void
+net_shaper_nl_cap_post_doit(const struct genl_split_ops *ops,
+			    struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_pre_dumpit(struct netlink_callback *cb);
+int net_shaper_nl_cap_pre_dumpit(struct netlink_callback *cb);
 int net_shaper_nl_post_dumpit(struct netlink_callback *cb);
+int net_shaper_nl_cap_post_dumpit(struct netlink_callback *cb);
 
 int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_delete_doit(struct sk_buff *skb, struct genl_info *info);
 int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info);
+int net_shaper_nl_cap_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb);
 
 extern struct genl_family net_shaper_nl_family;
 

index 98e17a95f39f..b7e5a3990328 100644
@@ -629,22 +629,29 @@ int net_shaper_nl_post_dumpit(struct netlink_callback *cb)
 int net_shaper_nl_cap_pre_doit(const struct genl_split_ops *ops,
 			       struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	return net_shaper_generic_pre(info, NET_SHAPER_A_CAPABILITIES_IFINDEX);
 }
 
 void net_shaper_nl_cap_post_doit(const struct genl_split_ops *ops,
 				 struct sk_buff *skb, struct genl_info *info)
 {
+	net_shaper_generic_post(info);
 }
 
 int net_shaper_nl_cap_pre_dumpit(struct netlink_callback *cb)
 {
-	return -EOPNOTSUPP;
+	struct net_shaper_nl_ctx *ctx = (struct net_shaper_nl_ctx *)cb->ctx;
+
+	return net_shaper_ctx_init(genl_info_dump(cb),
+				   NET_SHAPER_A_CAPABILITIES_IFINDEX, ctx);
 }
 
 int net_shaper_nl_cap_post_dumpit(struct netlink_callback *cb)
 {
-	return -EOPNOTSUPP;
+	struct net_shaper_nl_ctx *ctx = (struct net_shaper_nl_ctx *)cb->ctx;
+
+	net_shaper_ctx_cleanup(ctx);
+	return 0;
 }
 
 int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info)

@@ -1196,14 +1203,97 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
+static int
+net_shaper_cap_fill_one(struct sk_buff *msg,
+			struct net_shaper_binding *binding,
+			enum net_shaper_scope scope, unsigned long flags,
+			const struct genl_info *info)
+{
+	unsigned long cur;
+	void *hdr;
+
+	hdr = genlmsg_iput(msg, info);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (net_shaper_fill_binding(msg, binding,
+				    NET_SHAPER_A_CAPABILITIES_IFINDEX) ||
+	    nla_put_u32(msg, NET_SHAPER_A_CAPABILITIES_SCOPE, scope))
+		goto nla_put_failure;
+
+	for (cur = NET_SHAPER_A_CAPABILITIES_SUPPORT_METRIC_BPS;
+	     cur <= NET_SHAPER_A_CAPABILITIES_MAX; ++cur) {
+		if (flags & BIT(cur) && nla_put_flag(msg, cur))
+			goto nla_put_failure;
+	}
+
+	genlmsg_end(msg, hdr);
+
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
 int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
+	struct net_shaper_binding *binding = info->user_ptr[0];
+	const struct net_shaper_ops *ops;
+	enum net_shaper_scope scope;
+	struct sk_buff *msg;
+	unsigned long flags;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_CAPABILITIES_SCOPE))
+		return -EINVAL;
+
+	scope = nla_get_u32(info->attrs[NET_SHAPER_A_CAPABILITIES_SCOPE]);
+	ops = net_shaper_binding_ops(binding);
+	ret = ops->capabilities(binding, scope, &flags);
+	if (ret)
+		return ret;
+
+	msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	ret = net_shaper_cap_fill_one(msg, binding, scope, flags, info);
+	if (ret)
+		goto free_msg;
+
+	ret =  genlmsg_reply(msg, info);
+	if (ret)
+		goto free_msg;
 	return 0;
+
+free_msg:
+	nlmsg_free(msg);
+	return ret;
 }
 
 int net_shaper_nl_cap_get_dumpit(struct sk_buff *skb,
 				 struct netlink_callback *cb)
 {
+	const struct genl_info *info = genl_info_dump(cb);
+	struct net_shaper_binding *binding;
+	const struct net_shaper_ops *ops;
+	enum net_shaper_scope scope;
+	unsigned long flags;
+	int ret;
+
+	binding = net_shaper_binding_from_ctx(cb->ctx);
+	ops = net_shaper_binding_ops(binding);
+	for (scope = 0; scope <= NET_SHAPER_SCOPE_MAX; ++scope) {
+		if (ops->capabilities(binding, scope, &flags))
+			continue;
+
+		ret = net_shaper_cap_fill_one(skb, binding, scope, flags,
+					      info);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 

61 lines not on this page · raw message

index f41395264dca..223e433c39fe 100644
@@ -89,6 +89,9 @@ enum virtchnl_rx_hsplit {
 	VIRTCHNL_RX_HSPLIT_SPLIT_SCTP    = 8,
 };
 
+enum virtchnl_bw_limit_type {
+	VIRTCHNL_BW_SHAPER = 0,
+};
 /* END GENERIC DEFINES */
 
 /* Opcodes for VF-PF communication. These are placed in the v_opcode field

@@ -151,6 +154,11 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55,
 	VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56,
 	VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57,
+	/* opcode 57 - 65 are reserved */
+	VIRTCHNL_OP_GET_QOS_CAPS = 66,
+	/* opcode 68 through 111 are reserved */
+	VIRTCHNL_OP_CONFIG_QUEUE_BW = 112,
+	VIRTCHNL_OP_CONFIG_QUANTA = 113,
 	VIRTCHNL_OP_MAX,
 };
 

@@ -261,6 +269,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC	BIT(26)
 #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF		BIT(27)
 #define VIRTCHNL_VF_OFFLOAD_FDIR_PF		BIT(28)
+#define VIRTCHNL_VF_OFFLOAD_QOS			BIT(29)
 
 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \
 			       VIRTCHNL_VF_OFFLOAD_VLAN | \

@@ -1416,6 +1425,85 @@ struct virtchnl_fdir_del {
 
 VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 
+struct virtchnl_shaper_bw {
+	/* Unit is Kbps */
+	u32 committed;
+	u32 peak;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_shaper_bw);
+
+/* VIRTCHNL_OP_GET_QOS_CAPS
+ * VF sends this message to get its QoS Caps, such as
+ * TC number, Arbiter and Bandwidth.
+ */
+struct virtchnl_qos_cap_elem {
+	u8 tc_num;
+	u8 tc_prio;
+#define VIRTCHNL_ABITER_STRICT      0
+#define VIRTCHNL_ABITER_ETS         2
+	u8 arbiter;
+#define VIRTCHNL_STRICT_WEIGHT      1
+	u8 weight;
+	enum virtchnl_bw_limit_type type;
+	union {
+		struct virtchnl_shaper_bw shaper;
+		u8 pad2[32];
+	};
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_qos_cap_elem);
+
+struct virtchnl_qos_cap_list {
+	u16 vsi_id;
+	u16 num_elem;
+	struct virtchnl_qos_cap_elem cap[];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_qos_cap_list);
+#define virtchnl_qos_cap_list_LEGACY_SIZEOF	44
+
+/* VIRTCHNL_OP_CONFIG_QUEUE_BW */
+struct virtchnl_queue_bw {
+	u16 queue_id;
+	u8 tc;
+	u8 pad;
+	struct virtchnl_shaper_bw shaper;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_bw);
+
+struct virtchnl_queues_bw_cfg {
+	u16 vsi_id;
+	u16 num_queues;
+	struct virtchnl_queue_bw cfg[];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_queues_bw_cfg);
+#define virtchnl_queues_bw_cfg_LEGACY_SIZEOF	16
+
+enum virtchnl_queue_type {
+	VIRTCHNL_QUEUE_TYPE_TX			= 0,
+	VIRTCHNL_QUEUE_TYPE_RX			= 1,
+};
+
+/* structure to specify a chunk of contiguous queues */
+struct virtchnl_queue_chunk {
+	/* see enum virtchnl_queue_type */
+	s32 type;
+	u16 start_queue_id;
+	u16 num_queues;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_queue_chunk);
+
+struct virtchnl_quanta_cfg {
+	u16 quanta_size;
+	struct virtchnl_queue_chunk queue_select;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_quanta_cfg);
+
 #define __vss_byone(p, member, count, old)				      \
 	(struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0)))
 

@@ -1438,6 +1526,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 		 __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c),  \
 		 __vss(virtchnl_tc_info, __vss_byelem, p, m, c),	      \
 		 __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c),     \
+		 __vss(virtchnl_qos_cap_list, __vss_byelem, p, m, c),	      \
+		 __vss(virtchnl_queues_bw_cfg, __vss_byelem, p, m, c),	      \
 		 __vss(virtchnl_rss_key, __vss_byone, p, m, c),		      \
 		 __vss(virtchnl_rss_lut, __vss_byone, p, m, c))
 

@@ -1637,6 +1727,35 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2:
 		valid_len = sizeof(struct virtchnl_vlan_setting);
 		break;
+	case VIRTCHNL_OP_GET_QOS_CAPS:
+		break;
+	case VIRTCHNL_OP_CONFIG_QUEUE_BW:
+		valid_len = virtchnl_queues_bw_cfg_LEGACY_SIZEOF;
+		if (msglen >= valid_len) {
+			struct virtchnl_queues_bw_cfg *q_bw =
+				(struct virtchnl_queues_bw_cfg *)msg;
+
+			valid_len = virtchnl_struct_size(q_bw, cfg,
+							 q_bw->num_queues);
+			if (q_bw->num_queues == 0) {
+				err_msg_format = true;
+				break;
+			}
+		}
+		break;
+	case VIRTCHNL_OP_CONFIG_QUANTA:
+		valid_len = sizeof(struct virtchnl_quanta_cfg);
+		if (msglen >= valid_len) {
+			struct virtchnl_quanta_cfg *q_quanta =
+				(struct virtchnl_quanta_cfg *)msg;
+
+			if (q_quanta->quanta_size == 0 ||
+			    q_quanta->queue_select.num_queues == 0) {
+				err_msg_format = true;
+				break;
+			}
+		}
+		break;
 	/* These are always errors coming from the VF. */
 	case VIRTCHNL_OP_EVENT:
 	case VIRTCHNL_OP_UNKNOWN:

index caaa10157909..35ace1907a62 100644
@@ -659,6 +659,8 @@ struct ice_pf {
 	struct ice_agg_node vf_agg_node[ICE_MAX_VF_AGG_NODES];
 	struct ice_dplls dplls;
 	struct device *hwmon_dev;
+
+	u8 num_quanta_prof_used;
 };
 
 extern struct workqueue_struct *ice_lag_wq;

index f448d3a84564..c238d440a623 100644
@@ -349,6 +349,8 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf
 		break;
 	}
 
+	tlan_ctx->quanta_prof_idx = ring->quanta_prof_id;
+
 	tlan_ctx->tso_ena = ICE_TX_LEGACY;
 	tlan_ctx->tso_qnum = pf_q;
 

index 009716a12a26..b22e71dc59d4 100644
@@ -2436,6 +2436,25 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	ice_recalc_port_limited_caps(hw, &func_p->common_cap);
 }
 
+/**
+ * ice_func_id_to_logical_id - map from function id to logical pf id
+ * @active_function_bitmap: active function bitmap
+ * @pf_id: function number of device
+ *
+ * Return: logical PF ID.
+ */
+static int ice_func_id_to_logical_id(u32 active_function_bitmap, u8 pf_id)
+{
+	u8 logical_id = 0;
+	u8 i;
+
+	for (i = 0; i < pf_id; i++)
+		if (active_function_bitmap & BIT(i))
+			logical_id++;
+
+	return logical_id;
+}
+
 /**
  * ice_parse_valid_functions_cap - Parse ICE_AQC_CAPS_VALID_FUNCTIONS caps
  * @hw: pointer to the HW struct

@@ -2453,6 +2472,8 @@ ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 	dev_p->num_funcs = hweight32(number);
 	ice_debug(hw, ICE_DBG_INIT, "dev caps: num_funcs = %d\n",
 		  dev_p->num_funcs);
+
+	hw->logical_pf_id = ice_func_id_to_logical_id(number, hw->pf_id);
 }
 
 /**

index 91cbae1eec89..af9302f0e376 100644
@@ -6,6 +6,14 @@
 #ifndef _ICE_HW_AUTOGEN_H_
 #define _ICE_HW_AUTOGEN_H_
 
+#define GLCOMM_QUANTA_PROF(_i)			(0x002D2D68 + ((_i) * 4))
+#define GLCOMM_QUANTA_PROF_MAX_INDEX		15
+#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_S	0
+#define GLCOMM_QUANTA_PROF_QUANTA_SIZE_M	ICE_M(0x3FFF, 0)
+#define GLCOMM_QUANTA_PROF_MAX_CMD_S		16
+#define GLCOMM_QUANTA_PROF_MAX_CMD_M		ICE_M(0xFF, 16)
+#define GLCOMM_QUANTA_PROF_MAX_DESC_S		24
+#define GLCOMM_QUANTA_PROF_MAX_DESC_M		ICE_M(0x3F, 24)
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
 #define QTX_COMM_HEAD_HEAD_S			0

index feba314a3fe4..ea2fae9035b5 100644
@@ -406,6 +406,7 @@ struct ice_tx_ring {
 #define ICE_TX_FLAGS_RING_VLAN_L2TAG2	BIT(2)
 	u8 flags;
 	u8 dcb_tc;			/* Traffic class of ring */
+	u16 quanta_prof_id;
 } ____cacheline_internodealigned_in_smp;
 
 static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring)

index b9e443232335..953576003425 100644
@@ -904,6 +904,7 @@ struct ice_hw {
 	u8 revision_id;
 
 	u8 pf_id;		/* device profile info */
+	u8 logical_pf_id;
 
 	u16 max_burst_size;	/* driver sets this value */
 

index be4266899690..4261fe1c2bcd 100644
@@ -59,6 +59,13 @@ struct ice_fdir_prof_info {
 	u64 fdir_active_cnt;
 };
 
+struct ice_vf_qs_bw {
+	u32 committed;
+	u32 peak;
+	u16 queue_id;
+	u8 tc;
+};
+
 /* VF operations */
 struct ice_vf_ops {
 	enum ice_disq_rst_src reset_type;

@@ -140,6 +147,7 @@ struct ice_vf {
 	struct devlink_port devlink_port;
 
 	u16 num_msix;			/* num of MSI-X configured on this VF */
+	struct ice_vf_qs_bw qs_bw[ICE_MAX_RSS_QS_PER_VF];
 };
 
 /* Flags for controlling behavior of ice_reset_vf */

365 lines not on this page · raw message

index 3a4115869153..0c629aef9baf 100644
@@ -13,6 +13,13 @@
 /* Restrict number of MAC Addr and VLAN that non-trusted VF can programmed */
 #define ICE_MAX_VLAN_PER_VF		8
 
+#define ICE_DFLT_QUANTA 1024
+#define ICE_MAX_QUANTA_SIZE 4096
+#define ICE_MIN_QUANTA_SIZE 256
+
+#define calc_quanta_desc(x)	\
+	max_t(u16, 12, min_t(u16, 63, (((x) + 66) / 132) * 2 + 4))
+
 /* MAC filters: 1 is reserved for the VF's default/perm_addr/LAA MAC, 1 for
  * broadcast, and 16 for additional unicast/multicast filters
  */

@@ -61,6 +68,10 @@ struct ice_virtchnl_ops {
 	int (*dis_vlan_stripping_v2_msg)(struct ice_vf *vf, u8 *msg);
 	int (*ena_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg);
 	int (*dis_vlan_insertion_v2_msg)(struct ice_vf *vf, u8 *msg);
+	int (*get_qos_caps)(struct ice_vf *vf);
+	int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg);
+	int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg);
+	int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg);
 };
 
 #ifdef CONFIG_PCI_IOV

index d796dbd2a440..c105a82ee136 100644
@@ -84,6 +84,11 @@ static const u32 fdir_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER,
 };
 
+static const u32 tc_allowlist_opcodes[] = {
+	VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW,
+	VIRTCHNL_OP_CONFIG_QUANTA,
+};
+
 struct allowlist_opcode_info {
 	const u32 *opcodes;
 	size_t size;

@@ -104,6 +109,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = {
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF, adv_rss_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes),
+	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes),
 };
 
 /**

index 48cd1d06761c..a84bdbfbb0f7 100644
@@ -34,6 +34,7 @@
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_skbedit.h>
+#include <net/net_shaper.h>
 
 #include "iavf_type.h"
 #include <linux/avf/virtchnl.h>

@@ -336,6 +337,7 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION	BIT_ULL(36)
 #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION		BIT_ULL(37)
 #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION	BIT_ULL(38)
+#define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires

@@ -581,6 +583,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 int iavf_config_rss(struct iavf_adapter *adapter);
 int iavf_lan_add_device(struct iavf_adapter *adapter);
 int iavf_lan_del_device(struct iavf_adapter *adapter);
+void iavf_cfg_queues_bw(struct iavf_adapter *adapter);
 void iavf_enable_channels(struct iavf_adapter *adapter);
 void iavf_disable_channels(struct iavf_adapter *adapter);
 void iavf_add_cloud_filter(struct iavf_adapter *adapter);

171 lines not on this page · raw message

index d7b5587aeb8e..dd503ee50b7f 100644
@@ -296,6 +296,8 @@ struct iavf_ring {
 					 */
 
 	u32 rx_buf_len;
+	struct net_shaper_info q_shaper;
+	bool q_shaper_update;
 } ____cacheline_internodealigned_in_smp;
 
 #define IAVF_ITR_ADAPTIVE_MIN_INC	0x0002

83 lines not on this page · raw message

index a84bdbfbb0f7..75ac69670789 100644
@@ -251,6 +251,9 @@ struct iavf_cloud_filter {
 #define IAVF_RESET_WAIT_DETECTED_COUNT 500
 #define IAVF_RESET_WAIT_COMPLETE_COUNT 2000
 
+#define IAVF_MAX_QOS_TC_NUM		8
+#define IAVF_DEFAULT_QUANTA_SIZE	1024
+
 /* board specific private data structure */
 struct iavf_adapter {
 	struct workqueue_struct *wq;

@@ -338,6 +341,8 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION		BIT_ULL(37)
 #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION	BIT_ULL(38)
 #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
+#define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
+#define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires

@@ -410,6 +415,8 @@ struct iavf_adapter {
 			       VIRTCHNL_VF_OFFLOAD_FDIR_PF)
 #define ADV_RSS_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \
 			     VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
+#define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
+			 VIRTCHNL_VF_OFFLOAD_QOS)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;

@@ -418,6 +425,7 @@ struct iavf_adapter {
 	struct virtchnl_vlan_caps vlan_v2_caps;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
+	struct virtchnl_qos_cap_list *qos_caps;
 	struct iavf_vsi vsi;
 	u32 aq_wait_count;
 	/* RSS stuff */

@@ -584,6 +592,8 @@ int iavf_config_rss(struct iavf_adapter *adapter);
 int iavf_lan_add_device(struct iavf_adapter *adapter);
 int iavf_lan_del_device(struct iavf_adapter *adapter);
 void iavf_cfg_queues_bw(struct iavf_adapter *adapter);
+void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter);
+void iavf_get_qos_caps(struct iavf_adapter *adapter);
 void iavf_enable_channels(struct iavf_adapter *adapter);
 void iavf_disable_channels(struct iavf_adapter *adapter);
 void iavf_add_cloud_filter(struct iavf_adapter *adapter);

93 lines not on this page · raw message

116 lines not on this page · raw message