net: introduce TX H/W shaping API

index 60eb95a06d55..ebed05a2804c 100644
@@ -284,7 +284,7 @@ int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb,
 
 	ASSERT_RTNL();
 
-	NL_ASSERT_DUMP_CTX_FITS(struct vxlan_mdb_dump_ctx);
+	NL_ASSERT_CTX_FITS(struct vxlan_mdb_dump_ctx);
 
 	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
 			cb->nlh->nlmsg_seq, RTM_NEWMDB, sizeof(*bpm),

index b332c2048c75..a3ca198a3a9e 100644
@@ -34,6 +34,7 @@ struct netlink_skb_parms {
 
 #define NETLINK_CB(skb)		(*(struct netlink_skb_parms*)&((skb)->cb))
 #define NETLINK_CREDS(skb)	(&NETLINK_CB((skb)).creds)
+#define NETLINK_CTX_SIZE	48
 
 
 void netlink_table_grab(void);

@@ -293,7 +294,7 @@ struct netlink_callback {
 	int			flags;
 	bool			strict_check;
 	union {
-		u8		ctx[48];
+		u8		ctx[NETLINK_CTX_SIZE];
 
 		/* args is deprecated. Cast a struct over ctx instead
 		 * for proper type safety.

@@ -302,7 +303,7 @@ struct netlink_callback {
 	};
 };
 
-#define NL_ASSERT_DUMP_CTX_FITS(type_name)				\
+#define NL_ASSERT_CTX_FITS(type_name)					\
 	BUILD_BUG_ON(sizeof(type_name) >				\
 		     sizeof_field(struct netlink_callback, ctx))
 

index 9ab49bfeae78..9d3726e8f90e 100644
@@ -124,7 +124,8 @@ struct genl_family {
  * @genlhdr: generic netlink message header
  * @attrs: netlink attributes
  * @_net: network namespace
- * @user_ptr: user pointers
+ * @ctx: storage space for the use by the family
+ * @user_ptr: user pointers (deprecated, use ctx instead)
  * @extack: extended ACK report struct
  */
 struct genl_info {

@@ -135,7 +136,10 @@ struct genl_info {
 	struct genlmsghdr *	genlhdr;
 	struct nlattr **	attrs;
 	possible_net_t		_net;
-	void *			user_ptr[2];
+	union {
+		u8		ctx[NETLINK_CTX_SIZE];
+		void *		user_ptr[2];
+	};
 	struct netlink_ext_ack *extack;
 };
 

index a17d7eaeb001..bb2b9f53ef6b 100644
@@ -23,7 +23,7 @@ struct netdev_nl_dump_ctx {
 
 static struct netdev_nl_dump_ctx *netdev_dump_ctx(struct netlink_callback *cb)
 {
-	NL_ASSERT_DUMP_CTX_FITS(struct netdev_nl_dump_ctx);
+	NL_ASSERT_CTX_FITS(struct netdev_nl_dump_ctx);
 
 	return (struct netdev_nl_dump_ctx *)cb->ctx;
 }

index f0a520987085..472d1a27cdf8 100644
@@ -6169,7 +6169,7 @@ static int rtnl_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx, s_idx;
 	int err;
 
-	NL_ASSERT_DUMP_CTX_FITS(struct rtnl_mdb_dump_ctx);
+	NL_ASSERT_CTX_FITS(struct rtnl_mdb_dump_ctx);
 
 	if (cb->strict_check) {
 		err = rtnl_mdb_valid_dump_req(cb->nlh, cb->extack);

index c7a8e13f917c..a9f064ab9ed9 100644
@@ -166,7 +166,7 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb,
 static inline struct devlink_nl_dump_state *
 devlink_dump_state(struct netlink_callback *cb)
 {
-	NL_ASSERT_DUMP_CTX_FITS(struct devlink_nl_dump_state);
+	NL_ASSERT_CTX_FITS(struct devlink_nl_dump_state);
 
 	return (struct devlink_nl_dump_state *)cb->ctx;
 }

index e07386275e14..7cb106b590ab 100644
@@ -224,7 +224,7 @@ struct rss_nl_dump_ctx {
 
 static struct rss_nl_dump_ctx *rss_dump_ctx(struct netlink_callback *cb)
 {
-	NL_ASSERT_DUMP_CTX_FITS(struct rss_nl_dump_ctx);
+	NL_ASSERT_CTX_FITS(struct rss_nl_dump_ctx);
 
 	return (struct rss_nl_dump_ctx *)cb->ctx;
 }

index 4cbf71d0786b..cae4ee5d11d3 100644
@@ -3876,7 +3876,7 @@ static int __init ctnetlink_init(void)
 {
 	int ret;
 
-	NL_ASSERT_DUMP_CTX_FITS(struct ctnetlink_list_dump_ctx);
+	NL_ASSERT_CTX_FITS(struct ctnetlink_list_dump_ctx);
 
 	ret = nfnetlink_subsys_register(&ctnl_subsys);
 	if (ret < 0) {

index feb54c63a116..29387b605f3e 100644
@@ -997,7 +997,7 @@ static int genl_start(struct netlink_callback *cb)
 	info->info.attrs	= attrs;
 	genl_info_net_set(&info->info, sock_net(cb->skb->sk));
 	info->info.extack	= cb->extack;
-	memset(&info->info.user_ptr, 0, sizeof(info->info.user_ptr));
+	memset(&info->info.ctx, 0, sizeof(info->info.ctx));
 
 	cb->data = info;
 	if (ops->start) {

@@ -1104,7 +1104,7 @@ static int genl_family_rcv_msg_doit(const struct genl_family *family,
 	info.attrs = attrbuf;
 	info.extack = extack;
 	genl_info_net_set(&info, net);
-	memset(&info.user_ptr, 0, sizeof(info.user_ptr));
+	memset(&info.ctx, 0, sizeof(info.ctx));
 
 	if (ops->pre_doit) {
 		err = ops->pre_doit(ops, skb, &info);

80 lines not on this page · raw message

55 lines not on this page · raw message

133 lines not on this page · raw message

new file mode 100644
index 000000000000..fea70e94af48
@@ -0,0 +1,36 @@
+/* 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_leaf_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 ca5f0dda733b..9168449a51bd 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
 };
 
 /**

@@ -2399,6 +2407,19 @@ struct net_device {
 	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
 	struct dim_irq_moder	*irq_moder;
 
+	/**
+	 * @lock: protects @net_shaper_hierarchy, feel free to use for other
+	 * netdev-scope protection. Ordering: take after rtnl_lock.
+	 */
+	struct mutex		lock;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	/**
+	 * @net_shaper_hierarchy: data tracking the current shaper status
+	 *  see include/net/net_shapers.h
+	 */
+	struct net_shaper_hierarchy *net_shaper_hierarchy;
+#endif
 	u8			priv[] ____cacheline_aligned
 				       __counted_by(priv_len);
 } ____cacheline_aligned;

120 lines not on this page · raw message

index 98bb5f890b88..8615f16e8456 100644
@@ -10376,6 +10376,8 @@ int register_netdevice(struct net_device *dev)
 	xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1);
 	mutex_init(&dev->ethtool->rss_lock);
 
+	mutex_init(&dev->lock);
+
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 

@@ -11400,6 +11402,10 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 		mutex_destroy(&dev->ethtool->rss_lock);
 
+		net_shaper_flush_netdev(dev);
+
+		mutex_destroy(&dev->lock);
+
 		if (skb)
 			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh);
 

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;

378 lines not on this page · raw message

index 2d72f9112f23..8d6f3c5829b0 100644
@@ -36,6 +36,24 @@ static struct net_shaper_binding *net_shaper_binding_from_ctx(void *ctx)
 	return &((struct net_shaper_nl_ctx *)ctx)->binding;
 }
 
+static void net_shaper_lock(struct net_shaper_binding *binding)
+{
+	switch (binding->type) {
+	case NET_SHAPER_BINDING_TYPE_NETDEV:
+		mutex_lock(&binding->netdev->lock);
+		break;
+	}
+}
+
+static void net_shaper_unlock(struct net_shaper_binding *binding)
+{
+	switch (binding->type) {
+	case NET_SHAPER_BINDING_TYPE_NETDEV:
+		mutex_unlock(&binding->netdev->lock);
+		break;
+	}
+}
+
 static struct net_shaper_hierarchy *
 net_shaper_hierarchy(struct net_shaper_binding *binding)
 {

@@ -47,6 +65,16 @@ net_shaper_hierarchy(struct net_shaper_binding *binding)
 	return NULL;
 }
 
+static const struct net_shaper_ops *
+net_shaper_ops(struct net_shaper_binding *binding)
+{
+	if (binding->type == NET_SHAPER_BINDING_TYPE_NETDEV)
+		return binding->netdev->netdev_ops->net_shaper_ops;
+
+	/* No other type supported yet. */
+	return NULL;
+}
+
 static int net_shaper_fill_binding(struct sk_buff *msg,
 				   const struct net_shaper_binding *binding,
 				   u32 type)

@@ -171,6 +199,37 @@ static u32 net_shaper_handle_to_index(const struct net_shaper_handle *handle)
 		FIELD_PREP(NET_SHAPER_ID_MASK, handle->id);
 }
 
+static void net_shaper_index_to_handle(u32 index,
+				       struct net_shaper_handle *handle)
+{
+	handle->scope = FIELD_GET(NET_SHAPER_SCOPE_MASK, 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;
+}
+
+/*
+ * MARK_0 is already in use due to XA_FLAGS_ALLOC, can't reuse such flag as
+ * it's cleared by xa_store().
+ */
+#define NET_SHAPER_NOT_VALID XA_MARK_1
+
 static struct net_shaper *
 net_shaper_lookup(struct net_shaper_binding *binding,
 		  const struct net_shaper_handle *handle)

@@ -179,6 +238,135 @@ net_shaper_lookup(struct net_shaper_binding *binding,
 	u32 index = net_shaper_handle_to_index(handle);
 
 	return hierarchy ? xa_load(&hierarchy->shapers, index) : NULL;
+	if (!hierarchy || xa_get_mark(&hierarchy->shapers, index,
+				      NET_SHAPER_NOT_VALID))
+		return NULL;
+
+	return xa_load(&hierarchy->shapers, index);
+}
+
+/* Allocate on demand the per device shaper's hierarchy container.
+ * Called under the net shaper lock
+ */
+static struct net_shaper_hierarchy *
+net_shaper_hierarchy_setup(struct net_shaper_binding *binding)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+
+	if (hierarchy)
+		return hierarchy;
+
+	hierarchy = kmalloc(sizeof(*hierarchy), GFP_KERNEL);
+	if (!hierarchy)
+		return NULL;
+
+	/* The flag is required for ID allocation */
+	xa_init_flags(&hierarchy->shapers, XA_FLAGS_ALLOC);
+
+	switch (binding->type) {
+	case NET_SHAPER_BINDING_TYPE_NETDEV:
+		/* Pairs with READ_ONCE in net_shaper_hierarchy. */
+		WRITE_ONCE(binding->netdev->net_shaper_hierarchy, hierarchy);
+		break;
+	}
+	return hierarchy;
+}
+
+/* Prepare the hierarchy container to actually insert the given shaper, doing
+ * in advance the needed allocations.
+ */
+static int net_shaper_pre_insert(struct net_shaper_binding *binding,
+				 struct net_shaper_handle *handle,
+				 struct netlink_ext_ack *extack)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+	struct net_shaper *prev, *cur;
+	bool id_allocated = false;
+	int ret, index;
+
+	if (!hierarchy)
+		return -ENOMEM;
+
+	index = net_shaper_handle_to_index(handle);
+	cur = xa_load(&hierarchy->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) {
+		u32 min, max;
+
+		handle->id = NET_SHAPER_ID_MASK - 1;
+		max = net_shaper_handle_to_index(handle);
+		handle->id = 0;
+		min = net_shaper_handle_to_index(handle);
+
+		ret = xa_alloc(&hierarchy->shapers, &index, NULL,
+			       XA_LIMIT(min, max), GFP_KERNEL);
+		if (ret < 0) {
+			NL_SET_ERR_MSG(extack, "Can't allocate new id for NODE shaper");
+			return ret;
+		}
+
+		net_shaper_index_to_handle(index, handle);
+		id_allocated = true;
+	}
+
+	cur = kzalloc(sizeof(*cur), GFP_KERNEL);
+	if (!cur) {
+		ret = -ENOMEM;
+		goto free_id;
+	}
+
+	/* Mark 'tentative' shaper inside the hierarchy container.
+	 * xa_set_mark is a no-op if the previous store fails.
+	 */
+	xa_lock(&hierarchy->shapers);
+	prev = __xa_store(&hierarchy->shapers, index, cur, GFP_KERNEL);
+	__xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_NOT_VALID);
+	xa_unlock(&hierarchy->shapers);
+	if (xa_err(prev)) {
+		NL_SET_ERR_MSG(extack, "Can't insert shaper into device store");
+		kfree_rcu(cur, rcu);
+		ret = xa_err(prev);
+		goto free_id;
+	}
+	return 0;
+
+free_id:
+	if (id_allocated)
+		xa_erase(&hierarchy->shapers, index);
+	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_commit(struct net_shaper_binding *binding,
+			      int nr_shapers, const struct net_shaper *shapers)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+	struct net_shaper *cur;
+	int index;
+	int i;
+
+	xa_lock(&hierarchy->shapers);
+	for (i = 0; i < nr_shapers; ++i) {
+		index = net_shaper_handle_to_index(&shapers[i].handle);
+
+		cur = xa_load(&hierarchy->shapers, index);
+		if (WARN_ON_ONCE(!cur))
+			continue;
+
+		/* Successful update: drop the tentative mark
+		 * and update the hierarchy container.
+		 */
+		__xa_clear_mark(&hierarchy->shapers, index,
+				NET_SHAPER_NOT_VALID);
+		*cur = shapers[i];
+	}
+	xa_unlock(&hierarchy->shapers);
 }
 
 static int net_shaper_parse_handle(const struct nlattr *attr,

@@ -216,6 +404,85 @@ 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 *shaper,
+				 bool *exists)
+{
+	struct net_shaper *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,
+				      &shaper->handle);
+	if (ret)
+		return ret;
+
+	if (shaper->handle.scope == NET_SHAPER_SCOPE_UNSPEC) {
+		NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
+		return -EINVAL;
+	}
+
+	/* Fetch existing hierarchy, if any, so that user provide info will
+	 * incrementally update the existing shaper configuration.
+	 */
+	rcu_read_lock();
+	old = net_shaper_lookup(binding, &shaper->handle);
+	if (old)
+		*shaper = *old;
+	*exists = !!old;
+	rcu_read_unlock();
+
+	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 existing 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 *shaper)
+{
+	struct nlattr *tb[NET_SHAPER_A_WEIGHT + 1];
+	bool exists;
+	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, shaper, &exists);
+	if (ret < 0)
+		return ret;
+
+	if (!exists)
+		net_shaper_default_parent(&shaper->handle, &shaper->parent);
+	return 0;
+}
+
 static int net_shaper_generic_pre(struct genl_info *info, int type)
 {
 	struct net_shaper_nl_ctx *ctx = (struct net_shaper_nl_ctx *)info->ctx;

@@ -336,14 +603,143 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb,
 	return ret;
 }
 
+/* Update the H/W and on success update the hierarchy container, too. */
+static int net_shaper_set(struct net_shaper_binding *binding,
+			  const struct net_shaper *shaper,
+			  struct netlink_ext_ack *extack)
+{
+	const struct net_shaper_ops *ops = net_shaper_ops(binding);
+	struct net_shaper_handle handle = shaper->handle;
+	struct net_shaper_hierarchy *hierarchy;
+	int ret;
+
+	net_shaper_lock(binding);
+
+	hierarchy = net_shaper_hierarchy_setup(binding);
+	if (!hierarchy) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* The 'set' can't create node-scope shapers. */
+	if (handle.scope == NET_SHAPER_SCOPE_NODE &&
+	    !net_shaper_lookup(binding, &handle)) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	ret = net_shaper_pre_insert(binding, &handle, extack);
+	if (ret)
+		goto unlock;
+
+	ret = ops->set(binding, shaper, extack);
+	net_shaper_commit(binding, 1, shaper);
+
+unlock:
+	net_shaper_unlock(binding);
+	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 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->ctx);
+	attr = info->attrs[NET_SHAPER_A_SHAPER];
+	ret = net_shaper_parse_info_nest(binding, attr, info, &shaper);
+	if (ret)
+		return ret;
+
+	return net_shaper_set(binding, &shaper, info->extack);
+}
+
+static int __net_shaper_delete(struct net_shaper_binding *binding,
+			       struct net_shaper *shaper,
+			       struct netlink_ext_ack *extack)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+	struct net_shaper_handle parent_handle, handle = shaper->handle;
+	const struct net_shaper_ops *ops = net_shaper_ops(binding);
+	int ret;
+
+again:
+	parent_handle = shaper->parent;
+
+	ret = ops->delete(binding, &handle, extack);
+	if (ret < 0)
+		return ret;
+
+	xa_erase(&hierarchy->shapers, net_shaper_handle_to_index(&handle));
+	kfree_rcu(shaper, rcu);
+
+	/* Eventually delete the parent, if it is left over with no leaves. */
+	if (parent_handle.scope == NET_SHAPER_SCOPE_NODE) {
+		shaper = net_shaper_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_hierarchy *hierarchy;
+	struct net_shaper *shaper;
+	int ret;
+
+	net_shaper_lock(binding);
+
+	hierarchy = net_shaper_hierarchy(binding);
+	if (!hierarchy) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	shaper = net_shaper_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, shaper, extack);
+
+unlock:
+	net_shaper_unlock(binding);
+	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->ctx);
+	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)

@@ -355,12 +751,15 @@ static void net_shaper_flush(struct net_shaper_binding *binding)
 	if (!hierarchy)
 		return;
 
+	net_shaper_lock(binding);
 	xa_lock(&hierarchy->shapers);
 	xa_for_each(&hierarchy->shapers, index, cur) {
 		__xa_erase(&hierarchy->shapers, index);
 		kfree(cur);
 	}
 	xa_unlock(&hierarchy->shapers);
+	net_shaper_unlock(binding);
+
 	kfree(hierarchy);
 }
 

index 8d6f3c5829b0..c409acbe768c 100644
@@ -75,6 +75,24 @@ net_shaper_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)

@@ -369,6 +387,25 @@ static void net_shaper_commit(struct net_shaper_binding *binding,
 	xa_unlock(&hierarchy->shapers);
 }
 
+/* Rollback all the tentative inserts from the data container. */
+static void net_shaper_rollback(struct net_shaper_binding *binding)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+	struct net_shaper *cur;
+	unsigned long index;
+
+	if (!hierarchy)
+		return;
+
+	xa_lock(&hierarchy->shapers);
+	xa_for_each_marked(&hierarchy->shapers, index, cur,
+			   NET_SHAPER_NOT_VALID) {
+		__xa_erase(&hierarchy->shapers, index);
+		kfree(cur);
+	}
+	xa_unlock(&hierarchy->shapers);
+}
+
 static int net_shaper_parse_handle(const struct nlattr *attr,
 				   const struct genl_info *info,
 				   struct net_shaper_handle *handle)

@@ -463,6 +500,7 @@ 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,
+				      const struct net_shaper *node,
 				      struct net_shaper *shaper)
 {
 	struct nlattr *tb[NET_SHAPER_A_WEIGHT + 1];

@@ -478,11 +516,59 @@ static int net_shaper_parse_info_nest(struct net_shaper_binding *binding,
 	if (ret < 0)
 		return ret;
 
+	if (node && shaper->handle.scope != NET_SHAPER_SCOPE_QUEUE) {
+		NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
+		return -EINVAL;
+	}
+
 	if (!exists)
 		net_shaper_default_parent(&shaper->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 *shaper)
+{
+	struct nlattr *tb[NET_SHAPER_A_PARENT + 1];
+	bool exists;
+	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, shaper, &exists);
+	if (ret)
+		return ret;
+
+	if (shaper->handle.scope != NET_SHAPER_SCOPE_NODE &&
+	    shaper->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 = (struct net_shaper_nl_ctx *)info->ctx;

@@ -652,7 +738,7 @@ int net_shaper_nl_set_doit(struct sk_buff *skb, struct genl_info *info)
 
 	binding = net_shaper_binding_from_ctx(info->ctx);
 	attr = info->attrs[NET_SHAPER_A_SHAPER];
-	ret = net_shaper_parse_info_nest(binding, attr, info, &shaper);
+	ret = net_shaper_parse_info_nest(binding, attr, info, NULL, &shaper);
 	if (ret)
 		return ret;
 

@@ -689,6 +775,118 @@ static int __net_shaper_delete(struct net_shaper_binding *binding,
 	return 0;
 }
 
+static int net_shaper_handle_cmp(const struct net_shaper_handle *a,
+				 const struct net_shaper_handle *b)
+{
+	/* Must avoid holes in struct net_shaper_handle. */
+	BUILD_BUG_ON(sizeof(*a) != 8);
+
+	return memcmp(a, b, sizeof(*a));
+}
+
+static int net_shaper_parent_from_leaves(int leaves_count,
+					 const struct net_shaper *leaves,
+					 struct net_shaper *node,
+					 struct netlink_ext_ack *extack)
+{
+	struct net_shaper_handle parent = leaves[0].parent;
+	int i;
+
+	for (i = 1; i < leaves_count; ++i) {
+		if (net_shaper_handle_cmp(&leaves[i].parent, &parent)) {
+			NL_SET_ERR_MSG_FMT(extack, "All the leaves shapers must have the same old parent");
+			return -EINVAL;
+		}
+	}
+
+	node->parent = parent;
+	return 0;
+}
+
+static int __net_shaper_group(struct net_shaper_binding *binding,
+			      int leaves_count, struct net_shaper *leaves,
+			      struct net_shaper *node,
+			      struct netlink_ext_ack *extack)
+{
+	const struct net_shaper_ops *ops = net_shaper_ops(binding);
+	struct net_shaper_handle leaf_handle;
+	struct net_shaper *parent = NULL;
+	int i, ret;
+
+	if (node->handle.scope == NET_SHAPER_SCOPE_NODE) {
+		if (node->handle.id != NET_SHAPER_ID_UNSPEC &&
+		    !net_shaper_lookup(binding, &node->handle)) {
+			/* The related attribute is not available when
+			 * reaching here from the delete() op.
+			 */
+			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) {
+			ret = net_shaper_parent_from_leaves(leaves_count,
+							    leaves, node,
+							    extack);
+			if (ret)
+				return ret;
+		}
+
+	} else {
+		net_shaper_default_parent(&node->handle, &node->parent);
+	}
+
+	if (node->parent.scope == NET_SHAPER_SCOPE_NODE) {
+		parent = net_shaper_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_pre_insert(binding, &node->handle, extack);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < leaves_count; ++i) {
+		leaf_handle = leaves[i].handle;
+
+		ret = net_shaper_pre_insert(binding, &leaf_handle, extack);
+		if (ret)
+			goto rollback;
+
+		if (!net_shaper_handle_cmp(&leaves[i].parent, &node->handle))
+			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, node, extack);
+	if (ret < 0)
+		goto rollback;
+
+	if (parent)
+		parent->leaves++;
+	net_shaper_commit(binding, 1, node);
+	net_shaper_commit(binding, leaves_count, leaves);
+	return 0;
+
+rollback:
+	net_shaper_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)

@@ -742,6 +940,173 @@ 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 data container, too. */
+static int net_shaper_group(struct net_shaper_binding *binding,
+			    int leaves_count, struct net_shaper *leaves,
+			    struct net_shaper *node,
+			    struct netlink_ext_ack *extack)
+{
+	struct net_shaper_hierarchy *hierarchy;
+	struct net_shaper **old_nodes, *tmp;
+	int i, ret, old_nodes_count = 0;
+
+	old_nodes = kcalloc(leaves_count, sizeof(struct net_shaper *),
+			    GFP_KERNEL);
+	if (!old_nodes)
+		return -ENOMEM;
+
+	net_shaper_lock(binding);
+
+	hierarchy = net_shaper_hierarchy_setup(binding);
+	if (!hierarchy) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	/* Record the nodes shaper that this group() operation can make
+	 * childless for later cleanup.
+	 */
+	for (i = 0; i < leaves_count; i++) {
+		if (leaves[i].parent.scope == NET_SHAPER_SCOPE_NODE &&
+		    net_shaper_handle_cmp(&leaves[i].parent, &node->handle)) {
+			tmp = net_shaper_lookup(binding, &leaves[i].parent);
+			if (!tmp)
+				continue;
+
+			old_nodes[old_nodes_count++] = tmp;
+		}
+	}
+
+	ret = __net_shaper_group(binding, leaves_count, leaves, node, extack);
+
+	/* Check if we need to delete any nde left alone by the new leaves
+	 * linkage.
+	 */
+	for (i = 0; i < old_nodes_count; ++i) {
+		tmp = old_nodes[i];
+
+		if (--tmp->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, tmp, extack);
+	}
+
+unlock:
+	net_shaper_unlock(binding);
+
+	kfree(old_nodes);
+	return ret;
+}
+
+static int net_shaper_group_send_reply(struct net_shaper_binding *binding,
+				       const struct net_shaper_handle *handle,
+				       struct genl_info *info,
+				       struct sk_buff *msg)
+{
+	void *hdr;
+
+	hdr = genlmsg_iput(msg, info);
+	if (!hdr)
+		goto free_msg;
+
+	if (net_shaper_fill_binding(msg, binding, NET_SHAPER_A_IFINDEX) ||
+	    net_shaper_fill_handle(msg, handle, NET_SHAPER_A_HANDLE))
+		goto free_msg;
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+free_msg:
+	/* Should never happen as msg is pre-allocated with enough space. */
+	WARN_ONCE(true, "calculated message payload length (%d)",
+		  net_shaper_handle_size());
+	nlmsg_free(msg);
+	return -EMSGSIZE;
+}
+
+int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_shaper_binding *binding;
+	struct net_shaper *leaves, node;
+	int i, ret, rem, leaves_count;
+	struct sk_buff *msg;
+	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->ctx);
+
+	/* The group operation is optional. */
+	if (!net_shaper_ops(binding)->group)
+		return -EOPNOTSUPP;
+
+	leaves_count = net_shaper_list_len(info, NET_SHAPER_A_LEAVES);
+	if (!leaves_count) {
+		NL_SET_BAD_ATTR(info->extack,
+				info->attrs[NET_SHAPER_A_LEAVES]);
+		return -EINVAL;
+	}
+
+	leaves = kcalloc(leaves_count, sizeof(struct net_shaper), GFP_KERNEL);
+	if (!leaves)
+		return -ENOMEM;
+
+	ret = net_shaper_parse_node(binding, info->attrs[NET_SHAPER_A_NODE],
+				    info, &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;
+
+		/* Leaves parsing uses a broader attribute set than what is
+		 * enforced by the op policy. That is safe, as the NL core
+		 * should parse recursively and reject bad commands long
+		 * before it calls the family handler.
+		 */
+		ret = net_shaper_parse_info_nest(binding, attr, info,
+						 &node, &leaves[i]);
+		if (ret)
+			goto free_shapers;
+		i++;
+	}
+
+	/* Prepare the msg reply in advance, to avoid device operation
+	 * rollback on allocation failure.
+	 */
+	msg = genlmsg_new(net_shaper_handle_size(), GFP_KERNEL);
+	if (!msg)
+		goto free_shapers;
+
+	ret = net_shaper_group(binding, leaves_count, leaves, &node,
+			       info->extack);
+	if (ret < 0)
+		goto free_msg;
+
+	ret = net_shaper_group_send_reply(binding, &node.handle, info, msg);
+	if (ret)
+		GENL_SET_ERR_MSG_FMT(info, "Can't send reply");
+
+free_shapers:
+	kfree(leaves);
+	return ret;
+
+free_msg:
+	kfree_skb(msg);
+	goto free_shapers;
+}
+
 static void net_shaper_flush(struct net_shaper_binding *binding)
 {
 	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);

index c409acbe768c..1255d532b36a 100644
@@ -804,7 +804,8 @@ static int net_shaper_parent_from_leaves(int leaves_count,
 }
 
 static int __net_shaper_group(struct net_shaper_binding *binding,
-			      int leaves_count, struct net_shaper *leaves,
+			      bool update_node, int leaves_count,
+			      struct net_shaper *leaves,
 			      struct net_shaper *node,
 			      struct netlink_ext_ack *extack)
 {

@@ -848,12 +849,14 @@ 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_pre_insert(binding, &node->handle, extack);
-	if (ret)
-		return ret;
+	if (update_node) {
+		/* For newly created node scope shaper, the following will
+		 * update the handle, due to id allocation.
+		 */
+		ret = net_shaper_pre_insert(binding, &node->handle, extack);
+		if (ret)
+			return ret;
+	}
 
 	for (i = 0; i < leaves_count; ++i) {
 		leaf_handle = leaves[i].handle;

@@ -878,7 +881,8 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
 
 	if (parent)
 		parent->leaves++;
-	net_shaper_commit(binding, 1, node);
+	if (update_node)
+		net_shaper_commit(binding, 1, node);
 	net_shaper_commit(binding, leaves_count, leaves);
 	return 0;
 

@@ -887,6 +891,64 @@ 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 *shaper,
+				   struct netlink_ext_ack *extack)
+{
+	struct net_shaper_hierarchy *hierarchy = net_shaper_hierarchy(binding);
+	struct net_shaper *cur, *leaves, node = {};
+	int ret, leaves_count = 0;
+	unsigned long index;
+	bool update_node;
+
+	if (!shaper->leaves)
+		return 0;
+
+	/* Fetch the new node information. */
+	node.handle = shaper->parent;
+	cur = net_shaper_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 data 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),
+			 GFP_KERNEL);
+	if (!leaves)
+		return -ENOMEM;
+
+	/* Build the leaves arrays. */
+	xa_for_each(&hierarchy->shapers, index, cur) {
+		if (net_shaper_handle_cmp(&cur->parent, &shaper->handle))
+			continue;
+
+		if (WARN_ON_ONCE(leaves_count == shaper->leaves)) {
+			ret = -EINVAL;
+			goto free;
+		}
+
+		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.
+	 */
+	update_node = node.handle.scope != NET_SHAPER_SCOPE_NETDEV;
+	ret = __net_shaper_group(binding, update_node, leaves_count,
+				 leaves, &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)

@@ -910,9 +972,9 @@ 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, shaper, extack);
+		if (ret)
+			goto unlock;
 	}
 
 	ret = __net_shaper_delete(binding, shaper, extack);

@@ -977,7 +1039,8 @@ static int net_shaper_group(struct net_shaper_binding *binding,
 		}
 	}
 
-	ret = __net_shaper_group(binding, leaves_count, leaves, node, extack);
+	ret = __net_shaper_group(binding, true, leaves_count, leaves, node,
+				 extack);
 
 	/* Check if we need to delete any nde left alone by the new leaves
 	 * linkage.

index 8615f16e8456..33629a9d0661 100644
@@ -2948,6 +2948,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
 		if (dev->num_tc)
 			netif_setup_tc(dev, txq);
 
+		net_shaper_set_real_num_tx_queues(dev, txq);
+
 		dev_qdisc_change_real_num_tx(dev, txq);
 
 		dev->real_num_tx_queues = txq;

index 13c558874af3..d3ea92949ff3 100644
@@ -37,8 +37,12 @@ void dev_addr_check(struct net_device *dev);
 
 #if IS_ENABLED(CONFIG_NET_SHAPER)
 void net_shaper_flush_netdev(struct net_device *dev);
+void net_shaper_set_real_num_tx_queues(struct net_device *dev,
+				       unsigned int txq);
 #else
 static inline void net_shaper_flush_netdev(struct net_device *dev) {}
+static inline void net_shaper_set_real_num_tx_queues(struct net_device *dev,
+						     unsigned int txq) {}
 #endif
 
 /* sysctls not referred to from outside net/core/ */

index 1255d532b36a..f6f5712d7b3c 100644
@@ -1201,6 +1201,37 @@ void net_shaper_flush_netdev(struct net_device *dev)
 	net_shaper_flush(&binding);
 }
 
+void net_shaper_set_real_num_tx_queues(struct net_device *dev,
+				       unsigned int txq)
+{
+	struct net_shaper_hierarchy *hierarchy;
+	struct net_shaper_binding binding;
+	int i;
+
+	binding.type = NET_SHAPER_BINDING_TYPE_NETDEV;
+	binding.netdev = dev;
+	hierarchy = net_shaper_hierarchy(&binding);
+	if (!hierarchy)
+		return;
+
+	net_shaper_lock(&binding);
+
+	/* Take action only when decreasing the tx queue number. */
+	for (i = txq; i < dev->real_num_tx_queues; ++i) {
+		struct net_shaper_handle handle;
+		struct net_shaper *shaper;
+
+		handle.scope = NET_SHAPER_SCOPE_QUEUE;
+		handle.id = i;
+		shaper = net_shaper_lookup(&binding, &handle);
+		if (!shaper)
+			continue;
+
+		__net_shaper_delete(&binding, shaper, NULL);
+	}
+	net_shaper_unlock(&binding);
+}
+
 static int __init shaper_init(void)
 {
 	return genl_register_family(&net_shaper_nl_family);

index 03c774a2bec1..ff82c00bc305 100644
@@ -67,11 +67,28 @@ enum {
 	NET_SHAPER_A_HANDLE_MAX = (__NET_SHAPER_A_HANDLE_MAX - 1)
 };
 
+enum {
+	NET_SHAPER_A_CAPS_IFINDEX = 1,
+	NET_SHAPER_A_CAPS_SCOPE,
+	NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS,
+	NET_SHAPER_A_CAPS_SUPPORT_METRIC_PPS,
+	NET_SHAPER_A_CAPS_SUPPORT_NESTING,
+	NET_SHAPER_A_CAPS_SUPPORT_BW_MIN,
+	NET_SHAPER_A_CAPS_SUPPORT_BW_MAX,
+	NET_SHAPER_A_CAPS_SUPPORT_BURST,
+	NET_SHAPER_A_CAPS_SUPPORT_PRIORITY,
+	NET_SHAPER_A_CAPS_SUPPORT_WEIGHT,
+
+	__NET_SHAPER_A_CAPS_MAX,
+	NET_SHAPER_A_CAPS_MAX = (__NET_SHAPER_A_CAPS_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 f6f5712d7b3c..67d38b691bb8 100644
@@ -614,6 +614,27 @@ 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;

@@ -1170,6 +1191,17 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 	goto free_shapers;
 }
 
+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_hierarchy *hierarchy = net_shaper_hierarchy(binding);

index 76289f6df9aa..4393c9370cef 100644
@@ -73,6 +73,17 @@ 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_CAPS_SCOPE + 1] = {
+	[NET_SHAPER_A_CAPS_IFINDEX] = { .type = NLA_U32, },
+	[NET_SHAPER_A_CAPS_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_CAPS_IFINDEX + 1] = {
+	[NET_SHAPER_A_CAPS_IFINDEX] = { .type = NLA_U32, },
+};
+
 /* Ops table for net_shaper */
 static const struct genl_split_ops net_shaper_nl_ops[] = {
 	{

@@ -120,6 +131,24 @@ 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_CAPS_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_CAPS_IFINDEX,
+		.flags		= GENL_CMD_CAP_DUMP,
+	},
 };
 
 struct genl_family net_shaper_nl_family __ro_after_init = {

index fea70e94af48..3affdb21061f 100644
@@ -19,17 +19,27 @@ 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 67d38b691bb8..bc55dd53a5d7 100644
@@ -617,22 +617,29 @@ 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_CAPS_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_setup(genl_info_dump(cb),
+				    NET_SHAPER_A_CAPS_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)

@@ -1191,14 +1198,99 @@ int net_shaper_nl_group_doit(struct sk_buff *skb, struct genl_info *info)
 	goto free_shapers;
 }
 
+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_CAPS_IFINDEX) ||
+	    nla_put_u32(msg, NET_SHAPER_A_CAPS_SCOPE, scope))
+		goto nla_put_failure;
+
+	for (cur = NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS;
+	     cur <= NET_SHAPER_A_CAPS_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;
+	const struct net_shaper_ops *ops;
+	enum net_shaper_scope scope;
+	unsigned long flags = 0;
+	struct sk_buff *msg;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, NET_SHAPER_A_CAPS_SCOPE))
+		return -EINVAL;
+
+	binding = net_shaper_binding_from_ctx(info->ctx);
+	scope = nla_get_u32(info->attrs[NET_SHAPER_A_CAPS_SCOPE]);
+	ops = net_shaper_ops(binding);
+	ops->capabilities(binding, scope, &flags);
+	if (!flags)
+		return -EOPNOTSUPP;
+
+	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;
+	int ret;
+
+	binding = net_shaper_binding_from_ctx(cb->ctx);
+	ops = net_shaper_ops(binding);
+	for (scope = 0; scope <= NET_SHAPER_SCOPE_MAX; ++scope) {
+		unsigned long flags = 0;
+
+		ops->capabilities(binding, scope, &flags);
+		if (!flags)
+			continue;
+
+		ret = net_shaper_cap_fill_one(skb, binding, scope, flags,
+					      info);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 

index bc55dd53a5d7..2302faf9ee45 100644
@@ -441,6 +441,64 @@ static int net_shaper_parse_handle(const struct nlattr *attr,
 	return 0;
 }
 
+static int net_shaper_validate_caps(struct net_shaper_binding *binding,
+				    struct nlattr **tb,
+				    const struct genl_info *info,
+				    struct net_shaper *shaper)
+{
+	const struct net_shaper_ops *ops = net_shaper_ops(binding);
+	struct nlattr *bad = NULL;
+	unsigned long caps = 0;
+
+	ops->capabilities(binding, shaper->handle.scope, &caps);
+
+	if (tb[NET_SHAPER_A_PRIORITY] &&
+	    !(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_PRIORITY)))
+		bad = tb[NET_SHAPER_A_PRIORITY];
+	if (tb[NET_SHAPER_A_WEIGHT] &&
+	    !(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_WEIGHT)))
+		bad = tb[NET_SHAPER_A_WEIGHT];
+	if (tb[NET_SHAPER_A_BW_MIN] &&
+	    !(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MIN)))
+		bad = tb[NET_SHAPER_A_BW_MIN];
+	if (tb[NET_SHAPER_A_BW_MAX] &&
+	    !(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX)))
+		bad = tb[NET_SHAPER_A_BW_MAX];
+	if (tb[NET_SHAPER_A_BURST] &&
+	    !(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_BURST)))
+		bad = tb[NET_SHAPER_A_BURST];
+
+	if (!caps)
+		bad = tb[NET_SHAPER_A_HANDLE];
+
+	if (bad) {
+		NL_SET_BAD_ATTR(info->extack, bad);
+		return -EOPNOTSUPP;
+	}
+
+	/* The metric is really used only if there is *any* rate-related
+	 * setting, either in current attributes set or in pre-existing
+	 * values.
+	 */
+	if (shaper->burst || shaper->bw_min || shaper->bw_max) {
+		u32 metric_cap = NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS +
+				 shaper->metric;
+
+		/* The metric test can fail even when the user did not
+		 * specify the METRIC attribute. Pointing to rate related
+		 * attribute will be confusing, as the attribute itself
+		 * could be indeed supported, with a different metric.
+		 * Be more specific.
+		 */
+		if (!(caps & BIT(metric_cap))) {
+			NL_SET_ERR_MSG_FMT(info->extack, "Bad metric %d",
+					   shaper->metric);
+			return -EOPNOTSUPP;
+		}
+	}
+	return 0;
+}
+
 static int net_shaper_parse_info(struct net_shaper_binding *binding,
 				 struct nlattr **tb,
 				 const struct genl_info *info,

@@ -491,6 +549,28 @@ static int net_shaper_parse_info(struct net_shaper_binding *binding,
 
 	if (tb[NET_SHAPER_A_WEIGHT])
 		shaper->weight = nla_get_u32(tb[NET_SHAPER_A_WEIGHT]);
+
+	ret = net_shaper_validate_caps(binding, tb, info, shaper);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int net_shaper_validate_nesting(struct net_shaper_binding *binding,
+				       const struct net_shaper *shaper,
+				       struct netlink_ext_ack *extack)
+{
+	const struct net_shaper_ops *ops = net_shaper_ops(binding);
+	unsigned long caps = 0;
+
+	ops->capabilities(binding, shaper->handle.scope, &caps);
+	if (!(caps & BIT(NET_SHAPER_A_CAPS_SUPPORT_NESTING))) {
+		NL_SET_ERR_MSG_FMT(extack,
+				   "Nesting not supported for scope %d",
+				   shaper->handle.scope);
+		return -EOPNOTSUPP;
+	}
 	return 0;
 }
 

@@ -516,9 +596,21 @@ static int net_shaper_parse_info_nest(struct net_shaper_binding *binding,
 	if (ret < 0)
 		return ret;
 
-	if (node && shaper->handle.scope != NET_SHAPER_SCOPE_QUEUE) {
-		NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
-		return -EINVAL;
+	/* When node is specified, the shaper is actually a leaf for a
+	 * group() operation.
+	 */
+	if (node) {
+		if (shaper->handle.scope != NET_SHAPER_SCOPE_QUEUE) {
+			NL_SET_BAD_ATTR(info->extack, tb[NET_SHAPER_A_HANDLE]);
+			return -EINVAL;
+		}
+
+		if (node->handle.scope == NET_SHAPER_SCOPE_NODE) {
+			ret = net_shaper_validate_nesting(binding, shaper,
+							  info->extack);
+			if (ret < 0)
+				return ret;
+		}
 	}
 
 	if (!exists)

@@ -875,6 +967,10 @@ static int __net_shaper_group(struct net_shaper_binding *binding,
 					   node->parent.scope, node->parent.id);
 			return -ENOENT;
 		}
+
+		ret = net_shaper_validate_nesting(binding, node, extack);
+		if (ret < 0)
+			return ret;
 	}
 
 	if (update_node) {

index 017a6102be0a..cad85bb0cf54 100644
@@ -22,6 +22,7 @@
 #include <net/netdev_queues.h>
 #include <net/page_pool/helpers.h>
 #include <net/netlink.h>
+#include <net/net_shaper.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>

@@ -475,6 +476,43 @@ static int nsim_stop(struct net_device *dev)
 	return 0;
 }
 
+static int nsim_shaper_set(struct net_shaper_binding *binding,
+			   const struct net_shaper *shaper,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int nsim_shaper_del(struct net_shaper_binding *binding,
+			   const struct net_shaper_handle *handle,
+			   struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static int nsim_shaper_group(struct net_shaper_binding *binding,
+			     int leaves_count,
+			     const struct net_shaper *leaves,
+			     const struct net_shaper *root,
+			     struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void nsim_shaper_cap(struct net_shaper_binding *binding,
+			    enum net_shaper_scope scope,
+			    unsigned long *flags)
+{
+	*flags = ULONG_MAX;
+}
+
+static const struct net_shaper_ops nsim_shaper_ops = {
+	.set			= nsim_shaper_set,
+	.delete			= nsim_shaper_del,
+	.group			= nsim_shaper_group,
+	.capabilities		= nsim_shaper_cap,
+};
+
 static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_start_xmit		= nsim_start_xmit,
 	.ndo_set_rx_mode	= nsim_set_rx_mode,

@@ -496,6 +534,7 @@ static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_bpf		= nsim_bpf,
 	.ndo_open		= nsim_open,
 	.ndo_stop		= nsim_stop,
+	.net_shaper_ops		= &nsim_shaper_ops,
 };
 
 static const struct net_device_ops nsim_vf_netdev_ops = {

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);

140 lines not on this page · raw message

index d7b5587aeb8e..f97c702c0802 100644
@@ -296,6 +296,8 @@ struct iavf_ring {
 					 */
 
 	u32 rx_buf_len;
+	struct net_shaper 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