net-shapers: implement NL get operation

Paolo Abeni · kuba-moo · commit 4b623f9f0f59 · 2024-10-10T08:30:22.000-07:00
Introduce the basic infrastructure to implement the net-shaper core functionality. Each network devices carries a net-shaper cache, the NL get() operation fetches the data from such cache. The cache is initially empty, will be fill by the set()/group() operation implemented later and is destroyed at device cleanup time. The net_shaper_fill_handle(), net_shaper_ctx_init(), and net_shaper_generic_pre() implementations handle generic index type attributes, despite the current caller always pass a constant value to avoid more noise in later patches using them with different attributes. Reviewed-by: Jakub Kicinski <kuba@kernel.org> Reviewed-by: Jiri Pirko <jiri@nvidia.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Link: https://patch.msgid.link/ddd10fd645a9367803ad02fca4a5664ea5ace170.1728460186.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst
@@ -104,6 +104,9 @@ Driver Support
 .. kernel-doc:: include/linux/netdevice.h
    :internal:
 
+.. kernel-doc:: include/net/net_shaper.h
+   :internal:
+
 PHY Support
 -----------
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
@@ -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
 };
 
 /**
@@ -2406,6 +2414,19 @@ struct net_device {
 
 	u64			max_pacing_offload_horizon;
 
+	/**
+	 * @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;
diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _NET_SHAPER_H_
+#define _NET_SHAPER_H_
+
+#include <linux/types.h>
+
+#include <uapi/linux/net_shaper.h>
+
+struct net_device;
+struct devlink;
+struct netlink_ext_ack;
+
+enum net_shaper_binding_type {
+	NET_SHAPER_BINDING_TYPE_NETDEV,
+	/* NET_SHAPER_BINDING_TYPE_DEVLINK_PORT */
+};
+
+struct net_shaper_binding {
+	enum net_shaper_binding_type type;
+	union {
+		struct net_device *netdev;
+		struct devlink *devlink;
+	};
+};
+
+struct net_shaper_handle {
+	enum net_shaper_scope scope;
+	u32 id;
+};
+
+/**
+ * struct net_shaper - represents a shaping node on the NIC H/W
+ * zeroed field are considered not set.
+ * @parent: Unique identifier for the shaper parent, usually implied
+ * @handle: Unique identifier for this shaper
+ * @metric: Specify if the rate limits refers to PPS or BPS
+ * @bw_min: Minimum guaranteed rate for this shaper
+ * @bw_max: Maximum peak rate allowed for this shaper
+ * @burst: Maximum burst for the peek rate of this shaper
+ * @priority: Scheduling priority for this shaper
+ * @weight: Scheduling weight for this shaper
+ */
+struct net_shaper {
+	struct net_shaper_handle parent;
+	struct net_shaper_handle handle;
+	enum net_shaper_metric metric;
+	u64 bw_min;
+	u64 bw_max;
+	u64 burst;
+	u32 priority;
+	u32 weight;
+
+	/* private: */
+	u32 leaves; /* accounted only for NODE scope */
+	struct rcu_head rcu;
+};
+
+/**
+ * struct net_shaper_ops - Operations on device H/W shapers
+ *
+ * The operations applies to either net_device and devlink objects.
+ * The initial shaping configuration at device initialization is empty:
+ * does not constraint the rate in any way.
+ * The network core keeps track of the applied user-configuration in
+ * the net_device or devlink structure.
+ * The operations are serialized via a per device lock.
+ *
+ * Device not supporting any kind of nesting should not provide the
+ * group operation.
+ *
+ * Each shaper is uniquely identified within the device with a 'handle'
+ * comprising the shaper scope and a scope-specific id.
+ */
+struct net_shaper_ops {
+	/**
+	 * @group: create the specified shapers scheduling group
+	 *
+	 * Nest the @leaves shapers identified under the * @node shaper.
+	 * All the shapers belong to the device specified by @binding.
+	 * The @leaves arrays size is specified by @leaves_count.
+	 * Create either the @leaves and the @node shaper; or if they already
+	 * exists, links them together in the desired way.
+	 * @leaves scope must be NET_SHAPER_SCOPE_QUEUE.
+	 */
+	int (*group)(struct net_shaper_binding *binding, int leaves_count,
+		     const struct net_shaper *leaves,
+		     const struct net_shaper *node,
+		     struct netlink_ext_ack *extack);
+
+	/**
+	 * @set: Updates the specified shaper
+	 *
+	 * Updates or creates the @shaper on the device specified by @binding.
+	 */
+	int (*set)(struct net_shaper_binding *binding,
+		   const struct net_shaper *shaper,
+		   struct netlink_ext_ack *extack);
+
+	/**
+	 * @delete: Removes the specified shaper
+	 *
+	 * Removes the shaper configuration as identified by the given @handle
+	 * on the device specified by @binding, restoring the default behavior.
+	 */
+	int (*delete)(struct net_shaper_binding *binding,
+		      const struct net_shaper_handle *handle,
+		      struct netlink_ext_ack *extack);
+
+	/**
+	 * @capabilities: get the shaper features supported by the device
+	 *
+	 * Fills the bitmask @cap with the supported capabilities for the
+	 * specified @scope and device specified by @binding.
+	 */
+	void (*capabilities)(struct net_shaper_binding *binding,
+			     enum net_shaper_scope scope, unsigned long *cap);
+};
+
+#endif
diff --git a/net/core/dev.c b/net/core/dev.c
@@ -11147,6 +11147,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	hash_init(dev->qdisc_hash);
 #endif
 
+	mutex_init(&dev->lock);
+
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
 
@@ -11217,6 +11219,8 @@ void free_netdev(struct net_device *dev)
 		return;
 	}
 
+	mutex_destroy(&dev->lock);
+
 	kfree(dev->ethtool);
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
@@ -11426,6 +11430,8 @@ void unregister_netdevice_many_notify(struct list_head *head,
 
 		mutex_destroy(&dev->ethtool->rss_lock);
 
+		net_shaper_flush_netdev(dev);
+
 		if (skb)
 			rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh);
 
diff --git a/net/core/dev.h b/net/core/dev.h
@@ -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;
diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c
