nfp: flower: monitor and offload LAG groups

Monitor LAG events via the NETDEV_CHANGEUPPER/NETDEV_CHANGELOWERSTATE
notifiers to maintain a list of offloadable groups. Sync these groups with
HW via a delayed workqueue to prevent excessive re-configuration. When the
workqueue is triggered it may generate multiple control messages for
different groups. These messages are linked via a batch ID and flags to
indicate a new batch and the end of a batch.

Update private data in each repr to track their LAG lower state flags. The
state of a repr is used to determine the active netdevs that can be
offloaded. For example, in active-backup mode, we only offload the netdev
currently active.
Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/netronome/nfp/Makefile

@@ -37,6 +37,7 @@ ifeq ($(CONFIG_NFP_APP_FLOWER),y)
 nfp-objs += \
 	    flower/action.o \
 	    flower/cmsg.o \
+	    flower/lag_conf.o \
 	    flower/main.o \
 	    flower/match.o \
 	    flower/metadata.o \

drivers/net/ethernet/netronome/nfp/flower/main.c

@@ -575,12 +575,14 @@ static int nfp_flower_init(struct nfp_app *app)
 	/* Tell the firmware that the driver supports lag. */
 	err = nfp_rtsym_write_le(app->pf->rtbl,
 				 "_abi_flower_balance_sync_enable", 1);
-	if (!err)
+	if (!err) {
 		app_priv->flower_ext_feats |= NFP_FL_FEATS_LAG;
-	else if (err == -ENOENT)
+		nfp_flower_lag_init(&app_priv->nfp_lag);
+	} else if (err == -ENOENT) {
 		nfp_warn(app->cpp, "LAG not supported by FW.\n");
-	else
+	} else {
 		goto err_cleanup_metadata;
+	}
 
 	return 0;
 
@@ -599,6 +601,9 @@ static void nfp_flower_clean(struct nfp_app *app)
 	skb_queue_purge(&app_priv->cmsg_skbs_low);
 	flush_work(&app_priv->cmsg_work);
 
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+		nfp_flower_lag_cleanup(&app_priv->nfp_lag);
+
 	nfp_flower_metadata_cleanup(app);
 	vfree(app->priv);
 	app->priv = NULL;
@@ -665,11 +670,29 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 
 static int nfp_flower_start(struct nfp_app *app)
 {
+	struct nfp_flower_priv *app_priv = app->priv;
+	int err;
+
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+		err = nfp_flower_lag_reset(&app_priv->nfp_lag);
+		if (err)
+			return err;
+
+		err = register_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
+		if (err)
+			return err;
+	}
+
 	return nfp_tunnel_config_start(app);
 }
 
 static void nfp_flower_stop(struct nfp_app *app)
 {
+	struct nfp_flower_priv *app_priv = app->priv;
+
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
+		unregister_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
+
 	nfp_tunnel_config_stop(app);
 }
 

drivers/net/ethernet/netronome/nfp/flower/main.h

@@ -43,6 +43,7 @@
 #include <net/pkt_cls.h>
 #include <net/tcp.h>
 #include <linux/workqueue.h>
+#include <linux/idr.h>
 
 struct net_device;
 struct nfp_app;
@@ -97,6 +98,30 @@ struct nfp_mtu_conf {
 	spinlock_t lock;
 };
 
+/**
+ * struct nfp_fl_lag - Flower APP priv data for link aggregation
+ * @lag_nb:		Notifier to track master/slave events
+ * @work:		Work queue for writing configs to the HW
+ * @lock:		Lock to protect lag_group_list
+ * @group_list:		List of all master/slave groups offloaded
+ * @ida_handle:		IDA to handle group ids
+ * @pkt_num:		Incremented for each config packet sent
+ * @batch_ver:		Incremented for each batch of config packets
+ * @global_inst:	Instance allocator for groups
+ * @rst_cfg:		Marker to reset HW LAG config
+ */
+struct nfp_fl_lag {
+	struct notifier_block lag_nb;
+	struct delayed_work work;
+	struct mutex lock;
+	struct list_head group_list;
+	struct ida ida_handle;
+	unsigned int pkt_num;
+	unsigned int batch_ver;
+	u8 global_inst;
+	bool rst_cfg;
+};
+
 /**
  * struct nfp_flower_priv - Flower APP per-vNIC priv data
  * @app:		Back pointer to app
@@ -129,6 +154,7 @@ struct nfp_mtu_conf {
  *			from firmware for repr reify
  * @reify_wait_queue:	wait queue for repr reify response counting
  * @mtu_conf:		Configuration of repr MTU value
+ * @nfp_lag:		Link aggregation data block
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -158,6 +184,7 @@ struct nfp_flower_priv {
 	atomic_t reify_replies;
 	wait_queue_head_t reify_wait_queue;
 	struct nfp_mtu_conf mtu_conf;
+	struct nfp_fl_lag nfp_lag;
 };
 
 /**
@@ -250,5 +277,8 @@ void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
 void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
 				  void *cb_priv);
+void nfp_flower_lag_init(struct nfp_fl_lag *lag);
+void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag);
+int nfp_flower_lag_reset(struct nfp_fl_lag *lag);
 
 #endif