net: ethtool: attach an XArray of custom RSS contexts to a netdevice

Each context stores the RXFH settings (indir, key, and hfunc) as well
 as optionally some driver private data.
Delete any still-existing contexts at netdev unregister time.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/cbd1c402cec38f2e03124f2ab65b4ae4e08bd90d.1719502240.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 69 insertions, 0 deletions

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 374639e661d1..c741d6403364 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -159,6 +159,46 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
 	return index % n_rx_rings;
 }
 
+/**
+ * struct ethtool_rxfh_context - a custom RSS context configuration
+ * @indir_size: Number of u32 entries in indirection table
+ * @key_size: Size of hash key, in bytes
+ * @priv_size: Size of driver private data, in bytes
+ * @hfunc: RSS hash function identifier.  One of the %ETH_RSS_HASH_*
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
+ * @indir_configured: indir has been specified (at create time or subsequently)
+ * @key_configured: hkey has been specified (at create time or subsequently)
+ */
+struct ethtool_rxfh_context {
+	u32 indir_size;
+	u32 key_size;
+	u16 priv_size;
+	u8 hfunc;
+	u8 input_xfrm;
+	u8 indir_configured:1;
+	u8 key_configured:1;
+	/* private: driver private data, indirection table, and hash key are
+	 * stored sequentially in @data area.  Use below helpers to access.
+	 */
+	u8 data[] __aligned(sizeof(void *));
+};
+
+static inline void *ethtool_rxfh_context_priv(struct ethtool_rxfh_context *ctx)
+{
+	return ctx->data;
+}
+
+static inline u32 *ethtool_rxfh_context_indir(struct ethtool_rxfh_context *ctx)
+{
+	return (u32 *)(ctx->data + ALIGN(ctx->priv_size, sizeof(u32)));
+}
+
+static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx)
+{
+	return (u8 *)(ethtool_rxfh_context_indir(ctx) + ctx->indir_size);
+}
+
 /* declare a link mode bitmap */
 #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name)		\
 	DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS)
@@ -1006,9 +1046,11 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
 
 /**
  * struct ethtool_netdev_state - per-netdevice state for ethtool features
+ * @rss_ctx:		XArray of custom RSS contexts
  * @wol_enabled:	Wake-on-LAN is enabled
  */
 struct ethtool_netdev_state {
+	struct xarray		rss_ctx;
 	unsigned		wol_enabled:1;
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index c0c6e200e17f..bce810f8ae53 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10336,6 +10336,9 @@ int register_netdevice(struct net_device *dev)
 	if (ret)
 		return ret;
 
+	/* rss ctx ID 0 is reserved for the default context, start from 1 */
+	xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1);
+
 	spin_lock_init(&dev->addr_list_lock);
 	netdev_set_addr_lockdep_class(dev);
 
@@ -11235,6 +11238,28 @@ void synchronize_net(void)
 }
 EXPORT_SYMBOL(synchronize_net);
 
+static void netdev_rss_contexts_free(struct net_device *dev)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+
+	xa_for_each(&dev->ethtool->rss_ctx, context, ctx) {
+		struct ethtool_rxfh_param rxfh;
+
+		rxfh.indir = ethtool_rxfh_context_indir(ctx);
+		rxfh.key = ethtool_rxfh_context_key(ctx);
+		rxfh.hfunc = ctx->hfunc;
+		rxfh.input_xfrm = ctx->input_xfrm;
+		rxfh.rss_context = context;
+		rxfh.rss_delete = true;
+
+		xa_erase(&dev->ethtool->rss_ctx, context);
+		dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
+		kfree(ctx);
+	}
+	xa_destroy(&dev->ethtool->rss_ctx);
+}
+
 /**
  *	unregister_netdevice_queue - remove device from the kernel
  *	@dev: device
@@ -11338,6 +11363,8 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		netdev_name_node_alt_flush(dev);
 		netdev_name_node_free(dev->name_node);
 
+		netdev_rss_contexts_free(dev);
+
 		call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev);
 
 		if (dev->netdev_ops->ndo_uninit)