ethtool: Track user-provided RSS indirection table size

Track the number of indirection table entries the user originally
provided (context 0/default as well!).

Replace IFF_RXFH_CONFIGURED with rss_indir_user_size: the flag is
redundant now that user_size captures the same information.

Add ethtool_rxfh_indir_lost() for drivers that must reset the
indirection table.

Convert bnxt and mlx5 to use it.

Signed-off-by: Björn Töpel <bjorn@kernel.org>
Link: https://patch.msgid.link/20260320085826.1957255-2-bjorn@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 70 insertions, 29 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 604966a398f5..84eb53b4172b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -8118,8 +8118,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		    (bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) !=
 		     bnxt_get_nr_rss_ctxs(bp, rx_rings) ||
 		     bnxt_get_max_rss_ring(bp) >= rx_rings)) {
-			netdev_warn(bp->dev, "RSS table entries reverting to default\n");
-			bp->dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
+			ethtool_rxfh_indir_lost(bp->dev);
 		}
 	}
 	bp->rx_nr_rings = rx_rings;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3eebdf402129..1238e5356012 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -6480,12 +6480,23 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 
 	/* max number of channels may have changed */
 	max_nch = mlx5e_calc_max_nch(priv->mdev, priv->netdev, profile);
+
+	/* Locking is required by ethtool_rxfh_indir_lost() (sends
+	 * ETHTOOL_MSG_RSS_NTF) and by netif_set_real_num_*_queues in case
+	 * the netdev has been registered by this point (if this function
+	 * was called in the reload or resume flow).
+	 */
+	if (need_lock) {
+		rtnl_lock();
+		netdev_lock(priv->netdev);
+	}
+
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
 		/* Reducing the number of channels - RXFH has to be reset, and
 		 * mlx5e_num_channels_changed below will build the RQT.
 		 */
-		priv->netdev->priv_flags &= ~IFF_RXFH_CONFIGURED;
+		ethtool_rxfh_indir_lost(priv->netdev);
 		priv->channels.params.num_channels = max_nch;
 		if (priv->channels.params.mqprio.mode == TC_MQPRIO_MODE_CHANNEL) {
 			mlx5_core_warn(priv->mdev, "MLX5E: Disabling MQPRIO channel mode\n");
@@ -6502,15 +6513,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	/* 1. Set the real number of queues in the kernel the first time.
 	 * 2. Set our default XPS cpumask.
 	 * 3. Build the RQT.
-	 *
-	 * Locking is required by netif_set_real_num_*_queues in case the
-	 * netdev has been registered by this point (if this function was called
-	 * in the reload or resume flow).
 	 */
-	if (need_lock) {
-		rtnl_lock();
-		netdev_lock(priv->netdev);
-	}
 	err = mlx5e_num_channels_changed(priv);
 	if (need_lock) {
 		netdev_unlock(priv->netdev);
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 656d465bcd06..34ca9261de82 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -176,6 +176,8 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 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
+ * @indir_user_size: number of user provided entries for the
+ *	indirection table
  * @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
@@ -186,6 +188,7 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
 struct ethtool_rxfh_context {
 	u32 indir_size;
 	u32 key_size;
+	u32 indir_user_size;
 	u16 priv_size;
 	u8 hfunc;
 	u8 input_xfrm;
@@ -214,6 +217,7 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx)
 }
 
 void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id);
+void ethtool_rxfh_indir_lost(struct net_device *dev);
 
 struct link_mode_info {
 	int	speed;
@@ -1337,12 +1341,15 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
  * @rss_ctx:		XArray of custom RSS contexts
  * @rss_lock:		Protects entries in @rss_ctx.  May be taken from
  *			within RTNL.
+ * @rss_indir_user_size: Number of user provided entries for the default
+ *			 (context 0) indirection table.
  * @wol_enabled:	Wake-on-LAN is enabled
  * @module_fw_flash_in_progress: Module firmware flashing is in progress.
  */
 struct ethtool_netdev_state {
 	struct xarray		rss_ctx;
 	struct mutex		rss_lock;
+	u32			rss_indir_user_size;
 	unsigned		wol_enabled:1;
 	unsigned		module_fw_flash_in_progress:1;
 };
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6882b41bb3e8..e15367373f7c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1716,7 +1716,6 @@ struct net_device_ops {
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
  * @IFF_TEAM: device is a team device
- * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured
  * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external
  *	entity (i.e. the master device for bridged veth)
  * @IFF_MACSEC: device is a MACsec device
@@ -1752,7 +1751,6 @@ enum netdev_priv_flags {
 	IFF_OPENVSWITCH			= 1<<20,
 	IFF_L3MDEV_SLAVE		= 1<<21,
 	IFF_TEAM			= 1<<22,
-	IFF_RXFH_CONFIGURED		= 1<<23,
 	IFF_PHONY_HEADROOM		= 1<<24,
 	IFF_MACSEC			= 1<<25,
 	IFF_NO_RX_HANDLER		= 1<<26,
@@ -5580,10 +5578,7 @@ static inline bool netif_is_lag_port(const struct net_device *dev)
 	return netif_is_bond_slave(dev) || netif_is_team_port(dev);
 }
 
-static inline bool netif_is_rxfh_configured(const struct net_device *dev)
-{
-	return dev->priv_flags & IFF_RXFH_CONFIGURED;
-}
+bool netif_is_rxfh_configured(const struct net_device *dev);
 
 static inline bool netif_is_failover(const struct net_device *dev)
 {
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 6a4a3797a812..98e85f393f8c 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -1204,6 +1204,34 @@ void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id)
 }
 EXPORT_SYMBOL(ethtool_rxfh_context_lost);
 
+bool netif_is_rxfh_configured(const struct net_device *dev)
+{
+	return dev->ethtool->rss_indir_user_size;
+}
+EXPORT_SYMBOL(netif_is_rxfh_configured);
+
+/**
+ * ethtool_rxfh_indir_lost - Notify core that the RSS indirection table was lost
+ * @dev: network device
+ *
+ * Drivers should call this when the device can no longer maintain the
+ * user-configured indirection table, typically after a HW fault recovery
+ * that reduced the maximum queue count. Marks the default RSS context
+ * indirection table as unconfigured and sends an %ETHTOOL_MSG_RSS_NTF
+ * notification.
+ */
+void ethtool_rxfh_indir_lost(struct net_device *dev)
+{
+	WARN_ONCE(!rtnl_is_locked() &&
+		  !lockdep_is_held_type(&dev->ethtool->rss_lock, -1),
+		  "RSS context lock assertion failed\n");
+
+	netdev_err(dev, "device error, RSS indirection table lost\n");
+	dev->ethtool->rss_indir_user_size = 0;
+	ethtool_rss_notify(dev, ETHTOOL_MSG_RSS_NTF, 0);
+}
+EXPORT_SYMBOL(ethtool_rxfh_indir_lost);
+
 enum ethtool_link_medium ethtool_str_to_medium(const char *str)
 {
 	int i;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 11dfbf076b6d..3c713a91ad0d 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1405,9 +1405,9 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 
 	/* indicate whether rxfh was set to default */
 	if (user_size == 0)
-		dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
+		dev->ethtool->rss_indir_user_size = 0;
 	else
-		dev->priv_flags |= IFF_RXFH_CONFIGURED;
+		dev->ethtool->rss_indir_user_size = rxfh_dev.indir_size;
 
 out_unlock:
 	mutex_unlock(&dev->ethtool->rss_lock);
@@ -1722,9 +1722,9 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (!rxfh_dev.rss_context) {
 		/* indicate whether rxfh was set to default */
 		if (rxfh.indir_size == 0)
-			dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
+			dev->ethtool->rss_indir_user_size = 0;
 		else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE)
-			dev->priv_flags |= IFF_RXFH_CONFIGURED;
+			dev->ethtool->rss_indir_user_size = dev_indir_size;
 	}
 	/* Update rss_ctx tracking */
 	if (rxfh_dev.rss_delete) {
@@ -1737,6 +1737,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			ctx->indir_configured =
 				rxfh.indir_size &&
 				rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE;
+			ctx->indir_user_size = dev_indir_size;
 		}
 		if (rxfh_dev.key) {
 			memcpy(ethtool_rxfh_context_key(ctx), rxfh_dev.key,
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 0f4e5cd2ac71..5cf90d73e70b 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -686,7 +686,7 @@ rss_set_prep_indir(struct net_device *dev, struct genl_info *info,
 
 	*mod |= memcmp(rxfh->indir, data->indir_table, data->indir_size);
 
-	return 0;
+	return user_size;
 
 err_free:
 	kfree(rxfh->indir);
@@ -833,6 +833,7 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info)
 	struct nlattr **tb = info->attrs;
 	struct rss_reply_data data = {};
 	const struct ethtool_ops *ops;
+	u32 indir_user_size;
 	int ret;
 
 	ops = dev->ethtool_ops;
@@ -845,8 +846,9 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info)
 	rxfh.rss_context = request->rss_context;
 
 	ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_reset, &mod);
-	if (ret)
+	if (ret < 0)
 		goto exit_clean_data;
+	indir_user_size = ret;
 	indir_mod = !!tb[ETHTOOL_A_RSS_INDIR];
 
 	rxfh.hfunc = data.hfunc;
@@ -889,12 +891,15 @@ ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info)
 	if (ret)
 		goto exit_unlock;
 
-	if (ctx)
+	if (ctx) {
 		rss_set_ctx_update(ctx, tb, &data, &rxfh);
-	else if (indir_reset)
-		dev->priv_flags &= ~IFF_RXFH_CONFIGURED;
-	else if (indir_mod)
-		dev->priv_flags |= IFF_RXFH_CONFIGURED;
+		if (indir_user_size)
+			ctx->indir_user_size = indir_user_size;
+	} else if (indir_reset) {
+		dev->ethtool->rss_indir_user_size = 0;
+	} else if (indir_mod) {
+		dev->ethtool->rss_indir_user_size = indir_user_size;
+	}
 
 exit_unlock:
 	mutex_unlock(&dev->ethtool->rss_lock);
@@ -999,6 +1004,7 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info)
 	const struct ethtool_ops *ops;
 	struct rss_req_info req = {};
 	struct net_device *dev;
+	u32 indir_user_size;
 	struct sk_buff *rsp;
 	void *hdr;
 	u32 limit;
@@ -1035,8 +1041,9 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info)
 		goto exit_ops;
 
 	ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_dflt, &mod);
-	if (ret)
+	if (ret < 0)
 		goto exit_clean_data;
+	indir_user_size = ret;
 
 	ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod);
 
@@ -1080,6 +1087,7 @@ int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	/* Store the config from rxfh to Xarray.. */
 	rss_set_ctx_update(ctx, tb, &data, &rxfh);
+	ctx->indir_user_size = indir_user_size;
 	/* .. copy from Xarray to data. */
 	__rss_prepare_ctx(dev, &data, ctx);