Merge branch 'net-mlx5e-reduce-interface-downtime-on-configuration-change'

Tariq Toukan says:

====================
net/mlx5e: Reduce interface downtime on configuration change

This series significantly reduces the interface downtime while swapping
channels during a configuration change, on capable devices.

Here we remove an old requirement on operations ordering that became
obsolete on recent capable devices. This helps cutting the downtime by a
factor of magnitude, ~80% in our example.

Perf numbers:
Measured the number of dropped packets in a simple ping flood test,
during a configuration change operation, that switches the number of
channels from 247 to 248.

Before: 71 packets lost
After:  15 packets lost, ~80% saving.
====================

Link: https://patch.msgid.link/1761831159-1013140-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -1156,7 +1156,9 @@ extern const struct ethtool_ops mlx5e_ethtool_ops;
 int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey);
 int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises);
 void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
+int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+			 bool enable_mc_lb);
+int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb,
 		       bool enable_mc_lb);
 void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc);
 

drivers/net/ethernet/mellanox/mlx5/core/en/rss.c

@@ -231,6 +231,8 @@ mlx5e_rss_create_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 				    rqtn, rss_inner);
 	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
+	mlx5e_tir_builder_build_self_lb_block(builder, rss->params.self_lb_blk,
+					      rss->params.self_lb_blk);
 	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
 
 	err = mlx5e_tir_init(tir, builder, rss->mdev, true);

drivers/net/ethernet/mellanox/mlx5/core/en/rss.h

@@ -23,6 +23,7 @@ struct mlx5e_rss_init_params {
 struct mlx5e_rss_params {
 	bool inner_ft_support;
 	u32 drop_rqn;
+	bool self_lb_blk;
 };
 
 struct mlx5e_rss_params_traffic_type

drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c

@@ -71,6 +71,8 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
 	rss_params = (struct mlx5e_rss_params) {
 		.inner_ft_support = inner_ft_support,
 		.drop_rqn = res->drop_rqn,
+		.self_lb_blk =
+			res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK,
 	};
 
 	rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params);
@@ -104,6 +106,8 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 rss_idx, unsigned int in
 	rss_params = (struct mlx5e_rss_params) {
 		.inner_ft_support = inner_ft_support,
 		.drop_rqn = res->drop_rqn,
+		.self_lb_blk =
+			res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK,
 	};
 
 	rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params);
@@ -346,6 +350,7 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig
 static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
+	bool self_lb_blk = res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK;
 	struct mlx5e_tir_builder *builder;
 	int err = 0;
 	int ix;
@@ -376,6 +381,8 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res)
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 					    inner_ft_support);
 		mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param);
+		mlx5e_tir_builder_build_self_lb_block(builder, self_lb_blk,
+						      self_lb_blk);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);

drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h

@@ -21,6 +21,7 @@ enum mlx5e_rx_res_features {
 	MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0),
 	MLX5E_RX_RES_FEATURE_PTP = BIT(1),
 	MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2),
+	MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK = BIT(3),
 };
 
 /* Setup */

drivers/net/ethernet/mellanox/mlx5/core/en/tir.c

@@ -146,6 +146,31 @@ void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder)
 	MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8);
 }
 
+static void mlx5e_tir_context_self_lb_block(void *tirc, bool enable_uc_lb,
+					    bool enable_mc_lb)
+{
+	u8 lb_flags = 0;
+
+	if (enable_uc_lb)
+		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+	if (enable_mc_lb)
+		lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flags);
+}
+
+void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder,
+					   bool enable_uc_lb,
+					   bool enable_mc_lb)
+{
+	void *tirc = mlx5e_tir_builder_get_tirc(builder);
+
+	if (builder->modify)
+		MLX5_SET(modify_tir_in, builder->in, bitmask.self_lb_en, 1);
+
+	mlx5e_tir_context_self_lb_block(tirc, enable_uc_lb, enable_mc_lb);
+}
+
 void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder)
 {
 	void *tirc = mlx5e_tir_builder_get_tirc(builder);
@@ -153,9 +178,7 @@ void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder)
 	WARN_ON(builder->modify);
 
 	MLX5_SET(tirc, tirc, tls_en, 1);
-	MLX5_SET(tirc, tirc, self_lb_block,
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST |
-		 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST);
+	mlx5e_tir_context_self_lb_block(tirc, true, true);
 }
 
 int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder,

drivers/net/ethernet/mellanox/mlx5/core/en/tir.h

@@ -35,6 +35,9 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 				 const struct mlx5e_rss_params_traffic_type *rss_tt,
 				 bool inner);
 void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder);
+void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder,
+					   bool enable_uc_lb,
+					   bool enable_mc_lb);
 void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder);
 
 struct mlx5_core_dev;

drivers/net/ethernet/mellanox/mlx5/core/en_common.c

@@ -247,45 +247,43 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev)
 	memset(res, 0, sizeof(*res));
 }
 
-int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb,
-		       bool enable_mc_lb)
+int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+			 bool enable_mc_lb)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_tir_builder *builder;
 	struct mlx5e_tir *tir;
-	u8 lb_flags = 0;
-	int err  = 0;
-	u32 tirn = 0;
-	int inlen;
-	void *in;
+	int err = 0;
 
-	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	builder = mlx5e_tir_builder_alloc(true);
+	if (!builder)
 		return -ENOMEM;
 
-	if (enable_uc_lb)
-		lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
-
-	if (enable_mc_lb)
-		lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
-
-	if (lb_flags)
-		MLX5_SET(modify_tir_in, in, ctx.self_lb_block, lb_flags);
-
-	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
+	mlx5e_tir_builder_build_self_lb_block(builder, enable_uc_lb,
+					      enable_mc_lb);
 
 	mutex_lock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.hw_objs.td.tirs_list, list) {
-		tirn = tir->tirn;
-		err = mlx5_core_modify_tir(mdev, tirn, in);
-		if (err)
+		err = mlx5e_tir_modify(tir, builder);
+		if (err) {
+			mlx5_core_err(mdev,
+				      "modify tir(0x%x) enable_lb uc(%d) mc(%d) failed, %d\n",
+				      mlx5e_tir_get_tirn(tir),
+				      enable_uc_lb, enable_mc_lb, err);
 			break;
+		}
 	}
 	mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock);
 
-	kvfree(in);
-	if (err)
-		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mlx5e_tir_builder_free(builder);
 
 	return err;
 }
+
+int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb,
+		       bool enable_mc_lb)
+{
+	if (MLX5_CAP_GEN(mdev, tis_tir_td_order))
+		return 0; /* refresh not needed */
+
+	return mlx5e_modify_tirs_lb(mdev, enable_uc_lb, enable_mc_lb);
+}

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -3356,12 +3356,12 @@ static int mlx5e_switch_priv_params(struct mlx5e_priv *priv,
 }
 
 static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				      struct mlx5e_channels *old_chs,
 				      struct mlx5e_channels *new_chs,
 				      mlx5e_fp_preactivate preactivate,
 				      void *context)
 {
 	struct net_device *netdev = priv->netdev;
-	struct mlx5e_channels old_chs;
 	int carrier_ok;
 	int err = 0;
 
@@ -3370,7 +3370,6 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 
 	mlx5e_deactivate_priv_channels(priv);
 
-	old_chs = priv->channels;
 	priv->channels = *new_chs;
 
 	/* New channels are ready to roll, call the preactivate hook if needed
@@ -3379,12 +3378,13 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 	if (preactivate) {
 		err = preactivate(priv, context);
 		if (err) {
-			priv->channels = old_chs;
+			priv->channels = *old_chs;
 			goto out;
 		}
 	}
 
-	mlx5e_close_channels(&old_chs);
+	if (!MLX5_CAP_GEN(priv->mdev, tis_tir_td_order))
+		mlx5e_close_channels(old_chs);
 	priv->profile->update_rx(priv);
 
 	mlx5e_selq_apply(&priv->selq);
@@ -3403,16 +3403,20 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 			     mlx5e_fp_preactivate preactivate,
 			     void *context, bool reset)
 {
-	struct mlx5e_channels *new_chs;
+	struct mlx5e_channels *old_chs, *new_chs;
 	int err;
 
 	reset &= test_bit(MLX5E_STATE_OPENED, &priv->state);
 	if (!reset)
 		return mlx5e_switch_priv_params(priv, params, preactivate, context);
 
+	old_chs = kzalloc(sizeof(*old_chs), GFP_KERNEL);
 	new_chs = kzalloc(sizeof(*new_chs), GFP_KERNEL);
-	if (!new_chs)
-		return -ENOMEM;
+	if (!old_chs || !new_chs) {
+		err = -ENOMEM;
+		goto err_free_chs;
+	}
+
 	new_chs->params = *params;
 
 	mlx5e_selq_prepare_params(&priv->selq, &new_chs->params);
@@ -3421,11 +3425,18 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 	if (err)
 		goto err_cancel_selq;
 
-	err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context);
+	*old_chs = priv->channels;
+
+	err = mlx5e_switch_priv_channels(priv, old_chs, new_chs,
+					 preactivate, context);
 	if (err)
 		goto err_close;
 
+	if (MLX5_CAP_GEN(priv->mdev, tis_tir_td_order))
+		mlx5e_close_channels(old_chs);
+
 	kfree(new_chs);
+	kfree(old_chs);
 	return 0;
 
 err_close:
@@ -3433,7 +3444,9 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv,
 
 err_cancel_selq:
 	mlx5e_selq_cancel(&priv->selq);
+err_free_chs:
 	kfree(new_chs);
+	kfree(old_chs);
 	return err;
 }
 
@@ -6136,7 +6149,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 static int mlx5e_update_nic_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_refresh_tirs(priv, false, false);
+	return mlx5e_refresh_tirs(priv->mdev, false, false);
 }
 
 static const struct mlx5e_profile mlx5e_nic_profile = {

drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c

@@ -214,7 +214,7 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv,
 			return err;
 	}
 
-	err = mlx5e_refresh_tirs(priv, true, false);
+	err = mlx5e_modify_tirs_lb(priv->mdev, true, false);
 	if (err)
 		goto out;
 
@@ -243,7 +243,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv,
 		mlx5_nic_vport_update_local_lb(priv->mdev, false);
 
 	dev_remove_pack(&lbtp->pt);
-	mlx5e_refresh_tirs(priv, false, false);
+	mlx5e_modify_tirs_lb(priv->mdev, false, false);
 }
 
 static int mlx5e_cond_loopback(struct mlx5e_priv *priv)

drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c

@@ -334,7 +334,7 @@ void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn)
 
 int mlx5i_update_nic_rx(struct mlx5e_priv *priv)
 {
-	return mlx5e_refresh_tirs(priv, true, true);
+	return mlx5e_refresh_tirs(priv->mdev, true, true);
 }
 
 int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn)
@@ -427,6 +427,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
+	enum mlx5e_rx_res_features features;
 	int err;
 
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
@@ -445,7 +446,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	priv->rx_res = mlx5e_rx_res_create(priv->mdev, 0, priv->max_nch, priv->drop_rq.rqn,
+	features = MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK;
+	priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch,
+					   priv->drop_rq.rqn,
 					   &priv->channels.params.packet_merge,
 					   priv->channels.params.num_channels);
 	if (IS_ERR(priv->rx_res)) {