From: Maxim Mikityanskiy <maximmi@nvidia.com>
Date: Tue, 25 Jan 2022 12:52:59 +0200
Subject: net/mlx5e: Optimize modulo in mlx5e_select_queue
Patch-mainline: v5.18-rc1
Git-commit: 3a9e5fff2ab0d6f4af701757d35b9453dc563b78
References: jsc#PED-1549

To improve the performance of the modulo operation (%), it's replaced by
a subtracting the divisor in a loop. The modulo is used to fix up an
out-of-bounds value that might be returned by netdev_pick_tx or to
convert the queue number to the channel number when num_tcs > 1. Both
situations are unlikely, because XPS is configured not to pick higher
queues (qid >= num_channels) by default, so under normal circumstances
the flow won't go inside the loop, and it will be faster than %.

num_tcs == 8 adds at most 7 iterations to the loop. PTP adds at most 1
iteration to the loop. HTB would add at most 256 iterations (when
num_channels == 1), so there is an additional boundary check in the HTB
flow, which falls back to % if more than 7 iterations are expected.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/selq.c |    7 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/en/selq.h |   20 ++++++++++++++++++++
 2 files changed, 24 insertions(+), 3 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
@@ -178,7 +178,8 @@ u16 mlx5e_select_queue(struct net_device
 		 * So we can return a txq_ix that matches the channel and
 		 * packet UP.
 		 */
-		return txq_ix % selq->num_channels + up * selq->num_channels;
+		return mlx5e_txq_to_ch_ix(txq_ix, selq->num_channels) +
+			up * selq->num_channels;
 	}
 
 	if (unlikely(selq->is_htb)) {
@@ -198,7 +199,7 @@ u16 mlx5e_select_queue(struct net_device
 		 * Driver to select these queues only at mlx5e_select_ptpsq()
 		 * and mlx5e_select_htb_queue().
 		 */
-		return txq_ix % selq->num_channels;
+		return mlx5e_txq_to_ch_ix_htb(txq_ix, selq->num_channels);
 	}
 
 	/* PTP is enabled */
@@ -214,7 +215,7 @@ u16 mlx5e_select_queue(struct net_device
 	 * If netdev_pick_tx() picks ptp_channel, switch to a regular queue,
 	 * because driver should select the PTP only at mlx5e_select_ptpsq().
 	 */
-	txq_ix %= selq->num_channels;
+	txq_ix = mlx5e_txq_to_ch_ix(txq_ix, selq->num_channels);
 
 	if (selq->num_tcs <= 1)
 		return txq_ix;
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.h
@@ -25,6 +25,26 @@ void mlx5e_selq_prepare(struct mlx5e_sel
 void mlx5e_selq_apply(struct mlx5e_selq *selq);
 void mlx5e_selq_cancel(struct mlx5e_selq *selq);
 
+static inline u16 mlx5e_txq_to_ch_ix(u16 txq, u16 num_channels)
+{
+	while (unlikely(txq >= num_channels))
+		txq -= num_channels;
+	return txq;
+}
+
+static inline u16 mlx5e_txq_to_ch_ix_htb(u16 txq, u16 num_channels)
+{
+	if (unlikely(txq >= num_channels)) {
+		if (unlikely(txq >= num_channels << 3))
+			txq %= num_channels;
+		else
+			do
+				txq -= num_channels;
+			while (txq >= num_channels);
+	}
+	return txq;
+}
+
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       struct net_device *sb_dev);