All of lore.kernel.org
 help / color / mirror / Atom feed
From: Saeed Mahameed <saeed@kernel.org>
To: "David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeedm@nvidia.com>,
	netdev@vger.kernel.org, Tariq Toukan <tariqt@nvidia.com>,
	Maxim Mikityanskiy <maximmi@nvidia.com>
Subject: [net-next 15/15] net/mlx5e: Trigger NAPI after activating an SQ
Date: Sat,  4 Feb 2023 02:08:54 -0800	[thread overview]
Message-ID: <20230204100854.388126-16-saeed@kernel.org> (raw)
In-Reply-To: <20230204100854.388126-1-saeed@kernel.org>

From: Maxim Mikityanskiy <maximmi@nvidia.com>

If an SQ is deactivated and reactivated again, some packets could be
sent after MLX5E_SQ_STATE_ENABLED is cleared, but before
netif_tx_stop_queue, meaning that NAPI might miss some completions. In
order to handle them, make sure to trigger NAPI after SQ activation in
all cases where it can be relevant. Regular SQs, XDP SQs and XSK SQs are
good. Missing cases added: after recovery, after activating HTB SQs and
after activating PTP SQs.

Signed-off-by: Maxim Mikityanskiy <maximmi@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c  |  2 +-
 .../ethernet/mellanox/mlx5/core/en/reporter_tx.c  |  4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++------
 4 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 6f8723cc6874..125c7cb7d839 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -454,6 +454,7 @@ struct mlx5e_txqsq {
 	struct mlx5_clock         *clock;
 	struct net_device         *netdev;
 	struct mlx5_core_dev      *mdev;
+	struct mlx5e_channel      *channel;
 	struct mlx5e_priv         *priv;
 
 	/* control path */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 8469e9c38670..9a1bc93b7dc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -771,8 +771,8 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c)
 	if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
 		mlx5e_ptp_rx_set_fs(c->priv);
 		mlx5e_activate_rq(&c->rq);
-		mlx5e_trigger_napi_sched(&c->napi);
 	}
+	mlx5e_trigger_napi_sched(&c->napi);
 }
 
 void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index b195dbbf6c90..41e356d9d785 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -81,6 +81,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	sq->stats->recover++;
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
 	mlx5e_activate_txqsq(sq);
+	if (sq->channel)
+		mlx5e_trigger_napi_icosq(sq->channel);
+	else
+		mlx5e_trigger_napi_sched(sq->cq.napi);
 
 	return 0;
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e87432ec6f1..27f90baac768 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1470,6 +1470,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->mdev      = c->mdev;
+	sq->channel   = c;
 	sq->priv      = c->priv;
 	sq->ch_ix     = c->ix;
 	sq->txq_ix    = txq_ix;
@@ -2482,8 +2483,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 		mlx5e_activate_xsk(c);
 	else
 		mlx5e_activate_rq(&c->rq);
-
-	mlx5e_trigger_napi_icosq(c);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -2575,13 +2574,19 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	return err;
 }
 
-static void mlx5e_activate_channels(struct mlx5e_channels *chs)
+static void mlx5e_activate_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs)
 {
 	int i;
 
 	for (i = 0; i < chs->num; i++)
 		mlx5e_activate_channel(chs->c[i]);
 
+	if (priv->htb)
+		mlx5e_qos_activate_queues(priv);
+
+	for (i = 0; i < chs->num; i++)
+		mlx5e_trigger_napi_icosq(chs->c[i]);
+
 	if (chs->ptp)
 		mlx5e_ptp_activate_channel(chs->ptp);
 }
@@ -2888,9 +2893,7 @@ static void mlx5e_build_txq_maps(struct mlx5e_priv *priv)
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_build_txq_maps(priv);
-	mlx5e_activate_channels(&priv->channels);
-	if (priv->htb)
-		mlx5e_qos_activate_queues(priv);
+	mlx5e_activate_channels(priv, &priv->channels);
 	mlx5e_xdp_tx_enable(priv);
 
 	/* dev_watchdog() wants all TX queues to be started when the carrier is
-- 
2.39.1


      parent reply	other threads:[~2023-02-04 10:10 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-04 10:08 [pull request][net-next 00/15] mlx5 updates 2023-02-04 Saeed Mahameed
2023-02-04 10:08 ` [net-next 01/15] net/mlx5: Lag, Update multiport eswitch check to log an error Saeed Mahameed
2023-02-06  9:20   ` patchwork-bot+netdevbpf
2023-02-04 10:08 ` [net-next 02/15] net/mlx5: Lag, Use mlx5_lag_dev() instead of derefering pointers Saeed Mahameed
2023-02-04 10:08 ` [net-next 03/15] net/mlx5: Lag, Remove redundant bool allocation on the stack Saeed Mahameed
2023-02-04 10:08 ` [net-next 04/15] net/mlx5: Lag, Use flag to check for shared FDB mode Saeed Mahameed
2023-02-04 10:08 ` [net-next 05/15] net/mlx5: Lag, Move mpesw related definitions to mpesw.h Saeed Mahameed
2023-02-04 10:08 ` [net-next 06/15] net/mlx5: Separate mlx5 driver documentation into multiple pages Saeed Mahameed
2023-02-04 10:08 ` [net-next 07/15] net/mlx5: Update Kconfig parameter documentation Saeed Mahameed
2023-02-04 10:08 ` [net-next 08/15] net/mlx5: Document previously implemented mlx5 tracepoints Saeed Mahameed
2023-02-04 10:08 ` [net-next 09/15] net/mlx5: Add counter information to mlx5 driver documentation Saeed Mahameed
2023-02-04 10:08 ` [net-next 10/15] net/mlx5: Document support for RoCE HCA disablement capability Saeed Mahameed
2023-02-04 10:08 ` [net-next 11/15] net/mlx5: Add firmware support for MTUTC scaled_ppm frequency adjustments Saeed Mahameed
2023-02-04 10:08 ` [net-next 12/15] net/mlx5: Enhance debug print in page allocation failure Saeed Mahameed
2023-02-04 10:08 ` [net-next 13/15] net/mlx5e: IPoIB, Add support for XDR speed Saeed Mahameed
2023-02-04 10:08 ` [net-next 14/15] net/mlx5e: IPsec, support upper protocol selector field offload Saeed Mahameed
2023-02-04 10:08 ` Saeed Mahameed [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230204100854.388126-16-saeed@kernel.org \
    --to=saeed@kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=kuba@kernel.org \
    --cc=maximmi@nvidia.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=saeedm@nvidia.com \
    --cc=tariqt@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.