Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

Conflicts:

drivers/net/ethernet/intel/iavf/iavf_ethtool.c
  3a0b5a2929fd ("iavf: Introduce new state machines for flow director")
  95260816b489 ("iavf: use iavf_schedule_aq_request() helper")
https://lore.kernel.org/all/84e12519-04dc-bd80-bc34-8cf50d7898ce@intel.com/

drivers/net/ethernet/broadcom/bnxt/bnxt.c
  c13e268c0768 ("bnxt_en: Fix HWTSTAMP_FILTER_ALL packet timestamp logic")
  c2f8063309da ("bnxt_en: Refactor RX VLAN acceleration logic.")
  a7445d69809f ("bnxt_en: Add support for new RX and TPA_START completion types for P7")
  1c7fd6ee2fe4 ("bnxt_en: Rename some macros for the P5 chips")
https://lore.kernel.org/all/20231211110022.27926ad9@canb.auug.org.au/

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
  bd6781c18cb5 ("bnxt_en: Fix wrong return value check in bnxt_close_nic()")
  84793a499578 ("bnxt_en: Skip nic close/open when configuring tstamp filters")
https://lore.kernel.org/all/20231214113041.3a0c003c@canb.auug.org.au/

drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
  3d7a3f2612d7 ("net/mlx5: Nack sync reset request when HotPlug is enabled")
  cecf44ea1a1f ("net/mlx5: Allow sync reset flow when BF MGT interface device is present")
https://lore.kernel.org/all/20231211110328.76c925af@canb.auug.org.au/

No adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 24 insertions, 3 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 26a98cfb0a59..82eddfb19efc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2732,6 +2732,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 {
 	int i;
 
+	ASSERT_RTNL();
 	if (chs->ptp) {
 		mlx5e_ptp_close(chs->ptp);
 		chs->ptp = NULL;
@@ -3013,17 +3014,29 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_activate_channels(priv);
 
+	set_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
 
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_activate(priv->rx_res, &priv->channels);
 }
 
+static void mlx5e_cancel_tx_timeout_work(struct mlx5e_priv *priv)
+{
+	WARN_ON_ONCE(test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state));
+	if (current_work() != &priv->tx_timeout_work)
+		cancel_work_sync(&priv->tx_timeout_work);
+}
+
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	if (priv->rx_res)
 		mlx5e_rx_res_channels_deactivate(priv->rx_res);
 
+	clear_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state);
+	mlx5e_cancel_tx_timeout_work(priv);
+
 	if (mlx5e_is_vport_rep(priv))
 		mlx5e_rep_deactivate_channels(priv);
 
@@ -4802,8 +4815,17 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	struct net_device *netdev = priv->netdev;
 	int i;
 
-	rtnl_lock();
-	mutex_lock(&priv->state_lock);
+	/* Take rtnl_lock to ensure no change in netdev->real_num_tx_queues
+	 * through this flow. However, channel closing flows have to wait for
+	 * this work to finish while holding rtnl lock too. So either get the
+	 * lock or find that channels are being closed for other reason and
+	 * this work is not relevant anymore.
+	 */
+	while (!rtnl_trylock()) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+			return;
+		msleep(20);
+	}
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
 		goto unlock;
@@ -4822,7 +4844,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	}
 
 unlock:
-	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 }