[PATCH net-next] net: mana: Add debug knob to skip TX timeout recovery reset

[PATCH net-next] net: mana: Add debug knob to skip TX timeout recovery reset

[Aditya Garg]

Add a per-port debugfs boolean "tx_timeout_skip_reset" that, when
enabled, makes mana_tx_timeout() log the TX timeout and return without
queueing the per-port detach/attach recovery work.

This is a debug-only aid for bringup and qualification: skipping the
recovery reset keeps the device and queue state intact so a TX timeout
can be correlated with hardware telemetry. The knob defaults to false,
so production recovery behaviour is unchanged.

Signed-off-by: Aditya Garg <gargaditya@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Dipayaan Roy <dipayanroy@linux.microsoft.com>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 14 ++++++++++++++
 include/net/mana/mana.h                       |  3 +++
 2 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 89e7f59f635d..a8c329bdbacf 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -892,6 +892,17 @@ static void mana_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	struct mana_context *ac = apc->ac;
 	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 
+	/* Debug knob for bringup/qualification: when set, log the timeout and
+	 * skip the reset so the failing state is preserved for telemetry.
+	 * Disabled by default; production behaviour is unchanged.
+	 */
+	if (READ_ONCE(apc->tx_timeout_skip_reset)) {
+		netdev_warn(netdev,
+			    "TX timeout on queue %u: reset skipped (tx_timeout_skip_reset enabled)\n",
+			    txqueue);
+		return;
+	}
+
 	/* Already in service, hence tx queue reset is not required.*/
 	if (test_bit(GC_IN_SERVICE, &gc->flags))
 		return;
@@ -3486,6 +3497,9 @@ static int mana_init_port(struct net_device *ndev)
 			   &apc->steer_cqe_coalescing);
 	debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs,
 			   &apc->speed);
+	debugfs_create_bool("tx_timeout_skip_reset", 0600,
+			    apc->mana_port_debugfs,
+			    &apc->tx_timeout_skip_reset);
 	return 0;
 
 reset_apc:
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 226b61504596..4d041fb8437f 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -530,6 +530,9 @@ struct mana_port_context {
 	struct net_device *ndev;
 	struct work_struct queue_reset_work;
 
+	/* Debug knob to log TX timeout but skip recovery reset */
+	bool tx_timeout_skip_reset;
+
 	u8 mac_addr[ETH_ALEN];
 
 	struct mana_eq *eqs;
-- 
2.43.0