net/mlx5e: Fix misidentification of ASO CQE during poll loop

The ASO completion poll loop uses usleep_range() which can sleep much
longer than requested due to scheduler latency. Under load, we witnessed
a 20ms+ delay until the process was rescheduled, causing the jiffies
based timeout to expire while the thread is sleeping.

The original do-while loop structure (poll, sleep, check timeout) would
exit without a final poll when waking after timeout, missing a CQE that
arrived during sleep.

Instead of the open-coded while loop, use the kernel's
read_poll_timeout() which always performs an additional check after the
sleep expiration, and is less error-prone.

Note: read_poll_timeout() doesn't accept a sleep range, by passing 10
sleep_us the sleep range effectively changes from 2-10 to 3-10 usecs.

Fixes: 739cfa34518e ("net/mlx5: Make ASO poll CQ usable in atomic context")
Fixes: 7e3fce82d945 ("net/mlx5e: Overcome slow response for first macsec ASO WQE")
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <Jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20260218072904.1764634-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 6 insertions, 14 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
index 7819fb297280..d5d9146efca6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 
+#include <linux/iopoll.h>
 #include <linux/math64.h>
 #include "lib/aso.h"
 #include "en/tc/post_act.h"
@@ -115,7 +116,6 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev,
 	struct mlx5e_flow_meters *flow_meters;
 	u8 cir_man, cir_exp, cbs_man, cbs_exp;
 	struct mlx5_aso_wqe *aso_wqe;
-	unsigned long expires;
 	struct mlx5_aso *aso;
 	u64 rate, burst;
 	u8 ds_cnt;
@@ -187,12 +187,8 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev,
 	mlx5_aso_post_wqe(aso, true, &aso_wqe->ctrl);
 
 	/* With newer FW, the wait for the first ASO WQE is more than 2us, put the wait 10ms. */
-	expires = jiffies + msecs_to_jiffies(10);
-	do {
-		err = mlx5_aso_poll_cq(aso, true);
-		if (err)
-			usleep_range(2, 10);
-	} while (err && time_is_after_jiffies(expires));
+	read_poll_timeout(mlx5_aso_poll_cq, err, !err, 10, 10 * USEC_PER_MSEC,
+			  false, aso, true);
 	mutex_unlock(&flow_meters->aso_lock);
 
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 528b04d4de41..641cd3a2cdfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -5,6 +5,7 @@
 #include <linux/mlx5/mlx5_ifc.h>
 #include <linux/xarray.h>
 #include <linux/if_vlan.h>
+#include <linux/iopoll.h>
 
 #include "en.h"
 #include "lib/aso.h"
@@ -1397,7 +1398,6 @@ static int macsec_aso_query(struct mlx5_core_dev *mdev, struct mlx5e_macsec *mac
 	struct mlx5e_macsec_aso *aso;
 	struct mlx5_aso_wqe *aso_wqe;
 	struct mlx5_aso *maso;
-	unsigned long expires;
 	int err;
 
 	aso = &macsec->aso;
@@ -1411,12 +1411,8 @@ static int macsec_aso_query(struct mlx5_core_dev *mdev, struct mlx5e_macsec *mac
 	macsec_aso_build_wqe_ctrl_seg(aso, &aso_wqe->aso_ctrl, NULL);
 
 	mlx5_aso_post_wqe(maso, false, &aso_wqe->ctrl);
-	expires = jiffies + msecs_to_jiffies(10);
-	do {
-		err = mlx5_aso_poll_cq(maso, false);
-		if (err)
-			usleep_range(2, 10);
-	} while (err && time_is_after_jiffies(expires));
+	read_poll_timeout(mlx5_aso_poll_cq, err, !err, 10, 10 * USEC_PER_MSEC,
+			  false, maso, false);
 
 	if (err)
 		goto err_out;