net/mlx5e: Fix race condition during IPSec ESN update

In IPSec full offload mode, the device reports an ESN (Extended
Sequence Number) wrap event to the driver. The driver validates this
event by querying the IPSec ASO and checking that the esn_event_arm
field is 0x0, which indicates an event has occurred. After handling
the event, the driver must re-arm the context by setting esn_event_arm
back to 0x1.

A race condition exists in this handling path. After validating the
event, the driver calls mlx5_accel_esp_modify_xfrm() to update the
kernel's xfrm state. This function temporarily releases and
re-acquires the xfrm state lock.

So, need to acknowledge the event first by setting esn_event_arm to
0x1. This prevents the driver from reprocessing the same ESN update if
the hardware sends events for other reason. Since the next ESN update
only occurs after nearly 2^31 packets are received, there's no risk of
missing an update, as it will happen long after this handling has
finished.

Processing the event twice causes the ESN high-order bits (esn_msb) to
be incremented incorrectly. The driver then programs the hardware with
this invalid ESN state, which leads to anti-replay failures and a
complete halt of IPSec traffic.

Fix this by re-arming the ESN event immediately after it is validated,
before calling mlx5_accel_esp_modify_xfrm(). This ensures that any
spurious, duplicate events are correctly ignored, closing the race
window.

Fixes: fef06678931f ("net/mlx5e: Fix ESN update kernel panic")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260316094603.6999-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
index 71222f7247f131cda1f463a24ce6baaaeaef8ab6..05faad5083d9d5df7cbef885e34d89cc4d83dca7 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
@@ -310,10 +310,11 @@ static void mlx5e_ipsec_aso_update(struct mlx5e_ipsec_sa_entry *sa_entry,
        mlx5e_ipsec_aso_query(sa_entry, data);
 }
 
-static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
-                                        u32 mode_param)
+static void
+mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
+                            u32 mode_param,
+                            struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
-       struct mlx5_accel_esp_xfrm_attrs attrs = {};
        struct mlx5_wqe_aso_ctrl_seg data = {};
 
        if (mode_param < MLX5E_IPSEC_ESN_SCOPE_MID) {
@@ -323,18 +324,7 @@ static void mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry,
                sa_entry->esn_state.overlap = 1;
        }
 
-       mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, &attrs);
-
-       /* It is safe to execute the modify below unlocked since the only flows
-        * that could affect this HW object, are create, destroy and this work.
-        *
-        * Creation flow can't co-exist with this modify work, the destruction
-        * flow would cancel this work, and this work is a single entity that
-        * can't conflict with it self.
-        */
-       spin_unlock_bh(&sa_entry->x->lock);
-       mlx5_accel_esp_modify_xfrm(sa_entry, &attrs);
-       spin_lock_bh(&sa_entry->x->lock);
+       mlx5e_ipsec_build_accel_xfrm_attrs(sa_entry, attrs);
 
        data.data_offset_condition_operand =
                MLX5_IPSEC_ASO_REMOVE_FLOW_PKT_CNT_OFFSET;
@@ -451,7 +441,9 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
        struct mlx5e_ipsec_work *work =
                container_of(_work, struct mlx5e_ipsec_work, work);
        struct mlx5e_ipsec_sa_entry *sa_entry = work->data;
+       struct mlx5_accel_esp_xfrm_attrs tmp = {};
        struct mlx5_accel_esp_xfrm_attrs *attrs;
+       bool need_modify = false;
        int ret;
 
        attrs = &sa_entry->attrs;
@@ -461,19 +453,22 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
        if (ret)
                goto unlock;
 
+       if (attrs->lft.soft_packet_limit != XFRM_INF)
+               mlx5e_ipsec_handle_limits(sa_entry);
+
        if (attrs->replay_esn.trigger &&
            !MLX5_GET(ipsec_aso, sa_entry->ctx, esn_event_arm)) {
                u32 mode_param = MLX5_GET(ipsec_aso, sa_entry->ctx,
                                          mode_parameter);
 
-               mlx5e_ipsec_update_esn_state(sa_entry, mode_param);
+               mlx5e_ipsec_update_esn_state(sa_entry, mode_param, &tmp);
+               need_modify = true;
        }
 
-       if (attrs->lft.soft_packet_limit != XFRM_INF)
-               mlx5e_ipsec_handle_limits(sa_entry);
-
 unlock:
        spin_unlock_bh(&sa_entry->x->lock);
+       if (need_modify)
+               mlx5_accel_esp_modify_xfrm(sa_entry, &tmp);
        kfree(work);
 }