Merge tag 'mlx5-fixes-2023-01-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2023-01-18' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net: mlx5: eliminate anonymous module_init & module_exit
  net/mlx5: E-switch, Fix switchdev mode after devlink reload
  net/mlx5e: Protect global IPsec ASO
  net/mlx5e: Remove optimization which prevented update of ESN state
  net/mlx5e: Set decap action based on attr for sample
  net/mlx5e: QoS, Fix wrongfully setting parent_element_id on MODIFY_SCHEDULING_ELEMENT
  net/mlx5: E-switch, Fix setting of reserved fields on MODIFY_SCHEDULING_ELEMENT
  net/mlx5e: Remove redundant xsk pointer check in mlx5e_mpwrq_validate_xsk
  net/mlx5e: Avoid false lock dependency warning on tc_ht even more
  net/mlx5: fix missing mutex_unlock in mlx5_fw_fatal_reporter_err_work()
====================

Link: https://lore.kernel.org/r/Signed-off-by: Paolo Abeni <pabeni@redhat.com>

drivers/net/ethernet/mellanox/mlx5/core/en/htb.c

@@ -637,7 +637,7 @@ mlx5e_htb_update_children(struct mlx5e_htb *htb, struct mlx5e_qos_node *node,
 		if (child->bw_share == old_bw_share)
 			continue;
 
-		err_one = mlx5_qos_update_node(htb->mdev, child->hw_id, child->bw_share,
+		err_one = mlx5_qos_update_node(htb->mdev, child->bw_share,
 					       child->max_average_bw, child->hw_id);
 		if (!err && err_one) {
 			err = err_one;
@@ -671,7 +671,7 @@ mlx5e_htb_node_modify(struct mlx5e_htb *htb, u16 classid, u64 rate, u64 ceil,
 	mlx5e_htb_convert_rate(htb, rate, node->parent, &bw_share);
 	mlx5e_htb_convert_ceil(htb, ceil, &max_average_bw);
 
-	err = mlx5_qos_update_node(htb->mdev, node->parent->hw_id, bw_share,
+	err = mlx5_qos_update_node(htb->mdev, bw_share,
 				   max_average_bw, node->hw_id);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Firmware error when modifying a node.");

drivers/net/ethernet/mellanox/mlx5/core/en/params.c

@@ -578,7 +578,6 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa
 {
 	enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk);
 	u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk);
-	bool unaligned = xsk ? xsk->unaligned : false;
 	u16 max_mtu_pkts;
 
 	if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode))
@@ -591,7 +590,7 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa
 	 * needed number of WQEs exceeds the maximum.
 	 */
 	max_mtu_pkts = min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE,
-			     mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, unaligned));
+			     mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, xsk->unaligned));
 	if (params->log_rq_mtu_frames > max_mtu_pkts) {
 		mlx5_core_err(mdev, "Current RQ length %d is too big for XSK with given frame size %u\n",
 			      1 << params->log_rq_mtu_frames, xsk->chunk_size);

drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c

@@ -477,7 +477,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	struct mlx5e_sample_flow *sample_flow;
 	struct mlx5e_sample_attr *sample_attr;
 	struct mlx5_flow_attr *pre_attr;
-	u32 tunnel_id = attr->tunnel_id;
 	struct mlx5_eswitch *esw;
 	u32 default_tbl_id;
 	u32 obj_id;
@@ -522,7 +521,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	restore_obj.sample.group_id = sample_attr->group_num;
 	restore_obj.sample.rate = sample_attr->rate;
 	restore_obj.sample.trunc_size = sample_attr->trunc_size;
-	restore_obj.sample.tunnel_id = tunnel_id;
+	restore_obj.sample.tunnel_id = attr->tunnel_id;
 	err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id);
 	if (err)
 		goto err_obj_id;
@@ -548,7 +547,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample,
 	/* For decap action, do decap in the original flow table instead of the
 	 * default flow table.
 	 */
-	if (tunnel_id)
+	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
 		pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
 	pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
 	pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h

@@ -122,11 +122,8 @@ struct mlx5e_ipsec_aso {
 	u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)];
 	dma_addr_t dma_addr;
 	struct mlx5_aso *aso;
-	/* IPsec ASO caches data on every query call,
-	 * so in nested calls, we can use this boolean to save
-	 * recursive calls to mlx5e_ipsec_aso_query()
-	 */
-	u8 use_cache : 1;
+	/* Protect ASO WQ access, as it is global to whole IPsec */
+	spinlock_t lock;
 };
 
 struct mlx5e_ipsec {

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c

@@ -320,7 +320,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 	if (ret)
 		goto unlock;
 
-	aso->use_cache = true;
 	if (attrs->esn_trigger &&
 	    !MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) {
 		u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter);
@@ -333,7 +332,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work)
 		    !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) ||
 		    !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable))
 			xfrm_state_check_expire(sa_entry->x);
-	aso->use_cache = false;
 
 unlock:
 	spin_unlock(&sa_entry->x->lock);
@@ -398,6 +396,7 @@ int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec)
 		goto err_aso_create;
 	}
 
+	spin_lock_init(&aso->lock);
 	ipsec->nb.notifier_call = mlx5e_ipsec_event;
 	mlx5_notifier_register(mdev, &ipsec->nb);
 
@@ -456,13 +455,12 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
 	struct mlx5e_hw_objs *res;
 	struct mlx5_aso_wqe *wqe;
 	u8 ds_cnt;
+	int ret;
 
 	lockdep_assert_held(&sa_entry->x->lock);
-	if (aso->use_cache)
-		return 0;
-
 	res = &mdev->mlx5e_res.hw_objs;
 
+	spin_lock_bh(&aso->lock);
 	memset(aso->ctx, 0, sizeof(aso->ctx));
 	wqe = mlx5_aso_get_wqe(aso->aso);
 	ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
@@ -477,7 +475,9 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry,
 	mlx5e_ipsec_aso_copy(ctrl, data);
 
 	mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl);
-	return mlx5_aso_poll_cq(aso->aso, false);
+	ret = mlx5_aso_poll_cq(aso->aso, false);
+	spin_unlock_bh(&aso->lock);
+	return ret;
 }
 
 void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry,

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -166,6 +166,7 @@ struct mlx5_fs_chains *mlx5e_nic_chains(struct mlx5e_tc_table *tc)
  * it's different than the ht->mutex here.
  */
 static struct lock_class_key tc_ht_lock_key;
+static struct lock_class_key tc_ht_wq_key;
 
 static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
 static void free_flow_post_acts(struct mlx5e_tc_flow *flow);
@@ -5182,6 +5183,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 		return err;
 
 	lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key);
+	lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
 
 	mapping_id = mlx5_query_nic_system_image_guid(dev);
 
@@ -5288,6 +5290,7 @@ int mlx5e_tc_ht_init(struct rhashtable *tc_ht)
 		return err;
 
 	lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key);
+	lockdep_init_map(&tc_ht->run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0);
 
 	return 0;
 }

drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c

@@ -22,15 +22,13 @@ struct mlx5_esw_rate_group {
 };
 
 static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx,
-			       u32 parent_ix, u32 tsar_ix,
-			       u32 max_rate, u32 bw_share)
+			       u32 tsar_ix, u32 max_rate, u32 bw_share)
 {
 	u32 bitmask = 0;
 
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
 	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
 	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
@@ -51,7 +49,7 @@ static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_g
 	int err;
 
 	err = esw_qos_tsar_config(dev, sched_ctx,
-				  esw->qos.root_tsar_ix, group->tsar_ix,
+				  group->tsar_ix,
 				  max_rate, bw_share);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed");
@@ -67,23 +65,13 @@ static int esw_qos_vport_config(struct mlx5_eswitch *esw,
 				struct netlink_ext_ack *extack)
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
-	struct mlx5_esw_rate_group *group = vport->qos.group;
 	struct mlx5_core_dev *dev = esw->dev;
-	u32 parent_tsar_ix;
-	void *vport_elem;
 	int err;
 
 	if (!vport->qos.enabled)
 		return -EIO;
 
-	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
-	MLX5_SET(scheduling_context, sched_ctx, element_type,
-		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
-	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
-				  element_attributes);
-	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
-
-	err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix,
+	err = esw_qos_tsar_config(dev, sched_ctx, vport->qos.esw_tsar_ix,
 				  max_rate, bw_share);
 	if (err) {
 		esw_warn(esw->dev,

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1464,6 +1464,7 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 	mlx5_lag_disable_change(esw->dev);
 	down_write(&esw->mode_lock);
 	mlx5_eswitch_disable_locked(esw);
+	esw->mode = MLX5_ESWITCH_LEGACY;
 	up_write(&esw->mode_lock);
 	mlx5_lag_enable_change(esw->dev);
 }

drivers/net/ethernet/mellanox/mlx5/core/health.c

@@ -677,6 +677,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
 		mlx5_core_err(dev, "health works are not permitted at this stage\n");
+		mutex_unlock(&dev->intf_state_mutex);
 		return;
 	}
 	mutex_unlock(&dev->intf_state_mutex);

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -2098,7 +2098,7 @@ static void mlx5_core_verify_params(void)
 	}
 }
 
-static int __init init(void)
+static int __init mlx5_init(void)
 {
 	int err;
 
@@ -2133,7 +2133,7 @@ static int __init init(void)
 	return err;
 }
 
-static void __exit cleanup(void)
+static void __exit mlx5_cleanup(void)
 {
 	mlx5e_cleanup();
 	mlx5_sf_driver_unregister();
@@ -2141,5 +2141,5 @@ static void __exit cleanup(void)
 	mlx5_unregister_debugfs();
 }
 
-module_init(init);
-module_exit(cleanup);
+module_init(mlx5_init);
+module_exit(mlx5_cleanup);

drivers/net/ethernet/mellanox/mlx5/core/qos.c

@@ -62,13 +62,12 @@ int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id)
 	return mlx5_qos_create_inner_node(mdev, MLX5_QOS_DEFAULT_DWRR_UID, 0, 0, id);
 }
 
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev,
 			 u32 bw_share, u32 max_avg_bw, u32 id)
 {
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
 	u32 bitmask = 0;
 
-	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
 	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
 	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_avg_bw);
 

drivers/net/ethernet/mellanox/mlx5/core/qos.h

@@ -23,7 +23,7 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id,
 int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id,
 			       u32 bw_share, u32 max_avg_bw, u32 *id);
 int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id);
-int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share,
+int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share,
 			 u32 max_avg_bw, u32 id);
 int mlx5_qos_destroy_node(struct mlx5_core_dev *mdev, u32 id);