Merge tag 'mlx5-fixes-2022-05-31' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2022-05-31

This series provides bug fixes to mlx5 driver.
Please pull and let me know if there is any problem.

* tag 'mlx5-fixes-2022-05-31' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5: Fix mlx5_get_next_dev() peer device matching
  net/mlx5e: Update netdev features after changing XDP state
  net/mlx5: correct ECE offset in query qp output
  net/mlx5e: Disable softirq in mlx5e_activate_rq to avoid race condition
  net/mlx5: CT: Fix header-rewrite re-use for tupels
  net/mlx5e: TC NIC mode, fix tc chains miss table
  net/mlx5: Don't use already freed action pointer
====================

Link: https://lore.kernel.org/r/20220531205447.99236-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -571,18 +571,32 @@ static int _next_phys_dev(struct mlx5_core_dev *mdev,
 	return 1;
 }
 
+static void *pci_get_other_drvdata(struct device *this, struct device *other)
+{
+	if (this->driver != other->driver)
+		return NULL;
+
+	return pci_get_drvdata(to_pci_dev(other));
+}
+
 static int next_phys_dev(struct device *dev, const void *data)
 {
-	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
-	struct mlx5_core_dev *mdev = madev->mdev;
+	struct mlx5_core_dev *mdev, *this = (struct mlx5_core_dev *)data;
+
+	mdev = pci_get_other_drvdata(this->device, dev);
+	if (!mdev)
+		return 0;
 
 	return _next_phys_dev(mdev, data);
 }
 
 static int next_phys_dev_lag(struct device *dev, const void *data)
 {
-	struct mlx5_adev *madev = container_of(dev, struct mlx5_adev, adev.dev);
-	struct mlx5_core_dev *mdev = madev->mdev;
+	struct mlx5_core_dev *mdev, *this = (struct mlx5_core_dev *)data;
+
+	mdev = pci_get_other_drvdata(this->device, dev);
+	if (!mdev)
+		return 0;
 
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(mdev, lag_master) ||
@@ -596,19 +610,17 @@ static int next_phys_dev_lag(struct device *dev, const void *data)
 static struct mlx5_core_dev *mlx5_get_next_dev(struct mlx5_core_dev *dev,
 					       int (*match)(struct device *dev, const void *data))
 {
-	struct auxiliary_device *adev;
-	struct mlx5_adev *madev;
+	struct device *next;
 
 	if (!mlx5_core_is_pf(dev))
 		return NULL;
 
-	adev = auxiliary_find_device(NULL, dev, match);
-	if (!adev)
+	next = bus_find_device(&pci_bus_type, NULL, dev, match);
+	if (!next)
 		return NULL;
 
-	madev = container_of(adev, struct mlx5_adev, adev);
-	put_device(&adev->dev);
-	return madev->mdev;
+	put_device(next);
+	return pci_get_drvdata(to_pci_dev(next));
 }
 
 /* Must be called with intf_mutex held */

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

@@ -764,6 +764,7 @@ struct mlx5e_rq {
 	u8                     wq_type;
 	u32                    rqn;
 	struct mlx5_core_dev  *mdev;
+	struct mlx5e_channel  *channel;
 	u32  umr_mkey;
 	struct mlx5e_dma_info  wqe_overflow;
 
@@ -1076,6 +1077,9 @@ void mlx5e_close_cq(struct mlx5e_cq *cq);
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
 
+void mlx5e_trigger_napi_icosq(struct mlx5e_channel *c);
+void mlx5e_trigger_napi_sched(struct napi_struct *napi);
+
 int mlx5e_open_channels(struct mlx5e_priv *priv,
 			struct mlx5e_channels *chs);
 void mlx5e_close_channels(struct mlx5e_channels *chs);

drivers/net/ethernet/mellanox/mlx5/core/en/fs.h

@@ -12,6 +12,7 @@ struct mlx5e_post_act;
 enum {
 	MLX5E_TC_FT_LEVEL = 0,
 	MLX5E_TC_TTC_FT_LEVEL,
+	MLX5E_TC_MISS_LEVEL,
 };
 
 struct mlx5e_tc_table {
@@ -20,6 +21,7 @@ struct mlx5e_tc_table {
 	 */
 	struct mutex			t_lock;
 	struct mlx5_flow_table		*t;
+	struct mlx5_flow_table		*miss_t;
 	struct mlx5_fs_chains           *chains;
 	struct mlx5e_post_act		*post_act;
 

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

@@ -736,6 +736,7 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c)
 	if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
 		mlx5e_ptp_rx_set_fs(c->priv);
 		mlx5e_activate_rq(&c->rq);
+		mlx5e_trigger_napi_sched(&c->napi);
 	}
 }
 

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

@@ -123,6 +123,8 @@ static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx)
 		xskrq->stats->recover++;
 	}
 
+	mlx5e_trigger_napi_icosq(icosq->channel);
+
 	mutex_unlock(&icosq->channel->icosq_recovery_lock);
 
 	return 0;
@@ -166,6 +168,10 @@ static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx)
 	clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state);
 	mlx5e_activate_rq(rq);
 	rq->stats->recover++;
+	if (rq->channel)
+		mlx5e_trigger_napi_icosq(rq->channel);
+	else
+		mlx5e_trigger_napi_sched(rq->cq.napi);
 	return 0;
 out:
 	clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state);

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

@@ -715,7 +715,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 				struct mlx5_flow_attr *attr,
 				struct flow_rule *flow_rule,
 				struct mlx5e_mod_hdr_handle **mh,
-				u8 zone_restore_id, bool nat)
+				u8 zone_restore_id, bool nat_table, bool has_nat)
 {
 	DECLARE_MOD_HDR_ACTS_ACTIONS(actions_arr, MLX5_CT_MIN_MOD_ACTS);
 	DECLARE_MOD_HDR_ACTS(mod_acts, actions_arr);
@@ -731,11 +731,12 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 				     &attr->ct_attr.ct_labels_id);
 	if (err)
 		return -EOPNOTSUPP;
-	if (nat) {
-		err = mlx5_tc_ct_entry_create_nat(ct_priv, flow_rule,
-						  &mod_acts);
-		if (err)
-			goto err_mapping;
+	if (nat_table) {
+		if (has_nat) {
+			err = mlx5_tc_ct_entry_create_nat(ct_priv, flow_rule, &mod_acts);
+			if (err)
+				goto err_mapping;
+		}
 
 		ct_state |= MLX5_CT_STATE_NAT_BIT;
 	}
@@ -750,7 +751,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv,
 	if (err)
 		goto err_mapping;
 
-	if (nat) {
+	if (nat_table && has_nat) {
 		attr->modify_hdr = mlx5_modify_header_alloc(ct_priv->dev, ct_priv->ns_type,
 							    mod_acts.num_actions,
 							    mod_acts.actions);
@@ -818,7 +819,9 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv,
 
 	err = mlx5_tc_ct_entry_create_mod_hdr(ct_priv, attr, flow_rule,
 					      &zone_rule->mh,
-					      zone_restore_id, nat);
+					      zone_restore_id,
+					      nat,
+					      mlx5_tc_ct_entry_has_nat(entry));
 	if (err) {
 		ct_dbg("Failed to create ct entry mod hdr");
 		goto err_mod_hdr;

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

@@ -179,6 +179,7 @@ static void mlx5e_activate_trap(struct mlx5e_trap *trap)
 {
 	napi_enable(&trap->napi);
 	mlx5e_activate_rq(&trap->rq);
+	mlx5e_trigger_napi_sched(&trap->napi);
 }
 
 void mlx5e_deactivate_trap(struct mlx5e_priv *priv)

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c

@@ -117,6 +117,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 		goto err_remove_pool;
 
 	mlx5e_activate_xsk(c);
+	mlx5e_trigger_napi_icosq(c);
 
 	/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
 	 * any Fill Ring entries at the setup stage.

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -64,6 +64,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->clock        = &mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
+	rq->channel      = c;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->xdpsq        = &c->rq_xdpsq;
@@ -179,10 +180,6 @@ void mlx5e_activate_xsk(struct mlx5e_channel *c)
 	mlx5e_reporter_icosq_resume_recovery(c);
 
 	/* TX queue is created active. */
-
-	spin_lock_bh(&c->async_icosq_lock);
-	mlx5e_trigger_irq(&c->async_icosq);
-	spin_unlock_bh(&c->async_icosq_lock);
 }
 
 void mlx5e_deactivate_xsk(struct mlx5e_channel *c)

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

@@ -475,6 +475,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->clock        = &mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
+	rq->channel      = c;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->xdpsq        = &c->rq_xdpsq;
@@ -1066,13 +1067,6 @@ int mlx5e_open_rq(struct mlx5e_params *params, struct mlx5e_rq_param *param,
 void mlx5e_activate_rq(struct mlx5e_rq *rq)
 {
 	set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state);
-	if (rq->icosq) {
-		mlx5e_trigger_irq(rq->icosq);
-	} else {
-		local_bh_disable();
-		napi_schedule(rq->cq.napi);
-		local_bh_enable();
-	}
 }
 
 void mlx5e_deactivate_rq(struct mlx5e_rq *rq)
@@ -2227,6 +2221,20 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu)
 	return 0;
 }
 
+void mlx5e_trigger_napi_icosq(struct mlx5e_channel *c)
+{
+	spin_lock_bh(&c->async_icosq_lock);
+	mlx5e_trigger_irq(&c->async_icosq);
+	spin_unlock_bh(&c->async_icosq_lock);
+}
+
+void mlx5e_trigger_napi_sched(struct napi_struct *napi)
+{
+	local_bh_disable();
+	napi_schedule(napi);
+	local_bh_enable();
+}
+
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
@@ -2308,6 +2316,8 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 
 	if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
 		mlx5e_activate_xsk(c);
+
+	mlx5e_trigger_napi_icosq(c);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -4559,6 +4569,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 
 unlock:
 	mutex_unlock(&priv->state_lock);
+
+	/* Need to fix some features. */
+	if (!err)
+		netdev_update_features(netdev);
+
 	return err;
 }
 

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

@@ -4714,6 +4714,33 @@ static int mlx5e_tc_nic_get_ft_size(struct mlx5_core_dev *dev)
 	return tc_tbl_size;
 }
 
+static int mlx5e_tc_nic_create_miss_table(struct mlx5e_priv *priv)
+{
+	struct mlx5_flow_table **ft = &priv->fs.tc.miss_t;
+	struct mlx5_flow_table_attr ft_attr = {};
+	struct mlx5_flow_namespace *ns;
+	int err = 0;
+
+	ft_attr.max_fte = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft_attr.level = MLX5E_TC_MISS_LEVEL;
+	ft_attr.prio = 0;
+	ns = mlx5_get_flow_namespace(priv->mdev, MLX5_FLOW_NAMESPACE_KERNEL);
+
+	*ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);
+	if (IS_ERR(*ft)) {
+		err = PTR_ERR(*ft);
+		netdev_err(priv->netdev, "failed to create tc nic miss table err=%d\n", err);
+	}
+
+	return err;
+}
+
+static void mlx5e_tc_nic_destroy_miss_table(struct mlx5e_priv *priv)
+{
+	mlx5_destroy_flow_table(priv->fs.tc.miss_t);
+}
+
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tc_table *tc = &priv->fs.tc;
@@ -4746,19 +4773,23 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	}
 	tc->mapping = chains_mapping;
 
+	err = mlx5e_tc_nic_create_miss_table(priv);
+	if (err)
+		goto err_chains;
+
 	if (MLX5_CAP_FLOWTABLE_NIC_RX(priv->mdev, ignore_flow_level))
 		attr.flags = MLX5_CHAINS_AND_PRIOS_SUPPORTED |
 			MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
 	attr.ns = MLX5_FLOW_NAMESPACE_KERNEL;
 	attr.max_ft_sz = mlx5e_tc_nic_get_ft_size(dev);
 	attr.max_grp_num = MLX5E_TC_TABLE_NUM_GROUPS;
-	attr.default_ft = mlx5e_vlan_get_flowtable(priv->fs.vlan);
+	attr.default_ft = priv->fs.tc.miss_t;
 	attr.mapping = chains_mapping;
 
 	tc->chains = mlx5_chains_create(dev, &attr);
 	if (IS_ERR(tc->chains)) {
 		err = PTR_ERR(tc->chains);
-		goto err_chains;
+		goto err_miss;
 	}
 
 	tc->post_act = mlx5e_tc_post_act_init(priv, tc->chains, MLX5_FLOW_NAMESPACE_KERNEL);
@@ -4781,6 +4812,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	mlx5_tc_ct_clean(tc->ct);
 	mlx5e_tc_post_act_destroy(tc->post_act);
 	mlx5_chains_destroy(tc->chains);
+err_miss:
+	mlx5e_tc_nic_destroy_miss_table(priv);
 err_chains:
 	mapping_destroy(chains_mapping);
 err_mapping:
@@ -4821,6 +4854,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	mlx5e_tc_post_act_destroy(tc->post_act);
 	mapping_destroy(tc->mapping);
 	mlx5_chains_destroy(tc->chains);
+	mlx5e_tc_nic_destroy_miss_table(priv);
 }
 
 int mlx5e_tc_ht_init(struct rhashtable *tc_ht)

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

@@ -114,7 +114,7 @@
 #define KERNEL_MIN_LEVEL (KERNEL_NIC_PRIO_NUM_LEVELS + 1)
 
 #define KERNEL_NIC_TC_NUM_PRIOS  1
-#define KERNEL_NIC_TC_NUM_LEVELS 2
+#define KERNEL_NIC_TC_NUM_LEVELS 3
 
 #define ANCHOR_NUM_LEVELS 1
 #define ANCHOR_NUM_PRIOS 1

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c

@@ -44,11 +44,10 @@ static int set_miss_action(struct mlx5_flow_root_namespace *ns,
 	err = mlx5dr_table_set_miss_action(ft->fs_dr_table.dr_table, action);
 	if (err && action) {
 		err = mlx5dr_action_destroy(action);
-		if (err) {
-			action = NULL;
-			mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n",
-				      err);
-		}
+		if (err)
+			mlx5_core_err(ns->dev,
+				      "Failed to destroy action (%d)\n", err);
+		action = NULL;
 	}
 	ft->fs_dr_table.miss_action = action;
 	if (old_miss_action) {

include/linux/mlx5/mlx5_ifc.h

@@ -5176,12 +5176,11 @@ struct mlx5_ifc_query_qp_out_bits {
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x20];
-	u8         ece[0x20];
+	u8         reserved_at_40[0x40];
 
 	u8         opt_param_mask[0x20];
 
-	u8         reserved_at_a0[0x20];
+	u8         ece[0x20];
 
 	struct mlx5_ifc_qpc_bits qpc;