Merge tag 'mlx5-fixes-2022-08-22' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2022-08-22

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2022-08-22' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5: Unlock on error in mlx5_sriov_enable()
  net/mlx5e: Fix use after free in mlx5e_fs_init()
  net/mlx5e: kTLS, Use _safe() iterator in mlx5e_tls_priv_tx_list_cleanup()
  net/mlx5: unlock on error path in esw_vfs_changed_event_handler()
  net/mlx5e: Fix wrong tc flag used when set hw-tc-offload off
  net/mlx5e: TC, Add missing policer validation
  net/mlx5e: Fix wrong application of the LRO state
  net/mlx5: Avoid false positive lockdep warning by adding lock_class_key
  net/mlx5: Fix cmd error logging for manage pages cmd
  net/mlx5: Disable irq when locking lag_lock
  net/mlx5: Eswitch, Fix forwarding decision to uplink
  net/mlx5: LAG, fix logic over MLX5_LAG_FLAG_NDEVS_READY
  net/mlx5e: Properly disable vlan strip on non-UL reps
====================

Link: https://lore.kernel.org/r/20220822195917.216025-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 65 insertions, 42 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
index 37522352e4b2..c8e5ca65bb6e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c
@@ -79,6 +79,10 @@ tc_act_police_offload(struct mlx5e_priv *priv,
 	struct mlx5e_flow_meter_handle *meter;
 	int err = 0;
 
+	err = mlx5e_policer_validate(&fl_act->action, act, fl_act->extack);
+	if (err)
+		return err;
+
 	err = fill_meter_params_from_act(act, &params);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 0aef69527226..3a1f76eac542 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -246,7 +246,7 @@ static void mlx5e_tls_priv_tx_cleanup(struct mlx5e_ktls_offload_context_tx *priv
 static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
 					   struct list_head *list, int size)
 {
-	struct mlx5e_ktls_offload_context_tx *obj;
+	struct mlx5e_ktls_offload_context_tx *obj, *n;
 	struct mlx5e_async_ctx *bulk_async;
 	int i;
 
@@ -255,7 +255,7 @@ static void mlx5e_tls_priv_tx_list_cleanup(struct mlx5_core_dev *mdev,
 		return;
 
 	i = 0;
-	list_for_each_entry(obj, list, list_node) {
+	list_for_each_entry_safe(obj, n, list, list_node) {
 		mlx5e_tls_priv_tx_cleanup(obj, &bulk_async[i]);
 		i++;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index e2a9b9be5c1f..e0ce5a233d0b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1395,10 +1395,11 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 	}
 
 	return fs;
-err_free_fs:
-	kvfree(fs);
+
 err_free_vlan:
 	mlx5e_fs_vlan_free(fs);
+err_free_fs:
+	kvfree(fs);
 err:
 	return NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d858667736a3..02eb2f0fa2ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3682,7 +3682,9 @@ static int set_feature_hw_tc(struct net_device *netdev, bool enable)
 	int err = 0;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-	if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) {
+	int tc_flag = mlx5e_is_uplink_rep(priv) ? MLX5_TC_FLAG(ESW_OFFLOAD) :
+						  MLX5_TC_FLAG(NIC_OFFLOAD);
+	if (!enable && mlx5e_tc_num_filters(priv, tc_flag)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -4769,14 +4771,6 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
-	/* HW LRO */
-	if (MLX5_CAP_ETH(mdev, lro_cap) &&
-	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		/* No XSK params: checking the availability of striding RQ in general. */
-		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->packet_merge.type = slow_pci_heuristic(mdev) ?
-				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
-	}
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0c66774a1720..759f7d3c2cfd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -662,6 +662,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	params->mqprio.num_tc       = 1;
 	params->tunneled_offload_en = false;
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		params->vlan_strip_disable = true;
 
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ed73132129aa..a9f4c652f859 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -427,7 +427,8 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
 		dest[dest_idx].vport.vhca_id =
 			MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
 		dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
-		if (mlx5_lag_mpesw_is_activated(esw->dev))
+		if (dest[dest_idx].vport.num == MLX5_VPORT_UPLINK &&
+		    mlx5_lag_mpesw_is_activated(esw->dev))
 			dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_UPLINK;
 	}
 	if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
@@ -3115,8 +3116,10 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out)
 
 		err = mlx5_eswitch_load_vf_vports(esw, new_num_vfs,
 						  MLX5_VPORT_UC_ADDR_CHANGE);
-		if (err)
+		if (err) {
+			devl_unlock(devlink);
 			return;
+		}
 	}
 	esw->esw_funcs.num_vfs = new_num_vfs;
 	devl_unlock(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 0f34e3c80d1f..065102278cb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1067,30 +1067,32 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
 				 struct net_device *netdev)
 {
 	unsigned int fn = mlx5_get_dev_index(dev);
+	unsigned long flags;
 
 	if (fn >= ldev->ports)
 		return;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev->pf[fn].netdev = netdev;
 	ldev->tracker.netdev_state[fn].link_up = 0;
 	ldev->tracker.netdev_state[fn].tx_enabled = 0;
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 }
 
 static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
 				    struct net_device *netdev)
 {
+	unsigned long flags;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	for (i = 0; i < ldev->ports; i++) {
 		if (ldev->pf[i].netdev == netdev) {
 			ldev->pf[i].netdev = NULL;
 			break;
 		}
 	}
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 }
 
 static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
@@ -1234,7 +1236,7 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 	mlx5_ldev_add_netdev(ldev, dev, netdev);
 
 	for (i = 0; i < ldev->ports; i++)
-		if (!ldev->pf[i].dev)
+		if (!ldev->pf[i].netdev)
 			break;
 
 	if (i >= ldev->ports)
@@ -1246,12 +1248,13 @@ void mlx5_lag_add_netdev(struct mlx5_core_dev *dev,
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_roce(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1260,12 +1263,13 @@ EXPORT_SYMBOL(mlx5_lag_is_roce);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_active(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1274,13 +1278,14 @@ EXPORT_SYMBOL(mlx5_lag_is_active);
 bool mlx5_lag_is_master(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res = ldev && __mlx5_lag_is_active(ldev) &&
 		dev == ldev->pf[MLX5_LAG_P1].dev;
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1289,12 +1294,13 @@ EXPORT_SYMBOL(mlx5_lag_is_master);
 bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res  = ldev && __mlx5_lag_is_sriov(ldev);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1303,13 +1309,14 @@ EXPORT_SYMBOL(mlx5_lag_is_sriov);
 bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	bool res;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	res = ldev && __mlx5_lag_is_sriov(ldev) &&
 	      test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags);
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return res;
 }
@@ -1352,9 +1359,10 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 {
 	struct net_device *ndev = NULL;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
@@ -1373,7 +1381,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 		dev_hold(ndev);
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	return ndev;
 }
@@ -1383,10 +1391,11 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 			   struct net_device *slave)
 {
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	u8 port = 0;
 	int i;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
@@ -1401,7 +1410,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 	port = ldev->v2p_map[port * ldev->buckets];
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 	return port;
 }
 EXPORT_SYMBOL(mlx5_lag_get_slave_port);
@@ -1422,8 +1431,9 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_dev *peer_dev = NULL;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (!ldev)
 		goto unlock;
@@ -1433,7 +1443,7 @@ struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev)
 			   ldev->pf[MLX5_LAG_P1].dev;
 
 unlock:
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 	return peer_dev;
 }
 EXPORT_SYMBOL(mlx5_lag_get_peer_mdev);
@@ -1446,6 +1456,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out);
 	struct mlx5_core_dev **mdev;
 	struct mlx5_lag *ldev;
+	unsigned long flags;
 	int num_ports;
 	int ret, i, j;
 	void *out;
@@ -1462,7 +1473,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	memset(values, 0, sizeof(*values) * num_counters);
 
-	spin_lock(&lag_lock);
+	spin_lock_irqsave(&lag_lock, flags);
 	ldev = mlx5_lag_dev(dev);
 	if (ldev && __mlx5_lag_is_active(ldev)) {
 		num_ports = ldev->ports;
@@ -1472,7 +1483,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 		num_ports = 1;
 		mdev[MLX5_LAG_P1] = dev;
 	}
-	spin_unlock(&lag_lock);
+	spin_unlock_irqrestore(&lag_lock, flags);
 
 	for (i = 0; i < num_ports; ++i) {
 		u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = {};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index bec8d6d0b5f6..c085b031abfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1530,7 +1530,9 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	memcpy(&dev->profile, &profile[profile_idx], sizeof(dev->profile));
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
+	lockdep_register_key(&dev->lock_key);
 	mutex_init(&dev->intf_state_mutex);
+	lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
@@ -1597,6 +1599,7 @@ err_timeout_init:
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 	return err;
 }
 
@@ -1618,6 +1621,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev)
 	mutex_destroy(&priv->bfregs.wc_head.lock);
 	mutex_destroy(&priv->bfregs.reg_head.lock);
 	mutex_destroy(&dev->intf_state_mutex);
+	lockdep_unregister_key(&dev->lock_key);
 }
 
 static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index ec76a8b1acc1..60596357bfc7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -376,8 +376,8 @@ retry:
 			goto out_dropped;
 		}
 	}
+	err = mlx5_cmd_check(dev, err, in, out);
 	if (err) {
-		err = mlx5_cmd_check(dev, err, in, out);
 		mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n",
 			       func_id, npages, err);
 		goto out_dropped;
@@ -524,10 +524,13 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
 		dev->priv.reclaim_pages_discard += npages;
 	}
 	/* if triggered by FW event and failed by FW then ignore */
-	if (event && err == -EREMOTEIO)
+	if (event && err == -EREMOTEIO) {
 		err = 0;
+		goto out_free;
+	}
+
+	err = mlx5_cmd_check(dev, err, in, out);
 	if (err) {
-		err = mlx5_cmd_check(dev, err, in, out);
 		mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err);
 		goto out_free;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index ee2e1b7c1310..c0e6c487c63c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -159,11 +159,11 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 
 	devl_lock(devlink);
 	err = mlx5_device_enable_sriov(dev, num_vfs);
+	devl_unlock(devlink);
 	if (err) {
 		mlx5_core_warn(dev, "mlx5_device_enable_sriov failed : %d\n", err);
 		return err;
 	}
-	devl_unlock(devlink);
 
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 96b16fbe1aa4..7b7ce602c808 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -779,6 +779,7 @@ struct mlx5_core_dev {
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
+	struct lock_class_key	lock_key;
 	unsigned long		intf_state;
 	struct mlx5_priv	priv;
 	struct mlx5_profile	profile;