Merge tag 'mlx5-fixes-2020-06-11' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2020-06-11

This series introduces some fixes to mlx5 driver.
For more information please see tag log below.

Please pull and let me know if there is any problem.

For -stable v5.2
  ('net/mlx5: drain health workqueue in case of driver load error')

For -stable v5.3
  ('net/mlx5e: Fix repeated XSK usage on one channel')
  ('net/mlx5: Fix fatal error handling during device load')

For -stable v5.5
 ('net/mlx5: Disable reload while removing the device')

For -stable v5.7
  ('net/mlx5e: CT: Fix ipv6 nat header rewrite actions')
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

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

@@ -283,7 +283,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
-	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -293,7 +292,6 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);

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

@@ -328,21 +328,21 @@ mlx5_tc_ct_parse_mangle_to_mod_act(struct flow_action_entry *act,
 
 	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
 		MLX5_SET(set_action_in, modact, length, 0);
-		if (offset == offsetof(struct ipv6hdr, saddr))
+		if (offset == offsetof(struct ipv6hdr, saddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, saddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, saddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, saddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, saddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96;
-		else if (offset == offsetof(struct ipv6hdr, daddr))
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
-			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
 		else if (offset == offsetof(struct ipv6hdr, daddr) + 8)
+			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32;
+		else if (offset == offsetof(struct ipv6hdr, daddr) + 4)
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64;
-		else if (offset == offsetof(struct ipv6hdr, daddr) + 12)
+		else if (offset == offsetof(struct ipv6hdr, daddr))
 			field = MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96;
 		else
 			return -EOPNOTSUPP;

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

@@ -152,6 +152,10 @@ void mlx5e_close_xsk(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->xskicosq.cq);
 	mlx5e_close_xdpsq(&c->xsksq);
 	mlx5e_close_cq(&c->xsksq.cq);
+
+	memset(&c->xskrq, 0, sizeof(c->xskrq));
+	memset(&c->xsksq, 0, sizeof(c->xsksq));
+	memset(&c->xskicosq, 0, sizeof(c->xskicosq));
 }
 
 void mlx5e_activate_xsk(struct mlx5e_channel *c)

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

@@ -1173,7 +1173,8 @@ int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
-	bool hash_changed = false;
+	bool refresh_tirs = false;
+	bool refresh_rqt = false;
 	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
@@ -1189,36 +1190,38 @@ int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != rss->hfunc) {
 		rss->hfunc = hfunc;
-		hash_changed = true;
+		refresh_rqt = true;
+		refresh_tirs = true;
 	}
 
 	if (indir) {
 		memcpy(rss->indirection_rqt, indir,
 		       sizeof(rss->indirection_rqt));
-
-		if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-			u32 rqtn = priv->indir_rqt.rqtn;
-			struct mlx5e_redirect_rqt_param rrp = {
-				.is_rss = true,
-				{
-					.rss = {
-						.hfunc = rss->hfunc,
-						.channels  = &priv->channels,
-					},
-				},
-			};
-
-			mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
-		}
+		refresh_rqt = true;
 	}
 
 	if (key) {
 		memcpy(rss->toeplitz_hash_key, key,
 		       sizeof(rss->toeplitz_hash_key));
-		hash_changed = hash_changed || rss->hfunc == ETH_RSS_HASH_TOP;
+		refresh_tirs = refresh_tirs || rss->hfunc == ETH_RSS_HASH_TOP;
+	}
+
+	if (refresh_rqt && test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		struct mlx5e_redirect_rqt_param rrp = {
+			.is_rss = true,
+			{
+				.rss = {
+					.hfunc = rss->hfunc,
+					.channels  = &priv->channels,
+				},
+			},
+		};
+		u32 rqtn = priv->indir_rqt.rqtn;
+
+		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, rrp);
 	}
 
-	if (hash_changed)
+	if (refresh_tirs)
 		mlx5e_modify_tirs_hash(priv, in);
 
 	mutex_unlock(&priv->state_lock);

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c

@@ -162,10 +162,12 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 
 	if (MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) {
 		counter = mlx5_fc_create(esw->dev, false);
-		if (IS_ERR(counter))
+		if (IS_ERR(counter)) {
 			esw_warn(esw->dev,
 				 "vport[%d] configure ingress drop rule counter failed\n",
 				 vport->vport);
+			counter = NULL;
+		}
 		vport->ingress.legacy.drop_counter = counter;
 	}
 
@@ -272,7 +274,7 @@ void esw_acl_ingress_lgcy_cleanup(struct mlx5_eswitch *esw,
 	esw_acl_ingress_table_destroy(vport);
 
 clean_drop_counter:
-	if (!IS_ERR_OR_NULL(vport->ingress.legacy.drop_counter)) {
+	if (vport->ingress.legacy.drop_counter) {
 		mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
 		vport->ingress.legacy.drop_counter = NULL;
 	}

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

@@ -192,15 +192,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 {
+	bool err_detected = false;
+
+	/* Mark the device as fatal in order to abort FW commands */
+	if ((check_fatal_sensors(dev) || force) &&
+	    dev->state == MLX5_DEVICE_STATE_UP) {
+		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
+		err_detected = true;
+	}
 	mutex_lock(&dev->intf_state_mutex);
-	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
-		goto unlock;
+	if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
+		goto unlock;/* a previous error is still being handled */
 	if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		goto unlock;
 	}
 
-	if (check_fatal_sensors(dev) || force) {
+	if (check_fatal_sensors(dev) || force) { /* protected state setting */
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
 		mlx5_cmd_flush(dev);
 	}

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

@@ -785,6 +785,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 
 static void mlx5_pci_close(struct mlx5_core_dev *dev)
 {
+	/* health work might still be active, and it needs pci bar in
+	 * order to know the NIC state. Therefore, drain the health WQ
+	 * before removing the pci bars
+	 */
+	mlx5_drain_health_wq(dev);
 	iounmap(dev->iseg);
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
@@ -1194,23 +1199,22 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 	if (err)
 		goto err_load;
 
+	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+
 	if (boot) {
 		err = mlx5_devlink_register(priv_to_devlink(dev), dev->device);
 		if (err)
 			goto err_devlink_reg;
-	}
-
-	if (mlx5_device_registered(dev))
-		mlx5_attach_device(dev);
-	else
 		mlx5_register_device(dev);
-
-	set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
+	} else {
+		mlx5_attach_device(dev);
+	}
 
 	mutex_unlock(&dev->intf_state_mutex);
 	return 0;
 
 err_devlink_reg:
+	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 	mlx5_unload(dev);
 err_load:
 	if (boot)
@@ -1226,10 +1230,15 @@ int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 
 void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
-	if (cleanup)
+	mutex_lock(&dev->intf_state_mutex);
+
+	if (cleanup) {
 		mlx5_unregister_device(dev);
+		mlx5_devlink_unregister(priv_to_devlink(dev));
+	} else {
+		mlx5_detach_device(dev);
+	}
 
-	mutex_lock(&dev->intf_state_mutex);
 	if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		mlx5_core_warn(dev, "%s: interface is down, NOP\n",
 			       __func__);
@@ -1240,9 +1249,6 @@ void mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 
 	clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state);
 
-	if (mlx5_device_registered(dev))
-		mlx5_detach_device(dev);
-
 	mlx5_unload(dev);
 
 	if (cleanup)
@@ -1275,11 +1281,6 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 
 	priv->dbg_root = debugfs_create_dir(dev_name(dev->device),
 					    mlx5_debugfs_root);
-	if (!priv->dbg_root) {
-		dev_err(dev->device, "mlx5_core: error, Cannot create debugfs dir, aborting\n");
-		goto err_dbg_root;
-	}
-
 	err = mlx5_health_init(dev);
 	if (err)
 		goto err_health_init;
@@ -1294,7 +1295,6 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 	mlx5_health_cleanup(dev);
 err_health_init:
 	debugfs_remove(dev->priv.dbg_root);
-err_dbg_root:
 	mutex_destroy(&priv->pgdir_mutex);
 	mutex_destroy(&priv->alloc_mutex);
 	mutex_destroy(&priv->bfregs.wc_head.lock);
@@ -1362,6 +1362,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
 
 	pci_save_state(pdev);
+	devlink_reload_enable(devlink);
 	return 0;
 
 err_load_one:
@@ -1379,9 +1380,8 @@ static void remove_one(struct pci_dev *pdev)
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 	struct devlink *devlink = priv_to_devlink(dev);
 
+	devlink_reload_disable(devlink);
 	mlx5_crdump_disable(dev);
-	mlx5_devlink_unregister(devlink);
-
 	mlx5_drain_health_wq(dev);
 	mlx5_unload_one(dev, true);
 	mlx5_pci_close(dev);

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

@@ -179,7 +179,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
 	MLX5_SET(create_qp_in, in, opcode, MLX5_CMD_OP_CREATE_QP);
 	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
 	dr_qp->qpn = MLX5_GET(create_qp_out, out, qpn);
-	kfree(in);
+	kvfree(in);
 	if (err)
 		goto err_in;
 	dr_qp->uar = attr->uar;