Merge tag 'mlx5-fixes-2023-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2023-10-12

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2023-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: Fix VF representors reporting zero counters to "ip -s" command
  net/mlx5e: Don't offload internal port if filter device is out device
  net/mlx5e: Take RTNL lock before triggering netdev notifiers
  net/mlx5e: XDP, Fix XDP_REDIRECT mpwqe page fragment leaks on shutdown
  net/mlx5e: RX, Fix page_pool allocation failure recovery for legacy rq
  net/mlx5e: RX, Fix page_pool allocation failure recovery for striding rq
  net/mlx5: Handle fw tracer change ownership event based on MTRC
  net/mlx5: Bridge, fix peer entry ageing in LAG mode
  net/mlx5: E-switch, register event handler before arming the event
  net/mlx5: Perform DMA operations in the right locations
====================

Link: https://lore.kernel.org/r/20231012195127.129585-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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

@@ -2186,52 +2186,23 @@ static u16 cmdif_rev(struct mlx5_core_dev *dev)
 
 int mlx5_cmd_init(struct mlx5_core_dev *dev)
 {
-	int size = sizeof(struct mlx5_cmd_prot_block);
-	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
-	u32 cmd_l;
-	int err;
-
-	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
-	if (!cmd->pool)
-		return -ENOMEM;
 
-	err = alloc_cmd_page(dev, cmd);
-	if (err)
-		goto err_free_pool;
-
-	cmd_l = (u32)(cmd->dma);
-	if (cmd_l & 0xfff) {
-		mlx5_core_err(dev, "invalid command queue address\n");
-		err = -ENOMEM;
-		goto err_cmd_page;
-	}
 	cmd->checksum_disabled = 1;
 
 	spin_lock_init(&cmd->alloc_lock);
 	spin_lock_init(&cmd->token_lock);
 
-	create_msg_cache(dev);
-
 	set_wqname(dev);
 	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
 	if (!cmd->wq) {
 		mlx5_core_err(dev, "failed to create command workqueue\n");
-		err = -ENOMEM;
-		goto err_cache;
+		return -ENOMEM;
 	}
 
 	mlx5_cmdif_debugfs_init(dev);
 
 	return 0;
-
-err_cache:
-	destroy_msg_cache(dev);
-err_cmd_page:
-	free_cmd_page(dev, cmd);
-err_free_pool:
-	dma_pool_destroy(cmd->pool);
-	return err;
 }
 
 void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
@@ -2240,15 +2211,15 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
 
 	mlx5_cmdif_debugfs_cleanup(dev);
 	destroy_workqueue(cmd->wq);
-	destroy_msg_cache(dev);
-	free_cmd_page(dev, cmd);
-	dma_pool_destroy(cmd->pool);
 }
 
 int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 {
+	int size = sizeof(struct mlx5_cmd_prot_block);
+	int align = roundup_pow_of_two(size);
 	struct mlx5_cmd *cmd = &dev->cmd;
 	u32 cmd_h, cmd_l;
+	int err;
 
 	memset(&cmd->vars, 0, sizeof(cmd->vars));
 	cmd->vars.cmdif_rev = cmdif_rev(dev);
@@ -2281,10 +2252,21 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
 
+	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
+	if (!cmd->pool)
+		return -ENOMEM;
+
+	err = alloc_cmd_page(dev, cmd);
+	if (err)
+		goto err_free_pool;
+
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);
-	if (WARN_ON(cmd_l & 0xfff))
-		return -EINVAL;
+	if (cmd_l & 0xfff) {
+		mlx5_core_err(dev, "invalid command queue address\n");
+		err = -ENOMEM;
+		goto err_cmd_page;
+	}
 
 	iowrite32be(cmd_h, &dev->iseg->cmdq_addr_h);
 	iowrite32be(cmd_l, &dev->iseg->cmdq_addr_l_sz);
@@ -2297,17 +2279,27 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	cmd->mode = CMD_MODE_POLLING;
 	cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
 
+	create_msg_cache(dev);
 	create_debugfs_files(dev);
 
 	return 0;
+
+err_cmd_page:
+	free_cmd_page(dev, cmd);
+err_free_pool:
+	dma_pool_destroy(cmd->pool);
+	return err;
 }
 
 void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 
-	clean_debug_files(dev);
 	flush_workqueue(cmd->wq);
+	clean_debug_files(dev);
+	destroy_msg_cache(dev);
+	free_cmd_page(dev, cmd);
+	dma_pool_destroy(cmd->pool);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c

@@ -848,7 +848,7 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
 	if (tracer->owner) {
-		tracer->owner = false;
+		mlx5_fw_tracer_ownership_acquire(tracer);
 		return;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c

@@ -467,6 +467,17 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 		/* only handle the event on peers */
 		if (mlx5_esw_bridge_is_local(dev, rep, esw))
 			break;
+
+		fdb_info = container_of(info,
+					struct switchdev_notifier_fdb_info,
+					info);
+		/* Mark for deletion to prevent the update wq task from
+		 * spuriously refreshing the entry which would mark it again as
+		 * offloaded in SW bridge. After this fallthrough to regular
+		 * async delete code.
+		 */
+		mlx5_esw_bridge_fdb_mark_deleted(dev, vport_num, esw_owner_vhca_id, br_offloads,
+						 fdb_info);
 		fallthrough;
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:

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

@@ -24,7 +24,8 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
 
 	route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex);
 
-	if (!route_dev || !netif_is_ovs_master(route_dev))
+	if (!route_dev || !netif_is_ovs_master(route_dev) ||
+	    attr->parse_attr->filter_dev == e->out_dev)
 		goto out;
 
 	err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex,

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

@@ -874,11 +874,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	}
 
 out:
-	if (flags & XDP_XMIT_FLUSH) {
-		if (sq->mpwqe.wqe)
-			mlx5e_xdp_mpwqe_complete(sq);
+	if (sq->mpwqe.wqe)
+		mlx5e_xdp_mpwqe_complete(sq);
+
+	if (flags & XDP_XMIT_FLUSH)
 		mlx5e_xmit_xdp_doorbell(sq);
-	}
 
 	return nxmit;
 }

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

@@ -701,7 +701,7 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 	/* update HW stats in background for next time */
 	mlx5e_queue_update_stats(priv);
-	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
+	mlx5e_stats_copy_rep_stats(stats, &priv->stats.rep_stats);
 }
 
 static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu)
@@ -769,6 +769,7 @@ static int mlx5e_rep_max_nch_limit(struct mlx5_core_dev *mdev)
 
 static void mlx5e_build_rep_params(struct net_device *netdev)
 {
+	const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
@@ -794,8 +795,15 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
+	/* If netdev is already registered (e.g. move from nic profile to uplink,
+	 * RTNL lock must be held before triggering netdev notifiers.
+	 */
+	if (take_rtnl)
+		rtnl_lock();
 	/* update XDP supported features */
 	mlx5e_set_xdp_feature(netdev);
+	if (take_rtnl)
+		rtnl_unlock();
 
 	/* CQ moderation params */
 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);

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

@@ -457,26 +457,41 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
 static int mlx5e_refill_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
 {
 	int remaining = wqe_bulk;
-	int i = 0;
+	int total_alloc = 0;
+	int refill_alloc;
+	int refill;
 
 	/* The WQE bulk is split into smaller bulks that are sized
 	 * according to the page pool cache refill size to avoid overflowing
 	 * the page pool cache due to too many page releases at once.
 	 */
 	do {
-		int refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
-		int alloc_count;
+		refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
 
-		mlx5e_free_rx_wqes(rq, ix + i, refill);
-		alloc_count = mlx5e_alloc_rx_wqes(rq, ix + i, refill);
-		i += alloc_count;
-		if (unlikely(alloc_count != refill))
-			break;
+		mlx5e_free_rx_wqes(rq, ix + total_alloc, refill);
+		refill_alloc = mlx5e_alloc_rx_wqes(rq, ix + total_alloc, refill);
+		if (unlikely(refill_alloc != refill))
+			goto err_free;
 
+		total_alloc += refill_alloc;
 		remaining -= refill;
 	} while (remaining);
 
-	return i;
+	return total_alloc;
+
+err_free:
+	mlx5e_free_rx_wqes(rq, ix, total_alloc + refill_alloc);
+
+	for (int i = 0; i < total_alloc + refill; i++) {
+		int j = mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, ix + i);
+		struct mlx5e_wqe_frag_info *frag;
+
+		frag = get_frag(rq, j);
+		for (int k = 0; k < rq->wqe.info.num_frags; k++, frag++)
+			frag->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+	}
+
+	return 0;
 }
 
 static void
@@ -816,6 +831,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		mlx5e_page_release_fragmented(rq, frag_page);
 	}
 
+	bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
+
 err:
 	rq->stats->buff_alloc_err++;
 

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

@@ -484,11 +484,20 @@ struct mlx5e_stats {
 	struct mlx5e_vnic_env_stats vnic;
 	struct mlx5e_vport_stats vport;
 	struct mlx5e_pport_stats pport;
-	struct rtnl_link_stats64 vf_vport;
 	struct mlx5e_pcie_stats pcie;
 	struct mlx5e_rep_stats rep_stats;
 };
 
+static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport,
+					      struct mlx5e_rep_stats *rep_stats)
+{
+	memset(vf_vport, 0, sizeof(*vf_vport));
+	vf_vport->rx_packets = rep_stats->vport_rx_packets;
+	vf_vport->tx_packets = rep_stats->vport_tx_packets;
+	vf_vport->rx_bytes = rep_stats->vport_rx_bytes;
+	vf_vport->tx_bytes = rep_stats->vport_tx_bytes;
+}
+
 extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[];
 unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv);
 

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

@@ -4972,7 +4972,8 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv,
 			if (err)
 				return err;
 
-			rpriv->prev_vf_vport_stats = priv->stats.vf_vport;
+			mlx5e_stats_copy_rep_stats(&rpriv->prev_vf_vport_stats,
+						   &priv->stats.rep_stats);
 			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall");
@@ -5012,7 +5013,7 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
 	u64 dbytes;
 	u64 dpkts;
 
-	cur_stats = priv->stats.vf_vport;
+	mlx5e_stats_copy_rep_stats(&cur_stats, &priv->stats.rep_stats);
 	dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
 	dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
 	rpriv->prev_vf_vport_stats = cur_stats;

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

@@ -1748,6 +1748,28 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16
 	entry->lastuse = jiffies;
 }
 
+void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_esw_bridge *bridge;
+
+	bridge = mlx5_esw_bridge_from_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!bridge)
+		return;
+
+	entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid);
+	if (!entry) {
+		esw_debug(br_offloads->esw->dev,
+			  "FDB mark deleted entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+			  fdb_info->addr, fdb_info->vid, vport_num);
+		return;
+	}
+
+	entry->flags |= MLX5_ESW_BRIDGE_FLAG_DELETED;
+}
+
 void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info)
@@ -1810,7 +1832,8 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 			unsigned long lastuse =
 				(unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter);
 
-			if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
+			if (entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER |
+					    MLX5_ESW_BRIDGE_FLAG_DELETED))
 				continue;
 
 			if (time_after(lastuse, entry->lastuse))

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h

@@ -62,6 +62,9 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu
 void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 				     struct mlx5_esw_bridge_offloads *br_offloads,
 				     struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct switchdev_notifier_fdb_info *fdb_info);
 void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
 				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);

drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h

@@ -133,6 +133,7 @@ struct mlx5_esw_bridge_mdb_key {
 enum {
 	MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
 	MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1),
+	MLX5_ESW_BRIDGE_FLAG_DELETED = BIT(2),
 };
 
 enum {

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

@@ -1038,11 +1038,8 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 	return ERR_PTR(err);
 }
 
-static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw)
 {
-	MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
-	mlx5_eq_notifier_register(esw->dev, &esw->nb);
-
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
 		MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
 			     ESW_FUNCTIONS_CHANGED);
@@ -1050,13 +1047,11 @@ static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
 	}
 }
 
-static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw)
 {
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
 		mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
 
-	mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
-
 	flush_workqueue(esw->work_queue);
 }
 
@@ -1483,6 +1478,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 
 	mlx5_eswitch_update_num_of_vfs(esw, num_vfs);
 
+	MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+	mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
 	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_legacy_enable(esw);
 	} else {
@@ -1495,7 +1493,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
 
 	esw->fdb_table.flags |= MLX5_ESW_FDB_CREATED;
 
-	mlx5_eswitch_event_handlers_register(esw);
+	mlx5_eswitch_event_handler_register(esw);
 
 	esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
@@ -1622,7 +1620,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw)
 	 */
 	mlx5_esw_mode_change_notify(esw, MLX5_ESWITCH_LEGACY);
 
-	mlx5_eswitch_event_handlers_unregister(esw);
+	mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+	mlx5_eswitch_event_handler_unregister(esw);
 
 	esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
 		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",