Merge tag 'mlx5e-fixes-2018-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
Mellanox, mlx5 fixes 2018-09-05

This pull request contains some fixes for mlx5 etherent netdevice and
core driver.

Please pull and let me know if there's any problem.

For -stable v4.9:
('net/mlx5: Fix debugfs cleanup in the device init/remove flow')

For -stable v4.12:
("net/mlx5: E-Switch, Fix memory leak when creating switchdev mode FDB tables")

For -stable v4.13:
("net/mlx5: Fix use-after-free in self-healing flow")

For -stable v4.14:
("net/mlx5: Check for error in mlx5_attach_interface")

For -stable v4.15:
("net/mlx5: Fix not releasing read lock when adding flow rules")

For -stable v4.17:
("net/mlx5: Fix possible deadlock from lockdep when adding fte to fg")

For -stable v4.18:
("net/mlx5: Use u16 for Work Queue buffer fragment size")
====================

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

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

@@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	delayed_event_start(priv);
 
 	dev_ctx->context = intf->add(dev);
-	set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
-	if (intf->attach)
-		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
-
 	if (dev_ctx->context) {
+		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
+		if (intf->attach)
+			set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
+
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
 
@@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
 			goto out;
-		intf->attach(dev, dev_ctx->context);
+		if (intf->attach(dev, dev_ctx->context))
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
 			goto out;
 		dev_ctx->context = intf->add(dev);
+		if (!dev_ctx->context)
+			goto out;
+
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
 
@@ -391,16 +396,17 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
 		}
 }
 
-static u16 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
+static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
 {
-	return (u16)((dev->pdev->bus->number << 8) |
+	return (u32)((pci_domain_nr(dev->pdev->bus) << 16) |
+		     (dev->pdev->bus->number << 8) |
 		     PCI_SLOT(dev->pdev->devfn));
 }
 
 /* Must be called with intf_mutex held */
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 {
-	u16 pci_id = mlx5_gen_pci_id(dev);
+	u32 pci_id = mlx5_gen_pci_id(dev);
 	struct mlx5_core_dev *res = NULL;
 	struct mlx5_core_dev *tmp_dev;
 	struct mlx5_priv *priv;

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

@@ -191,7 +191,7 @@ set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
 {
 	if (psrc_m) {
 		MLX5E_FTE_SET(headers_c, udp_sport, 0xffff);
-		MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v));
+		MLX5E_FTE_SET(headers_v, udp_sport, ntohs(psrc_v));
 	}
 
 	if (pdst_m) {

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

@@ -663,6 +663,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	if (err)
 		goto miss_rule_err;
 
+	kvfree(flow_group_in);
 	return 0;
 
 miss_rule_err:

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

@@ -1578,6 +1578,33 @@ static u64 matched_fgs_get_version(struct list_head *match_head)
 	return version;
 }
 
+static struct fs_fte *
+lookup_fte_locked(struct mlx5_flow_group *g,
+		  u32 *match_value,
+		  bool take_write)
+{
+	struct fs_fte *fte_tmp;
+
+	if (take_write)
+		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+	else
+		nested_down_read_ref_node(&g->node, FS_LOCK_PARENT);
+	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value,
+					 rhash_fte);
+	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+		fte_tmp = NULL;
+		goto out;
+	}
+
+	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+out:
+	if (take_write)
+		up_write_ref_node(&g->node);
+	else
+		up_read_ref_node(&g->node);
+	return fte_tmp;
+}
+
 static struct mlx5_flow_handle *
 try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       struct list_head *match_head,
@@ -1600,10 +1627,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	if (IS_ERR(fte))
 		return  ERR_PTR(-ENOMEM);
 
-	list_for_each_entry(iter, match_head, list) {
-		nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT);
-	}
-
 search_again_locked:
 	version = matched_fgs_get_version(match_head);
 	/* Try to find a fg that already contains a matching fte */
@@ -1611,20 +1634,9 @@ search_again_locked:
 		struct fs_fte *fte_tmp;
 
 		g = iter->g;
-		fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value,
-						 rhash_fte);
-		if (!fte_tmp || !tree_get_node(&fte_tmp->node))
+		fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
+		if (!fte_tmp)
 			continue;
-
-		nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
-		if (!take_write) {
-			list_for_each_entry(iter, match_head, list)
-				up_read_ref_node(&iter->g->node);
-		} else {
-			list_for_each_entry(iter, match_head, list)
-				up_write_ref_node(&iter->g->node);
-		}
-
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte_tmp);
 		up_write_ref_node(&fte_tmp->node);
@@ -1633,19 +1645,6 @@ search_again_locked:
 		return rule;
 	}
 
-	/* No group with matching fte found. Try to add a new fte to any
-	 * matching fg.
-	 */
-
-	if (!take_write) {
-		list_for_each_entry(iter, match_head, list)
-			up_read_ref_node(&iter->g->node);
-		list_for_each_entry(iter, match_head, list)
-			nested_down_write_ref_node(&iter->g->node,
-						   FS_LOCK_PARENT);
-		take_write = true;
-	}
-
 	/* Check the ft version, for case that new flow group
 	 * was added while the fgs weren't locked
 	 */
@@ -1657,27 +1656,30 @@ search_again_locked:
 	/* Check the fgs version, for case the new FTE with the
 	 * same values was added while the fgs weren't locked
 	 */
-	if (version != matched_fgs_get_version(match_head))
+	if (version != matched_fgs_get_version(match_head)) {
+		take_write = true;
 		goto search_again_locked;
+	}
 
 	list_for_each_entry(iter, match_head, list) {
 		g = iter->g;
 
 		if (!g->node.active)
 			continue;
+
+		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+
 		err = insert_fte(g, fte);
 		if (err) {
+			up_write_ref_node(&g->node);
 			if (err == -ENOSPC)
 				continue;
-			list_for_each_entry(iter, match_head, list)
-				up_write_ref_node(&iter->g->node);
 			kmem_cache_free(steering->ftes_cache, fte);
 			return ERR_PTR(err);
 		}
 
 		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-		list_for_each_entry(iter, match_head, list)
-			up_write_ref_node(&iter->g->node);
+		up_write_ref_node(&g->node);
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node);
@@ -1686,8 +1688,6 @@ search_again_locked:
 	}
 	rule = ERR_PTR(-ENOENT);
 out:
-	list_for_each_entry(iter, match_head, list)
-		up_write_ref_node(&iter->g->node);
 	kmem_cache_free(steering->ftes_cache, fte);
 	return rule;
 }
@@ -1726,6 +1726,8 @@ search_again_locked:
 	if (err) {
 		if (take_write)
 			up_write_ref_node(&ft->node);
+		else
+			up_read_ref_node(&ft->node);
 		return ERR_PTR(err);
 	}
 

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

@@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev)
 	add_timer(&health->timer);
 }
 
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev)
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
+	unsigned long flags;
+
+	if (disable_health) {
+		spin_lock_irqsave(&health->wq_lock, flags);
+		set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
+		set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags);
+		spin_unlock_irqrestore(&health->wq_lock, flags);
+	}
 
 	del_timer_sync(&health->timer);
 }

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

@@ -878,8 +878,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
 	priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root);
-	if (!priv->dbg_root)
+	if (!priv->dbg_root) {
+		dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n");
 		return -ENOMEM;
+	}
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -928,7 +930,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	pci_clear_master(dev->pdev);
 	release_bar(dev->pdev);
 	mlx5_pci_disable_device(dev);
-	debugfs_remove(priv->dbg_root);
+	debugfs_remove_recursive(priv->dbg_root);
 }
 
 static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
@@ -1286,7 +1288,7 @@ err_cleanup_once:
 		mlx5_cleanup_once(dev);
 
 err_stop_poll:
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, boot);
 	if (mlx5_cmd_teardown_hca(dev)) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
 		goto out_err;
@@ -1346,7 +1348,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, cleanup);
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
@@ -1608,7 +1610,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
 	 * with the HCA, so the health polll is no longer needed.
 	 */
 	mlx5_drain_health_wq(dev);
-	mlx5_stop_health_poll(dev);
+	mlx5_stop_health_poll(dev, false);
 
 	ret = mlx5_cmd_force_teardown_hca(dev);
 	if (ret) {

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

@@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
 	return (u32)wq->fbc.sz_m1 + 1;
 }
 
-u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
+u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq)
 {
-	return (u32)wq->fbc.frag_sz_m1 + 1;
+	return wq->fbc.frag_sz_m1 + 1;
 }
 
 u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
@@ -138,7 +138,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
-	u32 sq_strides_offset;
+	u16 sq_strides_offset;
 	u32 rq_pg_remainder;
 	int err;
 

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

@@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
-u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
+u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,

include/linux/mlx5/driver.h

@@ -362,8 +362,8 @@ struct mlx5_frag_buf {
 struct mlx5_frag_buf_ctrl {
 	struct mlx5_frag_buf	frag_buf;
 	u32			sz_m1;
-	u32			frag_sz_m1;
-	u32			strides_offset;
+	u16			frag_sz_m1;
+	u16			strides_offset;
 	u8			log_sz;
 	u8			log_stride;
 	u8			log_frag_strides;
@@ -995,7 +995,7 @@ static inline u32 mlx5_base_mkey(const u32 key)
 }
 
 static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz,
-					u32 strides_offset,
+					u16 strides_offset,
 					struct mlx5_frag_buf_ctrl *fbc)
 {
 	fbc->log_stride = log_stride;
@@ -1052,7 +1052,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
-void mlx5_stop_health_poll(struct mlx5_core_dev *dev);
+void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health);
 void mlx5_drain_health_wq(struct mlx5_core_dev *dev);
 void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 void mlx5_drain_health_recovery(struct mlx5_core_dev *dev);