net/mlx4_core: Preserve pci_dev_data after __mlx4_remove_one()

[ Upstream commit befdf897 ]

pci_match_id() just match the static pci_device_id, which may return NULL if
someone binds the driver to a device manually using
/sys/bus/pci/drivers/.../new_id.

This patch wrap up a helper function __mlx4_remove_one() which does the tear
down function but preserve the drv_data. Functions like
mlx4_pci_err_detected() and mlx4_restart_one() will call this one with out
releasing drvdata.

Fixes: 97a5221f "net/mlx4_core: pass pci_device_id.driver_data to __mlx4_init_one during reset".

CC: Bjorn Helgaas <bhelgaas@google.com>
CC: Amir Vadai <amirv@mellanox.com>
CC: Jack Morgenstein <jackm@dev.mellanox.co.il>
CC: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Acked-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

drivers/net/ethernet/mellanox/mlx4/main.c

@@ -2134,13 +2134,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	/* Allow large DMA segments, up to the firmware limit of 1 GB */
 	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		err = -ENOMEM;
-		goto err_release_regions;
-	}
-
-	dev       = &priv->dev;
+	dev       = pci_get_drvdata(pdev);
+	priv      = mlx4_priv(dev);
 	dev->pdev = pdev;
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
@@ -2308,8 +2303,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 	mlx4_sense_init(dev);
 	mlx4_start_sense(dev);
 
-	priv->pci_dev_data = pci_dev_data;
-	pci_set_drvdata(pdev, dev);
+	priv->removed = 0;
 
 	return 0;
 
@@ -2375,24 +2369,38 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data)
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct mlx4_priv *priv;
+	struct mlx4_dev *dev;
+
 	printk_once(KERN_INFO "%s", mlx4_version);
 
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev       = &priv->dev;
+	pci_set_drvdata(pdev, dev);
+	priv->pci_dev_data = id->driver_data;
+
 	return __mlx4_init_one(pdev, id->driver_data);
 }
 
-static void mlx4_remove_one(struct pci_dev *pdev)
+static void __mlx4_remove_one(struct pci_dev *pdev)
 {
 	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	int               pci_dev_data;
 	int p;
 
-	if (dev) {
+	if (priv->removed)
+		return;
+
+	pci_dev_data = priv->pci_dev_data;
+
 	/* in SRIOV it is not allowed to unload the pf's
 	 * driver while there are alive vf's */
-		if (mlx4_is_master(dev)) {
-			if (mlx4_how_many_lives_vf(dev))
+	if (mlx4_is_master(dev) && mlx4_how_many_lives_vf(dev))
 		printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
-		}
 	mlx4_stop_sense(dev);
 	mlx4_unregister_device(dev);
 
@@ -2448,11 +2456,21 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	kfree(dev->caps.qp1_tunnel);
 	kfree(dev->caps.qp1_proxy);
 
-		kfree(priv);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	memset(priv, 0, sizeof(*priv));
+	priv->pci_dev_data = pci_dev_data;
+	priv->removed = 1;
+}
+
+static void mlx4_remove_one(struct pci_dev *pdev)
+{
+	struct mlx4_dev  *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	__mlx4_remove_one(pdev);
+	kfree(priv);
 	pci_set_drvdata(pdev, NULL);
-	}
 }
 
 int mlx4_restart_one(struct pci_dev *pdev)
@@ -2462,7 +2480,7 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	int		  pci_dev_data;
 
 	pci_dev_data = priv->pci_dev_data;
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 	return __mlx4_init_one(pdev, pci_dev_data);
 }
 
@@ -2517,7 +2535,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table);
 static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 					      pci_channel_state_t state)
 {
-	mlx4_remove_one(pdev);
+	__mlx4_remove_one(pdev);
 
 	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -2525,11 +2543,11 @@ static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev,
 
 static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev)
 {
-	const struct pci_device_id *id;
+	struct mlx4_dev	 *dev  = pci_get_drvdata(pdev);
+	struct mlx4_priv *priv = mlx4_priv(dev);
 	int               ret;
 
-	id = pci_match_id(mlx4_pci_table, pdev);
-	ret = __mlx4_init_one(pdev, id->driver_data);
+	ret = __mlx4_init_one(pdev, priv->pci_dev_data);
 
 	return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -774,6 +774,7 @@ struct mlx4_priv {
 	spinlock_t		ctx_lock;
 
 	int			pci_dev_data;
+	int                     removed;
 
 	struct list_head        pgdir_list;
 	struct mutex            pgdir_mutex;