1 files changed, 164 insertions, 46 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index f1b6d219e445..358f7230da58 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -42,6 +42,7 @@
 #include <linux/io-mapping.h>
 #include <linux/delay.h>
 #include <linux/kmod.h>
+#include <net/devlink.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -104,6 +105,11 @@ module_param(enable_64b_cqe_eqe, bool, 0444);
 MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
+static bool enable_4k_uar;
+module_param(enable_4k_uar, bool, 0444);
+MODULE_PARM_DESC(enable_4k_uar,
+		 "Enable using 4K UAR. Should not be enabled if have VFs which do not support 4K UARs (default: false)");
+
 #define PF_CONTEXT_BEHAVIOUR_MASK	(MLX4_FUNC_CAP_64B_EQE_CQE | \
 					 MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
 					 MLX4_FUNC_CAP_DMFS_A0_STATIC)
@@ -168,6 +174,20 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
+					      struct mlx4_dev_cap *dev_cap)
+{
+	/* The reserved_uars is calculated by system page size unit.
+	 * Therefore, adjustment is added when the uar page size is less
+	 * than the system page size
+	 */
+	dev->caps.reserved_uars	=
+		max_t(int,
+		      mlx4_get_num_reserved_uar(dev),
+		      dev_cap->reserved_uars /
+			(1 << (PAGE_SHIFT - dev->uar_page_shift)));
+}
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -386,8 +406,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
 	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;
 
-	/* The first 128 UARs are used for EQ doorbells */
-	dev->caps.reserved_uars	     = max_t(int, 128, dev_cap->reserved_uars);
 	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
 	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
 					dev_cap->reserved_xrcds : 0;
@@ -405,6 +423,19 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
+	/* Save uar page shift */
+	if (!mlx4_is_slave(dev)) {
+		/* Virtual PCI function needs to determine UAR page size from
+		 * firmware. Only master PCI function can set the uar page size
+		 */
+		if (enable_4k_uar)
+			dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT;
+		else
+			dev->uar_page_shift = PAGE_SHIFT;
+
+		mlx4_set_num_reserved_uars(dev, dev_cap);
+	}
+
 	if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) {
 		struct mlx4_init_hca_param hca_param;
 
@@ -815,16 +846,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENODEV;
 	}
 
-	/* slave gets uar page size from QUERY_HCA fw command */
-	dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);
+	/* Set uar_page_shift for VF */
+	dev->uar_page_shift = hca_param.uar_page_sz + 12;
 
-	/* TODO: relax this assumption */
-	if (dev->caps.uar_page_size != PAGE_SIZE) {
-		mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
-			 dev->caps.uar_page_size, PAGE_SIZE);
-		return -ENODEV;
+	/* Make sure the master uar page size is valid */
+	if (dev->uar_page_shift > PAGE_SHIFT) {
+		mlx4_err(dev,
+			 "Invalid configuration: uar page size is larger than system page size\n");
+		return  -ENODEV;
 	}
 
+	/* Set reserved_uars based on the uar_page_shift */
+	mlx4_set_num_reserved_uars(dev, &dev_cap);
+
+	/* Although uar page size in FW differs from system page size,
+	 * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core)
+	 * still works with assumption that uar page size == system page size
+	 */
+	dev->caps.uar_page_size = PAGE_SIZE;
+
 	memset(&func_cap, 0, sizeof(func_cap));
 	err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap);
 	if (err) {
@@ -1051,36 +1091,20 @@ static ssize_t show_port_type(struct device *dev,
 	return strlen(buf);
 }
 
-static ssize_t set_port_type(struct device *dev,
-			     struct device_attribute *attr,
-			     const char *buf, size_t count)
+static int __set_port_type(struct mlx4_port_info *info,
+			   enum mlx4_port_type port_type)
 {
-	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
-						   port_attr);
 	struct mlx4_dev *mdev = info->dev;
 	struct mlx4_priv *priv = mlx4_priv(mdev);
 	enum mlx4_port_type types[MLX4_MAX_PORTS];
 	enum mlx4_port_type new_types[MLX4_MAX_PORTS];
-	static DEFINE_MUTEX(set_port_type_mutex);
 	int i;
 	int err = 0;
 
-	mutex_lock(&set_port_type_mutex);
-
-	if (!strcmp(buf, "ib\n"))
-		info->tmp_type = MLX4_PORT_TYPE_IB;
-	else if (!strcmp(buf, "eth\n"))
-		info->tmp_type = MLX4_PORT_TYPE_ETH;
-	else if (!strcmp(buf, "auto\n"))
-		info->tmp_type = MLX4_PORT_TYPE_AUTO;
-	else {
-		mlx4_err(mdev, "%s is not supported port type\n", buf);
-		err = -EINVAL;
-		goto err_out;
-	}
-
 	mlx4_stop_sense(mdev);
 	mutex_lock(&priv->port_mutex);
+	info->tmp_type = port_type;
+
 	/* Possible type is always the one that was delivered */
 	mdev->caps.possible_type[info->port] = info->tmp_type;
 
@@ -1122,6 +1146,37 @@ static ssize_t set_port_type(struct device *dev,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
+
+	return err;
+}
+
+static ssize_t set_port_type(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_attr);
+	struct mlx4_dev *mdev = info->dev;
+	enum mlx4_port_type port_type;
+	static DEFINE_MUTEX(set_port_type_mutex);
+	int err;
+
+	mutex_lock(&set_port_type_mutex);
+
+	if (!strcmp(buf, "ib\n")) {
+		port_type = MLX4_PORT_TYPE_IB;
+	} else if (!strcmp(buf, "eth\n")) {
+		port_type = MLX4_PORT_TYPE_ETH;
+	} else if (!strcmp(buf, "auto\n")) {
+		port_type = MLX4_PORT_TYPE_AUTO;
+	} else {
+		mlx4_err(mdev, "%s is not supported port type\n", buf);
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	err = __set_port_type(info, port_type);
+
 err_out:
 	mutex_unlock(&set_port_type_mutex);
 
@@ -1226,6 +1281,7 @@ err_set_port:
 static int mlx4_mf_bond(struct mlx4_dev *dev)
 {
 	int err = 0;
+	int nvfs;
 	struct mlx4_slaves_pport slaves_port1;
 	struct mlx4_slaves_pport slaves_port2;
 	DECLARE_BITMAP(slaves_port_1_2, MLX4_MFUNC_MAX);
@@ -1242,11 +1298,18 @@ static int mlx4_mf_bond(struct mlx4_dev *dev)
 		return -EINVAL;
 	}
 
+	/* number of virtual functions is number of total functions minus one
+	 * physical function for each port.
+	 */
+	nvfs = bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
+		bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1) - 2;
+
 	/* limit on maximum allowed VFs */
-	if ((bitmap_weight(slaves_port1.slaves, dev->persist->num_vfs + 1) +
-	    bitmap_weight(slaves_port2.slaves, dev->persist->num_vfs + 1)) >
-	    MAX_MF_BOND_ALLOWED_SLAVES)
+	if (nvfs > MAX_MF_BOND_ALLOWED_SLAVES) {
+		mlx4_warn(dev, "HA mode is not supported for %d VFs (max %d are allowed)\n",
+			  nvfs, MAX_MF_BOND_ALLOWED_SLAVES);
 		return -EINVAL;
+	}
 
 	if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		mlx4_warn(dev, "HA mode unsupported for NON DMFS steering\n");
@@ -2179,8 +2242,15 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 
 		dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1;
 
-		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
-		init_hca.uar_page_sz = PAGE_SHIFT - 12;
+		if (enable_4k_uar) {
+			init_hca.log_uar_sz = ilog2(dev->caps.num_uars) +
+						    PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT;
+			init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12;
+		} else {
+			init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
+			init_hca.uar_page_sz = PAGE_SHIFT - 12;
+		}
+
 		init_hca.mw_enabled = 0;
 		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW ||
 		    dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN)
@@ -2847,8 +2917,13 @@ no_msi:
 
 static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 {
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	int err = 0;
+	int err;
+
+	err = devlink_port_register(devlink, &info->devlink_port, port);
+	if (err)
+		return err;
 
 	info->dev = dev;
 	info->port = port;
@@ -2873,6 +2948,7 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 	err = device_create_file(&dev->persist->pdev->dev, &info->port_attr);
 	if (err) {
 		mlx4_err(dev, "Failed to create file for port %d\n", port);
+		devlink_port_unregister(&info->devlink_port);
 		info->port = -1;
 	}
 
@@ -3644,23 +3720,54 @@ err_disable_pdev:
 	return err;
 }
 
+static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
+				      enum devlink_port_type port_type)
+{
+	struct mlx4_port_info *info = container_of(devlink_port,
+						   struct mlx4_port_info,
+						   devlink_port);
+	enum mlx4_port_type mlx4_port_type;
+
+	switch (port_type) {
+	case DEVLINK_PORT_TYPE_AUTO:
+		mlx4_port_type = MLX4_PORT_TYPE_AUTO;
+		break;
+	case DEVLINK_PORT_TYPE_ETH:
+		mlx4_port_type = MLX4_PORT_TYPE_ETH;
+		break;
+	case DEVLINK_PORT_TYPE_IB:
+		mlx4_port_type = MLX4_PORT_TYPE_IB;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return __set_port_type(info, mlx4_port_type);
+}
+
+static const struct devlink_ops mlx4_devlink_ops = {
+	.port_type_set	= mlx4_devlink_port_type_set,
+};
+
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct devlink *devlink;
 	struct mlx4_priv *priv;
 	struct mlx4_dev *dev;
 	int ret;
 
 	printk_once(KERN_INFO "%s", mlx4_version);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
+	devlink = devlink_alloc(&mlx4_devlink_ops, sizeof(*priv));
+	if (!devlink)
 		return -ENOMEM;
+	priv = devlink_priv(devlink);
 
 	dev       = &priv->dev;
 	dev->persist = kzalloc(sizeof(*dev->persist), GFP_KERNEL);
 	if (!dev->persist) {
-		kfree(priv);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_devlink_free;
 	}
 	dev->persist->pdev = pdev;
 	dev->persist->dev = dev;
@@ -3669,14 +3776,23 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&dev->persist->device_state_mutex);
 	mutex_init(&dev->persist->interface_state_mutex);
 
+	ret = devlink_register(devlink, &pdev->dev);
+	if (ret)
+		goto err_persist_free;
+
 	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
-	if (ret) {
-		kfree(dev->persist);
-		kfree(priv);
-	} else {
-		pci_save_state(pdev);
-	}
+	if (ret)
+		goto err_devlink_unregister;
 
+	pci_save_state(pdev);
+	return 0;
+
+err_devlink_unregister:
+	devlink_unregister(devlink);
+err_persist_free:
+	kfree(dev->persist);
+err_devlink_free:
+	devlink_free(devlink);
 	return ret;
 }
 
@@ -3777,6 +3893,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev  *dev  = persist->dev;
 	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct devlink *devlink = priv_to_devlink(priv);
 	int active_vfs = 0;
 
 	mutex_lock(&persist->interface_state_mutex);
@@ -3807,8 +3924,9 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+	devlink_unregister(devlink);
 	kfree(dev->persist);
-	kfree(priv);
+	devlink_free(devlink);
 	pci_set_drvdata(pdev, NULL);
 }