ldmvsw: Add ldmvsw.c driver code

  Add ldmvsw.c driver

  Details:

  The ldmvsw driver very closely follows the sunvnet.c code and makes
  use of the sunvnet_common.c code for core functionality.

  A significant difference between sunvnet and ldmvsw driver is
  sunvnet creates a network interface for each vnet-port *parent*
  node in the MD while the ldmvsw driver creates a network interface
  for every vsw-port node in the Machine Description (MD).
  Therefore the netdev_priv() for sunvnet is a vnet structure while
  the netdev_priv() for ldmvsw is a vnet_port structure.

  Vnet_port structures allocated by ldmvsw have the vsw bit set.
  When finding the net_device associated with a port, the common code keys
  off this bit to use either the net_device found in the vnet_port or the
  net_device in the vnet structure (see the VNET_PORT_TO_NET_DEVICE() macro in
  sunvnet_common.h). This scheme allows the common code to work with
  both drivers with minimal changes.

  Similar to Xen, network interfaces created by the ldmvsw driver will always
  have a HW Addr (i.e. mac address) of FE:FF:FF:FF:FF:FF and each will be
  assigned the devname "vif<cfg_handle>.<port_id>" - where <cfg_handle> and
  <port_id> are a unique handle/port pair assigned to the associated
  vsw-port node in the MD.

  Signed-off-by: Aaron Young <aaron.young@oracle.com>
  Signed-off-by: Rashmi Narasimhan <rashmi.narasimhan@oracle.com>
  Reviewed-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
  Reviewed-by: Alexandre Chartre <Alexandre.Chartre@oracle.com>

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

3 files changed, 480 insertions, 0 deletions

diff --git a/drivers/net/ethernet/sun/Kconfig b/drivers/net/ethernet/sun/Kconfig
index aa58c11ea6db..a4b40e3015e5 100644
--- a/drivers/net/ethernet/sun/Kconfig
+++ b/drivers/net/ethernet/sun/Kconfig
@@ -80,6 +80,17 @@ config SUNVNET
 	---help---
 	  Support for virtual network devices under Sun Logical Domains.
 
+config LDMVSW
+	tristate "Sun4v LDoms Virtual Switch support"
+	depends on SUN_LDOMS
+	---help---
+	  Support for virtual switch devices under Sun4v Logical Domains.
+	  This driver adds a network interface for every vsw-port node
+	  found in the machine description of a service domain.
+	  Linux bridge/switch software can use these interfaces for
+	  guest domain network interconnectivity or guest domain
+	  connection to a physical network on a service domain.
+
 config NIU
 	tristate "Sun Neptune 10Gbit Ethernet support"
 	depends on PCI
diff --git a/drivers/net/ethernet/sun/Makefile b/drivers/net/ethernet/sun/Makefile
index 7b622aa14c5b..37855438b3cb 100644
--- a/drivers/net/ethernet/sun/Makefile
+++ b/drivers/net/ethernet/sun/Makefile
@@ -9,4 +9,5 @@ obj-$(CONFIG_SUNGEM) += sungem.o
 obj-$(CONFIG_CASSINI) += cassini.o
 obj-$(CONFIG_SUNVNET_COMMON) += sunvnet_common.o
 obj-$(CONFIG_SUNVNET) += sunvnet.o
+obj-$(CONFIG_LDMVSW) += ldmvsw.o
 obj-$(CONFIG_NIU) += niu.o
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
new file mode 100644
index 000000000000..e15bf84fc6b2
--- /dev/null
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -0,0 +1,468 @@
+/* ldmvsw.c: Sun4v LDOM Virtual Switch Driver.
+ *
+ * Copyright (C) 2016 Oracle. All rights reserved.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/delay.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/highmem.h>
+#include <linux/if_vlan.h>
+#include <linux/init.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#if defined(CONFIG_IPV6)
+#include <linux/icmpv6.h>
+#endif
+
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/route.h>
+
+#include <asm/vio.h>
+#include <asm/ldc.h>
+
+/* This driver makes use of the common code in sunvnet_common.c */
+#include "sunvnet_common.h"
+
+/* Length of time before we decide the hardware is hung,
+ * and dev->tx_timeout() should be called to fix the problem.
+ */
+#define VSW_TX_TIMEOUT			(10 * HZ)
+
+/* Static HW Addr used for the network interfaces representing vsw ports */
+static u8 vsw_port_hwaddr[ETH_ALEN] = {0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
+
+#define DRV_MODULE_NAME		"ldmvsw"
+#define DRV_MODULE_VERSION	"1.0"
+#define DRV_MODULE_RELDATE	"Jan 15, 2016"
+
+static char version[] =
+	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
+MODULE_AUTHOR("Oracle");
+MODULE_DESCRIPTION("Sun4v LDOM Virtual Switch Driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_MODULE_VERSION);
+
+/* Ordered from largest major to lowest */
+static struct vio_version vsw_versions[] = {
+	{ .major = 1, .minor = 8 },
+	{ .major = 1, .minor = 7 },
+	{ .major = 1, .minor = 6 },
+	{ .major = 1, .minor = 0 },
+};
+
+static void vsw_get_drvinfo(struct net_device *dev,
+			    struct ethtool_drvinfo *info)
+{
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+}
+
+static u32 vsw_get_msglevel(struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	return port->vp->msg_enable;
+}
+
+static void vsw_set_msglevel(struct net_device *dev, u32 value)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	port->vp->msg_enable = value;
+}
+
+static const struct ethtool_ops vsw_ethtool_ops = {
+	.get_drvinfo		= vsw_get_drvinfo,
+	.get_msglevel		= vsw_get_msglevel,
+	.set_msglevel		= vsw_set_msglevel,
+	.get_link		= ethtool_op_get_link,
+};
+
+static LIST_HEAD(vnet_list);
+static DEFINE_MUTEX(vnet_list_mutex);
+
+/* func arg to vnet_start_xmit_common() to get the proper tx port */
+static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb,
+					  struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	return port;
+}
+
+static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    void *accel_priv, select_queue_fallback_t fallback)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	if (!port)
+		return 0;
+
+	return port->q_index;
+}
+
+/* Wrappers to common functions */
+static int vsw_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	return sunvnet_start_xmit_common(skb, dev, vsw_tx_port_find);
+}
+
+static void vsw_set_rx_mode(struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	return sunvnet_set_rx_mode_common(dev, port->vp);
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void vsw_poll_controller(struct net_device *dev)
+{
+	struct vnet_port *port = netdev_priv(dev);
+
+	return sunvnet_poll_controller_common(dev, port->vp);
+}
+#endif
+
+static const struct net_device_ops vsw_ops = {
+	.ndo_open		= sunvnet_open_common,
+	.ndo_stop		= sunvnet_close_common,
+	.ndo_set_rx_mode	= vsw_set_rx_mode,
+	.ndo_set_mac_address	= sunvnet_set_mac_addr_common,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_tx_timeout		= sunvnet_tx_timeout_common,
+	.ndo_change_mtu		= sunvnet_change_mtu_common,
+	.ndo_start_xmit		= vsw_start_xmit,
+	.ndo_select_queue	= vsw_select_queue,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller    = vsw_poll_controller,
+#endif
+};
+
+static const char *local_mac_prop = "local-mac-address";
+static const char *cfg_handle_prop = "cfg-handle";
+
+static struct vnet *vsw_get_vnet(struct mdesc_handle *hp,
+				 u64 port_node,
+				 u64 *handle)
+{
+	struct vnet *vp;
+	struct vnet *iter;
+	const u64 *local_mac = NULL;
+	const u64 *cfghandle = NULL;
+	u64 a;
+
+	/* Get the parent virtual-network-switch macaddr and cfghandle */
+	mdesc_for_each_arc(a, hp, port_node, MDESC_ARC_TYPE_BACK) {
+		u64 target = mdesc_arc_target(hp, a);
+		const char *name;
+
+		name = mdesc_get_property(hp, target, "name", NULL);
+		if (!name || strcmp(name, "virtual-network-switch"))
+			continue;
+
+		local_mac = mdesc_get_property(hp, target,
+					       local_mac_prop, NULL);
+		cfghandle = mdesc_get_property(hp, target,
+					       cfg_handle_prop, NULL);
+		break;
+	}
+	if (!local_mac || !cfghandle)
+		return ERR_PTR(-ENODEV);
+
+	/* find or create associated vnet */
+	vp = NULL;
+	mutex_lock(&vnet_list_mutex);
+	list_for_each_entry(iter, &vnet_list, list) {
+		if (iter->local_mac == *local_mac) {
+			vp = iter;
+			break;
+		}
+	}
+
+	if (!vp) {
+		vp = kzalloc(sizeof(*vp), GFP_KERNEL);
+		if (unlikely(!vp)) {
+			mutex_unlock(&vnet_list_mutex);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		spin_lock_init(&vp->lock);
+		INIT_LIST_HEAD(&vp->port_list);
+		INIT_LIST_HEAD(&vp->list);
+		vp->local_mac = *local_mac;
+		list_add(&vp->list, &vnet_list);
+	}
+
+	mutex_unlock(&vnet_list_mutex);
+
+	*handle = (u64)*cfghandle;
+
+	return vp;
+}
+
+static struct net_device *vsw_alloc_netdev(u8 hwaddr[],
+					   struct vio_dev *vdev,
+					   u64 handle,
+					   u64 port_id)
+{
+	struct net_device *dev;
+	struct vnet_port *port;
+	int i;
+
+	dev = alloc_etherdev_mqs(sizeof(*port), VNET_MAX_TXQS, 1);
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+	dev->needed_headroom = VNET_PACKET_SKIP + 8;
+	dev->needed_tailroom = 8;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		dev->dev_addr[i] = hwaddr[i];
+		dev->perm_addr[i] = dev->dev_addr[i];
+	}
+
+	sprintf(dev->name, "vif%d.%d", (int)handle, (int)port_id);
+
+	dev->netdev_ops = &vsw_ops;
+	dev->ethtool_ops = &vsw_ethtool_ops;
+	dev->watchdog_timeo = VSW_TX_TIMEOUT;
+
+	dev->hw_features = NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE |
+			   NETIF_F_HW_CSUM | NETIF_F_SG;
+	dev->features = dev->hw_features;
+
+	SET_NETDEV_DEV(dev, &vdev->dev);
+
+	return dev;
+}
+
+static struct ldc_channel_config vsw_ldc_cfg = {
+	.event		= sunvnet_event_common,
+	.mtu		= 64,
+	.mode		= LDC_MODE_UNRELIABLE,
+};
+
+static struct vio_driver_ops vsw_vio_ops = {
+	.send_attr		= sunvnet_send_attr_common,
+	.handle_attr		= sunvnet_handle_attr_common,
+	.handshake_complete	= sunvnet_handshake_complete_common,
+};
+
+static void print_version(void)
+{
+	printk_once(KERN_INFO "%s", version);
+}
+
+static const char *remote_macaddr_prop = "remote-mac-address";
+static const char *id_prop = "id";
+
+static int vsw_port_probe(struct vio_dev *vdev, const struct vio_device_id *id)
+{
+	struct mdesc_handle *hp;
+	struct vnet_port *port;
+	unsigned long flags;
+	struct vnet *vp;
+	struct net_device *dev;
+	const u64 *rmac;
+	int len, i, err;
+	const u64 *port_id;
+	u64 handle;
+
+	print_version();
+
+	hp = mdesc_grab();
+
+	rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len);
+	err = -ENODEV;
+	if (!rmac) {
+		pr_err("Port lacks %s property\n", remote_macaddr_prop);
+		mdesc_release(hp);
+		return err;
+	}
+
+	port_id = mdesc_get_property(hp, vdev->mp, id_prop, NULL);
+	err = -ENODEV;
+	if (!port_id) {
+		pr_err("Port lacks %s property\n", id_prop);
+		mdesc_release(hp);
+		return err;
+	}
+
+	/* Get (or create) the vnet associated with this port */
+	vp = vsw_get_vnet(hp, vdev->mp, &handle);
+	if (unlikely(IS_ERR(vp))) {
+		err = PTR_ERR(vp);
+		pr_err("Failed to get vnet for vsw-port\n");
+		mdesc_release(hp);
+		return err;
+	}
+
+	mdesc_release(hp);
+
+	dev = vsw_alloc_netdev(vsw_port_hwaddr, vdev, handle, *port_id);
+	if (IS_ERR(dev)) {
+		err = PTR_ERR(dev);
+		pr_err("Failed to alloc netdev for vsw-port\n");
+		return err;
+	}
+
+	port = netdev_priv(dev);
+
+	INIT_LIST_HEAD(&port->list);
+
+	for (i = 0; i < ETH_ALEN; i++)
+		port->raddr[i] = (*rmac >> (5 - i) * 8) & 0xff;
+
+	port->vp = vp;
+	port->dev = dev;
+	port->switch_port = 1;
+	port->tso = true;
+	port->tsolen = 0;
+
+	/* Mark the port as belonging to ldmvsw which directs the
+	 * the common code to use the net_device in the vnet_port
+	 * rather than the net_device in the vnet (which is used
+	 * by sunvnet). This bit is used by the VNET_PORT_TO_NET_DEVICE
+	 * macro.
+	 */
+	port->vsw = 1;
+
+	err = vio_driver_init(&port->vio, vdev, VDEV_NETWORK,
+			      vsw_versions, ARRAY_SIZE(vsw_versions),
+			      &vsw_vio_ops, dev->name);
+	if (err)
+		goto err_out_free_dev;
+
+	err = vio_ldc_alloc(&port->vio, &vsw_ldc_cfg, port);
+	if (err)
+		goto err_out_free_dev;
+
+	dev_set_drvdata(&vdev->dev, port);
+
+	netif_napi_add(dev, &port->napi, sunvnet_poll_common,
+		       NAPI_POLL_WEIGHT);
+
+	spin_lock_irqsave(&vp->lock, flags);
+	list_add_rcu(&port->list, &vp->port_list);
+	spin_unlock_irqrestore(&vp->lock, flags);
+
+	setup_timer(&port->clean_timer, sunvnet_clean_timer_expire_common,
+		    (unsigned long)port);
+
+	err = register_netdev(dev);
+	if (err) {
+		pr_err("Cannot register net device, aborting\n");
+		goto err_out_del_timer;
+	}
+
+	spin_lock_irqsave(&vp->lock, flags);
+	sunvnet_port_add_txq_common(port);
+	spin_unlock_irqrestore(&vp->lock, flags);
+
+	napi_enable(&port->napi);
+	vio_port_up(&port->vio);
+
+	netdev_info(dev, "LDOM vsw-port %pM\n", dev->dev_addr);
+
+	pr_info("%s: PORT ( remote-mac %pM%s )\n", dev->name,
+		port->raddr, " switch-port");
+
+	return 0;
+
+err_out_del_timer:
+	del_timer_sync(&port->clean_timer);
+	list_del_rcu(&port->list);
+	synchronize_rcu();
+	netif_napi_del(&port->napi);
+	dev_set_drvdata(&vdev->dev, NULL);
+	vio_ldc_free(&port->vio);
+
+err_out_free_dev:
+	free_netdev(dev);
+	return err;
+}
+
+static int vsw_port_remove(struct vio_dev *vdev)
+{
+	struct vnet_port *port = dev_get_drvdata(&vdev->dev);
+	unsigned long flags;
+
+	if (port) {
+		del_timer_sync(&port->vio.timer);
+
+		napi_disable(&port->napi);
+
+		list_del_rcu(&port->list);
+
+		synchronize_rcu();
+		del_timer_sync(&port->clean_timer);
+		spin_lock_irqsave(&port->vp->lock, flags);
+		sunvnet_port_rm_txq_common(port);
+		spin_unlock_irqrestore(&port->vp->lock, flags);
+		netif_napi_del(&port->napi);
+		sunvnet_port_free_tx_bufs_common(port);
+		vio_ldc_free(&port->vio);
+
+		dev_set_drvdata(&vdev->dev, NULL);
+
+		unregister_netdev(port->dev);
+		free_netdev(port->dev);
+	}
+
+	return 0;
+}
+
+static void vsw_cleanup(void)
+{
+	struct vnet *vp;
+
+	/* just need to free up the vnet list */
+	mutex_lock(&vnet_list_mutex);
+	while (!list_empty(&vnet_list)) {
+		vp = list_first_entry(&vnet_list, struct vnet, list);
+		list_del(&vp->list);
+		/* vio_unregister_driver() should have cleaned up port_list */
+		if (!list_empty(&vp->port_list))
+			pr_err("Ports not removed by VIO subsystem!\n");
+		kfree(vp);
+	}
+	mutex_unlock(&vnet_list_mutex);
+}
+
+static const struct vio_device_id vsw_port_match[] = {
+	{
+		.type = "vsw-port",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(vio, vsw_port_match);
+
+static struct vio_driver vsw_port_driver = {
+	.id_table	= vsw_port_match,
+	.probe		= vsw_port_probe,
+	.remove		= vsw_port_remove,
+	.name		= "vsw_port",
+};
+
+static int __init vsw_init(void)
+{
+	return vio_register_driver(&vsw_port_driver);
+}
+
+static void __exit vsw_exit(void)
+{
+	vio_unregister_driver(&vsw_port_driver);
+	vsw_cleanup();
+}
+
+module_init(vsw_init);
+module_exit(vsw_exit);