diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 10:05:34 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-03-19 10:05:34 -0700 |
commit | 1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe (patch) | |
tree | 552e03de245cdbd0780ca1215914edc4a26540f7 /drivers/net/ethernet/sun/ldmvsw.c | |
parent | Merge branch 'for-4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup (diff) | |
parent | bonding: fix bond_get_stats() (diff) | |
download | linux-dev-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.tar.xz linux-dev-1200b6809dfd9d73bc4c7db76d288c35fa4b2ebe.zip |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Support more Realtek wireless chips, from Jes Sorenson.
2) New BPF types for per-cpu hash and arrap maps, from Alexei
Starovoitov.
3) Make several TCP sysctls per-namespace, from Nikolay Borisov.
4) Allow the use of SO_REUSEPORT in order to do per-thread processing
of incoming TCP/UDP connections. The muxing can be done using a
BPF program which hashes the incoming packet. From Craig Gallek.
5) Add a multiplexer for TCP streams, to provide a messaged based
interface. BPF programs can be used to determine the message
boundaries. From Tom Herbert.
6) Add 802.1AE MACSEC support, from Sabrina Dubroca.
7) Avoid factorial complexity when taking down an inetdev interface
with lots of configured addresses. We were doing things like
traversing the entire address less for each address removed, and
flushing the entire netfilter conntrack table for every address as
well.
8) Add and use SKB bulk free infrastructure, from Jesper Brouer.
9) Allow offloading u32 classifiers to hardware, and implement for
ixgbe, from John Fastabend.
10) Allow configuring IRQ coalescing parameters on a per-queue basis,
from Kan Liang.
11) Extend ethtool so that larger link mode masks can be supported.
From David Decotigny.
12) Introduce devlink, which can be used to configure port link types
(ethernet vs Infiniband, etc.), port splitting, and switch device
level attributes as a whole. From Jiri Pirko.
13) Hardware offload support for flower classifiers, from Amir Vadai.
14) Add "Local Checksum Offload". Basically, for a tunneled packet
the checksum of the outer header is 'constant' (because with the
checksum field filled into the inner protocol header, the payload
of the outer frame checksums to 'zero'), and we can take advantage
of that in various ways. From Edward Cree"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1548 commits)
bonding: fix bond_get_stats()
net: bcmgenet: fix dma api length mismatch
net/mlx4_core: Fix backward compatibility on VFs
phy: mdio-thunder: Fix some Kconfig typos
lan78xx: add ndo_get_stats64
lan78xx: handle statistics counter rollover
RDS: TCP: Remove unused constant
RDS: TCP: Add sysctl tunables for sndbuf/rcvbuf on rds-tcp socket
net: smc911x: convert pxa dma to dmaengine
team: remove duplicate set of flag IFF_MULTICAST
bonding: remove duplicate set of flag IFF_MULTICAST
net: fix a comment typo
ethernet: micrel: fix some error codes
ip_tunnels, bpf: define IP_TUNNEL_OPTS_MAX and use it
bpf, dst: add and use dst_tclassid helper
bpf: make skb->tc_classid also readable
net: mvneta: bm: clarify dependencies
cls_bpf: reset class and reuse major in da
ldmvsw: Checkpatch sunvnet.c and sunvnet_common.c
ldmvsw: Add ldmvsw.c driver code
...
Diffstat (limited to 'drivers/net/ethernet/sun/ldmvsw.c')
-rw-r--r-- | drivers/net/ethernet/sun/ldmvsw.c | 468 |
1 files changed, 468 insertions, 0 deletions
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); |