diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 1 | ||||
| -rw-r--r-- | net/core/devlink.c | 22 | ||||
| -rw-r--r-- | net/core/failover.c | 315 | ||||
| -rw-r--r-- | net/core/flow_dissector.c | 2 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 6 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 18 | ||||
| -rw-r--r-- | net/core/sock.c | 15 |
7 files changed, 360 insertions, 19 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 7080417f8bc8..80175e6a2eb8 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -31,3 +31,4 @@ obj-$(CONFIG_DST_CACHE) += dst_cache.o obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o +obj-$(CONFIG_FAILOVER) += failover.o diff --git a/net/core/devlink.c b/net/core/devlink.c index 475246b355f0..22099705cc41 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -702,12 +702,13 @@ static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, return 0; } -static int devlink_port_split(struct devlink *devlink, - u32 port_index, u32 count) +static int devlink_port_split(struct devlink *devlink, u32 port_index, + u32 count, struct netlink_ext_ack *extack) { if (devlink->ops && devlink->ops->port_split) - return devlink->ops->port_split(devlink, port_index, count); + return devlink->ops->port_split(devlink, port_index, count, + extack); return -EOPNOTSUPP; } @@ -724,14 +725,15 @@ static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); - return devlink_port_split(devlink, port_index, count); + return devlink_port_split(devlink, port_index, count, info->extack); } -static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) +static int devlink_port_unsplit(struct devlink *devlink, u32 port_index, + struct netlink_ext_ack *extack) { if (devlink->ops && devlink->ops->port_unsplit) - return devlink->ops->port_unsplit(devlink, port_index); + return devlink->ops->port_unsplit(devlink, port_index, extack); return -EOPNOTSUPP; } @@ -745,7 +747,7 @@ static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return -EINVAL; port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); - return devlink_port_unsplit(devlink, port_index); + return devlink_port_unsplit(devlink, port_index, info->extack); } static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, @@ -1826,7 +1828,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2032,7 +2033,6 @@ int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) return 0; nla_put_failure: - genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr); nlmsg_free(dump_ctx->skb); return -EMSGSIZE; } @@ -2249,7 +2249,6 @@ send_done: nla_put_failure: err = -EMSGSIZE; err_table_put: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2551,7 +2550,6 @@ nla_put_failure: err = -EMSGSIZE; err_resource_put: err_skb_send_alloc: - genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } @@ -2603,7 +2601,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - return devlink->ops->reload(devlink); + return devlink->ops->reload(devlink, info->extack); } static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { diff --git a/net/core/failover.c b/net/core/failover.c new file mode 100644 index 000000000000..4a92a98ccce9 --- /dev/null +++ b/net/core/failover.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Intel Corporation. */ + +/* A common module to handle registrations and notifications for paravirtual + * drivers to enable accelerated datapath and support VF live migration. + * + * The notifier and event handling code is based on netvsc driver. + */ + +#include <linux/module.h> +#include <linux/etherdevice.h> +#include <uapi/linux/if_arp.h> +#include <linux/rtnetlink.h> +#include <linux/if_vlan.h> +#include <net/failover.h> + +static LIST_HEAD(failover_list); +static DEFINE_SPINLOCK(failover_lock); + +static struct net_device *failover_get_bymac(u8 *mac, struct failover_ops **ops) +{ + struct net_device *failover_dev; + struct failover *failover; + + spin_lock(&failover_lock); + list_for_each_entry(failover, &failover_list, list) { + failover_dev = rtnl_dereference(failover->failover_dev); + if (ether_addr_equal(failover_dev->perm_addr, mac)) { + *ops = rtnl_dereference(failover->ops); + spin_unlock(&failover_lock); + return failover_dev; + } + } + spin_unlock(&failover_lock); + return NULL; +} + +/** + * failover_slave_register - Register a slave netdev + * + * @slave_dev: slave netdev that is being registered + * + * Registers a slave device to a failover instance. Only ethernet devices + * are supported. + */ +static int failover_slave_register(struct net_device *slave_dev) +{ + struct netdev_lag_upper_info lag_upper_info; + struct net_device *failover_dev; + struct failover_ops *fops; + int err; + + if (slave_dev->type != ARPHRD_ETHER) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_register && + fops->slave_pre_register(slave_dev, failover_dev)) + goto done; + + err = netdev_rx_handler_register(slave_dev, fops->slave_handle_frame, + failover_dev); + if (err) { + netdev_err(slave_dev, "can not register failover rx handler (err = %d)\n", + err); + goto done; + } + + lag_upper_info.tx_type = NETDEV_LAG_TX_TYPE_ACTIVEBACKUP; + err = netdev_master_upper_dev_link(slave_dev, failover_dev, NULL, + &lag_upper_info, NULL); + if (err) { + netdev_err(slave_dev, "can not set failover device %s (err = %d)\n", + failover_dev->name, err); + goto err_upper_link; + } + + slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_register && + !fops->slave_register(slave_dev, failover_dev)) + return NOTIFY_OK; + + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; +err_upper_link: + netdev_rx_handler_unregister(slave_dev); +done: + return NOTIFY_DONE; +} + +/** + * failover_slave_unregister - Unregister a slave netdev + * + * @slave_dev: slave netdev that is being unregistered + * + * Unregisters a slave device from a failover instance. + */ +int failover_slave_unregister(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (fops && fops->slave_pre_unregister && + fops->slave_pre_unregister(slave_dev, failover_dev)) + goto done; + + netdev_rx_handler_unregister(slave_dev); + netdev_upper_dev_unlink(slave_dev, failover_dev); + slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + + if (fops && fops->slave_unregister && + !fops->slave_unregister(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} +EXPORT_SYMBOL_GPL(failover_slave_unregister); + +static int failover_slave_link_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_link_change && + !fops->slave_link_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int failover_slave_name_change(struct net_device *slave_dev) +{ + struct net_device *failover_dev; + struct failover_ops *fops; + + if (!netif_is_failover_slave(slave_dev)) + goto done; + + ASSERT_RTNL(); + + failover_dev = failover_get_bymac(slave_dev->perm_addr, &fops); + if (!failover_dev) + goto done; + + if (!netif_running(failover_dev)) + goto done; + + if (fops && fops->slave_name_change && + !fops->slave_name_change(slave_dev, failover_dev)) + return NOTIFY_OK; + +done: + return NOTIFY_DONE; +} + +static int +failover_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); + + /* Skip parent events */ + if (netif_is_failover(event_dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + return failover_slave_register(event_dev); + case NETDEV_UNREGISTER: + return failover_slave_unregister(event_dev); + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + return failover_slave_link_change(event_dev); + case NETDEV_CHANGENAME: + return failover_slave_name_change(event_dev); + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block failover_notifier = { + .notifier_call = failover_event, +}; + +static void +failover_existing_slave_register(struct net_device *failover_dev) +{ + struct net *net = dev_net(failover_dev); + struct net_device *dev; + + rtnl_lock(); + for_each_netdev(net, dev) { + if (netif_is_failover(dev)) + continue; + if (ether_addr_equal(failover_dev->perm_addr, dev->perm_addr)) + failover_slave_register(dev); + } + rtnl_unlock(); +} + +/** + * failover_register - Register a failover instance + * + * @dev: failover netdev + * @ops: failover ops + * + * Allocate and register a failover instance for a failover netdev. ops + * provides handlers for slave device register/unregister/link change/ + * name change events. + * + * Return: pointer to failover instance + */ +struct failover *failover_register(struct net_device *dev, + struct failover_ops *ops) +{ + struct failover *failover; + + if (dev->type != ARPHRD_ETHER) + return ERR_PTR(-EINVAL); + + failover = kzalloc(sizeof(*failover), GFP_KERNEL); + if (!failover) + return ERR_PTR(-ENOMEM); + + rcu_assign_pointer(failover->ops, ops); + dev_hold(dev); + dev->priv_flags |= IFF_FAILOVER; + rcu_assign_pointer(failover->failover_dev, dev); + + spin_lock(&failover_lock); + list_add_tail(&failover->list, &failover_list); + spin_unlock(&failover_lock); + + netdev_info(dev, "failover master:%s registered\n", dev->name); + + failover_existing_slave_register(dev); + + return failover; +} +EXPORT_SYMBOL_GPL(failover_register); + +/** + * failover_unregister - Unregister a failover instance + * + * @failover: pointer to failover instance + * + * Unregisters and frees a failover instance. + */ +void failover_unregister(struct failover *failover) +{ + struct net_device *failover_dev; + + failover_dev = rcu_dereference(failover->failover_dev); + + netdev_info(failover_dev, "failover master:%s unregistered\n", + failover_dev->name); + + failover_dev->priv_flags &= ~IFF_FAILOVER; + dev_put(failover_dev); + + spin_lock(&failover_lock); + list_del(&failover->list); + spin_unlock(&failover_lock); + + kfree(failover); +} +EXPORT_SYMBOL_GPL(failover_unregister); + +static __init int +failover_init(void) +{ + register_netdevice_notifier(&failover_notifier); + + return 0; +} +module_init(failover_init); + +static __exit +void failover_exit(void) +{ + unregister_netdevice_notifier(&failover_notifier); +} +module_exit(failover_exit); + +MODULE_DESCRIPTION("Generic failover infrastructure/interface"); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 4fc1e84d77ec..53f96e4f7bf5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1334,7 +1334,7 @@ __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys) keys->ports.src = fl6->fl6_sport; keys->ports.dst = fl6->fl6_dport; keys->keyid.keyid = fl6->fl6_gre_key; - keys->tags.flow_label = (__force u32)fl6->flowlabel; + keys->tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); keys->basic.ip_proto = fl6->flowi6_proto; return flow_hash_from_keys(keys); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c476f0794132..bb7e80f4ced3 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1214,9 +1214,6 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, cpumask_var_t mask; unsigned long index; - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - index = get_netdev_queue_index(queue); if (dev->num_tc) { @@ -1226,6 +1223,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, return -EINVAL; } + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_maps); if (dev_maps) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 80802546c279..9a1ba2015ad8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -59,6 +59,9 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> +#define RTNL_MAX_TYPE 48 +#define RTNL_SLAVE_MAX_TYPE 36 + struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; @@ -389,6 +392,11 @@ int rtnl_link_register(struct rtnl_link_ops *ops) { int err; + /* Sanity-check max sizes to avoid stack buffer overflow. */ + if (WARN_ON(ops->maxtype > RTNL_MAX_TYPE || + ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE)) + return -EINVAL; + rtnl_lock(); err = __rtnl_link_register(ops); rtnl_unlock(); @@ -2902,13 +2910,16 @@ replay: } if (1) { - struct nlattr *attr[ops ? ops->maxtype + 1 : 1]; - struct nlattr *slave_attr[m_ops ? m_ops->slave_maxtype + 1 : 1]; + struct nlattr *attr[RTNL_MAX_TYPE + 1]; + struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1]; struct nlattr **data = NULL; struct nlattr **slave_data = NULL; struct net *dest_net, *link_net = NULL; if (ops) { + if (ops->maxtype > RTNL_MAX_TYPE) + return -EINVAL; + if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { err = nla_parse_nested(attr, ops->maxtype, linkinfo[IFLA_INFO_DATA], @@ -2925,6 +2936,9 @@ replay: } if (m_ops) { + if (m_ops->slave_maxtype > RTNL_SLAVE_MAX_TYPE) + return -EINVAL; + if (m_ops->slave_maxtype && linkinfo[IFLA_INFO_SLAVE_DATA]) { err = nla_parse_nested(slave_attr, diff --git a/net/core/sock.c b/net/core/sock.c index 435a0ba85e52..feca4c98f8a0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -728,9 +728,22 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: - sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + val = (valbool ? SK_CAN_REUSE : SK_NO_REUSE); + if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) && + inet_sk(sk)->inet_num && + (sk->sk_reuse != val)) { + ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN; + break; + } + sk->sk_reuse = val; break; case SO_REUSEPORT: + if ((sk->sk_family == PF_INET || sk->sk_family == PF_INET6) && + inet_sk(sk)->inet_num && + (sk->sk_reuseport != valbool)) { + ret = (sk->sk_state == TCP_ESTABLISHED) ? -EISCONN : -EUCLEAN; + break; + } sk->sk_reuseport = valbool; break; case SO_TYPE: |
