diff options
Diffstat (limited to 'include/linux/netdevice.h')
| -rw-r--r-- | include/linux/netdevice.h | 181 |
1 files changed, 141 insertions, 40 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ca01eb3f7d2..87cafc932e9e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -162,7 +162,7 @@ static inline bool dev_xmit_complete(int rc) #if defined(CONFIG_HYPERV_NET) # define LL_MAX_HEADER 128 -#elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) +#elif defined(CONFIG_WLAN) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else @@ -300,9 +300,11 @@ struct hh_cache { * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ -#define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ +#define LL_RESERVED_SPACE_EX(dev, hlen) \ + ((((hlen) + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) +#define LL_RESERVED_SPACE(dev) \ + LL_RESERVED_SPACE_EX(dev, (dev)->hard_header_len) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) @@ -830,8 +832,13 @@ struct xps_dev_maps { #define TC_BITMASK 15 /* HW offloaded queuing disciplines txq count and offset maps */ struct netdev_tc_txq { - u16 count; - u16 offset; + union { + struct { + u16 count; + u16 offset; + }; + u32 combined; + }; }; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) @@ -892,6 +899,7 @@ struct net_device_path { u8 h_dest[ETH_ALEN]; } encap; struct { + struct dst_entry *dst; union { struct in_addr src_v4; struct in6_addr src_v6; @@ -901,7 +909,7 @@ struct net_device_path { struct in6_addr dst_v6; }; - u8 l3_proto; + u8 inner_proto; } tun; struct { enum { @@ -938,6 +946,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; u8 daddr[ETH_ALEN]; + __be16 ether_type; int num_vlans; struct { @@ -1119,6 +1128,20 @@ struct netdev_net_notifier { * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set * IFF_UNICAST_FLT in its priv_flags. + * Cannot sleep, called with netif_addr_lock_bh held. + * Deprecated in favor of ndo_set_rx_mode_async. + * + * int (*ndo_set_rx_mode_async)(struct net_device *dev, + * struct netdev_hw_addr_list *uc, + * struct netdev_hw_addr_list *mc); + * Async version of ndo_set_rx_mode which runs in process context + * with rtnl_lock and netdev_lock_ops(dev) held. The uc/mc parameters + * are snapshots of the address lists - iterate with + * netdev_hw_addr_list_for_each(ha, uc). Return 0 on success or a + * negative errno to request a retry via the core backoff. + * + * void (*ndo_work)(struct net_device *dev, unsigned long events); + * Run deferred work scheduled with netdev_work_sched(@events). * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address @@ -1139,8 +1162,8 @@ struct netdev_net_notifier { * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY * * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); - * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, - * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. + * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG and + * SIOCSMIIREG. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface @@ -1213,6 +1236,12 @@ struct netdev_net_notifier { * tx queues stopped. This allows the netdevice to perform queue * management safely. * + * NB: Returning -EOPNOTSUPP for whatever commands means "this qdisc + * is not offloaded (anymore, offloading may have silently stopped)", + * and the offloading flag is cleared. Notably, this is also true for + * dump queries (e.g. TC_*_STATS commands). If the underlying device does + * not report any statistics but is still offloading, return 0 instead. + * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); * Called when the FCoE protocol stack wants to start using LLD for FCoE @@ -1439,6 +1468,12 @@ struct net_device_ops { void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); + int (*ndo_set_rx_mode_async)( + struct net_device *dev, + struct netdev_hw_addr_list *uc, + struct netdev_hw_addr_list *mc); + void (*ndo_work)(struct net_device *dev, + unsigned long events); int (*ndo_set_mac_address)(struct net_device *dev, void *addr); int (*ndo_validate_addr)(struct net_device *dev); @@ -1716,7 +1751,6 @@ struct net_device_ops { * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device - * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device @@ -1752,7 +1786,6 @@ enum netdev_priv_flags { IFF_OPENVSWITCH = 1<<20, IFF_L3MDEV_SLAVE = 1<<21, IFF_TEAM = 1<<22, - IFF_RXFH_CONFIGURED = 1<<23, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, @@ -1776,6 +1809,12 @@ enum netdev_stat_type { NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ }; +enum netmem_tx_mode { + NETMEM_TX_NONE, /* no netmem TX support */ + NETMEM_TX_DMA, /* DMA-capable netmem TX (real HW) */ + NETMEM_TX_NO_DMA, /* no DMA, e.g. passthrough for virtual devs */ +}; + enum netdev_reg_state { NETREG_UNINITIALIZED = 0, NETREG_REGISTERED, /* completed register_netdevice */ @@ -1797,7 +1836,7 @@ enum netdev_reg_state { * @lltx: device supports lockless Tx. Deprecated for real HW * drivers. Mainly used by logical interfaces, such as * bonding and tunnels - * @netmem_tx: device support netmem_tx. + * @netmem_tx: device netmem TX mode * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name @@ -1815,6 +1854,8 @@ enum netdev_reg_state { * @napi_list: List entry used for polling NAPI devices * @unreg_list: List entry when we are unregistering the * device; see the function unregister_netdev + * @unreg_list_net:List entry when we are unregistering the cross-netns + * device; see the function unregister_netdevice_queue_net() * @close_list: List entry used when we are closing the device * @ptype_all: Device-specific packet handlers for all protocols * @ptype_specific: Device-specific, protocol-specific packet handlers @@ -1905,6 +1946,14 @@ enum netdev_reg_state { * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() + * @work_node: List entry for async netdev_work processing + * @work_tracker: Refcount tracker for async netdev_work + * @work_pending: Driver-defined pending netdev_work, passed to + * ndo_work() (see netdev_work_sched()) + * @work_core_pending: Core-defined pending netdev_work (NETDEV_WORK_*) + * @rx_mode_addr_cache: Recycled snapshot entries for rx_mode work + * @rx_mode_retry_timer: Timer that re-queues rx_mode work after failure + * @rx_mode_retry_count: Number of consecutive retries already scheduled * @uc: unicast mac addresses * @mc: multicast mac addresses * @dev_addrs: list of device hw addresses @@ -1917,10 +1966,8 @@ enum netdev_reg_state { * @vlan_info: VLAN info * @dsa_ptr: dsa specific data * @tipc_ptr: TIPC specific data - * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data * @ip6_ptr: IPv6 specific data - * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct @@ -1965,6 +2012,8 @@ enum netdev_reg_state { * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) + * @watchdog_lock: protect watchdog_ref_held + * @watchdog_ref_held: True if the watchdog device ref is taken. * @watchdog_timer: List of timers * * @proto_down_reason: reason a netdev interface is held down @@ -2117,7 +2166,7 @@ struct net_device { struct_group(priv_flags_fast, unsigned long priv_flags:32; unsigned long lltx:1; - unsigned long netmem_tx:1; + unsigned long netmem_tx:2; ); const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; @@ -2203,6 +2252,9 @@ struct net_device { struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; +#ifdef CONFIG_DEBUG_NET_SMALL_RTNL + struct list_head unreg_list_net; +#endif struct list_head close_list; struct list_head ptype_all; @@ -2296,6 +2348,13 @@ struct net_device { unsigned int promiscuity; unsigned int allmulti; bool uc_promisc; + struct list_head work_node; + netdevice_tracker work_tracker; + unsigned long work_pending; + unsigned long work_core_pending; + struct netdev_hw_addr_list rx_mode_addr_cache; + struct timer_list rx_mode_retry_timer; + unsigned int rx_mode_retry_count; #ifdef CONFIG_LOCKDEP unsigned char nested_level; #endif @@ -2315,12 +2374,6 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif -#if IS_ENABLED(CONFIG_ATALK) - void *atalk_ptr; -#endif -#if IS_ENABLED(CONFIG_AX25) - struct ax25_dev __rcu *ax25_ptr; -#endif #if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; #endif @@ -2377,6 +2430,8 @@ struct net_device { /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; int watchdog_timeo; + spinlock_t watchdog_lock; + bool watchdog_ref_held; u32 proto_down_reason; @@ -2557,13 +2612,23 @@ struct net_device { * Double protects: * @up, @moving_ns, @nd_net, @xdp_features * + * Ops protects: + * @cfg, @cfg_pending, @ethtool, @hwprov + * * Double ops protects: * @real_num_rx_queues, @real_num_tx_queues * * Also protects some fields in: * struct napi_struct, struct netdev_queue, struct netdev_rx_queue * - * Ordering: take after rtnl_lock. + * Ordering: + * + * - take after rtnl_lock + * + * - for the case of netdev queue leasing, the netdev-scope lock is + * taken for both the virtual and the physical device; to prevent + * deadlocks, the virtual device's lock must always be acquired + * before the physical device's (see netdev_nl_queue_create_doit) */ struct mutex lock; @@ -2607,16 +2672,16 @@ static inline bool netif_elide_gro(const struct net_device *dev) static inline int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) { - return dev->prio_tc_map[prio & TC_BITMASK]; + return READ_ONCE(dev->prio_tc_map[prio & TC_BITMASK]); } static inline int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) { - if (tc >= dev->num_tc) + if (tc >= READ_ONCE(dev->num_tc)) return -EINVAL; - dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; + WRITE_ONCE(dev->prio_tc_map[prio & TC_BITMASK], tc & TC_BITMASK); return 0; } @@ -2626,9 +2691,9 @@ int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline -int netdev_get_num_tc(struct net_device *dev) +int netdev_get_num_tc(const struct net_device *dev) { - return dev->num_tc; + return READ_ONCE(dev->num_tc); } static inline void net_prefetch(void *p) @@ -2655,7 +2720,7 @@ int netdev_bind_sb_channel_queue(struct net_device *dev, int netdev_set_sb_channel(struct net_device *dev, u16 channel); static inline int netdev_get_sb_channel(struct net_device *dev) { - return max_t(int, -dev->num_tc, 0); + return max_t(int, -READ_ONCE(dev->num_tc), 0); } static inline @@ -2765,6 +2830,17 @@ static inline void *netdev_priv(const struct net_device *dev) return (void *)dev->priv; } +/** + * netdev_from_priv() - get network device from priv + * @priv: network device private data + * + * Returns: net_device to which @priv belongs + */ +static inline struct net_device *netdev_from_priv(const void *priv) +{ + return container_of(priv, struct net_device, priv); +} + /* Set the sysfs physical device reference for the network logical device * if set prior to registration will cause a symlink during initialization. */ @@ -3345,7 +3421,6 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } -int netdev_boot_setup_check(struct net_device *dev); struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, @@ -3359,8 +3434,9 @@ void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); -int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, +int dev_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path_stack *stack); +void dev_fill_forward_path_release(struct net_device_path_stack *stack); struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); @@ -3404,11 +3480,32 @@ static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); +bool unregister_netdevice_queued(const struct net_device *dev); + static inline void unregister_netdevice(struct net_device *dev) { unregister_netdevice_queue(dev, NULL); } +#ifdef CONFIG_DEBUG_NET_SMALL_RTNL +void unregister_netdevice_queue_net(struct net *net, struct net_device *dev, + struct list_head *head); +void unregister_netdevice_many_net(struct net *net); +void unregister_netdevice_queue_many_net(struct net *net, struct list_head *head); +#else +static inline void unregister_netdevice_queue_net(struct net *net, + struct net_device *dev, + struct list_head *head) +{ + unregister_netdevice_queue(dev, head); +} + +static inline void unregister_netdevice_queue_many_net(struct net *net, + struct list_head *head) +{ +} +#endif + int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); @@ -3468,11 +3565,6 @@ static inline bool dev_validate_header(const struct net_device *dev, if (len < dev->min_header_len) return false; - if (capable(CAP_SYS_RAWIO)) { - memset(ll_header + len, 0, dev->hard_header_len - len); - return true; - } - if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); @@ -4986,6 +5078,14 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, int (*unsync)(struct net_device *, const unsigned char *)); void __hw_addr_init(struct netdev_hw_addr_list *list); +void __hw_addr_flush(struct netdev_hw_addr_list *list); +int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap, + const struct netdev_hw_addr_list *list, + int addr_len, struct netdev_hw_addr_list *cache); +void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list, + struct netdev_hw_addr_list *work, + struct netdev_hw_addr_list *ref, int addr_len, + struct netdev_hw_addr_list *cache); /* Functions used for device addresses handling */ void dev_addr_mod(struct net_device *dev, unsigned int offset, @@ -5095,6 +5195,7 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); +void netif_rx_mode_schedule_retry(struct net_device *dev); int netif_set_promiscuity(struct net_device *dev, int inc); int dev_set_promiscuity(struct net_device *dev, int inc); int netif_set_allmulti(struct net_device *dev, int inc, bool notify); @@ -5114,6 +5215,9 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); +void netdev_work_sched(struct net_device *dev, unsigned long events); +unsigned long netdev_work_cancel(struct net_device *dev, unsigned long mask); + enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, @@ -5339,9 +5443,9 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi } int netdev_class_create_file_ns(const struct class_attribute *class_attr, - const void *ns); + const struct ns_common *ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, - const void *ns); + const struct ns_common *ns); extern const struct kobj_ns_type_operations net_ns_type_operations; @@ -5569,10 +5673,7 @@ static inline bool netif_is_lag_port(const struct net_device *dev) return netif_is_bond_slave(dev) || netif_is_team_port(dev); } -static inline bool netif_is_rxfh_configured(const struct net_device *dev) -{ - return dev->priv_flags & IFF_RXFH_CONFIGURED; -} +bool netif_is_rxfh_configured(const struct net_device *dev); static inline bool netif_is_failover(const struct net_device *dev) { |