diff options
Diffstat (limited to 'include/linux/netdevice.h')
| -rw-r--r-- | include/linux/netdevice.h | 315 |
1 files changed, 134 insertions, 181 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e16a2a980ea8..f40f0ab3847a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -192,6 +192,7 @@ struct net_device_stats { #ifdef CONFIG_RPS #include <linux/static_key.h> extern struct static_key rps_needed; +extern struct static_key rfs_needed; #endif struct neighbour; @@ -316,7 +317,6 @@ struct napi_struct { unsigned int gro_count; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL - spinlock_t poll_lock; int poll_owner; #endif struct net_device *dev; @@ -334,6 +334,16 @@ enum { NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_HASHED, /* In NAPI hash (busy polling possible) */ NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ + NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ +}; + +enum { + NAPIF_STATE_SCHED = (1UL << NAPI_STATE_SCHED), + NAPIF_STATE_DISABLE = (1UL << NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = (1UL << NAPI_STATE_NPSVC), + NAPIF_STATE_HASHED = (1UL << NAPI_STATE_HASHED), + NAPIF_STATE_NO_BUSY_POLL = (1UL << NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = (1UL << NAPI_STATE_IN_BUSY_POLL), }; enum gro_result { @@ -342,6 +352,7 @@ enum gro_result { GRO_HELD, GRO_NORMAL, GRO_DROP, + GRO_CONSUMED, }; typedef enum gro_result gro_result_t; @@ -453,32 +464,21 @@ static inline bool napi_reschedule(struct napi_struct *napi) return false; } -void __napi_complete(struct napi_struct *n); -void napi_complete_done(struct napi_struct *n, int work_done); +bool napi_complete_done(struct napi_struct *n, int work_done); /** * napi_complete - NAPI processing complete * @n: NAPI context * * Mark NAPI processing as complete. * Consider using napi_complete_done() instead. + * Return false if device should avoid rearming interrupts. */ -static inline void napi_complete(struct napi_struct *n) +static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } /** - * napi_hash_add - add a NAPI to global hashtable - * @napi: NAPI context - * - * Generate a new napi_id and store a @napi under it in napi_hash. - * Used for busy polling (CONFIG_NET_RX_BUSY_POLL). - * Note: This is normally automatically done from netif_napi_add(), - * so might disappear in a future Linux version. - */ -void napi_hash_add(struct napi_struct *napi); - -/** * napi_hash_del - remove a NAPI from global table * @napi: NAPI context * @@ -732,8 +732,8 @@ struct xps_dev_maps { struct rcu_head rcu; struct xps_map __rcu *cpu_map[0]; }; -#define XPS_DEV_MAPS_SIZE (sizeof(struct xps_dev_maps) + \ - (nr_cpu_ids * sizeof(struct xps_map *))) +#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 @@ -803,6 +803,7 @@ struct tc_to_netdev { struct tc_cls_matchall_offload *cls_mall; struct tc_cls_bpf_offload *cls_bpf; }; + bool egress_dev; }; /* These structures hold the attributes of xdp state that are being passed @@ -865,11 +866,15 @@ struct netdev_xdp { * of useless work if you return NETDEV_TX_BUSY. * Required; cannot be NULL. * - * netdev_features_t (*ndo_fix_features)(struct net_device *dev, - * netdev_features_t features); - * Adjusts the requested feature flags according to device-specific - * constraints, and returns the resulting flags. Must not modify - * the device state. + * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, + * struct net_device *dev + * netdev_features_t features); + * Called by core transmit path to determine if device is capable of + * performing offload operations on a given packet. This is to give + * the device an opportunity to implement any restrictions that cannot + * be otherwise expressed by feature flags. The check is called with + * the set of features that the stack has calculated and it returns + * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * void *accel_priv, select_queue_fallback_t fallback); @@ -912,8 +917,8 @@ struct netdev_xdp { * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * - * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - * struct rtnl_link_stats64 *storage); + * void (*ndo_get_stats64)(struct net_device *dev, + * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: @@ -926,7 +931,7 @@ struct netdev_xdp { * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * - * bool (*ndo_has_offload_stats)(int attr_id) + * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id) * Return true if this device supports offload stats of this attr_id. * * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, @@ -963,11 +968,12 @@ struct netdev_xdp { * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); - * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) - * Called to setup 'tc' number of traffic classes in the net device. This - * is always called from the stack with the rtnl lock held and netif tx - * queues stopped. This allows the netdevice to perform queue management - * safely. + * int (*ndo_setup_tc)(struct net_device *dev, u32 handle, + * __be16 protocol, struct tc_to_netdev *tc); + * Called to setup any 'tc' scheduler, classifier or action on @dev. + * This is always called from the stack with the rtnl lock held and netif + * tx queues stopped. This allows the netdevice to perform queue + * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); @@ -1027,6 +1033,12 @@ struct netdev_xdp { * Called to release previously enslaved netdev. * * Feature/offload setting functions. + * netdev_features_t (*ndo_fix_features)(struct net_device *dev, + * netdev_features_t features); + * Adjusts the requested feature flags according to device-specific + * constraints, and returns the resulting flags. Must not modify + * the device state. + * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). @@ -1099,15 +1111,6 @@ struct netdev_xdp { * Callback to use for xmit over the accelerated station. This * is used in place of ndo_start_xmit on accelerated net * devices. - * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, - * struct net_device *dev - * netdev_features_t features); - * Called by core transmit path to determine if device is capable of - * performing offload operations on a given packet. This is to give - * the device an opportunity to implement any restrictions that cannot - * be otherwise expressed by feature flags. The check is called with - * the set of features that the stack has calculated and it returns - * those the driver believes to be appropriate. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific @@ -1164,9 +1167,9 @@ struct net_device_ops { struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev); - struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev, - struct rtnl_link_stats64 *storage); - bool (*ndo_has_offload_stats)(int attr_id); + void (*ndo_get_stats64)(struct net_device *dev, + struct rtnl_link_stats64 *storage); + bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, void *attr_data); @@ -1182,9 +1185,6 @@ struct net_device_ops { struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif -#ifdef CONFIG_NET_RX_BUSY_POLL - int (*ndo_busy_poll)(struct napi_struct *dev); -#endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, @@ -1456,7 +1456,6 @@ enum netdev_priv_flags { * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding - * @all_adj_list: All linked devices, *including* neighbours * @features: Currently active device features * @hw_features: User-changeable features * @@ -1506,8 +1505,11 @@ enum netdev_priv_flags { * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value + * @min_mtu: Interface Minimum MTU value + * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. + * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -1549,7 +1551,6 @@ enum netdev_priv_flags { * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * - * @last_rx: Time of last Rx * @dev_addr: Hw address (before bcast, * because most packets are unicast) * @@ -1673,11 +1674,6 @@ struct net_device { struct list_head lower; } adj_list; - struct { - struct list_head upper; - struct list_head lower; - } all_adj_list; - netdev_features_t features; netdev_features_t hw_features; netdev_features_t wanted_features; @@ -1726,8 +1722,11 @@ struct net_device { unsigned char dma; unsigned int mtu; + unsigned int min_mtu; + unsigned int max_mtu; unsigned short type; unsigned short hard_header_len; + unsigned short min_header_len; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1778,8 +1777,6 @@ struct net_device { /* * Cache lines mostly used on receive path (including eth_type_trans()) */ - unsigned long last_rx; - /* Interface address info used in eth_type_trans() */ unsigned char *dev_addr; @@ -1869,8 +1866,12 @@ struct net_device { struct pcpu_vstats __percpu *vstats; }; +#if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; +#endif +#if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; +#endif struct device dev; const struct attribute_group *sysfs_groups[4]; @@ -1922,34 +1923,10 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) return 0; } -static inline -void netdev_reset_tc(struct net_device *dev) -{ - dev->num_tc = 0; - memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); - memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); -} - -static inline -int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) -{ - if (tc >= dev->num_tc) - return -EINVAL; - - dev->tc_to_txq[tc].count = count; - dev->tc_to_txq[tc].offset = offset; - return 0; -} - -static inline -int netdev_set_num_tc(struct net_device *dev, u8 num_tc) -{ - if (num_tc > TC_MAX_QUEUE) - return -EINVAL; - - dev->num_tc = num_tc; - return 0; -} +int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); +void netdev_reset_tc(struct net_device *dev); +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) @@ -2502,14 +2479,19 @@ static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) return NAPI_GRO_CB(skb)->frag0_len < hlen; } +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, unsigned int offset) { if (!pskb_may_pull(skb, hlen)) return NULL; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; + skb_gro_frag0_invalidate(skb); return skb->data + offset; } @@ -2686,70 +2668,18 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, remcsum_unadjust((__sum16 *)ptr, grc->delta); } -struct skb_csum_offl_spec { - __u16 ipv4_okay:1, - ipv6_okay:1, - encap_okay:1, - ip_options_okay:1, - ext_hdrs_okay:1, - tcp_okay:1, - udp_okay:1, - sctp_okay:1, - vlan_okay:1, - no_encapped_ipv6:1, - no_not_encapped:1; -}; - -bool __skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help); - -static inline bool skb_csum_offload_chk(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec, - bool *csum_encapped, - bool csum_help) -{ - if (skb->ip_summed != CHECKSUM_PARTIAL) - return false; - - return __skb_csum_offload_chk(skb, spec, csum_encapped, csum_help); -} - -static inline bool skb_csum_offload_chk_help(struct sk_buff *skb, - const struct skb_csum_offl_spec *spec) +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { - bool csum_encapped; - - return skb_csum_offload_chk(skb, spec, &csum_encapped, true); + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; } - -static inline bool skb_csum_off_chk_help_cmn(struct sk_buff *skb) -{ - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .ipv6_okay = 1, - .vlan_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); -} - -static inline bool skb_csum_off_chk_help_cmn_v4_only(struct sk_buff *skb) +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) { - static const struct skb_csum_offl_spec csum_offl_spec = { - .ipv4_okay = 1, - .ip_options_okay = 1, - .tcp_okay = 1, - .udp_okay = 1, - .vlan_okay = 1, - }; - - return skb_csum_offload_chk_help(skb, &csum_offl_spec); + NAPI_GRO_CB(skb)->flush |= flush; } +#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -2778,6 +2708,8 @@ static inline bool dev_validate_header(const struct net_device *dev, { if (likely(len >= dev->hard_header_len)) return true; + if (len < dev->min_header_len) + return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); @@ -3191,7 +3123,19 @@ static inline bool netif_subqueue_stopped(const struct net_device *dev, return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } -void netif_wake_subqueue(struct net_device *dev, u16 queue_index); +/** + * netif_wake_subqueue - allow sending packets on subqueue + * @dev: network device + * @queue_index: sub queue index + * + * Resume individual transmit queue of a device with multiple transmit queues. + */ +static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) +{ + struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); + + netif_tx_wake_queue(txq); +} #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, @@ -3345,7 +3289,7 @@ int dev_get_phys_port_id(struct net_device *dev, int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_xdp_fd(struct net_device *dev, int fd); +int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); @@ -3554,6 +3498,17 @@ static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) txq->xmit_lock_owner = cpu; } +static inline bool __netif_tx_acquire(struct netdev_queue *txq) +{ + __acquire(&txq->_xmit_lock); + return true; +} + +static inline void __netif_tx_release(struct netdev_queue *txq) +{ + __release(&txq->_xmit_lock); +} + static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); @@ -3655,17 +3610,21 @@ static inline void netif_tx_unlock_bh(struct net_device *dev) #define HARD_TX_LOCK(dev, txq, cpu) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_lock(txq, cpu); \ + } else { \ + __netif_tx_acquire(txq); \ } \ } #define HARD_TX_TRYLOCK(dev, txq) \ (((dev->features & NETIF_F_LLTX) == 0) ? \ __netif_tx_trylock(txq) : \ - true ) + __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ + } else { \ + __netif_tx_release(txq); \ } \ } @@ -3870,6 +3829,10 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, extern int netdev_max_backlog; extern int netdev_tstamp_prequeue; extern int weight_p; +extern int dev_weight_rx_bias; +extern int dev_weight_tx_bias; +extern int dev_rx_weight; +extern int dev_tx_weight; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, @@ -3884,12 +3847,13 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) -/* iterate through upper list, must be called under RCU read lock */ -#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \ - for (iter = &(dev)->all_adj_list.upper, \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \ - updev; \ - updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter))) +int netdev_walk_all_upper_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *upper_dev, + void *data), + void *data); + +bool netdev_has_upper_dev_all_rcu(struct net_device *dev, + struct net_device *upper_dev); void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); @@ -3922,17 +3886,14 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, struct list_head **iter); -#define netdev_for_each_all_lower_dev(dev, ldev, iter) \ - for (iter = (dev)->all_adj_list.lower.next, \ - ldev = netdev_all_lower_get_next(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next(dev, &(iter))) - -#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \ - for (iter = &(dev)->all_adj_list.lower, \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \ - ldev; \ - ldev = netdev_all_lower_get_next_rcu(dev, &(iter))) +int netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *lower_dev, + void *data), + void *data); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); @@ -3949,10 +3910,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); -int netdev_default_l2upper_neigh_construct(struct net_device *dev, - struct neighbour *n); -void netdev_default_l2upper_neigh_destroy(struct net_device *dev, - struct neighbour *n); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 @@ -4009,19 +3966,6 @@ static inline bool can_checksum_protocol(netdev_features_t features, } } -/* Map an ethertype into IP protocol if possible */ -static inline int eproto_to_ipproto(int eproto) -{ - switch (eproto) { - case htons(ETH_P_IP): - return IPPROTO_IP; - case htons(ETH_P_IPV6): - return IPPROTO_IPV6; - default: - return -1; - } -} - #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev); #else @@ -4418,6 +4362,15 @@ do { \ }) #endif +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + #if defined(VERBOSE_DEBUG) #define netif_vdbg netif_dbg #else |