diff options
Diffstat (limited to 'include/linux/netdevice.h')
-rw-r--r-- | include/linux/netdevice.h | 321 |
1 files changed, 266 insertions, 55 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf44503ea81a..ca5ab98053c8 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -302,6 +302,17 @@ struct netdev_boot_setup { int __init netdev_boot_setup(char *str); +struct gro_list { + struct list_head list; + int count; +}; + +/* + * size of gro hash buckets, must less than bit number of + * napi_struct::gro_bitmask + */ +#define GRO_HASH_BUCKETS 8 + /* * Structure for NAPI scheduling similar to tasklet but with weighting */ @@ -316,13 +327,13 @@ struct napi_struct { unsigned long state; int weight; - unsigned int gro_count; + unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL int poll_owner; #endif struct net_device *dev; - struct sk_buff *gro_list; + struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct hrtimer timer; struct list_head dev_list; @@ -569,6 +580,9 @@ struct netdev_queue { * (/sys/class/net/DEV/Q/trans_timeout) */ unsigned long trans_timeout; + + /* Subordinate device that the queue has been assigned to */ + struct net_device *sb_dev; /* * write-mostly part */ @@ -730,10 +744,15 @@ struct xps_map { */ struct xps_dev_maps { struct rcu_head rcu; - struct xps_map __rcu *cpu_map[0]; + struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */ }; -#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ + +#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) + +#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ + (_rxqs * (_tcs) * sizeof(struct xps_map *))) + #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 @@ -779,7 +798,8 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + struct net_device *sb_dev); enum tc_setup_type { TC_SETUP_QDISC_MQPRIO, @@ -791,6 +811,8 @@ enum tc_setup_type { TC_SETUP_QDISC_CBS, TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, + TC_SETUP_QDISC_MQ, + TC_SETUP_QDISC_ETF, }; /* These structures hold the attributes of bpf state that are being passed @@ -806,21 +828,21 @@ enum bpf_netdev_command { */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, - /* Check if a bpf program is set on the device. The callee should - * set @prog_attached to one of XDP_ATTACHED_* values, note that "true" - * is equivalent to XDP_ATTACHED_DRV. - */ XDP_QUERY_PROG, + XDP_QUERY_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_VERIFIER_PREP, BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY, BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, + XDP_QUERY_XSK_UMEM, + XDP_SETUP_XSK_UMEM, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; +struct xdp_umem; struct netdev_bpf { enum bpf_netdev_command command; @@ -831,9 +853,8 @@ struct netdev_bpf { struct bpf_prog *prog; struct netlink_ext_ack *extack; }; - /* XDP_QUERY_PROG */ + /* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */ struct { - u8 prog_attached; u32 prog_id; /* flags with which program was installed */ u32 prog_flags; @@ -851,6 +872,11 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; + /* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ + struct { + struct xdp_umem *umem; /* out for query*/ + u16 queue_id; /* in for query */ + } xsk; }; }; @@ -865,6 +891,28 @@ struct xfrmdev_ops { }; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) +enum tls_offload_ctx_dir { + TLS_OFFLOAD_CTX_DIR_RX, + TLS_OFFLOAD_CTX_DIR_TX, +}; + +struct tls_crypto_info; +struct tls_context; + +struct tlsdev_ops { + int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn); + void (*tls_dev_del)(struct net_device *netdev, + struct tls_context *ctx, + enum tls_offload_ctx_dir direction); + void (*tls_dev_resync_rx)(struct net_device *netdev, + struct sock *sk, u32 seq, u64 rcd_sn); +}; +#endif + struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; @@ -913,7 +961,8 @@ struct dev_ifalias { * 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); + * struct net_device *sb_dev, + * select_queue_fallback_t fallback); * Called to decide which queue to use when device supports multiple * transmit queues. * @@ -1165,12 +1214,13 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); - * This function is used to submit a XDP packet for transmit on a - * netdevice. - * void (*ndo_xdp_flush)(struct net_device *dev); - * This function is used to inform the driver to flush a particular - * xdp tx queue. Must be called on same CPU as xdp_xmit. + * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, + * u32 flags); + * This function is used to submit @n XDP packets for transmit on a + * netdevice. Returns number of frames successfully transmitted, frames + * that got dropped are freed/returned via xdp_return_frame(). + * Returns negative number, means general error invoking ndo, meaning + * no frames were xmit'ed and core-caller will free all frames. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1184,7 +1234,7 @@ struct net_device_ops { netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, + struct net_device *sb_dev, select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); @@ -1355,9 +1405,11 @@ struct net_device_ops { int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); - int (*ndo_xdp_xmit)(struct net_device *dev, - struct xdp_buff *xdp); - void (*ndo_xdp_flush)(struct net_device *dev); + int (*ndo_xdp_xmit)(struct net_device *dev, int n, + struct xdp_frame **xdp, + u32 flags); + int (*ndo_xsk_async_xmit)(struct net_device *dev, + u32 queue_id); }; /** @@ -1401,6 +1453,8 @@ struct net_device_ops { * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook + * @IFF_FAILOVER: device is a failover master device + * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1430,6 +1484,8 @@ enum netdev_priv_flags { IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, + IFF_FAILOVER = 1<<27, + IFF_FAILOVER_SLAVE = 1<<28, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1458,6 +1514,8 @@ enum netdev_priv_flags { #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER +#define IFF_FAILOVER IFF_FAILOVER +#define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE /** * struct net_device - The DEVICE structure. @@ -1750,6 +1808,10 @@ struct net_device { const struct xfrmdev_ops *xfrmdev_ops; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) + const struct tlsdev_ops *tlsdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; @@ -1867,7 +1929,8 @@ struct net_device { int watchdog_timeo; #ifdef CONFIG_XPS - struct xps_dev_maps __rcu *xps_maps; + struct xps_dev_maps __rcu *xps_cpus_map; + struct xps_dev_maps __rcu *xps_rxqs_map; #endif #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; @@ -1936,7 +1999,7 @@ struct net_device { #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif - u8 num_tc; + s16 num_tc; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; u8 prio_tc_map[TC_BITMASK + 1]; @@ -1990,6 +2053,17 @@ int netdev_get_num_tc(struct net_device *dev) return dev->num_tc; } +void netdev_unbind_sb_channel(struct net_device *dev, + struct net_device *sb_dev); +int netdev_bind_sb_channel_queue(struct net_device *dev, + struct net_device *sb_dev, + u8 tc, u16 count, u16 offset); +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); +} + static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) @@ -2034,7 +2108,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev @@ -2213,10 +2287,10 @@ static inline int gro_recursion_inc_test(struct sk_buff *skb) return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; } -typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); -static inline struct sk_buff **call_gro_receive(gro_receive_t cb, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2226,12 +2300,12 @@ static inline struct sk_buff **call_gro_receive(gro_receive_t cb, return cb(head, skb); } -typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **, - struct sk_buff *); -static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct sk_buff **head, - struct sk_buff *skb) +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) { if (unlikely(gro_recursion_inc_test(skb))) { NAPI_GRO_CB(skb)->flush |= 1; @@ -2248,6 +2322,9 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); + void (*list_func) (struct list_head *, + struct packet_type *, + struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); void *af_packet_priv; @@ -2257,8 +2334,8 @@ struct packet_type { struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); - struct sk_buff **(*gro_receive)(struct sk_buff **head, - struct sk_buff *skb); + struct sk_buff *(*gro_receive)(struct list_head *head, + struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; @@ -2304,8 +2381,19 @@ enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_HASH, }; +enum netdev_lag_hash { + NETDEV_LAG_HASH_NONE, + NETDEV_LAG_HASH_L2, + NETDEV_LAG_HASH_L34, + NETDEV_LAG_HASH_L23, + NETDEV_LAG_HASH_E23, + NETDEV_LAG_HASH_E34, + NETDEV_LAG_HASH_UNKNOWN, +}; + struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; + enum netdev_lag_hash hash_type; }; struct netdev_lag_lower_state_info { @@ -2484,8 +2572,15 @@ void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); +u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); int dev_queue_xmit(struct sk_buff *skb); -int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev); +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); @@ -2514,7 +2609,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb); +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); static inline unsigned int skb_gro_offset(const struct sk_buff *skb) { @@ -2730,16 +2825,36 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, } #ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { if (PTR_ERR(pp) != -EINPROGRESS) NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} #else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush) +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) { NAPI_GRO_CB(skb)->flush |= flush; } +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} #endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, @@ -3204,6 +3319,92 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); +int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, + u16 index, bool is_rxqs_map); + +/** + * netif_attr_test_mask - Test a CPU or Rx queue set in a mask + * @j: CPU/Rx queue index + * @mask: bitmask of all cpus/rx queues + * @nr_bits: number of bits in the bitmask + * + * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. + */ +static inline bool netif_attr_test_mask(unsigned long j, + const unsigned long *mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + return test_bit(j, mask); +} + +/** + * netif_attr_test_online - Test for online CPU/Rx queue + * @j: CPU/Rx queue index + * @online_mask: bitmask for CPUs/Rx queues that are online + * @nr_bits: number of bits in the bitmask + * + * Returns true if a CPU/Rx queue is online. + */ +static inline bool netif_attr_test_online(unsigned long j, + const unsigned long *online_mask, + unsigned int nr_bits) +{ + cpu_max_bits_warn(j, nr_bits); + + if (online_mask) + return test_bit(j, online_mask); + + return (j < nr_bits); +} + +/** + * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask + * @n: CPU/Rx queue index + * @srcp: the cpumask/Rx queue mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set. + */ +static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (srcp) + return find_next_bit(srcp, nr_bits, n + 1); + + return n + 1; +} + +/** + * netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p + * @n: CPU/Rx queue index + * @src1p: the first CPUs/Rx queues mask pointer + * @src2p: the second CPUs/Rx queues mask pointer + * @nr_bits: number of bits in the bitmask + * + * Returns >= nr_bits if no further CPUs/Rx queues set in both. + */ +static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, + const unsigned long *src2p, + unsigned int nr_bits) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); + + if (src1p && src2p) + return find_next_and_bit(src1p, src2p, nr_bits, n + 1); + else if (src1p) + return find_next_bit(src1p, nr_bits, n + 1); + else if (src2p) + return find_next_bit(src2p, nr_bits, n + 1); + + return n + 1; +} #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, @@ -3211,20 +3412,14 @@ static inline int netif_set_xps_queue(struct net_device *dev, { return 0; } -#endif -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - -/* - * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used - * as a distribution range limit for the returned value. - */ -static inline u16 skb_tx_hash(const struct net_device *dev, - struct sk_buff *skb) +static inline int __netif_set_xps_queue(struct net_device *dev, + const unsigned long *mask, + u16 index, bool is_rxqs_map) { - return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); + return 0; } +#endif /** * netif_is_multiqueue - test if device has multiple transmit queues @@ -3243,8 +3438,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, - unsigned int rxq) + unsigned int rxqs) { + dev->real_num_rx_queues = rxqs; return 0; } #endif @@ -3323,6 +3519,7 @@ int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); @@ -3357,6 +3554,8 @@ int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int dev_change_net_namespace(struct net_device *, struct net *, const char *); int __dev_set_mtu(struct net_device *, int); +int dev_set_mtu_ext(struct net_device *dev, int mtu, + struct netlink_ext_ack *extack); int dev_set_mtu(struct net_device *, int); int dev_change_tx_queue_len(struct net_device *, unsigned long); void dev_set_group(struct net_device *, int); @@ -3374,8 +3573,9 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf); int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, u32 flags); -void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, - struct netdev_bpf *xdp); +u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op, + enum bpf_netdev_command cmd); +int xdp_umem_query(struct net_device *dev, u16 queue_id); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); @@ -4186,6 +4386,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } @@ -4308,6 +4509,16 @@ static inline bool netif_is_rxfh_configured(const struct net_device *dev) return dev->priv_flags & IFF_RXFH_CONFIGURED; } +static inline bool netif_is_failover(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER; +} + +static inline bool netif_is_failover_slave(const struct net_device *dev) +{ + return dev->priv_flags & IFF_FAILOVER_SLAVE; +} + /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { |