diff options
Diffstat (limited to 'include')
77 files changed, 2051 insertions, 1216 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b69e7a5869ff..39229c455cba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -117,35 +117,25 @@ enum bpf_access_type { }; /* types of values stored in eBPF registers */ +/* Pointer types represent: + * pointer + * pointer + imm + * pointer + (u16) var + * pointer + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) means that 'imm' was added + */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, + PTR_TO_STACK, /* reg == frame_pointer + offset */ + PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ - - /* PTR_TO_MAP_VALUE_ADJ is used for doing pointer math inside of a map - * elem value. We only allow this if we can statically verify that - * access from this register are going to fall within the size of the - * map element. - */ - PTR_TO_MAP_VALUE_ADJ, }; struct bpf_prog; @@ -318,6 +308,12 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); + +/* Map specifics */ +struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); +void __dev_map_insert_ctx(struct bpf_map *map, u32 index); +void __dev_map_flush(struct bpf_map *map); + #else static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -356,6 +352,20 @@ static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } + +static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index) +{ +} + +static inline void __dev_map_flush(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ /* verifier prototypes for helper functions called from eBPF programs */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 3d137c33d664..b1e1035ca24b 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -35,3 +35,6 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) +#ifdef CONFIG_NET +BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) +#endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 8e5d31f6faef..91d07efed2ba 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -9,41 +9,62 @@ #include <linux/bpf.h> /* for enum bpf_reg_type */ #include <linux/filter.h> /* for MAX_BPF_STACK */ +#include <linux/tnum.h> - /* Just some arbitrary values so we can safely do math without overflowing and - * are obviously wrong for any sort of memory access. - */ -#define BPF_REGISTER_MAX_RANGE (1024 * 1024 * 1024) -#define BPF_REGISTER_MIN_RANGE -1 +/* Maximum variable offset umax_value permitted when resolving memory accesses. + * In practice this is far bigger than any realistic pointer offset; this limit + * ensures that umax_value + (int)off + (int)size cannot overflow a u64. + */ +#define BPF_MAX_VAR_OFF (1ULL << 31) +/* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures + * that converting umax_value to int cannot overflow. + */ +#define BPF_MAX_VAR_SIZ INT_MAX + +enum bpf_reg_liveness { + REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */ + REG_LIVE_READ, /* reg was read, so we're sensitive to initial value */ + REG_LIVE_WRITTEN, /* reg was written first, screening off later reads */ +}; struct bpf_reg_state { enum bpf_reg_type type; union { - /* valid when type == CONST_IMM | PTR_TO_STACK | UNKNOWN_VALUE */ - s64 imm; - - /* valid when type == PTR_TO_PACKET* */ - struct { - u16 off; - u16 range; - }; + /* valid when type == PTR_TO_PACKET */ + u16 range; /* valid when type == CONST_PTR_TO_MAP | PTR_TO_MAP_VALUE | * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; }; + /* Fixed part of pointer offset, pointer types only */ + s32 off; + /* For PTR_TO_PACKET, used to find other pointers with the same variable + * offset, so they can share range knowledge. + * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we + * came from, when one is tested for != NULL. + */ u32 id; + /* Ordering of fields matters. See states_equal() */ + /* For scalar types (SCALAR_VALUE), this represents our knowledge of + * the actual value. + * For pointer types, this represents the variable part of the offset + * from the pointed-to object, and is shared with all bpf_reg_states + * with the same id as us. + */ + struct tnum var_off; /* Used to determine if any memory access using this register will - * result in a bad access. These two fields must be last. - * See states_equal() + * result in a bad access. + * These refer to the same value as var_off, not necessarily the actual + * contents of the register. */ - s64 min_value; - u64 max_value; - u32 min_align; - u32 aux_off; - u32 aux_off_align; - bool value_from_signed; + s64 smin_value; /* minimum possible (s64)value */ + s64 smax_value; /* maximum possible (s64)value */ + u64 umin_value; /* minimum possible (u64)value */ + u64 umax_value; /* maximum possible (u64)value */ + /* This field must be last, for states_equal() reasons. */ + enum bpf_reg_liveness live; }; enum bpf_stack_slot_type { @@ -61,6 +82,7 @@ struct bpf_verifier_state { struct bpf_reg_state regs[MAX_BPF_REG]; u8 stack_slot_type[MAX_BPF_STACK]; struct bpf_reg_state spilled_regs[MAX_BPF_STACK / BPF_REG_SIZE]; + struct bpf_verifier_state *parent; }; /* linked list of verifier states used to prune search */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 83cc9863444b..afdbb701fdb4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -374,5 +374,9 @@ struct ethtool_ops { struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); + int (*get_fecparam)(struct net_device *, + struct ethtool_fecparam *); + int (*set_fecparam)(struct net_device *, + struct ethtool_fecparam *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index bfef1e5734f8..d19ed3c15e1e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -711,7 +711,21 @@ bool bpf_helper_changes_pkt_data(void *func); struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); + +/* The pair of xdp_do_redirect and xdp_do_flush_map MUST be called in the + * same cpu context. Further for best results no more than a single map + * for the do_redirect/do_flush pair should be used. This limitation is + * because we only track one map and force a flush when the map changes. + * This does not appear to be a real limitation for existing software. + */ +int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb); +int xdp_do_redirect(struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *prog); +void xdp_do_flush_map(void); + void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_redirect(u32 ifindex); #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 97caf1821de8..f8231854b5d6 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -118,7 +118,8 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen); extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); -extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); +extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, + int dif, int sdif); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 474d6bbc158c..ac2da4e11d5e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -159,6 +159,16 @@ static inline bool inet6_is_jumbogram(const struct sk_buff *skb) } /* can not be used in TCP layer after tcp_v6_fill_cb */ +static inline int inet6_sdif(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv6_l3mdev_skb(IP6CB(skb)->flags)) + return IP6CB(skb)->iif; +#endif + return 0; +} + +/* can not be used in TCP layer after tcp_v6_fill_cb */ static inline bool inet6_exact_dif_match(struct net *net, struct sk_buff *skb) { #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..d26f18b39c4a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -550,6 +550,7 @@ struct mlx5_fc_stats { unsigned long sampling_interval; /* jiffies */ }; +struct mlx5_mpfs; struct mlx5_eswitch; struct mlx5_lag; struct mlx5_pagefault; @@ -646,7 +647,11 @@ struct mlx5_priv { struct list_head ctx_list; spinlock_t ctx_lock; + struct list_head waiting_events_list; + bool is_accum_events; + struct mlx5_flow_steering *steering; + struct mlx5_mpfs *mpfs; struct mlx5_eswitch *eswitch; struct mlx5_core_sriov sriov; struct mlx5_lag *lag; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3030121b4746..c99daffc3c3c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -963,7 +963,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_2a0[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_at_2c0[0x10]; + u8 max_flow_counter_31_16[0x10]; u8 max_wqe_sz_sq_dc[0x10]; u8 reserved_at_2e0[0x7]; @@ -981,7 +981,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_340[0x8]; u8 log_max_flow_counter_bulk[0x8]; - u8 max_flow_counter[0x10]; + u8 max_flow_counter_15_0[0x10]; u8 reserved_at_360[0x3]; @@ -1071,9 +1071,7 @@ struct mlx5_ifc_dest_format_struct_bits { }; struct mlx5_ifc_flow_counter_list_bits { - u8 clear[0x1]; - u8 num_of_counters[0xf]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_20[0x20]; }; @@ -4403,8 +4401,7 @@ struct mlx5_ifc_query_flow_counter_in_bits { u8 reserved_at_c1[0xf]; u8 num_of_counters[0x10]; - u8 reserved_at_e0[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { @@ -6272,8 +6269,7 @@ struct mlx5_ifc_dealloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; @@ -7098,8 +7094,7 @@ struct mlx5_ifc_alloc_flow_counter_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; - u8 flow_counter_id[0x10]; + u8 flow_counter_id[0x20]; u8 reserved_at_60[0x20]; }; diff --git a/include/linux/net.h b/include/linux/net.h index ebeb48c92005..d97d80d7fdf8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -190,8 +190,16 @@ struct proto_ops { struct pipe_inode_info *pipe, size_t len, unsigned int flags); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); + + /* The following functions are called internally by kernel with + * sock lock already held. + */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); + int (*sendpage_locked)(struct sock *sk, struct page *page, + int offset, size_t size, int flags); + int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, + size_t size); }; #define DECLARE_SOCKADDR(type, dst, src) \ @@ -279,6 +287,8 @@ do { \ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); +int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, + struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); @@ -297,6 +307,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 1d4737cffc71..dc8b4896b77b 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -36,7 +36,6 @@ enum { /**/NETIF_F_GSO_SHIFT, /* keep the order of SKB_GSO_* bits */ NETIF_F_TSO_BIT /* ... TCPv4 segmentation */ = NETIF_F_GSO_SHIFT, - NETIF_F_UFO_BIT, /* ... UDPv4 fragmentation */ NETIF_F_GSO_ROBUST_BIT, /* ... ->SKB_GSO_DODGY */ NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO_MANGLEID_BIT, /* ... IPV4 ID mangling allowed */ @@ -76,6 +75,7 @@ enum { NETIF_F_HW_TC_BIT, /* Offload TC infrastructure */ NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ + NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ /* * Add your fresh new feature above and remember to update @@ -118,7 +118,6 @@ enum { #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) #define NETIF_F_TSO __NETIF_F(TSO) -#define NETIF_F_UFO __NETIF_F(UFO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) @@ -140,6 +139,7 @@ enum { #define NETIF_F_HW_TC __NETIF_F(HW_TC) #define NETIF_F_HW_ESP __NETIF_F(HW_ESP) #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) +#define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) @@ -172,7 +172,7 @@ enum { NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_UFO | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ NETIF_F_GSO_SCTP) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 779b23595596..0f1c4cb2441e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -66,6 +66,7 @@ struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct bpf_prog; +struct xdp_buff; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -770,31 +771,14 @@ 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); -/* These structures hold the attributes of qdisc and classifiers - * that are being passed to the netdevice through the setup_tc op. - */ -enum { +enum tc_setup_type { TC_SETUP_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, - TC_SETUP_MATCHALL, + TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, }; -struct tc_cls_u32_offload; - -struct tc_to_netdev { - unsigned int type; - union { - struct tc_cls_u32_offload *cls_u32; - struct tc_cls_flower_offload *cls_flower; - struct tc_cls_matchall_offload *cls_mall; - struct tc_cls_bpf_offload *cls_bpf; - struct tc_mqprio_qopt *mqprio; - }; - bool egress_dev; -}; - /* These structures hold the attributes of xdp state that are being passed * to the netdevice through the xdp op. */ @@ -977,8 +961,8 @@ struct xfrmdev_ops { * 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, u32 handle, u32 chain_index, - * __be16 protocol, struct tc_to_netdev *tc); + * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, + * void *type_data); * 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 @@ -1138,7 +1122,12 @@ struct xfrmdev_ops { * int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); * This function is used to set or query state related to XDP on the * netdevice. See definition of enum xdp_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 paticular + * xpd tx queue. Must be called on same CPU as xdp_xmit. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1221,9 +1210,8 @@ struct net_device_ops { struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, - u32 handle, u32 chain_index, - __be16 protocol, - struct tc_to_netdev *tc); + enum tc_setup_type type, + void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -1323,6 +1311,9 @@ struct net_device_ops { int needed_headroom); int (*ndo_xdp)(struct net_device *dev, struct netdev_xdp *xdp); + int (*ndo_xdp_xmit)(struct net_device *dev, + struct xdp_buff *xdp); + void (*ndo_xdp_flush)(struct net_device *dev); }; /** @@ -2308,6 +2299,7 @@ struct netdev_lag_lower_state_info { #define NETDEV_PRECHANGEUPPER 0x001A #define NETDEV_CHANGELOWERSTATE 0x001B #define NETDEV_UDP_TUNNEL_PUSH_INFO 0x001C +#define NETDEV_UDP_TUNNEL_DROP_INFO 0x001D #define NETDEV_CHANGE_TX_QUEUE_LEN 0x001E int register_netdevice_notifier(struct notifier_block *nb); @@ -2423,8 +2415,8 @@ 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); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev); -int dev_close(struct net_device *dev); -int dev_close_many(struct list_head *head, bool unlink); +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); int dev_queue_xmit(struct sk_buff *skb); @@ -3251,6 +3243,8 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) __dev_kfree_skb_any(skb, SKB_REASON_CONSUMED); } +void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); +int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb); int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); @@ -4089,7 +4083,6 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); - BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); diff --git a/include/linux/phy.h b/include/linux/phy.h index 0bb5b212ab42..d78cd01ea513 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -182,6 +182,7 @@ static inline const char *phy_modes(phy_interface_t interface) #define MII_ADDR_C45 (1<<30) struct device; +struct phylink; struct sk_buff; /* @@ -469,11 +470,13 @@ struct phy_device { struct mutex lock; + struct phylink *phylink; struct net_device *attached_dev; u8 mdix; u8 mdix_ctrl; + void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); }; #define to_phy_device(d) container_of(to_mdio_device(d), \ @@ -667,6 +670,24 @@ struct phy_fixup { int (*run)(struct phy_device *phydev); }; +const char *phy_speed_to_str(int speed); +const char *phy_duplex_to_str(unsigned int duplex); + +/* A structure for mapping a particular speed and duplex + * combination to a particular SUPPORTED and ADVERTISED value + */ +struct phy_setting { + u32 speed; + u8 duplex; + u8 bit; +}; + +const struct phy_setting * +phy_lookup_setting(int speed, int duplex, const unsigned long *mask, + size_t maxbit, bool exact); +size_t phy_speeds(unsigned int *speeds, size_t size, + unsigned long *mask, size_t maxbit); + /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. diff --git a/include/linux/phylink.h b/include/linux/phylink.h new file mode 100644 index 000000000000..af67edd4ae38 --- /dev/null +++ b/include/linux/phylink.h @@ -0,0 +1,148 @@ +#ifndef NETDEV_PCS_H +#define NETDEV_PCS_H + +#include <linux/phy.h> +#include <linux/spinlock.h> +#include <linux/workqueue.h> + +struct device_node; +struct ethtool_cmd; +struct net_device; + +enum { + MLO_PAUSE_NONE, + MLO_PAUSE_ASYM = BIT(0), + MLO_PAUSE_SYM = BIT(1), + MLO_PAUSE_RX = BIT(2), + MLO_PAUSE_TX = BIT(3), + MLO_PAUSE_TXRX_MASK = MLO_PAUSE_TX | MLO_PAUSE_RX, + MLO_PAUSE_AN = BIT(4), + + MLO_AN_PHY = 0, /* Conventional PHY */ + MLO_AN_FIXED, /* Fixed-link mode */ + MLO_AN_SGMII, /* Cisco SGMII protocol */ + MLO_AN_8023Z, /* 1000base-X protocol */ +}; + +static inline bool phylink_autoneg_inband(unsigned int mode) +{ + return mode == MLO_AN_SGMII || mode == MLO_AN_8023Z; +} + +struct phylink_link_state { + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); + __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); + phy_interface_t interface; /* PHY_INTERFACE_xxx */ + int speed; + int duplex; + int pause; + unsigned int link:1; + unsigned int an_enabled:1; + unsigned int an_complete:1; +}; + +struct phylink_mac_ops { + /** + * validate: validate and update the link configuration + * @ndev: net_device structure associated with MAC + * @config: configuration to validate + * + * Update the %config->supported and %config->advertised masks + * clearing bits that can not be supported. + * + * Note: the PHY may be able to transform from one connection + * technology to another, so, eg, don't clear 1000BaseX just + * because the MAC is unable to support it. This is more about + * clearing unsupported speeds and duplex settings. + * + * If the %config->interface mode is %PHY_INTERFACE_MODE_1000BASEX + * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode + * based on %config->advertised and/or %config->speed. + */ + void (*validate)(struct net_device *ndev, unsigned long *supported, + struct phylink_link_state *state); + + /* Read the current link state from the hardware */ + int (*mac_link_state)(struct net_device *, struct phylink_link_state *); + + /* Configure the MAC */ + /** + * mac_config: configure the MAC for the selected mode and state + * @ndev: net_device structure for the MAC + * @mode: one of MLO_AN_FIXED, MLO_AN_PHY, MLO_AN_8023Z, MLO_AN_SGMII + * @state: state structure + * + * The action performed depends on the currently selected mode: + * + * %MLO_AN_FIXED, %MLO_AN_PHY: + * set the specified speed, duplex, pause mode, and phy interface + * mode in the provided @state. + * %MLO_AN_8023Z: + * place the link in 1000base-X mode, advertising the parameters + * given in advertising in @state. + * %MLO_AN_SGMII: + * place the link in Cisco SGMII mode - there is no advertisment + * to make as the PHY communicates the speed and duplex to the + * MAC over the in-band control word. Configuration of the pause + * mode is as per MLO_AN_PHY since this is not included. + */ + void (*mac_config)(struct net_device *ndev, unsigned int mode, + const struct phylink_link_state *state); + + /** + * mac_an_restart: restart 802.3z BaseX autonegotiation + * @ndev: net_device structure for the MAC + */ + void (*mac_an_restart)(struct net_device *ndev); + + void (*mac_link_down)(struct net_device *, unsigned int mode); + void (*mac_link_up)(struct net_device *, unsigned int mode, + struct phy_device *); +}; + +struct phylink *phylink_create(struct net_device *, struct device_node *, + phy_interface_t iface, const struct phylink_mac_ops *ops); +void phylink_destroy(struct phylink *); + +int phylink_connect_phy(struct phylink *, struct phy_device *); +int phylink_of_phy_connect(struct phylink *, struct device_node *); +void phylink_disconnect_phy(struct phylink *); + +void phylink_mac_change(struct phylink *, bool up); + +void phylink_start(struct phylink *); +void phylink_stop(struct phylink *); + +void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *); +int phylink_ethtool_set_wol(struct phylink *, struct ethtool_wolinfo *); + +int phylink_ethtool_ksettings_get(struct phylink *, + struct ethtool_link_ksettings *); +int phylink_ethtool_ksettings_set(struct phylink *, + const struct ethtool_link_ksettings *); +int phylink_ethtool_nway_reset(struct phylink *); +void phylink_ethtool_get_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_set_pauseparam(struct phylink *, + struct ethtool_pauseparam *); +int phylink_ethtool_get_module_info(struct phylink *, struct ethtool_modinfo *); +int phylink_ethtool_get_module_eeprom(struct phylink *, + struct ethtool_eeprom *, u8 *); +int phylink_init_eee(struct phylink *, bool); +int phylink_get_eee_err(struct phylink *); +int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); +int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); +int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); + +#define phylink_zero(bm) \ + bitmap_zero(bm, __ETHTOOL_LINK_MODE_MASK_NBITS) +#define __phylink_do_bit(op, bm, mode) \ + op(ETHTOOL_LINK_MODE_ ## mode ## _BIT, bm) + +#define phylink_set(bm, mode) __phylink_do_bit(__set_bit, bm, mode) +#define phylink_clear(bm, mode) __phylink_do_bit(__clear_bit, bm, mode) +#define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) + +void phylink_set_port_modes(unsigned long *bits); + +#endif diff --git a/include/linux/platform_data/mdio-bcm-unimac.h b/include/linux/platform_data/mdio-bcm-unimac.h new file mode 100644 index 000000000000..8a5f9f0b2c52 --- /dev/null +++ b/include/linux/platform_data/mdio-bcm-unimac.h @@ -0,0 +1,13 @@ +#ifndef __MDIO_BCM_UNIMAC_PDATA_H +#define __MDIO_BCM_UNIMAC_PDATA_H + +struct unimac_mdio_pdata { + u32 phy_mask; + int (*wait_func)(void *data); + void *wait_func_data; + const char *bus_name; +}; + +#define UNIMAC_MDIO_DRV_NAME "unimac-mdio" + +#endif /* __MDIO_BCM_UNIMAC_PDATA_H */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 0eef0a2b1901..d60de4a39810 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -323,6 +323,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, bool en_searcher); + int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ef39c7f40ae6..cc646ca97974 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -161,6 +161,18 @@ enum qed_nvm_images { QED_NVM_IMAGE_FCOE_CFG, }; +struct qed_link_eee_params { + u32 tx_lpi_timer; +#define QED_EEE_1G_ADV BIT(0) +#define QED_EEE_10G_ADV BIT(1) + + /* Capabilities are represented using QED_EEE_*_ADV values */ + u8 adv_caps; + u8 lp_adv_caps; + bool enable; + bool tx_lpi_enable; +}; + enum qed_led_mode { QED_LED_MODE_OFF, QED_LED_MODE_ON, @@ -172,8 +184,9 @@ enum qed_led_mode { #define DIRECT_REG_RD(reg_addr) readl((void __iomem *)(reg_addr)) -#define QED_COALESCE_MAX 0xFF +#define QED_COALESCE_MAX 0x1FF #define QED_DEFAULT_RX_USECS 12 +#define QED_DEFAULT_TX_USECS 48 /* forward */ struct qed_dev; @@ -408,6 +421,7 @@ struct qed_link_params { #define QED_LINK_OVERRIDE_SPEED_FORCED_SPEED BIT(2) #define QED_LINK_OVERRIDE_PAUSE_CONFIG BIT(3) #define QED_LINK_OVERRIDE_LOOPBACK_MODE BIT(4) +#define QED_LINK_OVERRIDE_EEE_CONFIG BIT(5) u32 override_flags; bool autoneg; u32 adv_speeds; @@ -422,6 +436,7 @@ struct qed_link_params { #define QED_LINK_LOOPBACK_EXT BIT(3) #define QED_LINK_LOOPBACK_MAC BIT(4) u32 loopback_mode; + struct qed_link_eee_params eee; }; struct qed_link_output { @@ -437,6 +452,12 @@ struct qed_link_output { u8 port; /* In PORT defs */ bool autoneg; u32 pause_config; + + /* EEE - capability & param */ + bool eee_supported; + bool eee_active; + u8 sup_caps; + struct qed_link_eee_params eee; }; struct qed_probe_params { @@ -654,16 +675,6 @@ struct qed_common_ops { enum qed_nvm_images type, u8 *buf, u16 len); /** - * @brief get_coalesce - Get coalesce parameters in usec - * - * @param cdev - * @param rx_coal - Rx coalesce value in usec - * @param tx_coal - Tx coalesce value in usec - * - */ - void (*get_coalesce)(struct qed_dev *cdev, u16 *rx_coal, u16 *tx_coal); - -/** * @brief set_coalesce - Configure Rx coalesce value in usec * * @param cdev @@ -674,8 +685,8 @@ struct qed_common_ops { * * @return 0 on success, error otherwise. */ - int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, - u16 qid, u16 sb_id); + int (*set_coalesce)(struct qed_dev *cdev, + u16 rx_coal, u16 tx_coal, void *handle); /** * @brief set_led - Configure LED mode diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 5d5415e129d4..3c07e4135127 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,7 +36,8 @@ struct user_struct { struct hlist_node uidhash_node; kuid_t uid; -#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) +#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ + defined(CONFIG_NET) atomic_long_t locked_vm; #endif }; diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 99e866487e2f..82b171e1aa0b 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -273,87 +273,85 @@ struct sctp_init_chunk { /* Section 3.3.2.1. IPv4 Address Parameter (5) */ -typedef struct sctp_ipv4addr_param { +struct sctp_ipv4addr_param { struct sctp_paramhdr param_hdr; - struct in_addr addr; -} sctp_ipv4addr_param_t; + struct in_addr addr; +}; /* Section 3.3.2.1. IPv6 Address Parameter (6) */ -typedef struct sctp_ipv6addr_param { +struct sctp_ipv6addr_param { struct sctp_paramhdr param_hdr; struct in6_addr addr; -} sctp_ipv6addr_param_t; +}; /* Section 3.3.2.1 Cookie Preservative (9) */ -typedef struct sctp_cookie_preserve_param { +struct sctp_cookie_preserve_param { struct sctp_paramhdr param_hdr; - __be32 lifespan_increment; -} sctp_cookie_preserve_param_t; + __be32 lifespan_increment; +}; /* Section 3.3.2.1 Host Name Address (11) */ -typedef struct sctp_hostname_param { +struct sctp_hostname_param { struct sctp_paramhdr param_hdr; uint8_t hostname[0]; -} sctp_hostname_param_t; +}; /* Section 3.3.2.1 Supported Address Types (12) */ -typedef struct sctp_supported_addrs_param { +struct sctp_supported_addrs_param { struct sctp_paramhdr param_hdr; __be16 types[0]; -} sctp_supported_addrs_param_t; - -/* Appendix A. ECN Capable (32768) */ -typedef struct sctp_ecn_capable_param { - struct sctp_paramhdr param_hdr; -} sctp_ecn_capable_param_t; +}; /* ADDIP Section 3.2.6 Adaptation Layer Indication */ -typedef struct sctp_adaptation_ind_param { +struct sctp_adaptation_ind_param { struct sctp_paramhdr param_hdr; __be32 adaptation_ind; -} sctp_adaptation_ind_param_t; +}; /* ADDIP Section 4.2.7 Supported Extensions Parameter */ -typedef struct sctp_supported_ext_param { +struct sctp_supported_ext_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_supported_ext_param_t; +}; /* AUTH Section 3.1 Random */ -typedef struct sctp_random_param { +struct sctp_random_param { struct sctp_paramhdr param_hdr; __u8 random_val[0]; -} sctp_random_param_t; +}; /* AUTH Section 3.2 Chunk List */ -typedef struct sctp_chunks_param { +struct sctp_chunks_param { struct sctp_paramhdr param_hdr; __u8 chunks[0]; -} sctp_chunks_param_t; +}; /* AUTH Section 3.3 HMAC Algorithm */ -typedef struct sctp_hmac_algo_param { +struct sctp_hmac_algo_param { struct sctp_paramhdr param_hdr; __be16 hmac_ids[0]; -} sctp_hmac_algo_param_t; +}; /* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2): * The INIT ACK chunk is used to acknowledge the initiation of an SCTP * association. */ -typedef struct sctp_init_chunk sctp_initack_chunk_t; +struct sctp_initack_chunk { + struct sctp_chunkhdr chunk_hdr; + struct sctp_inithdr init_hdr; +}; /* Section 3.3.3.1 State Cookie (7) */ -typedef struct sctp_cookie_param { +struct sctp_cookie_param { struct sctp_paramhdr p; __u8 body[0]; -} sctp_cookie_param_t; +}; /* Section 3.3.3.1 Unrecognized Parameters (8) */ -typedef struct sctp_unrecognized_param { +struct sctp_unrecognized_param { struct sctp_paramhdr param_hdr; struct sctp_paramhdr unrecognized; -} sctp_unrecognized_param_t; +}; @@ -365,30 +363,28 @@ typedef struct sctp_unrecognized_param { * subsequences of DATA chunks as represented by their TSNs. */ -typedef struct sctp_gap_ack_block { +struct sctp_gap_ack_block { __be16 start; __be16 end; -} sctp_gap_ack_block_t; - -typedef __be32 sctp_dup_tsn_t; +}; -typedef union { - sctp_gap_ack_block_t gab; - sctp_dup_tsn_t dup; -} sctp_sack_variable_t; +union sctp_sack_variable { + struct sctp_gap_ack_block gab; + __be32 dup; +}; -typedef struct sctp_sackhdr { +struct sctp_sackhdr { __be32 cum_tsn_ack; __be32 a_rwnd; __be16 num_gap_ack_blocks; __be16 num_dup_tsns; - sctp_sack_variable_t variable[0]; -} sctp_sackhdr_t; + union sctp_sack_variable variable[0]; +}; -typedef struct sctp_sack_chunk { +struct sctp_sack_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_sackhdr_t sack_hdr; -} sctp_sack_chunk_t; + struct sctp_sackhdr sack_hdr; +}; /* RFC 2960. Section 3.3.5 Heartbeat Request (HEARTBEAT) (4): @@ -398,49 +394,49 @@ typedef struct sctp_sack_chunk { * the present association. */ -typedef struct sctp_heartbeathdr { +struct sctp_heartbeathdr { struct sctp_paramhdr info; -} sctp_heartbeathdr_t; +}; -typedef struct sctp_heartbeat_chunk { +struct sctp_heartbeat_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_heartbeathdr_t hb_hdr; -} sctp_heartbeat_chunk_t; + struct sctp_heartbeathdr hb_hdr; +}; /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. */ -typedef struct sctp_abort_chunk { +struct sctp_abort_chunk { struct sctp_chunkhdr uh; -} sctp_abort_chunk_t; +}; /* For the graceful shutdown we must carry the tag (in common header) * and the highest consecutive acking value. */ -typedef struct sctp_shutdownhdr { +struct sctp_shutdownhdr { __be32 cum_tsn_ack; -} sctp_shutdownhdr_t; +}; -struct sctp_shutdown_chunk_t { +struct sctp_shutdown_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_shutdownhdr_t shutdown_hdr; + struct sctp_shutdownhdr shutdown_hdr; }; /* RFC 2960. Section 3.3.10 Operation Error (ERROR) (9) */ -typedef struct sctp_errhdr { +struct sctp_errhdr { __be16 cause; __be16 length; __u8 variable[0]; -} sctp_errhdr_t; +}; -typedef struct sctp_operr_chunk { +struct sctp_operr_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_errhdr_t err_hdr; -} sctp_operr_chunk_t; + struct sctp_errhdr err_hdr; +}; /* RFC 2960 3.3.10 - Operation Error * @@ -461,7 +457,7 @@ typedef struct sctp_operr_chunk { * 9 No User Data * 10 Cookie Received While Shutting Down */ -typedef enum { +enum sctp_error { SCTP_ERROR_NO_ERROR = cpu_to_be16(0x00), SCTP_ERROR_INV_STRM = cpu_to_be16(0x01), @@ -516,33 +512,28 @@ typedef enum { * 0x0105 Unsupported HMAC Identifier */ SCTP_ERROR_UNSUP_HMAC = cpu_to_be16(0x0105) -} sctp_error_t; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Explicit Congestion Notification Echo (ECNE) (12) */ -typedef struct sctp_ecnehdr { +struct sctp_ecnehdr { __be32 lowest_tsn; -} sctp_ecnehdr_t; +}; -typedef struct sctp_ecne_chunk { +struct sctp_ecne_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_ecnehdr_t ence_hdr; -} sctp_ecne_chunk_t; + struct sctp_ecnehdr ence_hdr; +}; /* RFC 2960. Appendix A. Explicit Congestion Notification. * Congestion Window Reduced (CWR) (13) */ -typedef struct sctp_cwrhdr { +struct sctp_cwrhdr { __be32 lowest_tsn; -} sctp_cwrhdr_t; - -typedef struct sctp_cwr_chunk { - struct sctp_chunkhdr chunk_hdr; - sctp_cwrhdr_t cwr_hdr; -} sctp_cwr_chunk_t; +}; /* PR-SCTP * 3.2 Forward Cumulative TSN Chunk Definition (FORWARD TSN) @@ -638,20 +629,20 @@ struct sctp_fwdtsn_chunk { * The ASCONF Parameter Response is used in the ASCONF-ACK to * report status of ASCONF processing. */ -typedef struct sctp_addip_param { - struct sctp_paramhdr param_hdr; - __be32 crr_id; -} sctp_addip_param_t; +struct sctp_addip_param { + struct sctp_paramhdr param_hdr; + __be32 crr_id; +}; -typedef struct sctp_addiphdr { +struct sctp_addiphdr { __be32 serial; __u8 params[0]; -} sctp_addiphdr_t; +}; -typedef struct sctp_addip_chunk { +struct sctp_addip_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_addiphdr_t addip_hdr; -} sctp_addip_chunk_t; + struct sctp_addiphdr addip_hdr; +}; /* AUTH * Section 4.1 Authentication Chunk (AUTH) @@ -702,16 +693,16 @@ typedef struct sctp_addip_chunk { * HMAC: n bytes (unsigned integer) This hold the result of the HMAC * calculation. */ -typedef struct sctp_authhdr { +struct sctp_authhdr { __be16 shkey_id; __be16 hmac_id; __u8 hmac[0]; -} sctp_authhdr_t; +}; -typedef struct sctp_auth_chunk { +struct sctp_auth_chunk { struct sctp_chunkhdr chunk_hdr; - sctp_authhdr_t auth_hdr; -} sctp_auth_chunk_t; + struct sctp_authhdr auth_hdr; +}; struct sctp_infox { struct sctp_info *sctpinfo; diff --git a/include/linux/seg6_local.h b/include/linux/seg6_local.h new file mode 100644 index 000000000000..ee63e76fe0c7 --- /dev/null +++ b/include/linux/seg6_local.h @@ -0,0 +1,6 @@ +#ifndef _LINUX_SEG6_LOCAL_H +#define _LINUX_SEG6_LOCAL_H + +#include <uapi/linux/seg6_local.h> + +#endif diff --git a/include/linux/sfp.h b/include/linux/sfp.h new file mode 100644 index 000000000000..4a906f560817 --- /dev/null +++ b/include/linux/sfp.h @@ -0,0 +1,434 @@ +#ifndef LINUX_SFP_H +#define LINUX_SFP_H + +#include <linux/phy.h> + +struct __packed sfp_eeprom_base { + u8 phys_id; + u8 phys_ext_id; + u8 connector; +#if defined __BIG_ENDIAN_BITFIELD + u8 e10g_base_er:1; + u8 e10g_base_lrm:1; + u8 e10g_base_lr:1; + u8 e10g_base_sr:1; + u8 if_1x_sx:1; + u8 if_1x_lx:1; + u8 if_1x_copper_active:1; + u8 if_1x_copper_passive:1; + + u8 escon_mmf_1310_led:1; + u8 escon_smf_1310_laser:1; + u8 sonet_oc192_short_reach:1; + u8 sonet_reach_bit1:1; + u8 sonet_reach_bit2:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_short_reach:1; + + u8 unallocated_5_7:1; + u8 sonet_oc12_smf_long_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_short_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc3_smf_long_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_short_reach:1; + + u8 e_base_px:1; + u8 e_base_bx10:1; + u8 e100_base_fx:1; + u8 e100_base_lx:1; + u8 e1000_base_t:1; + u8 e1000_base_cx:1; + u8 e1000_base_lx:1; + u8 e1000_base_sx:1; + + u8 fc_ll_v:1; + u8 fc_ll_s:1; + u8 fc_ll_i:1; + u8 fc_ll_l:1; + u8 fc_ll_m:1; + u8 fc_tech_sa:1; + u8 fc_tech_lc:1; + u8 fc_tech_electrical_inter_enclosure:1; + + u8 fc_tech_electrical_intra_enclosure:1; + u8 fc_tech_sn:1; + u8 fc_tech_sl:1; + u8 fc_tech_ll:1; + u8 sfp_ct_active:1; + u8 sfp_ct_passive:1; + u8 unallocated_8_1:1; + u8 unallocated_8_0:1; + + u8 fc_media_tw:1; + u8 fc_media_tp:1; + u8 fc_media_mi:1; + u8 fc_media_tv:1; + u8 fc_media_m6:1; + u8 fc_media_m5:1; + u8 unallocated_9_1:1; + u8 fc_media_sm:1; + + u8 fc_speed_1200:1; + u8 fc_speed_800:1; + u8 fc_speed_1600:1; + u8 fc_speed_400:1; + u8 fc_speed_3200:1; + u8 fc_speed_200:1; + u8 unallocated_10_1:1; + u8 fc_speed_100:1; +#elif defined __LITTLE_ENDIAN_BITFIELD + u8 if_1x_copper_passive:1; + u8 if_1x_copper_active:1; + u8 if_1x_lx:1; + u8 if_1x_sx:1; + u8 e10g_base_sr:1; + u8 e10g_base_lr:1; + u8 e10g_base_lrm:1; + u8 e10g_base_er:1; + + u8 sonet_oc3_short_reach:1; + u8 sonet_oc3_smf_intermediate_reach:1; + u8 sonet_oc3_smf_long_reach:1; + u8 unallocated_5_3:1; + u8 sonet_oc12_short_reach:1; + u8 sonet_oc12_smf_intermediate_reach:1; + u8 sonet_oc12_smf_long_reach:1; + u8 unallocated_5_7:1; + + u8 sonet_oc48_short_reach:1; + u8 sonet_oc48_intermediate_reach:1; + u8 sonet_oc48_long_reach:1; + u8 sonet_reach_bit2:1; + u8 sonet_reach_bit1:1; + u8 sonet_oc192_short_reach:1; + u8 escon_smf_1310_laser:1; + u8 escon_mmf_1310_led:1; + + u8 e1000_base_sx:1; + u8 e1000_base_lx:1; + u8 e1000_base_cx:1; + u8 e1000_base_t:1; + u8 e100_base_lx:1; + u8 e100_base_fx:1; + u8 e_base_bx10:1; + u8 e_base_px:1; + + u8 fc_tech_electrical_inter_enclosure:1; + u8 fc_tech_lc:1; + u8 fc_tech_sa:1; + u8 fc_ll_m:1; + u8 fc_ll_l:1; + u8 fc_ll_i:1; + u8 fc_ll_s:1; + u8 fc_ll_v:1; + + u8 unallocated_8_0:1; + u8 unallocated_8_1:1; + u8 sfp_ct_passive:1; + u8 sfp_ct_active:1; + u8 fc_tech_ll:1; + u8 fc_tech_sl:1; + u8 fc_tech_sn:1; + u8 fc_tech_electrical_intra_enclosure:1; + + u8 fc_media_sm:1; + u8 unallocated_9_1:1; + u8 fc_media_m5:1; + u8 fc_media_m6:1; + u8 fc_media_tv:1; + u8 fc_media_mi:1; + u8 fc_media_tp:1; + u8 fc_media_tw:1; + + u8 fc_speed_100:1; + u8 unallocated_10_1:1; + u8 fc_speed_200:1; + u8 fc_speed_3200:1; + u8 fc_speed_400:1; + u8 fc_speed_1600:1; + u8 fc_speed_800:1; + u8 fc_speed_1200:1; +#else +#error Unknown Endian +#endif + u8 encoding; + u8 br_nominal; + u8 rate_id; + u8 link_len[6]; + char vendor_name[16]; + u8 extended_cc; + char vendor_oui[3]; + char vendor_pn[16]; + char vendor_rev[4]; + union { + __be16 optical_wavelength; + u8 cable_spec; + }; + u8 reserved62; + u8 cc_base; +}; + +struct __packed sfp_eeprom_ext { + __be16 options; + u8 br_max; + u8 br_min; + char vendor_sn[16]; + char datecode[8]; + u8 diagmon; + u8 enhopts; + u8 sff8472_compliance; + u8 cc_ext; +}; + +struct __packed sfp_eeprom_id { + struct sfp_eeprom_base base; + struct sfp_eeprom_ext ext; +}; + +/* SFP EEPROM registers */ +enum { + SFP_PHYS_ID = 0x00, + SFP_PHYS_EXT_ID = 0x01, + SFP_CONNECTOR = 0x02, + SFP_COMPLIANCE = 0x03, + SFP_ENCODING = 0x0b, + SFP_BR_NOMINAL = 0x0c, + SFP_RATE_ID = 0x0d, + SFP_LINK_LEN_SM_KM = 0x0e, + SFP_LINK_LEN_SM_100M = 0x0f, + SFP_LINK_LEN_50UM_OM2_10M = 0x10, + SFP_LINK_LEN_62_5UM_OM1_10M = 0x11, + SFP_LINK_LEN_COPPER_1M = 0x12, + SFP_LINK_LEN_50UM_OM4_10M = 0x12, + SFP_LINK_LEN_50UM_OM3_10M = 0x13, + SFP_VENDOR_NAME = 0x14, + SFP_VENDOR_OUI = 0x25, + SFP_VENDOR_PN = 0x28, + SFP_VENDOR_REV = 0x38, + SFP_OPTICAL_WAVELENGTH_MSB = 0x3c, + SFP_OPTICAL_WAVELENGTH_LSB = 0x3d, + SFP_CABLE_SPEC = 0x3c, + SFP_CC_BASE = 0x3f, + SFP_OPTIONS = 0x40, /* 2 bytes, MSB, LSB */ + SFP_BR_MAX = 0x42, + SFP_BR_MIN = 0x43, + SFP_VENDOR_SN = 0x44, + SFP_DATECODE = 0x54, + SFP_DIAGMON = 0x5c, + SFP_ENHOPTS = 0x5d, + SFP_SFF8472_COMPLIANCE = 0x5e, + SFP_CC_EXT = 0x5f, + + SFP_PHYS_ID_SFP = 0x03, + SFP_PHYS_EXT_ID_SFP = 0x04, + SFP_CONNECTOR_UNSPEC = 0x00, + /* codes 01-05 not supportable on SFP, but some modules have single SC */ + SFP_CONNECTOR_SC = 0x01, + SFP_CONNECTOR_FIBERJACK = 0x06, + SFP_CONNECTOR_LC = 0x07, + SFP_CONNECTOR_MT_RJ = 0x08, + SFP_CONNECTOR_MU = 0x09, + SFP_CONNECTOR_SG = 0x0a, + SFP_CONNECTOR_OPTICAL_PIGTAIL = 0x0b, + SFP_CONNECTOR_MPO_1X12 = 0x0c, + SFP_CONNECTOR_MPO_2X16 = 0x0d, + SFP_CONNECTOR_HSSDC_II = 0x20, + SFP_CONNECTOR_COPPER_PIGTAIL = 0x21, + SFP_CONNECTOR_RJ45 = 0x22, + SFP_CONNECTOR_NOSEPARATE = 0x23, + SFP_CONNECTOR_MXC_2X16 = 0x24, + SFP_ENCODING_UNSPEC = 0x00, + SFP_ENCODING_8B10B = 0x01, + SFP_ENCODING_4B5B = 0x02, + SFP_ENCODING_NRZ = 0x03, + SFP_ENCODING_8472_MANCHESTER = 0x04, + SFP_ENCODING_8472_SONET = 0x05, + SFP_ENCODING_8472_64B66B = 0x06, + SFP_ENCODING_256B257B = 0x07, + SFP_ENCODING_PAM4 = 0x08, + SFP_OPTIONS_HIGH_POWER_LEVEL = BIT(13), + SFP_OPTIONS_PAGING_A2 = BIT(12), + SFP_OPTIONS_RETIMER = BIT(11), + SFP_OPTIONS_COOLED_XCVR = BIT(10), + SFP_OPTIONS_POWER_DECL = BIT(9), + SFP_OPTIONS_RX_LINEAR_OUT = BIT(8), + SFP_OPTIONS_RX_DECISION_THRESH = BIT(7), + SFP_OPTIONS_TUNABLE_TX = BIT(6), + SFP_OPTIONS_RATE_SELECT = BIT(5), + SFP_OPTIONS_TX_DISABLE = BIT(4), + SFP_OPTIONS_TX_FAULT = BIT(3), + SFP_OPTIONS_LOS_INVERTED = BIT(2), + SFP_OPTIONS_LOS_NORMAL = BIT(1), + SFP_DIAGMON_DDM = BIT(6), + SFP_DIAGMON_INT_CAL = BIT(5), + SFP_DIAGMON_EXT_CAL = BIT(4), + SFP_DIAGMON_RXPWR_AVG = BIT(3), + SFP_DIAGMON_ADDRMODE = BIT(2), + SFP_ENHOPTS_ALARMWARN = BIT(7), + SFP_ENHOPTS_SOFT_TX_DISABLE = BIT(6), + SFP_ENHOPTS_SOFT_TX_FAULT = BIT(5), + SFP_ENHOPTS_SOFT_RX_LOS = BIT(4), + SFP_ENHOPTS_SOFT_RATE_SELECT = BIT(3), + SFP_ENHOPTS_APP_SELECT_SFF8079 = BIT(2), + SFP_ENHOPTS_SOFT_RATE_SFF8431 = BIT(1), + SFP_SFF8472_COMPLIANCE_NONE = 0x00, + SFP_SFF8472_COMPLIANCE_REV9_3 = 0x01, + SFP_SFF8472_COMPLIANCE_REV9_5 = 0x02, + SFP_SFF8472_COMPLIANCE_REV10_2 = 0x03, + SFP_SFF8472_COMPLIANCE_REV10_4 = 0x04, + SFP_SFF8472_COMPLIANCE_REV11_0 = 0x05, + SFP_SFF8472_COMPLIANCE_REV11_3 = 0x06, + SFP_SFF8472_COMPLIANCE_REV11_4 = 0x07, + SFP_SFF8472_COMPLIANCE_REV12_0 = 0x08, +}; + +/* SFP Diagnostics */ +enum { + /* Alarm and warnings stored MSB at lower address then LSB */ + SFP_TEMP_HIGH_ALARM = 0x00, + SFP_TEMP_LOW_ALARM = 0x02, + SFP_TEMP_HIGH_WARN = 0x04, + SFP_TEMP_LOW_WARN = 0x06, + SFP_VOLT_HIGH_ALARM = 0x08, + SFP_VOLT_LOW_ALARM = 0x0a, + SFP_VOLT_HIGH_WARN = 0x0c, + SFP_VOLT_LOW_WARN = 0x0e, + SFP_BIAS_HIGH_ALARM = 0x10, + SFP_BIAS_LOW_ALARM = 0x12, + SFP_BIAS_HIGH_WARN = 0x14, + SFP_BIAS_LOW_WARN = 0x16, + SFP_TXPWR_HIGH_ALARM = 0x18, + SFP_TXPWR_LOW_ALARM = 0x1a, + SFP_TXPWR_HIGH_WARN = 0x1c, + SFP_TXPWR_LOW_WARN = 0x1e, + SFP_RXPWR_HIGH_ALARM = 0x20, + SFP_RXPWR_LOW_ALARM = 0x22, + SFP_RXPWR_HIGH_WARN = 0x24, + SFP_RXPWR_LOW_WARN = 0x26, + SFP_LASER_TEMP_HIGH_ALARM = 0x28, + SFP_LASER_TEMP_LOW_ALARM = 0x2a, + SFP_LASER_TEMP_HIGH_WARN = 0x2c, + SFP_LASER_TEMP_LOW_WARN = 0x2e, + SFP_TEC_CUR_HIGH_ALARM = 0x30, + SFP_TEC_CUR_LOW_ALARM = 0x32, + SFP_TEC_CUR_HIGH_WARN = 0x34, + SFP_TEC_CUR_LOW_WARN = 0x36, + SFP_CAL_RXPWR4 = 0x38, + SFP_CAL_RXPWR3 = 0x3c, + SFP_CAL_RXPWR2 = 0x40, + SFP_CAL_RXPWR1 = 0x44, + SFP_CAL_RXPWR0 = 0x48, + SFP_CAL_TXI_SLOPE = 0x4c, + SFP_CAL_TXI_OFFSET = 0x4e, + SFP_CAL_TXPWR_SLOPE = 0x50, + SFP_CAL_TXPWR_OFFSET = 0x52, + SFP_CAL_T_SLOPE = 0x54, + SFP_CAL_T_OFFSET = 0x56, + SFP_CAL_V_SLOPE = 0x58, + SFP_CAL_V_OFFSET = 0x5a, + SFP_CHKSUM = 0x5f, + + SFP_TEMP = 0x60, + SFP_VCC = 0x62, + SFP_TX_BIAS = 0x64, + SFP_TX_POWER = 0x66, + SFP_RX_POWER = 0x68, + SFP_LASER_TEMP = 0x6a, + SFP_TEC_CUR = 0x6c, + + SFP_STATUS = 0x6e, + SFP_ALARM = 0x70, + + SFP_EXT_STATUS = 0x76, + SFP_VSL = 0x78, + SFP_PAGE = 0x7f, +}; + +struct device_node; +struct ethtool_eeprom; +struct ethtool_modinfo; +struct net_device; +struct sfp_bus; + +struct sfp_upstream_ops { + int (*module_insert)(void *, const struct sfp_eeprom_id *id); + void (*module_remove)(void *); + void (*link_down)(void *); + void (*link_up)(void *); + int (*connect_phy)(void *, struct phy_device *); + void (*disconnect_phy)(void *); +}; + +#if IS_ENABLED(CONFIG_SFP) +int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); +phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id); +void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, + unsigned long *support); + +int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); +int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, + u8 *data); +void sfp_upstream_start(struct sfp_bus *bus); +void sfp_upstream_stop(struct sfp_bus *bus); +struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_unregister_upstream(struct sfp_bus *bus); +#else +static inline int sfp_parse_port(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ + return PORT_OTHER; +} + +static inline phy_interface_t sfp_parse_interface(struct sfp_bus *bus, + const struct sfp_eeprom_id *id) +{ + return PHY_INTERFACE_MODE_NA; +} + +static inline void sfp_parse_support(struct sfp_bus *bus, + const struct sfp_eeprom_id *id, + unsigned long *support) +{ +} + +static inline int sfp_get_module_info(struct sfp_bus *bus, + struct ethtool_modinfo *modinfo) +{ + return -EOPNOTSUPP; +} + +static inline int sfp_get_module_eeprom(struct sfp_bus *bus, + struct ethtool_eeprom *ee, u8 *data) +{ + return -EOPNOTSUPP; +} + +static inline void sfp_upstream_start(struct sfp_bus *bus) +{ +} + +static inline void sfp_upstream_stop(struct sfp_bus *bus) +{ +} + +static inline struct sfp_bus *sfp_register_upstream(struct device_node *np, + struct net_device *ndev, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return (struct sfp_bus *)-1; +} + +static inline void sfp_unregister_upstream(struct sfp_bus *bus) +{ +} +#endif + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbe29b6c9bd6..7594e19bce62 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -345,6 +345,42 @@ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) frag->size -= delta; } +static inline bool skb_frag_must_loop(struct page *p) +{ +#if defined(CONFIG_HIGHMEM) + if (PageHighMem(p)) + return true; +#endif + return false; +} + +/** + * skb_frag_foreach_page - loop over pages in a fragment + * + * @f: skb frag to operate on + * @f_off: offset from start of f->page.p + * @f_len: length from f_off to loop over + * @p: (temp var) current page + * @p_off: (temp var) offset from start of current page, + * non-zero only on first page. + * @p_len: (temp var) length in current page, + * < PAGE_SIZE only on first and last page. + * @copied: (temp var) length so far, excluding current p_len. + * + * A fragment can hold a compound page, in which case per-page + * operations, notably kmap_atomic, must be called for each + * regular page. + */ +#define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ + for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ + p_off = (f_off) & (PAGE_SIZE - 1), \ + p_len = skb_frag_must_loop(p) ? \ + min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ + copied = 0; \ + copied < f_len; \ + copied += p_len, p++, p_off = 0, \ + p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ + #define HAVE_HW_TIME_STAMP /** @@ -393,6 +429,7 @@ enum { SKBTX_SCHED_TSTAMP = 1 << 6, }; +#define SKBTX_ZEROCOPY_FRAG (SKBTX_DEV_ZEROCOPY | SKBTX_SHARED_FRAG) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | SKBTX_ANY_SW_TSTAMP) @@ -407,10 +444,46 @@ enum { */ struct ubuf_info { void (*callback)(struct ubuf_info *, bool zerocopy_success); - void *ctx; - unsigned long desc; + union { + struct { + unsigned long desc; + void *ctx; + }; + struct { + u32 id; + u16 len; + u16 zerocopy:1; + u32 bytelen; + }; + }; + atomic_t refcnt; + + struct mmpin { + struct user_struct *user; + unsigned int num_pg; + } mmp; }; +#define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) + +struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size); +struct ubuf_info *sock_zerocopy_realloc(struct sock *sk, size_t size, + struct ubuf_info *uarg); + +static inline void sock_zerocopy_get(struct ubuf_info *uarg) +{ + atomic_inc(&uarg->refcnt); +} + +void sock_zerocopy_put(struct ubuf_info *uarg); +void sock_zerocopy_put_abort(struct ubuf_info *uarg); + +void sock_zerocopy_callback(struct ubuf_info *uarg, bool success); + +int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, + struct msghdr *msg, int len, + struct ubuf_info *uarg); + /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ @@ -463,39 +536,38 @@ enum { enum { SKB_GSO_TCPV4 = 1 << 0, - SKB_GSO_UDP = 1 << 1, /* This indicates the skb is from an untrusted source. */ - SKB_GSO_DODGY = 1 << 2, + SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ - SKB_GSO_TCP_ECN = 1 << 3, + SKB_GSO_TCP_ECN = 1 << 2, - SKB_GSO_TCP_FIXEDID = 1 << 4, + SKB_GSO_TCP_FIXEDID = 1 << 3, - SKB_GSO_TCPV6 = 1 << 5, + SKB_GSO_TCPV6 = 1 << 4, - SKB_GSO_FCOE = 1 << 6, + SKB_GSO_FCOE = 1 << 5, - SKB_GSO_GRE = 1 << 7, + SKB_GSO_GRE = 1 << 6, - SKB_GSO_GRE_CSUM = 1 << 8, + SKB_GSO_GRE_CSUM = 1 << 7, - SKB_GSO_IPXIP4 = 1 << 9, + SKB_GSO_IPXIP4 = 1 << 8, - SKB_GSO_IPXIP6 = 1 << 10, + SKB_GSO_IPXIP6 = 1 << 9, - SKB_GSO_UDP_TUNNEL = 1 << 11, + SKB_GSO_UDP_TUNNEL = 1 << 10, - SKB_GSO_UDP_TUNNEL_CSUM = 1 << 12, + SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, - SKB_GSO_PARTIAL = 1 << 13, + SKB_GSO_PARTIAL = 1 << 12, - SKB_GSO_TUNNEL_REMCSUM = 1 << 14, + SKB_GSO_TUNNEL_REMCSUM = 1 << 13, - SKB_GSO_SCTP = 1 << 15, + SKB_GSO_SCTP = 1 << 14, - SKB_GSO_ESP = 1 << 16, + SKB_GSO_ESP = 1 << 15, }; #if BITS_PER_LONG > 32 @@ -945,12 +1017,6 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } -struct sk_buff *__alloc_skb_head(gfp_t priority, int node); -static inline struct sk_buff *alloc_skb_head(gfp_t priority) -{ - return __alloc_skb_head(priority, -1); -} - struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); @@ -1129,8 +1195,6 @@ static inline __u32 skb_get_hash(struct sk_buff *skb) return skb->hash; } -__u32 __skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6); - static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { @@ -1143,20 +1207,6 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 __skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl); - -static inline __u32 skb_get_hash_flowi4(struct sk_buff *skb, const struct flowi4 *fl4) -{ - if (!skb->l4_hash && !skb->sw_hash) { - struct flow_keys keys; - __u32 hash = __get_hash_from_flowi4(fl4, &keys); - - __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); - } - - return skb->hash; -} - __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) @@ -1201,6 +1251,50 @@ static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) return &skb_shinfo(skb)->hwtstamps; } +static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) +{ + bool is_zcopy = skb && skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY; + + return is_zcopy ? skb_uarg(skb) : NULL; +} + +static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg) +{ + if (skb && uarg && !skb_zcopy(skb)) { + sock_zerocopy_get(uarg); + skb_shinfo(skb)->destructor_arg = uarg; + skb_shinfo(skb)->tx_flags |= SKBTX_ZEROCOPY_FRAG; + } +} + +/* Release a reference on a zerocopy structure */ +static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + if (uarg->callback == sock_zerocopy_callback) { + uarg->zerocopy = uarg->zerocopy && zerocopy; + sock_zerocopy_put(uarg); + } else { + uarg->callback(uarg, zerocopy); + } + + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + +/* Abort a zerocopy operation and revert zckey on error in send syscall */ +static inline void skb_zcopy_abort(struct sk_buff *skb) +{ + struct ubuf_info *uarg = skb_zcopy(skb); + + if (uarg) { + sock_zerocopy_put_abort(uarg); + skb_shinfo(skb)->tx_flags &= ~SKBTX_ZEROCOPY_FRAG; + } +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1783,13 +1877,18 @@ static inline unsigned int skb_headlen(const struct sk_buff *skb) return skb->len - skb->data_len; } -static inline unsigned int skb_pagelen(const struct sk_buff *skb) +static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); - return len + skb_headlen(skb); + return len; +} + +static inline unsigned int skb_pagelen(const struct sk_buff *skb) +{ + return skb_headlen(skb) + __skb_pagelen(skb); } /** @@ -2434,7 +2533,17 @@ static inline void skb_orphan(struct sk_buff *skb) */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { - if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY))) + if (likely(!skb_zcopy(skb))) + return 0; + if (skb_uarg(skb)->callback == sock_zerocopy_callback) + return 0; + return skb_copy_ubufs(skb, gfp_mask); +} + +/* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ +static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) +{ + if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } @@ -2866,6 +2975,8 @@ static inline int skb_add_data(struct sk_buff *skb, static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { + if (skb_zcopy(skb)) + return false; if (i) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; @@ -3120,6 +3231,9 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); +int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, + int len); +int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b13db5163cc..8ad963cdc88c 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -287,6 +287,7 @@ struct ucred { #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN +#define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3cb15ea48aee..c9170218e9e6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -172,8 +172,20 @@ extern struct trace_event_functions exit_syscall_print_funcs; static struct syscall_metadata __used \ __attribute__((section("__syscalls_metadata"))) \ *__p_syscall_meta_##sname = &__syscall_meta_##sname; + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return tp_event->class == &event_class_syscall_enter || + tp_event->class == &event_class_syscall_exit; +} + #else #define SYSCALL_METADATA(sname, nb, ...) + +static inline int is_syscall_trace_event(struct trace_event_call *tp_event) +{ + return 0; +} #endif #define SYSCALL_DEFINE0(sname) \ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 542ca1ae02c4..267164a1d559 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -148,12 +148,6 @@ struct tcp_sock { u16 gso_segs; /* Max number of segs per GSO packet */ /* - * Header prediction flags - * 0x5?10 << 16 + snd_wnd in net byte order - */ - __be32 pred_flags; - -/* * RFC793 variables by their proper names. This means you can * read the code and the spec side by side (and laugh ...) * See RFC793 and RFC1122. The RFC writes these in capitals. @@ -192,15 +186,6 @@ struct tcp_sock { struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ - /* Data for direct copy to user */ - struct { - struct sk_buff_head prequeue; - struct task_struct *task; - struct msghdr *msg; - int memory; - int len; - } ucopy; - u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ u32 max_window; /* Maximal window ever seen from peer */ @@ -273,7 +258,7 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; - u32 prior_cwnd; /* Congestion window at start of Recovery. */ + u32 prior_cwnd; /* cwnd right before starting loss recovery */ u32 prr_delivered; /* Number of newly delivered packets to * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ diff --git a/include/linux/tnum.h b/include/linux/tnum.h new file mode 100644 index 000000000000..0d2d3da46139 --- /dev/null +++ b/include/linux/tnum.h @@ -0,0 +1,81 @@ +/* tnum: tracked (or tristate) numbers + * + * A tnum tracks knowledge about the bits of a value. Each bit can be either + * known (0 or 1), or unknown (x). Arithmetic operations on tnums will + * propagate the unknown bits such that the tnum result represents all the + * possible results for possible values of the operands. + */ +#include <linux/types.h> + +struct tnum { + u64 value; + u64 mask; +}; + +/* Constructors */ +/* Represent a known constant as a tnum. */ +struct tnum tnum_const(u64 value); +/* A completely unknown value */ +extern const struct tnum tnum_unknown; +/* A value that's unknown except that @min <= value <= @max */ +struct tnum tnum_range(u64 min, u64 max); + +/* Arithmetic and logical ops */ +/* Shift a tnum left (by a fixed shift) */ +struct tnum tnum_lshift(struct tnum a, u8 shift); +/* Shift a tnum right (by a fixed shift) */ +struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Add two tnums, return @a + @b */ +struct tnum tnum_add(struct tnum a, struct tnum b); +/* Subtract two tnums, return @a - @b */ +struct tnum tnum_sub(struct tnum a, struct tnum b); +/* Bitwise-AND, return @a & @b */ +struct tnum tnum_and(struct tnum a, struct tnum b); +/* Bitwise-OR, return @a | @b */ +struct tnum tnum_or(struct tnum a, struct tnum b); +/* Bitwise-XOR, return @a ^ @b */ +struct tnum tnum_xor(struct tnum a, struct tnum b); +/* Multiply two tnums, return @a * @b */ +struct tnum tnum_mul(struct tnum a, struct tnum b); + +/* Return a tnum representing numbers satisfying both @a and @b */ +struct tnum tnum_intersect(struct tnum a, struct tnum b); + +/* Return @a with all but the lowest @size bytes cleared */ +struct tnum tnum_cast(struct tnum a, u8 size); + +/* Returns true if @a is a known constant */ +static inline bool tnum_is_const(struct tnum a) +{ + return !a.mask; +} + +/* Returns true if @a == tnum_const(@b) */ +static inline bool tnum_equals_const(struct tnum a, u64 b) +{ + return tnum_is_const(a) && a.value == b; +} + +/* Returns true if @a is completely unknown */ +static inline bool tnum_is_unknown(struct tnum a) +{ + return !~a.mask; +} + +/* Returns true if @a is known to be a multiple of @size. + * @size must be a power of two. + */ +bool tnum_is_aligned(struct tnum a, u64 size); + +/* Returns true if @b represents a subset of @a. */ +bool tnum_in(struct tnum a, struct tnum b); + +/* Formatting functions. These have snprintf-like semantics: they will write + * up to @size bytes (including the terminating NUL byte), and return the number + * of bytes (excluding the terminating NUL) which would have been written had + * sufficient space been available. (Thus tnum_sbin always returns 64.) + */ +/* Format a tnum as a pair of hex numbers (value; mask) */ +int tnum_strn(char *str, size_t size, struct tnum a); +/* Format a tnum as tristate binary expansion */ +int tnum_sbin(char *str, size_t size, struct tnum a); diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 5209b5ed2a64..32fb046f2173 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -18,9 +18,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; break; - case VIRTIO_NET_HDR_GSO_UDP: - gso_type = SKB_GSO_UDP; - break; default: return -EINVAL; } @@ -73,8 +70,6 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb, hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else return -EINVAL; if (sinfo->gso_type & SKB_GSO_TCP_ECN) diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 53b1a2cca421..afb37f835449 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -58,7 +58,6 @@ struct unix_sock { struct list_head link; atomic_long_t inflight; spinlock_t lock; - unsigned char recursion_level; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 diff --git a/include/net/dsa.h b/include/net/dsa.h index 58969b9a090c..7f46b521313e 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -101,6 +101,15 @@ struct dsa_platform_data { struct packet_type; +struct dsa_device_ops { + struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev); + int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, + int *offset); +}; + struct dsa_switch_tree { struct list_head list; @@ -256,11 +265,6 @@ static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); } -static inline bool dsa_is_port_initialized(struct dsa_switch *ds, int p) -{ - return ds->enabled_port_mask & (1 << p) && ds->ports[p].netdev; -} - static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; @@ -277,6 +281,8 @@ static inline u8 dsa_upstream_port(struct dsa_switch *ds) return ds->rtable[dst->cpu_dp->ds->index]; } +typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, + bool is_static, void *data); struct dsa_switch_ops { /* * Legacy probing. @@ -337,13 +343,12 @@ struct dsa_switch_ops { struct phy_device *phy); /* - * EEE setttings + * Port's MAC EEE settings */ - int (*set_eee)(struct dsa_switch *ds, int port, - struct phy_device *phydev, - struct ethtool_eee *e); - int (*get_eee)(struct dsa_switch *ds, int port, - struct ethtool_eee *e); + int (*set_mac_eee)(struct dsa_switch *ds, int port, + struct ethtool_eee *e); + int (*get_mac_eee)(struct dsa_switch *ds, int port, + struct ethtool_eee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); @@ -384,24 +389,15 @@ struct dsa_switch_ops { struct switchdev_trans *trans); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); - int (*port_vlan_dump)(struct dsa_switch *ds, int port, - struct switchdev_obj_port_vlan *vlan, - switchdev_obj_dump_cb_t *cb); - /* * Forwarding database */ - int (*port_fdb_prepare)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_fdb *fdb, - struct switchdev_trans *trans); - void (*port_fdb_add)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_fdb *fdb, - struct switchdev_trans *trans); + int (*port_fdb_add)(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid); int (*port_fdb_del)(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_fdb *fdb); + const unsigned char *addr, u16 vid); int (*port_fdb_dump)(struct dsa_switch *ds, int port, - struct switchdev_obj_port_fdb *fdb, - switchdev_obj_dump_cb_t *cb); + dsa_fdb_dump_cb_t *cb, void *data); /* * Multicast database @@ -414,10 +410,6 @@ struct dsa_switch_ops { struct switchdev_trans *trans); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb); - int (*port_mdb_dump)(struct dsa_switch *ds, int port, - struct switchdev_obj_port_mdb *mdb, - switchdev_obj_dump_cb_t *cb); - /* * RXNFC */ diff --git a/include/net/fib_notifier.h b/include/net/fib_notifier.h new file mode 100644 index 000000000000..241475224f74 --- /dev/null +++ b/include/net/fib_notifier.h @@ -0,0 +1,44 @@ +#ifndef __NET_FIB_NOTIFIER_H +#define __NET_FIB_NOTIFIER_H + +#include <linux/types.h> +#include <linux/notifier.h> +#include <net/net_namespace.h> + +struct fib_notifier_info { + struct net *net; + int family; +}; + +enum fib_event_type { + FIB_EVENT_ENTRY_REPLACE, + FIB_EVENT_ENTRY_APPEND, + FIB_EVENT_ENTRY_ADD, + FIB_EVENT_ENTRY_DEL, + FIB_EVENT_RULE_ADD, + FIB_EVENT_RULE_DEL, + FIB_EVENT_NH_ADD, + FIB_EVENT_NH_DEL, +}; + +struct fib_notifier_ops { + int family; + struct list_head list; + unsigned int (*fib_seq_read)(struct net *net); + int (*fib_dump)(struct net *net, struct notifier_block *nb); + struct rcu_head rcu; +}; + +int call_fib_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info); +int call_fib_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info); +int register_fib_notifier(struct notifier_block *nb, + void (*cb)(struct notifier_block *nb)); +int unregister_fib_notifier(struct notifier_block *nb); +struct fib_notifier_ops * +fib_notifier_ops_register(const struct fib_notifier_ops *tmpl, struct net *net); +void fib_notifier_ops_unregister(struct fib_notifier_ops *ops); + +#endif diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index c487bfa2f479..3d7f1cefc6f5 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -8,6 +8,7 @@ #include <linux/refcount.h> #include <net/flow.h> #include <net/rtnetlink.h> +#include <net/fib_notifier.h> struct fib_kuid_range { kuid_t start; @@ -57,6 +58,7 @@ struct fib_rules_ops { int addr_size; int unresolved_rules; int nr_goto_rules; + unsigned int fib_rules_seq; int (*action)(struct fib_rule *, struct flowi *, int, @@ -89,6 +91,11 @@ struct fib_rules_ops { struct rcu_head rcu; }; +struct fib_rule_notifier_info { + struct fib_notifier_info info; /* must be first */ + struct fib_rule *rule; +}; + #define FRA_GENERIC_POLICY \ [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ @@ -143,6 +150,8 @@ int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); bool fib_rule_matchall(const struct fib_rule *rule); +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family); +unsigned int fib_rules_seq_read(struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); diff --git a/include/net/flow.h b/include/net/flow.h index bae198b3039e..f3dc61b29bb5 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -218,40 +218,6 @@ static inline unsigned int flow_key_size(u16 family) return 0; } -#define FLOW_DIR_IN 0 -#define FLOW_DIR_OUT 1 -#define FLOW_DIR_FWD 2 - -struct net; -struct sock; -struct flow_cache_ops; - -struct flow_cache_object { - const struct flow_cache_ops *ops; -}; - -struct flow_cache_ops { - struct flow_cache_object *(*get)(struct flow_cache_object *); - int (*check)(struct flow_cache_object *); - void (*delete)(struct flow_cache_object *); -}; - -typedef struct flow_cache_object *(*flow_resolve_t)( - struct net *net, const struct flowi *key, u16 family, - u8 dir, struct flow_cache_object *oldobj, void *ctx); - -struct flow_cache_object *flow_cache_lookup(struct net *net, - const struct flowi *key, u16 family, - u8 dir, flow_resolve_t resolver, - void *ctx); -int flow_cache_init(struct net *net); -void flow_cache_fini(struct net *net); -void flow_cache_hp_init(void); - -void flow_cache_flush(struct net *net); -void flow_cache_flush_deferred(struct net *net); -extern atomic_t flow_cache_genid; - __u32 __get_hash_from_flowi6(const struct flowi6 *fl6, struct flow_keys *keys); static inline __u32 get_hash_from_flowi6(const struct flowi6 *fl6) diff --git a/include/net/flowcache.h b/include/net/flowcache.h deleted file mode 100644 index 51eb971e8973..000000000000 --- a/include/net/flowcache.h +++ /dev/null @@ -1,25 +0,0 @@ -#ifndef _NET_FLOWCACHE_H -#define _NET_FLOWCACHE_H - -#include <linux/interrupt.h> -#include <linux/types.h> -#include <linux/timer.h> -#include <linux/notifier.h> - -struct flow_cache_percpu { - struct hlist_head *hash_table; - unsigned int hash_count; - u32 hash_rnd; - int hash_rnd_recalc; - struct tasklet_struct flush_tasklet; -}; - -struct flow_cache { - u32 hash_shift; - struct flow_cache_percpu __percpu *percpu; - struct hlist_node node; - unsigned int low_watermark; - unsigned int high_watermark; - struct timer_list rnd_timer; -}; -#endif /* _NET_FLOWCACHE_H */ diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index b87becacd9d3..6e91e38a31da 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -49,7 +49,8 @@ struct sock *__inet6_lookup_established(struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, - const u16 hnum, const int dif); + const u16 hnum, const int dif, + const int sdif); struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, @@ -57,7 +58,8 @@ struct sock *inet6_lookup_listener(struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, - const unsigned short hnum, const int dif); + const unsigned short hnum, + const int dif, const int sdif); static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, @@ -66,24 +68,25 @@ static inline struct sock *__inet6_lookup(struct net *net, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, - const int dif, + const int dif, const int sdif, bool *refcounted) { struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr, - sport, daddr, hnum, dif); + sport, daddr, hnum, + dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, - daddr, hnum, dif); + daddr, hnum, dif, sdif); } static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, - int iif, + int iif, int sdif, bool *refcounted) { struct sock *sk = skb_steal_sock(skb); @@ -95,7 +98,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, doff, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), - iif, refcounted); + iif, sdif, refcounted); } struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, @@ -107,13 +110,14 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, int inet6_hash(struct sock *sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ -#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ +#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif))) && \ + ((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 5026b1f08bb8..2dbbbff5e1e3 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -221,16 +221,16 @@ struct sock *__inet_lookup_listener(struct net *net, const __be32 saddr, const __be16 sport, const __be32 daddr, const unsigned short hnum, - const int dif); + const int dif, const int sdif); static inline struct sock *inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, __be16 dport, int dif) + __be32 daddr, __be16 dport, int dif, int sdif) { return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport, - daddr, ntohs(dport), dif); + daddr, ntohs(dport), dif, sdif); } /* Socket demux engine toys. */ @@ -262,22 +262,24 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__force __u64)(__be32)(__daddr)) << 32) | \ ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \ +#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_addrpair == (__cookie)) && \ (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif))) && \ + ((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #else /* 32-bit arch */ #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const int __name __deprecated __attribute__((unused)) -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif) \ +#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_daddr == (__saddr)) && \ ((__sk)->sk_rcv_saddr == (__daddr)) && \ (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif))) && \ + ((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* 64-bit arch */ @@ -288,7 +290,7 @@ struct sock *__inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 hnum, - const int dif); + const int dif, const int sdif); static inline struct sock * inet_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, @@ -297,7 +299,7 @@ static inline struct sock * const int dif) { return __inet_lookup_established(net, hashinfo, saddr, sport, daddr, - ntohs(dport), dif); + ntohs(dport), dif, 0); } static inline struct sock *__inet_lookup(struct net *net, @@ -305,20 +307,20 @@ static inline struct sock *__inet_lookup(struct net *net, struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, - const int dif, + const int dif, const int sdif, bool *refcounted) { u16 hnum = ntohs(dport); struct sock *sk; sk = __inet_lookup_established(net, hashinfo, saddr, sport, - daddr, hnum, dif); + daddr, hnum, dif, sdif); *refcounted = true; if (sk) return sk; *refcounted = false; return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, - sport, daddr, hnum, dif); + sport, daddr, hnum, dif, sdif); } static inline struct sock *inet_lookup(struct net *net, @@ -332,7 +334,7 @@ static inline struct sock *inet_lookup(struct net *net, bool refcounted; sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, - dport, dif, &refcounted); + dport, dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; @@ -344,6 +346,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, int doff, const __be16 sport, const __be16 dport, + const int sdif, bool *refcounted) { struct sock *sk = skb_steal_sock(skb); @@ -355,7 +358,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, doff, iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), + iph->daddr, dport, inet_iif(skb), sdif, refcounted); } diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index f2a215fc78e4..950ed182f62f 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -33,18 +33,12 @@ struct inetpeer_addr { }; struct inet_peer { - /* group together avl_left,avl_right,v4daddr to speedup lookups */ - struct inet_peer __rcu *avl_left, *avl_right; + struct rb_node rb_node; struct inetpeer_addr daddr; - __u32 avl_height; u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ unsigned long rate_last; - union { - struct list_head gc_list; - struct rcu_head gc_rcu; - }; /* * Once inet_peer is queued for deletion (refcnt == 0), following field * is not available: rid @@ -55,7 +49,6 @@ struct inet_peer { atomic_t rid; /* Frag reception counter */ }; struct rcu_head rcu; - struct inet_peer *gc_next; }; /* following fields might be frequently dirtied */ @@ -64,7 +57,7 @@ struct inet_peer { }; struct inet_peer_base { - struct inet_peer __rcu *root; + struct rb_root rb_root; seqlock_t lock; int total; }; diff --git a/include/net/ip.h b/include/net/ip.h index 821cedcc8e73..39db596eb89f 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -78,6 +78,16 @@ struct ipcm_cookie { #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb)) +/* return enslaved device index if relevant */ +static inline int inet_sdif(struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) + return IPCB(skb)->iif; +#endif + return 0; +} + struct ip_ra_chain { struct ip_ra_chain __rcu *next; struct sock *sk; @@ -567,11 +577,12 @@ int ip_forward(struct sk_buff *skb); void ip_options_build(struct sk_buff *skb, struct ip_options *opt, __be32 daddr, struct rtable *rt, int is_frag); -int __ip_options_echo(struct ip_options *dopt, struct sk_buff *skb, - const struct ip_options *sopt); -static inline int ip_options_echo(struct ip_options *dopt, struct sk_buff *skb) +int __ip_options_echo(struct net *net, struct ip_options *dopt, + struct sk_buff *skb, const struct ip_options *sopt); +static inline int ip_options_echo(struct net *net, struct ip_options *dopt, + struct sk_buff *skb) { - return __ip_options_echo(dopt, skb, &IPCB(skb)->opt); + return __ip_options_echo(net, dopt, skb, &IPCB(skb)->opt); } void ip_options_fragment(struct sk_buff *skb); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1a88008cc6f5..71c1646298ae 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -16,10 +16,12 @@ #include <linux/ipv6_route.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> +#include <linux/notifier.h> #include <net/dst.h> #include <net/flow.h> #include <net/netlink.h> #include <net/inetpeer.h> +#include <net/fib_notifier.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 @@ -118,6 +120,8 @@ struct rt6_info { atomic_t rt6i_ref; + unsigned int rt6i_nh_flags; + /* These are in a separate cache line. */ struct rt6key rt6i_dst ____cacheline_aligned_in_smp; u32 rt6i_flags; @@ -185,6 +189,22 @@ static inline void ip6_rt_put(struct rt6_info *rt) dst_release(&rt->dst); } +void rt6_free_pcpu(struct rt6_info *non_pcpu_rt); + +static inline void rt6_hold(struct rt6_info *rt) +{ + atomic_inc(&rt->rt6i_ref); +} + +static inline void rt6_release(struct rt6_info *rt) +{ + if (atomic_dec_and_test(&rt->rt6i_ref)) { + rt6_free_pcpu(rt); + dst_dev_put(&rt->dst); + dst_release(&rt->dst); + } +} + enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, @@ -233,6 +253,7 @@ struct fib6_table { struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; + unsigned int fib_seq; #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; @@ -256,6 +277,11 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, struct flowi6 *, int); +struct fib6_entry_notifier_info { + struct fib_notifier_info info; /* must be first */ + struct rt6_info *rt; +}; + /* * exported functions */ @@ -292,9 +318,24 @@ int fib6_init(void); int ipv6_route_open(struct inode *inode, struct file *file); +int call_fib6_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, + struct fib_notifier_info *info); +int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info); + +int __net_init fib6_notifier_init(struct net *net); +void __net_exit fib6_notifier_exit(struct net *net); + +unsigned int fib6_tables_seq_read(struct net *net); +int fib6_tables_dump(struct net *net, struct notifier_block *nb); + #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); void fib6_rules_cleanup(void); +bool fib6_rule_default(const struct fib_rule *rule); +int fib6_rules_dump(struct net *net, struct notifier_block *nb); +unsigned int fib6_rules_seq_read(struct net *net); #else static inline int fib6_rules_init(void) { @@ -304,5 +345,17 @@ static inline void fib6_rules_cleanup(void) { return ; } +static inline bool fib6_rule_default(const struct fib_rule *rule) +{ + return true; +} +static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} +static inline unsigned int fib6_rules_seq_read(struct net *net) +{ + return 0; +} #endif #endif diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 199056933dcb..907d39a42f6b 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -194,7 +194,7 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, struct rt6_info *rt = (struct rt6_info *)dst; return rt->rt6i_flags & RTF_ANYCAST || - (rt->rt6i_dst.plen != 128 && + (rt->rt6i_dst.plen < 127 && ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)); } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 41d580c6185f..1a7f7e424320 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -19,6 +19,7 @@ #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> +#include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inetpeer.h> #include <linux/percpu.h> @@ -124,7 +125,6 @@ struct fib_info { #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_weight; #endif - unsigned int fib_offload_cnt; struct rcu_head rcu; struct fib_nh fib_nh[0]; #define fib_dev fib_nh[0].nh_dev @@ -177,18 +177,6 @@ struct fib_result_nl { __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); -static inline void fib_info_offload_inc(struct fib_info *fi) -{ - fi->fib_offload_cnt++; - fi->fib_flags |= RTNH_F_OFFLOAD; -} - -static inline void fib_info_offload_dec(struct fib_info *fi) -{ - if (--fi->fib_offload_cnt == 0) - fi->fib_flags &= ~RTNH_F_OFFLOAD; -} - #define FIB_RES_SADDR(net, res) \ ((FIB_RES_NH(res).nh_saddr_genid == \ atomic_read(&(net)->ipv4.dev_addr_genid)) ? \ @@ -201,10 +189,6 @@ static inline void fib_info_offload_dec(struct fib_info *fi) #define FIB_RES_PREFSRC(net, res) ((res).fi->fib_prefsrc ? : \ FIB_RES_SADDR(net, res)) -struct fib_notifier_info { - struct net *net; -}; - struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; @@ -215,44 +199,21 @@ struct fib_entry_notifier_info { u32 tb_id; }; -struct fib_rule_notifier_info { - struct fib_notifier_info info; /* must be first */ - struct fib_rule *rule; -}; - struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; -enum fib_event_type { - FIB_EVENT_ENTRY_REPLACE, - FIB_EVENT_ENTRY_APPEND, - FIB_EVENT_ENTRY_ADD, - FIB_EVENT_ENTRY_DEL, - FIB_EVENT_RULE_ADD, - FIB_EVENT_RULE_DEL, - FIB_EVENT_NH_ADD, - FIB_EVENT_NH_DEL, -}; - -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)); -int unregister_fib_notifier(struct notifier_block *nb); -int call_fib_notifier(struct notifier_block *nb, struct net *net, - enum fib_event_type event_type, - struct fib_notifier_info *info); -int call_fib_notifiers(struct net *net, enum fib_event_type event_type, +int call_fib4_notifier(struct notifier_block *nb, struct net *net, + enum fib_event_type event_type, struct fib_notifier_info *info); +int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, + struct fib_notifier_info *info); + +int __net_init fib4_notifier_init(struct net *net); +void __net_exit fib4_notifier_exit(struct net *net); void fib_notify(struct net *net, struct notifier_block *nb); -#ifdef CONFIG_IP_MULTIPLE_TABLES -void fib_rules_notify(struct net *net, struct notifier_block *nb); -#else -static inline void fib_rules_notify(struct net *net, struct notifier_block *nb) -{ -} -#endif struct fib_table { struct hlist_node tb_hlist; @@ -325,6 +286,16 @@ static inline bool fib4_rule_default(const struct fib_rule *rule) return true; } +static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb) +{ + return 0; +} + +static inline unsigned int fib4_rules_seq_read(struct net *net) +{ + return 0; +} + #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); @@ -370,6 +341,8 @@ out: } bool fib4_rule_default(const struct fib_rule *rule); +int fib4_rules_dump(struct net *net, struct notifier_block *nb); +unsigned int fib4_rules_seq_read(struct net *net); #endif /* CONFIG_IP_MULTIPLE_TABLES */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1c401bd4c2e0..57faa375eab9 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -88,6 +88,7 @@ struct net { /* core fib_rules */ struct list_head rules_ops; + struct list_head fib_notifier_ops; /* protected by net_mutex */ struct net_device *loopback_dev; /* The loopback */ struct netns_core core; diff --git a/include/net/netlink.h b/include/net/netlink.h index ef8e6c3a80a6..82dd298b40c7 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -178,6 +178,7 @@ enum { NLA_S16, NLA_S32, NLA_S64, + NLA_BITFIELD32, __NLA_TYPE_MAX, }; @@ -206,6 +207,7 @@ enum { * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" + * NLA_BITFIELD32 A 32-bit bitmap/bitselector attribute * All other Minimum length of attribute payload * * Example: @@ -213,11 +215,13 @@ enum { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .len = sizeof(struct mystruct) }, + * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, * }; */ struct nla_policy { u16 type; u16 len; + void *validation_data; }; /** @@ -1203,6 +1207,18 @@ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) } /** + * nla_get_bitfield32 - return payload of 32 bitfield attribute + * @nla: nla_bitfield32 attribute + */ +static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) +{ + struct nla_bitfield32 tmp; + + nla_memcpy(&tmp, nla, sizeof(tmp)); + return tmp; +} + +/** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from * @gfp: GFP mask diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 9a14a0850b0e..20d061c805e3 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -159,6 +159,7 @@ struct netns_ipv4 { int sysctl_fib_multipath_hash_policy; #endif + struct fib_notifier_ops *notifier_ops; unsigned int fib_seq; /* protected by rtnl_mutex */ atomic_t rt_genid; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index de7745e2edcc..0e50bf3ed097 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -65,6 +65,7 @@ struct netns_ipv6 { unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES + bool fib6_has_custom_rules; struct rt6_info *ip6_prohibit_entry; struct rt6_info *ip6_blk_hole_entry; struct fib6_table *fib6_local_tbl; @@ -86,6 +87,7 @@ struct netns_ipv6 { atomic_t dev_addr_genid; atomic_t fib6_sernum; struct seg6_pernet_data *seg6_data; + struct fib_notifier_ops *notifier_ops; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 27bb9633c69d..611521646dd4 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -6,7 +6,6 @@ #include <linux/workqueue.h> #include <linux/xfrm.h> #include <net/dst_ops.h> -#include <net/flowcache.h> struct ctl_table_header; @@ -73,16 +72,6 @@ struct netns_xfrm { spinlock_t xfrm_state_lock; spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; - - /* flow cache part */ - struct flow_cache flow_cache_global; - atomic_t flow_cache_genid; - struct list_head flow_cache_gc_list; - atomic_t flow_cache_gc_count; - spinlock_t flow_cache_gc_lock; - struct work_struct flow_cache_gc_work; - struct work_struct flow_cache_flush_work; - struct mutex flow_flush_sem; }; #endif diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 537d0a0ad4c4..e80edd8879ef 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -11,7 +11,7 @@ struct tcf_walker { int stop; int skip; int count; - int (*fn)(struct tcf_proto *, unsigned long node, struct tcf_walker *); + int (*fn)(struct tcf_proto *, void *node, struct tcf_walker *); }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); @@ -113,36 +113,6 @@ static inline int tcf_exts_init(struct tcf_exts *exts, int action, int police) return 0; } -/** - * tcf_exts_is_predicative - check if a predicative extension is present - * @exts: tc filter extensions handle - * - * Returns 1 if a predicative extension is present, i.e. an extension which - * might cause further actions and thus overrule the regular tcf_result. - */ -static inline int -tcf_exts_is_predicative(struct tcf_exts *exts) -{ -#ifdef CONFIG_NET_CLS_ACT - return exts->nr_actions; -#else - return 0; -#endif -} - -/** - * tcf_exts_is_available - check if at least one extension is present - * @exts: tc filter extensions handle - * - * Returns 1 if at least one extension is present. - */ -static inline int -tcf_exts_is_available(struct tcf_exts *exts) -{ - /* All non-predicative extensions must be added here. */ - return tcf_exts_is_predicative(exts); -} - static inline void tcf_exts_to_list(const struct tcf_exts *exts, struct list_head *actions) { @@ -177,46 +147,61 @@ tcf_exts_stats_update(const struct tcf_exts *exts, } /** + * tcf_exts_has_actions - check if at least one action is present + * @exts: tc filter extensions handle + * + * Returns true if at least one action is present. + */ +static inline bool tcf_exts_has_actions(struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + return exts->nr_actions; +#else + return false; +#endif +} + +/** + * tcf_exts_has_one_action - check if exactly one action is present + * @exts: tc filter extensions handle + * + * Returns true if exactly one action is present. + */ +static inline bool tcf_exts_has_one_action(struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + return exts->nr_actions == 1; +#else + return false; +#endif +} + +/** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer * @exts: tc filter extensions handle * @res: desired result * - * Executes all configured extensions. Returns 0 on a normal execution, + * Executes all configured extensions. Returns TC_ACT_OK on a normal execution, * a negative number if the filter must be considered unmatched or * a positive action code (TC_ACT_*) which must be returned to the * underlying layer. */ static inline int tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, - struct tcf_result *res) + struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT - if (exts->nr_actions) - return tcf_action_exec(skb, exts->actions, exts->nr_actions, - res); + return tcf_action_exec(skb, exts->actions, exts->nr_actions, res); #endif - return 0; + return TC_ACT_OK; } -#ifdef CONFIG_NET_CLS_ACT - -#define tc_no_actions(_exts) ((_exts)->nr_actions == 0) -#define tc_single_action(_exts) ((_exts)->nr_actions == 1) - -#else /* CONFIG_NET_CLS_ACT */ - -#define tc_no_actions(_exts) true -#define tc_single_action(_exts) false - -#endif /* CONFIG_NET_CLS_ACT */ - int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr); void tcf_exts_destroy(struct tcf_exts *exts); -void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, - struct tcf_exts *src); +void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts); int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts, @@ -333,26 +318,6 @@ int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, struct tcf_pkt_info *); /** - * tcf_em_tree_change - replace ematch tree of a running classifier - * - * @tp: classifier kind handle - * @dst: destination ematch tree variable - * @src: source ematch tree (temporary tree from tcf_em_tree_validate) - * - * This functions replaces the ematch tree in @dst with the ematch - * tree in @src. The classifier in charge of the ematch tree may be - * running. - */ -static inline void tcf_em_tree_change(struct tcf_proto *tp, - struct tcf_ematch_tree *dst, - struct tcf_ematch_tree *src) -{ - tcf_tree_lock(tp); - memcpy(dst, src, sizeof(*dst)); - tcf_tree_unlock(tp); -} - -/** * tcf_em_tree_match - evaulate an ematch tree * * @skb: socket buffer of the packet in question @@ -386,7 +351,6 @@ struct tcf_ematch_tree { #define tcf_em_tree_validate(tp, tb, t) ((void)(t), 0) #define tcf_em_tree_destroy(t) do { (void)(t); } while(0) #define tcf_em_tree_dump(skb, t, tlv) (0) -#define tcf_em_tree_change(tp, dst, src) do { } while(0) #define tcf_em_tree_match(skb, t, info) ((void)(info), 1) #endif /* CONFIG_NET_EMATCH */ @@ -441,6 +405,23 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +struct tc_cls_common_offload { + u32 chain_index; + __be16 protocol; + u32 prio; + u32 classid; +}; + +static inline void +tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common, + const struct tcf_proto *tp) +{ + cls_common->chain_index = tp->chain->index; + cls_common->protocol = tp->protocol; + cls_common->prio = tp->prio; + cls_common->classid = tp->classid; +} + struct tc_cls_u32_knode { struct tcf_exts *exts; struct tc_u32_sel *sel; @@ -467,6 +448,7 @@ enum tc_clsu32_command { }; struct tc_cls_u32_offload { + struct tc_cls_common_offload common; /* knode values */ enum tc_clsu32_command command; union { @@ -475,19 +457,12 @@ struct tc_cls_u32_offload { }; }; -static inline bool tc_can_offload(const struct net_device *dev, - const struct tcf_proto *tp) +static inline bool tc_can_offload(const struct net_device *dev) { - const struct Qdisc *sch = tp->q; - const struct Qdisc_class_ops *cops = sch->ops->cl_ops; - if (!(dev->features & NETIF_F_HW_TC)) return false; if (!dev->netdev_ops->ndo_setup_tc) return false; - if (cops && cops->tcf_cl_offload) - return cops->tcf_cl_offload(tp->classid); - return true; } @@ -496,12 +471,11 @@ static inline bool tc_skip_hw(u32 flags) return (flags & TCA_CLS_FLAGS_SKIP_HW) ? true : false; } -static inline bool tc_should_offload(const struct net_device *dev, - const struct tcf_proto *tp, u32 flags) +static inline bool tc_should_offload(const struct net_device *dev, u32 flags) { if (tc_skip_hw(flags)) return false; - return tc_can_offload(dev, tp); + return tc_can_offload(dev); } static inline bool tc_skip_sw(u32 flags) @@ -533,13 +507,14 @@ enum tc_fl_command { }; struct tc_cls_flower_offload { + struct tc_cls_common_offload common; enum tc_fl_command command; - u32 prio; unsigned long cookie; struct flow_dissector *dissector; struct fl_flow_key *mask; struct fl_flow_key *key; struct tcf_exts *exts; + bool egress_dev; }; enum tc_matchall_command { @@ -548,6 +523,7 @@ enum tc_matchall_command { }; struct tc_cls_matchall_offload { + struct tc_cls_common_offload common; enum tc_matchall_command command; struct tcf_exts *exts; unsigned long cookie; @@ -561,6 +537,7 @@ enum tc_clsbpf_command { }; struct tc_cls_bpf_offload { + struct tc_cls_common_offload common; enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 2579c209ea51..259bc191ba59 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -5,6 +5,7 @@ #include <linux/ktime.h> #include <linux/if_vlan.h> #include <net/sch_generic.h> +#include <uapi/linux/pkt_sched.h> #define DEFAULT_TX_QUEUE_LEN 1000 @@ -132,4 +133,17 @@ static inline unsigned int psched_mtu(const struct net_device *dev) return dev->mtu + dev->hard_header_len; } +static inline bool is_classid_clsact_ingress(u32 classid) +{ + /* This also returns true for ingress qdisc */ + return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) && + TC_H_MIN(classid) != TC_H_MIN(TC_H_MIN_EGRESS); +} + +static inline bool is_classid_clsact_egress(u32 classid) +{ + return TC_H_MAJ(classid) == TC_H_MAJ(TC_H_CLSACT) && + TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS); +} + #endif diff --git a/include/net/raw.h b/include/net/raw.h index 57c33dd22ec4..99d26d0c4a19 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -26,7 +26,7 @@ extern struct proto raw_prot; extern struct raw_hashinfo raw_v4_hashinfo; struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, unsigned short num, __be32 raddr, - __be32 laddr, int dif); + __be32 laddr, int dif, int sdif); int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index cbe4e9de1894..4addc5c988e0 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -6,7 +6,7 @@ extern struct raw_hashinfo raw_v6_hashinfo; struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, - const struct in6_addr *rmt_addr, int dif); + const struct in6_addr *rmt_addr, int dif, int sdif); int raw_abort(struct sock *sk, int err); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index abe6b733d473..21837ca68ecc 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -7,12 +7,15 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *); typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); -typedef u16 (*rtnl_calcit_func)(struct sk_buff *, struct nlmsghdr *); + +enum rtnl_link_flags { + RTNL_FLAG_DOIT_UNLOCKED = 1, +}; int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, rtnl_calcit_func); + rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); void rtnl_register(int protocol, int msgtype, - rtnl_doit_func, rtnl_dumpit_func, rtnl_calcit_func); + rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_unregister(int protocol, int msgtype); void rtnl_unregister_all(int protocol); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1c123e2b2415..5865db91976b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -156,7 +156,6 @@ struct Qdisc_class_ops { /* Filter manipulation */ struct tcf_block * (*tcf_block)(struct Qdisc *, unsigned long); - bool (*tcf_cl_offload)(u32 classid); unsigned long (*bind_tcf)(struct Qdisc *, unsigned long, u32 classid); void (*unbind_tcf)(struct Qdisc *, unsigned long); @@ -213,16 +212,16 @@ struct tcf_proto_ops { int (*init)(struct tcf_proto*); void (*destroy)(struct tcf_proto*); - unsigned long (*get)(struct tcf_proto*, u32 handle); + void* (*get)(struct tcf_proto*, u32 handle); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, - unsigned long *, bool); - int (*delete)(struct tcf_proto*, unsigned long, bool*); + void **, bool); + int (*delete)(struct tcf_proto*, void *, bool*); void (*walk)(struct tcf_proto*, struct tcf_walker *arg); /* rtnetlink specific */ - int (*dump)(struct net*, struct tcf_proto*, unsigned long, + int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*); struct module *owner; diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h index d4679e7a5ed5..b55c6a48a206 100644 --- a/include/net/sctp/command.h +++ b/include/net/sctp/command.h @@ -40,7 +40,7 @@ #include <net/sctp/structs.h> -typedef enum { +enum sctp_verb { SCTP_CMD_NOP = 0, /* Do nothing. */ SCTP_CMD_NEW_ASOC, /* Register a new association. */ SCTP_CMD_DELETE_TCB, /* Delete the current association. */ @@ -108,16 +108,16 @@ typedef enum { SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/ SCTP_CMD_SET_ASOC, /* Restore association context */ SCTP_CMD_LAST -} sctp_verb_t; +}; -/* How many commands can you put in an sctp_cmd_seq_t? +/* How many commands can you put in an struct sctp_cmd_seq? * This is a rather arbitrary number, ideally derived from a careful * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ #define SCTP_MAX_NUM_COMMANDS 20 -typedef union { +union sctp_arg { void *zero_all; /* Set to NULL to clear the entire union */ __s32 i32; __u32 u32; @@ -126,8 +126,8 @@ typedef union { __u8 u8; int error; __be16 err; - sctp_state_t state; - sctp_event_timeout_t to; + enum sctp_state state; + enum sctp_event_timeout to; struct sctp_chunk *chunk; struct sctp_association *asoc; struct sctp_transport *transport; @@ -135,26 +135,26 @@ typedef union { struct sctp_init_chunk *init; struct sctp_ulpevent *ulpevent; struct sctp_packet *packet; - sctp_sackhdr_t *sackh; + struct sctp_sackhdr *sackh; struct sctp_datamsg *msg; -} sctp_arg_t; +}; /* We are simulating ML type constructors here. * * SCTP_ARG_CONSTRUCTOR(NAME, TYPE, ELT) builds a function called * SCTP_NAME() which takes an argument of type TYPE and returns an - * sctp_arg_t. It does this by inserting the sole argument into the - * ELT union element of a local sctp_arg_t. + * union sctp_arg. It does this by inserting the sole argument into + * the ELT union element of a local union sctp_arg. * * E.g., SCTP_ARG_CONSTRUCTOR(I32, __s32, i32) builds SCTP_I32(arg), - * which takes an __s32 and returns a sctp_arg_t containing the + * which takes an __s32 and returns a union sctp_arg containing the * __s32. So, after foo = SCTP_I32(arg), foo.i32 == arg. */ #define SCTP_ARG_CONSTRUCTOR(name, type, elt) \ -static inline sctp_arg_t \ +static inline union sctp_arg \ SCTP_## name (type arg) \ -{ sctp_arg_t retval;\ +{ union sctp_arg retval;\ retval.zero_all = NULL;\ retval.elt = arg;\ return retval;\ @@ -167,8 +167,8 @@ SCTP_ARG_CONSTRUCTOR(U16, __u16, u16) SCTP_ARG_CONSTRUCTOR(U8, __u8, u8) SCTP_ARG_CONSTRUCTOR(ERROR, int, error) SCTP_ARG_CONSTRUCTOR(PERR, __be16, err) /* protocol error */ -SCTP_ARG_CONSTRUCTOR(STATE, sctp_state_t, state) -SCTP_ARG_CONSTRUCTOR(TO, sctp_event_timeout_t, to) +SCTP_ARG_CONSTRUCTOR(STATE, enum sctp_state, state) +SCTP_ARG_CONSTRUCTOR(TO, enum sctp_event_timeout, to) SCTP_ARG_CONSTRUCTOR(CHUNK, struct sctp_chunk *, chunk) SCTP_ARG_CONSTRUCTOR(ASOC, struct sctp_association *, asoc) SCTP_ARG_CONSTRUCTOR(TRANSPORT, struct sctp_transport *, transport) @@ -176,42 +176,42 @@ SCTP_ARG_CONSTRUCTOR(BA, struct sctp_bind_addr *, bp) SCTP_ARG_CONSTRUCTOR(PEER_INIT, struct sctp_init_chunk *, init) SCTP_ARG_CONSTRUCTOR(ULPEVENT, struct sctp_ulpevent *, ulpevent) SCTP_ARG_CONSTRUCTOR(PACKET, struct sctp_packet *, packet) -SCTP_ARG_CONSTRUCTOR(SACKH, sctp_sackhdr_t *, sackh) +SCTP_ARG_CONSTRUCTOR(SACKH, struct sctp_sackhdr *, sackh) SCTP_ARG_CONSTRUCTOR(DATAMSG, struct sctp_datamsg *, msg) -static inline sctp_arg_t SCTP_FORCE(void) +static inline union sctp_arg SCTP_FORCE(void) { return SCTP_I32(1); } -static inline sctp_arg_t SCTP_NOFORCE(void) +static inline union sctp_arg SCTP_NOFORCE(void) { return SCTP_I32(0); } -static inline sctp_arg_t SCTP_NULL(void) +static inline union sctp_arg SCTP_NULL(void) { - sctp_arg_t retval; + union sctp_arg retval; retval.zero_all = NULL; return retval; } -typedef struct { - sctp_arg_t obj; - sctp_verb_t verb; -} sctp_cmd_t; +struct sctp_cmd { + union sctp_arg obj; + enum sctp_verb verb; +}; -typedef struct { - sctp_cmd_t cmds[SCTP_MAX_NUM_COMMANDS]; - sctp_cmd_t *last_used_slot; - sctp_cmd_t *next_cmd; -} sctp_cmd_seq_t; +struct sctp_cmd_seq { + struct sctp_cmd cmds[SCTP_MAX_NUM_COMMANDS]; + struct sctp_cmd *last_used_slot; + struct sctp_cmd *next_cmd; +}; /* Initialize a block of memory as a command sequence. * Return 0 if the initialization fails. */ -static inline int sctp_init_cmd_seq(sctp_cmd_seq_t *seq) +static inline int sctp_init_cmd_seq(struct sctp_cmd_seq *seq) { /* cmds[] is filled backwards to simplify the overflow BUG() check */ seq->last_used_slot = seq->cmds + SCTP_MAX_NUM_COMMANDS; @@ -220,15 +220,15 @@ static inline int sctp_init_cmd_seq(sctp_cmd_seq_t *seq) } -/* Add a command to an sctp_cmd_seq_t. +/* Add a command to an struct sctp_cmd_seq. * * Use the SCTP_* constructors defined by SCTP_ARG_CONSTRUCTOR() above * to wrap data which goes in the obj argument. */ -static inline void sctp_add_cmd_sf(sctp_cmd_seq_t *seq, sctp_verb_t verb, - sctp_arg_t obj) +static inline void sctp_add_cmd_sf(struct sctp_cmd_seq *seq, + enum sctp_verb verb, union sctp_arg obj) { - sctp_cmd_t *cmd = seq->last_used_slot - 1; + struct sctp_cmd *cmd = seq->last_used_slot - 1; BUG_ON(cmd < seq->cmds); @@ -240,7 +240,7 @@ static inline void sctp_add_cmd_sf(sctp_cmd_seq_t *seq, sctp_verb_t verb, /* Return the next command structure in an sctp_cmd_seq. * Return NULL at the end of the sequence. */ -static inline sctp_cmd_t *sctp_next_cmd(sctp_cmd_seq_t *seq) +static inline struct sctp_cmd *sctp_next_cmd(struct sctp_cmd_seq *seq) { if (seq->next_cmd <= seq->last_used_slot) return NULL; diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 9b18044c551e..deaafa9b09cb 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -42,7 +42,7 @@ #include <linux/sctp.h> #include <linux/ipv6.h> /* For ipv6hdr. */ -#include <net/tcp_states.h> /* For TCP states used in sctp_sock_state_t */ +#include <net/tcp_states.h> /* For TCP states used in enum sctp_sock_state */ /* Value used for stream negotiation. */ enum { SCTP_MAX_STREAM = 0xffff }; @@ -71,20 +71,18 @@ enum { SCTP_DEFAULT_INSTREAMS = SCTP_MAX_STREAM }; SCTP_NUM_AUTH_CHUNK_TYPES) /* These are the different flavours of event. */ -typedef enum { - +enum sctp_event { SCTP_EVENT_T_CHUNK = 1, SCTP_EVENT_T_TIMEOUT, SCTP_EVENT_T_OTHER, SCTP_EVENT_T_PRIMITIVE - -} sctp_event_t; +}; /* As a convenience for the state machine, we append SCTP_EVENT_* and * SCTP_ULP_* to the list of possible chunks. */ -typedef enum { +enum sctp_event_timeout { SCTP_EVENT_TIMEOUT_NONE = 0, SCTP_EVENT_TIMEOUT_T1_COOKIE, SCTP_EVENT_TIMEOUT_T1_INIT, @@ -96,21 +94,21 @@ typedef enum { SCTP_EVENT_TIMEOUT_RECONF, SCTP_EVENT_TIMEOUT_SACK, SCTP_EVENT_TIMEOUT_AUTOCLOSE, -} sctp_event_timeout_t; +}; #define SCTP_EVENT_TIMEOUT_MAX SCTP_EVENT_TIMEOUT_AUTOCLOSE #define SCTP_NUM_TIMEOUT_TYPES (SCTP_EVENT_TIMEOUT_MAX + 1) -typedef enum { +enum sctp_event_other { SCTP_EVENT_NO_PENDING_TSN = 0, SCTP_EVENT_ICMP_PROTO_UNREACH, -} sctp_event_other_t; +}; #define SCTP_EVENT_OTHER_MAX SCTP_EVENT_ICMP_PROTO_UNREACH #define SCTP_NUM_OTHER_TYPES (SCTP_EVENT_OTHER_MAX + 1) /* These are primitive requests from the ULP. */ -typedef enum { +enum sctp_event_primitive { SCTP_PRIMITIVE_ASSOCIATE = 0, SCTP_PRIMITIVE_SHUTDOWN, SCTP_PRIMITIVE_ABORT, @@ -118,7 +116,7 @@ typedef enum { SCTP_PRIMITIVE_REQUESTHEARTBEAT, SCTP_PRIMITIVE_ASCONF, SCTP_PRIMITIVE_RECONF, -} sctp_event_primitive_t; +}; #define SCTP_EVENT_PRIMITIVE_MAX SCTP_PRIMITIVE_RECONF #define SCTP_NUM_PRIMITIVE_TYPES (SCTP_EVENT_PRIMITIVE_MAX + 1) @@ -126,25 +124,25 @@ typedef enum { /* We define here a utility type for manipulating subtypes. * The subtype constructors all work like this: * - * sctp_subtype_t foo = SCTP_ST_CHUNK(SCTP_CID_INIT); + * union sctp_subtype foo = SCTP_ST_CHUNK(SCTP_CID_INIT); */ -typedef union { +union sctp_subtype { enum sctp_cid chunk; - sctp_event_timeout_t timeout; - sctp_event_other_t other; - sctp_event_primitive_t primitive; -} sctp_subtype_t; + enum sctp_event_timeout timeout; + enum sctp_event_other other; + enum sctp_event_primitive primitive; +}; #define SCTP_SUBTYPE_CONSTRUCTOR(_name, _type, _elt) \ -static inline sctp_subtype_t \ +static inline union sctp_subtype \ SCTP_ST_## _name (_type _arg) \ -{ sctp_subtype_t _retval; _retval._elt = _arg; return _retval; } +{ union sctp_subtype _retval; _retval._elt = _arg; return _retval; } SCTP_SUBTYPE_CONSTRUCTOR(CHUNK, enum sctp_cid, chunk) -SCTP_SUBTYPE_CONSTRUCTOR(TIMEOUT, sctp_event_timeout_t, timeout) -SCTP_SUBTYPE_CONSTRUCTOR(OTHER, sctp_event_other_t, other) -SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, sctp_event_primitive_t, primitive) +SCTP_SUBTYPE_CONSTRUCTOR(TIMEOUT, enum sctp_event_timeout, timeout) +SCTP_SUBTYPE_CONSTRUCTOR(OTHER, enum sctp_event_other, other) +SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, enum sctp_event_primitive, primitive) #define sctp_chunk_is_data(a) (a->chunk_hdr->type == SCTP_CID_DATA) @@ -155,8 +153,7 @@ SCTP_SUBTYPE_CONSTRUCTOR(PRIMITIVE, sctp_event_primitive_t, primitive) - sizeof(struct sctp_data_chunk))) /* Internal error codes */ -typedef enum { - +enum sctp_ierror { SCTP_IERROR_NO_ERROR = 0, SCTP_IERROR_BASE = 1000, SCTP_IERROR_NO_COOKIE, @@ -177,12 +174,12 @@ typedef enum { SCTP_IERROR_PROTO_VIOLATION, SCTP_IERROR_ERROR, SCTP_IERROR_ABORT, -} sctp_ierror_t; +}; /* SCTP state defines for internal state machine */ -typedef enum { +enum sctp_state { SCTP_STATE_CLOSED = 0, SCTP_STATE_COOKIE_WAIT = 1, @@ -193,7 +190,7 @@ typedef enum { SCTP_STATE_SHUTDOWN_RECEIVED = 6, SCTP_STATE_SHUTDOWN_ACK_SENT = 7, -} sctp_state_t; +}; #define SCTP_STATE_MAX SCTP_STATE_SHUTDOWN_ACK_SENT #define SCTP_STATE_NUM_STATES (SCTP_STATE_MAX + 1) @@ -214,19 +211,19 @@ typedef enum { * - A socket in SCTP_SS_ESTABLISHED state indicates that it has a single * association. */ -typedef enum { +enum sctp_sock_state { SCTP_SS_CLOSED = TCP_CLOSE, SCTP_SS_LISTENING = TCP_LISTEN, SCTP_SS_ESTABLISHING = TCP_SYN_SENT, SCTP_SS_ESTABLISHED = TCP_ESTABLISHED, SCTP_SS_CLOSING = TCP_CLOSE_WAIT, -} sctp_sock_state_t; +}; /* These functions map various type to printable names. */ -const char *sctp_cname(const sctp_subtype_t); /* chunk types */ -const char *sctp_oname(const sctp_subtype_t); /* other events */ -const char *sctp_tname(const sctp_subtype_t); /* timeouts */ -const char *sctp_pname(const sctp_subtype_t); /* primitives */ +const char *sctp_cname(const union sctp_subtype id); /* chunk types */ +const char *sctp_oname(const union sctp_subtype id); /* other events */ +const char *sctp_tname(const union sctp_subtype id); /* timeouts */ +const char *sctp_pname(const union sctp_subtype id); /* primitives */ /* This is a table of printable names of sctp_state_t's. */ extern const char *const sctp_state_tbl[]; @@ -312,19 +309,19 @@ enum { SCTP_MAX_GABS = 16 }; /* These return values describe the success or failure of a number of * routines which form the lower interface to SCTP_outqueue. */ -typedef enum { +enum sctp_xmit { SCTP_XMIT_OK, SCTP_XMIT_PMTU_FULL, SCTP_XMIT_RWND_FULL, SCTP_XMIT_DELAY, -} sctp_xmit_t; +}; /* These are the commands for manipulating transports. */ -typedef enum { +enum sctp_transport_cmd { SCTP_TRANSPORT_UP, SCTP_TRANSPORT_DOWN, SCTP_TRANSPORT_PF, -} sctp_transport_cmd_t; +}; /* These are the address scopes defined mainly for IPv4 addresses * based on draft of SCTP IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>. @@ -333,20 +330,22 @@ typedef enum { * At this point, the IPv6 scopes will be mapped to these internal scopes * as much as possible. */ -typedef enum { +enum sctp_scope { SCTP_SCOPE_GLOBAL, /* IPv4 global addresses */ SCTP_SCOPE_PRIVATE, /* IPv4 private addresses */ SCTP_SCOPE_LINK, /* IPv4 link local address */ SCTP_SCOPE_LOOPBACK, /* IPv4 loopback address */ SCTP_SCOPE_UNUSABLE, /* IPv4 unusable addresses */ -} sctp_scope_t; +}; -typedef enum { +enum { SCTP_SCOPE_POLICY_DISABLE, /* Disable IPv4 address scoping */ SCTP_SCOPE_POLICY_ENABLE, /* Enable IPv4 address scoping */ SCTP_SCOPE_POLICY_PRIVATE, /* Follow draft but allow IPv4 private addresses */ SCTP_SCOPE_POLICY_LINK, /* Follow draft but allow IPv4 link local addresses */ -} sctp_scope_policy_t; +}; + +#define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK /* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>, * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24, @@ -370,20 +369,20 @@ typedef enum { peer */ /* Reasons to retransmit. */ -typedef enum { +enum sctp_retransmit_reason { SCTP_RTXR_T3_RTX, SCTP_RTXR_FAST_RTX, SCTP_RTXR_PMTUD, SCTP_RTXR_T1_RTX, -} sctp_retransmit_reason_t; +}; /* Reasons to lower cwnd. */ -typedef enum { +enum sctp_lower_cwnd { SCTP_LOWER_CWND_T3_RTX, SCTP_LOWER_CWND_FAST_RTX, SCTP_LOWER_CWND_ECNE, SCTP_LOWER_CWND_INACTIVE, -} sctp_lower_cwnd_t; +}; /* SCTP-AUTH Necessary constants */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 45fd4c6056b5..06b4f515e157 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -94,8 +94,8 @@ /* * sctp/protocol.c */ -int sctp_copy_local_addr_list(struct net *, struct sctp_bind_addr *, - sctp_scope_t, gfp_t gfp, int flags); +int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *addr, + enum sctp_scope, gfp_t gfp, int flags); struct sctp_pf *sctp_get_pf_specific(sa_family_t family); int sctp_register_pf(struct sctp_pf *, sa_family_t); void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int); @@ -479,13 +479,13 @@ for (pos.v = chunk->member;\ _sctp_walk_errors((err), (chunk_hdr), ntohs((chunk_hdr)->length)) #define _sctp_walk_errors(err, chunk_hdr, end)\ -for (err = (sctp_errhdr_t *)((void *)chunk_hdr + \ +for (err = (struct sctp_errhdr *)((void *)chunk_hdr + \ sizeof(struct sctp_chunkhdr));\ - ((void *)err + offsetof(sctp_errhdr_t, length) + sizeof(err->length) <=\ + ((void *)err + offsetof(struct sctp_errhdr, length) + sizeof(err->length) <=\ (void *)chunk_hdr + end) &&\ (void *)err <= (void *)chunk_hdr + end - ntohs(err->length) &&\ - ntohs(err->length) >= sizeof(sctp_errhdr_t); \ - err = (sctp_errhdr_t *)((void *)err + SCTP_PAD4(ntohs(err->length)))) + ntohs(err->length) >= sizeof(struct sctp_errhdr); \ + err = (struct sctp_errhdr *)((void *)err + SCTP_PAD4(ntohs(err->length)))) #define sctp_walk_fwdtsn(pos, chunk)\ _sctp_walk_fwdtsn((pos), (chunk), ntohs((chunk)->chunk_hdr->length) - sizeof(struct sctp_fwdtsn_chunk)) @@ -550,7 +550,8 @@ static inline int sctp_ep_hashfn(struct net *net, __u16 lport) /* Is a socket of this style? */ #define sctp_style(sk, style) __sctp_style((sk), (SCTP_SOCKET_##style)) -static inline int __sctp_style(const struct sock *sk, sctp_socket_type_t style) +static inline int __sctp_style(const struct sock *sk, + enum sctp_socket_type style) { return sctp_sk(sk)->type == style; } @@ -558,14 +559,15 @@ static inline int __sctp_style(const struct sock *sk, sctp_socket_type_t style) /* Is the association in this state? */ #define sctp_state(asoc, state) __sctp_state((asoc), (SCTP_STATE_##state)) static inline int __sctp_state(const struct sctp_association *asoc, - sctp_state_t state) + enum sctp_state state) { return asoc->state == state; } /* Is the socket in this state? */ #define sctp_sstate(sk, state) __sctp_sstate((sk), (SCTP_SS_##state)) -static inline int __sctp_sstate(const struct sock *sk, sctp_sock_state_t state) +static inline int __sctp_sstate(const struct sock *sk, + enum sctp_sock_state state) { return sk->sk_state == state; } diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 860f378333b5..2db3d3a9ce1d 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -53,7 +53,7 @@ /* * Possible values for the disposition are: */ -typedef enum { +enum sctp_disposition { SCTP_DISPOSITION_DISCARD, /* No further processing. */ SCTP_DISPOSITION_CONSUME, /* Process return values normally. */ SCTP_DISPOSITION_NOMEM, /* We ran out of memory--recover. */ @@ -63,24 +63,20 @@ typedef enum { SCTP_DISPOSITION_NOT_IMPL, /* This entry is not implemented. */ SCTP_DISPOSITION_ERROR, /* This is plain old user error. */ SCTP_DISPOSITION_BUG, /* This is a bug. */ -} sctp_disposition_t; - -typedef struct { - int name; - int action; -} sctp_sm_command_t; - -typedef sctp_disposition_t (sctp_state_fn_t) (struct net *, - const struct sctp_endpoint *, - const struct sctp_association *, - const sctp_subtype_t type, - void *arg, - sctp_cmd_seq_t *); +}; + +typedef enum sctp_disposition (sctp_state_fn_t) ( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); typedef void (sctp_timer_event_t) (unsigned long); -typedef struct { +struct sctp_sm_table_entry { sctp_state_fn_t *fn; const char *name; -} sctp_sm_table_entry_t; +}; /* A naming convention of "sctp_sf_xxx" applies to all the state functions * currently in use. @@ -175,10 +171,11 @@ sctp_state_fn_t sctp_sf_autoclose_timer_expire; /* Prototypes for utility support functions. */ __u8 sctp_get_chunk_type(struct sctp_chunk *chunk); -const sctp_sm_table_entry_t *sctp_sm_lookup_event(struct net *, - sctp_event_t, - sctp_state_t, - sctp_subtype_t); +const struct sctp_sm_table_entry *sctp_sm_lookup_event( + struct net *net, + enum sctp_event event_type, + enum sctp_state state, + union sctp_subtype event_subtype); int sctp_chunk_iif(const struct sctp_chunk *); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, @@ -187,68 +184,69 @@ __u32 sctp_generate_verification_tag(void); void sctp_populate_tie_tags(__u8 *cookie, __u32 curTag, __u32 hisTag); /* Prototypes for chunk-building functions. */ -struct sctp_chunk *sctp_make_init(const struct sctp_association *, - const struct sctp_bind_addr *, - gfp_t gfp, int vparam_len); -struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *, - const struct sctp_chunk *, - const gfp_t gfp, - const int unkparam_len); -struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *, - const struct sctp_chunk *); -struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *, - const struct sctp_chunk *); -struct sctp_chunk *sctp_make_cwr(const struct sctp_association *, +struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, + const struct sctp_bind_addr *bp, + gfp_t gfp, int vparam_len); +struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + const gfp_t gfp, const int unkparam_len); +struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, + const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, + const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, - const struct sctp_chunk *); -struct sctp_chunk * sctp_make_datafrag_empty(struct sctp_association *, - const struct sctp_sndrcvinfo *sinfo, - int len, const __u8 flags, - __u16 ssn, gfp_t gfp); -struct sctp_chunk *sctp_make_ecne(const struct sctp_association *, - const __u32); -struct sctp_chunk *sctp_make_sack(const struct sctp_association *); + const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_datafrag_empty(struct sctp_association *asoc, + const struct sctp_sndrcvinfo *sinfo, + int len, const __u8 flags, + __u16 ssn, gfp_t gfp); +struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, + const __u32 lowest_tsn); +struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc); struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, - const struct sctp_chunk *); -struct sctp_chunk *sctp_make_shutdown_complete(const struct sctp_association *, - const struct sctp_chunk *); -void sctp_init_cause(struct sctp_chunk *, __be16 cause, size_t); -struct sctp_chunk *sctp_make_abort(const struct sctp_association *, - const struct sctp_chunk *, - const size_t hint); -struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *, - const struct sctp_chunk *, - __u32 tsn); -struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *, - struct msghdr *, size_t msg_len); -struct sctp_chunk *sctp_make_abort_violation(const struct sctp_association *, - const struct sctp_chunk *, - const __u8 *, - const size_t ); -struct sctp_chunk *sctp_make_violation_paramlen(const struct sctp_association *, - const struct sctp_chunk *, - struct sctp_paramhdr *); -struct sctp_chunk *sctp_make_violation_max_retrans(const struct sctp_association *, - const struct sctp_chunk *); -struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *, - const struct sctp_transport *); -struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *, - const struct sctp_chunk *, - const void *payload, - const size_t paylen); -struct sctp_chunk *sctp_make_op_error(const struct sctp_association *, - const struct sctp_chunk *chunk, - __be16 cause_code, - const void *payload, - size_t paylen, - size_t reserve_tail); - -struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *, - union sctp_addr *, - struct sockaddr *, - int, __be16); + const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_shutdown_complete( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk); +void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen); +struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + const size_t hint); +struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + __u32 tsn); +struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, + struct msghdr *msg, size_t msg_len); +struct sctp_chunk *sctp_make_abort_violation( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + const __u8 *payload, + const size_t paylen); +struct sctp_chunk *sctp_make_violation_paramlen( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + struct sctp_paramhdr *param); +struct sctp_chunk *sctp_make_violation_max_retrans( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, + const struct sctp_transport *transport); +struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + const void *payload, + const size_t paylen); +struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, + const struct sctp_chunk *chunk, + __be16 cause_code, const void *payload, + size_t paylen, size_t reserve_tail); + +struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, + union sctp_addr *laddr, + struct sockaddr *addrs, + int addrcnt, __be16 flags); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); bool sctp_verify_asconf(const struct sctp_association *asoc, @@ -262,27 +260,25 @@ struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_fwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc); -struct sctp_chunk *sctp_make_strreset_req( - const struct sctp_association *asoc, - __u16 stream_num, __u16 *stream_list, - bool out, bool in); +struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc, + __u16 stream_num, __u16 *stream_list, + bool out, bool in); struct sctp_chunk *sctp_make_strreset_tsnreq( - const struct sctp_association *asoc); + const struct sctp_association *asoc); struct sctp_chunk *sctp_make_strreset_addstrm( - const struct sctp_association *asoc, - __u16 out, __u16 in); -struct sctp_chunk *sctp_make_strreset_resp( - const struct sctp_association *asoc, - __u32 result, __u32 sn); -struct sctp_chunk *sctp_make_strreset_tsnresp( - struct sctp_association *asoc, - __u32 result, __u32 sn, - __u32 sender_tsn, __u32 receiver_tsn); + const struct sctp_association *asoc, + __u16 out, __u16 in); +struct sctp_chunk *sctp_make_strreset_resp(const struct sctp_association *asoc, + __u32 result, __u32 sn); +struct sctp_chunk *sctp_make_strreset_tsnresp(struct sctp_association *asoc, + __u32 result, __u32 sn, + __u32 sender_tsn, + __u32 receiver_tsn); bool sctp_verify_reconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_paramhdr **errp); -void sctp_chunk_assign_tsn(struct sctp_chunk *); -void sctp_chunk_assign_ssn(struct sctp_chunk *); +void sctp_chunk_assign_tsn(struct sctp_chunk *chunk); +void sctp_chunk_assign_ssn(struct sctp_chunk *chunk); /* Prototypes for stream-processing functions. */ struct sctp_chunk *sctp_process_strreset_outreq( @@ -312,12 +308,10 @@ struct sctp_chunk *sctp_process_strreset_resp( /* Prototypes for statetable processing. */ -int sctp_do_sm(struct net *net, sctp_event_t event_type, sctp_subtype_t subtype, - sctp_state_t state, - struct sctp_endpoint *, - struct sctp_association *asoc, - void *event_arg, - gfp_t gfp); +int sctp_do_sm(struct net *net, enum sctp_event event_type, + union sctp_subtype subtype, enum sctp_state state, + struct sctp_endpoint *ep, struct sctp_association *asoc, + void *event_arg, gfp_t gfp); /* 2nd level prototypes */ void sctp_generate_t3_rtx_event(unsigned long peer); @@ -327,11 +321,12 @@ void sctp_generate_proto_unreach_event(unsigned long peer); void sctp_ootb_pkt_free(struct sctp_packet *packet); -struct sctp_association *sctp_unpack_cookie(const struct sctp_endpoint *ep, - const struct sctp_association *asoc, - struct sctp_chunk *chunk, - gfp_t gfp, int *err, - struct sctp_chunk **err_chk_p); +struct sctp_association *sctp_unpack_cookie( + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk, + gfp_t gfp, int *err, + struct sctp_chunk **err_chk_p); /* 3rd level prototypes */ __u32 sctp_generate_tag(const struct sctp_endpoint *ep); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 5ab29af8ca8a..0477945de1a3 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -150,18 +150,18 @@ extern struct sctp_globals { #define sctp_checksum_disable (sctp_globals.checksum_disable) /* SCTP Socket type: UDP or TCP style. */ -typedef enum { +enum sctp_socket_type { SCTP_SOCKET_UDP = 0, SCTP_SOCKET_UDP_HIGH_BANDWIDTH, SCTP_SOCKET_TCP -} sctp_socket_type_t; +}; /* Per socket SCTP information. */ struct sctp_sock { /* inet_sock has to be the first member of sctp_sock */ struct inet_sock inet; /* What kind of a socket is this? */ - sctp_socket_type_t type; + enum sctp_socket_type type; /* PF_ family specific functions. */ struct sctp_pf *pf; @@ -371,12 +371,12 @@ union sctp_params { * chunk is sent and the destination transport address to which this * HEARTBEAT is sent (see Section 8.3). */ -typedef struct sctp_sender_hb_info { +struct sctp_sender_hb_info { struct sctp_paramhdr param_hdr; union sctp_addr daddr; unsigned long sent_at; __u64 hb_nonce; -} sctp_sender_hb_info_t; +}; int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp); @@ -449,7 +449,7 @@ struct sctp_af { int (*addr_valid) (union sctp_addr *, struct sctp_sock *, const struct sk_buff *); - sctp_scope_t (*scope) (union sctp_addr *); + enum sctp_scope (*scope)(union sctp_addr *); void (*inaddr_any) (union sctp_addr *, __be16); int (*is_any) (const union sctp_addr *); int (*available) (union sctp_addr *, @@ -657,8 +657,6 @@ struct sctp_sockaddr_entry { #define SCTP_ADDRESS_TICK_DELAY 500 -typedef struct sctp_chunk *(sctp_packet_phandler_t)(struct sctp_association *); - /* This structure holds lists of chunks as we are assembling for * transmission. */ @@ -697,10 +695,11 @@ struct sctp_packet { void sctp_packet_init(struct sctp_packet *, struct sctp_transport *, __u16 sport, __u16 dport); void sctp_packet_config(struct sctp_packet *, __u32 vtag, int); -sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *, - struct sctp_chunk *, int, gfp_t); -sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *, - struct sctp_chunk *); +enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk, + int one_packet, gfp_t gfp); +enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, + struct sctp_chunk *chunk); int sctp_packet_transmit(struct sctp_packet *, gfp_t); void sctp_packet_free(struct sctp_packet *); @@ -950,7 +949,8 @@ int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); -void sctp_transport_lower_cwnd(struct sctp_transport *, sctp_lower_cwnd_t); +void sctp_transport_lower_cwnd(struct sctp_transport *t, + enum sctp_lower_cwnd reason); void sctp_transport_burst_limited(struct sctp_transport *); void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); @@ -1053,8 +1053,8 @@ int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *); int sctp_outq_is_empty(const struct sctp_outq *); void sctp_outq_restart(struct sctp_outq *); -void sctp_retransmit(struct sctp_outq *, struct sctp_transport *, - sctp_retransmit_reason_t); +void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, + enum sctp_retransmit_reason reason); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); void sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); void sctp_prsctp_prune(struct sctp_association *asoc, @@ -1110,7 +1110,7 @@ void sctp_bind_addr_init(struct sctp_bind_addr *, __u16 port); void sctp_bind_addr_free(struct sctp_bind_addr *); int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, - sctp_scope_t scope, gfp_t gfp, + enum sctp_scope scope, gfp_t gfp, int flags); int sctp_bind_addr_dup(struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, @@ -1134,17 +1134,18 @@ union sctp_params sctp_bind_addrs_to_raw(const struct sctp_bind_addr *bp, int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw, int len, __u16 port, gfp_t gfp); -sctp_scope_t sctp_scope(const union sctp_addr *); -int sctp_in_scope(struct net *net, const union sctp_addr *addr, const sctp_scope_t scope); +enum sctp_scope sctp_scope(const union sctp_addr *addr); +int sctp_in_scope(struct net *net, const union sctp_addr *addr, + const enum sctp_scope scope); int sctp_is_any(struct sock *sk, const union sctp_addr *addr); int sctp_is_ep_boundall(struct sock *sk); /* What type of endpoint? */ -typedef enum { +enum sctp_endpoint_type { SCTP_EP_TYPE_SOCKET, SCTP_EP_TYPE_ASSOCIATION, -} sctp_endpoint_type_t; +}; /* * A common base class to bridge the implmentation view of a @@ -1168,7 +1169,7 @@ struct sctp_ep_common { int hashent; /* Runtime type information. What kind of endpoint is this? */ - sctp_endpoint_type_t type; + enum sctp_endpoint_type type; /* Some fields to help us manage this object. * refcnt - Reference count access to this object. @@ -1556,9 +1557,9 @@ struct sctp_association { * and authenticated chunk list. All that is part of the * cookie and these are just pointers to those locations */ - sctp_random_param_t *peer_random; - sctp_chunks_param_t *peer_chunks; - sctp_hmac_algo_param_t *peer_hmacs; + struct sctp_random_param *peer_random; + struct sctp_chunks_param *peer_chunks; + struct sctp_hmac_algo_param *peer_hmacs; } peer; /* State : A state variable indicating what state the @@ -1574,7 +1575,7 @@ struct sctp_association { * * State takes values from SCTP_STATE_*. */ - sctp_state_t state; + enum sctp_state state; /* Overall : The overall association error count. * Error Count : [Clear this any time I get something.] @@ -1924,8 +1925,8 @@ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) struct sctp_association * -sctp_association_new(const struct sctp_endpoint *, const struct sock *, - sctp_scope_t scope, gfp_t gfp); +sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, + enum sctp_scope scope, gfp_t gfp); void sctp_association_free(struct sctp_association *); void sctp_association_put(struct sctp_association *); void sctp_association_hold(struct sctp_association *); @@ -1945,9 +1946,10 @@ void sctp_assoc_del_peer(struct sctp_association *asoc, const union sctp_addr *addr); void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer); -void sctp_assoc_control_transport(struct sctp_association *, - struct sctp_transport *, - sctp_transport_cmd_t, sctp_sn_error_t); +void sctp_assoc_control_transport(struct sctp_association *asoc, + struct sctp_transport *transport, + enum sctp_transport_cmd command, + sctp_sn_error_t error); struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32); struct sctp_transport *sctp_assoc_is_match(struct sctp_association *, struct net *, @@ -1966,8 +1968,8 @@ void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, struct sctp_transport *); -int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *, - sctp_scope_t, gfp_t); +int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, + enum sctp_scope scope, gfp_t gfp); int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *, struct sctp_cookie*, gfp_t gfp); @@ -1983,16 +1985,16 @@ int sctp_cmp_addr_exact(const union sctp_addr *ss1, struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc); /* A convenience structure to parse out SCTP specific CMSGs. */ -typedef struct sctp_cmsgs { +struct sctp_cmsgs { struct sctp_initmsg *init; struct sctp_sndrcvinfo *srinfo; struct sctp_sndinfo *sinfo; -} sctp_cmsgs_t; +}; /* Structure for tracking memory objects */ -typedef struct { +struct sctp_dbg_objcnt_entry { char *label; atomic_t *counter; -} sctp_dbg_objcnt_entry_t; +}; #endif /* __sctp_structs_h__ */ diff --git a/include/net/seg6.h b/include/net/seg6.h index 4e0357517d79..5379f550f521 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -56,7 +56,11 @@ extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); +extern int seg6_local_init(void); +extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len); +extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); +extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); #endif diff --git a/include/net/sock.h b/include/net/sock.h index 7c0632c7e870..fe1a0bc25cd3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -294,6 +294,7 @@ struct sock_common { * @sk_stamp: time stamp of last packet received * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests + * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data * @sk_frag: cached page frag @@ -462,6 +463,7 @@ struct sock { u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; + atomic_t sk_zckey; struct socket *sk_socket; void *sk_user_data; #ifdef CONFIG_SECURITY @@ -1531,6 +1533,8 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); void __sock_wfree(struct sk_buff *skb); void sock_wfree(struct sk_buff *skb); +struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size, + gfp_t priority); void skb_orphan_partial(struct sk_buff *skb); void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); @@ -1582,11 +1586,14 @@ int sock_no_shutdown(struct socket *, int); int sock_no_getsockopt(struct socket *, int , int, char __user *, int __user *); int sock_no_setsockopt(struct socket *, int, int, char __user *, unsigned int); int sock_no_sendmsg(struct socket *, struct msghdr *, size_t); +int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); +ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol diff --git a/include/net/strparser.h b/include/net/strparser.h index 0c28ad97c52f..4fe966a0ad92 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -18,26 +18,26 @@ #define STRP_STATS_INCR(stat) ((stat)++) struct strp_stats { - unsigned long long rx_msgs; - unsigned long long rx_bytes; - unsigned int rx_mem_fail; - unsigned int rx_need_more_hdr; - unsigned int rx_msg_too_big; - unsigned int rx_msg_timeouts; - unsigned int rx_bad_hdr_len; + unsigned long long msgs; + unsigned long long bytes; + unsigned int mem_fail; + unsigned int need_more_hdr; + unsigned int msg_too_big; + unsigned int msg_timeouts; + unsigned int bad_hdr_len; }; struct strp_aggr_stats { - unsigned long long rx_msgs; - unsigned long long rx_bytes; - unsigned int rx_mem_fail; - unsigned int rx_need_more_hdr; - unsigned int rx_msg_too_big; - unsigned int rx_msg_timeouts; - unsigned int rx_bad_hdr_len; - unsigned int rx_aborts; - unsigned int rx_interrupted; - unsigned int rx_unrecov_intr; + unsigned long long msgs; + unsigned long long bytes; + unsigned int mem_fail; + unsigned int need_more_hdr; + unsigned int msg_too_big; + unsigned int msg_timeouts; + unsigned int bad_hdr_len; + unsigned int aborts; + unsigned int interrupted; + unsigned int unrecov_intr; }; struct strparser; @@ -48,16 +48,18 @@ struct strp_callbacks { void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); int (*read_sock_done)(struct strparser *strp, int err); void (*abort_parser)(struct strparser *strp, int err); + void (*lock)(struct strparser *strp); + void (*unlock)(struct strparser *strp); }; -struct strp_rx_msg { +struct strp_msg { int full_len; int offset; }; -static inline struct strp_rx_msg *strp_rx_msg(struct sk_buff *skb) +static inline struct strp_msg *strp_msg(struct sk_buff *skb) { - return (struct strp_rx_msg *)((void *)skb->cb + + return (struct strp_msg *)((void *)skb->cb + offsetof(struct qdisc_skb_cb, data)); } @@ -65,18 +67,18 @@ static inline struct strp_rx_msg *strp_rx_msg(struct sk_buff *skb) struct strparser { struct sock *sk; - u32 rx_stopped : 1; - u32 rx_paused : 1; - u32 rx_aborted : 1; - u32 rx_interrupted : 1; - u32 rx_unrecov_intr : 1; - - struct sk_buff **rx_skb_nextp; - struct timer_list rx_msg_timer; - struct sk_buff *rx_skb_head; - unsigned int rx_need_bytes; - struct delayed_work rx_delayed_work; - struct work_struct rx_work; + u32 stopped : 1; + u32 paused : 1; + u32 aborted : 1; + u32 interrupted : 1; + u32 unrecov_intr : 1; + + struct sk_buff **skb_nextp; + struct timer_list msg_timer; + struct sk_buff *skb_head; + unsigned int need_bytes; + struct delayed_work delayed_work; + struct work_struct work; struct strp_stats stats; struct strp_callbacks cb; }; @@ -84,7 +86,7 @@ struct strparser { /* Must be called with lock held for attached socket */ static inline void strp_pause(struct strparser *strp) { - strp->rx_paused = 1; + strp->paused = 1; } /* May be called without holding lock for attached socket */ @@ -97,37 +99,37 @@ static inline void save_strp_stats(struct strparser *strp, #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += \ strp->stats._stat) - SAVE_PSOCK_STATS(rx_msgs); - SAVE_PSOCK_STATS(rx_bytes); - SAVE_PSOCK_STATS(rx_mem_fail); - SAVE_PSOCK_STATS(rx_need_more_hdr); - SAVE_PSOCK_STATS(rx_msg_too_big); - SAVE_PSOCK_STATS(rx_msg_timeouts); - SAVE_PSOCK_STATS(rx_bad_hdr_len); + SAVE_PSOCK_STATS(msgs); + SAVE_PSOCK_STATS(bytes); + SAVE_PSOCK_STATS(mem_fail); + SAVE_PSOCK_STATS(need_more_hdr); + SAVE_PSOCK_STATS(msg_too_big); + SAVE_PSOCK_STATS(msg_timeouts); + SAVE_PSOCK_STATS(bad_hdr_len); #undef SAVE_PSOCK_STATS - if (strp->rx_aborted) - agg_stats->rx_aborts++; - if (strp->rx_interrupted) - agg_stats->rx_interrupted++; - if (strp->rx_unrecov_intr) - agg_stats->rx_unrecov_intr++; + if (strp->aborted) + agg_stats->aborts++; + if (strp->interrupted) + agg_stats->interrupted++; + if (strp->unrecov_intr) + agg_stats->unrecov_intr++; } static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, struct strp_aggr_stats *agg_stats) { #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) - SAVE_PSOCK_STATS(rx_msgs); - SAVE_PSOCK_STATS(rx_bytes); - SAVE_PSOCK_STATS(rx_mem_fail); - SAVE_PSOCK_STATS(rx_need_more_hdr); - SAVE_PSOCK_STATS(rx_msg_too_big); - SAVE_PSOCK_STATS(rx_msg_timeouts); - SAVE_PSOCK_STATS(rx_bad_hdr_len); - SAVE_PSOCK_STATS(rx_aborts); - SAVE_PSOCK_STATS(rx_interrupted); - SAVE_PSOCK_STATS(rx_unrecov_intr); + SAVE_PSOCK_STATS(msgs); + SAVE_PSOCK_STATS(bytes); + SAVE_PSOCK_STATS(mem_fail); + SAVE_PSOCK_STATS(need_more_hdr); + SAVE_PSOCK_STATS(msg_too_big); + SAVE_PSOCK_STATS(msg_timeouts); + SAVE_PSOCK_STATS(bad_hdr_len); + SAVE_PSOCK_STATS(aborts); + SAVE_PSOCK_STATS(interrupted); + SAVE_PSOCK_STATS(unrecov_intr); #undef SAVE_PSOCK_STATS } @@ -135,8 +137,11 @@ static inline void aggregate_strp_stats(struct strp_aggr_stats *stats, void strp_done(struct strparser *strp); void strp_stop(struct strparser *strp); void strp_check_rcv(struct strparser *strp); -int strp_init(struct strparser *strp, struct sock *csk, +int strp_init(struct strparser *strp, struct sock *sk, struct strp_callbacks *cb); void strp_data_ready(struct strparser *strp); +int strp_process(struct strparser *strp, struct sk_buff *orig_skb, + unsigned int orig_offset, size_t orig_len, + size_t max_msg_size, long timeo); #endif /* __NET_STRPARSER_H_ */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 8ae9e3b6392e..d767b7991887 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -74,7 +74,6 @@ struct switchdev_attr { enum switchdev_obj_id { SWITCHDEV_OBJ_ID_UNDEFINED, SWITCHDEV_OBJ_ID_PORT_VLAN, - SWITCHDEV_OBJ_ID_PORT_FDB, SWITCHDEV_OBJ_ID_PORT_MDB, }; @@ -97,17 +96,6 @@ struct switchdev_obj_port_vlan { #define SWITCHDEV_OBJ_PORT_VLAN(obj) \ container_of(obj, struct switchdev_obj_port_vlan, obj) -/* SWITCHDEV_OBJ_ID_PORT_FDB */ -struct switchdev_obj_port_fdb { - struct switchdev_obj obj; - unsigned char addr[ETH_ALEN]; - u16 vid; - u16 ndm_state; -}; - -#define SWITCHDEV_OBJ_PORT_FDB(obj) \ - container_of(obj, struct switchdev_obj_port_fdb, obj) - /* SWITCHDEV_OBJ_ID_PORT_MDB */ struct switchdev_obj_port_mdb { struct switchdev_obj obj; @@ -135,8 +123,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). * * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). - * - * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, @@ -149,9 +135,6 @@ struct switchdev_ops { struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, const struct switchdev_obj *obj); - int (*switchdev_port_obj_dump)(struct net_device *dev, - struct switchdev_obj *obj, - switchdev_obj_dump_cb_t *cb); }; enum switchdev_notifier_type { @@ -189,28 +172,10 @@ int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj, - switchdev_obj_dump_cb_t *cb); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info); -int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask, - int nlflags); -int switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags); -int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, const unsigned char *addr, - u16 vid, u16 nlm_flags); -int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, const unsigned char *addr, - u16 vid); -int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, - struct net_device *filter_dev, int *idx); void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); @@ -249,13 +214,6 @@ static inline int switchdev_port_obj_del(struct net_device *dev, return -EOPNOTSUPP; } -static inline int switchdev_port_obj_dump(struct net_device *dev, - const struct switchdev_obj *obj, - switchdev_obj_dump_cb_t *cb) -{ - return -EOPNOTSUPP; -} - static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; @@ -273,51 +231,6 @@ static inline int call_switchdev_notifiers(unsigned long val, return NOTIFY_DONE; } -static inline int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, - u32 seq, struct net_device *dev, - u32 filter_mask, int nlflags) -{ - return -EOPNOTSUPP; -} - -static inline int switchdev_port_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) -{ - return -EOPNOTSUPP; -} - -static inline int switchdev_port_bridge_dellink(struct net_device *dev, - struct nlmsghdr *nlh, - u16 flags) -{ - return -EOPNOTSUPP; -} - -static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, - u16 vid, u16 nlm_flags) -{ - return -EOPNOTSUPP; -} - -static inline int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) -{ - return -EOPNOTSUPP; -} - -static inline int switchdev_port_fdb_dump(struct sk_buff *skb, - struct netlink_callback *cb, - struct net_device *dev, - struct net_device *filter_dev, - int *idx) -{ - return *idx; -} - static inline bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { diff --git a/include/net/tcp.h b/include/net/tcp.h index ada65e767b28..afdab3781425 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -139,6 +139,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #endif #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) +#define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the @@ -150,8 +151,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes * for local resources. */ -#define TCP_REO_TIMEOUT_MIN (2000) /* Min RACK reordering timeout in usec */ - #define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */ #define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */ #define TCP_KEEPALIVE_INTVL (75*HZ) @@ -257,7 +256,6 @@ extern int sysctl_tcp_rmem[3]; extern int sysctl_tcp_app_win; extern int sysctl_tcp_adv_win_scale; extern int sysctl_tcp_frto; -extern int sysctl_tcp_low_latency; extern int sysctl_tcp_nometrics_save; extern int sysctl_tcp_moderate_rcvbuf; extern int sysctl_tcp_tso_win_divisor; @@ -352,8 +350,11 @@ int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, + size_t size, int flags); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tcp_release_cb(struct sock *sk); @@ -363,7 +364,7 @@ void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); + const struct tcphdr *th); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); @@ -633,29 +634,6 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } -static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd) -{ - tp->pred_flags = htonl((tp->tcp_header_len << 26) | - ntohl(TCP_FLAG_ACK) | - snd_wnd); -} - -static inline void tcp_fast_path_on(struct tcp_sock *tp) -{ - __tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale); -} - -static inline void tcp_fast_path_check(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (RB_EMPTY_ROOT(&tp->out_of_order_queue) && - tp->rcv_wnd && - atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf && - !tp->urg_data) - tcp_fast_path_on(tp); -} - /* Compute the actual rto_min value */ static inline u32 tcp_rto_min(struct sock *sk) { @@ -849,6 +827,16 @@ static inline int tcp_v6_iif(const struct sk_buff *skb) return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; } + +/* TCP_SKB_CB reference means this can not be used from early demux */ +static inline int tcp_v6_sdif(const struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags)) + return TCP_SKB_CB(skb)->header.h6.iif; +#endif + return 0; +} #endif /* TCP_SKB_CB reference means this can not be used from early demux */ @@ -862,6 +850,16 @@ static inline bool inet_exact_dif_match(struct net *net, struct sk_buff *skb) return false; } +/* TCP_SKB_CB reference means this can not be used from early demux */ +static inline int tcp_v4_sdif(struct sk_buff *skb) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + if (skb && ipv4_l3mdev_skb(TCP_SKB_CB(skb)->header.h4.flags)) + return TCP_SKB_CB(skb)->header.h4.iif; +#endif + return 0; +} + /* Due to TSO, an SKB can be composed of multiple actual * packets. To keep these tracked properly, we use this. */ @@ -905,9 +903,8 @@ enum tcp_ca_event { /* Information about inbound ACK, passed to cong_ops->in_ack_event() */ enum tcp_ca_ack_event_flags { - CA_ACK_SLOWPATH = (1 << 0), /* In slow path processing */ - CA_ACK_WIN_UPDATE = (1 << 1), /* ACK updated window */ - CA_ACK_ECE = (1 << 2), /* ECE bit is set on ack */ + CA_ACK_WIN_UPDATE = (1 << 0), /* ACK updated window */ + CA_ACK_ECE = (1 << 1), /* ECE bit is set on ack */ }; /* @@ -1245,17 +1242,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) __tcp_checksum_complete(skb); } -/* Prequeue for VJ style copy to user, combined with checksumming. */ - -static inline void tcp_prequeue_init(struct tcp_sock *tp) -{ - tp->ucopy.task = NULL; - tp->ucopy.len = 0; - tp->ucopy.memory = 0; - skb_queue_head_init(&tp->ucopy.prequeue); -} - -bool tcp_prequeue(struct sock *sk, struct sk_buff *skb); bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); int tcp_filter(struct sock *sk, struct sk_buff *skb); @@ -1929,7 +1915,8 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk) /* * Save and compile IPv4 options, return a pointer to it */ -static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb) +static inline struct ip_options_rcu *tcp_v4_save_options(struct net *net, + struct sk_buff *skb) { const struct ip_options *opt = &TCP_SKB_CB(skb)->header.h4.opt; struct ip_options_rcu *dopt = NULL; @@ -1938,7 +1925,7 @@ static inline struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb) int opt_size = sizeof(*dopt) + opt->optlen; dopt = kmalloc(opt_size, GFP_ATOMIC); - if (dopt && __ip_options_echo(&dopt->opt, skb, opt)) { + if (dopt && __ip_options_echo(net, &dopt->opt, skb, opt)) { kfree(dopt); dopt = NULL; } diff --git a/include/net/udp.h b/include/net/udp.h index 586de4b811b5..4e5f23fec35e 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -287,7 +287,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif); struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, - __be32 daddr, __be16 dport, int dif, + __be32 daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport); @@ -298,7 +298,7 @@ struct sock *udp6_lib_lookup(struct net *net, struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *tbl, + int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 02c5be037451..10cce0dd4450 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -115,6 +115,8 @@ struct udp_tunnel_info { /* Notify network devices of offloadable types */ void udp_tunnel_push_rx_port(struct net_device *dev, struct socket *sock, unsigned short type); +void udp_tunnel_drop_rx_port(struct net_device *dev, struct socket *sock, + unsigned short type); void udp_tunnel_notify_add_rx_port(struct socket *sock, unsigned short type); void udp_tunnel_notify_del_rx_port(struct socket *sock, unsigned short type); @@ -124,6 +126,12 @@ static inline void udp_tunnel_get_rx_info(struct net_device *dev) call_netdevice_notifiers(NETDEV_UDP_TUNNEL_PUSH_INFO, dev); } +static inline void udp_tunnel_drop_rx_info(struct net_device *dev) +{ + ASSERT_RTNL(); + call_netdevice_notifiers(NETDEV_UDP_TUNNEL_DROP_INFO, dev); +} + /* Transmit the skb using UDP encapsulation. */ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, __u8 ttl, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c0916ab18d32..afb4929d7232 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -317,6 +317,7 @@ int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int fam void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); +void xfrm_policy_cache_flush(void); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; @@ -563,7 +564,6 @@ struct xfrm_policy { refcount_t refcnt; struct timer_list timer; - struct flow_cache_object flo; atomic_t genid; u32 priority; u32 index; @@ -978,7 +978,6 @@ struct xfrm_dst { struct rt6_info rt6; } u; struct dst_entry *route; - struct flow_cache_object flo; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; u32 xfrm_genid; @@ -1226,9 +1225,6 @@ static inline void xfrm_sk_free_policy(struct sock *sk) } } -void xfrm_garbage_collect(struct net *net); -void xfrm_garbage_collect_deferred(struct net *net); - #else static inline void xfrm_sk_free_policy(struct sock *sk) {} @@ -1263,9 +1259,6 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, { return 1; } -static inline void xfrm_garbage_collect(struct net *net) -{ -} #endif static __inline__ diff --git a/include/rxrpc/packet.h b/include/rxrpc/packet.h deleted file mode 100644 index a2dcfb850b9f..000000000000 --- a/include/rxrpc/packet.h +++ /dev/null @@ -1,235 +0,0 @@ -/* packet.h: Rx packet layout and definitions - * - * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_RXRPC_PACKET_H -#define _LINUX_RXRPC_PACKET_H - -typedef u32 rxrpc_seq_t; /* Rx message sequence number */ -typedef u32 rxrpc_serial_t; /* Rx message serial number */ -typedef __be32 rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */ -typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */ - -/*****************************************************************************/ -/* - * on-the-wire Rx packet header - * - all multibyte fields should be in network byte order - */ -struct rxrpc_wire_header { - __be32 epoch; /* client boot timestamp */ -#define RXRPC_RANDOM_EPOCH 0x80000000 /* Random if set, date-based if not */ - - __be32 cid; /* connection and channel ID */ -#define RXRPC_MAXCALLS 4 /* max active calls per conn */ -#define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */ -#define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */ -#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */ -#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */ - - __be32 callNumber; /* call ID (0 for connection-level packets) */ - __be32 seq; /* sequence number of pkt in call stream */ - __be32 serial; /* serial number of pkt sent to network */ - - uint8_t type; /* packet type */ -#define RXRPC_PACKET_TYPE_DATA 1 /* data */ -#define RXRPC_PACKET_TYPE_ACK 2 /* ACK */ -#define RXRPC_PACKET_TYPE_BUSY 3 /* call reject */ -#define RXRPC_PACKET_TYPE_ABORT 4 /* call/connection abort */ -#define RXRPC_PACKET_TYPE_ACKALL 5 /* ACK all outstanding packets on call */ -#define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */ -#define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */ -#define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */ -#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */ -#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */ - - uint8_t flags; /* packet flags */ -#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */ -#define RXRPC_REQUEST_ACK 0x02 /* request an unconditional ACK of this packet */ -#define RXRPC_LAST_PACKET 0x04 /* the last packet from this side for this call */ -#define RXRPC_MORE_PACKETS 0x08 /* more packets to come */ -#define RXRPC_JUMBO_PACKET 0x20 /* [DATA] this is a jumbo packet */ -#define RXRPC_SLOW_START_OK 0x20 /* [ACK] slow start supported */ - - uint8_t userStatus; /* app-layer defined status */ -#define RXRPC_USERSTATUS_SERVICE_UPGRADE 0x01 /* AuriStor service upgrade request */ - - uint8_t securityIndex; /* security protocol ID */ - union { - __be16 _rsvd; /* reserved */ - __be16 cksum; /* kerberos security checksum */ - }; - __be16 serviceId; /* service ID */ - -} __packed; - -#define RXRPC_SUPPORTED_PACKET_TYPES ( \ - (1 << RXRPC_PACKET_TYPE_DATA) | \ - (1 << RXRPC_PACKET_TYPE_ACK) | \ - (1 << RXRPC_PACKET_TYPE_BUSY) | \ - (1 << RXRPC_PACKET_TYPE_ABORT) | \ - (1 << RXRPC_PACKET_TYPE_ACKALL) | \ - (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \ - (1 << RXRPC_PACKET_TYPE_RESPONSE) | \ - /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \ - (1 << RXRPC_PACKET_TYPE_VERSION)) - -/*****************************************************************************/ -/* - * jumbo packet secondary header - * - can be mapped to read header by: - * - new_serial = serial + 1 - * - new_seq = seq + 1 - * - new_flags = j_flags - * - new__rsvd = j__rsvd - * - duplicating all other fields - */ -struct rxrpc_jumbo_header { - uint8_t flags; /* packet flags (as per rxrpc_header) */ - uint8_t pad; - union { - __be16 _rsvd; /* reserved */ - __be16 cksum; /* kerberos security checksum */ - }; -}; - -#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ -#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) - -/*****************************************************************************/ -/* - * on-the-wire Rx ACK packet data payload - * - all multibyte fields should be in network byte order - */ -struct rxrpc_ackpacket { - __be16 bufferSpace; /* number of packet buffers available */ - __be16 maxSkew; /* diff between serno being ACK'd and highest serial no - * received */ - __be32 firstPacket; /* sequence no of first ACK'd packet in attached list */ - __be32 previousPacket; /* sequence no of previous packet received */ - __be32 serial; /* serial no of packet that prompted this ACK */ - - uint8_t reason; /* reason for ACK */ -#define RXRPC_ACK_REQUESTED 1 /* ACK was requested on packet */ -#define RXRPC_ACK_DUPLICATE 2 /* duplicate packet received */ -#define RXRPC_ACK_OUT_OF_SEQUENCE 3 /* out of sequence packet received */ -#define RXRPC_ACK_EXCEEDS_WINDOW 4 /* packet received beyond end of ACK window */ -#define RXRPC_ACK_NOSPACE 5 /* packet discarded due to lack of buffer space */ -#define RXRPC_ACK_PING 6 /* keep alive ACK */ -#define RXRPC_ACK_PING_RESPONSE 7 /* response to RXRPC_ACK_PING */ -#define RXRPC_ACK_DELAY 8 /* nothing happened since received packet */ -#define RXRPC_ACK_IDLE 9 /* ACK due to fully received ACK window */ -#define RXRPC_ACK__INVALID 10 /* Representation of invalid ACK reason */ - - uint8_t nAcks; /* number of ACKs */ -#define RXRPC_MAXACKS 255 - - uint8_t acks[0]; /* list of ACK/NAKs */ -#define RXRPC_ACK_TYPE_NACK 0 -#define RXRPC_ACK_TYPE_ACK 1 - -} __packed; - -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - -/* - * ACK packets can have a further piece of information tagged on the end - */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ - __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ - __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ -}; - -/*****************************************************************************/ -/* - * Kerberos security type-2 challenge packet - */ -struct rxkad_challenge { - __be32 version; /* version of this challenge type */ - __be32 nonce; /* encrypted random number */ - __be32 min_level; /* minimum security level */ - __be32 __padding; /* padding to 8-byte boundary */ -} __packed; - -/*****************************************************************************/ -/* - * Kerberos security type-2 response packet - */ -struct rxkad_response { - __be32 version; /* version of this response type */ - __be32 __pad; - - /* encrypted bit of the response */ - struct { - __be32 epoch; /* current epoch */ - __be32 cid; /* parent connection ID */ - __be32 checksum; /* checksum */ - __be32 securityIndex; /* security type */ - __be32 call_id[4]; /* encrypted call IDs */ - __be32 inc_nonce; /* challenge nonce + 1 */ - __be32 level; /* desired level */ - } encrypted; - - __be32 kvno; /* Kerberos key version number */ - __be32 ticket_len; /* Kerberos ticket length */ -} __packed; - -/*****************************************************************************/ -/* - * RxRPC-level abort codes - */ -#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */ -#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */ -#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */ -#define RX_EOF -4 /* unexpected end of data on read op */ -#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */ -#define RX_USER_ABORT -6 /* generic user abort */ -#define RX_ADDRINUSE -7 /* UDP port in use */ -#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */ - -/* - * (un)marshalling abort codes (rxgen) - */ -#define RXGEN_CC_MARSHAL -450 -#define RXGEN_CC_UNMARSHAL -451 -#define RXGEN_SS_MARSHAL -452 -#define RXGEN_SS_UNMARSHAL -453 -#define RXGEN_DECODE -454 -#define RXGEN_OPCODE -455 -#define RXGEN_SS_XDRFREE -456 -#define RXGEN_CC_XDRFREE -457 - -/* - * Rx kerberos security abort codes - * - unfortunately we have no generalised security abort codes to say things - * like "unsupported security", so we have to use these instead and hope the - * other side understands - */ -#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */ -#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */ -#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */ -#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */ -#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */ -#define RXKADNOAUTH 19270405 /* caller not authorised */ -#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */ -#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */ -#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */ -#define RXKADEXPIRED 19270409 /* authentication expired */ -#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */ -#define RXKADDATALEN 19270411 /* user data too long */ -#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ - -#endif /* _LINUX_RXRPC_PACKET_H */ diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index 1b61357d3f57..7b1eb7b4be41 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -12,7 +12,8 @@ FN(ABORTED) \ FN(DROP) \ FN(PASS) \ - FN(TX) + FN(TX) \ + FN(REDIRECT) #define __XDP_ACT_TP_FN(x) \ TRACE_DEFINE_ENUM(XDP_##x); @@ -48,6 +49,34 @@ TRACE_EVENT(xdp_exception, __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB)) ); +TRACE_EVENT(xdp_redirect, + + TP_PROTO(const struct net_device *from, + const struct net_device *to, + const struct bpf_prog *xdp, u32 act), + + TP_ARGS(from, to, xdp, act), + + TP_STRUCT__entry( + __string(name_from, from->name) + __string(name_to, to->name) + __array(u8, prog_tag, 8) + __field(u32, act) + ), + + TP_fast_assign( + BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(xdp->tag)); + memcpy(__entry->prog_tag, xdp->tag, sizeof(xdp->tag)); + __assign_str(name_from, from->name); + __assign_str(name_to, to->name); + __entry->act = act; + ), + + TP_printk("prog=%s from=%s to=%s action=%s", + __print_hex_str(__entry->prog_tag, 8), + __get_str(name_from), __get_str(name_to), + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB)) +); #endif /* _TRACE_XDP_H */ #include <trace/define_trace.h> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 9861be8da65e..e47c9e436221 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -104,4 +104,6 @@ #define SO_PEERGROUPS 59 +#define SO_ZEROCOPY 60 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e99e3e6f8b37..91da8371a2d0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -30,9 +30,14 @@ #define BPF_FROM_LE BPF_TO_LE #define BPF_FROM_BE BPF_TO_BE +/* jmp encodings */ #define BPF_JNE 0x50 /* jump != */ +#define BPF_JLT 0xa0 /* LT is unsigned, '<' */ +#define BPF_JLE 0xb0 /* LE is unsigned, '<=' */ #define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ #define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_JSLT 0xc0 /* SLT is signed, '<' */ +#define BPF_JSLE 0xd0 /* SLE is signed, '<=' */ #define BPF_CALL 0x80 /* function call */ #define BPF_EXIT 0x90 /* function return */ @@ -104,6 +109,7 @@ enum bpf_map_type { BPF_MAP_TYPE_LPM_TRIE, BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH_OF_MAPS, + BPF_MAP_TYPE_DEVMAP, }; enum bpf_prog_type { @@ -344,9 +350,20 @@ union bpf_attr { * int bpf_redirect(ifindex, flags) * redirect to another netdev * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT + * @flags: + * cls_bpf: + * bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * xdp_bpf: + * all bits - reserved + * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error + * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error + * int bpf_redirect_map(map, key, flags) + * redirect to endpoint in map + * @map: pointer to dev map + * @key: index in map to lookup + * @flags: -- + * Return: XDP_REDIRECT on success or XDP_ABORT on error * * u32 bpf_get_route_realm(skb) * retrieve a dst's tclassid @@ -591,7 +608,8 @@ union bpf_attr { FN(get_socket_uid), \ FN(set_hash), \ FN(setsockopt), \ - FN(skb_adjust_room), + FN(skb_adjust_room), \ + FN(redirect_map), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -717,6 +735,7 @@ enum xdp_action { XDP_DROP, XDP_PASS, XDP_TX, + XDP_REDIRECT, }; /* user accessible metadata for XDP packet hook diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index 07bdce1f444a..78fdf52d6b2f 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -18,10 +18,13 @@ struct sock_extended_err { #define SO_EE_ORIGIN_ICMP 2 #define SO_EE_ORIGIN_ICMP6 3 #define SO_EE_ORIGIN_TXSTATUS 4 +#define SO_EE_ORIGIN_ZEROCOPY 5 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) +#define SO_EE_CODE_ZEROCOPY_COPIED 1 + /** * struct scm_timestamping - timestamps exposed through cmsg * diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 7d4a594d5d58..9c041dae8e2c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1238,6 +1238,47 @@ struct ethtool_per_queue_op { char data[]; }; +/** + * struct ethtool_fecparam - Ethernet forward error correction(fec) parameters + * @cmd: Command number = %ETHTOOL_GFECPARAM or %ETHTOOL_SFECPARAM + * @active_fec: FEC mode which is active on porte + * @fec: Bitmask of supported/configured FEC modes + * @rsvd: Reserved for future extensions. i.e FEC bypass feature. + * + * Drivers should reject a non-zero setting of @autoneg when + * autoneogotiation is disabled (or not supported) for the link. + * + */ +struct ethtool_fecparam { + __u32 cmd; + /* bitmask of FEC modes */ + __u32 active_fec; + __u32 fec; + __u32 reserved; +}; + +/** + * enum ethtool_fec_config_bits - flags definition of ethtool_fec_configuration + * @ETHTOOL_FEC_NONE: FEC mode configuration is not supported + * @ETHTOOL_FEC_AUTO: Default/Best FEC mode provided by driver + * @ETHTOOL_FEC_OFF: No FEC Mode + * @ETHTOOL_FEC_RS: Reed-Solomon Forward Error Detection mode + * @ETHTOOL_FEC_BASER: Base-R/Reed-Solomon Forward Error Detection mode + */ +enum ethtool_fec_config_bits { + ETHTOOL_FEC_NONE_BIT, + ETHTOOL_FEC_AUTO_BIT, + ETHTOOL_FEC_OFF_BIT, + ETHTOOL_FEC_RS_BIT, + ETHTOOL_FEC_BASER_BIT, +}; + +#define ETHTOOL_FEC_NONE (1 << ETHTOOL_FEC_NONE_BIT) +#define ETHTOOL_FEC_AUTO (1 << ETHTOOL_FEC_AUTO_BIT) +#define ETHTOOL_FEC_OFF (1 << ETHTOOL_FEC_OFF_BIT) +#define ETHTOOL_FEC_RS (1 << ETHTOOL_FEC_RS_BIT) +#define ETHTOOL_FEC_BASER (1 << ETHTOOL_FEC_BASER_BIT) + /* CMDs currently supported */ #define ETHTOOL_GSET 0x00000001 /* DEPRECATED, Get settings. * Please use ETHTOOL_GLINKSETTINGS @@ -1330,6 +1371,8 @@ struct ethtool_per_queue_op { #define ETHTOOL_SLINKSETTINGS 0x0000004d /* Set ethtool_link_settings */ #define ETHTOOL_PHY_GTUNABLE 0x0000004e /* Get PHY tunable configuration */ #define ETHTOOL_PHY_STUNABLE 0x0000004f /* Set PHY tunable configuration */ +#define ETHTOOL_GFECPARAM 0x00000050 /* Get FEC settings */ +#define ETHTOOL_SFECPARAM 0x00000051 /* Set FEC settings */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET @@ -1387,6 +1430,9 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_2500baseT_Full_BIT = 47, ETHTOOL_LINK_MODE_5000baseT_Full_BIT = 48, + ETHTOOL_LINK_MODE_FEC_NONE_BIT = 49, + ETHTOOL_LINK_MODE_FEC_RS_BIT = 50, + ETHTOOL_LINK_MODE_FEC_BASER_BIT = 51, /* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit * 31. Please do NOT define any SUPPORTED_* or ADVERTISED_* @@ -1395,7 +1441,7 @@ enum ethtool_link_mode_bit_indices { */ __ETHTOOL_LINK_MODE_LAST - = ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + = ETHTOOL_LINK_MODE_FEC_BASER_BIT, }; #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name) \ diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h index 92724cba1eba..7fdd19ca7511 100644 --- a/include/uapi/linux/lwtunnel.h +++ b/include/uapi/linux/lwtunnel.h @@ -11,6 +11,7 @@ enum lwtunnel_encap_types { LWTUNNEL_ENCAP_IP6, LWTUNNEL_ENCAP_SEG6, LWTUNNEL_ENCAP_BPF, + LWTUNNEL_ENCAP_SEG6_LOCAL, __LWTUNNEL_ENCAP_MAX, }; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f86127a46cfc..f4fc9c9e123d 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -226,5 +226,22 @@ struct nlattr { #define NLA_ALIGN(len) (((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1)) #define NLA_HDRLEN ((int) NLA_ALIGN(sizeof(struct nlattr))) +/* Generic 32 bitflags attribute content sent to the kernel. + * + * The value is a bitmap that defines the values being set + * The selector is a bitmask that defines which value is legit + * + * Examples: + * value = 0x0, and selector = 0x1 + * implies we are selecting bit 1 and we want to set its value to 0. + * + * value = 0x2, and selector = 0x2 + * implies we are selecting bit 2 and we want to set its value to 1. + * + */ +struct nla_bitfield32 { + __u32 value; + __u32 selector; +}; #endif /* _UAPI__LINUX_NETLINK_H */ diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index d148505010a7..dab7dad9e01a 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -683,10 +683,29 @@ struct tcamsg { unsigned char tca__pad1; unsigned short tca__pad2; }; + +enum { + TCA_ROOT_UNSPEC, + TCA_ROOT_TAB, +#define TCA_ACT_TAB TCA_ROOT_TAB +#define TCAA_MAX TCA_ROOT_TAB + TCA_ROOT_FLAGS, + TCA_ROOT_COUNT, + TCA_ROOT_TIME_DELTA, /* in msecs */ + __TCA_ROOT_MAX, +#define TCA_ROOT_MAX (__TCA_ROOT_MAX - 1) +}; + #define TA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct tcamsg)))) #define TA_PAYLOAD(n) NLMSG_PAYLOAD(n,sizeof(struct tcamsg)) -#define TCA_ACT_TAB 1 /* attr type must be >=1 */ -#define TCAA_MAX 1 +/* tcamsg flags stored in attribute TCA_ROOT_FLAGS + * + * TCA_FLAG_LARGE_DUMP_ON user->kernel to request for larger than TCA_ACT_MAX_PRIO + * actions in a dump. All dump responses will contain the number of actions + * being dumped stored in for user app's consumption in TCA_ROOT_COUNT + * + */ +#define TCA_FLAG_LARGE_DUMP_ON (1 << 0) /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) diff --git a/include/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 7343f71783dc..9656aad8f8f7 100644 --- a/include/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -1,17 +1,18 @@ -/* AF_RXRPC parameters +/* Types and definitions for AF_RXRPC. * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License + * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. + * 2 of the Licence, or (at your option) any later version. */ -#ifndef _LINUX_RXRPC_H -#define _LINUX_RXRPC_H +#ifndef _UAPI_LINUX_RXRPC_H +#define _UAPI_LINUX_RXRPC_H +#include <linux/types.h> #include <linux/in.h> #include <linux/in6.h> @@ -76,4 +77,48 @@ enum rxrpc_cmsg_type { #define RXRPC_SECURITY_RXGK 4 /* gssapi-based */ #define RXRPC_SECURITY_RXK5 5 /* kerberos 5 */ -#endif /* _LINUX_RXRPC_H */ +/* + * RxRPC-level abort codes + */ +#define RX_CALL_DEAD -1 /* call/conn has been inactive and is shut down */ +#define RX_INVALID_OPERATION -2 /* invalid operation requested / attempted */ +#define RX_CALL_TIMEOUT -3 /* call timeout exceeded */ +#define RX_EOF -4 /* unexpected end of data on read op */ +#define RX_PROTOCOL_ERROR -5 /* low-level protocol error */ +#define RX_USER_ABORT -6 /* generic user abort */ +#define RX_ADDRINUSE -7 /* UDP port in use */ +#define RX_DEBUGI_BADTYPE -8 /* bad debugging packet type */ + +/* + * (un)marshalling abort codes (rxgen) + */ +#define RXGEN_CC_MARSHAL -450 +#define RXGEN_CC_UNMARSHAL -451 +#define RXGEN_SS_MARSHAL -452 +#define RXGEN_SS_UNMARSHAL -453 +#define RXGEN_DECODE -454 +#define RXGEN_OPCODE -455 +#define RXGEN_SS_XDRFREE -456 +#define RXGEN_CC_XDRFREE -457 + +/* + * Rx kerberos security abort codes + * - unfortunately we have no generalised security abort codes to say things + * like "unsupported security", so we have to use these instead and hope the + * other side understands + */ +#define RXKADINCONSISTENCY 19270400 /* security module structure inconsistent */ +#define RXKADPACKETSHORT 19270401 /* packet too short for security challenge */ +#define RXKADLEVELFAIL 19270402 /* security level negotiation failed */ +#define RXKADTICKETLEN 19270403 /* ticket length too short or too long */ +#define RXKADOUTOFSEQUENCE 19270404 /* packet had bad sequence number */ +#define RXKADNOAUTH 19270405 /* caller not authorised */ +#define RXKADBADKEY 19270406 /* illegal key: bad parity or weak */ +#define RXKADBADTICKET 19270407 /* security object was passed a bad ticket */ +#define RXKADUNKNOWNKEY 19270408 /* ticket contained unknown key version number */ +#define RXKADEXPIRED 19270409 /* authentication expired */ +#define RXKADSEALEDINCON 19270410 /* sealed data inconsistent */ +#define RXKADDATALEN 19270411 /* user data too long */ +#define RXKADILLEGALLEVEL 19270412 /* caller not authorised to use encrypted conns */ + +#endif /* _UAPI_LINUX_RXRPC_H */ diff --git a/include/uapi/linux/seg6_local.h b/include/uapi/linux/seg6_local.h new file mode 100644 index 000000000000..ef2d8c3e76c1 --- /dev/null +++ b/include/uapi/linux/seg6_local.h @@ -0,0 +1,68 @@ +/* + * SR-IPv6 implementation + * + * Author: + * David Lebrun <david.lebrun@uclouvain.be> + * + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_SEG6_LOCAL_H +#define _UAPI_LINUX_SEG6_LOCAL_H + +#include <linux/seg6.h> + +enum { + SEG6_LOCAL_UNSPEC, + SEG6_LOCAL_ACTION, + SEG6_LOCAL_SRH, + SEG6_LOCAL_TABLE, + SEG6_LOCAL_NH4, + SEG6_LOCAL_NH6, + SEG6_LOCAL_IIF, + SEG6_LOCAL_OIF, + __SEG6_LOCAL_MAX, +}; +#define SEG6_LOCAL_MAX (__SEG6_LOCAL_MAX - 1) + +enum { + SEG6_LOCAL_ACTION_UNSPEC = 0, + /* node segment */ + SEG6_LOCAL_ACTION_END = 1, + /* adjacency segment (IPv6 cross-connect) */ + SEG6_LOCAL_ACTION_END_X = 2, + /* lookup of next seg NH in table */ + SEG6_LOCAL_ACTION_END_T = 3, + /* decap and L2 cross-connect */ + SEG6_LOCAL_ACTION_END_DX2 = 4, + /* decap and IPv6 cross-connect */ + SEG6_LOCAL_ACTION_END_DX6 = 5, + /* decap and IPv4 cross-connect */ + SEG6_LOCAL_ACTION_END_DX4 = 6, + /* decap and lookup of DA in v6 table */ + SEG6_LOCAL_ACTION_END_DT6 = 7, + /* decap and lookup of DA in v4 table */ + SEG6_LOCAL_ACTION_END_DT4 = 8, + /* binding segment with insertion */ + SEG6_LOCAL_ACTION_END_B6 = 9, + /* binding segment with encapsulation */ + SEG6_LOCAL_ACTION_END_B6_ENCAP = 10, + /* binding segment with MPLS encap */ + SEG6_LOCAL_ACTION_END_BM = 11, + /* lookup last seg in table */ + SEG6_LOCAL_ACTION_END_S = 12, + /* forward to SR-unaware VNF with static proxy */ + SEG6_LOCAL_ACTION_END_AS = 13, + /* forward to SR-unaware VNF with masquerading */ + SEG6_LOCAL_ACTION_END_AM = 14, + + __SEG6_LOCAL_ACTION_MAX, +}; + +#define SEG6_LOCAL_ACTION_MAX (__SEG6_LOCAL_ACTION_MAX - 1) + +#endif diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index d85693295798..b3f346fb9fe3 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -184,14 +184,7 @@ enum LINUX_MIB_DELAYEDACKLOST, /* DelayedACKLost */ LINUX_MIB_LISTENOVERFLOWS, /* ListenOverflows */ LINUX_MIB_LISTENDROPS, /* ListenDrops */ - LINUX_MIB_TCPPREQUEUED, /* TCPPrequeued */ - LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, /* TCPDirectCopyFromBacklog */ - LINUX_MIB_TCPDIRECTCOPYFROMPREQUEUE, /* TCPDirectCopyFromPrequeue */ - LINUX_MIB_TCPPREQUEUEDROPPED, /* TCPPrequeueDropped */ - LINUX_MIB_TCPHPHITS, /* TCPHPHits */ - LINUX_MIB_TCPHPHITSTOUSER, /* TCPHPHitsToUser */ LINUX_MIB_TCPPUREACKS, /* TCPPureAcks */ - LINUX_MIB_TCPHPACKS, /* TCPHPAcks */ LINUX_MIB_TCPRENORECOVERY, /* TCPRenoRecovery */ LINUX_MIB_TCPSACKRECOVERY, /* TCPSackRecovery */ LINUX_MIB_TCPSACKRENEGING, /* TCPSACKReneging */ @@ -208,14 +201,12 @@ enum LINUX_MIB_TCPSACKFAILURES, /* TCPSackFailures */ LINUX_MIB_TCPLOSSFAILURES, /* TCPLossFailures */ LINUX_MIB_TCPFASTRETRANS, /* TCPFastRetrans */ - LINUX_MIB_TCPFORWARDRETRANS, /* TCPForwardRetrans */ LINUX_MIB_TCPSLOWSTARTRETRANS, /* TCPSlowStartRetrans */ LINUX_MIB_TCPTIMEOUTS, /* TCPTimeouts */ LINUX_MIB_TCPLOSSPROBES, /* TCPLossProbes */ LINUX_MIB_TCPLOSSPROBERECOVERY, /* TCPLossProbeRecovery */ LINUX_MIB_TCPRENORECOVERYFAIL, /* TCPRenoRecoveryFail */ LINUX_MIB_TCPSACKRECOVERYFAIL, /* TCPSackRecoveryFail */ - LINUX_MIB_TCPSCHEDULERFAILED, /* TCPSchedulerFailed */ LINUX_MIB_TCPRCVCOLLAPSED, /* TCPRcvCollapsed */ LINUX_MIB_TCPDSACKOLDSENT, /* TCPDSACKOldSent */ LINUX_MIB_TCPDSACKOFOSENT, /* TCPDSACKOfoSent */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index a5507c977497..030e594bab45 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -231,6 +231,14 @@ enum { TCP_NLA_SNDBUF_LIMITED, /* Time (usec) limited by send buffer */ TCP_NLA_DATA_SEGS_OUT, /* Data pkts sent including retransmission */ TCP_NLA_TOTAL_RETRANS, /* Data pkts retransmitted */ + TCP_NLA_PACING_RATE, /* Pacing rate in bytes per second */ + TCP_NLA_DELIVERY_RATE, /* Delivery rate in bytes per second */ + TCP_NLA_SND_CWND, /* Sending congestion window */ + TCP_NLA_REORDERING, /* Reordering metric */ + TCP_NLA_MIN_RTT, /* minimum RTT */ + TCP_NLA_RECUR_RETRANS, /* Recurring retransmits for the current pkt */ + TCP_NLA_DELIVERY_RATE_APP_LMT, /* delivery rate application limited ? */ + }; /* for TCP_MD5SIG socket option */ |