diff options
Diffstat (limited to 'include/net')
32 files changed, 273 insertions, 586 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 87214927314a..55dab604861f 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -239,6 +239,12 @@ int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct netlink_ext_ack *newchain); struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action, struct tcf_chain *newchain); + +#ifdef CONFIG_INET +DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); +#endif + +int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h index 3c516dd07caf..0e85713f56df 100644 --- a/include/net/bpf_sk_storage.h +++ b/include/net/bpf_sk_storage.h @@ -20,6 +20,8 @@ void bpf_sk_storage_free(struct sock *sk); extern const struct bpf_func_proto bpf_sk_storage_get_proto; extern const struct bpf_func_proto bpf_sk_storage_delete_proto; +extern const struct bpf_func_proto bpf_sk_storage_get_tracing_proto; +extern const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto; struct bpf_local_storage_elem; struct bpf_sk_storage_diag; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index d5ab8d99739f..78c763dfc99a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -10,6 +10,7 @@ * Copyright (C) 2018-2020 Intel Corporation */ +#include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/debugfs.h> #include <linux/list.h> @@ -1008,6 +1009,21 @@ struct survey_info { * @sae_pwd: password for SAE authentication (for devices supporting SAE * offload) * @sae_pwd_len: length of SAE password (for devices supporting SAE offload) + * @sae_pwe: The mechanisms allowed for SAE PWE derivation: + * + * NL80211_SAE_PWE_UNSPECIFIED + * Not-specified, used to indicate userspace did not specify any + * preference. The driver should follow its internal policy in + * such a scenario. + * + * NL80211_SAE_PWE_HUNT_AND_PECK + * Allow hunting-and-pecking loop only + * + * NL80211_SAE_PWE_HASH_TO_ELEMENT + * Allow hash-to-element only + * + * NL80211_SAE_PWE_BOTH + * Allow either hunting-and-pecking loop or hash-to-element */ struct cfg80211_crypto_settings { u32 wpa_versions; @@ -1026,6 +1042,7 @@ struct cfg80211_crypto_settings { const u8 *psk; const u8 *sae_pwd; u8 sae_pwd_len; + enum nl80211_sae_pwe_mechanism sae_pwe; }; /** @@ -3736,8 +3753,6 @@ struct mgmt_frame_regs { * @get_tx_power: store the current TX power into the dbm variable; * return 0 if successful * - * @set_wds_peer: set the WDS peer for a WDS interface - * * @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting * functions to adjust rfkill hw state * @@ -4058,9 +4073,6 @@ struct cfg80211_ops { int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, int *dbm); - int (*set_wds_peer)(struct wiphy *wiphy, struct net_device *dev, - const u8 *addr); - void (*rfkill_poll)(struct wiphy *wiphy); #ifdef CONFIG_NL80211_TESTMODE diff --git a/include/net/compat.h b/include/net/compat.h index 745db0d605b6..84805bdc4435 100644 --- a/include/net/compat.h +++ b/include/net/compat.h @@ -5,8 +5,6 @@ struct sock; -#if defined(CONFIG_COMPAT) - #include <linux/compat.h> struct compat_msghdr { @@ -48,14 +46,6 @@ struct compat_rtentry { unsigned short rt_irtt; /* Initial RTT */ }; -#else /* defined(CONFIG_COMPAT) */ -/* - * To avoid compiler warnings: - */ -#define compat_msghdr msghdr -#define compat_mmsghdr mmsghdr -#endif /* defined(CONFIG_COMPAT) */ - int __get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg, struct sockaddr __user **save_addr, compat_uptr_t *ptr, compat_size_t *len); diff --git a/include/net/devlink.h b/include/net/devlink.h index b01bb9bca5a2..f466819cc477 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -19,6 +19,7 @@ #include <net/flow_offload.h> #include <uapi/linux/devlink.h> #include <linux/xarray.h> +#include <linux/firmware.h> #define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) @@ -566,15 +567,15 @@ enum devlink_param_generic_id { /** * struct devlink_flash_update_params - Flash Update parameters - * @file_name: the name of the flash firmware file to update from + * @fw: pointer to the firmware data to update from * @component: the flash component to update * - * With the exception of file_name, drivers must opt-in to parameters by + * With the exception of fw, drivers must opt-in to parameters by * setting the appropriate bit in the supported_flash_update_params field in * their devlink_ops structure. */ struct devlink_flash_update_params { - const char *file_name; + const struct firmware *fw; const char *component; u32 overwrite_mask; }; @@ -834,6 +835,7 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_DCCP_PARSING, DEVLINK_TRAP_GENERIC_ID_GTP_PARSING, DEVLINK_TRAP_GENERIC_ID_ESP_PARSING, + DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_NEXTHOP, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -1057,7 +1059,8 @@ enum devlink_trap_group_generic_id { "gtp_parsing" #define DEVLINK_TRAP_GENERIC_NAME_ESP_PARSING \ "esp_parsing" - +#define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_NEXTHOP \ + "blackhole_nexthop" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" @@ -1576,8 +1579,6 @@ void devlink_remote_reload_actions_performed(struct devlink *devlink, enum devlink_reload_limit limit, u32 actions_performed); -void devlink_flash_update_begin_notify(struct devlink *devlink); -void devlink_flash_update_end_notify(struct devlink *devlink); void devlink_flash_update_status_notify(struct devlink *devlink, const char *status_msg, const char *component, diff --git a/include/net/dsa.h b/include/net/dsa.h index 35429a140dfa..4e60d2610f20 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -45,6 +45,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 +#define DSA_TAG_PROTO_HELLCREEK_VALUE 18 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -65,6 +66,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, + DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, }; struct packet_type; @@ -535,6 +537,12 @@ struct dsa_switch_ops { struct ethtool_regs *regs, void *p); /* + * Upper device tracking. + */ + int (*port_prechangeupper)(struct dsa_switch *ds, int port, + struct netdev_notifier_changeupper_info *info); + + /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); diff --git a/include/net/dst.h b/include/net/dst.h index 8ea8812b0b41..10f0a8399867 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -400,14 +400,12 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - struct neighbour *n = NULL; + struct neighbour *n; - /* The packets from tunnel devices (eg bareudp) may have only - * metadata in the dst pointer of skb. Hence a pointer check of - * neigh_lookup is needed. - */ - if (dst->ops->neigh_lookup) - n = dst->ops->neigh_lookup(dst, skb, NULL); + if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) + return NULL; + + n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 19c00d100096..c0854933e24f 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -118,6 +118,7 @@ enum ieee80211_radiotap_tx_flags { IEEE80211_RADIOTAP_F_TX_RTS = 0x0004, IEEE80211_RADIOTAP_F_TX_NOACK = 0x0008, IEEE80211_RADIOTAP_F_TX_NOSEQNO = 0x0010, + IEEE80211_RADIOTAP_F_TX_ORDER = 0x0020, }; /* for IEEE80211_RADIOTAP_MCS "have" flags */ diff --git a/include/net/ip.h b/include/net/ip.h index 2d6b985d11cc..e20874059f82 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -99,7 +99,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, #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) +static inline int inet_sdif(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) if (skb && ipv4_l3mdev_skb(IPCB(skb)->flags)) diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 61620677b034..548b65bd3973 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -274,8 +274,6 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); -void ip_tunnel_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *tot); struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, int link, __be16 flags, __be32 remote, __be32 local, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dcdba96814a2..05c7524bab26 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -621,7 +621,8 @@ struct ieee80211_fils_discovery { * nontransmitted BSSIDs * @profile_periodicity: the least number of beacon frames need to be received * in order to discover all the nontransmitted BSSIDs in the set. - * @he_oper: HE operation information of the AP we are connected to + * @he_oper: HE operation information of the BSS (AP/Mesh) or of the AP we are + * connected to (STA) * @he_obss_pd: OBSS Packet Detection parameters. * @he_bss_color: BSS coloring settings, if BSS supports HE * @fils_discovery: FILS discovery configuration @@ -856,6 +857,9 @@ enum mac80211_tx_info_flags { * it can be sent out. * @IEEE80211_TX_CTRL_NO_SEQNO: Do not overwrite the sequence number that * has already been assigned to this frame. + * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered + * relative to other frames that have this flag set, independent + * of their QoS TID or other priority field values. * * These flags are used in tx_info->control.flags. */ @@ -868,6 +872,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_SKIP_MPATH_LOOKUP = BIT(5), IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), + IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), }; /* diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 753ba7e755d6..b6cf07143a8a 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -29,7 +29,8 @@ struct mptcp_ext { use_ack:1, ack64:1, mpc_map:1, - __unused:2; + frozen:1, + __unused:1; /* one byte hole */ }; @@ -87,7 +88,8 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts); void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); -void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts); +void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, + struct mptcp_out_options *opts); /* move the skb extension owership, with the assumption that 'to' is * newly allocated @@ -106,6 +108,19 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to, from->active_extensions = 0; } +static inline void mptcp_skb_ext_copy(struct sk_buff *to, + struct sk_buff *from) +{ + struct mptcp_ext *from_ext; + + from_ext = skb_ext_find(from, SKB_EXT_MPTCP); + if (!from_ext) + return; + + from_ext->frozen = 1; + skb_ext_copy(to, from); +} + static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext, const struct mptcp_ext *from_ext) { @@ -193,6 +208,11 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to, { } +static inline void mptcp_skb_ext_copy(struct sk_buff *to, + struct sk_buff *from) +{ +} + static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 40e0e0623f46..0d8ff84a2588 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -18,4 +18,14 @@ struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); +struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code); +struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook); + + #endif /* _IPV4_NF_REJECT_H */ diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 4a3ef9ebdf6f..edcf6d1cd316 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -20,4 +20,13 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth, unsigned int otcplen); +struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook); +struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code); + #endif /* _IPV6_NF_REJECT_H */ diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 88186b95b3c2..9be7320b994f 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -203,6 +203,20 @@ static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) { return &net->ct.nf_ct_proto.icmpv6; } + +/* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */ +static inline void nf_ct_set_tcp_be_liberal(struct nf_conn *ct) +{ + ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; + ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL; +} + +/* Caller must check nf_ct_protonum(ct) is IPPROTO_TCP before calling. */ +static inline bool nf_conntrack_tcp_established(const struct nf_conn *ct) +{ + return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED && + test_bit(IPS_ASSURED_BIT, &ct->status); +} #endif #ifdef CONFIG_NF_CT_PROTO_DCCP diff --git a/include/net/netlink.h b/include/net/netlink.h index 7356f41d23ba..1ceec518ab49 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -142,7 +142,7 @@ * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area - * nla_strlcpy(dst, nla, size) copy attribute to a sized string + * nla_strscpy(dst, nla, size) copy attribute to a sized string * nla_strcmp(nla, str) compare attribute with string * * Attribute Parsing: @@ -506,7 +506,7 @@ int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); -size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); +ssize_t nla_strscpy(char *dst, const struct nlattr *nla, size_t dstsize); char *nla_strdup(const struct nlattr *nla, gfp_t flags); int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index d8d02e4188d1..a0f315effa94 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -22,6 +22,14 @@ struct netns_sctp { */ struct sock *ctl_sock; + /* UDP tunneling listening sock. */ + struct sock *udp4_sock; + struct sock *udp6_sock; + /* UDP tunneling listening port. */ + int udp_port; + /* UDP tunneling remote encap port. */ + int encap_port; + /* This is the global local address list. * We actively maintain this complete list of addresses on * the system by catching address add/delete events. diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 2fd76a9b6dc8..226930d66b63 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,11 +105,49 @@ struct nexthop { }; enum nexthop_event_type { - NEXTHOP_EVENT_DEL + NEXTHOP_EVENT_DEL, + NEXTHOP_EVENT_REPLACE, }; -int register_nexthop_notifier(struct net *net, struct notifier_block *nb); +struct nh_notifier_single_info { + struct net_device *dev; + u8 gw_family; + union { + __be32 ipv4; + struct in6_addr ipv6; + }; + u8 is_reject:1, + is_fdb:1, + has_encap:1; +}; + +struct nh_notifier_grp_entry_info { + u8 weight; + u32 id; + struct nh_notifier_single_info nh; +}; + +struct nh_notifier_grp_info { + u16 num_nh; + bool is_fdb; + struct nh_notifier_grp_entry_info nh_entries[]; +}; + +struct nh_notifier_info { + struct net *net; + struct netlink_ext_ack *extack; + u32 id; + bool is_grp; + union { + struct nh_notifier_single_info *nh; + struct nh_notifier_grp_info *nh_grp; + }; +}; + +int register_nexthop_notifier(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); +void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 81d7773f96cd..b5b195305346 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -152,6 +152,8 @@ struct page_pool *page_pool_create(const struct page_pool_params *params); void page_pool_destroy(struct page_pool *pool); void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); void page_pool_release_page(struct page_pool *pool, struct page *page); +void page_pool_put_page_bulk(struct page_pool *pool, void **data, + int count); #else static inline void page_pool_destroy(struct page_pool *pool) { @@ -165,6 +167,11 @@ static inline void page_pool_release_page(struct page_pool *pool, struct page *page) { } + +static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data, + int count) +{ +} #endif void page_pool_put_page(struct page_pool *pool, struct page *page, @@ -215,4 +222,23 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) if (unlikely(pool->p.nid != new_nid)) page_pool_update_nid(pool, new_nid); } + +static inline void page_pool_ring_lock(struct page_pool *pool) + __acquires(&pool->ring.producer_lock) +{ + if (in_serving_softirq()) + spin_lock(&pool->ring.producer_lock); + else + spin_lock_bh(&pool->ring.producer_lock); +} + +static inline void page_pool_ring_unlock(struct page_pool *pool) + __releases(&pool->ring.producer_lock) +{ + if (in_serving_softirq()) + spin_unlock(&pool->ring.producer_lock); + else + spin_unlock_bh(&pool->ring.producer_lock); +} + #endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index d4d461236351..133f9ad4d4f9 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -512,7 +512,7 @@ tcf_change_indev(struct net *net, struct nlattr *indev_tlv, char indev[IFNAMSIZ]; struct net_device *dev; - if (nla_strlcpy(indev, indev_tlv, IFNAMSIZ) >= IFNAMSIZ) { + if (nla_strscpy(indev, indev_tlv, IFNAMSIZ) < 0) { NL_SET_ERR_MSG_ATTR(extack, indev_tlv, "Interface name too long"); return -EINVAL; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 4ed32e6b0201..15b1b30f454e 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -24,6 +24,11 @@ static inline void *qdisc_priv(struct Qdisc *q) return &q->privdata; } +static inline struct Qdisc *qdisc_from_priv(void *priv) +{ + return container_of(priv, struct Qdisc, privdata); +} + /* Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d8fd8676fc72..162ed6249e8b 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1281,9 +1281,6 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); -static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) -{ - return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb); -} +int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #endif diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 122d9e2d8dfd..14a0d22c9113 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -286,6 +286,8 @@ enum { SCTP_MAX_GABS = 16 }; * functions simpler to write. */ +#define SCTP_DEFAULT_UDP_PORT 9899 /* default UDP tunneling port */ + /* These are the values for pf exposure, UNUSED is to keep compatible with old * applications by default. */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 4fc747b778eb..86f74f2fe6de 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -84,6 +84,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *addr, 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); +int sctp_udp_sock_start(struct net *net); +void sctp_udp_sock_stop(struct net *net); /* * sctp/socket.c @@ -576,10 +578,13 @@ static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, { __u32 overhead = sizeof(struct sctphdr) + extra; - if (sp) + if (sp) { overhead += sp->pf->af->net_header_len; - else + if (sp->udp_port) + overhead += sizeof(struct udphdr); + } else { overhead += sizeof(struct ipv6hdr); + } if (WARN_ON_ONCE(mtu && mtu <= overhead)) mtu = overhead; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 5c491a3bc27e..fd223c94589a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -221,6 +221,9 @@ struct sctp_chunk *sctp_make_violation_paramlen( struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_new_encap_port( + 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, @@ -380,6 +383,7 @@ sctp_vtag_verify(const struct sctp_chunk *chunk, if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag) return 1; + chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; return 0; } diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0bdff38eb4bb..1aa585216f34 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -178,6 +178,9 @@ struct sctp_sock { */ __u32 hbinterval; + __be16 udp_port; + __be16 encap_port; + /* This is the max_retrans value for new associations. */ __u16 pathmaxrxt; @@ -877,6 +880,8 @@ struct sctp_transport { */ unsigned long last_time_ecne_reduced; + __be16 encap_port; + /* This is the max_retrans value for the transport and will * be initialized from the assocs value. This can be changed * using the SCTP_SET_PEER_ADDR_PARAMS socket option. @@ -1117,13 +1122,14 @@ static inline void sctp_outq_cork(struct sctp_outq *q) */ struct sctp_input_cb { union { - struct inet_skb_parm h4; + struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) - struct inet6_skb_parm h6; + struct inet6_skb_parm h6; #endif } header; struct sctp_chunk *chunk; struct sctp_af *af; + __be16 encap_port; }; #define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) @@ -1790,6 +1796,8 @@ struct sctp_association { */ unsigned long hbinterval; + __be16 encap_port; + /* This is the max_retrans value for new transports in the * association. */ diff --git a/include/net/sock.h b/include/net/sock.h index a5c6ae78df77..80469c2c448d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -60,7 +60,7 @@ #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> - +#include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <net/dst.h> @@ -1264,13 +1264,22 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ +INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake)); + static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false; +#ifdef CONFIG_INET + return sk->sk_prot->stream_memory_free ? + INDIRECT_CALL_1(sk->sk_prot->stream_memory_free, + tcp_stream_memory_free, + sk, wake) : true; +#else return sk->sk_prot->stream_memory_free ? sk->sk_prot->stream_memory_free(sk, wake) : true; +#endif } static inline bool sk_stream_memory_free(const struct sock *sk) @@ -1591,7 +1600,8 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk); +bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + /** * unlock_sock_fast - complement of lock_sock_fast * @sk: socket @@ -1601,11 +1611,14 @@ bool lock_sock_fast(struct sock *sk); * If slow mode is on, we call regular release_sock() */ static inline void unlock_sock_fast(struct sock *sk, bool slow) + __releases(&sk->sk_lock.slock) { - if (slow) + if (slow) { release_sock(sk); - else + __release(&sk->sk_lock.slock); + } else { spin_unlock_bh(&sk->sk_lock.slock); + } } /* Used by processes to "lock" a socket state, so that diff --git a/include/net/tcp.h b/include/net/tcp.h index d4ef5bf94168..d5d22c411918 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -322,6 +322,7 @@ void tcp_shutdown(struct sock *sk, int how); int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); +void tcp_remove_empty_skb(struct sock *sk, 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); @@ -329,6 +330,8 @@ 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); +struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, + struct page *page, int offset, size_t *size); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); @@ -386,12 +389,13 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); -void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag); +void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst); +void __tcp_close(struct sock *sk, long timeout); void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb); @@ -1965,18 +1969,7 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } -/* @wake is one when sk_stream_write_space() calls us. - * This sends EPOLLOUT only if notsent_bytes is half the limit. - * This mimics the strategy used in sock_def_write_space(). - */ -static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) -{ - const struct tcp_sock *tp = tcp_sk(sk); - u32 notsent_bytes = READ_ONCE(tp->write_seq) - - READ_ONCE(tp->snd_nxt); - - return (notsent_bytes << wake) < tcp_notsent_lowat(tp); -} +bool tcp_stream_memory_free(const struct sock *sk, int wake); #ifdef CONFIG_PROC_FS int tcp4_proc_init(void); diff --git a/include/net/tls.h b/include/net/tls.h index 2bdd802212fe..3eccb525e8f7 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -217,6 +217,7 @@ union tls_crypto_context { union { struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; + struct tls12_crypto_info_chacha20_poly1305 chacha20_poly1305; }; }; @@ -507,32 +508,33 @@ static inline void tls_advance_record_sn(struct sock *sk, if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) tls_err_abort(sk, EBADMSG); - if (prot->version != TLS_1_3_VERSION) - tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + if (prot->version != TLS_1_3_VERSION && + prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) + tls_bigint_increment(ctx->iv + prot->salt_size, prot->iv_size); } static inline void tls_fill_prepend(struct tls_context *ctx, char *buf, size_t plaintext_len, - unsigned char record_type, - int version) + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; size_t pkt_len, iv_size = prot->iv_size; pkt_len = plaintext_len + prot->tag_size; - if (version != TLS_1_3_VERSION) { + if (prot->version != TLS_1_3_VERSION && + prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) { pkt_len += iv_size; memcpy(buf + TLS_NONCE_OFFSET, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); + ctx->tx.iv + prot->salt_size, iv_size); } /* we cover nonce explicit here as well, so buf should be of * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ - buf[0] = version == TLS_1_3_VERSION ? + buf[0] = prot->version == TLS_1_3_VERSION ? TLS_RECORD_TYPE_DATA : record_type; /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ buf[1] = TLS_1_2_VERSION_MINOR; @@ -545,18 +547,17 @@ static inline void tls_fill_prepend(struct tls_context *ctx, static inline void tls_make_aad(char *buf, size_t size, char *record_sequence, - int record_sequence_size, unsigned char record_type, - int version) + struct tls_prot_info *prot) { - if (version != TLS_1_3_VERSION) { - memcpy(buf, record_sequence, record_sequence_size); + if (prot->version != TLS_1_3_VERSION) { + memcpy(buf, record_sequence, prot->rec_seq_size); buf += 8; } else { - size += TLS_CIPHER_AES_GCM_128_TAG_SIZE; + size += prot->tag_size; } - buf[0] = version == TLS_1_3_VERSION ? + buf[0] = prot->version == TLS_1_3_VERSION ? TLS_RECORD_TYPE_DATA : record_type; buf[1] = TLS_1_2_VERSION_MAJOR; buf[2] = TLS_1_2_VERSION_MINOR; @@ -564,11 +565,12 @@ static inline void tls_make_aad(char *buf, buf[4] = size & 0xFF; } -static inline void xor_iv_with_seq(int version, char *iv, char *seq) +static inline void xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq) { int i; - if (version == TLS_1_3_VERSION) { + if (prot->version == TLS_1_3_VERSION || + prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) { for (i = 0; i < 8; i++) iv[i + 4] ^= seq[i]; } diff --git a/include/net/udp.h b/include/net/udp.h index 295d52a73598..877832bed471 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -164,7 +164,7 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr); } -typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport, +typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, @@ -313,7 +313,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __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, +struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, @@ -324,7 +324,7 @@ struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *daddr, __be16 dport, int dif, int sdif, struct udp_table *tbl, struct sk_buff *skb); -struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, +struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid diff --git a/include/net/wimax.h b/include/net/wimax.h deleted file mode 100644 index f6e31d2f47aa..000000000000 --- a/include/net/wimax.h +++ /dev/null @@ -1,503 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Linux WiMAX - * Kernel space API for accessing WiMAX devices - * - * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com> - * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> - * - * The WiMAX stack provides an API for controlling and managing the - * system's WiMAX devices. This API affects the control plane; the - * data plane is accessed via the network stack (netdev). - * - * Parts of the WiMAX stack API and notifications are exported to - * user space via Generic Netlink. In user space, libwimax (part of - * the wimax-tools package) provides a shim layer for accessing those - * calls. - * - * The API is standarized for all WiMAX devices and different drivers - * implement the backend support for it. However, device-specific - * messaging pipes are provided that can be used to issue commands and - * receive notifications in free form. - * - * Currently the messaging pipes are the only means of control as it - * is not known (due to the lack of more devices in the market) what - * will be a good abstraction layer. Expect this to change as more - * devices show in the market. This API is designed to be growable in - * order to address this problem. - * - * USAGE - * - * Embed a `struct wimax_dev` at the beginning of the device's - * private structure, initialize and register it. For details, see - * `struct wimax_dev`s documentation. - * - * Once this is done, wimax-tools's libwimaxll can be used to - * communicate with the driver from user space. You user space - * application does not have to forcibily use libwimaxll and can talk - * the generic netlink protocol directly if desired. - * - * Remember this is a very low level API that will to provide all of - * WiMAX features. Other daemons and services running in user space - * are the expected clients of it. They offer a higher level API that - * applications should use (an example of this is the Intel's WiMAX - * Network Service for the i2400m). - * - * DESIGN - * - * Although not set on final stone, this very basic interface is - * mostly completed. Remember this is meant to grow as new common - * operations are decided upon. New operations will be added to the - * interface, intent being on keeping backwards compatibility as much - * as possible. - * - * This layer implements a set of calls to control a WiMAX device, - * exposing a frontend to the rest of the kernel and user space (via - * generic netlink) and a backend implementation in the driver through - * function pointers. - * - * WiMAX devices have a state, and a kernel-only API allows the - * drivers to manipulate that state. State transitions are atomic, and - * only some of them are allowed (see `enum wimax_st`). - * - * Most API calls will set the state automatically; in most cases - * drivers have to only report state changes due to external - * conditions. - * - * All API operations are 'atomic', serialized through a mutex in the - * `struct wimax_dev`. - * - * EXPORTING TO USER SPACE THROUGH GENERIC NETLINK - * - * The API is exported to user space using generic netlink (other - * methods can be added as needed). - * - * There is a Generic Netlink Family named "WiMAX", where interfaces - * supporting the WiMAX interface receive commands and broadcast their - * signals over a multicast group named "msg". - * - * Mapping to the source/destination interface is done by an interface - * index attribute. - * - * For user-to-kernel traffic (commands) we use a function call - * marshalling mechanism, where a message X with attributes A, B, C - * sent from user space to kernel space means executing the WiMAX API - * call wimax_X(A, B, C), sending the results back as a message. - * - * Kernel-to-user (notifications or signals) communication is sent - * over multicast groups. This allows to have multiple applications - * monitoring them. - * - * Each command/signal gets assigned it's own attribute policy. This - * way the validator will verify that all the attributes in there are - * only the ones that should be for each command/signal. Thing of an - * attribute mapping to a type+argumentname for each command/signal. - * - * If we had a single policy for *all* commands/signals, after running - * the validator we'd have to check "does this attribute belong in - * here"? for each one. It can be done manually, but it's just easier - * to have the validator do that job with multiple policies. As well, - * it makes it easier to later expand each command/signal signature - * without affecting others and keeping the namespace more or less - * sane. Not that it is too complicated, but it makes it even easier. - * - * No state information is maintained in the kernel for each user - * space connection (the connection is stateless). - * - * TESTING FOR THE INTERFACE AND VERSIONING - * - * If network interface X is a WiMAX device, there will be a Generic - * Netlink family named "WiMAX X" and the device will present a - * "wimax" directory in it's network sysfs directory - * (/sys/class/net/DEVICE/wimax) [used by HAL]. - * - * The inexistence of any of these means the device does not support - * this WiMAX API. - * - * By querying the generic netlink controller, versioning information - * and the multicast groups available can be found. Applications using - * the interface can either rely on that or use the generic netlink - * controller to figure out which generic netlink commands/signals are - * supported. - * - * NOTE: this versioning is a last resort to avoid hard - * incompatibilities. It is the intention of the design of this - * stack not to introduce backward incompatible changes. - * - * The version code has to fit in one byte (restrictions imposed by - * generic netlink); we use `version / 10` for the major version and - * `version % 10` for the minor. This gives 9 minors for each major - * and 25 majors. - * - * The version change protocol is as follow: - * - * - Major versions: needs to be increased if an existing message/API - * call is changed or removed. Doesn't need to be changed if a new - * message is added. - * - * - Minor version: needs to be increased if new messages/API calls are - * being added or some other consideration that doesn't impact the - * user-kernel interface too much (like some kind of bug fix) and - * that is kind of left up in the air to common sense. - * - * User space code should not try to work if the major version it was - * compiled for differs from what the kernel offers. As well, if the - * minor version of the kernel interface is lower than the one user - * space is expecting (the one it was compiled for), the kernel - * might be missing API calls; user space shall be ready to handle - * said condition. Use the generic netlink controller operations to - * find which ones are supported and which not. - * - * libwimaxll:wimaxll_open() takes care of checking versions. - * - * THE OPERATIONS: - * - * Each operation is defined in its on file (drivers/net/wimax/op-*.c) - * for clarity. The parts needed for an operation are: - * - * - a function pointer in `struct wimax_dev`: optional, as the - * operation might be implemented by the stack and not by the - * driver. - * - * All function pointers are named wimax_dev->op_*(), and drivers - * must implement them except where noted otherwise. - * - * - When exported to user space, a `struct nla_policy` to define the - * attributes of the generic netlink command and a `struct genl_ops` - * to define the operation. - * - * All the declarations for the operation codes (WIMAX_GNL_OP_<NAME>) - * and generic netlink attributes (WIMAX_GNL_<NAME>_*) are declared in - * include/linux/wimax.h; this file is intended to be cloned by user - * space to gain access to those declarations. - * - * A few caveats to remember: - * - * - Need to define attribute numbers starting in 1; otherwise it - * fails. - * - * - the `struct genl_family` requires a maximum attribute id; when - * defining the `struct nla_policy` for each message, it has to have - * an array size of WIMAX_GNL_ATTR_MAX+1. - * - * The op_*() function pointers will not be called if the wimax_dev is - * in a state <= %WIMAX_ST_UNINITIALIZED. The exception is: - * - * - op_reset: can be called at any time after wimax_dev_add() has - * been called. - * - * THE PIPE INTERFACE: - * - * This interface is kept intentionally simple. The driver can send - * and receive free-form messages to/from user space through a - * pipe. See drivers/net/wimax/op-msg.c for details. - * - * The kernel-to-user messages are sent with - * wimax_msg(). user-to-kernel messages are delivered via - * wimax_dev->op_msg_from_user(). - * - * RFKILL: - * - * RFKILL support is built into the wimax_dev layer; the driver just - * needs to call wimax_report_rfkill_{hw,sw}() to inform of changes in - * the hardware or software RF kill switches. When the stack wants to - * turn the radio off, it will call wimax_dev->op_rfkill_sw_toggle(), - * which the driver implements. - * - * User space can set the software RF Kill switch by calling - * wimax_rfkill(). - * - * The code for now only supports devices that don't require polling; - * If the device needs to be polled, create a self-rearming delayed - * work struct for polling or look into adding polled support to the - * WiMAX stack. - * - * When initializing the hardware (_probe), after calling - * wimax_dev_add(), query the device for it's RF Kill switches status - * and feed it back to the WiMAX stack using - * wimax_report_rfkill_{hw,sw}(). If any switch is missing, always - * report it as ON. - * - * NOTE: the wimax stack uses an inverted terminology to that of the - * RFKILL subsystem: - * - * - ON: radio is ON, RFKILL is DISABLED or OFF. - * - OFF: radio is OFF, RFKILL is ENABLED or ON. - * - * MISCELLANEOUS OPS: - * - * wimax_reset() can be used to reset the device to power on state; by - * default it issues a warm reset that maintains the same device - * node. If that is not possible, it falls back to a cold reset - * (device reconnect). The driver implements the backend to this - * through wimax_dev->op_reset(). - */ - -#ifndef __NET__WIMAX_H__ -#define __NET__WIMAX_H__ - -#include <linux/wimax.h> -#include <net/genetlink.h> -#include <linux/netdevice.h> - -struct net_device; -struct genl_info; -struct wimax_dev; - -/** - * struct wimax_dev - Generic WiMAX device - * - * @net_dev: [fill] Pointer to the &struct net_device this WiMAX - * device implements. - * - * @op_msg_from_user: [fill] Driver-specific operation to - * handle a raw message from user space to the driver. The - * driver can send messages to user space using with - * wimax_msg_to_user(). - * - * @op_rfkill_sw_toggle: [fill] Driver-specific operation to act on - * userspace (or any other agent) requesting the WiMAX device to - * change the RF Kill software switch (WIMAX_RF_ON or - * WIMAX_RF_OFF). - * If such hardware support is not present, it is assumed the - * radio cannot be switched off and it is always on (and the stack - * will error out when trying to switch it off). In such case, - * this function pointer can be left as NULL. - * - * @op_reset: [fill] Driver specific operation to reset the - * device. - * This operation should always attempt first a warm reset that - * does not disconnect the device from the bus and return 0. - * If that fails, it should resort to some sort of cold or bus - * reset (even if it implies a bus disconnection and device - * disappearance). In that case, -ENODEV should be returned to - * indicate the device is gone. - * This operation has to be synchronous, and return only when the - * reset is complete. In case of having had to resort to bus/cold - * reset implying a device disconnection, the call is allowed to - * return immediately. - * NOTE: wimax_dev->mutex is NOT locked when this op is being - * called; however, wimax_dev->mutex_reset IS locked to ensure - * serialization of calls to wimax_reset(). - * See wimax_reset()'s documentation. - * - * @name: [fill] A way to identify this device. We need to register a - * name with many subsystems (rfkill, workqueue creation, etc). - * We can't use the network device name as that - * might change and in some instances we don't know it yet (until - * we don't call register_netdev()). So we generate an unique one - * using the driver name and device bus id, place it here and use - * it across the board. Recommended naming: - * DRIVERNAME-BUSNAME:BUSID (dev->bus->name, dev->bus_id). - * - * @id_table_node: [private] link to the list of wimax devices kept by - * id-table.c. Protected by it's own spinlock. - * - * @mutex: [private] Serializes all concurrent access and execution of - * operations. - * - * @mutex_reset: [private] Serializes reset operations. Needs to be a - * different mutex because as part of the reset operation, the - * driver has to call back into the stack to do things such as - * state change, that require wimax_dev->mutex. - * - * @state: [private] Current state of the WiMAX device. - * - * @rfkill: [private] integration into the RF-Kill infrastructure. - * - * @rf_sw: [private] State of the software radio switch (OFF/ON) - * - * @rf_hw: [private] State of the hardware radio switch (OFF/ON) - * - * @debugfs_dentry: [private] Used to hook up a debugfs entry. This - * shows up in the debugfs root as wimax\:DEVICENAME. - * - * Description: - * This structure defines a common interface to access all WiMAX - * devices from different vendors and provides a common API as well as - * a free-form device-specific messaging channel. - * - * Usage: - * 1. Embed a &struct wimax_dev at *the beginning* the network - * device structure so that netdev_priv() points to it. - * - * 2. memset() it to zero - * - * 3. Initialize with wimax_dev_init(). This will leave the WiMAX - * device in the %__WIMAX_ST_NULL state. - * - * 4. Fill all the fields marked with [fill]; once called - * wimax_dev_add(), those fields CANNOT be modified. - * - * 5. Call wimax_dev_add() *after* registering the network - * device. This will leave the WiMAX device in the %WIMAX_ST_DOWN - * state. - * Protect the driver's net_device->open() against succeeding if - * the wimax device state is lower than %WIMAX_ST_DOWN. - * - * 6. Select when the device is going to be turned on/initialized; - * for example, it could be initialized on 'ifconfig up' (when the - * netdev op 'open()' is called on the driver). - * - * When the device is initialized (at `ifconfig up` time, or right - * after calling wimax_dev_add() from _probe(), make sure the - * following steps are taken - * - * a. Move the device to %WIMAX_ST_UNINITIALIZED. This is needed so - * some API calls that shouldn't work until the device is ready - * can be blocked. - * - * b. Initialize the device. Make sure to turn the SW radio switch - * off and move the device to state %WIMAX_ST_RADIO_OFF when - * done. When just initialized, a device should be left in RADIO - * OFF state until user space devices to turn it on. - * - * c. Query the device for the state of the hardware rfkill switch - * and call wimax_rfkill_report_hw() and wimax_rfkill_report_sw() - * as needed. See below. - * - * wimax_dev_rm() undoes before unregistering the network device. Once - * wimax_dev_add() is called, the driver can get called on the - * wimax_dev->op_* function pointers - * - * CONCURRENCY: - * - * The stack provides a mutex for each device that will disallow API - * calls happening concurrently; thus, op calls into the driver - * through the wimax_dev->op*() function pointers will always be - * serialized and *never* concurrent. - * - * For locking, take wimax_dev->mutex is taken; (most) operations in - * the API have to check for wimax_dev_is_ready() to return 0 before - * continuing (this is done internally). - * - * REFERENCE COUNTING: - * - * The WiMAX device is reference counted by the associated network - * device. The only operation that can be used to reference the device - * is wimax_dev_get_by_genl_info(), and the reference it acquires has - * to be released with dev_put(wimax_dev->net_dev). - * - * RFKILL: - * - * At startup, both HW and SW radio switchess are assumed to be off. - * - * At initialization time [after calling wimax_dev_add()], have the - * driver query the device for the status of the software and hardware - * RF kill switches and call wimax_report_rfkill_hw() and - * wimax_rfkill_report_sw() to indicate their state. If any is - * missing, just call it to indicate it is ON (radio always on). - * - * Whenever the driver detects a change in the state of the RF kill - * switches, it should call wimax_report_rfkill_hw() or - * wimax_report_rfkill_sw() to report it to the stack. - */ -struct wimax_dev { - struct net_device *net_dev; - struct list_head id_table_node; - struct mutex mutex; /* Protects all members and API calls */ - struct mutex mutex_reset; - enum wimax_st state; - - int (*op_msg_from_user)(struct wimax_dev *wimax_dev, - const char *, - const void *, size_t, - const struct genl_info *info); - int (*op_rfkill_sw_toggle)(struct wimax_dev *wimax_dev, - enum wimax_rf_state); - int (*op_reset)(struct wimax_dev *wimax_dev); - - struct rfkill *rfkill; - unsigned int rf_hw; - unsigned int rf_sw; - char name[32]; - - struct dentry *debugfs_dentry; -}; - - - -/* - * WiMAX stack public API for device drivers - * ----------------------------------------- - * - * These functions are not exported to user space. - */ -void wimax_dev_init(struct wimax_dev *); -int wimax_dev_add(struct wimax_dev *, struct net_device *); -void wimax_dev_rm(struct wimax_dev *); - -static inline -struct wimax_dev *net_dev_to_wimax(struct net_device *net_dev) -{ - return netdev_priv(net_dev); -} - -static inline -struct device *wimax_dev_to_dev(struct wimax_dev *wimax_dev) -{ - return wimax_dev->net_dev->dev.parent; -} - -void wimax_state_change(struct wimax_dev *, enum wimax_st); -enum wimax_st wimax_state_get(struct wimax_dev *); - -/* - * Radio Switch state reporting. - * - * enum wimax_rf_state is declared in linux/wimax.h so the exports - * to user space can use it. - */ -void wimax_report_rfkill_hw(struct wimax_dev *, enum wimax_rf_state); -void wimax_report_rfkill_sw(struct wimax_dev *, enum wimax_rf_state); - - -/* - * Free-form messaging to/from user space - * - * Sending a message: - * - * wimax_msg(wimax_dev, pipe_name, buf, buf_size, GFP_KERNEL); - * - * Broken up: - * - * skb = wimax_msg_alloc(wimax_dev, pipe_name, buf_size, GFP_KERNEL); - * ...fill up skb... - * wimax_msg_send(wimax_dev, pipe_name, skb); - * - * Be sure not to modify skb->data in the middle (ie: don't use - * skb_push()/skb_pull()/skb_reserve() on the skb). - * - * "pipe_name" is any string, that can be interpreted as the name of - * the pipe or recipient; the interpretation of it is driver - * specific, so the recipient can multiplex it as wished. It can be - * NULL, it won't be used - an example is using a "diagnostics" tag to - * send diagnostics information that a device-specific diagnostics - * tool would be interested in. - */ -struct sk_buff *wimax_msg_alloc(struct wimax_dev *, const char *, const void *, - size_t, gfp_t); -int wimax_msg_send(struct wimax_dev *, struct sk_buff *); -int wimax_msg(struct wimax_dev *, const char *, const void *, size_t, gfp_t); - -const void *wimax_msg_data_len(struct sk_buff *, size_t *); -const void *wimax_msg_data(struct sk_buff *); -ssize_t wimax_msg_len(struct sk_buff *); - - -/* - * WiMAX stack user space API - * -------------------------- - * - * This API is what gets exported to user space for general - * operations. As well, they can be called from within the kernel, - * (with a properly referenced `struct wimax_dev`). - * - * Properly referenced means: the 'struct net_device' that embeds the - * device's control structure and (as such) the 'struct wimax_dev' is - * referenced by the caller. - */ -int wimax_rfkill(struct wimax_dev *, enum wimax_rf_state); -int wimax_reset(struct wimax_dev *); - -#endif /* #ifndef __NET__WIMAX_H__ */ diff --git a/include/net/xdp.h b/include/net/xdp.h index 3814fb631d52..7d48b2ae217a 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -104,6 +104,18 @@ struct xdp_frame { struct net_device *dev_rx; /* used by cpumap */ }; +#define XDP_BULK_QUEUE_SIZE 16 +struct xdp_frame_bulk { + int count; + void *xa; + void *q[XDP_BULK_QUEUE_SIZE]; +}; + +static __always_inline void xdp_frame_bulk_init(struct xdp_frame_bulk *bq) +{ + /* bq->count will be zero'ed when bq->xa gets updated */ + bq->xa = NULL; +} static inline struct skb_shared_info * xdp_get_shared_info_from_frame(struct xdp_frame *frame) @@ -194,6 +206,9 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp) void xdp_return_frame(struct xdp_frame *xdpf); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf); void xdp_return_buff(struct xdp_buff *xdp); +void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq); +void xdp_return_frame_bulk(struct xdp_frame *xdpf, + struct xdp_frame_bulk *bq); /* When sending xdp_frame into the network stack, then there is no * return point callback, which is needed to release e.g. DMA-mapping @@ -245,6 +260,6 @@ bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf); -#define DEV_MAP_BULK_SIZE 16 +#define DEV_MAP_BULK_SIZE XDP_BULK_QUEUE_SIZE #endif /* __LINUX_NET_XDP_H__ */ |