diff options
Diffstat (limited to 'include/net')
61 files changed, 1408 insertions, 254 deletions
diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index 2f6a3f2233ed..da3a77d25fcb 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -75,6 +75,8 @@ #define LOWPAN_IPHC_MAX_HC_BUF_LEN (sizeof(struct ipv6hdr) + \ LOWPAN_IPHC_MAX_HEADER_LEN + \ LOWPAN_NHC_MAX_HDR_LEN) +/* SCI/DCI is 4 bit width, so we have maximum 16 entries */ +#define LOWPAN_IPHC_CTX_TABLE_SIZE (1 << 4) #define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ #define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ @@ -98,9 +100,39 @@ enum lowpan_lltypes { LOWPAN_LLTYPE_IEEE802154, }; +enum lowpan_iphc_ctx_flags { + LOWPAN_IPHC_CTX_FLAG_ACTIVE, + LOWPAN_IPHC_CTX_FLAG_COMPRESSION, +}; + +struct lowpan_iphc_ctx { + u8 id; + struct in6_addr pfx; + u8 plen; + unsigned long flags; +}; + +struct lowpan_iphc_ctx_table { + spinlock_t lock; + const struct lowpan_iphc_ctx_ops *ops; + struct lowpan_iphc_ctx table[LOWPAN_IPHC_CTX_TABLE_SIZE]; +}; + +static inline bool lowpan_iphc_ctx_is_active(const struct lowpan_iphc_ctx *ctx) +{ + return test_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags); +} + +static inline bool +lowpan_iphc_ctx_is_compression(const struct lowpan_iphc_ctx *ctx) +{ + return test_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags); +} + struct lowpan_priv { enum lowpan_lltypes lltype; struct dentry *iface_debugfs; + struct lowpan_iphc_ctx_table ctx; /* must be last */ u8 priv[0] __aligned(sizeof(void *)); diff --git a/include/net/act_api.h b/include/net/act_api.h index 9d446f136607..03e322b30218 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -7,6 +7,8 @@ #include <net/sch_generic.h> #include <net/pkt_sched.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> struct tcf_common { struct hlist_node tcfc_head; @@ -65,11 +67,6 @@ static inline int tcf_hashinfo_init(struct tcf_hashinfo *hf, unsigned int mask) return 0; } -static inline void tcf_hashinfo_destroy(struct tcf_hashinfo *hf) -{ - kfree(hf->htab); -} - /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. */ @@ -81,42 +78,77 @@ static inline void tcf_lastuse_update(struct tcf_t *tm) tm->lastuse = now; } -#ifdef CONFIG_NET_CLS_ACT - -#define ACT_P_CREATED 1 -#define ACT_P_DELETED 1 - struct tc_action { void *priv; const struct tc_action_ops *ops; __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ __u32 order; struct list_head list; + struct tcf_hashinfo *hinfo; }; +#ifdef CONFIG_NET_CLS_ACT + +#define ACT_P_CREATED 1 +#define ACT_P_DELETED 1 + struct tc_action_ops { struct list_head head; - struct tcf_hashinfo *hinfo; char kind[IFNAMSIZ]; __u32 type; /* TBD to match kind */ struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, struct tcf_result *); int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *, int bind); - int (*lookup)(struct tc_action *, u32); + int (*lookup)(struct net *, struct tc_action *, u32); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action *act, int ovr, int bind); - int (*walk)(struct sk_buff *, struct netlink_callback *, int, struct tc_action *); + int (*walk)(struct net *, struct sk_buff *, + struct netlink_callback *, int, struct tc_action *); +}; + +struct tc_action_net { + struct tcf_hashinfo *hinfo; + const struct tc_action_ops *ops; }; -int tcf_hash_search(struct tc_action *a, u32 index); -u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo); -int tcf_hash_check(u32 index, struct tc_action *a, int bind); -int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a, - int size, int bind, bool cpustats); +static inline +int tc_action_net_init(struct tc_action_net *tn, const struct tc_action_ops *ops, + unsigned int mask) +{ + int err = 0; + + tn->hinfo = kmalloc(sizeof(*tn->hinfo), GFP_KERNEL); + if (!tn->hinfo) + return -ENOMEM; + tn->ops = ops; + err = tcf_hashinfo_init(tn->hinfo, mask); + if (err) + kfree(tn->hinfo); + return err; +} + +void tcf_hashinfo_destroy(const struct tc_action_ops *ops, + struct tcf_hashinfo *hinfo); + +static inline void tc_action_net_exit(struct tc_action_net *tn) +{ + tcf_hashinfo_destroy(tn->ops, tn->hinfo); + kfree(tn->hinfo); +} + +int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, + struct netlink_callback *cb, int type, + struct tc_action *a); +int tcf_hash_search(struct tc_action_net *tn, struct tc_action *a, u32 index); +u32 tcf_hash_new_index(struct tc_action_net *tn); +int tcf_hash_check(struct tc_action_net *tn, u32 index, struct tc_action *a, + int bind); +int tcf_hash_create(struct tc_action_net *tn, u32 index, struct nlattr *est, + struct tc_action *a, int size, int bind, bool cpustats); void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est); -void tcf_hash_insert(struct tc_action *a); +void tcf_hash_insert(struct tc_action_net *tn, struct tc_action *a); int __tcf_hash_release(struct tc_action *a, bool bind, bool strict); @@ -125,8 +157,8 @@ static inline int tcf_hash_release(struct tc_action *a, bool bind) return __tcf_hash_release(a, bind, false); } -int tcf_register_action(struct tc_action_ops *a, unsigned int mask); -int tcf_unregister_action(struct tc_action_ops *a); +int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); +int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, struct tcf_result *res); @@ -140,5 +172,16 @@ int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int); int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); + +#define tc_no_actions(_exts) \ + (list_empty(&(_exts)->actions)) + +#define tc_for_each_action(_a, _exts) \ + list_for_each_entry(a, &(_exts)->actions, list) +#else /* CONFIG_NET_CLS_ACT */ + +#define tc_no_actions(_exts) true +#define tc_for_each_action(_a, _exts) while (0) + #endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 47f52d3cd8df..730d856683e5 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -87,6 +87,8 @@ int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, u32 banned_flags); int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, u32 banned_flags); +int ipv4_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard); int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard); void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 339ea57be423..5d38d980b89d 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -233,6 +233,7 @@ enum { HCI_SC_ENABLED, HCI_SC_ONLY, HCI_PRIVACY, + HCI_LIMITED_PRIVACY, HCI_RPA_EXPIRED, HCI_RPA_RESOLVING, HCI_HS_ENABLED, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index d4f82edb5cff..dc71473462ac 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -25,6 +25,7 @@ #ifndef __HCI_CORE_H #define __HCI_CORE_H +#include <linux/leds.h> #include <net/bluetooth/hci.h> #include <net/bluetooth/hci_sock.h> @@ -396,6 +397,8 @@ struct hci_dev { struct delayed_work rpa_expired; bdaddr_t rpa; + struct led_trigger *power_led; + int (*open)(struct hci_dev *hdev); int (*close)(struct hci_dev *hdev); int (*flush)(struct hci_dev *hdev); diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index f1fbc3b11962..f358ad5e4214 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -306,5 +306,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); int bond_3ad_set_carrier(struct bonding *bond); void bond_3ad_update_lacp_rate(struct bonding *bond); +void bond_3ad_update_ad_actor_settings(struct bonding *bond); #endif /* _NET_BOND_3AD_H */ diff --git a/include/net/bonding.h b/include/net/bonding.h index ee6c52053aa3..791800ddd6d9 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -215,6 +215,7 @@ struct bonding { * ALB mode (6) - to sync the use and modifications of its hash table */ spinlock_t mode_lock; + spinlock_t stats_lock; u8 send_peer_notif; u8 igmp_retrans; #ifdef CONFIG_PROC_FS diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9bcaaf7cd15a..9e1b24c29f0c 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -712,6 +712,8 @@ struct cfg80211_acl_data { * @p2p_opp_ps: P2P opportunistic PS * @acl: ACL configuration used by the drivers which has support for * MAC address based access control + * @pbss: If set, start as a PCP instead of AP. Relevant for DMG + * networks. */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -730,6 +732,7 @@ struct cfg80211_ap_settings { u8 p2p_ctwindow; bool p2p_opp_ps; const struct cfg80211_acl_data *acl; + bool pbss; }; /** @@ -1888,6 +1891,8 @@ struct cfg80211_ibss_params { * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT Capability overrides * @vht_capa_mask: The bits of vht_capa which are to be used. + * @pbss: if set, connect to a PCP instead of AP. Valid for DMG + * networks. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; @@ -1910,6 +1915,7 @@ struct cfg80211_connect_params { struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa; struct ieee80211_vht_cap vht_capa_mask; + bool pbss; }; /** @@ -3489,6 +3495,7 @@ struct cfg80211_cached_keys; * registered for unexpected class 3 frames (AP mode) * @conn: (private) cfg80211 software SME connection state machine data * @connect_keys: (private) keys to set after connection is established + * @conn_bss_type: connecting/connected BSS type * @ibss_fixed: (private) IBSS is using fixed BSSID * @ibss_dfs_possible: (private) IBSS may change to a DFS channel * @event_list: (private) list for internal event processing @@ -3519,6 +3526,7 @@ struct wireless_dev { u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; + enum ieee80211_bss_type conn_bss_type; struct list_head event_list; spinlock_t event_lock; diff --git a/include/net/checksum.h b/include/net/checksum.h index 10a16b5bd1c7..5c30891e84e5 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -88,8 +88,11 @@ static inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); + + /* rotate sum to align it with a 16b boundary */ + if (offset & 1) + sum = ror32(sum, 8); + return csum_add(csum, (__force __wsum)sum); } @@ -102,10 +105,7 @@ csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) static inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { - u32 sum = (__force u32)csum2; - if (offset&1) - sum = ((sum&0xFF00FF)<<8)+((sum>>8)&0xFF00FF); - return csum_sub(csum, (__force __wsum)sum); + return csum_block_add(csum, ~csum2, offset); } static inline __wsum csum_unfold(__sum16 n) @@ -120,6 +120,11 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) #define CSUM_MANGLED_0 ((__force __sum16)0xffff) +static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) +{ + *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); +} + static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index c0a92e2c286d..74c9693d4941 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -17,6 +17,7 @@ #include <linux/hardirq.h> #include <linux/rcupdate.h> #include <net/sock.h> +#include <net/inet_sock.h> #ifdef CONFIG_CGROUP_NET_CLASSID struct cgroup_cls_state { @@ -63,11 +64,13 @@ static inline u32 task_get_classid(const struct sk_buff *skb) * softirqs always disables bh. */ if (in_serving_softirq()) { + struct sock *sk = skb_to_full_sk(skb); + /* If there is an sock_cgroup_classid we'll use that. */ - if (!skb->sk) + if (!sk || !sk_fullsock(sk)) return 0; - classid = sock_cgroup_classid(&skb->sk->sk_cgrp_data); + classid = sock_cgroup_classid(&sk->sk_cgrp_data); } return classid; diff --git a/include/net/codel.h b/include/net/codel.h index 267e70210061..d168aca115cc 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -162,12 +162,14 @@ struct codel_vars { * struct codel_stats - contains codel shared variables and stats * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() + * @drop_len: bytes of dropped packets in dequeue() * ecn_mark: number of packets we ECN marked instead of dropping * ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; u32 drop_count; + u32 drop_len; u32 ecn_mark; u32 ce_mark; }; @@ -308,6 +310,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, vars->rec_inv_sqrt); goto end; } + stats->drop_len += qdisc_pkt_len(skb); qdisc_drop(skb, sch); stats->drop_count++; skb = dequeue_func(vars, sch); @@ -330,6 +333,7 @@ static struct sk_buff *codel_dequeue(struct Qdisc *sch, if (params->ecn && INET_ECN_set_ce(skb)) { stats->ecn_mark++; } else { + stats->drop_len += qdisc_pkt_len(skb); qdisc_drop(skb, sch); stats->drop_count++; diff --git a/include/net/devlink.h b/include/net/devlink.h new file mode 100644 index 000000000000..c37d257891d6 --- /dev/null +++ b/include/net/devlink.h @@ -0,0 +1,140 @@ +/* + * include/net/devlink.h - Network physical device Netlink interface + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.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 _NET_DEVLINK_H_ +#define _NET_DEVLINK_H_ + +#include <linux/device.h> +#include <linux/slab.h> +#include <linux/gfp.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <net/net_namespace.h> +#include <uapi/linux/devlink.h> + +struct devlink_ops; + +struct devlink { + struct list_head list; + struct list_head port_list; + const struct devlink_ops *ops; + struct device *dev; + possible_net_t _net; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +struct devlink_port { + struct list_head list; + struct devlink *devlink; + unsigned index; + bool registered; + enum devlink_port_type type; + enum devlink_port_type desired_type; + void *type_dev; + bool split; + u32 split_group; +}; + +struct devlink_ops { + size_t priv_size; + int (*port_type_set)(struct devlink_port *devlink_port, + enum devlink_port_type port_type); + int (*port_split)(struct devlink *devlink, unsigned int port_index, + unsigned int count); + int (*port_unsplit)(struct devlink *devlink, unsigned int port_index); +}; + +static inline void *devlink_priv(struct devlink *devlink) +{ + BUG_ON(!devlink); + return &devlink->priv; +} + +static inline struct devlink *priv_to_devlink(void *priv) +{ + BUG_ON(!priv); + return container_of(priv, struct devlink, priv); +} + +struct ib_device; + +#if IS_ENABLED(CONFIG_NET_DEVLINK) + +struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); +int devlink_register(struct devlink *devlink, struct device *dev); +void devlink_unregister(struct devlink *devlink); +void devlink_free(struct devlink *devlink); +int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); +void devlink_port_unregister(struct devlink_port *devlink_port); +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev); +void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev); +void devlink_port_type_clear(struct devlink_port *devlink_port); +void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group); + +#else + +static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, + size_t priv_size) +{ + return kzalloc(sizeof(struct devlink) + priv_size, GFP_KERNEL); +} + +static inline int devlink_register(struct devlink *devlink, struct device *dev) +{ + return 0; +} + +static inline void devlink_unregister(struct devlink *devlink) +{ +} + +static inline void devlink_free(struct devlink *devlink) +{ + kfree(devlink); +} + +static inline int devlink_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index) +{ + return 0; +} + +static inline void devlink_port_unregister(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ +} + +static inline void devlink_port_type_ib_set(struct devlink_port *devlink_port, + struct ib_device *ibdev) +{ +} + +static inline void devlink_port_type_clear(struct devlink_port *devlink_port) +{ +} + +static inline void devlink_port_split_set(struct devlink_port *devlink_port, + u32 split_group) +{ +} + +#endif + +#endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 26a0e86e611e..6463bb2863ac 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -296,16 +296,17 @@ struct dsa_switch_driver { /* * Bridge integration */ - int (*port_join_bridge)(struct dsa_switch *ds, int port, - u32 br_port_mask); - int (*port_leave_bridge)(struct dsa_switch *ds, int port, - u32 br_port_mask); + int (*port_bridge_join)(struct dsa_switch *ds, int port, + struct net_device *bridge); + void (*port_bridge_leave)(struct dsa_switch *ds, int port); int (*port_stp_update)(struct dsa_switch *ds, int port, u8 state); /* * VLAN support */ + int (*port_vlan_filtering)(struct dsa_switch *ds, int port, + bool vlan_filtering); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); @@ -314,9 +315,9 @@ struct dsa_switch_driver { struct switchdev_trans *trans); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); - int (*port_pvid_get)(struct dsa_switch *ds, int port, u16 *pvid); - int (*vlan_getnext)(struct dsa_switch *ds, u16 *vid, - unsigned long *ports, unsigned long *untagged); + int (*port_vlan_dump)(struct dsa_switch *ds, int port, + struct switchdev_obj_port_vlan *vlan, + int (*cb)(struct switchdev_obj *obj)); /* * Forwarding database diff --git a/include/net/dst.h b/include/net/dst.h index c7329dcd90cc..5c98443c1c9e 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -398,6 +398,18 @@ static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev, __skb_tunnel_rx(skb, dev, net); } +static inline u32 dst_tclassid(const struct sk_buff *skb) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst(skb); + if (dst) + return dst->tclassid; +#endif + return 0; +} + int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static inline int dst_discard(struct sk_buff *skb) { diff --git a/include/net/dst_cache.h b/include/net/dst_cache.h new file mode 100644 index 000000000000..151accae708b --- /dev/null +++ b/include/net/dst_cache.h @@ -0,0 +1,97 @@ +#ifndef _NET_DST_CACHE_H +#define _NET_DST_CACHE_H + +#include <linux/jiffies.h> +#include <net/dst.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ip6_fib.h> +#endif + +struct dst_cache { + struct dst_cache_pcpu __percpu *cache; + unsigned long reset_ts; +}; + +/** + * dst_cache_get - perform cache lookup + * @dst_cache: the cache + * + * The caller should use dst_cache_get_ip4() if it need to retrieve the + * source address to be used when xmitting to the cached dst. + * local BH must be disabled. + */ +struct dst_entry *dst_cache_get(struct dst_cache *dst_cache); + +/** + * dst_cache_get_ip4 - perform cache lookup and fetch ipv4 source address + * @dst_cache: the cache + * @saddr: return value for the retrieved source address + * + * local BH must be disabled. + */ +struct rtable *dst_cache_get_ip4(struct dst_cache *dst_cache, __be32 *saddr); + +/** + * dst_cache_set_ip4 - store the ipv4 dst into the cache + * @dst_cache: the cache + * @dst: the entry to be cached + * @saddr: the source address to be stored inside the cache + * + * local BH must be disabled. + */ +void dst_cache_set_ip4(struct dst_cache *dst_cache, struct dst_entry *dst, + __be32 saddr); + +#if IS_ENABLED(CONFIG_IPV6) + +/** + * dst_cache_set_ip6 - store the ipv6 dst into the cache + * @dst_cache: the cache + * @dst: the entry to be cached + * @saddr: the source address to be stored inside the cache + * + * local BH must be disabled. + */ +void dst_cache_set_ip6(struct dst_cache *dst_cache, struct dst_entry *dst, + const struct in6_addr *addr); + +/** + * dst_cache_get_ip6 - perform cache lookup and fetch ipv6 source address + * @dst_cache: the cache + * @saddr: return value for the retrieved source address + * + * local BH must be disabled. + */ +struct dst_entry *dst_cache_get_ip6(struct dst_cache *dst_cache, + struct in6_addr *saddr); +#endif + +/** + * dst_cache_reset - invalidate the cache contents + * @dst_cache: the cache + * + * This do not free the cached dst to avoid races and contentions. + * the dst will be freed on later cache lookup. + */ +static inline void dst_cache_reset(struct dst_cache *dst_cache) +{ + dst_cache->reset_ts = jiffies; +} + +/** + * dst_cache_init - initialize the cache, allocating the required storage + * @dst_cache: the cache + * @gfp: allocation flags + */ +int dst_cache_init(struct dst_cache *dst_cache, gfp_t gfp); + +/** + * dst_cache_destroy - empty the cache and free the allocated storage + * @dst_cache: the cache + * + * No synchronization is enforced: it must be called only when the cache + * is unsed. + */ +void dst_cache_destroy(struct dst_cache *dst_cache); + +#endif diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 30a56ab2ccfb..5db9f5910428 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -62,6 +62,7 @@ static inline int skb_metadata_dst_cmp(const struct sk_buff *skb_a, sizeof(a->u.tun_info) + a->u.tun_info.options_len); } +void metadata_dst_free(struct metadata_dst *); struct metadata_dst *metadata_dst_alloc(u8 optslen, gfp_t flags); struct metadata_dst __percpu *metadata_dst_alloc_percpu(u8 optslen, gfp_t flags); @@ -125,7 +126,7 @@ static inline struct metadata_dst *ip_tun_rx_dst(struct sk_buff *skb, ip_tunnel_key_init(&tun_dst->u.tun_info.key, iph->saddr, iph->daddr, iph->tos, iph->ttl, - 0, 0, tunnel_id, flags); + 0, 0, 0, tunnel_id, flags); return tun_dst; } @@ -151,8 +152,11 @@ static inline struct metadata_dst *ipv6_tun_rx_dst(struct sk_buff *skb, info->key.u.ipv6.src = ip6h->saddr; info->key.u.ipv6.dst = ip6h->daddr; + info->key.tos = ipv6_get_dsfield(ip6h); info->key.ttl = ip6h->hop_limit; + info->key.label = ip6_flowlabel(ip6h); + return tun_dst; } diff --git a/include/net/flow.h b/include/net/flow.h index 83969eebebf3..d47ef4bb5423 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -127,7 +127,6 @@ struct flowi6 { #define flowi6_oif __fl_common.flowic_oif #define flowi6_iif __fl_common.flowic_iif #define flowi6_mark __fl_common.flowic_mark -#define flowi6_tos __fl_common.flowic_tos #define flowi6_scope __fl_common.flowic_scope #define flowi6_proto __fl_common.flowic_proto #define flowi6_flags __fl_common.flowic_flags @@ -135,6 +134,7 @@ struct flowi6 { #define flowi6_tun_key __fl_common.flowic_tun_key struct in6_addr daddr; struct in6_addr saddr; + /* Note: flowi6_tos is encoded in flowlabel, too. */ __be32 flowlabel; union flowi_uli uli; #define fl6_sport uli.ports.sport diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 8c8548cf5888..d3d60dccd19f 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -184,4 +184,17 @@ static inline bool flow_keys_have_l4(struct flow_keys *keys) u32 flow_hash_from_keys(struct flow_keys *keys); +static inline bool dissector_uses_key(const struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id) +{ + return flow_dissector->used_keys & (1 << key_id); +} + +static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissector, + enum flow_dissector_key_id key_id, + void *target_container) +{ + return ((char *)target_container) + flow_dissector->offset[key_id]; +} + #endif diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 43c0e771f417..8d4608ce8716 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -83,7 +83,6 @@ struct genl_family { * @attrs: netlink attributes * @_net: network namespace * @user_ptr: user pointers - * @dst_sk: destination socket */ struct genl_info { u32 snd_seq; @@ -94,7 +93,6 @@ struct genl_info { struct nlattr ** attrs; possible_net_t _net; void * user_ptr[2]; - struct sock * dst_sk; }; static inline struct net *genl_info_net(struct genl_info *info) @@ -188,8 +186,6 @@ int genl_unregister_family(struct genl_family *family); void genl_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info, u32 group, gfp_t flags); -struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, - gfp_t flags); void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, struct genl_family *family, int flags, u8 cmd); diff --git a/include/net/hwbm.h b/include/net/hwbm.h new file mode 100644 index 000000000000..47d08662501b --- /dev/null +++ b/include/net/hwbm.h @@ -0,0 +1,28 @@ +#ifndef _HWBM_H +#define _HWBM_H + +struct hwbm_pool { + /* Capacity of the pool */ + int size; + /* Size of the buffers managed */ + int frag_size; + /* Number of buffers currently used by this pool */ + int buf_num; + /* constructor called during alocation */ + int (*construct)(struct hwbm_pool *bm_pool, void *buf); + /* protect acces to the buffer counter*/ + spinlock_t lock; + /* private data */ + void *priv; +}; +#ifdef CONFIG_HWBM +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf); +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp); +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp); +#else +void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {} +int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; } +int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num, gfp_t gfp) +{ return 0; } +#endif /* CONFIG_HWBM */ +#endif /* _HWBM_H */ diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 064cfbe639d0..954ad6bfb56a 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -15,7 +15,6 @@ #include <linux/types.h> -struct in6_addr; struct inet_bind_bucket; struct request_sock; struct sk_buff; diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 7ff588ca6817..28332bdac333 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -53,6 +53,7 @@ struct sock *__inet6_lookup_established(struct net *net, struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, @@ -60,6 +61,7 @@ struct sock *inet6_lookup_listener(struct net *net, static inline struct sock *__inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, @@ -71,12 +73,12 @@ static inline struct sock *__inet6_lookup(struct net *net, if (sk) return sk; - return inet6_lookup_listener(net, hashinfo, saddr, sport, + return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, hnum, dif); } static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, - struct sk_buff *skb, + struct sk_buff *skb, int doff, const __be16 sport, const __be16 dport, int iif) @@ -86,16 +88,19 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo, if (sk) return sk; - return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, - &ipv6_hdr(skb)->saddr, sport, + return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + doff, &ipv6_hdr(skb)->saddr, sport, &ipv6_hdr(skb)->daddr, ntohs(dport), iif); } struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif); + +int inet6_hash(struct sock *sk); #endif /* IS_ENABLED(CONFIG_IPV6) */ #define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif) \ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 481fe1c9044c..49dcad4fe99e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child); +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 12aac0fd6ee7..909972aa3acd 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -13,6 +13,7 @@ struct netns_frags { int timeout; int high_thresh; int low_thresh; + int max_dist; }; /** diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index de2e3ade6102..50f635c2c536 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -207,12 +207,16 @@ void inet_hashinfo_init(struct inet_hashinfo *h); bool inet_ehash_insert(struct sock *sk, struct sock *osk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); -void __inet_hash(struct sock *sk, struct sock *osk); -void inet_hash(struct sock *sk); +int __inet_hash(struct sock *sk, struct sock *osk, + int (*saddr_same)(const struct sock *sk1, + const struct sock *sk2, + bool match_wildcard)); +int inet_hash(struct sock *sk); void inet_unhash(struct sock *sk); struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const unsigned short hnum, @@ -220,10 +224,11 @@ struct sock *__inet_lookup_listener(struct net *net, 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) { - return __inet_lookup_listener(net, hashinfo, saddr, sport, + return __inet_lookup_listener(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif); } @@ -299,6 +304,7 @@ static inline struct sock * static inline struct sock *__inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) @@ -307,12 +313,13 @@ static inline struct sock *__inet_lookup(struct net *net, struct sock *sk = __inet_lookup_established(net, hashinfo, saddr, sport, daddr, hnum, dif); - return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport, - daddr, hnum, dif); + return sk ? : __inet_lookup_listener(net, hashinfo, skb, doff, saddr, + sport, daddr, hnum, dif); } static inline struct sock *inet_lookup(struct net *net, struct inet_hashinfo *hashinfo, + struct sk_buff *skb, int doff, const __be32 saddr, const __be16 sport, const __be32 daddr, const __be16 dport, const int dif) @@ -320,7 +327,8 @@ static inline struct sock *inet_lookup(struct net *net, struct sock *sk; local_bh_disable(); - sk = __inet_lookup(net, hashinfo, saddr, sport, daddr, dport, dif); + sk = __inet_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, + dport, dif); local_bh_enable(); return sk; @@ -328,6 +336,7 @@ static inline struct sock *inet_lookup(struct net *net, static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, struct sk_buff *skb, + int doff, const __be16 sport, const __be16 dport) { @@ -337,8 +346,8 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo, if (sk) return sk; else - return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, - iph->saddr, sport, + return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb, + doff, iph->saddr, sport, iph->daddr, dport, inet_iif(skb)); } diff --git a/include/net/ip.h b/include/net/ip.h index 1a98f1ca1638..fad74d323bd6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -240,17 +240,13 @@ static inline int inet_is_local_reserved_port(struct net *net, int port) } #endif +__be32 inet_current_timestamp(void); + /* From inetpeer.c */ extern int inet_peer_threshold; extern int inet_peer_minttl; extern int inet_peer_maxttl; -/* From ip_input.c */ -extern int sysctl_ip_early_demux; - -/* From ip_output.c */ -extern int sysctl_ip_dynaddr; - void ipfrag_init(void); void ip_static_sysctl_init(void); diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index 1a49b73f7f6e..cca840584c88 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -37,8 +37,7 @@ #ifndef _HAVE_ARCH_IPV6_CSUM __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, - __u32 len, unsigned short proto, - __wsum csum); + __u32 len, __u8 proto, __wsum csum); #endif static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 295d291269e2..54c779416eec 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -101,6 +101,9 @@ void fib6_force_start_gc(struct net *net); struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, const struct in6_addr *addr, bool anycast); +struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, + int flags); + /* * support functions for ND * diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 0d0ce0b2d870..499a707765ea 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -6,6 +6,7 @@ #include <linux/if_tunnel.h> #include <linux/ip6_tunnel.h> #include <net/ip_tunnels.h> +#include <net/dst_cache.h> #define IP6TUNNEL_ERR_TIMEO (30*HZ) @@ -33,12 +34,6 @@ struct __ip6_tnl_parm { __be32 o_key; }; -struct ip6_tnl_dst { - seqlock_t lock; - struct dst_entry __rcu *dst; - u32 cookie; -}; - /* IPv6 tunnel */ struct ip6_tnl { struct ip6_tnl __rcu *next; /* next tunnel in list */ @@ -46,7 +41,7 @@ struct ip6_tnl { struct net *net; /* netns for packet i/o */ struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ - struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */ + struct dst_cache dst_cache; /* cached dst */ int err_count; unsigned long err_time; @@ -66,11 +61,6 @@ struct ipv6_tlv_tnl_enc_lim { __u8 encap_limit; /* tunnel encapsulation limit */ } __packed; -struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t); -int ip6_tnl_dst_init(struct ip6_tnl *t); -void ip6_tnl_dst_destroy(struct ip6_tnl *t); -void ip6_tnl_dst_reset(struct ip6_tnl *t); -void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst); int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr); int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7029527725dd..4079fc18ffe4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -61,6 +61,7 @@ struct fib_nh_exception { struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; + struct rcu_head rcu; }; struct fnhe_hash_bucket { diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index dda9abf6b89c..56050f913339 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -7,12 +7,15 @@ #include <linux/socket.h> #include <linux/types.h> #include <linux/u64_stats_sync.h> +#include <linux/bitops.h> + #include <net/dsfield.h> #include <net/gro_cells.h> #include <net/inet_ecn.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/lwtunnel.h> +#include <net/dst_cache.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -47,6 +50,7 @@ struct ip_tunnel_key { __be16 tun_flags; u8 tos; /* TOS for IPv4, TC for IPv6 */ u8 ttl; /* TTL for IPv4, HL for IPv6 */ + __be32 label; /* Flow Label for IPv6 */ __be16 tp_src; __be16 tp_dst; }; @@ -55,8 +59,16 @@ struct ip_tunnel_key { #define IP_TUNNEL_INFO_TX 0x01 /* represents tx tunnel parameters */ #define IP_TUNNEL_INFO_IPV6 0x02 /* key contains IPv6 addresses */ +/* Maximum tunnel options length. */ +#define IP_TUNNEL_OPTS_MAX \ + GENMASK((FIELD_SIZEOF(struct ip_tunnel_info, \ + options_len) * BITS_PER_BYTE) - 1, 0) + struct ip_tunnel_info { struct ip_tunnel_key key; +#ifdef CONFIG_DST_CACHE + struct dst_cache dst_cache; +#endif u8 options_len; u8 mode; }; @@ -85,11 +97,6 @@ struct ip_tunnel_prl_entry { struct rcu_head rcu_head; }; -struct ip_tunnel_dst { - struct dst_entry __rcu *dst; - __be32 saddr; -}; - struct metadata_dst; struct ip_tunnel { @@ -108,7 +115,7 @@ struct ip_tunnel { int tun_hlen; /* Precalculated header length */ int mlink; - struct ip_tunnel_dst __percpu *dst_cache; + struct dst_cache dst_cache; struct ip_tunnel_parm parms; @@ -141,6 +148,7 @@ struct ip_tunnel { #define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400) #define TUNNEL_GENEVE_OPT __cpu_to_be16(0x0800) #define TUNNEL_VXLAN_OPT __cpu_to_be16(0x1000) +#define TUNNEL_NOCACHE __cpu_to_be16(0x2000) #define TUNNEL_OPTIONS_PRESENT (TUNNEL_GENEVE_OPT | TUNNEL_VXLAN_OPT) @@ -181,7 +189,7 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, __be32 saddr, __be32 daddr, - u8 tos, u8 ttl, + u8 tos, u8 ttl, __be32 label, __be16 tp_src, __be16 tp_dst, __be64 tun_id, __be16 tun_flags) { @@ -192,6 +200,7 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, IP_TUNNEL_KEY_IPV4_PAD_LEN); key->tos = tos; key->ttl = ttl; + key->label = label; key->tun_flags = tun_flags; /* For the tunnel types on the top of IPsec, the tp_src and tp_dst of @@ -207,6 +216,20 @@ static inline void ip_tunnel_key_init(struct ip_tunnel_key *key, 0, sizeof(*key) - IP_TUNNEL_KEY_SIZE); } +static inline bool +ip_tunnel_dst_cache_usable(const struct sk_buff *skb, + const struct ip_tunnel_info *info) +{ + if (skb->mark) + return false; + if (!info) + return true; + if (info->key.tun_flags & TUNNEL_NOCACHE) + return false; + + return true; +} + static inline unsigned short ip_tunnel_info_af(const struct ip_tunnel_info *tun_info) { @@ -248,7 +271,6 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[], int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p); void ip_tunnel_setup(struct net_device *dev, int net_id); -void ip_tunnel_dst_reset_all(struct ip_tunnel *t); int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); @@ -273,15 +295,31 @@ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, return INET_ECN_encapsulate(tos, inner); } -int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto); +int iptunnel_pull_header(struct sk_buff *skb, int hdr_len, __be16 inner_proto, + bool xnet); void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, __be32 src, __be32 dst, u8 proto, u8 tos, u8 ttl, __be16 df, bool xnet); struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, gfp_t flags); -struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, bool gre_csum, - int gso_type_mask); +struct sk_buff *iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); + +static inline int iptunnel_pull_offloads(struct sk_buff *skb) +{ + if (skb_is_gso(skb)) { + int err; + + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + return err; + skb_shinfo(skb)->gso_type &= ~(NETIF_F_GSO_ENCAP_ALL >> + NETIF_F_GSO_SHIFT); + } + + skb->encapsulation = 0; + return 0; +} static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) { @@ -356,6 +394,17 @@ static inline void ip_tunnel_unneed_metadata(void) { } +static inline void ip_tunnel_info_opts_get(void *to, + const struct ip_tunnel_info *info) +{ +} + +static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info, + const void *from, int len) +{ + info->options_len = 0; +} + #endif /* CONFIG_INET */ #endif /* __NET_IP_TUNNELS_H */ diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 0816c872b689..a6cc576fd467 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1588,6 +1588,23 @@ static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) } #endif /* CONFIG_IP_VS_NFCT */ +/* Really using conntrack? */ +static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp, + struct sk_buff *skb) +{ +#ifdef CONFIG_IP_VS_NFCT + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + if (!(cp->flags & IP_VS_CONN_F_NFCT)) + return false; + ct = nf_ct_get(skb, &ctinfo); + if (ct && !nf_ct_is_untracked(ct)) + return true; +#endif + return false; +} + static inline int ip_vs_dest_conn_overhead(struct ip_vs_dest *dest) { diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 6570f379aba2..1be050ada8c5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -259,8 +259,12 @@ static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) rcu_read_lock(); opt = rcu_dereference(np->opt); - if (opt && !atomic_inc_not_zero(&opt->refcnt)) - opt = NULL; + if (opt) { + if (!atomic_inc_not_zero(&opt->refcnt)) + opt = NULL; + else + opt = rcu_pointer_handoff(opt); + } rcu_read_unlock(); return opt; } @@ -831,6 +835,12 @@ static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } + +static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) +{ + return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; +} + /* * Prototypes exported by ipv6 */ @@ -949,6 +959,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); +int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); +void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index 8f81bbbc38fc..e0f4109e64c6 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -439,6 +439,12 @@ int dev_get_wireless_info(char *buffer, char **start, off_t offset, int length); /* Send a single event to user space */ void wireless_send_event(struct net_device *dev, unsigned int cmd, union iwreq_data *wrqu, const char *extra); +#ifdef CONFIG_WEXT_CORE +/* flush all previous wext events - if work is done from netdev notifiers */ +void wireless_nlevent_flush(void); +#else +static inline void wireless_nlevent_flush(void) {} +#endif /* We may need a function to send a stream of events to user space. * More on that later... */ diff --git a/include/net/kcm.h b/include/net/kcm.h new file mode 100644 index 000000000000..2840b5825dcc --- /dev/null +++ b/include/net/kcm.h @@ -0,0 +1,226 @@ +/* + * Kernel Connection Multiplexor + * + * Copyright (c) 2016 Tom Herbert <tom@herbertland.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + */ + +#ifndef __NET_KCM_H_ +#define __NET_KCM_H_ + +#include <linux/skbuff.h> +#include <net/sock.h> +#include <uapi/linux/kcm.h> + +extern unsigned int kcm_net_id; + +#define KCM_STATS_ADD(stat, count) ((stat) += (count)) +#define KCM_STATS_INCR(stat) ((stat)++) + +struct kcm_psock_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_aborts; + 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 reserved; + unsigned long long unreserved; + unsigned int tx_aborts; +}; + +struct kcm_mux_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; + unsigned int rx_ready_drops; + unsigned int tx_retries; + unsigned int psock_attach; + unsigned int psock_unattach_rsvd; + unsigned int psock_unattach; +}; + +struct kcm_stats { + unsigned long long rx_msgs; + unsigned long long rx_bytes; + unsigned long long tx_msgs; + unsigned long long tx_bytes; +}; + +struct kcm_tx_msg { + unsigned int sent; + unsigned int fragidx; + unsigned int frag_offset; + unsigned int msg_flags; + struct sk_buff *frag_skb; + struct sk_buff *last_skb; +}; + +struct kcm_rx_msg { + int full_len; + int accum_len; + int offset; + int early_eaten; +}; + +/* Socket structure for KCM client sockets */ +struct kcm_sock { + struct sock sk; + struct kcm_mux *mux; + struct list_head kcm_sock_list; + int index; + u32 done : 1; + struct work_struct done_work; + + struct kcm_stats stats; + + /* Transmit */ + struct kcm_psock *tx_psock; + struct work_struct tx_work; + struct list_head wait_psock_list; + struct sk_buff *seq_skb; + + /* Don't use bit fields here, these are set under different locks */ + bool tx_wait; + bool tx_wait_more; + + /* Receive */ + struct kcm_psock *rx_psock; + struct list_head wait_rx_list; /* KCMs waiting for receiving */ + bool rx_wait; + u32 rx_disabled : 1; +}; + +struct bpf_prog; + +/* Structure for an attached lower socket */ +struct kcm_psock { + struct sock *sk; + struct kcm_mux *mux; + int index; + + u32 tx_stopped : 1; + u32 rx_stopped : 1; + u32 done : 1; + u32 unattaching : 1; + + void (*save_state_change)(struct sock *sk); + void (*save_data_ready)(struct sock *sk); + void (*save_write_space)(struct sock *sk); + + struct list_head psock_list; + + struct kcm_psock_stats stats; + + /* Receive */ + struct sk_buff *rx_skb_head; + struct sk_buff **rx_skb_nextp; + struct sk_buff *ready_rx_msg; + struct list_head psock_ready_list; + struct work_struct rx_work; + struct delayed_work rx_delayed_work; + struct bpf_prog *bpf_prog; + struct kcm_sock *rx_kcm; + unsigned long long saved_rx_bytes; + unsigned long long saved_rx_msgs; + struct timer_list rx_msg_timer; + unsigned int rx_need_bytes; + + /* Transmit */ + struct kcm_sock *tx_kcm; + struct list_head psock_avail_list; + unsigned long long saved_tx_bytes; + unsigned long long saved_tx_msgs; +}; + +/* Per net MUX list */ +struct kcm_net { + struct mutex mutex; + struct kcm_psock_stats aggregate_psock_stats; + struct kcm_mux_stats aggregate_mux_stats; + struct list_head mux_list; + int count; +}; + +/* Structure for a MUX */ +struct kcm_mux { + struct list_head kcm_mux_list; + struct rcu_head rcu; + struct kcm_net *knet; + + struct list_head kcm_socks; /* All KCM sockets on MUX */ + int kcm_socks_cnt; /* Total KCM socket count for MUX */ + struct list_head psocks; /* List of all psocks on MUX */ + int psocks_cnt; /* Total attached sockets */ + + struct kcm_mux_stats stats; + struct kcm_psock_stats aggregate_psock_stats; + + /* Receive */ + spinlock_t rx_lock ____cacheline_aligned_in_smp; + struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */ + struct list_head psocks_ready; /* List of psocks with a msg ready */ + struct sk_buff_head rx_hold_queue; + + /* Transmit */ + spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */ + struct list_head psocks_avail; /* List of available psocks */ + struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */ +}; + +#ifdef CONFIG_PROC_FS +int kcm_proc_init(void); +void kcm_proc_exit(void); +#else +static inline int kcm_proc_init(void) { return 0; } +static inline void kcm_proc_exit(void) { } +#endif + +static inline void aggregate_psock_stats(struct kcm_psock_stats *stats, + struct kcm_psock_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_PSOCK_STATS(rx_msgs); + SAVE_PSOCK_STATS(rx_bytes); + SAVE_PSOCK_STATS(rx_aborts); + 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(tx_msgs); + SAVE_PSOCK_STATS(tx_bytes); + SAVE_PSOCK_STATS(reserved); + SAVE_PSOCK_STATS(unreserved); + SAVE_PSOCK_STATS(tx_aborts); +#undef SAVE_PSOCK_STATS +} + +static inline void aggregate_mux_stats(struct kcm_mux_stats *stats, + struct kcm_mux_stats *agg_stats) +{ + /* Save psock statistics in the mux when psock is being unattached. */ + +#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat) + SAVE_MUX_STATS(rx_msgs); + SAVE_MUX_STATS(rx_bytes); + SAVE_MUX_STATS(tx_msgs); + SAVE_MUX_STATS(tx_bytes); + SAVE_MUX_STATS(rx_ready_drops); + SAVE_MUX_STATS(psock_attach); + SAVE_MUX_STATS(psock_unattach_rsvd); + SAVE_MUX_STATS(psock_unattach); +#undef SAVE_MUX_STATS +} + +#endif /* __NET_KCM_H_ */ diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 5567d46b3cff..c43a9c73de5e 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -39,7 +39,7 @@ struct l3mdev_ops { #ifdef CONFIG_NET_L3_MASTER_DEV -int l3mdev_master_ifindex_rcu(struct net_device *dev); +int l3mdev_master_ifindex_rcu(const struct net_device *dev); static inline int l3mdev_master_ifindex(struct net_device *dev) { int ifindex; @@ -179,7 +179,7 @@ struct dst_entry *l3mdev_rt6_dst_by_oif(struct net *net, #else -static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) +static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev) { return 0; } diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 66350ce3e955..e9f116e29c22 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -170,6 +170,8 @@ static inline int lwtunnel_input(struct sk_buff *skb) return -EOPNOTSUPP; } -#endif +#endif /* CONFIG_LWTUNNEL */ + +#define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_H */ diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7c30faff245f..e385eb3076a1 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2015 Intel Deutschland GmbH + * Copyright (C) 2015 - 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -298,6 +298,7 @@ struct ieee80211_vif_chanctx_switch { * note that this is only called when it changes after the channel * context had been assigned. * @BSS_CHANGED_OCB: OCB join status changed + * @BSS_CHANGED_MU_GROUPS: VHT MU-MIMO group id or user position changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -323,6 +324,7 @@ enum ieee80211_bss_change { BSS_CHANGED_BEACON_INFO = 1<<20, BSS_CHANGED_BANDWIDTH = 1<<21, BSS_CHANGED_OCB = 1<<22, + BSS_CHANGED_MU_GROUPS = 1<<23, /* when adding here, make sure to change ieee80211_reconfig */ }; @@ -436,6 +438,19 @@ struct ieee80211_event { }; /** + * struct ieee80211_mu_group_data - STA's VHT MU-MIMO group data + * + * This structure describes the group id data of VHT MU-MIMO + * + * @membership: 64 bits array - a bit is set if station is member of the group + * @position: 2 bits per group id indicating the position in the group + */ +struct ieee80211_mu_group_data { + u8 membership[WLAN_MEMBERSHIP_LEN]; + u8 position[WLAN_USER_POSITION_LEN]; +}; + +/** * struct ieee80211_bss_conf - holds the BSS's changing parameters * * This structure keeps information about a BSS (and an association @@ -477,6 +492,7 @@ struct ieee80211_event { * @enable_beacon: whether beaconing should be enabled or not * @chandef: Channel definition for this BSS -- the hardware might be * configured a higher bandwidth than this BSS uses, for example. + * @mu_group: VHT MU-MIMO group membership data * @ht_operation_mode: HT operation mode like in &struct ieee80211_ht_operation. * This field is only valid when the channel is a wide HT/VHT channel. * Note that with TDLS this can be the case (channel is HT, protection must @@ -535,6 +551,7 @@ struct ieee80211_bss_conf { s32 cqm_rssi_thold; u32 cqm_rssi_hyst; struct cfg80211_chan_def chandef; + struct ieee80211_mu_group_data mu_group; __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; int arp_addr_cnt; bool qos; @@ -691,12 +708,14 @@ enum mac80211_tx_info_flags { * protocol frame (e.g. EAP) * @IEEE80211_TX_CTRL_PS_RESPONSE: This frame is a response to a poll * frame (PS-Poll or uAPSD). + * @IEEE80211_TX_CTRL_RATE_INJECT: This frame is injected with rate information * * These flags are used in tx_info->control.flags. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTRL_PORT_CTRL_PROTO = BIT(0), IEEE80211_TX_CTRL_PS_RESPONSE = BIT(1), + IEEE80211_TX_CTRL_RATE_INJECT = BIT(2), }; /* @@ -982,6 +1001,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * flag indicates that the PN was verified for replay protection. * Note that this flag is also currently only supported when a frame * is also decrypted (ie. @RX_FLAG_DECRYPTED must be set) + * @RX_FLAG_DUP_VALIDATED: The driver should set this flag if it did + * de-duplication by itself. * @RX_FLAG_FAILED_FCS_CRC: Set this flag if the FCS check failed on * the frame. * @RX_FLAG_FAILED_PLCP_CRC: Set this flag if the PCLP check failed on @@ -993,6 +1014,8 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_MACTIME_END: The timestamp passed in the RX status (@mactime * field) is valid and contains the time the last symbol of the MPDU * (including FCS) was received. + * @RX_FLAG_MACTIME_PLCP_START: The timestamp passed in the RX status (@mactime + * field) is valid and contains the time the SYNC preamble was received. * @RX_FLAG_SHORTPRE: Short preamble was used for this frame * @RX_FLAG_HT: HT MCS was used and rate_idx is MCS index * @RX_FLAG_VHT: VHT MCS was used and rate_index is MCS index @@ -1014,6 +1037,14 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_DELIM_CRC_KNOWN: The delimiter CRC field is known (the CRC * is stored in the @ampdu_delimiter_crc field) * @RX_FLAG_LDPC: LDPC was used + * @RX_FLAG_ONLY_MONITOR: Report frame only to monitor interfaces without + * processing it in any regular way. + * This is useful if drivers offload some frames but still want to report + * them for sniffing purposes. + * @RX_FLAG_SKIP_MONITOR: Process and report frame to all interfaces except + * monitor interfaces. + * This is useful if drivers offload some frames but still want to report + * them for sniffing purposes. * @RX_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_FLAG_10MHZ: 10 MHz (half channel) was used * @RX_FLAG_5MHZ: 5 MHz (quarter channel) was used @@ -1033,6 +1064,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), RX_FLAG_DECRYPTED = BIT(1), + RX_FLAG_MACTIME_PLCP_START = BIT(2), RX_FLAG_MMIC_STRIPPED = BIT(3), RX_FLAG_IV_STRIPPED = BIT(4), RX_FLAG_FAILED_FCS_CRC = BIT(5), @@ -1046,7 +1078,7 @@ enum mac80211_rx_flags { RX_FLAG_HT_GF = BIT(13), RX_FLAG_AMPDU_DETAILS = BIT(14), RX_FLAG_PN_VALIDATED = BIT(15), - /* bit 16 free */ + RX_FLAG_DUP_VALIDATED = BIT(16), RX_FLAG_AMPDU_LAST_KNOWN = BIT(17), RX_FLAG_AMPDU_IS_LAST = BIT(18), RX_FLAG_AMPDU_DELIM_CRC_ERROR = BIT(19), @@ -1054,6 +1086,8 @@ enum mac80211_rx_flags { RX_FLAG_MACTIME_END = BIT(21), RX_FLAG_VHT = BIT(22), RX_FLAG_LDPC = BIT(23), + RX_FLAG_ONLY_MONITOR = BIT(24), + RX_FLAG_SKIP_MONITOR = BIT(25), RX_FLAG_STBC_MASK = BIT(26) | BIT(27), RX_FLAG_10MHZ = BIT(28), RX_FLAG_5MHZ = BIT(29), @@ -1072,6 +1106,7 @@ enum mac80211_rx_flags { * @RX_VHT_FLAG_160MHZ: 160 MHz was used * @RX_VHT_FLAG_BF: packet was beamformed */ + enum mac80211_rx_vht_flags { RX_VHT_FLAG_80MHZ = BIT(0), RX_VHT_FLAG_160MHZ = BIT(1), @@ -1091,6 +1126,8 @@ enum mac80211_rx_vht_flags { * it but can store it and pass it back to the driver for synchronisation * @band: the active band when this frame was received * @freq: frequency the radio was tuned to when receiving this frame, in MHz + * This field must be set for management frames, but isn't strictly needed + * for data (other) frames - for those it only affects radiotap reporting. * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* @@ -1347,6 +1384,7 @@ enum ieee80211_vif_flags { * @csa_active: marks whether a channel switch is going on. Internally it is * write-protected by sdata_lock and local->mtx so holding either is fine * for read access. + * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed @@ -1373,6 +1411,7 @@ struct ieee80211_vif { u8 addr[ETH_ALEN]; bool p2p; bool csa_active; + bool mu_mimo_owner; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; @@ -1486,9 +1525,8 @@ enum ieee80211_key_flags { * wants to be given when a frame is transmitted and needs to be * encrypted in hardware. * @cipher: The key's cipher suite selector. - * @tx_pn: PN used for TX on non-TKIP keys, may be used by the driver - * as well if it needs to do software PN assignment by itself - * (e.g. due to TSO) + * @tx_pn: PN used for TX keys, may be used by the driver as well if it + * needs to do software PN assignment by itself (e.g. due to TSO) * @flags: key flags, see &enum ieee80211_key_flags. * @keyidx: the key index (0-3) * @keylen: key material length @@ -1514,6 +1552,9 @@ struct ieee80211_key_conf { #define IEEE80211_MAX_PN_LEN 16 +#define TKIP_PN_TO_IV16(pn) ((u16)(pn & 0xffff)) +#define TKIP_PN_TO_IV32(pn) ((u32)((pn >> 16) & 0xffffffff)) + /** * struct ieee80211_key_seq - key sequence counter * @@ -1684,6 +1725,18 @@ struct ieee80211_sta_rates { * @tdls_initiator: indicates the STA is an initiator of the TDLS link. Only * valid if the STA is a TDLS peer in the first place. * @mfp: indicates whether the STA uses management frame protection or not. + * @max_amsdu_subframes: indicates the maximal number of MSDUs in a single + * A-MSDU. Taken from the Extended Capabilities element. 0 means + * unlimited. + * @max_amsdu_len: indicates the maximal length of an A-MSDU in bytes. This + * field is always valid for packets with a VHT preamble. For packets + * with a HT preamble, additional limits apply: + * + If the skb is transmitted as part of a BA agreement, the + * A-MSDU maximal size is min(max_amsdu_len, 4065) bytes. + * + If the skb is not part of a BA aggreement, the A-MSDU maximal + * size is min(max_amsdu_len, 7935) bytes. + * Both additional HT limits must be enforced by the low level driver. + * This is defined by the spec (IEEE 802.11-2012 section 8.3.2.2 NOTE 2). * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) */ struct ieee80211_sta { @@ -1702,6 +1755,8 @@ struct ieee80211_sta { bool tdls; bool tdls_initiator; bool mfp; + u8 max_amsdu_subframes; + u16 max_amsdu_len; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; @@ -1910,6 +1965,11 @@ struct ieee80211_txq { * by just its MAC address; this prevents, for example, the same station * from connecting to two virtual AP interfaces at the same time. * + * @IEEE80211_HW_SUPPORTS_REORDERING_BUFFER: Hardware (or driver) manages the + * reordering buffer internally, guaranteeing mac80211 receives frames in + * order and does not need to manage its own reorder buffer or BA session + * timeout. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -1946,6 +2006,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_AMSDU_IN_AMPDU, IEEE80211_HW_BEACON_TX_STATUS, IEEE80211_HW_NEEDS_UNIQUE_STA_ADDR, + IEEE80211_HW_SUPPORTS_REORDERING_BUFFER, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2167,7 +2228,7 @@ static inline void SET_IEEE80211_DEV(struct ieee80211_hw *hw, struct device *dev * @hw: the &struct ieee80211_hw to set the MAC address for * @addr: the address to set */ -static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, u8 *addr) +static inline void SET_IEEE80211_PERM_ADDR(struct ieee80211_hw *hw, const u8 *addr) { memcpy(hw->wiphy->perm_addr, addr, ETH_ALEN); } @@ -2684,6 +2745,33 @@ enum ieee80211_ampdu_mlme_action { }; /** + * struct ieee80211_ampdu_params - AMPDU action parameters + * + * @action: the ampdu action, value from %ieee80211_ampdu_mlme_action. + * @sta: peer of this AMPDU session + * @tid: tid of the BA session + * @ssn: start sequence number of the session. TX/RX_STOP can pass 0. When + * action is set to %IEEE80211_AMPDU_RX_START the driver passes back the + * actual ssn value used to start the session and writes the value here. + * @buf_size: reorder buffer size (number of subframes). Valid only when the + * action is set to %IEEE80211_AMPDU_RX_START or + * %IEEE80211_AMPDU_TX_OPERATIONAL + * @amsdu: indicates the peer's ability to receive A-MSDU within A-MPDU. + * valid when the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL + * @timeout: BA session timeout. Valid only when the action is set to + * %IEEE80211_AMPDU_RX_START + */ +struct ieee80211_ampdu_params { + enum ieee80211_ampdu_mlme_action action; + struct ieee80211_sta *sta; + u16 tid; + u16 ssn; + u8 buf_size; + bool amsdu; + u16 timeout; +}; + +/** * enum ieee80211_frame_release_type - frame release reason * @IEEE80211_FRAME_RELEASE_PSPOLL: frame released for PS-Poll * @IEEE80211_FRAME_RELEASE_UAPSD: frame(s) released due to @@ -3027,13 +3115,9 @@ enum ieee80211_reconfig_type { * @ampdu_action: Perform a certain A-MPDU action * The RA/TID combination determines the destination and TID we want * the ampdu action to be performed for. The action is defined through - * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) - * is the first frame we expect to perform the action on. Notice - * that TX/RX_STOP can pass NULL for this parameter. - * The @buf_size parameter is only valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder - * buffer size (number of subframes) for this session -- the driver - * may neither send aggregates containing more subframes than this + * ieee80211_ampdu_mlme_action. + * When the action is set to %IEEE80211_AMPDU_TX_OPERATIONAL the driver + * may neither send aggregates containing more subframes than @buf_size * nor send aggregates in a way that lost frames would exceed the * buffer size. If just limiting the aggregate size, this would be * possible with a buf_size of 8: @@ -3044,9 +3128,6 @@ enum ieee80211_reconfig_type { * buffer size of 8. Correct ways to retransmit #1 would be: * - TX: 1 or 18 or 81 * Even "189" would be wrong since 1 could be lost again. - * The @amsdu parameter is valid when the action is set to - * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's ability - * to receive A-MSDU within A-MPDU. * * Returns a negative error code on failure. * The callback can sleep. @@ -3388,9 +3469,7 @@ struct ieee80211_ops { int (*tx_last_beacon)(struct ieee80211_hw *hw); int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn, - u8 buf_size, bool amsdu); + struct ieee80211_ampdu_params *params); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); @@ -4374,21 +4453,19 @@ void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf, struct sk_buff *skb, u8 *p2k); /** - * ieee80211_get_key_tx_seq - get key TX sequence counter + * ieee80211_tkip_add_iv - write TKIP IV and Ext. IV to pos * + * @pos: start of crypto header * @keyconf: the parameter passed with the set key - * @seq: buffer to receive the sequence data + * @pn: PN to add * - * This function allows a driver to retrieve the current TX IV/PN - * for the given key. It must not be called if IV generation is - * offloaded to the device. + * Returns: pointer to the octet following IVs (i.e. beginning of + * the packet payload) * - * Note that this function may only be called when no TX processing - * can be done concurrently, for example when queues are stopped - * and the stop has been synchronized. + * This function writes the tkip IV value to pos (which should + * point to the crypto header) */ -void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq); +u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key_conf *keyconf, u64 pn); /** * ieee80211_get_key_rx_seq - get key RX sequence counter @@ -4410,23 +4487,6 @@ void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, int tid, struct ieee80211_key_seq *seq); /** - * ieee80211_set_key_tx_seq - set key TX sequence counter - * - * @keyconf: the parameter passed with the set key - * @seq: new sequence data - * - * This function allows a driver to set the current TX IV/PNs for the - * given key. This is useful when resuming from WoWLAN sleep and the - * device may have transmitted frames using the PTK, e.g. replies to - * ARP requests. - * - * Note that this function may only be called when no TX processing - * can be done concurrently. - */ -void ieee80211_set_key_tx_seq(struct ieee80211_key_conf *keyconf, - struct ieee80211_key_seq *seq); - -/** * ieee80211_set_key_rx_seq - set key RX sequence counter * * @keyconf: the parameter passed with the set key @@ -5121,6 +5181,24 @@ void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, const u8 *addr); /** + * ieee80211_mark_rx_ba_filtered_frames - move RX BA window and mark filtered + * @pubsta: station struct + * @tid: the session's TID + * @ssn: starting sequence number of the bitmap, all frames before this are + * assumed to be out of the window after the call + * @filtered: bitmap of filtered frames, BIT(0) is the @ssn entry etc. + * @received_mpdus: number of received mpdus in firmware + * + * This function moves the BA window and releases all frames before @ssn, and + * marks frames marked in the bitmap as having been filtered. Afterwards, it + * checks if any frames in the window starting from @ssn can now be released + * (in case they were only waiting for frames that were filtered.) + */ +void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, + u16 ssn, u64 filtered, + u16 received_mpdus); + +/** * ieee80211_send_bar - send a BlockAckReq frame * * can be used to flush pending frames from the peer's aggregation reorder @@ -5371,6 +5449,21 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) return ieee80211_iftype_p2p(vif->type, vif->p2p); } +/** + * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data + * + * @vif: the specified virtual interface + * @membership: 64 bits array - a bit is set if station is member of the group + * @position: 2 bits per group id indicating the position in the group + * + * Note: This function assumes that the given vif is valid and the position and + * membership data is of the correct size and are in the same byte order as the + * matching GroupId management frame. + * Calls to this function need to be serialized with RX path. + */ +void ieee80211_update_mu_groups(struct ieee80211_vif *vif, + const u8 *membership, const u8 *position); + void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, int rssi_min_thold, int rssi_max_thold); @@ -5523,4 +5616,19 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); */ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + +/** + * ieee80211_txq_get_depth - get pending frame/byte count of given txq + * + * The values are not guaranteed to be coherent with regard to each other, i.e. + * txq state can change half-way of this function and the caller may end up + * with "new" frame_cnt and "old" byte_cnt or vice-versa. + * + * @txq: pointer obtained from station or virtual interface + * @frame_cnt: pointer to store frame count + * @byte_cnt: pointer to store byte count + */ +void ieee80211_txq_get_depth(struct ieee80211_txq *txq, + unsigned long *frame_cnt, + unsigned long *byte_cnt); #endif /* MAC80211_H */ diff --git a/include/net/mac802154.h b/include/net/mac802154.h index da574bbdc333..6cd7a70706a9 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -16,10 +16,10 @@ #ifndef NET_MAC802154_H #define NET_MAC802154_H +#include <asm/unaligned.h> #include <net/af_ieee802154.h> #include <linux/ieee802154.h> #include <linux/skbuff.h> -#include <linux/unaligned/memmove.h> #include <net/cfg802154.h> @@ -247,13 +247,14 @@ struct ieee802154_ops { */ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) { - /* return some invalid fc on failure */ - if (unlikely(skb->len < 2)) { + /* check if we can fc at skb_mac_header of sk buffer */ + if (unlikely(!skb_mac_header_was_set(skb) || + (skb_tail_pointer(skb) - skb_mac_header(skb)) < 2)) { WARN_ON(1); return cpu_to_le16(0); } - return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb)); + return get_unaligned_le16(skb_mac_header(skb)); } /** @@ -263,7 +264,7 @@ static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) */ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) { - __put_unaligned_memmove64(swab64p(be64_src), le64_dst); + put_unaligned_le64(get_unaligned_be64(be64_src), le64_dst); } /** @@ -273,7 +274,7 @@ static inline void ieee802154_be64_to_le64(void *le64_dst, const void *be64_src) */ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) { - __put_unaligned_memmove64(swab64p(le64_src), be64_dst); + put_unaligned_be64(get_unaligned_le64(le64_src), be64_dst); } /** @@ -283,7 +284,7 @@ static inline void ieee802154_le64_to_be64(void *be64_dst, const void *le64_src) */ static inline void ieee802154_le16_to_be16(void *be16_dst, const void *le16_src) { - __put_unaligned_memmove16(swab16p(le16_src), be16_dst); + put_unaligned_be16(get_unaligned_le16(le16_src), be16_dst); } /** diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h index e2a518b60e19..a3f3c11b2526 100644 --- a/include/net/netfilter/nft_masq.h +++ b/include/net/netfilter/nft_masq.h @@ -2,7 +2,9 @@ #define _NFT_MASQ_H_ struct nft_masq { - u32 flags; + u32 flags; + enum nft_registers sreg_proto_min:8; + enum nft_registers sreg_proto_max:8; }; extern const struct nla_policy nft_masq_policy[]; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2b7907a35568..a69cde3ce460 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -80,9 +80,13 @@ struct netns_ipv4 { int sysctl_tcp_ecn; int sysctl_tcp_ecn_fallback; + int sysctl_ip_default_ttl; int sysctl_ip_no_pmtu_disc; int sysctl_ip_fwd_use_pmtu; int sysctl_ip_nonlocal_bind; + /* Shall we try to damage output packets if routing dev changes? */ + int sysctl_ip_dynaddr; + int sysctl_ip_early_demux; int sysctl_fwmark_reflect; int sysctl_tcp_fwmark_accept; @@ -98,6 +102,21 @@ struct netns_ipv4 { int sysctl_tcp_keepalive_probes; int sysctl_tcp_keepalive_intvl; + int sysctl_tcp_syn_retries; + int sysctl_tcp_synack_retries; + int sysctl_tcp_syncookies; + int sysctl_tcp_reordering; + int sysctl_tcp_retries1; + int sysctl_tcp_retries2; + int sysctl_tcp_orphan_retries; + int sysctl_tcp_fin_timeout; + unsigned int sysctl_tcp_notsent_lowat; + + int sysctl_igmp_max_memberships; + int sysctl_igmp_max_msf; + int sysctl_igmp_llm_reports; + int sysctl_igmp_qrv; + struct ping_group_range ping_group_range; atomic_t dev_addr_genid; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c0368db6df54..10d0848f5b8a 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -58,7 +58,10 @@ struct netns_ipv6 { struct timer_list ip6_fib_timer; struct hlist_head *fib_table_hash; struct fib6_table *fib6_main_tbl; + struct list_head fib6_walkers; struct dst_ops ip6_dst_ops; + rwlock_t fib6_walker_lock; + spinlock_t fib6_gc_lock; unsigned int ip6_rt_gc_expire; unsigned long ip6_rt_last_gc; #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 68e509750caa..039cc29cb4a8 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -51,7 +51,7 @@ void pn_sock_init(void); struct sock *pn_find_sock_by_sa(struct net *net, const struct sockaddr_pn *sa); void pn_deliver_sock_broadcast(struct net *net, struct sk_buff *skb); void phonet_get_local_port_range(int *min, int *max); -void pn_sock_hash(struct sock *sk); +int pn_sock_hash(struct sock *sk); void pn_sock_unhash(struct sock *sk); int pn_sock_get_port(struct sock *sk, unsigned short sport); diff --git a/include/net/ping.h b/include/net/ping.h index ac80cb45e630..4cd90d6b5c25 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -65,7 +65,7 @@ struct pingfakehdr { }; int ping_get_port(struct sock *sk, unsigned short ident); -void ping_hash(struct sock *sk); +int ping_hash(struct sock *sk); void ping_unhash(struct sock *sk); int ping_init_sock(struct sock *sk); @@ -79,7 +79,6 @@ int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len); int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, void *user_icmph, size_t icmph_len); -int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); bool ping_rcv(struct sk_buff *skb); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index bc49967e1a68..caa5e18636df 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -358,4 +358,69 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +struct tc_cls_u32_knode { + struct tcf_exts *exts; + struct tc_u32_sel *sel; + u32 handle; + u32 val; + u32 mask; + u32 link_handle; + u8 fshift; +}; + +struct tc_cls_u32_hnode { + u32 handle; + u32 prio; + unsigned int divisor; +}; + +enum tc_clsu32_command { + TC_CLSU32_NEW_KNODE, + TC_CLSU32_REPLACE_KNODE, + TC_CLSU32_DELETE_KNODE, + TC_CLSU32_NEW_HNODE, + TC_CLSU32_REPLACE_HNODE, + TC_CLSU32_DELETE_HNODE, +}; + +struct tc_cls_u32_offload { + /* knode values */ + enum tc_clsu32_command command; + union { + struct tc_cls_u32_knode knode; + struct tc_cls_u32_hnode hnode; + }; +}; + +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW 1 + +static inline bool tc_should_offload(struct net_device *dev, u32 flags) +{ + if (!(dev->features & NETIF_F_HW_TC)) + return false; + + if (flags & TCA_CLS_FLAGS_SKIP_HW) + return false; + + if (!dev->netdev_ops->ndo_setup_tc) + return false; + + return true; +} + +enum tc_fl_command { + TC_CLSFLOWER_REPLACE, + TC_CLSFLOWER_DESTROY, +}; + +struct tc_cls_flower_offload { + enum tc_fl_command command; + unsigned long cookie; + struct flow_dissector *dissector; + struct fl_flow_key *mask; + struct fl_flow_key *key; + struct tcf_exts *exts; +}; + #endif diff --git a/include/net/raw.h b/include/net/raw.h index 6a40c6562dd2..3e789008394d 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -57,7 +57,7 @@ int raw_seq_open(struct inode *ino, struct file *file, #endif -void raw_hash_sk(struct sock *sk); +int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); struct raw_sock { diff --git a/include/net/route.h b/include/net/route.h index a3b9ef74a389..6de665bf1750 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -209,6 +209,9 @@ unsigned int inet_addr_type_dev_table(struct net *net, void ip_rt_multicast_event(struct in_device *); int ip_rt_ioctl(struct net *, unsigned int cmd, void __user *arg); void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); +struct rtable *rt_dst_alloc(struct net_device *dev, + unsigned int flags, u16 type, + bool nopolicy, bool noxfrm, bool will_cache); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); @@ -329,14 +332,13 @@ static inline int inet_iif(const struct sk_buff *skb) return skb->skb_iif; } -extern int sysctl_ip_default_ttl; - static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); + struct net *net = dev_net(dst->dev); if (hoplimit == 0) - hoplimit = sysctl_ip_default_ttl; + hoplimit = net->ipv4.sysctl_ip_default_ttl; return hoplimit; } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 636a362a0e03..46e55f0202a6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -345,6 +345,12 @@ extern struct Qdisc_ops pfifo_fast_ops; extern struct Qdisc_ops mq_qdisc_ops; extern struct Qdisc_ops noqueue_qdisc_ops; extern const struct Qdisc_ops *default_qdisc_ops; +static inline const struct Qdisc_ops * +get_default_qdisc_ops(const struct net_device *dev, int ntx) +{ + return ntx < dev->real_num_tx_queues ? + default_qdisc_ops : &pfifo_fast_ops; +} struct Qdisc_class_common { u32 classid; @@ -396,7 +402,8 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc); void qdisc_reset(struct Qdisc *qdisc); void qdisc_destroy(struct Qdisc *qdisc); -void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n); +void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, + unsigned int len); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, @@ -707,6 +714,23 @@ static inline void qdisc_reset_queue(struct Qdisc *sch) sch->qstats.backlog = 0; } +static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, + struct Qdisc **pold) +{ + struct Qdisc *old; + + sch_tree_lock(sch); + old = *pold; + *pold = new; + if (old != NULL) { + qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); + qdisc_reset(old); + } + sch_tree_unlock(sch); + + return old; +} + static inline unsigned int __qdisc_queue_drop(struct Qdisc *sch, struct sk_buff_head *list) { diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index f2d58aa37a6f..9b9fb122b31f 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -31,12 +31,12 @@ #define __sctp_auth_h__ #include <linux/list.h> -#include <linux/crypto.h> struct sctp_endpoint; struct sctp_association; struct sctp_authkey; struct sctp_hmacalgo; +struct crypto_shash; /* * Define a generic struct that will hold all the info @@ -90,7 +90,7 @@ int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep, struct sctp_association *asoc, gfp_t gfp); int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp); -void sctp_auth_destroy_hmacs(struct crypto_hash *auth_hmacs[]); +void sctp_auth_destroy_hmacs(struct crypto_shash *auth_hmacs[]); struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id); struct sctp_hmac *sctp_auth_asoc_get_hmac(const struct sctp_association *asoc); void sctp_auth_asoc_set_default_hmac(struct sctp_association *asoc, diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 835aa2ed9870..03fb33efcae2 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -82,6 +82,11 @@ #define SCTP_PROTOSW_FLAG INET_PROTOSW_PERMANENT #endif +/* Round an int up to the next multiple of 4. */ +#define WORD_ROUND(s) (((s)+3)&~3) +/* Truncate to the previous multiple of 4. */ +#define WORD_TRUNC(s) ((s)&~3) + /* * Function declarations. */ @@ -381,11 +386,9 @@ static inline struct list_head *sctp_list_dequeue(struct list_head *list) { struct list_head *result = NULL; - if (list->next != list) { + if (!list_empty(list)) { result = list->next; - list->next = result->next; - list->next->prev = list; - INIT_LIST_HEAD(result); + list_del_init(result); } return result; } @@ -426,7 +429,7 @@ static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu) if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag); - frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN); + frag = WORD_TRUNC(min_t(int, frag, SCTP_MAX_CHUNK_LEN)); return frag; } @@ -475,9 +478,6 @@ for (pos = chunk->subh.fwdtsn_hdr->skip;\ (void *)pos <= (void *)chunk->subh.fwdtsn_hdr->skip + end - sizeof(struct sctp_fwdtsn_skip);\ pos++) -/* Round an int up to the next multiple of 4. */ -#define WORD_ROUND(s) (((s)+3)&~3) - /* External references. */ extern struct proto sctp_prot; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 487ef34bbd63..efc01743b9d6 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -201,7 +201,7 @@ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *, struct sctp_chunk * sctp_make_datafrag_empty(struct sctp_association *, const struct sctp_sndrcvinfo *sinfo, int len, const __u8 flags, - __u16 ssn); + __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 *); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 205630bb5010..5a404c354f4c 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -82,7 +82,7 @@ struct sctp_bind_addr; struct sctp_ulpq; struct sctp_ep_common; struct sctp_ssnmap; -struct crypto_hash; +struct crypto_shash; #include <net/sctp/tsnmap.h> @@ -166,7 +166,7 @@ struct sctp_sock { struct sctp_pf *pf; /* Access to HMAC transform. */ - struct crypto_hash *hmac; + struct crypto_shash *hmac; char *sctp_hmac_alg; /* What is our base endpointer? */ @@ -535,7 +535,6 @@ struct sctp_datamsg { struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, struct sctp_sndrcvinfo *, struct iov_iter *); -void sctp_datamsg_free(struct sctp_datamsg *); void sctp_datamsg_put(struct sctp_datamsg *); void sctp_chunk_fail(struct sctp_chunk *, int error); int sctp_chunk_abandoned(struct sctp_chunk *); @@ -656,7 +655,7 @@ void sctp_chunk_free(struct sctp_chunk *); void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data); struct sctp_chunk *sctp_chunkify(struct sk_buff *, const struct sctp_association *, - struct sock *); + struct sock *, gfp_t gfp); void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *, union sctp_addr *); const union sctp_addr *sctp_source(const struct sctp_chunk *chunk); @@ -718,10 +717,10 @@ struct sctp_packet *sctp_packet_init(struct sctp_packet *, __u16 sport, __u16 dport); struct sctp_packet *sctp_packet_config(struct sctp_packet *, __u32 vtag, int); sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *, - struct sctp_chunk *, int); + struct sctp_chunk *, int, gfp_t); sctp_xmit_t sctp_packet_append_chunk(struct sctp_packet *, struct sctp_chunk *); -int sctp_packet_transmit(struct sctp_packet *); +int sctp_packet_transmit(struct sctp_packet *, gfp_t); void sctp_packet_free(struct sctp_packet *); static inline int sctp_packet_empty(struct sctp_packet *packet) @@ -848,6 +847,11 @@ struct sctp_transport { */ ktime_t last_time_heard; + /* When was the last time that we sent a chunk using this + * transport? We use this to check for idle transports + */ + unsigned long last_time_sent; + /* Last time(in jiffies) when cwnd is reduced due to the congestion * indication based on ECNE chunk. */ @@ -953,7 +957,8 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, struct sctp_sock *); void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk); void sctp_transport_free(struct sctp_transport *); -void sctp_transport_reset_timers(struct sctp_transport *); +void sctp_transport_reset_t3_rtx(struct sctp_transport *); +void sctp_transport_reset_hb_timer(struct sctp_transport *); int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1054,7 +1059,7 @@ struct sctp_outq { void sctp_outq_init(struct sctp_association *, struct sctp_outq *); void sctp_outq_teardown(struct sctp_outq *); void sctp_outq_free(struct sctp_outq*); -int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk); +int sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); 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 *); @@ -1062,7 +1067,7 @@ void sctp_outq_restart(struct sctp_outq *); void sctp_retransmit(struct sctp_outq *, struct sctp_transport *, sctp_retransmit_reason_t); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); -int sctp_outq_uncork(struct sctp_outq *); +int sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { @@ -1098,7 +1103,7 @@ int sctp_bind_addr_dup(struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, gfp_t gfp); int sctp_add_bind_addr(struct sctp_bind_addr *, union sctp_addr *, - __u8 addr_state, gfp_t gfp); + int new_size, __u8 addr_state, gfp_t gfp); int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *); int sctp_bind_addr_match(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *); @@ -1234,7 +1239,7 @@ struct sctp_endpoint { /* SCTP AUTH: array of the HMACs that will be allocated * we need this per association so that we don't serialize */ - struct crypto_hash **auth_hmacs; + struct crypto_shash **auth_hmacs; /* SCTP-AUTH: hmacs for the endpoint encoded into parameter */ struct sctp_hmac_algo_param *auth_hmacs_list; diff --git a/include/net/sock.h b/include/net/sock.h index f5ea148853e2..121ffc115c4f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -630,7 +630,11 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list) static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { - hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); + if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && + sk->sk_family == AF_INET6) + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); + else + hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) @@ -984,7 +988,7 @@ struct proto { void (*release_cb)(struct sock *sk); /* Keeping track of sk's, looking them up, and port selection methods. */ - void (*hash)(struct sock *sk); + int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); @@ -1194,10 +1198,10 @@ static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, /* With per-bucket locks this operation is not-atomic, so that * this version is not worse. */ -static inline void __sk_prot_rehash(struct sock *sk) +static inline int __sk_prot_rehash(struct sock *sk) { sk->sk_prot->unhash(sk); - sk->sk_prot->hash(sk); + return sk->sk_prot->hash(sk); } void sk_prot_clear_portaddr_nulls(struct sock *sk, int size); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index d451122e8404..51d77b2ce2b2 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -54,6 +54,8 @@ struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ @@ -75,6 +77,8 @@ struct switchdev_obj { struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; + void *complete_priv; + void (*complete)(struct net_device *dev, int err, void *priv); }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index 592a6bc02b0b..93c520b83d10 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -2,6 +2,7 @@ #define __NET_TC_GACT_H #include <net/act_api.h> +#include <linux/tc_act/tc_gact.h> struct tcf_gact { struct tcf_common common; @@ -15,4 +16,19 @@ struct tcf_gact { #define to_gact(a) \ container_of(a->priv, struct tcf_gact, common) +static inline bool is_tcf_gact_shot(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + struct tcf_gact *gact; + + if (a->ops && a->ops->type != TCA_ACT_GACT) + return false; + + gact = a->priv; + if (gact->tcf_action == TC_ACT_SHOT) + return true; + +#endif + return false; +} #endif /* __NET_TC_GACT_H */ diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h new file mode 100644 index 000000000000..dc9a09aefb33 --- /dev/null +++ b/include/net/tc_act/tc_ife.h @@ -0,0 +1,61 @@ +#ifndef __NET_TC_IFE_H +#define __NET_TC_IFE_H + +#include <net/act_api.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/module.h> + +#define IFE_METAHDRLEN 2 +struct tcf_ife_info { + struct tcf_common common; + u8 eth_dst[ETH_ALEN]; + u8 eth_src[ETH_ALEN]; + u16 eth_type; + u16 flags; + /* list of metaids allowed */ + struct list_head metalist; +}; +#define to_ife(a) \ + container_of(a->priv, struct tcf_ife_info, common) + +struct tcf_meta_info { + const struct tcf_meta_ops *ops; + void *metaval; + u16 metaid; + struct list_head metalist; +}; + +struct tcf_meta_ops { + u16 metaid; /*Maintainer provided ID */ + u16 metatype; /*netlink attribute type (look at net/netlink.h) */ + const char *name; + const char *synopsis; + struct list_head list; + int (*check_presence)(struct sk_buff *, struct tcf_meta_info *); + int (*encode)(struct sk_buff *, void *, struct tcf_meta_info *); + int (*decode)(struct sk_buff *, void *, u16 len); + int (*get)(struct sk_buff *skb, struct tcf_meta_info *mi); + int (*alloc)(struct tcf_meta_info *, void *); + void (*release)(struct tcf_meta_info *); + int (*validate)(void *val, int len); + struct module *owner; +}; + +#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta" __stringify_1(metan)) + +int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi); +int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, + const void *dval); +int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval); +int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval); +int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi); +int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi); +int ife_validate_meta_u32(void *val, int len); +int ife_validate_meta_u16(void *val, int len); +void ife_release_meta_gen(struct tcf_meta_info *mi); +int register_ife_op(struct tcf_meta_ops *mops); +int unregister_ife_op(struct tcf_meta_ops *mops); + +#endif /* __NET_TC_IFE_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 0df9a0db4a8e..b496d5ad7d42 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -20,6 +20,7 @@ #define __NET_TC_SKBEDIT_H #include <net/act_api.h> +#include <linux/tc_act/tc_skbedit.h> struct tcf_skbedit { struct tcf_common common; @@ -32,4 +33,19 @@ struct tcf_skbedit { #define to_skbedit(a) \ container_of(a->priv, struct tcf_skbedit, common) +/* Return true iff action is mark */ +static inline bool is_tcf_skbedit_mark(const struct tc_action *a) +{ +#ifdef CONFIG_NET_CLS_ACT + if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) + return to_skbedit(a)->flags == SKBEDIT_F_MARK; +#endif + return false; +} + +static inline u32 tcf_skbedit_mark(const struct tc_action *a) +{ + return to_skbedit(a)->mark; +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index ae6468f5c9f3..6db10228113f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -27,7 +27,6 @@ #include <linux/cache.h> #include <linux/percpu.h> #include <linux/skbuff.h> -#include <linux/crypto.h> #include <linux/cryptohash.h> #include <linux/kref.h> #include <linux/ktime.h> @@ -239,13 +238,6 @@ extern struct inet_timewait_death_row tcp_death_row; extern int sysctl_tcp_timestamps; extern int sysctl_tcp_window_scaling; extern int sysctl_tcp_sack; -extern int sysctl_tcp_fin_timeout; -extern int sysctl_tcp_syn_retries; -extern int sysctl_tcp_synack_retries; -extern int sysctl_tcp_retries1; -extern int sysctl_tcp_retries2; -extern int sysctl_tcp_orphan_retries; -extern int sysctl_tcp_syncookies; extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; @@ -274,7 +266,6 @@ extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; -extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; extern int sysctl_tcp_min_rtt_wlen; extern int sysctl_tcp_autocorking; @@ -561,6 +552,8 @@ void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); bool tcp_schedule_loss_probe(struct sock *sk); +void tcp_skb_collapse_tstamp(struct sk_buff *skb, + const struct sk_buff *next_skb); /* tcp_input.c */ void tcp_resume_early_retransmit(struct sock *sk); @@ -568,6 +561,7 @@ void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); +void tcp_fin(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -963,9 +957,11 @@ static inline void tcp_enable_fack(struct tcp_sock *tp) */ static inline void tcp_enable_early_retrans(struct tcp_sock *tp) { + struct net *net = sock_net((struct sock *)tp); + tp->do_early_retrans = sysctl_tcp_early_retrans && sysctl_tcp_early_retrans < 4 && !sysctl_tcp_thin_dupack && - sysctl_tcp_reordering == 3; + net->ipv4.sysctl_tcp_reordering == 3; } static inline void tcp_disable_early_retrans(struct tcp_sock *tp) @@ -1252,7 +1248,7 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) static inline int tcp_fin_time(const struct sock *sk) { - int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout; + int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout; const int rto = inet_csk(sk)->icsk_rto; if (fin_timeout < (rto << 2) - (rto >> 1)) @@ -1325,9 +1321,6 @@ static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp) tp->retransmit_skb_hint = NULL; } -/* MD5 Signature */ -struct crypto_hash; - union tcp_md5_addr { struct in_addr a4; #if IS_ENABLED(CONFIG_IPV6) @@ -1376,7 +1369,7 @@ union tcp_md5sum_block { /* - pool: digest algorithm, hash description and scratch buffer */ struct tcp_md5sig_pool { - struct hash_desc md5_desc; + struct ahash_request *md5_req; union tcp_md5sum_block md5_blk; }; @@ -1437,6 +1430,7 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); +void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb); struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, @@ -1685,7 +1679,8 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { - return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat; + struct net *net = sock_net((struct sock *)tp); + return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } static inline bool tcp_stream_memory_free(const struct sock *sk) @@ -1819,4 +1814,38 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) skb->truesize = 2; } +static inline int tcp_inq(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int answ; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { + answ = 0; + } else if (sock_flag(sk, SOCK_URGINLINE) || + !tp->urg_data || + before(tp->urg_seq, tp->copied_seq) || + !before(tp->urg_seq, tp->rcv_nxt)) { + + answ = tp->rcv_nxt - tp->copied_seq; + + /* Subtract 1, if FIN was received */ + if (answ && sock_flag(sk, SOCK_DONE)) + answ--; + } else { + answ = tp->urg_seq - tp->copied_seq; + } + + return answ; +} + +static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) +{ + u16 segs_in; + + segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); + tp->segs_in += segs_in; + if (skb->len > tcp_hdrlen(skb)) + tp->data_segs_in += segs_in; +} + #endif /* _TCP_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 2842541e28e7..92927f729ac8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -177,9 +177,10 @@ static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) } /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ -static inline void udp_lib_hash(struct sock *sk) +static inline int udp_lib_hash(struct sock *sk) { BUG(); + return 0; } void udp_lib_unhash(struct sock *sk); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index cca2ad3082c3..b83114077cee 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -88,8 +88,8 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, - __u8 prio, __u8 ttl, __be16 src_port, - __be16 dst_port, bool nocheck); + __u8 prio, __u8 ttl, __be32 label, + __be16 src_port, __be16 dst_port, bool nocheck); #endif void udp_tunnel_sock_release(struct socket *sock); @@ -103,7 +103,7 @@ static inline struct sk_buff *udp_tunnel_handle_offloads(struct sk_buff *skb, { int type = udp_csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; - return iptunnel_handle_offloads(skb, udp_csum, type); + return iptunnel_handle_offloads(skb, type); } static inline void udp_tunnel_gro_complete(struct sk_buff *skb, int nhoff) diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 0fb86442544b..35437c779da8 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -9,17 +9,71 @@ #include <linux/udp.h> #include <net/dst_metadata.h> +/* VXLAN protocol (RFC 7348) header: + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |R|R|R|R|I|R|R|R| Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | VXLAN Network Identifier (VNI) | Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * I = VXLAN Network Identifier (VNI) present. + */ +struct vxlanhdr { + __be32 vx_flags; + __be32 vx_vni; +}; + +/* VXLAN header flags. */ +#define VXLAN_HF_VNI cpu_to_be32(BIT(27)) + +#define VXLAN_N_VID (1u << 24) +#define VXLAN_VID_MASK (VXLAN_N_VID - 1) +#define VXLAN_VNI_MASK cpu_to_be32(VXLAN_VID_MASK << 8) +#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) + #define VNI_HASH_BITS 10 #define VNI_HASH_SIZE (1<<VNI_HASH_BITS) +#define FDB_HASH_BITS 8 +#define FDB_HASH_SIZE (1<<FDB_HASH_BITS) + +/* Remote checksum offload for VXLAN (VXLAN_F_REMCSUM_[RT]X): + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * |R|R|R|R|I|R|R|R|R|R|C| Reserved | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | VXLAN Network Identifier (VNI) |O| Csum start | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * + * C = Remote checksum offload bit. When set indicates that the + * remote checksum offload data is present. + * + * O = Offset bit. Indicates the checksum offset relative to + * checksum start. + * + * Csum start = Checksum start divided by two. + * + * http://tools.ietf.org/html/draft-herbert-vxlan-rco + */ + +/* VXLAN-RCO header flags. */ +#define VXLAN_HF_RCO cpu_to_be32(BIT(21)) + +/* Remote checksum offload header option */ +#define VXLAN_RCO_MASK cpu_to_be32(0x7f) /* Last byte of vni field */ +#define VXLAN_RCO_UDP cpu_to_be32(0x80) /* Indicate UDP RCO (TCP when not set *) */ +#define VXLAN_RCO_SHIFT 1 /* Left shift of start */ +#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1) +#define VXLAN_MAX_REMCSUM_START (0x7f << VXLAN_RCO_SHIFT) /* - * VXLAN Group Based Policy Extension: + * VXLAN Group Based Policy Extension (VXLAN_F_GBP): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * |1|-|-|-|1|-|-|-|R|D|R|R|A|R|R|R| Group Policy ID | + * |G|R|R|R|I|R|R|R|R|D|R|R|A|R|R|R| Group Policy ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | VXLAN Network Identifier (VNI) | Reserved | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * + * G = Group Policy ID present. + * * D = Don't Learn bit. When set, this bit indicates that the egress * VTEP MUST NOT learn the source address of the encapsulated frame. * @@ -27,18 +81,18 @@ * this packet. Policies MUST NOT be applied by devices when the * A bit is set. * - * [0] https://tools.ietf.org/html/draft-smith-vxlan-group-policy + * https://tools.ietf.org/html/draft-smith-vxlan-group-policy */ struct vxlanhdr_gbp { - __u8 vx_flags; + u8 vx_flags; #ifdef __LITTLE_ENDIAN_BITFIELD - __u8 reserved_flags1:3, + u8 reserved_flags1:3, policy_applied:1, reserved_flags2:2, dont_learn:1, reserved_flags3:1; #elif defined(__BIG_ENDIAN_BITFIELD) - __u8 reserved_flags1:1, + u8 reserved_flags1:1, dont_learn:1, reserved_flags2:2, policy_applied:1, @@ -50,7 +104,10 @@ struct vxlanhdr_gbp { __be32 vx_vni; }; -#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | 0xFFFFFF) +/* VXLAN-GBP header flags. */ +#define VXLAN_HF_GBP cpu_to_be32(BIT(31)) + +#define VXLAN_GBP_USED_BITS (VXLAN_HF_GBP | cpu_to_be32(0xFFFFFF)) /* skb->mark mapping * @@ -62,44 +119,6 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) -/* VXLAN protocol header: - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * |G|R|R|R|I|R|R|C| Reserved | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * | VXLAN Network Identifier (VNI) | Reserved | - * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - * - * G = 1 Group Policy (VXLAN-GBP) - * I = 1 VXLAN Network Identifier (VNI) present - * C = 1 Remote checksum offload (RCO) - */ -struct vxlanhdr { - __be32 vx_flags; - __be32 vx_vni; -}; - -/* VXLAN header flags. */ -#define VXLAN_HF_RCO BIT(21) -#define VXLAN_HF_VNI BIT(27) -#define VXLAN_HF_GBP BIT(31) - -/* Remote checksum offload header option */ -#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */ -#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */ -#define VXLAN_RCO_SHIFT 1 /* Left shift of start */ -#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1) -#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT) - -#define VXLAN_N_VID (1u << 24) -#define VXLAN_VID_MASK (VXLAN_N_VID - 1) -#define VXLAN_VNI_MASK (VXLAN_VID_MASK << 8) -#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr)) - -#define VNI_HASH_BITS 10 -#define VNI_HASH_SIZE (1<<VNI_HASH_BITS) -#define FDB_HASH_BITS 8 -#define FDB_HASH_SIZE (1<<FDB_HASH_BITS) - struct vxlan_metadata { u32 gbp; }; @@ -125,23 +144,25 @@ union vxlan_addr { struct vxlan_rdst { union vxlan_addr remote_ip; __be16 remote_port; - u32 remote_vni; + __be32 remote_vni; u32 remote_ifindex; struct list_head list; struct rcu_head rcu; + struct dst_cache dst_cache; }; struct vxlan_config { union vxlan_addr remote_ip; union vxlan_addr saddr; - u32 vni; + __be32 vni; int remote_ifindex; int mtu; __be16 dst_port; - __u16 port_min; - __u16 port_max; - __u8 tos; - __u8 ttl; + u16 port_min; + u16 port_max; + u8 tos; + u8 ttl; + __be32 label; u32 flags; unsigned long age_interval; unsigned int addrmax; @@ -177,7 +198,7 @@ struct vxlan_dev { #define VXLAN_F_L2MISS 0x08 #define VXLAN_F_L3MISS 0x10 #define VXLAN_F_IPV6 0x20 -#define VXLAN_F_UDP_CSUM 0x40 +#define VXLAN_F_UDP_ZERO_CSUM_TX 0x40 #define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80 #define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100 #define VXLAN_F_REMCSUM_TX 0x200 @@ -231,7 +252,9 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, (skb->inner_protocol_type != ENCAP_TYPE_ETHER || skb->inner_protocol != htons(ETH_P_TEB) || (skb_inner_mac_header(skb) - skb_transport_header(skb) != - sizeof(struct udphdr) + sizeof(struct vxlanhdr)))) + sizeof(struct udphdr) + sizeof(struct vxlanhdr)) || + (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, inner_eth_hdr(skb)->h_proto)))) return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); return features; @@ -242,6 +265,68 @@ static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, /* IPv6 header + UDP + VXLAN + Ethernet header */ #define VXLAN6_HEADROOM (40 + 8 + 8 + 14) +static inline struct vxlanhdr *vxlan_hdr(struct sk_buff *skb) +{ + return (struct vxlanhdr *)(udp_hdr(skb) + 1); +} + +static inline __be32 vxlan_vni(__be32 vni_field) +{ +#if defined(__BIG_ENDIAN) + return (__force __be32)((__force u32)vni_field >> 8); +#else + return (__force __be32)((__force u32)(vni_field & VXLAN_VNI_MASK) << 8); +#endif +} + +static inline __be32 vxlan_vni_field(__be32 vni) +{ +#if defined(__BIG_ENDIAN) + return (__force __be32)((__force u32)vni << 8); +#else + return (__force __be32)((__force u32)vni >> 8); +#endif +} + +static inline __be32 vxlan_tun_id_to_vni(__be64 tun_id) +{ +#if defined(__BIG_ENDIAN) + return (__force __be32)tun_id; +#else + return (__force __be32)((__force u64)tun_id >> 32); +#endif +} + +static inline __be64 vxlan_vni_to_tun_id(__be32 vni) +{ +#if defined(__BIG_ENDIAN) + return (__force __be64)vni; +#else + return (__force __be64)((u64)(__force u32)vni << 32); +#endif +} + +static inline size_t vxlan_rco_start(__be32 vni_field) +{ + return be32_to_cpu(vni_field & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT; +} + +static inline size_t vxlan_rco_offset(__be32 vni_field) +{ + return (vni_field & VXLAN_RCO_UDP) ? + offsetof(struct udphdr, check) : + offsetof(struct tcphdr, check); +} + +static inline __be32 vxlan_compute_rco(unsigned int start, unsigned int offset) +{ + __be32 vni_field = cpu_to_be32(start >> VXLAN_RCO_SHIFT); + + if (offset == offsetof(struct udphdr, check)) + vni_field |= VXLAN_RCO_UDP; + return vni_field; +} + #if IS_ENABLED(CONFIG_VXLAN) void vxlan_get_rx_port(struct net_device *netdev); #else |