diff options
Diffstat (limited to 'include/net')
43 files changed, 814 insertions, 294 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 3049cb69c025..9cf6870b526e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -134,7 +134,8 @@ struct tc_action_ops { (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); int (*offload_act_setup)(struct tc_action *act, void *entry_data, - u32 *index_inc, bool bind); + u32 *index_inc, bool bind, + struct netlink_ext_ack *extack); }; struct tc_action_net { diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 69ef31cea582..fe7935be7dc4 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -265,6 +265,15 @@ enum { * runtime suspend, because event filtering takes place there. */ HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, + + /* + * When this quirk is set, disables the use of + * HCI_OP_ENHANCED_SETUP_SYNC_CONN command to setup SCO connections. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, }; /* HCI device flags */ @@ -616,6 +625,7 @@ enum { #define EIR_SSP_RAND_R192 0x0F /* Simple Pairing Randomizer R-192 */ #define EIR_DEVICE_ID 0x10 /* device ID */ #define EIR_APPEARANCE 0x19 /* Device appearance */ +#define EIR_SERVICE_DATA 0x16 /* Service Data */ #define EIR_LE_BDADDR 0x1B /* LE Bluetooth device address */ #define EIR_LE_ROLE 0x1C /* LE role */ #define EIR_SSP_HASH_C256 0x1D /* Simple Pairing Hash C-256 */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 62d7b81b1cb7..5a52a2018b56 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1495,8 +1495,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ (hdev->commands[39] & 0x04)) -/* Use enhanced synchronous connection if command is supported */ -#define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) +/* Use enhanced synchronous connection if command is supported and its quirk + * has not been set. + */ +#define enhanced_sync_conn_capable(dev) \ + (((dev)->commands[29] & 0x08) && \ + !test_bit(HCI_QUIRK_BROKEN_ENHANCED_SETUP_SYNC_CONN, &(dev)->quirks)) /* Use ext scanning if set ext scan param and ext scan enable is supported */ #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 68713388b617..6d02e12e4702 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1183,6 +1183,9 @@ struct cfg80211_mbssid_elems { * Token (measurement type 11) * @lci_len: LCI data length * @civicloc_len: Civic location data length + * @he_bss_color: BSS Color settings + * @he_bss_color_valid: indicates whether bss color + * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { const u8 *head, *tail; @@ -1202,6 +1205,8 @@ struct cfg80211_beacon_data { size_t probe_resp_len; size_t lci_len; size_t civicloc_len; + struct cfg80211_he_bss_color he_bss_color; + bool he_bss_color_valid; }; struct mac_address { @@ -1292,7 +1297,6 @@ struct cfg80211_unsol_bcast_probe_resp { * @sae_h2e_required: stations must support direct H2E technique in SAE * @flags: flags, as defined in enum cfg80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings - * @he_bss_color: BSS Color settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters @@ -1326,7 +1330,6 @@ struct cfg80211_ap_settings { bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; - struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_mbssid_config mbssid_config; @@ -2735,6 +2738,7 @@ struct cfg80211_auth_request { * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE + * @ASSOC_REQ_DISABLE_EHT: Disable EHT */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2742,6 +2746,7 @@ enum cfg80211_assoc_req_flags { ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), + ASSOC_REQ_DISABLE_EHT = BIT(5), }; /** @@ -5549,8 +5554,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @conn_owner_nlportid: (private) connection owner socket port ID * @disconnect_wk: (private) auto-disconnect work * @disconnect_bssid: (private) the BSSID to use for auto-disconnect - * @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 * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID @@ -5599,9 +5602,6 @@ struct wireless_dev { struct cfg80211_chan_def preset_chandef; struct cfg80211_chan_def chandef; - bool ibss_fixed; - bool ibss_dfs_possible; - bool ps; int ps_timeout; @@ -8006,7 +8006,9 @@ int cfg80211_register_netdevice(struct net_device *dev); */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { +#if IS_ENABLED(CONFIG_CFG80211) cfg80211_unregister_wdev(dev->ieee80211_ptr); +#endif } /** diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index 833672d6fbe4..d8d8719315fd 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -203,8 +203,8 @@ struct wpan_phy { /* PHY depended MAC PIB values */ - /* 802.15.4 acronym: Tdsym in usec */ - u8 symbol_duration; + /* 802.15.4 acronym: Tdsym in nsec */ + u32 symbol_duration; /* lifs and sifs periods timing */ u16 lifs_period; u16 sifs_period; @@ -373,6 +373,7 @@ struct wpan_dev { #define to_phy(_dev) container_of(_dev, struct wpan_phy, dev) +#if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) static inline int wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, const struct ieee802154_addr *daddr, @@ -383,6 +384,7 @@ wpan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, return wpan_dev->header_ops->create(skb, dev, daddr, saddr, len); } +#endif struct wpan_phy * wpan_phy_new(const struct cfg802154_ops *ops, size_t priv_size); @@ -415,4 +417,6 @@ static inline const char *wpan_phy_name(struct wpan_phy *phy) return dev_name(&phy->dev); } +void ieee802154_configure_durations(struct wpan_phy *phy); + #endif /* __NET_CFG802154_H */ diff --git a/include/net/devlink.h b/include/net/devlink.h index a30180c0988a..2a2a2a0c93f7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -22,6 +22,7 @@ #include <linux/firmware.h> struct devlink; +struct devlink_linecard; struct devlink_port_phys_attrs { u32 port_number; /* Same value as "split group". @@ -135,6 +136,7 @@ struct devlink_port { struct mutex reporters_lock; /* Protects reporter_list */ struct devlink_rate *devlink_rate; + struct devlink_linecard *linecard; }; struct devlink_port_new_attrs { @@ -148,6 +150,40 @@ struct devlink_port_new_attrs { sfnum_valid:1; }; +/** + * struct devlink_linecard_ops - Linecard operations + * @provision: callback to provision the linecard slot with certain + * type of linecard. As a result of this operation, + * driver is expected to eventually (could be after + * the function call returns) call one of: + * devlink_linecard_provision_set() + * devlink_linecard_provision_fail() + * @unprovision: callback to unprovision the linecard slot. As a result + * of this operation, driver is expected to eventually + * (could be after the function call returns) call + * devlink_linecard_provision_clear() + * devlink_linecard_provision_fail() + * @same_provision: callback to ask the driver if linecard is already + * provisioned in the same way user asks this linecard to be + * provisioned. + * @types_count: callback to get number of supported types + * @types_get: callback to get next type in list + */ +struct devlink_linecard_ops { + int (*provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv, + struct netlink_ext_ack *extack); + int (*unprovision)(struct devlink_linecard *linecard, void *priv, + struct netlink_ext_ack *extack); + bool (*same_provision)(struct devlink_linecard *linecard, void *priv, + const char *type, const void *type_priv); + unsigned int (*types_count)(struct devlink_linecard *linecard, + void *priv); + void (*types_get)(struct devlink_linecard *linecard, + void *priv, unsigned int index, const char **type, + const void **type_priv); +}; + struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; @@ -1536,6 +1572,18 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, int devlink_rate_leaf_create(struct devlink_port *port, void *priv); void devlink_rate_leaf_destroy(struct devlink_port *devlink_port); void devlink_rate_nodes_destroy(struct devlink *devlink); +void devlink_port_linecard_set(struct devlink_port *devlink_port, + struct devlink_linecard *linecard); +struct devlink_linecard * +devlink_linecard_create(struct devlink *devlink, unsigned int linecard_index, + const struct devlink_linecard_ops *ops, void *priv); +void devlink_linecard_destroy(struct devlink_linecard *linecard); +void devlink_linecard_provision_set(struct devlink_linecard *linecard, + const char *type); +void devlink_linecard_provision_clear(struct devlink_linecard *linecard); +void devlink_linecard_provision_fail(struct devlink_linecard *linecard); +void devlink_linecard_activate(struct devlink_linecard *linecard); +void devlink_linecard_deactivate(struct devlink_linecard *linecard); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, diff --git a/include/net/dsa.h b/include/net/dsa.h index 934958fda962..14f07275852b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -579,6 +579,10 @@ static inline bool dsa_is_user_port(struct dsa_switch *ds, int p) dsa_switch_for_each_port((_dp), (_ds)) \ if (dsa_port_is_cpu((_dp))) +#define dsa_switch_for_each_cpu_port_continue_reverse(_dp, _ds) \ + dsa_switch_for_each_port_continue_reverse((_dp), (_ds)) \ + if (dsa_port_is_cpu((_dp))) + static inline u32 dsa_user_ports(struct dsa_switch *ds) { struct dsa_port *dp; @@ -590,6 +594,17 @@ static inline u32 dsa_user_ports(struct dsa_switch *ds) return mask; } +static inline u32 dsa_cpu_ports(struct dsa_switch *ds) +{ + struct dsa_port *cpu_dp; + u32 mask = 0; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) + mask |= BIT(cpu_dp->index); + + return mask; +} + /* Return the local port used to reach an arbitrary switch device */ static inline unsigned int dsa_routing_port(struct dsa_switch *ds, int device) { @@ -792,7 +807,7 @@ struct dsa_switch_ops { enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol mprot); - int (*change_tag_protocol)(struct dsa_switch *ds, int port, + int (*change_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); /* * Method for switch drivers to connect to the tagging protocol driver @@ -967,6 +982,8 @@ struct dsa_switch_ops { int (*port_bridge_flags)(struct dsa_switch *ds, int port, struct switchdev_brport_flags flags, struct netlink_ext_ack *extack); + void (*port_set_host_flood)(struct dsa_switch *ds, int port, + bool uc, bool mc); /* * VLAN support @@ -1239,12 +1256,6 @@ struct dsa_switch_driver { struct net_device *dsa_dev_to_net_device(struct device *dev); -typedef int dsa_fdb_walk_cb_t(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db); - -int dsa_port_walk_fdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); -int dsa_port_walk_mdbs(struct dsa_switch *ds, int port, dsa_fdb_walk_cb_t cb); bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 9f65f1bfbd24..a4c6057c7097 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -253,6 +253,14 @@ struct flow_dissector_key_hash { u32 hash; }; +/** + * struct flow_dissector_key_num_of_vlans: + * @num_of_vlans: num_of_vlans value + */ +struct flow_dissector_key_num_of_vlans { + u8 num_of_vlans; +}; + enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_CONTROL, /* struct flow_dissector_key_control */ FLOW_DISSECTOR_KEY_BASIC, /* struct flow_dissector_key_basic */ @@ -282,6 +290,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_META, /* struct flow_dissector_key_meta */ FLOW_DISSECTOR_KEY_CT, /* struct flow_dissector_key_ct */ FLOW_DISSECTOR_KEY_HASH, /* struct flow_dissector_key_hash */ + FLOW_DISSECTOR_KEY_NUM_OF_VLANS, /* struct flow_dissector_key_num_of_vlans */ FLOW_DISSECTOR_KEY_MAX, }; diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 4cfdef6ca4f6..c8490729b4ae 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,6 +64,14 @@ struct inet6_ifaddr { struct hlist_node addr_lst; struct list_head if_list; + /* + * Used to safely traverse idev->addr_list in process context + * if the idev->lock needed to protect idev->addr_list cannot be held. + * In that case, add the items to this list temporarily and iterate + * without holding idev->lock. + * See addrconf_ifdown and dev_forward_change. + */ + struct list_head if_list_aux; struct list_head tmp_list; struct inet6_ifaddr *ifpub; diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 81b965953036..f259e1ae14ba 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -103,15 +103,25 @@ struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, const int dif); int inet6_hash(struct sock *sk); -#endif /* IS_ENABLED(CONFIG_IPV6) */ -#define INET6_MATCH(__sk, __net, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_family == AF_INET6) && \ - ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ - ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) +static inline bool inet6_match(struct net *net, const struct sock *sk, + const struct in6_addr *saddr, + const struct in6_addr *daddr, + const __portpair ports, + const int dif, const int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_family != AF_INET6 || + sk->sk_portpair != ports || + !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) + return false; + + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} +#endif /* IS_ENABLED(CONFIG_IPV6) */ #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 3908296d103f..077cd730ce2f 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -25,6 +25,7 @@ #undef INET_CSK_CLEAR_TIMERS struct inet_bind_bucket; +struct inet_bind2_bucket; struct tcp_congestion_ops; /* @@ -57,6 +58,7 @@ struct inet_connection_sock_af_ops { * * @icsk_accept_queue: FIFO of established children * @icsk_bind_hash: Bind node + * @icsk_bind2_hash: Bind node in the bhash2 table * @icsk_timeout: Timeout * @icsk_retransmit_timer: Resend (no ack) * @icsk_rto: Retransmit timeout @@ -66,7 +68,6 @@ struct inet_connection_sock_af_ops { * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data * @icsk_clean_acked Clean acked data hook - * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@ -84,6 +85,7 @@ struct inet_connection_sock { struct inet_sock icsk_inet; struct request_sock_queue icsk_accept_queue; struct inet_bind_bucket *icsk_bind_hash; + struct inet_bind2_bucket *icsk_bind2_hash; unsigned long icsk_timeout; struct timer_list icsk_retransmit_timer; struct timer_list icsk_delack_timer; @@ -96,7 +98,6 @@ struct inet_connection_sock { const struct tcp_ulp_ops *icsk_ulp_ops; void __rcu *icsk_ulp_data; void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); - struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:5, icsk_ca_initialized:1, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 98e1ec1a14f0..a0887b70967b 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -90,11 +90,32 @@ struct inet_bind_bucket { struct hlist_head owners; }; +struct inet_bind2_bucket { + possible_net_t ib_net; + int l3mdev; + unsigned short port; + union { +#if IS_ENABLED(CONFIG_IPV6) + struct in6_addr v6_rcv_saddr; +#endif + __be32 rcv_saddr; + }; + /* Node in the inet2_bind_hashbucket chain */ + struct hlist_node node; + /* List of sockets hashed to this bucket */ + struct hlist_head owners; +}; + static inline struct net *ib_net(struct inet_bind_bucket *ib) { return read_pnet(&ib->ib_net); } +static inline struct net *ib2_net(struct inet_bind2_bucket *ib) +{ + return read_pnet(&ib->ib_net); +} + #define inet_bind_bucket_for_each(tb, head) \ hlist_for_each_entry(tb, head, node) @@ -103,6 +124,15 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; +/* This is synchronized using the inet_bind_hashbucket's spinlock. + * Instead of having separate spinlocks, the inet_bind2_hashbucket can share + * the inet_bind_hashbucket's given that in every case where the bhash2 table + * is useful, a lookup in the bhash table also occurs. + */ +struct inet_bind2_hashbucket { + struct hlist_head chain; +}; + /* Sockets can be hashed in established or listening table. * We must use different 'nulls' end-of-chain value for all hash buckets : * A socket might transition from ESTABLISH to LISTEN state without @@ -111,11 +141,7 @@ struct inet_bind_hashbucket { #define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; - unsigned int count; - union { - struct hlist_head head; - struct hlist_nulls_head nulls_head; - }; + struct hlist_nulls_head nulls_head; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ @@ -138,37 +164,19 @@ struct inet_hashinfo { */ struct kmem_cache *bind_bucket_cachep; struct inet_bind_hashbucket *bhash; + /* The 2nd binding table hashed by port and address. + * This is used primarily for expediting the resolution of bind + * conflicts. + */ + struct kmem_cache *bind2_bucket_cachep; + struct inet_bind2_hashbucket *bhash2; unsigned int bhash_size; /* The 2nd listener table hashed by local port and address */ unsigned int lhash2_mask; struct inet_listen_hashbucket *lhash2; - - /* All the above members are written once at bootup and - * never written again _or_ are predominantly read-access. - * - * Now align to a new cache line as all the following members - * might be often dirty. - */ - /* All sockets in TCP_LISTEN state will be in listening_hash. - * This is the only table where wildcard'd TCP sockets can - * exist. listening_hash is only hashed by local port number. - * If lhash2 is initialized, the same socket will also be hashed - * to lhash2 by port and address. - */ - struct inet_listen_hashbucket listening_hash[INET_LHTABLE_SIZE] - ____cacheline_aligned_in_smp; }; -#define inet_lhash2_for_each_icsk_continue(__icsk) \ - hlist_for_each_entry_continue(__icsk, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk(__icsk, list) \ - hlist_for_each_entry(__icsk, list, icsk_listen_portaddr_node) - -#define inet_lhash2_for_each_icsk_rcu(__icsk, list) \ - hlist_for_each_entry_rcu(__icsk, list, icsk_listen_portaddr_node) - static inline struct inet_listen_hashbucket * inet_lhash2_bucket(struct inet_hashinfo *h, u32 hash) { @@ -221,32 +229,50 @@ inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); -static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, - const u32 bhash_size) +static inline bool check_bind_bucket_match(struct inet_bind_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev) { - return (lport + net_hash_mix(net)) & (bhash_size - 1); + return net_eq(ib_net(tb), net) && tb->port == port && + tb->l3mdev == l3mdev; } -void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - const unsigned short snum); +struct inet_bind2_bucket * +inet_bind2_bucket_create(struct kmem_cache *cachep, struct net *net, + struct inet_bind2_hashbucket *head, + const unsigned short port, int l3mdev, + const struct sock *sk); -/* These can have wildcards, don't try too hard. */ -static inline u32 inet_lhashfn(const struct net *net, const unsigned short num) -{ - return (num + net_hash_mix(net)) & (INET_LHTABLE_SIZE - 1); -} +void inet_bind2_bucket_destroy(struct kmem_cache *cachep, + struct inet_bind2_bucket *tb); + +struct inet_bind2_bucket * +inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, + const unsigned short port, int l3mdev, + struct sock *sk, + struct inet_bind2_hashbucket **head); -static inline int inet_sk_listen_hashfn(const struct sock *sk) +bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, + struct net *net, + const unsigned short port, + int l3mdev, + const struct sock *sk); + +static inline u32 inet_bhashfn(const struct net *net, const __u16 lport, + const u32 bhash_size) { - return inet_lhashfn(sock_net(sk), inet_sk(sk)->inet_num); + return (lport + net_hash_mix(net)) & (bhash_size - 1); } +void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, + struct inet_bind2_bucket *tb2, const unsigned short snum); + /* Caller must disable local BH processing. */ int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); -void inet_hashinfo_init(struct inet_hashinfo *h); void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, @@ -295,7 +321,6 @@ static inline struct sock *inet_lookup_listener(struct net *net, ((__force __portpair)(((__u32)(__dport) << 16) | (__force __u32)(__be16)(__sport))) #endif -#if (BITS_PER_LONG == 64) #ifdef __BIG_ENDIAN #define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ const __addrpair __name = (__force __addrpair) ( \ @@ -307,24 +332,22 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__force __u64)(__be32)(__daddr)) << 32) | \ ((__force __u64)(__be32)(__saddr))) #endif /* __BIG_ENDIAN */ -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_addrpair == (__cookie)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#else /* 32-bit arch */ -#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \ - const int __name __deprecated __attribute__((unused)) - -#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ - (((__sk)->sk_portpair == (__ports)) && \ - ((__sk)->sk_daddr == (__saddr)) && \ - ((__sk)->sk_rcv_saddr == (__daddr)) && \ - (((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ - net_eq(sock_net(__sk), (__net))) -#endif /* 64-bit arch */ + +static inline bool inet_match(struct net *net, const struct sock *sk, + const __addrpair cookie, const __portpair ports, + int dif, int sdif) +{ + int bound_dev_if; + + if (!net_eq(sock_net(sk), net) || + sk->sk_portpair != ports || + sk->sk_addrpair != cookie) + return false; + + /* Paired with WRITE_ONCE() from sock_bindtoindex_locked() */ + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + return bound_dev_if == dif || bound_dev_if == sdif; +} /* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so we need * not check it for lookups anymore, thanks Alexey. -DaveM diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 234d70ae5f4c..c1b5dcd6597c 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -116,14 +116,15 @@ static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); - if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) + if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif - return sk->sk_bound_dev_if; + return bound_dev_if; } static inline int inet_sk_bound_l3mdev(const struct sock *sk) diff --git a/include/net/ip.h b/include/net/ip.h index 0161137914cf..26fffda78cca 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -94,7 +94,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->sockc.mark = inet->sk.sk_mark; ipcm->sockc.tsflags = inet->sk.sk_tsflags; - ipcm->oif = inet->sk.sk_bound_dev_if; + ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; } diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 6a82bcb8813b..a378eff827c7 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -212,7 +212,7 @@ struct fib_rt_info { u32 tb_id; __be32 dst; int dst_len; - u8 tos; + dscp_t dscp; u8 type; u8 offload:1, trap:1, @@ -225,7 +225,7 @@ struct fib_entry_notifier_info { u32 dst; int dst_len; struct fib_info *fi; - u8 tos; + dscp_t dscp; u8 type; u32 tb_id; }; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 213612f1680c..5b38bf1a586b 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -151,6 +151,17 @@ struct frag_hdr { __be32 identification; }; +/* + * Jumbo payload option, as described in RFC 2675 2. + */ +struct hop_jumbo_hdr { + u8 nexthdr; + u8 hdrlen; + u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ + u8 tlv_len; /* 4 */ + __be32 jumbo_payload_len; +}; + #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 @@ -456,6 +467,39 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); +/* This helper is specialized for BIG TCP needs. + * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. + * It assumes headers are already in skb->head. + * Returns 0, or IPPROTO_TCP if a BIG TCP packet is there. + */ +static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) +{ + const struct hop_jumbo_hdr *jhdr; + const struct ipv6hdr *nhdr; + + if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) + return 0; + + if (skb->protocol != htons(ETH_P_IPV6)) + return 0; + + if (skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) + return 0; + + nhdr = ipv6_hdr(skb); + + if (nhdr->nexthdr != NEXTHDR_HOP) + return 0; + + jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); + if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || + jhdr->nexthdr != IPPROTO_TCP) + return 0; + return jhdr->nexthdr; +} + static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 382ebb862ea8..ebadb2103968 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -514,7 +514,6 @@ struct ieee80211_fils_discovery { * to that BSS) that can change during the lifetime of the BSS. * * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE - * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK * @uora_exists: is the UORA element advertised by AP * @ack_enabled: indicates support to receive a multi-TID that solicits either * ACK, BACK or both @@ -1144,20 +1143,41 @@ ieee80211_info_get_tx_time_est(struct ieee80211_tx_info *info) return info->tx_time_est << 2; } +/*** + * struct ieee80211_rate_status - mrr stage for status path + * + * This struct is used in struct ieee80211_tx_status to provide drivers a + * dynamic way to report about used rates and power levels per packet. + * + * @rate_idx The actual used rate. + * @try_count How often the rate was tried. + * @tx_power_idx An idx into the ieee80211_hw->tx_power_levels list of the + * corresponding wifi hardware. The idx shall point to the power level + * that was used when sending the packet. + */ +struct ieee80211_rate_status { + struct rate_info rate_idx; + u8 try_count; + u8 tx_power_idx; +}; + /** * struct ieee80211_tx_status - extended tx status info for rate control * * @sta: Station that the packet was transmitted for * @info: Basic tx status information * @skb: Packet skb (can be NULL if not provided by the driver) - * @rate: The TX rate that was used when sending the packet + * @rates: Mrr stages that were used when sending the packet + * @n_rates: Number of mrr stages (count of instances for @rates) * @free_list: list where processed skbs are stored to be free'd by the driver */ struct ieee80211_tx_status { struct ieee80211_sta *sta; struct ieee80211_tx_info *info; struct sk_buff *skb; - struct rate_info *rate; + struct ieee80211_rate_status *rates; + u8 n_rates; + struct list_head *free_list; }; @@ -1201,9 +1221,9 @@ static inline struct ieee80211_rx_status *IEEE80211_SKB_RXCB(struct sk_buff *skb * in the TX status but the rate control information (it does clear * the count since you need to fill that in anyway). * - * NOTE: You can only use this function if you do NOT use - * info->driver_data! Use info->rate_driver_data - * instead if you need only the less space that allows. + * NOTE: While the rates array is kept intact, this will wipe all of the + * driver_data fields in info, so it's up to the driver to restore + * any fields it needs after calling this helper. */ static inline void ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) @@ -1701,7 +1721,7 @@ enum ieee80211_offload_flags { * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed * at runtime, mac80211 will never touch this field - * @offloaad_flags: hardware offload capabilities/flags for this interface. + * @offload_flags: hardware offload capabilities/flags for this interface. * These are initialized by mac80211 before calling .add_interface, * .change_interface or .update_vif_offload and updated by the driver * within these ops, based on supported features or runtime change @@ -2056,6 +2076,45 @@ struct ieee80211_sta_txpwr { enum nl80211_tx_power_setting type; }; +#define MAX_STA_LINKS 15 + +/** + * struct ieee80211_link_sta - station Link specific info + * All link specific info for a STA link for a non MLD STA(single) + * or a MLD STA(multiple entries) are stored here. + * + * @addr: MAC address of the Link STA. For non-MLO STA this is same as the addr + * in ieee80211_sta. For MLO Link STA this addr can be same or different + * from addr in ieee80211_sta (representing MLD STA addr) + * @supp_rates: Bitmap of supported rates + * @ht_cap: HT capabilities of this STA; restricted to our own capabilities + * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities + * @he_cap: HE capabilities of this STA + * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities + * @eht_cap: EHT capabilities of this STA + * @bandwidth: current bandwidth the station can receive with + * @rx_nss: in HT/VHT, the maximum number of spatial streams the + * station can receive at the moment, changed by operating mode + * notifications and capabilities. The value is only valid after + * the station moves to associated state. + * @txpwr: the station tx power configuration + * + */ +struct ieee80211_link_sta { + u8 addr[ETH_ALEN]; + + u32 supp_rates[NUM_NL80211_BANDS]; + struct ieee80211_sta_ht_cap ht_cap; + struct ieee80211_sta_vht_cap vht_cap; + struct ieee80211_sta_he_cap he_cap; + struct ieee80211_he_6ghz_capa he_6ghz_capa; + struct ieee80211_sta_eht_cap eht_cap; + + u8 rx_nss; + enum ieee80211_sta_rx_bandwidth bandwidth; + struct ieee80211_sta_txpwr txpwr; +}; + /** * struct ieee80211_sta - station table entry * @@ -2065,15 +2124,11 @@ struct ieee80211_sta_txpwr { * either be protected by rcu_read_lock() explicitly or implicitly, * or you must take good care to not use such a pointer after a * call to your sta_remove callback that removed it. + * This also represents the MLD STA in case of MLO association + * and holds pointers to various link STA's * * @addr: MAC address * @aid: AID we assigned to the station if we're an AP - * @supp_rates: Bitmap of supported rates (per band) - * @ht_cap: HT capabilities of this STA; restricted to our own capabilities - * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities - * @he_cap: HE capabilities of this STA - * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities - * @eht_cap: EHT capabilities of this STA * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU * that this station is allowed to transmit to us. * Can be modified by driver. @@ -2085,11 +2140,6 @@ struct ieee80211_sta_txpwr { * if wme is supported. The bits order is like in * IEEE80211_WMM_IE_STA_QOSINFO_AC_*. * @max_sp: max Service Period. Only valid if wme is supported. - * @bandwidth: current bandwidth the station can receive with - * @rx_nss: in HT/VHT, the maximum number of spatial streams the - * station can receive at the moment, changed by operating mode - * notifications and capabilities. The value is only valid after - * the station moves to associated state. * @smps_mode: current SMPS mode (off, static or dynamic) * @rates: rate control selection table * @tdls: indicates whether the STA is a TDLS peer @@ -2102,25 +2152,28 @@ struct ieee80211_sta_txpwr { * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID - * @txpwr: the station tx power configuration * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames + * @multi_link_sta: Identifies if this sta is a MLD STA + * @deflink: This holds the default link STA information, for non MLO STA all link + * specific STA information is accessed through @deflink or through + * link[0] which points to address of @deflink. For MLO Link STA + * the first added link STA will point to deflink. + * @link: reference to Link Sta entries. For Non MLO STA, except 1st link, + * i.e link[0] all links would be assigned to NULL by default and + * would access link information via @deflink or link[0]. For MLO + * STA, first link STA being added will point its link pointer to + * @deflink address and remaining would be allocated and the address + * would be assigned to link[link_id] where link_id is the id assigned + * by the AP. */ struct ieee80211_sta { - u32 supp_rates[NUM_NL80211_BANDS]; u8 addr[ETH_ALEN]; u16 aid; - struct ieee80211_sta_ht_cap ht_cap; - struct ieee80211_sta_vht_cap vht_cap; - struct ieee80211_sta_he_cap he_cap; - struct ieee80211_he_6ghz_capa he_6ghz_capa; - struct ieee80211_sta_eht_cap eht_cap; u16 max_rx_aggregation_subframes; bool wme; u8 uapsd_queues; u8 max_sp; - u8 rx_nss; - enum ieee80211_sta_rx_bandwidth bandwidth; enum ieee80211_smps_mode smps_mode; struct ieee80211_sta_rates __rcu *rates; bool tdls; @@ -2147,10 +2200,13 @@ struct ieee80211_sta { bool support_p2p_ps; u16 max_rc_amsdu_len; u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; - struct ieee80211_sta_txpwr txpwr; struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; + bool multi_link_sta; + struct ieee80211_link_sta deflink; + struct ieee80211_link_sta *link[MAX_STA_LINKS]; + /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); }; @@ -2434,6 +2490,9 @@ struct ieee80211_txq { * usage and 802.11 frames with %RX_FLAG_ONLY_MONITOR set for monitor to * the stack. * + * @IEEE80211_HW_DETECTS_COLOR_COLLISION: HW/driver has support for BSS color + * collision detection and doesn't need it in software. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2489,6 +2548,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_TX_ENCAP_OFFLOAD, IEEE80211_HW_SUPPORTS_RX_DECAP_OFFLOAD, IEEE80211_HW_SUPPORTS_CONC_MON_RX_DECAP, + IEEE80211_HW_DETECTS_COLOR_COLLISION, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2618,6 +2678,12 @@ enum ieee80211_hw_flags { * refilling deficit of each TXQ. * * @max_mtu: the max mtu could be set. + * + * @tx_power_levels: a list of power levels supported by the wifi hardware. + * The power levels can be specified either as integer or fractions. + * The power level at idx 0 shall be the maximum positive power level. + * + * @max_txpwr_levels_idx: the maximum valid idx of 'tx_power_levels' list. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2656,6 +2722,8 @@ struct ieee80211_hw { u8 tx_sk_pacing_shift; u8 weight_multiplier; u32 max_mtu; + const s8 *tx_power_levels; + u8 max_txpwr_levels_idx; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -6367,7 +6435,7 @@ static inline int rate_supported(struct ieee80211_sta *sta, enum nl80211_band band, int index) { - return (sta == NULL || sta->supp_rates[band] & BIT(index)); + return (sta == NULL || sta->deflink.supp_rates[band] & BIT(index)); } static inline s8 diff --git a/include/net/mac802154.h b/include/net/mac802154.h index 2c3bbc6645ba..bdac0ddbdcdb 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -498,4 +498,23 @@ void ieee802154_stop_queue(struct ieee802154_hw *hw); void ieee802154_xmit_complete(struct ieee802154_hw *hw, struct sk_buff *skb, bool ifs_handling); +/** + * ieee802154_xmit_error - offloaded frame transmission failed + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + * @reason: error code + */ +void ieee802154_xmit_error(struct ieee802154_hw *hw, struct sk_buff *skb, + int reason); + +/** + * ieee802154_xmit_hw_error - frame could not be offloaded to the transmitter + * because of a hardware error (bus error, timeout, etc) + * + * @hw: pointer as obtained from ieee802154_alloc_hw(). + * @skb: buffer for transmission + */ +void ieee802154_xmit_hw_error(struct ieee802154_hw *hw, struct sk_buff *skb); + #endif /* NET_MAC802154_H */ diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0a3b0fb04a3b..4d761ad530c9 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -35,7 +35,8 @@ struct mptcp_ext { frozen:1, reset_transient:1; u8 reset_reason:4, - csum_reqd:1; + csum_reqd:1, + infinite_map:1; }; #define MPTCP_RM_IDS_MAX 8 @@ -124,7 +125,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, struct mptcp_out_options *opts); bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts); void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); @@ -283,4 +284,10 @@ static inline int mptcpv6_init(void) { return 0; } static inline void mptcpv6_handle_mapped(struct sock *sk, bool mapped) { } #endif +#if defined(CONFIG_MPTCP) && defined(CONFIG_BPF_SYSCALL) +struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk); +#else +static inline struct mptcp_sock *bpf_mptcp_sock_from_subflow(struct sock *sk) { return NULL; } +#endif + #endif /* __NET_MPTCP_H */ diff --git a/include/net/net_debug.h b/include/net/net_debug.h new file mode 100644 index 000000000000..1e74684cbbdb --- /dev/null +++ b/include/net/net_debug.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NET_DEBUG_H +#define _LINUX_NET_DEBUG_H + +#include <linux/bug.h> +#include <linux/kern_levels.h> + +struct net_device; + +__printf(3, 4) __cold +void netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...); +__printf(2, 3) __cold +void netdev_emerg(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_alert(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_crit(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_err(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_warn(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_notice(const struct net_device *dev, const char *format, ...); +__printf(2, 3) __cold +void netdev_info(const struct net_device *dev, const char *format, ...); + +#define netdev_level_once(level, dev, fmt, ...) \ +do { \ + static bool __section(".data.once") __print_once; \ + \ + if (!__print_once) { \ + __print_once = true; \ + netdev_printk(level, dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define netdev_emerg_once(dev, fmt, ...) \ + netdev_level_once(KERN_EMERG, dev, fmt, ##__VA_ARGS__) +#define netdev_alert_once(dev, fmt, ...) \ + netdev_level_once(KERN_ALERT, dev, fmt, ##__VA_ARGS__) +#define netdev_crit_once(dev, fmt, ...) \ + netdev_level_once(KERN_CRIT, dev, fmt, ##__VA_ARGS__) +#define netdev_err_once(dev, fmt, ...) \ + netdev_level_once(KERN_ERR, dev, fmt, ##__VA_ARGS__) +#define netdev_warn_once(dev, fmt, ...) \ + netdev_level_once(KERN_WARNING, dev, fmt, ##__VA_ARGS__) +#define netdev_notice_once(dev, fmt, ...) \ + netdev_level_once(KERN_NOTICE, dev, fmt, ##__VA_ARGS__) +#define netdev_info_once(dev, fmt, ...) \ + netdev_level_once(KERN_INFO, dev, fmt, ##__VA_ARGS__) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netdev_dbg(__dev, format, args...) \ +do { \ + dynamic_netdev_dbg(__dev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netdev_dbg(__dev, format, args...) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args) +#else +#define netdev_dbg(__dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, __dev, format, ##args); \ +}) +#endif + +#if defined(VERBOSE_DEBUG) +#define netdev_vdbg netdev_dbg +#else + +#define netdev_vdbg(dev, format, args...) \ +({ \ + if (0) \ + netdev_printk(KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* netif printk helpers, similar to netdev_printk */ + +#define netif_printk(priv, type, level, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_printk(level, (dev), fmt, ##args); \ +} while (0) + +#define netif_level(level, priv, type, dev, fmt, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + netdev_##level(dev, fmt, ##args); \ +} while (0) + +#define netif_emerg(priv, type, dev, fmt, args...) \ + netif_level(emerg, priv, type, dev, fmt, ##args) +#define netif_alert(priv, type, dev, fmt, args...) \ + netif_level(alert, priv, type, dev, fmt, ##args) +#define netif_crit(priv, type, dev, fmt, args...) \ + netif_level(crit, priv, type, dev, fmt, ##args) +#define netif_err(priv, type, dev, fmt, args...) \ + netif_level(err, priv, type, dev, fmt, ##args) +#define netif_warn(priv, type, dev, fmt, args...) \ + netif_level(warn, priv, type, dev, fmt, ##args) +#define netif_notice(priv, type, dev, fmt, args...) \ + netif_level(notice, priv, type, dev, fmt, ##args) +#define netif_info(priv, type, dev, fmt, args...) \ + netif_level(info, priv, type, dev, fmt, ##args) + +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) +#define netif_dbg(priv, type, netdev, format, args...) \ +do { \ + if (netif_msg_##type(priv)) \ + dynamic_netdev_dbg(netdev, format, ##args); \ +} while (0) +#elif defined(DEBUG) +#define netif_dbg(priv, type, dev, format, args...) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args) +#else +#define netif_dbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + +/* if @cond then downgrade to debug, else print at @level */ +#define netif_cond_dbg(priv, type, netdev, cond, level, fmt, args...) \ + do { \ + if (cond) \ + netif_dbg(priv, type, netdev, fmt, ##args); \ + else \ + netif_ ## level(priv, type, netdev, fmt, ##args); \ + } while (0) + +#if defined(VERBOSE_DEBUG) +#define netif_vdbg netif_dbg +#else +#define netif_vdbg(priv, type, dev, format, args...) \ +({ \ + if (0) \ + netif_printk(priv, type, KERN_DEBUG, dev, format, ##args); \ + 0; \ +}) +#endif + + +#if defined(CONFIG_DEBUG_NET) +#define DEBUG_NET_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) +#else +#define DEBUG_NET_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#endif + +#endif /* _LINUX_NET_DEBUG_H */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index b08b70989d2c..a32be8aa7ed2 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -43,6 +43,12 @@ union nf_conntrack_expect_proto { /* insert expect proto private data here */ }; +struct nf_conntrack_net_ecache { + struct delayed_work dwork; + spinlock_t dying_lock; + struct hlist_nulls_head dying_list; +}; + struct nf_conntrack_net { /* only used when new connection is allocated: */ atomic_t count; @@ -58,8 +64,7 @@ struct nf_conntrack_net { struct ctl_table_header *sysctl_header; #endif #ifdef CONFIG_NF_CONNTRACK_EVENTS - struct delayed_work ecache_dwork; - struct netns_ct *ct_net; + struct nf_conntrack_net_ecache ecache; #endif }; @@ -96,7 +101,6 @@ struct nf_conn { /* Have we seen traffic both ways yet? (bitset) */ unsigned long status; - u16 cpu; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) @@ -232,13 +236,16 @@ static inline bool nf_ct_kill(struct nf_conn *ct) return nf_ct_delete(ct, 0, 0); } -/* Set all unconfirmed conntrack as dying */ -void nf_ct_unconfirmed_destroy(struct net *); +struct nf_ct_iter_data { + struct net *net; + void *data; + u32 portid; + int report; +}; /* Iterate over all conntracks: if iter returns true, it's deleted. */ -void nf_ct_iterate_cleanup_net(struct net *net, - int (*iter)(struct nf_conn *i, void *data), - void *data, u32 portid, int report); +void nf_ct_iterate_cleanup_net(int (*iter)(struct nf_conn *i, void *data), + const struct nf_ct_iter_data *iter_data); /* also set unconfirmed conntracks as dying. Only use in module exit path. */ void nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 13807ea94cd2..6406cfee34c2 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) if (ct) { if (!nf_ct_is_confirmed(ct)) ret = __nf_conntrack_confirm(skb); - if (likely(ret == NF_ACCEPT)) + if (ret == NF_ACCEPT && nf_ct_ecache_exist(ct)) nf_ct_deliver_cached_events(ct); } return ret; diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 9645b47fa7e4..e227d997fc71 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -10,6 +10,7 @@ struct nf_conncount_data; struct nf_conncount_list { spinlock_t list_lock; + u32 last_gc; /* jiffies at most recent gc */ struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ }; diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 6c4c490a3e34..0c1dac318e02 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -14,7 +14,6 @@ #include <net/netfilter/nf_conntrack_extend.h> enum nf_ct_ecache_state { - NFCT_ECACHE_UNKNOWN, /* destroy event not sent */ NFCT_ECACHE_DESTROY_FAIL, /* tried but failed to send destroy event */ NFCT_ECACHE_DESTROY_SENT, /* sent destroy event after failure */ }; @@ -23,7 +22,6 @@ struct nf_conntrack_ecache { unsigned long cache; /* bitops want long */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ - enum nf_ct_ecache_state state:8;/* ecache state */ u32 missed; /* missed events */ u32 portid; /* netlink portid of destroyer */ }; @@ -38,28 +36,12 @@ nf_ct_ecache_find(const struct nf_conn *ct) #endif } -static inline struct nf_conntrack_ecache * -nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) +static inline bool nf_ct_ecache_exist(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - struct net *net = nf_ct_net(ct); - struct nf_conntrack_ecache *e; - - if (!ctmask && !expmask && net->ct.sysctl_events) { - ctmask = ~0; - expmask = ~0; - } - if (!ctmask && !expmask) - return NULL; - - e = nf_ct_ext_add(ct, NF_CT_EXT_ECACHE, gfp); - if (e) { - e->ctmask = ctmask; - e->expmask = expmask; - } - return e; + return nf_ct_ext_exist(ct, NF_CT_EXT_ECACHE); #else - return NULL; + return false; #endif } @@ -91,6 +73,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct); int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, u32 portid, int report); +bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp); #else static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) @@ -105,6 +88,10 @@ static inline int nf_conntrack_eventmask_report(unsigned int eventmask, return 0; } +static inline bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) +{ + return false; +} #endif static inline void @@ -130,30 +117,20 @@ nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, u32 portid, int report) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, portid, report); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, portid, report); #endif + return 0; } static inline int nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_EVENTS - const struct net *net = nf_ct_net(ct); - - if (!rcu_access_pointer(net->ct.nf_conntrack_event_cb)) - return 0; - - return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); -#else - return 0; + if (nf_ct_ecache_exist(ct)) + return nf_conntrack_eventmask_report(1 << event, ct, 0, 0); #endif + return 0; } #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -166,6 +143,8 @@ void nf_conntrack_ecache_work(struct net *net, enum nf_ct_ecache_state state); void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); +struct nf_conntrack_net_ecache *nf_conn_pernet_ecache(const struct net *net); + static inline bool nf_conntrack_ecache_dwork_pending(const struct net *net) { return net->ct.ecache_dwork_pending; diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 96635ad2acc7..0b247248b032 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -34,21 +34,11 @@ enum nf_ct_ext_id { NF_CT_EXT_NUM, }; -#define NF_CT_EXT_HELPER_TYPE struct nf_conn_help -#define NF_CT_EXT_NAT_TYPE struct nf_conn_nat -#define NF_CT_EXT_SEQADJ_TYPE struct nf_conn_seqadj -#define NF_CT_EXT_ACCT_TYPE struct nf_conn_acct -#define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache -#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp -#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout -#define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels -#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy -#define NF_CT_EXT_ACT_CT_TYPE struct nf_conn_act_ct_ext - /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { u8 offset[NF_CT_EXT_NUM]; u8 len; + unsigned int gen_id; char data[] __aligned(8); }; @@ -62,17 +52,28 @@ static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id) return (ct->ext && __nf_ct_ext_exist(ct->ext, id)); } -static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id) +void *__nf_ct_ext_find(const struct nf_ct_ext *ext, u8 id); + +static inline void *nf_ct_ext_find(const struct nf_conn *ct, u8 id) { - if (!nf_ct_ext_exist(ct, id)) + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, id)) return NULL; + if (unlikely(ext->gen_id)) + return __nf_ct_ext_find(ext, id); + return (void *)ct->ext + ct->ext->offset[id]; } -#define nf_ct_ext_find(ext, id) \ - ((id##_TYPE *)__nf_ct_ext_find((ext), (id))) /* Add this type, returns pointer to data or NULL. */ void *nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp); +/* ext genid. if ext->id != ext_genid, extensions cannot be used + * anymore unless conntrack has CONFIRMED bit set. + */ +extern atomic_t nf_conntrack_ext_genid; +void nf_ct_ext_bump_genid(void); + #endif /* _NF_CONNTRACK_EXTEND_H */ diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index 3c23298e68ca..66bab6c60d12 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -17,10 +17,18 @@ struct nf_conn_labels { unsigned long bits[NF_CT_LABELS_MAX_SIZE / sizeof(long)]; }; +/* Can't use nf_ct_ext_find(), flow dissector cannot use symbols + * exported by nf_conntrack module. + */ static inline struct nf_conn_labels *nf_ct_labels_find(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_LABELS - return nf_ct_ext_find(ct, NF_CT_EXT_LABELS); + struct nf_ct_ext *ext = ct->ext; + + if (!ext || !__nf_ct_ext_exist(ext, NF_CT_EXT_LABELS)) + return NULL; + + return (void *)ct->ext + ct->ext->offset[NF_CT_EXT_LABELS]; #else return NULL; #endif diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index 3ea94f6f3844..fea258983d23 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -17,14 +17,6 @@ struct nf_ct_timeout { char data[]; }; -struct ctnl_timeout { - struct list_head head; - struct rcu_head rcu_head; - refcount_t refcnt; - char name[CTNL_TIMEOUT_NAME_MAX]; - struct nf_ct_timeout timeout; -}; - struct nf_conn_timeout { struct nf_ct_timeout __rcu *timeout; }; diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h index 9051c3a0c8e7..7c669792fb9c 100644 --- a/include/net/netfilter/nf_reject.h +++ b/include/net/netfilter/nf_reject.h @@ -5,12 +5,28 @@ #include <linux/types.h> #include <uapi/linux/in.h> -static inline bool nf_reject_verify_csum(__u8 proto) +static inline bool nf_reject_verify_csum(struct sk_buff *skb, int dataoff, + __u8 proto) { /* Skip protocols that don't use 16-bit one's complement checksum * of the entire payload. */ switch (proto) { + /* Protocols with optional checksums. */ + case IPPROTO_UDP: { + const struct udphdr *udp_hdr; + struct udphdr _udp_hdr; + + udp_hdr = skb_header_pointer(skb, dataoff, + sizeof(_udp_hdr), + &_udp_hdr); + if (!udp_hdr || udp_hdr->check) + return true; + + return false; + } + case IPPROTO_GRE: + /* Protocols with other integrity checks. */ case IPPROTO_AH: case IPPROTO_ESP: @@ -19,9 +35,6 @@ static inline bool nf_reject_verify_csum(__u8 proto) /* Protocols with partial checksums. */ case IPPROTO_UDPLITE: case IPPROTO_DCCP: - - /* Protocols with optional checksums. */ - case IPPROTO_GRE: return false; } return true; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 0294f3d473af..0677cd3de034 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -93,14 +93,9 @@ struct nf_ip_net { #endif }; -struct ct_pcpu { - spinlock_t lock; - struct hlist_nulls_head unconfirmed; - struct hlist_nulls_head dying; -}; - struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS + bool ctnetlink_has_listener; bool ecache_dwork_pending; #endif u8 sysctl_log_invalid; /* Log invalid packets */ @@ -110,7 +105,6 @@ struct netns_ct { u8 sysctl_tstamp; u8 sysctl_checksum; - struct ct_pcpu __percpu *pcpu_lists; struct ip_conntrack_stat __percpu *stat; struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; struct nf_ip_net nf_ct_proto; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index ea5fb70e5101..813c93499f20 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -117,6 +117,10 @@ struct page_pool_stats { struct page_pool_recycle_stats recycle_stats; }; +int page_pool_ethtool_stats_get_count(void); +u8 *page_pool_ethtool_stats_get_strings(u8 *data); +u64 *page_pool_ethtool_stats_get(u64 *data, void *stats); + /* * Drivers that wish to harvest page pool stats and report them to users * (perhaps via ethtool, debugfs, or another mechanism) can allocate a @@ -124,6 +128,23 @@ struct page_pool_stats { */ bool page_pool_get_stats(struct page_pool *pool, struct page_pool_stats *stats); +#else + +static inline int page_pool_ethtool_stats_get_count(void) +{ + return 0; +} + +static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data) +{ + return data; +} + +static inline u64 *page_pool_ethtool_stats_get(u64 *data, void *stats) +{ + return data; +} + #endif struct page_pool { diff --git a/include/net/ping.h b/include/net/ping.h index 2fe78874318c..e4ff3911cbf5 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -71,12 +71,12 @@ void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); -int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, +int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 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_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -bool ping_rcv(struct sk_buff *skb); +enum skb_drop_reason ping_rcv(struct sk_buff *skb); #ifdef CONFIG_PROC_FS void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index a3b57a93228a..8cf001aed858 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -547,10 +547,12 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } int tc_setup_offload_action(struct flow_action *flow_action, - const struct tcf_exts *exts); + const struct tcf_exts *exts, + struct netlink_ext_ack *extack); void tc_cleanup_offload_action(struct flow_action *flow_action); int tc_setup_action(struct flow_action *flow_action, - struct tc_action *actions[]); + struct tc_action *actions[], + struct netlink_ext_ack *extack); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); diff --git a/include/net/route.h b/include/net/route.h index 25404fc2b483..991a3985712d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -43,6 +43,19 @@ #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) +static inline __u8 ip_sock_rt_scope(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_LOCALROUTE)) + return RT_SCOPE_LINK; + + return RT_SCOPE_UNIVERSE; +} + +static inline __u8 ip_sock_rt_tos(const struct sock *sk) +{ + return RT_TOS(inet_sk(sk)->tos); +} + struct ip_tunnel_info; struct fib_nh; struct fib_info; @@ -289,39 +302,38 @@ static inline char rt_tos2priority(u8 tos) * ip_route_newports() calls. */ -static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 src, - u32 tos, int oif, u8 protocol, +static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, - struct sock *sk) + const struct sock *sk) { __u8 flow_flags = 0; if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, - protocol, flow_flags, dst, src, dport, sport, - sk->sk_uid); + flowi4_init_output(fl4, oif, sk->sk_mark, ip_sock_rt_tos(sk), + ip_sock_rt_scope(sk), protocol, flow_flags, dst, + src, dport, sport, sk->sk_uid); } -static inline struct rtable *ip_route_connect(struct flowi4 *fl4, - __be32 dst, __be32 src, u32 tos, - int oif, u8 protocol, +static inline struct rtable *ip_route_connect(struct flowi4 *fl4, __be32 dst, + __be32 src, int oif, u8 protocol, __be16 sport, __be16 dport, struct sock *sk) { struct net *net = sock_net(sk); struct rtable *rt; - ip_route_connect_init(fl4, dst, src, tos, oif, protocol, - sport, dport, sk); + ip_route_connect_init(fl4, dst, src, oif, protocol, sport, dport, sk); if (!dst || !src) { rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) return rt; ip_rt_put(rt); - flowi4_update_output(fl4, oif, tos, fl4->daddr, fl4->saddr); + flowi4_update_output(fl4, oif, fl4->flowi4_tos, fl4->daddr, + fl4->saddr); } security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4)); return ip_route_output_flow(net, fl4, sk); diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 9f48733bfd21..bf8bb3357825 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -10,9 +10,23 @@ typedef int (*rtnl_doit_func)(struct sk_buff *, struct nlmsghdr *, typedef int (*rtnl_dumpit_func)(struct sk_buff *, struct netlink_callback *); enum rtnl_link_flags { - RTNL_FLAG_DOIT_UNLOCKED = 1, + RTNL_FLAG_DOIT_UNLOCKED = BIT(0), + RTNL_FLAG_BULK_DEL_SUPPORTED = BIT(1), }; +enum rtnl_kinds { + RTNL_KIND_NEW, + RTNL_KIND_DEL, + RTNL_KIND_GET, + RTNL_KIND_SET +}; +#define RTNL_KIND_MASK 0x3 + +static inline enum rtnl_kinds rtnl_msgtype_kind(int msgtype) +{ + return msgtype & RTNL_KIND_MASK; +} + void rtnl_register(int protocol, int msgtype, rtnl_doit_func, rtnl_dumpit_func, unsigned int flags); int rtnl_register_module(struct module *owner, int protocol, int msgtype, diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index bf3716fe83e0..a04999ee99b0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -103,7 +103,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct sctp_association *asoc); extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); -struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *); +struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int *); typedef int (*sctp_callback_t)(struct sctp_endpoint *, struct sctp_transport *, void *); void sctp_transport_walk_start(struct rhashtable_iter *iter); diff --git a/include/net/sock.h b/include/net/sock.h index c4b91fc19b9c..c585ef6565d9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -161,9 +161,6 @@ typedef __u64 __bitwise __addrpair; * for struct sock and struct inet_timewait_sock. */ struct sock_common { - /* skc_daddr and skc_rcv_saddr must be grouped on a 8 bytes aligned - * address on 64bit arches : cf INET_MATCH() - */ union { __addrpair skc_addrpair; struct { @@ -292,7 +289,6 @@ struct sk_filter; * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held - * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, @@ -352,6 +348,7 @@ struct sk_filter; * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference + * @sk_bind2_node: bind node in the bhash2 table */ struct sock { /* @@ -417,7 +414,6 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; - struct llist_head defer_list; #define sk_rmem_alloc sk_backlog.rmem_alloc @@ -542,6 +538,7 @@ struct sock { #endif struct rcu_head sk_rcu; netns_tracker ns_tracker; + struct hlist_node sk_bind2_node; }; enum sk_pacing { @@ -822,6 +819,16 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_add_head(&sk->sk_bind_node, list); } +static inline void __sk_del_bind2_node(struct sock *sk) +{ + __hlist_del(&sk->sk_bind2_node); +} + +static inline void sk_add_bind2_node(struct sock *sk, struct hlist_head *list) +{ + hlist_add_head(&sk->sk_bind2_node, list); +} + #define sk_for_each(__sk, list) \ hlist_for_each_entry(__sk, list, sk_node) #define sk_for_each_rcu(__sk, list) \ @@ -839,6 +846,8 @@ static inline void sk_add_bind_node(struct sock *sk, hlist_for_each_entry_safe(__sk, tmp, list, sk_node) #define sk_for_each_bound(__sk, list) \ hlist_for_each_entry(__sk, list, sk_bind_node) +#define sk_for_each_bound_bhash2(__sk, list) \ + hlist_for_each_entry(__sk, list, sk_bind2_node) /** * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset @@ -895,6 +904,7 @@ enum sock_flags { SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ + SOCK_RCVMARK, /* Receive SO_MARK ancillary data with packet */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -1202,8 +1212,7 @@ struct proto { int (*sendmsg)(struct sock *sk, struct msghdr *msg, size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, - int *addr_len); + size_t len, int flags, int *addr_len); int (*sendpage)(struct sock *sk, struct page *page, int offset, size_t size, int flags); int (*bind)(struct sock *sk, @@ -1825,11 +1834,17 @@ int sock_getsockopt(struct socket *sock, int level, int op, char __user *optval, int __user *optlen); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32); -struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, - int noblock, int *errcode); struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, unsigned long data_len, int noblock, int *errcode, int max_page_order); + +static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk, + unsigned long size, + int noblock, int *errcode) +{ + return sock_alloc_send_pskb(sk, size, 0, noblock, errcode, 0); +} + void *sock_kmalloc(struct sock *sk, int size, gfp_t priority); void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); @@ -2392,7 +2407,14 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, void (*destructor)(struct sock *sk, struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); + +int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); + +static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + return sock_queue_rcv_skb_reason(sk, skb, NULL); +} int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb); struct sk_buff *sock_dequeue_err_skb(struct sock *sk); @@ -2643,20 +2665,21 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) __sock_recv_wifi_status(msg, sk, skb); } -void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb); +void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); #define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC) -static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, - struct sk_buff *skb) +static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) { -#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_RCVTSTAMP)) +#define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVMARK)) #define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \ SOF_TIMESTAMPING_RAW_HARDWARE) - if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) - __sock_recv_ts_and_drops(msg, sk, skb); + if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY) + __sock_recv_cmsgs(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) @@ -2866,13 +2889,14 @@ static inline void sk_pacing_shift_update(struct sock *sk, int val) */ static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) { + int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); int mdif; - if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + if (!bound_dev_if || bound_dev_if == dif) return true; mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); - if (mdif && mdif == sk->sk_bound_dev_if) + if (mdif && mdif == bound_dev_if) return true; return false; diff --git a/include/net/strparser.h b/include/net/strparser.h index 732b7097d78e..a191486eb1e4 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -70,6 +70,10 @@ struct sk_skb_cb { * when dst_reg == src_reg. */ u64 temp_reg; + struct tls_msg { + u8 control; + u8 decrypted; + } tls; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index eb8f01c819e6..832efd40e023 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -59,4 +59,19 @@ static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a) return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK; } +static inline bool is_tcf_gact_continue(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_UNSPEC, false); +} + +static inline bool is_tcf_gact_reclassify(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_RECLASSIFY, false); +} + +static inline bool is_tcf_gact_pipe(const struct tc_action *a) +{ + return __is_tcf_gact_act(a, TC_ACT_PIPE, false); +} + #endif /* __NET_TC_GACT_H */ diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 00bfee70609e..dc1079f28e13 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -17,6 +17,7 @@ struct tcf_skbedit_params { u32 mark; u32 mask; u16 queue_mapping; + u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; @@ -94,4 +95,16 @@ static inline u32 tcf_skbedit_priority(const struct tc_action *a) return priority; } +/* Return true iff action is queue_mapping */ +static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); +} + +/* Return true iff action is inheritdsfield */ +static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) +{ + return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); +} + #endif /* __NET_TC_SKBEDIT_H */ diff --git a/include/net/tcp.h b/include/net/tcp.h index cc1295037533..1e99f5c61f84 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -407,7 +407,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); -int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, +int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); int tcp_set_window_clamp(struct sock *sk, int val); @@ -1142,15 +1142,6 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } -static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (icsk->icsk_ca_ops->set_state) - icsk->icsk_ca_ops->set_state(sk, ca_state); - icsk->icsk_ca_state = ca_state; -} - static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1159,6 +1150,9 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) icsk->icsk_ca_ops->cwnd_event(sk, event); } +/* From tcp_cong.c */ +void tcp_set_ca_state(struct sock *sk, const u8 ca_state); + /* From tcp_rate.c */ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, @@ -1215,9 +1209,20 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) #define TCP_INFINITE_SSTHRESH 0x7fffffff +static inline u32 tcp_snd_cwnd(const struct tcp_sock *tp) +{ + return tp->snd_cwnd; +} + +static inline void tcp_snd_cwnd_set(struct tcp_sock *tp, u32 val) +{ + WARN_ON_ONCE((int)val <= 0); + tp->snd_cwnd = val; +} + static inline bool tcp_in_slow_start(const struct tcp_sock *tp) { - return tp->snd_cwnd < tp->snd_ssthresh; + return tcp_snd_cwnd(tp) < tp->snd_ssthresh; } static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) @@ -1243,8 +1248,8 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, - ((tp->snd_cwnd >> 1) + - (tp->snd_cwnd >> 2))); + ((tcp_snd_cwnd(tp) >> 1) + + (tcp_snd_cwnd(tp) >> 2))); } /* Use define here intentionally to get WARN_ON location shown at the caller */ @@ -1286,7 +1291,7 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk) /* If in slow start, ensure cwnd grows to twice what was ACKed. */ if (tcp_in_slow_start(tp)) - return tp->snd_cwnd < 2 * tp->max_packets_out; + return tcp_snd_cwnd(tp) < 2 * tp->max_packets_out; return tp->is_cwnd_limited; } @@ -1378,18 +1383,6 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); -#ifdef CONFIG_INET -void __sk_defer_free_flush(struct sock *sk); - -static inline void sk_defer_free_flush(struct sock *sk) -{ - if (llist_empty(&sk->defer_list)) - return; - __sk_defer_free_flush(sk); -} -#else -static inline void sk_defer_free_flush(struct sock *sk) {} -#endif int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); diff --git a/include/net/tls.h b/include/net/tls.h index b6968a5b5538..8017f1703447 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -64,6 +64,7 @@ #define TLS_AAD_SPACE_SIZE 13 #define MAX_IV_SIZE 16 +#define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. @@ -117,11 +118,6 @@ struct tls_rec { u8 aead_req_ctx[]; }; -struct tls_msg { - struct strp_msg rxm; - u8 control; -}; - struct tx_work { struct delayed_work work; struct sock *sk; @@ -152,13 +148,10 @@ struct tls_sw_context_rx { void (*saved_data_ready)(struct sock *sk); struct sk_buff *recv_pkt; - u8 control; u8 async_capable:1; - u8 decrypted:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; - bool async_notify; }; struct tls_record_info { @@ -245,6 +238,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; + u8 zerocopy_sendfile:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); @@ -378,7 +372,7 @@ void tls_sw_free_resources_rx(struct sock *sk); void tls_sw_release_resources_rx(struct sock *sk); void tls_sw_free_ctx_rx(struct tls_context *tls_ctx); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); + int flags, int *addr_len); bool tls_sw_sock_is_readable(struct sock *sk); ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, @@ -411,7 +405,9 @@ void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); static inline struct tls_msg *tls_msg(struct sk_buff *skb) { - return (struct tls_msg *)strp_msg(skb); + struct sk_skb_cb *scb = (struct sk_skb_cb *)skb->cb; + + return &scb->tls; } static inline bool tls_is_partially_sent_record(struct tls_context *ctx) diff --git a/include/net/udp.h b/include/net/udp.h index f1c2a88c9005..b83a00330566 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -250,14 +250,14 @@ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb); void udp_skb_destructor(struct sock *sk, struct sk_buff *skb); -struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *off, int *err); +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off, + int *err); static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *err) + int *err) { int off = 0; - return __skb_recv_udp(sk, flags, noblock, &off, err); + return __skb_recv_udp(sk, flags, &off, err); } int udp_v4_early_demux(struct sk_buff *skb); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d2efddce65d4..c39d910d4b45 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -126,13 +126,17 @@ struct xfrm_state_walk { struct xfrm_address_filter *filter; }; -struct xfrm_state_offload { +enum { + XFRM_DEV_OFFLOAD_IN = 1, + XFRM_DEV_OFFLOAD_OUT, +}; + +struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; - unsigned int num_exthdrs; - u8 flags; + u8 dir : 2; }; struct xfrm_mode { @@ -247,7 +251,7 @@ struct xfrm_state { struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; - struct xfrm_state_offload xso; + struct xfrm_dev_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; @@ -1006,7 +1010,7 @@ struct xfrm_offload { #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 -#define XFRM_ESP_NO_TRAILER 64 +/* 64 is free */ #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 @@ -1878,7 +1882,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); @@ -1904,7 +1908,7 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) static inline void xfrm_dev_state_delete(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; if (xso->dev) xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); @@ -1912,7 +1916,7 @@ static inline void xfrm_dev_state_delete(struct xfrm_state *x) static inline void xfrm_dev_state_free(struct xfrm_state *x) { - struct xfrm_state_offload *xso = &x->xso; + struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { |