diff options
Diffstat (limited to 'include/net')
52 files changed, 864 insertions, 316 deletions
diff --git a/include/net/act_api.h b/include/net/act_api.h index 05c7df41d737..dbc795ec659e 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -194,35 +194,5 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, #endif } -#ifdef CONFIG_NET_CLS_ACT -int tc_setup_cb_egdev_register(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv); -void tc_setup_cb_egdev_unregister(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv); -int tc_setup_cb_egdev_call(const struct net_device *dev, - enum tc_setup_type type, void *type_data, - bool err_stop); -#else -static inline -int tc_setup_cb_egdev_register(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ - return 0; -} - -static inline -void tc_setup_cb_egdev_unregister(const struct net_device *dev, - tc_setup_cb_t *cb, void *cb_priv) -{ -} - -static inline -int tc_setup_cb_egdev_call(const struct net_device *dev, - enum tc_setup_type type, void *type_data, - bool err_stop) -{ - return 0; -} -#endif #endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1fa41b7a1be3..e0c41eb1c860 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -777,8 +777,10 @@ struct cfg80211_crypto_settings { * @probe_resp: probe response template (AP mode only) * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) - * @lci: LCI subelement content - * @civicloc: Civic location subelement content + * @lci: Measurement Report element content, starting with Measurement Token + * (measurement type 8) + * @civicloc: Measurement Report element content, starting with Measurement + * Token (measurement type 11) * @lci_len: LCI data length * @civicloc_len: Civic location data length */ @@ -1296,6 +1298,7 @@ struct cfg80211_tid_stats { * @rx_beacon: number of beacons received from this peer * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received * from this peer + * @connected_to_gate: true if mesh STA has a path to mesh gate * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. @@ -1350,6 +1353,8 @@ struct station_info { u64 rx_beacon; u64 rx_duration; u8 rx_beacon_signal_avg; + u8 connected_to_gate; + struct cfg80211_tid_stats *pertid; s8 ack_signal; s8 avg_ack_signal; @@ -1559,6 +1564,10 @@ struct bss_parameters { * @plink_timeout: If no tx activity is seen from a STA we've established * peering with for longer than this time (in seconds), then remove it * from the STA's list of peers. Default is 30 minutes. + * @dot11MeshConnectedToMeshGate: if set to true, advertise that this STA is + * connected to a mesh gate in mesh formation info. If false, the + * value in mesh formation is determined by the presence of root paths + * in the mesh path table */ struct mesh_config { u16 dot11MeshRetryTimeout; @@ -1578,6 +1587,7 @@ struct mesh_config { u16 dot11MeshHWMPperrMinInterval; u16 dot11MeshHWMPnetDiameterTraversalTime; u8 dot11MeshHWMPRootMode; + bool dot11MeshConnectedToMeshGate; u16 dot11MeshHWMPRannInterval; bool dot11MeshGateAnnouncementProtocol; bool dot11MeshForwarding; @@ -2815,7 +2825,7 @@ struct cfg80211_external_auth_params { }; /** - * cfg80211_ftm_responder_stats - FTM responder statistics + * struct cfg80211_ftm_responder_stats - FTM responder statistics * * @filled: bitflag of flags using the bits of &enum nl80211_ftm_stats to * indicate the relevant values in this struct for them @@ -2849,6 +2859,190 @@ struct cfg80211_ftm_responder_stats { }; /** + * struct cfg80211_pmsr_ftm_result - FTM result + * @failure_reason: if this measurement failed (PMSR status is + * %NL80211_PMSR_STATUS_FAILURE), this gives a more precise + * reason than just "failure" + * @burst_index: if reporting partial results, this is the index + * in [0 .. num_bursts-1] of the burst that's being reported + * @num_ftmr_attempts: number of FTM request frames transmitted + * @num_ftmr_successes: number of FTM request frames acked + * @busy_retry_time: if failure_reason is %NL80211_PMSR_FTM_FAILURE_PEER_BUSY, + * fill this to indicate in how many seconds a retry is deemed possible + * by the responder + * @num_bursts_exp: actual number of bursts exponent negotiated + * @burst_duration: actual burst duration negotiated + * @ftms_per_burst: actual FTMs per burst negotiated + * @lci_len: length of LCI information (if present) + * @civicloc_len: length of civic location information (if present) + * @lci: LCI data (may be %NULL) + * @civicloc: civic location data (may be %NULL) + * @rssi_avg: average RSSI over FTM action frames reported + * @rssi_spread: spread of the RSSI over FTM action frames reported + * @tx_rate: bitrate for transmitted FTM action frame response + * @rx_rate: bitrate of received FTM action frame + * @rtt_avg: average of RTTs measured (must have either this or @dist_avg) + * @rtt_variance: variance of RTTs measured (note that standard deviation is + * the square root of the variance) + * @rtt_spread: spread of the RTTs measured + * @dist_avg: average of distances (mm) measured + * (must have either this or @rtt_avg) + * @dist_variance: variance of distances measured (see also @rtt_variance) + * @dist_spread: spread of distances measured (see also @rtt_spread) + * @num_ftmr_attempts_valid: @num_ftmr_attempts is valid + * @num_ftmr_successes_valid: @num_ftmr_successes is valid + * @rssi_avg_valid: @rssi_avg is valid + * @rssi_spread_valid: @rssi_spread is valid + * @tx_rate_valid: @tx_rate is valid + * @rx_rate_valid: @rx_rate is valid + * @rtt_avg_valid: @rtt_avg is valid + * @rtt_variance_valid: @rtt_variance is valid + * @rtt_spread_valid: @rtt_spread is valid + * @dist_avg_valid: @dist_avg is valid + * @dist_variance_valid: @dist_variance is valid + * @dist_spread_valid: @dist_spread is valid + */ +struct cfg80211_pmsr_ftm_result { + const u8 *lci; + const u8 *civicloc; + unsigned int lci_len; + unsigned int civicloc_len; + enum nl80211_peer_measurement_ftm_failure_reasons failure_reason; + u32 num_ftmr_attempts, num_ftmr_successes; + s16 burst_index; + u8 busy_retry_time; + u8 num_bursts_exp; + u8 burst_duration; + u8 ftms_per_burst; + s32 rssi_avg; + s32 rssi_spread; + struct rate_info tx_rate, rx_rate; + s64 rtt_avg; + s64 rtt_variance; + s64 rtt_spread; + s64 dist_avg; + s64 dist_variance; + s64 dist_spread; + + u16 num_ftmr_attempts_valid:1, + num_ftmr_successes_valid:1, + rssi_avg_valid:1, + rssi_spread_valid:1, + tx_rate_valid:1, + rx_rate_valid:1, + rtt_avg_valid:1, + rtt_variance_valid:1, + rtt_spread_valid:1, + dist_avg_valid:1, + dist_variance_valid:1, + dist_spread_valid:1; +}; + +/** + * struct cfg80211_pmsr_result - peer measurement result + * @addr: address of the peer + * @host_time: host time (use ktime_get_boottime() adjust to the time when the + * measurement was made) + * @ap_tsf: AP's TSF at measurement time + * @status: status of the measurement + * @final: if reporting partial results, mark this as the last one; if not + * reporting partial results always set this flag + * @ap_tsf_valid: indicates the @ap_tsf value is valid + * @type: type of the measurement reported, note that we only support reporting + * one type at a time, but you can report multiple results separately and + * they're all aggregated for userspace. + */ +struct cfg80211_pmsr_result { + u64 host_time, ap_tsf; + enum nl80211_peer_measurement_status status; + + u8 addr[ETH_ALEN]; + + u8 final:1, + ap_tsf_valid:1; + + enum nl80211_peer_measurement_type type; + + union { + struct cfg80211_pmsr_ftm_result ftm; + }; +}; + +/** + * struct cfg80211_pmsr_ftm_request_peer - FTM request data + * @requested: indicates FTM is requested + * @preamble: frame preamble to use + * @burst_period: burst period to use + * @asap: indicates to use ASAP mode + * @num_bursts_exp: number of bursts exponent + * @burst_duration: burst duration + * @ftms_per_burst: number of FTMs per burst + * @ftmr_retries: number of retries for FTM request + * @request_lci: request LCI information + * @request_civicloc: request civic location information + * + * See also nl80211 for the respective attribute documentation. + */ +struct cfg80211_pmsr_ftm_request_peer { + enum nl80211_preamble preamble; + u16 burst_period; + u8 requested:1, + asap:1, + request_lci:1, + request_civicloc:1; + u8 num_bursts_exp; + u8 burst_duration; + u8 ftms_per_burst; + u8 ftmr_retries; +}; + +/** + * struct cfg80211_pmsr_request_peer - peer data for a peer measurement request + * @addr: MAC address + * @chandef: channel to use + * @report_ap_tsf: report the associated AP's TSF + * @ftm: FTM data, see &struct cfg80211_pmsr_ftm_request_peer + */ +struct cfg80211_pmsr_request_peer { + u8 addr[ETH_ALEN]; + struct cfg80211_chan_def chandef; + u8 report_ap_tsf:1; + struct cfg80211_pmsr_ftm_request_peer ftm; +}; + +/** + * struct cfg80211_pmsr_request - peer measurement request + * @cookie: cookie, set by cfg80211 + * @nl_portid: netlink portid - used by cfg80211 + * @drv_data: driver data for this request, if required for aborting, + * not otherwise freed or anything by cfg80211 + * @mac_addr: MAC address used for (randomised) request + * @mac_addr_mask: MAC address mask used for randomisation, bits that + * are 0 in the mask should be randomised, bits that are 1 should + * be taken from the @mac_addr + * @list: used by cfg80211 to hold on to the request + * @timeout: timeout (in milliseconds) for the whole operation, if + * zero it means there's no timeout + * @n_peers: number of peers to do measurements with + * @peers: per-peer measurement request data + */ +struct cfg80211_pmsr_request { + u64 cookie; + void *drv_data; + u32 n_peers; + u32 nl_portid; + + u32 timeout; + + u8 mac_addr[ETH_ALEN] __aligned(2); + u8 mac_addr_mask[ETH_ALEN] __aligned(2); + + struct list_head list; + + struct cfg80211_pmsr_request_peer peers[]; +}; + +/** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks @@ -3183,6 +3377,8 @@ struct cfg80211_ftm_responder_stats { * * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. * Statistics should be cumulative, currently no way to reset is provided. + * @start_pmsr: start peer measurement (e.g. FTM) + * @abort_pmsr: abort peer measurement */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -3492,6 +3688,11 @@ struct cfg80211_ops { int (*get_ftm_responder_stats)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats); + + int (*start_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_pmsr_request *request); + void (*abort_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev, + struct cfg80211_pmsr_request *request); }; /* @@ -3864,6 +4065,42 @@ struct wiphy_iftype_ext_capab { }; /** + * struct cfg80211_pmsr_capabilities - cfg80211 peer measurement capabilities + * @max_peers: maximum number of peers in a single measurement + * @report_ap_tsf: can report assoc AP's TSF for radio resource measurement + * @randomize_mac_addr: can randomize MAC address for measurement + * @ftm.supported: FTM measurement is supported + * @ftm.asap: ASAP-mode is supported + * @ftm.non_asap: non-ASAP-mode is supported + * @ftm.request_lci: can request LCI data + * @ftm.request_civicloc: can request civic location data + * @ftm.preambles: bitmap of preambles supported (&enum nl80211_preamble) + * @ftm.bandwidths: bitmap of bandwidths supported (&enum nl80211_chan_width) + * @ftm.max_bursts_exponent: maximum burst exponent supported + * (set to -1 if not limited; note that setting this will necessarily + * forbid using the value 15 to let the responder pick) + * @ftm.max_ftms_per_burst: maximum FTMs per burst supported (set to 0 if + * not limited) + */ +struct cfg80211_pmsr_capabilities { + unsigned int max_peers; + u8 report_ap_tsf:1, + randomize_mac_addr:1; + + struct { + u32 preambles; + u32 bandwidths; + s8 max_bursts_exponent; + u8 max_ftms_per_burst; + u8 supported:1, + asap:1, + non_asap:1, + request_lci:1, + request_civicloc:1; + } ftm; +}; + +/** * struct wiphy - wireless hardware description * @reg_notifier: the driver's regulatory notification callback, * note that if your driver uses wiphy_apply_custom_regulatory() @@ -4027,6 +4264,8 @@ struct wiphy_iftype_ext_capab { * @txq_limit: configuration of internal TX queue frame limit * @txq_memory_limit: configuration internal TX queue memory limit * @txq_quantum: configuration of internal TX queue scheduler quantum + * + * @pmsr_capa: peer measurement capabilities */ struct wiphy { /* assign these fields before you register the wiphy */ @@ -4163,6 +4402,8 @@ struct wiphy { u32 txq_memory_limit; u32 txq_quantum; + const struct cfg80211_pmsr_capabilities *pmsr_capa; + char priv[0] __aligned(NETDEV_ALIGN); }; @@ -4365,6 +4606,9 @@ struct cfg80211_cqm_config; * @owner_nlportid: (private) owner socket port ID * @nl_owner_dead: (private) owner socket went away * @cqm_config: (private) nl80211 RSSI monitor state + * @pmsr_list: (private) peer measurement requests + * @pmsr_lock: (private) peer measurements requests/results lock + * @pmsr_free_wk: (private) peer measurements cleanup work */ struct wireless_dev { struct wiphy *wiphy; @@ -4436,6 +4680,10 @@ struct wireless_dev { #endif struct cfg80211_cqm_config *cqm_config; + + struct list_head pmsr_list; + spinlock_t pmsr_lock; + struct work_struct pmsr_free_wk; }; static inline u8 *wdev_address(struct wireless_dev *wdev) @@ -5328,7 +5576,8 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * cfg80211 then sends a notification to userspace. */ void cfg80211_notify_new_peer_candidate(struct net_device *dev, - const u8 *macaddr, const u8 *ie, u8 ie_len, gfp_t gfp); + const u8 *macaddr, const u8 *ie, u8 ie_len, + int sig_dbm, gfp_t gfp); /** * DOC: RFkill integration @@ -6630,6 +6879,31 @@ int cfg80211_external_auth_request(struct net_device *netdev, struct cfg80211_external_auth_params *params, gfp_t gfp); +/** + * cfg80211_pmsr_report - report peer measurement result data + * @wdev: the wireless device reporting the measurement + * @req: the original measurement request + * @result: the result data + * @gfp: allocation flags + */ +void cfg80211_pmsr_report(struct wireless_dev *wdev, + struct cfg80211_pmsr_request *req, + struct cfg80211_pmsr_result *result, + gfp_t gfp); + +/** + * cfg80211_pmsr_complete - report peer measurement completed + * @wdev: the wireless device reporting the measurement + * @req: the original measurement request + * @gfp: allocation flags + * + * Report that the entire measurement completed, after this + * the request pointer will no longer be valid. + */ +void cfg80211_pmsr_complete(struct wireless_dev *wdev, + struct cfg80211_pmsr_request *req, + gfp_t gfp); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/net/devlink.h b/include/net/devlink.h index 45db0c79462d..67f4293bc970 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -365,6 +365,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -392,6 +393,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_NAME "msix_vec_per_pf_min" #define DEVLINK_PARAM_GENERIC_MSIX_VEC_PER_PF_MIN_TYPE DEVLINK_PARAM_TYPE_U32 +#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy" +#define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/include/net/dsa.h b/include/net/dsa.h index 23690c44e167..b3eefe8e18fd 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -36,7 +36,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, DSA_TAG_PROTO_GSWIP, - DSA_TAG_PROTO_KSZ, + DSA_TAG_PROTO_KSZ9477, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_QCA, @@ -113,6 +113,7 @@ struct dsa_device_ops { struct packet_type *pt); int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + unsigned int overhead; }; struct dsa_switch_tree { diff --git a/include/net/flow.h b/include/net/flow.h index 8ce21793094e..93f2c9a0f098 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -38,8 +38,8 @@ struct flowi_common { #define FLOWI_FLAG_KNOWN_NH 0x02 #define FLOWI_FLAG_SKIP_NH_OIF 0x04 __u32 flowic_secid; - struct flowi_tunnel flowic_tun_key; kuid_t flowic_uid; + struct flowi_tunnel flowic_tun_key; }; union flowi_uli { diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 6a4586dcdede..2b26979efb48 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -209,8 +209,8 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_ETH_ADDRS, /* struct flow_dissector_key_eth_addrs */ FLOW_DISSECTOR_KEY_TIPC, /* struct flow_dissector_key_tipc */ FLOW_DISSECTOR_KEY_ARP, /* struct flow_dissector_key_arp */ - FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_flow_vlan */ - FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_flow_tags */ + FLOW_DISSECTOR_KEY_VLAN, /* struct flow_dissector_key_vlan */ + FLOW_DISSECTOR_KEY_FLOW_LABEL, /* struct flow_dissector_key_tags */ FLOW_DISSECTOR_KEY_GRE_KEYID, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_MPLS_ENTROPY, /* struct flow_dissector_key_keyid */ FLOW_DISSECTOR_KEY_ENC_KEYID, /* struct flow_dissector_key_keyid */ @@ -221,7 +221,7 @@ enum flow_dissector_key_id { FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */ FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */ FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */ - FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */ + FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_vlan */ FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */ FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */ diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 946bd53a9f81..ca23860adbb9 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -10,7 +10,7 @@ struct gnet_stats_basic_cpu { struct gnet_stats_basic_packed bstats; struct u64_stats_sync syncp; -}; +} __aligned(2 * sizeof(u64)); struct net_rate_estimator; diff --git a/include/net/geneve.h b/include/net/geneve.h index a7600ed55ea3..fc6a7e0a874a 100644 --- a/include/net/geneve.h +++ b/include/net/geneve.h @@ -60,6 +60,12 @@ struct genevehdr { struct geneve_opt options[]; }; +static inline bool netif_is_geneve(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "geneve"); +} + #ifdef CONFIG_INET struct net_device *geneve_dev_create_fb(struct net *net, const char *name, u8 name_assign_type, u16 dst_port); diff --git a/include/net/gre.h b/include/net/gre.h index 797142eee9cd..b60f212c16c6 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -37,8 +37,17 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs); -bool is_gretap_dev(const struct net_device *dev); -bool is_ip6gretap_dev(const struct net_device *dev); +static inline bool netif_is_gretap(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "gretap"); +} + +static inline bool netif_is_ip6gretap(const struct net_device *dev) +{ + return dev->rtnl_link_ops && + !strcmp(dev->rtnl_link_ops->kind, "ip6gretap"); +} static inline int gre_calc_hlen(__be16 o_flags) { diff --git a/include/net/icmp.h b/include/net/icmp.h index 3ef2743a8eec..6ac3a5bd0117 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -41,7 +41,7 @@ struct net; void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info); int icmp_rcv(struct sk_buff *skb); -void icmp_err(struct sk_buff *skb, u32 info); +int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); void icmp_out_count(struct net *net, unsigned char type); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 6e91e38a31da..9db98af46985 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk); ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \ ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* _INET6_HASHTABLES_H */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 3ca969cbd161..975901a95c0f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -2,6 +2,8 @@ #ifndef _INET_COMMON_H #define _INET_COMMON_H +#include <linux/indirect_call_wrapper.h> + extern const struct proto_ops inet_stream_ops; extern const struct proto_ops inet_dgram_ops; @@ -54,4 +56,11 @@ static inline void inet_ctl_sock_destroy(struct sock *sk) sock_release(sk->sk_socket); } +#define indirect_call_gro_receive(f2, f1, cb, head, skb) \ +({ \ + unlikely(gro_recursion_inc_test(skb)) ? \ + NAPI_GRO_CB(skb)->flush |= 1, NULL : \ + INDIRECT_CALL_2(cb, f2, f1, head, skb); \ +}) + #endif diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 9141e95529e7..babb14136705 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -79,6 +79,7 @@ struct inet_ehash_bucket { struct inet_bind_bucket { possible_net_t ib_net; + int l3mdev; unsigned short port; signed char fastreuse; signed char fastreuseport; @@ -188,10 +189,21 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo) hashinfo->ehash_locks = NULL; } +static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, - const unsigned short snum); + const unsigned short snum, int l3mdev); void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb); @@ -225,6 +237,7 @@ void inet_hashinfo2_init(struct inet_hashinfo *h, const char *name, unsigned long numentries, int scale, unsigned long low_limit, unsigned long high_limit); +int inet_hashinfo2_init_mod(struct inet_hashinfo *h); bool inet_ehash_insert(struct sock *sk, struct sock *osk); bool inet_ehash_nolisten(struct sock *sk, struct sock *osk); @@ -282,9 +295,8 @@ static inline struct sock *inet_lookup_listener(struct net *net, #define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \ (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_addrpair == (__cookie)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__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) \ @@ -294,9 +306,8 @@ static inline struct sock *inet_lookup_listener(struct net *net, (((__sk)->sk_portpair == (__ports)) && \ ((__sk)->sk_daddr == (__saddr)) && \ ((__sk)->sk_rcv_saddr == (__daddr)) && \ - (!(__sk)->sk_bound_dev_if || \ - ((__sk)->sk_bound_dev_if == (__dif)) || \ - ((__sk)->sk_bound_dev_if == (__sdif))) && \ + (((__sk)->sk_bound_dev_if == (__dif)) || \ + ((__sk)->sk_bound_dev_if == (__sdif))) && \ net_eq(sock_net(__sk), (__net))) #endif /* 64-bit arch */ diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index a80fd0ac4563..e8eef85006aa 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -130,6 +130,27 @@ static inline int inet_request_bound_dev_if(const struct sock *sk, return sk->sk_bound_dev_if; } +static inline int inet_sk_bound_l3mdev(const struct sock *sk) +{ +#ifdef CONFIG_NET_L3_MASTER_DEV + struct net *net = sock_net(sk); + + if (!net->ipv4.sysctl_tcp_l3mdev_accept) + return l3mdev_master_ifindex_by_index(net, + sk->sk_bound_dev_if); +#endif + + return 0; +} + +static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if, + int dif, int sdif) +{ + if (!bound_dev_if) + return !sdif || l3mdev_accept; + return bound_dev_if == dif || bound_dev_if == sdif; +} + struct inet_cork { unsigned int flags; __be32 addr; diff --git a/include/net/ip.h b/include/net/ip.h index 72593e171d14..8866bfce6121 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -155,6 +155,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, void ip_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip_local_deliver(struct sk_buff *skb); +void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto); int ip_mr_input(struct sk_buff *skb); int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -421,7 +422,8 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, } struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx, - int fc_mx_len); + int fc_mx_len, + struct netlink_ext_ack *extack); static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics) { if (fib_metrics != &dst_default_metrics && diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 236e40ba06bf..69b4bcf880c9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -69,6 +69,8 @@ struct ip6_tnl_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi6 *fl6); + int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, + u8 type, u8 code, int offset, __be32 info); }; #ifdef CONFIG_INET diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 5ce926701bd0..cbcf35ce1b14 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -292,6 +292,7 @@ struct ip_tunnel_encap_ops { size_t (*encap_hlen)(struct ip_tunnel_encap *e); int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4); + int (*err_handler)(struct sk_buff *skb, u32 info); }; #define MAX_IPTUN_ENCAP_OPS 8 diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 829650540780..daf80863d3a5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -975,6 +975,8 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); +void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, + bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 3832099289c5..78fa0ac4613c 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -101,6 +101,17 @@ struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev) return master; } +int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex); +static inline +int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) +{ + rcu_read_lock(); + ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex); + rcu_read_unlock(); + + return ifindex; +} + u32 l3mdev_fib_table_rcu(const struct net_device *dev); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); static inline u32 l3mdev_fib_table(const struct net_device *dev) @@ -208,6 +219,17 @@ static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex) } static inline +int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) +{ + return 0; +} +static inline +int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex) +{ + return 0; +} + +static inline struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev) { return NULL; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 71985e95d2d9..88219cc137c3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -467,7 +467,7 @@ struct ieee80211_mu_group_data { }; /** - * ieee80211_ftm_responder_params - FTM responder parameters + * struct ieee80211_ftm_responder_params - FTM responder parameters * * @lci: LCI subelement content * @civicloc: CIVIC location subelement content @@ -496,6 +496,8 @@ struct ieee80211_ftm_responder_params { * @uora_ocw_range: UORA element's OCW Range field * @frame_time_rts_th: HE duration RTS threshold, in units of 32us * @he_support: does this BSS support HE + * @twt_requester: does this BSS support TWT requester (relevant for managed + * mode only, set if the AP advertises TWT responder role) * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS * or not @@ -594,6 +596,7 @@ struct ieee80211_bss_conf { u8 uora_ocw_range; u16 frame_time_rts_th; bool he_support; + bool twt_requester; /* association related data */ bool assoc, ibss_joined; bool ibss_creator; @@ -3239,6 +3242,11 @@ enum ieee80211_reconfig_type { * When the scan finishes, ieee80211_scan_completed() must be called; * note that it also must be called when the scan cannot finish due to * any error unless this callback returned a negative error code. + * This callback is also allowed to return the special return value 1, + * this indicates that hardware scan isn't desirable right now and a + * software scan should be done instead. A driver wishing to use this + * capability must ensure its (hardware) scan capabilities aren't + * advertised as more capable than mac80211's software scan is. * The callback can sleep. * * @cancel_hw_scan: Ask the low-level tp cancel the active hw scan. @@ -3623,6 +3631,9 @@ enum ieee80211_reconfig_type { * skb is always a real frame, head may or may not be an A-MSDU. * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. * Statistics should be cumulative, currently no way to reset is provided. + * + * @start_pmsr: start peer measurement (e.g. FTM) (this call can sleep) + * @abort_pmsr: abort peer measurement (this call can sleep) */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3911,6 +3922,10 @@ struct ieee80211_ops { int (*get_ftm_responder_stats)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_ftm_responder_stats *ftm_stats); + int (*start_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct cfg80211_pmsr_request *request); + void (*abort_pmsr)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + struct cfg80211_pmsr_request *request); }; /** @@ -6091,6 +6106,14 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * @txq: pointer obtained from station or virtual interface * * Returns the skb if successful, %NULL if no frame was available. + * + * Note that this must be called in an rcu_read_lock() critical section, + * which can only be released after the SKB was handled. Some pointers in + * skb->cb, e.g. the key pointer, are protected by by RCU and thus the + * critical section must persist not just for the duration of this call + * but for the duration of the frame handling. + * However, also note that while in the wake_tx_queue() method, + * rcu_read_lock() is already held. */ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 665990c7dec8..7c1ab9edba03 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -140,8 +140,8 @@ struct neighbour { unsigned long updated; rwlock_t lock; refcount_t refcnt; - struct sk_buff_head arp_queue; unsigned int arp_queue_len_bytes; + struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; @@ -149,11 +149,13 @@ struct neighbour { __u8 nud_state; __u8 type; __u8 dead; + u8 protocol; seqlock_t ha_lock; - unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))]; + unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; + struct list_head gc_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -172,6 +174,7 @@ struct pneigh_entry { possible_net_t net; struct net_device *dev; u8 flags; + u8 protocol; u8 key[0]; }; @@ -214,6 +217,8 @@ struct neigh_table { struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; + atomic_t gc_entries; + struct list_head gc_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,6 +255,7 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 +extern const struct nla_policy nda_policy[]; static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) { @@ -546,24 +552,6 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, } while (read_seqretry(&n->ha_lock, seq)); } -static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) -{ - u8 ndm_flags = 0; - - if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return; - - ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { - if (ndm_flags & NTF_EXT_LEARNED) - neigh->flags |= NTF_EXT_LEARNED; - else - neigh->flags &= ~NTF_EXT_LEARNED; - *notify = 1; - } -} - static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, int *notify) { diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index 74af19c3a8f7..4cd56808ac4e 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -6,12 +6,12 @@ static inline struct nf_bridge_info *nf_bridge_alloc(struct sk_buff *skb) { - skb->nf_bridge = kzalloc(sizeof(struct nf_bridge_info), GFP_ATOMIC); + struct nf_bridge_info *b = skb_ext_add(skb, SKB_EXT_BRIDGE_NF); - if (likely(skb->nf_bridge)) - refcount_set(&(skb->nf_bridge->use), 1); + if (b) + memset(b, 0, sizeof(*b)); - return skb->nf_bridge; + return b; } void nf_bridge_update_protocol(struct sk_buff *skb); @@ -22,12 +22,6 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, struct sock *sk, int (*okfn)(struct net *, struct sock *, struct sk_buff *)); -static inline struct nf_bridge_info * -nf_bridge_info_get(const struct sk_buff *skb) -{ - return skb->nf_bridge; -} - unsigned int nf_bridge_encap_header_len(const struct sk_buff *skb); static inline void nf_bridge_push_encap_header(struct sk_buff *skb) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 7e012312cd61..249d0a5b12b8 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -27,12 +27,17 @@ #include <net/netfilter/nf_conntrack_tuple.h> +struct nf_ct_udp { + unsigned long stream_ts; +}; + /* per conntrack: protocol private data */ union nf_conntrack_proto { /* insert conntrack proto private data here */ struct nf_ct_dccp dccp; struct ip_ct_sctp sctp; struct ip_ct_tcp tcp; + struct nf_ct_udp udp; struct nf_ct_gre gre; unsigned int tmpl_padto; }; diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h index 79d8d16732b4..bc6745d3010e 100644 --- a/include/net/netfilter/nf_conntrack_acct.h +++ b/include/net/netfilter/nf_conntrack_acct.h @@ -46,9 +46,6 @@ struct nf_conn_acct *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp) return acct; }; -unsigned int seq_print_acct(struct seq_file *s, const struct nf_conn *ct, - int dir); - /* Check if connection tracking accounting is enabled */ static inline bool nf_ct_acct_enabled(struct net *net) { @@ -61,8 +58,7 @@ static inline void nf_ct_set_acct(struct net *net, bool enable) net->ct.sysctl_acct = enable; } -int nf_conntrack_acct_pernet_init(struct net *net); -void nf_conntrack_acct_pernet_fini(struct net *net); +void nf_conntrack_acct_pernet_init(struct net *net); int nf_conntrack_acct_init(void); void nf_conntrack_acct_fini(void); diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 3f1ce9a8776e..52b44192b43f 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -142,7 +142,7 @@ void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_conntrack_expect *exp, u32 portid, int report); -int nf_conntrack_ecache_pernet_init(struct net *net); +void nf_conntrack_ecache_pernet_init(struct net *net); void nf_conntrack_ecache_pernet_fini(struct net *net); int nf_conntrack_ecache_init(void); @@ -182,10 +182,7 @@ static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events e, u32 portid, int report) {} -static inline int nf_conntrack_ecache_pernet_init(struct net *net) -{ - return 0; -} +static inline void nf_conntrack_ecache_pernet_init(struct net *net) {} static inline void nf_conntrack_ecache_pernet_fini(struct net *net) { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 2492120b8097..ec52a8dc32fd 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -124,8 +124,7 @@ static inline void *nfct_help_data(const struct nf_conn *ct) return (void *)help->data; } -int nf_conntrack_helper_pernet_init(struct net *net); -void nf_conntrack_helper_pernet_fini(struct net *net); +void nf_conntrack_helper_pernet_init(struct net *net); int nf_conntrack_helper_init(void); void nf_conntrack_helper_fini(void); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h index 3b661986be8f..0ed617bf0a3d 100644 --- a/include/net/netfilter/nf_conntrack_timestamp.h +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -49,21 +49,12 @@ static inline void nf_ct_set_tstamp(struct net *net, bool enable) } #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP -int nf_conntrack_tstamp_pernet_init(struct net *net); -void nf_conntrack_tstamp_pernet_fini(struct net *net); +void nf_conntrack_tstamp_pernet_init(struct net *net); int nf_conntrack_tstamp_init(void); void nf_conntrack_tstamp_fini(void); #else -static inline int nf_conntrack_tstamp_pernet_init(struct net *net) -{ - return 0; -} - -static inline void nf_conntrack_tstamp_pernet_fini(struct net *net) -{ - return; -} +static inline void nf_conntrack_tstamp_pernet_init(struct net *net) {} static inline int nf_conntrack_tstamp_init(void) { diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 77e2761d4f2f..7d5cda7ce32a 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -95,10 +95,6 @@ void flow_offload_free(struct flow_offload *flow); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); struct flow_offload_tuple_rhash *flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple); -int nf_flow_table_iterate(struct nf_flowtable *flow_table, - void (*iter)(struct flow_offload *flow, void *data), - void *data); - void nf_flow_table_cleanup(struct net_device *dev); int nf_flow_table_init(struct nf_flowtable *flow_table); diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index d300b8f03972..d774ca0c4c5e 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -2,18 +2,11 @@ #ifndef _NF_NAT_L3PROTO_H #define _NF_NAT_L3PROTO_H -struct nf_nat_l4proto; struct nf_nat_l3proto { u8 l3proto; - bool (*in_range)(const struct nf_conntrack_tuple *t, - const struct nf_nat_range2 *range); - - u32 (*secure_port)(const struct nf_conntrack_tuple *t, __be16); - bool (*manip_pkt)(struct sk_buff *skb, unsigned int iphdroff, - const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *target, enum nf_nat_manip_type maniptype); diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h index b4d6b29bca62..95a4655bd1ad 100644 --- a/include/net/netfilter/nf_nat_l4proto.h +++ b/include/net/netfilter/nf_nat_l4proto.h @@ -5,78 +5,12 @@ #include <net/netfilter/nf_nat.h> #include <linux/netfilter/nfnetlink_conntrack.h> -struct nf_nat_range; struct nf_nat_l3proto; -struct nf_nat_l4proto { - /* Protocol number. */ - u8 l4proto; - - /* Translate a packet to the target according to manip type. - * Return true if succeeded. - */ - bool (*manip_pkt)(struct sk_buff *skb, - const struct nf_nat_l3proto *l3proto, - unsigned int iphdroff, unsigned int hdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype); - - /* Is the manipable part of the tuple between min and max incl? */ - bool (*in_range)(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max); - - /* Alter the per-proto part of the tuple (depending on - * maniptype), to give a unique tuple in the given range if - * possible. Per-protocol part of tuple is initialized to the - * incoming packet. - */ - void (*unique_tuple)(const struct nf_nat_l3proto *l3proto, - struct nf_conntrack_tuple *tuple, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct); - - int (*nlattr_to_range)(struct nlattr *tb[], - struct nf_nat_range2 *range); -}; - -/* Protocol registration. */ -int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto); -void nf_nat_l4proto_unregister(u8 l3proto, - const struct nf_nat_l4proto *l4proto); - -const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto); - -/* Built-in protocols. */ -extern const struct nf_nat_l4proto nf_nat_l4proto_tcp; -extern const struct nf_nat_l4proto nf_nat_l4proto_udp; -extern const struct nf_nat_l4proto nf_nat_l4proto_icmp; -extern const struct nf_nat_l4proto nf_nat_l4proto_icmpv6; -extern const struct nf_nat_l4proto nf_nat_l4proto_unknown; -#ifdef CONFIG_NF_NAT_PROTO_DCCP -extern const struct nf_nat_l4proto nf_nat_l4proto_dccp; -#endif -#ifdef CONFIG_NF_NAT_PROTO_SCTP -extern const struct nf_nat_l4proto nf_nat_l4proto_sctp; -#endif -#ifdef CONFIG_NF_NAT_PROTO_UDPLITE -extern const struct nf_nat_l4proto nf_nat_l4proto_udplite; -#endif - -bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max); - -void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, - struct nf_conntrack_tuple *tuple, - const struct nf_nat_range2 *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct, u16 *rover); - -int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range2 *range); - +/* Translate a packet to the target according to manip type. Return on success. */ +bool nf_nat_l4proto_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype); #endif /*_NF_NAT_L4PROTO_H*/ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 9795d628a127..51cba0b8adf5 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -97,18 +97,14 @@ struct netns_ct { struct delayed_work ecache_dwork; bool ecache_dwork_pending; #endif + bool auto_assign_helper_warned; #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; - struct ctl_table_header *acct_sysctl_header; - struct ctl_table_header *tstamp_sysctl_header; - struct ctl_table_header *event_sysctl_header; - struct ctl_table_header *helper_sysctl_header; #endif unsigned int sysctl_log_invalid; /* Log invalid packets */ int sysctl_events; int sysctl_acct; int sysctl_auto_assign_helper; - bool auto_assign_helper_warned; int sysctl_tstamp; int sysctl_checksum; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index e47503b4e4d1..104a6669e344 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -103,6 +103,9 @@ struct netns_ipv4 { /* Shall we try to damage output packets if routing dev changes? */ int sysctl_ip_dynaddr; int sysctl_ip_early_demux; +#ifdef CONFIG_NET_L3_MASTER_DEV + int sysctl_raw_l3mdev_accept; +#endif int sysctl_tcp_early_demux; int sysctl_udp_early_demux; diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 9991e5ef52cc..59f45b1e9dac 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -5,6 +5,7 @@ #include <linux/list.h> #include <linux/wait.h> #include <linux/workqueue.h> +#include <linux/rhashtable-types.h> #include <linux/xfrm.h> #include <net/dst_ops.h> @@ -53,6 +54,7 @@ struct netns_xfrm { unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; struct xfrm_policy_hthresh policy_hthresh; + struct list_head inexact_bins; struct sock *nlsk; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 72ffb3120ced..40965fbbcd31 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -81,6 +81,14 @@ void __tcf_block_cb_unregister(struct tcf_block *block, struct tcf_block_cb *block_cb); void tcf_block_cb_unregister(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_ident); +int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +void __tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident); +void tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident); int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode); @@ -183,6 +191,32 @@ void tcf_block_cb_unregister(struct tcf_block *block, { } +static inline +int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + return 0; +} + +static inline +int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ + return 0; +} + +static inline +void __tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ +} + +static inline +void tc_indr_block_cb_unregister(struct net_device *dev, + tc_indr_block_bind_cb_t *cb, void *cb_ident) +{ +} + static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res, bool compat_mode) { @@ -585,8 +619,8 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ -int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts, - enum tc_setup_type type, void *type_data, bool err_stop); +int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, + void *type_data, bool err_stop); enum tc_block_command { TC_BLOCK_BIND, @@ -609,6 +643,7 @@ struct tc_cls_common_offload { struct tc_cls_u32_knode { struct tcf_exts *exts; + struct tcf_result *res; struct tc_u32_sel *sel; u32 handle; u32 val; @@ -787,12 +822,21 @@ enum tc_mq_command { TC_MQ_CREATE, TC_MQ_DESTROY, TC_MQ_STATS, + TC_MQ_GRAFT, +}; + +struct tc_mq_opt_offload_graft_params { + unsigned long queue; + u32 child_handle; }; struct tc_mq_qopt_offload { enum tc_mq_command command; u32 handle; - struct tc_qopt_offload_stats stats; + union { + struct tc_qopt_offload_stats stats; + struct tc_mq_opt_offload_graft_params graft_params; + }; }; enum tc_red_command { @@ -800,13 +844,16 @@ enum tc_red_command { TC_RED_DESTROY, TC_RED_STATS, TC_RED_XSTATS, + TC_RED_GRAFT, }; struct tc_red_qopt_offload_params { u32 min; u32 max; u32 probability; + u32 limit; bool is_ecn; + bool is_harddrop; struct gnet_stats_queue *qstats; }; @@ -818,6 +865,51 @@ struct tc_red_qopt_offload { struct tc_red_qopt_offload_params set; struct tc_qopt_offload_stats stats; struct red_stats *xstats; + u32 child_handle; + }; +}; + +enum tc_gred_command { + TC_GRED_REPLACE, + TC_GRED_DESTROY, + TC_GRED_STATS, +}; + +struct tc_gred_vq_qopt_offload_params { + bool present; + u32 limit; + u32 prio; + u32 min; + u32 max; + bool is_ecn; + bool is_harddrop; + u32 probability; + /* Only need backlog, see struct tc_prio_qopt_offload_params */ + u32 *backlog; +}; + +struct tc_gred_qopt_offload_params { + bool grio_on; + bool wred_on; + unsigned int dp_cnt; + unsigned int dp_def; + struct gnet_stats_queue *qstats; + struct tc_gred_vq_qopt_offload_params tab[MAX_DPs]; +}; + +struct tc_gred_qopt_offload_stats { + struct gnet_stats_basic_packed bstats[MAX_DPs]; + struct gnet_stats_queue qstats[MAX_DPs]; + struct red_stats *xstats[MAX_DPs]; +}; + +struct tc_gred_qopt_offload { + enum tc_gred_command command; + u32 handle; + u32 parent; + union { + struct tc_gred_qopt_offload_params set; + struct tc_gred_qopt_offload_stats stats; }; }; @@ -854,4 +946,14 @@ struct tc_prio_qopt_offload { }; }; +enum tc_root_command { + TC_ROOT_GRAFT, +}; + +struct tc_root_qopt_offload { + enum tc_root_command command; + u32 handle; + bool ingress; +}; + #endif diff --git a/include/net/protocol.h b/include/net/protocol.h index 4fc75f7ae23b..92b3eaad6088 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -42,7 +42,10 @@ struct net_protocol { int (*early_demux)(struct sk_buff *skb); int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); - void (*err_handler)(struct sk_buff *skb, u32 info); + + /* This returns an error if we weren't able to handle the error. */ + int (*err_handler)(struct sk_buff *skb, u32 info); + unsigned int no_policy:1, netns_ok:1, /* does the protocol do more stringent @@ -58,10 +61,12 @@ struct inet6_protocol { void (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); - void (*err_handler)(struct sk_buff *skb, + /* This returns an error if we weren't able to handle the error. */ + int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); + unsigned int flags; /* INET6_PROTO_xxx */ }; diff --git a/include/net/raw.h b/include/net/raw.h index 9c9fa98a91a4..821ff4887f77 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -17,7 +17,7 @@ #ifndef _RAW_H #define _RAW_H - +#include <net/inet_sock.h> #include <net/protocol.h> #include <linux/icmp.h> @@ -61,6 +61,7 @@ void raw_seq_stop(struct seq_file *seq, void *v); int raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); +void raw_init(void); struct raw_sock { /* inet_sock has to be the first member */ @@ -74,4 +75,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk) return (struct raw_sock *)sk; } +static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + #endif /* _RAW_H */ diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index cf26e5aacac4..e2091bb2b3a8 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -159,7 +159,8 @@ struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]); struct net_device *rtnl_create_link(struct net *net, const char *ifname, unsigned char name_assign_type, const struct rtnl_link_ops *ops, - struct nlattr *tb[]); + struct nlattr *tb[], + struct netlink_ext_ack *extack); int rtnl_delete_link(struct net_device *dev); int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 4d736427a4cb..9481f2c142e2 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -24,6 +24,9 @@ struct bpf_flow_keys; typedef int tc_setup_cb_t(enum tc_setup_type type, void *type_data, void *cb_priv); +typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, + enum tc_setup_type type, void *type_data); + struct qdisc_rate_table { struct tc_ratespec rate; u32 data[256]; @@ -579,6 +582,30 @@ void qdisc_put(struct Qdisc *qdisc); void qdisc_put_unlocked(struct Qdisc *qdisc); void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, unsigned int len); +#ifdef CONFIG_NET_SCHED +int qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, + void *type_data); +void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack); +#else +static inline int +qdisc_offload_dump_helper(struct Qdisc *q, enum tc_setup_type type, + void *type_data) +{ + q->flags &= ~TCQ_F_OFFLOADED; + return 0; +} + +static inline void +qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, + struct Qdisc *new, struct Qdisc *old, + enum tc_setup_type type, void *type_data, + struct netlink_ext_ack *extack) +{ +} +#endif struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 8dadc74c22e7..4588bdc2b8f0 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -71,7 +71,7 @@ enum { SCTP_DEFAULT_INSTREAMS = SCTP_MAX_STREAM }; SCTP_NUM_AUTH_CHUNK_TYPES) /* These are the different flavours of event. */ -enum sctp_event { +enum sctp_event_type { SCTP_EVENT_T_CHUNK = 1, SCTP_EVENT_T_TIMEOUT, SCTP_EVENT_T_OTHER, diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 2abbc15824af..1d13ec3f2707 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -151,8 +151,8 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc, * sctp/input.c */ int sctp_rcv(struct sk_buff *skb); -void sctp_v4_err(struct sk_buff *skb, u32 info); -void sctp_hash_endpoint(struct sctp_endpoint *); +int sctp_v4_err(struct sk_buff *skb, u32 info); +int sctp_hash_endpoint(struct sctp_endpoint *ep); void sctp_unhash_endpoint(struct sctp_endpoint *); struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *, struct sctphdr *, struct sctp_association **, diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 9e3d32746430..24825a81829e 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -173,7 +173,7 @@ sctp_state_fn_t sctp_sf_autoclose_timer_expire; __u8 sctp_get_chunk_type(struct sctp_chunk *chunk); const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, - enum sctp_event event_type, + enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); int sctp_chunk_iif(const struct sctp_chunk *); @@ -313,7 +313,7 @@ struct sctp_chunk *sctp_process_strreset_resp( /* Prototypes for statetable processing. */ -int sctp_do_sm(struct net *net, enum sctp_event event_type, +int sctp_do_sm(struct net *net, enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, gfp_t gfp); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index feada358d872..003020eb6e66 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -96,7 +96,9 @@ struct sctp_stream; struct sctp_bind_bucket { unsigned short port; - unsigned short fastreuse; + signed char fastreuse; + signed char fastreuseport; + kuid_t fastuid; struct hlist_node node; struct hlist_head owner; struct net *net; @@ -215,7 +217,7 @@ struct sctp_sock { * These two structures must be grouped together for the usercopy * whitelist region. */ - struct sctp_event_subscribe subscribe; + __u16 subscribe; struct sctp_initmsg initmsg; int user_frag; @@ -1190,6 +1192,8 @@ int sctp_bind_addr_conflict(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *, struct sctp_sock *); int sctp_bind_addr_state(const struct sctp_bind_addr *bp, const union sctp_addr *addr); +int sctp_bind_addrs_check(struct sctp_sock *sp, + struct sctp_sock *sp2, int cnt2); union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, const union sctp_addr *addrs, int addrcnt, @@ -2073,6 +2077,8 @@ struct sctp_association { int sent_cnt_removable; + __u16 subscribe; + __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index 51b4e0626c34..bd922a0fe914 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -164,30 +164,39 @@ void sctp_ulpevent_read_nxtinfo(const struct sctp_ulpevent *event, __u16 sctp_ulpevent_get_notification_type(const struct sctp_ulpevent *event); +static inline void sctp_ulpevent_type_set(__u16 *subscribe, + __u16 sn_type, __u8 on) +{ + if (sn_type > SCTP_SN_TYPE_MAX) + return; + + if (on) + *subscribe |= (1 << (sn_type - SCTP_SN_TYPE_BASE)); + else + *subscribe &= ~(1 << (sn_type - SCTP_SN_TYPE_BASE)); +} + /* Is this event type enabled? */ -static inline int sctp_ulpevent_type_enabled(__u16 sn_type, - struct sctp_event_subscribe *mask) +static inline bool sctp_ulpevent_type_enabled(__u16 subscribe, __u16 sn_type) { - int offset = sn_type - SCTP_SN_TYPE_BASE; - char *amask = (char *) mask; + if (sn_type > SCTP_SN_TYPE_MAX) + return false; - if (offset >= sizeof(struct sctp_event_subscribe)) - return 0; - return amask[offset]; + return subscribe & (1 << (sn_type - SCTP_SN_TYPE_BASE)); } /* Given an event subscription, is this event enabled? */ -static inline int sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event, - struct sctp_event_subscribe *mask) +static inline bool sctp_ulpevent_is_enabled(const struct sctp_ulpevent *event, + __u16 subscribe) { __u16 sn_type; - int enabled = 1; - if (sctp_ulpevent_is_notification(event)) { - sn_type = sctp_ulpevent_get_notification_type(event); - enabled = sctp_ulpevent_type_enabled(sn_type, mask); - } - return enabled; + if (!sctp_ulpevent_is_notification(event)) + return true; + + sn_type = sctp_ulpevent_get_notification_type(event); + + return sctp_ulpevent_type_enabled(subscribe, sn_type); } #endif /* __sctp_ulpevent_h__ */ diff --git a/include/net/seg6.h b/include/net/seg6.h index 2567941a2f32..8b2dc6869fd1 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -16,7 +16,6 @@ #include <linux/net.h> #include <linux/ipv6.h> -#include <net/lwtunnel.h> #include <linux/seg6.h> #include <linux/rhashtable-types.h> diff --git a/include/net/sock.h b/include/net/sock.h index 0e3a09380655..a6235c286ef9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1110,7 +1110,7 @@ struct proto { unsigned int inuse_idx; #endif - bool (*stream_memory_free)(const struct sock *sk); + bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*stream_memory_read)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); @@ -1192,19 +1192,29 @@ static inline void sk_refcnt_debug_release(const struct sock *sk) #define sk_refcnt_debug_release(sk) do { } while (0) #endif /* SOCK_REFCNT_DEBUG */ -static inline bool sk_stream_memory_free(const struct sock *sk) +static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { if (sk->sk_wmem_queued >= sk->sk_sndbuf) return false; return sk->sk_prot->stream_memory_free ? - sk->sk_prot->stream_memory_free(sk) : true; + sk->sk_prot->stream_memory_free(sk, wake) : true; } -static inline bool sk_stream_is_writeable(const struct sock *sk) +static inline bool sk_stream_memory_free(const struct sock *sk) +{ + return __sk_stream_memory_free(sk, 0); +} + +static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake) { return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && - sk_stream_memory_free(sk); + __sk_stream_memory_free(sk, wake); +} + +static inline bool sk_stream_is_writeable(const struct sock *sk) +{ + return __sk_stream_is_writeable(sk, 0); } static inline int sk_under_cgroup_hierarchy(struct sock *sk, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 881ecb1555bf..a7fdab5ee6c3 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -95,8 +95,8 @@ struct switchdev_obj_port_vlan { u16 vid_end; }; -#define SWITCHDEV_OBJ_PORT_VLAN(obj) \ - container_of(obj, struct switchdev_obj_port_vlan, obj) +#define SWITCHDEV_OBJ_PORT_VLAN(OBJ) \ + container_of((OBJ), struct switchdev_obj_port_vlan, obj) /* SWITCHDEV_OBJ_ID_PORT_MDB */ struct switchdev_obj_port_mdb { @@ -105,8 +105,8 @@ struct switchdev_obj_port_mdb { u16 vid; }; -#define SWITCHDEV_OBJ_PORT_MDB(obj) \ - container_of(obj, struct switchdev_obj_port_mdb, obj) +#define SWITCHDEV_OBJ_PORT_MDB(OBJ) \ + container_of((OBJ), struct switchdev_obj_port_mdb, obj) void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), @@ -121,10 +121,6 @@ typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). - * - * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). - * - * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, @@ -132,11 +128,6 @@ struct switchdev_ops { int (*switchdev_port_attr_set)(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans); - int (*switchdev_port_obj_add)(struct net_device *dev, - const struct switchdev_obj *obj, - struct switchdev_trans *trans); - int (*switchdev_port_obj_del)(struct net_device *dev, - const struct switchdev_obj *obj); }; enum switchdev_notifier_type { @@ -146,6 +137,11 @@ enum switchdev_notifier_type { SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, + SWITCHDEV_PORT_OBJ_ADD, /* Blocking. */ + SWITCHDEV_PORT_OBJ_DEL, /* Blocking. */ + + SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE, + SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE, SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE, SWITCHDEV_VXLAN_FDB_OFFLOADED, @@ -153,6 +149,7 @@ enum switchdev_notifier_type { struct switchdev_notifier_info { struct net_device *dev; + struct netlink_ext_ack *extack; }; struct switchdev_notifier_fdb_info { @@ -163,12 +160,25 @@ struct switchdev_notifier_fdb_info { offloaded:1; }; +struct switchdev_notifier_port_obj_info { + struct switchdev_notifier_info info; /* must be first */ + const struct switchdev_obj *obj; + struct switchdev_trans *trans; + bool handled; +}; + static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { return info->dev; } +static inline struct netlink_ext_ack * +switchdev_notifier_info_to_extack(const struct switchdev_notifier_info *info) +{ + return info->extack; +} + #ifdef CONFIG_NET_SWITCHDEV void switchdev_deferred_process(void); @@ -177,13 +187,22 @@ int switchdev_port_attr_get(struct net_device *dev, int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, - const struct switchdev_obj *obj); + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack); int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); + int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info); + +int register_switchdev_blocking_notifier(struct notifier_block *nb); +int unregister_switchdev_blocking_notifier(struct notifier_block *nb); +int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack); + void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); @@ -191,6 +210,19 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b); +int switchdev_handle_port_obj_add(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*add_cb)(struct net_device *dev, + const struct switchdev_obj *obj, + struct switchdev_trans *trans, + struct netlink_ext_ack *extack)); +int switchdev_handle_port_obj_del(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*del_cb)(struct net_device *dev, + const struct switchdev_obj *obj)); + #define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops)) #else @@ -211,7 +243,8 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - const struct switchdev_obj *obj) + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } @@ -239,12 +272,55 @@ static inline int call_switchdev_notifiers(unsigned long val, return NOTIFY_DONE; } +static inline int +register_switchdev_blocking_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +unregister_switchdev_blocking_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +call_switchdev_blocking_notifiers(unsigned long val, + struct net_device *dev, + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack) +{ + return NOTIFY_DONE; +} + static inline bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { return false; } +static inline int +switchdev_handle_port_obj_add(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*add_cb)(struct net_device *dev, + const struct switchdev_obj *obj, + struct switchdev_trans *trans, + struct netlink_ext_ack *extack)) +{ + return 0; +} + +static inline int +switchdev_handle_port_obj_del(struct net_device *dev, + struct switchdev_notifier_port_obj_info *port_obj_info, + bool (*check_cb)(const struct net_device *dev), + int (*del_cb)(struct net_device *dev, + const struct switchdev_obj *obj)) +{ + return 0; +} + #define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0) #endif diff --git a/include/net/tcp.h b/include/net/tcp.h index a18914d20486..e0a65c067662 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -313,7 +313,7 @@ extern struct proto tcp_prot; void tcp_tasklet_init(void); -void tcp_v4_err(struct sk_buff *skb, u32); +int tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); @@ -1124,7 +1124,7 @@ void tcp_rate_check_app_limited(struct sock *sk); */ static inline int tcp_is_sack(const struct tcp_sock *tp) { - return tp->rx_opt.sack_ok; + return likely(tp->rx_opt.sack_ok); } static inline bool tcp_is_reno(const struct tcp_sock *tp) @@ -1315,33 +1315,16 @@ static inline __sum16 tcp_v4_check(int len, __be32 saddr, return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base); } -static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb) -{ - return __skb_checksum_complete(skb); -} - static inline bool tcp_checksum_complete(struct sk_buff *skb) { return !skb_csum_unnecessary(skb) && - __tcp_checksum_complete(skb); + __skb_checksum_complete(skb); } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); int tcp_filter(struct sock *sk, struct sk_buff *skb); - -#undef STATE_TRACE - -#ifdef STATE_TRACE -static const char *statename[]={ - "Unused","Established","Syn Sent","Syn Recv", - "Fin Wait 1","Fin Wait 2","Time Wait", "Close", - "Close Wait","Last ACK","Listen","Closing" -}; -#endif void tcp_set_state(struct sock *sk, int state); - void tcp_done(struct sock *sk); - int tcp_abort(struct sock *sk, int err); static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) @@ -1385,7 +1368,7 @@ static inline int tcp_win_from_space(const struct sock *sk, int space) /* Note: caller must be prepared to deal with negative returns */ static inline int tcp_space(const struct sock *sk) { - return tcp_win_from_space(sk, sk->sk_rcvbuf - + return tcp_win_from_space(sk, sk->sk_rcvbuf - sk->sk_backlog.len - atomic_read(&sk->sk_rmem_alloc)); } @@ -1572,9 +1555,21 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, - const union tcp_md5_addr *addr, - int family); +#include <linux/jump_label.h> +extern struct static_key tcp_md5_needed; +struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, + const union tcp_md5_addr *addr, + int family); +static inline struct tcp_md5sig_key * +tcp_md5_do_lookup(const struct sock *sk, + const union tcp_md5_addr *addr, + int family) +{ + if (!static_key_false(&tcp_md5_needed)) + return NULL; + return __tcp_md5_do_lookup(sk, addr, family); +} + #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, @@ -1875,12 +1870,16 @@ static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat; } -static inline bool tcp_stream_memory_free(const struct sock *sk) +/* @wake is one when sk_stream_write_space() calls us. + * This sends EPOLLOUT only if notsent_bytes is half the limit. + * This mimics the strategy used in sock_def_write_space(). + */ +static inline bool tcp_stream_memory_free(const struct sock *sk, int wake) { const struct tcp_sock *tp = tcp_sk(sk); u32 notsent_bytes = tp->write_seq - tp->snd_nxt; - return notsent_bytes < tcp_notsent_lowat(tp); + return (notsent_bytes << wake) < tcp_notsent_lowat(tp); } #ifdef CONFIG_PROC_FS diff --git a/include/net/tls.h b/include/net/tls.h index 3cbcd12303fd..2a6ac8d642af 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -460,6 +460,15 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx) return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx; } +static inline bool tls_sw_has_ctx_tx(const struct sock *sk) +{ + struct tls_context *ctx = tls_get_ctx(sk); + + if (!ctx) + return false; + return !!tls_sw_ctx_tx(ctx); +} + static inline struct tls_offload_context_rx * tls_offload_ctx_rx(const struct tls_context *tls_ctx) { diff --git a/include/net/udp.h b/include/net/udp.h index 9e82cb391dea..fd6d948755c8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk) return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit); } +static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if, + int dif, int sdif) +{ +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV) + return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept, + bound_dev_if, dif, sdif); +#else + return inet_bound_dev_eq(true, bound_dev_if, dif, sdif); +#endif +} + /* net/ipv4/udp.c */ void udp_destruct_sock(struct sock *sk); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len); @@ -272,7 +283,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); -void udp_err(struct sk_buff *, u32); +int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); @@ -406,17 +417,24 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, } while(0) #if IS_ENABLED(CONFIG_IPV6) -#define __UDPX_INC_STATS(sk, field) \ -do { \ - if ((sk)->sk_family == AF_INET) \ - __UDP_INC_STATS(sock_net(sk), field, 0); \ - else \ - __UDP6_INC_STATS(sock_net(sk), field, 0); \ -} while (0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics) : \ + (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 : \ + sock_net(sk)->mib.udp_stats_in6); \ +}) #else -#define __UDPX_INC_STATS(sk, field) __UDP_INC_STATS(sock_net(sk), field, 0) +#define __UDPX_MIB(sk, ipv4) \ +({ \ + IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics : \ + sock_net(sk)->mib.udp_statistics; \ +}) #endif +#define __UDPX_INC_STATS(sk, field) \ + __SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field) + #ifdef CONFIG_PROC_FS struct udp_seq_afinfo { sa_family_t family; @@ -450,4 +468,26 @@ DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void); #endif +static inline struct sk_buff *udp_rcv_segment(struct sock *sk, + struct sk_buff *skb, bool ipv4) +{ + struct sk_buff *segs; + + /* the GSO CB lays after the UDP one, no need to save and restore any + * CB fragment + */ + segs = __skb_gso_segment(skb, NETIF_F_SG, false); + if (unlikely(IS_ERR_OR_NULL(segs))) { + int segs_nr = skb_shinfo(skb)->gso_segs; + + atomic_add(segs_nr, &sk->sk_drops); + SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr); + kfree_skb(skb); + return NULL; + } + + consume_skb(skb); + return segs; +} + #endif /* _UDP_H */ diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index fe680ab6b15a..b8137953fea3 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -30,6 +30,7 @@ struct udp_port_cfg { __be16 local_udp_port; __be16 peer_udp_port; + int bind_ifindex; unsigned int use_udp_checksums:1, use_udp6_tx_checksums:1, use_udp6_rx_checksums:1, @@ -64,6 +65,8 @@ static inline int udp_sock_create(struct net *net, } typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb); +typedef int (*udp_tunnel_encap_err_lookup_t)(struct sock *sk, + struct sk_buff *skb); typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk); typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk, struct list_head *head, @@ -76,6 +79,7 @@ struct udp_tunnel_sock_cfg { /* Used for setting up udp_sock fields, see udp.h for details */ __u8 encap_type; udp_tunnel_encap_rcv_t encap_rcv; + udp_tunnel_encap_err_lookup_t encap_err_lookup; udp_tunnel_encap_destroy_t encap_destroy; udp_tunnel_gro_receive_t gro_receive; udp_tunnel_gro_complete_t gro_complete; @@ -165,6 +169,12 @@ static inline int udp_tunnel_handle_offloads(struct sk_buff *skb, bool udp_csum) static inline void udp_tunnel_encap_enable(struct socket *sock) { + struct udp_sock *up = udp_sk(sock->sk); + + if (up->encap_enabled) + return; + + up->encap_enabled = 1; #if IS_ENABLED(CONFIG_IPV6) if (sock->sk->sk_family == PF_INET6) ipv6_stub->udpv6_encap_enable(); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 03431c148e16..236403eb5ba6 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -216,6 +216,7 @@ struct vxlan_config { unsigned long age_interval; unsigned int addrmax; bool no_share; + enum ifla_vxlan_df df; }; struct vxlan_dev_node { @@ -420,11 +421,16 @@ struct switchdev_notifier_vxlan_fdb_info { u8 eth_addr[ETH_ALEN]; __be32 vni; bool offloaded; + bool added_by_user; }; #if IS_ENABLED(CONFIG_VXLAN) int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, struct switchdev_notifier_vxlan_fdb_info *fdb_info); +int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, + struct notifier_block *nb); +void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni); + #else static inline int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, @@ -432,6 +438,17 @@ vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni, { return -ENOENT; } + +static inline int vxlan_fdb_replay(const struct net_device *dev, __be32 vni, + struct notifier_block *nb) +{ + return -EOPNOTSUPP; +} + +static inline void +vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni) +{ +} #endif #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index da588def3c61..7298a53b9702 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -577,6 +577,7 @@ struct xfrm_policy { /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; + u32 pos; struct timer_list timer; atomic_t genid; @@ -589,6 +590,7 @@ struct xfrm_policy { struct xfrm_lifetime_cur curlft; struct xfrm_policy_walk_entry walk; struct xfrm_policy_queue polq; + bool bydst_reinsert; u8 type; u8 action; u8 flags; @@ -596,6 +598,7 @@ struct xfrm_policy { u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; + struct hlist_node bydst_inexact_list; struct rcu_head rcu; }; @@ -1093,7 +1096,6 @@ struct xfrm_offload { }; struct sec_path { - refcount_t refcnt; int len; int olen; @@ -1101,41 +1103,13 @@ struct sec_path { struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; }; -static inline int secpath_exists(struct sk_buff *skb) -{ -#ifdef CONFIG_XFRM - return skb->sp != NULL; -#else - return 0; -#endif -} - -static inline struct sec_path * -secpath_get(struct sec_path *sp) -{ - if (sp) - refcount_inc(&sp->refcnt); - return sp; -} - -void __secpath_destroy(struct sec_path *sp); - -static inline void -secpath_put(struct sec_path *sp) -{ - if (sp && refcount_dec_and_test(&sp->refcnt)) - __secpath_destroy(sp); -} - -struct sec_path *secpath_dup(struct sec_path *src); -int secpath_set(struct sk_buff *skb); +struct sec_path *secpath_set(struct sk_buff *skb); static inline void secpath_reset(struct sk_buff *skb) { #ifdef CONFIG_XFRM - secpath_put(skb->sp); - skb->sp = NULL; + skb_ext_del(skb, SKB_EXT_SEC_PATH); #endif } @@ -1191,7 +1165,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); - return (!net->xfrm.policy_count[dir] && !skb->sp) || + return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || (skb_dst(skb)->flags & DST_NOPOLICY) || __xfrm_policy_check(sk, ndir, skb, family); } @@ -1903,14 +1877,16 @@ static inline void xfrm_states_delete(struct xfrm_state **states, int n) #ifdef CONFIG_XFRM static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) { - return skb->sp->xvec[skb->sp->len - 1]; + struct sec_path *sp = skb_sec_path(skb); + + return sp->xvec[sp->len - 1]; } #endif static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) { #ifdef CONFIG_XFRM - struct sec_path *sp = skb->sp; + struct sec_path *sp = skb_sec_path(skb); if (!sp || !sp->olen || sp->len != sp->olen) return NULL; @@ -1968,7 +1944,7 @@ 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 net_device *dev = xso->dev; + struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { if (dev->xfrmdev_ops->xdo_dev_state_free) |