diff options
Diffstat (limited to 'include/net')
| -rw-r--r-- | include/net/af_unix.h | 5 | ||||
| -rw-r--r-- | include/net/bond_options.h | 14 | ||||
| -rw-r--r-- | include/net/bonding.h | 1 | ||||
| -rw-r--r-- | include/net/cfg80211.h | 265 | ||||
| -rw-r--r-- | include/net/devlink.h | 19 | ||||
| -rw-r--r-- | include/net/dropreason.h | 256 | ||||
| -rw-r--r-- | include/net/dsa.h | 9 | ||||
| -rw-r--r-- | include/net/flow_dissector.h | 16 | ||||
| -rw-r--r-- | include/net/flow_offload.h | 6 | ||||
| -rw-r--r-- | include/net/fq_impl.h | 5 | ||||
| -rw-r--r-- | include/net/ip_tunnels.h | 4 | ||||
| -rw-r--r-- | include/net/mac80211.h | 264 | ||||
| -rw-r--r-- | include/net/mptcp.h | 3 | ||||
| -rw-r--r-- | include/net/neighbour.h | 1 | ||||
| -rw-r--r-- | include/net/net_namespace.h | 2 | ||||
| -rw-r--r-- | include/net/netns/unix.h | 6 | ||||
| -rw-r--r-- | include/net/pkt_cls.h | 2 | ||||
| -rw-r--r-- | include/net/pkt_sched.h | 17 | ||||
| -rw-r--r-- | include/net/raw.h | 18 | ||||
| -rw-r--r-- | include/net/rawv6.h | 7 | ||||
| -rw-r--r-- | include/net/route.h | 4 | ||||
| -rw-r--r-- | include/net/sock.h | 114 | ||||
| -rw-r--r-- | include/net/strparser.h | 12 | ||||
| -rw-r--r-- | include/net/switchdev.h | 3 | ||||
| -rw-r--r-- | include/net/tcp.h | 4 | ||||
| -rw-r--r-- | include/net/tls.h | 279 | ||||
| -rw-r--r-- | include/net/udp.h | 4 | ||||
| -rw-r--r-- | include/net/xfrm.h | 4 |
28 files changed, 810 insertions, 534 deletions
diff --git a/include/net/af_unix.h b/include/net/af_unix.h index a7ef624ed726..480fa579787e 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -16,12 +16,11 @@ void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); struct sock *unix_peer_get(struct sock *sk); -#define UNIX_HASH_SIZE 256 +#define UNIX_HASH_MOD (256 - 1) +#define UNIX_HASH_SIZE (256 * 2) #define UNIX_HASH_BITS 8 extern unsigned int unix_tot_inflight; -extern spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE]; -extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; struct unix_address { refcount_t refcnt; diff --git a/include/net/bond_options.h b/include/net/bond_options.h index 61b49063791c..d2aea5cf1e41 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -67,6 +67,7 @@ enum { BOND_OPT_LACP_ACTIVE, BOND_OPT_MISSED_MAX, BOND_OPT_NS_TARGETS, + BOND_OPT_PRIO, BOND_OPT_LAST }; @@ -83,7 +84,10 @@ struct bond_opt_value { char *string; u64 value; u32 flags; - char extra[BOND_OPT_EXTRA_MAXLEN]; + union { + char extra[BOND_OPT_EXTRA_MAXLEN]; + struct net_device *slave_dev; + }; }; struct bonding; @@ -107,7 +111,8 @@ struct bond_option { }; int __bond_opt_set(struct bonding *bond, unsigned int option, - struct bond_opt_value *val); + struct bond_opt_value *val, + struct nlattr *bad_attr, struct netlink_ext_ack *extack); int __bond_opt_set_notify(struct bonding *bond, unsigned int option, struct bond_opt_value *val); int bond_opt_tryset_rtnl(struct bonding *bond, unsigned int option, char *buf); @@ -132,13 +137,16 @@ static inline void __bond_opt_init(struct bond_opt_value *optval, optval->value = value; else if (string) optval->string = string; - else if (extra_len <= BOND_OPT_EXTRA_MAXLEN) + + if (extra && extra_len <= BOND_OPT_EXTRA_MAXLEN) memcpy(optval->extra, extra, extra_len); } #define bond_opt_initval(optval, value) __bond_opt_init(optval, NULL, value, NULL, 0) #define bond_opt_initstr(optval, str) __bond_opt_init(optval, str, ULLONG_MAX, NULL, 0) #define bond_opt_initextra(optval, extra, extra_len) \ __bond_opt_init(optval, NULL, ULLONG_MAX, extra, extra_len) +#define bond_opt_slave_initval(optval, slave_dev, value) \ + __bond_opt_init(optval, NULL, value, slave_dev, sizeof(struct net_device *)) void bond_option_arp_ip_targets_clear(struct bonding *bond); #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/bonding.h b/include/net/bonding.h index cb904d356e31..6e78d657aa05 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -178,6 +178,7 @@ struct slave { u32 speed; u16 queue_id; u8 perm_hwaddr[MAX_ADDR_LEN]; + int prio; struct ad_slave_info *ad_info; struct tlb_slave_info tlb_info; #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 80f41446b1f0..3bcdd20ace66 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -374,6 +374,7 @@ struct ieee80211_sta_he_cap { * and NSS Set field" * * @only_20mhz: MCS/NSS support for 20 MHz-only STA. + * @bw: MCS/NSS support for 80, 160 and 320 MHz * @bw._80: MCS/NSS support for BW <= 80 MHz * @bw._160: MCS/NSS support for BW = 160 MHz * @bw._320: MCS/NSS support for BW = 320 MHz @@ -420,6 +421,7 @@ struct ieee80211_sta_eht_cap { * @he_cap: holds the HE capabilities * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a * 6 GHz band channel (and 0 may be valid value). + * @eht_cap: STA's EHT capabilities * @vendor_elems: vendor element(s) to advertise * @vendor_elems.data: vendor element(s) data * @vendor_elems.len: vendor element(s) length @@ -495,7 +497,7 @@ struct ieee80211_edmg { * This structure describes most essential parameters needed * to describe 802.11ah S1G capabilities for a STA. * - * @s1g_supported: is STA an S1G STA + * @s1g: is STA an S1G STA * @cap: S1G capabilities information * @nss_mcs: Supported NSS MCS set */ @@ -1061,6 +1063,7 @@ struct survey_info { }; #define CFG80211_MAX_WEP_KEYS 4 +#define CFG80211_MAX_NUM_AKM_SUITES 10 /** * struct cfg80211_crypto_settings - Crypto settings @@ -1112,7 +1115,7 @@ struct cfg80211_crypto_settings { int n_ciphers_pairwise; u32 ciphers_pairwise[NL80211_MAX_NR_CIPHER_SUITES]; int n_akm_suites; - u32 akm_suites[NL80211_MAX_NR_AKM_SUITES]; + u32 akm_suites[CFG80211_MAX_NUM_AKM_SUITES]; bool control_port; __be16 control_port_ethertype; bool control_port_no_encrypt; @@ -1158,6 +1161,7 @@ struct cfg80211_mbssid_elems { /** * struct cfg80211_beacon_data - beacon data + * @link_id: the link ID for the AP MLD link sending this beacon * @head: head portion of beacon (before TIM IE) * or %NULL if not changed * @tail: tail portion of beacon (after TIM IE) @@ -1188,6 +1192,8 @@ struct cfg80211_mbssid_elems { * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { + unsigned int link_id; + const u8 *head, *tail; const u8 *beacon_ies; const u8 *proberesp_ies; @@ -1290,6 +1296,8 @@ struct cfg80211_unsol_bcast_probe_resp { * @ht_cap: HT capabilities (or %NULL if HT isn't enabled) * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) * @he_cap: HE capabilities (or %NULL if HE isn't enabled) + * @eht_cap: EHT capabilities (or %NULL if EHT isn't enabled) + * @eht_oper: EHT operation IE (or %NULL if EHT isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time @@ -1326,6 +1334,8 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; const struct ieee80211_he_operation *he_oper; + const struct ieee80211_eht_cap_elem *eht_cap; + const struct ieee80211_eht_operation *eht_oper; bool ht_required, vht_required, he_required, sae_h2e_required; bool twt_responder; u32 flags; @@ -1370,8 +1380,8 @@ struct cfg80211_csa_settings { * Used for bss color change * * @beacon_color_change: beacon data while performing the color countdown - * @counter_offsets_beacon: offsets of the counters within the beacon (tail) - * @counter_offsets_presp: offsets of the counters within the probe response + * @counter_offset_beacon: offsets of the counters within the beacon (tail) + * @counter_offset_presp: offsets of the counters within the probe response * @beacon_next: beacon data to be used after the color change * @count: number of beacons until the color change * @color: the color used after the change @@ -1414,6 +1424,7 @@ struct iface_combination_params { * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state + * @STATION_PARAM_APPLY_STA_TXPOWER: apply tx power for STA * * Not all station parameters have in-band "no change" signalling, * for those that don't these flags will are used. @@ -2146,6 +2157,9 @@ 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. + * @dot11MeshConnectedToAuthServer: if set to true then this mesh STA + * will advertise that it is connected to a authentication server + * in the mesh formation field. * @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 @@ -2318,12 +2332,12 @@ struct cfg80211_scan_info { /** * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only * - * @short_bssid: short ssid to scan for + * @short_ssid: short ssid to scan for * @bssid: bssid to scan for * @channel_idx: idx of the channel in the channel array in the scan request * which the above info relvant to * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU - * @short_ssid_valid: short_ssid is valid and can be used + * @short_ssid_valid: @short_ssid is valid and can be used * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait * 20 TUs before starting to send probe requests. */ @@ -2715,6 +2729,12 @@ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) * Authentication algorithm number, i.e., starting at the Authentication * transaction sequence number field. * @auth_data_len: Length of auth_data buffer in octets + * @link_id: if >= 0, indicates authentication should be done as an MLD, + * the interface address is included as the MLD address and the + * necessary link (with the given link_id) will be created (and + * given an MLD address) by the driver + * @ap_mld_addr: AP MLD address in case of authentication request with + * an AP MLD, valid iff @link_id >= 0 */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -2725,6 +2745,21 @@ struct cfg80211_auth_request { u8 key_len, key_idx; const u8 *auth_data; size_t auth_data_len; + s8 link_id; + const u8 *ap_mld_addr; +}; + +/** + * struct cfg80211_assoc_link - per-link information for MLO association + * @bss: the BSS pointer, see also &struct cfg80211_assoc_request::bss; + * if this is %NULL for a link, that link is not requested + * @elems: extra elements for the per-STA profile for this link + * @elems_len: length of the elements + */ +struct cfg80211_assoc_link { + struct cfg80211_bss *bss; + const u8 *elems; + size_t elems_len; }; /** @@ -2739,6 +2774,9 @@ struct cfg80211_auth_request { * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE * @ASSOC_REQ_DISABLE_EHT: Disable EHT + * @CONNECT_REQ_MLO_SUPPORT: Userspace indicates support for handling MLD links. + * Drivers shall disable MLO features for the current association if this + * flag is not set. */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -2747,6 +2785,7 @@ enum cfg80211_assoc_req_flags { CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), ASSOC_REQ_DISABLE_EHT = BIT(5), + CONNECT_REQ_MLO_SUPPORT = BIT(6), }; /** @@ -2758,6 +2797,8 @@ enum cfg80211_assoc_req_flags { * given a reference that it must give back to cfg80211_send_rx_assoc() * or to cfg80211_assoc_timeout(). To ensure proper refcounting, new * association requests while already associating must be rejected. + * This also applies to the @links.bss parameter, which is used instead + * of this one (it is %NULL) for MLO associations. * @ie: Extra IEs to add to (Re)Association Request frame or %NULL * @ie_len: Length of ie buffer in octets * @use_mfp: Use management frame protection (IEEE 802.11w) in this association @@ -2782,6 +2823,11 @@ enum cfg80211_assoc_req_flags { * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. * @s1g_capa: S1G capability override * @s1g_capa_mask: S1G capability override mask + * @links: per-link information for MLO connections + * @link_id: >= 0 for MLO connections, where links are given, and indicates + * the link on which the association request should be sent + * @ap_mld_addr: AP MLD address in case of MLO association request, + * valid iff @link_id >= 0 */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; @@ -2797,6 +2843,9 @@ struct cfg80211_assoc_request { size_t fils_kek_len; const u8 *fils_nonces; struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; + struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS]; + const u8 *ap_mld_addr; + s8 link_id; }; /** @@ -3279,7 +3328,7 @@ struct cfg80211_wowlan_wakeup { * @kck: key confirmation key (@kck_len bytes) * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) * @kek_len: length of kek - * @kck_len length of kck + * @kck_len: length of kck * @akm: akm (oui, id) */ struct cfg80211_gtk_rekey_data { @@ -3641,6 +3690,7 @@ struct cfg80211_pmsr_ftm_result { * @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. + * @ftm: FTM result */ struct cfg80211_pmsr_result { u64 host_time, ap_tsf; @@ -3779,7 +3829,7 @@ struct cfg80211_update_owe_info { * for the entire device * @interface_stypes: bitmap of management frame subtypes registered * for the given interface - * @global_mcast_rx: mcast RX is needed globally for these subtypes + * @global_mcast_stypes: mcast RX is needed globally for these subtypes * @interface_mcast_stypes: mcast RX is needed on this interface * for these subtypes */ @@ -3824,6 +3874,11 @@ struct mgmt_frame_regs { * keep the struct wireless_dev's iftype updated. * This additionally holds the RTNL to be able to do netdev changes. * + * @add_intf_link: Add a new MLO link to the given interface. Note that + * the wdev->link[] data structure has been updated, so the new link + * address is available. + * @del_intf_link: Remove an MLO link from the given interface. + * * @add_key: add a key with the given parameters. @mac_addr will be %NULL * when adding a group key. * @@ -4178,6 +4233,13 @@ struct cfg80211_ops { enum nl80211_iftype type, struct vif_params *params); + int (*add_intf_link)(struct wiphy *wiphy, + struct wireless_dev *wdev, + unsigned int link_id); + void (*del_intf_link)(struct wiphy *wiphy, + struct wireless_dev *wdev, + unsigned int link_id); + int (*add_key)(struct wiphy *wiphy, struct net_device *netdev, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params); @@ -4201,7 +4263,8 @@ struct cfg80211_ops { struct cfg80211_ap_settings *settings); int (*change_beacon)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_beacon_data *info); - int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev); + int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id); int (*add_station)(struct wiphy *wiphy, struct net_device *dev, @@ -4309,6 +4372,7 @@ struct cfg80211_ops { int (*set_bitrate_mask)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask); @@ -4384,6 +4448,7 @@ struct cfg80211_ops { int (*get_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*start_p2p_device)(struct wiphy *wiphy, @@ -4420,6 +4485,7 @@ struct cfg80211_ops { struct cfg80211_qos_map *qos_map); int (*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev, + unsigned int link_id, struct cfg80211_chan_def *chandef); int (*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev, @@ -4545,10 +4611,14 @@ struct cfg80211_ops { * @WIPHY_FLAG_HAS_STATIC_WEP: The device supports static WEP key installation * before connection. * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys + * @WIPHY_FLAG_SUPPORTS_MLO: This is a temporary flag gating the MLO APIs, + * in order to not have them reachable in normal drivers, until we have + * complete feature/interface combinations/etc. advertisement. No driver + * should set this flag for now. */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), - /* use hole at 1 */ + WIPHY_FLAG_SUPPORTS_MLO = BIT(1), WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), @@ -4882,6 +4952,7 @@ struct wiphy_iftype_ext_capab { * @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: FTM measurement data * @ftm.supported: FTM measurement is supported * @ftm.asap: ASAP-mode is supported * @ftm.non_asap: non-ASAP-mode is supported @@ -5134,6 +5205,13 @@ struct wiphy_iftype_akm_suites { * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). + * @max_num_akm_suites: maximum number of AKM suites allowed for + * configuration through %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and + * %NL80211_CMD_START_AP. Set to NL80211_MAX_NR_AKM_SUITES if not set by + * driver. If set by driver minimum allowed value is + * NL80211_MAX_NR_AKM_SUITES in order to avoid compatibility issues with + * legacy userspace and maximum allowed value is + * CFG80211_MAX_NUM_AKM_SUITES. */ struct wiphy { struct mutex mtx; @@ -5280,6 +5358,7 @@ struct wiphy { u8 mbssid_max_interfaces; u8 ema_max_profile_periodicity; + u16 max_num_akm_suites; char priv[] __aligned(NETDEV_ALIGN); }; @@ -5505,16 +5584,9 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this * wireless device if it has no netdev - * @current_bss: (private) Used by the internal configuration code - * @chandef: (private) Used by the internal configuration code to track - * the user-set channel definition. - * @preset_chandef: (private) Used by the internal configuration code to - * track the channel to be used for AP later + * @u: union containing data specific to @iftype + * @connected: indicates if connected or not (STA mode) * @bssid: (private) Used by the internal configuration code - * @ssid: (private) Used by the internal configuration code - * @ssid_len: (private) Used by the internal configuration code - * @mesh_id_len: (private) Used by the internal configuration code - * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code * @wext.ibss: (private) IBSS data part of wext handling * @wext.connect: (private) connection handling data @@ -5564,6 +5636,9 @@ static inline void wiphy_unlock(struct wiphy *wiphy) * @pmsr_free_wk: (private) peer measurements cleanup work * @unprot_beacon_reported: (private) timestamp of last * unprotected beacon report + * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr + * @ap and @client for each link + * @valid_links: bitmap describing what elements of @links are valid */ struct wireless_dev { struct wiphy *wiphy; @@ -5585,8 +5660,6 @@ struct wireless_dev { u8 address[ETH_ALEN] __aligned(sizeof(u16)); /* currently used for IBSS and SME - might be rearranged later */ - u8 ssid[IEEE80211_MAX_SSID_LEN]; - u8 ssid_len, mesh_id_len, mesh_id_up_len; struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; enum ieee80211_bss_type conn_bss_type; @@ -5598,20 +5671,17 @@ struct wireless_dev { struct list_head event_list; spinlock_t event_lock; - struct cfg80211_internal_bss *current_bss; /* associated / joined */ - struct cfg80211_chan_def preset_chandef; - struct cfg80211_chan_def chandef; + u8 connected:1; bool ps; int ps_timeout; - int beacon_interval; - u32 ap_unexpected_nlportid; u32 owner_nlportid; bool nl_owner_dead; + /* FIXME: need to rework radar detection for MLO */ bool cac_started; unsigned long cac_start_time; unsigned int cac_time_ms; @@ -5639,6 +5709,50 @@ struct wireless_dev { struct work_struct pmsr_free_wk; unsigned long unprot_beacon_reported; + + union { + struct { + u8 connected_addr[ETH_ALEN] __aligned(2); + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } client; + struct { + int beacon_interval; + struct cfg80211_chan_def preset_chandef; + struct cfg80211_chan_def chandef; + u8 id[IEEE80211_MAX_SSID_LEN]; + u8 id_len, id_up_len; + } mesh; + struct { + struct cfg80211_chan_def preset_chandef; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + struct cfg80211_chan_def chandef; + int beacon_interval; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + u8 ssid_len; + } ibss; + struct { + struct cfg80211_chan_def chandef; + } ocb; + } u; + + struct { + u8 addr[ETH_ALEN] __aligned(2); + union { + struct { + unsigned int beacon_interval; + struct cfg80211_chan_def chandef; + } ap; + struct { + struct cfg80211_internal_bss *current_bss; + } client; + }; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 valid_links; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) @@ -5668,6 +5782,32 @@ static inline void *wdev_priv(struct wireless_dev *wdev) } /** + * wdev_chandef - return chandef pointer from wireless_dev + * @wdev: the wdev + * @link_id: the link ID for MLO + * + * Return: The chandef depending on the mode, or %NULL. + */ +struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, + unsigned int link_id); + +static inline void WARN_INVALID_LINK_ID(struct wireless_dev *wdev, + unsigned int link_id) +{ + WARN_ON(link_id && !wdev->valid_links); + WARN_ON(wdev->valid_links && + !(wdev->valid_links & BIT(link_id))); +} + +#define for_each_valid_link(link_info, link_id) \ + for (link_id = 0; \ + link_id < ((link_info)->valid_links ? \ + ARRAY_SIZE((link_info)->links) : 1); \ + link_id++) \ + if (!(link_info)->valid_links || \ + ((link_info)->valid_links & BIT(link_id))) + +/** * DOC: Utility functions * * cfg80211 offers a number of utility functions that can be useful. @@ -5943,6 +6083,7 @@ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); * @addr: the device MAC address * @iftype: the virtual interface type * @data_offset: offset of payload after the 802.11 header + * @is_amsdu: true if the 802.11 header is A-MSDU * Return: 0 on success. Non-zero on error. */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, @@ -6812,6 +6953,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * @macaddr: the MAC address of the new candidate * @ie: information elements advertised by the peer candidate * @ie_len: length of the information elements buffer + * @sig_dbm: signal level in dBm * @gfp: allocation flags * * This function notifies cfg80211 that the mesh peer candidate has been @@ -7176,13 +7318,6 @@ struct cfg80211_fils_resp_params { * indicate that this is a failure, but without a status code. * @timeout_reason is used to report the reason for the timeout in that * case. - * @bssid: The BSSID of the AP (may be %NULL) - * @bss: Entry of bss to which STA got connected to, can be obtained through - * cfg80211_get_bss() (may be %NULL). But it is recommended to store the - * bss from the connect_request and hold a reference to it and return - * through this param to avoid a warning if the bss is expired during the - * connection, esp. for those drivers implementing connect op. - * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) @@ -7194,17 +7329,41 @@ struct cfg80211_fils_resp_params { * not known. This value is used only if @status < 0 to indicate that the * failure is due to a timeout and not due to explicit rejection by the AP. * This value is ignored in other cases (@status >= 0). + * @valid_links: For MLO connection, BIT mask of the valid link ids. Otherwise + * zero. + * @ap_mld_addr: For MLO connection, MLD address of the AP. Otherwise %NULL. + * @links : For MLO connection, contains link info for the valid links indicated + * using @valid_links. For non-MLO connection, links[0] contains the + * connected AP info. + * @links.addr: For MLO connection, MAC address of the STA link. Otherwise + * %NULL. + * @links.bssid: For MLO connection, MAC address of the AP link. For non-MLO + * connection, links[0].bssid points to the BSSID of the AP (may be %NULL). + * @links.bss: For MLO connection, entry of bss to which STA link is connected. + * For non-MLO connection, links[0].bss points to entry of bss to which STA + * is connected. It can be obtained through cfg80211_get_bss() (may be + * %NULL). It is recommended to store the bss from the connect_request and + * hold a reference to it and return through this param to avoid a warning + * if the bss is expired during the connection, esp. for those drivers + * implementing connect op. Only one parameter among @bssid and @bss needs + * to be specified. */ struct cfg80211_connect_resp_params { int status; - const u8 *bssid; - struct cfg80211_bss *bss; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** @@ -7274,8 +7433,8 @@ cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, memset(¶ms, 0, sizeof(params)); params.status = status; - params.bssid = bssid; - params.bss = bss; + params.links[0].bssid = bssid; + params.links[0].bss = bss; params.req_ie = req_ie; params.req_ie_len = req_ie_len; params.resp_ie = resp_ie; @@ -7346,24 +7505,40 @@ cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, /** * struct cfg80211_roam_info - driver initiated roaming information * - * @channel: the channel of the new AP - * @bss: entry of bss to which STA got roamed (may be %NULL if %bssid is set) - * @bssid: the BSSID of the new AP (may be %NULL if %bss is set) * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @fils: FILS related roaming information. + * @valid_links: For MLO roaming, BIT mask of the new valid links is set. + * Otherwise zero. + * @ap_mld_addr: For MLO roaming, MLD address of the new AP. Otherwise %NULL. + * @links : For MLO roaming, contains new link info for the valid links set in + * @valid_links. For non-MLO roaming, links[0] contains the new AP info. + * @links.addr: For MLO roaming, MAC address of the STA link. Otherwise %NULL. + * @links.bssid: For MLO roaming, MAC address of the new AP link. For non-MLO + * roaming, links[0].bssid points to the BSSID of the new AP. May be + * %NULL if %links.bss is set. + * @links.channel: the channel of the new AP. + * @links.bss: For MLO roaming, entry of new bss to which STA link got + * roamed. For non-MLO roaming, links[0].bss points to entry of bss to + * which STA got roamed (may be %NULL if %links.bssid is set) */ struct cfg80211_roam_info { - struct ieee80211_channel *channel; - struct cfg80211_bss *bss; - const u8 *bssid; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; + + const u8 *ap_mld_addr; + u16 valid_links; + struct { + const u8 *addr; + const u8 *bssid; + struct ieee80211_channel *channel; + struct cfg80211_bss *bss; + } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** @@ -7882,12 +8057,14 @@ bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition + * @link_id: the link ID for MLO, must be 0 for non-MLO * * Caller must acquire wdev_lock, therefore must only be called from sleepable * driver context! */ void cfg80211_ch_switch_notify(struct net_device *dev, - struct cfg80211_chan_def *chandef); + struct cfg80211_chan_def *chandef, + unsigned int link_id); /* * cfg80211_ch_switch_started_notify - notify channel switch start diff --git a/include/net/devlink.h b/include/net/devlink.h index 2a2a2a0c93f7..b1b5c19a8316 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1521,15 +1521,6 @@ void devl_unlock(struct devlink *devlink); void devl_assert_locked(struct devlink *devlink); bool devl_lock_is_held(struct devlink *devlink); -int devl_port_register(struct devlink *devlink, - struct devlink_port *devlink_port, - unsigned int port_index); -void devl_port_unregister(struct devlink_port *devlink_port); - -int devl_rate_leaf_create(struct devlink_port *port, void *priv); -void devl_rate_leaf_destroy(struct devlink_port *devlink_port); -void devl_rate_nodes_destroy(struct devlink *devlink); - struct ib_device; struct net *devlink_net(const struct devlink *devlink); @@ -1551,9 +1542,13 @@ void devlink_set_features(struct devlink *devlink, u64 features); void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_free(struct devlink *devlink); +int devl_port_register(struct devlink *devlink, + struct devlink_port *devlink_port, + unsigned int port_index); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index); +void devl_port_unregister(struct devlink_port *devlink_port); void devlink_port_unregister(struct devlink_port *devlink_port); void devlink_port_type_eth_set(struct devlink_port *devlink_port, struct net_device *netdev); @@ -1569,9 +1564,9 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 contro void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller, u16 pf, u32 sf, bool external); -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); +int devl_rate_leaf_create(struct devlink_port *port, void *priv); +void devl_rate_leaf_destroy(struct devlink_port *devlink_port); +void devl_rate_nodes_destroy(struct devlink *devlink); void devlink_port_linecard_set(struct devlink_port *devlink_port, struct devlink_linecard *linecard); struct devlink_linecard * diff --git a/include/net/dropreason.h b/include/net/dropreason.h new file mode 100644 index 000000000000..fae9b40e54fa --- /dev/null +++ b/include/net/dropreason.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _LINUX_DROPREASON_H +#define _LINUX_DROPREASON_H + +/** + * enum skb_drop_reason - the reasons of skb drops + * + * The reason of skb drop, which is used in kfree_skb_reason(). + */ +enum skb_drop_reason { + /** + * @SKB_NOT_DROPPED_YET: skb is not dropped yet (used for no-drop case) + */ + SKB_NOT_DROPPED_YET = 0, + /** @SKB_DROP_REASON_NOT_SPECIFIED: drop reason is not specified */ + SKB_DROP_REASON_NOT_SPECIFIED, + /** @SKB_DROP_REASON_NO_SOCKET: socket not found */ + SKB_DROP_REASON_NO_SOCKET, + /** @SKB_DROP_REASON_PKT_TOO_SMALL: packet size is too small */ + SKB_DROP_REASON_PKT_TOO_SMALL, + /** @SKB_DROP_REASON_TCP_CSUM: TCP checksum error */ + SKB_DROP_REASON_TCP_CSUM, + /** @SKB_DROP_REASON_SOCKET_FILTER: dropped by socket filter */ + SKB_DROP_REASON_SOCKET_FILTER, + /** @SKB_DROP_REASON_UDP_CSUM: UDP checksum error */ + SKB_DROP_REASON_UDP_CSUM, + /** @SKB_DROP_REASON_NETFILTER_DROP: dropped by netfilter */ + SKB_DROP_REASON_NETFILTER_DROP, + /** + * @SKB_DROP_REASON_OTHERHOST: packet don't belong to current host + * (interface is in promisc mode) + */ + SKB_DROP_REASON_OTHERHOST, + /** @SKB_DROP_REASON_IP_CSUM: IP checksum error */ + SKB_DROP_REASON_IP_CSUM, + /** + * @SKB_DROP_REASON_IP_INHDR: there is something wrong with IP header (see + * IPSTATS_MIB_INHDRERRORS) + */ + SKB_DROP_REASON_IP_INHDR, + /** + * @SKB_DROP_REASON_IP_RPFILTER: IP rpfilter validate failed. see the + * document for rp_filter in ip-sysctl.rst for more information + */ + SKB_DROP_REASON_IP_RPFILTER, + /** + * @SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST: destination address of L2 is + * multicast, but L3 is unicast. + */ + SKB_DROP_REASON_UNICAST_IN_L2_MULTICAST, + /** @SKB_DROP_REASON_XFRM_POLICY: xfrm policy check failed */ + SKB_DROP_REASON_XFRM_POLICY, + /** @SKB_DROP_REASON_IP_NOPROTO: no support for IP protocol */ + SKB_DROP_REASON_IP_NOPROTO, + /** @SKB_DROP_REASON_SOCKET_RCVBUFF: socket receive buff is full */ + SKB_DROP_REASON_SOCKET_RCVBUFF, + /** + * @SKB_DROP_REASON_PROTO_MEM: proto memory limition, such as udp packet + * drop out of udp_memory_allocated. + */ + SKB_DROP_REASON_PROTO_MEM, + /** + * @SKB_DROP_REASON_TCP_MD5NOTFOUND: no MD5 hash and one expected, + * corresponding to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, + /** + * @SKB_DROP_REASON_TCP_MD5UNEXPECTED: MD5 hash and we're not expecting + * one, corresponding to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, + /** + * @SKB_DROP_REASON_TCP_MD5FAILURE: MD5 hash and its wrong, corresponding + * to LINUX_MIB_TCPMD5FAILURE + */ + SKB_DROP_REASON_TCP_MD5FAILURE, + /** + * @SKB_DROP_REASON_SOCKET_BACKLOG: failed to add skb to socket backlog ( + * see LINUX_MIB_TCPBACKLOGDROP) + */ + SKB_DROP_REASON_SOCKET_BACKLOG, + /** @SKB_DROP_REASON_TCP_FLAGS: TCP flags invalid */ + SKB_DROP_REASON_TCP_FLAGS, + /** + * @SKB_DROP_REASON_TCP_ZEROWINDOW: TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_ZEROWINDOW, + /** + * @SKB_DROP_REASON_TCP_OLD_DATA: the TCP data reveived is already + * received before (spurious retrans may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OLD_DATA, + /** + * @SKB_DROP_REASON_TCP_OVERWINDOW: the TCP data is out of window, + * the seq of the first byte exceed the right edges of receive + * window + */ + SKB_DROP_REASON_TCP_OVERWINDOW, + /** + * @SKB_DROP_REASON_TCP_OFOMERGE: the data of skb is already in the ofo + * queue, corresponding to LINUX_MIB_TCPOFOMERGE + */ + SKB_DROP_REASON_TCP_OFOMERGE, + /** + * @SKB_DROP_REASON_TCP_RFC7323_PAWS: PAWS check, corresponding to + * LINUX_MIB_PAWSESTABREJECTED + */ + SKB_DROP_REASON_TCP_RFC7323_PAWS, + /** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */ + SKB_DROP_REASON_TCP_INVALID_SEQUENCE, + /** @SKB_DROP_REASON_TCP_RESET: Invalid RST packet */ + SKB_DROP_REASON_TCP_RESET, + /** + * @SKB_DROP_REASON_TCP_INVALID_SYN: Incoming packet has unexpected + * SYN flag + */ + SKB_DROP_REASON_TCP_INVALID_SYN, + /** @SKB_DROP_REASON_TCP_CLOSE: TCP socket in CLOSE state */ + SKB_DROP_REASON_TCP_CLOSE, + /** @SKB_DROP_REASON_TCP_FASTOPEN: dropped by FASTOPEN request socket */ + SKB_DROP_REASON_TCP_FASTOPEN, + /** @SKB_DROP_REASON_TCP_OLD_ACK: TCP ACK is old, but in window */ + SKB_DROP_REASON_TCP_OLD_ACK, + /** @SKB_DROP_REASON_TCP_TOO_OLD_ACK: TCP ACK is too old */ + SKB_DROP_REASON_TCP_TOO_OLD_ACK, + /** + * @SKB_DROP_REASON_TCP_ACK_UNSENT_DATA: TCP ACK for data we haven't + * sent yet + */ + SKB_DROP_REASON_TCP_ACK_UNSENT_DATA, + /** @SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE: pruned from TCP OFO queue */ + SKB_DROP_REASON_TCP_OFO_QUEUE_PRUNE, + /** @SKB_DROP_REASON_TCP_OFO_DROP: data already in receive queue */ + SKB_DROP_REASON_TCP_OFO_DROP, + /** @SKB_DROP_REASON_IP_OUTNOROUTES: route lookup failed */ + SKB_DROP_REASON_IP_OUTNOROUTES, + /** + * @SKB_DROP_REASON_BPF_CGROUP_EGRESS: dropped by BPF_PROG_TYPE_CGROUP_SKB + * eBPF program + */ + SKB_DROP_REASON_BPF_CGROUP_EGRESS, + /** @SKB_DROP_REASON_IPV6DISABLED: IPv6 is disabled on the device */ + SKB_DROP_REASON_IPV6DISABLED, + /** @SKB_DROP_REASON_NEIGH_CREATEFAIL: failed to create neigh entry */ + SKB_DROP_REASON_NEIGH_CREATEFAIL, + /** @SKB_DROP_REASON_NEIGH_FAILED: neigh entry in failed state */ + SKB_DROP_REASON_NEIGH_FAILED, + /** @SKB_DROP_REASON_NEIGH_QUEUEFULL: arp_queue for neigh entry is full */ + SKB_DROP_REASON_NEIGH_QUEUEFULL, + /** @SKB_DROP_REASON_NEIGH_DEAD: neigh entry is dead */ + SKB_DROP_REASON_NEIGH_DEAD, + /** @SKB_DROP_REASON_TC_EGRESS: dropped in TC egress HOOK */ + SKB_DROP_REASON_TC_EGRESS, + /** + * @SKB_DROP_REASON_QDISC_DROP: dropped by qdisc when packet outputting ( + * failed to enqueue to current qdisc) + */ + SKB_DROP_REASON_QDISC_DROP, + /** + * @SKB_DROP_REASON_CPU_BACKLOG: failed to enqueue the skb to the per CPU + * backlog queue. This can be caused by backlog queue full (see + * netdev_max_backlog in net.rst) or RPS flow limit + */ + SKB_DROP_REASON_CPU_BACKLOG, + /** @SKB_DROP_REASON_XDP: dropped by XDP in input path */ + SKB_DROP_REASON_XDP, + /** @SKB_DROP_REASON_TC_INGRESS: dropped in TC ingress HOOK */ + SKB_DROP_REASON_TC_INGRESS, + /** @SKB_DROP_REASON_UNHANDLED_PROTO: protocol not implemented or not supported */ + SKB_DROP_REASON_UNHANDLED_PROTO, + /** @SKB_DROP_REASON_SKB_CSUM: sk_buff checksum computation error */ + SKB_DROP_REASON_SKB_CSUM, + /** @SKB_DROP_REASON_SKB_GSO_SEG: gso segmentation error */ + SKB_DROP_REASON_SKB_GSO_SEG, + /** + * @SKB_DROP_REASON_SKB_UCOPY_FAULT: failed to copy data from user space, + * e.g., via zerocopy_sg_from_iter() or skb_orphan_frags_rx() + */ + SKB_DROP_REASON_SKB_UCOPY_FAULT, + /** @SKB_DROP_REASON_DEV_HDR: device driver specific header/metadata is invalid */ + SKB_DROP_REASON_DEV_HDR, + /** + * @SKB_DROP_REASON_DEV_READY: the device is not ready to xmit/recv due to + * any of its data structure that is not up/ready/initialized, + * e.g., the IFF_UP is not set, or driver specific tun->tfiles[txq] + * is not initialized + */ + SKB_DROP_REASON_DEV_READY, + /** @SKB_DROP_REASON_FULL_RING: ring buffer is full */ + SKB_DROP_REASON_FULL_RING, + /** @SKB_DROP_REASON_NOMEM: error due to OOM */ + SKB_DROP_REASON_NOMEM, + /** + * @SKB_DROP_REASON_HDR_TRUNC: failed to trunc/extract the header from + * networking data, e.g., failed to pull the protocol header from + * frags via pskb_may_pull() + */ + SKB_DROP_REASON_HDR_TRUNC, + /** + * @SKB_DROP_REASON_TAP_FILTER: dropped by (ebpf) filter directly attached + * to tun/tap, e.g., via TUNSETFILTEREBPF + */ + SKB_DROP_REASON_TAP_FILTER, + /** + * @SKB_DROP_REASON_TAP_TXFILTER: dropped by tx filter implemented at + * tun/tap, e.g., check_filter() + */ + SKB_DROP_REASON_TAP_TXFILTER, + /** @SKB_DROP_REASON_ICMP_CSUM: ICMP checksum error */ + SKB_DROP_REASON_ICMP_CSUM, + /** + * @SKB_DROP_REASON_INVALID_PROTO: the packet doesn't follow RFC 2211, + * such as a broadcasts ICMP_TIMESTAMP + */ + SKB_DROP_REASON_INVALID_PROTO, + /** + * @SKB_DROP_REASON_IP_INADDRERRORS: host unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INADDRERRORS, + /** + * @SKB_DROP_REASON_IP_INNOROUTES: network unreachable, corresponding to + * IPSTATS_MIB_INADDRERRORS + */ + SKB_DROP_REASON_IP_INNOROUTES, + /** + * @SKB_DROP_REASON_PKT_TOO_BIG: packet size is too big (maybe exceed the + * MTU) + */ + SKB_DROP_REASON_PKT_TOO_BIG, + /** + * @SKB_DROP_REASON_MAX: the maximum of drop reason, which shouldn't be + * used as a real 'reason' + */ + SKB_DROP_REASON_MAX, +}; + +#define SKB_DR_INIT(name, reason) \ + enum skb_drop_reason name = SKB_DROP_REASON_##reason +#define SKB_DR(name) \ + SKB_DR_INIT(name, NOT_SPECIFIED) +#define SKB_DR_SET(name, reason) \ + (name = SKB_DROP_REASON_##reason) +#define SKB_DR_OR(name, reason) \ + do { \ + if (name == SKB_DROP_REASON_NOT_SPECIFIED || \ + name == SKB_NOT_DROPPED_YET) \ + SKB_DR_SET(name, reason); \ + } while (0) + +extern const char * const drop_reasons[]; + +#endif diff --git a/include/net/dsa.h b/include/net/dsa.h index 14f07275852b..b902b31bebce 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -53,6 +53,8 @@ struct phylink_link_state; #define DSA_TAG_PROTO_SJA1110_VALUE 23 #define DSA_TAG_PROTO_RTL8_4_VALUE 24 #define DSA_TAG_PROTO_RTL8_4T_VALUE 25 +#define DSA_TAG_PROTO_RZN1_A5PSW_VALUE 26 +#define DSA_TAG_PROTO_LAN937X_VALUE 27 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -81,6 +83,8 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, DSA_TAG_PROTO_RTL8_4 = DSA_TAG_PROTO_RTL8_4_VALUE, DSA_TAG_PROTO_RTL8_4T = DSA_TAG_PROTO_RTL8_4T_VALUE, + DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, + DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, }; struct dsa_switch; @@ -888,8 +892,13 @@ struct dsa_switch_ops { struct ethtool_eth_mac_stats *mac_stats); void (*get_eth_ctrl_stats)(struct dsa_switch *ds, int port, struct ethtool_eth_ctrl_stats *ctrl_stats); + void (*get_rmon_stats)(struct dsa_switch *ds, int port, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges); void (*get_stats64)(struct dsa_switch *ds, int port, struct rtnl_link_stats64 *s); + void (*get_pause_stats)(struct dsa_switch *ds, int port, + struct ethtool_pause_stats *pause_stats); void (*self_test)(struct dsa_switch *ds, int port, struct ethtool_test *etest, u64 *data); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index a4c6057c7097..0f9544a9bb9e 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -179,6 +179,22 @@ struct flow_dissector_key_ports { }; /** + * struct flow_dissector_key_ports_range + * @tp: port number from packet + * @tp_min: min port number in range + * @tp_max: max port number in range + */ +struct flow_dissector_key_ports_range { + union { + struct flow_dissector_key_ports tp; + struct { + struct flow_dissector_key_ports tp_min; + struct flow_dissector_key_ports tp_max; + }; + }; +}; + +/** * flow_dissector_key_icmp: * type: ICMP type * code: ICMP code diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 7ac313858037..a8d8512b7059 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -48,6 +48,10 @@ struct flow_match_ports { struct flow_dissector_key_ports *key, *mask; }; +struct flow_match_ports_range { + struct flow_dissector_key_ports_range *key, *mask; +}; + struct flow_match_icmp { struct flow_dissector_key_icmp *key, *mask; }; @@ -94,6 +98,8 @@ void flow_rule_match_ip(const struct flow_rule *rule, struct flow_match_ip *out); void flow_rule_match_ports(const struct flow_rule *rule, struct flow_match_ports *out); +void flow_rule_match_ports_range(const struct flow_rule *rule, + struct flow_match_ports_range *out); void flow_rule_match_tcp(const struct flow_rule *rule, struct flow_match_tcp *out); void flow_rule_match_icmp(const struct flow_rule *rule, diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h index a5f67a2c0c73..524b510f1c68 100644 --- a/include/net/fq_impl.h +++ b/include/net/fq_impl.h @@ -358,8 +358,7 @@ static int fq_init(struct fq *fq, int flows_cnt) if (!fq->flows) return -ENOMEM; - fq->flows_bitmap = kcalloc(BITS_TO_LONGS(fq->flows_cnt), sizeof(long), - GFP_KERNEL); + fq->flows_bitmap = bitmap_zalloc(fq->flows_cnt, GFP_KERNEL); if (!fq->flows_bitmap) { kvfree(fq->flows); fq->flows = NULL; @@ -383,7 +382,7 @@ static void fq_reset(struct fq *fq, kvfree(fq->flows); fq->flows = NULL; - kfree(fq->flows_bitmap); + bitmap_free(fq->flows_bitmap); fq->flows_bitmap = NULL; } diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index c24fa934221d..70cbc4a72669 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -456,8 +456,8 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len) struct pcpu_sw_netstats *tstats = get_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); - tstats->tx_bytes += pkt_len; - tstats->tx_packets++; + u64_stats_add(&tstats->tx_bytes, pkt_len); + u64_stats_inc(&tstats->tx_packets); u64_stats_update_end(&tstats->syncp); put_cpu_ptr(tstats); } else { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 47642b020706..1c005a30313f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -261,11 +261,13 @@ enum ieee80211_chanctx_switch_mode { * done. * * @vif: the vif that should be switched from old_ctx to new_ctx + * @link_id: the link ID that's switching * @old_ctx: the old context to which the vif was assigned * @new_ctx: the new context to which the vif must be assigned */ struct ieee80211_vif_chanctx_switch { struct ieee80211_vif *vif; + unsigned int link_id; struct ieee80211_chanctx_conf *old_ctx; struct ieee80211_chanctx_conf *new_ctx; }; @@ -273,8 +275,8 @@ struct ieee80211_vif_chanctx_switch { /** * enum ieee80211_bss_change - BSS change notification flags * - * These flags are used with the bss_info_changed() callback - * to indicate which BSS parameter changed. + * These flags are used with the bss_info_changed(), link_info_changed() + * and vif_cfg_changed() callbacks to indicate which parameter(s) changed. * * @BSS_CHANGED_ASSOC: association status changed (associated/disassociated), * also implies a change in the AID. @@ -513,6 +515,7 @@ struct ieee80211_fils_discovery { * This structure keeps information about a BSS (and an association * to that BSS) that can change during the lifetime of the BSS. * + * @addr: (link) address used locally * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE * @uora_exists: is the UORA element advertised by AP * @ack_enabled: indicates support to receive a multi-TID that solicits either @@ -526,11 +529,6 @@ struct ieee80211_fils_discovery { * mode only, set if the AP advertises TWT responder role) * @twt_protected: does this BSS support protected TWT frames * @twt_broadcast: does this BSS support broadcast TWT - * @assoc: association status - * @ibss_joined: indicates whether this station is part of an IBSS - * or not - * @ibss_creator: indicates if a new IBSS network is being created - * @aid: association ID number, valid only when @assoc is true * @use_cts_prot: use CTS protection * @use_short_preamble: use 802.11b short preamble * @use_short_slot: use short slot time (only relevant for ERP) @@ -551,6 +549,8 @@ struct ieee80211_fils_discovery { * IMPORTANT: These three sync_* parameters would possibly be out of sync * by the time the driver will use them. The synchronized view is currently * guaranteed only in certain callbacks. + * Note also that this is not used with MLD associations, mac80211 doesn't + * know how to track beacons for all of the links for this. * @beacon_int: beacon interval * @assoc_capability: capabilities taken from assoc resp * @basic_rates: bitmap of basic rates, each bit stands for an @@ -576,21 +576,9 @@ struct ieee80211_fils_discovery { * threshold event and can't be enabled simultaneously with it. * @cqm_rssi_high: Connection quality monitor RSSI upper threshold. * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis - * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The - * may filter ARP queries targeted for other addresses than listed here. - * The driver must allow ARP queries targeted for all address listed here - * to pass through. An empty list implies no ARP queries need to pass. - * @arp_addr_cnt: Number of addresses currently on the list. Note that this - * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list - * array size), it's up to the driver what to do in that case. * @qos: This is a QoS-enabled BSS. - * @idle: This interface is idle. There's also a global idle flag in the - * hardware config which may be more appropriate depending on what - * your driver/device needs to do. * @ps: power-save mode (STA only). This flag is NOT affected by * offchannel/dynamic_ps operations. - * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. - * @ssid_len: Length of SSID given in @ssid. * @hidden_ssid: The SSID of the current vif is hidden. Only valid in AP-mode. * @txpower: TX power in dBm. INT_MIN means not configured. * @txpower_type: TX power adjustment used to control per packet Transmit @@ -628,7 +616,6 @@ struct ieee80211_fils_discovery { * @fils_discovery: FILS discovery configuration * @unsol_bcast_probe_resp_interval: Unsolicited broadcast probe response * interval. - * @s1g: BSS is S1G BSS (affects Association Request format). * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. * @power_type: power type of BSS for 6 GHz @@ -636,9 +623,23 @@ struct ieee80211_fils_discovery { * @tx_pwr_env_num: number of @tx_pwr_env. * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT + * @csa_active: marks whether a channel switch is going on. Internally it is + * write-protected by sdata_lock and local->mtx so holding either is fine + * for read access. + * @mu_mimo_owner: indicates interface owns MU-MIMO capability + * @chanctx_conf: The channel context this interface is assigned to, or %NULL + * when it is not assigned. This pointer is RCU-protected due to the TX + * path needing to access it; even though the netdev carrier will always + * be off when it is %NULL there can still be races and packets could be + * processed after it switches back to %NULL. + * @color_change_active: marks whether a color change is ongoing. Internally it is + * write-protected by sdata_lock and local->mtx so holding either is fine + * for read access. + * @color_change_color: the bss color that will be used after the change. */ struct ieee80211_bss_conf { const u8 *bssid; + u8 addr[ETH_ALEN] __aligned(2); u8 htc_trig_based_pkt_ext; bool uora_exists; u8 uora_ocw_range; @@ -648,10 +649,6 @@ struct ieee80211_bss_conf { bool twt_responder; bool twt_protected; bool twt_broadcast; - /* association related data */ - bool assoc, ibss_joined; - bool ibss_creator; - u16 aid; /* erp related data */ bool use_cts_prot; bool use_short_preamble; @@ -673,13 +670,8 @@ struct ieee80211_bss_conf { s32 cqm_rssi_high; struct cfg80211_chan_def chandef; struct ieee80211_mu_group_data mu_group; - __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; - int arp_addr_cnt; bool qos; - bool idle; bool ps; - u8 ssid[IEEE80211_MAX_SSID_LEN]; - size_t ssid_len; bool hidden_ssid; int txpower; enum nl80211_tx_power_setting txpower_type; @@ -704,13 +696,19 @@ struct ieee80211_bss_conf { struct cfg80211_he_bss_color he_bss_color; struct ieee80211_fils_discovery fils_discovery; u32 unsol_bcast_probe_resp_interval; - bool s1g; struct cfg80211_bitrate_mask beacon_tx_rate; enum ieee80211_ap_reg_power power_type; struct ieee80211_tx_pwr_env tx_pwr_env[IEEE80211_TPE_MAX_IE_COUNT]; u8 tx_pwr_env_num; u8 pwr_reduction; bool eht_support; + + bool csa_active; + bool mu_mimo_owner; + struct ieee80211_chanctx_conf __rcu *chanctx_conf; + + bool color_change_active; + u8 color_change_color; }; /** @@ -869,6 +867,10 @@ enum mac80211_tx_info_flags { * @IEEE80211_TX_CTRL_DONT_REORDER: This frame should not be reordered * relative to other frames that have this flag set, independent * of their QoS TID or other priority field values. + * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this + * frame should be transmitted on the specific link. This really is + * only relevant for frames that do not have data present, and is + * also not used for 802.3 format frames. * * These flags are used in tx_info->control.flags. */ @@ -882,8 +884,11 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTCFL_NEED_TXPROCESSING = BIT(6), IEEE80211_TX_CTRL_NO_SEQNO = BIT(7), IEEE80211_TX_CTRL_DONT_REORDER = BIT(8), + IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000, }; +#define IEEE80211_LINK_UNSPECIFIED 0xf + /** * enum mac80211_tx_status_flags - flags to describe transmit status * @@ -1031,7 +1036,9 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * (3) TX status information - driver tells mac80211 what happened * * @flags: transmit info flags, defined above - * @band: the band to transmit on (use for checking for races) + * @band: the band to transmit on (use e.g. for checking for races), + * not valid if the interface is an MLD since we won't know which + * link the frame will be transmitted on * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @ack_frame_id: internal frame ID for TX status, used internally * @tx_time_est: TX time estimate in units of 4us, used internally @@ -1702,21 +1709,55 @@ enum ieee80211_offload_flags { }; /** + * struct ieee80211_vif_cfg - interface configuration + * @assoc: association status + * @ibss_joined: indicates whether this station is part of an IBSS or not + * @ibss_creator: indicates if a new IBSS network is being created + * @aid: association ID number, valid only when @assoc is true + * @arp_addr_list: List of IPv4 addresses for hardware ARP filtering. The + * may filter ARP queries targeted for other addresses than listed here. + * The driver must allow ARP queries targeted for all address listed here + * to pass through. An empty list implies no ARP queries need to pass. + * @arp_addr_cnt: Number of addresses currently on the list. Note that this + * may be larger than %IEEE80211_BSS_ARP_ADDR_LIST_LEN (the arp_addr_list + * array size), it's up to the driver what to do in that case. + * @ssid: The SSID of the current vif. Valid in AP and IBSS mode. + * @ssid_len: Length of SSID given in @ssid. + * @s1g: BSS is S1G BSS (affects Association Request format). + * @idle: This interface is idle. There's also a global idle flag in the + * hardware config which may be more appropriate depending on what + * your driver/device needs to do. + */ +struct ieee80211_vif_cfg { + /* association related data */ + bool assoc, ibss_joined; + bool ibss_creator; + u16 aid; + + __be32 arp_addr_list[IEEE80211_BSS_ARP_ADDR_LIST_LEN]; + int arp_addr_cnt; + u8 ssid[IEEE80211_MAX_SSID_LEN]; + size_t ssid_len; + bool s1g; + bool idle; +}; + +/** * struct ieee80211_vif - per-interface data * * Data in this structure is continually present for driver * use during the life of a virtual interface. * * @type: type of this virtual interface + * @cfg: vif configuration, see &struct ieee80211_vif_cfg * @bss_conf: BSS configuration for this interface, either our own * or the BSS we're associated to + * @link_conf: in case of MLD, the per-link BSS configuration, + * indexed by link ID + * @valid_links: bitmap of valid links, or 0 for non-MLO. * @addr: address of this interface * @p2p: indicates whether this AP or STA interface is a p2p * interface, i.e. a GO or p2p-sta respectively - * @csa_active: marks whether a channel switch is going on. Internally it is - * write-protected by sdata_lock and local->mtx so holding either is fine - * for read access. - * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @driver_flags: flags/capabilities the driver has for this interface, * these need to be set (or cleared) when the interface is added * or, if supported by the driver, the interface type is changed @@ -1728,11 +1769,6 @@ enum ieee80211_offload_flags { * restrictions. * @hw_queue: hardware queue for each AC * @cab_queue: content-after-beacon (DTIM beacon really) queue, AP mode only - * @chanctx_conf: The channel context this interface is assigned to, or %NULL - * when it is not assigned. This pointer is RCU-protected due to the TX - * path needing to access it; even though the netdev carrier will always - * be off when it is %NULL there can still be races and packets could be - * processed after it switches back to %NULL. * @debugfs_dir: debugfs dentry, can be used by drivers to create own per * interface debug files. Note that it will be NULL for the virtual * monitor interface (if that is requested.) @@ -1747,27 +1783,22 @@ enum ieee80211_offload_flags { * protected by fq->lock. * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. - * @color_change_active: marks whether a color change is ongoing. Internally it is - * write-protected by sdata_lock and local->mtx so holding either is fine - * for read access. - * @color_change_color: the bss color that will be used after the change. * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. */ struct ieee80211_vif { enum nl80211_iftype type; + struct ieee80211_vif_cfg cfg; struct ieee80211_bss_conf bss_conf; + struct ieee80211_bss_conf *link_conf[IEEE80211_MLD_MAX_NUM_LINKS]; + u16 valid_links; u8 addr[ETH_ALEN] __aligned(2); bool p2p; - bool csa_active; - bool mu_mimo_owner; u8 cab_queue; u8 hw_queue[IEEE80211_NUM_ACS]; struct ieee80211_txq *txq; - struct ieee80211_chanctx_conf __rcu *chanctx_conf; - u32 driver_flags; u32 offload_flags; @@ -1780,9 +1811,6 @@ struct ieee80211_vif { bool txqs_stopped[IEEE80211_NUM_ACS]; - bool color_change_active; - u8 color_change_color; - struct ieee80211_vif *mbssid_tx_vif; /* must be last */ @@ -1959,36 +1987,6 @@ struct ieee80211_key_seq { }; /** - * struct ieee80211_cipher_scheme - cipher scheme - * - * This structure contains a cipher scheme information defining - * the secure packet crypto handling. - * - * @cipher: a cipher suite selector - * @iftype: a cipher iftype bit mask indicating an allowed cipher usage - * @hdr_len: a length of a security header used the cipher - * @pn_len: a length of a packet number in the security header - * @pn_off: an offset of pn from the beginning of the security header - * @key_idx_off: an offset of key index byte in the security header - * @key_idx_mask: a bit mask of key_idx bits - * @key_idx_shift: a bit shift needed to get key_idx - * key_idx value calculation: - * (sec_header_base[key_idx_off] & key_idx_mask) >> key_idx_shift - * @mic_len: a mic length in bytes - */ -struct ieee80211_cipher_scheme { - u32 cipher; - u16 iftype; - u8 hdr_len; - u8 pn_len; - u8 pn_off; - u8 key_idx_off; - u8 key_idx_mask; - u8 key_idx_shift; - u8 mic_len; -}; - -/** * enum set_key_cmd - key command * * Used with the set_key() callback in &struct ieee80211_ops, this @@ -2076,8 +2074,6 @@ 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) @@ -2154,7 +2150,6 @@ struct ieee80211_link_sta { * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID * @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 @@ -2166,6 +2161,7 @@ struct ieee80211_link_sta { * @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. + * @valid_links: bitmap of valid links, or 0 for non-MLO */ struct ieee80211_sta { u8 addr[ETH_ALEN]; @@ -2203,9 +2199,9 @@ struct ieee80211_sta { struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; - bool multi_link_sta; + u16 valid_links; struct ieee80211_link_sta deflink; - struct ieee80211_link_sta *link[MAX_STA_LINKS]; + struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; /* must be last */ u8 drv_priv[] __aligned(sizeof(void *)); @@ -2664,9 +2660,6 @@ enum ieee80211_hw_flags { * deliver to a WMM STA during any Service Period triggered by the WMM STA. * Use IEEE80211_WMM_IE_STA_QOSINFO_SP_* for correct values. * - * @n_cipher_schemes: a size of an array of cipher schemes definitions. - * @cipher_schemes: a pointer to an array of cipher scheme definitions - * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. * @@ -2716,8 +2709,6 @@ struct ieee80211_hw { netdev_features_t netdev_features; u8 uapsd_queues; u8 uapsd_max_sp_len; - u8 n_cipher_schemes; - const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; u8 weight_multiplier; @@ -3549,6 +3540,22 @@ struct ieee80211_prep_tx_info { * for association indication. The @changed parameter indicates which * of the bss parameters has changed when a call is made. The callback * can sleep. + * Note: this callback is called if @vif_cfg_changed or @link_info_changed + * are not implemented. + * + * @vif_cfg_changed: Handler for configuration requests related to interface + * (MLD) parameters from &struct ieee80211_vif_cfg that vary during the + * lifetime of the interface (e.g. assoc status, IP addresses, etc.) + * The @changed parameter indicates which value changed. + * The callback can sleep. + * + * @link_info_changed: Handler for configuration requests related to link + * parameters from &struct ieee80211_bss_conf that are related to an + * individual link. e.g. legacy/HT/VHT/... rate information. + * The @changed parameter indicates which value changed, and the @link_id + * parameter indicates the link ID. Note that the @link_id will be 0 for + * non-MLO connections. + * The callback can sleep. * * @prepare_multicast: Prepare for multicast filter configuration. * This callback is optional, and its return value is passed @@ -4034,6 +4041,18 @@ struct ieee80211_prep_tx_info { * disable background CAC/radar detection. * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to * resolve a path for hardware flow offloading + * @change_vif_links: Change the valid links on an interface, note that while + * removing the old link information is still valid (link_conf pointer), + * but may immediately disappear after the function returns. The old or + * new links bitmaps may be 0 if going from/to a non-MLO situation. + * The @old array contains pointers to the old bss_conf structures + * that were already removed, in case they're needed. + * This callback can sleep. + * @change_sta_links: Change the valid links of a station, similar to + * @change_vif_links. This callback can sleep. + * Note that a sta can also be inserted or removed with valid links, + * i.e. passed to @sta_add/@sta_state with sta->valid_links not zero. + * In fact, cannot change from having valid_links and not having them. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4057,10 +4076,18 @@ struct ieee80211_ops { void (*bss_info_changed)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *info, - u32 changed); + u64 changed); + void (*vif_cfg_changed)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u64 changed); + void (*link_info_changed)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + unsigned int link_id, u64 changed); - int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); - void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); + int (*start_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id); + void (*stop_ap)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id); u64 (*prepare_multicast)(struct ieee80211_hw *hw, struct netdev_hw_addr_list *mc_list); @@ -4262,9 +4289,11 @@ struct ieee80211_ops { u32 changed); int (*assign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, struct ieee80211_chanctx_conf *ctx); void (*unassign_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + unsigned int link_id, struct ieee80211_chanctx_conf *ctx); int (*switch_vif_chanctx)(struct ieee80211_hw *hw, struct ieee80211_vif_chanctx_switch *vifs, @@ -4369,6 +4398,14 @@ struct ieee80211_ops { struct ieee80211_sta *sta, struct net_device_path_ctx *ctx, struct net_device_path *path); + int (*change_vif_links)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u16 old_links, u16 new_links, + struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS]); + int (*change_sta_links)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + u16 old_links, u16 new_links); }; /** @@ -5032,6 +5069,7 @@ struct ieee80211_mutable_offsets { * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @offs: &struct ieee80211_mutable_offsets pointer to struct that will * receive the offsets that may be updated by the driver. + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * If the driver implements beaconing modes, it must use this function to * obtain the beacon template. @@ -5048,7 +5086,8 @@ struct ieee80211_mutable_offsets { struct sk_buff * ieee80211_beacon_get_template(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - struct ieee80211_mutable_offsets *offs); + struct ieee80211_mutable_offsets *offs, + unsigned int link_id); /** * ieee80211_beacon_get_tim - beacon generation function @@ -5059,6 +5098,7 @@ ieee80211_beacon_get_template(struct ieee80211_hw *hw, * @tim_length: pointer to variable that will receive the TIM IE length, * (including the ID and length bytes!). * Set to 0 if invalid (in non-AP modes). + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * If the driver implements beaconing modes, it must use this function to * obtain the beacon frame. @@ -5074,21 +5114,24 @@ ieee80211_beacon_get_template(struct ieee80211_hw *hw, */ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_vif *vif, - u16 *tim_offset, u16 *tim_length); + u16 *tim_offset, u16 *tim_length, + unsigned int link_id); /** * ieee80211_beacon_get - beacon generation function * @hw: pointer obtained from ieee80211_alloc_hw(). * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: the link id to which the beacon belongs (or 0 for a non-MLD AP) * * See ieee80211_beacon_get_tim(). * * Return: See ieee80211_beacon_get_tim(). */ static inline struct sk_buff *ieee80211_beacon_get(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) + struct ieee80211_vif *vif, + unsigned int link_id) { - return ieee80211_beacon_get_tim(hw, vif, NULL, NULL); + return ieee80211_beacon_get_tim(hw, vif, NULL, NULL, link_id); } /** @@ -6195,7 +6238,7 @@ void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success); /** * ieee80211_channel_switch_disconnect - disconnect due to channel switch error - * @vif &struct ieee80211_vif pointer from the add_interface callback. + * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @block_tx: if %true, do not send deauth frame. * * Instruct mac80211 to disconnect due to a channel switch error. The channel @@ -6208,13 +6251,14 @@ void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, /** * ieee80211_request_smps - request SM PS transition * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @link_id: link ID for MLO, or 0 * @smps_mode: new SM PS mode * * This allows the driver to request an SM PS transition in managed * mode. This is useful when the driver has more information than * the stack about possible interference, for example by bluetooth. */ -void ieee80211_request_smps(struct ieee80211_vif *vif, +void ieee80211_request_smps(struct ieee80211_vif *vif, unsigned int link_id, enum ieee80211_smps_mode smps_mode); /** @@ -6546,6 +6590,7 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data * * @vif: the specified virtual interface + * @link_id: the link ID for MLO, otherwise 0 * @membership: 64 bits array - a bit is set if station is member of the group * @position: 2 bits per group id indicating the position in the group * @@ -6554,7 +6599,7 @@ ieee80211_vif_type_p2p(struct ieee80211_vif *vif) * matching GroupId management frame. * Calls to this function need to be serialized with RX path. */ -void ieee80211_update_mu_groups(struct ieee80211_vif *vif, +void ieee80211_update_mu_groups(struct ieee80211_vif *vif, unsigned int link_id, const u8 *membership, const u8 *position); void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, @@ -6787,6 +6832,9 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) { } +void __ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq, bool force); + /** * ieee80211_schedule_txq - schedule a TXQ for transmission * @@ -6799,7 +6847,11 @@ static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) * The driver may call this function if it has buffered packets for * this TXQ internally. */ -void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); +static inline void +ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) +{ + __ieee80211_schedule_txq(hw, txq, true); +} /** * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() @@ -6811,8 +6863,12 @@ void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); * The driver may set force=true if it has buffered packets for this TXQ * internally. */ -void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, - bool force); +static inline void +ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq, + bool force) +{ + __ieee80211_schedule_txq(hw, txq, force); +} /** * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 4d761ad530c9..ac9cf7271d46 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -39,6 +39,7 @@ struct mptcp_ext { infinite_map:1; }; +#define MPTCPOPT_HMAC_LEN 20 #define MPTCP_RM_IDS_MAX 8 struct mptcp_rm_list { @@ -89,7 +90,7 @@ struct mptcp_out_options { u32 nonce; u32 token; u64 thmac; - u8 hmac[20]; + u8 hmac[MPTCPOPT_HMAC_LEN]; }; }; #endif diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 87419f7f5421..9f0bab0589d9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -48,6 +48,7 @@ enum { NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, + NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c4f5601f6e32..20a2992901c2 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -120,7 +120,9 @@ struct net { struct netns_core core; struct netns_mib mib; struct netns_packet packet; +#if IS_ENABLED(CONFIG_UNIX) struct netns_unix unx; +#endif struct netns_nexthop nexthop; struct netns_ipv4 ipv4; #if IS_ENABLED(CONFIG_IPV6) diff --git a/include/net/netns/unix.h b/include/net/netns/unix.h index 91a3d7e39198..6f1a33df061d 100644 --- a/include/net/netns/unix.h +++ b/include/net/netns/unix.h @@ -5,8 +5,14 @@ #ifndef __NETNS_UNIX_H__ #define __NETNS_UNIX_H__ +struct unix_table { + spinlock_t *locks; + struct hlist_head *buckets; +}; + struct ctl_table_header; struct netns_unix { + struct unix_table table; int sysctl_max_dgram_qlen; struct ctl_table_header *ctl; }; diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 8cf001aed858..d9d90e6925e1 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -23,7 +23,7 @@ struct tcf_walker { }; int register_tcf_proto_ops(struct tcf_proto_ops *ops); -int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); +void unregister_tcf_proto_ops(struct tcf_proto_ops *ops); struct tcf_block_ext_info { enum flow_block_binder_type binder_type; diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 44a35531952e..3372a1f67cf4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -173,11 +173,28 @@ struct tc_taprio_qopt_offload { struct tc_taprio_sched_entry entries[]; }; +#if IS_ENABLED(CONFIG_NET_SCH_TAPRIO) + /* Reference counting */ struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload *offload); void taprio_offload_free(struct tc_taprio_qopt_offload *offload); +#else + +/* Reference counting */ +static inline struct tc_taprio_qopt_offload * +taprio_offload_get(struct tc_taprio_qopt_offload *offload) +{ + return NULL; +} + +static inline void taprio_offload_free(struct tc_taprio_qopt_offload *offload) +{ +} + +#endif + /* Ensure skb_mstamp_ns, which might have been populated with the txtime, is * not mistaken for a software timestamp, because this will otherwise prevent * the dispatch of hardware timestamps to the socket. diff --git a/include/net/raw.h b/include/net/raw.h index c51a635671a7..5e665934ebc7 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -20,9 +20,8 @@ extern struct proto raw_prot; extern struct raw_hashinfo raw_v4_hashinfo; -struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, - unsigned short num, __be32 raddr, - __be32 laddr, int dif, int sdif); +bool raw_v4_match(struct net *net, struct sock *sk, unsigned short num, + __be32 raddr, __be32 laddr, int dif, int sdif); int raw_abort(struct sock *sk, int err); void raw_icmp_error(struct sk_buff *, int, u32); @@ -33,10 +32,19 @@ int raw_rcv(struct sock *, struct sk_buff *); #define RAW_HTABLE_SIZE MAX_INET_PROTOS struct raw_hashinfo { - rwlock_t lock; - struct hlist_head ht[RAW_HTABLE_SIZE]; + spinlock_t lock; + struct hlist_nulls_head ht[RAW_HTABLE_SIZE]; }; +static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) +{ + int i; + + spin_lock_init(&hashinfo->lock); + for (i = 0; i < RAW_HTABLE_SIZE; i++) + INIT_HLIST_NULLS_HEAD(&hashinfo->ht[i], i); +} + #ifdef CONFIG_PROC_FS int raw_proc_init(void); void raw_proc_exit(void); diff --git a/include/net/rawv6.h b/include/net/rawv6.h index 53d86b6055e8..bc70909625f6 100644 --- a/include/net/rawv6.h +++ b/include/net/rawv6.h @@ -3,11 +3,12 @@ #define _NET_RAWV6_H #include <net/protocol.h> +#include <net/raw.h> extern struct raw_hashinfo raw_v6_hashinfo; -struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, - unsigned short num, const struct in6_addr *loc_addr, - const struct in6_addr *rmt_addr, int dif, int sdif); +bool raw_v6_match(struct net *net, struct sock *sk, unsigned short num, + const struct in6_addr *loc_addr, + const struct in6_addr *rmt_addr, int dif, int sdif); int raw_abort(struct sock *sk, int err); diff --git a/include/net/route.h b/include/net/route.h index 991a3985712d..651424ef09c9 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -201,10 +201,6 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct in_device *in_dev, u32 *itag); int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin); -int ip_route_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, - u8 tos, struct net_device *devin, - struct fib_result *res); - int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src, u8 tos, struct net_device *devin, const struct sk_buff *hint); diff --git a/include/net/sock.h b/include/net/sock.h index 9fa54762e077..f7ad1a7705e9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -609,7 +609,7 @@ void sock_net_set(struct sock *sk, struct net *net) int sk_set_peek_off(struct sock *sk, int val); -static inline int sk_peek_offset(struct sock *sk, int flags) +static inline int sk_peek_offset(const struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { return READ_ONCE(sk->sk_peek_off); @@ -849,7 +849,7 @@ static inline void sk_add_bind_node(struct sock *sk, ({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;}); \ pos = rcu_dereference(hlist_next_rcu(pos))) -static inline struct user_namespace *sk_user_ns(struct sock *sk) +static inline struct user_namespace *sk_user_ns(const struct sock *sk) { /* Careful only use this in a context where these parameters * can not change and must all be valid, such as recvmsg from @@ -895,7 +895,7 @@ enum sock_flags { #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) -static inline void sock_copy_flags(struct sock *nsk, struct sock *osk) +static inline void sock_copy_flags(struct sock *nsk, const struct sock *osk) { nsk->sk_flags = osk->sk_flags; } @@ -1240,6 +1240,7 @@ struct proto { void (*enter_memory_pressure)(struct sock *sk); void (*leave_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ + int __percpu *per_cpu_fw_alloc; struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* @@ -1383,21 +1384,46 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long -sk_memory_allocated(const struct sock *sk) +proto_memory_allocated(const struct proto *prot) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return max(0L, atomic_long_read(prot->memory_allocated)); } static inline long +sk_memory_allocated(const struct sock *sk) +{ + return proto_memory_allocated(sk->sk_prot); +} + +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + +static inline void sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1426,12 +1452,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { @@ -1518,30 +1538,18 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind); void __sk_mem_reduce_allocated(struct sock *sk, int amount); void __sk_mem_reclaim(struct sock *sk, int amount); -/* We used to have PAGE_SIZE here, but systems with 64KB pages - * do not necessarily have 16x time more memory than 4KB ones. - */ -#define SK_MEM_QUANTUM 4096 -#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM) #define SK_MEM_SEND 0 #define SK_MEM_RECV 1 -/* sysctl_mem values are in pages, we convert them in SK_MEM_QUANTUM units */ +/* sysctl_mem values are in pages */ static inline long sk_prot_mem_limits(const struct sock *sk, int index) { - long val = READ_ONCE(sk->sk_prot->sysctl_mem[index]); - -#if PAGE_SIZE > SK_MEM_QUANTUM - val <<= PAGE_SHIFT - SK_MEM_QUANTUM_SHIFT; -#elif PAGE_SIZE < SK_MEM_QUANTUM - val >>= SK_MEM_QUANTUM_SHIFT - PAGE_SHIFT; -#endif - return val; + return READ_ONCE(sk->sk_prot->sysctl_mem[index]); } static inline int sk_mem_pages(int amt) { - return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT; + return (amt + PAGE_SIZE - 1) >> PAGE_SHIFT; } static inline bool sk_has_account(struct sock *sk) @@ -1552,19 +1560,23 @@ static inline bool sk_has_account(struct sock *sk) static inline bool sk_wmem_schedule(struct sock *sk, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_SEND); + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_SEND); } static inline bool sk_rmem_schedule(struct sock *sk, struct sk_buff *skb, int size) { + int delta; + if (!sk_has_account(sk)) return true; - return size <= sk->sk_forward_alloc || - __sk_mem_schedule(sk, size, SK_MEM_RECV) || + delta = size - sk->sk_forward_alloc; + return delta <= 0 || __sk_mem_schedule(sk, delta, SK_MEM_RECV) || skb_pfmemalloc(skb); } @@ -1590,7 +1602,7 @@ static inline void sk_mem_reclaim(struct sock *sk) reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - if (reclaimable >= SK_MEM_QUANTUM) + if (reclaimable >= (int)PAGE_SIZE) __sk_mem_reclaim(sk, reclaimable); } @@ -1600,19 +1612,6 @@ static inline void sk_mem_reclaim_final(struct sock *sk) sk_mem_reclaim(sk); } -static inline void sk_mem_reclaim_partial(struct sock *sk) -{ - int reclaimable; - - if (!sk_has_account(sk)) - return; - - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - if (reclaimable > SK_MEM_QUANTUM) - __sk_mem_reclaim(sk, reclaimable - 1); -} - static inline void sk_mem_charge(struct sock *sk, int size) { if (!sk_has_account(sk)) @@ -1620,29 +1619,12 @@ static inline void sk_mem_charge(struct sock *sk, int size) sk->sk_forward_alloc -= size; } -/* the following macros control memory reclaiming in sk_mem_uncharge() - */ -#define SK_RECLAIM_THRESHOLD (1 << 21) -#define SK_RECLAIM_CHUNK (1 << 20) - static inline void sk_mem_uncharge(struct sock *sk, int size) { - int reclaimable; - if (!sk_has_account(sk)) return; sk->sk_forward_alloc += size; - reclaimable = sk->sk_forward_alloc - sk_unused_reserved_mem(sk); - - /* Avoid a possible overflow. - * TCP send queues can make this happen, if sk_mem_reclaim() - * is not called and more than 2 GBytes are released at once. - * - * If we reach 2 MBytes, reclaim 1 MBytes right now, there is - * no need to hold that much forward allocation anyway. - */ - if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD)) - __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); + sk_mem_reclaim(sk); } /* @@ -2232,9 +2214,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro if (err) return err; - skb->len += copy; - skb->data_len += copy; - skb->truesize += copy; + skb_len_add(skb, copy); sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; diff --git a/include/net/strparser.h b/include/net/strparser.h index a191486eb1e4..88900b05443e 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -65,15 +65,19 @@ struct _strp_msg { struct sk_skb_cb { #define SK_SKB_CB_PRIV_LEN 20 unsigned char data[SK_SKB_CB_PRIV_LEN]; + /* align strp on cache line boundary within skb->cb[] */ + unsigned char pad[4]; struct _strp_msg strp; - /* temp_reg is a temporary register used for bpf_convert_data_end_access - * when dst_reg == src_reg. - */ - u64 temp_reg; + + /* strp users' data follows */ struct tls_msg { u8 control; u8 decrypted; } tls; + /* temp_reg is a temporary register used for bpf_convert_data_end_access + * when dst_reg == src_reg. + */ + u64 temp_reg; }; static inline struct strp_msg *strp_msg(struct sk_buff *skb) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index aa0171d5786d..7dcdc97c0bc3 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -239,6 +239,9 @@ struct switchdev_notifier_info { const void *ctx; }; +/* Remember to update br_switchdev_fdb_populate() when adding + * new members to this structure + */ struct switchdev_notifier_fdb_info { struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; diff --git a/include/net/tcp.h b/include/net/tcp.h index 1e99f5c61f84..8e48dc56837b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,8 @@ extern long sysctl_tcp_mem[3]; #define TCP_RACK_NO_DUPTHRESH 0x4 /* Do not use DUPACK threshold in RACK */ extern atomic_long_t tcp_memory_allocated; +DECLARE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); + extern struct percpu_counter tcp_sockets_allocated; extern unsigned long tcp_memory_pressure; @@ -432,6 +434,7 @@ u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie); u16 tcp_v6_get_syncookie(struct sock *sk, struct ipv6hdr *iph, struct tcphdr *th, u32 *cookie); +u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss); u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct tcphdr *th); @@ -669,6 +672,7 @@ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); +int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); void tcp_initialize_rcv_mss(struct sock *sk); diff --git a/include/net/tls.h b/include/net/tls.h index 8bd938f98bdd..8742e13bc362 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -39,7 +39,6 @@ #include <linux/crypto.h> #include <linux/socket.h> #include <linux/tcp.h> -#include <linux/skmsg.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> @@ -50,6 +49,7 @@ #include <crypto/aead.h> #include <uapi/linux/tls.h> +struct tls_rec; /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) @@ -66,6 +66,7 @@ #define MAX_IV_SIZE 16 #define TLS_TAG_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 +#define TLS_MAX_AAD_SIZE TLS_AAD_SPACE_SIZE /* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. * @@ -77,13 +78,6 @@ #define TLS_AES_CCM_IV_B0_BYTE 2 #define TLS_SM4_CCM_IV_B0_BYTE 2 -#define __TLS_INC_STATS(net, field) \ - __SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define TLS_INC_STATS(net, field) \ - SNMP_INC_STATS((net)->mib.tls_statistics, field) -#define TLS_DEC_STATS(net, field) \ - SNMP_DEC_STATS((net)->mib.tls_statistics, field) - enum { TLS_BASE, TLS_SW, @@ -92,32 +86,6 @@ enum { TLS_NUM_CONFIG, }; -/* TLS records are maintained in 'struct tls_rec'. It stores the memory pages - * allocated or mapped for each TLS record. After encryption, the records are - * stores in a linked list. - */ -struct tls_rec { - struct list_head list; - int tx_ready; - int tx_flags; - - struct sk_msg msg_plaintext; - struct sk_msg msg_encrypted; - - /* AAD | msg_plaintext.sg.data | sg_tag */ - struct scatterlist sg_aead_in[2]; - /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ - struct scatterlist sg_aead_out[2]; - - char content_type; - struct scatterlist sg_content_type; - - char aad_space[TLS_AAD_SPACE_SIZE]; - u8 iv_data[MAX_IV_SIZE]; - struct aead_request aead_req; - u8 aead_req_ctx[]; -}; - struct tx_work { struct delayed_work work; struct sock *sk; @@ -149,6 +117,7 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 async_capable:1; + u8 zc_capable:1; atomic_t decrypt_pending; /* protect crypto_wait with decrypt_pending*/ spinlock_t decrypt_compl_lock; @@ -239,6 +208,7 @@ struct tls_context { u8 tx_conf:3; u8 rx_conf:3; u8 zerocopy_sendfile:1; + u8 rx_no_pad:1; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); @@ -346,43 +316,6 @@ struct tls_offload_context_rx { #define TLS_OFFLOAD_CONTEXT_SIZE_RX \ (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX) -struct tls_context *tls_ctx_create(struct sock *sk); -void tls_ctx_free(struct sock *sk, struct tls_context *ctx); -void update_sk_prot(struct sock *sk, struct tls_context *ctx); - -int wait_on_pending_writer(struct sock *sk, long *timeo); -int tls_sk_query(struct sock *sk, int optname, char __user *optval, - int __user *optlen); -int tls_sk_attach(struct sock *sk, int optname, char __user *optval, - unsigned int optlen); -void tls_err_abort(struct sock *sk, int err); - -int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx); -void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); -void tls_sw_strparser_done(struct tls_context *tls_ctx); -int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int tls_sw_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -int tls_sw_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); -void tls_sw_release_resources_tx(struct sock *sk); -void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); -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 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, - size_t len, unsigned int flags); - -int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -int tls_device_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -int tls_tx_records(struct sock *sk, int flags); - struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn); @@ -396,58 +329,6 @@ static inline u32 tls_record_start_seq(struct tls_record_info *rec) return rec->end_seq - rec->len; } -int tls_push_sg(struct sock *sk, struct tls_context *ctx, - struct scatterlist *sg, u16 first_offset, - int flags); -int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, - int flags); -void tls_free_partial_record(struct sock *sk, struct tls_context *ctx); - -static inline struct tls_msg *tls_msg(struct sk_buff *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) -{ - return !!ctx->partially_sent_record; -} - -static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) -{ - return tls_ctx->pending_open_record_frags; -} - -static inline bool is_tx_ready(struct tls_sw_context_tx *ctx) -{ - struct tls_rec *rec; - - rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); - if (!rec) - return false; - - return READ_ONCE(rec->tx_ready); -} - -static inline u16 tls_user_config(struct tls_context *ctx, bool tx) -{ - u16 config = tx ? ctx->tx_conf : ctx->rx_conf; - - switch (config) { - case TLS_BASE: - return TLS_CONF_BASE; - case TLS_SW: - return TLS_CONF_SW; - case TLS_HW: - return TLS_CONF_HW; - case TLS_HW_RECORD: - return TLS_CONF_HW_RECORD; - } - return 0; -} - struct sk_buff * tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, struct sk_buff *skb); @@ -466,31 +347,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) #endif } -static inline bool tls_bigint_increment(unsigned char *seq, int len) -{ - int i; - - for (i = len - 1; i >= 0; i--) { - ++seq[i]; - if (seq[i] != 0) - break; - } - - return (i == -1); -} - -static inline void tls_bigint_subtract(unsigned char *seq, int n) -{ - u64 rcd_sn; - __be64 *p; - - BUILD_BUG_ON(TLS_MAX_REC_SEQ_SIZE != 8); - - p = (__be64 *)seq; - rcd_sn = be64_to_cpu(*p); - *p = cpu_to_be64(rcd_sn - n); -} - static inline struct tls_context *tls_get_ctx(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -501,82 +357,6 @@ static inline struct tls_context *tls_get_ctx(const struct sock *sk) return (__force void *)icsk->icsk_ulp_data; } -static inline void tls_advance_record_sn(struct sock *sk, - struct tls_prot_info *prot, - struct cipher_context *ctx) -{ - if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) - tls_err_abort(sk, -EBADMSG); - - if (prot->version != TLS_1_3_VERSION && - prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) - tls_bigint_increment(ctx->iv + prot->salt_size, - prot->iv_size); -} - -static inline void tls_fill_prepend(struct tls_context *ctx, - char *buf, - size_t plaintext_len, - unsigned char record_type) -{ - struct tls_prot_info *prot = &ctx->prot_info; - size_t pkt_len, iv_size = prot->iv_size; - - pkt_len = plaintext_len + prot->tag_size; - if (prot->version != TLS_1_3_VERSION && - prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305) { - pkt_len += iv_size; - - memcpy(buf + TLS_NONCE_OFFSET, - ctx->tx.iv + prot->salt_size, iv_size); - } - - /* we cover nonce explicit here as well, so buf should be of - * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE - */ - buf[0] = prot->version == TLS_1_3_VERSION ? - TLS_RECORD_TYPE_DATA : record_type; - /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ - buf[1] = TLS_1_2_VERSION_MINOR; - buf[2] = TLS_1_2_VERSION_MAJOR; - /* we can use IV for nonce explicit according to spec */ - buf[3] = pkt_len >> 8; - buf[4] = pkt_len & 0xFF; -} - -static inline void tls_make_aad(char *buf, - size_t size, - char *record_sequence, - unsigned char record_type, - struct tls_prot_info *prot) -{ - if (prot->version != TLS_1_3_VERSION) { - memcpy(buf, record_sequence, prot->rec_seq_size); - buf += 8; - } else { - size += prot->tag_size; - } - - buf[0] = prot->version == TLS_1_3_VERSION ? - TLS_RECORD_TYPE_DATA : record_type; - buf[1] = TLS_1_2_VERSION_MAJOR; - buf[2] = TLS_1_2_VERSION_MINOR; - buf[3] = size >> 8; - buf[4] = size & 0xFF; -} - -static inline void xor_iv_with_seq(struct tls_prot_info *prot, char *iv, char *seq) -{ - int i; - - if (prot->version == TLS_1_3_VERSION || - prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305) { - for (i = 0; i < 8; i++) - iv[i + 4] ^= seq[i]; - } -} - - static inline struct tls_sw_context_rx *tls_sw_ctx_rx( const struct tls_context *tls_ctx) { @@ -613,9 +393,6 @@ static inline bool tls_sw_has_ctx_rx(const struct sock *sk) return !!tls_sw_ctx_rx(ctx); } -void tls_sw_write_space(struct sock *sk, struct tls_context *ctx); -void tls_device_write_space(struct sock *sk, struct tls_context *ctx); - static inline struct tls_offload_context_rx * tls_offload_ctx_rx(const struct tls_context *tls_ctx) { @@ -690,31 +467,11 @@ static inline bool tls_offload_tx_resync_pending(struct sock *sk) return ret; } -int __net_init tls_proc_init(struct net *net); -void __net_exit tls_proc_fini(struct net *net); - -int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, - unsigned char *record_type); -int decrypt_skb(struct sock *sk, struct sk_buff *skb, - struct scatterlist *sgout); struct sk_buff *tls_encrypt_skb(struct sk_buff *skb); -int tls_sw_fallback_init(struct sock *sk, - struct tls_offload_context_tx *offload_ctx, - struct tls_crypto_info *crypto_info); - #ifdef CONFIG_TLS_DEVICE -int tls_device_init(void); -void tls_device_cleanup(void); void tls_device_sk_destruct(struct sock *sk); -int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); -void tls_device_free_resources_tx(struct sock *sk); -int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx); -void tls_device_offload_cleanup_rx(struct sock *sk); -void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq); void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq); -int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, - struct sk_buff *skb, struct strp_msg *rxm); static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) { @@ -723,33 +480,5 @@ static inline bool tls_is_sk_rx_device_offloaded(struct sock *sk) return false; return tls_get_ctx(sk)->rx_conf == TLS_HW; } -#else -static inline int tls_device_init(void) { return 0; } -static inline void tls_device_cleanup(void) {} - -static inline int -tls_set_device_offload(struct sock *sk, struct tls_context *ctx) -{ - return -EOPNOTSUPP; -} - -static inline void tls_device_free_resources_tx(struct sock *sk) {} - -static inline int -tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) -{ - return -EOPNOTSUPP; -} - -static inline void tls_device_offload_cleanup_rx(struct sock *sk) {} -static inline void -tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) {} - -static inline int -tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx, - struct sk_buff *skb, struct strp_msg *rxm) -{ - return 0; -} #endif #endif /* _TLS_OFFLOAD_H */ diff --git a/include/net/udp.h b/include/net/udp.h index b83a00330566..987f7fc7c0aa 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -95,6 +95,7 @@ static inline struct udp_hslot *udp_hashslot2(struct udp_table *table, extern struct proto udp_prot; extern atomic_long_t udp_memory_allocated; +DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); /* sysctl variables for udp */ extern long sysctl_udp_mem[3]; @@ -305,8 +306,7 @@ struct sock *__udp6_lib_lookup(struct net *net, struct sk_buff *skb); struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport); -int udp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor); +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); /* UDP uses skb->dev_scratch to cache as much information as possible and avoid * possibly multiple cache miss on dequeue() diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c39d910d4b45..67b799ef5f67 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1195,6 +1195,8 @@ int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { + if (!sk_fullsock(osk)) + return 0; sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) @@ -1923,7 +1925,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put_track(dev, &xso->dev_tracker); + netdev_put(dev, &xso->dev_tracker); } } #else |