diff options
Diffstat (limited to 'include/net')
48 files changed, 1222 insertions, 516 deletions
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index d40e978126e3..d3ff48a2fbe0 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/workqueue.h> +#include <net/netns/vsock.h> #include <net/sock.h> #include <uapi/linux/vm_sockets.h> @@ -124,7 +125,7 @@ struct vsock_transport { size_t len, int flags); int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *, struct msghdr *, size_t len); - bool (*dgram_allow)(u32 cid, u32 port); + bool (*dgram_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* STREAM. */ /* TODO: stream_bind() */ @@ -136,14 +137,14 @@ struct vsock_transport { s64 (*stream_has_space)(struct vsock_sock *); u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); - bool (*stream_allow)(u32 cid, u32 port); + bool (*stream_allow)(struct vsock_sock *vsk, u32 cid, u32 port); /* SEQ_PACKET. */ ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, int flags); int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, size_t len); - bool (*seqpacket_allow)(u32 remote_cid); + bool (*seqpacket_allow)(struct vsock_sock *vsk, u32 remote_cid); u32 (*seqpacket_has_data)(struct vsock_sock *vsk); /* Notification. */ @@ -216,6 +217,11 @@ void vsock_remove_connected(struct vsock_sock *vsk); struct sock *vsock_find_bound_socket(struct sockaddr_vm *addr); struct sock *vsock_find_connected_socket(struct sockaddr_vm *src, struct sockaddr_vm *dst); +struct sock *vsock_find_bound_socket_net(struct sockaddr_vm *addr, + struct net *net); +struct sock *vsock_find_connected_socket_net(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + struct net *net); void vsock_remove_sock(struct vsock_sock *vsk); void vsock_for_each_connected_socket(struct vsock_transport *transport, void (*fn)(struct sock *sk)); @@ -256,4 +262,53 @@ static inline bool vsock_msgzerocopy_allow(const struct vsock_transport *t) { return t->msgzerocopy_allow && t->msgzerocopy_allow(); } + +static inline enum vsock_net_mode vsock_net_mode(struct net *net) +{ + if (!net) + return VSOCK_NET_MODE_GLOBAL; + + return READ_ONCE(net->vsock.mode); +} + +static inline bool vsock_net_mode_global(struct vsock_sock *vsk) +{ + return vsock_net_mode(sock_net(sk_vsock(vsk))) == VSOCK_NET_MODE_GLOBAL; +} + +static inline void vsock_net_set_child_mode(struct net *net, + enum vsock_net_mode mode) +{ + WRITE_ONCE(net->vsock.child_ns_mode, mode); +} + +static inline enum vsock_net_mode vsock_net_child_mode(struct net *net) +{ + return READ_ONCE(net->vsock.child_ns_mode); +} + +/* Return true if two namespaces pass the mode rules. Otherwise, return false. + * + * A NULL namespace is treated as VSOCK_NET_MODE_GLOBAL. + * + * Read more about modes in the comment header of net/vmw_vsock/af_vsock.c. + */ +static inline bool vsock_net_check_mode(struct net *ns0, struct net *ns1) +{ + enum vsock_net_mode mode0, mode1; + + /* Any vsocks within the same network namespace are always reachable, + * regardless of the mode. + */ + if (net_eq(ns0, ns1)) + return true; + + mode0 = vsock_net_mode(ns0); + mode1 = vsock_net_mode(ns1); + + /* Different namespaces are only reachable if they are both + * global mode. + */ + return mode0 == VSOCK_NET_MODE_GLOBAL && mode0 == mode1; +} #endif /* __AF_VSOCK_H__ */ diff --git a/include/net/ax25.h b/include/net/ax25.h index a7bba42dde15..ad3d7626130e 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -116,10 +116,6 @@ enum { AX25_PROTO_STD_DUPLEX, #ifdef CONFIG_AX25_DAMA_SLAVE AX25_PROTO_DAMA_SLAVE, -#ifdef CONFIG_AX25_DAMA_MASTER - AX25_PROTO_DAMA_MASTER, -#define AX25_PROTO_MAX AX25_PROTO_DAMA_MASTER -#endif #endif __AX25_PROTO_MAX, AX25_PROTO_MAX = __AX25_PROTO_MAX -1 @@ -138,7 +134,7 @@ enum { AX25_VALUES_IDLE, /* Connected mode idle timer */ AX25_VALUES_N2, /* Default N2 value */ AX25_VALUES_PACLEN, /* AX.25 MTU */ - AX25_VALUES_PROTOCOL, /* Std AX.25, DAMA Slave, DAMA Master */ + AX25_VALUES_PROTOCOL, /* Std AX.25, DAMA Slave */ #ifdef CONFIG_AX25_DAMA_SLAVE AX25_VALUES_DS_TIMEOUT, /* DAMA Slave timeout */ #endif @@ -226,7 +222,7 @@ typedef struct ax25_dev { struct net_device *forward; struct ctl_table_header *sysheader; int values[AX25_MAX_VALUES]; -#if defined(CONFIG_AX25_DAMA_SLAVE) || defined(CONFIG_AX25_DAMA_MASTER) +#ifdef CONFIG_AX25_DAMA_SLAVE ax25_dama_info dama; #endif refcount_t refcount; diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index d46ed9011ee5..69eed69f7f26 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -130,21 +130,30 @@ struct bt_voice { #define BT_RCVMTU 13 #define BT_PHY 14 -#define BT_PHY_BR_1M_1SLOT 0x00000001 -#define BT_PHY_BR_1M_3SLOT 0x00000002 -#define BT_PHY_BR_1M_5SLOT 0x00000004 -#define BT_PHY_EDR_2M_1SLOT 0x00000008 -#define BT_PHY_EDR_2M_3SLOT 0x00000010 -#define BT_PHY_EDR_2M_5SLOT 0x00000020 -#define BT_PHY_EDR_3M_1SLOT 0x00000040 -#define BT_PHY_EDR_3M_3SLOT 0x00000080 -#define BT_PHY_EDR_3M_5SLOT 0x00000100 -#define BT_PHY_LE_1M_TX 0x00000200 -#define BT_PHY_LE_1M_RX 0x00000400 -#define BT_PHY_LE_2M_TX 0x00000800 -#define BT_PHY_LE_2M_RX 0x00001000 -#define BT_PHY_LE_CODED_TX 0x00002000 -#define BT_PHY_LE_CODED_RX 0x00004000 +#define BT_PHY_BR_1M_1SLOT BIT(0) +#define BT_PHY_BR_1M_3SLOT BIT(1) +#define BT_PHY_BR_1M_5SLOT BIT(2) +#define BT_PHY_EDR_2M_1SLOT BIT(3) +#define BT_PHY_EDR_2M_3SLOT BIT(4) +#define BT_PHY_EDR_2M_5SLOT BIT(5) +#define BT_PHY_EDR_3M_1SLOT BIT(6) +#define BT_PHY_EDR_3M_3SLOT BIT(7) +#define BT_PHY_EDR_3M_5SLOT BIT(8) +#define BT_PHY_LE_1M_TX BIT(9) +#define BT_PHY_LE_1M_RX BIT(10) +#define BT_PHY_LE_2M_TX BIT(11) +#define BT_PHY_LE_2M_RX BIT(12) +#define BT_PHY_LE_CODED_TX BIT(13) +#define BT_PHY_LE_CODED_RX BIT(14) + +#define BT_PHY_BREDR_MASK (BT_PHY_BR_1M_1SLOT | BT_PHY_BR_1M_3SLOT | \ + BT_PHY_BR_1M_5SLOT | BT_PHY_EDR_2M_1SLOT | \ + BT_PHY_EDR_2M_3SLOT | BT_PHY_EDR_2M_5SLOT | \ + BT_PHY_EDR_3M_1SLOT | BT_PHY_EDR_3M_3SLOT | \ + BT_PHY_EDR_3M_5SLOT) +#define BT_PHY_LE_MASK (BT_PHY_LE_1M_TX | BT_PHY_LE_1M_RX | \ + BT_PHY_LE_2M_TX | BT_PHY_LE_2M_RX | \ + BT_PHY_LE_CODED_TX | BT_PHY_LE_CODED_RX) #define BT_MODE 15 @@ -173,7 +182,7 @@ struct bt_iso_io_qos { __u32 interval; __u16 latency; __u16 sdu; - __u8 phy; + __u8 phys; __u8 rtn; }; @@ -212,9 +221,9 @@ struct bt_iso_qos { }; }; -#define BT_ISO_PHY_1M 0x01 -#define BT_ISO_PHY_2M 0x02 -#define BT_ISO_PHY_CODED 0x04 +#define BT_ISO_PHY_1M BIT(0) +#define BT_ISO_PHY_2M BIT(1) +#define BT_ISO_PHY_CODED BIT(2) #define BT_ISO_PHY_ANY (BT_ISO_PHY_1M | BT_ISO_PHY_2M | \ BT_ISO_PHY_CODED) diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index a27cd3626b87..89ad9470fa71 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -654,6 +654,8 @@ enum { #define HCI_LE_ISO_BROADCASTER 0x40 #define HCI_LE_ISO_SYNC_RECEIVER 0x80 #define HCI_LE_LL_EXT_FEATURE 0x80 +#define HCI_LE_CS 0x40 +#define HCI_LE_CS_HOST 0x80 /* Connection modes */ #define HCI_CM_ACTIVE 0x0000 @@ -1883,6 +1885,15 @@ struct hci_cp_le_set_default_phy { #define HCI_LE_SET_PHY_2M 0x02 #define HCI_LE_SET_PHY_CODED 0x04 +#define HCI_OP_LE_SET_PHY 0x2032 +struct hci_cp_le_set_phy { + __le16 handle; + __u8 all_phys; + __u8 tx_phys; + __u8 rx_phys; + __le16 phy_opts; +} __packed; + #define HCI_OP_LE_SET_EXT_SCAN_PARAMS 0x2041 struct hci_cp_le_set_ext_scan_params { __u8 own_addr_type; @@ -2136,8 +2147,8 @@ struct hci_cis_params { __u8 cis_id; __le16 c_sdu; __le16 p_sdu; - __u8 c_phy; - __u8 p_phy; + __u8 c_phys; + __u8 p_phys; __u8 c_rtn; __u8 p_rtn; } __packed; @@ -2269,6 +2280,204 @@ struct hci_cp_le_read_all_remote_features { __u8 pages; } __packed; +/* Channel Sounding Commands */ +#define HCI_OP_LE_CS_RD_LOCAL_SUPP_CAP 0x2089 +struct hci_rp_le_cs_rd_local_supp_cap { + __u8 status; + __u8 num_config_supported; + __le16 max_consecutive_procedures_supported; + __u8 num_antennas_supported; + __u8 max_antenna_paths_supported; + __u8 roles_supported; + __u8 modes_supported; + __u8 rtt_capability; + __u8 rtt_aa_only_n; + __u8 rtt_sounding_n; + __u8 rtt_random_payload_n; + __le16 nadm_sounding_capability; + __le16 nadm_random_capability; + __u8 cs_sync_phys_supported; + __le16 subfeatures_supported; + __le16 t_ip1_times_supported; + __le16 t_ip2_times_supported; + __le16 t_fcs_times_supported; + __le16 t_pm_times_supported; + __u8 t_sw_time_supported; + __u8 tx_snr_capability; +} __packed; + +#define HCI_OP_LE_CS_RD_RMT_SUPP_CAP 0x208A +struct hci_cp_le_cs_rd_local_supp_cap { + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_WR_CACHED_RMT_SUPP_CAP 0x208B +struct hci_cp_le_cs_wr_cached_rmt_supp_cap { + __le16 handle; + __u8 num_config_supported; + __le16 max_consecutive_procedures_supported; + __u8 num_antennas_supported; + __u8 max_antenna_paths_supported; + __u8 roles_supported; + __u8 modes_supported; + __u8 rtt_capability; + __u8 rtt_aa_only_n; + __u8 rtt_sounding_n; + __u8 rtt_random_payload_n; + __le16 nadm_sounding_capability; + __le16 nadm_random_capability; + __u8 cs_sync_phys_supported; + __le16 subfeatures_supported; + __le16 t_ip1_times_supported; + __le16 t_ip2_times_supported; + __le16 t_fcs_times_supported; + __le16 t_pm_times_supported; + __u8 t_sw_time_supported; + __u8 tx_snr_capability; +} __packed; + +struct hci_rp_le_cs_wr_cached_rmt_supp_cap { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_SEC_ENABLE 0x208C +struct hci_cp_le_cs_sec_enable { + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_SET_DEFAULT_SETTINGS 0x208D +struct hci_cp_le_cs_set_default_settings { + __le16 handle; + __u8 role_enable; + __u8 cs_sync_ant_sel; + __s8 max_tx_power; +} __packed; + +struct hci_rp_le_cs_set_default_settings { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_RD_RMT_FAE_TABLE 0x208E +struct hci_cp_le_cs_rd_rmt_fae_table { + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_WR_CACHED_RMT_FAE_TABLE 0x208F +struct hci_cp_le_cs_wr_rmt_cached_fae_table { + __le16 handle; + __u8 remote_fae_table[72]; +} __packed; + +struct hci_rp_le_cs_wr_rmt_cached_fae_table { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_CREATE_CONFIG 0x2090 +struct hci_cp_le_cs_create_config { + __le16 handle; + __u8 config_id; + __u8 create_context; + __u8 main_mode_type; + __u8 sub_mode_type; + __u8 min_main_mode_steps; + __u8 max_main_mode_steps; + __u8 main_mode_repetition; + __u8 mode_0_steps; + __u8 role; + __u8 rtt_type; + __u8 cs_sync_phy; + __u8 channel_map[10]; + __u8 channel_map_repetition; + __u8 channel_selection_type; + __u8 ch3c_shape; + __u8 ch3c_jump; + __u8 reserved; +} __packed; + +#define HCI_OP_LE_CS_REMOVE_CONFIG 0x2091 +struct hci_cp_le_cs_remove_config { + __le16 handle; + __u8 config_id; +} __packed; + +#define HCI_OP_LE_CS_SET_CH_CLASSIFICATION 0x2092 +struct hci_cp_le_cs_set_ch_classification { + __u8 ch_classification[10]; +} __packed; + +struct hci_rp_le_cs_set_ch_classification { + __u8 status; +} __packed; + +#define HCI_OP_LE_CS_SET_PROC_PARAM 0x2093 +struct hci_cp_le_cs_set_proc_param { + __le16 handle; + __u8 config_id; + __le16 max_procedure_len; + __le16 min_procedure_interval; + __le16 max_procedure_interval; + __le16 max_procedure_count; + __u8 min_subevent_len[3]; + __u8 max_subevent_len[3]; + __u8 tone_antenna_config_selection; + __u8 phy; + __u8 tx_power_delta; + __u8 preferred_peer_antenna; + __u8 snr_control_initiator; + __u8 snr_control_reflector; +} __packed; + +struct hci_rp_le_cs_set_proc_param { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_OP_LE_CS_SET_PROC_ENABLE 0x2094 +struct hci_cp_le_cs_set_proc_enable { + __le16 handle; + __u8 config_id; + __u8 enable; +} __packed; + +#define HCI_OP_LE_CS_TEST 0x2095 +struct hci_cp_le_cs_test { + __u8 main_mode_type; + __u8 sub_mode_type; + __u8 main_mode_repetition; + __u8 mode_0_steps; + __u8 role; + __u8 rtt_type; + __u8 cs_sync_phy; + __u8 cs_sync_antenna_selection; + __u8 subevent_len[3]; + __le16 subevent_interval; + __u8 max_num_subevents; + __u8 transmit_power_level; + __u8 t_ip1_time; + __u8 t_ip2_time; + __u8 t_fcs_time; + __u8 t_pm_time; + __u8 t_sw_time; + __u8 tone_antenna_config_selection; + __u8 reserved; + __u8 snr_control_initiator; + __u8 snr_control_reflector; + __le16 drbg_nonce; + __u8 channel_map_repetition; + __le16 override_config; + __u8 override_parameters_length; + __u8 override_parameters_data[]; +} __packed; + +struct hci_rp_le_cs_test { + __u8 status; +} __packed; + +#define HCI_OP_LE_CS_TEST_END 0x2096 + /* ---- HCI Events ---- */ struct hci_ev_status { __u8 status; @@ -2960,6 +3169,129 @@ struct hci_evt_le_read_all_remote_features_complete { __u8 features[248]; } __packed; +/* Channel Sounding Events */ +#define HCI_EVT_LE_CS_READ_RMT_SUPP_CAP_COMPLETE 0x2C +struct hci_evt_le_cs_read_rmt_supp_cap_complete { + __u8 status; + __le16 handle; + __u8 num_configs_supp; + __le16 max_consec_proc_supp; + __u8 num_ant_supp; + __u8 max_ant_path_supp; + __u8 roles_supp; + __u8 modes_supp; + __u8 rtt_cap; + __u8 rtt_aa_only_n; + __u8 rtt_sounding_n; + __u8 rtt_rand_payload_n; + __le16 nadm_sounding_cap; + __le16 nadm_rand_cap; + __u8 cs_sync_phys_supp; + __le16 sub_feat_supp; + __le16 t_ip1_times_supp; + __le16 t_ip2_times_supp; + __le16 t_fcs_times_supp; + __le16 t_pm_times_supp; + __u8 t_sw_times_supp; + __u8 tx_snr_cap; +} __packed; + +#define HCI_EVT_LE_CS_READ_RMT_FAE_TABLE_COMPLETE 0x2D +struct hci_evt_le_cs_read_rmt_fae_table_complete { + __u8 status; + __le16 handle; + __u8 remote_fae_table[72]; +} __packed; + +#define HCI_EVT_LE_CS_SECURITY_ENABLE_COMPLETE 0x2E +struct hci_evt_le_cs_security_enable_complete { + __u8 status; + __le16 handle; +} __packed; + +#define HCI_EVT_LE_CS_CONFIG_COMPLETE 0x2F +struct hci_evt_le_cs_config_complete { + __u8 status; + __le16 handle; + __u8 config_id; + __u8 action; + __u8 main_mode_type; + __u8 sub_mode_type; + __u8 min_main_mode_steps; + __u8 max_main_mode_steps; + __u8 main_mode_rep; + __u8 mode_0_steps; + __u8 role; + __u8 rtt_type; + __u8 cs_sync_phy; + __u8 channel_map[10]; + __u8 channel_map_rep; + __u8 channel_sel_type; + __u8 ch3c_shape; + __u8 ch3c_jump; + __u8 reserved; + __u8 t_ip1_time; + __u8 t_ip2_time; + __u8 t_fcs_time; + __u8 t_pm_time; +} __packed; + +#define HCI_EVT_LE_CS_PROCEDURE_ENABLE_COMPLETE 0x30 +struct hci_evt_le_cs_procedure_enable_complete { + __u8 status; + __le16 handle; + __u8 config_id; + __u8 state; + __u8 tone_ant_config_sel; + __s8 sel_tx_pwr; + __u8 sub_evt_len[3]; + __u8 sub_evts_per_evt; + __le16 sub_evt_intrvl; + __le16 evt_intrvl; + __le16 proc_intrvl; + __le16 proc_counter; + __le16 max_proc_len; +} __packed; + +#define HCI_EVT_LE_CS_SUBEVENT_RESULT 0x31 +struct hci_evt_le_cs_subevent_result { + __le16 handle; + __u8 config_id; + __le16 start_acl_conn_evt_counter; + __le16 proc_counter; + __le16 freq_comp; + __u8 ref_pwr_lvl; + __u8 proc_done_status; + __u8 subevt_done_status; + __u8 abort_reason; + __u8 num_ant_paths; + __u8 num_steps_reported; + __u8 step_mode[0]; /* depends on num_steps_reported */ + __u8 step_channel[0]; /* depends on num_steps_reported */ + __u8 step_data_length[0]; /* depends on num_steps_reported */ + __u8 step_data[0]; /* depends on num_steps_reported */ +} __packed; + +#define HCI_EVT_LE_CS_SUBEVENT_RESULT_CONTINUE 0x32 +struct hci_evt_le_cs_subevent_result_continue { + __le16 handle; + __u8 config_id; + __u8 proc_done_status; + __u8 subevt_done_status; + __u8 abort_reason; + __u8 num_ant_paths; + __u8 num_steps_reported; + __u8 step_mode[0]; /* depends on num_steps_reported */ + __u8 step_channel[0]; /* depends on num_steps_reported */ + __u8 step_data_length[0]; /* depends on num_steps_reported */ + __u8 step_data[0]; /* depends on num_steps_reported */ +} __packed; + +#define HCI_EVT_LE_CS_TEST_END_COMPLETE 0x33 +struct hci_evt_le_cs_test_end_complete { + __u8 status; +} __packed; + #define HCI_EV_VENDOR 0xff /* Internal events generated by Bluetooth stack */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4263e71a23ef..a7bffb908c1e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -730,6 +730,8 @@ struct hci_conn { __u16 le_per_adv_data_offset; __u8 le_adv_phy; __u8 le_adv_sec_phy; + __u8 le_tx_def_phys; + __u8 le_rx_def_phys; __u8 le_tx_phy; __u8 le_rx_phy; __s8 rssi; @@ -2071,6 +2073,12 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define ll_ext_feature_capable(dev) \ ((dev)->le_features[7] & HCI_LE_LL_EXT_FEATURE) +/* Channel sounding support */ +#define le_cs_capable(dev) \ + ((dev)->le_features[5] & HCI_LE_CS) +#define le_cs_host_capable(dev) \ + ((dev)->le_features[5] & HCI_LE_CS_HOST) + #define mws_transport_config_capable(dev) (((dev)->commands[30] & 0x08) && \ (!hci_test_quirk((dev), HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG))) @@ -2334,6 +2342,7 @@ void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); void *hci_recv_event_data(struct hci_dev *hdev, __u8 event); u32 hci_conn_get_phy(struct hci_conn *conn); +int hci_conn_set_phy(struct hci_conn *conn, u32 phys); /* ----- HCI Sockets ----- */ void hci_send_to_sock(struct hci_dev *hdev, struct sk_buff *skb); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 56076bbc981d..73e494b2591d 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -191,3 +191,6 @@ int hci_connect_big_sync(struct hci_dev *hdev, struct hci_conn *conn); int hci_past_sync(struct hci_conn *conn, struct hci_conn *le); int hci_le_read_remote_features(struct hci_conn *conn); + +int hci_acl_change_pkt_type(struct hci_conn *conn, u16 pkt_type); +int hci_le_set_phy(struct hci_conn *conn, u8 tx_phys, u8 rx_phys); diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 00e182a22720..ec3af01e4db9 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -655,8 +655,7 @@ struct l2cap_conn { struct sk_buff *rx_skb; __u32 rx_len; - __u8 tx_ident; - struct mutex ident_lock; + struct ida tx_ida; struct sk_buff_head pending_rx; struct work_struct pending_rx_work; diff --git a/include/net/bonding.h b/include/net/bonding.h index 462078403557..4ad5521e7731 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -254,6 +254,7 @@ struct bonding { struct delayed_work ad_work; struct delayed_work mcast_work; struct delayed_work slave_arr_work; + struct delayed_work peer_notify_work; #ifdef CONFIG_DEBUG_FS /* debugging support via debugfs */ struct dentry *debug_dir; @@ -710,6 +711,7 @@ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, int level); int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave); void bond_slave_arr_work_rearm(struct bonding *bond, unsigned long delay); +void bond_peer_notify_work_rearm(struct bonding *bond, unsigned long delay); void bond_work_init_all(struct bonding *bond); void bond_work_cancel_all(struct bonding *bond); diff --git a/include/net/can.h b/include/net/can.h new file mode 100644 index 000000000000..6db9e826f0e0 --- /dev/null +++ b/include/net/can.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* + * net/can.h + * + * Definitions for the CAN network socket buffer extensions + * + * Copyright (C) 2026 Oliver Hartkopp <socketcan@hartkopp.net> + * + */ + +#ifndef _NET_CAN_H +#define _NET_CAN_H + +/** + * struct can_skb_ext - skb extensions for CAN specific content + * @can_iif: ifindex of the first interface the CAN frame appeared on + * @can_framelen: cached echo CAN frame length for bql + * @can_gw_hops: can-gw CAN frame time-to-live counter + * @can_ext_flags: CAN skb extensions flags + */ +struct can_skb_ext { + int can_iif; + u16 can_framelen; + u8 can_gw_hops; + u8 can_ext_flags; +}; + +#endif /* _NET_CAN_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 2900202588a5..fc01de19c798 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7,7 +7,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2025 Intel Corporation + * Copyright (C) 2018-2026 Intel Corporation */ #include <linux/ethtool.h> @@ -126,6 +126,7 @@ struct wiphy; * @IEEE80211_CHAN_NO_4MHZ: 4 MHz bandwidth is not permitted on this channel. * @IEEE80211_CHAN_NO_8MHZ: 8 MHz bandwidth is not permitted on this channel. * @IEEE80211_CHAN_NO_16MHZ: 16 MHz bandwidth is not permitted on this channel. + * @IEEE80211_CHAN_NO_UHR: UHR operation is not permitted on this channel. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = BIT(0), @@ -143,6 +144,7 @@ enum ieee80211_channel_flags { IEEE80211_CHAN_NO_10MHZ = BIT(12), IEEE80211_CHAN_NO_HE = BIT(13), /* can use free bits here */ + IEEE80211_CHAN_NO_UHR = BIT(18), IEEE80211_CHAN_NO_320MHZ = BIT(19), IEEE80211_CHAN_NO_EHT = BIT(20), IEEE80211_CHAN_DFS_CONCURRENT = BIT(21), @@ -429,6 +431,18 @@ struct ieee80211_sta_eht_cap { u8 eht_ppe_thres[IEEE80211_EHT_PPE_THRES_MAX_LEN]; }; +/** + * struct ieee80211_sta_uhr_cap - STA's UHR capabilities + * @has_uhr: true iff UHR is supported and data is valid + * @mac: fixed MAC capabilities + * @phy: fixed PHY capabilities + */ +struct ieee80211_sta_uhr_cap { + bool has_uhr; + struct ieee80211_uhr_cap_mac mac; + struct ieee80211_uhr_cap_phy phy; +}; + /* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ /* @@ -454,6 +468,7 @@ struct ieee80211_sta_eht_cap { * @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 + * @uhr_cap: STA's UHR capabilities * @vendor_elems: vendor element(s) to advertise * @vendor_elems.data: vendor element(s) data * @vendor_elems.len: vendor element(s) length @@ -463,6 +478,7 @@ struct ieee80211_sband_iftype_data { struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; + struct ieee80211_sta_uhr_cap uhr_cap; struct { const u8 *data; unsigned int len; @@ -705,6 +721,26 @@ ieee80211_get_eht_iftype_cap(const struct ieee80211_supported_band *sband, } /** + * ieee80211_get_uhr_iftype_cap - return UHR capabilities for an sband's iftype + * @sband: the sband to search for the iftype on + * @iftype: enum nl80211_iftype + * + * Return: pointer to the struct ieee80211_sta_uhr_cap, or NULL is none found + */ +static inline const struct ieee80211_sta_uhr_cap * +ieee80211_get_uhr_iftype_cap(const struct ieee80211_supported_band *sband, + enum nl80211_iftype iftype) +{ + const struct ieee80211_sband_iftype_data *data = + ieee80211_get_sband_iftype_data(sband, iftype); + + if (data && data->uhr_cap.has_uhr) + return &data->uhr_cap; + + return NULL; +} + +/** * wiphy_read_of_freq_limits - read frequency limits from device tree * * @wiphy: the wireless device to get extra limits for @@ -1486,6 +1522,7 @@ struct cfg80211_s1g_short_beacon { * @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) + * @uhr_oper: UHR operation (or %NULL if UHR isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time @@ -1525,6 +1562,7 @@ struct cfg80211_ap_settings { const struct ieee80211_he_operation *he_oper; const struct ieee80211_eht_cap_elem *eht_cap; const struct ieee80211_eht_operation *eht_oper; + const struct ieee80211_uhr_operation *uhr_oper; bool ht_required, vht_required, he_required, sae_h2e_required; bool twt_responder; u32 flags; @@ -1698,6 +1736,8 @@ struct sta_txpwr { * @eht_capa: EHT capabilities of station * @eht_capa_len: the length of the EHT capabilities * @s1g_capa: S1G capabilities of station + * @uhr_capa: UHR capabilities of the station + * @uhr_capa_len: the length of the UHR capabilities */ struct link_station_parameters { const u8 *mld_mac; @@ -1717,6 +1757,8 @@ struct link_station_parameters { const struct ieee80211_eht_cap_elem *eht_capa; u8 eht_capa_len; const struct ieee80211_s1g_cap *s1g_capa; + const struct ieee80211_uhr_cap *uhr_capa; + u8 uhr_capa_len; }; /** @@ -1785,6 +1827,7 @@ struct cfg80211_ttlm_params { * present/updated * @eml_cap: EML capabilities of this station * @link_sta_params: link related params. + * @epp_peer: EPP peer indication */ struct station_parameters { struct net_device *vlan; @@ -1811,6 +1854,7 @@ struct station_parameters { bool eml_cap_present; u16 eml_cap; struct link_station_parameters link_sta_params; + bool epp_peer; }; /** @@ -1896,6 +1940,11 @@ int cfg80211_check_station_change(struct wiphy *wiphy, * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS * @RATE_INFO_FLAGS_EHT_MCS: EHT MCS information * @RATE_INFO_FLAGS_S1G_MCS: MCS field filled with S1G MCS + * @RATE_INFO_FLAGS_UHR_MCS: UHR MCS information + * @RATE_INFO_FLAGS_UHR_ELR_MCS: UHR ELR MCS was used + * (set together with @RATE_INFO_FLAGS_UHR_MCS) + * @RATE_INFO_FLAGS_UHR_IM: UHR Interference Mitigation + * was used */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), @@ -1907,6 +1956,9 @@ enum rate_info_flags { RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), RATE_INFO_FLAGS_EHT_MCS = BIT(7), RATE_INFO_FLAGS_S1G_MCS = BIT(8), + RATE_INFO_FLAGS_UHR_MCS = BIT(9), + RATE_INFO_FLAGS_UHR_ELR_MCS = BIT(10), + RATE_INFO_FLAGS_UHR_IM = BIT(11), }; /** @@ -1922,7 +1974,7 @@ enum rate_info_flags { * @RATE_INFO_BW_160: 160 MHz bandwidth * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation * @RATE_INFO_BW_320: 320 MHz bandwidth - * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT RU allocation + * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT/UHR RU allocation * @RATE_INFO_BW_1: 1 MHz bandwidth * @RATE_INFO_BW_2: 2 MHz bandwidth * @RATE_INFO_BW_4: 4 MHz bandwidth @@ -1953,7 +2005,7 @@ enum rate_info_bw { * * @flags: bitflag of flags from &enum rate_info_flags * @legacy: bitrate in 100kbit/s for 802.11abg - * @mcs: mcs index if struct describes an HT/VHT/HE/EHT/S1G rate + * @mcs: mcs index if struct describes an HT/VHT/HE/EHT/S1G/UHR rate * @nss: number of streams (VHT & HE only) * @bw: bandwidth (from &enum rate_info_bw) * @he_gi: HE guard interval (from &enum nl80211_he_gi) @@ -3260,6 +3312,7 @@ struct cfg80211_ml_reconf_req { * Drivers shall disable MLO features for the current association if this * flag is not set. * @ASSOC_REQ_SPP_AMSDU: SPP A-MSDUs will be used on this connection (if any) + * @ASSOC_REQ_DISABLE_UHR: Disable UHR */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), @@ -3270,6 +3323,7 @@ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_EHT = BIT(5), CONNECT_REQ_MLO_SUPPORT = BIT(6), ASSOC_REQ_SPP_AMSDU = BIT(7), + ASSOC_REQ_DISABLE_UHR = BIT(8), }; /** @@ -4187,6 +4241,7 @@ struct cfg80211_ftm_responder_stats { * @num_bursts_exp: actual number of bursts exponent negotiated * @burst_duration: actual burst duration negotiated * @ftms_per_burst: actual FTMs per burst negotiated + * @burst_period: actual burst period negotiated in units of 100ms * @lci_len: length of LCI information (if present) * @civicloc_len: length of civic location information (if present) * @lci: LCI data (may be %NULL) @@ -4228,6 +4283,7 @@ struct cfg80211_pmsr_ftm_result { u8 num_bursts_exp; u8 burst_duration; u8 ftms_per_burst; + u16 burst_period; s32 rssi_avg; s32 rssi_spread; struct rate_info tx_rate, rx_rate; @@ -4290,7 +4346,9 @@ struct cfg80211_pmsr_result { * @burst_period: burst period to use * @asap: indicates to use ASAP mode * @num_bursts_exp: number of bursts exponent - * @burst_duration: burst duration + * @burst_duration: burst duration. If @trigger_based or @non_trigger_based is + * set, this is the burst duration in milliseconds, and zero means the + * device should pick an appropriate value based on @ftms_per_burst. * @ftms_per_burst: number of FTMs per burst * @ftmr_retries: number of retries for FTM request * @request_lci: request LCI information @@ -4303,6 +4361,8 @@ struct cfg80211_pmsr_result { * EDCA based ranging will be used. * @lmr_feedback: negotiate for I2R LMR feedback. Only valid if either * @trigger_based or @non_trigger_based is set. + * @rsta: Operate as the RSTA in the measurement. Only valid if @lmr_feedback + * and either @trigger_based or @non_trigger_based is set. * @bss_color: the bss color of the responder. Optional. Set to zero to * indicate the driver should set the BSS color. Only valid if * @non_trigger_based or @trigger_based is set. @@ -4318,7 +4378,8 @@ struct cfg80211_pmsr_ftm_request_peer { request_civicloc:1, trigger_based:1, non_trigger_based:1, - lmr_feedback:1; + lmr_feedback:1, + rsta:1; u8 num_bursts_exp; u8 burst_duration; u8 ftms_per_burst; @@ -5638,6 +5699,18 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); * not limited) * @ftm.trigger_based: trigger based ranging measurement is supported * @ftm.non_trigger_based: non trigger based ranging measurement is supported + * @ftm.support_6ghz: supports ranging in 6 GHz band + * @ftm.max_tx_ltf_rep: maximum number of TX LTF repetitions supported (0 means + * only one LTF, no repetitions) + * @ftm.max_rx_ltf_rep: maximum number of RX LTF repetitions supported (0 means + * only one LTF, no repetitions) + * @ftm.max_tx_sts: maximum number of TX STS supported (zero based) + * @ftm.max_rx_sts: maximum number of RX STS supported (zero based) + * @ftm.max_total_ltf_tx: maximum total number of LTFs that can be transmitted + * (0 means unknown) + * @ftm.max_total_ltf_rx: maximum total number of LTFs that can be received + * (0 means unknown) + * @ftm.support_rsta: supports operating as RSTA in PMSR FTM request */ struct cfg80211_pmsr_capabilities { unsigned int max_peers; @@ -5655,7 +5728,15 @@ struct cfg80211_pmsr_capabilities { request_lci:1, request_civicloc:1, trigger_based:1, - non_trigger_based:1; + non_trigger_based:1, + support_6ghz:1; + u8 max_tx_ltf_rep; + u8 max_rx_ltf_rep; + u8 max_tx_sts; + u8 max_rx_sts; + u8 max_total_ltf_tx; + u8 max_total_ltf_rx; + u8 support_rsta:1; } ftm; }; @@ -9785,6 +9866,21 @@ int cfg80211_iter_combinations(struct wiphy *wiphy, int cfg80211_get_radio_idx_by_chan(struct wiphy *wiphy, const struct ieee80211_channel *chan); +/** + * cfg80211_stop_link - stop AP/P2P_GO link if link_id is non-negative or stops + * all links on the interface. + * + * @wiphy: the wiphy + * @wdev: wireless device + * @link_id: valid link ID in case of MLO AP/P2P_GO Operation or else -1 + * @gfp: context flags + * + * If link_id is set during MLO operation, stops only the specified AP/P2P_GO + * link and if link_id is set to -1 or last link is stopped, the entire + * interface is stopped as if AP was stopped, IBSS/mesh left, STA disconnected. + */ +void cfg80211_stop_link(struct wiphy *wiphy, struct wireless_dev *wdev, + int link_id, gfp_t gfp); /** * cfg80211_stop_iface - trigger interface disconnection @@ -9798,8 +9894,11 @@ int cfg80211_get_radio_idx_by_chan(struct wiphy *wiphy, * * Note: This doesn't need any locks and is asynchronous. */ -void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, - gfp_t gfp); +static inline void +cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, gfp_t gfp) +{ + cfg80211_stop_link(wiphy, wdev, -1, gfp); +} /** * cfg80211_shutdown_all_interfaces - shut down all interfaces for a wiphy @@ -10147,9 +10246,9 @@ cfg80211_6ghz_power_type(u8 control, u32 client_flags) case IEEE80211_6GHZ_CTRL_REG_LPI_AP: case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: case IEEE80211_6GHZ_CTRL_REG_AP_ROLE_NOT_RELEVANT: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: return IEEE80211_REG_LPI_AP; case IEEE80211_6GHZ_CTRL_REG_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: return IEEE80211_REG_SP_AP; case IEEE80211_6GHZ_CTRL_REG_VLP_AP: return IEEE80211_REG_VLP_AP; diff --git a/include/net/dsa.h b/include/net/dsa.h index 6b2b5ed64ea4..6c17446f3dcc 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -57,6 +57,7 @@ struct tc_action; #define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 #define DSA_TAG_PROTO_YT921X_VALUE 30 #define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 +#define DSA_TAG_PROTO_MXL862_VALUE 32 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -91,6 +92,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, + DSA_TAG_PROTO_MXL862 = DSA_TAG_PROTO_MXL862_VALUE, }; struct dsa_switch; @@ -216,12 +218,6 @@ struct dsa_mall_mirror_tc_entry { bool ingress; }; -/* TC port policer entry */ -struct dsa_mall_policer_tc_entry { - u32 burst; - u64 rate_bytes_per_sec; -}; - /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; @@ -229,7 +225,7 @@ struct dsa_mall_tc_entry { enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; - struct dsa_mall_policer_tc_entry policer; + struct flow_action_police policer; }; }; @@ -1110,7 +1106,7 @@ struct dsa_switch_ops { void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); int (*port_policer_add)(struct dsa_switch *ds, int port, - struct dsa_mall_policer_tc_entry *policer); + const struct flow_action_police *policer); void (*port_policer_del)(struct dsa_switch *ds, int port); int (*port_setup_tc)(struct dsa_switch *ds, int port, enum tc_setup_type type, void *type_data); diff --git a/include/net/dst.h b/include/net/dst.h index f8aa1239b4db..307073eae7f8 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -219,6 +219,12 @@ static inline u32 dst_mtu(const struct dst_entry *dst) return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst); } +/* Variant of dst_mtu() for IPv4 users. */ +static inline u32 dst4_mtu(const struct dst_entry *dst) +{ + return INDIRECT_CALL_1(dst->ops->mtu, ipv4_mtu, dst); +} + /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric) { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 596ab9791e4d..70a02ee14308 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -231,6 +231,21 @@ struct flow_action_cookie *flow_action_cookie_create(void *data, gfp_t gfp); void flow_action_cookie_destroy(struct flow_action_cookie *cookie); +struct flow_action_police { + u32 burst; + u64 rate_bytes_ps; + u64 peakrate_bytes_ps; + u32 avrate; + u16 overhead; + u64 burst_pkt; + u64 rate_pkt_ps; + u32 mtu; + struct { + enum flow_action_id act_id; + u32 extval; + } exceed, notexceed; +}; + struct flow_action_entry { enum flow_action_id id; u32 hw_index; @@ -275,20 +290,7 @@ struct flow_action_entry { u32 trunc_size; bool truncate; } sample; - struct { /* FLOW_ACTION_POLICE */ - u32 burst; - u64 rate_bytes_ps; - u64 peakrate_bytes_ps; - u32 avrate; - u16 overhead; - u64 burst_pkt; - u64 rate_pkt_ps; - u32 mtu; - struct { - enum flow_action_id act_id; - u32 extval; - } exceed, notexceed; - } police; + struct flow_action_police police; /* FLOW_ACTION_POLICE */ struct { /* FLOW_ACTION_CT */ int action; u16 zone; @@ -526,7 +528,7 @@ static inline bool flow_rule_has_enc_control_flags(const u32 enc_ctrl_flags, * * Return: true if control flags are set, false otherwise. */ -static inline bool flow_rule_match_has_control_flags(struct flow_rule *rule, +static inline bool flow_rule_match_has_control_flags(const struct flow_rule *rule, struct netlink_ext_ack *extack) { struct flow_match_control match; @@ -718,7 +720,7 @@ struct flow_offload_action { struct flow_offload_action *offload_action_alloc(unsigned int num_actions); static inline struct flow_rule * -flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) +flow_cls_offload_flow_rule(const struct flow_cls_offload *flow_cmd) { return flow_cmd->rule; } diff --git a/include/net/gro.h b/include/net/gro.h index b65f631c521d..2300b6da05b2 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -405,9 +405,8 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); +struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *); +int udp6_gro_complete(struct sk_buff *, int); #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \ ({ \ diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 745891d2e113..ece8dabd209a 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -18,7 +18,9 @@ struct sk_buff; struct sock; struct sockaddr; -struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *inet6_csk_route_req(const struct sock *sk, + struct dst_entry *dst, + struct flowi6 *fl6, const struct request_sock *req, u8 proto); int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ea32393464a2..827b87a95dab 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -51,11 +51,25 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; } +/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + static inline void INET_ECN_xmit(struct sock *sk) { - inet_sk(sk)->tos |= INET_ECN_ECT_0; - if (inet6_sk(sk) != NULL) - inet6_sk(sk)->tclass |= INET_ECN_ECT_0; + __INET_ECN_xmit(sk, false); } static inline void INET_ECN_dontxmit(struct sock *sk) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index ac1c75975908..7cdcbed3e5cb 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -26,6 +26,8 @@ #include <net/tcp_states.h> #include <net/l3mdev.h> +#define IP_OPTIONS_DATA_FIXED_SIZE 40 + /** struct ip_options - IP Options * * @faddr - Saved first hop address @@ -58,12 +60,9 @@ struct ip_options { struct ip_options_rcu { struct rcu_head rcu; - struct ip_options opt; -}; -struct ip_options_data { - struct ip_options_rcu opt; - char data[40]; + /* Must be last as it ends in a flexible-array member. */ + struct ip_options opt; }; struct inet_request_sock { @@ -101,10 +100,7 @@ struct inet_request_sock { }; }; -static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) -{ - return (struct inet_request_sock *)sk; -} +#define inet_rsk(ptr) container_of_const(ptr, struct inet_request_sock, req) static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { @@ -163,6 +159,13 @@ static inline bool inet_sk_bound_dev_eq(const struct net *net, #endif } +struct inet6_cork { + struct ipv6_txoptions *opt; + u8 hop_limit; + u8 tclass; + u8 dontfrag:1; +}; + struct inet_cork { unsigned int flags; __be32 addr; @@ -183,6 +186,9 @@ struct inet_cork { struct inet_cork_full { struct inet_cork base; struct flowi fl; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_cork base6; +#endif }; struct ip_mc_socklist; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 7c5512baa4b2..a55f9bf95fe3 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -266,6 +266,12 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); +/* Variant of dst_mtu() for IPv6 users */ +static inline u32 dst6_mtu(const struct dst_entry *dst) +{ + return INDIRECT_CALL_1(dst->ops->mtu, ip6_mtu, dst); +} + static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 74fbf1ad8065..cc56e09525d0 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -25,8 +25,6 @@ struct ip_tunnel_info; #define SIN6_LEN_RFC2133 24 -#define IPV6_MAXPLEN 65535 - /* * NextHeader field of IPv6 header */ @@ -151,17 +149,6 @@ struct frag_hdr { __be32 identification; }; -/* - * Jumbo payload option, as described in RFC 2675 2. - */ -struct hop_jumbo_hdr { - u8 nexthdr; - u8 hdrlen; - u8 tlv_type; /* IPV6_TLV_JUMBO, 0xC2 */ - u8 tlv_len; /* 4 */ - __be32 jumbo_payload_len; -}; - #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 @@ -464,72 +451,6 @@ bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); -/* This helper is specialized for BIG TCP needs. - * It assumes the hop_jumbo_hdr will immediately follow the IPV6 header. - * It assumes headers are already in skb->head. - * Returns: 0, or IPPROTO_TCP if a BIG TCP packet is there. - */ -static inline int ipv6_has_hopopt_jumbo(const struct sk_buff *skb) -{ - const struct hop_jumbo_hdr *jhdr; - const struct ipv6hdr *nhdr; - - if (likely(skb->len <= GRO_LEGACY_MAX_SIZE)) - return 0; - - if (skb->protocol != htons(ETH_P_IPV6)) - return 0; - - if (skb_network_offset(skb) + - sizeof(struct ipv6hdr) + - sizeof(struct hop_jumbo_hdr) > skb_headlen(skb)) - return 0; - - nhdr = ipv6_hdr(skb); - - if (nhdr->nexthdr != NEXTHDR_HOP) - return 0; - - jhdr = (const struct hop_jumbo_hdr *) (nhdr + 1); - if (jhdr->tlv_type != IPV6_TLV_JUMBO || jhdr->hdrlen != 0 || - jhdr->nexthdr != IPPROTO_TCP) - return 0; - return jhdr->nexthdr; -} - -/* Return 0 if HBH header is successfully removed - * Or if HBH removal is unnecessary (packet is not big TCP) - * Return error to indicate dropping the packet - */ -static inline int ipv6_hopopt_jumbo_remove(struct sk_buff *skb) -{ - const int hophdr_len = sizeof(struct hop_jumbo_hdr); - int nexthdr = ipv6_has_hopopt_jumbo(skb); - struct ipv6hdr *h6; - - if (!nexthdr) - return 0; - - if (skb_cow_head(skb, 0)) - return -1; - - /* Remove the HBH header. - * Layout: [Ethernet header][IPv6 header][HBH][L4 Header] - */ - memmove(skb_mac_header(skb) + hophdr_len, skb_mac_header(skb), - skb_network_header(skb) - skb_mac_header(skb) + - sizeof(struct ipv6hdr)); - - __skb_pull(skb, hophdr_len); - skb->network_header += hophdr_len; - skb->mac_header += hophdr_len; - - h6 = ipv6_hdr(skb); - h6->nexthdr = nexthdr; - - return 0; -} - static inline bool ipv6_accept_ra(const struct inet6_dev *idev) { s32 accept_ra = READ_ONCE(idev->cnf.accept_ra); @@ -931,10 +852,10 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, #if IS_ENABLED(CONFIG_IPV6) -static inline bool ipv6_can_nonlocal_bind(struct net *net, - struct inet_sock *inet) +static inline bool ipv6_can_nonlocal_bind(const struct net *net, + const struct inet_sock *inet) { - return net->ipv6.sysctl.ip_nonlocal_bind || + return READ_ONCE(net->ipv6.sysctl.ip_nonlocal_bind) || test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) || test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags); } @@ -949,10 +870,12 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net, #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT -static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, +static inline __be32 ip6_make_flowlabel(const struct net *net, + struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { + u8 auto_flowlabels; u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. @@ -960,10 +883,12 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, */ flowlabel &= IPV6_FLOWLABEL_MASK; - if (flowlabel || - net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || - (!autolabel && - net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) + if (flowlabel) + return flowlabel; + + auto_flowlabels = READ_ONCE(net->ipv6.sysctl.auto_flowlabels); + if (auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || + (!autolabel && auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); @@ -976,15 +901,15 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; - if (net->ipv6.sysctl.flowlabel_state_ranges) + if (READ_ONCE(net->ipv6.sysctl.flowlabel_state_ranges)) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } -static inline int ip6_default_np_autolabel(struct net *net) +static inline int ip6_default_np_autolabel(const struct net *net) { - switch (net->ipv6.sysctl.auto_flowlabels) { + switch (READ_ONCE(net->ipv6.sysctl.auto_flowlabels)) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: @@ -995,13 +920,13 @@ static inline int ip6_default_np_autolabel(struct net *net) } } #else -static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, +static inline __be32 ip6_make_flowlabel(const struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } -static inline int ip6_default_np_autolabel(struct net *net) +static inline int ip6_default_np_autolabel(const struct net *net) { return 0; } @@ -1010,11 +935,11 @@ static inline int ip6_default_np_autolabel(struct net *net) #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { - return net->ipv6.sysctl.multipath_hash_policy; + return READ_ONCE(net->ipv6.sysctl.multipath_hash_policy); } static inline u32 ip6_multipath_hash_fields(const struct net *net) { - return net->ipv6.sysctl.multipath_hash_fields; + return READ_ONCE(net->ipv6.sysctl.multipath_hash_fields); } #else static inline int ip6_multipath_hash_policy(const struct net *net) @@ -1103,8 +1028,7 @@ void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, - struct inet_cork_full *cork, - struct inet6_cork *v6_cork); + struct inet_cork_full *cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), @@ -1115,8 +1039,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { - return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, - &inet6_sk(sk)->cork); + return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, @@ -1147,11 +1070,11 @@ int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); * Extension header (options) processing */ -void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, - u8 *proto, struct in6_addr **daddr_p, - struct in6_addr *saddr); -void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, - u8 *proto); +u8 ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, + u8 proto, struct in6_addr **daddr_p, + struct in6_addr *saddr); +u8 ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, + u8 proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); @@ -1170,9 +1093,19 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); -struct in6_addr *fl6_update_dst(struct flowi6 *fl6, - const struct ipv6_txoptions *opt, - struct in6_addr *orig); +struct in6_addr *__fl6_update_dst(struct flowi6 *fl6, + const struct ipv6_txoptions *opt, + struct in6_addr *orig); + +static inline struct in6_addr * +fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, + struct in6_addr *orig) +{ + if (likely(!opt)) + return NULL; + + return __fl6_update_dst(fl6, opt, orig); +} /* * socket options (ipv6_sockglue.c) diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 9804fa5d9c67..5606ed6e7084 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -195,35 +195,15 @@ struct iucv_handler { struct list_head paths; }; -/** - * iucv_register: - * @handler: address of iucv handler structure - * @smp: != 0 indicates that the handler can deal with out of order messages - * - * Registers a driver with IUCV. - * - * Returns: 0 on success, -ENOMEM if the memory allocation for the pathid - * table failed, or -EIO if IUCV_DECLARE_BUFFER failed on all cpus. - */ int iucv_register(struct iucv_handler *handler, int smp); +void iucv_unregister(struct iucv_handler *handler, int smp); /** - * iucv_unregister - * @handler: address of iucv handler structure - * @smp: != 0 indicates that the handler can deal with out of order messages - * - * Unregister driver from IUCV. - */ -void iucv_unregister(struct iucv_handler *handle, int smp); - -/** - * iucv_path_alloc + * iucv_path_alloc - Allocate a new path structure for use with iucv_connect. * @msglim: initial message limit * @flags: initial flags * @gfp: kmalloc allocation flag * - * Allocate a new path structure for use with iucv_connect. - * * Returns: NULL if the memory allocation failed or a pointer to the * path structure. */ @@ -240,229 +220,48 @@ static inline struct iucv_path *iucv_path_alloc(u16 msglim, u8 flags, gfp_t gfp) } /** - * iucv_path_free + * iucv_path_free - Frees a path structure. * @path: address of iucv path structure - * - * Frees a path structure. */ static inline void iucv_path_free(struct iucv_path *path) { kfree(path); } -/** - * iucv_path_accept - * @path: address of iucv path structure - * @handler: address of iucv handler structure - * @userdata: 16 bytes of data reflected to the communication partner - * @private: private data passed to interrupt handlers for this path - * - * This function is issued after the user received a connection pending - * external interrupt and now wishes to complete the IUCV communication path. - * - * Returns: the result of the CP IUCV call. - */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, u8 *userdata, void *private); -/** - * iucv_path_connect - * @path: address of iucv path structure - * @handler: address of iucv handler structure - * @userid: 8-byte user identification - * @system: 8-byte target system identification - * @userdata: 16 bytes of data reflected to the communication partner - * @private: private data passed to interrupt handlers for this path - * - * This function establishes an IUCV path. Although the connect may complete - * successfully, you are not able to use the path until you receive an IUCV - * Connection Complete external interrupt. - * - * Returns: the result of the CP IUCV call. - */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, u8 *userid, u8 *system, u8 *userdata, void *private); -/** - * iucv_path_quiesce: - * @path: address of iucv path structure - * @userdata: 16 bytes of data reflected to the communication partner - * - * This function temporarily suspends incoming messages on an IUCV path. - * You can later reactivate the path by invoking the iucv_resume function. - * - * Returns: the result from the CP IUCV call. - */ int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); -/** - * iucv_path_resume: - * @path: address of iucv path structure - * @userdata: 16 bytes of data reflected to the communication partner - * - * This function resumes incoming messages on an IUCV path that has - * been stopped with iucv_path_quiesce. - * - * Returns: the result from the CP IUCV call. - */ int iucv_path_resume(struct iucv_path *path, u8 *userdata); -/** - * iucv_path_sever - * @path: address of iucv path structure - * @userdata: 16 bytes of data reflected to the communication partner - * - * This function terminates an IUCV path. - * - * Returns: the result from the CP IUCV call. - */ int iucv_path_sever(struct iucv_path *path, u8 *userdata); -/** - * iucv_message_purge - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @srccls: source class of message - * - * Cancels a message you have sent. - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg, u32 srccls); -/** - * iucv_message_receive - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: flags that affect how the message is received (IUCV_IPBUFLST) - * @buffer: address of data buffer or address of struct iucv_array - * @size: length of data buffer - * @residual: - * - * This function receives messages that are being sent to you over - * established paths. This function will deal with RMDATA messages - * embedded in struct iucv_message as well. - * - * Locking: local_bh_enable/local_bh_disable - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, size_t *residual); -/** - * __iucv_message_receive - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: flags that affect how the message is received (IUCV_IPBUFLST) - * @buffer: address of data buffer or address of struct iucv_array - * @size: length of data buffer - * @residual: - * - * This function receives messages that are being sent to you over - * established paths. This function will deal with RMDATA messages - * embedded in struct iucv_message as well. - * - * Locking: no locking. - * - * Returns: the result from the CP IUCV call. - */ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *buffer, size_t size, size_t *residual); -/** - * iucv_message_reject - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * - * The reject function refuses a specified message. Between the time you - * are notified of a message and the time that you complete the message, - * the message may be rejected. - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_reject(struct iucv_path *path, struct iucv_message *msg); -/** - * iucv_message_reply - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: how the reply is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST) - * @reply: address of data buffer or address of struct iucv_array - * @size: length of reply data buffer - * - * This function responds to the two-way messages that you receive. You - * must identify completely the message to which you wish to reply. ie, - * pathid, msgid, and trgcls. Prmmsg signifies the data is moved into - * the parameter list. - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg, u8 flags, void *reply, size_t size); -/** - * iucv_message_send - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: how the message is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST) - * @srccls: source class of message - * @buffer: address of data buffer or address of struct iucv_array - * @size: length of send buffer - * - * This function transmits data to another application. Data to be - * transmitted is in a buffer and this is a one-way message and the - * receiver will not reply to the message. - * - * Locking: local_bh_enable/local_bh_disable - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); -/** - * __iucv_message_send - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: how the message is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST) - * @srccls: source class of message - * @buffer: address of data buffer or address of struct iucv_array - * @size: length of send buffer - * - * This function transmits data to another application. Data to be - * transmitted is in a buffer and this is a one-way message and the - * receiver will not reply to the message. - * - * Locking: no locking. - * - * Returns: the result from the CP IUCV call. - */ int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size); -/** - * iucv_message_send2way - * @path: address of iucv path structure - * @msg: address of iucv msg structure - * @flags: how the message is sent and the reply is received - * (IUCV_IPRMDATA, IUCV_IPBUFLST, IUCV_IPPRTY, IUCV_ANSLST) - * @srccls: source class of message - * @buffer: address of data buffer or address of struct iucv_array - * @size: length of send buffer - * @ansbuf: address of answer buffer or address of struct iucv_array - * @asize: size of reply buffer - * - * This function transmits data to another application. Data to be - * transmitted is in a buffer. The receiver of the send is expected to - * reply to the message and a buffer is provided into which IUCV moves - * the reply to this message. - * - * Returns: the result from the CP IUCV call. - */ int iucv_message_send2way(struct iucv_path *path, struct iucv_message *msg, u8 flags, u32 srccls, void *buffer, size_t size, void *answer, size_t asize, size_t *residual); diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 1eb8dad18f7e..710e98665eb3 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -207,18 +207,19 @@ struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb) static inline struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) { - struct net_device *dev = skb_dst(skb)->dev; + struct net_device *dev; + rcu_read_lock(); + dev = skb_dst_dev_rcu(skb); if (netif_is_l3_slave(dev)) { struct net_device *master; - rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); - rcu_read_unlock(); } + rcu_read_unlock(); return skb; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c2e49542626c..7f9d96939a4e 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -7,7 +7,7 @@ * Copyright 2007-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2025 Intel Corporation + * Copyright (C) 2018 - 2026 Intel Corporation */ #ifndef MAC80211_H @@ -706,6 +706,7 @@ struct ieee80211_parsed_tpe { * @pwr_reduction: power constraint of BSS. * @eht_support: does this BSS support EHT * @epcs_support: does this BSS support EPCS + * @uhr_support: does this BSS support UHR * @csa_active: marks whether a channel switch is going on. * @mu_mimo_owner: indicates interface owns MU-MIMO capability * @chanctx_conf: The channel context this interface is assigned to, or %NULL @@ -832,6 +833,8 @@ struct ieee80211_bss_conf { u8 pwr_reduction; bool eht_support; bool epcs_support; + bool uhr_support; + bool csa_active; bool mu_mimo_owner; @@ -1598,6 +1601,7 @@ enum mac80211_rx_encoding { RX_ENC_VHT, RX_ENC_HE, RX_ENC_EHT, + RX_ENC_UHR, }; /** @@ -1631,7 +1635,7 @@ enum mac80211_rx_encoding { * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT or VHT is used (%RX_FLAG_HT/%RX_FLAG_VHT) - * @nss: number of streams (VHT, HE and EHT only) + * @nss: number of streams (VHT, HE, EHT and UHR only) * @flag: %RX_FLAG_\* * @encoding: &enum mac80211_rx_encoding * @bw: &enum rate_info_bw @@ -1642,6 +1646,11 @@ enum mac80211_rx_encoding { * @eht: EHT specific rate information * @eht.ru: EHT RU, from &enum nl80211_eht_ru_alloc * @eht.gi: EHT GI, from &enum nl80211_eht_gi + * @uhr: UHR specific rate information + * @uhr.ru: UHR RU, from &enum nl80211_eht_ru_alloc + * @uhr.gi: UHR GI, from &enum nl80211_eht_gi + * @uhr.elr: UHR ELR MCS was used + * @uhr.im: UHR interference mitigation was used * @rx_flags: internal RX flags for mac80211 * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU @@ -1673,6 +1682,12 @@ struct ieee80211_rx_status { u8 ru:4; u8 gi:2; } eht; + struct { + u8 ru:4; + u8 gi:2; + u8 elr:1; + u8 im:1; + } uhr; }; u8 rate_idx; u8 nss; @@ -1903,6 +1918,31 @@ enum ieee80211_offload_flags { }; /** + * struct ieee80211_eml_params - EHT Operating mode notification parameters + * + * EML Operating mode notification parameters received in the Operating mode + * notification frame. This struct is used as a container to pass the info to + * the underlay driver. + * + * @link_id: the link ID where the Operating mode notification frame has been + * received. + * @control: EML control field defined in P802.11be section 9.4.1.76. + * @link_bitmap: eMLSR/eMLMR enabled links defined in P802.11be + * section 9.4.1.76. + * @emlmr_mcs_map_count: eMLMR number of valid mcs_map_bw fields according to + * P802.11be section 9.4.1.76 (valid if eMLMR mode control bit is set). + * @emlmr_mcs_map_bw: eMLMR supported MCS and NSS set subfileds defined in + * P802.11be section 9.4.1.76 (valid if eMLMR mode control bit is set). + */ +struct ieee80211_eml_params { + u8 link_id; + u8 control; + u16 link_bitmap; + u8 emlmr_mcs_map_count; + u8 emlmr_mcs_map_bw[9]; +}; + +/** * struct ieee80211_vif_cfg - interface configuration * @assoc: association status * @ibss_joined: indicates whether this station is part of an IBSS or not @@ -2434,6 +2474,7 @@ struct ieee80211_sta_aggregates { * @he_cap: HE capabilities of this STA * @he_6ghz_capa: on 6 GHz, holds the HE 6 GHz band capabilities * @eht_cap: EHT capabilities of this STA + * @uhr_cap: UHR capabilities of this STA * @s1g_cap: S1G capabilities of this STA * @agg: per-link data for multi-link aggregation * @bandwidth: current bandwidth the station can receive with @@ -2457,6 +2498,7 @@ struct ieee80211_link_sta { struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; + struct ieee80211_sta_uhr_cap uhr_cap; struct ieee80211_sta_s1g_cap s1g_cap; struct ieee80211_sta_aggregates agg; @@ -2520,6 +2562,7 @@ struct ieee80211_link_sta { * by the AP. * @valid_links: bitmap of valid links, or 0 for non-MLO * @spp_amsdu: indicates whether the STA uses SPP A-MSDU or not. + * @epp_peer: indicates that the peer is an EPP peer. */ struct ieee80211_sta { u8 addr[ETH_ALEN] __aligned(2); @@ -2544,6 +2587,7 @@ struct ieee80211_sta { struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; u16 valid_links; + bool epp_peer; struct ieee80211_link_sta deflink; struct ieee80211_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS]; @@ -4511,6 +4555,9 @@ struct ieee80211_prep_tx_info { * interface with the specified type would be added, and thus drivers that * implement this callback need to handle such cases. The type is the full * &enum nl80211_iftype. + * @set_eml_op_mode: Configure eMLSR/eMLMR operation mode in the underlay + * driver according to the parameter received in the EML Operating mode + * notification frame. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4906,6 +4953,10 @@ struct ieee80211_ops { struct ieee80211_neg_ttlm *ttlm); void (*prep_add_interface)(struct ieee80211_hw *hw, enum nl80211_iftype type); + int (*set_eml_op_mode)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_eml_params *eml_params); }; /** @@ -6272,6 +6323,30 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, struct ieee80211_vif *vif), void *data); +struct ieee80211_vif * +__ieee80211_iterate_interfaces(struct ieee80211_hw *hw, + struct ieee80211_vif *prev, + u32 iter_flags); + +/** + * for_each_interface - iterate interfaces under wiphy mutex + * @vif: the iterator variable + * @hw: the HW to iterate for + * @flags: the iteration flags, see &enum ieee80211_interface_iteration_flags + */ +#define for_each_interface(vif, hw, flags) \ + for (vif = __ieee80211_iterate_interfaces(hw, NULL, flags); \ + vif; \ + vif = __ieee80211_iterate_interfaces(hw, vif, flags)) + +/** + * for_each_active_interface - iterate active interfaces under wiphy mutex + * @vif: the iterator variable + * @hw: the HW to iterate for + */ +#define for_each_active_interface(vif, hw) \ + for_each_interface(vif, hw, IEEE80211_IFACE_ITER_ACTIVE) + /** * ieee80211_iterate_active_interfaces_mtx - iterate active interfaces * @@ -6284,12 +6359,18 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, * @iterator: the iterator function to call, cannot sleep * @data: first argument of the iterator function */ -void ieee80211_iterate_active_interfaces_mtx(struct ieee80211_hw *hw, - u32 iter_flags, - void (*iterator)(void *data, - u8 *mac, - struct ieee80211_vif *vif), - void *data); +static inline void +ieee80211_iterate_active_interfaces_mtx(struct ieee80211_hw *hw, + u32 iter_flags, + void (*iterator)(void *data, u8 *mac, + struct ieee80211_vif *vif), + void *data) +{ + struct ieee80211_vif *vif; + + for_each_interface(vif, hw, iter_flags | IEEE80211_IFACE_ITER_ACTIVE) + iterator(data, vif->addr, vif); +} /** * ieee80211_iterate_stations_atomic - iterate stations @@ -6308,6 +6389,20 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, struct ieee80211_sta *sta), void *data); +struct ieee80211_sta * +__ieee80211_iterate_stations(struct ieee80211_hw *hw, + struct ieee80211_sta *prev); + +/** + * for_each_station - iterate stations under wiphy mutex + * @sta: the iterator variable + * @hw: the HW to iterate for + */ +#define for_each_station(sta, hw) \ + for (sta = __ieee80211_iterate_stations(hw, NULL); \ + sta; \ + sta = __ieee80211_iterate_stations(hw, sta)) + /** * ieee80211_iterate_stations_mtx - iterate stations * @@ -6320,10 +6415,17 @@ void ieee80211_iterate_stations_atomic(struct ieee80211_hw *hw, * @iterator: the iterator function to call * @data: first argument of the iterator function */ -void ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, - void (*iterator)(void *data, - struct ieee80211_sta *sta), - void *data); +static inline void +ieee80211_iterate_stations_mtx(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data) +{ + struct ieee80211_sta *sta; + + for_each_station(sta, hw) + iterator(data, sta); +} /** * ieee80211_queue_work - add work onto the mac80211 workqueue @@ -7237,6 +7339,20 @@ ieee80211_get_eht_iftype_cap_vif(const struct ieee80211_supported_band *sband, } /** + * ieee80211_get_uhr_iftype_cap_vif - return UHR capabilities for sband/vif + * @sband: the sband to search for the iftype on + * @vif: the vif to get the iftype from + * + * Return: pointer to the struct ieee80211_sta_uhr_cap, or %NULL is none found + */ +static inline const struct ieee80211_sta_uhr_cap * +ieee80211_get_uhr_iftype_cap_vif(const struct ieee80211_supported_band *sband, + struct ieee80211_vif *vif) +{ + return ieee80211_get_uhr_iftype_cap(sband, ieee80211_vif_type_p2p(vif)); +} + +/** * ieee80211_update_mu_groups - set the VHT MU-MIMO groud data * * @vif: the specified virtual interface diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index eaa27483f99b..a59bd4035a99 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -598,6 +598,10 @@ enum { /* Driver can self reset on FPGA Reconfig EQE notification */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) + +/* Driver detects stalled send queues and recovers them */ +#define GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY BIT(18) + #define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) /* Driver supports linearizing the skb when num_sge exceeds hardware limit */ @@ -621,7 +625,8 @@ enum { GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY | \ GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \ - GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY) + GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \ + GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index d7e089c6b694..a078af283bdd 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -480,7 +480,7 @@ struct mana_context { struct mana_ethtool_hc_stats hc_stats; struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; - + struct workqueue_struct *per_port_queue_reset_wq; /* Workqueue for querying hardware stats */ struct delayed_work gf_stats_work; bool hwc_timeout_occurred; @@ -495,6 +495,7 @@ struct mana_context { struct mana_port_context { struct mana_context *ac; struct net_device *ndev; + struct work_struct queue_reset_work; u8 mac_addr[ETH_ALEN]; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index cb664f6e3558..d7bec49ee9ea 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -37,6 +37,7 @@ #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> +#include <net/netns/vsock.h> #include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> @@ -120,6 +121,7 @@ struct net { * it is critical that it is on a read_mostly cache line. */ u32 hash_mix; + bool is_dying; struct net_device *loopback_dev; /* The loopback */ @@ -196,6 +198,9 @@ struct net { /* Move to a better place when the config guard is removed. */ struct mutex rtnl_mutex; #endif +#if IS_ENABLED(CONFIG_VSOCKETS) + struct netns_vsock vsock; +#endif } __randomize_layout; #include <linux/seq_file_net.h> diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index cd00e0406cf4..95ed28212f4e 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -14,6 +14,10 @@ struct netdev_config { u8 hds_config; }; +struct netdev_queue_config { + u32 rx_page_size; +}; + /* See the netdev.yaml spec for definition of each statistic */ struct netdev_queue_stats_rx { u64 bytes; @@ -111,6 +115,11 @@ void netdev_stat_queue_sum(struct net_device *netdev, int tx_start, int tx_end, struct netdev_queue_stats_tx *tx_sum); +enum { + /* The queue checks and honours the page size qcfg parameter */ + QCFG_RX_PAGE_SIZE = 0x1, +}; + /** * struct netdev_queue_mgmt_ops - netdev ops for queue management * @@ -130,27 +139,52 @@ void netdev_stat_queue_sum(struct net_device *netdev, * @ndo_queue_get_dma_dev: Get dma device for zero-copy operations to be used * for this queue. Return NULL on error. * + * @ndo_default_qcfg: (Optional) Populate queue config struct with defaults. + * Queue config structs are passed to this helper before + * the user-requested settings are applied. + * + * @ndo_validate_qcfg: (Optional) Check if queue config is supported. + * Called when configuration affecting a queue may be + * changing, either due to NIC-wide config, or config + * scoped to the queue at a specified index. + * When NIC-wide config is changed the callback will + * be invoked for all queues. + * + * @supported_params: Bitmask of supported parameters, see QCFG_*. + * * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only * be called for an interface which is open. */ struct netdev_queue_mgmt_ops { - size_t ndo_queue_mem_size; - int (*ndo_queue_mem_alloc)(struct net_device *dev, - void *per_queue_mem, - int idx); - void (*ndo_queue_mem_free)(struct net_device *dev, - void *per_queue_mem); - int (*ndo_queue_start)(struct net_device *dev, - void *per_queue_mem, - int idx); - int (*ndo_queue_stop)(struct net_device *dev, - void *per_queue_mem, - int idx); - struct device * (*ndo_queue_get_dma_dev)(struct net_device *dev, - int idx); + size_t ndo_queue_mem_size; + int (*ndo_queue_mem_alloc)(struct net_device *dev, + struct netdev_queue_config *qcfg, + void *per_queue_mem, + int idx); + void (*ndo_queue_mem_free)(struct net_device *dev, + void *per_queue_mem); + int (*ndo_queue_start)(struct net_device *dev, + struct netdev_queue_config *qcfg, + void *per_queue_mem, + int idx); + int (*ndo_queue_stop)(struct net_device *dev, + void *per_queue_mem, + int idx); + void (*ndo_default_qcfg)(struct net_device *dev, + struct netdev_queue_config *qcfg); + int (*ndo_validate_qcfg)(struct net_device *dev, + struct netdev_queue_config *qcfg, + struct netlink_ext_ack *extack); + struct device * (*ndo_queue_get_dma_dev)(struct net_device *dev, + int idx); + + unsigned int supported_params; }; +void netdev_queue_config(struct net_device *dev, int rxq, + struct netdev_queue_config *qcfg); + bool netif_rxq_has_unreadable_mp(struct net_device *dev, int idx); /** @@ -310,6 +344,17 @@ static inline void netif_subqueue_sent(const struct net_device *dev, netdev_tx_sent_queue(txq, bytes); } +static inline unsigned int netif_xmit_timeout_ms(struct netdev_queue *txq) +{ + unsigned long trans_start = READ_ONCE(txq->trans_start); + + if (netif_xmit_stopped(txq) && + time_after(jiffies, trans_start + txq->dev->watchdog_timeo)) + return jiffies_to_msecs(jiffies - trans_start); + + return 0; +} + #define netif_subqueue_maybe_stop(dev, idx, get_desc, stop_thrs, start_thrs) \ ({ \ struct netdev_queue *_txq; \ diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h index 8cdcd138b33f..cfa72c485387 100644 --- a/include/net/netdev_rx_queue.h +++ b/include/net/netdev_rx_queue.h @@ -7,6 +7,7 @@ #include <linux/sysfs.h> #include <net/xdp.h> #include <net/page_pool/types.h> +#include <net/netdev_queues.h> /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { @@ -27,6 +28,7 @@ struct netdev_rx_queue { struct xsk_buff_pool *pool; #endif struct napi_struct *napi; + struct netdev_queue_config qcfg; struct pp_memory_provider_params mp_params; } ____cacheline_aligned_in_smp; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index aa0a7c82199e..bc42dd0e10e6 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -16,6 +16,7 @@ #include <linux/bitops.h> #include <linux/compiler.h> +#include <net/netns/generic.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/netfilter/nf_conntrack_tcp.h> #include <linux/netfilter/nf_conntrack_sctp.h> diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 52a06de41aa0..cf0166520cf3 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -13,6 +13,7 @@ struct nf_conncount_list { u32 last_gc; /* jiffies at most recent gc */ struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ + unsigned int last_gc_count; /* length of list at most recent gc */ }; struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int keylen); diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h index f7dd950ff250..4d55b7325707 100644 --- a/include/net/netfilter/nf_conntrack_tuple.h +++ b/include/net/netfilter/nf_conntrack_tuple.h @@ -11,7 +11,7 @@ #ifndef _NF_CONNTRACK_TUPLE_H #define _NF_CONNTRACK_TUPLE_H -#include <linux/netfilter/x_tables.h> +#include <linux/netfilter.h> #include <linux/netfilter/nf_conntrack_tuple_common.h> #include <linux/list_nulls.h> diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 4aeffddb7586..45eb26b2e95b 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -6,11 +6,13 @@ #include <linux/ipv6.h> #include <linux/jhash.h> #include <linux/netfilter.h> +#include <linux/rhashtable-types.h> #include <linux/skbuff.h> /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { struct list_head list; + struct rhash_head hash_node; struct sk_buff *skb; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ @@ -19,7 +21,9 @@ struct nf_queue_entry { struct net_device *physout; #endif struct nf_hook_state state; + bool nf_ct_is_unconfirmed; u16 size; /* sizeof(entry) + saved route keys */ + u16 queue_num; /* extra space to store route keys */ }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 0e266c2d0e7f..426534a711b0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -6,7 +6,6 @@ #include <linux/list.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> -#include <linux/netfilter/x_tables.h> #include <linux/netfilter/nf_tables.h> #include <linux/u64_stats_sync.h> #include <linux/rhashtable.h> @@ -278,6 +277,8 @@ struct nft_userdata { unsigned char data[]; }; +#define NFT_SET_ELEM_INTERNAL_LAST 0x1 + /* placeholder structure for opaque set element backend representation. */ struct nft_elem_priv { }; @@ -287,6 +288,7 @@ struct nft_elem_priv { }; * @key: element key * @key_end: closing element key * @data: element data + * @flags: flags * @priv: element private data and extensions */ struct nft_set_elem { @@ -302,6 +304,7 @@ struct nft_set_elem { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; + u32 flags; struct nft_elem_priv *priv; }; @@ -452,6 +455,7 @@ struct nft_set_ext; * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @gc_init: initialize garbage collection + * @abort_skip_removal: skip removal of elements from abort path * @elemsize: element private size * * Operations lookup, update and delete have simpler interfaces, are faster @@ -509,6 +513,7 @@ struct nft_set_ops { const struct nft_set *set); void (*gc_init)(const struct nft_set *set); + bool abort_skip_removal; unsigned int elemsize; }; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index a0633eeaec97..c53ac00bb974 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -42,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt) if (ip6h->version != 6) return -1; - pkt_len = ntohs(ip6h->payload_len); + pkt_len = ipv6_payload_len(pkt->skb, ip6h); skb_len = pkt->skb->len - skb_network_offset(pkt->skb); if (pkt_len + sizeof(*ip6h) > skb_len) return -1; @@ -86,7 +86,7 @@ static inline int nft_set_pktinfo_ipv6_ingress(struct nft_pktinfo *pkt) if (ip6h->version != 6) goto inhdr_error; - pkt_len = ntohs(ip6h->payload_len); + pkt_len = ipv6_payload_len(pkt->skb, ip6h); if (pkt_len + sizeof(*ip6h) > pkt->skb->len) { idev = __in6_dev_get(nft_in(pkt)); __IP6_INC_STATS(nft_net(pkt), idev, IPSTATS_MIB_INTRUNCATEDPKTS); diff --git a/include/net/netmem.h b/include/net/netmem.h index 9e10f4ac50c3..a96b3e5e5574 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -389,8 +389,36 @@ static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) return netmem_to_nmdesc(netmem)->dma_addr; } -void get_netmem(netmem_ref netmem); -void put_netmem(netmem_ref netmem); +#if defined(CONFIG_NET_DEVMEM) +static inline bool net_is_devmem_iov(const struct net_iov *niov) +{ + return niov->type == NET_IOV_DMABUF; +} +#else +static inline bool net_is_devmem_iov(const struct net_iov *niov) +{ + return false; +} +#endif + +void __get_netmem(netmem_ref netmem); +void __put_netmem(netmem_ref netmem); + +static __always_inline void get_netmem(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + __get_netmem(netmem); + else + get_page(netmem_to_page(netmem)); +} + +static __always_inline void put_netmem(netmem_ref netmem) +{ + if (netmem_is_net_iov(netmem)) + __put_netmem(netmem); + else + put_page(netmem_to_page(netmem)); +} #define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL) \ do { \ diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 08d2ecc96e2b..34bdb1308e8f 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -30,19 +30,23 @@ struct netns_sysctl_ipv6 { int ip6_rt_min_advmss; u32 multipath_hash_fields; u8 multipath_hash_policy; - u8 bindv6only; + + __cacheline_group_begin(sysctl_ipv6_flowlabel); u8 flowlabel_consistency; u8 auto_flowlabels; - int icmpv6_time; + u8 flowlabel_state_ranges; + __cacheline_group_end(sysctl_ipv6_flowlabel); + u8 icmpv6_echo_ignore_all; u8 icmpv6_echo_ignore_multicast; u8 icmpv6_echo_ignore_anycast; + int icmpv6_time; DECLARE_BITMAP(icmpv6_ratemask, ICMPV6_MSG_MAX + 1); unsigned long *icmpv6_ratemask_ptr; u8 anycast_src_echo_reply; + u8 bindv6only; u8 ip_nonlocal_bind; u8 fwmark_reflect; - u8 flowlabel_state_ranges; int idgen_retries; int idgen_delay; int flowlabel_reflect; diff --git a/include/net/netns/vsock.h b/include/net/netns/vsock.h new file mode 100644 index 000000000000..b34d69a22fa8 --- /dev/null +++ b/include/net/netns/vsock.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NET_NAMESPACE_VSOCK_H +#define __NET_NET_NAMESPACE_VSOCK_H + +#include <linux/types.h> + +enum vsock_net_mode { + VSOCK_NET_MODE_GLOBAL, + VSOCK_NET_MODE_LOCAL, +}; + +struct netns_vsock { + struct ctl_table_header *sysctl_hdr; + + /* protected by the vsock_table_lock in af_vsock.c */ + u32 port; + + enum vsock_net_mode mode; + enum vsock_net_mode child_ns_mode; +}; +#endif /* __NET_NET_NAMESPACE_VSOCK_H */ diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 1509a536cb85..0d453484a585 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -161,6 +161,7 @@ struct memory_provider_ops; struct pp_memory_provider_params { void *mp_priv; const struct memory_provider_ops *mp_ops; + u32 rx_page_size; }; struct page_pool { diff --git a/include/net/phy/realtek_phy.h b/include/net/phy/realtek_phy.h new file mode 100644 index 000000000000..d683bc1b0659 --- /dev/null +++ b/include/net/phy/realtek_phy.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _REALTEK_PHY_H +#define _REALTEK_PHY_H + +#define PHY_ID_RTL_DUMMY_SFP 0x001ccbff + +#endif /* _REALTEK_PHY_H */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index e703c507d0da..18a419cd9d94 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -308,4 +308,28 @@ static inline unsigned int qdisc_peek_len(struct Qdisc *sch) return len; } +static inline void qdisc_lock_init(struct Qdisc *sch, + const struct Qdisc_ops *ops) +{ + spin_lock_init(&sch->q.lock); + + /* Skip dynamic keys if nesting is not possible */ + if (ops->static_flags & TCQ_F_INGRESS || + ops == &noqueue_qdisc_ops) + return; + + lockdep_register_key(&sch->root_lock_key); + lockdep_set_class(&sch->q.lock, &sch->root_lock_key); +} + +static inline void qdisc_lock_uninit(struct Qdisc *sch, + const struct Qdisc_ops *ops) +{ + if (ops->static_flags & TCQ_F_INGRESS || + ops == &noqueue_qdisc_ops) + return; + + lockdep_unregister_key(&sch->root_lock_key); +} + #endif diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 9b9e04f6bb89..5a9c826a7092 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -123,14 +123,7 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb, return sk; } -static inline void __reqsk_free(struct request_sock *req) -{ - req->rsk_ops->destructor(req); - if (req->rsk_listener) - sock_put(req->rsk_listener); - kfree(req->saved_syn); - kmem_cache_free(req->rsk_ops->slab, req); -} +void __reqsk_free(struct request_sock *req); static inline void reqsk_free(struct request_sock *req) { @@ -196,8 +189,6 @@ struct request_sock_queue { */ }; -void reqsk_queue_alloc(struct request_sock_queue *queue); - void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset); diff --git a/include/net/sch_priv.h b/include/net/sch_priv.h new file mode 100644 index 000000000000..4789f668ae87 --- /dev/null +++ b/include/net/sch_priv.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_SCHED_PRIV_H +#define __NET_SCHED_PRIV_H + +#include <net/sch_generic.h> + +struct mq_sched { + struct Qdisc **qdiscs; +}; + +int mq_init_common(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack, + const struct Qdisc_ops *qdisc_ops); +void mq_destroy_common(struct Qdisc *sch); +void mq_attach(struct Qdisc *sch); +void mq_dump_common(struct Qdisc *sch, struct sk_buff *skb); +struct netdev_queue *mq_select_queue(struct Qdisc *sch, + struct tcmsg *tcm); +struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl); +unsigned long mq_find(struct Qdisc *sch, u32 classid); +int mq_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm); +int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d); +void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg); + +#endif diff --git a/include/net/sock.h b/include/net/sock.h index aafe8bdb2c0f..66b56288c1d3 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -341,6 +341,7 @@ struct sk_filter; * @sk_reuseport_cb: reuseport group container * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period + * @sk_freeptr: used for SLAB_TYPESAFE_BY_RCU managed sockets * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME @@ -582,7 +583,14 @@ struct sock { struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct numa_drop_counters *sk_drop_counters; - struct rcu_head sk_rcu; + /* sockets using SLAB_TYPESAFE_BY_RCU can use sk_freeptr. + * By the time kfree() is called, sk_rcu can not be in + * use and can be mangled. + */ + union { + struct rcu_head sk_rcu; + freeptr_t sk_freeptr; + }; netns_tracker ns_tracker; struct xarray sk_user_frags; @@ -1368,6 +1376,7 @@ struct proto { struct kmem_cache *slab; unsigned int obj_size; + unsigned int freeptr_offset; unsigned int ipv6_pinfo_offset; slab_flags_t slab_flags; unsigned int useroffset; /* Usercopy region offset */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 0deb5e9dd911..40e72b9cb85f 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -347,6 +347,15 @@ extern struct proto tcp_prot; #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) +/* + * TCP splice context + */ +struct tcp_splice_state { + struct pipe_inode_info *pipe; + size_t len; + unsigned int flags; +}; + void tcp_tsq_work_init(void); int tcp_v4_err(struct sk_buff *skb, u32); @@ -378,6 +387,8 @@ void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); void tcp_twsk_purge(struct list_head *net_exit_list); +int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, + unsigned int offset, size_t len); ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); @@ -541,6 +552,7 @@ enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, + TCP_SYNACK_RETRANS, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, @@ -751,7 +763,15 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_done_with_error(struct sock *sk, int err); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_fin(struct sock *sk); -void tcp_check_space(struct sock *sk); +void __tcp_check_space(struct sock *sk); +static inline void tcp_check_space(struct sock *sk) +{ + /* pairs with tcp_poll() */ + smp_mb(); + + if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) + __tcp_check_space(sk); +} void tcp_sack_compress_send_ack(struct sock *sk); static inline void tcp_cleanup_skb(struct sk_buff *skb) @@ -809,6 +829,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) /* tcp.c */ void tcp_get_info(struct sock *, struct tcp_info *); +void tcp_rate_check_app_limited(struct sock *sk); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, @@ -1203,7 +1224,15 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) -#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) +/* Require successfully negotiated AccECN capability */ +#define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ +#define TCP_CONG_ECT_1_NEGOTIATION BIT(3) +/* Cannot fallback to RFC3168 during AccECN negotiation */ +#define TCP_CONG_NO_FALLBACK_RFC3168 BIT(4) +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ + TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \ + TCP_CONG_NO_FALLBACK_RFC3168) union tcp_cc_info; @@ -1243,12 +1272,27 @@ struct rate_sample { struct tcp_congestion_ops { /* fast path fields are put first to fill one cache line */ + /* A congestion control (CC) must provide one of either: + * + * (a) a cong_avoid function, if the CC wants to use the core TCP + * stack's default functionality to implement a "classic" + * (Reno/CUBIC-style) response to packet loss, RFC3168 ECN, + * idle periods, pacing rate computations, etc. + * + * (b) a cong_control function, if the CC wants custom behavior and + * complete control of all congestion control behaviors. + */ + /* (a) "classic" response: calculate new cwnd. + */ + void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); + /* (b) "custom" response: call when packets are delivered to update + * cwnd and pacing rate, after all the ca_state processing. + */ + void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); + /* return slow start threshold (required) */ u32 (*ssthresh)(struct sock *sk); - /* do new cwnd calculation (required) */ - void (*cong_avoid)(struct sock *sk, u32 ack, u32 acked); - /* call before changing ca_state (optional) */ void (*set_state)(struct sock *sk, u8 new_state); @@ -1261,15 +1305,9 @@ struct tcp_congestion_ops { /* hook for packet ack accounting (optional) */ void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample); - /* override sysctl_tcp_min_tso_segs */ + /* override sysctl_tcp_min_tso_segs (optional) */ u32 (*min_tso_segs)(struct sock *sk); - /* call when packets are delivered to update cwnd and pacing rate, - * after all the ca_state processing. (optional) - */ - void (*cong_control)(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs); - - /* new value of cwnd after loss (required) */ u32 (*undo_cwnd)(struct sock *sk); /* returns the multiplier used in tcp_sndbuf_expand (optional) */ @@ -1335,6 +1373,27 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } +static inline bool tcp_ca_needs_accecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; +} + +static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION; +} + +static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; +} + static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1346,13 +1405,6 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) /* From tcp_cong.c */ void tcp_set_ca_state(struct sock *sk, const u8 ca_state); -/* From tcp_rate.c */ -void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb); -void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, - struct rate_sample *rs); -void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, - bool is_sack_reneg, struct rate_sample *rs); -void tcp_rate_check_app_limited(struct sock *sk); static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) { @@ -1581,8 +1633,14 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); +static inline int tcp_filter(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason) +{ + const struct tcphdr *th = (const struct tcphdr *)skb->data; + + return sk_filter_trim_cap(sk, skb, __tcp_hdrlen(th), reason); +} -int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); @@ -2318,8 +2376,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff)); INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)); -INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)); #ifdef CONFIG_INET void tcp_gro_complete(struct sk_buff *skb); #else @@ -2513,10 +2569,7 @@ void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced); extern s32 tcp_rack_skb_timeout(struct tcp_sock *tp, struct sk_buff *skb, u32 reo_wnd); extern bool tcp_rack_mark_lost(struct sock *sk); -extern void tcp_rack_advance(struct tcp_sock *tp, u8 sacked, u32 end_seq, - u64 xmit_time); extern void tcp_rack_reo_timeout(struct sock *sk); -extern void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs); /* tcp_plb.c */ diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f13e5cd2b1ac..e9a933641636 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -29,8 +29,15 @@ enum tcp_accecn_option { TCP_ACCECN_OPTION_DISABLED = 0, TCP_ACCECN_OPTION_MINIMUM = 1, TCP_ACCECN_OPTION_FULL = 2, + TCP_ACCECN_OPTION_PERSIST = 3, }; +/* Apply either ECT(0) or ECT(1) based on TCP_CONG_ECT_1_NEGOTIATION flag */ +static inline void INET_ECN_xmit_ect_1_negotiation(struct sock *sk) +{ + __INET_ECN_xmit(sk, tcp_ca_ect_1_negotiation(sk)); +} + static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp) { /* Do not set CWR if in AccECN mode! */ @@ -60,12 +67,6 @@ static inline void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; } -/* tp->accecn_fail_mode */ -#define TCP_ACCECN_ACE_FAIL_SEND BIT(0) -#define TCP_ACCECN_ACE_FAIL_RECV BIT(1) -#define TCP_ACCECN_OPT_FAIL_SEND BIT(2) -#define TCP_ACCECN_OPT_FAIL_RECV BIT(3) - static inline bool tcp_accecn_ace_fail_send(const struct tcp_sock *tp) { return tp->accecn_fail_mode & TCP_ACCECN_ACE_FAIL_SEND; @@ -91,11 +92,6 @@ static inline void tcp_accecn_fail_mode_set(struct tcp_sock *tp, u8 mode) tp->accecn_fail_mode |= mode; } -#define TCP_ACCECN_OPT_NOT_SEEN 0x0 -#define TCP_ACCECN_OPT_EMPTY_SEEN 0x1 -#define TCP_ACCECN_OPT_COUNTER_SEEN 0x2 -#define TCP_ACCECN_OPT_FAIL_SEEN 0x3 - static inline u8 tcp_accecn_ace(const struct tcphdr *th) { return (th->ae << 2) | (th->cwr << 1) | th->ece; @@ -169,7 +165,9 @@ static inline void tcp_accecn_third_ack(struct sock *sk, switch (ace) { case 0x0: /* Invalid value */ - tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV); + if (!TCP_SKB_CB(skb)->sacked) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV | + TCP_ACCECN_OPT_FAIL_RECV); break; case 0x7: case 0x5: @@ -398,6 +396,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp) tp->received_ce_pending = 0; __tcp_accecn_init_bytes_counters(tp->received_ecn_bytes); __tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes); + tp->accecn_opt_sent_w_dsack = 0; tp->accecn_minlen = 0; tp->accecn_opt_demand = 0; tp->est_ecnfield = 0; @@ -467,6 +466,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb, return TCP_ACCECN_OPT_COUNTER_SEEN; } +static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk, + const struct sk_buff *skb, u8 dsf) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_rcv = dsf & INET_ECN_MASK; + /* Demand Accurate ECN option in response to the SYN on the SYN/ACK + * and the TCP server will try to send one more packet with an AccECN + * Option at a later point during the connection. + */ + if (tp->rx_opt.accecn && + tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + tp->accecn_opt_demand = 2; + } +} + /* See Table 2 of the AccECN draft */ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th, u8 ip_dsfield) @@ -489,32 +508,32 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); break; case 0x1: - case 0x5: /* +========+========+============+=============+ * | A | B | SYN/ACK | Feedback | * | | | B->A | Mode of A | * | | | AE CWR ECE | | * +========+========+============+=============+ - * | AccECN | Nonce | 1 0 1 | (Reserved) | * | AccECN | ECN | 0 0 1 | Classic ECN | * | Nonce | AccECN | 0 0 1 | Classic ECN | * | ECN | AccECN | 0 0 1 | Classic ECN | * +========+========+============+=============+ */ - if (tcp_ecn_mode_pending(tp)) - /* Downgrade from AccECN, or requested initially */ + if (tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); + else tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; - default: - tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); - tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK; - if (tp->rx_opt.accecn && - tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { - u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); - - tcp_accecn_saw_opt_fail_recv(tp, saw_opt); - tp->accecn_opt_demand = 2; + case 0x5: + if (tcp_ecn_mode_pending(tp)) { + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); + if (INET_ECN_is_ce(ip_dsfield)) { + tp->received_ce++; + tp->received_ce_pending++; + } } + break; + default: + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); if (INET_ECN_is_ce(ip_dsfield) && tcp_accecn_validate_syn_feedback(sk, ace, tp->syn_ect_snt)) { @@ -525,9 +544,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb } } -static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, +static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + if (tcp_ecn_mode_pending(tp)) { if (!tcp_accecn_syn_requested(th)) { /* Downgrade to classic ECN feedback */ @@ -539,7 +560,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); } } - if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr)) + if (tcp_ecn_mode_rfc3168(tp) && + (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk))) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } @@ -561,7 +583,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE; @@ -579,7 +601,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) bool use_ecn, use_accecn; u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); - use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN; + use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN || + tcp_ca_needs_accecn(sk); use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN || tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN || tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn; @@ -595,7 +618,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; if (use_accecn) { @@ -619,12 +642,22 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) } static inline void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) +tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th, + enum tcp_synack_type synack_type) { - if (tcp_rsk(req)->accecn_ok) - tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); - else if (inet_rsk(req)->ecn_ok) - th->ece = 1; + /* Accurate ECN shall retransmit SYN/ACK with ACE=0 if the + * previously retransmitted SYN/ACK also times out. + */ + if (!req->num_timeout || synack_type != TCP_SYNACK_RETRANS) { + if (tcp_rsk(req)->accecn_ok) + tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); + else if (inet_rsk(req)->ecn_ok) + th->ece = 1; + } else if (tcp_rsk(req)->accecn_ok) { + th->ae = 0; + th->cwr = 0; + th->ece = 0; + } } static inline bool tcp_accecn_option_beacon_check(const struct sock *sk) diff --git a/include/net/udp.h b/include/net/udp.h index a061d1b22ddc..700dbedcb15f 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -527,18 +527,18 @@ static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, * SNMP statistics for UDP and UDP-Lite */ #define UDP_INC_STATS(net, field, is_udplite) do { \ - if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + if (unlikely(is_udplite)) SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP_INC_STATS(net, field, is_udplite) do { \ - if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ + if (unlikely(is_udplite)) __SNMP_INC_STATS((net)->mib.udplite_statistics, field); \ else __SNMP_INC_STATS((net)->mib.udp_statistics, field); } while(0) #define __UDP6_INC_STATS(net, field, is_udplite) do { \ - if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\ + if (unlikely(is_udplite)) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ else __SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) #define UDP6_INC_STATS(net, field, __lite) do { \ - if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ + if (unlikely(__lite)) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field); \ else SNMP_INC_STATS((net)->mib.udp_stats_in6, field); \ } while(0) diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 9acef2fbd2fd..d9c6d04bb3b5 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -10,6 +10,11 @@ #include <net/ipv6_stubs.h> #endif +#define UDP_TUNNEL_PARTIAL_FEATURES NETIF_F_GSO_ENCAP_ALL +#define UDP_TUNNEL_STRIPPED_GSO_TYPES ((UDP_TUNNEL_PARTIAL_FEATURES | \ + NETIF_F_GSO_PARTIAL) >> \ + NETIF_F_GSO_SHIFT) + struct udp_port_cfg { u8 family; @@ -145,6 +150,33 @@ void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, __be16 src_port, __be16 dst_port, bool nocheck, u16 ip6cb_flags); +static inline bool udp_tunnel_handle_partial(struct sk_buff *skb) +{ + bool double_encap = !!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL); + + /* + * If the skb went through partial segmentation, lower devices + * will not need to offload the related features - except for + * UDP_TUNNEL, that will be re-added by the later + * udp_tunnel_handle_offloads(). + */ + if (double_encap) + skb_shinfo(skb)->gso_type &= ~UDP_TUNNEL_STRIPPED_GSO_TYPES; + return double_encap; +} + +static inline void udp_tunnel_set_inner_protocol(struct sk_buff *skb, + bool double_encap, + __be16 inner_proto) +{ + /* + * The inner protocol has been set by the nested tunnel, don't + * overraid it. + */ + if (!double_encap) + skb_set_inner_protocol(skb, inner_proto); +} + void udp_tunnel_sock_release(struct socket *sock); struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 0a14daaa5dd4..10d3edde6b2f 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1156,19 +1156,19 @@ struct xfrm_offload { #define CRYPTO_INVALID_PROTOCOL 128 /* Used to keep whole l2 header for transport mode GRO */ - __u32 orig_mac_len; + __u16 orig_mac_len; __u8 proto; __u8 inner_ipproto; }; struct sec_path { - int len; - int olen; - int verified_cnt; - struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; + + u8 len; + u8 olen; + u8 verified_cnt; }; struct sec_path *secpath_set(struct sk_buff *skb); diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 92a2358c6ce3..0b1abdb99c9e 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -90,11 +90,6 @@ struct xsk_buff_pool { * destructor callback. */ spinlock_t cq_prod_lock; - /* Mutual exclusion of the completion ring in the SKB mode. - * Protect: when sockets share a single cq when the same netdev - * and queue id is shared. - */ - spinlock_t cq_cached_prod_lock; struct xdp_buff_xsk *free_heads[]; }; |